X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=drivers%2Fblock%2Floop.c;h=99e9c565558590fe184c6080c297e8bad492b7e1;hb=97bf2856c6014879bd04983a3e9dfcdac1e7fe85;hp=5f6d1a5cce11fc3bebdf1f0ab29c875db7850e09;hpb=76828883507a47dae78837ab5dec5a5b4513c667;p=linux-2.6.git diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 5f6d1a5cc..99e9c5655 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -50,7 +50,6 @@ * */ -#include #include #include #include @@ -63,17 +62,19 @@ #include #include #include -#include #include #include #include #include +#include #include #include #include /* for invalidate_bdev() */ #include #include #include +#include +#include #include @@ -210,7 +211,7 @@ static int do_lo_send_aops(struct loop_device *lo, struct bio_vec *bvec, { struct file *file = lo->lo_backing_file; /* kudos to NFsckingS */ struct address_space *mapping = file->f_mapping; - struct address_space_operations *aops = mapping->a_ops; + const struct address_space_operations *aops = mapping->a_ops; pgoff_t index; unsigned offset, bv_offs; int len, ret; @@ -295,7 +296,7 @@ fail: * and do_lo_send_write(). */ static int __do_lo_send_write(struct file *file, - u8 __user *buf, const int len, loff_t pos) + u8 *buf, const int len, loff_t pos) { ssize_t bw; mm_segment_t old_fs = get_fs(); @@ -324,7 +325,7 @@ static int do_lo_send_direct_write(struct loop_device *lo, struct bio_vec *bvec, int bsize, loff_t pos, struct page *page) { ssize_t bw = __do_lo_send_write(lo->lo_backing_file, - (u8 __user *)kmap(bvec->bv_page) + bvec->bv_offset, + kmap(bvec->bv_page) + bvec->bv_offset, bvec->bv_len, pos); kunmap(bvec->bv_page); cond_resched(); @@ -351,7 +352,7 @@ static int do_lo_send_write(struct loop_device *lo, struct bio_vec *bvec, bvec->bv_offset, bvec->bv_len, pos >> 9); if (likely(!ret)) return __do_lo_send_write(lo->lo_backing_file, - (u8 __user *)page_address(page), bvec->bv_len, + page_address(page), bvec->bv_len, pos); printk(KERN_ERR "loop: Transfer error at byte offset %llu, " "length %i.\n", (unsigned long long)pos, bvec->bv_len); @@ -524,15 +525,12 @@ static int loop_make_request(request_queue_t *q, struct bio *old_bio) goto out; if (unlikely(rw == WRITE && (lo->lo_flags & LO_FLAGS_READ_ONLY))) goto out; - lo->lo_pending++; loop_add_bio(lo, old_bio); + wake_up(&lo->lo_event); spin_unlock_irq(&lo->lo_lock); - complete(&lo->lo_bh_done); return 0; out: - if (lo->lo_pending == 0) - complete(&lo->lo_bh_done); spin_unlock_irq(&lo->lo_lock); bio_io_error(old_bio, old_bio->bi_size); return 0; @@ -572,14 +570,18 @@ static inline void loop_handle_bio(struct loop_device *lo, struct bio *bio) * to avoid blocking in our make_request_fn. it also does loop decrypting * on reads for block backed loop, as that is too heavy to do from * b_end_io context where irqs may be disabled. + * + * Loop explanation: loop_clr_fd() sets lo_state to Lo_rundown before + * calling kthread_stop(). Therefore once kthread_should_stop() is + * true, make_request will not place any more requests. Therefore + * once kthread_should_stop() is true and lo_bio is NULL, we are + * done with the loop. */ static int loop_thread(void *data) { struct loop_device *lo = data; struct bio *bio; - daemonize("loop%d", lo->lo_number); - /* * loop can be used in an encrypted device, * hence, it mustn't be stopped at all @@ -589,47 +591,21 @@ static int loop_thread(void *data) set_user_nice(current, -20); - lo->lo_state = Lo_bound; - lo->lo_pending = 1; + while (!kthread_should_stop() || lo->lo_bio) { - /* - * complete it, we are running - */ - complete(&lo->lo_done); - - for (;;) { - int pending; + wait_event_interruptible(lo->lo_event, + lo->lo_bio || kthread_should_stop()); - if (wait_for_completion_interruptible(&lo->lo_bh_done)) + if (!lo->lo_bio) continue; - spin_lock_irq(&lo->lo_lock); - - /* - * could be completed because of tear-down, not pending work - */ - if (unlikely(!lo->lo_pending)) { - spin_unlock_irq(&lo->lo_lock); - break; - } - bio = loop_get_bio(lo); - lo->lo_pending--; - pending = lo->lo_pending; spin_unlock_irq(&lo->lo_lock); BUG_ON(!bio); loop_handle_bio(lo, bio); - - /* - * upped both for pending work and tear-down, lo_pending - * will hit zero then - */ - if (unlikely(!pending)) - break; } - complete(&lo->lo_done); return 0; } @@ -664,7 +640,8 @@ static void do_loop_switch(struct loop_device *lo, struct switch_request *p) mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask); lo->lo_backing_file = file; - lo->lo_blocksize = mapping->host->i_blksize; + lo->lo_blocksize = S_ISBLK(mapping->host->i_mode) ? + mapping->host->i_bdev->bd_block_size : PAGE_SIZE; lo->old_gfp_mask = mapping_gfp_mask(mapping); mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS)); complete(&p->wait); @@ -784,7 +761,7 @@ static int loop_set_fd(struct loop_device *lo, struct file *lo_file, error = -EINVAL; if (S_ISREG(inode->i_mode) || S_ISBLK(inode->i_mode)) { - struct address_space_operations *aops = mapping->a_ops; + const struct address_space_operations *aops = mapping->a_ops; /* * If we can't read - sorry. If we only can't write - well, * it's going to be read-only. @@ -796,7 +773,9 @@ static int loop_set_fd(struct loop_device *lo, struct file *lo_file, if (!(lo_flags & LO_FLAGS_USE_AOPS) && !file->f_op->write) lo_flags |= LO_FLAGS_READ_ONLY; - lo_blocksize = inode->i_blksize; + lo_blocksize = S_ISBLK(inode->i_mode) ? + inode->i_bdev->bd_block_size : PAGE_SIZE; + error = 0; } else { goto out_putf; @@ -817,8 +796,9 @@ static int loop_set_fd(struct loop_device *lo, struct file *lo_file, lo->lo_blocksize = lo_blocksize; lo->lo_device = bdev; lo->lo_flags = lo_flags; + lo->lo_xid = vx_current_xid(); lo->lo_backing_file = file; - lo->transfer = NULL; + lo->transfer = transfer_none; lo->ioctl = NULL; lo->lo_sizelimit = 0; lo->old_gfp_mask = mapping_gfp_mask(mapping); @@ -839,10 +819,26 @@ static int loop_set_fd(struct loop_device *lo, struct file *lo_file, set_blocksize(bdev, lo_blocksize); - kernel_thread(loop_thread, lo, CLONE_KERNEL); - wait_for_completion(&lo->lo_done); + lo->lo_thread = kthread_create(loop_thread, lo, "loop%d", + lo->lo_number); + if (IS_ERR(lo->lo_thread)) { + error = PTR_ERR(lo->lo_thread); + goto out_clr; + } + lo->lo_state = Lo_bound; + wake_up_process(lo->lo_thread); return 0; +out_clr: + lo->lo_thread = NULL; + lo->lo_device = NULL; + lo->lo_backing_file = NULL; + lo->lo_flags = 