int efx_ef10_sriov_set_vf_mac(struct efx_nic *efx, int vf_i, u8 *mac)
{
struct efx_ef10_nic_data *nic_data = efx->nic_data;
struct ef10_vf *vf;
int rc;
if (nic_data->vf == NULL)
return -EOPNOTSUPP;
if (vf_i >= efx->vf_count)
return -EINVAL;
vf = nic_data->vf + vf_i;
if (vf->efx) {
efx_device_detach_sync(vf->efx);
efx_net_stop(vf->efx->net_dev);
down_write(&vf->efx->filter_sem);
vf->efx->type->filter_table_remove(vf->efx);
rc = efx_ef10_vadaptor_free(vf->efx, EVB_PORT_ID_ASSIGNED);
if (rc) {
up_write(&vf->efx->filter_sem);
return rc;
}
}
rc = efx_ef10_evb_port_assign(efx, EVB_PORT_ID_NULL, vf_i);
if (rc)
return rc;
if (!is_zero_ether_addr(vf->mac)) {
rc = efx_ef10_vport_del_vf_mac(efx, vf->vport_id, vf->mac);
if (rc)
return rc;
}
if (!is_zero_ether_addr(mac)) {
rc = efx_ef10_vport_add_mac(efx, vf->vport_id, mac);
if (rc) {
eth_zero_addr(vf->mac);
goto fail;
}
if (vf->efx)
ether_addr_copy(vf->efx->net_dev->dev_addr, mac);
}
ether_addr_copy(vf->mac, mac);
rc = efx_ef10_evb_port_assign(efx, vf->vport_id, vf_i);
if (rc)
goto fail;
if (vf->efx) {
/* VF cannot use the vport_id that the PF created */
rc = efx_ef10_vadaptor_alloc(vf->efx, EVB_PORT_ID_ASSIGNED);
if (rc) {
up_write(&vf->efx->filter_sem);
return rc;
}
vf->efx->type->filter_table_probe(vf->efx);
up_write(&vf->efx->filter_sem);
efx_net_open(vf->efx->net_dev);
netif_device_attach(vf->efx->net_dev);
}
return 0;
fail:
memset(vf->mac, 0, ETH_ALEN);
return rc;
}
static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
{
struct vm_area_struct *mpnt, *tmp, *prev, **pprev;
struct rb_node **rb_link, *rb_parent;
int retval;
unsigned long charge;
struct mempolicy *pol;
down_write(&oldmm->mmap_sem);
flush_cache_dup_mm(oldmm);
/*
* Not linked in yet - no deadlock potential:
*/
down_write_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING);
mm->locked_vm = 0;
mm->mmap = NULL;
mm->mmap_cache = NULL;
mm->free_area_cache = oldmm->mmap_base;
mm->cached_hole_size = ~0UL;
mm->map_count = 0;
cpumask_clear(mm_cpumask(mm));
mm->mm_rb = RB_ROOT;
rb_link = &mm->mm_rb.rb_node;
rb_parent = NULL;
pprev = &mm->mmap;
retval = ksm_fork(mm, oldmm);
if (retval)
goto out;
retval = khugepaged_fork(mm, oldmm);
if (retval)
goto out;
prev = NULL;
for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
struct file *file;
if (mpnt->vm_flags & VM_DONTCOPY) {
long pages = vma_pages(mpnt);
mm->total_vm -= pages;
vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file,
-pages);
continue;
}
charge = 0;
if (mpnt->vm_flags & VM_ACCOUNT) {
unsigned int len = (mpnt->vm_end - mpnt->vm_start) >> PAGE_SHIFT;
if (security_vm_enough_memory_mm(oldmm, len)) /* sic */
goto fail_nomem;
charge = len;
}
tmp = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
if (!tmp)
goto fail_nomem;
*tmp = *mpnt;
INIT_LIST_HEAD(&tmp->anon_vma_chain);
pol = mpol_dup(vma_policy(mpnt));
retval = PTR_ERR(pol);
if (IS_ERR(pol))
goto fail_nomem_policy;
vma_set_policy(tmp, pol);
tmp->vm_mm = mm;
if (anon_vma_fork(tmp, mpnt))
goto fail_nomem_anon_vma_fork;
tmp->vm_flags &= ~VM_LOCKED;
tmp->vm_next = tmp->vm_prev = NULL;
file = tmp->vm_file;
if (file) {
struct inode *inode = file->f_path.dentry->d_inode;
struct address_space *mapping = file->f_mapping;
get_file(file);
if (tmp->vm_flags & VM_DENYWRITE)
atomic_dec(&inode->i_writecount);
mutex_lock(&mapping->i_mmap_mutex);
if (tmp->vm_flags & VM_SHARED)
mapping->i_mmap_writable++;
flush_dcache_mmap_lock(mapping);
/* insert tmp into the share list, just after mpnt */
vma_prio_tree_add(tmp, mpnt);
flush_dcache_mmap_unlock(mapping);
mutex_unlock(&mapping->i_mmap_mutex);
}
/*
* Clear hugetlb-related page reserves for children. This only
* affects MAP_PRIVATE mappings. Faults generated by the child
* are not guaranteed to succeed, even if read-only
*/
if (is_vm_hugetlb_page(tmp))
reset_vma_resv_huge_pages(tmp);
/*
* Link in the new vma and copy the page table entries.
*/
*pprev = tmp;
pprev = &tmp->vm_next;
tmp->vm_prev = prev;
prev = tmp;
__vma_link_rb(mm, tmp, rb_link, rb_parent);
rb_link = &tmp->vm_rb.rb_right;
rb_parent = &tmp->vm_rb;
mm->map_count++;
retval = copy_page_range(mm, oldmm, mpnt);
if (tmp->vm_ops && tmp->vm_ops->open)
tmp->vm_ops->open(tmp);
if (retval)
goto out;
}
static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(old_dir);
struct inode *old_inode = d_inode(old_dentry);
struct inode *new_inode = d_inode(new_dentry);
struct page *old_dir_page, *new_dir_page;
struct page *old_page, *new_page;
struct f2fs_dir_entry *old_dir_entry = NULL, *new_dir_entry = NULL;
struct f2fs_dir_entry *old_entry, *new_entry;
int old_nlink = 0, new_nlink = 0;
int err = -ENOENT;
if ((f2fs_encrypted_inode(old_dir) || f2fs_encrypted_inode(new_dir)) &&
(old_dir != new_dir) &&
(!fscrypt_has_permitted_context(new_dir, old_inode) ||
!fscrypt_has_permitted_context(old_dir, new_inode)))
return -EPERM;
old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
if (!old_entry) {
if (IS_ERR(old_page))
err = PTR_ERR(old_page);
goto out;
}
new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name, &new_page);
if (!new_entry) {
if (IS_ERR(new_page))
err = PTR_ERR(new_page);
goto out_old;
}
/* prepare for updating ".." directory entry info later */
if (old_dir != new_dir) {
if (S_ISDIR(old_inode->i_mode)) {
old_dir_entry = f2fs_parent_dir(old_inode,
&old_dir_page);
if (!old_dir_entry) {
if (IS_ERR(old_dir_page))
err = PTR_ERR(old_dir_page);
goto out_new;
}
}
if (S_ISDIR(new_inode->i_mode)) {
new_dir_entry = f2fs_parent_dir(new_inode,
&new_dir_page);
if (!new_dir_entry) {
if (IS_ERR(new_dir_page))
err = PTR_ERR(new_dir_page);
goto out_old_dir;
}
}
}
/*
* If cross rename between file and directory those are not
* in the same directory, we will inc nlink of file's parent
* later, so we should check upper boundary of its nlink.
*/
if ((!old_dir_entry || !new_dir_entry) &&
old_dir_entry != new_dir_entry) {
old_nlink = old_dir_entry ? -1 : 1;
new_nlink = -old_nlink;
err = -EMLINK;
if ((old_nlink > 0 && old_inode->i_nlink >= F2FS_LINK_MAX) ||
(new_nlink > 0 && new_inode->i_nlink >= F2FS_LINK_MAX))
goto out_new_dir;
}
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
err = update_dent_inode(old_inode, new_inode, &new_dentry->d_name);
if (err)
goto out_unlock;
if (file_enc_name(new_inode))
file_set_enc_name(old_inode);
err = update_dent_inode(new_inode, old_inode, &old_dentry->d_name);
if (err)
goto out_undo;
if (file_enc_name(old_inode))
file_set_enc_name(new_inode);
/* update ".." directory entry info of old dentry */
if (old_dir_entry)
f2fs_set_link(old_inode, old_dir_entry, old_dir_page, new_dir);
/* update ".." directory entry info of new dentry */
if (new_dir_entry)
f2fs_set_link(new_inode, new_dir_entry, new_dir_page, old_dir);
/* update directory entry info of old dir inode */
f2fs_set_link(old_dir, old_entry, old_page, new_inode);
down_write(&F2FS_I(old_inode)->i_sem);
file_lost_pino(old_inode);
up_write(&F2FS_I(old_inode)->i_sem);
old_dir->i_ctime = current_time(old_dir);
if (old_nlink) {
down_write(&F2FS_I(old_dir)->i_sem);
f2fs_i_links_write(old_dir, old_nlink > 0);
up_write(&F2FS_I(old_dir)->i_sem);
}
f2fs_mark_inode_dirty_sync(old_dir);
/* update directory entry info of new dir inode */
f2fs_set_link(new_dir, new_entry, new_page, old_inode);
down_write(&F2FS_I(new_inode)->i_sem);
file_lost_pino(new_inode);
up_write(&F2FS_I(new_inode)->i_sem);
new_dir->i_ctime = current_time(new_dir);
if (new_nlink) {
down_write(&F2FS_I(new_dir)->i_sem);
f2fs_i_links_write(new_dir, new_nlink > 0);
up_write(&F2FS_I(new_dir)->i_sem);
}
f2fs_mark_inode_dirty_sync(new_dir);
f2fs_unlock_op(sbi);
if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
f2fs_sync_fs(sbi->sb, 1);
return 0;
out_undo:
/*
* Still we may fail to recover name info of f2fs_inode here
* Drop it, once its name is set as encrypted
*/
update_dent_inode(old_inode, old_inode, &old_dentry->d_name);
out_unlock:
f2fs_unlock_op(sbi);
out_new_dir:
if (new_dir_entry) {
f2fs_dentry_kunmap(new_inode, new_dir_page);
f2fs_put_page(new_dir_page, 0);
}
out_old_dir:
if (old_dir_entry) {
f2fs_dentry_kunmap(old_inode, old_dir_page);
f2fs_put_page(old_dir_page, 0);
}
out_new:
f2fs_dentry_kunmap(new_dir, new_page);
f2fs_put_page(new_page, 0);
out_old:
f2fs_dentry_kunmap(old_dir, old_page);
f2fs_put_page(old_page, 0);
out:
return err;
}
static int nilfs_remount(struct super_block *sb, int *flags, char *data)
{
struct the_nilfs *nilfs = sb->s_fs_info;
unsigned long old_sb_flags;
unsigned long old_mount_opt;
int err;
sync_filesystem(sb);
old_sb_flags = sb->s_flags;
old_mount_opt = nilfs->ns_mount_opt;
if (!parse_options(data, sb, 1)) {
err = -EINVAL;
goto restore_opts;
}
sb->s_flags = (sb->s_flags & ~SB_POSIXACL);
err = -EINVAL;
if (!nilfs_valid_fs(nilfs)) {
nilfs_msg(sb, KERN_WARNING,
"couldn't remount because the filesystem is in an incomplete recovery state");
goto restore_opts;
}
if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb))
goto out;
if (*flags & SB_RDONLY) {
/* Shutting down log writer */
nilfs_detach_log_writer(sb);
sb->s_flags |= SB_RDONLY;
/*
* Remounting a valid RW partition RDONLY, so set
* the RDONLY flag and then mark the partition as valid again.
*/
down_write(&nilfs->ns_sem);
nilfs_cleanup_super(sb);
up_write(&nilfs->ns_sem);
} else {
__u64 features;
struct nilfs_root *root;
/*
* Mounting a RDONLY partition read-write, so reread and
* store the current valid flag. (It may have been changed
* by fsck since we originally mounted the partition.)
