aha/fs/nfsd/nfs4proc.c

1362 lines
37 KiB
C
Raw Normal View History

/*
* fs/nfsd/nfs4proc.c
*
* Server-side procedures for NFSv4.
*
* Copyright (c) 2002 The Regents of the University of Michigan.
* All rights reserved.
*
* Kendrick Smith <kmsmith@umich.edu>
* Andy Adamson <andros@umich.edu>
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the name of the University nor the names of its
* contributors may be used to endorse or promote products derived
* from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
* MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
* BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
* LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
* NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#include <linux/param.h>
#include <linux/major.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/sunrpc/svc.h>
#include <linux/nfsd/nfsd.h>
#include <linux/nfsd/cache.h>
#include <linux/nfs4.h>
#include <linux/nfsd/state.h>
#include <linux/nfsd/xdr4.h>
#include <linux/nfs4_acl.h>
#include <linux/sunrpc/gss_api.h>
#define NFSDDBG_FACILITY NFSDDBG_PROC
static u32 nfsd_attrmask[] = {
NFSD_WRITEABLE_ATTRS_WORD0,
NFSD_WRITEABLE_ATTRS_WORD1,
NFSD_WRITEABLE_ATTRS_WORD2
};
static u32 nfsd41_ex_attrmask[] = {
NFSD_SUPPATTR_EXCLCREAT_WORD0,
NFSD_SUPPATTR_EXCLCREAT_WORD1,
NFSD_SUPPATTR_EXCLCREAT_WORD2
};
static __be32
check_attr_support(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
u32 *bmval, u32 *writable)
{
struct dentry *dentry = cstate->current_fh.fh_dentry;
struct svc_export *exp = cstate->current_fh.fh_export;
/*
* Check about attributes are supported by the NFSv4 server or not.
* According to spec, unsupported attributes return ERR_ATTRNOTSUPP.
*/
if ((bmval[0] & ~nfsd_suppattrs0(cstate->minorversion)) ||
(bmval[1] & ~nfsd_suppattrs1(cstate->minorversion)) ||
(bmval[2] & ~nfsd_suppattrs2(cstate->minorversion)))
return nfserr_attrnotsupp;
/*
* Check FATTR4_WORD0_ACL & FATTR4_WORD0_FS_LOCATIONS can be supported
* in current environment or not.
*/
if (bmval[0] & FATTR4_WORD0_ACL) {
if (!IS_POSIXACL(dentry->d_inode))
return nfserr_attrnotsupp;
}
if (bmval[0] & FATTR4_WORD0_FS_LOCATIONS) {
if (exp->ex_fslocs.locations == NULL)
return nfserr_attrnotsupp;
}
/*
* According to spec, read-only attributes return ERR_INVAL.
*/
if (writable) {
if ((bmval[0] & ~writable[0]) || (bmval[1] & ~writable[1]) ||
(bmval[2] & ~writable[2]))
return nfserr_inval;
}
return nfs_ok;
}
static __be32
nfsd4_check_open_attributes(struct svc_rqst *rqstp,
struct nfsd4_compound_state *cstate, struct nfsd4_open *open)
{
__be32 status = nfs_ok;
if (open->op_create == NFS4_OPEN_CREATE) {
if (open->op_createmode == NFS4_CREATE_UNCHECKED
|| open->op_createmode == NFS4_CREATE_GUARDED)
status = check_attr_support(rqstp, cstate,
open->op_bmval, nfsd_attrmask);
else if (open->op_createmode == NFS4_CREATE_EXCLUSIVE4_1)
status = check_attr_support(rqstp, cstate,
open->op_bmval, nfsd41_ex_attrmask);
}
return status;
}
static inline void
fh_dup2(struct svc_fh *dst, struct svc_fh *src)
{
fh_put(dst);
dget(src->fh_dentry);
if (src->fh_export)
cache_get(&src->fh_export->h);
*dst = *src;
}
static __be32
do_open_permission(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open, int accmode)
{
__be32 status;
if (open->op_truncate &&
!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE))
return nfserr_inval;
if (open->op_share_access & NFS4_SHARE_ACCESS_READ)
accmode |= NFSD_MAY_READ;
if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
accmode |= (NFSD_MAY_WRITE | NFSD_MAY_TRUNC);
if (open->op_share_deny & NFS4_SHARE_DENY_WRITE)
accmode |= NFSD_MAY_WRITE;
status = fh_verify(rqstp, current_fh, S_IFREG, accmode);
return status;
}
static __be32
do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open)
{
struct svc_fh resfh;
__be32 status;
int created = 0;
fh_init(&resfh, NFS4_FHSIZE);
open->op_truncate = 0;
if (open->op_create) {
/* FIXME: check session persistence and pnfs flags.
* The nfsv4.1 spec requires the following semantics:
*
* Persistent | pNFS | Server REQUIRED | Client Allowed
* Reply Cache | server | |
* -------------+--------+-----------------+--------------------
* no | no | EXCLUSIVE4_1 | EXCLUSIVE4_1
* | | | (SHOULD)
* | | and EXCLUSIVE4 | or EXCLUSIVE4
* | | | (SHOULD NOT)
* no | yes | EXCLUSIVE4_1 | EXCLUSIVE4_1
* yes | no | GUARDED4 | GUARDED4
* yes | yes | GUARDED4 | GUARDED4
*/
/*
* Note: create modes (UNCHECKED,GUARDED...) are the same
* in NFSv4 as in v3.
