/*
* convert regular fh to dentry
*
* FIXME: we should try harder by querying the mds for the ino.
*/
static struct dentry *__fh_to_dentry(struct super_block *sb,
struct ceph_nfs_fh *fh, int fh_len)
{
struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
struct inode *inode;
struct dentry *dentry;
struct ceph_vino vino;
int err;
if (fh_len < sizeof(*fh) / 4)
return ERR_PTR(-ESTALE);
dout("__fh_to_dentry %llx\n", fh->ino);
vino.ino = fh->ino;
vino.snap = CEPH_NOSNAP;
inode = ceph_find_inode(sb, vino);
if (!inode) {
struct ceph_mds_request *req;
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPINO,
USE_ANY_MDS);
if (IS_ERR(req))
return ERR_CAST(req);
req->r_ino1 = vino;
req->r_num_caps = 1;
err = ceph_mdsc_do_request(mdsc, NULL, req);
inode = req->r_target_inode;
if (inode)
ihold(inode);
ceph_mdsc_put_request(req);
if (!inode)
return ERR_PTR(-ESTALE);
}
dentry = d_obtain_alias(inode);
if (IS_ERR(dentry)) {
pr_err("fh_to_dentry %llx -- inode %p but ENOMEM\n",
fh->ino, inode);
iput(inode);
return dentry;
}
err = ceph_init_dentry(dentry);
if (err < 0) {
iput(inode);
return ERR_PTR(err);
}
dout("__fh_to_dentry %llx %p dentry %p\n", fh->ino, inode, dentry);
return dentry;
}
static struct dentry *__get_parent(struct super_block *sb,
struct dentry *child, u64 ino)
{
struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
struct ceph_mds_request *req;
struct inode *inode;
struct dentry *dentry;
int err;
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPPARENT,
USE_ANY_MDS);
if (IS_ERR(req))
return ERR_CAST(req);
if (child) {
req->r_inode = child->d_inode;
ihold(child->d_inode);
} else {
req->r_ino1 = (struct ceph_vino) {
.ino = ino,
.snap = CEPH_NOSNAP,
};
}
req->r_num_caps = 1;
err = ceph_mdsc_do_request(mdsc, NULL, req);
inode = req->r_target_inode;
if (inode)
ihold(inode);
ceph_mdsc_put_request(req);
if (!inode)
return ERR_PTR(-ENOENT);
dentry = d_obtain_alias(inode);
if (IS_ERR(dentry)) {
iput(inode);
return dentry;
}
err = ceph_init_dentry(dentry);
if (err < 0) {
dput(dentry);
return ERR_PTR(err);
}
dout("__get_parent ino %llx parent %p ino %llx.%llx\n",
child ? ceph_ino(child->d_inode) : ino,
dentry, ceph_vinop(inode));
return dentry;
}
static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino)
{
struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
struct inode *inode;
struct ceph_vino vino;
int err;
vino.ino = ino;
vino.snap = CEPH_NOSNAP;
inode = ceph_find_inode(sb, vino);
if (!inode) {
struct ceph_mds_request *req;
int mask;
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPINO,
USE_ANY_MDS);
if (IS_ERR(req))
return ERR_CAST(req);
mask = CEPH_STAT_CAP_INODE;
if (ceph_security_xattr_wanted(d_inode(sb->s_root)))
mask |= CEPH_CAP_XATTR_SHARED;
req->r_args.getattr.mask = cpu_to_le32(mask);
req->r_ino1 = vino;
req->r_num_caps = 1;
err = ceph_mdsc_do_request(mdsc, NULL, req);
inode = req->r_target_inode;
if (inode)
ihold(inode);
ceph_mdsc_put_request(req);
if (!inode)
return ERR_PTR(-ESTALE);
if (inode->i_nlink == 0) {
iput(inode);
return ERR_PTR(-ESTALE);
}
}
return d_obtain_alias(inode);
}
/*
* Prepare an open request. Preallocate ceph_cap to avoid an
* inopportune ENOMEM later.
