linux/fs/nfsd/nfs4xdr.c
Frank Filz 406a7ea97d 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>
2008-02-01 16:42:06 -05:00

2812 lines
69 KiB
C

/*
* fs/nfs/nfs4xdr.c
*
* Server-side XDR 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.
*
* TODO: Neil Brown made the following observation: We currently
* initially reserve NFSD_BUFSIZE space on the transmit queue and
* never release any of that until the request is complete.
* It would be good to calculate a new maximum response size while
* decoding the COMPOUND, and call svc_reserve with this number
* at the end of nfs4svc_decode_compoundargs.
*/
#include <linux/param.h>
#include <linux/smp.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/vfs.h>
#include <linux/sunrpc/xdr.h>
#include <linux/sunrpc/svc.h>
#include <linux/sunrpc/clnt.h>
#include <linux/nfsd/nfsd.h>
#include <linux/nfsd/state.h>
#include <linux/nfsd/xdr4.h>
#include <linux/nfsd_idmap.h>
#include <linux/nfs4.h>
#include <linux/nfs4_acl.h>
#include <linux/sunrpc/gss_api.h>
#include <linux/sunrpc/svcauth_gss.h>
#define NFSDDBG_FACILITY NFSDDBG_XDR
/*
* As per referral draft, the fsid for a referral MUST be different from the fsid of the containing
* directory in order to indicate to the client that a filesystem boundary is present
* We use a fixed fsid for a referral
*/
#define NFS4_REFERRAL_FSID_MAJOR 0x8000000ULL
#define NFS4_REFERRAL_FSID_MINOR 0x8000000ULL
static __be32
check_filename(char *str, int len, __be32 err)
{
int i;
if (len == 0)
return nfserr_inval;
if (isdotent(str, len))
return err;
for (i = 0; i < len; i++)
if (str[i] == '/')
return err;
return 0;
}
/*
* START OF "GENERIC" DECODE ROUTINES.
* These may look a little ugly since they are imported from a "generic"
* set of XDR encode/decode routines which are intended to be shared by
* all of our NFSv4 implementations (OpenBSD, MacOS X...).
*
* If the pain of reading these is too great, it should be a straightforward
* task to translate them into Linux-specific versions which are more
* consistent with the style used in NFSv2/v3...
*/
#define DECODE_HEAD \
__be32 *p; \
__be32 status
#define DECODE_TAIL \
status = 0; \
out: \
return status; \
xdr_error: \
dprintk("NFSD: xdr error (%s:%d)\n", \
__FILE__, __LINE__); \
status = nfserr_bad_xdr; \
goto out
#define READ32(x) (x) = ntohl(*p++)
#define READ64(x) do { \
(x) = (u64)ntohl(*p++) << 32; \
(x) |= ntohl(*p++); \
} while (0)
#define READTIME(x) do { \
p++; \
(x) = ntohl(*p++); \
p++; \
} while (0)
#define READMEM(x,nbytes) do { \
x = (char *)p; \
p += XDR_QUADLEN(nbytes); \
} while (0)
#define SAVEMEM(x,nbytes) do { \
if (!(x = (p==argp->tmp || p == argp->tmpp) ? \
savemem(argp, p, nbytes) : \
(char *)p)) { \
dprintk("NFSD: xdr error (%s:%d)\n", \
__FILE__, __LINE__); \
goto xdr_error; \
} \
p += XDR_QUADLEN(nbytes); \
} while (0)
#define COPYMEM(x,nbytes) do { \
memcpy((x), p, nbytes); \
p += XDR_QUADLEN(nbytes); \
} while (0)
/* READ_BUF, read_buf(): nbytes must be <= PAGE_SIZE */
#define READ_BUF(nbytes) do { \
if (nbytes <= (u32)((char *)argp->end - (char *)argp->p)) { \
p = argp->p; \
argp->p += XDR_QUADLEN(nbytes); \
} else if (!(p = read_buf(argp, nbytes))) { \
dprintk("NFSD: xdr error (%s:%d)\n", \
__FILE__, __LINE__); \
goto xdr_error; \
} \
} while (0)
static __be32 *read_buf(struct nfsd4_compoundargs *argp, u32 nbytes)
{
/* We want more bytes than seem to be available.
* Maybe we need a new page, maybe we have just run out
*/
unsigned int avail = (char *)argp->end - (char *)argp->p;
__be32 *p;
if (avail + argp->pagelen < nbytes)
return NULL;
if (avail + PAGE_SIZE < nbytes) /* need more than a page !! */
return NULL;
/* ok, we can do it with the current plus the next page */
if (nbytes <= sizeof(argp->tmp))
p = argp->tmp;
else {
kfree(argp->tmpp);
p = argp->tmpp = kmalloc(nbytes, GFP_KERNEL);
if (!p)
return NULL;
}
/*
* The following memcpy is safe because read_buf is always
* called with nbytes > avail, and the two cases above both
* guarantee p points to at least nbytes bytes.
*/
memcpy(p, argp->p, avail);
/* step to next page */
argp->p = page_address(argp->pagelist[0]);
argp->pagelist++;
if (argp->pagelen < PAGE_SIZE) {
argp->end = p + (argp->pagelen>>2);
argp->pagelen = 0;
} else {
argp->end = p + (PAGE_SIZE>>2);
argp->pagelen -= PAGE_SIZE;
}
memcpy(((char*)p)+avail, argp->p, (nbytes - avail));
argp->p += XDR_QUADLEN(nbytes - avail);
return p;
}
static int
defer_free(struct nfsd4_compoundargs *argp,
void (*release)(const void *), void *p)
{
struct tmpbuf *tb;
tb = kmalloc(sizeof(*tb), GFP_KERNEL);
if (!tb)
return -ENOMEM;
tb->buf = p;
tb->release = release;
tb->next = argp->to_free;
argp->to_free = tb;
return 0;
}
static char *savemem(struct nfsd4_compoundargs *argp, __be32 *p, int nbytes)
{
if (p == argp->tmp) {
p = kmalloc(nbytes, GFP_KERNEL);
if (!p)
return NULL;
memcpy(p, argp->tmp, nbytes);
} else {
BUG_ON(p != argp->tmpp);
argp->tmpp = NULL;
}
if (defer_free(argp, kfree, p)) {
kfree(p);
return NULL;
} else
return (char *)p;
}
static __be32
nfsd4_decode_bitmap(struct nfsd4_compoundargs *argp, u32 *bmval)
{
u32 bmlen;
DECODE_HEAD;
bmval[0] = 0;
bmval[1] = 0;
READ_BUF(4);
READ32(bmlen);
if (bmlen > 1000)
goto xdr_error;
READ_BUF(bmlen << 2);
if (bmlen > 0)
READ32(bmval[0]);
if (bmlen > 1)
READ32(bmval[1]);
DECODE_TAIL;
}
static __be32
nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, struct iattr *iattr,
struct nfs4_acl **acl)
{
int expected_len, len = 0;
u32 dummy32;
char *buf;
int host_err;
DECODE_HEAD;
iattr->ia_valid = 0;
if ((status = nfsd4_decode_bitmap(argp, bmval)))
return status;
/*
* According to spec, unsupported attributes return ERR_ATTRNOTSUPP;
* read-only attributes return ERR_INVAL.
*/
if ((bmval[0] & ~NFSD_SUPPORTED_ATTRS_WORD0) || (bmval[1] & ~NFSD_SUPPORTED_ATTRS_WORD1))
return nfserr_attrnotsupp;
if ((bmval[0] & ~NFSD_WRITEABLE_ATTRS_WORD0) || (bmval[1] & ~NFSD_WRITEABLE_ATTRS_WORD1))
return nfserr_inval;
READ_BUF(4);
READ32(expected_len);
if (bmval[0] & FATTR4_WORD0_SIZE) {
READ_BUF(8);
len += 8;
READ64(iattr->ia_size);
iattr->ia_valid |= ATTR_SIZE;
}
if (bmval[0] & FATTR4_WORD0_ACL) {
int nace;
struct nfs4_ace *ace;
READ_BUF(4); len += 4;
READ32(nace);
if (nace > NFS4_ACL_MAX)
return nfserr_resource;
*acl = nfs4_acl_new(nace);
if (*acl == NULL) {
host_err = -ENOMEM;
goto out_nfserr;
}
defer_free(argp, kfree, *acl);
(*acl)->naces = nace;
for (ace = (*acl)->aces; ace < (*acl)->aces + nace; ace++) {
READ_BUF(16); len += 16;
READ32(ace->type);
READ32(ace->flag);
READ32(ace->access_mask);
READ32(dummy32);
READ_BUF(dummy32);
len += XDR_QUADLEN(dummy32) << 2;
READMEM(buf, dummy32);
ace->whotype = nfs4_acl_get_whotype(buf, dummy32);
host_err = 0;
if (ace->whotype != NFS4_ACL_WHO_NAMED)
ace->who = 0;
else if (ace->flag & NFS4_ACE_IDENTIFIER_GROUP)
host_err = nfsd_map_name_to_gid(argp->rqstp,
buf, dummy32, &ace->who);
else
host_err = nfsd_map_name_to_uid(argp->rqstp,
buf, dummy32, &ace->who);
if (host_err)
goto out_nfserr;
}
} else
*acl = NULL;
if (bmval[1] & FATTR4_WORD1_MODE) {
READ_BUF(4);
len += 4;
READ32(iattr->ia_mode);
iattr->ia_mode &= (S_IFMT | S_IALLUGO);
iattr->ia_valid |= ATTR_MODE;
}
if (bmval[1] & FATTR4_WORD1_OWNER) {
READ_BUF(4);
len += 4;
READ32(dummy32);
READ_BUF(dummy32);
len += (XDR_QUADLEN(dummy32) << 2);
READMEM(buf, dummy32);
if ((host_err = nfsd_map_name_to_uid(argp->rqstp, buf, dummy32, &iattr->ia_uid)))
goto out_nfserr;
iattr->ia_valid |= ATTR_UID;
}
if (bmval[1] & FATTR4_WORD1_OWNER_GROUP) {
READ_BUF(4);
len += 4;
READ32(dummy32);
READ_BUF(dummy32);
len += (XDR_QUADLEN(dummy32) << 2);
READMEM(buf, dummy32);
if ((host_err = nfsd_map_name_to_gid(argp->rqstp, buf, dummy32, &iattr->ia_gid)))
goto out_nfserr;
iattr->ia_valid |= ATTR_GID;
}
if (bmval[1] & FATTR4_WORD1_TIME_ACCESS_SET) {
READ_BUF(4);
len += 4;
READ32(dummy32);
switch (dummy32) {
case NFS4_SET_TO_CLIENT_TIME:
/* We require the high 32 bits of 'seconds' to be 0, and we ignore
all 32 bits of 'nseconds'. */
READ_BUF(12);
len += 12;
READ32(dummy32);
if (dummy32)
