int
xfs_discard_extents(
struct xfs_mount *mp,
struct list_head *list)
{
struct xfs_busy_extent *busyp;
int error = 0;
list_for_each_entry(busyp, list, list) {
trace_xfs_discard_extent(mp, busyp->agno, busyp->bno,
busyp->length);
error = -blkdev_issue_discard(mp->m_ddev_targp->bt_bdev,
XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno),
XFS_FSB_TO_BB(mp, busyp->length),
GFP_NOFS, 0);
if (error && error != EOPNOTSUPP) {
xfs_info(mp,
"discard failed for extent [0x%llu,%u], error %d",
(unsigned long long)busyp->bno,
busyp->length,
error);
return error;
}
}
static int bch_allocator_thread(void *arg)
{
struct cache *ca = arg;
mutex_lock(&ca->set->bucket_lock);
while (1) {
/*
* First, we pull buckets off of the unused and free_inc lists,
* possibly issue discards to them, then we add the bucket to
* the free list:
*/
while (1) {
long bucket;
if ((!atomic_read(&ca->set->prio_blocked) ||
!CACHE_SYNC(&ca->set->sb)) &&
!fifo_empty(&ca->unused))
fifo_pop(&ca->unused, bucket);
else if (!fifo_empty(&ca->free_inc))
fifo_pop(&ca->free_inc, bucket);
else
break;
if (ca->discard) {
mutex_unlock(&ca->set->bucket_lock);
blkdev_issue_discard(ca->bdev,
bucket_to_sector(ca->set, bucket),
ca->sb.block_size, GFP_KERNEL, 0);
mutex_lock(&ca->set->bucket_lock);
}
allocator_wait(ca, bch_allocator_push(ca, bucket));
wake_up(&ca->set->bucket_wait);
}
/*
* We've run out of free buckets, we need to find some buckets
* we can invalidate. First, invalidate them in memory and add
* them to the free_inc list:
*/
allocator_wait(ca, ca->set->gc_mark_valid &&
(ca->need_save_prio > 64 ||
!ca->invalidate_needs_gc));
invalidate_buckets(ca);
/*
* Now, we write their new gens to disk so we can start writing
* new stuff to them:
*/
allocator_wait(ca, !atomic_read(&ca->set->prio_blocked));
if (CACHE_SYNC(&ca->set->sb) &&
(!fifo_empty(&ca->free_inc) ||
ca->need_save_prio > 64))
bch_prio_write(ca);
}
}
static sense_reason_t
iblock_do_unmap(struct se_cmd *cmd, void *priv,
sector_t lba, sector_t nolb)
{
struct block_device *bdev = priv;
int ret;
ret = blkdev_issue_discard(bdev, lba, nolb, GFP_KERNEL, 0);
if (ret < 0) {
pr_err("blkdev_issue_discard() failed: %d\n", ret);
return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
}
return 0;
}
static int iblock_execute_write_same(struct se_cmd *cmd)
{
struct iblock_dev *ibd = cmd->se_dev->dev_ptr;
int ret;
ret = blkdev_issue_discard(ibd->ibd_bd, cmd->t_task_lba,
spc_get_write_same_sectors(cmd), GFP_KERNEL,
0);
if (ret < 0) {
pr_debug("blkdev_issue_discard() failed for WRITE_SAME\n");
return ret;
}
target_complete_cmd(cmd, GOOD);
return 0;
}
int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, bool discard)
{
struct request_queue *q = bdev_get_queue(bdev);
if (discard && blk_queue_discard(q) && q->limits.discard_zeroes_data &&
blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, 0) == 0)
return 0;
if (bdev_write_same(bdev) &&
blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
