linux_dsm_epyc7002/fs/nfsd/nfsxdr.c

602 lines
14 KiB
C
Raw Normal View History

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 21:07:57 +07:00
// SPDX-License-Identifier: GPL-2.0
/*
* XDR support for nfsd
*
* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
*/
#include "vfs.h"
#include "xdr.h"
#include "auth.h"
#define NFSDDBG_FACILITY NFSDDBG_XDR
/*
* Mapping of S_IF* types to NFS file types
*/
static u32 nfs_ftypes[] = {
NFNON, NFCHR, NFCHR, NFBAD,
NFDIR, NFBAD, NFBLK, NFBAD,
NFREG, NFBAD, NFLNK, NFBAD,
NFSOCK, NFBAD, NFLNK, NFBAD,
};
/*
* XDR functions for basic NFS types
*/
static __be32 *
decode_fh(__be32 *p, struct svc_fh *fhp)
{
fh_init(fhp, NFS_FHSIZE);
memcpy(&fhp->fh_handle.fh_base, p, NFS_FHSIZE);
fhp->fh_handle.fh_size = NFS_FHSIZE;
/* FIXME: Look up export pointer here and verify
* Sun Secure RPC if requested */
return p + (NFS_FHSIZE >> 2);
}
/* Helper function for NFSv2 ACL code */
__be32 *nfs2svc_decode_fh(__be32 *p, struct svc_fh *fhp)
{
return decode_fh(p, fhp);
}
static __be32 *
encode_fh(__be32 *p, struct svc_fh *fhp)
{
memcpy(p, &fhp->fh_handle.fh_base, NFS_FHSIZE);
return p + (NFS_FHSIZE>> 2);
}
/*
* Decode a file name and make sure that the path contains
* no slashes or null bytes.
*/
static __be32 *
decode_filename(__be32 *p, char **namp, unsigned int *lenp)
{
char *name;
unsigned int i;
if ((p = xdr_decode_string_inplace(p, namp, lenp, NFS_MAXNAMLEN)) != NULL) {
for (i = 0, name = *namp; i < *lenp; i++, name++) {
if (*name == '\0' || *name == '/')
return NULL;
}
}
return p;
}
static __be32 *
decode_sattr(__be32 *p, struct iattr *iap, struct user_namespace *userns)
{
u32 tmp, tmp1;
iap->ia_valid = 0;
/* Sun client bug compatibility check: some sun clients seem to
* put 0xffff in the mode field when they mean 0xffffffff.
* Quoting the 4.4BSD nfs server code: Nah nah nah nah na nah.
*/
if ((tmp = ntohl(*p++)) != (u32)-1 && tmp != 0xffff) {
iap->ia_valid |= ATTR_MODE;
iap->ia_mode = tmp;
}
if ((tmp = ntohl(*p++)) != (u32)-1) {
iap->ia_uid = make_kuid(userns, tmp);
if (uid_valid(iap->ia_uid))
iap->ia_valid |= ATTR_UID;
}
if ((tmp = ntohl(*p++)) != (u32)-1) {
iap->ia_gid = make_kgid(userns, tmp);
if (gid_valid(iap->ia_gid))
iap->ia_valid |= ATTR_GID;
}
if ((tmp = ntohl(*p++)) != (u32)-1) {
iap->ia_valid |= ATTR_SIZE;
iap->ia_size = tmp;
}
tmp = ntohl(*p++); tmp1 = ntohl(*p++);
if (tmp != (u32)-1 && tmp1 != (u32)-1) {
iap->ia_valid |= ATTR_ATIME | ATTR_ATIME_SET;
iap->ia_atime.tv_sec = tmp;
iap->ia_atime.tv_nsec = tmp1 * 1000;
}
tmp = ntohl(*p++); tmp1 = ntohl(*p++);
if (tmp != (u32)-1 && tmp1 != (u32)-1) {
iap->ia_valid |= ATTR_MTIME | ATTR_MTIME_SET;
iap->ia_mtime.tv_sec = tmp;
iap->ia_mtime.tv_nsec = tmp1 * 1000;
/*
* Passing the invalid value useconds=1000000 for mtime
* is a Sun convention for "set both mtime and atime to
* current server time". It's needed to make permissions
* checks for the "touch" program across v2 mounts to
* Solaris and Irix boxes work correctly. See description of
