/*
* Set the Access and/or Default ACL of a file.
*/
static __be32 nfsacld_proc_setacl(struct svc_rqst * rqstp,
struct nfsd3_setaclargs *argp,
struct nfsd_attrstat *resp)
{
svc_fh *fh;
__be32 nfserr = 0;
dprintk("nfsd: SETACL(2acl) %s\n", SVCFH_fmt(&argp->fh));
fh = fh_copy(&resp->fh, &argp->fh);
nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_SATTR);
if (!nfserr) {
nfserr = nfserrno( nfsd_set_posix_acl(
fh, ACL_TYPE_ACCESS, argp->acl_access) );
}
if (!nfserr) {
nfserr = nfserrno( nfsd_set_posix_acl(
fh, ACL_TYPE_DEFAULT, argp->acl_default) );
}
/* argp->acl_{access,default} may have been allocated in
nfssvc_decode_setaclargs. */
posix_acl_release(argp->acl_access);
posix_acl_release(argp->acl_default);
return nfserr;
}
/*
* Set the Access and/or Default ACL of a file.
*/
static __be32 nfsd3_proc_setacl(struct svc_rqst * rqstp,
struct nfsd3_setaclargs *argp,
struct nfsd3_attrstat *resp)
{
svc_fh *fh;
__be32 nfserr = 0;
fh = fh_copy(&resp->fh, &argp->fh);
nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_SATTR);
if (!nfserr) {
nfserr = nfserrno( nfsd_set_posix_acl(
fh, ACL_TYPE_ACCESS, argp->acl_access) );
}
if (!nfserr) {
nfserr = nfserrno( nfsd_set_posix_acl(
fh, ACL_TYPE_DEFAULT, argp->acl_default) );
}
/* argp->acl_{access,default} may have been allocated in
nfs3svc_decode_setaclargs. */
posix_acl_release(argp->acl_access);
posix_acl_release(argp->acl_default);
RETURN_STATUS(nfserr);
}
/*
* Get the Access and/or Default ACL of a file.
*/
static __be32 nfsacld_proc_getacl(struct svc_rqst * rqstp,
struct nfsd3_getaclargs *argp, struct nfsd3_getaclres *resp)
{
struct posix_acl *acl;
struct inode *inode;
svc_fh *fh;
__be32 nfserr = 0;
dprintk("nfsd: GETACL(2acl) %s\n", SVCFH_fmt(&argp->fh));
fh = fh_copy(&resp->fh, &argp->fh);
nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP);
if (nfserr)
RETURN_STATUS(nfserr);
inode = fh->fh_dentry->d_inode;
if (argp->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT))
RETURN_STATUS(nfserr_inval);
resp->mask = argp->mask;
nfserr = fh_getattr(fh, &resp->stat);
if (nfserr)
goto fail;
if (resp->mask & (NFS_ACL|NFS_ACLCNT)) {
acl = get_acl(inode, ACL_TYPE_ACCESS);
if (IS_ERR(acl)) {
nfserr = nfserrno(PTR_ERR(acl));
goto fail;
}
if (acl == NULL) {
/* Solaris returns the inode's minimum ACL. */
acl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
}
resp->acl_access = acl;
}
if (resp->mask & (NFS_DFACL|NFS_DFACLCNT)) {
/* Check how Solaris handles requests for the Default ACL
of a non-directory! */
acl = get_acl(inode, ACL_TYPE_DEFAULT);
if (IS_ERR(acl)) {
nfserr = nfserrno(PTR_ERR(acl));
goto fail;
}
resp->acl_default = acl;
}
/* resp->acl_{access,default} are released in nfssvc_release_getacl. */
RETURN_STATUS(0);
fail:
posix_acl_release(resp->acl_access);
posix_acl_release(resp->acl_default);
RETURN_STATUS(nfserr);
}
static __be32
nfsd4_block_proc_layoutcommit(struct inode *inode,
struct nfsd4_layoutcommit *lcp)
{
loff_t new_size = lcp->lc_last_wr + 1;
struct iattr iattr = { .ia_valid = 0 };
struct iomap *iomaps;
int nr_iomaps;
int error;
nr_iomaps = nfsd4_block_decode_layoutupdate(lcp->lc_up_layout,
lcp->lc_up_len, &iomaps, 1 << inode->i_blkbits);
if (nr_iomaps < 0)
return nfserrno(nr_iomaps);
if (lcp->lc_mtime.tv_nsec == UTIME_NOW ||
timespec_compare(&lcp->lc_mtime, &inode->i_mtime) < 0)
lcp->lc_mtime = current_fs_time(inode->i_sb);
iattr.ia_valid |= ATTR_ATIME | ATTR_CTIME | ATTR_MTIME;
iattr.ia_atime = iattr.ia_ctime = iattr.ia_mtime = lcp->lc_mtime;
if (new_size > i_size_read(inode)) {
iattr.ia_valid |= ATTR_SIZE;
iattr.ia_size = new_size;
}
error = inode->i_sb->s_export_op->commit_blocks(inode, iomaps,
nr_iomaps, &iattr);
kfree(iomaps);
return nfserrno(error);
}
const struct nfsd4_layout_ops bl_layout_ops = {
/*
* Pretend that we send notification to the client. This is a blatant
* lie to force recent Linux clients to cache our device IDs.
* We rarely ever change the device ID, so the harm of leaking deviceids
* for a while isn't too bad. Unfortunately RFC5661 is a complete mess
* in this regard, but I filed errata 4119 for this a while ago, and
* hopefully the Linux client will eventually start caching deviceids
* without this again.
*/
.notify_types =
NOTIFY_DEVICEID4_DELETE | NOTIFY_DEVICEID4_CHANGE,
.proc_getdeviceinfo = nfsd4_block_proc_getdeviceinfo,
.encode_getdeviceinfo = nfsd4_block_encode_getdeviceinfo,
.proc_layoutget = nfsd4_block_proc_layoutget,
.encode_layoutget = nfsd4_block_encode_layoutget,
.proc_layoutcommit = nfsd4_block_proc_layoutcommit,
};
static __be32
nfsd4_block_proc_getdeviceinfo(struct super_block *sb,
struct nfsd4_getdeviceinfo *gdp)
{
if (sb->s_bdev != sb->s_bdev->bd_contains)
return nfserr_inval;
return nfserrno(nfsd4_block_get_device_info_simple(sb, gdp));
}
static __be32
nfsd4_ff_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
struct nfsd4_layoutget *args)
{
struct nfsd4_layout_seg *seg = &args->lg_seg;
u32 device_generation = 0;
int error;
uid_t u;
struct pnfs_ff_layout *fl;
/*
* The super simple flex file server has 1 mirror, 1 data server,
* and 1 file handle. So instead of 4 allocs, do 1 for now.
* Zero it out for the stateid - don't want junk in there!
*/
error = -ENOMEM;
fl = kzalloc(sizeof(*fl), GFP_KERNEL);
if (!fl)
goto out_error;
args->lg_content = fl;
/*
* Avoid layout commit, try to force the I/O to the DS,
* and for fun, cause all IOMODE_RW layout segments to
* effectively be WRITE only.
*/
fl->flags = FF_FLAGS_NO_LAYOUTCOMMIT | FF_FLAGS_NO_IO_THRU_MDS |
FF_FLAGS_NO_READ_IO;
/* Do not allow a IOMODE_READ segment to have write pemissions */
if (seg->iomode == IOMODE_READ) {
u = from_kuid(&init_user_ns, inode->i_uid) + 1;
fl->uid = make_kuid(&init_user_ns, u);
} else
fl->uid = inode->i_uid;
fl->gid = inode->i_gid;
error = nfsd4_set_deviceid(&fl->deviceid, fhp, device_generation);
if (error)
goto out_error;
fl->fh.size = fhp->fh_handle.fh_size;
memcpy(fl->fh.data, &fhp->fh_handle.fh_base, fl->fh.size);
/* Give whole file layout segments */
seg->offset = 0;
seg->length = NFS4_MAX_UINT64;
dprintk("GET: 0x%llx:0x%llx %d\n", seg->offset, seg->length,
seg->iomode);
return 0;
out_error:
seg->length = 0;
return nfserrno(error);
}
/*
* Open an existing file or directory.
