diff options
Diffstat (limited to 'block/ioctl.c')
| -rw-r--r-- | block/ioctl.c | 241 |
1 files changed, 150 insertions, 91 deletions
diff --git a/block/ioctl.c b/block/ioctl.c index 0f22e629b13..7d5c3b20af4 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -1,10 +1,11 @@ #include <linux/capability.h> #include <linux/blkdev.h> +#include <linux/export.h> +#include <linux/gfp.h> #include <linux/blkpg.h> #include <linux/hdreg.h> #include <linux/backing-dev.h> -#include <linux/buffer_head.h> -#include <linux/smp_lock.h> +#include <linux/fs.h> #include <linux/blktrace_api.h> #include <asm/uaccess.h> @@ -12,7 +13,7 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user { struct block_device *bdevp; struct gendisk *disk; - struct hd_struct *part; + struct hd_struct *part, *lpart; struct blkpg_ioctl_arg a; struct blkpg_partition p; struct disk_part_iter piter; @@ -35,12 +36,12 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user case BLKPG_ADD_PARTITION: start = p.start >> 9; length = p.length >> 9; - /* check for fit in a hd_struct */ - if (sizeof(sector_t) == sizeof(long) && + /* check for fit in a hd_struct */ + if (sizeof(sector_t) == sizeof(long) && sizeof(long long) > sizeof(long)) { long pstart = start, plength = length; if (pstart != start || plength != length - || pstart < 0 || plength < 0) + || pstart < 0 || plength < 0 || partno > 65535) return -EINVAL; } @@ -61,9 +62,9 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user /* all seems OK */ part = add_partition(disk, partno, start, length, - ADDPART_FLAG_NONE); + ADDPART_FLAG_NONE, NULL); mutex_unlock(&bdev->bd_mutex); - return IS_ERR(part) ? PTR_ERR(part) : 0; + return PTR_ERR_OR_ZERO(part); case BLKPG_DEL_PARTITION: part = disk_get_part(disk, partno); if (!part) @@ -91,6 +92,59 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user bdput(bdevp); return 0; + case BLKPG_RESIZE_PARTITION: + start = p.start >> 9; + /* new length of partition in bytes */ + length = p.length >> 9; + /* check for fit in a hd_struct */ + if (sizeof(sector_t) == sizeof(long) && + sizeof(long long) > sizeof(long)) { + long pstart = start, plength = length; + if (pstart != start || plength != length + || pstart < 0 || plength < 0) + return -EINVAL; + } + part = disk_get_part(disk, partno); + if (!part) + return -ENXIO; + bdevp = bdget(part_devt(part)); + if (!bdevp) { + disk_put_part(part); + return -ENOMEM; + } + mutex_lock(&bdevp->bd_mutex); + mutex_lock_nested(&bdev->bd_mutex, 1); + if (start != part->start_sect) { + mutex_unlock(&bdevp->bd_mutex); + mutex_unlock(&bdev->bd_mutex); + bdput(bdevp); + disk_put_part(part); + return -EINVAL; + } + /* overlap? */ + disk_part_iter_init(&piter, disk, + DISK_PITER_INCL_EMPTY); + while ((lpart = disk_part_iter_next(&piter))) { + if (lpart->partno != partno && + !(start + length <= lpart->start_sect || + start >= lpart->start_sect + lpart->nr_sects) + ) { + disk_part_iter_exit(&piter); + mutex_unlock(&bdevp->bd_mutex); + mutex_unlock(&bdev->bd_mutex); + bdput(bdevp); + disk_put_part(part); + return -EBUSY; + } + } + disk_part_iter_exit(&piter); + part_nr_sects_write(part, (sector_t)length); + i_size_write(bdevp->bd_inode, p.length); + mutex_unlock(&bdevp->bd_mutex); + mutex_unlock(&bdev->bd_mutex); + bdput(bdevp); + disk_put_part(part); + return 0; default: return -EINVAL; } @@ -101,7 +155,7 @@ static int blkdev_reread_part(struct block_device *bdev) struct gendisk *disk = bdev->bd_disk; int res; - if (!disk_partitionable(disk) || bdev != bdev->bd_contains) + if (!disk_part_scan_enabled(disk) || bdev != bdev->bd_contains) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EACCES; @@ -112,21 +166,10 @@ static int blkdev_reread_part(struct block_device *bdev) return res; } -static void blk_ioc_discard_endio(struct bio *bio, int err) -{ - if (err) { - if (err == -EOPNOTSUPP) - set_bit(BIO_EOPNOTSUPP, &bio->bi_flags); - clear_bit(BIO_UPTODATE, &bio->bi_flags); - } - complete(bio->bi_private); -} - static int blk_ioctl_discard(struct block_device *bdev, uint64_t start, - uint64_t len) + uint64_t len, int secure) { - struct request_queue *q = bdev_get_queue(bdev); - int ret = 0; + unsigned long flags = 0; if (start & 511) return -EINVAL; @@ -135,44 +178,27 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start, start >>= 9; len >>= 9; - if (start + len > (bdev->bd_inode->i_size >> 9)) + if (start + len > (i_size_read(bdev->bd_inode) >> 9)) return -EINVAL; + if (secure) + flags |= BLKDEV_DISCARD_SECURE; + return blkdev_issue_discard(bdev, start, len, GFP_KERNEL, flags); +} - if (!q->prepare_discard_fn) - return -EOPNOTSUPP; - - while (len && !ret) { - DECLARE_COMPLETION_ONSTACK(wait); - struct bio *bio; - - bio = bio_alloc(GFP_KERNEL, 0); - if (!bio) - return -ENOMEM; - - bio->bi_end_io = blk_ioc_discard_endio; - bio->bi_bdev = bdev; - bio->bi_private = &wait; - bio->bi_sector = start; - - if (len > q->max_hw_sectors) { - bio->bi_size = q->max_hw_sectors << 9; - len -= q->max_hw_sectors; - start += q->max_hw_sectors; - } else { - bio->bi_size = len << 9; - len = 0; - } - submit_bio(DISCARD_NOBARRIER, bio); +static int blk_ioctl_zeroout(struct block_device *bdev, uint64_t start, + uint64_t len) +{ + if (start & 511) + return -EINVAL; + if (len & 511) + return -EINVAL; + start >>= 9; + len >>= 9; - wait_for_completion(&wait); + if (start + len > (i_size_read(bdev->bd_inode) >> 9)) + return -EINVAL; - if (bio_flagged(bio, BIO_EOPNOTSUPP)) - ret = -EOPNOTSUPP; - else if (!bio_flagged(bio, BIO_UPTODATE)) - ret = -EIO; - bio_put(bio); - } - return ret; + return blkdev_issue_zeroout(bdev, start, len, GFP_KERNEL); } static int put_ushort(unsigned long arg, unsigned short val) @@ -185,6 +211,11 @@ static int put_int(unsigned long arg, int val) return put_user(val, (int __user *)arg); } +static int put_uint(unsigned long arg, unsigned int val) +{ + return put_user(val, (unsigned int __user *)arg); +} + static int put_long(unsigned long arg, long val) { return put_user(val, (long __user *)arg); @@ -204,18 +235,10 @@ int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long arg) { struct gendisk *disk = bdev->bd_disk; - int ret; if (disk->fops->ioctl) return disk->fops->ioctl(bdev, mode, cmd, arg); - if (disk->fops->locked_ioctl) { - lock_kernel(); - ret = disk->fops->locked_ioctl(bdev, mode, cmd, arg); - unlock_kernel(); - return ret; - } - return -ENOTTY; } /* @@ -226,8 +249,27 @@ int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode, EXPORT_SYMBOL_GPL(__blkdev_driver_ioctl); /* - * always keep this in sync with compat_blkdev_ioctl() and - * compat_blkdev_locked_ioctl() + * Is it an unrecognized ioctl? The correct returns are either + * ENOTTY (final) or ENOIOCTLCMD ("I don't know this one, try a + * fallback"). ENOIOCTLCMD gets turned into ENOTTY by the ioctl + * code before returning. + * + * Confused drivers sometimes return EINVAL, which is wrong. It + * means "I understood the ioctl command, but the parameters to + * it were wrong". + * + * We should aim to just fix the broken drivers, the EINVAL case + * should go away. + */ +static inline int is_unrecognized_ioctl(int ret) +{ + return ret == -EINVAL || + ret == -ENOTTY || + ret == -ENOIOCTLCMD; +} + +/* + * always keep this in sync with compat_blkdev_ioctl() */ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long arg) @@ -243,31 +285,38 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, return -EACCES; ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg); - /* -EINVAL to handle old uncorrected drivers */ - if (ret != -EINVAL && ret != -ENOTTY) + if (!is_unrecognized_ioctl(ret)) return ret; - lock_kernel(); fsync_bdev(bdev); invalidate_bdev(bdev); - unlock_kernel(); return 0; case BLKROSET: ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg); - /* -EINVAL to handle old uncorrected drivers */ - if (ret != -EINVAL && ret != -ENOTTY) + if (!is_unrecognized_ioctl(ret)) return ret; if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (get_user(n, (int __user *)(arg))) return -EFAULT; - lock_kernel(); set_device_ro(bdev, n); - unlock_kernel(); return 0; - case BLKDISCARD: { + case BLKDISCARD: + case BLKSECDISCARD: { + uint64_t range[2]; + + if (!