return nfserr_inval;
READ32(iattr->ia_atime.tv_sec);
READ32(iattr->ia_atime.tv_nsec);
if (iattr->ia_atime.tv_nsec >= (u32)1000000000)
return nfserr_inval;
iattr->ia_valid |= (ATTR_ATIME | ATTR_ATIME_SET);
break;
case NFS4_SET_TO_SERVER_TIME:
iattr->ia_valid |= ATTR_ATIME;
break;
default:
goto xdr_error;
}
}
if (bmval[1] & FATTR4_WORD1_TIME_METADATA) {
/* We require the high 32 bits of 'seconds' to be 0, and we ignore
all 32 bits of 'nseconds'. */
READ_BUF(12);
len += 12;
READ32(dummy32);
if (dummy32)
return nfserr_inval;
READ32(iattr->ia_ctime.tv_sec);
READ32(iattr->ia_ctime.tv_nsec);
if (iattr->ia_ctime.tv_nsec >= (u32)1000000000)
return nfserr_inval;
iattr->ia_valid |= ATTR_CTIME;
}
if (bmval[1] & FATTR4_WORD1_TIME_MODIFY_SET) {
READ_BUF(4);
len += 4;
READ32(dummy32);
switch (dummy32) {
case NFS4_SET_TO_CLIENT_TIME:
/* We require the high 32 bits of 'seconds' to be 0, and we ignore
all 32 bits of 'nseconds'. */
READ_BUF(12);
len += 12;
READ32(dummy32);
if (dummy32)
return nfserr_inval;
READ32(iattr->ia_mtime.tv_sec);
READ32(iattr->ia_mtime.tv_nsec);
if (iattr->ia_mtime.tv_nsec >= (u32)1000000000)
return nfserr_inval;
iattr->ia_valid |= (ATTR_MTIME | ATTR_MTIME_SET);
break;
case NFS4_SET_TO_SERVER_TIME:
iattr->ia_valid |= ATTR_MTIME;
break;
default:
goto xdr_error;
}
}
if (len != expected_len)
goto xdr_error;
DECODE_TAIL;
out_nfserr:
status = nfserrno(host_err);
goto out;
}
static __be32
nfsd4_decode_access(struct nfsd4_compoundargs *argp, struct nfsd4_access *access)
{
DECODE_HEAD;
READ_BUF(4);
READ32(access->ac_req_access);
DECODE_TAIL;
}
static __be32
nfsd4_decode_close(struct nfsd4_compoundargs *argp, struct nfsd4_close *close)
{
DECODE_HEAD;
close->cl_stateowner = NULL;
READ_BUF(4 + sizeof(stateid_t));
READ32(close->cl_seqid);
READ32(close->cl_stateid.si_generation);
COPYMEM(&close->cl_stateid.si_opaque, sizeof(stateid_opaque_t));
DECODE_TAIL;
}
static __be32
nfsd4_decode_commit(struct nfsd4_compoundargs *argp, struct nfsd4_commit *commit)
{
DECODE_HEAD;
READ_BUF(12);
READ64(commit->co_offset);
READ32(commit->co_count);
DECODE_TAIL;
}
static __be32
nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create)
{
DECODE_HEAD;
READ_BUF(4);
READ32(create->cr_type);
switch (create->cr_type) {
case NF4LNK:
READ_BUF(4);
READ32(create->cr_linklen);
READ_BUF(create->cr_linklen);
SAVEMEM(create->cr_linkname, create->cr_linklen);
break;
case NF4BLK:
case NF4CHR:
READ_BUF(8);
READ32(create->cr_specdata1);
READ32(create->cr_specdata2);
break;
case NF4SOCK:
case NF4FIFO:
case NF4DIR:
default:
break;
}
READ_BUF(4);
READ32(create->cr_namelen);
READ_BUF(create->cr_namelen);
SAVEMEM(create->cr_name, create->cr_namelen);
if ((status = check_filename(create->cr_name, create->cr_namelen, nfserr_inval)))
return status;
if ((status = nfsd4_decode_fattr(argp, create->cr_bmval, &create->cr_iattr, &create->cr_acl)))
goto out;
DECODE_TAIL;
}
static inline __be32
nfsd4_decode_delegreturn(struct nfsd4_compoundargs *argp, struct nfsd4_delegreturn *dr)
{
DECODE_HEAD;
READ_BUF(sizeof(stateid_t));
READ32(dr->dr_stateid.si_generation);
COPYMEM(&dr->dr_stateid.si_opaque, sizeof(stateid_opaque_t));
DECODE_TAIL;
}
static inline __be32
nfsd4_decode_getattr(struct nfsd4_compoundargs *argp, struct nfsd4_getattr *getattr)
{
return nfsd4_decode_bitmap(argp, getattr->ga_bmval);
}
static __be32
nfsd4_decode_link(struct nfsd4_compoundargs *argp, struct nfsd4_link *link)
{
DECODE_HEAD;
READ_BUF(4);
READ32(link->li_namelen);
READ_BUF(link->li_namelen);
SAVEMEM(link->li_name, link->li_namelen);
if ((status = check_filename(link->li_name, link->li_namelen, nfserr_inval)))
return status;
DECODE_TAIL;
}
static __be32
nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock)
{
DECODE_HEAD;
lock->lk_replay_owner = NULL;
/*
* type, reclaim(boolean), offset, length, new_lock_owner(boolean)
*/
READ_BUF(28);
READ32(lock->lk_type);
if ((lock->lk_type < NFS4_READ_LT) || (lock->lk_type > NFS4_WRITEW_LT))
goto xdr_error;
READ32(lock->lk_reclaim);
READ64(lock->lk_offset);
READ64(lock->lk_length);
READ32(lock->lk_is_new);
if (lock->lk_is_new) {
READ_BUF(36);
READ32(lock->lk_new_open_seqid);
READ32(lock->lk_new_open_stateid.si_generation);
COPYMEM(&lock->lk_new_open_stateid.si_opaque, sizeof(stateid_opaque_t));
READ32(lock->lk_new_lock_seqid);
COPYMEM(&lock->lk_new_clientid, sizeof(clientid_t));
READ32(lock->lk_new_owner.len);
READ_BUF(lock->lk_new_owner.len);
READMEM(lock->lk_new_owner.data, lock->lk_new_owner.len);
} else {
READ_BUF(20);
READ32(lock->lk_old_lock_stateid.si_generation);
COPYMEM(&lock->lk_old_lock_stateid.si_opaque, sizeof(stateid_opaque_t));
READ32(lock->lk_old_lock_seqid);
}
DECODE_TAIL;
}
static __be32
nfsd4_decode_lockt(struct nfsd4_compoundargs *argp, struct nfsd4_lockt *lockt)
{
DECODE_HEAD;
READ_BUF(32);
READ32(lockt->lt_type);
if((lockt->lt_type < NFS4_READ_LT) || (lockt->lt_type > NFS4_WRITEW_LT))
goto xdr_error;
READ64(lockt->lt_offset);
READ64(lockt->lt_length);
COPYMEM(&lockt->lt_clientid, 8);
READ32(lockt->lt_owner.len);
READ_BUF(lockt->lt_owner.len);
READMEM(lockt->lt_owner.data, lockt->lt_owner.len);
DECODE_TAIL;
}
static __be32
nfsd4_decode_locku(struct nfsd4_compoundargs *argp, struct nfsd4_locku *locku)
{
DECODE_HEAD;
locku->lu_stateowner = NULL;
READ_BUF(24 + sizeof(stateid_t));
READ32(locku->lu_type);
if ((locku->lu_type < NFS4_READ_LT) || (locku->lu_type > NFS4_WRITEW_LT))
goto xdr_error;
READ32(locku->lu_seqid);
READ32(locku->lu_stateid.si_generation);
COPYMEM(&locku->lu_stateid.si_opaque, sizeof(stateid_opaque_t));
READ64(locku->lu_offset);
READ64(locku->lu_length);
DECODE_TAIL;
}
static __be32
nfsd4_decode_lookup(struct nfsd4_compoundargs *argp, struct nfsd4_lookup *lookup)
{
DECODE_HEAD;
READ_BUF(4);
READ32(lookup->lo_len);
READ_BUF(lookup->lo_len);
SAVEMEM(lookup->lo_name, lookup->lo_len);
if ((status = check_filename(lookup->lo_name, lookup->lo_len, nfserr_noent)))
return status;
DECODE_TAIL;
}
static __be32
nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
{
DECODE_HEAD;
memset(open->op_bmval, 0, sizeof(open->op_bmval));
open->op_iattr.ia_valid = 0;
open->op_stateowner = NULL;
/* seqid, share_access, share_deny, clientid, ownerlen */
READ_BUF(16 + sizeof(clientid_t));
READ32(open->op_seqid);
READ32(open->op_share_access);
READ32(open->op_share_deny);
COPYMEM(&open->op_clientid, sizeof(clientid_t));
READ32(open->op_owner.len);
/* owner, open_flag */
READ_BUF(open->op_owner.len + 4);
SAVEMEM(open->op_owner.data, open->op_owner.len);
READ32(open->op_create);
switch (open->op_create) {
case NFS4_OPEN_NOCREATE:
break;
case NFS4_OPEN_CREATE:
READ_BUF(4);
READ32(open->op_createmode);
switch (open->op_createmode) {
case NFS4_CREATE_UNCHECKED:
case NFS4_CREATE_GUARDED:
if ((status = nfsd4_decode_fattr(argp, open->op_bmval, &open->op_iattr, &open->op_acl)))
goto out;
break;
case NFS4_CREATE_EXCLUSIVE:
READ_BUF(8);
COPYMEM(open->op_verf.data, 8);
break;
default:
goto xdr_error;
}
break;
default:
goto xdr_error;
}
/* open_claim */
READ_BUF(4);
READ32(open->op_claim_type);
switch (open->op_claim_type) {
case NFS4_OPEN_CLAIM_NULL:
case NFS4_OPEN_CLAIM_DELEGATE_PREV:
READ_BUF(4);
READ32(open->op_fname.len);
READ_BUF(open->op_fname.len);
SAVEMEM(open->op_fname.data, open->op_fname.len);
if ((status = check_filename(open->op_fname.data, open->op_fname.len, nfserr_inval)))
return status;
break;
case NFS4_OPEN_CLAIM_PREVIOUS:
READ_BUF(4);
READ32(open->op_delegate_type);
break;
case NFS4_OPEN_CLAIM_DELEGATE_CUR:
READ_BUF(sizeof(stateid_t) + 4);
COPYMEM(&open->op_delegate_stateid, sizeof(stateid_t));
READ32(open->op_fname.len);
READ_BUF(open->op_fname.len);
SAVEMEM(open->op_fname.data, open->op_fname.len);
if ((status = check_filename(open->op_fname.data, open->op_fname.len, nfserr_inval)))
return status;
break;
default:
goto xdr_error;
}
DECODE_TAIL;
}
static __be32
nfsd4_decode_open_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_open_confirm *open_conf)
{
DECODE_HEAD;
open_conf->oc_stateowner = NULL;
READ_BUF(4 + sizeof(stateid_t));
