WSL2-Linux-Kernel/fs/nfsd/nfs3xdr.c

1449 строки
33 KiB
C
Исходник Обычный вид История

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 17:07:57 +03:00
// SPDX-License-Identifier: GPL-2.0
/*
* XDR support for nfsd/protocol version 3.
*
* Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de>
*
* 2003-08-09 Jamie Lokier: Use htonl() for nanoseconds, not htons()!
*/
#include <linux/namei.h>
#include <linux/sunrpc/svc_xprt.h>
#include "xdr3.h"
#include "auth.h"
#include "netns.h"
#include "vfs.h"
/*
* Force construction of an empty post-op attr
*/
static const struct svc_fh nfs3svc_null_fh = {
.fh_no_wcc = true,
};
/*
* time_delta. {1, 0} means the server is accurate only
* to the nearest second.
*/
static const struct timespec64 nfs3svc_time_delta = {
.tv_sec = 1,
.tv_nsec = 0,
};
/*
* Mapping of S_IF* types to NFS file types
*/
static const u32 nfs3_ftypes[] = {
NF3NON, NF3FIFO, NF3CHR, NF3BAD,
NF3DIR, NF3BAD, NF3BLK, NF3BAD,
NF3REG, NF3BAD, NF3LNK, NF3BAD,
NF3SOCK, NF3BAD, NF3LNK, NF3BAD,
};
/*
* Basic NFSv3 data types (RFC 1813 Sections 2.5 and 2.6)
*/
static __be32 *
encode_nfstime3(__be32 *p, const struct timespec64 *time)
{
*p++ = cpu_to_be32((u32)time->tv_sec);
*p++ = cpu_to_be32(time->tv_nsec);
return p;
}
static bool
svcxdr_decode_nfstime3(struct xdr_stream *xdr, struct timespec64 *timep)
{
__be32 *p;
p = xdr_inline_decode(xdr, XDR_UNIT * 2);
if (!p)
return false;
timep->tv_sec = be32_to_cpup(p++);
timep->tv_nsec = be32_to_cpup(p);
return true;
}
/**
* svcxdr_decode_nfs_fh3 - Decode an NFSv3 file handle
* @xdr: XDR stream positioned at an undecoded NFSv3 FH
* @fhp: OUT: filled-in server file handle
*
* Return values:
* %false: The encoded file handle was not valid
* %true: @fhp has been initialized
*/
bool
svcxdr_decode_nfs_fh3(struct xdr_stream *xdr, struct svc_fh *fhp)
{
__be32 *p;
u32 size;
if (xdr_stream_decode_u32(xdr, &size) < 0)
return false;
if (size == 0 || size > NFS3_FHSIZE)
return false;
p = xdr_inline_decode(xdr, size);
if (!p)
return false;
fh_init(fhp, NFS3_FHSIZE);
fhp->fh_handle.fh_size = size;
memcpy(&fhp->fh_handle.fh_base, p, size);
return true;
}
/**
* svcxdr_encode_nfsstat3 - Encode an NFSv3 status code
* @xdr: XDR stream
* @status: status value to encode
*
* Return values:
* %false: Send buffer space was exhausted
* %true: Success
*/
bool
svcxdr_encode_nfsstat3(struct xdr_stream *xdr, __be32 status)
{
__be32 *p;
p = xdr_reserve_space(xdr, sizeof(status));
if (!p)
return false;
*p = status;
return true;
}
static bool
svcxdr_encode_nfs_fh3(struct xdr_stream *xdr, const struct svc_fh *fhp)
{
u32 size = fhp->fh_handle.fh_size;
__be32 *p;
p = xdr_reserve_space(xdr, XDR_UNIT + size);
if (!p)
return false;
*p++ = cpu_to_be32(size);
if (size)
p[XDR_QUADLEN(size) - 1] = 0;
memcpy(p, &fhp->fh_handle.fh_base, size);
return true;
}
static bool
svcxdr_encode_post_op_fh3(struct xdr_stream *xdr, const struct svc_fh *fhp)
{
if (xdr_stream_encode_item_present(xdr) < 0)
return false;
if (!svcxdr_encode_nfs_fh3(xdr, fhp))
return false;
return true;
}
static bool
svcxdr_encode_cookieverf3(struct xdr_stream *xdr, const __be32 *verf)
{
__be32 *p;
p = xdr_reserve_space(xdr, NFS3_COOKIEVERFSIZE);
if (!p)
return false;
memcpy(p, verf, NFS3_COOKIEVERFSIZE);
return true;
}
static bool
svcxdr_encode_writeverf3(struct xdr_stream *xdr, const __be32 *verf)
{
__be32 *p;
p = xdr_reserve_space(xdr, NFS3_WRITEVERFSIZE);
if (!p)
return false;
memcpy(p, verf, NFS3_WRITEVERFSIZE);
return true;
}
static bool
svcxdr_decode_filename3(struct xdr_stream *xdr, char **name, unsigned int *len)
{
u32 size, i;
__be32 *p;
char *c;
if (xdr_stream_decode_u32(xdr, &size) < 0)
return false;
if (size == 0 || size > NFS3_MAXNAMLEN)
return false;
p = xdr_inline_decode(xdr, size);
if (!p)
return false;
*len = size;
*name = (char *)p;
for (i = 0, c = *name; i < size; i++, c++) {
if (*c == '\0' || *c == '/')
return false;
}
return true;
}
static bool
svcxdr_decode_diropargs3(struct xdr_stream *xdr, struct svc_fh *fhp,
char **name, unsigned int *len)
{
return svcxdr_decode_nfs_fh3(xdr, fhp) &&
svcxdr_decode_filename3(xdr, name, len);
}
static bool
svcxdr_decode_sattr3(struct svc_rqst *rqstp, struct xdr_stream *xdr,
struct iattr *iap)
{
u32 set_it;
iap->ia_valid = 0;
if (xdr_stream_decode_bool(xdr, &set_it) < 0)
return false;
if (set_it) {
u32 mode;
if (xdr_stream_decode_u32(xdr, &mode) < 0)
return false;
iap->ia_valid |= ATTR_MODE;
iap->ia_mode = mode;
}
if (xdr_stream_decode_bool(xdr, &set_it) < 0)
return false;
if (set_it) {
u32 uid;
if (xdr_stream_decode_u32(xdr, &uid) < 0)
return false;