*/
status = nfsd_create_v3(rqstp, current_fh, open->op_fname.data,
open->op_fname.len, &open->op_iattr,
&resfh, open->op_createmode,
(u32 *)open->op_verf.data,
&open->op_truncate, &created);
/*
* Following rfc 3530 14.2.16, use the returned bitmask
* to indicate which attributes we used to store the
* verifier:
*/
if (open->op_createmode == NFS4_CREATE_EXCLUSIVE && status == 0)
open->op_bmval[1] = (FATTR4_WORD1_TIME_ACCESS |
FATTR4_WORD1_TIME_MODIFY);
} else {
status = nfsd_lookup(rqstp, current_fh,
open->op_fname.data, open->op_fname.len, &resfh);
fh_unlock(current_fh);
}
if (status)
goto out;
set_change_info(&open->op_cinfo, current_fh);
fh_dup2(current_fh, &resfh);
/* set reply cache */
fh_copy_shallow(&open->op_stateowner->so_replay.rp_openfh,
&resfh.fh_handle);
if (!created)
status = do_open_permission(rqstp, current_fh, open,
NFSD_MAY_NOP);
out:
fh_put(&resfh);
return status;
}
static __be32
do_open_fhandle(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open)
{
__be32 status;
/* Only reclaims from previously confirmed clients are valid */
if ((status = nfs4_check_open_reclaim(&open->op_clientid)))
return status;
/* We don't know the target directory, and therefore can not
* set the change info
*/
memset(&open->op_cinfo, 0, sizeof(struct nfsd4_change_info));
/* set replay cache */
fh_copy_shallow(&open->op_stateowner->so_replay.rp_openfh,
&current_fh->fh_handle);
open->op_truncate = (open->op_iattr.ia_valid & ATTR_SIZE) &&
(open->op_iattr.ia_size == 0);
status = do_open_permission(rqstp, current_fh, open,
NFSD_MAY_OWNER_OVERRIDE);
return status;
}
static void
copy_clientid(clientid_t *clid, struct nfsd4_session *session)
{
struct nfsd4_sessionid *sid =
(struct nfsd4_sessionid *)session->se_sessionid.data;
clid->cl_boot = sid->clientid.cl_boot;
clid->cl_id = sid->clientid.cl_id;
}
static __be32
nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_open *open)
{
__be32 status;
struct nfsd4_compoundres *resp;
dprintk("NFSD: nfsd4_open filename %.*s op_stateowner %p\n",
(int)open->op_fname.len, open->op_fname.data,
open->op_stateowner);
/* This check required by spec. */
if (open->op_create && open->op_claim_type != NFS4_OPEN_CLAIM_NULL)
return nfserr_inval;
if (nfsd4_has_session(cstate))
copy_clientid(&open->op_clientid, cstate->session);
nfs4_lock_state();
/* check seqid for replay. set nfs4_owner */
resp = rqstp->rq_resp;
status = nfsd4_process_open1(&resp->cstate, open);
if (status == nfserr_replay_me) {
struct nfs4_replay *rp = &open->op_stateowner->so_replay;
fh_put(&cstate->current_fh);
fh_copy_shallow(&cstate->current_fh.fh_handle,
&rp->rp_openfh);
status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
if (status)
dprintk("nfsd4_open: replay failed"
" restoring previous filehandle\n");
else
status = nfserr_replay_me;
}
if (status)
goto out;
status = nfsd4_check_open_attributes(rqstp, cstate, open);
if (status)
goto out;
/* Openowner is now set, so sequence id will get bumped. Now we need
* these checks before we do any creates: */
status = nfserr_grace;
if (locks_in_grace() && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
goto out;
status = nfserr_no_grace;
if (!locks_in_grace() && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
goto out;
switch (open->op_claim_type) {
case NFS4_OPEN_CLAIM_DELEGATE_CUR:
case NFS4_OPEN_CLAIM_NULL:
/*
* (1) set CURRENT_FH to the file being opened,
* creating it if necessary, (2) set open->op_cinfo,
* (3) set open->op_truncate if the file is to be
* truncated after opening, (4) do permission checking.
*/
status = do_open_lookup(rqstp, &cstate->current_fh,
open);
if (status)
goto out;
break;
case NFS4_OPEN_CLAIM_PREVIOUS:
open->op_stateowner->so_confirmed = 1;
/*
* The CURRENT_FH is already set to the file being
* opened. (1) set open->op_cinfo, (2) set
* open->op_truncate if the file is to be truncated
* after opening, (3) do permission checking.
*/
status = do_open_fhandle(rqstp, &cstate->current_fh,
open);
if (status)
goto out;
break;
case NFS4_OPEN_CLAIM_DELEGATE_PREV:
open->op_stateowner->so_confirmed = 1;
dprintk("NFSD: unsupported OPEN claim type %d\n",
open->op_claim_type);
status = nfserr_notsupp;
goto out;
default:
dprintk("NFSD: Invalid OPEN claim type %d\n",
open->op_claim_type);
status = nfserr_inval;
goto out;
}
/*
* nfsd4_process_open2() does the actual opening of the file. If
* successful, it (1) truncates the file if open->op_truncate was
* set, (2) sets open->op_stateid, (3) sets open->op_delegation.
*/
status = nfsd4_process_open2(rqstp, &cstate->current_fh, open);
out:
if (open->op_stateowner) {
nfs4_get_stateowner(open->op_stateowner);
cstate->replay_owner = open->op_stateowner;
}
nfs4_unlock_state();
return status;
}
/*
* filehandle-manipulating ops.