* The wflag argument indicates write access.
* N.B. After this call fhp needs an fh_put
*/
int
nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
int wflag, struct file *filp)
{
struct dentry *dentry;
struct inode *inode;
int access, err;
access = wflag? MAY_WRITE : MAY_READ;
err = fh_verify(rqstp, fhp, type, access);
if (err)
goto out;
dentry = fhp->fh_dentry;
inode = dentry->d_inode;
/* Disallow access to files with the append-only bit set or
* with mandatory locking enabled
*/
err = nfserr_perm;
if (IS_APPEND(inode) || IS_ISMNDLK(inode))
goto out;
if (!inode->i_op || !inode->i_op->default_file_ops)
goto out;
if (wflag && (err = get_write_access(inode)) != 0)
goto out_nfserr;
memset(filp, 0, sizeof(*filp));
filp->f_op = inode->i_op->default_file_ops;
filp->f_count = 1;
filp->f_flags = wflag? O_WRONLY : O_RDONLY;
filp->f_mode = wflag? FMODE_WRITE : FMODE_READ;
filp->f_dentry = dentry;
if (wflag)
DQUOT_INIT(inode);
err = 0;
if (filp->f_op && filp->f_op->open) {
err = filp->f_op->open(inode, filp);
if (err) {
if (wflag)
put_write_access(inode);
/* I nearly added put_filp() call here, but this filp
* is really on callers stack frame. -DaveM
*/
filp->f_count--;
}
}
out_nfserr:
if (err)
err = nfserrno(-err);
out:
return err;
}
/*
* Read data from a file. count must contain the requested read count
* on entry. On return, *count contains the number of bytes actually read.
* N.B. After this call fhp needs an fh_put
*/
int
nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset,
char *buf, unsigned long *count)
{
struct raparms *ra;
mm_segment_t oldfs;
int err;
struct file file;
err = nfsd_open(rqstp, fhp, S_IFREG, OPEN_READ, &file);
if (err)
goto out;
err = nfserr_perm;
if (!file.f_op->read)
goto out_close;
/* Get readahead parameters */
ra = nfsd_get_raparms(fhp->fh_handle.fh_dev, fhp->fh_handle.fh_ino);
if (ra) {
file.f_reada = ra->p_reada;
file.f_ramax = ra->p_ramax;
file.f_raend = ra->p_raend;
file.f_ralen = ra->p_ralen;
file.f_rawin = ra->p_rawin;
}
file.f_pos = offset;
oldfs = get_fs(); set_fs(KERNEL_DS);
err = file.f_op->read(&file, buf, *count, &file.f_pos);
set_fs(oldfs);
/* Write back readahead params */
if (ra != NULL) {
dprintk("nfsd: raparms %ld %ld %ld %ld %ld\n",
file.f_reada, file.f_ramax, file.f_raend,
file.f_ralen, file.f_rawin);
ra->p_reada = file.f_reada;
ra->p_ramax = file.f_ramax;
ra->p_raend = file.f_raend;
ra->p_ralen = file.f_ralen;
ra->p_rawin = file.f_rawin;
ra->p_count -= 1;
}
if (err >= 0) {
*count = err;
err = 0;
} else
err = nfserrno(-err);
out_close:
nfsd_close(&file);
out:
return err;
}
static __be32
nfsd4_block_proc_layoutcommit(struct inode *inode,
struct nfsd4_layoutcommit *lcp)
{
loff_t new_size = lcp->lc_last_wr + 1;
struct iattr iattr = { .ia_valid = 0 };
struct iomap *iomaps;
int nr_iomaps;
int error;
nr_iomaps = nfsd4_block_decode_layoutupdate(lcp->lc_up_layout,
lcp->lc_up_len, &iomaps, 1 << inode->i_blkbits);
if (nr_iomaps < 0)
return nfserrno(nr_iomaps);
if (lcp->lc_mtime.tv_nsec == UTIME_NOW ||
timespec_compare(&lcp->lc_mtime, &inode->i_mtime) < 0)
lcp->lc_mtime = current_fs_time(inode->i_sb);
iattr.ia_valid |= ATTR_ATIME | ATTR_CTIME | ATTR_MTIME;
iattr.ia_atime = iattr.ia_ctime = iattr.ia_mtime = lcp->lc_mtime;
if (new_size > i_size_read(inode)) {
iattr.ia_valid |= ATTR_SIZE;
iattr.ia_size = new_size;
}
error = inode->i_sb->s_export_op->commit_blocks(inode, iomaps,
nr_iomaps, &iattr);
kfree(iomaps);
return nfserrno(error);
}
const struct nfsd4_layout_ops bl_layout_ops = {
.proc_getdeviceinfo = nfsd4_block_proc_getdeviceinfo,
.encode_getdeviceinfo = nfsd4_block_encode_getdeviceinfo,
.proc_layoutget = nfsd4_block_proc_layoutget,
.encode_layoutget = nfsd4_block_encode_layoutget,
.proc_layoutcommit = nfsd4_block_proc_layoutcommit,
};
__be32
nfsd4_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
struct nfs4_acl *acl)
{
__be32 error;
int host_error;
struct dentry *dentry;
struct inode *inode;
struct posix_acl *pacl = NULL, *dpacl = NULL;
unsigned int flags = 0;
/* Get inode */
error = fh_verify(rqstp, fhp, 0 /* S_IFREG */, MAY_SATTR);
if (error)
goto out;
dentry = fhp->fh_dentry;
inode = dentry->d_inode;
if (S_ISDIR(inode->i_mode))
flags = NFS4_ACL_DIR;
host_error = nfs4_acl_nfsv4_to_posix(acl, &pacl, &dpacl, flags);
if (host_error == -EINVAL) {
error = nfserr_attrnotsupp;
goto out;
} else if (host_error < 0)
goto out_nfserr;
host_error = set_nfsv4_acl_one(dentry, pacl, POSIX_ACL_XATTR_ACCESS);
if (host_error < 0)
goto out_nfserr;
if (S_ISDIR(inode->i_mode)) {
host_error = set_nfsv4_acl_one(dentry, dpacl, POSIX_ACL_XATTR_DEFAULT);
if (host_error < 0)
goto out_nfserr;
}
error = nfs_ok;
out:
posix_acl_release(pacl);
posix_acl_release(dpacl);
return (error);
out_nfserr:
if (host_error == -EOPNOTSUPP)
error = nfserr_attrnotsupp;
else
error = nfserrno(host_error);
goto out;
}
/*
* Set the Access and/or Default ACL of a file.