READ32(open_conf->oc_req_stateid.si_generation);
COPYMEM(&open_conf->oc_req_stateid.si_opaque, sizeof(stateid_opaque_t));
READ32(open_conf->oc_seqid);
DECODE_TAIL;
}
static __be32
nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, struct nfsd4_open_downgrade *open_down)
{
DECODE_HEAD;
open_down->od_stateowner = NULL;
READ_BUF(12 + sizeof(stateid_t));
READ32(open_down->od_stateid.si_generation);
COPYMEM(&open_down->od_stateid.si_opaque, sizeof(stateid_opaque_t));
READ32(open_down->od_seqid);
READ32(open_down->od_share_access);
READ32(open_down->od_share_deny);
DECODE_TAIL;
}
static __be32
nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, struct nfsd4_putfh *putfh)
{
DECODE_HEAD;
READ_BUF(4);
READ32(putfh->pf_fhlen);
if (putfh->pf_fhlen > NFS4_FHSIZE)
goto xdr_error;
READ_BUF(putfh->pf_fhlen);
SAVEMEM(putfh->pf_fhval, putfh->pf_fhlen);
DECODE_TAIL;
}
static __be32
nfsd4_decode_read(struct nfsd4_compoundargs *argp, struct nfsd4_read *read)
{
DECODE_HEAD;
READ_BUF(sizeof(stateid_t) + 12);
READ32(read->rd_stateid.si_generation);
COPYMEM(&read->rd_stateid.si_opaque, sizeof(stateid_opaque_t));
READ64(read->rd_offset);
READ32(read->rd_length);
DECODE_TAIL;
}
static __be32
nfsd4_decode_readdir(struct nfsd4_compoundargs *argp, struct nfsd4_readdir *readdir)
{
DECODE_HEAD;
READ_BUF(24);
READ64(readdir->rd_cookie);
COPYMEM(readdir->rd_verf.data, sizeof(readdir->rd_verf.data));
READ32(readdir->rd_dircount); /* just in case you needed a useless field... */
READ32(readdir->rd_maxcount);
if ((status = nfsd4_decode_bitmap(argp, readdir->rd_bmval)))
goto out;
DECODE_TAIL;
}
static __be32
nfsd4_decode_remove(struct nfsd4_compoundargs *argp, struct nfsd4_remove *remove)
{
DECODE_HEAD;
READ_BUF(4);
READ32(remove->rm_namelen);
READ_BUF(remove->rm_namelen);
SAVEMEM(remove->rm_name, remove->rm_namelen);
if ((status = check_filename(remove->rm_name, remove->rm_namelen, nfserr_noent)))
return status;
DECODE_TAIL;
}
static __be32
nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename)
{
DECODE_HEAD;
READ_BUF(4);
READ32(rename->rn_snamelen);
READ_BUF(rename->rn_snamelen + 4);
SAVEMEM(rename->rn_sname, rename->rn_snamelen);
READ32(rename->rn_tnamelen);
READ_BUF(rename->rn_tnamelen);
SAVEMEM(rename->rn_tname, rename->rn_tnamelen);
if ((status = check_filename(rename->rn_sname, rename->rn_snamelen, nfserr_noent)))
return status;
if ((status = check_filename(rename->rn_tname, rename->rn_tnamelen, nfserr_inval)))
return status;
DECODE_TAIL;
}
static __be32
nfsd4_decode_renew(struct nfsd4_compoundargs *argp, clientid_t *clientid)
{
DECODE_HEAD;
READ_BUF(sizeof(clientid_t));
COPYMEM(clientid, sizeof(clientid_t));
DECODE_TAIL;
}
static __be32
nfsd4_decode_secinfo(struct nfsd4_compoundargs *argp,
struct nfsd4_secinfo *secinfo)
{
DECODE_HEAD;
READ_BUF(4);
READ32(secinfo->si_namelen);
READ_BUF(secinfo->si_namelen);
SAVEMEM(secinfo->si_name, secinfo->si_namelen);
status = check_filename(secinfo->si_name, secinfo->si_namelen,
nfserr_noent);
if (status)
return status;
DECODE_TAIL;
}
static __be32
nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, struct nfsd4_setattr *setattr)
{
DECODE_HEAD;
READ_BUF(sizeof(stateid_t));
READ32(setattr->sa_stateid.si_generation);
COPYMEM(&setattr->sa_stateid.si_opaque, sizeof(stateid_opaque_t));
if ((status = nfsd4_decode_fattr(argp, setattr->sa_bmval, &setattr->sa_iattr, &setattr->sa_acl)))
goto out;
DECODE_TAIL;
}
static __be32
nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclientid *setclientid)
{
DECODE_HEAD;
READ_BUF(12);
COPYMEM(setclientid->se_verf.data, 8);
READ32(setclientid->se_namelen);
READ_BUF(setclientid->se_namelen + 8);
SAVEMEM(setclientid->se_name, setclientid->se_namelen);
READ32(setclientid->se_callback_prog);
READ32(setclientid->se_callback_netid_len);
READ_BUF(setclientid->se_callback_netid_len + 4);
SAVEMEM(setclientid->se_callback_netid_val, setclientid->se_callback_netid_len);
READ32(setclientid->se_callback_addr_len);
READ_BUF(setclientid->se_callback_addr_len + 4);
SAVEMEM(setclientid->se_callback_addr_val, setclientid->se_callback_addr_len);
READ32(setclientid->se_callback_ident);
DECODE_TAIL;
}
static __be32
nfsd4_decode_setclientid_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_setclientid_confirm *scd_c)
{
DECODE_HEAD;
READ_BUF(8 + sizeof(nfs4_verifier));
COPYMEM(&scd_c->sc_clientid, 8);
COPYMEM(&scd_c->sc_confirm, sizeof(nfs4_verifier));
DECODE_TAIL;
}
/* Also used for NVERIFY */
static __be32
nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify)
{
#if 0
struct nfsd4_compoundargs save = {
.p = argp->p,
.end = argp->end,
.rqstp = argp->rqstp,
};
u32 ve_bmval[2];
struct iattr ve_iattr; /* request */
struct nfs4_acl *ve_acl; /* request */
#endif
DECODE_HEAD;
if ((status = nfsd4_decode_bitmap(argp, verify->ve_bmval)))
goto out;
/* For convenience's sake, we compare raw xdr'd attributes in
* nfsd4_proc_verify; however we still decode here just to return
* correct error in case of bad xdr. */
#if 0
status = nfsd4_decode_fattr(ve_bmval, &ve_iattr, &ve_acl);
if (status == nfserr_inval) {
status = nfserrno(status);
goto out;
}
#endif
READ_BUF(4);
READ32(verify->ve_attrlen);
READ_BUF(verify->ve_attrlen);
SAVEMEM(verify->ve_attrval, verify->ve_attrlen);
DECODE_TAIL;
}
static __be32
nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write)
{
int avail;
int v;
int len;
DECODE_HEAD;
READ_BUF(sizeof(stateid_opaque_t) + 20);
READ32(write->wr_stateid.si_generation);
COPYMEM(&write->wr_stateid.si_opaque, sizeof(stateid_opaque_t));
READ64(write->wr_offset);
READ32(write->wr_stable_how);
if (write->wr_stable_how > 2)
goto xdr_error;
READ32(write->wr_buflen);
/* Sorry .. no magic macros for this.. *
* READ_BUF(write->wr_buflen);
* SAVEMEM(write->wr_buf, write->wr_buflen);
*/
avail = (char*)argp->end - (char*)argp->p;
if (avail + argp->pagelen < write->wr_buflen) {
dprintk("NFSD: xdr error (%s:%d)\n",
__FILE__, __LINE__);
goto xdr_error;
}
argp->rqstp->rq_vec[0].iov_base = p;
argp->rqstp->rq_vec[0].iov_len = avail;
v = 0;
len = write->wr_buflen;
while (len > argp->rqstp->rq_vec[v].iov_len) {
len -= argp->rqstp->rq_vec[v].iov_len;
v++;
argp->rqstp->rq_vec[v].iov_base = page_address(argp->pagelist[0]);
argp->pagelist++;
if (argp->pagelen >= PAGE_SIZE) {
argp->rqstp->rq_vec[v].iov_len = PAGE_SIZE;
argp->pagelen -= PAGE_SIZE;
} else {
argp->rqstp->rq_vec[v].iov_len = argp->pagelen;
argp->pagelen -= len;
}
}
argp->end = (__be32*) (argp->rqstp->rq_vec[v].iov_base + argp->rqstp->rq_vec[v].iov_len);
argp->p = (__be32*) (argp->rqstp->rq_vec[v].iov_base + (XDR_QUADLEN(len) << 2));
argp->rqstp->rq_vec[v].iov_len = len;
write->wr_vlen = v+1;
DECODE_TAIL;
}
static __be32
nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, struct nfsd4_release_lockowner *rlockowner)
{
DECODE_HEAD;
READ_BUF(12);
COPYMEM(&rlockowner->rl_clientid, sizeof(clientid_t));
READ32(rlockowner->rl_owner.len);
READ_BUF(rlockowner->rl_owner.len);
READMEM(rlockowner->rl_owner.data, rlockowner->rl_owner.len);
DECODE_TAIL;
}
static __be32
nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
{
DECODE_HEAD;
struct nfsd4_op *op;
int i;
/*
* XXX: According to spec, we should check the tag
* for UTF-8 compliance. I'm postponing this for
* now because it seems that some clients do use
* binary tags.
*/
READ_BUF(4);
READ32(argp->taglen);
READ_BUF(argp->taglen + 8);
SAVEMEM(argp->tag, argp->taglen);
READ32(argp->minorversion);
READ32(argp->opcnt);
if (argp->taglen > NFSD4_MAX_TAGLEN)
goto xdr_error;
if (argp->opcnt > 100)
goto xdr_error;
if (argp->opcnt > ARRAY_SIZE(argp->iops)) {
argp->ops = kmalloc(argp->opcnt * sizeof(*argp->ops), GFP_KERNEL);
if (!argp->ops) {
argp->ops = argp->iops;
dprintk("nfsd: couldn't allocate room for COMPOUND\n");
goto xdr_error;
}
}
for (i = 0; i < argp->opcnt; i++) {
op = &argp->ops[i];
op->replay = NULL;
/*
* We can't use READ_BUF() here because we need to handle
* a missing opcode as an OP_WRITE + 1. So we need to check
* to see if we're truly at the end of our buffer or if there
* is another page we need to flip to.