* sattr in section 6.1 of "NFS Illustrated" by
* Brent Callaghan, Addison-Wesley, ISBN 0-201-32750-5
*/
if (tmp1 == 1000000)
iap->ia_valid &= ~(ATTR_ATIME_SET|ATTR_MTIME_SET);
}
return p;
}
static __be32 *
encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
struct kstat *stat)
{
struct user_namespace *userns = nfsd_user_namespace(rqstp);
struct dentry *dentry = fhp->fh_dentry;
int type;
vfs: change inode times to use struct timespec64 struct timespec is not y2038 safe. Transition vfs to use y2038 safe struct timespec64 instead. The change was made with the help of the following cocinelle script. This catches about 80% of the changes. All the header file and logic changes are included in the first 5 rules. The rest are trivial substitutions. I avoid changing any of the function signatures or any other filesystem specific data structures to keep the patch simple for review. The script can be a little shorter by combining different cases. But, this version was sufficient for my usecase. virtual patch @ depends on patch @ identifier now; @@ - struct timespec + struct timespec64 current_time ( ... ) { - struct timespec now = current_kernel_time(); + struct timespec64 now = current_kernel_time64(); ... - return timespec_trunc( + return timespec64_trunc( ... ); } @ depends on patch @ identifier xtime; @@ struct \( iattr \| inode \| kstat \) { ... - struct timespec xtime; + struct timespec64 xtime; ... } @ depends on patch @ identifier t; @@ struct inode_operations { ... int (*update_time) (..., - struct timespec t, + struct timespec64 t, ...); ... } @ depends on patch @ identifier t; identifier fn_update_time =~ "update_time$"; @@ fn_update_time (..., - struct timespec *t, + struct timespec64 *t, ...) { ... } @ depends on patch @ identifier t; @@ lease_get_mtime( ... , - struct timespec *t + struct timespec64 *t ) { ... } @te depends on patch forall@ identifier ts; local idexpression struct inode *inode_node; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; identifier fn_update_time =~ "update_time$"; identifier fn; expression e, E3; local idexpression struct inode *node1; local idexpression struct inode *node2; local idexpression struct iattr *attr1; local idexpression struct iattr *attr2; local idexpression struct iattr attr; identifier i_xtime1 =~ "^i_[acm]time$"; identifier i_xtime2 =~ "^i_[acm]time$"; identifier ia_xtime1 =~ "^ia_[acm]time$"; identifier ia_xtime2 =~ "^ia_[acm]time$"; @@ ( ( - struct timespec ts; + struct timespec64 ts; | - struct timespec ts = current_time(inode_node); + struct timespec64 ts = current_time(inode_node); ) <+... when != ts ( - timespec_equal(&inode_node->i_xtime, &ts) + timespec64_equal(&inode_node->i_xtime, &ts) | - timespec_equal(&ts, &inode_node->i_xtime) + timespec64_equal(&ts, &inode_node->i_xtime) | - timespec_compare(&inode_node->i_xtime, &ts) + timespec64_compare(&inode_node->i_xtime, &ts) | - timespec_compare(&ts, &inode_node->i_xtime) + timespec64_compare(&ts, &inode_node->i_xtime) | ts = current_time(e) | fn_update_time(..., &ts,...) | inode_node->i_xtime = ts | node1->i_xtime = ts | ts = inode_node->i_xtime | <+... attr1->ia_xtime ...