*/
static __be32 nfsacld_proc_setacl(struct svc_rqst * rqstp,
struct nfsd3_setaclargs *argp,
struct nfsd_attrstat *resp)
{
struct inode *inode;
svc_fh *fh;
__be32 nfserr = 0;
int error;
dprintk("nfsd: SETACL(2acl) %s\n", SVCFH_fmt(&argp->fh));
fh = fh_copy(&resp->fh, &argp->fh);
nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_SATTR);
if (nfserr)
goto out;
inode = fh->fh_dentry->d_inode;
if (!IS_POSIXACL(inode) || !inode->i_op->set_acl) {
error = -EOPNOTSUPP;
goto out_errno;
}
error = fh_want_write(fh);
if (error)
goto out_errno;
error = inode->i_op->set_acl(inode, argp->acl_access, ACL_TYPE_ACCESS);
if (error)
goto out_drop_write;
error = inode->i_op->set_acl(inode, argp->acl_default,
ACL_TYPE_DEFAULT);
if (error)
goto out_drop_write;
fh_drop_write(fh);
nfserr = fh_getattr(fh, &resp->stat);
out:
/* argp->acl_{access,default} may have been allocated in
nfssvc_decode_setaclargs. */
posix_acl_release(argp->acl_access);
posix_acl_release(argp->acl_default);
return nfserr;
out_drop_write:
fh_drop_write(fh);
out_errno:
nfserr = nfserrno(error);
goto out;
}
static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp,
struct svc_export *exp)
{
/* Check if the request originated from a secure port. */
if (!rqstp->rq_secure && EX_SECURE(exp)) {
RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
dprintk(KERN_WARNING
"nfsd: request from insecure port %s!\n",
svc_print_addr(rqstp, buf, sizeof(buf)));
return nfserr_perm;
}
/* Set user creds for this exportpoint */
return nfserrno(nfsd_setuser(rqstp, exp));
}
static __be32
nfsd4_ff_proc_getdeviceinfo(struct super_block *sb, struct svc_rqst *rqstp,
struct nfs4_client *clp, struct nfsd4_getdeviceinfo *gdp)
{
struct pnfs_ff_device_addr *da;
u16 port;
char addr[INET6_ADDRSTRLEN];
da = kzalloc(sizeof(struct pnfs_ff_device_addr), GFP_KERNEL);
if (!da)
return nfserrno(-ENOMEM);
gdp->gd_device = da;
da->version = 3;
da->minor_version = 0;
da->rsize = svc_max_payload(rqstp);
da->wsize = da->rsize;
rpc_ntop((struct sockaddr *)&rqstp->rq_daddr,
addr, INET6_ADDRSTRLEN);
if (rqstp->rq_daddr.ss_family == AF_INET) {
struct sockaddr_in *sin;
sin = (struct sockaddr_in *)&rqstp->rq_daddr;
port = ntohs(sin->sin_port);
snprintf(da->netaddr.netid, FF_NETID_LEN + 1, "tcp");
da->netaddr.netid_len = 3;
} else {
struct sockaddr_in6 *sin6;
sin6 = (struct sockaddr_in6 *)&rqstp->rq_daddr;
port = ntohs(sin6->sin6_port);
snprintf(da->netaddr.netid, FF_NETID_LEN + 1, "tcp6");
da->netaddr.netid_len = 4;
}
da->netaddr.addr_len =
snprintf(da->netaddr.addr, FF_ADDR_LEN + 1,
"%s.%hhu.%hhu", addr, port >> 8, port & 0xff);
da->tightly_coupled = false;
return 0;
}
/*
* Truncate a file.
* The calling routines must make sure to update the ctime
* field and call notify_change.
*
* XXX Nobody calls this thing? -DaveM
* N.B. After this call fhp needs an fh_put
*/
int
nfsd_truncate(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned long size)
{
struct dentry *dentry;
struct inode *inode;
struct iattr newattrs;
int err;
kernel_cap_t saved_cap;
err = fh_verify(rqstp, fhp, S_IFREG, MAY_WRITE | MAY_TRUNC);
if (err)
goto out;
dentry = fhp->fh_dentry;
inode = dentry->d_inode;
err = get_write_access(inode);
if (err)
goto out_nfserr;
/* Things look sane, lock and do it. */
fh_lock(fhp);
DQUOT_INIT(inode);
newattrs.ia_size = size;
newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME;
if (current->fsuid != 0) {
saved_cap = current->cap_effective;
cap_clear(current->cap_effective);
}
err = notify_change(dentry, &newattrs);
if (current->fsuid != 0)
current->cap_effective = saved_cap;
if (!err) {
vmtruncate(inode, size);
if (inode->i_op && inode->i_op->truncate)
inode->i_op->truncate(inode);
}
put_write_access(inode);
DQUOT_DROP(inode);
fh_unlock(fhp);
out_nfserr:
if (err)
err = nfserrno(-err);
out:
return err;
}
/*
* Set the Access and/or Default ACL of a file.
*/
static __be32 nfsd3_proc_setacl(struct svc_rqst * rqstp,
struct nfsd3_setaclargs *argp,
struct nfsd3_attrstat *resp)
{
struct inode *inode;
svc_fh *fh;
__be32 nfserr = 0;
int error;
fh = fh_copy(&resp->fh, &argp->fh);
nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_SATTR);
if (nfserr)
goto out;
inode = d_inode(fh->fh_dentry);
if (!IS_POSIXACL(inode) || !inode->i_op->set_acl) {
error = -EOPNOTSUPP;
goto out_errno;
}
error = fh_want_write(fh);
if (error)
goto out_errno;
error = inode->i_op->set_acl(inode, argp->acl_access, ACL_TYPE_ACCESS);
if (error)
goto out_drop_write;
error = inode->i_op->set_acl(inode, argp->acl_default,
ACL_TYPE_DEFAULT);
out_drop_write:
fh_drop_write(fh);
out_errno:
nfserr = nfserrno(error);
out:
/* argp->acl_{access,default} may have been allocated in
nfs3svc_decode_setaclargs. */
posix_acl_release(argp->acl_access);
posix_acl_release(argp->acl_default);
RETURN_STATUS(nfserr);
}
/*
* Read a symlink. On entry, *lenp must contain the maximum path length that
* fits into the buffer. On return, it contains the true length.
* N.B. After this call fhp needs an fh_put
*/
int
nfsd_readlink(struct svc_rqst *rqstp, struct svc_fh *fhp, char *buf, int *lenp)
{
struct dentry *dentry;
struct inode *inode;
mm_segment_t oldfs;
int err;
err = fh_verify(rqstp, fhp, S_IFLNK, MAY_READ);
if (err)
goto out;
dentry = fhp->fh_dentry;
inode = dentry->d_inode;
err = nfserr_inval;
if (!inode->i_op || !inode->i_op->readlink)
goto out;
UPDATE_ATIME(inode);
/* N.B. Why does this call need a get_fs()?? */
oldfs = get_fs(); set_fs(KERNEL_DS);
err = inode->i_op->readlink(dentry, buf, *lenp);
set_fs(oldfs);
if (err < 0)
goto out_nfserr;
*lenp = err;
err = 0;
out:
return err;
out_nfserr:
err = nfserrno(-err);
goto out;
}
/*
* Create a symlink and look up its inode
* N.B. After this call _both_ fhp and resfhp need an fh_put
*/
int
nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
char *fname, int flen,
char *path, int plen,
struct svc_fh *resfhp)
{
struct dentry *dentry, *dnew;
struct inode *dirp;
int err;
err = nfserr_noent;
if (!flen || !plen)
goto out;
err = fh_verify(rqstp, fhp, S_IFDIR, MAY_CREATE);
if (err)
goto out;
dentry = fhp->fh_dentry;
err = nfserr_perm;
if (nfsd_iscovered(dentry, fhp->fh_export))
goto out;
dirp = dentry->d_inode;
if (!dirp->i_op || !dirp->i_op->symlink)
goto out;
dnew = lookup_dentry(fname, dget(dentry), 0);
err = PTR_ERR(dnew);
if (IS_ERR(dnew))
goto out_nfserr;
/*
* Lock the parent before checking for existence
*/
err = fh_lock_parent(fhp, dnew);
if (err)
goto out_compose;
err = nfserr_exist;
if (!dnew->d_inode) {
DQUOT_INIT(dirp);
err = dirp->i_op->symlink(dirp, dnew, path);
DQUOT_DROP(dirp);
if (!err) {
if (EX_ISSYNC(fhp->fh_export))
write_inode_now(dirp);
} else
err = nfserrno(-err);
}
fh_unlock(fhp);
/* Compose the fh so the dentry will be freed ... */
out_compose:
fh_compose(resfhp, fhp->fh_export, dnew);
out:
return err;
out_nfserr:
err = nfserrno(-err);
goto out;
}
/*
* Get the Access and/or Default ACL of a file.