iap->ia_uid = make_kuid(nfsd_user_namespace(rqstp), uid);
if (uid_valid(iap->ia_uid))
iap->ia_valid |= ATTR_UID;
}
if (xdr_stream_decode_bool(xdr, &set_it) < 0)
return false;
if (set_it) {
u32 gid;
if (xdr_stream_decode_u32(xdr, &gid) < 0)
return false;
iap->ia_gid = make_kgid(nfsd_user_namespace(rqstp), gid);
if (gid_valid(iap->ia_gid))
iap->ia_valid |= ATTR_GID;
}
if (xdr_stream_decode_bool(xdr, &set_it) < 0)
return false;
if (set_it) {
u64 newsize;
if (xdr_stream_decode_u64(xdr, &newsize) < 0)
return false;
iap->ia_valid |= ATTR_SIZE;
iap->ia_size = newsize;
}
if (xdr_stream_decode_u32(xdr, &set_it) < 0)
return false;
switch (set_it) {
case DONT_CHANGE:
break;
case SET_TO_SERVER_TIME:
iap->ia_valid |= ATTR_ATIME;
break;
case SET_TO_CLIENT_TIME:
if (!svcxdr_decode_nfstime3(xdr, &iap->ia_atime))
return false;
iap->ia_valid |= ATTR_ATIME | ATTR_ATIME_SET;
break;
default:
return false;
}
if (xdr_stream_decode_u32(xdr, &set_it) < 0)
return false;
switch (set_it) {
case DONT_CHANGE:
break;
case SET_TO_SERVER_TIME:
iap->ia_valid |= ATTR_MTIME;
break;
case SET_TO_CLIENT_TIME:
if (!svcxdr_decode_nfstime3(xdr, &iap->ia_mtime))
return false;
iap->ia_valid |= ATTR_MTIME | ATTR_MTIME_SET;
break;
default:
return false;
}
return true;
}
static bool
svcxdr_decode_sattrguard3(struct xdr_stream *xdr, struct nfsd3_sattrargs *args)
{
__be32 *p;
u32 check;
if (xdr_stream_decode_bool(xdr, &check) < 0)
return false;
if (check) {
p = xdr_inline_decode(xdr, XDR_UNIT * 2);
if (!p)
return false;
args->check_guard = 1;
args->guardtime = be32_to_cpup(p);
} else
args->check_guard = 0;
return true;
}
static bool
svcxdr_decode_specdata3(struct xdr_stream *xdr, struct nfsd3_mknodargs *args)
{
__be32 *p;
p = xdr_inline_decode(xdr, XDR_UNIT * 2);
if (!p)
return false;
args->major = be32_to_cpup(p++);
args->minor = be32_to_cpup(p);
return true;
}
static bool
svcxdr_decode_devicedata3(struct svc_rqst *rqstp, struct xdr_stream *xdr,
struct nfsd3_mknodargs *args)
{
return svcxdr_decode_sattr3(rqstp, xdr, &args->attrs) &&
svcxdr_decode_specdata3(xdr, args);
}
static bool
svcxdr_encode_fattr3(struct svc_rqst *rqstp, struct xdr_stream *xdr,
const struct svc_fh *fhp, const struct kstat *stat)
{
struct user_namespace *userns = nfsd_user_namespace(rqstp);
__be32 *p;
u64 fsid;
p = xdr_reserve_space(xdr, XDR_UNIT * 21);
if (!p)
return false;
*p++ = cpu_to_be32(nfs3_ftypes[(stat->mode & S_IFMT) >> 12]);
*p++ = cpu_to_be32((u32)(stat->mode & S_IALLUGO));
*p++ = cpu_to_be32((u32)stat->nlink);
*p++ = cpu_to_be32((u32)from_kuid_munged(userns, stat->uid));
*p++ = cpu_to_be32((u32)from_kgid_munged(userns, stat->gid));
if (S_ISLNK(stat->mode) && stat->size > NFS3_MAXPATHLEN)
p = xdr_encode_hyper(p, (u64)NFS3_MAXPATHLEN);
else
p = xdr_encode_hyper(p, (u64)stat->size);
/* used */
p = xdr_encode_hyper(p, ((u64)stat->blocks) << 9);
/* rdev */
*p++ = cpu_to_be32((u32)MAJOR(stat->rdev));
*p++ = cpu_to_be32((u32)MINOR(stat->rdev));
switch(fsid_source(fhp)) {
case FSIDSOURCE_FSID:
fsid = (u64)fhp->fh_export->ex_fsid;
break;
case FSIDSOURCE_UUID:
fsid = ((u64 *)fhp->fh_export->ex_uuid)[0];
fsid ^= ((u64 *)fhp->fh_export->ex_uuid)[1];
break;
default:
fsid = (u64)huge_encode_dev(fhp->fh_dentry->d_sb->s_dev);
}
p = xdr_encode_hyper(p, fsid);
/* fileid */
p = xdr_encode_hyper(p, stat->ino);
p = encode_nfstime3(p, &stat->atime);
p = encode_nfstime3(p, &stat->mtime);
encode_nfstime3(p, &stat->ctime);
return true;
}
static bool
svcxdr_encode_wcc_attr(struct xdr_stream *xdr, const struct svc_fh *fhp)
{
__be32 *p;
p = xdr_reserve_space(xdr, XDR_UNIT * 6);
if (!p)
return false;
p = xdr_encode_hyper(p, (u64)fhp->fh_pre_size);
p = encode_nfstime3(p, &fhp->fh_pre_mtime);
encode_nfstime3(p, &fhp->fh_pre_ctime);
return true;
}
static bool
svcxdr_encode_pre_op_attr(struct xdr_stream *xdr, const struct svc_fh *fhp)
{
if (!fhp->fh_pre_saved) {
if (xdr_stream_encode_item_absent(xdr) < 0)
return false;
return true;
}
if (xdr_stream_encode_item_present(xdr) < 0)
return false;
return svcxdr_encode_wcc_attr(xdr, fhp);
}
/**
* svcxdr_encode_post_op_attr - Encode NFSv3 post-op attributes
* @rqstp: Context of a completed RPC transaction
* @xdr: XDR stream
* @fhp: File handle to encode
*
* Return values:
* %false: Send buffer space was exhausted
* %true: Success
*/
bool
svcxdr_encode_post_op_attr(struct svc_rqst *rqstp, struct xdr_stream *xdr,
const struct svc_fh *fhp)
{
struct dentry *dentry = fhp->fh_dentry;
struct kstat stat;
/*
* The inode may be NULL if the call failed because of a
* stale file handle. In this case, no attributes are
* returned.