(mode & FMODE_WRITE)) + return -EBADF; + + if (copy_from_user(range, (void __user *)arg, sizeof(range))) + return -EFAULT; + + return blk_ioctl_discard(bdev, range[0], range[1], + cmd == BLKSECDISCARD); + } + case BLKZEROOUT: { uint64_t range[2]; if (!(mode & FMODE_WRITE)) @@ -276,7 +325,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, if (copy_from_user(range, (void __user *)arg, sizeof(range))) return -EFAULT; - return blk_ioctl_discard(bdev, range[0], range[1]); + return blk_ioctl_zeroout(bdev, range[0], range[1]); } case HDIO_GETGEO: { @@ -291,6 +340,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, * We need to set the startsect first, the driver may * want to override it. */ + memset(&geo, 0, sizeof(geo)); geo.start = get_start_sect(bdev); ret = disk->fops->getgeo(bdev, &geo); if (ret) @@ -310,12 +360,24 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, return put_long(arg, (bdi->ra_pages * PAGE_CACHE_SIZE) / 512); case BLKROGET: return put_int(arg, bdev_read_only(bdev) != 0); - case BLKBSZGET: /* get the logical block size (cf. BLKSSZGET) */ + case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */ return put_int(arg, block_size(bdev)); - case BLKSSZGET: /* get block device hardware sector size */ - return put_int(arg, bdev_hardsect_size(bdev)); + case BLKSSZGET: /* get block device logical block size */ + return put_int(arg, bdev_logical_block_size(bdev)); + case BLKPBSZGET: /* get block device physical block size */ + return put_uint(arg, bdev_physical_block_size(bdev)); + case BLKIOMIN: + return put_uint(arg, bdev_io_min(bdev)); + case BLKIOOPT: + return put_uint(arg, bdev_io_opt(bdev)); + case BLKALIGNOFF: + return put_int(arg, bdev_alignment_offset(bdev)); + case BLKDISCARDZEROES: + return put_uint(arg, bdev_discard_zeroes_data(bdev)); case BLKSECTGET: - return put_ushort(arg, bdev_get_queue(bdev)->max_sectors); + return put_ushort(arg, queue_max_sectors(bdev_get_queue(bdev))); + case BLKROTATIONAL: + return put_ushort(arg, !blk_queue_nonrot(bdev_get_queue(bdev))); case BLKRASET: case BLKFRASET: if(!capable(CAP_SYS_ADMIN)) @@ -333,36 +395,33 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, return -EINVAL; if (get_user(n, (int __user *) arg)) return -EFAULT; - if (!(mode & FMODE_EXCL) && bd_claim(bdev, &bdev) < 0) - return -EBUSY; + if (!(mode & FMODE_EXCL)) { + bdgrab(bdev); + if (blkdev_get(bdev, mode | FMODE_EXCL, &bdev) < 0) + return -EBUSY; + } ret = set_blocksize(bdev, n); if (!(mode & FMODE_EXCL)) - bd_release(bdev); + blkdev_put(bdev, mode | FMODE_EXCL); return ret; case BLKPG: - lock_kernel(); ret = blkpg_ioctl(bdev, (struct blkpg_ioctl_arg __user *) arg); - unlock_kernel(); break; case BLKRRPART: - lock_kernel(); ret = blkdev_reread_part(bdev); - unlock_kernel(); break; case BLKGETSIZE: - size = bdev->bd_inode->i_size; + size = i_size_read(bdev->bd_inode); if ((size >> 9) > ~0UL) return -EFBIG; return put_ulong(arg, size >> 9); case BLKGETSIZE64: - return put_u64(arg, bdev->bd_inode->i_size); + return put_u64(arg, i_size_read(bdev->bd_inode)); case BLKTRACESTART: case BLKTRACESTOP: case BLKTRACESETUP: case BLKTRACETEARDOWN: - lock_kernel(); ret = blk_trace_ioctl(bdev, cmd, (char __user *) arg); - unlock_kernel(); break; default: ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg); |