+> = ts | ts = attr1->ia_xtime | ts.tv_sec | ts.tv_nsec | btrfs_set_stack_timespec_sec(..., ts.tv_sec) | btrfs_set_stack_timespec_nsec(..., ts.tv_nsec) | - ts = timespec64_to_timespec( + ts = ... -) | - ts = ktime_to_timespec( + ts = ktime_to_timespec64( ...) | - ts = E3 + ts = timespec_to_timespec64(E3) | - ktime_get_real_ts(&ts) + ktime_get_real_ts64(&ts) | fn(..., - ts + timespec64_to_timespec(ts) ,...) ) ...+> ( <... when != ts - return ts; + return timespec64_to_timespec(ts); ...> ) | - timespec_equal(&node1->i_xtime1, &node2->i_xtime2) + timespec64_equal(&node1->i_xtime2, &node2->i_xtime2) | - timespec_equal(&node1->i_xtime1, &attr2->ia_xtime2) + timespec64_equal(&node1->i_xtime2, &attr2->ia_xtime2) | - timespec_compare(&node1->i_xtime1, &node2->i_xtime2) + timespec64_compare(&node1->i_xtime1, &node2->i_xtime2) | node1->i_xtime1 = - timespec_trunc(attr1->ia_xtime1, + timespec64_trunc(attr1->ia_xtime1, ...) | - attr1->ia_xtime1 = timespec_trunc(attr2->ia_xtime2, + attr1->ia_xtime1 = timespec64_trunc(attr2->ia_xtime2, ...) | - ktime_get_real_ts(&attr1->ia_xtime1) + ktime_get_real_ts64(&attr1->ia_xtime1) | - ktime_get_real_ts(&attr.ia_xtime1) + ktime_get_real_ts64(&attr.ia_xtime1) ) @ depends on patch @ struct inode *node; struct iattr *attr; identifier fn; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; expression e; @@ ( - fn(node->i_xtime); + fn(timespec64_to_timespec(node->i_xtime)); | fn(..., - node->i_xtime); + timespec64_to_timespec(node->i_xtime)); | - e = fn(attr->ia_xtime); + e = fn(timespec64_to_timespec(attr->ia_xtime)); ) @ depends on patch forall @ struct inode *node; struct iattr *attr; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; identifier fn; @@ { + struct timespec ts; <+... ( + ts = timespec64_to_timespec(node->i_xtime); fn (..., - &node->i_xtime, + &ts, ...); | + ts = timespec64_to_timespec(attr->ia_xtime); fn (..., - &attr->ia_xtime, + &ts, ...); ) ...+> } @ depends on patch forall @ struct inode *node; struct iattr *attr; struct kstat *stat; identifier ia_xtime =~ "^ia_[acm]time$"; identifier i_xtime =~ "^i_[acm]time$"; identifier xtime =~ "^[acm]time$"; identifier fn, ret; @@ { + struct timespec ts; <+... ( + ts = timespec64_to_timespec(node->i_xtime); ret = fn (..., - &node->i_xtime, + &ts, ...); | + ts = timespec64_to_timespec(node->i_xtime); ret = fn (..., - &node->i_xtime); + &ts); | + ts = timespec64_to_timespec(attr->ia_xtime); ret = fn (..., - &attr->ia_xtime, + &ts, ...); | + ts = timespec64_to_timespec(attr->ia_xtime); ret = fn (..., - &attr->ia_xtime); + &ts); | + ts = timespec64_to_timespec(stat->xtime); ret = fn (..., - &stat->xtime); + &ts); ) ...