*/
if (fhp->fh_no_wcc || !dentry || !d_really_is_positive(dentry))
goto no_post_op_attrs;
if (fh_getattr(fhp, &stat) != nfs_ok)
goto no_post_op_attrs;
if (xdr_stream_encode_item_present(xdr) < 0)
return false;
lease_get_mtime(d_inode(dentry), &stat.mtime);
if (!svcxdr_encode_fattr3(rqstp, xdr, fhp, &stat))
return false;
return true;
no_post_op_attrs:
return xdr_stream_encode_item_absent(xdr) > 0;
}
/*
* Encode weak cache consistency data
*/
static bool
svcxdr_encode_wcc_data(struct svc_rqst *rqstp, struct xdr_stream *xdr,
const struct svc_fh *fhp)
{
struct dentry *dentry = fhp->fh_dentry;
if (!dentry || !d_really_is_positive(dentry) || !fhp->fh_post_saved)
goto neither;
/* before */
if (!svcxdr_encode_pre_op_attr(xdr, fhp))
return false;
/* after */
if (xdr_stream_encode_item_present(xdr) < 0)
return false;
if (!svcxdr_encode_fattr3(rqstp, xdr, fhp, &fhp->fh_post_attr))
return false;
return true;
neither:
if (xdr_stream_encode_item_absent(xdr) < 0)
return false;
if (!svcxdr_encode_post_op_attr(rqstp, xdr, fhp))
return false;
return true;
}
/*
* Fill in the pre_op attr for the wcc data
*/
void fill_pre_wcc(struct svc_fh *fhp)
{
struct inode *inode;
struct kstat stat;
bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE);
Revert "nfsd: skip some unnecessary stats in the v4 case" [ Upstream commit 58f258f65267542959487dbe8b5641754411843d ] On the wire, I observed NFSv4 OPEN(CREATE) operations sometimes returning a reasonable-looking value in the cinfo.before field and zero in the cinfo.after field. RFC 8881 Section 10.8.1 says: > When a client is making changes to a given directory, it needs to > determine whether there have been changes made to the directory by > other clients. It does this by using the change attribute as > reported before and after the directory operation in the associated > change_info4 value returned for the operation. and > ... The post-operation change > value needs to be saved as the basis for future change_info4 > comparisons. A good quality client implementation therefore saves the zero cinfo.after value. During a subsequent OPEN operation, it will receive a different non-zero value in the cinfo.before field for that directory, and it will incorrectly believe the directory has changed, triggering an undesirable directory cache invalidation. There are filesystem types where fs_supports_change_attribute() returns false, tmpfs being one. On NFSv4 mounts, this means the fh_getattr() call site in fill_pre_wcc() and fill_post_wcc() is never invoked. Subsequently, nfsd4_change_attribute() is invoked with an uninitialized @stat argument. In fill_pre_wcc(), @stat contains stale stack garbage, which is then placed on the wire. In fill_post_wcc(), ->fh_post_wc is all zeroes, so zero is placed on the wire. Both of these values are meaningless. This fix can be applied immediately to stable kernels. Once there are more regression tests in this area, this optimization can be attempted again. Fixes: 428a23d2bf0c ("nfsd: skip some unnecessary stats in the v4 case") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2021-12-24 22:22:28 +03:00
__be32 err;
nfsd: add a new EXPORT_OP_NOWCC flag to struct export_operations With NFSv3 nfsd will always attempt to send along WCC data to the client. This generally involves saving off the in-core inode information prior to doing the operation on the given filehandle, and then issuing a vfs_getattr to it after the op. Some filesystems (particularly clustered or networked ones) have an expensive ->getattr inode operation. Atomicity is also often difficult or impossible to guarantee on such filesystems. For those, we're best off not trying to provide WCC information to the client at all, and to simply allow it to poll for that information as needed with a GETATTR RPC. This patch adds a new flags field to struct export_operations, and defines a new EXPORT_OP_NOWCC flag that filesystems can use to indicate that nfsd should not attempt to provide WCC info in NFSv3 replies. It also adds a blurb about the new flags field and flag to the exporting documentation. The server will also now skip collecting this information for NFSv2 as well, since that info is never used there anyway. Note that this patch does not add this flag to any filesystem export_operations structures. This was originally developed to allow reexporting nfs via nfsd. Other filesystems may want to consider enabling this flag too. It's hard to tell however which ones have export operations to enable export via knfsd and which ones mostly rely on them for open-by-filehandle support, so I'm leaving that up to the individual maintainers to decide. I am cc'ing the relevant lists for those filesystems that I think may want to consider adding this though. Cc: HPDD-discuss@lists.01.org Cc: ceph-devel@vger.kernel.org Cc: cluster-devel@redhat.com Cc: fuse-devel@lists.sourceforge.net Cc: ocfs2-devel@oss.oracle.com Signed-off-by: Jeff Layton <jeff.layton@primarydata.com> Signed-off-by: Lance Shelton <lance.shelton@hammerspace.com> Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
2020-12-01 01:03:14 +03:00
if (fhp->fh_no_wcc || fhp->fh_pre_saved)
return;
inode = d_inode(fhp->fh_dentry);