*/
if (argp->p == argp->end) {
if (argp->pagelen < 4) {
/* There isn't an opcode still on the wire */
op->opnum = OP_WRITE + 1;
op->status = nfserr_bad_xdr;
argp->opcnt = i+1;
break;
}
/*
* False alarm. We just hit a page boundary, but there
* is still data available. Move pointer across page
* boundary. *snip from READ_BUF*
*/
argp->p = page_address(argp->pagelist[0]);
argp->pagelist++;
if (argp->pagelen < PAGE_SIZE) {
argp->end = p + (argp->pagelen>>2);
argp->pagelen = 0;
} else {
argp->end = p + (PAGE_SIZE>>2);
argp->pagelen -= PAGE_SIZE;
}
}
op->opnum = ntohl(*argp->p++);
switch (op->opnum) {
case 2: /* Reserved operation */
op->opnum = OP_ILLEGAL;
if (argp->minorversion == 0)
op->status = nfserr_op_illegal;
else
op->status = nfserr_minor_vers_mismatch;
break;
case OP_ACCESS:
op->status = nfsd4_decode_access(argp, &op->u.access);
break;
case OP_CLOSE:
op->status = nfsd4_decode_close(argp, &op->u.close);
break;
case OP_COMMIT:
op->status = nfsd4_decode_commit(argp, &op->u.commit);
break;
case OP_CREATE:
op->status = nfsd4_decode_create(argp, &op->u.create);
break;
case OP_DELEGRETURN:
op->status = nfsd4_decode_delegreturn(argp, &op->u.delegreturn);
break;
case OP_GETATTR:
op->status = nfsd4_decode_getattr(argp, &op->u.getattr);
break;
case OP_GETFH:
op->status = nfs_ok;
break;
case OP_LINK:
op->status = nfsd4_decode_link(argp, &op->u.link);
break;
case OP_LOCK:
op->status = nfsd4_decode_lock(argp, &op->u.lock);
break;
case OP_LOCKT:
op->status = nfsd4_decode_lockt(argp, &op->u.lockt);
break;
case OP_LOCKU:
op->status = nfsd4_decode_locku(argp, &op->u.locku);
break;
case OP_LOOKUP:
op->status = nfsd4_decode_lookup(argp, &op->u.lookup);
break;
case OP_LOOKUPP:
op->status = nfs_ok;
break;
case OP_NVERIFY:
op->status = nfsd4_decode_verify(argp, &op->u.nverify);
break;
case OP_OPEN:
op->status = nfsd4_decode_open(argp, &op->u.open);
break;
case OP_OPEN_CONFIRM:
op->status = nfsd4_decode_open_confirm(argp, &op->u.open_confirm);
break;
case OP_OPEN_DOWNGRADE:
op->status = nfsd4_decode_open_downgrade(argp, &op->u.open_downgrade);
break;
case OP_PUTFH:
op->status = nfsd4_decode_putfh(argp, &op->u.putfh);
break;
case OP_PUTROOTFH:
op->status = nfs_ok;
break;
case OP_READ:
op->status = nfsd4_decode_read(argp, &op->u.read);
break;
case OP_READDIR:
op->status = nfsd4_decode_readdir(argp, &op->u.readdir);
break;
case OP_READLINK:
op->status = nfs_ok;
break;
case OP_REMOVE:
op->status = nfsd4_decode_remove(argp, &op->u.remove);
break;
case OP_RENAME:
op->status = nfsd4_decode_rename(argp, &op->u.rename);
break;
case OP_RESTOREFH:
op->status = nfs_ok;
break;
case OP_RENEW:
op->status = nfsd4_decode_renew(argp, &op->u.renew);
break;
case OP_SAVEFH:
op->status = nfs_ok;
break;
case OP_SECINFO:
op->status = nfsd4_decode_secinfo(argp, &op->u.secinfo);
break;
case OP_SETATTR:
op->status = nfsd4_decode_setattr(argp, &op->u.setattr);
break;
case OP_SETCLIENTID:
op->status = nfsd4_decode_setclientid(argp, &op->u.setclientid);
break;
case OP_SETCLIENTID_CONFIRM:
op->status = nfsd4_decode_setclientid_confirm(argp, &op->u.setclientid_confirm);
break;
case OP_VERIFY:
op->status = nfsd4_decode_verify(argp, &op->u.verify);
break;
case OP_WRITE:
op->status = nfsd4_decode_write(argp, &op->u.write);
break;
case OP_RELEASE_LOCKOWNER:
op->status = nfsd4_decode_release_lockowner(argp, &op->u.release_lockowner);
break;
default:
op->opnum = OP_ILLEGAL;
op->status = nfserr_op_illegal;
break;
}
if (op->status) {
argp->opcnt = i+1;
break;
}
}
DECODE_TAIL;
}
/*
* END OF "GENERIC" DECODE ROUTINES.
*/
/*
* START OF "GENERIC" ENCODE ROUTINES.
* These may look a little ugly since they are imported from a "generic"
* set of XDR encode/decode routines which are intended to be shared by
* all of our NFSv4 implementations (OpenBSD, MacOS X...).
*
* If the pain of reading these is too great, it should be a straightforward
* task to translate them into Linux-specific versions which are more
* consistent with the style used in NFSv2/v3...
*/
#define ENCODE_HEAD __be32 *p
#define WRITE32(n) *p++ = htonl(n)
#define WRITE64(n) do { \
*p++ = htonl((u32)((n) >> 32)); \
*p++ = htonl((u32)(n)); \
} while (0)
#define WRITEMEM(ptr,nbytes) do { \
*(p + XDR_QUADLEN(nbytes) -1) = 0; \
memcpy(p, ptr, nbytes); \
p += XDR_QUADLEN(nbytes); \
} while (0)
#define WRITECINFO(c) do { \
*p++ = htonl(c.atomic); \
*p++ = htonl(c.before_ctime_sec); \
*p++ = htonl(c.before_ctime_nsec); \
*p++ = htonl(c.after_ctime_sec); \
*p++ = htonl(c.after_ctime_nsec); \
} while (0)
#define RESERVE_SPACE(nbytes) do { \
p = resp->p; \
BUG_ON(p + XDR_QUADLEN(nbytes) > resp->end); \
} while (0)
#define ADJUST_ARGS() resp->p = p
/*
* Header routine to setup seqid operation replay cache
*/
#define ENCODE_SEQID_OP_HEAD \
__be32 *p; \
__be32 *save; \
\
save = resp->p;
/*
* Routine for encoding the result of a "seqid-mutating" NFSv4 operation. This
* is where sequence id's are incremented, and the replay cache is filled.
* Note that we increment sequence id's here, at the last moment, so we're sure
* we know whether the error to be returned is a sequence id mutating error.
*/
#define ENCODE_SEQID_OP_TAIL(stateowner) do { \
if (seqid_mutating_err(nfserr) && stateowner) { \
stateowner->so_seqid++; \
stateowner->so_replay.rp_status = nfserr; \
stateowner->so_replay.rp_buflen = \
(((char *)(resp)->p - (char *)save)); \
memcpy(stateowner->so_replay.rp_buf, save, \
stateowner->so_replay.rp_buflen); \
} } while (0);
/* Encode as an array of strings the string given with components
* seperated @sep.
*/
static __be32 nfsd4_encode_components(char sep, char *components,
__be32 **pp, int *buflen)
{
__be32 *p = *pp;
__be32 *countp = p;
int strlen, count=0;
char *str, *end;
dprintk("nfsd4_encode_components(%s)\n", components);
if ((*buflen -= 4) < 0)
return nfserr_resource;
WRITE32(0); /* We will fill this in with @count later */
end = str = components;
while (*end) {
for (; *end && (*end != sep); end++)
; /* Point to end of component */
strlen = end - str;
if (strlen) {
if ((*buflen -= ((XDR_QUADLEN(strlen) << 2) + 4)) < 0)
return nfserr_resource;
WRITE32(strlen);
WRITEMEM(str, strlen);
count++;
}
else
end++;
str = end;
}
*pp = p;
p = countp;
WRITE32(count);
return 0;
}
/*
* encode a location element of a fs_locations structure
*/
static __be32 nfsd4_encode_fs_location4(struct nfsd4_fs_location *location,
__be32 **pp, int *buflen)
{
__be32 status;
__be32 *p = *pp;
status = nfsd4_encode_components(':', location->hosts, &p, buflen);
if (status)
return status;
status = nfsd4_encode_components('/', location->path, &p, buflen);
if (status)
return status;
*pp = p;
return 0;
}
/*
* Return the path to an export point in the pseudo filesystem namespace
* Returned string is safe to use as long as the caller holds a reference
* to @exp.
*/
static char *nfsd4_path(struct svc_rqst *rqstp, struct svc_export *exp, __be32 *stat)
{
struct svc_fh tmp_fh;
char *path, *rootpath;
fh_init(&tmp_fh, NFS4_FHSIZE);
*stat = exp_pseudoroot(rqstp, &tmp_fh);
if (*stat)
return NULL;
rootpath = tmp_fh.fh_export->ex_path;
path = exp->ex_path;
if (strncmp(path, rootpath, strlen(rootpath))) {
dprintk("nfsd: fs_locations failed;"
"%s is not contained in %s\n", path, rootpath);
*stat = nfserr_notsupp;
return NULL;
}
return path + strlen(rootpath);
}
/*
* encode a fs_locations structure
*/
static __be32 nfsd4_encode_fs_locations(struct svc_rqst *rqstp,
struct svc_export *exp,
__be32 **pp, int *buflen)
{
__be32 status;
int i;
__be32 *p = *pp;
struct nfsd4_fs_locations *fslocs = &exp->ex_fslocs;
char *root = nfsd4_path(rqstp, exp, &status);
if (status)
return status;
status = nfsd4_encode_components('/', root, &p, buflen);
if (status)
return status;
if ((*buflen -= 4) < 0)
return nfserr_resource;
WRITE32(fslocs->locations_count);
for (i=0; i<fslocs->locations_count; i++) {
status = nfsd4_encode_fs_location4(&fslocs->locations[i],
&p, buflen);
if (status)
return status;
}
*pp = p;
return 0;
}
static u32 nfs4_ftypes[16] = {
NF4BAD, NF4FIFO, NF4CHR, NF4BAD,
NF4DIR, NF4BAD, NF4BLK, NF4BAD,
NF4REG, NF4BAD, NF4LNK, NF4BAD,
NF4SOCK, NF4BAD, NF4LNK, NF4BAD,
};
static __be32
nfsd4_encode_name(struct svc_rqst *rqstp, int whotype, uid_t id, int group,
__be32 **p, int *buflen)
{
int status;
if (*buflen < (XDR_QUADLEN(IDMAP_NAMESZ) << 2) + 4)
return nfserr_resource;
if (whotype != NFS4_ACL_WHO_NAMED)
status = nfs4_acl_write_who(whotype, (u8 *)(*p + 1));
else if (group)
status = nfsd_map_gid_to_name(rqstp, id, (u8 *)(*p + 1));
else
status = nfsd_map_uid_to_name(rqstp, id, (u8 *)(*p + 1));
if (status < 0)
return nfserrno(status);
*p = xdr_encode_opaque(*p, NULL, status);
*buflen -= (XDR_QUADLEN(status) << 2) + 4;
BUG_ON(*buflen < 0);
return 0;
}
static inline __be32
nfsd4_encode_user(struct svc_rqst *rqstp, uid_t uid, __be32 **p, int *buflen)
{
return nfsd4_encode_name(rqstp, NFS4_ACL_WHO_NAMED, uid, 0, p, buflen);
}
static inline __be32
nfsd4_encode_group(struct svc_rqst *rqstp, uid_t gid, __be32 **p, int *buflen)
{
return nfsd4_encode_name(rqstp, NFS4_ACL_WHO_NAMED, gid, 1, p, buflen);
}
static inline __be32
nfsd4_encode_aclname(struct svc_rqst *rqstp, int whotype, uid_t id, int group,
__be32 **p, int *buflen)
{
return nfsd4_encode_name(rqstp, whotype, id, group, p, buflen);
}
#define WORD0_ABSENT_FS_ATTRS (FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_FSID | \
FATTR4_WORD0_RDATTR_ERROR)
#define WORD1_ABSENT_FS_ATTRS FATTR4_WORD1_MOUNTED_ON_FILEID
static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *rdattr_err)
{
/* As per referral draft: */
if (*bmval0 & ~WORD0_ABSENT_FS_ATTRS ||
*bmval1 & ~WORD1_ABSENT_FS_ATTRS) {
if (*bmval0 & FATTR4_WORD0_RDATTR_ERROR ||
*bmval0 & FATTR4_WORD0_FS_LOCATIONS)
*rdattr_err = NFSERR_MOVED;
else
return nfserr_moved;
}
*bmval0 &= WORD0_ABSENT_FS_ATTRS;
*bmval1 &= WORD1_ABSENT_FS_ATTRS;
return 0;
}
/*
* Note: @fhp can be NULL; in this case, we might have to compose the filehandle
* ourselves.