*/
static __be32 nfsd3_proc_getacl(struct svc_rqst * rqstp,
struct nfsd3_getaclargs *argp, struct nfsd3_getaclres *resp)
{
svc_fh *fh;
struct posix_acl *acl;
__be32 nfserr = 0;
fh = fh_copy(&resp->fh, &argp->fh);
nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP);
if (nfserr)
RETURN_STATUS(nfserr);
if (argp->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT))
RETURN_STATUS(nfserr_inval);
resp->mask = argp->mask;
if (resp->mask & (NFS_ACL|NFS_ACLCNT)) {
acl = nfsd_get_posix_acl(fh, ACL_TYPE_ACCESS);
if (IS_ERR(acl)) {
int err = PTR_ERR(acl);
if (err == -ENODATA || err == -EOPNOTSUPP)
acl = NULL;
else {
nfserr = nfserrno(err);
goto fail;
}
}
if (acl == NULL) {
/* Solaris returns the inode's minimum ACL. */
struct inode *inode = fh->fh_dentry->d_inode;
acl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
}
resp->acl_access = acl;
}
if (resp->mask & (NFS_DFACL|NFS_DFACLCNT)) {
/* Check how Solaris handles requests for the Default ACL
of a non-directory! */
acl = nfsd_get_posix_acl(fh, ACL_TYPE_DEFAULT);
if (IS_ERR(acl)) {
int err = PTR_ERR(acl);
if (err == -ENODATA || err == -EOPNOTSUPP)
acl = NULL;
else {
nfserr = nfserrno(err);
goto fail;
}
}
resp->acl_default = acl;
}
/* resp->acl_{access,default} are released in nfs3svc_release_getacl. */
RETURN_STATUS(0);
fail:
posix_acl_release(resp->acl_access);
posix_acl_release(resp->acl_default);
RETURN_STATUS(nfserr);
}
/*
* Look up one component of a pathname.
* N.B. After this call _both_ fhp and resfh need an fh_put
*/
int
nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
int len, struct svc_fh *resfh)
{
struct svc_export *exp;
struct dentry *dparent, *dchild;
int err;
dprintk("nfsd: nfsd_lookup(fh %p, %s)\n", SVCFH_DENTRY(fhp), name);
/* Obtain dentry and export. */
err = fh_verify(rqstp, fhp, S_IFDIR, MAY_EXEC);
if (err)
goto out;
dparent = fhp->fh_dentry;
exp = fhp->fh_export;
#if 0
err = nfsd_permission(exp, dparent, MAY_EXEC);
if (err)
goto out;
#endif
err = nfserr_noent;
if (fs_off_limits(dparent->d_sb))
goto out;
err = nfserr_acces;
if (nfsd_iscovered(dparent, exp))
goto out;
/* Lookup the name, but don't follow links */
dchild = lookup_dentry(name, dget(dparent), 0);
if (IS_ERR(dchild))
goto out_nfserr;
/*
* check if we have crossed a mount point ...
*/
if (dchild->d_sb != dparent->d_sb) {
struct dentry *tdentry;
tdentry = dchild->d_covers;
if (tdentry == dchild)
goto out_dput;
dput(dchild);
dchild = dget(tdentry);
if (dchild->d_sb != dparent->d_sb) {
printk("nfsd_lookup: %s/%s crossed mount point!\n", dparent->d_name.name, dchild->d_name.name);
goto out_dput;
}
}
/*
* Note: we compose the file handle now, but as the
* dentry may be negative, it may need to be updated.
*/
fh_compose(resfh, exp, dchild);
err = nfserr_noent;
if (dchild->d_inode)
err = 0;
out:
return err;
out_nfserr:
err = nfserrno(-PTR_ERR(dchild));
goto out;
out_dput:
dput(dchild);
err = nfserr_acces;
goto out;
}
/*
* Look up one component of a pathname.
* N.B. After this call _both_ fhp and resfh need an fh_put
*
* If the lookup would cross a mountpoint, and the mounted filesystem
* is exported to the client with NFSEXP_CROSSMNT, then the lookup is
* accepted as it stands and the mounted directory is
* returned. Otherwise the covered directory is returned.
* NOTE: this mountpoint crossing is not supported properly by all
* clients and is explicitly disallowed for NFSv3
* NeilBrown <*****@*****.**>
*/
int
nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
int len, struct svc_fh *resfh)
{
struct svc_export *exp;
struct dentry *dparent;
struct dentry *dentry;
int err;
dprintk("nfsd: nfsd_lookup(fh %s, %.*s)\n", SVCFH_fmt(fhp), len,name);
/* Obtain dentry and export. */
err = fh_verify(rqstp, fhp, S_IFDIR, MAY_EXEC);
if (err)
goto out;
dparent = fhp->fh_dentry;
exp = fhp->fh_export;
err = nfserr_acces;
/* Lookup the name, but don't follow links */
if (isdotent(name, len)) {
if (len==1)
dentry = dget(dparent);
else { /* must be ".." */
/* checking mountpoint crossing is very different when stepping up */
if (dparent == exp->ex_dentry) {
if (!EX_CROSSMNT(exp))
dentry = dget(dparent); /* .. == . just like at / */
else
{
struct svc_export *exp2 = NULL;
struct dentry *dp;
struct vfsmount *mnt = mntget(exp->ex_mnt);
dentry = dget(dparent);
while(follow_up(&mnt, &dentry))
;
dp = dget(dentry->d_parent);
dput(dentry);
dentry = dp;
for ( ; exp2 == NULL && dp->d_parent != dp;
dp=dp->d_parent)
exp2 = exp_get(exp->ex_client, dp->d_inode->i_dev, dp->d_inode->i_ino);
if (exp2==NULL) {
dput(dentry);
dentry = dget(dparent);
} else {
exp = exp2;
}
mntput(mnt);
}
} else
dentry = dget(dparent->d_parent);
}
} else {
fh_lock(fhp);
dentry = lookup_one_len(name, dparent, len);
err = PTR_ERR(dentry);
if (IS_ERR(dentry))
goto out_nfserr;
/*
* check if we have crossed a mount point ...
*/
if (d_mountpoint(dentry)) {
struct svc_export *exp2 = NULL;
struct vfsmount *mnt = mntget(exp->ex_mnt);
struct dentry *mounts = dget(dentry);
while (follow_down(&mnt,&mounts)&&d_mountpoint(mounts))
;
exp2 = exp_get(rqstp->rq_client,
mounts->d_inode->i_dev,
mounts->d_inode->i_ino);
if (exp2 && EX_CROSSMNT(exp2)) {
/* successfully crossed mount point */
exp = exp2;
dput(dentry);
dentry = mounts;
} else
dput(mounts);
mntput(mnt);
}
}
/*
* Note: we compose the file handle now, but as the
* dentry may be negative, it may need to be updated.
*/
err = fh_compose(resfh, exp, dentry, fhp);
if (!err && !dentry->d_inode)
err = nfserr_noent;
out:
return err;
out_nfserr:
err = nfserrno(err);
goto out;
}
/*
* Set various file attributes.
* N.B. After this call fhp needs an fh_put
*/
int
nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
int check_guard, time_t guardtime)
{
struct dentry *dentry;
struct inode *inode;
int accmode = MAY_SATTR;
int ftype = 0;
int imode;
int err;
int size_change = 0;
if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
accmode |= MAY_WRITE|MAY_OWNER_OVERRIDE;
if (iap->ia_valid & ATTR_SIZE)
ftype = S_IFREG;
/* Get inode */
err = fh_verify(rqstp, fhp, ftype, accmode);
if (err || !iap->ia_valid)
goto out;
dentry = fhp->fh_dentry;
inode = dentry->d_inode;
/* NFSv2 does not differentiate between "set-[ac]time-to-now"
* which only requires access, and "set-[ac]time-to-X" which
* requires ownership.
* So if it looks like it might be "set both to the same time which
* is close to now", and if inode_change_ok fails, then we
* convert to "set to now" instead of "set to explicit time"
*
* We only call inode_change_ok as the last test as technically
* it is not an interface that we should be using. It is only
* valid if the filesystem does not define it's own i_op->setattr.
*/
#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET)
#define MAX_TOUCH_TIME_ERROR (30*60)
if ((iap->ia_valid & BOTH_TIME_SET) == BOTH_TIME_SET
&& iap->ia_mtime == iap->ia_atime
) {
/* Looks probable. Now just make sure time is in the right ballpark.
* Solaris, at least, doesn't seem to care what the time request is.
* We require it be within 30 minutes of now.
*/
time_t delta = iap->ia_atime - CURRENT_TIME;
if (delta<0) delta = -delta;
if (delta < MAX_TOUCH_TIME_ERROR &&
inode_change_ok(inode, iap) != 0) {
/* turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME
* this will cause notify_change to set these times to "now"
*/
iap->ia_valid &= ~BOTH_TIME_SET;
}
}
/* The size case is special. It changes the file as well as the attributes. */
if (iap->ia_valid & ATTR_SIZE) {
if (iap->ia_size < inode->i_size) {
err = nfsd_permission(fhp->fh_export, dentry, MAY_TRUNC|MAY_OWNER_OVERRIDE);
if (err)
goto out;
}
/*
* If we are changing the size of the file, then
* we need to break all leases.
