diff options
Diffstat (limited to 'fs/xfs/xfs_ioctl.c')
| -rw-r--r-- | fs/xfs/xfs_ioctl.c | 423 |
1 files changed, 137 insertions, 286 deletions
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index f0117188f302..59eaad774371 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -40,6 +40,7 @@ #include "xfs_file.h" #include "xfs_exchrange.h" #include "xfs_handle.h" +#include "xfs_rtgroup.h" #include <linux/mount.h> #include <linux/fileattr.h> @@ -218,7 +219,7 @@ xfs_bulk_ireq_setup( else if (XFS_INO_TO_AGNO(mp, breq->startino) < hdr->agno) return -EINVAL; - breq->flags |= XFS_IBULK_SAME_AG; + breq->iwalk_flags |= XFS_IWALK_SAME_AG; /* Asking for an inode past the end of the AG? We're done! */ if (XFS_INO_TO_AGNO(mp, breq->startino) > hdr->agno) @@ -233,6 +234,10 @@ xfs_bulk_ireq_setup( if (hdr->flags & XFS_BULK_IREQ_NREXT64) breq->flags |= XFS_IBULK_NREXT64; + /* Caller wants to see metadata directories in bulkstat output. */ + if (hdr->flags & XFS_BULK_IREQ_METADIR) + breq->flags |= XFS_IBULK_METADIR; + return 0; } @@ -323,6 +328,9 @@ xfs_ioc_inumbers( if (copy_from_user(&hdr, &arg->hdr, sizeof(hdr))) return -EFAULT; + if (hdr.flags & XFS_BULK_IREQ_METADIR) + return -EINVAL; + error = xfs_bulk_ireq_setup(mp, &hdr, &breq, arg->inumbers); if (error == -ECANCELED) goto out_teardown; @@ -396,6 +404,38 @@ xfs_ioc_ag_geometry( return 0; } +STATIC int +xfs_ioc_rtgroup_geometry( + struct xfs_mount *mp, + void __user *arg) +{ + struct xfs_rtgroup *rtg; + struct xfs_rtgroup_geometry rgeo; + int error; + + if (copy_from_user(&rgeo, arg, sizeof(rgeo))) + return -EFAULT; + if (rgeo.rg_flags) + return -EINVAL; + if (memchr_inv(&rgeo.rg_reserved, 0, sizeof(rgeo.rg_reserved))) + return -EINVAL; + if (!xfs_has_rtgroups(mp)) + return -EINVAL; + + rtg = xfs_rtgroup_get(mp, rgeo.rg_number); + if (!rtg) + return -EINVAL; + + error = xfs_rtgroup_get_geometry(rtg, &rgeo); + xfs_rtgroup_put(rtg); + if (error) + return error; + + if (copy_to_user(arg, &rgeo, sizeof(rgeo))) + return -EFAULT; + return 0; +} + /* * Linux extended inode flags interface. */ @@ -404,7 +444,7 @@ static void xfs_fill_fsxattr( struct xfs_inode *ip, int whichfork, - struct fileattr *fa) + struct file_kattr *fa) { struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); @@ -429,8 +469,21 @@ xfs_fill_fsxattr( } } - if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) - fa->fsx_cowextsize = XFS_FSB_TO_B(mp, ip->i_cowextsize); + if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) { + /* + * Don't let a misaligned CoW extent size hint on a directory + * escape to userspace if it won't pass the setattr checks + * later. + */ + if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) && + ip->i_cowextsize % mp->m_sb.sb_rextsize > 0) { + fa->fsx_xflags &= ~FS_XFLAG_COWEXTSIZE; + fa->fsx_cowextsize = 0; + } else { + fa->fsx_cowextsize = XFS_FSB_TO_B(mp, ip->i_cowextsize); + } + } + fa->fsx_projid = ip->i_projid; if (ifp && !xfs_need_iread_extents(ifp)) fa->fsx_nextents = xfs_iext_count(ifp); @@ -443,7 +496,7 @@ xfs_ioc_fsgetxattra( xfs_inode_t *ip, void __user *arg) { - struct fileattr fa; + struct file_kattr fa; xfs_ilock(ip, XFS_ILOCK_SHARED); xfs_fill_fsxattr(ip, XFS_ATTR_FORK, &fa); @@ -455,13 +508,10 @@ xfs_ioc_fsgetxattra( int xfs_fileattr_get( struct dentry *dentry, - struct fileattr *fa) + struct file_kattr *fa) { struct xfs_inode *ip = XFS_I(d_inode(dentry)); - if (d_is_special(dentry)) - return -ENOTTY; - xfs_ilock(ip, XFS_ILOCK_SHARED); xfs_fill_fsxattr(ip, XFS_DATA_FORK, fa); xfs_iunlock(ip, XFS_ILOCK_SHARED); @@ -469,71 +519,11 @@ xfs_fileattr_get( return 0; } -STATIC uint16_t -xfs_flags2diflags( - struct xfs_inode *ip, - unsigned int xflags) -{ - /* can't set PREALLOC this way, just preserve it */ - uint16_t di_flags = - (ip->i_diflags & XFS_DIFLAG_PREALLOC); - - if (xflags & FS_XFLAG_IMMUTABLE) - di_flags |= XFS_DIFLAG_IMMUTABLE; - if (xflags & FS_XFLAG_APPEND) - di_flags |= XFS_DIFLAG_APPEND; - if (xflags & FS_XFLAG_SYNC) - di_flags |= XFS_DIFLAG_SYNC; - if (xflags & FS_XFLAG_NOATIME) - di_flags |= XFS_DIFLAG_NOATIME; - if (xflags & FS_XFLAG_NODUMP) - di_flags |= XFS_DIFLAG_NODUMP; - if (xflags & FS_XFLAG_NODEFRAG) - di_flags |= XFS_DIFLAG_NODEFRAG; - if (xflags & FS_XFLAG_FILESTREAM) - di_flags |= XFS_DIFLAG_FILESTREAM; - if (S_ISDIR(VFS_I(ip)->i_mode)) { - if (xflags & FS_XFLAG_RTINHERIT) - di_flags |= XFS_DIFLAG_RTINHERIT; - if (xflags & FS_XFLAG_NOSYMLINKS) - di_flags |= XFS_DIFLAG_NOSYMLINKS; - if (xflags & FS_XFLAG_EXTSZINHERIT) - di_flags |= XFS_DIFLAG_EXTSZINHERIT; - if (xflags & FS_XFLAG_PROJINHERIT) - di_flags |= XFS_DIFLAG_PROJINHERIT; - } else if (S_ISREG(VFS_I(ip)->i_mode)) { - if (xflags & FS_XFLAG_REALTIME) - di_flags |= XFS_DIFLAG_REALTIME; - if (xflags & FS_XFLAG_EXTSIZE) - di_flags |= XFS_DIFLAG_EXTSIZE; - } - - return di_flags; -} - -STATIC uint64_t -xfs_flags2diflags2( - struct xfs_inode *ip, - unsigned int xflags) -{ - uint64_t di_flags2 = - (ip->i_diflags2 & (XFS_DIFLAG2_REFLINK | - XFS_DIFLAG2_BIGTIME | - XFS_DIFLAG2_NREXT64)); - - if (xflags & FS_XFLAG_DAX) - di_flags2 |= XFS_DIFLAG2_DAX; - if (xflags & FS_XFLAG_COWEXTSIZE) - di_flags2 |= XFS_DIFLAG2_COWEXTSIZE; - - return di_flags2; -} - static int xfs_ioctl_setattr_xflags( struct xfs_trans *tp, struct xfs_inode *ip, - struct fileattr *fa) + struct file_kattr *fa) { struct xfs_mount *mp = ip->i_mount; bool rtflag = (fa->fsx_xflags & FS_XFLAG_REALTIME); @@ -541,7 +531,18 @@ xfs_ioctl_setattr_xflags( if (rtflag != XFS_IS_REALTIME_INODE(ip)) { /* Can't change realtime flag if any extents are allocated. */ - if (ip->i_df.if_nextents || ip->i_delayed_blks) + if (xfs_inode_has_filedata(ip)) + return -EINVAL; + + /* + * If S_DAX is enabled on this file, we can only switch the + * device if both support fsdax. We can't update S_DAX because + * there might be other threads walking down the access paths. + */ + if (IS_DAX(VFS_I(ip)) && + (mp->m_ddev_targp->bt_daxdev == NULL || + (mp->m_rtdev_targp && + mp->m_rtdev_targp->bt_daxdev == NULL))) return -EINVAL; } @@ -550,10 +551,6 @@ xfs_ioctl_setattr_xflags( if (mp->m_sb.sb_rblocks == 0 || mp->m_sb.sb_rextsize == 0 || xfs_extlen_to_rtxmod(mp, ip->i_extsize)) return -EINVAL; - - /* Clear reflink if we are actually able to set the rt flag. */ - if (xfs_is_reflink_inode(ip)) - ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK; } /* diflags2 only valid for v3 inodes. */ @@ -582,7 +579,7 @@ xfs_ioctl_setattr_xflags( static void xfs_ioctl_setattr_prepare_dax( struct xfs_inode *ip, - struct fileattr *fa) + struct file_kattr *fa) { struct xfs_mount *mp = ip->i_mount; struct inode *inode = VFS_I(ip); @@ -642,7 +639,7 @@ out_error: static int xfs_ioctl_setattr_check_extsize( struct xfs_inode *ip, - struct fileattr *fa) + struct file_kattr *fa) { struct xfs_mount *mp = ip->i_mount; xfs_failaddr_t failaddr; @@ -651,7 +648,7 @@ xfs_ioctl_setattr_check_extsize( if (!fa->fsx_valid) return 0; - if (S_ISREG(VFS_I(ip)->i_mode) && ip->i_df.if_nextents && + if (S_ISREG(VFS_I(ip)->i_mode) && xfs_inode_has_filedata(ip) && XFS_FSB_TO_B(mp, ip->i_extsize) != fa->fsx_extsize) return -EINVAL; @@ -684,7 +681,7 @@ xfs_ioctl_setattr_check_extsize( static int xfs_ioctl_setattr_check_cowextsize( struct xfs_inode *ip, - struct fileattr *fa) + struct file_kattr *fa) { struct xfs_mount *mp = ip->i_mount; xfs_failaddr_t failaddr; @@ -709,7 +706,7 @@ xfs_ioctl_setattr_check_cowextsize( static int xfs_ioctl_setattr_check_projid( struct xfs_inode *ip, - struct fileattr *fa) + struct file_kattr *fa) { if (!fa->fsx_valid) return 0; @@ -725,7 +722,7 @@ int xfs_fileattr_set( struct mnt_idmap *idmap, struct dentry *dentry, - struct fileattr *fa) + struct file_kattr *fa) { struct xfs_inode *ip = XFS_I(d_inode(dentry)); struct xfs_mount *mp = ip->i_mount; @@ -736,9 +733,6 @@ xfs_fileattr_set( trace_xfs_ioctl_setattr(ip); - if (d_is_special(dentry)) - return -ENOTTY; - if (!fa->fsx_valid) { if (fa->flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NOATIME_FL | FS_NODUMP_FL | @@ -925,214 +919,57 @@ out_free_buf: return error; } -STATIC int -xfs_ioc_getfsmap( - struct xfs_inode *ip, - struct fsmap_head __user *arg) -{ - struct xfs_fsmap_head xhead = {0}; - struct fsmap_head head; - struct fsmap *recs; - unsigned int count; - __u32 last_flags = 0; - bool done = false; - int error; - - if (copy_from_user(&head, arg, sizeof(struct fsmap_head))) - return -EFAULT; - if (memchr_inv(head.fmh_reserved, 0, sizeof(head.fmh_reserved)) || - memchr_inv(head.fmh_keys[0].fmr_reserved, 0, - sizeof(head.fmh_keys[0].fmr_reserved)) || - memchr_inv(head.fmh_keys[1].fmr_reserved, 0, - sizeof(head.fmh_keys[1].fmr_reserved))) - return -EINVAL; - - /* - * Use an internal memory buffer so that we don't have to copy fsmap - * data to userspace while holding locks. Start by trying to allocate - * up to 128k for the buffer, but fall back to a single page if needed. - */ - count = min_t(unsigned int, head.fmh_count, - 131072 / sizeof(struct fsmap)); - recs = kvcalloc(count, sizeof(struct fsmap), GFP_KERNEL); - if (!recs) { - count = min_t(unsigned int, head.fmh_count, - PAGE_SIZE / sizeof(struct fsmap)); - recs = kvcalloc(count, sizeof(struct fsmap), GFP_KERNEL); - if (!recs) - return -ENOMEM; - } - - xhead.fmh_iflags = head.fmh_iflags; - xfs_fsmap_to_internal(&xhead.fmh_keys[0], &head.fmh_keys[0]); - xfs_fsmap_to_internal(&xhead.fmh_keys[1], &head.fmh_keys[1]); - - trace_xfs_getfsmap_low_key(ip->i_mount, &xhead.fmh_keys[0]); - trace_xfs_getfsmap_high_key(ip->i_mount, &xhead.fmh_keys[1]); - - head.fmh_entries = 0; - do { - struct fsmap __user *user_recs; - struct fsmap *last_rec; - - user_recs = &arg->fmh_recs[head.fmh_entries]; - xhead.fmh_entries = 0; - xhead.fmh_count = min_t(unsigned int, count, - head.fmh_count - head.fmh_entries); - - /* Run query, record how many entries we got. */ - error = xfs_getfsmap(ip->i_mount, &xhead, recs); - switch (error) { - case 0: - /* - * There are no more records in the result set. Copy - * whatever we got to userspace and break out. - */ - done = true; - break; - case -ECANCELED: - /* - * The internal memory buffer is full. Copy whatever - * records we got to userspace and go again if we have - * not yet filled the userspace buffer. - */ - error = 0; - break; - default: - goto out_free; - } - head.fmh_entries += xhead.fmh_entries; - head.fmh_oflags = xhead.fmh_oflags; - - /* - * If the caller wanted a record count or there aren't any - * new records to return, we're done. - */ - if (head.fmh_count == 0 || xhead.fmh_entries == 0) - break; - - /* Copy all the records we got out to userspace. */ - if (copy_to_user(user_recs, recs, - xhead.fmh_entries * sizeof(struct fsmap))) { - error = -EFAULT; - goto out_free; - } - - /* Remember the last record flags we copied to userspace. */ - last_rec = &recs[xhead.fmh_entries - 1]; - last_flags = last_rec->fmr_flags; - - /* Set up the low key for the next iteration. */ - xfs_fsmap_to_internal(&xhead.fmh_keys[0], last_rec); - trace_xfs_getfsmap_low_key(ip->i_mount, &xhead.fmh_keys[0]); - } while (!done && head.fmh_entries < head.fmh_count); - - /* - * If there are no more records in the query result set and we're not - * in counting mode, mark the last record returned with the LAST flag. - */ - if (done && head.fmh_count > 0 && head.fmh_entries > 0) { - struct fsmap __user *user_rec; - - last_flags |= FMR_OF_LAST; - user_rec = &arg->fmh_recs[head.fmh_entries - 1]; - - if (copy_to_user(&user_rec->fmr_flags, &last_flags, - sizeof(last_flags))) { - error = -EFAULT; - goto out_free; - } - } - - /* copy back header */ - if (copy_to_user(arg, &head, sizeof(struct fsmap_head))) { - error = -EFAULT; - goto out_free; - } - -out_free: - kvfree(recs); - return error; -} - int xfs_ioc_swapext( xfs_swapext_t *sxp) { xfs_inode_t *ip, *tip; - struct fd f, tmp; - int error = 0; /* Pull information for the target fd */ - f = fdget((int)sxp->sx_fdtarget); - if (!f.file) { - error = -EINVAL; - goto out; - } + CLASS(fd, f)((int)sxp->sx_fdtarget); + if (fd_empty(f)) + return -EINVAL; - if (!