+> } @ depends on patch @ struct inode *node; struct inode *node2; identifier i_xtime1 =~ "^i_[acm]time$"; identifier i_xtime2 =~ "^i_[acm]time$"; identifier i_xtime3 =~ "^i_[acm]time$"; struct iattr *attrp; struct iattr *attrp2; struct iattr attr ; identifier ia_xtime1 =~ "^ia_[acm]time$"; identifier ia_xtime2 =~ "^ia_[acm]time$"; struct kstat *stat; struct kstat stat1; struct timespec64 ts; identifier xtime =~ "^[acmb]time$"; expression e; @@ ( ( node->i_xtime2 \| attrp->ia_xtime2 \| attr.ia_xtime2 \) = node->i_xtime1 ; | node->i_xtime2 = \( node2->i_xtime1 \| timespec64_trunc(...) \); | node->i_xtime2 = node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \); | node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \); | stat->xtime = node2->i_xtime1; | stat1.xtime = node2->i_xtime1; | ( node->i_xtime2 \| attrp->ia_xtime2 \) = attrp->ia_xtime1 ; | ( attrp->ia_xtime1 \| attr.ia_xtime1 \) = attrp2->ia_xtime2; | - e = node->i_xtime1; + e = timespec64_to_timespec( node->i_xtime1 ); | - e = attrp->ia_xtime1; + e = timespec64_to_timespec( attrp->ia_xtime1 ); | node->i_xtime1 = current_time(...); | node->i_xtime2 = node->i_xtime1 = node->i_xtime3 = - e; + timespec_to_timespec64(e); | node->i_xtime1 = node->i_xtime3 = - e; + timespec_to_timespec64(e); | - node->i_xtime1 = e; + node->i_xtime1 = timespec_to_timespec64(e); ) Signed-off-by: Deepa Dinamani <deepa.kernel@gmail.com> Cc: <anton@tuxera.com> Cc: <balbi@kernel.org> Cc: <bfields@fieldses.org> Cc: <darrick.wong@oracle.com> Cc: <dhowells@redhat.com> Cc: <dsterba@suse.com> Cc: <dwmw2@infradead.org> Cc: <hch@lst.de> Cc: <hirofumi@mail.parknet.co.jp> Cc: <hubcap@omnibond.com> Cc: <jack@suse.com> Cc: <jaegeuk@kernel.org> Cc: <jaharkes@cs.cmu.edu> Cc: <jslaby@suse.com> Cc: <keescook@chromium.org> Cc: <mark@fasheh.com> Cc: <miklos@szeredi.hu> Cc: <nico@linaro.org> Cc: <reiserfs-devel@vger.kernel.org> Cc: <richard@nod.at> Cc: <sage@redhat.com> Cc: <sfrench@samba.org> Cc: <swhiteho@redhat.com> Cc: <tj@kernel.org> Cc: <trond.myklebust@primarydata.com> Cc: <tytso@mit.edu> Cc: <viro@zeniv.linux.org.uk>
2018-05-09 09:36:02 +07:00
struct timespec64 time;
u32 f;
type = (stat->mode & S_IFMT);
*p++ = htonl(nfs_ftypes[type >> 12]);
*p++ = htonl((u32) stat->mode);
*p++ = htonl((u32) stat->nlink);
*p++ = htonl((u32) from_kuid_munged(userns, stat->uid));
*p++ = htonl((u32) from_kgid_munged(userns, stat->gid));
if (S_ISLNK(type) && stat->size > NFS_MAXPATHLEN) {
*p++ = htonl(NFS_MAXPATHLEN);
} else {
*p++ = htonl((u32) stat->size);
}
*p++ = htonl((u32) stat->blksize);
if (S_ISCHR(type) || S_ISBLK(type))
*p++ = htonl(new_encode_dev(stat->rdev));
else
*p++ = htonl(0xffffffff);
*p++ = htonl((u32) stat->blocks);
switch (fsid_source(fhp)) {
default:
case FSIDSOURCE_DEV:
*p++ = htonl(new_encode_dev(stat->dev));
break;
case FSIDSOURCE_FSID:
*p++ = htonl((u32) fhp->fh_export->ex_fsid);
break;
case FSIDSOURCE_UUID:
f = ((u32*)fhp->fh_export->ex_uuid)[0];
f ^= ((u32*)fhp->fh_export->ex_uuid)[1];
f ^= ((u32*)fhp->fh_export->ex_uuid)[2];
f ^= ((u32*)fhp->fh_export->ex_uuid)[3];
*p++ = htonl(f);
