/*
* Initialize ceph dentry state.
*/
int ceph_init_dentry(struct dentry *dentry)
{
struct ceph_dentry_info *di;
if (dentry->d_fsdata)
return 0;
if (ceph_snap(dentry->d_parent->d_inode) == CEPH_NOSNAP)
dentry->d_op = &ceph_dentry_ops;
else if (ceph_snap(dentry->d_parent->d_inode) == CEPH_SNAPDIR)
dentry->d_op = &ceph_snapdir_dentry_ops;
else
dentry->d_op = &ceph_snap_dentry_ops;
di = kmem_cache_alloc(ceph_dentry_cachep, GFP_NOFS | __GFP_ZERO);
if (!di)
return -ENOMEM; /* oh well */
spin_lock(&dentry->d_lock);
if (dentry->d_fsdata) {
/* lost a race */
kmem_cache_free(ceph_dentry_cachep, di);
goto out_unlock;
}
di->dentry = dentry;
di->lease_session = NULL;
dentry->d_fsdata = di;
dentry->d_time = jiffies;
ceph_dentry_lru_add(dentry);
out_unlock:
spin_unlock(&dentry->d_lock);
return 0;
}
static struct dentry *ceph_get_parent(struct dentry *child)
{
/* don't re-export snaps */
if (ceph_snap(d_inode(child)) != CEPH_NOSNAP)
return ERR_PTR(-EINVAL);
dout("get_parent %p ino %llx.%llx\n",
child, ceph_vinop(d_inode(child)));
return __get_parent(child->d_sb, child, 0);
}
/*
* Initialize ceph dentry state.
*/
int ceph_init_dentry(struct dentry *dentry)
{
struct ceph_dentry_info *di;
if (dentry->d_fsdata)
return 0;
di = kmem_cache_zalloc(ceph_dentry_cachep, GFP_KERNEL);
if (!di)
return -ENOMEM; /* oh well */
spin_lock(&dentry->d_lock);
if (dentry->d_fsdata) {
/* lost a race */
kmem_cache_free(ceph_dentry_cachep, di);
goto out_unlock;
}
if (ceph_snap(d_inode(dentry->d_parent)) == CEPH_NOSNAP)
d_set_d_op(dentry, &ceph_dentry_ops);
else if (ceph_snap(d_inode(dentry->d_parent)) == CEPH_SNAPDIR)
d_set_d_op(dentry, &ceph_snapdir_dentry_ops);
else
d_set_d_op(dentry, &ceph_snap_dentry_ops);
di->dentry = dentry;
di->lease_session = NULL;
di->time = jiffies;
/* avoid reordering d_fsdata setup so that the check above is safe */
smp_mb();
dentry->d_fsdata = di;
ceph_dentry_lru_add(dentry);
out_unlock:
spin_unlock(&dentry->d_lock);
return 0;
}
/*
* The presence of @parent_inode here tells us whether NFS wants a
* connectable file handle. However, we want to make a connectionable
* file handle unconditionally so that the MDS gets as much of a hint
* as possible. That means we only use @parent_dentry to indicate
* whether nfsd wants a connectable fh, and whether we should indicate
* failure from a too-small @max_len.
*/
static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len,
struct inode *parent_inode)
{
int type;
struct ceph_nfs_fh *fh = (void *)rawfh;
struct ceph_nfs_confh *cfh = (void *)rawfh;
int connected_handle_length = sizeof(*cfh)/4;
int handle_length = sizeof(*fh)/4;
struct dentry *dentry = d_find_alias(inode);
struct dentry *parent;
/* don't re-export snaps */
if (ceph_snap(inode) != CEPH_NOSNAP)
return -EINVAL;
/* if we found an alias, generate a connectable fh */
if (*max_len >= connected_handle_length && dentry) {
dout("encode_fh %p connectable\n", dentry);
spin_lock(&dentry->d_lock);
parent = dentry->d_parent;
cfh->ino = ceph_ino(inode);
cfh->parent_ino = ceph_ino(parent->d_inode);
cfh->parent_name_hash = ceph_dentry_hash(parent->d_inode,
dentry);
*max_len = connected_handle_length;
type = 2;
spin_unlock(&dentry->d_lock);
} else if (*max_len >= handle_length) {
if (parent_inode) {
/* nfsd wants connectable */
*max_len = connected_handle_length;
type = 255;
} else {
dout("encode_fh %p\n", dentry);
fh->ino = ceph_ino(inode);
*max_len = handle_length;
type = 1;
}
} else {
*max_len = handle_length;
type = 255;
}
if (dentry)
dput(dentry);
return type;
}
static int ceph_encode_fh(struct dentry *dentry, u32 *rawfh, int *max_len,
int connectable)
{
int type;
struct ceph_nfs_fh *fh = (void *)rawfh;
struct ceph_nfs_confh *cfh = (void *)rawfh;
struct dentry *parent;
struct inode *inode = dentry->d_inode;
int connected_handle_length = sizeof(*cfh)/4;
int handle_length = sizeof(*fh)/4;
/* don't re-export snaps */
if (ceph_snap(inode) != CEPH_NOSNAP)
return -EINVAL;
spin_lock(&dentry->d_lock);
parent = dentry->d_parent;
if (*max_len >= connected_handle_length) {
dout("encode_fh %p connectable\n", dentry);
cfh->ino = ceph_ino(dentry->d_inode);
cfh->parent_ino = ceph_ino(parent->d_inode);
cfh->parent_name_hash = ceph_dentry_hash(parent->d_inode,
dentry);
*max_len = connected_handle_length;
type = 2;
} else if (*max_len >= handle_length) {
if (connectable) {
*max_len = connected_handle_length;
type = 255;
} else {
dout("encode_fh %p\n", dentry);
fh->ino = ceph_ino(dentry->d_inode);
*max_len = handle_length;
type = 1;
}
} else {
*max_len = handle_length;
type = 255;
}
spin_unlock(&dentry->d_lock);
return type;
}
/*
* This function walks through the snaprealm for an inode and returns the
* ceph_snap_realm for the first snaprealm that has quotas set (either max_files
* or max_bytes). If the root is reached, return the root ceph_snap_realm
* instead.
