/*
* Note: some of the ioctl's return positive numbers as a
* byte count indicating success, such as readlink_by_handle.
* So we don't "sign flip" like most other routines. This means
* true errors need to be returned as a negative value.
*/
long
xfs_file_ioctl(
struct file *filp,
unsigned int cmd,
unsigned long p)
{
struct inode *inode = file_inode(filp);
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
void __user *arg = (void __user *)p;
int ioflags = 0;
int error;
if (filp->f_mode & FMODE_NOCMTIME)
ioflags |= IO_INVIS;
trace_xfs_file_ioctl(ip);
switch (cmd) {
case FITRIM:
return xfs_ioc_trim(mp, arg);
case XFS_IOC_ALLOCSP:
case XFS_IOC_FREESP:
case XFS_IOC_RESVSP:
case XFS_IOC_UNRESVSP:
case XFS_IOC_ALLOCSP64:
case XFS_IOC_FREESP64:
case XFS_IOC_RESVSP64:
case XFS_IOC_UNRESVSP64:
case XFS_IOC_ZERO_RANGE: {
xfs_flock64_t bf;
if (copy_from_user(&bf, arg, sizeof(bf)))
return -XFS_ERROR(EFAULT);
return xfs_ioc_space(ip, inode, filp, ioflags, cmd, &bf);
}
case XFS_IOC_DIOINFO: {
struct dioattr da;
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
da.d_mem = da.d_miniosz = 1 << target->bt_sshift;
da.d_maxiosz = INT_MAX & ~(da.d_miniosz - 1);
if (copy_to_user(arg, &da, sizeof(da)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_FSBULKSTAT_SINGLE:
case XFS_IOC_FSBULKSTAT:
case XFS_IOC_FSINUMBERS:
return xfs_ioc_bulkstat(mp, cmd, arg);
case XFS_IOC_FSGEOMETRY_V1:
return xfs_ioc_fsgeometry_v1(mp, arg);
case XFS_IOC_FSGEOMETRY:
return xfs_ioc_fsgeometry(mp, arg);
case XFS_IOC_GETVERSION:
return put_user(inode->i_generation, (int __user *)arg);
case XFS_IOC_FSGETXATTR:
return xfs_ioc_fsgetxattr(ip, 0, arg);
case XFS_IOC_FSGETXATTRA:
return xfs_ioc_fsgetxattr(ip, 1, arg);
case XFS_IOC_FSSETXATTR:
return xfs_ioc_fssetxattr(ip, filp, arg);
case XFS_IOC_GETXFLAGS:
return xfs_ioc_getxflags(ip, arg);
case XFS_IOC_SETXFLAGS:
return xfs_ioc_setxflags(ip, filp, arg);
case XFS_IOC_FSSETDM: {
struct fsdmidata dmi;
if (copy_from_user(&dmi, arg, sizeof(dmi)))
return -XFS_ERROR(EFAULT);
error = mnt_want_write_file(filp);
if (error)
return error;
error = xfs_set_dmattrs(ip, dmi.fsd_dmevmask,
dmi.fsd_dmstate);
mnt_drop_write_file(filp);
return -error;
}
case XFS_IOC_GETBMAP:
case XFS_IOC_GETBMAPA:
return xfs_ioc_getbmap(ip, ioflags, cmd, arg);
case XFS_IOC_GETBMAPX:
return xfs_ioc_getbmapx(ip, arg);
case XFS_IOC_FD_TO_HANDLE:
case XFS_IOC_PATH_TO_HANDLE:
case XFS_IOC_PATH_TO_FSHANDLE: {
xfs_fsop_handlereq_t hreq;
if (copy_from_user(&hreq, arg, sizeof(hreq)))
return -XFS_ERROR(EFAULT);
return xfs_find_handle(cmd, &hreq);
}
case XFS_IOC_OPEN_BY_HANDLE: {
xfs_fsop_handlereq_t hreq;
if (copy_from_user(&hreq, arg, sizeof(xfs_fsop_handlereq_t)))
return -XFS_ERROR(EFAULT);
return xfs_open_by_handle(filp, &hreq);
}
case XFS_IOC_FSSETDM_BY_HANDLE:
return xfs_fssetdm_by_handle(filp, arg);
case XFS_IOC_READLINK_BY_HANDLE: {
xfs_fsop_handlereq_t hreq;
if (copy_from_user(&hreq, arg, sizeof(xfs_fsop_handlereq_t)))
return -XFS_ERROR(EFAULT);
return xfs_readlink_by_handle(filp, &hreq);
}
case XFS_IOC_ATTRLIST_BY_HANDLE:
return xfs_attrlist_by_handle(filp, arg);
case XFS_IOC_ATTRMULTI_BY_HANDLE:
return xfs_attrmulti_by_handle(filp, arg);
case XFS_IOC_SWAPEXT: {
struct xfs_swapext sxp;
if (copy_from_user(&sxp, arg, sizeof(xfs_swapext_t)))
return -XFS_ERROR(EFAULT);
error = mnt_want_write_file(filp);
