diff options
Diffstat (limited to 'block')
| -rw-r--r-- | block/Kconfig | 17 | ||||
| -rw-r--r-- | block/Makefile | 1 | ||||
| -rw-r--r-- | block/as-iosched.c | 3 | ||||
| -rw-r--r-- | block/bsg.c | 1095 | ||||
| -rw-r--r-- | block/cfq-iosched.c | 100 | ||||
| -rw-r--r-- | block/deadline-iosched.c | 3 | ||||
| -rw-r--r-- | block/elevator.c | 16 | ||||
| -rw-r--r-- | block/genhd.c | 20 | ||||
| -rw-r--r-- | block/ll_rw_blk.c | 33 | ||||
| -rw-r--r-- | block/scsi_ioctl.c | 166 |
10 files changed, 1315 insertions, 139 deletions
diff --git a/block/Kconfig b/block/Kconfig index a50f4811164..0768741d681 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -1,7 +1,7 @@ # # Block layer core configuration # -config BLOCK +menuconfig BLOCK bool "Enable the block layer" if EMBEDDED default y help @@ -49,6 +49,19 @@ config LSF If unsure, say Y. -endif +endif # BLOCK + +config BLK_DEV_BSG + bool "Block layer SG support v4 (EXPERIMENTAL)" + depends on (SCSI=y) && EXPERIMENTAL + ---help--- + Saying Y here will enable generic SG (SCSI generic) v4 support + for any block device. + + Unlike SG v3 (aka block/scsi_ioctl.c drivers/scsi/sg.c), SG v4 + can handle complicated SCSI commands: tagged variable length cdbs + with bidirectional data transfers and generic request/response + protocols (e.g. Task Management Functions and SMP in Serial + Attached SCSI). source block/Kconfig.iosched diff --git a/block/Makefile b/block/Makefile index 4b84d0d5947..959feeb253b 100644 --- a/block/Makefile +++ b/block/Makefile @@ -4,6 +4,7 @@ obj-$(CONFIG_BLOCK) := elevator.o ll_rw_blk.o ioctl.o genhd.o scsi_ioctl.o +obj-$(CONFIG_BLK_DEV_BSG) += bsg.o obj-$(CONFIG_IOSCHED_NOOP) += noop-iosched.o obj-$(CONFIG_IOSCHED_AS) += as-iosched.o obj-$(CONFIG_IOSCHED_DEADLINE) += deadline-iosched.o diff --git a/block/as-iosched.c b/block/as-iosched.c index 109e91b91ff..3e316dd7252 100644 --- a/block/as-iosched.c +++ b/block/as-iosched.c @@ -1322,10 +1322,9 @@ static void *as_init_queue(request_queue_t *q) { struct as_data *ad; - ad = kmalloc_node(sizeof(*ad), GFP_KERNEL, q->node); + ad = kmalloc_node(sizeof(*ad), GFP_KERNEL | __GFP_ZERO, q->node); if (!ad) return NULL; - memset(ad, 0, sizeof(*ad)); ad->q = q; /* Identify what queue the data belongs to */ diff --git a/block/bsg.c b/block/bsg.c new file mode 100644 index 00000000000..f2992e72b84 --- /dev/null +++ b/block/bsg.c @@ -0,0 +1,1095 @@ +/* + * bsg.c - block layer implementation of the sg v3 interface + * + * Copyright (C) 2004 Jens Axboe <axboe@suse.de> SUSE Labs + * Copyright (C) 2004 Peter M. Jones <pjones@redhat.com> + * + * 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. + * + */ +/* + * TODO + * - Should this get merged, block/scsi_ioctl.c will be migrated into + * this file. To keep maintenance down, it's easier to have them + * seperated right now. + * + */ +#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/percpu.h> +#include <linux/uio.h> +#include <linux/bsg.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 { + request_queue_t *queue; + spinlock_t lock; + struct list_head busy_list; + struct list_head done_list; + struct hlist_node dev_list; + atomic_t ref_count; + int minor; + int queued_cmds; + int done_cmds; + wait_queue_head_t wq_done; + wait_queue_head_t wq_free; + char name[BUS_ID_SIZE]; + int max_queue; + unsigned long flags; +}; + +enum { + BSG_F_BLOCK = 1, + BSG_F_WRITE_PERM = 2, +}; + +#define BSG_DEFAULT_CMDS 64 +#define BSG_MAX_DEVS 32768 + +#undef BSG_DEBUG + +#ifdef BSG_DEBUG +#define dprintk(fmt, args...) printk(KERN_ERR "%s: " fmt, __FUNCTION__, ##args) +#else +#define dprintk(fmt, args...) +#endif + +static DEFINE_MUTEX(bsg_mutex); +static int bsg_device_nr, bsg_minor_idx; + +#define BSG_LIST_ARRAY_SIZE 8 +static struct hlist_head bsg_device_list[BSG_LIST_ARRAY_SIZE]; + +static struct class *bsg_class; +static LIST_HEAD(bsg_class_list); +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; + struct sg_io_v4 __user *uhdr; + char sense[SCSI_SENSE_BUFFERSIZE]; +}; + +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); +} + +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; +} + +static inline struct hlist_head *bsg_dev_idx_hash(int index) +{ + return &bsg_device_list[index & (BSG_LIST_ARRAY_SIZE - 1)]; +} + +static int bsg_io_schedule(struct bsg_device *bd) +{ + DEFINE_WAIT(wait); + int ret = 0; + + spin_lock_irq(&bd->lock); + + BUG_ON(bd->done_cmds > bd->queued_cmds); + + /* + * -ENOSPC or -ENODATA? I'm going for -ENODATA, meaning "I have no + * work to do", even though we return -ENOSPC after this same test + * during bsg_write() -- there, it means our buffer can't have more + * bsg_commands added to it, thus has no space left. + */ + if (bd->done_cmds == bd->queued_cmds) { + ret = -ENODATA; + goto unlock; + } + + if (!test_bit(BSG_F_BLOCK, &bd->flags)) { + ret = -EAGAIN; + goto unlock; + } + + prepare_to_wait(&bd->wq_done, &wait, TASK_UNINTERRUPTIBLE); + spin_unlock_irq(&bd->lock); + io_schedule(); + finish_wait(&bd->wq_done, &wait); + + return ret; +unlock: + spin_unlock_irq(&bd->lock); + return ret; +} + +static int blk_fill_sgv4_hdr_rq(request_queue_t *q, struct request *rq, + struct sg_io_v4 *hdr, int has_write_perm) +{ + memset(rq->cmd, 0, BLK_MAX_CDB); /* ATAPI hates garbage after CDB */ + + if (copy_from_user(rq->cmd, (void *)(unsigned long)hdr->request, + hdr->request_len)) + return -EFAULT; + + if (hdr->subprotocol == BSG_SUB_PROTOCOL_SCSI_CMD) { + if (blk_verify_command(rq->cmd, has_write_perm)) + return -EPERM; + } else if (!capable(CAP_SYS_RAWIO)) + return -EPERM; + + /* + * fill in request structure + */ + rq->cmd_len = hdr->request_len; + rq->cmd_type = REQ_TYPE_BLOCK_PC; + + rq->timeout = (hdr->timeout * HZ) / 1000; + if (!rq->timeout) + rq->timeout = q->sg_timeout; + if (!rq->timeout) + rq->timeout = BLK_DEFAULT_SG_TIMEOUT; + + return 0; +} + +/* + * Check if sg_io_v4 from user is allowed and valid + */ +static int +bsg_validate_sgv4_hdr(request_queue_t *q, struct sg_io_v4 *hdr, int *rw) +{ + int ret = 0; + + if (hdr->guard != 'Q') + return -EINVAL; + if (hdr->request_len > BLK_MAX_CDB) + return -EINVAL; + if (hdr->dout_xfer_len > (q->max_sectors << 9) || + hdr->din_xfer_len > (q->max_sectors << 9)) + return -EIO; + + 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; + } + + *rw = hdr->dout_xfer_len ? WRITE : READ; + return ret; +} + +/* + * map sg_io_v4 to a request. + */ +static struct request * +bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr) +{ + request_queue_t *q = bd->queue; + struct request *rq, *next_rq = NULL; + int ret, rw; + unsigned int dxfer_len; + void *dxferp = NULL; + + 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(q, hdr, &rw); + if (ret) + return ERR_PTR(ret); + + /* + * map scatter-gather elements seperately and string them to request + */ + rq = blk_get_request(q, rw, GFP_KERNEL); + if (!rq) + return ERR_PTR(-ENOMEM); + ret = blk_fill_sgv4_hdr_rq(q, rq, hdr, test_bit(BSG_F_WRITE_PERM, + &bd->flags)); + if (ret) + goto out; + + if (rw == WRITE && hdr->din_xfer_len) { + if (!test_bit(QUEUE_FLAG_BIDI, &q->queue_flags)) { + ret = -EOPNOTSUPP; + goto out; + } + + next_rq = blk_get_request(q, READ, GFP_KERNEL); + if (!next_rq) { + ret = -ENOMEM; + goto out; + } + rq->next_rq = next_rq; + + dxferp = (void*)(unsigned long)hdr->din_xferp; + ret = blk_rq_map_user(q, next_rq, dxferp, hdr->din_xfer_len); + if (ret) + goto out; + } + + if (hdr->dout_xfer_len) { + dxfer_len = hdr->dout_xfer_len; + dxferp = (void*)(unsigned long)hdr->dout_xferp; + } else if (hdr->din_xfer_len) { + dxfer_len = hdr->din_xfer_len; + dxferp = (void*)(unsigned long)hdr->din_xferp; + } else + dxfer_len = 0; + + if (dxfer_len) { + ret = blk_rq_map_user(q, rq, dxferp, dxfer_len); + if (ret) + goto out; + } + return rq; +out: + blk_put_request(rq); + if (next_rq) { + blk_rq_unmap_user(next_rq->bio); + blk_put_request(next_rq); + } + return ERR_PTR(ret); +} + +/* + * 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); +} + +/* + * 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, request_queue_t *q, + struct bsg_command *bc, struct request *rq) +{ + rq->sense = bc->sense; + rq->sense_len = 0; + + /* + * 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, 1, bsg_rq_end_io); +} + +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_entry(bd->done_list.next, struct bsg_command, list); + list_del(&bc->list); + bd->done_cmds--; + } + spin_unlock_irq(&bd->lock); + + return bc; +} + +/* + * 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; +} + +static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr, + struct bio *bio, struct bio *bidi_bio) +{ + int ret = 0; + + dprintk("rq %p bio %p %u\n", rq, bio, rq->errors); + /* + * fill in all the output members + */ + hdr->device_status = status_byte(rq->errors); + hdr->transport_status = host_byte(rq->errors); + hdr->driver_status = driver_byte(rq->errors); + hdr->info = 0; + if (hdr->device_status || hdr->transport_status || hdr->driver_status) + hdr->info |= SG_INFO_CHECK; + hdr->din_resid = rq->data_len; + hdr->response_len = 0; + + if (rq->sense_len && hdr->response) { + int len = min_t(unsigned int, hdr->max_response_len, + rq->sense_len); + + ret = copy_to_user((void*)(unsigned long)hdr->response, + rq->sense, len); + if (!ret) + hdr->response_len = len; + else + ret = -EFAULT; + } + + if (rq->next_rq) { + blk_rq_unmap_user(bidi_bio); + blk_put_request(rq->next_rq); + } + + blk_rq_unmap_user(bio); + blk_put_request(rq); + + return ret; +} + +static int bsg_complete_all_commands(struct bsg_device *bd) +{ + struct bsg_command *bc; + int ret, tret; + + dprintk("%s: entered\n", bd->name); + + set_bit(BSG_F_BLOCK, &bd->flags); + + /* + * wait for all commands to complete + */ + ret = 0; + do { + ret = bsg_io_schedule(bd); + /* + * look for -ENODATA specifically -- we'll sometimes get + * -ERESTARTSYS when we've taken a signal, but we can't + * return until we're done freeing the queue, so ignore + * it. The signal will get handled when we're done freeing + * the bsg_device. + */ + } while (ret != -ENODATA); + + /* + * 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; +} + +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; +} + +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); +} + +static inline void bsg_set_write_perm(struct bsg_device *bd, struct file *file) +{ + if (file->f_mode & FMODE_WRITE) + set_bit(BSG_F_WRITE_PERM, &bd->flags); + else + clear_bit(BSG_F_WRITE_PERM, &bd->flags); +} + +/* + * 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; +} + +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 || (bytes_read && err_block_err(ret))) + bytes_read = ret; + + return bytes_read; +} + +static int __bsg_write(struct bsg_device *bd, const char __user *buf, + size_t count, ssize_t *bytes_written) +{ + 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) { + request_queue_t *q = bd->queue; + + bc = bsg_alloc_command(bd); + if (IS_ERR(bc)) { + ret = PTR_ERR(bc); + bc = NULL; + break; + } + + bc->uhdr = (struct sg_io_v4 __user *) buf; + 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); + 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; +} + +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); + + bsg_set_block(bd, file); + bsg_set_write_perm(bd, file); + + bytes_written = 0; + ret = __bsg_write(bd, buf, count, &bytes_written); + *ppos = bytes_written; + + /* + * return bytes written on non-fatal errors + */ + if (!bytes_written || (bytes_written && err_block_err(ret))) + bytes_written = ret; + + dprintk("%s: returning %Zd\n", bd->name, bytes_written); + return bytes_written; +} + +static struct bsg_device *bsg_alloc_device(void) +{ + struct bsg_device *bd; + + bd = kzalloc(sizeof(struct bsg_device), GFP_KERNEL); + if (unlikely(!bd)) + return NULL; + + spin_lock_init(&bd->lock); + + bd->max_queue = BSG_DEFAULT_CMDS; + + INIT_LIST_HEAD(&bd->busy_list); + INIT_LIST_HEAD(&bd->done_list); + INIT_HLIST_NODE(&bd->dev_list); + + init_waitqueue_head(&bd->wq_free); + init_waitqueue_head(&bd->wq_done); + return bd; +} + +static int bsg_put_device(struct bsg_device *bd) +{ + int ret = 0; + + mutex_lock(&bsg_mutex); + + if (!atomic_dec_and_test(&bd->ref_count)) + goto out; + + dprintk("%s: tearing down\n", bd->name); + + /* + * close can always block + */ + set_bit(BSG_F_BLOCK, &bd->flags); + + /* + * correct error detection baddies here again. it's the responsibility + * of the app to properly reap commands before close() if it wants + * fool-proof error detection + */ + ret = bsg_complete_all_commands(bd); + + blk_put_queue(bd->queue); + hlist_del(&bd->dev_list); + kfree(bd); +out: + mutex_unlock(&bsg_mutex); + return ret; +} + +static struct bsg_device *bsg_add_device(struct inode *inode, + struct request_queue *rq, + struct file *file) +{ + struct bsg_device *bd; +#ifdef BSG_DEBUG + unsigned char buf[32]; +#endif + + bd = bsg_alloc_device(); + if (!bd) + return ERR_PTR(-ENOMEM); + + bd->queue = rq; + kobject_get(&rq->kobj); + bsg_set_block(bd, file); + + atomic_set(&bd->ref_count, 1); + bd->minor = iminor(inode); + mutex_lock(&bsg_mutex); + hlist_add_head(&bd->dev_list, bsg_dev_idx_hash(bd->minor)); + + strncpy(bd->name, rq->bsg_dev.class_dev->class_id, sizeof(bd->name) - 1); + dprintk("bound to <%s>, max queue %d\n", + format_dev_t(buf, inode->i_rdev), bd->max_queue); + + mutex_unlock(&bsg_mutex); + return bd; +} + +static struct bsg_device *__bsg_get_device(int minor) +{ + struct bsg_device *bd = NULL; + struct hlist_node *entry; + + mutex_lock(&bsg_mutex); + + hlist_for_each(entry, bsg_dev_idx_hash(minor)) { + bd = hlist_entry(entry, struct bsg_device, dev_list); + if (bd->minor == minor) { + atomic_inc(&bd->ref_count); + break; + } + + bd = NULL; + } + + mutex_unlock(&bsg_mutex); + return bd; +} + +static struct bsg_device *bsg_get_device(struct inode *inode, struct file *file) +{ + struct bsg_device *bd = __bsg_get_device(iminor(inode)); + struct bsg_class_device *bcd, *__bcd; + + if (bd) + return bd; + + /* + * find the class device + */ + bcd = NULL; + mutex_lock(&bsg_mutex); + list_for_each_entry(__bcd, &bsg_class_list, list) { + if (__bcd->minor == iminor(inode)) { + bcd = __bcd; + break; + } + } + mutex_unlock(&bsg_mutex); + + if (!bcd) + return ERR_PTR(-ENODEV); + + return bsg_add_device(inode, bcd->queue, file); +} + +static int bsg_open(struct inode *inode, struct file *file) +{ + struct bsg_device *bd = bsg_get_device(inode, file); + + if (IS_ERR(bd)) + return PTR_ERR(bd); + + file->private_data = bd; + return 0; +} + +static int bsg_release(struct inode *inode, struct file *file) +{ + struct bsg_device *bd = file->private_data; + + file->private_data = NULL; + return bsg_put_device(bd); +} + +static unsigned int bsg_poll(struct file *file, poll_table *wait) +{ + struct bsg_device *bd = file->private_data; + unsigned int mask = 0; + + poll_wait(file, &bd->wq_done, wait); + poll_wait(file, &bd->wq_free, wait); + + spin_lock_irq(&bd->lock); + if (!list_empty(&bd->done_list)) + mask |= POLLIN | POLLRDNORM; + if (bd->queued_cmds >= bd->max_queue) + mask |= POLLOUT; + spin_unlock_irq(&bd->lock); + + return mask; +} + +static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct bsg_device *bd = file->private_data; + int __user *uarg = (int __user *) arg; + + switch (cmd) { + /* + * our own ioctls + */ + case SG_GET_COMMAND_Q: + return put_user(bd->max_queue, uarg); + case SG_SET_COMMAND_Q: { + int queue; + + if (get_user(queue, uarg)) + return -EFAULT; + if (queue < 1) + return -EINVAL; + + spin_lock_irq(&bd->lock); + bd->max_queue = queue; + spin_unlock_irq(&bd->lock); + return 0; + } + + /* + * SCSI/sg ioctls + */ + case SG_GET_VERSION_NUM: + case SCSI_IOCTL_GET_IDLUN: + case SCSI_IOCTL_GET_BUS_NUMBER: + case SG_SET_TIMEOUT: + case SG_GET_TIMEOUT: + case SG_GET_RESERVED_SIZE: + case SG_SET_RESERVED_SIZE: + case SG_EMULATED_HOST: + case SCSI_IOCTL_SEND_COMMAND: { + void __user *uarg = (void __user *) arg; + return scsi_cmd_ioctl(file, bd->queue, NULL, cmd, uarg); + } + case SG_IO: { + struct request *rq; + struct bio *bio, *bidi_bio = NULL; + struct sg_io_v4 hdr; + + if (copy_from_user(&hdr, uarg, sizeof(hdr))) + return -EFAULT; + + rq = bsg_map_hdr(bd, &hdr); + if (IS_ERR(rq)) + return PTR_ERR(rq); + + bio = rq->bio; + if (rq->next_rq) + bidi_bio = rq->next_rq->bio; + blk_execute_rq(bd->queue, NULL, rq, 0); + blk_complete_sgv4_hdr_rq(rq, &hdr, bio, bidi_bio); + + if (copy_to_user(uarg, &hdr, sizeof(hdr))) + return -EFAULT; + + return 0; + } + /* + * block device ioctls + */ + default: +#if 0 + return ioctl_by_bdev(bd->bdev, cmd, arg); +#else + return -ENOTTY; +#endif + } +} + +static struct file_operations bsg_fops = { + .read = bsg_read, + .write = bsg_write, + .poll = bsg_poll, + .open = bsg_open, + .release = bsg_release, + .unlocked_ioctl = bsg_ioctl, + .owner = THIS_MODULE, +}; + +void bsg_unregister_queue(struct request_queue *q) +{ + struct bsg_class_device *bcd = &q->bsg_dev; + + WARN_ON(!bcd->class_dev); + + mutex_lock(&bsg_mutex); + sysfs_remove_link(&q->kobj, "bsg"); + class_device_destroy(bsg_class, MKDEV(bsg_major, bcd->minor)); + bcd->class_dev = NULL; + list_del_init(&bcd->list); + bsg_device_nr--; + mutex_unlock(&bsg_mutex); +} +EXPORT_SYMBOL_GPL(bsg_unregister_queue); + +int bsg_register_queue(struct request_queue *q, const char *name) +{ + struct bsg_class_device *bcd, *__bcd; + dev_t dev; + int ret = -EMFILE; + struct class_device *class_dev = NULL; + + /* + * we need a proper transport to send commands, not a stacked device + */ + if (!q->request_fn) + return 0; + + bcd = &q->bsg_dev; + memset(bcd, 0, sizeof(*bcd)); + INIT_LIST_HEAD(&bcd->list); + + mutex_lock(&bsg_mutex); + if (bsg_device_nr == BSG_MAX_DEVS) { + printk(KERN_ERR "bsg: too many bsg devices\n"); + goto err; + } + +retry: + list_for_each_entry(__bcd, &bsg_class_list, list) { + if (__bcd->minor == bsg_minor_idx) { + bsg_minor_idx++; + if (bsg_minor_idx == BSG_MAX_DEVS) + bsg_minor_idx = 0; + goto retry; + } + } + + bcd->minor = bsg_minor_idx++; + if (bsg_minor_idx == BSG_MAX_DEVS) + bsg_minor_idx = 0; + + bcd->queue = q; + dev = MKDEV(bsg_major, bcd->minor); + class_dev = class_device_create(bsg_class, NULL, dev, bcd->dev, "%s", name); + if (IS_ERR(class_dev)) { + ret = PTR_ERR(class_dev); + goto err; + } + bcd->class_dev = class_dev; + + if (q->kobj.sd) { + ret = sysfs_create_link(&q->kobj, &bcd->class_dev->kobj, "bsg"); + if (ret) + goto err; + } + + list_add_tail(&bcd->list, &bsg_class_list); + bsg_device_nr++; + + mutex_unlock(&bsg_mutex); + return 0; +err: + if (class_dev) + class_device_destroy(bsg_class, MKDEV(bsg_major, bcd->minor)); + mutex_unlock(&bsg_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(bsg_register_queue); + +static int bsg_add(struct class_device *cl_dev, struct class_interface *cl_intf) +{ + int ret; + struct scsi_device *sdp = to_scsi_device(cl_dev->dev); + struct request_queue *rq = sdp->request_queue; + + if (rq->kobj.parent) + ret = bsg_register_queue(rq, kobject_name(rq->kobj.parent)); + else + ret = bsg_register_queue(rq, kobject_name(&sdp->sdev_gendev.kobj)); + return ret; +} + +static void bsg_remove(struct class_device *cl_dev, struct class_interface *cl_intf) +{ + bsg_unregister_queue(to_scsi_device(cl_dev->dev)->request_queue); +} + +static struct class_interface bsg_intf = { + .add = bsg_add, + .remove = bsg_remove, +}; + +static struct cdev bsg_cdev = { + .kobj = {.name = "bsg", }, + .owner = THIS_MODULE, +}; + +static int __init bsg_init(void) +{ + int ret, i; + dev_t devid; + + bsg_cmd_cachep = kmem_cache_create("bsg_cmd", + sizeof(struct bsg_command), 0, 0, NULL); + if (!bsg_cmd_cachep) { + printk(KERN_ERR "bsg: failed creating slab cache\n"); + return -ENOMEM; + } + + for (i = 0; i < BSG_LIST_ARRAY_SIZE; i++) + INIT_HLIST_HEAD(&bsg_device_list[i]); + + bsg_class = class_create(THIS_MODULE, "bsg"); + if (IS_ERR(bsg_class)) { + ret = PTR_ERR(bsg_class); + goto destroy_kmemcache; + } + + ret = alloc_chrdev_region(&devid, 0, BSG_MAX_DEVS, "bsg"); + if (ret) + goto destroy_bsg_class; + + bsg_major = MAJOR(devid); + + cdev_init(&bsg_cdev, &bsg_fops); + ret = cdev_add(&bsg_cdev, MKDEV(bsg_major, 0), BSG_MAX_DEVS); + if (ret) + goto unregister_chrdev; + + ret = scsi_register_interface(&bsg_intf); + if (ret) + goto remove_cdev; + + printk(KERN_INFO BSG_DESCRIPTION " version " BSG_VERSION + " loaded (major %d)\n", bsg_major); + return 0; +remove_cdev: + printk(KERN_ERR "bsg: failed register scsi interface %d\n", ret); + cdev_del(&bsg_cdev); +unregister_chrdev: + unregister_chrdev_region(MKDEV(bsg_major, 0), BSG_MAX_DEVS); +destroy_bsg_class: + class_destroy(bsg_class); +destroy_kmemcache: + kmem_cache_destroy(bsg_cmd_cachep); + return ret; +} + +MODULE_AUTHOR("Jens Axboe"); +MODULE_DESCRIPTION(BSG_DESCRIPTION); +MODULE_LICENSE("GPL"); + +device_initcall(bsg_init); diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index baef5fc7cff..d148ccbc36d 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -92,6 +92,12 @@ struct cfq_data { struct cfq_queue *active_queue; struct cfq_io_context *active_cic; + /* + * async queue for each priority case + */ + struct cfq_queue *async_cfqq[2][IOPRIO_BE_NR]; + struct cfq_queue *async_idle_cfqq; + struct timer_list idle_class_timer; sector_t last_position; @@ -109,9 +115,6 @@ struct cfq_data { unsigned int cfq_slice_idle; struct list_head cic_list; - - sector_t new_seek_mean; - u64 new_seek_total; }; /* @@ -151,8 +154,6 @@ struct cfq_queue { /* various state flags, see below */ unsigned int flags; - - sector_t last_request_pos; }; enum cfqq_state_flags { @@ -1249,9 +1250,9 @@ cfq_alloc_io_context(struct cfq_data *cfqd, gfp_t gfp_mask) { struct cfq_io_context *cic; - cic = kmem_cache_alloc_node(cfq_ioc_pool, gfp_mask, cfqd->queue->node); + cic = kmem_cache_alloc_node(cfq_ioc_pool, gfp_mask | __GFP_ZERO, + cfqd->queue->node); if (cic) { - memset(cic, 0, sizeof(*cic)); cic->last_end_request = jiffies; INIT_LIST_HEAD(&cic->queue_list); cic->dtor = cfq_free_io_context; @@ -1351,8 +1352,8 @@ static void cfq_ioc_set_ioprio(struct io_context *ioc) } static struct cfq_queue * -cfq_get_queue(struct cfq_data *cfqd, int is_sync, struct task_struct *tsk, - gfp_t gfp_mask) +cfq_find_alloc_queue(struct cfq_data *cfqd, int is_sync, + struct task_struct *tsk, gfp_t gfp_mask) { struct cfq_queue *cfqq, *new_cfqq = NULL; struct cfq_io_context *cic; @@ -1374,17 +1375,19 @@ retry: * free memory. */ spin_unlock_irq(cfqd->queue->queue_lock); - new_cfqq = kmem_cache_alloc_node(cfq_pool, gfp_mask|__GFP_NOFAIL, cfqd->queue->node); + new_cfqq = kmem_cache_alloc_node(cfq_pool, + gfp_mask | __GFP_NOFAIL | __GFP_ZERO, + cfqd->queue->node); spin_lock_irq(cfqd->queue->queue_lock); goto retry; } else { - cfqq = kmem_cache_alloc_node(cfq_pool, gfp_mask, cfqd->queue->node); + cfqq = kmem_cache_alloc_node(cfq_pool, + gfp_mask | __GFP_ZERO, + cfqd->queue->node); if (!cfqq) goto out; } - memset(cfqq, 0, sizeof(*cfqq)); - RB_CLEAR_NODE(&cfqq->rb_node); INIT_LIST_HEAD(&cfqq->fifo); @@ -1405,12 +1408,55 @@ retry: if (new_cfqq) kmem_cache_free(cfq_pool, new_cfqq); - atomic_inc(&cfqq->ref); out: WARN_ON((gfp_mask & __GFP_WAIT) && !cfqq); return cfqq; } +static struct cfq_queue ** +cfq_async_queue_prio(struct cfq_data *cfqd, int ioprio_class, int ioprio) +{ + switch(ioprio_class) { + case IOPRIO_CLASS_RT: + return &cfqd->async_cfqq[0][ioprio]; + case IOPRIO_CLASS_BE: + return &cfqd->async_cfqq[1][ioprio]; + case IOPRIO_CLASS_IDLE: + return &cfqd->async_idle_cfqq; + default: + BUG(); + } +} + +static struct cfq_queue * +cfq_get_queue(struct cfq_data *cfqd, int is_sync, struct task_struct *tsk, + gfp_t gfp_mask) +{ + const int ioprio = task_ioprio(tsk); + const int ioprio_class = task_ioprio_class(tsk); + struct cfq_queue **async_cfqq = NULL; + struct cfq_queue *cfqq = NULL; + + if (!is_sync) { + async_cfqq = cfq_async_queue_prio(cfqd, ioprio_class, ioprio); + cfqq = *async_cfqq; + } + + if (!cfqq) + cfqq = cfq_find_alloc_queue(cfqd, is_sync, tsk, gfp_mask); + + /* + * pin the queue now that it's allocated, scheduler exit will prune it + */ + if (!is_sync && !(*async_cfqq)) { + atomic_inc(&cfqq->ref); + *async_cfqq = cfqq; + } + + atomic_inc(&cfqq->ref); + return cfqq; +} + /* * We drop cfq io contexts lazily, so we may find a dead one. */ @@ -1570,11 +1616,6 @@ cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_io_context *cic, else sdist = cic->last_request_pos - rq->sector; - if (!cic->seek_samples) { - cfqd->new_seek_total = (7*cic->seek_total + (u64)256*sdist) / 8; - cfqd->new_seek_mean = cfqd->new_seek_total / 256; - } - /* * Don't allow the seek distance to get too large from the * odd fragment, pagein, etc @@ -1710,7 +1751,6 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, cfq_update_idle_window(cfqd, cfqq, cic); cic->last_request_pos = rq->sector + rq->nr_sectors; - cfqq->last_request_pos = cic->last_request_pos; if (cfqq == cfqd->active_queue) { /* @@ -2015,6 +2055,20 @@ static void cfq_shutdown_timer_wq(struct cfq_data *cfqd) blk_sync_queue(cfqd->queue); } +static void cfq_put_async_queues(struct cfq_data *cfqd) +{ + int i; + + for (i = 0; i < IOPRIO_BE_NR; i++) { + if (cfqd->async_cfqq[0][i]) + cfq_put_queue(cfqd->async_cfqq[0][i]); + if (cfqd->async_cfqq[1][i]) + cfq_put_queue(cfqd->async_cfqq[1][i]); + if (cfqd->async_idle_cfqq) + cfq_put_queue(cfqd->async_idle_cfqq); + } +} + static void cfq_exit_queue(elevator_t *e) { struct cfq_data *cfqd = e->elevator_data; @@ -2035,6 +2089,8 @@ static void cfq_exit_queue(elevator_t *e) __cfq_exit_single_io_context(cfqd, cic); } + cfq_put_async_queues(cfqd); + spin_unlock_irq(q->queue_lock); cfq_shutdown_timer_wq(cfqd); @@ -2046,12 +2102,10 @@ static void *cfq_init_queue(request_queue_t *q) { struct cfq_data *cfqd; - cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL, q->node); + cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node); if (!cfqd) return NULL; - memset(cfqd, 0, sizeof(*cfqd)); - cfqd->service_tree = CFQ_RB_ROOT; INIT_LIST_HEAD(&cfqd->cic_list); diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c index 6d673e938d3..87ca02ac84c 100644 --- a/block/deadline-iosched.c +++ b/block/deadline-iosched.c @@ -360,10 +360,9 @@ static void *deadline_init_queue(request_queue_t *q) { struct deadline_data *dd; - dd = kmalloc_node(sizeof(*dd), GFP_KERNEL, q->node); + dd = kmalloc_node(sizeof(*dd), GFP_KERNEL | __GFP_ZERO, q->node); if (!dd) return NULL; - memset(dd, 0, sizeof(*dd)); INIT_LIST_HEAD(&dd->fifo_list[READ]); INIT_LIST_HEAD(&dd->fifo_list[WRITE]); diff --git a/block/elevator.c b/block/elevator.c index ce866eb75f6..d265963d1ed 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -112,12 +112,8 @@ static inline int elv_try_merge(struct request *__rq, struct bio *bio) static struct elevator_type *elevator_find(const char *name) { struct elevator_type *e; - struct list_head *entry; - - list_for_each(entry, &elv_list) { - - e = list_entry(entry, struct elevator_type, list); + list_for_each_entry(e, &elv_list, list) { if (!strcmp(e->elevator_name, name)) return e; } @@ -181,11 +177,10 @@ static elevator_t *elevator_alloc(request_queue_t *q, struct elevator_type *e) elevator_t *eq; int i; - eq = kmalloc_node(sizeof(elevator_t), GFP_KERNEL, q->node); + eq = kmalloc_node(sizeof(elevator_t), GFP_KERNEL | __GFP_ZERO, q->node); if (unlikely(!eq)) goto err; - memset(eq, 0, sizeof(*eq)); eq->ops = &e->ops; eq->elevator_type = e; kobject_init(&eq->kobj); @@ -1116,14 +1111,11 @@ ssize_t elv_iosched_show(request_queue_t *q, char *name) { elevator_t *e = q->elevator; struct elevator_type *elv = e->elevator_type; - struct list_head *entry; + struct elevator_type *__e; int len = 0; spin_lock(&elv_list_lock); - list_for_each(entry, &elv_list) { - struct elevator_type *__e; - - __e = list_entry(entry, struct elevator_type, list); + list_for_each_entry(__e, &elv_list, list) { if (!strcmp(elv->elevator_name, __e->elevator_name)) len += sprintf(name+len, "[%s] ", elv->elevator_name); else diff --git a/block/genhd.c b/block/genhd.c index 863a8c0623e..3af1e7a378d 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -108,28 +108,24 @@ out: EXPORT_SYMBOL(register_blkdev); -/* todo: make void - error printk here */ -int unregister_blkdev(unsigned int major, const char *name) +void unregister_blkdev(unsigned int major, const char *name) { struct blk_major_name **n; struct blk_major_name *p = NULL; int index = major_to_index(major); - int ret = 0; mutex_lock(&block_subsys_lock); for (n = &major_names[index]; *n; n = &(*n)->next) if ((*n)->major == major) break; - if (!*n || strcmp((*n)->name, name)) - ret = -EINVAL; - else { + if (!*n || strcmp((*n)->name, name)) { + WARN_ON(1); + } else { p = *n; *n = p->next; } mutex_unlock(&block_subsys_lock); kfree(p); - - return ret; } EXPORT_SYMBOL(unregister_blkdev); @@ -726,21 +722,21 @@ struct gendisk *alloc_disk_node(int minors, int node_id) { struct gendisk *disk; - disk = kmalloc_node(sizeof(struct gendisk), GFP_KERNEL, node_id); + disk = kmalloc_node(sizeof(struct gendisk), + GFP_KERNEL | __GFP_ZERO, node_id); if (disk) { - memset(disk, 0, sizeof(struct gendisk)); if (!init_disk_stats(disk)) { kfree(disk); return NULL; } if (minors > 1) { int size = (minors - 1) * sizeof(struct hd_struct *); - disk->part = kmalloc_node(size, GFP_KERNEL, node_id); + disk->part = kmalloc_node(size, + GFP_KERNEL | __GFP_ZERO, node_id); if (!disk->part) { kfree(disk); return NULL; } - memset(disk->part, 0, size); } disk->minors = minors; kobj_set_kset_s(disk,block_subsys); diff --git a/block/ll_rw_blk.c b/block/ll_rw_blk.c index 6b5173ac813..66056ca5e63 100644 --- a/block/ll_rw_blk.c +++ b/block/ll_rw_blk.c @@ -256,6 +256,7 @@ static void rq_init(request_queue_t *q, struct request *rq) rq->end_io = NULL; rq->end_io_data = NULL; rq->completion_data = NULL; + rq->next_rq = NULL; } /** @@ -340,6 +341,15 @@ unsigned blk_ordered_req_seq(struct request *rq) if (rq == &q->post_flush_rq) return QUEUE_ORDSEQ_POSTFLUSH; + /* + * !fs requests don't need to follow barrier ordering. Always + * put them at the front. This fixes the following deadlock. + * + * http://thread.gmane.org/gmane.linux.kernel/537473 + */ + if (!blk_fs_request(rq)) + return