*/
err = get_lease(inode, FMODE_WRITE);
if (err)
goto out_nfserr;
err = get_write_access(inode);
if (err)
goto out_nfserr;
err = locks_verify_truncate(inode, NULL, iap->ia_size);
if (err) {
put_write_access(inode);
goto out_nfserr;
}
DQUOT_INIT(inode);
}
imode = inode->i_mode;
if (iap->ia_valid & ATTR_MODE) {
iap->ia_mode &= S_IALLUGO;
imode = iap->ia_mode |= (imode & ~S_IALLUGO);
}
/* Revoke setuid/setgid bit on chown/chgrp */
if ((iap->ia_valid & ATTR_UID) && (imode & S_ISUID)
&& iap->ia_uid != inode->i_uid) {
iap->ia_valid |= ATTR_MODE;
iap->ia_mode = imode &= ~S_ISUID;
}
if ((iap->ia_valid & ATTR_GID) && (imode & S_ISGID)
&& iap->ia_gid != inode->i_gid) {
iap->ia_valid |= ATTR_MODE;
iap->ia_mode = imode &= ~S_ISGID;
}
/* Change the attributes. */
iap->ia_valid |= ATTR_CTIME;
if (iap->ia_valid & ATTR_SIZE) {
fh_lock(fhp);
size_change = 1;
}
err = nfserr_notsync;
if (!check_guard || guardtime == inode->i_ctime) {
err = notify_change(dentry, iap);
err = nfserrno(err);
}
if (size_change) {
fh_unlock(fhp);
put_write_access(inode);
}
if (!err)
if (EX_ISSYNC(fhp->fh_export))
write_inode_now(inode, 1);
out:
return err;
out_nfserr:
err = nfserrno(err);
goto out;
}
/*
* Set various file attributes.
* N.B. After this call fhp needs an fh_put
*/
int
nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap)
{
struct dentry *dentry;
struct inode *inode;
int accmode = MAY_SATTR;
int ftype = 0;
int imode;
int err;
if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
accmode |= MAY_WRITE;
if (iap->ia_valid & ATTR_SIZE)
ftype = S_IFREG;
/* Get inode */
err = fh_verify(rqstp, fhp, ftype, accmode);
if (err)
goto out;
dentry = fhp->fh_dentry;
inode = dentry->d_inode;
err = inode_change_ok(inode, iap);
if (err)
goto out_nfserr;
/* The size case is special... */
if (iap->ia_valid & ATTR_SIZE) {
if (!S_ISREG(inode->i_mode))
printk("nfsd_setattr: size change??\n");
if (iap->ia_size < inode->i_size) {
err = nfsd_permission(fhp->fh_export, dentry, MAY_TRUNC);
if (err)
goto out;
}
err = get_write_access(inode);
if (err)
goto out_nfserr;
/* N.B. Should we update the inode cache here? */
inode->i_size = iap->ia_size;
if (inode->i_op && inode->i_op->truncate)
inode->i_op->truncate(inode);
mark_inode_dirty(inode);
put_write_access(inode);
iap->ia_valid &= ~ATTR_SIZE;
iap->ia_valid |= ATTR_MTIME;
iap->ia_mtime = CURRENT_TIME;
}
imode = inode->i_mode;
if (iap->ia_valid & ATTR_MODE) {
iap->ia_mode &= S_IALLUGO;
imode = iap->ia_mode |= (imode & ~S_IALLUGO);
}
/* Revoke setuid/setgid bit on chown/chgrp */
if ((iap->ia_valid & ATTR_UID) && (imode & S_ISUID)
&& iap->ia_uid != inode->i_uid) {
iap->ia_valid |= ATTR_MODE;
iap->ia_mode = imode &= ~S_ISUID;
}
if ((iap->ia_valid & ATTR_GID) && (imode & S_ISGID)
&& iap->ia_gid != inode->i_gid) {
iap->ia_valid |= ATTR_MODE;
iap->ia_mode = imode &= ~S_ISGID;
}
/* Change the attributes. */
if (iap->ia_valid) {
kernel_cap_t saved_cap = 0;
iap->ia_valid |= ATTR_CTIME;
iap->ia_ctime = CURRENT_TIME;
if (current->fsuid != 0) {
saved_cap = current->cap_effective;
cap_clear(current->cap_effective);
}
err = notify_change(dentry, iap);
if (current->fsuid != 0)
current->cap_effective = saved_cap;
if (err)
goto out_nfserr;
if (EX_ISSYNC(fhp->fh_export))
write_inode_now(inode);
}
err = 0;
out:
return err;
out_nfserr:
err = nfserrno(-err);
goto out;
}
/*
* Look up one component of a pathname.
* N.B. After this call _both_ fhp and resfh need an fh_put
*
* If the lookup would cross a mountpoint, and the mounted filesystem
* is exported to the client with NFSEXP_NOHIDE, then the lookup is
* accepted as it stands and the mounted directory is
* returned. Otherwise the covered directory is returned.
* NOTE: this mountpoint crossing is not supported properly by all
* clients and is explicitly disallowed for NFSv3
* NeilBrown <*****@*****.**>
*/
int
nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
int len, struct svc_fh *resfh)
{
struct svc_export *exp;
struct dentry *dparent;
struct dentry *dentry;
int err;
dprintk("nfsd: nfsd_lookup(fh %s, %.*s)\n", SVCFH_fmt(fhp), len,name);
/* Obtain dentry and export. */
err = fh_verify(rqstp, fhp, S_IFDIR, MAY_EXEC);
if (err)
return err;
dparent = fhp->fh_dentry;
exp = fhp->fh_export;
exp_get(exp);
err = nfserr_acces;
/* Lookup the name, but don't follow links */
if (isdotent(name, len)) {
if (len==1)
dentry = dget(dparent);
else if (dparent != exp->ex_dentry) {
dentry = dget_parent(dparent);
} else if (!EX_NOHIDE(exp))
dentry = dget(dparent); /* .. == . just like at / */
else {
/* checking mountpoint crossing is very different when stepping up */
struct svc_export *exp2 = NULL;
struct dentry *dp;
struct vfsmount *mnt = mntget(exp->ex_mnt);
dentry = dget(dparent);
while(dentry == mnt->mnt_root && follow_up(&mnt, &dentry))
;
dp = dget_parent(dentry);
dput(dentry);
dentry = dp;
exp2 = exp_parent(exp->ex_client, mnt, dentry,
&rqstp->rq_chandle);
if (IS_ERR(exp2)) {
err = PTR_ERR(exp2);
dput(dentry);
mntput(mnt);
goto out_nfserr;
}
if (!exp2) {
dput(dentry);
dentry = dget(dparent);
} else {
exp_put(exp);
exp = exp2;
}
mntput(mnt);
}
} else {
fh_lock(fhp);
dentry = lookup_one_len(name, dparent, len);
err = PTR_ERR(dentry);
if (IS_ERR(dentry))
goto out_nfserr;
/*
* check if we have crossed a mount point ...
*/
if (d_mountpoint(dentry)) {
if ((err = nfsd_cross_mnt(rqstp, &dentry, &exp))) {
dput(dentry);
goto out_nfserr;
}
}
}
/*
* Note: we compose the file handle now, but as the
* dentry may be negative, it may need to be updated.
*/
err = fh_compose(resfh, exp, dentry, fhp);
if (!err && !dentry->d_inode)
err = nfserr_noent;
dput(dentry);
out:
exp_put(exp);
return err;
out_nfserr:
err = nfserrno(err);
goto out;
}
/*
* Write data to a file.
* The stable flag requests synchronous writes.