break;
}
*p++ = htonl((u32) stat->ino);
*p++ = htonl((u32) stat->atime.tv_sec);
*p++ = htonl(stat->atime.tv_nsec ? stat->atime.tv_nsec / 1000 : 0);
time = stat->mtime;
lease_get_mtime(d_inode(dentry), &time);
*p++ = htonl((u32) time.tv_sec);
*p++ = htonl(time.tv_nsec ? time.tv_nsec / 1000 : 0);
*p++ = htonl((u32) stat->ctime.tv_sec);
*p++ = htonl(stat->ctime.tv_nsec ? stat->ctime.tv_nsec / 1000 : 0);
return p;
}
/* Helper function for NFSv2 ACL code */
__be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat)
{
return encode_fattr(rqstp, p, fhp, stat);
}
/*
* XDR decode functions
*/
int
nfssvc_decode_void(struct svc_rqst *rqstp, __be32 *p)
{
return xdr_argsize_check(rqstp, p);
}
int
nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd_fhandle *args = rqstp->rq_argp;
p = decode_fh(p, &args->fh);
if (!p)
return 0;
return xdr_argsize_check(rqstp, p);
}
int
nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd_sattrargs *args = rqstp->rq_argp;
p = decode_fh(p, &args->fh);
if (!p)
return 0;
p = decode_sattr(p, &args->attrs, nfsd_user_namespace(rqstp));
return xdr_argsize_check(rqstp, p);
}
int
nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd_diropargs *args = rqstp->rq_argp;
if (!(p = decode_fh(p, &args->fh))
|| !(p = decode_filename(p, &args->name, &args->len)))
return 0;
return xdr_argsize_check(rqstp, p);
}
int
nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd_readargs *args = rqstp->rq_argp;
unsigned int len;
int v;
p = decode_fh(p, &args->fh);
if (!p)
return 0;
args->offset = ntohl(*p++);
len = args->count = ntohl(*p++);
p++; /* totalcount - unused */
len = min_t(unsigned int, len, NFSSVC_MAXBLKSIZE_V2);
/* set up somewhere to store response.
* We take pages, put them on reslist and include in iovec
*/
v=0;
while (len > 0) {
struct page *p = *(rqstp->rq_next_page++);
rqstp->rq_vec[v].iov_base = page_address(p);
rqstp->rq_vec[v].iov_len = min_t(unsigned int, len, PAGE_SIZE);
len -= rqstp->rq_vec[v].iov_len;
v++;
}
args->vlen = v;
return xdr_argsize_check(rqstp, p);
}
int
nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd_writeargs *args = rqstp->rq_argp;
unsigned int len, hdr, dlen;
struct kvec *head = rqstp->rq_arg.head;
p = decode_fh(p, &args->fh);
if (!p)
return 0;
p++; /* beginoffset */
args->offset = ntohl(*p++); /* offset */
p++; /* totalcount */
len = args->len = ntohl(*p++);
/*
* The protocol specifies a maximum of 8192 bytes.
*/
if (len > NFSSVC_MAXBLKSIZE_V2)
return 0;
/*
* Check to make sure that we got the right number of
* bytes.
*/
hdr = (void*)p - head->iov_base;
if (hdr > head->iov_len)
return 0;
dlen = head->iov_len + rqstp->rq_arg.page_len - hdr;
/*
* Round the length of the data which was specified up to
* the next multiple of XDR units and then compare that
* against the length which was actually received.
* Note that when RPCSEC/GSS (for example) is used, the
* data buffer can be padded so dlen might be larger
* than required. It must never be smaller.