(f.file->f_mode & FMODE_WRITE) || - !(f.file->f_mode & FMODE_READ) || - (f.file->f_flags & O_APPEND)) { - error = -EBADF; - goto out_put_file; - } + if (!(fd_file(f)->f_mode & FMODE_WRITE) || + !(fd_file(f)->f_mode & FMODE_READ) || + (fd_file(f)->f_flags & O_APPEND)) + return -EBADF; - tmp = fdget((int)sxp->sx_fdtmp); - if (!tmp.file) { - error = -EINVAL; - goto out_put_file; - } + CLASS(fd, tmp)((int)sxp->sx_fdtmp); + if (fd_empty(tmp)) + return -EINVAL; - if (!(tmp.file->f_mode & FMODE_WRITE) || - !(tmp.file->f_mode & FMODE_READ) || - (tmp.file->f_flags & O_APPEND)) { - error = -EBADF; - goto out_put_tmp_file; - } + if (!(fd_file(tmp)->f_mode & FMODE_WRITE) || + !(fd_file(tmp)->f_mode & FMODE_READ) || + (fd_file(tmp)->f_flags & O_APPEND)) + return -EBADF; - if (IS_SWAPFILE(file_inode(f.file)) || - IS_SWAPFILE(file_inode(tmp.file))) { - error = -EINVAL; - goto out_put_tmp_file; - } + if (IS_SWAPFILE(file_inode(fd_file(f))) || + IS_SWAPFILE(file_inode(fd_file(tmp)))) + return -EINVAL; /* * We need to ensure that the fds passed in point to XFS inodes * before we cast and access them as XFS structures as we have no * control over what the user passes us here. */ - if (f.file->f_op != &xfs_file_operations || - tmp.file->f_op != &xfs_file_operations) { - error = -EINVAL; - goto out_put_tmp_file; - } + if (fd_file(f)->f_op != &xfs_file_operations || + fd_file(tmp)->f_op != &xfs_file_operations) + return -EINVAL; - ip = XFS_I(file_inode(f.file)); - tip = XFS_I(file_inode(tmp.file)); + ip = XFS_I(file_inode(fd_file(f))); + tip = XFS_I(file_inode(fd_file(tmp))); - if (ip->i_mount != tip->i_mount) { - error = -EINVAL; - goto out_put_tmp_file; - } - - if (ip->i_ino == tip->i_ino) { - error = -EINVAL; - goto out_put_tmp_file; - } + if (ip->i_mount != tip->i_mount) + return -EINVAL; - if (xfs_is_shutdown(ip->i_mount)) { - error = -EIO; - goto out_put_tmp_file; - } + if (ip->i_ino == tip->i_ino) + return -EINVAL; - error = xfs_swap_extents(ip, tip, sxp); + if (xfs_is_shutdown(ip->i_mount)) + return -EIO; - out_put_tmp_file: - fdput(tmp); - out_put_file: - fdput(f); - out: - return error; + return xfs_swap_extents(ip, tip, sxp); } static int @@ -1147,9 +984,8 @@ xfs_ioc_getlabel( BUILD_BUG_ON(sizeof(sbp->sb_fname) > FSLABEL_MAX); /* 1 larger than sb_fname, so this ensures a trailing NUL char */ - memset(label, 0, sizeof(label)); spin_lock(&mp->m_sb_lock); - strncpy(label, sbp->sb_fname, XFSLABEL_MAX); + memtostr_pad(label, sbp->sb_fname); spin_unlock(&mp->m_sb_lock); if (copy_to_user(user_label, label, sizeof(label))) @@ -1200,7 +1036,7 @@ xfs_ioc_setlabel( * buffered reads from userspace (i.e. from blkid) are invalidated, * and userspace will see the newly-written label. */ - error = xfs_sync_sb_buf(mp); + error = xfs_sync_sb_buf(mp, true); if (error) goto