*/
static __be32
nfsd4_getfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct svc_fh **getfh)
{
if (!cstate->current_fh.fh_dentry)
return nfserr_nofilehandle;
*getfh = &cstate->current_fh;
return nfs_ok;
}
static __be32
nfsd4_putfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_putfh *putfh)
{
fh_put(&cstate->current_fh);
cstate->current_fh.fh_handle.fh_size = putfh->pf_fhlen;
memcpy(&cstate->current_fh.fh_handle.fh_base, putfh->pf_fhval,
putfh->pf_fhlen);
return fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
}
static __be32
nfsd4_putrootfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
void *arg)
{
__be32 status;
fh_put(&cstate->current_fh);
status = exp_pseudoroot(rqstp, &cstate->current_fh);
return status;
}
static __be32
nfsd4_restorefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
void *arg)
{
if (!cstate->save_fh.fh_dentry)
return nfserr_restorefh;
fh_dup2(&cstate->current_fh, &cstate->save_fh);
return nfs_ok;
}
static __be32
nfsd4_savefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
void *arg)
{
if (!cstate->current_fh.fh_dentry)
return nfserr_nofilehandle;
fh_dup2(&cstate->save_fh, &cstate->current_fh);
return nfs_ok;
}
/*
* misc nfsv4 ops
*/
static __be32
nfsd4_access(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_access *access)
{
if (access->ac_req_access & ~NFS3_ACCESS_FULL)
return nfserr_inval;
access->ac_resp_access = access->ac_req_access;
return nfsd_access(rqstp, &cstate->current_fh, &access->ac_resp_access,
&access->ac_supported);
}
static __be32
nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_commit *commit)
{
__be32 status;
u32 *p = (u32 *)commit->co_verf.data;
*p++ = nfssvc_boot.tv_sec;
*p++ = nfssvc_boot.tv_usec;
status = nfsd_commit(rqstp, &cstate->current_fh, commit->co_offset,
commit->co_count);
if (status == nfserr_symlink)
status = nfserr_inval;
return status;
}
static __be32
nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_create *create)
{
struct svc_fh resfh;
__be32 status;
dev_t rdev;
fh_init(&resfh, NFS4_FHSIZE);
status = fh_verify(rqstp, &cstate->current_fh, S_IFDIR,
NFSD_MAY_CREATE);
if (status == nfserr_symlink)
status = nfserr_notdir;
if (status)
return status;
status = check_attr_support(rqstp, cstate, create->cr_bmval,
nfsd_attrmask);
if (status)
return status;
switch (create->cr_type) {
case NF4LNK:
/* ugh! we have to null-terminate the linktext, or
* vfs_symlink() will choke. it is always safe to
* null-terminate by brute force, since at worst we
* will overwrite the first byte of the create namelen
* in the XDR buffer, which has already been extracted
* during XDR decode.
*/
create->cr_linkname[create->cr_linklen] = 0;
status = nfsd_symlink(rqstp, &cstate->current_fh,
create->cr_name, create->cr_namelen,
create->cr_linkname, create->cr_linklen,
&resfh, &create->cr_iattr);
break;
case NF4BLK:
rdev = MKDEV(create->cr_specdata1, create->cr_specdata2);
if (MAJOR(rdev) != create->cr_specdata1 ||
MINOR(rdev) != create->cr_specdata2)
return nfserr_inval;
status = nfsd_create(rqstp, &cstate->current_fh,
create->cr_name, create->cr_namelen,
&create->cr_iattr, S_IFBLK, rdev, &resfh);
break;
case NF4CHR:
rdev = MKDEV(create->cr_specdata1, create->cr_specdata2);
if (MAJOR(rdev) != create->cr_specdata1 ||
MINOR(rdev) != create->cr_specdata2)
return nfserr_inval;
status = nfsd_create(rqstp, &cstate->current_fh,
create->cr_name, create->cr_namelen,
&create->cr_iattr,S_IFCHR, rdev, &resfh);
break;
case NF4SOCK:
status = nfsd_create(rqstp, &cstate->current_fh,
create->cr_name, create->cr_namelen,
&create->cr_iattr, S_IFSOCK, 0, &resfh);
break;
case NF4FIFO:
status = nfsd_create(rqstp, &cstate->current_fh,
create->cr_name, create->cr_namelen,
&create->cr_iattr, S_IFIFO, 0, &resfh);
break;
case NF4DIR:
create->cr_iattr.ia_valid &= ~ATTR_SIZE;
status = nfsd_create(rqstp, &cstate->current_fh,
create->cr_name, create->cr_namelen,
&create->cr_iattr, S_IFDIR, 0, &resfh);
break;
default:
status = nfserr_badtype;
}
if (!status) {
fh_unlock(&cstate->current_fh);
set_change_info(&create->cr_cinfo, &cstate->current_fh);
fh_dup2(&cstate->current_fh, &resfh);
}
fh_put(&resfh);
return status;
}
static __be32
nfsd4_getattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_getattr *getattr)
{
__be32 status;
status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
if (status)
return status;
if (getattr->ga_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1)
return nfserr_inval;
getattr->ga_bmval[0] &= nfsd_suppattrs0(cstate->minorversion);
getattr->ga_bmval[1] &= nfsd_suppattrs1(cstate->minorversion);
getattr->ga_bmval[2] &= nfsd_suppattrs2(cstate->minorversion);
getattr->ga_fhp = &cstate->current_fh;
return nfs_ok;
}
static __be32
nfsd4_link(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_link *link)
{
__be32 status = nfserr_nofilehandle;
if (!cstate->save_fh.fh_dentry)
return status;
