linux/block/ioctl.c

352 lines
8.7 KiB
C
Raw Normal View History

#include <linux/capability.h>
#include <linux/blkdev.h>
#include <linux/export.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/gfp.h>
#include <linux/blkpg.h>
#include <linux/hdreg.h>
#include <linux/backing-dev.h>
#include <linux/fs.h>
#include <linux/blktrace_api.h>
#include <asm/uaccess.h>
static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user *arg)
{
struct block_device *bdevp;
struct gendisk *disk;
struct hd_struct *part;
struct blkpg_ioctl_arg a;
struct blkpg_partition p;
struct disk_part_iter piter;
long long start, length;
int partno;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
if (copy_from_user(&a, arg, sizeof(struct blkpg_ioctl_arg)))
return -EFAULT;
if (copy_from_user(&p, a.data, sizeof(struct blkpg_partition)))
return -EFAULT;
disk = bdev->bd_disk;
if (bdev != bdev->bd_contains)
return -EINVAL;
partno = p.pno;
if (partno <= 0)
return -EINVAL;
switch (a.op) {
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) &&
sizeof(long long) > sizeof(long)) {
long pstart = start, plength = length;
if (pstart != start || plength != length
|| pstart < 0 || plength < 0)
return -EINVAL;
}
mutex_lock(&bdev->bd_mutex);
/* overlap? */
disk_part_iter_init(&piter, disk,
DISK_PITER_INCL_EMPTY);
while ((part = disk_part_iter_next(&piter))) {
if (!(start + length <= part->start_sect ||
start >= part->start_sect + part->nr_sects)) {
disk_part_iter_exit(&piter);
mutex_unlock(&bdev->bd_mutex);
return -EBUSY;
}
}
disk_part_iter_exit(&piter);
/* all seems OK */
part = add_partition(disk, partno, start, length,
ADDPART_FLAG_NONE, NULL);
mutex_unlock(&bdev->bd_mutex);
return IS_ERR(part) ? PTR_ERR(part) : 0;
case BLKPG_DEL_PARTITION:
part = disk_get_part(disk, partno);
if (!part)
return -ENXIO;
bdevp = bdget(part_devt(part));
disk_put_part(part);
if (!bdevp)
return -ENOMEM;
mutex_lock(&bdevp->bd_mutex);
if (bdevp->bd_openers) {
mutex_unlock(&bdevp->bd_mutex);
bdput(bdevp);
return -EBUSY;
}
/* all seems OK */
fsync_bdev(bdevp);
invalidate_bdev(bdevp);
mutex_lock_nested(&bdev->bd_mutex, 1);
delete_partition(disk, partno);
mutex_unlock(&bdev->bd_mutex);
mutex_unlock(&bdevp->bd_mutex);
bdput(bdevp);
return 0;
default:
return -EINVAL;
}
}
static int blkdev_reread_part(struct block_device *bdev)
{
struct gendisk *disk = bdev->bd_disk;
int res;
if (!disk_part_scan_enabled(disk) || bdev != bdev->bd_contains)
return -EINVAL;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
if (!mutex_trylock(&bdev->bd_mutex))
return -EBUSY;
res = rescan_partitions(disk, bdev);
mutex_unlock(&bdev->bd_mutex);
return res;
}
static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
uint64_t len, int secure)
{
unsigned long flags = 0;
if (start & 511)
return -EINVAL;
if (len & 511)
return -EINVAL;
start >>= 9;
len >>= 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);
}
static int put_ushort(unsigned long arg, unsigned short val)
{
return put_user(val, (unsigned short __user *)arg);
}
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);
}
static int put_ulong(unsigned long arg, unsigned long val)
{
return put_user(val, (unsigned long __user *)arg);
}
static int put_u64(unsigned long arg, u64 val)
{
return put_user(val, (u64 __user *)arg);
}
int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode,
unsigned cmd, unsigned long arg)
{
struct gendisk *disk = bdev->bd_disk;
if (disk->fops->ioctl)
return disk->fops->ioctl(bdev, mode, cmd, arg);
return -ENOTTY;
}
/*
* For the record: _GPL here is only because somebody decided to slap it
* on the previous export. Sheer idiocy, since it wasn't copyrightable
* at all and could be open-coded without any exports by anybody who cares.
