static void
xfs_bmbt_to_iomap(
struct xfs_inode *ip,
struct iomap *iomap,
struct xfs_bmbt_irec *imap)
{
struct xfs_mount *mp = ip->i_mount;
if (imap->br_startblock == HOLESTARTBLOCK) {
iomap->blkno = IOMAP_NULL_BLOCK;
iomap->type = IOMAP_HOLE;
} else if (imap->br_startblock == DELAYSTARTBLOCK) {
iomap->blkno = IOMAP_NULL_BLOCK;
iomap->type = IOMAP_DELALLOC;
} else {
iomap->blkno =
XFS_FSB_TO_DADDR(ip->i_mount, imap->br_startblock);
if (imap->br_state == XFS_EXT_UNWRITTEN)
iomap->type = IOMAP_UNWRITTEN;
else
iomap->type = IOMAP_MAPPED;
}
iomap->offset = XFS_FSB_TO_B(mp, imap->br_startoff);
iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount);
}
/*
* Inode btree record insertion/removal modifies the inode btree and free space
* btrees (since the inobt does not use the agfl). This requires the following
* reservation:
*
* the inode btree: max depth * blocksize
* the allocation btrees: 2 trees * (max depth - 1) * block size
*
* The caller must account for SB and AG header modifications, etc.
*/
STATIC uint
xfs_calc_inobt_res(
struct xfs_mount *mp)
{
return xfs_calc_buf_res(mp->m_in_maxlevels, XFS_FSB_TO_B(mp, 1)) +
xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1),
XFS_FSB_TO_B(mp, 1));
}
static int
_xfs_bmap(
struct vop_bmap_args /* {
struct vnode *a_vp;
daddr_t a_bn;
struct bufobj **a_bop;
daddr_t *a_bnp;
int *a_runp;
int *a_runb;
} */ *ap)
{
xfs_iomap_t iomap;
xfs_off_t offset;
ssize_t size;
struct mount *mp;
struct xfs_mount *xmp;
struct xfs_vnode *xvp;
int error, maxrun, retbm;
mp = ap->a_vp->v_mount;
xmp = XFS_VFSTOM(MNTTOVFS(mp));
if (ap->a_bop != NULL)
*ap->a_bop = &xmp->m_ddev_targp->specvp->v_bufobj;
if (ap->a_bnp == NULL)
return (0);
xvp = VPTOXFSVP(ap->a_vp);
retbm = 1;
offset = XFS_FSB_TO_B(xmp, ap->a_bn);
size = XFS_FSB_TO_B(xmp, 1);
XVOP_BMAP(xvp, offset, size, BMAPI_READ, &iomap, &retbm, error);
if (error)
return (error);
if (retbm == 0 || iomap.iomap_bn == IOMAP_DADDR_NULL) {
*ap->a_bnp = (daddr_t)-1;
if (ap->a_runb)
*ap->a_runb = 0;
if (ap->a_runp)
*ap->a_runp = 0;
} else {
*ap->a_bnp = iomap.iomap_bn + btodb(iomap.iomap_delta);
maxrun = mp->mnt_iosize_max / mp->mnt_stat.f_iosize - 1;
if (ap->a_runb) {
*ap->a_runb = XFS_B_TO_FSB(xmp, iomap.iomap_delta);
if (*ap->a_runb > maxrun)
*ap->a_runb = maxrun;
}
if (ap->a_runp) {
*ap->a_runp =
XFS_B_TO_FSB(xmp, iomap.iomap_bsize
- iomap.iomap_delta - size);
if (*ap->a_runp > maxrun)
*ap->a_runp = maxrun;
}
}
return (0);
}
/*
* trim a range of the filesystem.
*
* Note: the parameters passed from userspace are byte ranges into the
* filesystem which does not match to the format we use for filesystem block
* addressing. FSB addressing is sparse (AGNO|AGBNO), while the incoming format
* is a linear address range. Hence we need to use DADDR based conversions and
* comparisons for determining the correct offset and regions to trim.