* N.B. After this call fhp needs an fh_put
*/
int
nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset,
char *buf, unsigned long cnt, int stable)
{
struct svc_export *exp;
struct file file;
struct dentry *dentry;
struct inode *inode;
mm_segment_t oldfs;
int err = 0;
#ifdef CONFIG_QUOTA
uid_t saved_euid;
#endif
if (!cnt)
goto out;
err = nfsd_open(rqstp, fhp, S_IFREG, OPEN_WRITE, &file);
if (err)
goto out;
err = nfserr_perm;
if (!file.f_op->write)
goto out_close;
dentry = file.f_dentry;
inode = dentry->d_inode;
exp = fhp->fh_export;
/*
* Request sync writes if
* - the sync export option has been set, or
* - the client requested O_SYNC behavior (NFSv3 feature).
* When gathered writes have been configured for this volume,
* flushing the data to disk is handled separately below.
*/
if ((stable || (stable = EX_ISSYNC(exp))) && !EX_WGATHER(exp))
file.f_flags |= O_SYNC;
fh_lock(fhp); /* lock inode */
file.f_pos = offset; /* set write offset */
/* Write the data. */
oldfs = get_fs(); set_fs(KERNEL_DS);
#ifdef CONFIG_QUOTA
/* This is for disk quota. */
saved_euid = current->euid;
current->euid = current->fsuid;
err = file.f_op->write(&file, buf, cnt, &file.f_pos);
current->euid = saved_euid;
#else
err = file.f_op->write(&file, buf, cnt, &file.f_pos);
#endif
set_fs(oldfs);
/* clear setuid/setgid flag after write */
if (err >= 0 && (inode->i_mode & (S_ISUID | S_ISGID))) {
struct iattr ia;
kernel_cap_t saved_cap;
ia.ia_valid = ATTR_MODE;
ia.ia_mode = inode->i_mode & ~(S_ISUID | S_ISGID);
if (current->fsuid != 0) {
saved_cap = current->cap_effective;
cap_clear(current->cap_effective);
}
notify_change(dentry, &ia);
if (current->fsuid != 0)
current->cap_effective = saved_cap;
}
fh_unlock(fhp); /* unlock inode */
if (err >= 0 && stable) {
static unsigned long last_ino = 0;
static kdev_t last_dev = NODEV;
/*
* Gathered writes: If another process is currently
* writing to the file, there's a high chance
* this is another nfsd (triggered by a bulk write
* from a client's biod). Rather than syncing the
* file with each write request, we sleep for 10 msec.
*
* I don't know if this roughly approximates
* C. Juszak's idea of gathered writes, but it's a
* nice and simple solution (IMHO), and it seems to
* work:-)
*/
if (EX_WGATHER(exp) && (inode->i_writecount > 1
|| (last_ino == inode->i_ino && last_dev == inode->i_dev))) {
#if 0
interruptible_sleep_on_timeout(&inode->i_wait, 10 * HZ / 1000);
#else
dprintk("nfsd: write defer %d\n", current->pid);
schedule_timeout((HZ+99)/100);
dprintk("nfsd: write resume %d\n", current->pid);
#endif
}
if (inode->i_state & I_DIRTY) {
dprintk("nfsd: write sync %d\n", current->pid);
nfsd_sync(inode, &file);
write_inode_now(inode);
}
wake_up(&inode->i_wait);
last_ino = inode->i_ino;
last_dev = inode->i_dev;
}
dprintk("nfsd: write complete\n");
if (err >= 0)
err = 0;
else
err = nfserrno(-err);
out_close:
nfsd_close(&file);
out:
return err;
}
/*
* Create a file (regular, directory, device, fifo); UNIX sockets
* not yet implemented.
* If the response fh has been verified, the parent directory should
* already be locked. Note that the parent directory is left locked.
*
* N.B. Every call to nfsd_create needs an fh_put for _both_ fhp and resfhp
*/
int
nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
char *fname, int flen, struct iattr *iap,
int type, dev_t rdev, struct svc_fh *resfhp)
{
struct dentry *dentry, *dchild;
struct inode *dirp;
nfsd_dirop_t opfunc = NULL;
int err;
err = nfserr_perm;
if (!flen)
goto out;
err = fh_verify(rqstp, fhp, S_IFDIR, MAY_CREATE);
if (err)
goto out;
dentry = fhp->fh_dentry;
dirp = dentry->d_inode;
err = nfserr_notdir;
if(!dirp->i_op || !dirp->i_op->lookup)
goto out;
/*
* Check whether the response file handle has been verified yet.
* If it has, the parent directory should already be locked.
*/
if (!resfhp->fh_dverified) {
dchild = lookup_dentry(fname, dget(dentry), 0);
err = PTR_ERR(dchild);
if (IS_ERR(dchild))
goto out_nfserr;
fh_compose(resfhp, fhp->fh_export, dchild);
/* Lock the parent and check for errors ... */
err = fh_lock_parent(fhp, dchild);
if (err)
goto out;
} else {
dchild = resfhp->fh_dentry;
if (!fhp->fh_locked)
printk(KERN_ERR
"nfsd_create: parent %s/%s not locked!\n",
dentry->d_parent->d_name.name,
dentry->d_name.name);
}
/*
* Make sure the child dentry is still negative ...
*/
err = nfserr_exist;
if (dchild->d_inode) {
printk(KERN_WARNING
"nfsd_create: dentry %s/%s not negative!\n",
dentry->d_name.name, dchild->d_name.name);
goto out;
}
/*
* Get the dir op function pointer.
*/
err = nfserr_perm;
switch (type) {
case S_IFREG:
opfunc = (nfsd_dirop_t) dirp->i_op->create;
break;
case S_IFDIR:
opfunc = (nfsd_dirop_t) dirp->i_op->mkdir;
break;
case S_IFCHR:
case S_IFBLK:
/* The client is _NOT_ required to do security enforcement */
if(!capable(CAP_SYS_ADMIN))
{
err = -EPERM;
goto out;
}
case S_IFIFO:
case S_IFSOCK:
opfunc = dirp->i_op->mknod;
break;
}
if (!opfunc)
goto out;
if (!(iap->ia_valid & ATTR_MODE))
iap->ia_mode = 0;
/*
* Call the dir op function to create the object.
*/
DQUOT_INIT(dirp);
err = opfunc(dirp, dchild, iap->ia_mode, rdev);
DQUOT_DROP(dirp);
if (err < 0)
goto out_nfserr;
if (EX_ISSYNC(fhp->fh_export))
write_inode_now(dirp);
/*
* Update the file handle to get the new inode info.
*/
fh_update(resfhp);
/* Set file attributes. Mode has already been set and
* setting uid/gid works only for root. Irix appears to
* send along the gid when it tries to implement setgid
* directories via NFS.
*/
err = 0;
if ((iap->ia_valid &= (ATTR_UID|ATTR_GID|ATTR_MODE)) != 0)
err = nfsd_setattr(rqstp, resfhp, iap);
out:
return err;
out_nfserr:
err = nfserrno(-err);
goto out;
}
__be32
nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
const char *name, unsigned int len,
struct svc_export **exp_ret, struct dentry **dentry_ret)
{
struct svc_export *exp;
struct dentry *dparent;
struct dentry *dentry;
__be32 err;
int host_err;
dprintk("nfsd: nfsd_lookup(fh %s, %.*s)\n", SVCFH_fmt(fhp), len,name);
/* Obtain dentry and export. */
err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC);
if (err)
return err;
dparent = fhp->fh_dentry;
exp = fhp->fh_export;
exp_get(exp);
/* Lookup the name, but don't follow links */
if (isdotent(name, len)) {
if (len==1)
dentry = dget(dparent);
else if (dparent != exp->ex_path.dentry)
dentry = dget_parent(dparent);
else if (!EX_NOHIDE(exp))
dentry = dget(dparent); /* .. == . just like at / */
else {
/* checking mountpoint crossing is very different when stepping up */
struct svc_export *exp2 = NULL;
struct dentry *dp;
struct vfsmount *mnt = mntget(exp->ex_path.mnt);
dentry = dget(dparent);
while(dentry == mnt->mnt_root && follow_up(&mnt, &dentry))
;
dp = dget_parent(dentry);
dput(dentry);
dentry = dp;
exp2 = rqst_exp_parent(rqstp, mnt, dentry);
if (PTR_ERR(exp2) == -ENOENT) {
dput(dentry);
dentry = dget(dparent);
} else if (IS_ERR(exp2)) {
host_err = PTR_ERR(exp2);
dput(dentry);
mntput(mnt);
goto out_nfserr;
} else {
exp_put(exp);
exp = exp2;
}
mntput(mnt);
}
} else {
fh_lock(fhp);
dentry = lookup_one_len(name, dparent, len);
host_err = PTR_ERR(dentry);
if (IS_ERR(dentry))
goto out_nfserr;
/*
* check if we have crossed a mount point ...