Revert "nfsd: skip some unnecessary stats in the v4 case" [ Upstream commit 58f258f65267542959487dbe8b5641754411843d ] On the wire, I observed NFSv4 OPEN(CREATE) operations sometimes returning a reasonable-looking value in the cinfo.before field and zero in the cinfo.after field. RFC 8881 Section 10.8.1 says: > When a client is making changes to a given directory, it needs to > determine whether there have been changes made to the directory by > other clients. It does this by using the change attribute as > reported before and after the directory operation in the associated > change_info4 value returned for the operation. and > ... The post-operation change > value needs to be saved as the basis for future change_info4 > comparisons. A good quality client implementation therefore saves the zero cinfo.after value. During a subsequent OPEN operation, it will receive a different non-zero value in the cinfo.before field for that directory, and it will incorrectly believe the directory has changed, triggering an undesirable directory cache invalidation. There are filesystem types where fs_supports_change_attribute() returns false, tmpfs being one. On NFSv4 mounts, this means the fh_getattr() call site in fill_pre_wcc() and fill_post_wcc() is never invoked. Subsequently, nfsd4_change_attribute() is invoked with an uninitialized @stat argument. In fill_pre_wcc(), @stat contains stale stack garbage, which is then placed on the wire. In fill_post_wcc(), ->fh_post_wc is all zeroes, so zero is placed on the wire. Both of these values are meaningless. This fix can be applied immediately to stable kernels. Once there are more regression tests in this area, this optimization can be attempted again. Fixes: 428a23d2bf0c ("nfsd: skip some unnecessary stats in the v4 case") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2021-12-24 22:22:28 +03:00
err = fh_getattr(fhp, &stat);
if (err) {
/* Grab the times from inode anyway */
stat.mtime = inode->i_mtime;
stat.ctime = inode->i_ctime;
stat.size = inode->i_size;
}
if (v4)
fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode);
Revert "nfsd: skip some unnecessary stats in the v4 case" [ Upstream commit 58f258f65267542959487dbe8b5641754411843d ] On the wire, I observed NFSv4 OPEN(CREATE) operations sometimes returning a reasonable-looking value in the cinfo.before field and zero in the cinfo.after field. RFC 8881 Section 10.8.1 says: > When a client is making changes to a given directory, it needs to > determine whether there have been changes made to the directory by > other clients. It does this by using the change attribute as > reported before and after the directory operation in the associated > change_info4 value returned for the operation. and > ... The post-operation change > value needs to be saved as the basis for future change_info4 > comparisons. A good quality client implementation therefore saves the zero cinfo.after value. During a subsequent OPEN operation, it will receive a different non-zero value in the cinfo.before field for that directory, and it will incorrectly believe the directory has changed, triggering an undesirable directory cache invalidation. There are filesystem types where fs_supports_change_attribute() returns false, tmpfs being one. On NFSv4 mounts, this means the fh_getattr() call site in fill_pre_wcc() and fill_post_wcc() is never invoked. Subsequently, nfsd4_change_attribute() is invoked with an uninitialized @stat argument. In fill_pre_wcc(), @stat contains stale stack garbage, which is then placed on the wire. In fill_post_wcc(), ->fh_post_wc is all zeroes, so zero is placed on the wire. Both of these values are meaningless. This fix can be applied immediately to stable kernels. Once there are more regression tests in this area, this optimization can be attempted again. Fixes: 428a23d2bf0c ("nfsd: skip some unnecessary stats in the v4 case") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2021-12-24 22:22:28 +03:00
fhp->fh_pre_mtime = stat.mtime;
fhp->fh_pre_ctime = stat.ctime;
fhp->fh_pre_size = stat.size;
fhp->fh_pre_saved = true;
}
/*
* Fill in the post_op attr for the wcc data
*/
void fill_post_wcc(struct svc_fh *fhp)
{
bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE);
struct inode *inode = d_inode(fhp->fh_dentry);
Revert "nfsd: skip some unnecessary stats in the v4 case" [ Upstream commit 58f258f65267542959487dbe8b5641754411843d ] On the wire, I observed NFSv4 OPEN(CREATE) operations sometimes returning a reasonable-looking value in the cinfo.before field and zero in the cinfo.after field. RFC 8881 Section 10.8.1 says: > When a client is making changes to a given directory, it needs to > determine whether there have been changes made to the directory by > other clients. It does this by using the change attribute as > reported before and after the directory operation in the associated > change_info4 value returned for the operation. and > ... The post-operation change > value needs to be saved as the basis for future change_info4 > comparisons. A good quality client implementation therefore saves the zero cinfo.after value. During a subsequent OPEN operation, it will receive a different non-zero value in the cinfo.before field for that directory, and it will incorrectly believe the directory has changed, triggering an undesirable directory cache invalidation. There are filesystem types where fs_supports_change_attribute() returns false, tmpfs being one. On NFSv4 mounts, this means the fh_getattr() call site in fill_pre_wcc() and fill_post_wcc() is never invoked. Subsequently, nfsd4_change_attribute() is invoked with an uninitialized @stat argument. In fill_pre_wcc(), @stat contains stale stack garbage, which is then placed on the wire. In fill_post_wcc(), ->fh_post_wc is all zeroes, so zero is placed on the wire. Both of these values are meaningless. This fix can be applied immediately to stable kernels. Once there are more regression tests in this area, this optimization can be attempted again. Fixes: 428a23d2bf0c ("nfsd: skip some unnecessary stats in the v4 case") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2021-12-24 22:22:28 +03:00