*/
int
xfs_ioc_trim(
struct xfs_mount *mp,
struct fstrim_range __user *urange)
{
struct request_queue *q = bdev_get_queue(mp->m_ddev_targp->bt_bdev);
unsigned int granularity = q->limits.discard_granularity;
struct fstrim_range range;
xfs_daddr_t start, end, minlen;
xfs_agnumber_t start_agno, end_agno, agno;
__uint64_t blocks_trimmed = 0;
int error, last_error = 0;
if (!capable(CAP_SYS_ADMIN))
return -XFS_ERROR(EPERM);
if (!blk_queue_discard(q))
return -XFS_ERROR(EOPNOTSUPP);
if (copy_from_user(&range, urange, sizeof(range)))
return -XFS_ERROR(EFAULT);
/*
* Truncating down the len isn't actually quite correct, but using
* BBTOB would mean we trivially get overflows for values
* of ULLONG_MAX or slightly lower. And ULLONG_MAX is the default
* used by the fstrim application. In the end it really doesn't
* matter as trimming blocks is an advisory interface.
*/
if (range.start >= XFS_FSB_TO_B(mp, mp->m_sb.sb_dblocks) ||
range.minlen > XFS_FSB_TO_B(mp, XFS_ALLOC_AG_MAX_USABLE(mp)) ||
range.len < mp->m_sb.sb_blocksize)
return -XFS_ERROR(EINVAL);
start = BTOBB(range.start);
end = start + BTOBBT(range.len) - 1;
minlen = BTOBB(max_t(u64, granularity, range.minlen));
if (end > XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) - 1)
end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)- 1;
start_agno = xfs_daddr_to_agno(mp, start);
end_agno = xfs_daddr_to_agno(mp, end);
for (agno = start_agno; agno <= end_agno; agno++) {
error = -xfs_trim_extents(mp, agno, start, end, minlen,
&blocks_trimmed);
if (error)
last_error = error;
}
if (last_error)
return last_error;
range.len = XFS_FSB_TO_B(mp, blocks_trimmed);
if (copy_to_user(urange, &range, sizeof(range)))
return -XFS_ERROR(EFAULT);
return 0;
}
/*
* For create we can modify:
* the parent directory inode: inode size
* the new inode: inode size
* the inode btree entry: block size
* the superblock for the nlink flag: sector size
* the directory btree: (max depth + v2) * dir block size
* the directory inode's bmap btree: (max depth + v2) * block size
* the finobt (record modification and allocation btrees)
*/
STATIC uint
xfs_calc_create_resv_modify(
struct xfs_mount *mp)
{
return xfs_calc_inode_res(mp, 2) +
xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
(uint)XFS_FSB_TO_B(mp, 1) +
xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1)) +
xfs_calc_finobt_res(mp, 1, 1);
}
int extent_overlaps_buffer(xfs_mount_t *mp, xfs_bmbt_irec_t rec, off_t offset, size_t len) {
size_t extent_size = XFS_FSB_TO_B(mp, rec.br_blockcount);
size_t extent_start = XFS_FSB_TO_B(mp, rec.br_startoff);
/* check that the extent overlaps the intended read area */
/* First: the offset lies in the extent */
if ((extent_start <= offset) && (offset < extent_start + extent_size)) return 1;
/* Second: the extent start lies in the buffer */
if ((offset <= extent_start) && (extent_start < offset + len)) return 1;
return 0;
}
int copy_extent_to_buffer(xfs_mount_t *mp, xfs_bmbt_irec_t rec, void *buffer, off_t offset, size_t len) {
xfs_buf_t *block_buffer;
int64_t copylen, copy_start;
xfs_daddr_t block, start, end;
char *src;
off_t cofs = offset;
xfs_off_t block_start;
xfs_daddr_t block_size = XFS_FSB_TO_B(mp, 1);
//xfs_daddr_t extent_size = XFS_FSB_TO_B(mp, rec.br_blockcount);
xfs_daddr_t extent_start = XFS_FSB_TO_B(mp, rec.br_startoff);
/* compute a block to start reading from */