*/
if (d_mountpoint(dentry)) {
if ((host_err = nfsd_cross_mnt(rqstp, &dentry, &exp))) {
dput(dentry);
goto out_nfserr;
}
}
}
*dentry_ret = dentry;
*exp_ret = exp;
return 0;
out_nfserr:
exp_put(exp);
return nfserrno(host_err);
}
static __be32
nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
struct nfsd4_layoutget *args)
{
struct nfsd4_layout_seg *seg = &args->lg_seg;
struct super_block *sb = inode->i_sb;
u32 block_size = (1 << inode->i_blkbits);
struct pnfs_block_extent *bex;
struct iomap iomap;
u32 device_generation = 0;
int error;
/*
* We do not attempt to support I/O smaller than the fs block size,
* or not aligned to it.
*/
if (args->lg_minlength < block_size) {
dprintk("pnfsd: I/O too small\n");
goto out_layoutunavailable;
}
if (seg->offset & (block_size - 1)) {
dprintk("pnfsd: I/O misaligned\n");
goto out_layoutunavailable;
}
/*
* Some clients barf on non-zero block numbers for NONE or INVALID
* layouts, so make sure to zero the whole structure.
*/
error = -ENOMEM;
bex = kzalloc(sizeof(*bex), GFP_KERNEL);
if (!bex)
goto out_error;
args->lg_content = bex;
error = sb->s_export_op->map_blocks(inode, seg->offset, seg->length,
&iomap, seg->iomode != IOMODE_READ,
&device_generation);
if (error) {
if (error == -ENXIO)
goto out_layoutunavailable;
goto out_error;
}
if (iomap.length < args->lg_minlength) {
dprintk("pnfsd: extent smaller than minlength\n");
goto out_layoutunavailable;
}
switch (iomap.type) {
case IOMAP_MAPPED:
if (seg->iomode == IOMODE_READ)
bex->es = PNFS_BLOCK_READ_DATA;
else
bex->es = PNFS_BLOCK_READWRITE_DATA;
bex->soff = (iomap.blkno << 9);
break;
case IOMAP_UNWRITTEN:
if (seg->iomode & IOMODE_RW) {
/*
* Crack monkey special case from section 2.3.1.
*/
if (args->lg_minlength == 0) {
dprintk("pnfsd: no soup for you!\n");
goto out_layoutunavailable;
}
bex->es = PNFS_BLOCK_INVALID_DATA;
bex->soff = (iomap.blkno << 9);
break;
}
/*FALLTHRU*/
case IOMAP_HOLE:
if (seg->iomode == IOMODE_READ) {
bex->es = PNFS_BLOCK_NONE_DATA;
break;
}
/*FALLTHRU*/
case IOMAP_DELALLOC:
default:
WARN(1, "pnfsd: filesystem returned %d extent\n", iomap.type);
goto out_layoutunavailable;
}
error = nfsd4_set_deviceid(&bex->vol_id, fhp, device_generation);
if (error)
goto out_error;
bex->foff = iomap.offset;
bex->len = iomap.length;
seg->offset = iomap.offset;
seg->length = iomap.length;
dprintk("GET: %lld:%lld %d\n", bex->foff, bex->len, bex->es);
return 0;
out_error:
seg->length = 0;
return nfserrno(error);
out_layoutunavailable:
seg->length = 0;
return nfserr_layoutunavailable;
}
/*
* Create a hardlink
* N.B. After this call _both_ ffhp and tfhp need an fh_put
*/
int
nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
char *fname, int len, struct svc_fh *tfhp)
{
struct dentry *ddir, *dnew, *dold;
struct inode *dirp, *dest;
int err;
err = fh_verify(rqstp, ffhp, S_IFDIR, MAY_CREATE);
if (err)
goto out;
err = fh_verify(rqstp, tfhp, S_IFREG, MAY_NOP);
if (err)
goto out;
err = nfserr_perm;
if (!len)
goto out;
ddir = ffhp->fh_dentry;
dirp = ddir->d_inode;
dnew = lookup_dentry(fname, dget(ddir), 0);
err = PTR_ERR(dnew);
if (IS_ERR(dnew))
goto out_nfserr;
/*
* Lock the parent before checking for existence
*/
err = fh_lock_parent(ffhp, dnew);
if (err)
goto out_dput;
err = nfserr_exist;
if (dnew->d_inode)
goto out_unlock;
dold = tfhp->fh_dentry;
dest = dold->d_inode;
err = nfserr_acces;
if (nfsd_iscovered(ddir, ffhp->fh_export))
goto out_unlock;
/* FIXME: nxdev for NFSv3 */
if (dirp->i_dev != dest->i_dev)
goto out_unlock;
err = nfserr_perm;
if (IS_IMMUTABLE(dest) /* || IS_APPEND(dest) */ )
goto out_unlock;
if (!dirp->i_op || !dirp->i_op->link)
goto out_unlock;
DQUOT_INIT(dirp);
err = dirp->i_op->link(dold, dirp, dnew);
DQUOT_DROP(dirp);
if (!err) {
if (EX_ISSYNC(ffhp->fh_export)) {
write_inode_now(dirp);
write_inode_now(dest);
}
} else
err = nfserrno(-err);
out_unlock:
fh_unlock(ffhp);
out_dput:
dput(dnew);
out:
return err;
out_nfserr:
err = nfserrno(-err);
goto out;
}
/*
* Set various file attributes.
* N.B. After this call fhp needs an fh_put
*/
__be32
nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
int check_guard, time_t guardtime)
{
struct dentry *dentry;
struct inode *inode;
int accmode = NFSD_MAY_SATTR;
int ftype = 0;
__be32 err;
int host_err;
int size_change = 0;
if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
if (iap->ia_valid & ATTR_SIZE)
ftype = S_IFREG;
/* Get inode */
err = fh_verify(rqstp, fhp, ftype, accmode);
if (err)
goto out;
dentry = fhp->fh_dentry;
inode = dentry->d_inode;
/* Ignore any mode updates on symlinks */
if (S_ISLNK(inode->i_mode))
iap->ia_valid &= ~ATTR_MODE;
if (!iap->ia_valid)
goto out;
/*
* NFSv2 does not differentiate between "set-[ac]time-to-now"
* which only requires access, and "set-[ac]time-to-X" which
* requires ownership.
* So if it looks like it might be "set both to the same time which
* is close to now", and if inode_change_ok fails, then we
* convert to "set to now" instead of "set to explicit time"
*
* We only call inode_change_ok as the last test as technically
* it is not an interface that we should be using. It is only
* valid if the filesystem does not define it's own i_op->setattr.
*/
#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET)
#define MAX_TOUCH_TIME_ERROR (30*60)
if ((iap->ia_valid & BOTH_TIME_SET) == BOTH_TIME_SET &&
iap->ia_mtime.tv_sec == iap->ia_atime.tv_sec) {
/*
* Looks probable.
*
* Now just make sure time is in the right ballpark.
* Solaris, at least, doesn't seem to care what the time
* request is. We require it be within 30 minutes of now.
*/
time_t delta = iap->ia_atime.tv_sec - get_seconds();
if (delta < 0)
delta = -delta;
if (delta < MAX_TOUCH_TIME_ERROR &&
inode_change_ok(inode, iap) != 0) {
/*
* Turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME.
* This will cause notify_change to set these times
* to "now"
*/
iap->ia_valid &= ~BOTH_TIME_SET;
}
}
/*
* The size case is special.
* It changes the file as well as the attributes.