if (error)
return error;
error = xfs_swapext(&sxp);
mnt_drop_write_file(filp);
return -error;
}
case XFS_IOC_FSCOUNTS: {
xfs_fsop_counts_t out;
error = xfs_fs_counts(mp, &out);
if (error)
return -error;
if (copy_to_user(arg, &out, sizeof(out)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_SET_RESBLKS: {
xfs_fsop_resblks_t inout;
__uint64_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (mp->m_flags & XFS_MOUNT_RDONLY)
return -XFS_ERROR(EROFS);
if (copy_from_user(&inout, arg, sizeof(inout)))
return -XFS_ERROR(EFAULT);
error = mnt_want_write_file(filp);
if (error)
return error;
/* input parameter is passed in resblks field of structure */
in = inout.resblks;
error = xfs_reserve_blocks(mp, &in, &inout);
mnt_drop_write_file(filp);
if (error)
return -error;
if (copy_to_user(arg, &inout, sizeof(inout)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_GET_RESBLKS: {
xfs_fsop_resblks_t out;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
error = xfs_reserve_blocks(mp, NULL, &out);
if (error)
return -error;
if (copy_to_user(arg, &out, sizeof(out)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_FSGROWFSDATA: {
xfs_growfs_data_t in;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = mnt_want_write_file(filp);
if (error)
return error;
error = xfs_growfs_data(mp, &in);
mnt_drop_write_file(filp);
return -error;
}
case XFS_IOC_FSGROWFSLOG: {
xfs_growfs_log_t in;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = mnt_want_write_file(filp);
if (error)
return error;
error = xfs_growfs_log(mp, &in);
mnt_drop_write_file(filp);
return -error;
}
case XFS_IOC_FSGROWFSRT: {
xfs_growfs_rt_t in;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = mnt_want_write_file(filp);
if (error)
return error;
error = xfs_growfs_rt(mp, &in);
mnt_drop_write_file(filp);
return -error;
}
case XFS_IOC_GOINGDOWN: {
__uint32_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(in, (__uint32_t __user *)arg))
return -XFS_ERROR(EFAULT);
error = xfs_fs_goingdown(mp, in);
return -error;
}
case XFS_IOC_ERROR_INJECTION: {
xfs_error_injection_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_errortag_add(in.errtag, mp);
return -error;
}
case XFS_IOC_ERROR_CLEARALL:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
error = xfs_errortag_clearall(mp, 1);
return -error;
case XFS_IOC_FREE_EOFBLOCKS: {
struct xfs_eofblocks eofb;
if (copy_from_user(&eofb, arg, sizeof(eofb)))
return -XFS_ERROR(EFAULT);
if (eofb.eof_version != XFS_EOFBLOCKS_VERSION)
return -XFS_ERROR(EINVAL);
if (eofb.eof_flags & ~XFS_EOF_FLAGS_VALID)
return -XFS_ERROR(EINVAL);
if (memchr_inv(&eofb.pad32, 0, sizeof(eofb.pad32)) ||
memchr_inv(eofb.pad64, 0, sizeof(eofb.pad64)))
return -XFS_ERROR(EINVAL);
error = xfs_icache_free_eofblocks(mp, &eofb);
return -error;
}
default:
return -ENOTTY;
}
}
int
xfs_ioctl(
xfs_inode_t *ip,
struct file *filp,
int ioflags,
unsigned int cmd,
void __user *arg)
{
struct inode *inode = filp->f_path.dentry->d_inode;
xfs_mount_t *mp = ip->i_mount;
int error;
xfs_itrace_entry(XFS_I(inode));
switch (cmd) {
case XFS_IOC_ALLOCSP:
case XFS_IOC_FREESP:
case XFS_IOC_RESVSP:
case XFS_IOC_UNRESVSP:
case XFS_IOC_ALLOCSP64:
case XFS_IOC_FREESP64:
case XFS_IOC_RESVSP64:
case XFS_IOC_UNRESVSP64:
/*
* Only allow the sys admin to reserve space unless
* unwritten extents are enabled.