QUEUE_ORDSEQ_DRAIN; + if ((rq->cmd_flags & REQ_ORDERED_COLOR) == (q->orig_bar_rq->cmd_flags & REQ_ORDERED_COLOR)) return QUEUE_ORDSEQ_DRAIN; @@ -518,8 +528,6 @@ int blk_do_ordered(request_queue_t *q, struct request **rqp) static int flush_dry_bio_endio(struct bio *bio, unsigned int bytes, int error) { request_queue_t *q = bio->bi_private; - struct bio_vec *bvec; - int i; /* * This is dry run, restore bio_sector and size. We'll finish @@ -531,13 +539,6 @@ static int flush_dry_bio_endio(struct bio *bio, unsigned int bytes, int error) if (bio->bi_size) return 1; - /* Rewind bvec's */ - bio->bi_idx = 0; - bio_for_each_segment(bvec, bio, i) { - bvec->bv_len += bvec->bv_offset; - bvec->bv_offset = 0; - } - /* Reset bio */ set_bit(BIO_UPTODATE, &bio->bi_flags); bio->bi_size = q->bi_size; @@ -1295,9 +1296,9 @@ static int blk_hw_contig_segment(request_queue_t *q, struct bio *bio, if (unlikely(!bio_flagged(nxt, BIO_SEG_VALID))) blk_recount_segments(q, nxt); if (!BIOVEC_VIRT_MERGEABLE(__BVEC_END(bio), __BVEC_START(nxt)) || - BIOVEC_VIRT_OVERSIZE(bio->bi_hw_front_size + bio->bi_hw_back_size)) + BIOVEC_VIRT_OVERSIZE(bio->bi_hw_back_size + nxt->bi_hw_front_size)) return 0; - if (bio->bi_size + nxt->bi_size > q->max_segment_size) + if (bio->bi_hw_back_size + nxt->bi_hw_front_size > q->max_segment_size) return 0; return 1; @@ -1828,11 +1829,11 @@ request_queue_t *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) { request_queue_t *q; - q = kmem_cache_alloc_node(requestq_cachep, gfp_mask, node_id); + q = kmem_cache_alloc_node(requestq_cachep, + gfp_mask | __GFP_ZERO, node_id); if (!q) return NULL; - memset(q, 0, sizeof(*q)); init_timer(&q->unplug_timer); snprintf(q->kobj.name, KOBJ_NAME_LEN, "%s", "queue"); @@ -3697,13 +3698,13 @@ int __init blk_dev_init(void) panic("Failed to create kblockd\n"); request_cachep = kmem_cache_create("blkdev_requests", - sizeof(struct request), 0, SLAB_PANIC, NULL, NULL); + sizeof(struct request), 0, SLAB_PANIC, NULL); requestq_cachep = kmem_cache_create("blkdev_queue", - sizeof(request_queue_t), 0, SLAB_PANIC, NULL, NULL); + sizeof(request_queue_t), 0, SLAB_PANIC, NULL); iocontext_cachep = kmem_cache_create("blkdev_ioc", - sizeof(struct io_context), 0, SLAB_PANIC, NULL, NULL); + sizeof(struct io_context), 0, SLAB_PANIC, NULL); for_each_possible_cpu(i) INIT_LIST_HEAD(&per_cpu(blk_cpu_done, i)); diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index e83f1dbf7c2..71bdf88884b 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -41,8 +41,6 @@ const unsigned char scsi_command_size[8] = EXPORT_SYMBOL(scsi_command_size); -#define BLK_DEFAULT_TIMEOUT (60 * HZ) - #include <scsi/sg.h> static int sg_get_version(int __user *p) @@ -114,7 +112,7 @@ static int sg_emulated_host(request_queue_t *q, int __user *p) #define safe_for_read(cmd) [cmd] = CMD_READ_SAFE #define safe_for_write(cmd) [cmd] = CMD_WRITE_SAFE -static int verify_command(struct file *file, unsigned char *cmd) +int blk_verify_command(unsigned char *cmd, int has_write_perm) { static unsigned char cmd_type[256] = { @@ -193,18 +191,11 @@ static int verify_command(struct file *file, unsigned char *cmd) safe_for_write(GPCMD_SET_STREAMING), }; unsigned char type = cmd_type[cmd[0]]; - int has_write_perm = 0; /* Anybody who can open the device can do a read-safe command */ if (type & CMD_READ_SAFE) return 0; - /* - * file can be NULL from ioctl_by_bdev()... - */ - if (file) - has_write_perm = file->f_mode & FMODE_WRITE; - /* Write-safe commands just require a writable open.. */ if ((type & CMD_WRITE_SAFE) && has_write_perm) return 0; @@ -221,25 +212,96 @@ static int verify_command(struct file *file, unsigned char *cmd) /* Otherwise fail it with an "Operation not permitted" */ return -EPERM; } +EXPORT_SYMBOL_GPL(blk_verify_command); + +int blk_fill_sghdr_rq(request_queue_t *q, struct request *rq, + struct sg_io_hdr *hdr, int has_write_perm) +{ + memset(rq->cmd, 0, BLK_MAX_CDB); /* ATAPI hates garbage after CDB */ + + if (copy_from_user(rq->cmd, hdr->cmdp, hdr->cmd_len)) + return -EFAULT; + if (blk_verify_command(rq->cmd, has_write_perm)) + return -EPERM; + + /* + * fill in request structure + */ + rq->cmd_len = hdr->cmd_len; + rq->cmd_type = REQ_TYPE_BLOCK_PC; + + rq->timeout = (hdr->timeout * HZ) / 1000; + if (!rq->timeout) + rq->timeout = q->sg_timeout; + if (!rq->timeout) + rq->timeout = BLK_DEFAULT_SG_TIMEOUT; + + return 0; +} +EXPORT_SYMBOL_GPL(blk_fill_sghdr_rq); + +/* + * unmap a request that was previously mapped to this sg_io_hdr. handles + * both sg and non-sg sg_io_hdr. + */ +int blk_unmap_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr) +{ + blk_rq_unmap_user(rq->bio); + blk_put_request(rq); + return 0; +} +EXPORT_SYMBOL_GPL(blk_unmap_sghdr_rq); + +int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr, + struct bio *bio) +{ + int r, ret = 0; + + /* + * fill in all the output members + */ + hdr->status = rq->errors & 0xff; + hdr->masked_status = status_byte(rq->errors); + hdr->msg_status = msg_byte(rq->errors); + hdr->host_status = host_byte(rq->errors); + hdr->driver_status = driver_byte(rq->errors); + hdr->info = 0; + if (hdr->masked_status || hdr->host_status || hdr->driver_status) + hdr->info |= SG_INFO_CHECK; + hdr->resid = rq->data_len; + hdr->sb_len_wr = 0; + + if (rq->sense_len && hdr->sbp) { + int len = min((unsigned int) hdr->mx_sb_len, rq->sense_len); + + if (!copy_to_user(hdr->sbp, rq->sense, len)) + hdr->sb_len_wr = len; + else + ret = -EFAULT; + } + + rq->bio = bio; + r = blk_unmap_sghdr_rq(rq, hdr); + if (ret) + r = ret; + + return r; +} +EXPORT_SYMBOL_GPL(blk_complete_sghdr_rq); static int sg_io(struct file *file, request_queue_t *q, struct gendisk *bd_disk, struct sg_io_hdr *hdr) { - unsigned long start_time, timeout; - int writing = 0, ret = 0; + unsigned long start_time; + int writing = 0, ret = 0, has_write_perm = 0; struct request *rq; char sense[SCSI_SENSE_BUFFERSIZE]; - unsigned char cmd[BLK_MAX_CDB]; struct bio *bio; if (hdr->interface_id != 'S') return -EINVAL; if (hdr->cmd_len > BLK_MAX_CDB) return -EINVAL; - if (copy_from_user(cmd, hdr->cmdp, hdr->cmd_len)) - return -EFAULT; - if (verify_command(file, cmd)) - return -EPERM; if (hdr->dxfer_len > (q->max_hw_sectors << 9)) return -EIO; @@ -260,25 +322,13 @@ static int sg_io(struct file *file, request_queue_t *q, if (!rq) return -ENOMEM; - /* - * fill in request structure - */ - rq->cmd_len = hdr->cmd_len; - memset(rq->cmd, 0, BLK_MAX_CDB); /* ATAPI hates garbage after CDB */ - memcpy(rq->cmd, cmd, hdr->cmd_len); - - memset(sense, 0, sizeof(sense)); - rq->sense = sense; - rq->sense_len = 0; - - rq->cmd_type = REQ_TYPE_BLOCK_PC; + if (file) + has_write_perm = file->f_mode & FMODE_WRITE; - timeout = msecs_to_jiffies(hdr->timeout); - rq->timeout = (timeout < INT_MAX) ? timeout : INT_MAX; - if (!rq->timeout) - rq->timeout = q->sg_timeout; - if (!rq->timeout) - rq->timeout = BLK_DEFAULT_TIMEOUT; + if (blk_fill_sghdr_rq(q, rq, hdr, has_write_perm)) { + blk_put_request(rq); + return -EFAULT; + } if (hdr->iovec_count) { const int size = sizeof(struct sg_iovec) * hdr->iovec_count; @@ -306,6 +356,9 @@ static int sg_io(struct file *file, request_queue_t *q, goto out; bio = rq->bio; + memset(sense, 0, sizeof(sense)); + rq->sense = sense; + rq->sense_len = 0; rq->retries = 0; start_time = jiffies; @@ -316,31 +369,9 @@ static int sg_io(struct file *file, request_queue_t *q, */ blk_execute_rq(q, bd_disk, rq, 0); - /* write to all output members */ - hdr->status = 0xff & rq->errors; - hdr->masked_status = status_byte(rq->errors); - hdr->msg_status = msg_byte(rq->errors); - hdr->host_status = host_byte(rq->errors); - hdr->driver_status = driver_byte(rq->errors); - hdr->info = 0; - if (hdr->masked_status || hdr->host_status || hdr->driver_status) - hdr->info |= SG_INFO_CHECK; - hdr->resid = rq->data_len; hdr->duration = ((jiffies - start_time) * 1000) / HZ; - hdr->sb_len_wr = 0; - - if (rq->sense_len && hdr->sbp) { - int len = min((unsigned int) hdr->mx_sb_len, rq->sense_len); - - if (!copy_to_user(hdr->sbp, rq->sense, len)) - hdr->sb_len_wr = len; - } - if (blk_rq_unmap_user(bio)) - ret = -EFAULT; - - /* may not have succeeded, but output values written to control - * structure (struct sg_io_hdr). */ + return blk_complete_sghdr_rq(rq, hdr, bio); out: blk_put_request(rq); return ret; @@ -405,11 +436,10 @@ int sg_scsi_ioctl(struct file *file, struct request_queue *q, bytes = max(in_len, out_len); if (bytes) { - buffer = kmalloc(bytes, q->bounce_gfp | GFP_USER| __GFP_NOWARN); + buffer = kzalloc(bytes, q->bounce_gfp | GFP_USER| __GFP_NOWARN); if (!buffer) return -ENOMEM; - memset(buffer, 0, bytes); } rq = blk_get_request(q, in_len ? WRITE : READ, __GFP_WAIT); @@ -427,7 +457,7 @@ int sg_scsi_ioctl(struct file *file, struct request_queue *q, if (in_len && copy_from_user(buffer, sic->data + cmdlen, in_len)) goto error; - err = verify_command(file, rq->cmd); + err = blk_verify_command(rq->cmd, file->f_mode & FMODE_WRITE); if (err) goto error; @@ -454,7 +484,7 @@ int sg_scsi_ioctl(struct file *file, struct request_queue *q, rq->retries = 1; break; default: - rq->timeout = BLK_DEFAULT_TIMEOUT; + rq->timeout = BLK_DEFAULT_SG_TIMEOUT; break; } @@ -501,7 +531,7 @@ static int __blk_send_generic(request_queue_t *q, struct gendisk *bd_disk, int c rq->cmd_type = REQ_TYPE_BLOCK_PC; rq->data = NULL; rq->data_len = 0; - rq->timeout = BLK_DEFAULT_TIMEOUT; + rq->timeout = BLK_DEFAULT_SG_TIMEOUT; memset(rq->cmd, 0, sizeof(rq->cmd)); rq->cmd[0] = cmd; rq->cmd[4] = data; @@ -517,16 +547,12 @@ static inline int blk_send_start_stop(request_queue_t *q, struct gendisk *bd_dis return __blk_send_generic(q, bd_disk, GPCMD_START_STOP_UNIT, data); } -int scsi_cmd_ioctl(struct file *file, struct gendisk *bd_disk, unsigned int cmd, void __user *arg) +int scsi_cmd_ioctl(struct file *file, struct request_queue *q, + struct gendisk *bd_disk, unsigned int cmd, void __user *arg) { - request_queue_t *q; int err; - q = bd_disk->queue; - if (!q) - return -ENXIO; - - if (blk_get_queue(q)) + if (!q || blk_get_queue(q)) return -ENXIO; switch (cmd) { |