0; + set_capacity(disks[lo->lo_number], 0); + invalidate_bdev(bdev, 0); + bd_set_size(bdev, 0); + mapping_set_gfp_mask(mapping, lo->old_gfp_mask); + lo->lo_state = Lo_unbound; out_putf: fput(file); out: @@ -904,12 +900,9 @@ static int loop_clr_fd(struct loop_device *lo, struct block_device *bdev) spin_lock_irq(&lo->lo_lock); lo->lo_state = Lo_rundown; - lo->lo_pending--; - if (!lo->lo_pending) - complete(&lo->lo_bh_done); spin_unlock_irq(&lo->lo_lock); - wait_for_completion(&lo->lo_done); + kthread_stop(lo->lo_thread); lo->lo_backing_file = NULL; @@ -922,6 +915,7 @@ static int loop_clr_fd(struct loop_device *lo, struct block_device *bdev) lo->lo_sizelimit = 0; lo->lo_encrypt_key_size = 0; lo->lo_flags = 0; + lo->lo_thread = NULL; memset(lo->lo_encrypt_key, 0, LO_KEY_SIZE); memset(lo->lo_crypt_name, 0, LO_NAME_SIZE); memset(lo->lo_file_name, 0, LO_NAME_SIZE); @@ -943,7 +937,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) struct loop_func_table *xfer; if (lo->lo_encrypt_key_size && lo->lo_key_owner != current->uid && - !capable(CAP_SYS_ADMIN)) + !vx_capable(CAP_SYS_ADMIN, VXC_ADMIN_CLOOP)) return -EPERM; if (lo->lo_state != Lo_bound) return -ENXIO; @@ -1008,7 +1002,7 @@ loop_get_status(struct loop_device *lo, struct loop_info64 *info) if (lo->lo_state != Lo_bound) return -ENXIO; - error = vfs_getattr(file->f_vfsmnt, file->f_dentry, &stat); + error = vfs_getattr(file->f_path.mnt, file->f_path.dentry, &stat); if (error) return error; memset(info, 0, sizeof(*info)); @@ -1023,7 +1017,8 @@ loop_get_status(struct loop_device *lo, struct loop_info64 *info) memcpy(info->lo_crypt_name, lo->lo_crypt_name, LO_NAME_SIZE); info->lo_encrypt_type = lo->lo_encryption ? lo->lo_encryption->number : 0; - if (lo->lo_encrypt_key_size && capable(CAP_SYS_ADMIN)) { + if (lo->lo_encrypt_key_size && + vx_capable(CAP_SYS_ADMIN, VXC_ADMIN_CLOOP)) { info->lo_encrypt_key_size = lo->lo_encrypt_key_size; memcpy(info->lo_encrypt_key, lo->lo_encrypt_key, lo->lo_encrypt_key_size); @@ -1144,7 +1139,7 @@ static int lo_ioctl(struct inode * inode, struct file * file, struct loop_device *lo = inode->i_bdev->bd_disk->private_data; int err; - down(&lo->lo_ctl_mutex); + mutex_lock(&lo->lo_ctl_mutex); switch (cmd) { case LOOP_SET_FD: err = loop_set_fd(lo, file, inode->i_bdev, arg); @@ -1170,17 +1165,176 @@ static int lo_ioctl(struct inode * inode, struct file * file, default: err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL; } - up(&lo->lo_ctl_mutex); + mutex_unlock(&lo->lo_ctl_mutex); return err; } +#ifdef CONFIG_COMPAT +struct compat_loop_info { + compat_int_t lo_number; /* ioctl r/o */ + compat_dev_t lo_device; /* ioctl r/o */ + compat_ulong_t lo_inode; /* ioctl r/o */ + compat_dev_t lo_rdevice; /* ioctl r/o */ + compat_int_t lo_offset; + compat_int_t lo_encrypt_type; + compat_int_t lo_encrypt_key_size; /* ioctl w/o */ + compat_int_t lo_flags; /* ioctl r/o */ + char lo_name[LO_NAME_SIZE]; + unsigned char lo_encrypt_key[LO_KEY_SIZE]; /* ioctl w/o */ + compat_ulong_t lo_init[2]; + char reserved[4]; +}; + +/* + * Transfer 32-bit compatibility structure in userspace to 64-bit loop info + * - noinlined to reduce stack space usage in main part of driver + */ +static noinline