ZERO_PAGE(0)) == 0)
return 0;
return __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask);
}
static int bch_allocator_thread(void *arg)
{
struct cache *ca = arg;
mutex_lock(&ca->set->bucket_lock);
while (1) {
/*
* First, we pull buckets off of the unused and free_inc lists,
* possibly issue discards to them, then we add the bucket to
* the free list:
*/
while (!fifo_empty(&ca->free_inc)) {
long bucket;
fifo_pop(&ca->free_inc, bucket);
if (ca->discard) {
mutex_unlock(&ca->set->bucket_lock);
blkdev_issue_discard(ca->bdev,
bucket_to_sector(ca->set, bucket),
ca->sb.block_size, GFP_KERNEL, 0);
mutex_lock(&ca->set->bucket_lock);
}
allocator_wait(ca, bch_allocator_push(ca, bucket));
wake_up(&ca->set->btree_cache_wait);
wake_up(&ca->set->bucket_wait);
}
/*
* We've run out of free buckets, we need to find some buckets
* we can invalidate. First, invalidate them in memory and add
* them to the free_inc list:
*/
retry_invalidate:
allocator_wait(ca, ca->set->gc_mark_valid &&
!ca->invalidate_needs_gc);
invalidate_buckets(ca);
/*
* Now, we write their new gens to disk so we can start writing
* new stuff to them:
*/
allocator_wait(ca, !atomic_read(&ca->set->prio_blocked));
if (CACHE_SYNC(&ca->set->sb)) {
/*
* This could deadlock if an allocation with a btree
* node locked ever blocked - having the btree node
* locked would block garbage collection, but here we're
* waiting on garbage collection before we invalidate
* and free anything.
*
* But this should be safe since the btree code always
* uses btree_check_reserve() before allocating now, and
* if it fails it blocks without btree nodes locked.
*/
if (!fifo_full(&ca->free_inc))
goto retry_invalidate;
bch_prio_write(ca);
}
}
}
long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int flags;
ext4_debug("cmd = %u, arg = %lu\n", cmd, arg);
switch (cmd) {
case EXT4_IOC_GETFLAGS:
ext4_get_inode_flags(ei);
flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
return put_user(flags, (int __user *) arg);
case EXT4_IOC_SETFLAGS: {
handle_t *handle = NULL;
int err, migrate = 0;
struct ext4_iloc iloc;
unsigned int oldflags, mask, i;
unsigned int jflag;
if (!inode_owner_or_capable(inode))
return -EACCES;
if (get_user(flags, (int __user *) arg))
return -EFAULT;
err = mnt_want_write_file(filp);
if (err)
return err;
flags = ext4_mask_flags(inode->i_mode, flags);
err = -EPERM;
mutex_lock(&inode->i_mutex);
/* Is it quota file? Do not allow user to mess with it */
if (IS_NOQUOTA(inode))
goto flags_out;
oldflags = ei->i_flags;
/* The JOURNAL_DATA flag is modifiable only by root */
jflag = flags & EXT4_JOURNAL_DATA_FL;
/*
* The IMMUTABLE and APPEND_ONLY flags can only be changed by
* the relevant capability.
*
* This test looks nicer. Thanks to Pauline Middelink
*/
if ((flags ^ oldflags) & (EXT4_APPEND_FL | EXT4_IMMUTABLE_FL)) {
if (!capable(CAP_LINUX_IMMUTABLE))
goto flags_out;
}
/*
* The JOURNAL_DATA flag can only be changed by
* the relevant capability.