if (offset >= extent_start) {
start = XFS_B_TO_FSBT(mp, offset - extent_start);
} else {
buffer = buffer + extent_start - offset;
cofs += extent_start - offset;
start = 0;
}
end = min(rec.br_blockcount, XFS_B_TO_FSBT(mp, offset + len - extent_start - 1) + 1);
for (block=start; block<end; block++) {
block_start = XFS_FSB_TO_B(mp, (rec.br_startoff + block));
block_buffer = libxfs_readbuf(mp->m_dev, XFS_FSB_TO_DADDR(mp, (rec.br_startblock + block)),
XFS_FSB_TO_BB(mp, 1), 0);
if (block_buffer == NULL) {
printf("Buffer error\n");
return XFS_ERROR(EIO);
}
src = block_buffer->b_addr;
copy_start = block_start;
copylen = block_size;
if (block_start < offset) {
copylen = block_size + block_start - offset;
copy_start = (block_size - copylen) + block_start;
src = block_buffer->b_addr + (block_size - copylen);
}
if ((block_start + block_size) > (offset + len)) {
copylen = offset + len - copy_start;
}
if (copylen > 0) {
memcpy(buffer, src, copylen);
buffer += copylen;
cofs += copylen;
}
libxfs_putbuf(block_buffer);
}
return 0;
}
/*
* Removing the attribute fork of a file
* the inode being truncated: inode size
* the inode's bmap btree: max depth * block size
* And the bmap_finish transaction can free the blocks and bmap blocks:
* the agf for each of the ags: 4 * sector size
* the agfl for each of the ags: 4 * sector size
* the super block to reflect the freed blocks: sector size
* worst case split in allocation btrees per extent assuming 4 extents:
* 4 exts * 2 trees * (2 * max depth - 1) * block size
*/
STATIC uint
xfs_calc_attrinval_reservation(
struct xfs_mount *mp)
{
return max((xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_ATTR_FORK),
XFS_FSB_TO_B(mp, 1))),
(xfs_calc_buf_res(9, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(xfs_allocfree_log_count(mp, 4),
XFS_FSB_TO_B(mp, 1))));
}
/*
* For icreate we can allocate some inodes giving:
* the agi and agf of the ag getting the new inodes: 2 * sectorsize
* the superblock for the nlink flag: sector size
* the inode btree: max depth * blocksize
* the allocation btrees: 2 trees * (max depth - 1) * block size
* the finobt (record insertion)
*/
STATIC uint
xfs_calc_icreate_resv_alloc(
struct xfs_mount *mp)
{
return xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
mp->m_sb.sb_sectsize +
xfs_calc_buf_res(mp->m_in_maxlevels, XFS_FSB_TO_B(mp, 1)) +
xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
XFS_FSB_TO_B(mp, 1)) +
xfs_calc_finobt_res(mp, 0, 0);
}
/*
* Removing the attribute fork of a file
* the inode being truncated: inode size
* the inode's bmap btree: max depth * block size
* And the bmap_finish transaction can free the blocks and bmap blocks:
* the agf for each of the ags: 4 * sector size
* the agfl for each of the ags: 4 * sector size
* the super block to reflect the freed blocks: sector size
* worst case split in allocation btrees per extent assuming 4 extents:
* 4 exts * 2 trees * (2 * max depth - 1) * block size
*/
STATIC uint
xfs_calc_attrinval_reservation(
struct xfs_mount *mp)
{
return MAX((xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_ATTR_FORK),
XFS_FSB_TO_B(mp, 1))),
(xfs_calc_buf_res(9, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 4),
XFS_FSB_TO_B(mp, 1))));
}
/*
* Growing the rt section of the filesystem.
* In the first set of transactions (ALLOC) we allocate space to the
* bitmap or summary files.