*/
static struct ceph_mds_request *
prepare_open_request(struct super_block *sb, int flags, int create_mode)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
int want_auth = USE_ANY_MDS;
int op = (flags & O_CREAT) ? CEPH_MDS_OP_CREATE : CEPH_MDS_OP_OPEN;
if (flags & (O_WRONLY|O_RDWR|O_CREAT|O_TRUNC))
want_auth = USE_AUTH_MDS;
req = ceph_mdsc_create_request(mdsc, op, want_auth);
if (IS_ERR(req))
goto out;
req->r_fmode = ceph_flags_to_mode(flags);
req->r_args.open.flags = cpu_to_le32(flags);
req->r_args.open.mode = cpu_to_le32(create_mode);
out:
return req;
}
static struct dentry *__get_parent(struct super_block *sb,
struct dentry *child, u64 ino)
{
struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
struct ceph_mds_request *req;
struct inode *inode;
int mask;
int err;
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPPARENT,
USE_ANY_MDS);
if (IS_ERR(req))
return ERR_CAST(req);
if (child) {
req->r_inode = d_inode(child);
ihold(d_inode(child));
} else {
req->r_ino1 = (struct ceph_vino) {
.ino = ino,
.snap = CEPH_NOSNAP,
};
}
mask = CEPH_STAT_CAP_INODE;
if (ceph_security_xattr_wanted(d_inode(sb->s_root)))
mask |= CEPH_CAP_XATTR_SHARED;
req->r_args.getattr.mask = cpu_to_le32(mask);
req->r_num_caps = 1;
err = ceph_mdsc_do_request(mdsc, NULL, req);
inode = req->r_target_inode;
if (inode)
ihold(inode);
ceph_mdsc_put_request(req);
if (!inode)
return ERR_PTR(-ENOENT);
return d_obtain_alias(inode);
}
static int ceph_get_name(struct dentry *parent, char *name,
struct dentry *child)
{
struct ceph_mds_client *mdsc;
struct ceph_mds_request *req;
int err;
mdsc = ceph_inode_to_client(d_inode(child))->mdsc;
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPNAME,
USE_ANY_MDS);
if (IS_ERR(req))
return PTR_ERR(req);
inode_lock(d_inode(parent));
req->r_inode = d_inode(child);
ihold(d_inode(child));
req->r_ino2 = ceph_vino(d_inode(parent));
req->r_parent = d_inode(parent);
set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
req->r_num_caps = 2;
err = ceph_mdsc_do_request(mdsc, NULL, req);
inode_unlock(d_inode(parent));
if (!err) {
struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
memcpy(name, rinfo->dname, rinfo->dname_len);
name[rinfo->dname_len] = 0;
dout("get_name %p ino %llx.%llx name %s\n",
child, ceph_vinop(d_inode(child)), name);
} else {
dout("get_name %p ino %llx.%llx err %d\n",
child, ceph_vinop(d_inode(child)), err);
}
ceph_mdsc_put_request(req);
return err;
}
static int ceph_get_name(struct dentry *parent, char *name,
struct dentry *child)
{
struct ceph_mds_client *mdsc;
struct ceph_mds_request *req;
int err;
mdsc = ceph_inode_to_client(child->d_inode)->mdsc;
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPNAME,
USE_ANY_MDS);
if (IS_ERR(req))
return PTR_ERR(req);
mutex_lock(&parent->d_inode->i_mutex);
req->r_inode = child->d_inode;
ihold(child->d_inode);
req->r_ino2 = ceph_vino(parent->d_inode);
req->r_locked_dir = parent->d_inode;
req->r_num_caps = 2;
err = ceph_mdsc_do_request(mdsc, NULL, req);
mutex_unlock(&parent->d_inode->i_mutex);
if (!err) {
struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
memcpy(name, rinfo->dname, rinfo->dname_len);
name[rinfo->dname_len] = 0;
dout("get_name %p ino %llx.%llx name %s\n",
child, ceph_vinop(child->d_inode), name);
} else {
dout("get_name %p ino %llx.%llx err %d\n",
child, ceph_vinop(child->d_inode), err);
}
ceph_mdsc_put_request(req);
return err;
}
/*
* Set a layout policy on a directory inode. All items in the tree
* rooted at this inode will inherit this layout on creation,
* (It doesn't apply retroactively )
* unless a subdirectory has its own layout policy.