status = nfsd_link(rqstp, &cstate->current_fh,
link->li_name, link->li_namelen, &cstate->save_fh);
if (!status)
set_change_info(&link->li_cinfo, &cstate->current_fh);
return status;
}
static __be32
nfsd4_lookupp(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
void *arg)
{
struct svc_fh tmp_fh;
__be32 ret;
fh_init(&tmp_fh, NFS4_FHSIZE);
ret = exp_pseudoroot(rqstp, &tmp_fh);
if (ret)
return ret;
if (tmp_fh.fh_dentry == cstate->current_fh.fh_dentry) {
fh_put(&tmp_fh);
return nfserr_noent;
}
fh_put(&tmp_fh);
return nfsd_lookup(rqstp, &cstate->current_fh,
"..", 2, &cstate->current_fh);
}
static __be32
nfsd4_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_lookup *lookup)
{
return nfsd_lookup(rqstp, &cstate->current_fh,
lookup->lo_name, lookup->lo_len,
&cstate->current_fh);
}
static __be32
nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_read *read)
{
__be32 status;
/* no need to check permission - this will be done in nfsd_read() */
read->rd_filp = NULL;
if (read->rd_offset >= OFFSET_MAX)
return nfserr_inval;
nfs4_lock_state();
/* check stateid */
if ((status = nfs4_preprocess_stateid_op(cstate, &read->rd_stateid,
RD_STATE, &read->rd_filp))) {
dprintk("NFSD: nfsd4_read: couldn't process stateid!\n");
goto out;
}
if (read->rd_filp)
get_file(read->rd_filp);
status = nfs_ok;
out:
nfs4_unlock_state();
read->rd_rqstp = rqstp;
read->rd_fhp = &cstate->current_fh;
return status;
}
static __be32
nfsd4_readdir(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_readdir *readdir)
{
u64 cookie = readdir->rd_cookie;
static const nfs4_verifier zeroverf;
/* no need to check permission - this will be done in nfsd_readdir() */
if (readdir->rd_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1)
return nfserr_inval;
readdir->rd_bmval[0] &= nfsd_suppattrs0(cstate->minorversion);
readdir->rd_bmval[1] &= nfsd_suppattrs1(cstate->minorversion);
readdir->rd_bmval[2] &= nfsd_suppattrs2(cstate->minorversion);
if ((cookie > ~(u32)0) || (cookie == 1) || (cookie == 2) ||
(cookie == 0 && memcmp(readdir->rd_verf.data, zeroverf.data, NFS4_VERIFIER_SIZE)))
return nfserr_bad_cookie;
readdir->rd_rqstp = rqstp;
readdir->rd_fhp = &cstate->current_fh;
return nfs_ok;
}
static __be32
nfsd4_readlink(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_readlink *readlink)
{
readlink->rl_rqstp = rqstp;
readlink->rl_fhp = &cstate->current_fh;
return nfs_ok;
}
static __be32
nfsd4_remove(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_remove *remove)
{
__be32 status;
if (locks_in_grace())
return nfserr_grace;
status = nfsd_unlink(rqstp, &cstate->current_fh, 0,
remove->rm_name, remove->rm_namelen);
if (status == nfserr_symlink)
return nfserr_notdir;
if (!status) {
fh_unlock(&cstate->current_fh);
set_change_info(&remove->rm_cinfo, &cstate->current_fh);
}
return status;
}
static __be32
nfsd4_rename(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_rename *rename)
{
__be32 status = nfserr_nofilehandle;
if (!cstate->save_fh.fh_dentry)
return status;
if (locks_in_grace() && !(cstate->save_fh.fh_export->ex_flags
& NFSEXP_NOSUBTREECHECK))
return nfserr_grace;
status = nfsd_rename(rqstp, &cstate->save_fh, rename->rn_sname,
rename->rn_snamelen, &cstate->current_fh,
rename->rn_tname, rename->rn_tnamelen);
/* the underlying filesystem returns different error's than required
* by NFSv4. both save_fh and current_fh have been verified.. */
if (status == nfserr_isdir)
status = nfserr_exist;
else if ((status == nfserr_notdir) &&
(S_ISDIR(cstate->save_fh.fh_dentry->d_inode->i_mode) &&
S_ISDIR(cstate->current_fh.fh_dentry->d_inode->i_mode)))
status = nfserr_exist;
else if (status == nfserr_symlink)
status = nfserr_notdir;
if (!status) {
set_change_info(&rename->rn_sinfo, &cstate->current_fh);
set_change_info(&rename->rn_tinfo, &cstate->save_fh);
}
return status;
}
static __be32
nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_secinfo *secinfo)
{
struct svc_fh resfh;
struct svc_export *exp;
struct dentry *dentry;
__be32 err;
fh_init(&resfh, NFS4_FHSIZE);
err = nfsd_lookup_dentry(rqstp, &cstate->current_fh,
secinfo->si_name, secinfo->si_namelen,
&exp, &dentry);
if (err)
return err;
if (dentry->d_inode == NULL) {
exp_put(exp);
err = nfserr_noent;
} else
secinfo->si_exp = exp;
dput(dentry);
return err;
}
static __be32
nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_setattr *setattr)
{
__be32 status = nfs_ok;
if (setattr->sa_iattr.ia_valid & ATTR_SIZE) {
nfs4_lock_state();
status = nfs4_preprocess_stateid_op(cstate,
&setattr->sa_stateid, WR_STATE, NULL);
nfs4_unlock_state();
if (status) {
dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n");
return status;
}
}
status = mnt_want_write(cstate->current_fh.fh_export->ex_path.mnt);
if (status)
return status;
status = nfs_ok;
status = check_attr_support(rqstp, cstate, setattr->sa_bmval,
nfsd_attrmask);
if (status)
goto out;
if (setattr->sa_acl != NULL)