out; /* @@ -1211,6 +1047,8 @@ xfs_ioc_setlabel( mutex_unlock(&mp->m_growlock); invalidate_bdev(mp->m_ddev_targp->bt_bdev); + if (xfs_has_rtsb(mp) && mp->m_rtdev_targp) + invalidate_bdev(mp->m_rtdev_targp->bt_bdev); out: mnt_drop_write_file(filp); @@ -1286,15 +1124,15 @@ xfs_ioctl_getset_resblocks( error = mnt_want_write_file(filp); if (error) return error; - error = xfs_reserve_blocks(mp, fsop.resblks); + error = xfs_reserve_blocks(mp, XC_FREE_BLOCKS, fsop.resblks); mnt_drop_write_file(filp); if (error) return error; } spin_lock(&mp->m_sb_lock); - fsop.resblks = mp->m_resblks; - fsop.resblks_avail = mp->m_resblks_avail; + fsop.resblks = mp->m_free[XC_FREE_BLOCKS].res_total; + fsop.resblks_avail = mp->m_free[XC_FREE_BLOCKS].res_avail; spin_unlock(&mp->m_sb_lock); if (copy_to_user(arg, &fsop, sizeof(fsop))) @@ -1310,9 +1148,9 @@ xfs_ioctl_fs_counts( struct xfs_fsop_counts out = { .allocino = percpu_counter_read_positive(&mp->m_icount), .freeino = percpu_counter_read_positive(&mp->m_ifree), - .freedata = percpu_counter_read_positive(&mp->m_fdblocks) - - xfs_fdblocks_unavailable(mp), - .freertx = percpu_counter_read_positive(&mp->m_frextents), + .freedata = xfs_estimate_freecounter(mp, XC_FREE_BLOCKS) - + xfs_freecounter_unavailable(mp, XC_FREE_BLOCKS), + .freertx = xfs_estimate_freecounter(mp, XC_FREE_RTEXTENTS), }; if (copy_to_user(uarg, &out, sizeof(out))) @@ -1365,12 +1203,21 @@ xfs_file_ioctl( current->comm); return -ENOTTY; case XFS_IOC_DIOINFO: { - struct xfs_buftarg *target = xfs_inode_buftarg(ip); + struct kstat st; struct dioattr da; - da.d_mem = da.d_miniosz = target->bt_logical_sectorsize; - da.d_maxiosz = INT_MAX & ~(da.d_miniosz - 1); + error = vfs_getattr(&filp->f_path, &st, STATX_DIOALIGN, 0); + if (error) + return error; + /* + * Some userspace directly feeds the return value to + * posix_memalign, which fails for values that are smaller than + * the pointer size. Round up the value to not break userspace. + */ + da.d_mem = roundup(st.dio_mem_align, sizeof(void *)); + da.d_miniosz = st.dio_offset_align; + da.d_maxiosz = INT_MAX & ~(da.d_miniosz - 1); if (copy_to_user(arg, &da, sizeof(da))) return -EFAULT; return 0; @@ -1395,6 +1242,8 @@ xfs_file_ioctl( case XFS_IOC_AG_GEOMETRY: return xfs_ioc_ag_geometry(mp, arg); + case XFS_IOC_RTGROUP_GEOMETRY: + return xfs_ioc_rtgroup_geometry(mp, arg); case XFS_IOC_GETVERSION: return put_user(inode->i_generation, (int __user *)arg); @@ -1559,14 +1408,16 @@ xfs_file_ioctl( trace_xfs_ioc_free_eofblocks(mp, &icw, _RET_IP_); - sb_start_write(mp->m_super); - error = xfs_blockgc_free_space(mp, &icw); - sb_end_write(mp->m_super); - return error; + guard(super_write)(mp->m_super); + return xfs_blockgc_free_space(mp, &icw); } case XFS_IOC_EXCHANGE_RANGE: return xfs_ioc_exchange_range(filp, arg); + case XFS_IOC_START_COMMIT: + return xfs_ioc_start_commit(filp, arg); + case XFS_IOC_COMMIT_RANGE: + return xfs_ioc_commit_range(filp, arg); default: return -ENOTTY; |