*/
static long ceph_ioctl_set_layout_policy (struct file *file, void __user *arg)
{
struct inode *inode = file_inode(file);
struct ceph_mds_request *req;
struct ceph_ioctl_layout l;
int err;
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
/* copy and validate */
if (copy_from_user(&l, arg, sizeof(l)))
return -EFAULT;
err = __validate_layout(mdsc, &l);
if (err)
return err;
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETDIRLAYOUT,
USE_AUTH_MDS);
if (IS_ERR(req))
return PTR_ERR(req);
req->r_inode = inode;
ihold(inode);
req->r_args.setlayout.layout.fl_stripe_unit =
cpu_to_le32(l.stripe_unit);
req->r_args.setlayout.layout.fl_stripe_count =
cpu_to_le32(l.stripe_count);
req->r_args.setlayout.layout.fl_object_size =
cpu_to_le32(l.object_size);
req->r_args.setlayout.layout.fl_pg_pool =
cpu_to_le32(l.data_pool);
err = ceph_mdsc_do_request(mdsc, inode, req);
ceph_mdsc_put_request(req);
return err;
}
/**
* Implement fcntl and flock locking functions.
*/
static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
int cmd, u8 wait, struct file_lock *fl)
{
struct inode *inode = file->f_dentry->d_inode;
struct ceph_mds_client *mdsc =
ceph_sb_to_client(inode->i_sb)->mdsc;
struct ceph_mds_request *req;
int err;
u64 length = 0;
req = ceph_mdsc_create_request(mdsc, operation, USE_AUTH_MDS);
if (IS_ERR(req))
return PTR_ERR(req);
req->r_inode = inode;
ihold(inode);
/* mds requires start and length rather than start and end */
if (LLONG_MAX == fl->fl_end)
length = 0;
else
length = fl->fl_end - fl->fl_start + 1;
dout("ceph_lock_message: rule: %d, op: %d, pid: %llu, start: %llu, "
"length: %llu, wait: %d, type: %d", (int)lock_type,
(int)operation, (u64)fl->fl_pid, fl->fl_start,
length, wait, fl->fl_type);
req->r_args.filelock_change.rule = lock_type;
req->r_args.filelock_change.type = cmd;
req->r_args.filelock_change.pid = cpu_to_le64((u64)fl->fl_pid);
/* This should be adjusted, but I'm not sure if
namespaces actually get id numbers*/
req->r_args.filelock_change.pid_namespace =
cpu_to_le64((u64)(unsigned long)fl->fl_nspid);
req->r_args.filelock_change.start = cpu_to_le64(fl->fl_start);
req->r_args.filelock_change.length = cpu_to_le64(length);
req->r_args.filelock_change.wait = wait;
err = ceph_mdsc_do_request(mdsc, inode, req);
if ( operation == CEPH_MDS_OP_GETFILELOCK){
fl->fl_pid = le64_to_cpu(req->r_reply_info.filelock_reply->pid);
if (CEPH_LOCK_SHARED == req->r_reply_info.filelock_reply->type)
fl->fl_type = F_RDLCK;
else if (CEPH_LOCK_EXCL == req->r_reply_info.filelock_reply->type)
fl->fl_type = F_WRLCK;
else
fl->fl_type = F_UNLCK;
fl->fl_start = le64_to_cpu(req->r_reply_info.filelock_reply->start);
length = le64_to_cpu(req->r_reply_info.filelock_reply->start) +
le64_to_cpu(req->r_reply_info.filelock_reply->length);
if (length >= 1)
fl->fl_end = length -1;
else
fl->fl_end = 0;
}
ceph_mdsc_put_request(req);
dout("ceph_lock_message: rule: %d, op: %d, pid: %llu, start: %llu, "
"length: %llu, wait: %d, type: %d, err code %d", (int)lock_type,
(int)operation, (u64)fl->fl_pid, fl->fl_start,
length, wait, fl->fl_type, err);
return err;
}
static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