*/
if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
if (!capable(CAP_SYS_RESOURCE))
goto flags_out;
}
if ((flags ^ oldflags) & EXT4_EXTENTS_FL)
migrate = 1;
if (flags & EXT4_EOFBLOCKS_FL) {
/* we don't support adding EOFBLOCKS flag */
if (!(oldflags & EXT4_EOFBLOCKS_FL)) {
err = -EOPNOTSUPP;
goto flags_out;
}
} else if (oldflags & EXT4_EOFBLOCKS_FL)
ext4_truncate(inode);
handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto flags_out;
}
if (IS_SYNC(inode))
ext4_handle_sync(handle);
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
goto flags_err;
for (i = 0, mask = 1; i < 32; i++, mask <<= 1) {
if (!(mask & EXT4_FL_USER_MODIFIABLE))
continue;
if (mask & flags)
ext4_set_inode_flag(inode, i);
else
ext4_clear_inode_flag(inode, i);
}
ext4_set_inode_flags(inode);
inode->i_ctime = ext4_current_time(inode);
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
flags_err:
ext4_journal_stop(handle);
if (err)
goto flags_out;
if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL))
err = ext4_change_inode_journal_flag(inode, jflag);
if (err)
goto flags_out;
if (migrate) {
if (flags & EXT4_EXTENTS_FL)
err = ext4_ext_migrate(inode);
else
err = ext4_ind_migrate(inode);
}
flags_out:
mutex_unlock(&inode->i_mutex);
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_GETVERSION:
case EXT4_IOC_GETVERSION_OLD:
return put_user(inode->i_generation, (int __user *) arg);
case EXT4_IOC_SETVERSION:
case EXT4_IOC_SETVERSION_OLD: {
handle_t *handle;
struct ext4_iloc iloc;
__u32 generation;
int err;
if (!inode_owner_or_capable(inode))
return -EPERM;
if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
ext4_warning(sb, "Setting inode version is not "
"supported with metadata_csum enabled.");
return -ENOTTY;
}
err = mnt_want_write_file(filp);
if (err)
return err;
if (get_user(generation, (int __user *) arg)) {
err = -EFAULT;
goto setversion_out;
}
mutex_lock(&inode->i_mutex);
handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto unlock_out;
}
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err == 0) {
inode->i_ctime = ext4_current_time(inode);
inode->i_generation = generation;
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
}
ext4_journal_stop(handle);
unlock_out:
mutex_unlock(&inode->i_mutex);
setversion_out:
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_GROUP_EXTEND: {
ext4_fsblk_t n_blocks_count;
int err, err2=0;
err = ext4_resize_begin(sb);
if (err)
return err;
if (get_user(n_blocks_count, (__u32 __user *)arg)) {
err = -EFAULT;
goto group_extend_out;
}
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not supported with bigalloc");
err = -EOPNOTSUPP;
goto group_extend_out;
}
err = mnt_want_write_file(filp);
if (err)
goto group_extend_out;
err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write_file(filp);
group_extend_out:
ext4_resize_end(sb);
return err;
}
case EXT4_IOC_MOVE_EXT: {
struct move_extent me;
struct fd donor;
int err;
if (!(filp->f_mode & FMODE_READ) ||
!(filp->f_mode & FMODE_WRITE))
return -EBADF;
if (copy_from_user(&me,
(struct move_extent __user *)arg, sizeof(me)))
return -EFAULT;
me.moved_len = 0;
donor = fdget(me.donor_fd);
if (!donor.file)
return -EBADF;
if (!(donor.file->f_mode & FMODE_WRITE)) {
err = -EBADF;
goto mext_out;
}
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"Online defrag not supported with bigalloc");
err = -EOPNOTSUPP;
goto mext_out;
}
err = mnt_want_write_file(filp);
if (err)
goto mext_out;
err = ext4_move_extents(filp, donor.file, me.orig_start,
me.donor_start, me.len, &me.moved_len);
mnt_drop_write_file(filp);
if (copy_to_user((struct move_extent __user *)arg,
&me, sizeof(me)))
err = -EFAULT;
mext_out:
fdput(donor);
return err;
}
case EXT4_IOC_GROUP_ADD: {
struct ext4_new_group_data input;
int err, err2=0;
err = ext4_resize_begin(sb);
if (err)
return err;
if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg,
sizeof(input))) {
err = -EFAULT;
goto group_add_out;
}
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not supported with bigalloc");
err = -EOPNOTSUPP;
goto group_add_out;
}
err = mnt_want_write_file(filp);
if (err)
goto group_add_out;
err = ext4_group_add(sb, &input);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write_file(filp);
if (!err && ext4_has_group_desc_csum(sb) &&
test_opt(sb, INIT_INODE_TABLE))
err = ext4_register_li_request(sb, input.group);
group_add_out:
ext4_resize_end(sb);
return err;
}
case EXT4_IOC_MIGRATE:
{
int err;
if (!inode_owner_or_capable(inode))
return -EACCES;
err = mnt_want_write_file(filp);
if (err)
return err;
/*
* inode_mutex prevent write and truncate on the file.