*/
if (dlen < XDR_QUADLEN(len)*4)
return 0;
NFSD: Clean up legacy NFS WRITE argument XDR decoders Move common code in NFSD's legacy NFS WRITE decoders into a helper. The immediate benefit is reduction of code duplication and some nice micro-optimizations (see below). In the long term, this helper can perform a per-transport call-out to fill the rq_vec (say, using RDMA Reads). The legacy WRITE decoders and procs are changed to work like NFSv4, which constructs the rq_vec just before it is about to call vfs_writev. Why? Calling a transport call-out from the proc instead of the XDR decoder means that the incoming FH can be resolved to a particular filesystem and file. This would allow pages from the backing file to be presented to the transport to be filled, rather than presenting anonymous pages and copying or flipping them into the file's page cache later. I also prefer using the pages in rq_arg.pages, instead of pulling the data pages directly out of the rqstp::rq_pages array. This is currently the way the NFSv3 write decoder works, but the other two do not seem to take this approach. Fixing this removes the only reference to rq_pages found in NFSD, eliminating an NFSD assumption about how transports use the pages in rq_pages. Lastly, avoid setting up the first element of rq_vec as a zero- length buffer. This happens with an RDMA transport when a normal Read chunk is present because the data payload is in rq_arg's page list (none of it is in the head buffer). Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2018-03-27 21:54:07 +07:00
args->first.iov_base = (void *)p;
args->first.iov_len = head->iov_len - hdr;
return 1;
}
int
nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd_createargs *args = rqstp->rq_argp;
if ( !(p = decode_fh(p, &args->fh))
|| !(p = decode_filename(p, &args->name, &args->len)))
return 0;
p = decode_sattr(p, &args->attrs, nfsd_user_namespace(rqstp));
return xdr_argsize_check(rqstp, p);
}
int
nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd_renameargs *args = rqstp->rq_argp;
if (!(p = decode_fh(p, &args->ffh))
|| !(p = decode_filename(p, &args->fname, &args->flen))
|| !(p = decode_fh(p, &args->tfh))
|| !(p = decode_filename(p, &args->tname, &args->tlen)))
return 0;
return xdr_argsize_check(rqstp, p);
}
int
nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd_readlinkargs *args = rqstp->rq_argp;
p = decode_fh(p, &args->fh);
if (!p)
return 0;
args->buffer = page_address(*(rqstp->rq_next_page++));
return xdr_argsize_check(rqstp, p);
}
int
nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd_linkargs *args = rqstp->rq_argp;
if (!(p = decode_fh(p, &args->ffh))
|| !(p = decode_fh(p, &args->tfh))
|| !(p = decode_filename(p, &args->tname, &args->tlen)))
return 0;
return xdr_argsize_check(rqstp, p);
}
int
nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd_symlinkargs *args = rqstp->rq_argp;
char *base = (char *)p;
size_t xdrlen;
if ( !(p = decode_fh(p, &args->ffh))
|| !(p = decode_filename(p, &args->fname, &args->flen)))
return 0;
args->tlen = ntohl(*p++);
if (args->tlen == 0)
return 0;
args->first.iov_base = p;
args->first.iov_len = rqstp->rq_arg.head[0].iov_len;
args->first.iov_len -= (char *)p - base;
/* This request is never larger than a page. Therefore,
* transport will deliver either:
* 1. pathname in the pagelist -> sattr is in the tail.
* 2. everything in the head buffer -> sattr is in the head.
*/
if (rqstp->rq_arg.page_len) {
if (args->tlen != rqstp->rq_arg.page_len)
return 0;
p = rqstp->rq_arg.tail[0].iov_base;
} else {
xdrlen = XDR_QUADLEN(args->tlen);
if (xdrlen > args->first.iov_len - (8 * sizeof(__be32)))
return 0;
p += xdrlen;
}
decode_sattr(p, &args->attrs, nfsd_user_namespace(rqstp));
return 1;
}
int
nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd_readdirargs *args = rqstp->rq_argp;
p = decode_fh(p, &args->fh);
if (!p)
return 0;
args->cookie = ntohl(*p++);
args->count = ntohl(*p++);