*/
down_read(&nilfs->ns_sem);
features = le64_to_cpu(nilfs->ns_sbp[0]->s_feature_compat_ro) &
~NILFS_FEATURE_COMPAT_RO_SUPP;
up_read(&nilfs->ns_sem);
if (features) {
nilfs_msg(sb, KERN_WARNING,
"couldn't remount RDWR because of unsupported optional features (%llx)",
(unsigned long long)features);
err = -EROFS;
goto restore_opts;
}
sb->s_flags &= ~SB_RDONLY;
root = NILFS_I(d_inode(sb->s_root))->i_root;
err = nilfs_attach_log_writer(sb, root);
if (err)
goto restore_opts;
down_write(&nilfs->ns_sem);
nilfs_setup_super(sb, true);
up_write(&nilfs->ns_sem);
}
out:
return 0;
restore_opts:
sb->s_flags = old_sb_flags;
nilfs->ns_mount_opt = old_mount_opt;
return err;
}
static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode,
struct inode *tmp_inode)
{
int retval;
__le32 i_data[3];
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_inode_info *tmp_ei = EXT4_I(tmp_inode);
/*
* One credit accounted for writing the
* i_data field of the original inode
*/
retval = ext4_journal_extend(handle, 1);
if (retval) {
retval = ext4_journal_restart(handle, 1);
if (retval)
goto err_out;
}
i_data[0] = ei->i_data[EXT4_IND_BLOCK];
i_data[1] = ei->i_data[EXT4_DIND_BLOCK];
i_data[2] = ei->i_data[EXT4_TIND_BLOCK];
down_write(&EXT4_I(inode)->i_data_sem);
/*
* if EXT4_EXT_MIGRATE is cleared a block allocation
* happened after we started the migrate. We need to
* fail the migrate
*/
if (!(EXT4_I(inode)->i_flags & EXT4_EXT_MIGRATE)) {
retval = -EAGAIN;
up_write(&EXT4_I(inode)->i_data_sem);
goto err_out;
} else
EXT4_I(inode)->i_flags = EXT4_I(inode)->i_flags &
~EXT4_EXT_MIGRATE;
/*
* We have the extent map build with the tmp inode.
* Now copy the i_data across
*/
ei->i_flags |= EXT4_EXTENTS_FL;
memcpy(ei->i_data, tmp_ei->i_data, sizeof(ei->i_data));
/*
* Update i_blocks with the new blocks that got
* allocated while adding extents for extent index
* blocks.
*
* While converting to extents we need not
* update the orignal inode i_blocks for extent blocks
* via quota APIs. The quota update happened via tmp_inode already.
*/
spin_lock(&inode->i_lock);
inode->i_blocks += tmp_inode->i_blocks;
spin_unlock(&inode->i_lock);
up_write(&EXT4_I(inode)->i_data_sem);
/*
* We mark the inode dirty after, because we decrement the
* i_blocks when freeing the indirect meta-data blocks
*/
retval = free_ind_block(handle, inode, i_data);
ext4_mark_inode_dirty(handle, inode);
err_out:
return retval;
}
int fimg2d_add_command(struct fimg2d_control *info, struct fimg2d_context *ctx,
struct fimg2d_blit *blit)
{
int i, ret;
struct fimg2d_image *buf[MAX_IMAGES] = image_table(blit);
struct fimg2d_bltcmd *cmd;
struct fimg2d_image dst;
if (blit->dst)
if (copy_from_user(&dst, (void *)blit->dst, sizeof(dst)))
return -EFAULT;
if ((blit->dst) && (dst.addr.type == ADDR_USER))
up_write(&page_alloc_slow_rwsem);
cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
if ((blit->dst) && (dst.addr.type == ADDR_USER))
down_write(&page_alloc_slow_rwsem);
if (!cmd)
return -ENOMEM;
for (i = 0; i < MAX_IMAGES; i++) {
if (!buf[i])
continue;
if (copy_from_user(&cmd->image[i], buf[i],
sizeof(struct fimg2d_image))) {
ret = -EFAULT;
goto err_user;
}
}
cmd->ctx = ctx;
cmd->op = blit->op;
cmd->sync = blit->sync;
cmd->seq_no = blit->seq_no;
memcpy(&cmd->param, &blit->param, sizeof(cmd->param));
#ifdef CONFIG_VIDEO_FIMG2D_DEBUG
fimg2d_dump_command(cmd);
#endif
if (fimg2d_check_params(cmd)) {
printk(KERN_ERR "[%s] invalid params\n", __func__);
fimg2d_dump_command(cmd);
ret = -EINVAL;
goto err_user;
}
fimg2d_fixup_params(cmd);
if (fimg2d_check_dma_sync(cmd)) {
ret = -EFAULT;
goto err_user;
}
/* add command node and increase ncmd */
spin_lock(&info->bltlock);
if (atomic_read(&info->suspended)) {
fimg2d_debug("fimg2d suspended, do sw fallback\n");
spin_unlock(&info->bltlock);
ret = -EFAULT;
goto err_user;
}
atomic_inc(&ctx->ncmd);
fimg2d_enqueue(&cmd->node, &info->cmd_q);
fimg2d_debug("ctx %p pgd %p ncmd(%d) seq_no(%u)\n",
cmd->ctx, (unsigned long *)cmd->ctx->mm->pgd,
atomic_read(&ctx->ncmd), cmd->seq_no);
spin_unlock(&info->bltlock);
return 0;
err_user:
kfree(cmd);
return ret;
}
static int nilfs_remount(struct super_block *sb, int *flags, char *data)
{
struct nilfs_sb_info *sbi = NILFS_SB(sb);
struct the_nilfs *nilfs = sbi->s_nilfs;
unsigned long old_sb_flags;
struct nilfs_mount_options old_opts;
int was_snapshot, err;
lock_kernel();
down_write(&nilfs->ns_super_sem);
old_sb_flags = sb->s_flags;
old_opts.mount_opt = sbi->s_mount_opt;
old_opts.snapshot_cno = sbi->s_snapshot_cno;
was_snapshot = nilfs_test_opt(sbi, SNAPSHOT);
if (!parse_options(data, sb, 1)) {
err = -EINVAL;
goto restore_opts;
}
sb->s_flags = (sb->s_flags & ~MS_POSIXACL);
err = -EINVAL;
if (was_snapshot && !(*flags & MS_RDONLY)) {
printk(KERN_ERR "NILFS (device %s): cannot remount snapshot "
"read/write.\n", sb->s_id);
goto restore_opts;
}
if (!nilfs_valid_fs(nilfs)) {
printk(KERN_WARNING "NILFS (device %s): couldn't "
"remount because the filesystem is in an "
"incomplete recovery state.\n", sb->s_id);
goto restore_opts;
}
if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
goto out;
if (*flags & MS_RDONLY) {
/* Shutting down the segment constructor */
nilfs_detach_segment_constructor(sbi);
sb->s_flags |= MS_RDONLY;
/*
* Remounting a valid RW partition RDONLY, so set
* the RDONLY flag and then mark the partition as valid again.
*/
down_write(&nilfs->ns_sem);
nilfs_cleanup_super(sbi);
up_write(&nilfs->ns_sem);
} else {
__u64 features;
/*
* Mounting a RDONLY partition read-write, so reread and
* store the current valid flag. (It may have been changed
* by fsck since we originally mounted the partition.)
*/
down_read(&nilfs->ns_sem);
features = le64_to_cpu(nilfs->ns_sbp[0]->s_feature_compat_ro) &
~NILFS_FEATURE_COMPAT_RO_SUPP;
up_read(&nilfs->ns_sem);
if (features) {
printk(KERN_WARNING "NILFS (device %s): couldn't "
"remount RDWR because of unsupported optional "
"features (%llx)\n",
sb->s_id, (unsigned long long)features);
err = -EROFS;
goto restore_opts;
}
sb->s_flags &= ~MS_RDONLY;
err = nilfs_attach_segment_constructor(sbi);
if (err)
goto restore_opts;
down_write(&nilfs->ns_sem);
nilfs_setup_super(sbi);
up_write(&nilfs->ns_sem);
}
out:
up_write(&nilfs->ns_super_sem);
unlock_kernel();
return 0;
restore_opts:
sb->s_flags = old_sb_flags;
sbi->s_mount_opt = old_opts.mount_opt;
sbi->s_snapshot_cno = old_opts.snapshot_cno;
up_write(&nilfs->ns_super_sem);
unlock_kernel();
return err;
}
static int lfsck_namespace_exec_dir(const struct lu_env *env,
struct lfsck_component *com,
struct dt_object *obj,
struct lu_dirent *ent)
{
struct lfsck_thread_info *info = lfsck_env_info(env);
struct lu_attr *la = &info->lti_la;
struct lfsck_instance *lfsck = com->lc_lfsck;
struct lfsck_bookmark *bk = &lfsck->li_bookmark_ram;
struct lfsck_namespace *ns = com->lc_file_ram;
struct linkea_data ldata = { 0 };
const struct lu_fid *pfid = lfsck_dto2fid(lfsck->li_obj_dir);
const struct lu_fid *cfid = lfsck_dto2fid(obj);
const struct lu_name *cname;
struct thandle *handle = NULL;
bool repaired = false;
bool locked = false;
bool remove;
bool newdata;
int count = 0;
int rc;
ENTRY;
cname = lfsck_name_get_const(env, ent->lde_name, ent->lde_namelen);
down_write(&com->lc_sem);
com->lc_new_checked++;
if (ent->lde_attrs & LUDA_UPGRADE) {
ns->ln_flags |= LF_UPGRADE;
repaired = true;
} else if (ent->lde_attrs & LUDA_REPAIR) {
ns->ln_flags |= LF_INCONSISTENT;
repaired = true;
}
if (ent->lde_name[0] == '.' &&
(ent->lde_namelen == 1 ||
(ent->lde_namelen == 2 && ent->lde_name[1] == '.') ||
fid_is_dot_lustre(&ent->lde_fid)))
GOTO(out, rc = 0);
if (!(bk->lb_param & LPF_DRYRUN) &&
(com->lc_journal || repaired)) {
again:
LASSERT(!locked);
com->lc_journal = 1;
handle = dt_trans_create(env, lfsck->li_next);
if (IS_ERR(handle))
GOTO(out, rc = PTR_ERR(handle));
rc = lfsck_declare_namespace_exec_dir(env, obj, handle);
if (rc != 0)
GOTO(stop, rc);
rc = dt_trans_start(env, lfsck->li_next, handle);
if (rc != 0)
GOTO(stop, rc);
dt_write_lock(env, obj, MOR_TGT_CHILD);
locked = true;
}
rc = lfsck_namespace_check_exist(env, lfsck, obj, ent->lde_name);
if (rc != 0)
GOTO(stop, rc);
rc = lfsck_links_read(env, obj, &ldata);
if (rc == 0) {
count = ldata.ld_leh->leh_reccount;
rc = linkea_links_find(&ldata, cname, pfid);
if ((rc == 0) &&
(count == 1 || !S_ISDIR(lfsck_object_type(obj))))
goto record;
ns->ln_flags |= LF_INCONSISTENT;
/* For dir, if there are more than one linkea entries, or the
* linkea entry does not match the name entry, then remove all
* and add the correct one. */
if (S_ISDIR(lfsck_object_type(obj))) {
remove = true;
newdata = true;
} else {
remove = false;
newdata = false;
}
goto nodata;
} else if (unlikely(rc == -EINVAL)) {
count = 1;
ns->ln_flags |= LF_INCONSISTENT;
/* The magic crashed, we are not sure whether there are more
* corrupt data in the linkea, so remove all linkea entries. */
remove = true;
newdata = true;
goto nodata;
} else if (rc == -ENODATA) {
count = 1;
ns->ln_flags |= LF_UPGRADE;
remove = false;
newdata = true;
nodata:
if (bk->lb_param & LPF_DRYRUN) {
repaired = true;
goto record;
}
if (!com->lc_journal)
goto again;
if (remove) {
LASSERT(newdata);
rc = dt_xattr_del(env, obj, XATTR_NAME_LINK, handle,
BYPASS_CAPA);
if (rc != 0)
GOTO(stop, rc);
}
if (newdata) {
rc = linkea_data_new(&ldata,
&lfsck_env_info(env)->lti_linkea_buf);
if (rc != 0)
GOTO(stop, rc);
}
rc = linkea_add_buf(&ldata, cname, pfid);
if (rc != 0)
GOTO(stop, rc);
rc = lfsck_links_write(env, obj, &ldata, handle);
if (rc != 0)
GOTO(stop, rc);
count = ldata.ld_leh->leh_reccount;
repaired = true;
} else {
GOTO(stop, rc);
}
record:
LASSERT(count > 0);
rc = dt_attr_get(env, obj, la, BYPASS_CAPA);
if (rc != 0)
GOTO(stop, rc);
if ((count == 1) &&
(la->la_nlink == 1 || S_ISDIR(lfsck_object_type(obj))))
/* Usually, it is for single linked object or dir, do nothing.*/
GOTO(stop, rc);
/* Following modification will be in another transaction. */
if (handle != NULL) {
LASSERT(dt_write_locked(env, obj));
dt_write_unlock(env, obj);
locked = false;
dt_trans_stop(env, lfsck->li_next, handle);
handle = NULL;
}
ns->ln_mlinked_checked++;
rc = lfsck_namespace_update(env, com, cfid,
count != la->la_nlink ? LLF_UNMATCH_NLINKS : 0, false);
GOTO(out, rc);
stop:
if (locked)
dt_write_unlock(env, obj);
if (handle != NULL)
dt_trans_stop(env, lfsck->li_next, handle);
out:
if (rc < 0) {
ns->ln_items_failed++;
if (lfsck_pos_is_zero(&ns->ln_pos_first_inconsistent))
lfsck_pos_fill(env, lfsck,
&ns->ln_pos_first_inconsistent, false);
if (!(bk->lb_param & LPF_FAILOUT))
rc = 0;
} else {
if (repaired) {
ns->ln_items_repaired++;
if (bk->lb_param & LPF_DRYRUN &&
lfsck_pos_is_zero(&ns->ln_pos_first_inconsistent))
lfsck_pos_fill(env, lfsck,
&ns->ln_pos_first_inconsistent,
false);
} else {
com->lc_journal = 0;
}
rc = 0;
}
up_write(&com->lc_sem);
return rc;
}
static int
islpci_reset_if(islpci_private *priv)
{
long remaining;
int result = -ETIME;
int count;
DEFINE_WAIT(wait);
prepare_to_wait(&priv->reset_done, &wait, TASK_UNINTERRUPTIBLE);
/* now the last step is to reset the interface */
isl38xx_interface_reset(priv->device_base, priv->device_host_address);
islpci_set_state(priv, PRV_STATE_PREINIT);
for(count = 0; count < 2 && result; count++) {
/* The software reset acknowledge needs about 220 msec here.