* superblock: sector size
* agf of the ag from which the extent is allocated: sector size
* bmap btree for bitmap/summary inode: max depth * blocksize
* bitmap/summary inode: inode size
* allocation btrees for 1 block alloc: 2 * (2 * maxdepth - 1) * blocksize
*/
STATIC uint
xfs_calc_growrtalloc_reservation(
struct xfs_mount *mp)
{
return xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK),
XFS_FSB_TO_B(mp, 1)) +
xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
XFS_FSB_TO_B(mp, 1));
}
/*
* In renaming a files we can modify:
* the four inodes involved: 4 * inode size
* the two directory btrees: 2 * (max depth + v2) * dir block size
* the two directory bmap btrees: 2 * max depth * block size
* And the bmap_finish transaction can free dir and bmap blocks (two sets
* of bmap blocks) giving:
* the agf for the ags in which the blocks live: 3 * sector size
* the agfl for the ags in which the blocks live: 3 * sector size
* the superblock for the free block count: sector size
* the allocation btrees: 3 exts * 2 trees * (2 * max depth - 1) * block size
*/
STATIC uint
xfs_calc_rename_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
MAX((xfs_calc_inode_res(mp, 4) +
xfs_calc_buf_res(2 * XFS_DIROP_LOG_COUNT(mp),
XFS_FSB_TO_B(mp, 1))),
(xfs_calc_buf_res(7, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 3),
XFS_FSB_TO_B(mp, 1))));
}
/*
* In truncating a file we free up to two extents at once. We can modify:
* the inode being truncated: inode size
* the inode's bmap btree: (max depth + 1) * block size
* And the bmap_finish transaction can free the blocks and bmap blocks:
* the agf for each of the ags: 4 * sector size
* the agfl for each of the ags: 4 * sector size
* the super block to reflect the freed blocks: sector size
* worst case split in allocation btrees per extent assuming 4 extents:
* 4 exts * 2 trees * (2 * max depth - 1) * block size
*/
STATIC uint
xfs_calc_itruncate_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
max((xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) + 1,
XFS_FSB_TO_B(mp, 1))),
(xfs_calc_buf_res(9, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(xfs_allocfree_log_count(mp, 4),
XFS_FSB_TO_B(mp, 1))));
}
/*
* In renaming a files we can modify:
* the four inodes involved: 4 * inode size
* the two directory btrees: 2 * (max depth + v2) * dir block size
* the two directory bmap btrees: 2 * max depth * block size
* And the bmap_finish transaction can free dir and bmap blocks (two sets
* of bmap blocks) giving:
* the agf for the ags in which the blocks live: 3 * sector size
* the agfl for the ags in which the blocks live: 3 * sector size
* the superblock for the free block count: sector size
* the allocation btrees: 3 exts * 2 trees * (2 * max depth - 1) * block size
*/
STATIC uint
xfs_calc_rename_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
max((xfs_calc_inode_res(mp, 4) +
xfs_calc_buf_res(2 * XFS_DIROP_LOG_COUNT(mp),
XFS_FSB_TO_B(mp, 1))),
(xfs_calc_buf_res(7, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(xfs_allocfree_log_count(mp, 3),
XFS_FSB_TO_B(mp, 1))));
}
STATIC int
xfs_imap_to_bmap(
xfs_iocore_t *io,
xfs_off_t offset,
xfs_bmbt_irec_t *imap,
xfs_iomap_t *iomapp,
int imaps, /* Number of imap entries */
int iomaps, /* Number of iomap entries */
int flags)
{
xfs_mount_t *mp;
xfs_fsize_t nisize;
int pbm;
xfs_fsblock_t start_block;
mp = io->io_mount;
nisize = XFS_SIZE(mp, io);
if (io->io_new_size > nisize)
nisize = io->io_new_size;
for (pbm = 0; imaps && pbm < iomaps; imaps--, iomapp++, imap++, pbm++) {
iomapp->iomap_offset = XFS_FSB_TO_B(mp, imap->br_startoff);
iomapp->iomap_delta = offset - iomapp->iomap_offset;
iomapp->iomap_bsize = XFS_FSB_TO_B(mp, imap->br_blockcount);
iomapp->iomap_flags = flags;
if (io->io_flags & XFS_IOCORE_RT) {
iomapp->iomap_flags |= IOMAP_REALTIME;
iomapp->iomap_target = mp->m_rtdev_targp;
} else {
iomapp->iomap_target = mp->m_ddev_targp;
}
start_block = imap->br_startblock;
if (start_block == HOLESTARTBLOCK) {
iomapp->iomap_bn = IOMAP_DADDR_NULL;
iomapp->iomap_flags |= IOMAP_HOLE;
} else if (start_block == DELAYSTARTBLOCK) {
iomapp->iomap_bn = IOMAP_DADDR_NULL;
iomapp->iomap_flags |= IOMAP_DELAY;
} else {
iomapp->iomap_bn = XFS_FSB_TO_DB_IO(io, start_block);
if (ISUNWRITTEN(imap))
iomapp->iomap_flags |= IOMAP_UNWRITTEN;
}
if ((iomapp->iomap_offset + iomapp->iomap_bsize) >= nisize) {
iomapp->iomap_flags |= IOMAP_EOF;
}
offset += iomapp->iomap_bsize - iomapp->iomap_delta;
}
return pbm; /* Return the number filled */
}
/*
* Converting the inode from non-attributed to attributed.