*/
if (!xfs_sb_version_hasextflgbit(&mp->m_sb) &&
!capable(CAP_SYS_ADMIN))
return -EPERM;
return xfs_ioc_space(ip, inode, filp, ioflags, cmd, arg);
case XFS_IOC_DIOINFO: {
struct dioattr da;
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
da.d_mem = da.d_miniosz = 1 << target->bt_sshift;
da.d_maxiosz = INT_MAX & ~(da.d_miniosz - 1);
if (copy_to_user(arg, &da, sizeof(da)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_FSBULKSTAT_SINGLE:
case XFS_IOC_FSBULKSTAT:
case XFS_IOC_FSINUMBERS:
return xfs_ioc_bulkstat(mp, cmd, arg);
case XFS_IOC_FSGEOMETRY_V1:
return xfs_ioc_fsgeometry_v1(mp, arg);
case XFS_IOC_FSGEOMETRY:
return xfs_ioc_fsgeometry(mp, arg);
case XFS_IOC_GETVERSION:
return put_user(inode->i_generation, (int __user *)arg);
case XFS_IOC_FSGETXATTR:
return xfs_ioc_fsgetxattr(ip, 0, arg);
case XFS_IOC_FSGETXATTRA:
return xfs_ioc_fsgetxattr(ip, 1, arg);
case XFS_IOC_FSSETXATTR:
return xfs_ioc_fssetxattr(ip, filp, arg);
case XFS_IOC_GETXFLAGS:
return xfs_ioc_getxflags(ip, arg);
case XFS_IOC_SETXFLAGS:
return xfs_ioc_setxflags(ip, filp, arg);
case XFS_IOC_FSSETDM: {
struct fsdmidata dmi;
if (copy_from_user(&dmi, arg, sizeof(dmi)))
return -XFS_ERROR(EFAULT);
error = xfs_set_dmattrs(ip, dmi.fsd_dmevmask,
dmi.fsd_dmstate);
return -error;
}
case XFS_IOC_GETBMAP:
case XFS_IOC_GETBMAPA:
return xfs_ioc_getbmap(ip, ioflags, cmd, arg);
case XFS_IOC_GETBMAPX:
return xfs_ioc_getbmapx(ip, arg);
case XFS_IOC_FD_TO_HANDLE:
case XFS_IOC_PATH_TO_HANDLE:
case XFS_IOC_PATH_TO_FSHANDLE:
return xfs_find_handle(cmd, arg);
case XFS_IOC_OPEN_BY_HANDLE:
return xfs_open_by_handle(mp, arg, filp, inode);
case XFS_IOC_FSSETDM_BY_HANDLE:
return xfs_fssetdm_by_handle(mp, arg, inode);
case XFS_IOC_READLINK_BY_HANDLE:
return xfs_readlink_by_handle(mp, arg, inode);
case XFS_IOC_ATTRLIST_BY_HANDLE:
return xfs_attrlist_by_handle(mp, arg, inode);
case XFS_IOC_ATTRMULTI_BY_HANDLE:
return xfs_attrmulti_by_handle(mp, arg, inode);
case XFS_IOC_SWAPEXT: {
error = xfs_swapext((struct xfs_swapext __user *)arg);
return -error;
}
case XFS_IOC_FSCOUNTS: {
xfs_fsop_counts_t out;
error = xfs_fs_counts(mp, &out);
if (error)
return -error;
if (copy_to_user(arg, &out, sizeof(out)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_SET_RESBLKS: {
xfs_fsop_resblks_t inout;
__uint64_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&inout, arg, sizeof(inout)))
return -XFS_ERROR(EFAULT);
/* input parameter is passed in resblks field of structure */
in = inout.resblks;
error = xfs_reserve_blocks(mp, &in, &inout);
if (error)
return -error;