*
* @countp is the buffer size in _words_; upon successful return this becomes
* replaced with the number of words written.
*/
__be32
nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
struct dentry *dentry, __be32 *buffer, int *countp, u32 *bmval,
struct svc_rqst *rqstp, int ignore_crossmnt)
{
u32 bmval0 = bmval[0];
u32 bmval1 = bmval[1];
struct kstat stat;
struct svc_fh tempfh;
struct kstatfs statfs;
int buflen = *countp << 2;
__be32 *attrlenp;
u32 dummy;
u64 dummy64;
u32 rdattr_err = 0;
__be32 *p = buffer;
__be32 status;
int err;
int aclsupport = 0;
struct nfs4_acl *acl = NULL;
BUG_ON(bmval1 & NFSD_WRITEONLY_ATTRS_WORD1);
BUG_ON(bmval0 & ~NFSD_SUPPORTED_ATTRS_WORD0);
BUG_ON(bmval1 & ~NFSD_SUPPORTED_ATTRS_WORD1);
if (exp->ex_fslocs.migrated) {
status = fattr_handle_absent_fs(&bmval0, &bmval1, &rdattr_err);
if (status)
goto out;
}
err = vfs_getattr(exp->ex_mnt, dentry, &stat);
if (err)
goto out_nfserr;
if ((bmval0 & (FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL |
FATTR4_WORD0_MAXNAME)) ||
(bmval1 & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE |
FATTR4_WORD1_SPACE_TOTAL))) {
err = vfs_statfs(dentry, &statfs);
if (err)
goto out_nfserr;
}
if ((bmval0 & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID)) && !fhp) {
fh_init(&tempfh, NFS4_FHSIZE);
status = fh_compose(&tempfh, exp, dentry, NULL);
if (status)
goto out;
fhp = &tempfh;
}
if (bmval0 & (FATTR4_WORD0_ACL | FATTR4_WORD0_ACLSUPPORT
| FATTR4_WORD0_SUPPORTED_ATTRS)) {
err = nfsd4_get_nfs4_acl(rqstp, dentry, &acl);
aclsupport = (err == 0);
if (bmval0 & FATTR4_WORD0_ACL) {
if (err == -EOPNOTSUPP)
bmval0 &= ~FATTR4_WORD0_ACL;
else if (err == -EINVAL) {
status = nfserr_attrnotsupp;
goto out;
} else if (err != 0)
goto out_nfserr;
}
}
if (bmval0 & FATTR4_WORD0_FS_LOCATIONS) {
if (exp->ex_fslocs.locations == NULL) {
bmval0 &= ~FATTR4_WORD0_FS_LOCATIONS;
}
}
if ((buflen -= 16) < 0)
goto out_resource;
WRITE32(2);
WRITE32(bmval0);
WRITE32(bmval1);
attrlenp = p++; /* to be backfilled later */
if (bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) {
u32 word0 = NFSD_SUPPORTED_ATTRS_WORD0;
if ((buflen -= 12) < 0)
goto out_resource;
if (!aclsupport)
word0 &= ~FATTR4_WORD0_ACL;
if (!exp->ex_fslocs.locations)
word0 &= ~FATTR4_WORD0_FS_LOCATIONS;
WRITE32(2);
WRITE32(word0);
WRITE32(NFSD_SUPPORTED_ATTRS_WORD1);
}
if (bmval0 & FATTR4_WORD0_TYPE) {
if ((buflen -= 4) < 0)
goto out_resource;
dummy = nfs4_ftypes[(stat.mode & S_IFMT) >> 12];
if (dummy == NF4BAD)
goto out_serverfault;
WRITE32(dummy);
}
if (bmval0 & FATTR4_WORD0_FH_EXPIRE_TYPE) {
if ((buflen -= 4) < 0)
goto out_resource;
if (exp->ex_flags & NFSEXP_NOSUBTREECHECK)
WRITE32(NFS4_FH_PERSISTENT);
else
WRITE32(NFS4_FH_PERSISTENT|NFS4_FH_VOL_RENAME);
}
if (bmval0 & FATTR4_WORD0_CHANGE) {
/*
* Note: This _must_ be consistent with the scheme for writing
* change_info, so any changes made here must be reflected there
* as well. (See xdr4.h:set_change_info() and the WRITECINFO()
* macro above.)
*/
if ((buflen -= 8) < 0)
goto out_resource;
WRITE32(stat.ctime.tv_sec);
WRITE32(stat.ctime.tv_nsec);
}
if (bmval0 & FATTR4_WORD0_SIZE) {
if ((buflen -= 8) < 0)
goto out_resource;
WRITE64(stat.size);
}
if (bmval0 & FATTR4_WORD0_LINK_SUPPORT) {
if ((buflen -= 4) < 0)
goto out_resource;
WRITE32(1);
}
if (bmval0 & FATTR4_WORD0_SYMLINK_SUPPORT) {
if ((buflen -= 4) < 0)
goto out_resource;
WRITE32(1);
}
if (bmval0 & FATTR4_WORD0_NAMED_ATTR) {
if ((buflen -= 4) < 0)
goto out_resource;
WRITE32(0);
}
if (bmval0 & FATTR4_WORD0_FSID) {
if ((buflen -= 16) < 0)
goto out_resource;
if (exp->ex_fslocs.migrated) {
WRITE64(NFS4_REFERRAL_FSID_MAJOR);
WRITE64(NFS4_REFERRAL_FSID_MINOR);
} else switch(fsid_source(fhp)) {
case FSIDSOURCE_FSID:
WRITE64((u64)exp->ex_fsid);
WRITE64((u64)0);
break;
case FSIDSOURCE_DEV:
WRITE32(0);
WRITE32(MAJOR(stat.dev));
WRITE32(0);
WRITE32(MINOR(stat.dev));
break;
case FSIDSOURCE_UUID:
WRITEMEM(exp->ex_uuid, 16);
break;
}
}
if (bmval0 & FATTR4_WORD0_UNIQUE_HANDLES) {
if ((buflen -= 4) < 0)
goto out_resource;
WRITE32(0);
}
if (bmval0 & FATTR4_WORD0_LEASE_TIME) {
if ((buflen -= 4) < 0)
goto out_resource;
WRITE32(NFSD_LEASE_TIME);
}
if (bmval0 & FATTR4_WORD0_RDATTR_ERROR) {
if ((buflen -= 4) < 0)
goto out_resource;
WRITE32(rdattr_err);
}
if (bmval0 & FATTR4_WORD0_ACL) {
struct nfs4_ace *ace;
if (acl == NULL) {
if ((buflen -= 4) < 0)
goto out_resource;
WRITE32(0);
goto out_acl;
}
if ((buflen -= 4) < 0)
goto out_resource;
WRITE32(acl->naces);
for (ace = acl->aces; ace < acl->aces + acl->naces; ace++) {
if ((buflen -= 4*3) < 0)
goto out_resource;
WRITE32(ace->type);
WRITE32(ace->flag);
WRITE32(ace->access_mask & NFS4_ACE_MASK_ALL);
status = nfsd4_encode_aclname(rqstp, ace->whotype,
ace->who, ace->flag & NFS4_ACE_IDENTIFIER_GROUP,
&p, &buflen);
if (status == nfserr_resource)
goto out_resource;
if (status)
goto out;
}
}
out_acl:
if (bmval0 & FATTR4_WORD0_ACLSUPPORT) {
if ((buflen -= 4) < 0)
goto out_resource;
WRITE32(aclsupport ?