* Be conservative and wait for up to one second. */
remaining = schedule_timeout_uninterruptible(HZ);
if(remaining > 0) {
result = 0;
break;
}
/* If we're here it's because our IRQ hasn't yet gone through.
* Retry a bit more...
*/
printk(KERN_ERR "%s: no 'reset complete' IRQ seen - retrying\n",
priv->ndev->name);
}
finish_wait(&priv->reset_done, &wait);
if (result) {
printk(KERN_ERR "%s: interface reset failure\n", priv->ndev->name);
return result;
}
islpci_set_state(priv, PRV_STATE_INIT);
/* Now that the device is 100% up, let's allow
* for the other interrupts --
* NOTE: this is not *yet* true since we've only allowed the
* INIT interrupt on the IRQ line. We can perhaps poll
* the IRQ line until we know for sure the reset went through */
isl38xx_enable_common_interrupts(priv->device_base);
down_write(&priv->mib_sem);
result = mgt_commit(priv);
if (result) {
printk(KERN_ERR "%s: interface reset failure\n", priv->ndev->name);
up_write(&priv->mib_sem);
return result;
}
up_write(&priv->mib_sem);
islpci_set_state(priv, PRV_STATE_READY);
printk(KERN_DEBUG "%s: interface reset complete\n", priv->ndev->name);
return 0;
}
static int lfsck_namespace_reset(const struct lu_env *env,
struct lfsck_component *com, bool init)
{
struct lfsck_instance *lfsck = com->lc_lfsck;
struct lfsck_namespace *ns = com->lc_file_ram;
struct dt_object *root;
struct dt_object *dto;
int rc;
ENTRY;
root = dt_locate(env, lfsck->li_bottom, &lfsck->li_local_root_fid);
if (IS_ERR(root))
RETURN(PTR_ERR(root));
if (unlikely(!dt_try_as_dir(env, root))) {
lu_object_put(env, &root->do_lu);
RETURN(-ENOTDIR);
}
down_write(&com->lc_sem);
if (init) {
memset(ns, 0, sizeof(*ns));
} else {
__u32 count = ns->ln_success_count;
__u64 last_time = ns->ln_time_last_complete;
memset(ns, 0, sizeof(*ns));
ns->ln_success_count = count;
ns->ln_time_last_complete = last_time;
}
ns->ln_magic = LFSCK_NAMESPACE_MAGIC;
ns->ln_status = LS_INIT;
rc = local_object_unlink(env, lfsck->li_bottom, root,
lfsck_namespace_name);
if (rc != 0)
GOTO(out, rc);
lfsck_object_put(env, com->lc_obj);
com->lc_obj = NULL;
dto = local_index_find_or_create(env, lfsck->li_los, root,
lfsck_namespace_name,
S_IFREG | S_IRUGO | S_IWUSR,
&dt_lfsck_features);
if (IS_ERR(dto))
GOTO(out, rc = PTR_ERR(dto));
com->lc_obj = dto;
rc = dto->do_ops->do_index_try(env, dto, &dt_lfsck_features);
if (rc != 0)
GOTO(out, rc);
rc = lfsck_namespace_store(env, com, true);
GOTO(out, rc);
out:
up_write(&com->lc_sem);
lu_object_put(env, &root->do_lu);
return rc;
}
static int lfsck_namespace_prep(const struct lu_env *env,
struct lfsck_component *com,
struct lfsck_start_param *lsp)
{
struct lfsck_instance *lfsck = com->lc_lfsck;
struct lfsck_namespace *ns = com->lc_file_ram;
struct lfsck_position *pos = &com->lc_pos_start;
if (ns->ln_status == LS_COMPLETED) {
int rc;
rc = lfsck_namespace_reset(env, com, false);
if (rc != 0)
return rc;
}
down_write(&com->lc_sem);
ns->ln_time_latest_start = cfs_time_current_sec();
spin_lock(&lfsck->li_lock);
if (ns->ln_flags & LF_SCANNED_ONCE) {
if (!lfsck->li_drop_dryrun ||
lfsck_pos_is_zero(&ns->ln_pos_first_inconsistent)) {
ns->ln_status = LS_SCANNING_PHASE2;
cfs_list_del_init(&com->lc_link);
cfs_list_add_tail(&com->lc_link,
&lfsck->li_list_double_scan);
if (!cfs_list_empty(&com->lc_link_dir))
cfs_list_del_init(&com->lc_link_dir);
lfsck_pos_set_zero(pos);
} else {
ns->ln_status = LS_SCANNING_PHASE1;
ns->ln_run_time_phase1 = 0;
ns->ln_run_time_phase2 = 0;
ns->ln_items_checked = 0;
ns->ln_items_repaired = 0;
ns->ln_items_failed = 0;
ns->ln_dirs_checked = 0;
ns->ln_mlinked_checked = 0;
ns->ln_objs_checked_phase2 = 0;
ns->ln_objs_repaired_phase2 = 0;
ns->ln_objs_failed_phase2 = 0;
ns->ln_objs_nlink_repaired = 0;
ns->ln_objs_lost_found = 0;
fid_zero(&ns->ln_fid_latest_scanned_phase2);
if (cfs_list_empty(&com->lc_link_dir))
cfs_list_add_tail(&com->lc_link_dir,
&lfsck->li_list_dir);
*pos = ns->ln_pos_first_inconsistent;
}
} else {
ns->ln_status = LS_SCANNING_PHASE1;
if (cfs_list_empty(&com->lc_link_dir))
cfs_list_add_tail(&com->lc_link_dir,
&lfsck->li_list_dir);
if (!lfsck->li_drop_dryrun ||
lfsck_pos_is_zero(&ns->ln_pos_first_inconsistent)) {
*pos = ns->ln_pos_last_checkpoint;
pos->lp_oit_cookie++;
} else {
*pos = ns->ln_pos_first_inconsistent;
}
}
spin_unlock(&lfsck->li_lock);
up_write(&com->lc_sem);
return 0;
}
static int lfsck_namespace_double_scan_main(void *args)
{
struct lfsck_thread_args *lta = args;
const struct lu_env *env = <a->lta_env;
struct lfsck_component *com = lta->lta_com;
struct lfsck_instance *lfsck = com->lc_lfsck;
struct ptlrpc_thread *thread = &lfsck->li_thread;
struct lfsck_bookmark *bk = &lfsck->li_bookmark_ram;
struct lfsck_namespace *ns = com->lc_file_ram;
struct dt_object *obj = com->lc_obj;
const struct dt_it_ops *iops = &obj->do_index_ops->dio_it;
struct dt_object *target;
struct dt_it *di;
struct dt_key *key;
struct lu_fid fid;
int rc;
__u8 flags = 0;
ENTRY;
com->lc_new_checked = 0;
com->lc_new_scanned = 0;
com->lc_time_last_checkpoint = cfs_time_current();
com->lc_time_next_checkpoint = com->lc_time_last_checkpoint +
cfs_time_seconds(LFSCK_CHECKPOINT_INTERVAL);
di = iops->init(env, obj, 0, BYPASS_CAPA);
if (IS_ERR(di))
GOTO(out, rc = PTR_ERR(di));
fid_cpu_to_be(&fid, &ns->ln_fid_latest_scanned_phase2);
rc = iops->get(env, di, (const struct dt_key *)&fid);
if (rc < 0)
GOTO(fini, rc);
/* Skip the start one, which either has been processed or non-exist. */
rc = iops->next(env, di);
if (rc != 0)
GOTO(put, rc);
if (OBD_FAIL_CHECK(OBD_FAIL_LFSCK_NO_DOUBLESCAN))
GOTO(put, rc = 0);
do {
if (OBD_FAIL_CHECK(OBD_FAIL_LFSCK_DELAY3) &&
cfs_fail_val > 0) {
struct l_wait_info lwi;
lwi = LWI_TIMEOUT(cfs_time_seconds(cfs_fail_val),
NULL, NULL);
l_wait_event(thread->t_ctl_waitq,
!thread_is_running(thread),
&lwi);
}
key = iops->key(env, di);
fid_be_to_cpu(&fid, (const struct lu_fid *)key);
target = lfsck_object_find(env, lfsck, &fid);
down_write(&com->lc_sem);
if (target == NULL) {
rc = 0;
goto checkpoint;
} else if (IS_ERR(target)) {
rc = PTR_ERR(target);
goto checkpoint;
}
/* XXX: Currently, skip remote object, the consistency for
* remote object will be processed in LFSCK phase III. */
if (dt_object_exists(target) && !dt_object_remote(target)) {
rc = iops->rec(env, di, (struct dt_rec *)&flags, 0);
if (rc == 0)
rc = lfsck_namespace_double_scan_one(env, com,
target, flags);
}
lfsck_object_put(env, target);
checkpoint:
com->lc_new_checked++;
com->lc_new_scanned++;
ns->ln_fid_latest_scanned_phase2 = fid;
if (rc > 0)
ns->ln_objs_repaired_phase2++;
else if (rc < 0)
ns->ln_objs_failed_phase2++;
up_write(&com->lc_sem);
if ((rc == 0) || ((rc > 0) && !(bk->lb_param & LPF_DRYRUN))) {
lfsck_namespace_delete(env, com, &fid);
} else if (rc < 0) {
flags |= LLF_REPAIR_FAILED;
lfsck_namespace_update(env, com, &fid, flags, true);
}
if (rc < 0 && bk->lb_param & LPF_FAILOUT)
GOTO(put, rc);
if (unlikely(cfs_time_beforeq(com->lc_time_next_checkpoint,
cfs_time_current())) &&
com->lc_new_checked != 0) {
down_write(&com->lc_sem);
ns->ln_run_time_phase2 +=
cfs_duration_sec(cfs_time_current() +
HALF_SEC - com->lc_time_last_checkpoint);
ns->ln_time_last_checkpoint = cfs_time_current_sec();
ns->ln_objs_checked_phase2 += com->lc_new_checked;
com->lc_new_checked = 0;
rc = lfsck_namespace_store(env, com, false);
up_write(&com->lc_sem);
if (rc != 0)
GOTO(put, rc);
com->lc_time_last_checkpoint = cfs_time_current();
com->lc_time_next_checkpoint =
com->lc_time_last_checkpoint +
cfs_time_seconds(LFSCK_CHECKPOINT_INTERVAL);
}
lfsck_control_speed_by_self(com);
if (unlikely(!thread_is_running(thread)))
GOTO(put, rc = 0);
rc = iops->next(env, di);
} while (rc == 0);
GOTO(put, rc);
put:
iops->put(env, di);
fini:
iops->fini(env, di);
out:
down_write(&com->lc_sem);
ns->ln_run_time_phase2 += cfs_duration_sec(cfs_time_current() +
HALF_SEC - lfsck->li_time_last_checkpoint);
ns->ln_time_last_checkpoint = cfs_time_current_sec();
ns->ln_objs_checked_phase2 += com->lc_new_checked;
com->lc_new_checked = 0;
if (rc > 0) {
com->lc_journal = 0;
ns->ln_status = LS_COMPLETED;
if (!(bk->lb_param & LPF_DRYRUN))
ns->ln_flags &= ~(LF_SCANNED_ONCE | LF_INCONSISTENT);
ns->ln_time_last_complete = ns->ln_time_last_checkpoint;
ns->ln_success_count++;
} else if (rc == 0) {
ns->ln_status = lfsck->li_status;
if (ns->ln_status == 0)
ns->ln_status = LS_STOPPED;
} else {
ns->ln_status = LS_FAILED;
}
if (ns->ln_status != LS_PAUSED) {
spin_lock(&lfsck->li_lock);
cfs_list_del_init(&com->lc_link);
cfs_list_add_tail(&com->lc_link, &lfsck->li_list_idle);
spin_unlock(&lfsck->li_lock);
}
rc = lfsck_namespace_store(env, com, false);
up_write(&com->lc_sem);
if (atomic_dec_and_test(&lfsck->li_double_scan_count))
wake_up_all(&thread->t_ctl_waitq);
lfsck_thread_args_fini(lta);
return rc;
}
int notify_change(struct dentry * dentry, struct iattr * attr)
{
struct inode *inode = dentry->d_inode;
mode_t mode = inode->i_mode;
int error;
struct timespec now;
unsigned int ia_valid = attr->ia_valid;
if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) {
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
return -EPERM;
}
now = current_fs_time(inode->i_sb);
attr->ia_ctime = now;
if (!(ia_valid & ATTR_ATIME_SET))
attr->ia_atime = now;
if (!(ia_valid & ATTR_MTIME_SET))
attr->ia_mtime = now;
if (ia_valid & ATTR_KILL_PRIV) {
attr->ia_valid &= ~ATTR_KILL_PRIV;
ia_valid &= ~ATTR_KILL_PRIV;
error = security_inode_need_killpriv(dentry);
if (error > 0)
error = security_inode_killpriv(dentry);
if (error)
return error;
}
/*
* We now pass ATTR_KILL_S*ID to the lower level setattr function so
* that the function has the ability to reinterpret a mode change
* that's due to these bits. This adds an implicit restriction that
* no function will ever call notify_change with both ATTR_MODE and
* ATTR_KILL_S*ID set.