{
struct inode *inode = file_inode(file);
struct inode *parent_inode;
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
struct ceph_mds_request *req;
struct ceph_ioctl_layout l;
struct ceph_inode_info *ci = ceph_inode(file_inode(file));
struct ceph_ioctl_layout nl;
int err;
if (copy_from_user(&l, arg, sizeof(l)))
return -EFAULT;
/* validate changed params against current layout */
err = ceph_do_getattr(file_inode(file), CEPH_STAT_CAP_LAYOUT);
if (err)
return err;
memset(&nl, 0, sizeof(nl));
if (l.stripe_count)
nl.stripe_count = l.stripe_count;
else
nl.stripe_count = ceph_file_layout_stripe_count(ci->i_layout);
if (l.stripe_unit)
nl.stripe_unit = l.stripe_unit;
else
nl.stripe_unit = ceph_file_layout_su(ci->i_layout);
if (l.object_size)
nl.object_size = l.object_size;
else
nl.object_size = ceph_file_layout_object_size(ci->i_layout);
if (l.data_pool)
nl.data_pool = l.data_pool;
else
nl.data_pool = ceph_file_layout_pg_pool(ci->i_layout);
/* this is obsolete, and always -1 */
nl.preferred_osd = le64_to_cpu(-1);
err = __validate_layout(mdsc, &nl);
if (err)
return err;
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETLAYOUT,
USE_AUTH_MDS);
if (IS_ERR(req))
return PTR_ERR(req);
req->r_inode = inode;
ihold(inode);
req->r_inode_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_EXCL;
req->r_args.setlayout.layout.fl_stripe_unit =
cpu_to_le32(l.stripe_unit);
req->r_args.setlayout.layout.fl_stripe_count =
cpu_to_le32(l.stripe_count);
req->r_args.setlayout.layout.fl_object_size =
cpu_to_le32(l.object_size);
req->r_args.setlayout.layout.fl_pg_pool = cpu_to_le32(l.data_pool);
parent_inode = ceph_get_dentry_parent_inode(file->f_dentry);
err = ceph_mdsc_do_request(mdsc, parent_inode, req);
iput(parent_inode);
ceph_mdsc_put_request(req);
return err;
}
static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
{
struct inode *inode = file_inode(file);
struct inode *parent_inode;
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
struct ceph_mds_request *req;
struct ceph_ioctl_layout l;
struct ceph_inode_info *ci = ceph_inode(file_inode(file));
struct ceph_ioctl_layout nl;
int err, i;
if (copy_from_user(&l, arg, sizeof(l)))
return -EFAULT;
/* validate changed params against current layout */
err = ceph_do_getattr(file_inode(file), CEPH_STAT_CAP_LAYOUT);
if (!err) {
nl.stripe_unit = ceph_file_layout_su(ci->i_layout);
nl.stripe_count = ceph_file_layout_stripe_count(ci->i_layout);
nl.object_size = ceph_file_layout_object_size(ci->i_layout);
nl.data_pool = le32_to_cpu(ci->i_layout.fl_pg_pool);
nl.preferred_osd =
(s32)le32_to_cpu(ci->i_layout.fl_pg_preferred);
} else
return err;
if (l.stripe_count)
nl.stripe_count = l.stripe_count;
if (l.stripe_unit)
nl.stripe_unit = l.stripe_unit;
if (l.object_size)
nl.object_size = l.object_size;
if (l.data_pool)
nl.data_pool = l.data_pool;
if (l.preferred_osd)
nl.preferred_osd = l.preferred_osd;
if ((nl.object_size & ~PAGE_MASK) ||
(nl.stripe_unit & ~PAGE_MASK) ||
((unsigned)nl.object_size % (unsigned)nl.stripe_unit))
return -EINVAL;
/* make sure it's a valid data pool */
if (l.data_pool > 0) {
mutex_lock(&mdsc->mutex);
err = -EINVAL;