ACL4_SUPPORT_ALLOW_ACL|ACL4_SUPPORT_DENY_ACL : 0);
}
if (bmval0 & FATTR4_WORD0_CANSETTIME) {
if ((buflen -= 4) < 0)
goto out_resource;
WRITE32(1);
}
if (bmval0 & FATTR4_WORD0_CASE_INSENSITIVE) {
if ((buflen -= 4) < 0)
goto out_resource;
WRITE32(1);
}
if (bmval0 & FATTR4_WORD0_CASE_PRESERVING) {
if ((buflen -= 4) < 0)
goto out_resource;
WRITE32(1);
}
if (bmval0 & FATTR4_WORD0_CHOWN_RESTRICTED) {
if ((buflen -= 4) < 0)
goto out_resource;
WRITE32(1);
}
if (bmval0 & FATTR4_WORD0_FILEHANDLE) {
buflen -= (XDR_QUADLEN(fhp->fh_handle.fh_size) << 2) + 4;
if (buflen < 0)
goto out_resource;
WRITE32(fhp->fh_handle.fh_size);
WRITEMEM(&fhp->fh_handle.fh_base, fhp->fh_handle.fh_size);
}
if (bmval0 & FATTR4_WORD0_FILEID) {
if ((buflen -= 8) < 0)
goto out_resource;
WRITE64(stat.ino);
}
if (bmval0 & FATTR4_WORD0_FILES_AVAIL) {
if ((buflen -= 8) < 0)
goto out_resource;
WRITE64((u64) statfs.f_ffree);
}
if (bmval0 & FATTR4_WORD0_FILES_FREE) {
if ((buflen -= 8) < 0)
goto out_resource;
WRITE64((u64) statfs.f_ffree);
}
if (bmval0 & FATTR4_WORD0_FILES_TOTAL) {
if ((buflen -= 8) < 0)
goto out_resource;
WRITE64((u64) statfs.f_files);
}
if (bmval0 & FATTR4_WORD0_FS_LOCATIONS) {
status = nfsd4_encode_fs_locations(rqstp, exp, &p, &buflen);
if (status == nfserr_resource)
goto out_resource;
if (status)
goto out;
}
if (bmval0 & FATTR4_WORD0_HOMOGENEOUS) {
if ((buflen -= 4) < 0)
goto out_resource;
WRITE32(1);
}
if (bmval0 & FATTR4_WORD0_MAXFILESIZE) {
if ((buflen -= 8) < 0)
goto out_resource;
WRITE64(~(u64)0);
}
if (bmval0 & FATTR4_WORD0_MAXLINK) {
if ((buflen -= 4) < 0)
goto out_resource;
WRITE32(255);
}
if (bmval0 & FATTR4_WORD0_MAXNAME) {
if ((buflen -= 4) < 0)
goto out_resource;
WRITE32(statfs.f_namelen);
}
if (bmval0 & FATTR4_WORD0_MAXREAD) {
if ((buflen -= 8) < 0)
goto out_resource;
WRITE64((u64) svc_max_payload(rqstp));
}
if (bmval0 & FATTR4_WORD0_MAXWRITE) {
if ((buflen -= 8) < 0)
goto out_resource;
WRITE64((u64) svc_max_payload(rqstp));
}
if (bmval1 & FATTR4_WORD1_MODE) {
if ((buflen -= 4) < 0)
goto out_resource;
WRITE32(stat.mode & S_IALLUGO);
}
if (bmval1 & FATTR4_WORD1_NO_TRUNC) {
if ((buflen -= 4) < 0)
goto out_resource;
WRITE32(1);
}
if (bmval1 & FATTR4_WORD1_NUMLINKS) {
if ((buflen -= 4) < 0)
goto out_resource;
WRITE32(stat.nlink);
}
if (bmval1 & FATTR4_WORD1_OWNER) {
status = nfsd4_encode_user(rqstp, stat.uid, &p, &buflen);
if (status == nfserr_resource)
goto out_resource;
if (status)
goto out;
}
if (bmval1 & FATTR4_WORD1_OWNER_GROUP) {
status = nfsd4_encode_group(rqstp, stat.gid, &p, &buflen);
if (status == nfserr_resource)
goto out_resource;
if (status)
goto out;
}
if (bmval1 & FATTR4_WORD1_RAWDEV) {
if ((buflen -= 8) < 0)
goto out_resource;
WRITE32((u32) MAJOR(stat.rdev));
WRITE32((u32) MINOR(stat.rdev));
}
if (bmval1 & FATTR4_WORD1_SPACE_AVAIL) {
if ((buflen -= 8) < 0)
goto out_resource;
dummy64 = (u64)statfs.f_bavail * (u64)statfs.f_bsize;
WRITE64(dummy64);
}
if (bmval1 & FATTR4_WORD1_SPACE_FREE) {
if ((buflen -= 8) < 0)
goto out_resource;
dummy64 = (u64)statfs.f_bfree * (u64)statfs.f_bsize;
WRITE64(dummy64);
}
if (bmval1 & FATTR4_WORD1_SPACE_TOTAL) {
if ((buflen -= 8) < 0)
goto out_resource;
dummy64 = (u64)statfs.f_blocks * (u64)statfs.f_bsize;
WRITE64(dummy64);
}
if (bmval1 & FATTR4_WORD1_SPACE_USED) {
if ((buflen -= 8) < 0)
goto out_resource;
dummy64 = (u64)stat.blocks << 9;
WRITE64(dummy64);
}
if (bmval1 & FATTR4_WORD1_TIME_ACCESS) {
if ((buflen -= 12) < 0)
goto out_resource;
WRITE32(0);
WRITE32(stat.atime.tv_sec);
WRITE32(stat.atime.tv_nsec);
}
if (bmval1 & FATTR4_WORD1_TIME_DELTA) {
if ((buflen -= 12) < 0)
goto out_resource;
WRITE32(0);
WRITE32(1);
WRITE32(0);
}
if (bmval1 & FATTR4_WORD1_TIME_METADATA) {
if ((buflen -= 12) < 0)
goto out_resource;
WRITE32(0);
WRITE32(stat.ctime.tv_sec);
WRITE32(stat.ctime.tv_nsec);
}
if (bmval1 & FATTR4_WORD1_TIME_MODIFY) {
if ((buflen -= 12) < 0)
goto out_resource;
WRITE32(0);
WRITE32(stat.mtime.tv_sec);
WRITE32(stat.mtime.tv_nsec);
}
if (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID) {
if ((buflen -= 8) < 0)
goto out_resource;
/*
* Get parent's attributes if not ignoring crossmount
* and this is the root of a cross-mounted filesystem.
*/
if (ignore_crossmnt == 0 &&
exp->ex_mnt->mnt_root->d_inode == dentry->d_inode) {
err = vfs_getattr(exp->ex_mnt->mnt_parent,
exp->ex_mnt->mnt_mountpoint, &stat);
if (err)
goto out_nfserr;
}
WRITE64(stat.ino);
}
*attrlenp = htonl((char *)p - (char *)attrlenp - 4);
*countp = p - buffer;
status = nfs_ok;
out:
kfree(acl);
if (fhp == &tempfh)
fh_put(&tempfh);
return status;
out_nfserr:
status = nfserrno(err);
goto out;
out_resource:
*countp = 0;
status = nfserr_resource;
goto out;
out_serverfault:
status = nfserr_serverfault;
goto out;
}
static __be32
nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd,
const char *name, int namlen, __be32 *p, int *buflen)
{
struct svc_export *exp = cd->rd_fhp->fh_export;
struct dentry *dentry;
__be32 nfserr;
int ignore_crossmnt = 0;
dentry = lookup_one_len(name, cd->rd_fhp->fh_dentry, namlen);
if (IS_ERR(dentry))
return nfserrno(PTR_ERR(dentry));
exp_get(exp);
/*
* In the case of a mountpoint, the client may be asking for
* attributes that are only properties of the underlying filesystem
* as opposed to the cross-mounted file system. In such a case,
* we will not follow the cross mount and will fill the attribtutes
* directly from the mountpoint dentry.
*/
if (d_mountpoint(dentry) &&
(cd->rd_bmval[0] & ~FATTR4_WORD0_RDATTR_ERROR) == 0 &&
(cd->rd_bmval[1] & ~FATTR4_WORD1_MOUNTED_ON_FILEID) == 0)
ignore_crossmnt = 1;
else if (d_mountpoint(dentry)) {
int err;
/*
* Why the heck aren't we just using nfsd_lookup??
* Different "."/".." handling? Something else?
* At least, add a comment here to explain....
*/
err = nfsd_cross_mnt(cd->rd_rqstp, &dentry, &exp);
if (err) {
nfserr = nfserrno(err);
goto out_put;
}
nfserr = check_nfsd_access(exp, cd->rd_rqstp);
if (nfserr)
goto out_put;
}
nfserr = nfsd4_encode_fattr(NULL, exp, dentry, p, buflen, cd->rd_bmval,
cd->rd_rqstp, ignore_crossmnt);
out_put:
dput(dentry);
exp_put(exp);
return nfserr;
}
static __be32 *
nfsd4_encode_rdattr_error(__be32 *p, int buflen, __be32 nfserr)
{
__be32 *attrlenp;
if (buflen < 6)
return NULL;
*p++ = htonl(2);
*p++ = htonl(FATTR4_WORD0_RDATTR_ERROR); /* bmval0 */
*p++ = htonl(0); /* bmval1 */
attrlenp = p++;
*p++ = nfserr; /* no htonl */
*attrlenp = htonl((char *)p - (char *)attrlenp - 4);
return p;
}
static int
nfsd4_encode_dirent(void *ccdv, const char *name, int namlen,
loff_t offset, u64 ino, unsigned int d_type)
{
struct readdir_cd *ccd = ccdv;
struct nfsd4_readdir *cd = container_of(ccd, struct nfsd4_readdir, common);
int buflen;
__be32 *p = cd->buffer;
__be32 nfserr = nfserr_toosmall;
/* In nfsv4, "." and ".." never make it onto the wire.. */
if (name && isdotent(name, namlen)) {
cd->common.err = nfs_ok;
return 0;
}
if (cd->offset)
xdr_encode_hyper(cd->offset, (u64) offset);
buflen = cd->buflen - 4 - XDR_QUADLEN(namlen);
if (buflen < 0)
goto fail;
*p++ = xdr_one; /* mark entry present */
cd->offset = p; /* remember pointer */
p = xdr_encode_hyper(p, NFS_OFFSET_MAX); /* offset of next entry */
p = xdr_encode_array(p, name, namlen); /* name length & name */
nfserr = nfsd4_encode_dirent_fattr(cd, name, namlen, p, &buflen);
switch (nfserr) {
case nfs_ok:
p += buflen;
break;
case nfserr_resource:
nfserr = nfserr_toosmall;
goto fail;
case nfserr_dropit:
goto fail;
default:
/*
* If the client requested the RDATTR_ERROR attribute,
* we stuff the error code into this attribute
* and continue. If this attribute was not requested,
* then in accordance with the spec, we fail the
* entire READDIR operation(!)
*/
if (!(cd->rd_bmval[0] & FATTR4_WORD0_RDATTR_ERROR))
goto fail;
p = nfsd4_encode_rdattr_error(p, buflen, nfserr);
if (p == NULL) {
nfserr = nfserr_toosmall;
goto fail;
}
}
cd->buflen -= (p - cd->buffer);
cd->buffer = p;
cd->common.err = nfs_ok;
return 0;
fail:
cd->common.err = nfserr;
return -EINVAL;
}
static void
nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_access *access)
{
ENCODE_HEAD;
if (!nfserr) {
RESERVE_SPACE(8);
WRITE32(access->ac_supported);
WRITE32(access->ac_resp_access);
ADJUST_ARGS();
}
}
static void
nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_close *close)
{
ENCODE_SEQID_OP_HEAD;
if (!nfserr) {
RESERVE_SPACE(sizeof(stateid_t));
WRITE32(close->cl_stateid.si_generation);
WRITEMEM(&close->cl_stateid.si_opaque, sizeof(stateid_opaque_t));
ADJUST_ARGS();
}
ENCODE_SEQID_OP_TAIL(close->cl_stateowner);
}
static void
nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_commit *commit)
{
ENCODE_HEAD;
if (!nfserr) {
RESERVE_SPACE(8);
WRITEMEM(commit->co_verf.data, 8);
ADJUST_ARGS();
}
}
static void
nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_create *create)
{
ENCODE_HEAD;
if (!nfserr) {
RESERVE_SPACE(32);
WRITECINFO(create->cr_cinfo);
WRITE32(2);
WRITE32(create->cr_bmval[0]);
WRITE32(create->cr_bmval[1]);
ADJUST_ARGS();
}
}
static __be32
nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_getattr *getattr)
{
struct svc_fh *fhp = getattr->ga_fhp;
int buflen;
if (nfserr)
return nfserr;
buflen = resp->end - resp->p - (COMPOUND_ERR_SLACK_SPACE >> 2);
nfserr = nfsd4_encode_fattr(fhp, fhp->fh_export, fhp->fh_dentry,
resp->p, &buflen, getattr->ga_bmval,
resp->rqstp, 0);
if (!nfserr)
resp->p += buflen;
return nfserr;
}
static void
nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh *fhp)
{
unsigned int len;
ENCODE_HEAD;
if (!nfserr) {
len = fhp->fh_handle.fh_size;
RESERVE_SPACE(len + 4);
WRITE32(len);
WRITEMEM(&fhp->fh_handle.fh_base, len);
ADJUST_ARGS();
}
}
/*
* Including all fields other than the name, a LOCK4denied structure requires
* 8(clientid) + 4(namelen) + 8(offset) + 8(length) + 4(type) = 32 bytes.