* the inode being converted: inode size
* agf block and superblock (for block allocation)
* the new block (directory sized)
* bmap blocks for the new directory block
* allocation btrees
*/
STATIC uint
xfs_calc_addafork_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(1, mp->m_dir_geo->blksize) +
xfs_calc_buf_res(XFS_DAENTER_BMAP1B(mp, XFS_DATA_FORK) + 1,
XFS_FSB_TO_B(mp, 1)) +
xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
XFS_FSB_TO_B(mp, 1));
}
/*
* For creating a link to an inode:
* the parent directory inode: inode size
* the linked inode: inode size
* the directory btree could split: (max depth + v2) * dir block size
* the directory bmap btree could join or split: (max depth + v2) * blocksize
* And the bmap_finish transaction can free some bmap blocks giving:
* the agf for the ag in which the blocks live: sector size
* the agfl for the ag in which the blocks live: sector size
* the superblock for the free block count: sector size
* the allocation btrees: 2 trees * (2 * max depth - 1) * block size
*/
STATIC uint
xfs_calc_link_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
xfs_calc_iunlink_remove_reservation(mp) +
max((xfs_calc_inode_res(mp, 2) +
xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp),
XFS_FSB_TO_B(mp, 1))),
(xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1),
XFS_FSB_TO_B(mp, 1))));
}
/*
* For removing a directory entry we can modify:
* the parent directory inode: inode size
* the removed inode: inode size
* the directory btree could join: (max depth + v2) * dir block size
* the directory bmap btree could join or split: (max depth + v2) * blocksize
* And the bmap_finish transaction can free the dir and bmap blocks giving:
* the agf for the ag in which the blocks live: 2 * sector size
* the agfl for the ag in which the blocks live: 2 * sector size
* the superblock for the free block count: sector size
* the allocation btrees: 2 exts * 2 trees * (2 * max depth - 1) * block size
*/
STATIC uint
xfs_calc_remove_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
xfs_calc_iunlink_add_reservation(mp) +
MAX((xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp),
XFS_FSB_TO_B(mp, 1))),
(xfs_calc_buf_res(4, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 2),
XFS_FSB_TO_B(mp, 1))));
}
STATIC int
xfs_iomap_eof_align_last_fsb(
xfs_mount_t *mp,
xfs_iocore_t *io,
xfs_fsize_t isize,
xfs_extlen_t extsize,
xfs_fileoff_t *last_fsb)
{
xfs_fileoff_t new_last_fsb = 0;
xfs_extlen_t align;
int eof, error;
if (io->io_flags & XFS_IOCORE_RT)
;
/*
* If mounted with the "-o swalloc" option, roundup the allocation
* request to a stripe width boundary if the file size is >=
* stripe width and we are allocating past the allocation eof.
*/
else if (mp->m_swidth && (mp->m_flags & XFS_MOUNT_SWALLOC) &&
(isize >= XFS_FSB_TO_B(mp, mp->m_swidth)))
new_last_fsb = roundup_64(*last_fsb, mp->m_swidth);
/*
* Roundup the allocation request to a stripe unit (m_dalign) boundary
* if the file size is >= stripe unit size, and we are allocating past
* the allocation eof.
*/
else if (mp->m_dalign && (isize >= XFS_FSB_TO_B(mp, mp->m_dalign)))
new_last_fsb = roundup_64(*last_fsb, mp->m_dalign);
/*
* Always round up the allocation request to an extent boundary
* (when file on a real-time subvolume or has di_extsize hint).
*/
if (extsize) {
if (new_last_fsb)
align = roundup_64(new_last_fsb, extsize);
else
align = extsize;
new_last_fsb = roundup_64(*last_fsb, align);
}
if (new_last_fsb) {
error = XFS_BMAP_EOF(mp, io, new_last_fsb, XFS_DATA_FORK, &eof);
if (error)
return error;
if (eof)
*last_fsb = new_last_fsb;
}
return 0;
}
/*
* Removing an attribute.