status = nfsd4_set_nfs4_acl(rqstp, &cstate->current_fh,
setattr->sa_acl);
if (status)
goto out;
status = nfsd_setattr(rqstp, &cstate->current_fh, &setattr->sa_iattr,
0, (time_t)0);
out:
mnt_drop_write(cstate->current_fh.fh_export->ex_path.mnt);
return status;
}
static __be32
nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_write *write)
{
stateid_t *stateid = &write->wr_stateid;
struct file *filp = NULL;
u32 *p;
__be32 status = nfs_ok;
unsigned long cnt;
/* no need to check permission - this will be done in nfsd_write() */
if (write->wr_offset >= OFFSET_MAX)
return nfserr_inval;
nfs4_lock_state();
status = nfs4_preprocess_stateid_op(cstate, stateid, WR_STATE, &filp);
if (filp)
get_file(filp);
nfs4_unlock_state();
if (status) {
dprintk("NFSD: nfsd4_write: couldn't process stateid!\n");
return status;
}
cnt = write->wr_buflen;
write->wr_how_written = write->wr_stable_how;
p = (u32 *)write->wr_verifier.data;
*p++ = nfssvc_boot.tv_sec;
*p++ = nfssvc_boot.tv_usec;
status = nfsd_write(rqstp, &cstate->current_fh, filp,
write->wr_offset, rqstp->rq_vec, write->wr_vlen,
&cnt, &write->wr_how_written);
if (filp)
fput(filp);
write->wr_bytes_written = cnt;
if (status == nfserr_symlink)
status = nfserr_inval;
return status;
}
/* This routine never returns NFS_OK! If there are no other errors, it
* will return NFSERR_SAME or NFSERR_NOT_SAME depending on whether the
* attributes matched. VERIFY is implemented by mapping NFSERR_SAME
* to NFS_OK after the call; NVERIFY by mapping NFSERR_NOT_SAME to NFS_OK.
*/
static __be32
_nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_verify *verify)
{
__be32 *buf, *p;
int count;
__be32 status;
status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
if (status)
return status;
status = check_attr_support(rqstp, cstate, verify->ve_bmval, NULL);
if (status)
return status;
if ((verify->ve_bmval[0] & FATTR4_WORD0_RDATTR_ERROR)
|| (verify->ve_bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1))
return nfserr_inval;
if (verify->ve_attrlen & 3)
return nfserr_inval;
/* count in words:
* bitmap_len(1) + bitmap(2) + attr_len(1) = 4
*/
count = 4 + (verify->ve_attrlen >> 2);
buf = kmalloc(count << 2, GFP_KERNEL);
if (!buf)
return nfserr_resource;
status = nfsd4_encode_fattr(&cstate->current_fh,
cstate->current_fh.fh_export,
cstate->current_fh.fh_dentry, buf,
&count, verify->ve_bmval,
nfsd: Allow AIX client to read dir containing mountpoints This patch addresses a compatibility issue with a Linux NFS server and AIX NFS client. I have exported /export as fsid=0 with sec=krb5:krb5i I have mount --bind /home onto /export/home I have exported /export/home with sec=krb5i The AIX client mounts / -o sec=krb5:krb5i onto /mnt If I do an ls /mnt, the AIX client gets a permission error. Looking at the network traceIwe see a READDIR looking for attributes FATTR4_RDATTR_ERROR and FATTR4_MOUNTED_ON_FILEID. The response gives a NFS4ERR_WRONGSEC which the AIX client is not expecting. Since the AIX client is only asking for an attribute that is an attribute of the parent file system (pseudo root in my example), it seems reasonable that there should not be an error. In discussing this issue with Bruce Fields, I initially proposed ignoring the error in nfsd4_encode_dirent_fattr() if all that was being asked for was FATTR4_RDATTR_ERROR and FATTR4_MOUNTED_ON_FILEID, however, Bruce suggested that we avoid calling cross_mnt() if only these attributes are requested. The following patch implements bypassing cross_mnt() if only FATTR4_RDATTR_ERROR and FATTR4_MOUNTED_ON_FILEID are called. Since there is some complexity in the code in nfsd4_encode_fattr(), I didn't want to duplicate code (and introduce a maintenance nightmare), so I added a parameter to nfsd4_encode_fattr() that indicates whether it should ignore cross mounts and simply fill in the attribute using the passed in dentry as opposed to it's parent. Signed-off-by: Frank Filz <ffilzlnx@us.ibm.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2007-11-27 19:34:05 +00:00
rqstp, 0);
/* this means that nfsd4_encode_fattr() ran out of space */
if (status == nfserr_resource && count == 0)
status = nfserr_not_same;
if (status)
goto out_kfree;
/* skip bitmap */
p = buf + 1 + ntohl(buf[0]);
status = nfserr_not_same;
if (ntohl(*p++) != verify->ve_attrlen)
goto out_kfree;
if (!memcmp(p, verify->ve_attrval, verify->ve_attrlen))
status = nfserr_same;
out_kfree:
kfree(buf);
return status;
}
static __be32
nfsd4_nverify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_verify *verify)
{
__be32 status;
status = _nfsd4_verify(rqstp, cstate, verify);
return status == nfserr_not_same ? nfs_ok : status;
}
static __be32
nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_verify *verify)
{
__be32 status;
status = _nfsd4_verify(rqstp, cstate, verify);
return status == nfserr_same ? nfs_ok : status;
}
/*
* NULL call.