*/
static void
nfsd4_encode_lock_denied(struct nfsd4_compoundres *resp, struct nfsd4_lock_denied *ld)
{
ENCODE_HEAD;
RESERVE_SPACE(32 + XDR_LEN(ld->ld_sop ? ld->ld_sop->so_owner.len : 0));
WRITE64(ld->ld_start);
WRITE64(ld->ld_length);
WRITE32(ld->ld_type);
if (ld->ld_sop) {
WRITEMEM(&ld->ld_clientid, 8);
WRITE32(ld->ld_sop->so_owner.len);
WRITEMEM(ld->ld_sop->so_owner.data, ld->ld_sop->so_owner.len);
kref_put(&ld->ld_sop->so_ref, nfs4_free_stateowner);
} else { /* non - nfsv4 lock in conflict, no clientid nor owner */
WRITE64((u64)0); /* clientid */
WRITE32(0); /* length of owner name */
}
ADJUST_ARGS();
}
static void
nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lock *lock)
{
ENCODE_SEQID_OP_HEAD;
if (!nfserr) {
RESERVE_SPACE(4 + sizeof(stateid_t));
WRITE32(lock->lk_resp_stateid.si_generation);
WRITEMEM(&lock->lk_resp_stateid.si_opaque, sizeof(stateid_opaque_t));
ADJUST_ARGS();
} else if (nfserr == nfserr_denied)
nfsd4_encode_lock_denied(resp, &lock->lk_denied);
ENCODE_SEQID_OP_TAIL(lock->lk_replay_owner);
}
static void
nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lockt *lockt)
{
if (nfserr == nfserr_denied)
nfsd4_encode_lock_denied(resp, &lockt->lt_denied);
}
static void
nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_locku *locku)
{
ENCODE_SEQID_OP_HEAD;
if (!nfserr) {
RESERVE_SPACE(sizeof(stateid_t));
WRITE32(locku->lu_stateid.si_generation);
WRITEMEM(&locku->lu_stateid.si_opaque, sizeof(stateid_opaque_t));
ADJUST_ARGS();
}
ENCODE_SEQID_OP_TAIL(locku->lu_stateowner);
}
static void
nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_link *link)
{
ENCODE_HEAD;
if (!nfserr) {
RESERVE_SPACE(20);
WRITECINFO(link->li_cinfo);
ADJUST_ARGS();
}
}
static void
nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open *open)
{
ENCODE_SEQID_OP_HEAD;
if (nfserr)
goto out;
RESERVE_SPACE(36 + sizeof(stateid_t));
WRITE32(open->op_stateid.si_generation);
WRITEMEM(&open->op_stateid.si_opaque, sizeof(stateid_opaque_t));
WRITECINFO(open->op_cinfo);
WRITE32(open->op_rflags);
WRITE32(2);
WRITE32(open->op_bmval[0]);
WRITE32(open->op_bmval[1]);
WRITE32(open->op_delegate_type);
ADJUST_ARGS();
switch (open->op_delegate_type) {
case NFS4_OPEN_DELEGATE_NONE:
break;
case NFS4_OPEN_DELEGATE_READ:
RESERVE_SPACE(20 + sizeof(stateid_t));
WRITEMEM(&open->op_delegate_stateid, sizeof(stateid_t));
WRITE32(open->op_recall);
/*
* TODO: ACE's in delegations
*/
WRITE32(NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE);
WRITE32(0);
WRITE32(0);
WRITE32(0); /* XXX: is NULL principal ok? */
ADJUST_ARGS();
break;
case NFS4_OPEN_DELEGATE_WRITE:
RESERVE_SPACE(32 + sizeof(stateid_t));
WRITEMEM(&open->op_delegate_stateid, sizeof(stateid_t));
WRITE32(0);
/*
* TODO: space_limit's in delegations
*/
WRITE32(NFS4_LIMIT_SIZE);
WRITE32(~(u32)0);
WRITE32(~(u32)0);
/*
* TODO: ACE's in delegations
*/
WRITE32(NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE);
WRITE32(0);
WRITE32(0);
WRITE32(0); /* XXX: is NULL principal ok? */
ADJUST_ARGS();
break;
default:
BUG();
}
/* XXX save filehandle here */
out:
ENCODE_SEQID_OP_TAIL(open->op_stateowner);
}
static void
nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_confirm *oc)
{
ENCODE_SEQID_OP_HEAD;
if (!nfserr) {
RESERVE_SPACE(sizeof(stateid_t));
WRITE32(oc->oc_resp_stateid.si_generation);
WRITEMEM(&oc->oc_resp_stateid.si_opaque, sizeof(stateid_opaque_t));
ADJUST_ARGS();
}
ENCODE_SEQID_OP_TAIL(oc->oc_stateowner);
}
static void
nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_downgrade *od)
{
ENCODE_SEQID_OP_HEAD;
if (!nfserr) {
RESERVE_SPACE(sizeof(stateid_t));
WRITE32(od->od_stateid.si_generation);
WRITEMEM(&od->od_stateid.si_opaque, sizeof(stateid_opaque_t));
ADJUST_ARGS();
}
ENCODE_SEQID_OP_TAIL(od->od_stateowner);
}
static __be32
nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_read *read)
{
u32 eof;
int v, pn;
unsigned long maxcount;
long len;
ENCODE_HEAD;
if (nfserr)
return nfserr;
if (resp->xbuf->page_len)
return nfserr_resource;
RESERVE_SPACE(8); /* eof flag and byte count */
maxcount = svc_max_payload(resp->rqstp);
if (maxcount > read->rd_length)
maxcount = read->rd_length;
len = maxcount;
v = 0;
while (len > 0) {
pn = resp->rqstp->rq_resused++;
resp->rqstp->rq_vec[v].iov_base =
page_address(resp->rqstp->rq_respages[pn]);
resp->rqstp->rq_vec[v].iov_len =
len < PAGE_SIZE ? len : PAGE_SIZE;
v++;
len -= PAGE_SIZE;
}
read->rd_vlen = v;
nfserr = nfsd_read(read->rd_rqstp, read->rd_fhp, read->rd_filp,
read->rd_offset, resp->rqstp->rq_vec, read->rd_vlen,
&maxcount);
if (nfserr == nfserr_symlink)
nfserr = nfserr_inval;
if (nfserr)
return nfserr;
eof = (read->rd_offset + maxcount >=
read->rd_fhp->fh_dentry->d_inode->i_size);
WRITE32(eof);
WRITE32(maxcount);
ADJUST_ARGS();
resp->xbuf->head[0].iov_len = (char*)p
- (char*)resp->xbuf->head[0].iov_base;
resp->xbuf->page_len = maxcount;
/* Use rest of head for padding and remaining ops: */
resp->xbuf->tail[0].iov_base = p;
resp->xbuf->tail[0].iov_len = 0;
if (maxcount&3) {
RESERVE_SPACE(4);
WRITE32(0);
resp->xbuf->tail[0].iov_base += maxcount&3;
resp->xbuf->tail[0].iov_len = 4 - (maxcount&3);
ADJUST_ARGS();
}
return 0;
}
static __be32
nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readlink *readlink)
{
int maxcount;
char *page;
ENCODE_HEAD;
if (nfserr)
return nfserr;
if (resp->xbuf->page_len)
return nfserr_resource;
page = page_address(resp->rqstp->rq_respages[resp->rqstp->rq_resused++]);
maxcount = PAGE_SIZE;
RESERVE_SPACE(4);
/*
* XXX: By default, the ->readlink() VFS op will truncate symlinks
* if they would overflow the buffer. Is this kosher in NFSv4? If
* not, one easy fix is: if ->readlink() precisely fills the buffer,
* assume that truncation occurred, and return NFS4ERR_RESOURCE.
*/
nfserr = nfsd_readlink(readlink->rl_rqstp, readlink->rl_fhp, page, &maxcount);
if (nfserr == nfserr_isdir)
return nfserr_inval;
if (nfserr)
return nfserr;
WRITE32(maxcount);
ADJUST_ARGS();
resp->xbuf->head[0].iov_len = (char*)p
- (char*)resp->xbuf->head[0].iov_base;
resp->xbuf->page_len = maxcount;
/* Use rest of head for padding and remaining ops: */
resp->xbuf->tail[0].iov_base = p;
resp->xbuf->tail[0].iov_len = 0;
if (maxcount&3) {
RESERVE_SPACE(4);
WRITE32(0);
resp->xbuf->tail[0].iov_base += maxcount&3;
resp->xbuf->tail[0].iov_len = 4 - (maxcount&3);
ADJUST_ARGS();
}
return 0;
}
static __be32
nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readdir *readdir)
{
int maxcount;
loff_t offset;
__be32 *page, *savep, *tailbase;
ENCODE_HEAD;
if (nfserr)
return nfserr;
if (resp->xbuf->page_len)
return nfserr_resource;
RESERVE_SPACE(8); /* verifier */
savep = p;
/* XXX: Following NFSv3, we ignore the READDIR verifier for now. */
WRITE32(0);
WRITE32(0);
ADJUST_ARGS();
resp->xbuf->head[0].iov_len = ((char*)resp->p) - (char*)resp->xbuf->head[0].iov_base;
tailbase = p;
maxcount = PAGE_SIZE;
if (maxcount > readdir->rd_maxcount)
maxcount = readdir->rd_maxcount;
/*
* Convert from bytes to words, account for the two words already
* written, make sure to leave two words at the end for the next
* pointer and eof field.