* the inode: inode size
* the attribute btree could join: max depth * block size
* the inode bmap btree could join or split: max depth * block size
* And the bmap_finish transaction can free the attr blocks freed giving:
* the agf for the ag in which the blocks live: 2 * sector size
* the agfl for the ag in which the blocks live: 2 * sector size
* the superblock for the free block count: sector size
* the allocation btrees: 2 exts * 2 trees * (2 * max depth - 1) * block size
*/
STATIC uint
xfs_calc_attrrm_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
MAX((xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(XFS_DA_NODE_MAXDEPTH,
XFS_FSB_TO_B(mp, 1)) +
(uint)XFS_FSB_TO_B(mp,
XFS_BM_MAXLEVELS(mp, XFS_ATTR_FORK)) +
xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK), 0)),
(xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 2),
XFS_FSB_TO_B(mp, 1))));
}
/*
* In freeing an inode we can modify:
* the inode being freed: inode size
* the super block free inode counter: sector size
* the agi hash list and counters: sector size
* the inode btree entry: block size
* the on disk inode before ours in the agi hash list: inode cluster size
* the inode btree: max depth * blocksize
* the allocation btrees: 2 trees * (max depth - 1) * block size
* the finobt (record insertion, removal or modification)
*/
STATIC uint
xfs_calc_ifree_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(1, XFS_FSB_TO_B(mp, 1)) +
xfs_calc_iunlink_remove_reservation(mp) +
xfs_calc_buf_res(1, 0) +
xfs_calc_buf_res(2 + mp->m_ialloc_blks +
mp->m_in_maxlevels, 0) +
xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
XFS_FSB_TO_B(mp, 1)) +
xfs_calc_finobt_res(mp, 0, 1);
}
/*
* For removing an inode from unlinked list at first, we can modify:
* the agi hash list and counters: sector size
* the on disk inode before ours in the agi hash list: inode cluster size
*/
STATIC uint
xfs_calc_iunlink_remove_reservation(
struct xfs_mount *mp)
{
return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
max_t(uint, XFS_FSB_TO_B(mp, 1), mp->m_inode_cluster_size);
}
/*
* This routine is called to handle zeroing any space in the last
* block of the file that is beyond the EOF. We do this since the
* size is being increased without writing anything to that block
* and we don't want anyone to read the garbage on the disk.
*/
STATIC int /* error (positive) */
xfs_zero_last_block(
xfs_vnode_t *vp,
xfs_iocore_t *io,
xfs_fsize_t isize,
xfs_fsize_t end_size)
{
xfs_fileoff_t last_fsb;
xfs_mount_t *mp;
int nimaps;
int zero_offset;
int zero_len;
int error = 0;
xfs_bmbt_irec_t imap;
xfs_off_t loff;
ASSERT(ismrlocked(io->io_lock, MR_UPDATE) != 0);
mp = io->io_mount;
zero_offset = XFS_B_FSB_OFFSET(mp, isize);
if (zero_offset == 0) {
/*
* There are no extra bytes in the last block on disk to
* zero, so return.
*/
return 0;
}
last_fsb = XFS_B_TO_FSBT(mp, isize);
nimaps = 1;
error = XFS_BMAPI(mp, NULL, io, last_fsb, 1, 0, NULL, 0, &imap,
&nimaps, NULL, NULL);
if (error) {
return error;
}
ASSERT(nimaps > 0);
/*
* If the block underlying isize is just a hole, then there
* is nothing to zero.
*/
if (imap.br_startblock == HOLESTARTBLOCK) {
return 0;
}
/*
* Zero the part of the last block beyond the EOF, and write it
* out sync. We need to drop the ilock while we do this so we
* don't deadlock when the buffer cache calls back to us.
*/
XFS_IUNLOCK(mp, io, XFS_ILOCK_EXCL| XFS_EXTSIZE_RD);
loff = XFS_FSB_TO_B(mp, last_fsb);
zero_len = mp->m_sb.sb_blocksize - zero_offset;
error = xfs_iozero(vp, loff + zero_offset, zero_len, end_size);
XFS_ILOCK(mp, io, XFS_ILOCK_EXCL|XFS_EXTSIZE_RD);
ASSERT(error >= 0);
return error;
}
/*
* Growing the data section of the filesystem.
* superblock
* agi and agf
* allocation btrees
*/
STATIC uint
xfs_calc_growdata_reservation(
struct xfs_mount *mp)
{
return xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
XFS_FSB_TO_B(mp, 1));
}
/*
* Growing the data section of the filesystem.
* superblock
* agi and agf
* allocation btrees
*/
STATIC uint
xfs_calc_growdata_reservation(
struct xfs_mount *mp)
{
return xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1),
XFS_FSB_TO_B(mp, 1));
}
/*
* Allocating quota on disk if needed.