__be32 err;
nfsd: add a new EXPORT_OP_NOWCC flag to struct export_operations With NFSv3 nfsd will always attempt to send along WCC data to the client. This generally involves saving off the in-core inode information prior to doing the operation on the given filehandle, and then issuing a vfs_getattr to it after the op. Some filesystems (particularly clustered or networked ones) have an expensive ->getattr inode operation. Atomicity is also often difficult or impossible to guarantee on such filesystems. For those, we're best off not trying to provide WCC information to the client at all, and to simply allow it to poll for that information as needed with a GETATTR RPC. This patch adds a new flags field to struct export_operations, and defines a new EXPORT_OP_NOWCC flag that filesystems can use to indicate that nfsd should not attempt to provide WCC info in NFSv3 replies. It also adds a blurb about the new flags field and flag to the exporting documentation. The server will also now skip collecting this information for NFSv2 as well, since that info is never used there anyway. Note that this patch does not add this flag to any filesystem export_operations structures. This was originally developed to allow reexporting nfs via nfsd. Other filesystems may want to consider enabling this flag too. It's hard to tell however which ones have export operations to enable export via knfsd and which ones mostly rely on them for open-by-filehandle support, so I'm leaving that up to the individual maintainers to decide. I am cc'ing the relevant lists for those filesystems that I think may want to consider adding this though. Cc: HPDD-discuss@lists.01.org Cc: ceph-devel@vger.kernel.org Cc: cluster-devel@redhat.com Cc: fuse-devel@lists.sourceforge.net Cc: ocfs2-devel@oss.oracle.com Signed-off-by: Jeff Layton <jeff.layton@primarydata.com> Signed-off-by: Lance Shelton <lance.shelton@hammerspace.com> Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
2020-12-01 01:03:14 +03:00
if (fhp->fh_no_wcc)
return;
if (fhp->fh_post_saved)
printk("nfsd: inode locked twice during operation.\n");
Revert "nfsd: skip some unnecessary stats in the v4 case" [ Upstream commit 58f258f65267542959487dbe8b5641754411843d ] On the wire, I observed NFSv4 OPEN(CREATE) operations sometimes returning a reasonable-looking value in the cinfo.before field and zero in the cinfo.after field. RFC 8881 Section 10.8.1 says: > When a client is making changes to a given directory, it needs to > determine whether there have been changes made to the directory by > other clients. It does this by using the change attribute as > reported before and after the directory operation in the associated > change_info4 value returned for the operation. and > ... The post-operation change > value needs to be saved as the basis for future change_info4 > comparisons. A good quality client implementation therefore saves the zero cinfo.after value. During a subsequent OPEN operation, it will receive a different non-zero value in the cinfo.before field for that directory, and it will incorrectly believe the directory has changed, triggering an undesirable directory cache invalidation. There are filesystem types where fs_supports_change_attribute() returns false, tmpfs being one. On NFSv4 mounts, this means the fh_getattr() call site in fill_pre_wcc() and fill_post_wcc() is never invoked. Subsequently, nfsd4_change_attribute() is invoked with an uninitialized @stat argument. In fill_pre_wcc(), @stat contains stale stack garbage, which is then placed on the wire. In fill_post_wcc(), ->fh_post_wc is all zeroes, so zero is placed on the wire. Both of these values are meaningless. This fix can be applied immediately to stable kernels. Once there are more regression tests in this area, this optimization can be attempted again. Fixes: 428a23d2bf0c ("nfsd: skip some unnecessary stats in the v4 case") Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2021-12-24 22:22:28 +03:00
err = fh_getattr(fhp, &fhp->fh_post_attr);
if (err) {
fhp->fh_post_saved = false;
fhp->fh_post_attr.ctime = inode->i_ctime;
} else
fhp->fh_post_saved = true;
if (v4)
fhp->fh_post_change =
nfsd4_change_attribute(&fhp->fh_post_attr, inode);
}
/*
* XDR decode functions
*/
int
nfs3svc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd_fhandle *args = rqstp->rq_argp;
return svcxdr_decode_nfs_fh3(xdr, &args->fh);
}
int
nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_sattrargs *args = rqstp->rq_argp;
return svcxdr_decode_nfs_fh3(xdr, &args->fh) &&
svcxdr_decode_sattr3(rqstp, xdr, &args->attrs) &&
svcxdr_decode_sattrguard3(xdr, args);
}
int
nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_diropargs *args = rqstp->rq_argp;
return svcxdr_decode_diropargs3(xdr, &args->fh, &args->name, &args->len);
}
int
nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_accessargs *args = rqstp->rq_argp;
if (!svcxdr_decode_nfs_fh3(xdr, &args->fh))
return 0;
if (xdr_stream_decode_u32(xdr, &args->access) < 0)
return 0;
return 1;
}
int
nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_readargs *args = rqstp->rq_argp;
if (!svcxdr_decode_nfs_fh3(xdr, &args->fh))
return 0;
if (xdr_stream_decode_u64(xdr, &args->offset) < 0)
return 0;
if (xdr_stream_decode_u32(xdr, &args->count) < 0)
return 0;
return 1;
}
int
nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_writeargs *args = rqstp->rq_argp;
u32 max_blocksize = svc_max_payload(rqstp);
if (!svcxdr_decode_nfs_fh3(xdr, &args->fh))
return 0;
if (xdr_stream_decode_u64(xdr, &args->offset) < 0)
return 0;
if (xdr_stream_decode_u32(xdr, &args->count) < 0)
return 0;
if (xdr_stream_decode_u32(xdr, &args->stable) < 0)
return 0;
/* opaque data */
if (xdr_stream_decode_u32(xdr, &args->len) < 0)
return 0;
/* request sanity */
if (args->count != args->len)
return 0;
if (args->count > max_blocksize) {
args->count = max_blocksize;
args->len = max_blocksize;
}
if (!xdr_stream_subsegment(xdr, &args->payload, args->count))
return 0;
return 1;
}
int
nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_createargs *args = rqstp->rq_argp;
if (!svcxdr_decode_diropargs3(xdr, &args->fh, &args->name, &args->len))
return 0;
if (xdr_stream_decode_u32(xdr, &args->createmode) < 0)
return 0;
switch (args->createmode) {
case NFS3_CREATE_UNCHECKED:
case NFS3_CREATE_GUARDED:
return svcxdr_decode_sattr3(rqstp, xdr, &args->attrs);
case NFS3_CREATE_EXCLUSIVE:
args->verf = xdr_inline_decode(xdr, NFS3_CREATEVERFSIZE);
if (!args->verf)
return 0;
break;
default:
return 0;
}
return 1;
}
int
nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_createargs *args = rqstp->rq_argp;