*
* Note that the caller is responsible for calling ceph_put_snap_realm() on the
* returned realm.
*/
static struct ceph_snap_realm *get_quota_realm(struct ceph_mds_client *mdsc,
struct inode *inode)
{
struct ceph_inode_info *ci = NULL;
struct ceph_snap_realm *realm, *next;
struct inode *in;
bool has_quota;
if (ceph_snap(inode) != CEPH_NOSNAP)
return NULL;
realm = ceph_inode(inode)->i_snap_realm;
if (realm)
ceph_get_snap_realm(mdsc, realm);
else
pr_err_ratelimited("get_quota_realm: ino (%llx.%llx) "
"null i_snap_realm\n", ceph_vinop(inode));
while (realm) {
spin_lock(&realm->inodes_with_caps_lock);
in = realm->inode ? igrab(realm->inode) : NULL;
spin_unlock(&realm->inodes_with_caps_lock);
if (!in)
break;
ci = ceph_inode(in);
has_quota = __ceph_has_any_quota(ci);
iput(in);
next = realm->parent;
if (has_quota || !next)
return realm;
ceph_get_snap_realm(mdsc, next);
ceph_put_snap_realm(mdsc, realm);
realm = next;
}
if (realm)
ceph_put_snap_realm(mdsc, realm);
return NULL;
}
static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len,
struct inode *parent_inode)
{
int type;
struct ceph_nfs_fh *fh = (void *)rawfh;
struct ceph_nfs_confh *cfh = (void *)rawfh;
int connected_handle_length = sizeof(*cfh)/4;
int handle_length = sizeof(*fh)/4;
/* don't re-export snaps */
if (ceph_snap(inode) != CEPH_NOSNAP)
return -EINVAL;
if (parent_inode && (*max_len < connected_handle_length)) {
*max_len = connected_handle_length;
return FILEID_INVALID;
} else if (*max_len < handle_length) {
*max_len = handle_length;
return FILEID_INVALID;
}
if (parent_inode) {
dout("encode_fh %llx with parent %llx\n",
ceph_ino(inode), ceph_ino(parent_inode));
cfh->ino = ceph_ino(inode);
cfh->parent_ino = ceph_ino(parent_inode);
*max_len = connected_handle_length;
type = FILEID_INO32_GEN_PARENT;
} else {
dout("encode_fh %llx\n", ceph_ino(inode));
fh->ino = ceph_ino(inode);
*max_len = handle_length;
type = FILEID_INO32_GEN;
}
return type;
}
/*
* If the filp already has private_data, that means the file was
* already opened by intent during lookup, and we do nothing.
*
* If we already have the requisite capabilities, we can satisfy
* the open request locally (no need to request new caps from the
* MDS). We do, however, need to inform the MDS (asynchronously)
* if our wanted caps set expands.
*/
int ceph_open(struct inode *inode, struct file *file)
{
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
struct ceph_file_info *cf = file->private_data;
struct inode *parent_inode = file->f_dentry->d_parent->d_inode;
int err;
int flags, fmode, wanted;
if (cf) {
dout("open file %p is already opened\n", file);
return 0;
}
/* filter out O_CREAT|O_EXCL; vfs did that already. yuck. */
flags = file->f_flags & ~(O_CREAT|O_EXCL);
if (S_ISDIR(inode->i_mode))
flags = O_DIRECTORY; /* mds likes to know */
dout("open inode %p ino %llx.%llx file %p flags %d (%d)\n", inode,
ceph_vinop(inode), file, flags, file->f_flags);
fmode = ceph_flags_to_mode(flags);
wanted = ceph_caps_for_mode(fmode);
/* snapped files are read-only */
if (ceph_snap(inode) != CEPH_NOSNAP && (file->f_mode & FMODE_WRITE))
return -EROFS;
/* trivially open snapdir */
if (ceph_snap(inode) == CEPH_SNAPDIR) {
spin_lock(&inode->i_lock);
__ceph_get_fmode(ci, fmode);
spin_unlock(&inode->i_lock);
return ceph_init_file(inode, file, fmode);
}
/*
* No need to block if we have caps on the auth MDS (for
* write) or any MDS (for read). Update wanted set
* asynchronously.