* the write transaction log space for quota file extent allocation
* the unit of quota allocation: one system block size
*/
STATIC uint
xfs_calc_qm_dqalloc_reservation(
struct xfs_mount *mp)
{
return xfs_calc_write_reservation(mp) +
xfs_calc_buf_res(1,
XFS_FSB_TO_B(mp, XFS_DQUOT_CLUSTER_SIZE_FSB) - 1);
}
/*
* In truncating a file we free up to two extents at once. We can modify:
* the inode being truncated: inode size
* the inode's bmap btree: (max depth + 1) * block size
* And the bmap_finish transaction can free the blocks and bmap blocks:
* the agf for each of the ags: 4 * sector size
* the agfl for each of the ags: 4 * sector size
* the super block to reflect the freed blocks: sector size
* worst case split in allocation btrees per extent assuming 4 extents:
* 4 exts * 2 trees * (2 * max depth - 1) * block size
* the inode btree: max depth * blocksize
* the allocation btrees: 2 trees * (max depth - 1) * block size
*/
STATIC uint
xfs_calc_itruncate_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
MAX((xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) + 1,
XFS_FSB_TO_B(mp, 1))),
(xfs_calc_buf_res(9, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 4),
XFS_FSB_TO_B(mp, 1)) +
xfs_calc_buf_res(5, 0) +
xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
XFS_FSB_TO_B(mp, 1)) +
xfs_calc_buf_res(2 + mp->m_ialloc_blks +
mp->m_in_maxlevels, 0)));
}
/*
* Setting an attribute at runtime, transaction space unit per block.
* the superblock for allocations: sector size
* the inode bmap btree could join or split: max depth * block size
* Since the runtime attribute transaction space is dependent on the total
* blocks needed for the 1st bmap, here we calculate out the space unit for
* one block so that the caller could figure out the total space according
* to the attibute extent length in blocks by:
* ext * M_RES(mp)->tr_attrsetrt.tr_logres
*/
STATIC uint
xfs_calc_attrsetrt_reservation(
struct xfs_mount *mp)
{
return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_ATTR_FORK),
XFS_FSB_TO_B(mp, 1));
}
/*
* Setting an attribute at mount time.
* the inode getting the attribute
* the superblock for allocations
* the agfs extents are allocated from
* the attribute btree * max depth
* the inode allocation btree
* Since attribute transaction space is dependent on the size of the attribute,
* the calculation is done partially at mount time and partially at runtime(see
* below).
*/
STATIC uint
xfs_calc_attrsetm_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(XFS_DA_NODE_MAXDEPTH, XFS_FSB_TO_B(mp, 1));
}
STATIC int
xfs_imap_to_bmap(
xfs_inode_t *ip,
xfs_off_t offset,
xfs_bmbt_irec_t *imap,
xfs_iomap_t *iomapp,
int imaps, /* Number of imap entries */
int iomaps, /* Number of iomap entries */
int flags)
{
xfs_mount_t *mp = ip->i_mount;
int pbm;
xfs_fsblock_t start_block;
for (pbm = 0; imaps && pbm < iomaps; imaps--, iomapp++, imap++, pbm++) {
iomapp->iomap_offset = XFS_FSB_TO_B(mp, imap->br_startoff);
iomapp->iomap_delta = offset - iomapp->iomap_offset;
iomapp->iomap_bsize = XFS_FSB_TO_B(mp, imap->br_blockcount);
iomapp->iomap_flags = flags;
if (XFS_IS_REALTIME_INODE(ip)) {
iomapp->iomap_flags |= IOMAP_REALTIME;
iomapp->iomap_target = mp->m_rtdev_targp;
} else {
iomapp->iomap_target = mp->m_ddev_targp;
}
start_block = imap->br_startblock;
if (start_block == HOLESTARTBLOCK) {
iomapp->iomap_bn = IOMAP_DADDR_NULL;
iomapp->iomap_flags |= IOMAP_HOLE;
} else if (start_block == DELAYSTARTBLOCK) {
iomapp->iomap_bn = IOMAP_DADDR_NULL;
iomapp->iomap_flags |= IOMAP_DELAY;
} else {
iomapp->iomap_bn = xfs_fsb_to_db(ip, start_block);
if (ISUNWRITTEN(imap))
iomapp->iomap_flags |= IOMAP_UNWRITTEN;
}
offset += iomapp->iomap_bsize - iomapp->iomap_delta;
}
return pbm; /* Return the number filled */
}