*/
if ((ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) &&
(ia_valid & ATTR_MODE))
BUG();
if (ia_valid & ATTR_KILL_SUID) {
if (mode & S_ISUID) {
ia_valid = attr->ia_valid |= ATTR_MODE;
attr->ia_mode = (inode->i_mode & ~S_ISUID);
}
}
if (ia_valid & ATTR_KILL_SGID) {
if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
if (!(ia_valid & ATTR_MODE)) {
ia_valid = attr->ia_valid |= ATTR_MODE;
attr->ia_mode = inode->i_mode;
}
attr->ia_mode &= ~S_ISGID;
}
}
if (!(attr->ia_valid & ~(ATTR_KILL_SUID | ATTR_KILL_SGID)))
return 0;
error = security_inode_setattr(dentry, attr);
if (error)
return error;
if (ia_valid & ATTR_SIZE)
down_write(&dentry->d_inode->i_alloc_sem);
if (inode->i_op->setattr)
error = inode->i_op->setattr(dentry, attr);
else
error = simple_setattr(dentry, attr);
if (ia_valid & ATTR_SIZE)
up_write(&dentry->d_inode->i_alloc_sem);
if (!error)
fsnotify_change(dentry, ia_valid);
return error;
}
int efx_ef10_sriov_set_vf_vlan(struct efx_nic *efx, int vf_i, u16 vlan,
u8 qos)
{
struct efx_ef10_nic_data *nic_data = efx->nic_data;
struct ef10_vf *vf;
u16 old_vlan, new_vlan;
int rc = 0, rc2 = 0;
if (vf_i >= efx->vf_count)
return -EINVAL;
if (qos != 0)
return -EINVAL;
vf = nic_data->vf + vf_i;
new_vlan = (vlan == 0) ? EFX_EF10_NO_VLAN : vlan;
if (new_vlan == vf->vlan)
return 0;
if (vf->efx) {
efx_device_detach_sync(vf->efx);
efx_net_stop(vf->efx->net_dev);
down_write(&vf->efx->filter_sem);
vf->efx->type->filter_table_remove(vf->efx);
rc = efx_ef10_vadaptor_free(vf->efx, EVB_PORT_ID_ASSIGNED);
if (rc)
goto restore_filters;
}
if (vf->vport_assigned) {
rc = efx_ef10_evb_port_assign(efx, EVB_PORT_ID_NULL, vf_i);
if (rc) {
netif_warn(efx, drv, efx->net_dev,
"Failed to change vlan on VF %d.\n", vf_i);
netif_warn(efx, drv, efx->net_dev,
"This is likely because the VF is bound to a driver in a VM.\n");
netif_warn(efx, drv, efx->net_dev,
"Please unload the driver in the VM.\n");
goto restore_vadaptor;
}
vf->vport_assigned = 0;
}
if (!is_zero_ether_addr(vf->mac)) {
rc = efx_ef10_vport_del_mac(efx, vf->vport_id, vf->mac);
if (rc)
goto restore_evb_port;
}
if (vf->vport_id) {
rc = efx_ef10_vport_free(efx, vf->vport_id);
if (rc)
goto restore_mac;
vf->vport_id = 0;
}
/* Do the actual vlan change */
old_vlan = vf->vlan;
vf->vlan = new_vlan;
/* Restore everything in reverse order */
rc = efx_ef10_vport_alloc(efx, EVB_PORT_ID_ASSIGNED,
MC_CMD_VPORT_ALLOC_IN_VPORT_TYPE_NORMAL,
vf->vlan, &vf->vport_id);
if (rc)
goto reset_nic;
restore_mac:
if (!is_zero_ether_addr(vf->mac)) {
rc2 = efx_ef10_vport_add_mac(efx, vf->vport_id, vf->mac);
if (rc2) {
eth_zero_addr(vf->mac);
goto reset_nic;
}
}
restore_evb_port:
rc2 = efx_ef10_evb_port_assign(efx, vf->vport_id, vf_i);
if (rc2)
goto reset_nic;
else
vf->vport_assigned = 1;
restore_vadaptor:
if (vf->efx) {
rc2 = efx_ef10_vadaptor_alloc(vf->efx, EVB_PORT_ID_ASSIGNED);
if (rc2)
goto reset_nic;
}
restore_filters:
if (vf->efx) {
rc2 = vf->efx->type->filter_table_probe(vf->efx);
if (rc2)
goto reset_nic;
rc2 = efx_net_open(vf->efx->net_dev);
if (rc2)
goto reset_nic;
up_write(&vf->efx->filter_sem);
netif_device_attach(vf->efx->net_dev);
}
return rc;
reset_nic:
if (vf->efx) {
up_write(&vf->efx->filter_sem);
netif_err(efx, drv, efx->net_dev,
"Failed to restore the VF - scheduling reset.\n");
efx_schedule_reset(vf->efx, RESET_TYPE_DATAPATH);
} else {
netif_err(efx, drv, efx->net_dev,
"Failed to restore the VF and cannot reset the VF "
"- VF is not functional.\n");
netif_err(efx, drv, efx->net_dev,
"Please reload the driver attached to the VF.\n");
}
return rc ? rc : rc2;
}
/*
* iterate through the VL servers in a cell until one of them admits knowing
* about the volume in question
*/
static int afs_vlocation_access_vl_by_id(struct afs_vlocation *vl,
struct key *key,
afs_volid_t volid,
afs_voltype_t voltype,
struct afs_cache_vlocation *vldb)
{
struct afs_cell *cell = vl->cell;
struct in_addr addr;
int count, ret;
_enter("%s,%x,%d,", cell->name, volid, voltype);
down_write(&vl->cell->vl_sem);
ret = -ENOMEDIUM;
for (count = cell->vl_naddrs; count > 0; count--) {
addr = cell->vl_addrs[cell->vl_curr_svix];
_debug("CellServ[%hu]: %08x", cell->vl_curr_svix, addr.s_addr);
/* attempt to access the VL server */
ret = afs_vl_get_entry_by_id(&addr, key, volid, voltype, vldb,
&afs_sync_call);
switch (ret) {
case 0:
goto out;
case -ENOMEM:
case -ENONET:
case -ENETUNREACH:
case -EHOSTUNREACH:
case -ECONNREFUSED:
if (ret == -ENOMEM || ret == -ENONET)
goto out;
goto rotate;
case -EBUSY:
vl->upd_busy_cnt++;
if (vl->upd_busy_cnt <= 3) {
if (vl->upd_busy_cnt > 1) {
/* second+ BUSY - sleep a little bit */
set_current_state(TASK_UNINTERRUPTIBLE);
schedule_timeout(1);
__set_current_state(TASK_RUNNING);
}
continue;
}
break;
case -ENOMEDIUM:
vl->upd_rej_cnt++;
goto rotate;
default:
ret = -EIO;
goto rotate;
}
/* rotate the server records upon lookup failure */
rotate:
cell->vl_curr_svix++;
cell->vl_curr_svix %= cell->vl_naddrs;
vl->upd_busy_cnt = 0;
}
out:
if (ret < 0 && vl->upd_rej_cnt > 0) {
// printk(KERN_NOTICE "kAFS:"
// " Active volume no longer valid '%s'\n",
;
vl->valid = 0;
ret = -ENOMEDIUM;
}
up_write(&vl->cell->vl_sem);
_leave(" = %d", ret);
return ret;
}
/**
* nilfs_fill_super() - initialize a super block instance
* @sb: super_block
* @data: mount options
* @silent: silent mode flag
*
* This function is called exclusively by nilfs->ns_mount_mutex.
* So, the recovery process is protected from other simultaneous mounts.