*/
static __be32
nfsd4_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
{
return nfs_ok;
}
static inline void nfsd4_increment_op_stats(u32 opnum)
{
if (opnum >= FIRST_NFS4_OP && opnum <= LAST_NFS4_OP)
nfsdstats.nfs4_opcount[opnum]++;
}
typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *,
void *);
enum nfsd4_op_flags {
ALLOWED_WITHOUT_FH = 1 << 0, /* No current filehandle required */
ALLOWED_ON_ABSENT_FS = 2 << 0, /* ops processed on absent fs */
ALLOWED_AS_FIRST_OP = 3 << 0, /* ops reqired first in compound */
};
struct nfsd4_operation {
nfsd4op_func op_func;
u32 op_flags;
char *op_name;
};
static struct nfsd4_operation nfsd4_ops[];
static const char *nfsd4_op_name(unsigned opnum);
/*
* This is a replay of a compound for which no cache entry pages
* were used. Encode the sequence operation, and if cachethis is FALSE
* encode the uncache rep error on the next operation.
*/
static __be32
nfsd4_enc_uncached_replay(struct nfsd4_compoundargs *args,
struct nfsd4_compoundres *resp)
{
struct nfsd4_op *op;
dprintk("--> %s resp->opcnt %d ce_cachethis %u \n", __func__,
resp->opcnt, resp->cstate.slot->sl_cache_entry.ce_cachethis);
/* Encode the replayed sequence operation */
BUG_ON(resp->opcnt != 1);
op = &args->ops[resp->opcnt - 1];
nfsd4_encode_operation(resp, op);
/*return nfserr_retry_uncached_rep in next operation. */
if (resp->cstate.slot->sl_cache_entry.ce_cachethis == 0) {
op = &args->ops[resp->opcnt++];
op->status = nfserr_retry_uncached_rep;
nfsd4_encode_operation(resp, op);
}
return op->status;
}
/*
* Enforce NFSv4.1 COMPOUND ordering rules.
*
* TODO:
* - enforce NFS4ERR_NOT_ONLY_OP,
* - DESTROY_SESSION MUST be the final operation in the COMPOUND request.
*/
static bool nfs41_op_ordering_ok(struct nfsd4_compoundargs *args)
{
if (args->minorversion && args->opcnt > 0) {
struct nfsd4_op *op = &args->ops[0];
return (op->status == nfserr_op_illegal) ||
(nfsd4_ops[op->opnum].op_flags & ALLOWED_AS_FIRST_OP);
}
return true;
}
/*
* COMPOUND call.
*/
static __be32
nfsd4_proc_compound(struct svc_rqst *rqstp,
struct nfsd4_compoundargs *args,
struct nfsd4_compoundres *resp)
{
struct nfsd4_op *op;
struct nfsd4_operation *opdesc;
struct nfsd4_compound_state *cstate = &resp->cstate;
int slack_bytes;
__be32 status;
resp->xbuf = &rqstp->rq_res;
resp->p = rqstp->rq_res.head[0].iov_base +
rqstp->rq_res.head[0].iov_len;
resp->tagp = resp->p;
/* reserve space for: taglen, tag, and opcnt */
resp->p += 2 + XDR_QUADLEN(args->taglen);
resp->end = rqstp->rq_res.head[0].iov_base + PAGE_SIZE;
resp->taglen = args->taglen;
resp->tag = args->tag;
resp->opcnt = 0;
resp->rqstp = rqstp;
resp->cstate.minorversion = args->minorversion;
resp->cstate.replay_owner = NULL;
fh_init(&resp->cstate.current_fh, NFS4_FHSIZE);
fh_init(&resp->cstate.save_fh, NFS4_FHSIZE);
/* Use the deferral mechanism only for NFSv4.0 compounds */
rqstp->rq_usedeferral = (args->minorversion == 0);
/*
* According to RFC3010, this takes precedence over all other errors.
*/
status = nfserr_minor_vers_mismatch;
if (args->minorversion > nfsd_supported_minorversion)
goto out;
if (!nfs41_op_ordering_ok(args)) {
op = &args->ops[0];
op->status = nfserr_sequence_pos;
goto encode_op;
}
status = nfs_ok;
while (!status && resp->opcnt < args->opcnt) {
op = &args->ops[resp->opcnt++];
dprintk("nfsv4 compound op #%d/%d: %d (%s)\n",
resp->opcnt, args->opcnt, op->opnum,
nfsd4_op_name(op->opnum));
/*
* The XDR decode routines may have pre-set op->status;
* for example, if there is a miscellaneous XDR error
* it will be set to nfserr_bad_xdr.
*/
if (op->status)
goto encode_op;
/* We must be able to encode a successful response to
* this operation, with enough room left over to encode a
* failed response to the next operation. If we don't
* have enough room, fail with ERR_RESOURCE.