*/
spin_lock(&inode->i_lock);
if (__ceph_is_any_real_caps(ci) &&
(((fmode & CEPH_FILE_MODE_WR) == 0) || ci->i_auth_cap)) {
int mds_wanted = __ceph_caps_mds_wanted(ci);
int issued = __ceph_caps_issued(ci, NULL);
dout("open %p fmode %d want %s issued %s using existing\n",
inode, fmode, ceph_cap_string(wanted),
ceph_cap_string(issued));
__ceph_get_fmode(ci, fmode);
spin_unlock(&inode->i_lock);
/* adjust wanted? */
if ((issued & wanted) != wanted &&
(mds_wanted & wanted) != wanted &&
ceph_snap(inode) != CEPH_SNAPDIR)
ceph_check_caps(ci, 0, NULL);
return ceph_init_file(inode, file, fmode);
} else if (ceph_snap(inode) != CEPH_NOSNAP &&
(ci->i_snap_caps & wanted) == wanted) {
__ceph_get_fmode(ci, fmode);
spin_unlock(&inode->i_lock);
return ceph_init_file(inode, file, fmode);
}
spin_unlock(&inode->i_lock);
dout("open fmode %d wants %s\n", fmode, ceph_cap_string(wanted));
req = prepare_open_request(inode->i_sb, flags, 0);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto out;
}
req->r_inode = igrab(inode);
req->r_num_caps = 1;
err = ceph_mdsc_do_request(mdsc, parent_inode, req);
if (!err)
err = ceph_init_file(inode, file, req->r_fmode);
ceph_mdsc_put_request(req);
dout("open result=%d on %llx.%llx\n", err, ceph_vinop(inode));
out:
return err;
}
int ceph_open(struct inode *inode, struct file *file)
{
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
struct ceph_file_info *cf = file->private_data;
struct inode *parent_inode = NULL;
int err;
int flags, fmode, wanted;
if (cf) {
dout("open file %p is already opened\n", file);
return 0;
}
flags = file->f_flags & ~(O_CREAT|O_EXCL);
if (S_ISDIR(inode->i_mode))
flags = O_DIRECTORY;
dout("open inode %p ino %llx.%llx file %p flags %d (%d)\n", inode,
ceph_vinop(inode), file, flags, file->f_flags);
fmode = ceph_flags_to_mode(flags);
wanted = ceph_caps_for_mode(fmode);
if (ceph_snap(inode) != CEPH_NOSNAP && (file->f_mode & FMODE_WRITE))
return -EROFS;
if (ceph_snap(inode) == CEPH_SNAPDIR) {
spin_lock(&ci->i_ceph_lock);
__ceph_get_fmode(ci, fmode);
spin_unlock(&ci->i_ceph_lock);
return ceph_init_file(inode, file, fmode);
}
spin_lock(&ci->i_ceph_lock);
if (__ceph_is_any_real_caps(ci) &&
(((fmode & CEPH_FILE_MODE_WR) == 0) || ci->i_auth_cap)) {
int mds_wanted = __ceph_caps_mds_wanted(ci);
int issued = __ceph_caps_issued(ci, NULL);
dout("open %p fmode %d want %s issued %s using existing\n",
inode, fmode, ceph_cap_string(wanted),
ceph_cap_string(issued));
__ceph_get_fmode(ci, fmode);
spin_unlock(&ci->i_ceph_lock);
if ((issued & wanted) != wanted &&
(mds_wanted & wanted) != wanted &&
ceph_snap(inode) != CEPH_SNAPDIR)
ceph_check_caps(ci, 0, NULL);
return ceph_init_file(inode, file, fmode);
} else if (ceph_snap(inode) != CEPH_NOSNAP &&
(ci->i_snap_caps & wanted) == wanted) {
__ceph_get_fmode(ci, fmode);
spin_unlock(&ci->i_ceph_lock);
return ceph_init_file(inode, file, fmode);
}
spin_unlock(&ci->i_ceph_lock);
dout("open fmode %d wants %s\n", fmode, ceph_cap_string(wanted));
req = prepare_open_request(inode->i_sb, flags, 0);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto out;
}
req->r_inode = inode;
ihold(inode);
req->r_num_caps = 1;
if (flags & (O_CREAT|O_TRUNC))
parent_inode = ceph_get_dentry_parent_inode(file->f_dentry);
err = ceph_mdsc_do_request(mdsc, parent_inode, req);
iput(parent_inode);
if (!err)
err = ceph_init_file(inode, file, req->r_fmode);
ceph_mdsc_put_request(req);
dout("open result=%d on %llx.%llx\n", err, ceph_vinop(inode));
out:
return err;
}