* Read still goes through. We take i_data_sem in
* ext4_ext_swap_inode_data before we switch the
* inode format to prevent read.
*/
mutex_lock(&(inode->i_mutex));
err = ext4_ext_migrate(inode);
mutex_unlock(&(inode->i_mutex));
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_ALLOC_DA_BLKS:
{
int err;
if (!inode_owner_or_capable(inode))
return -EACCES;
err = mnt_want_write_file(filp);
if (err)
return err;
err = ext4_alloc_da_blocks(inode);
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_SWAP_BOOT:
if (!(filp->f_mode & FMODE_WRITE))
return -EBADF;
return swap_inode_boot_loader(sb, inode);
case EXT4_IOC_RESIZE_FS: {
ext4_fsblk_t n_blocks_count;
int err = 0, err2 = 0;
ext4_group_t o_group = EXT4_SB(sb)->s_groups_count;
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not (yet) supported with bigalloc");
return -EOPNOTSUPP;
}
if (copy_from_user(&n_blocks_count, (__u64 __user *)arg,
sizeof(__u64))) {
return -EFAULT;
}
err = ext4_resize_begin(sb);
if (err)
return err;
err = mnt_want_write_file(filp);
if (err)
goto resizefs_out;
err = ext4_resize_fs(sb, n_blocks_count);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write_file(filp);
if (!err && (o_group > EXT4_SB(sb)->s_groups_count) &&
ext4_has_group_desc_csum(sb) &&
test_opt(sb, INIT_INODE_TABLE))
err = ext4_register_li_request(sb, o_group);
resizefs_out:
ext4_resize_end(sb);
return err;
}
case FSECTRIM:
{
struct request_queue *q = bdev_get_queue(sb->s_bdev);
struct fstrim_range range;
int ret = 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"FSECTRIM not supported with bigalloc");
return -EOPNOTSUPP;
}
if (copy_from_user(&range, (struct fstrim_range __user *)arg,
sizeof(range)))
return -EFAULT;
range.minlen = max((unsigned int)range.minlen,
q->limits.discard_granularity);
ret = blkdev_issue_discard(sb->s_bdev, range.start, range.len, GFP_NOFS, 1);
if (ret < 0)
return ret;
return 0;
}
case FITRIM:
{
struct request_queue *q = bdev_get_queue(sb->s_bdev);
struct fstrim_range range;
int ret = 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
if (copy_from_user(&range, (struct fstrim_range __user *)arg,
sizeof(range)))
return -EFAULT;
range.minlen = max((unsigned int)range.minlen,
q->limits.discard_granularity);
ret = ext4_trim_fs(sb, &range);
if (ret < 0)
return ret;
if (copy_to_user((struct fstrim_range __user *)arg, &range,
sizeof(range)))
return -EFAULT;
return 0;
}
default:
return -ENOTTY;
}
}
STATIC int
xfs_trim_extents(
struct xfs_mount *mp,
xfs_agnumber_t agno,
xfs_fsblock_t start,
xfs_fsblock_t len,
xfs_fsblock_t minlen,
__uint64_t *blocks_trimmed)
{
struct block_device *bdev = mp->m_ddev_targp->bt_bdev;
struct xfs_btree_cur *cur;
struct xfs_buf *agbp;
struct xfs_perag *pag;
int error;
int i;
pag = xfs_perag_get(mp, agno);
error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
if (error || !agbp)
goto out_put_perag;
cur = xfs_allocbt_init_cursor(mp, NULL, agbp, agno, XFS_BTNUM_CNT);
/*
* Force out the log. This means any transactions that might have freed
* space before we took the AGF buffer lock are now on disk, and the
* volatile disk cache is flushed.
*/
xfs_log_force(mp, XFS_LOG_SYNC);
/*
* Look up the longest btree in the AGF and start with it.
*/
error = xfs_alloc_lookup_le(cur, 0,
XFS_BUF_TO_AGF(agbp)->agf_longest, &i);
if (error)
goto out_del_cursor;
/*
* Loop until we are done with all extents that are large
* enough to be worth discarding.