if (copy_to_user(arg, &inout, sizeof(inout)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_GET_RESBLKS: {
xfs_fsop_resblks_t out;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
error = xfs_reserve_blocks(mp, NULL, &out);
if (error)
return -error;
if (copy_to_user(arg, &out, sizeof(out)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_FSGROWFSDATA: {
xfs_growfs_data_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_growfs_data(mp, &in);
return -error;
}
case XFS_IOC_FSGROWFSLOG: {
xfs_growfs_log_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_growfs_log(mp, &in);
return -error;
}
case XFS_IOC_FSGROWFSRT: {
xfs_growfs_rt_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_growfs_rt(mp, &in);
return -error;
}
case XFS_IOC_FREEZE:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (inode->i_sb->s_frozen == SB_UNFROZEN)
freeze_bdev(inode->i_sb->s_bdev);
return 0;
case XFS_IOC_THAW:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (inode->i_sb->s_frozen != SB_UNFROZEN)
thaw_bdev(inode->i_sb->s_bdev, inode->i_sb);
return 0;
case XFS_IOC_GOINGDOWN: {
__uint32_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(in, (__uint32_t __user *)arg))
return -XFS_ERROR(EFAULT);
error = xfs_fs_goingdown(mp, in);
return -error;
}
case XFS_IOC_ERROR_INJECTION: {
xfs_error_injection_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_errortag_add(in.errtag, mp);
return -error;
}
case XFS_IOC_ERROR_CLEARALL:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
error = xfs_errortag_clearall(mp, 1);
return -error;
default:
return -ENOTTY;
}
}
int
xfs_ioctl(
bhv_desc_t *bdp,
struct inode *inode,
struct file *filp,
int ioflags,
unsigned int cmd,
unsigned long arg)
{
int error;
vnode_t *vp;
xfs_inode_t *ip;
xfs_mount_t *mp;
vp = LINVFS_GET_VP(inode);
vn_trace_entry(vp, "xfs_ioctl", (inst_t *)__return_address);
ip = XFS_BHVTOI(bdp);
mp = ip->i_mount;
switch (cmd) {
case XFS_IOC_ALLOCSP:
case XFS_IOC_FREESP:
case XFS_IOC_RESVSP:
case XFS_IOC_UNRESVSP:
case XFS_IOC_ALLOCSP64:
case XFS_IOC_FREESP64:
case XFS_IOC_RESVSP64:
case XFS_IOC_UNRESVSP64:
/*
* Only allow the sys admin to reserve space unless
* unwritten extents are enabled.
*/
if (!XFS_SB_VERSION_HASEXTFLGBIT(&mp->m_sb) &&
!capable(CAP_SYS_ADMIN))
return -EPERM;
return xfs_ioc_space(bdp, vp, filp, ioflags, cmd, arg);
case XFS_IOC_DIOINFO: {
struct dioattr da;
da.d_miniosz = mp->m_sb.sb_blocksize;
da.d_mem = mp->m_sb.sb_blocksize;
/*
* this only really needs to be BBSIZE.
* it is set to the file system block size to
* avoid having to do block zeroing on short writes.