for (i = 0; i < mdsc->mdsmap->m_num_data_pg_pools; i++)
if (mdsc->mdsmap->m_data_pg_pools[i] == l.data_pool) {
err = 0;
break;
}
mutex_unlock(&mdsc->mutex);
if (err)
return err;
}
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETLAYOUT,
USE_AUTH_MDS);
if (IS_ERR(req))
return PTR_ERR(req);
req->r_inode = inode;
ihold(inode);
req->r_inode_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_EXCL;
req->r_args.setlayout.layout.fl_stripe_unit =
cpu_to_le32(l.stripe_unit);
req->r_args.setlayout.layout.fl_stripe_count =
cpu_to_le32(l.stripe_count);
req->r_args.setlayout.layout.fl_object_size =
cpu_to_le32(l.object_size);
req->r_args.setlayout.layout.fl_pg_pool = cpu_to_le32(l.data_pool);
req->r_args.setlayout.layout.fl_pg_preferred =
cpu_to_le32(l.preferred_osd);
parent_inode = ceph_get_dentry_parent_inode(file->f_dentry);
err = ceph_mdsc_do_request(mdsc, parent_inode, req);
iput(parent_inode);
ceph_mdsc_put_request(req);
return err;
}
/**
* Implement fcntl and flock locking functions.
*/
static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
int cmd, u8 wait, struct file_lock *fl)
{
struct inode *inode = file_inode(file);
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
struct ceph_mds_request *req;
int err;
u64 length = 0;
u64 owner;
req = ceph_mdsc_create_request(mdsc, operation, USE_AUTH_MDS);
if (IS_ERR(req))
return PTR_ERR(req);
req->r_inode = inode;
ihold(inode);
req->r_num_caps = 1;
/* mds requires start and length rather than start and end */
if (LLONG_MAX == fl->fl_end)
length = 0;
else
length = fl->fl_end - fl->fl_start + 1;
if (lock_type == CEPH_LOCK_FCNTL)
owner = secure_addr(fl->fl_owner);
else
owner = secure_addr(fl->fl_file);
dout("ceph_lock_message: rule: %d, op: %d, owner: %llx, pid: %llu, "
"start: %llu, length: %llu, wait: %d, type: %d", (int)lock_type,
(int)operation, owner, (u64)fl->fl_pid, fl->fl_start, length,
wait, fl->fl_type);
req->r_args.filelock_change.rule = lock_type;
req->r_args.filelock_change.type = cmd;
req->r_args.filelock_change.owner = cpu_to_le64(owner);
req->r_args.filelock_change.pid = cpu_to_le64((u64)fl->fl_pid);
req->r_args.filelock_change.start = cpu_to_le64(fl->fl_start);
req->r_args.filelock_change.length = cpu_to_le64(length);
req->r_args.filelock_change.wait = wait;
err = ceph_mdsc_do_request(mdsc, inode, req);
if (operation == CEPH_MDS_OP_GETFILELOCK) {
fl->fl_pid = le64_to_cpu(req->r_reply_info.filelock_reply->pid);
if (CEPH_LOCK_SHARED == req->r_reply_info.filelock_reply->type)
fl->fl_type = F_RDLCK;
else if (CEPH_LOCK_EXCL == req->r_reply_info.filelock_reply->type)
fl->fl_type = F_WRLCK;
else
fl->fl_type = F_UNLCK;
fl->fl_start = le64_to_cpu(req->r_reply_info.filelock_reply->start);
length = le64_to_cpu(req->r_reply_info.filelock_reply->start) +
le64_to_cpu(req->r_reply_info.filelock_reply->length);
if (length >= 1)
fl->fl_end = length -1;
else
fl->fl_end = 0;
}
ceph_mdsc_put_request(req);
dout("ceph_lock_message: rule: %d, op: %d, pid: %llu, start: %llu, "
"length: %llu, wait: %d, type: %d, err code %d", (int)lock_type,
(int)operation, (u64)fl->fl_pid, fl->fl_start,
length, wait, fl->fl_type, err);
return err;
}