*/
static int
nilfs_fill_super(struct super_block *sb, void *data, int silent)
{
struct the_nilfs *nilfs;
struct nilfs_root *fsroot;
struct backing_dev_info *bdi;
__u64 cno;
int err;
nilfs = alloc_nilfs(sb->s_bdev);
if (!nilfs)
return -ENOMEM;
sb->s_fs_info = nilfs;
err = init_nilfs(nilfs, sb, (char *)data);
if (err)
goto failed_nilfs;
sb->s_op = &nilfs_sops;
sb->s_export_op = &nilfs_export_ops;
sb->s_root = NULL;
sb->s_time_gran = 1;
sb->s_max_links = NILFS_LINK_MAX;
bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info;
sb->s_bdi = bdi ? : &default_backing_dev_info;
err = load_nilfs(nilfs, sb);
if (err)
goto failed_nilfs;
cno = nilfs_last_cno(nilfs);
err = nilfs_attach_checkpoint(sb, cno, true, &fsroot);
if (err) {
printk(KERN_ERR "NILFS: error loading last checkpoint "
"(checkpoint number=%llu).\n", (unsigned long long)cno);
goto failed_unload;
}
if (!(sb->s_flags & MS_RDONLY)) {
err = nilfs_attach_log_writer(sb, fsroot);
if (err)
goto failed_checkpoint;
}
err = nilfs_get_root_dentry(sb, fsroot, &sb->s_root);
if (err)
goto failed_segctor;
nilfs_put_root(fsroot);
if (!(sb->s_flags & MS_RDONLY)) {
down_write(&nilfs->ns_sem);
nilfs_setup_super(sb, true);
up_write(&nilfs->ns_sem);
}
return 0;
failed_segctor:
nilfs_detach_log_writer(sb);
failed_checkpoint:
nilfs_put_root(fsroot);
failed_unload:
iput(nilfs->ns_sufile);
iput(nilfs->ns_cpfile);
iput(nilfs->ns_dat);
failed_nilfs:
destroy_nilfs(nilfs);
return err;
}
struct dentry *f2fs_get_parent(struct dentry *child)
{
struct qstr dotdot = {.len = 2, .name = ".."};
unsigned long ino = f2fs_inode_by_name(child->d_inode, &dotdot);
if (!ino)
return ERR_PTR(-ENOENT);
return d_obtain_alias(f2fs_iget(child->d_inode->i_sb, ino));
}
static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
struct nameidata *nd)
{
struct inode *inode = NULL;
struct f2fs_dir_entry *de;
struct page *page;
if (dentry->d_name.len > F2FS_NAME_LEN)
return ERR_PTR(-ENAMETOOLONG);
de = f2fs_find_entry(dir, &dentry->d_name, &page);
if (de) {
nid_t ino = le32_to_cpu(de->ino);
f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
inode = f2fs_iget(dir->i_sb, ino);
if (IS_ERR(inode))
return ERR_CAST(inode);
}
return d_splice_alias(inode, dentry);
}
static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode = dentry->d_inode;
struct f2fs_dir_entry *de;
struct page *page;
int err = -ENOENT;
trace_f2fs_unlink_enter(dir, dentry);
f2fs_balance_fs(sbi);
de = f2fs_find_entry(dir, &dentry->d_name, &page);
if (!de)
goto fail;
f2fs_lock_op(sbi);
err = acquire_orphan_inode(sbi);
if (err) {
f2fs_unlock_op(sbi);
f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
goto fail;
}
f2fs_delete_entry(de, page, dir, inode);
f2fs_unlock_op(sbi);
/* In order to evict this inode, we set it dirty */
mark_inode_dirty(inode);
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
fail:
trace_f2fs_unlink_exit(inode, err);
return err;
}
static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
const char *symname)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
size_t symlen = strlen(symname) + 1;
int err;
f2fs_balance_fs(sbi);
inode = f2fs_new_inode(dir, S_IFLNK | S_IRWXUGO);
if (IS_ERR(inode))
return PTR_ERR(inode);
inode->i_op = &f2fs_symlink_inode_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
if (err)
goto out;
f2fs_unlock_op(sbi);
err = page_symlink(inode, symname, symlen);
alloc_nid_done(sbi, inode->i_ino);
d_instantiate(dentry, inode);
unlock_new_inode(inode);
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
return err;
out:
handle_failed_inode(inode);
return err;
}
static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
int err;
f2fs_balance_fs(sbi);
inode = f2fs_new_inode(dir, S_IFDIR | mode);
if (IS_ERR(inode))
return PTR_ERR(inode);
inode->i_op = &f2fs_dir_inode_operations;
inode->i_fop = &f2fs_dir_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
set_inode_flag(F2FS_I(inode), FI_INC_LINK);
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
if (err)
goto out_fail;
f2fs_unlock_op(sbi);
stat_inc_inline_dir(inode);
alloc_nid_done(sbi, inode->i_ino);
d_instantiate(dentry, inode);
unlock_new_inode(inode);
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
return 0;
out_fail:
clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
handle_failed_inode(inode);
return err;
}
static int f2fs_rmdir(struct inode *dir, struct dentry *dentry)
{
struct inode *inode = dentry->d_inode;
if (f2fs_empty_dir(inode))
return f2fs_unlink(dir, dentry);
return -ENOTEMPTY;
}
static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
umode_t mode, dev_t rdev)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
int err = 0;
if (!new_valid_dev(rdev))
return -EINVAL;
f2fs_balance_fs(sbi);
inode = f2fs_new_inode(dir, mode);
if (IS_ERR(inode))
return PTR_ERR(inode);
init_special_inode(inode, inode->i_mode, rdev);
inode->i_op = &f2fs_special_inode_operations;
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
if (err)
goto out;
f2fs_unlock_op(sbi);
alloc_nid_done(sbi, inode->i_ino);
d_instantiate(dentry, inode);
unlock_new_inode(inode);
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
return 0;
out:
handle_failed_inode(inode);
return err;
}
static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(old_dir);
struct inode *old_inode = old_dentry->d_inode;
struct inode *new_inode = new_dentry->d_inode;
struct page *old_dir_page;
struct page *old_page, *new_page;
struct f2fs_dir_entry *old_dir_entry = NULL;
struct f2fs_dir_entry *old_entry;
struct f2fs_dir_entry *new_entry;
int err = -ENOENT;
f2fs_balance_fs(sbi);
old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
if (!old_entry)
goto out;
if (S_ISDIR(old_inode->i_mode)) {
err = -EIO;
old_dir_entry = f2fs_parent_dir(old_inode, &old_dir_page);
if (!old_dir_entry)
goto out_old;
}
if (new_inode) {
err = -ENOTEMPTY;
if (old_dir_entry && !f2fs_empty_dir(new_inode))
goto out_dir;
err = -ENOENT;
new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name,
&new_page);
if (!new_entry)
goto out_dir;
f2fs_lock_op(sbi);
err = acquire_orphan_inode(sbi);
if (err)
goto put_out_dir;
if (update_dent_inode(old_inode, &new_dentry->d_name)) {
release_orphan_inode(sbi);
goto put_out_dir;
}
f2fs_set_link(new_dir, new_entry, new_page, old_inode);
new_inode->i_ctime = CURRENT_TIME;
down_write(&F2FS_I(new_inode)->i_sem);
if (old_dir_entry)
drop_nlink(new_inode);
drop_nlink(new_inode);
up_write(&F2FS_I(new_inode)->i_sem);
mark_inode_dirty(new_inode);
if (!new_inode->i_nlink)
add_orphan_inode(sbi, new_inode->i_ino);
else
release_orphan_inode(sbi);
update_inode_page(old_inode);
update_inode_page(new_inode);
} else {
f2fs_lock_op(sbi);
err = f2fs_add_link(new_dentry, old_inode);
if (err) {
f2fs_unlock_op(sbi);
goto out_dir;
}
if (old_dir_entry) {
inc_nlink(new_dir);
update_inode_page(new_dir);
}
}
down_write(&F2FS_I(old_inode)->i_sem);
file_lost_pino(old_inode);
up_write(&F2FS_I(old_inode)->i_sem);
old_inode->i_ctime = CURRENT_TIME;
mark_inode_dirty(old_inode);
f2fs_delete_entry(old_entry, old_page, old_dir, NULL);
if (old_dir_entry) {
if (old_dir != new_dir) {
f2fs_set_link(old_inode, old_dir_entry,
old_dir_page, new_dir);
update_inode_page(old_inode);
} else {
f2fs_dentry_kunmap(old_inode, old_dir_page);
f2fs_put_page(old_dir_page, 0);
}
drop_nlink(old_dir);
mark_inode_dirty(old_dir);
update_inode_page(old_dir);
}
f2fs_unlock_op(sbi);
if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
f2fs_sync_fs(sbi->sb, 1);
return 0;
put_out_dir:
f2fs_unlock_op(sbi);
f2fs_dentry_kunmap(new_dir, new_page);
f2fs_put_page(new_page, 0);
out_dir:
if (old_dir_entry) {
f2fs_dentry_kunmap(old_inode, old_dir_page);
f2fs_put_page(old_dir_page, 0);
}
out_old:
f2fs_dentry_kunmap(old_dir, old_page);
f2fs_put_page(old_page, 0);
out:
return err;
}
const struct inode_operations f2fs_dir_inode_operations = {
.create = f2fs_create,
.lookup = f2fs_lookup,
.link = f2fs_link,
.unlink = f2fs_unlink,
.symlink = f2fs_symlink,
.mkdir = f2fs_mkdir,
.rmdir = f2fs_rmdir,
.mknod = f2fs_mknod,
.rename = f2fs_rename,
.getattr = f2fs_getattr,
.setattr = f2fs_setattr,
.get_acl = f2fs_get_acl,
#ifdef CONFIG_F2FS_FS_XATTR
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = f2fs_listxattr,
.removexattr = generic_removexattr,
#endif
};
const struct inode_operations f2fs_symlink_inode_operations = {
.readlink = generic_readlink,
.follow_link = page_follow_link_light,
.put_link = page_put_link,
.getattr = f2fs_getattr,
.setattr = f2fs_setattr,
#ifdef CONFIG_F2FS_FS_XATTR
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = f2fs_listxattr,
.removexattr = generic_removexattr,
#endif
};
const struct inode_operations f2fs_special_inode_operations = {
.getattr = f2fs_getattr,
.setattr = f2fs_setattr,
.get_acl = f2fs_get_acl,
#ifdef CONFIG_F2FS_FS_XATTR
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = f2fs_listxattr,
.removexattr = generic_removexattr,
#endif
};
int ext4_inline_data_truncate(struct inode *inode, int *has_inline)
{
handle_t *handle;
int inline_size, value_len, needed_blocks, no_expand, err = 0;
size_t i_size;
void *value = NULL;
struct ext4_xattr_ibody_find is = {
.s = { .not_found = -ENODATA, },
};
struct ext4_xattr_info i = {
.name_index = EXT4_XATTR_INDEX_SYSTEM,
.name = EXT4_XATTR_SYSTEM_DATA,
};
needed_blocks = ext4_writepage_trans_blocks(inode);
handle = ext4_journal_start(inode, EXT4_HT_INODE, needed_blocks);
if (IS_ERR(handle))
return PTR_ERR(handle);
ext4_write_lock_xattr(inode, &no_expand);
if (!ext4_has_inline_data(inode)) {
*has_inline = 0;
ext4_journal_stop(handle);
return 0;
}
if ((err = ext4_orphan_add(handle, inode)) != 0)
goto out;
if ((err = ext4_get_inode_loc(inode, &is.iloc)) != 0)
goto out;
down_write(&EXT4_I(inode)->i_data_sem);
i_size = inode->i_size;
inline_size = ext4_get_inline_size(inode);
EXT4_I(inode)->i_disksize = i_size;
if (i_size < inline_size) {
/* Clear the content in the xattr space. */
if (inline_size > EXT4_MIN_INLINE_DATA_SIZE) {
if ((err = ext4_xattr_ibody_find(inode, &i, &is)) != 0)
goto out_error;
BUG_ON(is.s.not_found);
value_len = le32_to_cpu(is.s.here->e_value_size);
value = kmalloc(value_len, GFP_NOFS);
if (!value) {
err = -ENOMEM;
goto out_error;
}
err = ext4_xattr_ibody_get(inode, i.name_index,
i.name, value, value_len);
if (err <= 0)
goto out_error;
i.value = value;
i.value_len = i_size > EXT4_MIN_INLINE_DATA_SIZE ?
i_size - EXT4_MIN_INLINE_DATA_SIZE : 0;
err = ext4_xattr_ibody_inline_set(handle, inode,
&i, &is);
if (err)
goto out_error;
}
/* Clear the content within i_blocks. */
if (i_size < EXT4_MIN_INLINE_DATA_SIZE) {
void *p = (void *) ext4_raw_inode(&is.iloc)->i_block;
memset(p + i_size, 0,
EXT4_MIN_INLINE_DATA_SIZE - i_size);
}
EXT4_I(inode)->i_inline_size = i_size <
EXT4_MIN_INLINE_DATA_SIZE ?
EXT4_MIN_INLINE_DATA_SIZE : i_size;
}
out_error:
up_write(&EXT4_I(inode)->i_data_sem);
out:
brelse(is.iloc.bh);
ext4_write_unlock_xattr(inode, &no_expand);
kfree(value);
if (inode->i_nlink)
ext4_orphan_del(handle, inode);
if (err == 0) {
inode->i_mtime = inode->i_ctime = current_time(inode);
err = ext4_mark_inode_dirty(handle, inode);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
}
ext4_journal_stop(handle);
return err;
}
/**
* nilfs_fill_super() - initialize a super block instance
* @sb: super_block
* @data: mount options
* @silent: silent mode flag
* @nilfs: the_nilfs struct
*
* This function is called exclusively by nilfs->ns_mount_mutex.
* So, the recovery process is protected from other simultaneous mounts.
*/
static int
nilfs_fill_super(struct super_block *sb, void *data, int silent,
struct the_nilfs *nilfs)
{
struct nilfs_sb_info *sbi;
struct inode *root;
__u64 cno;
int err;
sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
if (!sbi)
return -ENOMEM;
sb->s_fs_info = sbi;
get_nilfs(nilfs);
sbi->s_nilfs = nilfs;
sbi->s_super = sb;
atomic_set(&sbi->s_count, 1);
err = init_nilfs(nilfs, sbi, (char *)data);
if (err)
goto failed_sbi;
spin_lock_init(&sbi->s_inode_lock);
INIT_LIST_HEAD(&sbi->s_dirty_files);
INIT_LIST_HEAD(&sbi->s_list);
/*
* Following initialization is overlapped because
* nilfs_sb_info structure has been cleared at the beginning.
* But we reserve them to keep our interest and make ready
* for the future change.
*/
get_random_bytes(&sbi->s_next_generation,
sizeof(sbi->s_next_generation));
spin_lock_init(&sbi->s_next_gen_lock);
sb->s_op = &nilfs_sops;
sb->s_export_op = &nilfs_export_ops;
sb->s_root = NULL;
sb->s_time_gran = 1;
sb->s_bdi = nilfs->ns_bdi;
err = load_nilfs(nilfs, sbi);
if (err)
goto failed_sbi;
cno = nilfs_last_cno(nilfs);
if (sb->s_flags & MS_RDONLY) {
if (nilfs_test_opt(sbi, SNAPSHOT)) {
down_read(&nilfs->ns_segctor_sem);
err = nilfs_cpfile_is_snapshot(nilfs->ns_cpfile,
sbi->s_snapshot_cno);
up_read(&nilfs->ns_segctor_sem);
if (err < 0) {
if (err == -ENOENT)
err = -EINVAL;
goto failed_sbi;
}
if (!err) {
printk(KERN_ERR
"NILFS: The specified checkpoint is "
"not a snapshot "
"(checkpoint number=%llu).\n",
(unsigned long long)sbi->s_snapshot_cno);
err = -EINVAL;
goto failed_sbi;
}
cno = sbi->s_snapshot_cno;
}
}
err = nilfs_attach_checkpoint(sbi, cno);
if (err) {
printk(KERN_ERR "NILFS: error loading a checkpoint"
" (checkpoint number=%llu).\n", (unsigned long long)cno);
goto failed_sbi;
}
if (!(sb->s_flags & MS_RDONLY)) {
err = nilfs_attach_segment_constructor(sbi);
if (err)
goto failed_checkpoint;
}
root = nilfs_iget(sb, NILFS_ROOT_INO);
if (IS_ERR(root)) {
printk(KERN_ERR "NILFS: get root inode failed\n");
err = PTR_ERR(root);
goto failed_segctor;
}
if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
iput(root);
printk(KERN_ERR "NILFS: corrupt root inode.\n");
err = -EINVAL;
goto failed_segctor;
}
sb->s_root = d_alloc_root(root);
if (!sb->s_root) {
iput(root);
printk(KERN_ERR "NILFS: get root dentry failed\n");
err = -ENOMEM;
goto failed_segctor;
}
if (!(sb->s_flags & MS_RDONLY)) {
down_write(&nilfs->ns_sem);
nilfs_setup_super(sbi);
up_write(&nilfs->ns_sem);
}
down_write(&nilfs->ns_super_sem);
if (!nilfs_test_opt(sbi, SNAPSHOT))
nilfs->ns_current = sbi;
up_write(&nilfs->ns_super_sem);
return 0;
failed_segctor:
nilfs_detach_segment_constructor(sbi);
failed_checkpoint:
nilfs_detach_checkpoint(sbi);
failed_sbi:
put_nilfs(nilfs);
sb->s_fs_info = NULL;
nilfs_put_sbinfo(sbi);
return err;
}
/**
* Swap the information from the given @inode and the inode
* EXT4_BOOT_LOADER_INO. It will basically swap i_data and all other
* important fields of the inodes.