*/
da.d_maxiosz = XFS_FSB_TO_B(mp,
XFS_B_TO_FSBT(mp, KIO_MAX_ATOMIC_IO << 10));
if (copy_to_user((struct dioattr *)arg, &da, sizeof(da)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_FSBULKSTAT_SINGLE:
case XFS_IOC_FSBULKSTAT:
case XFS_IOC_FSINUMBERS:
return xfs_ioc_bulkstat(mp, cmd, arg);
case XFS_IOC_FSGEOMETRY_V1:
return xfs_ioc_fsgeometry_v1(mp, arg);
case XFS_IOC_FSGEOMETRY:
return xfs_ioc_fsgeometry(mp, arg);
case XFS_IOC_GETVERSION:
case XFS_IOC_GETXFLAGS:
case XFS_IOC_SETXFLAGS:
case XFS_IOC_FSGETXATTR:
case XFS_IOC_FSSETXATTR:
case XFS_IOC_FSGETXATTRA:
return xfs_ioc_xattr(vp, ip, filp, cmd, arg);
case XFS_IOC_FSSETDM: {
struct fsdmidata dmi;
if (copy_from_user(&dmi, (struct fsdmidata *)arg, sizeof(dmi)))
return -XFS_ERROR(EFAULT);
error = xfs_set_dmattrs(bdp, dmi.fsd_dmevmask, dmi.fsd_dmstate,
NULL);
return -error;
}
case XFS_IOC_GETBMAP:
case XFS_IOC_GETBMAPA:
return xfs_ioc_getbmap(bdp, filp, ioflags, cmd, arg);
case XFS_IOC_GETBMAPX:
return xfs_ioc_getbmapx(bdp, arg);
case XFS_IOC_FD_TO_HANDLE:
case XFS_IOC_PATH_TO_HANDLE:
case XFS_IOC_PATH_TO_FSHANDLE:
return xfs_find_handle(cmd, arg);
case XFS_IOC_OPEN_BY_HANDLE:
return xfs_open_by_handle(mp, arg, filp, inode);
case XFS_IOC_FSSETDM_BY_HANDLE:
return xfs_fssetdm_by_handle(mp, arg, filp, inode);
case XFS_IOC_READLINK_BY_HANDLE:
return xfs_readlink_by_handle(mp, arg, filp, inode);
case XFS_IOC_ATTRLIST_BY_HANDLE:
return xfs_attrlist_by_handle(mp, arg, filp, inode);
case XFS_IOC_ATTRMULTI_BY_HANDLE:
return xfs_attrmulti_by_handle(mp, arg, filp, inode);
case XFS_IOC_SWAPEXT: {
error = xfs_swapext((struct xfs_swapext *)arg);
return -error;
}
case XFS_IOC_FSCOUNTS: {
xfs_fsop_counts_t out;
error = xfs_fs_counts(mp, &out);
if (error)
return -error;
if (copy_to_user((char *)arg, &out, sizeof(out)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_SET_RESBLKS: {
xfs_fsop_resblks_t inout;
__uint64_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&inout, (char *)arg, sizeof(inout)))
return -XFS_ERROR(EFAULT);
/* input parameter is passed in resblks field of structure */
in = inout.resblks;
error = xfs_reserve_blocks(mp, &in, &inout);
if (error)
return -error;
if (copy_to_user((char *)arg, &inout, sizeof(inout)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_GET_RESBLKS: {
xfs_fsop_resblks_t out;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
error = xfs_reserve_blocks(mp, NULL, &out);
if (error)
return -error;
if (copy_to_user((char *)arg, &out, sizeof(out)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_FSGROWFSDATA: {
xfs_growfs_data_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&in, (char *)arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_growfs_data(mp, &in);
return -error;
}
case XFS_IOC_FSGROWFSLOG: {
xfs_growfs_log_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&in, (char *)arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_growfs_log(mp, &in);
return -error;
}
case XFS_IOC_FSGROWFSRT: {
xfs_growfs_rt_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&in, (char *)arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_growfs_rt(mp, &in);
return -error;
}
case XFS_IOC_FREEZE:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (vp->v_vfsp->vfs_frozen == SB_UNFROZEN) {
freeze_bdev(mp->m_ddev_targp->pbr_bdev);
if (mp->m_rtdev_targp)
freeze_bdev(mp->m_rtdev_targp->pbr_bdev);
}
return 0;
case XFS_IOC_THAW:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (vp->v_vfsp->vfs_frozen != SB_UNFROZEN) {
thaw_bdev(mp->m_ddev_targp->pbr_bdev, inode->i_sb);
if (mp->m_rtdev_targp)
thaw_bdev(mp->m_ddev_targp->pbr_bdev, NULL);
}
return 0;
case XFS_IOC_GOINGDOWN: {
__uint32_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(in, (__uint32_t *)arg))
return -XFS_ERROR(EFAULT);
error = xfs_fs_goingdown(mp, in);
return -error;
}
case XFS_IOC_ERROR_INJECTION: {
xfs_error_injection_t in;
if (!capable(CAP_SYS_ADMIN))
return EPERM;
if (copy_from_user(&in, (char *)arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_errortag_add(in.errtag, mp);
return -error;
}
case XFS_IOC_ERROR_CLEARALL:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
error = xfs_errortag_clearall(mp);
return -error;
default:
return -ENOTTY;
}
}
/*
* Do the defragmentation of a single file.