*/
slack_bytes = (char *)resp->end - (char *)resp->p;
if (slack_bytes < COMPOUND_SLACK_SPACE
+ COMPOUND_ERR_SLACK_SPACE) {
BUG_ON(slack_bytes < COMPOUND_ERR_SLACK_SPACE);
op->status = nfserr_resource;
goto encode_op;
}
opdesc = &nfsd4_ops[op->opnum];
if (!cstate->current_fh.fh_dentry) {
if (!(opdesc->op_flags & ALLOWED_WITHOUT_FH)) {
op->status = nfserr_nofilehandle;
goto encode_op;
}
} else if (cstate->current_fh.fh_export->ex_fslocs.migrated &&
!(opdesc->op_flags & ALLOWED_ON_ABSENT_FS)) {
op->status = nfserr_moved;
goto encode_op;
}
if (opdesc->op_func)
op->status = opdesc->op_func(rqstp, cstate, &op->u);
else
BUG_ON(op->status == nfs_ok);
encode_op:
/* Only from SEQUENCE or CREATE_SESSION */
if (resp->cstate.status == nfserr_replay_cache) {
dprintk("%s NFS4.1 replay from cache\n", __func__);
if (nfsd4_not_cached(resp))
status = nfsd4_enc_uncached_replay(args, resp);
else
status = op->status;
goto out;
}
if (op->status == nfserr_replay_me) {
op->replay = &cstate->replay_owner->so_replay;
nfsd4_encode_replay(resp, op);
status = op->status = op->replay->rp_status;
} else {
nfsd4_encode_operation(resp, op);
status = op->status;
}
dprintk("nfsv4 compound op %p opcnt %d #%d: %d: status %d\n",
args->ops, args->opcnt, resp->opcnt, op->opnum,
be32_to_cpu(status));
if (cstate->replay_owner) {
nfs4_put_stateowner(cstate->replay_owner);
cstate->replay_owner = NULL;
}
/* XXX Ugh, we need to get rid of this kind of special case: */
if (op->opnum == OP_READ && op->u.read.rd_filp)
fput(op->u.read.rd_filp);
nfsd4_increment_op_stats(op->opnum);
}
if (!rqstp->rq_usedeferral && status == nfserr_dropit) {
dprintk("%s Dropit - send NFS4ERR_DELAY\n", __func__);
status = nfserr_jukebox;
}
resp->cstate.status = status;
fh_put(&resp->cstate.current_fh);
fh_put(&resp->cstate.save_fh);
BUG_ON(resp->cstate.replay_owner);
out:
nfsd4_release_compoundargs(args);
/* Reset deferral mechanism for RPC deferrals */
rqstp->rq_usedeferral = 1;
dprintk("nfsv4 compound returned %d\n", ntohl(status));
return status;
}
static struct nfsd4_operation nfsd4_ops[] = {
[OP_ACCESS] = {
.op_func = (nfsd4op_func)nfsd4_access,
.op_name = "OP_ACCESS",
},
[OP_CLOSE] = {
.op_func = (nfsd4op_func)nfsd4_close,
.op_name = "OP_CLOSE",
},
[OP_COMMIT] = {
.op_func = (nfsd4op_func)nfsd4_commit,
.op_name = "OP_COMMIT",
},
[OP_CREATE] = {
.op_func = (nfsd4op_func)nfsd4_create,
.op_name = "OP_CREATE",
},
[OP_DELEGRETURN] = {
.op_func = (nfsd4op_func)nfsd4_delegreturn,
.op_name = "OP_DELEGRETURN",
},
[OP_GETATTR] = {
.op_func = (nfsd4op_func)nfsd4_getattr,
.op_flags = ALLOWED_ON_ABSENT_FS,
.op_name = "OP_GETATTR",
},
[OP_GETFH] = {
.op_func = (nfsd4op_func)nfsd4_getfh,
.op_name = "OP_GETFH",
},
[OP_LINK] = {
.op_func = (nfsd4op_func)nfsd4_link,
.op_name = "OP_LINK",
},
[OP_LOCK] = {
.op_func = (nfsd4op_func)nfsd4_lock,
.op_name = "OP_LOCK",
},
[OP_LOCKT] = {
.op_func = (nfsd4op_func)nfsd4_lockt,
.op_name = "OP_LOCKT",
},
[OP_LOCKU] = {
.op_func = (nfsd4op_func)nfsd4_locku,
.op_name = "OP_LOCKU",
},
[OP_LOOKUP] = {
.op_func = (nfsd4op_func)nfsd4_lookup,
.op_name = "OP_LOOKUP",
},
[OP_LOOKUPP] = {
.op_func = (nfsd4op_func)nfsd4_lookupp,
.op_name = "OP_LOOKUPP",
},
[OP_NVERIFY] = {
.op_func = (nfsd4op_func)nfsd4_nverify,
.op_name = "OP_NVERIFY",
},
[OP_OPEN] = {
.op_func = (nfsd4op_func)nfsd4_open,
.op_name = "OP_OPEN",
},
[OP_OPEN_CONFIRM] = {
.op_func = (nfsd4op_func)nfsd4_open_confirm,
.op_name = "OP_OPEN_CONFIRM",
},
[OP_OPEN_DOWNGRADE] = {
.op_func = (nfsd4op_func)nfsd4_open_downgrade,
.op_name = "OP_OPEN_DOWNGRADE",
},
[OP_PUTFH] = {
.op_func = (nfsd4op_func)nfsd4_putfh,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
.op_name = "OP_PUTFH",
},
[OP_PUTPUBFH] = {
.op_func = (nfsd4op_func)nfsd4_putrootfh,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
.op_name = "OP_PUTPUBFH",
},
[OP_PUTROOTFH] = {
.op_func = (nfsd4op_func)nfsd4_putrootfh,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