return svcxdr_decode_diropargs3(xdr, &args->fh,
&args->name, &args->len) &&
svcxdr_decode_sattr3(rqstp, xdr, &args->attrs);
}
int
nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_symlinkargs *args = rqstp->rq_argp;
struct kvec *head = rqstp->rq_arg.head;
struct kvec *tail = rqstp->rq_arg.tail;
size_t remaining;
if (!svcxdr_decode_diropargs3(xdr, &args->ffh, &args->fname, &args->flen))
return 0;
if (!svcxdr_decode_sattr3(rqstp, xdr, &args->attrs))
return 0;
if (xdr_stream_decode_u32(xdr, &args->tlen) < 0)
return 0;
/* request sanity */
remaining = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len;
remaining -= xdr_stream_pos(xdr);
if (remaining < xdr_align_size(args->tlen))
return 0;
args->first.iov_base = xdr->p;
args->first.iov_len = head->iov_len - xdr_stream_pos(xdr);
return 1;
}
int
nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_mknodargs *args = rqstp->rq_argp;
if (!svcxdr_decode_diropargs3(xdr, &args->fh, &args->name, &args->len))
return 0;
if (xdr_stream_decode_u32(xdr, &args->ftype) < 0)
return 0;
switch (args->ftype) {
case NF3CHR:
case NF3BLK:
return svcxdr_decode_devicedata3(rqstp, xdr, args);
case NF3SOCK:
case NF3FIFO:
return svcxdr_decode_sattr3(rqstp, xdr, &args->attrs);
case NF3REG:
case NF3DIR:
case NF3LNK:
/* Valid XDR but illegal file types */
break;
default:
return 0;
}
return 1;
}
int
nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_renameargs *args = rqstp->rq_argp;
return svcxdr_decode_diropargs3(xdr, &args->ffh,
&args->fname, &args->flen) &&
svcxdr_decode_diropargs3(xdr, &args->tfh,
&args->tname, &args->tlen);
}
int
nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_linkargs *args = rqstp->rq_argp;
return svcxdr_decode_nfs_fh3(xdr, &args->ffh) &&
svcxdr_decode_diropargs3(xdr, &args->tfh,
&args->tname, &args->tlen);
}
int
nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_readdirargs *args = rqstp->rq_argp;
if (!svcxdr_decode_nfs_fh3(xdr, &args->fh))
return 0;
if (xdr_stream_decode_u64(xdr, &args->cookie) < 0)
return 0;
args->verf = xdr_inline_decode(xdr, NFS3_COOKIEVERFSIZE);
if (!args->verf)
return 0;
if (xdr_stream_decode_u32(xdr, &args->count) < 0)
return 0;
return 1;
}
int
nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_readdirargs *args = rqstp->rq_argp;
u32 dircount;
if (!svcxdr_decode_nfs_fh3(xdr, &args->fh))
return 0;
if (xdr_stream_decode_u64(xdr, &args->cookie) < 0)
return 0;
args->verf = xdr_inline_decode(xdr, NFS3_COOKIEVERFSIZE);
if (!args->verf)
return 0;
/* dircount is ignored */
if (xdr_stream_decode_u32(xdr, &dircount) < 0)
return 0;
if (xdr_stream_decode_u32(xdr, &args->count) < 0)
return 0;
return 1;
}
int
nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_arg_stream;
struct nfsd3_commitargs *args = rqstp->rq_argp;
if (!svcxdr_decode_nfs_fh3(xdr, &args->fh))
return 0;
if (xdr_stream_decode_u64(xdr, &args->offset) < 0)
return 0;
if (xdr_stream_decode_u32(xdr, &args->count) < 0)
return 0;
return 1;
}
/*
* XDR encode functions
*/
/* GETATTR */
int
nfs3svc_encode_getattrres(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_attrstat *resp = rqstp->rq_resp;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
return 0;
switch (resp->status) {
case nfs_ok:
lease_get_mtime(d_inode(resp->fh.fh_dentry), &resp->stat.mtime);
if (!svcxdr_encode_fattr3(rqstp, xdr, &resp->fh, &resp->stat))
return 0;
break;
}
return 1;
}
/* SETATTR, REMOVE, RMDIR */
int
nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_attrstat *resp = rqstp->rq_resp;
return svcxdr_encode_nfsstat3(xdr, resp->status) &&
svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh);
}
/* LOOKUP */
int nfs3svc_encode_lookupres(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_diropres *resp = rqstp->rq_resp;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
return 0;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_nfs_fh3(xdr, &resp->fh))
return 0;
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
return 0;
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->dirfh))
return 0;
break;
default:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->dirfh))
return 0;
}
return 1;
}
/* ACCESS */
int
nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_accessres *resp = rqstp->rq_resp;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
return 0;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
return 0;
if (xdr_stream_encode_u32(xdr, resp->access) < 0)
return 0;
break;
default:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
return 0;
}
return 1;
}
/* READLINK */
int
nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_readlinkres *resp = rqstp->rq_resp;
struct kvec *head = rqstp->rq_res.head;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
return 0;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
return 0;
if (xdr_stream_encode_u32(xdr, resp->len) < 0)
return 0;
xdr_write_pages(xdr, resp->pages, 0, resp->len);
if (svc_encode_result_payload(rqstp, head->iov_len, resp->len) < 0)
return 0;
break;
default:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
return 0;
}
return 1;
}
/* READ */
int
nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_readres *resp = rqstp->rq_resp;
struct kvec *head = rqstp->rq_res.head;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
return 0;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
return 0;
if (xdr_stream_encode_u32(xdr, resp->count) < 0)
return 0;
if (xdr_stream_encode_bool(xdr, resp->eof) < 0)
return 0;
if (xdr_stream_encode_u32(xdr, resp->count) < 0)
return 0;
xdr_write_pages(xdr, resp->pages, rqstp->rq_res.page_base,
resp->count);
if (svc_encode_result_payload(rqstp, head->iov_len, resp->count) < 0)
return 0;
break;
default:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
return 0;
}
return 1;
}
/* WRITE */
int
nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_writeres *resp = rqstp->rq_resp;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
return 0;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh))