*/
if (iap->ia_valid & ATTR_SIZE) {
if (iap->ia_size < inode->i_size) {
err = nfsd_permission(rqstp, fhp->fh_export, dentry,
NFSD_MAY_TRUNC|NFSD_MAY_OWNER_OVERRIDE);
if (err)
goto out;
}
/*
* If we are changing the size of the file, then
* we need to break all leases.
*/
host_err = break_lease(inode, FMODE_WRITE | O_NONBLOCK);
if (host_err == -EWOULDBLOCK)
host_err = -ETIMEDOUT;
if (host_err) /* ENOMEM or EWOULDBLOCK */
goto out_nfserr;
host_err = get_write_access(inode);
if (host_err)
goto out_nfserr;
size_change = 1;
host_err = locks_verify_truncate(inode, NULL, iap->ia_size);
if (host_err) {
put_write_access(inode);
goto out_nfserr;
}
DQUOT_INIT(inode);
}
/* sanitize the mode change */
if (iap->ia_valid & ATTR_MODE) {
iap->ia_mode &= S_IALLUGO;
iap->ia_mode |= (inode->i_mode & ~S_IALLUGO);
}
/* Revoke setuid/setgid on chown */
if (((iap->ia_valid & ATTR_UID) && iap->ia_uid != inode->i_uid) ||
((iap->ia_valid & ATTR_GID) && iap->ia_gid != inode->i_gid)) {
iap->ia_valid |= ATTR_KILL_PRIV;
if (iap->ia_valid & ATTR_MODE) {
/* we're setting mode too, just clear the s*id bits */
iap->ia_mode &= ~S_ISUID;
if (iap->ia_mode & S_IXGRP)
iap->ia_mode &= ~S_ISGID;
} else {
/* set ATTR_KILL_* bits and let VFS handle it */
iap->ia_valid |= (ATTR_KILL_SUID | ATTR_KILL_SGID);
}
}
/* Change the attributes. */
iap->ia_valid |= ATTR_CTIME;
err = nfserr_notsync;
if (!check_guard || guardtime == inode->i_ctime.tv_sec) {
fh_lock(fhp);
host_err = notify_change(dentry, iap);
err = nfserrno(host_err);
fh_unlock(fhp);
}
if (size_change)
put_write_access(inode);
if (!err)
if (EX_ISSYNC(fhp->fh_export))
write_inode_now(inode, 1);
out:
return err;
out_nfserr:
err = nfserrno(host_err);
goto out;
}
/*
* Perform sanity checks on the dentry in a client's file handle.
*
* Note that the file handle dentry may need to be freed even after
* an error return.
*
* This is only called at the start of an nfsproc call, so fhp points to
* a svc_fh which is all 0 except for the over-the-wire file handle.
*/
__be32
fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access)
{
struct knfsd_fh *fh = &fhp->fh_handle;
struct svc_export *exp = NULL;
struct dentry *dentry;
__be32 error = 0;
dprintk("nfsd: fh_verify(%s)\n", SVCFH_fmt(fhp));
if (!fhp->fh_dentry) {
__u32 *datap=NULL;
__u32 tfh[3]; /* filehandle fragment for oldstyle filehandles */
int fileid_type;
int data_left = fh->fh_size/4;
error = nfserr_stale;
if (rqstp->rq_client == NULL)
goto out;
if (rqstp->rq_vers > 2)
error = nfserr_badhandle;
if (rqstp->rq_vers == 4 && fh->fh_size == 0)
return nfserr_nofilehandle;
if (fh->fh_version == 1) {
int len;
datap = fh->fh_auth;
if (--data_left<0) goto out;
switch (fh->fh_auth_type) {
case 0: break;
default: goto out;
}
len = key_len(fh->fh_fsid_type) / 4;
if (len == 0) goto out;
if (fh->fh_fsid_type == FSID_MAJOR_MINOR) {
/* deprecated, convert to type 3 */
len = key_len(FSID_ENCODE_DEV)/4;
fh->fh_fsid_type = FSID_ENCODE_DEV;
fh->fh_fsid[0] = new_encode_dev(MKDEV(ntohl(fh->fh_fsid[0]), ntohl(fh->fh_fsid[1])));
fh->fh_fsid[1] = fh->fh_fsid[2];
}
if ((data_left -= len)<0) goto out;
exp = exp_find(rqstp->rq_client, fh->fh_fsid_type, datap, &rqstp->rq_chandle);
datap += len;
} else {
dev_t xdev;
ino_t xino;
if (fh->fh_size != NFS_FHSIZE)
goto out;
/* assume old filehandle format */
xdev = old_decode_dev(fh->ofh_xdev);
xino = u32_to_ino_t(fh->ofh_xino);
mk_fsid(FSID_DEV, tfh, xdev, xino, 0, NULL);
exp = exp_find(rqstp->rq_client, FSID_DEV, tfh,
&rqstp->rq_chandle);
}
if (IS_ERR(exp) && (PTR_ERR(exp) == -EAGAIN
|| PTR_ERR(exp) == -ETIMEDOUT)) {
error = nfserrno(PTR_ERR(exp));
goto out;
}
error = nfserr_stale;
if (!exp || IS_ERR(exp))
goto out;
/* Check if the request originated from a secure port. */
error = nfserr_perm;
if (!rqstp->rq_secure && EX_SECURE(exp)) {
char buf[RPC_MAX_ADDRBUFLEN];
printk(KERN_WARNING
"nfsd: request from insecure port %s!\n",
svc_print_addr(rqstp, buf, sizeof(buf)));
goto out;
}
/* Set user creds for this exportpoint */
error = nfserrno(nfsd_setuser(rqstp, exp));
if (error)
goto out;
/*
* Look up the dentry using the NFS file handle.
*/
error = nfserr_stale;
if (rqstp->rq_vers > 2)
error = nfserr_badhandle;
if (fh->fh_version != 1) {
tfh[0] = fh->ofh_ino;
tfh[1] = fh->ofh_generation;
tfh[2] = fh->ofh_dirino;
datap = tfh;
data_left = 3;
if (fh->ofh_dirino == 0)
fileid_type = 1;
else
fileid_type = 2;
} else
fileid_type = fh->fh_fileid_type;
if (fileid_type == 0)
dentry = dget(exp->ex_dentry);
else {
struct export_operations *nop = exp->ex_mnt->mnt_sb->s_export_op;
dentry = CALL(nop,decode_fh)(exp->ex_mnt->mnt_sb,
datap, data_left,
fileid_type,
nfsd_acceptable, exp);
}
if (dentry == NULL)
goto out;
if (IS_ERR(dentry)) {
if (PTR_ERR(dentry) != -EINVAL)
error = nfserrno(PTR_ERR(dentry));
goto out;
}
if (S_ISDIR(dentry->d_inode->i_mode) &&
(dentry->d_flags & DCACHE_DISCONNECTED)) {
printk("nfsd: find_fh_dentry returned a DISCONNECTED directory: %s/%s\n",
dentry->d_parent->d_name.name, dentry->d_name.name);
}
fhp->fh_dentry = dentry;
fhp->fh_export = exp;
nfsd_nr_verified++;
} else {
/* just rechecking permissions
* (e.g. nfsproc_create calls fh_verify, then nfsd_create does as well)
*/
dprintk("nfsd: fh_verify - just checking\n");
dentry = fhp->fh_dentry;
exp = fhp->fh_export;
/* Set user creds for this exportpoint; necessary even
* in the "just checking" case because this may be a
* filehandle that was created by fh_compose, and that
* is about to be used in another nfsv4 compound
* operation */
error = nfserrno(nfsd_setuser(rqstp, exp));
if (error)
goto out;
}
cache_get(&exp->h);
error = nfsd_mode_check(rqstp, dentry->d_inode->i_mode, type);
if (error)
goto out;
/* Finally, check access permissions. */
error = nfsd_permission(exp, dentry, access);
if (error) {
dprintk("fh_verify: %s/%s permission failure, "
"acc=%x, error=%d\n",
dentry->d_parent->d_name.name,
dentry->d_name.name,
access, ntohl(error));
}
out:
if (exp && !IS_ERR(exp))
exp_put(exp);
if (error == nfserr_stale)
nfsdstats.fh_stale++;
return error;
}