int +loop_info64_from_compat(const struct compat_loop_info __user *arg, + struct loop_info64 *info64) +{ + struct compat_loop_info info; + + if (copy_from_user(&info, arg, sizeof(info))) + return -EFAULT; + + memset(info64, 0, sizeof(*info64)); + info64->lo_number = info.lo_number; + info64->lo_device = info.lo_device; + info64->lo_inode = info.lo_inode; + info64->lo_rdevice = info.lo_rdevice; + info64->lo_offset = info.lo_offset; + info64->lo_sizelimit = 0; + info64->lo_encrypt_type = info.lo_encrypt_type; + info64->lo_encrypt_key_size = info.lo_encrypt_key_size; + info64->lo_flags = info.lo_flags; + info64->lo_init[0] = info.lo_init[0]; + info64->lo_init[1] = info.lo_init[1]; + if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI) + memcpy(info64->lo_crypt_name, info.lo_name, LO_NAME_SIZE); + else + memcpy(info64->lo_file_name, info.lo_name, LO_NAME_SIZE); + memcpy(info64->lo_encrypt_key, info.lo_encrypt_key, LO_KEY_SIZE); + return 0; +} + +/* + * Transfer 64-bit loop info to 32-bit compatibility structure in userspace + * - noinlined to reduce stack space usage in main part of driver + */ +static noinline int +loop_info64_to_compat(const struct loop_info64 *info64, + struct compat_loop_info __user *arg) +{ + struct compat_loop_info info; + + memset(&info, 0, sizeof(info)); + info.lo_number = info64->lo_number; + info.lo_device = info64->lo_device; + info.lo_inode = info64->lo_inode; + info.lo_rdevice = info64->lo_rdevice; + info.lo_offset = info64->lo_offset; + info.lo_encrypt_type = info64->lo_encrypt_type; + info.lo_encrypt_key_size = info64->lo_encrypt_key_size; + info.lo_flags = info64->lo_flags; + info.lo_init[0] = info64->lo_init[0]; + info.lo_init[1] = info64->lo_init[1]; + if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI) + memcpy(info.lo_name, info64->lo_crypt_name, LO_NAME_SIZE); + else + memcpy(info.lo_name, info64->lo_file_name, LO_NAME_SIZE); + memcpy(info.lo_encrypt_key, info64->lo_encrypt_key, LO_KEY_SIZE); + + /* error in case values were truncated */ + if (info.lo_device != info64->lo_device || + info.lo_rdevice != info64->lo_rdevice || + info.lo_inode != info64->lo_inode || + info.lo_offset != info64->lo_offset || + info.lo_init[0] != info64->lo_init[0] || + info.lo_init[1] != info64->lo_init[1]) + return -EOVERFLOW; + + if (copy_to_user(arg, &info, sizeof(info))) + return -EFAULT; + return 0; +} + +static int +loop_set_status_compat(struct loop_device *lo, + const struct compat_loop_info __user *arg) +{ + struct loop_info64 info64; + int ret; + + ret = loop_info64_from_compat(arg, &info64); + if (ret < 0) + return ret; + return loop_set_status(lo, &info64); +} + +static int +loop_get_status_compat(struct loop_device *lo, + struct compat_loop_info __user *arg) +{ + struct loop_info64 info64; + int err = 0; + + if (!arg) + err = -EINVAL; + if (!err) + err = loop_get_status(lo, &info64); + if (!err) + err = loop_info64_to_compat(&info64, arg); + return err; +} + +static long lo_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct inode *inode = file->f_path.dentry->d_inode; + struct loop_device *lo = inode->i_bdev->bd_disk->private_data; + int err; + + lock_kernel(); + switch(cmd) { + case