return 0;
if (xdr_stream_encode_u32(xdr, resp->count) < 0)
return 0;
if (xdr_stream_encode_u32(xdr, resp->committed) < 0)
return 0;
if (!svcxdr_encode_writeverf3(xdr, resp->verf))
return 0;
break;
default:
if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh))
return 0;
}
return 1;
}
/* CREATE, MKDIR, SYMLINK, MKNOD */
int
nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_diropres *resp = rqstp->rq_resp;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
return 0;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_post_op_fh3(xdr, &resp->fh))
return 0;
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
return 0;
if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->dirfh))
return 0;
break;
default:
if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->dirfh))
return 0;
}
return 1;
}
/* RENAME */
int
nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_renameres *resp = rqstp->rq_resp;
return svcxdr_encode_nfsstat3(xdr, resp->status) &&
svcxdr_encode_wcc_data(rqstp, xdr, &resp->ffh) &&
svcxdr_encode_wcc_data(rqstp, xdr, &resp->tfh);
}
/* LINK */
int
nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_linkres *resp = rqstp->rq_resp;
return svcxdr_encode_nfsstat3(xdr, resp->status) &&
svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh) &&
svcxdr_encode_wcc_data(rqstp, xdr, &resp->tfh);
}
/* READDIR */
int
nfs3svc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_readdirres *resp = rqstp->rq_resp;
struct xdr_buf *dirlist = &resp->dirlist;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
return 0;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
return 0;
if (!svcxdr_encode_cookieverf3(xdr, resp->verf))
return 0;
xdr_write_pages(xdr, dirlist->pages, 0, dirlist->len);
/* no more entries */
if (xdr_stream_encode_item_absent(xdr) < 0)
return 0;
if (xdr_stream_encode_bool(xdr, resp->common.err == nfserr_eof) < 0)
return 0;
break;
default:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
return 0;
}
return 1;
}
static __be32
compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp,
const char *name, int namlen, u64 ino)
{
struct svc_export *exp;
struct dentry *dparent, *dchild;
__be32 rv = nfserr_noent;
dparent = cd->fh.fh_dentry;
exp = cd->fh.fh_export;
if (isdotent(name, namlen)) {
if (namlen == 2) {
dchild = dget_parent(dparent);
/*
* Don't return filehandle for ".." if we're at
* the filesystem or export root:
*/
if (dchild == dparent)
goto out;
if (dparent == exp->ex_path.dentry)
goto out;
} else
dchild = dget(dparent);
} else
dchild = lookup_positive_unlocked(name, dparent, namlen);
if (IS_ERR(dchild))
return rv;
if (d_mountpoint(dchild))
goto out;
if (dchild->d_inode->i_ino != ino)
goto out;
rv = fh_compose(fhp, exp, dchild, &cd->fh);
out:
dput(dchild);
return rv;
}
/**
* nfs3svc_encode_cookie3 - Encode a directory offset cookie
* @resp: readdir result context
* @offset: offset cookie to encode
*
* The buffer space for the offset cookie has already been reserved
* by svcxdr_encode_entry3_common().
*/
void nfs3svc_encode_cookie3(struct nfsd3_readdirres *resp, u64 offset)
{
__be64 cookie = cpu_to_be64(offset);
if (!resp->cookie_offset)
return;
write_bytes_to_xdr_buf(&resp->dirlist, resp->cookie_offset, &cookie,
sizeof(cookie));
resp->cookie_offset = 0;
}
static bool
svcxdr_encode_entry3_common(struct nfsd3_readdirres *resp, const char *name,
int namlen, loff_t offset, u64 ino)
{
struct xdr_buf *dirlist = &resp->dirlist;
struct xdr_stream *xdr = &resp->xdr;
if (xdr_stream_encode_item_present(xdr) < 0)
return false;
/* fileid */
if (xdr_stream_encode_u64(xdr, ino) < 0)
return false;
/* name */
if (xdr_stream_encode_opaque(xdr, name, min(namlen, NFS3_MAXNAMLEN)) < 0)
return false;
/* cookie */
resp->cookie_offset = dirlist->len;
if (xdr_stream_encode_u64(xdr, NFS_OFFSET_MAX) < 0)
return false;
return true;
}
/**
* nfs3svc_encode_entry3 - encode one NFSv3 READDIR entry
* @data: directory context
* @name: name of the object to be encoded
* @namlen: length of that name, in bytes
* @offset: the offset of the previous entry
* @ino: the fileid of this entry
* @d_type: unused
*
* Return values:
* %0: Entry was successfully encoded.
* %-EINVAL: An encoding problem occured, secondary status code in resp->common.err
*
* On exit, the following fields are updated:
* - resp->xdr
* - resp->common.err
* - resp->cookie_offset
*/
int nfs3svc_encode_entry3(void *data, const char *name, int namlen,
loff_t offset, u64 ino, unsigned int d_type)
{
struct readdir_cd *ccd = data;
struct nfsd3_readdirres *resp = container_of(ccd,
struct nfsd3_readdirres,
common);
unsigned int starting_length = resp->dirlist.len;
/* The offset cookie for the previous entry */
nfs3svc_encode_cookie3(resp, offset);
if (!svcxdr_encode_entry3_common(resp, name, namlen, offset, ino))
goto out_toosmall;
xdr_commit_encode(&resp->xdr);
resp->common.err = nfs_ok;
return 0;
out_toosmall:
resp->cookie_offset = 0;
resp->common.err = nfserr_toosmall;
resp->dirlist.len = starting_length;
return -EINVAL;
}
static bool
svcxdr_encode_entry3_plus(struct nfsd3_readdirres *resp, const char *name,
int namlen, u64 ino)
{
struct xdr_stream *xdr = &resp->xdr;
struct svc_fh *fhp = &resp->scratch;
bool result;
result = false;
fh_init(fhp, NFS3_FHSIZE);
if (compose_entry_fh(resp, fhp, name, namlen, ino) != nfs_ok)
goto out_noattrs;
if (!svcxdr_encode_post_op_attr(resp->rqstp, xdr, fhp))
goto out;
if (!svcxdr_encode_post_op_fh3(xdr, fhp))
goto out;
result = true;
out:
fh_put(fhp);
return result;
out_noattrs:
if (xdr_stream_encode_item_absent(xdr) < 0)
return false;
if (xdr_stream_encode_item_absent(xdr) < 0)
return false;
return true;
}
/**
* nfs3svc_encode_entryplus3 - encode one NFSv3 READDIRPLUS entry
* @data: directory context
* @name: name of the object to be encoded
* @namlen: length of that name, in bytes
* @offset: the offset of the previous entry
* @ino: the fileid of this entry
* @d_type: unused
*
* Return values:
* %0: Entry was successfully encoded.
