nfs4xdr.c

linux 内核源代码

/*
 *  fs/nfs/nfs4xdr.c
 *
 *  Server-side XDR for NFSv4
 *
 *  Copyright (c) 2002 The Regents of the University of Michigan.
 *  All rights reserved.
 *
 *  Kendrick Smith <[e-mail]>
 *  Andy Adamson   <[e-mail]>
 *
 *  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, int nbytes)
{
	/* We want more bytes than seem to be available.
	 * Maybe we need a new page, maybe we have just run out
	 */
	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;
		
	}
	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)