*
* @sb: the super block of the filesystem
* @inode: the inode to swap with EXT4_BOOT_LOADER_INO
*
*/
static long swap_inode_boot_loader(struct super_block *sb,
struct inode *inode)
{
handle_t *handle;
int err;
struct inode *inode_bl;
struct ext4_inode_info *ei_bl;
qsize_t size, size_bl, diff;
blkcnt_t blocks;
unsigned short bytes;
inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO, EXT4_IGET_SPECIAL);
if (IS_ERR(inode_bl))
return PTR_ERR(inode_bl);
ei_bl = EXT4_I(inode_bl);
/* Protect orig inodes against a truncate and make sure,
* that only 1 swap_inode_boot_loader is running. */
lock_two_nondirectories(inode, inode_bl);
if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode) ||
IS_SWAPFILE(inode) || IS_ENCRYPTED(inode) ||
(EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) ||
ext4_has_inline_data(inode)) {
err = -EINVAL;
goto journal_err_out;
}
if (IS_RDONLY(inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) ||
!inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) {
err = -EPERM;
goto journal_err_out;
}
down_write(&EXT4_I(inode)->i_mmap_sem);
err = filemap_write_and_wait(inode->i_mapping);
if (err)
goto err_out;
err = filemap_write_and_wait(inode_bl->i_mapping);
if (err)
goto err_out;
/* Wait for all existing dio workers */
inode_dio_wait(inode);
inode_dio_wait(inode_bl);
truncate_inode_pages(&inode->i_data, 0);
truncate_inode_pages(&inode_bl->i_data, 0);
handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2);
if (IS_ERR(handle)) {
err = -EINVAL;
goto err_out;
}
/* Protect extent tree against block allocations via delalloc */
ext4_double_down_write_data_sem(inode, inode_bl);
if (inode_bl->i_nlink == 0) {
/* this inode has never been used as a BOOT_LOADER */
set_nlink(inode_bl, 1);
i_uid_write(inode_bl, 0);
i_gid_write(inode_bl, 0);
inode_bl->i_flags = 0;
ei_bl->i_flags = 0;
inode_set_iversion(inode_bl, 1);
i_size_write(inode_bl, 0);
inode_bl->i_mode = S_IFREG;
if (ext4_has_feature_extents(sb)) {
ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS);
ext4_ext_tree_init(handle, inode_bl);
} else
memset(ei_bl->i_data, 0, sizeof(ei_bl->i_data));
}
err = dquot_initialize(inode);
if (err)
goto err_out1;
size = (qsize_t)(inode->i_blocks) * (1 << 9) + inode->i_bytes;
size_bl = (qsize_t)(inode_bl->i_blocks) * (1 << 9) + inode_bl->i_bytes;
diff = size - size_bl;
swap_inode_data(inode, inode_bl);
inode->i_ctime = inode_bl->i_ctime = current_time(inode);
inode->i_generation = prandom_u32();
inode_bl->i_generation = prandom_u32();
reset_inode_seed(inode);
reset_inode_seed(inode_bl);
ext4_discard_preallocations(inode);
err = ext4_mark_inode_dirty(handle, inode);
if (err < 0) {
/* No need to update quota information. */
ext4_warning(inode->i_sb,
"couldn't mark inode #%lu dirty (err %d)",
inode->i_ino, err);
/* Revert all changes: */
swap_inode_data(inode, inode_bl);
ext4_mark_inode_dirty(handle, inode);
goto err_out1;
}
blocks = inode_bl->i_blocks;
bytes = inode_bl->i_bytes;
inode_bl->i_blocks = inode->i_blocks;
inode_bl->i_bytes = inode->i_bytes;
err = ext4_mark_inode_dirty(handle, inode_bl);
if (err < 0) {
/* No need to update quota information. */
ext4_warning(inode_bl->i_sb,
"couldn't mark inode #%lu dirty (err %d)",
inode_bl->i_ino, err);
goto revert;
}
/* Bootloader inode should not be counted into quota information. */
if (diff > 0)
dquot_free_space(inode, diff);
else
err = dquot_alloc_space(inode, -1 * diff);
if (err < 0) {
revert:
/* Revert all changes: */
inode_bl->i_blocks = blocks;
inode_bl->i_bytes = bytes;
swap_inode_data(inode, inode_bl);
ext4_mark_inode_dirty(handle, inode);
ext4_mark_inode_dirty(handle, inode_bl);
}
err_out1:
ext4_journal_stop(handle);
ext4_double_up_write_data_sem(inode, inode_bl);
err_out:
up_write(&EXT4_I(inode)->i_mmap_sem);
journal_err_out:
unlock_two_nondirectories(inode, inode_bl);
iput(inode_bl);
return err;
}
/**
* nilfs_fill_super() - initialize a super block instance
* @sb: super_block
* @data: mount options
* @silent: silent mode flag
*
* This function is called exclusively by nilfs->ns_mount_mutex.
* So, the recovery process is protected from other simultaneous mounts.
*/
static int
nilfs_fill_super(struct super_block *sb, void *data, int silent)
{
struct the_nilfs *nilfs;
struct nilfs_root *fsroot;
__u64 cno;
int err;
nilfs = alloc_nilfs(sb);
if (!nilfs)
return -ENOMEM;
sb->s_fs_info = nilfs;
err = init_nilfs(nilfs, sb, (char *)data);
if (err)
goto failed_nilfs;
sb->s_op = &nilfs_sops;
sb->s_export_op = &nilfs_export_ops;
sb->s_root = NULL;
sb->s_time_gran = 1;
sb->s_max_links = NILFS_LINK_MAX;
sb->s_bdi = bdi_get(sb->s_bdev->bd_bdi);
err = load_nilfs(nilfs, sb);
if (err)
goto failed_nilfs;
cno = nilfs_last_cno(nilfs);
err = nilfs_attach_checkpoint(sb, cno, true, &fsroot);
if (err) {
nilfs_msg(sb, KERN_ERR,
"error %d while loading last checkpoint (checkpoint number=%llu)",
err, (unsigned long long)cno);
goto failed_unload;
}
if (!sb_rdonly(sb)) {
err = nilfs_attach_log_writer(sb, fsroot);
if (err)
goto failed_checkpoint;
}
err = nilfs_get_root_dentry(sb, fsroot, &sb->s_root);
if (err)
goto failed_segctor;
nilfs_put_root(fsroot);
if (!sb_rdonly(sb)) {
down_write(&nilfs->ns_sem);
nilfs_setup_super(sb, true);
up_write(&nilfs->ns_sem);
}
return 0;
failed_segctor:
nilfs_detach_log_writer(sb);
failed_checkpoint:
nilfs_put_root(fsroot);
failed_unload:
iput(nilfs->ns_sufile);
iput(nilfs->ns_cpfile);
iput(nilfs->ns_dat);
failed_nilfs:
destroy_nilfs(nilfs);
return err;
}
/* Note: HP-UX just uses the old suser() function to check perms
* in this system call. We'll use capable(CAP_SYS_ADMIN).
*/
int hpux_utssys(char *ubuf, int n, int type)
{
int len;
int error;
switch( type ) {
case 0:
/* uname(): */
return( hpux_uname( (struct hpux_utsname *)ubuf ) );
break ;
case 1:
/* Obsolete (used to be umask().) */
return -EFAULT ;
break ;
case 2:
/* ustat(): */
return( hpux_ustat((dev_t)n, (struct hpux_ustat *)ubuf) );
break ;
case 3:
/* setuname():
*
* On linux (unlike HP-UX), utsname.nodename
* is the same as the hostname.
*
* sys_sethostname() is defined in linux/kernel/sys.c.
*/
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
/* Unlike Linux, HP-UX returns an error if n==0: */
if ( n <= 0 )
return -EINVAL ;
/* Unlike Linux, HP-UX truncates it if n is too big: */
len = (n <= __NEW_UTS_LEN) ? n : __NEW_UTS_LEN ;
return( sys_sethostname(ubuf, len) );
break ;
case 4:
/* sethostname():
*
* sys_sethostname() is defined in linux/kernel/sys.c.
*/
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
/* Unlike Linux, HP-UX returns an error if n==0: */
if ( n <= 0 )
return -EINVAL ;
/* Unlike Linux, HP-UX truncates it if n is too big: */
len = (n <= __NEW_UTS_LEN) ? n : __NEW_UTS_LEN ;
return( sys_sethostname(ubuf, len) );
break ;
case 5:
/* gethostname():
*
* sys_gethostname() is defined in linux/kernel/sys.c.
*/
/* Unlike Linux, HP-UX returns an error if n==0: */
if ( n <= 0 )
return -EINVAL ;
return( sys_gethostname(ubuf, n) );
break ;
case 6:
/* Supposedly called from setuname() in libc.
* TODO: When and why is this called?
* Is it ever even called?
*
* This code should look a lot like sys_sethostname(),
* defined in linux/kernel/sys.c. If that gets updated,
* update this code similarly.
*/
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
/* Unlike Linux, HP-UX returns an error if n==0: */
if ( n <= 0 )
return -EINVAL ;
/* Unlike Linux, HP-UX truncates it if n is too big: */
len = (n <= __NEW_UTS_LEN) ? n : __NEW_UTS_LEN ;
/**/
/* TODO: print a warning about using this? */
down_write(&uts_sem);
error = -EFAULT;
if (!copy_from_user(system_utsname.sysname, ubuf, len)) {
system_utsname.sysname[len] = 0;
error = 0;
}
up_write(&uts_sem);
return error;
break ;
case 7:
/* Sets utsname.release, if you're allowed.
* Undocumented. Used by swinstall to change the
* OS version, during OS updates. Yuck!!!
*
* This code should look a lot like sys_sethostname()
* in linux/kernel/sys.c. If that gets updated, update
* this code similarly.
*/
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
/* Unlike Linux, HP-UX returns an error if n==0: */
if ( n <= 0 )
return -EINVAL ;
/* Unlike Linux, HP-UX truncates it if n is too big: */
len = (n <= __NEW_UTS_LEN) ? n : __NEW_UTS_LEN ;
/**/
/* TODO: print a warning about this? */
down_write(&uts_sem);
error = -EFAULT;
if (!copy_from_user(system_utsname.release, ubuf, len)) {
system_utsname.release[len] = 0;
error = 0;
}
up_write(&uts_sem);
return error;
break ;
default:
/* This system call returns -EFAULT if given an unknown type.
* Why not -EINVAL? I don't know, it's just not what they did.
*/
return -EFAULT ;
}
}
/**
* nilfs_resize_fs - resize the filesystem
* @sb: super block instance
* @newsize: new size of the filesystem (in bytes)
*/
int nilfs_resize_fs(struct super_block *sb, __u64 newsize)
{
struct the_nilfs *nilfs = sb->s_fs_info;
struct nilfs_super_block **sbp;
__u64 devsize, newnsegs;
loff_t sb2off;
int ret;
ret = -ERANGE;
devsize = i_size_read(sb->s_bdev->bd_inode);
if (newsize > devsize)
goto out;
/*
* Write lock is required to protect some functions depending
* on the number of segments, the number of reserved segments,
* and so forth.
*/
down_write(&nilfs->ns_segctor_sem);
sb2off = NILFS_SB2_OFFSET_BYTES(newsize);
newnsegs = sb2off >> nilfs->ns_blocksize_bits;
do_div(newnsegs, nilfs->ns_blocks_per_segment);
ret = nilfs_sufile_resize(nilfs->ns_sufile, newnsegs);
up_write(&nilfs->ns_segctor_sem);
if (ret < 0)
goto out;
ret = nilfs_construct_segment(sb);
if (ret < 0)
goto out;
down_write(&nilfs->ns_sem);
nilfs_move_2nd_super(sb, sb2off);
ret = -EIO;
sbp = nilfs_prepare_super(sb, 0);
if (likely(sbp)) {
nilfs_set_log_cursor(sbp[0], nilfs);
/*
* Drop NILFS_RESIZE_FS flag for compatibility with
* mount-time resize which may be implemented in a
* future release.