*/
maxcount = (maxcount >> 2) - 4;
if (maxcount < 0) {
nfserr = nfserr_toosmall;
goto err_no_verf;
}
page = page_address(resp->rqstp->rq_respages[resp->rqstp->rq_resused++]);
readdir->common.err = 0;
readdir->buflen = maxcount;
readdir->buffer = page;
readdir->offset = NULL;
offset = readdir->rd_cookie;
nfserr = nfsd_readdir(readdir->rd_rqstp, readdir->rd_fhp,
&offset,
&readdir->common, nfsd4_encode_dirent);
if (nfserr == nfs_ok &&
readdir->common.err == nfserr_toosmall &&
readdir->buffer == page)
nfserr = nfserr_toosmall;
if (nfserr == nfserr_symlink)
nfserr = nfserr_notdir;
if (nfserr)
goto err_no_verf;
if (readdir->offset)
xdr_encode_hyper(readdir->offset, offset);
p = readdir->buffer;
*p++ = 0; /* no more entries */
*p++ = htonl(readdir->common.err == nfserr_eof);
resp->xbuf->page_len = ((char*)p) - (char*)page_address(
resp->rqstp->rq_respages[resp->rqstp->rq_resused-1]);
/* Use rest of head for padding and remaining ops: */
resp->xbuf->tail[0].iov_base = tailbase;
resp->xbuf->tail[0].iov_len = 0;
resp->p = resp->xbuf->tail[0].iov_base;
resp->end = resp->p + (PAGE_SIZE - resp->xbuf->head[0].iov_len)/4;
return 0;
err_no_verf:
p = savep;
ADJUST_ARGS();
return nfserr;
}
static void
nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_remove *remove)
{
ENCODE_HEAD;
if (!nfserr) {
RESERVE_SPACE(20);
WRITECINFO(remove->rm_cinfo);
ADJUST_ARGS();
}
}
static void
nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_rename *rename)
{
ENCODE_HEAD;
if (!nfserr) {
RESERVE_SPACE(40);
WRITECINFO(rename->rn_sinfo);
WRITECINFO(rename->rn_tinfo);
ADJUST_ARGS();
}
}
static void
nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_secinfo *secinfo)
{
int i = 0;
struct svc_export *exp = secinfo->si_exp;
u32 nflavs;
struct exp_flavor_info *flavs;
struct exp_flavor_info def_flavs[2];
ENCODE_HEAD;
if (nfserr)
goto out;
if (exp->ex_nflavors) {
flavs = exp->ex_flavors;
nflavs = exp->ex_nflavors;
} else { /* Handling of some defaults in absence of real secinfo: */
flavs = def_flavs;
if (exp->ex_client->flavour->flavour == RPC_AUTH_UNIX) {
nflavs = 2;
flavs[0].pseudoflavor = RPC_AUTH_UNIX;
flavs[1].pseudoflavor = RPC_AUTH_NULL;
} else if (exp->ex_client->flavour->flavour == RPC_AUTH_GSS) {
nflavs = 1;
flavs[0].pseudoflavor
= svcauth_gss_flavor(exp->ex_client);
} else {
nflavs = 1;
flavs[0].pseudoflavor
= exp->ex_client->flavour->flavour;
}
}
RESERVE_SPACE(4);
WRITE32(nflavs);
ADJUST_ARGS();
for (i = 0; i < nflavs; i++) {
u32 flav = flavs[i].pseudoflavor;
struct gss_api_mech *gm = gss_mech_get_by_pseudoflavor(flav);
if (gm) {
RESERVE_SPACE(4);
WRITE32(RPC_AUTH_GSS);
ADJUST_ARGS();
RESERVE_SPACE(4 + gm->gm_oid.len);
WRITE32(gm->gm_oid.len);
WRITEMEM(gm->gm_oid.data, gm->gm_oid.len);
ADJUST_ARGS();
RESERVE_SPACE(4);
WRITE32(0); /* qop */
ADJUST_ARGS();
RESERVE_SPACE(4);
WRITE32(gss_pseudoflavor_to_service(gm, flav));
ADJUST_ARGS();
gss_mech_put(gm);
} else {
RESERVE_SPACE(4);
WRITE32(flav);
ADJUST_ARGS();
}
}
out:
if (exp)
exp_put(exp);
}
/*
* The SETATTR encode routine is special -- it always encodes a bitmap,
* regardless of the error status.
*/
static void
nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setattr *setattr)
{
ENCODE_HEAD;
RESERVE_SPACE(12);
if (nfserr) {
WRITE32(2);
WRITE32(0);
WRITE32(0);
}
else {
WRITE32(2);
WRITE32(setattr->sa_bmval[0]);
WRITE32(setattr->sa_bmval[1]);
}
ADJUST_ARGS();
}
static void
nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setclientid *scd)
{
ENCODE_HEAD;
if (!nfserr) {
RESERVE_SPACE(8 + sizeof(nfs4_verifier));
WRITEMEM(&scd->se_clientid, 8);
WRITEMEM(&scd->se_confirm, sizeof(nfs4_verifier));
ADJUST_ARGS();
}
else if (nfserr == nfserr_clid_inuse) {
RESERVE_SPACE(8);
WRITE32(0);
WRITE32(0);
ADJUST_ARGS();
}
}
static void
nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_write *write)
{
ENCODE_HEAD;
if (!nfserr) {
RESERVE_SPACE(16);
WRITE32(write->wr_bytes_written);
WRITE32(write->wr_how_written);
WRITEMEM(write->wr_verifier.data, 8);
ADJUST_ARGS();
}
}
void
nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op)
{
__be32 *statp;
ENCODE_HEAD;
RESERVE_SPACE(8);
WRITE32(op->opnum);
statp = p++; /* to be backfilled at the end */
ADJUST_ARGS();
switch (op->opnum) {
case OP_ACCESS:
nfsd4_encode_access(resp, op->status, &op->u.access);
break;
case OP_CLOSE:
nfsd4_encode_close(resp, op->status, &op->u.close);
break;
case OP_COMMIT:
nfsd4_encode_commit(resp, op->status, &op->u.commit);
break;
case OP_CREATE:
nfsd4_encode_create(resp, op->status, &op->u.create);
break;
case OP_DELEGRETURN:
break;
case OP_GETATTR:
op->status = nfsd4_encode_getattr(resp, op->status, &op->u.getattr);
break;
case OP_GETFH:
nfsd4_encode_getfh(resp, op->status, op->u.getfh);
break;
case OP_LINK:
nfsd4_encode_link(resp, op->status, &op->u.link);
break;
case OP_LOCK:
nfsd4_encode_lock(resp, op->status, &op->u.lock);
break;
case OP_LOCKT:
nfsd4_encode_lockt(resp, op->status, &op->u.lockt);
break;
case OP_LOCKU:
nfsd4_encode_locku(resp, op->status, &op->u.locku);
break;
case OP_LOOKUP:
break;
case OP_LOOKUPP:
break;
case OP_NVERIFY:
break;
case OP_OPEN:
nfsd4_encode_open(resp, op->status, &op->u.open);
break;
case OP_OPEN_CONFIRM:
nfsd4_encode_open_confirm(resp, op->status, &op->u.open_confirm);
break;
case OP_OPEN_DOWNGRADE:
nfsd4_encode_open_downgrade(resp, op->status, &op->u.open_downgrade);
break;
case OP_PUTFH:
break;
case OP_PUTROOTFH:
break;
case OP_READ:
op->status = nfsd4_encode_read(resp, op->status, &op->u.read);
break;
case OP_READDIR:
op->status = nfsd4_encode_readdir(resp, op->status, &op->u.readdir);
break;
case OP_READLINK:
op->status = nfsd4_encode_readlink(resp, op->status, &op->u.readlink);
break;
case OP_REMOVE:
nfsd4_encode_remove(resp, op->status, &op->u.remove);
break;
case OP_RENAME:
nfsd4_encode_rename(resp, op->status, &op->u.rename);
break;
case OP_RENEW:
break;
case OP_RESTOREFH:
break;
case OP_SAVEFH:
break;
case OP_SECINFO:
nfsd4_encode_secinfo(resp, op->status, &op->u.secinfo);
break;
case OP_SETATTR:
nfsd4_encode_setattr(resp, op->status, &op->u.setattr);
break;
case OP_SETCLIENTID:
nfsd4_encode_setclientid(resp, op->status, &op->u.setclientid);
break;
case OP_SETCLIENTID_CONFIRM:
break;
case OP_VERIFY:
break;
case OP_WRITE:
nfsd4_encode_write(resp, op->status, &op->u.write);
break;
case OP_RELEASE_LOCKOWNER:
break;
default:
break;
}
/*
* Note: We write the status directly, instead of using WRITE32(),
* since it is already in network byte order.
*/
*statp = op->status;
}
/*
* Encode the reply stored in the stateowner reply cache
*
* XDR note: do not encode rp->rp_buflen: the buffer contains the
* previously sent already encoded operation.
*
* called with nfs4_lock_state() held
*/
void
nfsd4_encode_replay(struct nfsd4_compoundres *resp, struct nfsd4_op *op)
{
ENCODE_HEAD;
struct nfs4_replay *rp = op->replay;
BUG_ON(!rp);
RESERVE_SPACE(8);
WRITE32(op->opnum);
*p++ = rp->rp_status; /* already xdr'ed */
ADJUST_ARGS();
RESERVE_SPACE(rp->rp_buflen);
WRITEMEM(rp->rp_buf, rp->rp_buflen);
ADJUST_ARGS();
}
/*
* END OF "GENERIC" ENCODE ROUTINES.
*/
int
nfs4svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy)
{
return xdr_ressize_check(rqstp, p);
}
void nfsd4_release_compoundargs(struct nfsd4_compoundargs *args)
{
if (args->ops != args->iops) {
kfree(args->ops);
args->ops = args->iops;
}
kfree(args->tmpp);
args->tmpp = NULL;
while (args->to_free) {
struct tmpbuf *tb = args->to_free;
args->to_free = tb->next;
tb->release(tb->buf);
kfree(tb);
}
}
int
nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compoundargs *args)
{
__be32 status;
args->p = p;
args->end = rqstp->rq_arg.head[0].iov_base + rqstp->rq_arg.head[0].iov_len;
args->pagelist = rqstp->rq_arg.pages;
args->pagelen = rqstp->rq_arg.page_len;
args->tmpp = NULL;
args->to_free = NULL;
args->ops = args->iops;
args->rqstp = rqstp;
status = nfsd4_decode_compound(args);
if (status) {
nfsd4_release_compoundargs(args);
}
return !status;
}
int
nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compoundres *resp)
{
/*
* All that remains is to write the tag and operation count...
*/
struct kvec *iov;
p = resp->tagp;
*p++ = htonl(resp->taglen);
memcpy(p, resp->tag, resp->taglen);
p += XDR_QUADLEN(resp->taglen);
*p++ = htonl(resp->opcnt);
if (rqstp->rq_res.page_len)
iov = &rqstp->rq_res.tail[0];
else
iov = &rqstp->rq_res.head[0];
iov->iov_len = ((char*)resp->p) - (char*)iov->iov_base;
BUG_ON(iov->iov_len > PAGE_SIZE);
return 1;
}
/*
* Local variables:
* c-basic-offset: 8
* End:
*/