* We already are pretty sure we can and want to
* defragment the file. Create the tmp file, copy
* the data (maintaining holes) and call the kernel
* extent swap routinte.
*/
static int
packfile(char *fname, char *tname, int fd, xfs_bstat_t *statp, int do_rt)
{
int tfd;
int srval;
int nextents, extent, cur_nextents, new_nextents;
unsigned blksz_dio;
unsigned dio_min;
struct dioattr dio;
static xfs_swapext_t sx;
struct xfs_flock64 space;
off64_t cnt, pos;
void *fbuf;
int ct, wc, wc_b4;
struct fsxattr tfsx;
char ffname[SMBUFSZ];
int ffd = 0;
/*
* Work out the extent map - nextents will be set to the
* minimum number of extents needed for the file (taking
* into account holes), cur_nextents is the current number
* of extents.
*/
nextents = read_fd_bmap(fd, statp, &cur_nextents);
if ( cur_nextents == 1 || cur_nextents <= nextents ) {
if (vflag)
fsrprintf("%s already fully defragmented.\n", fname);
return 1; /* indicates no change/no error */
}
if (dflag)
fsrprintf("%s extents=%d can_save=%d tmp=%s\n",
fname, cur_nextents, (cur_nextents - nextents),
tname);
if ((tfd = open(tname, openopts, 0666)) < 0) {
if (vflag)
fsrprintf("could not open tmp as uid %d: %s: %s\n",
statp->bs_uid,tname, strerror(errno));
return -1;
}
unlink(tname);
/* Setup extended attributes */
if( statp->bs_xflags & XFS_XFLAG_HASATTR ) {
if (attr_setf(tfd, "X", "X", 1, ATTR_CREATE) != 0) {
fsrprintf("could not set ATTR on tmp: %s:\n", tname);
close(tfd);
return -1;
}
if (dflag)
fsrprintf("%s set temp attr\n", tname);
}
if ((ioctl(tfd, XFS_IOC_DIOINFO, &dio)) < 0 ) {
fsrprintf("could not get I/O info on tmp: %s\n", tname);
close(tfd);
return -1;
}
if (do_rt) {
int rt_textsize = fsgeom.rtextsize * fsgeom.blocksize;
tfsx.fsx_xflags = XFS_XFLAG_REALTIME;
if ((tfsx.fsx_extsize = rt_textsize) <= 0 ) {
fsrprintf("realtime geom not avail for tmp: %s\n", fname);
close(tfd);
return -1;
}
if (ioctl( tfd, XFS_IOC_FSSETXATTR, &tfsx) < 0) {
fsrprintf("could not set rt on tmp: %s\n", tname);
close(tfd);
return -1;
}
}
dio_min = dio.d_miniosz;
if (statp->bs_size <= dio_min)
blksz_dio = dio_min;
else {
blksz_dio = min(dio.d_maxiosz, BUFFER_MAX - pagesize);
if (argv_blksz_dio != 0)
blksz_dio = min(argv_blksz_dio, blksz_dio);
blksz_dio = (min(statp->bs_size, blksz_dio) / dio_min) * dio_min;
}
if (dflag) {
fsrprintf("DEBUG: fsize=%lld blsz_dio=%d d_min=%d d_max=%d pgsz=%d\n",
statp->bs_size, blksz_dio, dio.d_miniosz, dio.d_maxiosz, pagesize);
}
/* Malloc a buffer */
if (! (fbuf = (char *)memalign(dio.d_mem, blksz_dio))) {
fsrprintf("could not allocate buf: %s\n", tname);
close(tfd);
return -1;
}
if (nfrags) {
/* Create new tmp file in same AG as first */
sprintf(ffname, "%s.frag", tname);
/* Open the new file for sync writes */
if ((ffd = open(ffname, openopts, 0666))
< 0) {
fsrprintf("could not open fragfile: %s : %s\n",
ffname, strerror(errno));
return -1;
}
unlink(ffname);
}
/* Loop through block map copying the file. */
for (extent = 0; extent < nextents; extent++) {
pos = outmap[extent].bmv_offset;
if (outmap[extent].bmv_block == -1) {
space.l_whence = 0;
space.l_start = pos;