*/
sbp[0]->s_state = cpu_to_le16(le16_to_cpu(sbp[0]->s_state) &
~NILFS_RESIZE_FS);
sbp[0]->s_dev_size = cpu_to_le64(newsize);
sbp[0]->s_nsegments = cpu_to_le64(nilfs->ns_nsegments);
if (sbp[1])
memcpy(sbp[1], sbp[0], nilfs->ns_sbsize);
ret = nilfs_commit_super(sb, NILFS_SB_COMMIT_ALL);
}
up_write(&nilfs->ns_sem);
/*
* Reset the range of allocatable segments last. This order
* is important in the case of expansion because the secondary
* superblock must be protected from log write until migration
* completes.
*/
if (!ret)
nilfs_sufile_set_alloc_range(nilfs->ns_sufile, 0, newnsegs - 1);
out:
return ret;
}
/*
* Caller should grab and release a rwsem by calling f2fs_lock_op() and
* f2fs_unlock_op().
*/
int __f2fs_add_link(struct inode *dir, const struct qstr *name,
struct inode *inode)
{
unsigned int bit_pos;
unsigned int level;
unsigned int current_depth;
unsigned long bidx, block;
f2fs_hash_t dentry_hash;
struct f2fs_dir_entry *de;
unsigned int nbucket, nblock;
size_t namelen = name->len;
struct page *dentry_page = NULL;
struct f2fs_dentry_block *dentry_blk = NULL;
int slots = GET_DENTRY_SLOTS(namelen);
struct page *page;
int err = 0;
int i;
dentry_hash = f2fs_dentry_hash(name);
level = 0;
current_depth = F2FS_I(dir)->i_current_depth;
if (F2FS_I(dir)->chash == dentry_hash) {
level = F2FS_I(dir)->clevel;
F2FS_I(dir)->chash = 0;
}
start:
if (unlikely(current_depth == MAX_DIR_HASH_DEPTH))
return -ENOSPC;
/* Increase the depth, if required */
if (level == current_depth)
++current_depth;
nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level);
nblock = bucket_blocks(level);
bidx = dir_block_index(level, F2FS_I(dir)->i_dir_level,
(le32_to_cpu(dentry_hash) % nbucket));
for (block = bidx; block <= (bidx + nblock - 1); block++) {
dentry_page = get_new_data_page(dir, NULL, block, true);
if (IS_ERR(dentry_page))
return PTR_ERR(dentry_page);
dentry_blk = kmap(dentry_page);
bit_pos = room_for_filename(dentry_blk, slots);
if (bit_pos < NR_DENTRY_IN_BLOCK)
goto add_dentry;
kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
}
/* Move to next level to find the empty slot for new dentry */
++level;
goto start;
add_dentry:
f2fs_wait_on_page_writeback(dentry_page, DATA);
down_write(&F2FS_I(inode)->i_sem);
page = init_inode_metadata(inode, dir, name);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto fail;
}
de = &dentry_blk->dentry[bit_pos];
de->hash_code = dentry_hash;
de->name_len = cpu_to_le16(namelen);
memcpy(dentry_blk->filename[bit_pos], name->name, name->len);
de->ino = cpu_to_le32(inode->i_ino);
set_de_type(de, inode);
for (i = 0; i < slots; i++)
test_and_set_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap);
set_page_dirty(dentry_page);
/* we don't need to mark_inode_dirty now */
F2FS_I(inode)->i_pino = dir->i_ino;
update_inode(inode, page);
f2fs_put_page(page, 1);
update_parent_metadata(dir, inode, current_depth);
fail:
up_write(&F2FS_I(inode)->i_sem);
if (is_inode_flag_set(F2FS_I(dir), FI_UPDATE_DIR)) {
update_inode_page(dir);
clear_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
}
kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
return err;
}
static inline int dup_mmap(struct mm_struct * mm, struct mm_struct * oldmm)
{
struct vm_area_struct * mpnt, *tmp, **pprev;
struct rb_node **rb_link, *rb_parent;
int retval;
unsigned long charge;
struct mempolicy *pol;
down_write(&oldmm->mmap_sem);
flush_cache_mm(current->mm);
mm->locked_vm = 0;
mm->mmap = NULL;
mm->mmap_cache = NULL;
mm->free_area_cache = oldmm->mmap_base;
mm->map_count = 0;
mm->rss = 0;
mm->anon_rss = 0;
cpus_clear(mm->cpu_vm_mask);
mm->mm_rb = RB_ROOT;
rb_link = &mm->mm_rb.rb_node;
rb_parent = NULL;
pprev = &mm->mmap;
for (mpnt = current->mm->mmap ; mpnt ; mpnt = mpnt->vm_next) {
struct file *file;
if (mpnt->vm_flags & VM_DONTCOPY) {
__vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file,
-vma_pages(mpnt));
continue;
}
charge = 0;
if (mpnt->vm_flags & VM_ACCOUNT) {
unsigned int len = (mpnt->vm_end - mpnt->vm_start) >> PAGE_SHIFT;
if (security_vm_enough_memory(len))
goto fail_nomem;
charge = len;
}
tmp = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
if (!tmp)
goto fail_nomem;
*tmp = *mpnt;
pol = mpol_copy(vma_policy(mpnt));
retval = PTR_ERR(pol);
if (IS_ERR(pol))
goto fail_nomem_policy;
vma_set_policy(tmp, pol);
tmp->vm_flags &= ~VM_LOCKED;
tmp->vm_mm = mm;
tmp->vm_next = NULL;
anon_vma_link(tmp);
file = tmp->vm_file;
if (file) {
struct inode *inode = file->f_dentry->d_inode;
get_file(file);
if (tmp->vm_flags & VM_DENYWRITE)
atomic_dec(&inode->i_writecount);
/* insert tmp into the share list, just after mpnt */
spin_lock(&file->f_mapping->i_mmap_lock);
tmp->vm_truncate_count = mpnt->vm_truncate_count;
flush_dcache_mmap_lock(file->f_mapping);
vma_prio_tree_add(tmp, mpnt);
flush_dcache_mmap_unlock(file->f_mapping);
spin_unlock(&file->f_mapping->i_mmap_lock);
}
/*
* Link in the new vma and copy the page table entries:
* link in first so that swapoff can see swap entries,
* and try_to_unmap_one's find_vma find the new vma.
*/
spin_lock(&mm->page_table_lock);
*pprev = tmp;
pprev = &tmp->vm_next;
__vma_link_rb(mm, tmp, rb_link, rb_parent);
rb_link = &tmp->vm_rb.rb_right;
rb_parent = &tmp->vm_rb;
mm->map_count++;
retval = copy_page_range(mm, current->mm, tmp);
spin_unlock(&mm->page_table_lock);
if (tmp->vm_ops && tmp->vm_ops->open)
tmp->vm_ops->open(tmp);
if (retval)
goto out;
}
/* returns negative on error; 0 if success; 1 if success & log destroyed */
int llog_cancel_rec(const struct lu_env *env, struct llog_handle *loghandle,
int index)
{
struct llog_thread_info *lgi = llog_info(env);
struct dt_device *dt;
struct llog_log_hdr *llh = loghandle->lgh_hdr;
struct thandle *th;
int rc;
int rc1;
bool subtract_count = false;
ENTRY;
CDEBUG(D_RPCTRACE, "Canceling %d in log "DOSTID"\n", index,
POSTID(&loghandle->lgh_id.lgl_oi));
if (index == 0) {
CERROR("Can't cancel index 0 which is header\n");
RETURN(-EINVAL);
}
LASSERT(loghandle != NULL);
LASSERT(loghandle->lgh_ctxt != NULL);
LASSERT(loghandle->lgh_obj != NULL);
dt = lu2dt_dev(loghandle->lgh_obj->do_lu.lo_dev);
th = dt_trans_create(env, dt);
if (IS_ERR(th))
RETURN(PTR_ERR(th));
rc = llog_declare_write_rec(env, loghandle, &llh->llh_hdr, index, th);
if (rc < 0)
GOTO(out_trans, rc);
if ((llh->llh_flags & LLOG_F_ZAP_WHEN_EMPTY)) {
rc = llog_declare_destroy(env, loghandle, th);
if (rc < 0)
GOTO(out_trans, rc);
}
th->th_wait_submit = 1;
rc = dt_trans_start_local(env, dt, th);
if (rc < 0)
GOTO(out_trans, rc);
down_write(&loghandle->lgh_lock);
/* clear bitmap */
mutex_lock(&loghandle->lgh_hdr_mutex);
if (!ext2_clear_bit(index, LLOG_HDR_BITMAP(llh))) {
CDEBUG(D_RPCTRACE, "Catalog index %u already clear?\n", index);
GOTO(out_unlock, rc);
}
loghandle->lgh_hdr->llh_count--;
subtract_count = true;
/* Pass this index to llog_osd_write_rec(), which will use the index
* to only update the necesary bitmap. */
lgi->lgi_cookie.lgc_index = index;
/* update header */
rc = llog_write_rec(env, loghandle, &llh->llh_hdr, &lgi->lgi_cookie,
LLOG_HEADER_IDX, th);
if (rc != 0)
GOTO(out_unlock, rc);
if ((llh->llh_flags & LLOG_F_ZAP_WHEN_EMPTY) &&
(llh->llh_count == 1) &&
((loghandle->lgh_last_idx == LLOG_HDR_BITMAP_SIZE(llh) - 1) ||
(loghandle->u.phd.phd_cat_handle != NULL &&
loghandle->u.phd.phd_cat_handle->u.chd.chd_current_log !=
loghandle))) {
/* never try to destroy it again */
llh->llh_flags &= ~LLOG_F_ZAP_WHEN_EMPTY;
rc = llog_trans_destroy(env, loghandle, th);
if (rc < 0) {
/* Sigh, can not destroy the final plain llog, but
* the bitmap has been clearly, so the record can not
* be accessed anymore, let's return 0 for now, and
* the orphan will be handled by LFSCK. */
CERROR("%s: can't destroy empty llog #"DOSTID
"#%08x: rc = %d\n",
loghandle->lgh_ctxt->loc_obd->obd_name,
POSTID(&loghandle->lgh_id.lgl_oi),
loghandle->lgh_id.lgl_ogen, rc);
GOTO(out_unlock, rc);
}
rc = LLOG_DEL_PLAIN;
}
out_unlock:
mutex_unlock(&loghandle->lgh_hdr_mutex);
up_write(&loghandle->lgh_lock);
out_trans:
rc1 = dt_trans_stop(env, dt, th);
if (rc == 0)
rc = rc1;
if (rc < 0 && subtract_count) {
mutex_lock(&loghandle->lgh_hdr_mutex);
loghandle->lgh_hdr->llh_count++;
ext2_set_bit(index, LLOG_HDR_BITMAP(llh));
mutex_unlock(&loghandle->lgh_hdr_mutex);
}
RETURN(rc);
}
static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(old_dir);
struct inode *old_inode = d_inode(old_dentry);
struct inode *new_inode = d_inode(new_dentry);
struct inode *whiteout = NULL;
struct page *old_dir_page;
struct page *old_page, *new_page = NULL;
struct f2fs_dir_entry *old_dir_entry = NULL;
struct f2fs_dir_entry *old_entry;
struct f2fs_dir_entry *new_entry;
bool is_old_inline = f2fs_has_inline_dentry(old_dir);
int err = -ENOENT;
if ((old_dir != new_dir) && f2fs_encrypted_inode(new_dir) &&
!fscrypt_has_permitted_context(new_dir, old_inode)) {
err = -EPERM;
goto out;
}
old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
if (!old_entry) {
if (IS_ERR(old_page))
err = PTR_ERR(old_page);
goto out;
}
if (S_ISDIR(old_inode->i_mode)) {
old_dir_entry = f2fs_parent_dir(old_inode, &old_dir_page);
if (!old_dir_entry) {
if (IS_ERR(old_dir_page))
err = PTR_ERR(old_dir_page);
goto out_old;
}
}
if (flags & RENAME_WHITEOUT) {
err = f2fs_create_whiteout(old_dir, &whiteout);
if (err)
goto out_dir;
}
if (new_inode) {
err = -ENOTEMPTY;
if (old_dir_entry && !f2fs_empty_dir(new_inode))
goto out_whiteout;
err = -ENOENT;
new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name,
&new_page);
if (!new_entry) {
if (IS_ERR(new_page))
err = PTR_ERR(new_page);
goto out_whiteout;
}
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
err = acquire_orphan_inode(sbi);
if (err)
goto put_out_dir;
err = update_dent_inode(old_inode, new_inode,
&new_dentry->d_name);
if (err) {
release_orphan_inode(sbi);
goto put_out_dir;
}
f2fs_set_link(new_dir, new_entry, new_page, old_inode);
new_inode->i_ctime = current_time(new_inode);
down_write(&F2FS_I(new_inode)->i_sem);
if (old_dir_entry)
f2fs_i_links_write(new_inode, false);
f2fs_i_links_write(new_inode, false);
up_write(&F2FS_I(new_inode)->i_sem);
if (!new_inode->i_nlink)
add_orphan_inode(new_inode);
else
release_orphan_inode(sbi);
} else {
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
err = f2fs_add_link(new_dentry, old_inode);
if (err) {
f2fs_unlock_op(sbi);
goto out_whiteout;
}
if (old_dir_entry)
f2fs_i_links_write(new_dir, true);
/*
* old entry and new entry can locate in the same inline
* dentry in inode, when attaching new entry in inline dentry,
* it could force inline dentry conversion, after that,
* old_entry and old_page will point to wrong address, in
* order to avoid this, let's do the check and update here.