args->count = min_t(u32, args->count, PAGE_SIZE);
args->buffer = page_address(*(rqstp->rq_next_page++));
return xdr_argsize_check(rqstp, p);
}
/*
* XDR encode functions
*/
int
nfssvc_encode_void(struct svc_rqst *rqstp, __be32 *p)
{
return xdr_ressize_check(rqstp, p);
}
int
nfssvc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd_attrstat *resp = rqstp->rq_resp;
if (resp->status != nfs_ok)
return xdr_ressize_check(rqstp, p);
p = encode_fattr(rqstp, p, &resp->fh, &resp->stat);
return xdr_ressize_check(rqstp, p);
}
int
nfssvc_encode_diropres(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd_diropres *resp = rqstp->rq_resp;
if (resp->status != nfs_ok)
return xdr_ressize_check(rqstp, p);
p = encode_fh(p, &resp->fh);
p = encode_fattr(rqstp, p, &resp->fh, &resp->stat);
return xdr_ressize_check(rqstp, p);
}
int
nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd_readlinkres *resp = rqstp->rq_resp;
if (resp->status != nfs_ok)
return xdr_ressize_check(rqstp, p);
*p++ = htonl(resp->len);
xdr_ressize_check(rqstp, p);
rqstp->rq_res.page_len = resp->len;
if (resp->len & 3) {
/* need to pad the tail */
rqstp->rq_res.tail[0].iov_base = p;
*p = 0;
rqstp->rq_res.tail[0].iov_len = 4 - (resp->len&3);
}
return 1;
}
int
nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd_readres *resp = rqstp->rq_resp;
if (resp->status != nfs_ok)
return xdr_ressize_check(rqstp, p);
p = encode_fattr(rqstp, p, &resp->fh, &resp->stat);
*p++ = htonl(resp->count);
xdr_ressize_check(rqstp, p);
/* now update rqstp->rq_res to reflect data as well */
rqstp->rq_res.page_len = resp->count;
if (resp->count & 3) {
/* need to pad the tail */
rqstp->rq_res.tail[0].iov_base = p;
*p = 0;
rqstp->rq_res.tail[0].iov_len = 4 - (resp->count&3);
}
return 1;
}
int
nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd_readdirres *resp = rqstp->rq_resp;
if (resp->status != nfs_ok)
return xdr_ressize_check(rqstp, p);
xdr_ressize_check(rqstp, p);
p = resp->buffer;
*p++ = 0; /* no more entries */
*p++ = htonl((resp->common.err == nfserr_eof));
rqstp->rq_res.page_len = (((unsigned long)p-1) & ~PAGE_MASK)+1;
return 1;
}
int
nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd_statfsres *resp = rqstp->rq_resp;
struct kstatfs *stat = &resp->stats;
if (resp->status != nfs_ok)
return xdr_ressize_check(rqstp, p);
*p++ = htonl(NFSSVC_MAXBLKSIZE_V2); /* max transfer size */
*p++ = htonl(stat->f_bsize);
*p++ = htonl(stat->f_blocks);
*p++ = htonl(stat->f_bfree);
*p++ = htonl(stat->f_bavail);
return xdr_ressize_check(rqstp, p);
}
int
nfssvc_encode_entry(void *ccdv, const char *name,
int namlen, loff_t offset, u64 ino, unsigned int d_type)
{
struct readdir_cd *ccd = ccdv;
struct nfsd_readdirres *cd = container_of(ccd, struct nfsd_readdirres, common);
__be32 *p = cd->buffer;
int buflen, slen;
/*
dprintk("nfsd: entry(%.*s off %ld ino %ld)\n",
namlen, name, offset, ino);
*/
if (offset > ~((u32) 0)) {
cd->common.err = nfserr_fbig;
return -EINVAL;
}
if (cd->offset)
*cd->offset = htonl(offset);
/* truncate filename */
namlen = min(namlen, NFS2_MAXNAMLEN);
slen = XDR_QUADLEN(namlen);
if ((buflen = cd->buflen - slen - 4) < 0) {
cd->common.err = nfserr_toosmall;
return -EINVAL;
}
if (ino > ~((u32) 0)) {
cd->common.err = nfserr_fbig;
return -EINVAL;
}
*p++ = xdr_one; /* mark entry present */
*p++ = htonl((u32) ino); /* file id */
p = xdr_encode_array(p, name, namlen);/* name length & name */
cd->offset = p; /* remember pointer */
*p++ = htonl(~0U); /* offset of next entry */
cd->buflen = buflen;
cd->buffer = p;
cd->common.err = nfs_ok;
return 0;
}
/*
* XDR release functions
*/
void nfssvc_release_attrstat(struct svc_rqst *rqstp)
{
struct nfsd_attrstat *resp = rqstp->rq_resp;
fh_put(&resp->fh);
}
void nfssvc_release_diropres(struct svc_rqst *rqstp)
{
struct nfsd_diropres *resp = rqstp->rq_resp;
fh_put(&resp->fh);
}
void nfssvc_release_readres(struct svc_rqst *rqstp)
{
struct nfsd_readres *resp = rqstp->rq_resp;
fh_put(&resp->fh);
}