*/
EXPORT_SYMBOL_GPL(__blkdev_driver_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)
{
struct gendisk *disk = bdev->bd_disk;
struct backing_dev_info *bdi;
loff_t size;
int ret, n;
switch(cmd) {
case BLKFLSBUF:
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
if (!is_unrecognized_ioctl(ret))
return ret;
fsync_bdev(bdev);
invalidate_bdev(bdev);
return 0;
case BLKROSET:
ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
if (!is_unrecognized_ioctl(ret))
return ret;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
if (get_user(n, (int __user *)(arg)))
return -EFAULT;
set_device_ro(bdev, n);
return 0;
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 HDIO_GETGEO: {
struct hd_geometry geo;
if (!arg)
return -EINVAL;
if (!disk->fops->getgeo)
return -ENOTTY;
/*
* 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)
return ret;
if (copy_to_user((struct hd_geometry __user *)arg, &geo,
sizeof(geo)))
return -EFAULT;
return 0;
}
case BLKRAGET:
case BLKFRAGET:
if (!arg)
return -EINVAL;
bdi = blk_get_backing_dev_info(bdev);
if (bdi == NULL)
return -ENOTTY;
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 block device soft block size (cf. BLKSSZGET) */
return put_int(arg, block_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, 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))
return -EACCES;
bdi = blk_get_backing_dev_info(bdev);
if (bdi == NULL)
return -ENOTTY;
bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE;
return 0;
case BLKBSZSET:
/* set the logical block size */
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
if (!arg)
return -EINVAL;
if (get_user(n, (int __user *) arg))
return -EFAULT;
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))
block: make blkdev_get/put() handle exclusive access Over time, block layer has accumulated a set of APIs dealing with bdev open, close, claim and release. * blkdev_get/put() are the primary open and close functions. * bd_claim/release() deal with exclusive open. * open/close_bdev_exclusive() are combination of open and claim and the other way around, respectively. * bd_link/unlink_disk_holder() to create and remove holder/slave symlinks. * open_by_devnum() wraps bdget() + blkdev_get(). The interface is a bit confusing and the decoupling of open and claim makes it impossible to properly guarantee exclusive access as in-kernel open + claim sequence can disturb the existing exclusive open even before the block layer knows the current open if for another exclusive access. Reorganize the interface such that, * blkdev_get() is extended to include exclusive access management. @holder argument is added and, if is @FMODE_EXCL specified, it will gain exclusive access atomically w.r.t. other exclusive accesses. * blkdev_put() is similarly extended. It now takes @mode argument and if @FMODE_EXCL is set, it releases an exclusive access. Also, when the last exclusive claim is released, the holder/slave symlinks are removed automatically. * bd_claim/release() and close_bdev_exclusive() are no longer necessary and either made static or removed. * bd_link_disk_holder() remains the same but bd_unlink_disk_holder() is no longer necessary and removed. * open_bdev_exclusive() becomes a simple wrapper around lookup_bdev() and blkdev_get(). It also has an unexpected extra bdev_read_only() test which probably should be moved into blkdev_get(). * open_by_devnum() is modified to take @holder argument and pass it to blkdev_get(). Most of bdev open/close operations are unified into blkdev_get/put() and most exclusive accesses are tested atomically at the open time (as it should). This cleans up code and removes some, both valid and invalid, but unnecessary all the same, corner cases. open_bdev_exclusive() and open_by_devnum() can use further cleanup - rename to blkdev_get_by_path() and blkdev_get_by_devt() and drop special features. Well, let's leave them for another day. Most conversions are straight-forward. drbd conversion is a bit more involved as there was some reordering, but the logic should stay the same. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Neil Brown <neilb@suse.de> Acked-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Acked-by: Mike Snitzer <snitzer@redhat.com> Acked-by: Philipp Reisner <philipp.reisner@linbit.com> Cc: Peter Osterlund <petero2@telia.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Jan Kara <jack@suse.cz> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <joel.becker@oracle.com> Cc: Alex Elder <aelder@sgi.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: dm-devel@redhat.com Cc: drbd-dev@lists.linbit.com Cc: Leo Chen <leochen@broadcom.com> Cc: Scott Branden <sbranden@broadcom.com> Cc: Chris Mason <chris.mason@oracle.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@linux.vnet.ibm.com> Cc: Joern Engel <joern@logfs.org> Cc: reiserfs-devel@vger.kernel.org Cc: Alexander Viro <viro@zeniv.linux.org.uk>
2010-11-13 10:55:17 +00:00
blkdev_put(bdev, mode | FMODE_EXCL);
return ret;
case BLKPG:
ret = blkpg_ioctl(bdev, (struct blkpg_ioctl_arg __user *) arg);
break;
case BLKRRPART:
ret = blkdev_reread_part(bdev);
break;
case BLKGETSIZE:
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, i_size_read(bdev->bd_inode));
case BLKTRACESTART:
case BLKTRACESTOP:
case BLKTRACESETUP:
case BLKTRACETEARDOWN:
ret = blk_trace_ioctl(bdev, cmd, (char __user *) arg);
break;
default:
ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
}
return ret;
}
EXPORT_SYMBOL_GPL(blkdev_ioctl);