*/
if (is_old_inline && !f2fs_has_inline_dentry(old_dir)) {
f2fs_put_page(old_page, 0);
old_page = NULL;
old_entry = f2fs_find_entry(old_dir,
&old_dentry->d_name, &old_page);
if (!old_entry) {
err = -ENOENT;
if (IS_ERR(old_page))
err = PTR_ERR(old_page);
f2fs_unlock_op(sbi);
goto out_whiteout;
}
}
}
down_write(&F2FS_I(old_inode)->i_sem);
file_lost_pino(old_inode);
if (new_inode && file_enc_name(new_inode))
file_set_enc_name(old_inode);
up_write(&F2FS_I(old_inode)->i_sem);
old_inode->i_ctime = current_time(old_inode);
f2fs_mark_inode_dirty_sync(old_inode);
f2fs_delete_entry(old_entry, old_page, old_dir, NULL);
if (whiteout) {
whiteout->i_state |= I_LINKABLE;
set_inode_flag(whiteout, FI_INC_LINK);
err = f2fs_add_link(old_dentry, whiteout);
if (err)
goto put_out_dir;
whiteout->i_state &= ~I_LINKABLE;
iput(whiteout);
}
if (old_dir_entry) {
if (old_dir != new_dir && !whiteout) {
f2fs_set_link(old_inode, old_dir_entry,
old_dir_page, new_dir);
} else {
f2fs_dentry_kunmap(old_inode, old_dir_page);
f2fs_put_page(old_dir_page, 0);
}
f2fs_i_links_write(old_dir, false);
}
f2fs_unlock_op(sbi);
if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
f2fs_sync_fs(sbi->sb, 1);
return 0;
put_out_dir:
f2fs_unlock_op(sbi);
if (new_page) {
f2fs_dentry_kunmap(new_dir, new_page);
f2fs_put_page(new_page, 0);
}
out_whiteout:
if (whiteout)
iput(whiteout);
out_dir:
if (old_dir_entry) {
f2fs_dentry_kunmap(old_inode, old_dir_page);
f2fs_put_page(old_dir_page, 0);
}
out_old:
f2fs_dentry_kunmap(old_dir, old_page);
f2fs_put_page(old_page, 0);
out:
return err;
}
/*
* inode->i_mutex: down
*/
int
reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th,
struct inode *inode, const char *name,
const void *buffer, size_t buffer_size, int flags)
{
int err = 0;
struct dentry *dentry;
struct page *page;
char *data;
size_t file_pos = 0;
size_t buffer_pos = 0;
size_t new_size;
__u32 xahash = 0;
if (get_inode_sd_version(inode) == STAT_DATA_V1)
return -EOPNOTSUPP;
reiserfs_write_unlock(inode->i_sb);
if (!buffer) {
err = lookup_and_delete_xattr(inode, name);
reiserfs_write_lock(inode->i_sb);
return err;
}
dentry = xattr_lookup(inode, name, flags);
if (IS_ERR(dentry)) {
reiserfs_write_lock(inode->i_sb);
return PTR_ERR(dentry);
}
down_write(&REISERFS_I(inode)->i_xattr_sem);
reiserfs_write_lock(inode->i_sb);
xahash = xattr_hash(buffer, buffer_size);
while (buffer_pos < buffer_size || buffer_pos == 0) {
size_t chunk;
size_t skip = 0;
size_t page_offset = (file_pos & (PAGE_CACHE_SIZE - 1));
if (buffer_size - buffer_pos > PAGE_CACHE_SIZE)
chunk = PAGE_CACHE_SIZE;
else
chunk = buffer_size - buffer_pos;
page = reiserfs_get_page(dentry->d_inode, file_pos);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto out_unlock;
}
lock_page(page);
data = page_address(page);
if (file_pos == 0) {
struct reiserfs_xattr_header *rxh;
skip = file_pos = sizeof(struct reiserfs_xattr_header);
if (chunk + skip > PAGE_CACHE_SIZE)
chunk = PAGE_CACHE_SIZE - skip;
rxh = (struct reiserfs_xattr_header *)data;
rxh->h_magic = cpu_to_le32(REISERFS_XATTR_MAGIC);
rxh->h_hash = cpu_to_le32(xahash);
}
err = __reiserfs_write_begin(page, page_offset, chunk + skip);
if (!err) {
if (buffer)
memcpy(data + skip, buffer + buffer_pos, chunk);
err = reiserfs_commit_write(NULL, page, page_offset,
page_offset + chunk +
skip);
}
unlock_page(page);
reiserfs_put_page(page);
buffer_pos += chunk;
file_pos += chunk;
skip = 0;
if (err || buffer_size == 0 || !buffer)
break;
}
new_size = buffer_size + sizeof(struct reiserfs_xattr_header);
if (!err && new_size < i_size_read(dentry->d_inode)) {
struct iattr newattrs = {
.ia_ctime = current_fs_time(inode->i_sb),
.ia_size = new_size,
.ia_valid = ATTR_SIZE | ATTR_CTIME,
};
reiserfs_write_unlock(inode->i_sb);
mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_XATTR);
inode_dio_wait(dentry->d_inode);
reiserfs_write_lock(inode->i_sb);
err = reiserfs_setattr(dentry, &newattrs);
mutex_unlock(&dentry->d_inode->i_mutex);
} else
update_ctime(inode);
out_unlock:
up_write(&REISERFS_I(inode)->i_xattr_sem);
dput(dentry);
return err;
}
void
ia64_elf32_init (struct pt_regs *regs)
{
struct vm_area_struct *vma;
/*
* Map GDT below 4GB, where the processor can find it. We need to map
* it with privilege level 3 because the IVE uses non-privileged accesses to these
* tables. IA-32 segmentation is used to protect against IA-32 accesses to them.
*/
vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
if (vma) {
vma->vm_mm = current->mm;
vma->vm_start = IA32_GDT_OFFSET;
vma->vm_end = vma->vm_start + PAGE_SIZE;
vma->vm_page_prot = PAGE_SHARED;
vma->vm_flags = VM_READ|VM_MAYREAD|VM_RESERVED;
vma->vm_ops = &ia32_shared_page_vm_ops;
down_write(¤t->mm->mmap_sem);
{
if (insert_vm_struct(current->mm, vma)) {
kmem_cache_free(vm_area_cachep, vma);
up_write(¤t->mm->mmap_sem);
BUG();
}
}
up_write(¤t->mm->mmap_sem);
}
/*
* When user stack is not executable, push sigreturn code to stack makes
* segmentation fault raised when returning to kernel. So now sigreturn
* code is locked in specific gate page, which is pointed by pretcode
* when setup_frame_ia32
*/
vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
if (vma) {
vma->vm_mm = current->mm;
vma->vm_start = IA32_GATE_OFFSET;
vma->vm_end = vma->vm_start + PAGE_SIZE;
vma->vm_page_prot = PAGE_COPY_EXEC;
vma->vm_flags = VM_READ | VM_MAYREAD | VM_EXEC
| VM_MAYEXEC | VM_RESERVED;
vma->vm_ops = &ia32_gate_page_vm_ops;
down_write(¤t->mm->mmap_sem);
{
if (insert_vm_struct(current->mm, vma)) {
kmem_cache_free(vm_area_cachep, vma);
up_write(¤t->mm->mmap_sem);
BUG();
}
}
up_write(¤t->mm->mmap_sem);
}
/*
* Install LDT as anonymous memory. This gives us all-zero segment descriptors
* until a task modifies them via modify_ldt().
*/
vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
if (vma) {
vma->vm_mm = current->mm;
vma->vm_start = IA32_LDT_OFFSET;
vma->vm_end = vma->vm_start + PAGE_ALIGN(IA32_LDT_ENTRIES*IA32_LDT_ENTRY_SIZE);
vma->vm_page_prot = PAGE_SHARED;
vma->vm_flags = VM_READ|VM_WRITE|VM_MAYREAD|VM_MAYWRITE;
down_write(¤t->mm->mmap_sem);
{
if (insert_vm_struct(current->mm, vma)) {
kmem_cache_free(vm_area_cachep, vma);
up_write(¤t->mm->mmap_sem);
BUG();
}
}
up_write(¤t->mm->mmap_sem);
}
ia64_psr(regs)->ac = 0; /* turn off alignment checking */
regs->loadrs = 0;
/*
* According to the ABI %edx points to an `atexit' handler. Since we don't have
* one we'll set it to 0 and initialize all the other registers just to make
* things more deterministic, ala the i386 implementation.
*/
regs->r8 = 0; /* %eax */
regs->r11 = 0; /* %ebx */
regs->r9 = 0; /* %ecx */
regs->r10 = 0; /* %edx */
regs->r13 = 0; /* %ebp */
regs->r14 = 0; /* %esi */
regs->r15 = 0; /* %edi */
current->thread.eflag = IA32_EFLAG;
current->thread.fsr = IA32_FSR_DEFAULT;
current->thread.fcr = IA32_FCR_DEFAULT;
current->thread.fir = 0;
current->thread.fdr = 0;
/*
* Setup GDTD. Note: GDTD is the descrambled version of the pseudo-descriptor
* format defined by Figure 3-11 "Pseudo-Descriptor Format" in the IA-32
* architecture manual. Also note that the only fields that are not ignored are
* `base', `limit', 'G', `P' (must be 1) and `S' (must be 0).
*/
regs->r31 = IA32_SEG_UNSCRAMBLE(IA32_SEG_DESCRIPTOR(IA32_GDT_OFFSET, IA32_PAGE_SIZE - 1,
0, 0, 0, 1, 0, 0, 0));
/* Setup the segment selectors */
regs->r16 = (__USER_DS << 16) | __USER_DS; /* ES == DS, GS, FS are zero */
regs->r17 = (__USER_DS << 16) | __USER_CS; /* SS, CS; ia32_load_state() sets TSS and LDT */
ia32_load_segment_descriptors(current);
ia32_load_state(current);
}
/* We use the SunOS mmap() semantics. */
asmlinkage unsigned long sunos_mmap(unsigned long addr, unsigned long len,
unsigned long prot, unsigned long flags,
unsigned long fd, unsigned long off)
{
struct file * file = NULL;
unsigned long retval, ret_type;
if (flags & MAP_NORESERVE) {
static int cnt;
if (cnt++ < 10)
printk("%s: unimplemented SunOS MAP_NORESERVE mmap() flag\n",
current->comm);
flags &= ~MAP_NORESERVE;
}
retval = -EBADF;
if (!(flags & MAP_ANONYMOUS)) {
if (fd >= SUNOS_NR_OPEN)
goto out;
file = fget(fd);
if (!file)
goto out;
}
retval = -EINVAL;
/* If this is ld.so or a shared library doing an mmap
* of /dev/zero, transform it into an anonymous mapping.
* SunOS is so stupid some times... hmph!
*/
if (file) {
if (imajor(file->f_path.dentry->d_inode) == MEM_MAJOR &&
iminor(file->f_path.dentry->d_inode) == 5) {
flags |= MAP_ANONYMOUS;
fput(file);
file = NULL;
}
}
ret_type = flags & _MAP_NEW;
flags &= ~_MAP_NEW;
if (!(flags & MAP_FIXED))
addr = 0;
else {
if (ARCH_SUN4C_SUN4 &&
(len > 0x20000000 ||
((flags & MAP_FIXED) &&
addr < 0xe0000000 && addr + len > 0x20000000)))
goto out_putf;
/* See asm-sparc/uaccess.h */
if (len > TASK_SIZE - PAGE_SIZE ||
addr + len > TASK_SIZE - PAGE_SIZE)
goto out_putf;
}
flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
down_write(¤t->mm->mmap_sem);
retval = do_mmap(file, addr, len, prot, flags, off);
up_write(¤t->mm->mmap_sem);
if (!ret_type)
retval = ((retval < PAGE_OFFSET) ? 0 : retval);
out_putf:
if (file)
fput(file);
out:
return retval;
}