.op_name = "OP_PUTROOTFH",
},
[OP_READ] = {
.op_func = (nfsd4op_func)nfsd4_read,
.op_name = "OP_READ",
},
[OP_READDIR] = {
.op_func = (nfsd4op_func)nfsd4_readdir,
.op_name = "OP_READDIR",
},
[OP_READLINK] = {
.op_func = (nfsd4op_func)nfsd4_readlink,
.op_name = "OP_READLINK",
},
[OP_REMOVE] = {
.op_func = (nfsd4op_func)nfsd4_remove,
.op_name = "OP_REMOVE",
},
[OP_RENAME] = {
.op_name = "OP_RENAME",
.op_func = (nfsd4op_func)nfsd4_rename,
},
[OP_RENEW] = {
.op_func = (nfsd4op_func)nfsd4_renew,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
.op_name = "OP_RENEW",
},
[OP_RESTOREFH] = {
.op_func = (nfsd4op_func)nfsd4_restorefh,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
.op_name = "OP_RESTOREFH",
},
[OP_SAVEFH] = {
.op_func = (nfsd4op_func)nfsd4_savefh,
.op_name = "OP_SAVEFH",
},
[OP_SECINFO] = {
.op_func = (nfsd4op_func)nfsd4_secinfo,
.op_name = "OP_SECINFO",
},
[OP_SETATTR] = {
.op_func = (nfsd4op_func)nfsd4_setattr,
.op_name = "OP_SETATTR",
},
[OP_SETCLIENTID] = {
.op_func = (nfsd4op_func)nfsd4_setclientid,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
.op_name = "OP_SETCLIENTID",
},
[OP_SETCLIENTID_CONFIRM] = {
.op_func = (nfsd4op_func)nfsd4_setclientid_confirm,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
.op_name = "OP_SETCLIENTID_CONFIRM",
},
[OP_VERIFY] = {
.op_func = (nfsd4op_func)nfsd4_verify,
.op_name = "OP_VERIFY",
},
[OP_WRITE] = {
.op_func = (nfsd4op_func)nfsd4_write,
.op_name = "OP_WRITE",
},
[OP_RELEASE_LOCKOWNER] = {
.op_func = (nfsd4op_func)nfsd4_release_lockowner,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
.op_name = "OP_RELEASE_LOCKOWNER",
},
/* NFSv4.1 operations */
[OP_EXCHANGE_ID] = {
.op_func = (nfsd4op_func)nfsd4_exchange_id,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP,
.op_name = "OP_EXCHANGE_ID",
},
[OP_CREATE_SESSION] = {
.op_func = (nfsd4op_func)nfsd4_create_session,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP,
.op_name = "OP_CREATE_SESSION",
},
[OP_DESTROY_SESSION] = {
.op_func = (nfsd4op_func)nfsd4_destroy_session,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP,
.op_name = "OP_DESTROY_SESSION",
},
[OP_SEQUENCE] = {
.op_func = (nfsd4op_func)nfsd4_sequence,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP,
.op_name = "OP_SEQUENCE",
},
};
static const char *nfsd4_op_name(unsigned opnum)
{
if (opnum < ARRAY_SIZE(nfsd4_ops))
return nfsd4_ops[opnum].op_name;
return "unknown_operation";
}
#define nfsd4_voidres nfsd4_voidargs
struct nfsd4_voidargs { int dummy; };
/*
* TODO: At the present time, the NFSv4 server does not do XID caching
* of requests. Implementing XID caching would not be a serious problem,
* although it would require a mild change in interfaces since one
* doesn't know whether an NFSv4 request is idempotent until after the
* XDR decode. However, XID caching totally confuses pynfs (Peter
* Astrand's regression testsuite for NFSv4 servers), which reuses
* XID's liberally, so I've left it unimplemented until pynfs generates
* better XID's.
*/
static struct svc_procedure nfsd_procedures4[2] = {
[NFSPROC4_NULL] = {
.pc_func = (svc_procfunc) nfsd4_proc_null,
.pc_encode = (kxdrproc_t) nfs4svc_encode_voidres,
.pc_argsize = sizeof(struct nfsd4_voidargs),
.pc_ressize = sizeof(struct nfsd4_voidres),
.pc_cachetype = RC_NOCACHE,
.pc_xdrressize = 1,
},
[NFSPROC4_COMPOUND] = {
.pc_func = (svc_procfunc) nfsd4_proc_compound,
.pc_decode = (kxdrproc_t) nfs4svc_decode_compoundargs,
.pc_encode = (kxdrproc_t) nfs4svc_encode_compoundres,
.pc_argsize = sizeof(struct nfsd4_compoundargs),
.pc_ressize = sizeof(struct nfsd4_compoundres),
.pc_cachetype = RC_NOCACHE,
.pc_xdrressize = NFSD_BUFSIZE/4,
},
};
struct svc_version nfsd_version4 = {
.vs_vers = 4,
.vs_nproc = 2,
.vs_proc = nfsd_procedures4,
.vs_dispatch = nfsd_dispatch,
.vs_xdrsize = NFS4_SVC_XDRSIZE,
};
/*
* Local variables:
* c-basic-offset: 8
* End:
*/