LOOP_SET_STATUS: + mutex_lock(&lo->lo_ctl_mutex); + err = loop_set_status_compat( + lo, (const struct compat_loop_info __user *) arg); + mutex_unlock(&lo->lo_ctl_mutex); + break; + case LOOP_GET_STATUS: + mutex_lock(&lo->lo_ctl_mutex); + err = loop_get_status_compat( + lo, (struct compat_loop_info __user *) arg); + mutex_unlock(&lo->lo_ctl_mutex); + break; + case LOOP_CLR_FD: + case LOOP_GET_STATUS64: + case LOOP_SET_STATUS64: + arg = (unsigned long) compat_ptr(arg); + case LOOP_SET_FD: + case LOOP_CHANGE_FD: + err = lo_ioctl(inode, file, cmd, arg); + break; + default: + err = -ENOIOCTLCMD; + break; + } + unlock_kernel(); + return err; +} +#endif + static int lo_open(struct inode *inode, struct file *file) { struct loop_device *lo = inode->i_bdev->bd_disk->private_data; - down(&lo->lo_ctl_mutex); + if (!vx_check(lo->lo_xid, VS_IDENT|VS_HOSTID)) + return -EACCES; + + mutex_lock(&lo->lo_ctl_mutex); lo->lo_refcnt++; - up(&lo->lo_ctl_mutex); + mutex_unlock(&lo->lo_ctl_mutex); return 0; } @@ -1189,9 +1343,9 @@ static int lo_release(struct inode *inode, struct file *file) { struct loop_device *lo = inode->i_bdev->bd_disk->private_data; - down(&lo->lo_ctl_mutex); + mutex_lock(&lo->lo_ctl_mutex); --lo->lo_refcnt; - up(&lo->lo_ctl_mutex); + mutex_unlock(&lo->lo_ctl_mutex); return 0; } @@ -1201,6 +1355,9 @@ static struct block_device_operations lo_fops = { .open = lo_open, .release = lo_release, .ioctl = lo_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = lo_compat_ioctl, +#endif }; /* @@ -1233,12 +1390,12 @@ int loop_unregister_transfer(int number) xfer_funcs[n] = NULL; for (lo = &loop_dev[0]; lo < &loop_dev[max_loop]; lo++) { - down(&lo->lo_ctl_mutex); + mutex_lock(&lo->lo_ctl_mutex); if (lo->lo_encryption == xfer) loop_release_xfer(lo); - up(&lo->lo_ctl_mutex); + mutex_unlock(&lo->lo_ctl_mutex); } return 0; @@ -1275,8 +1432,6 @@ static int __init loop_init(void) goto out_mem3; } - devfs_mk_dir("loop"); - for (i = 0; i < max_loop; i++) { struct loop_device *lo = &loop_dev[i]; struct gendisk *disk = disks[i]; @@ -1285,16 +1440,15 @@ static int __init loop_init(void) lo->lo_queue = blk_alloc_queue(GFP_KERNEL); if (!lo->lo_queue) goto out_mem4; - init_MUTEX(&lo->lo_ctl_mutex); - init_completion(&lo->lo_done); - init_completion(&lo->lo_bh_done); + mutex_init(&lo->lo_ctl_mutex); lo->lo_number = i; + lo->lo_thread = NULL; + init_waitqueue_head(&lo->lo_event); spin_lock_init(&lo->lo_lock); disk->major = LOOP_MAJOR; disk->first_minor = i; disk->fops = &lo_fops; sprintf(disk->disk_name, "loop%d", i); - sprintf(disk->devfs_name, "loop/%d", i); disk->private_data = lo; disk->queue = lo->lo_queue; } @@ -1307,8 +1461,7 @@ static int __init loop_init(void) out_mem4: while (i--) - blk_put_queue(loop_dev[i].lo_queue); - devfs_remove("loop"); + blk_cleanup_queue(loop_dev[i].lo_queue); i = max_loop; out_mem3: while (i--) @@ -1328,10 +1481,9 @@ static void loop_exit(void) for (i = 0; i < max_loop; i++) { del_gendisk(disks[i]); - blk_put_queue(loop_dev[i].lo_queue); + blk_cleanup_queue(loop_dev[i].lo_queue); put_disk(disks[i]); } - devfs_remove("loop"); if (unregister_blkdev(LOOP_MAJOR, "loop")) printk(KERN_WARNING "loop: cannot unregister blkdev\n");