space.l_len = outmap[extent].bmv_length;
if (ioctl(tfd, XFS_IOC_UNRESVSP64, &space) < 0) {
fsrprintf("could not trunc tmp %s\n",
tname);
}
lseek64(tfd, outmap[extent].bmv_length, SEEK_CUR);
lseek64(fd, outmap[extent].bmv_length, SEEK_CUR);
continue;
} else if (outmap[extent].bmv_length == 0) {
/* to catch holes at the beginning of the file */
continue;
}
if (! nfrags) {
space.l_whence = SEEK_CUR;
space.l_start = 0;
space.l_len = outmap[extent].bmv_length;
if (ioctl(tfd, XFS_IOC_RESVSP64, &space) < 0) {
fsrprintf("could not pre-alloc tmp space: %s\n",
tname);
close(tfd);
free(fbuf);
return -1;
}
}
for (cnt = outmap[extent].bmv_length; cnt > 0;
cnt -= ct, pos += ct) {
if (nfrags && --nfrags) {
ct = min(cnt, dio_min);
} else if (cnt % dio_min == 0) {
ct = min(cnt, blksz_dio);
} else {
ct = min(cnt + dio_min - (cnt % dio_min),
blksz_dio);
}
ct = read(fd, fbuf, ct);
if (ct == 0) {
/* EOF, stop trying to read */
extent = nextents;
break;
}
/* Ensure we do direct I/O to correct block
* boundaries.
*/
if (ct % dio_min != 0) {
wc = ct + dio_min - (ct % dio_min);
} else {
wc = ct;
}
wc_b4 = wc;
if (ct < 0 || ((wc = write(tfd, fbuf, wc)) != wc_b4)) {
if (ct < 0)
fsrprintf("bad read of %d bytes from %s:%s\n",
wc_b4, fname, strerror(errno));
else if (wc < 0)
fsrprintf("bad write of %d bytes to %s: %s\n",
wc_b4, tname, strerror(errno));
else {
/*
* Might be out of space
*
* Try to finish write
*/
int resid = ct-wc;
if ((wc = write(tfd, ((char *)fbuf)+wc,
resid)) == resid) {
/* worked on second attempt? */
continue;
}
else
if (wc < 0) {
fsrprintf("bad write2 of %d bytes to %s: %s\n",
resid, tname, strerror(errno));
} else {
fsrprintf("bad copy to %s\n",
tname);
}
}
free(fbuf);
return -1;
}
if (nfrags) {
/* Do a matching write to the tmp file */
wc = wc_b4;
if (((wc = write(ffd, fbuf, wc)) != wc_b4)) { fsrprintf("bad write of %d bytes "
"to %s: %s\n",
wc_b4, ffname, strerror(errno));
}
}
}
}
ftruncate64(tfd, statp->bs_size);
if (ffd) close(ffd);
fsync(tfd);
free(fbuf);
sx.sx_stat = *statp; /* struct copy */
sx.sx_version = XFS_SX_VERSION;
sx.sx_fdtarget = fd;
sx.sx_fdtmp = tfd;
sx.sx_offset = 0;
sx.sx_length = statp->bs_size;
/* Check if the extent count improved */
new_nextents = getnextents(tfd);
if (cur_nextents <= new_nextents) {
if (vflag)
fsrprintf("No improvement made: %s\n", fname);
close(tfd);
return 1; /* no change/no error */
}
/* Swap the extents */
srval = xfs_swapext(fd, &sx);
if (srval < 0) {
if (errno == ENOTSUP) {
if (vflag || dflag)
fsrprintf("%s: file type not supported\n", fname);
} else if (errno == EFAULT) {
/* The file has changed since we started the copy */
if (vflag || dflag)
fsrprintf("%s:file modified defrag aborted\n",
fname);
} else if (errno == EBUSY) {
/* Timestamp has changed or mmap'ed file */
if (vflag || dflag)
fsrprintf("%s: file busy \n", fname);
} else {
fsrprintf("XFS_IOC_SWAPEXT failed: %s: %s\n",
fname, strerror(errno));
}
close(tfd);
return -1;
}
/* Report progress */
if (vflag)
fsrprintf("extents before:%d after:%d %s %s\n",
cur_nextents, new_nextents,
(new_nextents <= nextents ? "DONE" : " " ),
fname);
close(tfd);
return 0;
}