* %-EINVAL: An encoding problem occured, secondary status code in resp->common.err
*
* On exit, the following fields are updated:
* - resp->xdr
* - resp->common.err
* - resp->cookie_offset
*/
int nfs3svc_encode_entryplus3(void *data, const char *name, int namlen,
loff_t offset, u64 ino, unsigned int d_type)
{
struct readdir_cd *ccd = data;
struct nfsd3_readdirres *resp = container_of(ccd,
struct nfsd3_readdirres,
common);
unsigned int starting_length = resp->dirlist.len;
/* The offset cookie for the previous entry */
nfs3svc_encode_cookie3(resp, offset);
if (!svcxdr_encode_entry3_common(resp, name, namlen, offset, ino))
goto out_toosmall;
if (!svcxdr_encode_entry3_plus(resp, name, namlen, ino))
goto out_toosmall;
xdr_commit_encode(&resp->xdr);
resp->common.err = nfs_ok;
return 0;
out_toosmall:
resp->cookie_offset = 0;
resp->common.err = nfserr_toosmall;
resp->dirlist.len = starting_length;
return -EINVAL;
}
static bool
svcxdr_encode_fsstat3resok(struct xdr_stream *xdr,
const struct nfsd3_fsstatres *resp)
{
const struct kstatfs *s = &resp->stats;
u64 bs = s->f_bsize;
__be32 *p;
p = xdr_reserve_space(xdr, XDR_UNIT * 13);
if (!p)
return false;
p = xdr_encode_hyper(p, bs * s->f_blocks); /* total bytes */
p = xdr_encode_hyper(p, bs * s->f_bfree); /* free bytes */
p = xdr_encode_hyper(p, bs * s->f_bavail); /* user available bytes */
p = xdr_encode_hyper(p, s->f_files); /* total inodes */
p = xdr_encode_hyper(p, s->f_ffree); /* free inodes */
p = xdr_encode_hyper(p, s->f_ffree); /* user available inodes */
*p = cpu_to_be32(resp->invarsec); /* mean unchanged time */
return true;
}
/* FSSTAT */
int
nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_fsstatres *resp = rqstp->rq_resp;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
return 0;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
return 0;
if (!svcxdr_encode_fsstat3resok(xdr, resp))
return 0;
break;
default:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
return 0;
}
return 1;
}
static bool
svcxdr_encode_fsinfo3resok(struct xdr_stream *xdr,
const struct nfsd3_fsinfores *resp)
{
__be32 *p;
p = xdr_reserve_space(xdr, XDR_UNIT * 12);
if (!p)
return false;
*p++ = cpu_to_be32(resp->f_rtmax);
*p++ = cpu_to_be32(resp->f_rtpref);
*p++ = cpu_to_be32(resp->f_rtmult);
*p++ = cpu_to_be32(resp->f_wtmax);
*p++ = cpu_to_be32(resp->f_wtpref);
*p++ = cpu_to_be32(resp->f_wtmult);
*p++ = cpu_to_be32(resp->f_dtpref);
p = xdr_encode_hyper(p, resp->f_maxfilesize);
p = encode_nfstime3(p, &nfs3svc_time_delta);
*p = cpu_to_be32(resp->f_properties);
return true;
}
/* FSINFO */
int
nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_fsinfores *resp = rqstp->rq_resp;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
return 0;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
return 0;
if (!svcxdr_encode_fsinfo3resok(xdr, resp))
return 0;
break;
default:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
return 0;
}
return 1;
}
static bool
svcxdr_encode_pathconf3resok(struct xdr_stream *xdr,
const struct nfsd3_pathconfres *resp)
{
__be32 *p;
p = xdr_reserve_space(xdr, XDR_UNIT * 6);
if (!p)
return false;
*p++ = cpu_to_be32(resp->p_link_max);
*p++ = cpu_to_be32(resp->p_name_max);
p = xdr_encode_bool(p, resp->p_no_trunc);
p = xdr_encode_bool(p, resp->p_chown_restricted);
p = xdr_encode_bool(p, resp->p_case_insensitive);
xdr_encode_bool(p, resp->p_case_preserving);
return true;
}
/* PATHCONF */
int
nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_pathconfres *resp = rqstp->rq_resp;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
return 0;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
return 0;
if (!svcxdr_encode_pathconf3resok(xdr, resp))
return 0;
break;
default:
if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
return 0;
}
return 1;
}
/* COMMIT */
int
nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p)
{
struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_commitres *resp = rqstp->rq_resp;
if (!svcxdr_encode_nfsstat3(xdr, resp->status))
return 0;
switch (resp->status) {
case nfs_ok:
if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh))
return 0;
if (!svcxdr_encode_writeverf3(xdr, resp->verf))
return 0;
break;
default:
if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh))
return 0;
}
return 1;
}
/*
* XDR release functions
*/
void
nfs3svc_release_fhandle(struct svc_rqst *rqstp)
{
struct nfsd3_attrstat *resp = rqstp->rq_resp;
fh_put(&resp->fh);
}
void
nfs3svc_release_fhandle2(struct svc_rqst *rqstp)
{
struct nfsd3_fhandle_pair *resp = rqstp->rq_resp;
fh_put(&resp->fh1);
fh_put(&resp->fh2);
}