*/
while (i) {
xfs_agblock_t fbno;
xfs_extlen_t flen;
error = xfs_alloc_get_rec(cur, &fbno, &flen, &i);
if (error)
goto out_del_cursor;
XFS_WANT_CORRUPTED_GOTO(i == 1, out_del_cursor);
ASSERT(flen <= XFS_BUF_TO_AGF(agbp)->agf_longest);
/*
* Too small? Give up.
*/
if (flen < minlen) {
trace_xfs_discard_toosmall(mp, agno, fbno, flen);
goto out_del_cursor;
}
/*
* If the extent is entirely outside of the range we are
* supposed to discard skip it. Do not bother to trim
* down partially overlapping ranges for now.
*/
if (XFS_AGB_TO_FSB(mp, agno, fbno) + flen < start ||
XFS_AGB_TO_FSB(mp, agno, fbno) >= start + len) {
trace_xfs_discard_exclude(mp, agno, fbno, flen);
goto next_extent;
}
/*
* If any blocks in the range are still busy, skip the
* discard and try again the next time.
*/
if (xfs_alloc_busy_search(mp, agno, fbno, flen)) {
trace_xfs_discard_busy(mp, agno, fbno, flen);
goto next_extent;
}
trace_xfs_discard_extent(mp, agno, fbno, flen);
error = -blkdev_issue_discard(bdev,
XFS_AGB_TO_DADDR(mp, agno, fbno),
XFS_FSB_TO_BB(mp, flen),
GFP_NOFS, 0);
if (error)
goto out_del_cursor;
*blocks_trimmed += flen;
next_extent:
error = xfs_btree_decrement(cur, 0, &i);
if (error)
goto out_del_cursor;
}
out_del_cursor:
xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
xfs_buf_relse(agbp);
out_put_perag:
xfs_perag_put(pag);
return error;
}
static int iblock_execute_unmap(struct se_cmd *cmd)
{
struct se_device *dev = cmd->se_dev;
struct iblock_dev *ibd = dev->dev_ptr;
unsigned char *buf, *ptr = NULL;
sector_t lba;
int size;
u32 range;
int ret = 0;
int dl, bd_dl;
if (cmd->data_length < 8) {
pr_warn("UNMAP parameter list length %u too small\n",
cmd->data_length);
cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
return -EINVAL;
}
buf = transport_kmap_data_sg(cmd);
dl = get_unaligned_be16(&buf[0]);
bd_dl = get_unaligned_be16(&buf[2]);
size = cmd->data_length - 8;
if (bd_dl > size)
pr_warn("UNMAP parameter list length %u too small, ignoring bd_dl %u\n",
cmd->data_length, bd_dl);
else
size = bd_dl;
if (size / 16 > dev->se_sub_dev->se_dev_attrib.max_unmap_block_desc_count) {
cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
ret = -EINVAL;
goto err;
}
/* First UNMAP block descriptor starts at 8 byte offset */
ptr = &buf[8];
pr_debug("UNMAP: Sub: %s Using dl: %u bd_dl: %u size: %u"
" ptr: %p\n", dev->transport->name, dl, bd_dl, size, ptr);
while (size >= 16) {
lba = get_unaligned_be64(&ptr[0]);
range = get_unaligned_be32(&ptr[8]);
pr_debug("UNMAP: Using lba: %llu and range: %u\n",
(unsigned long long)lba, range);
if (range > dev->se_sub_dev->se_dev_attrib.max_unmap_lba_count) {
cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST;
ret = -EINVAL;
goto err;
}
if (lba + range > dev->transport->get_blocks(dev) + 1) {
cmd->scsi_sense_reason = TCM_ADDRESS_OUT_OF_RANGE;
ret = -EINVAL;
goto err;
}
ret = blkdev_issue_discard(ibd->ibd_bd, lba, range,
GFP_KERNEL, 0);
if (ret < 0) {
pr_err("blkdev_issue_discard() failed: %d\n",
ret);
goto err;
}
ptr += 16;
size -= 16;
}
err:
transport_kunmap_data_sg(cmd);
if (!ret)
target_complete_cmd(cmd, GOOD);
return ret;
}