UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge branch 'for-3.8' of git://linux-nfs.org/~bfields/linux 

Pull nfsd update from Bruce Fields:
 "Included this time:

   - more nfsd containerization work from Stanislav Kinsbursky: we're
     not quite there yet, but should be by 3.9.

   - NFSv4.1 progress: implementation of basic backchannel security
     negotiation and the mandatory BACKCHANNEL_CTL operation.  See

       http://wiki.linux-nfs.org/wiki/index.php/Server_4.0_and_4.1_issues

     for remaining TODO's

   - Fixes for some bugs that could be triggered by unusual compounds.
     Our xdr code wasn't designed with v4 compounds in mind, and it
     shows.  A more thorough rewrite is still a todo.

   - If you've ever seen "RPC: multiple fragments per record not
     supported" logged while using some sort of odd userland NFS client,
     that should now be fixed.

   - Further work from Jeff Layton on our mechanism for storing
     information about NFSv4 clients across reboots.

   - Further work from Bryan Schumaker on his fault-injection mechanism
     (which allows us to discard selective NFSv4 state, to excercise
     rarely-taken recovery code paths in the client.)

   - The usual mix of miscellaneous bugs and cleanup.

  Thanks to everyone who tested or contributed this cycle."

* 'for-3.8' of git://linux-nfs.org/~bfields/linux: (111 commits)
  nfsd4: don't leave freed stateid hashed
  nfsd4: free_stateid can use the current stateid
  nfsd4: cleanup: replace rq_resused count by rq_next_page pointer
  nfsd: warn on odd reply state in nfsd_vfs_read
  nfsd4: fix oops on unusual readlike compound
  nfsd4: disable zero-copy on non-final read ops
  svcrpc: fix some printks
  NFSD: Correct the size calculation in fault_inject_write
  NFSD: Pass correct buffer size to rpc_ntop
  nfsd: pass proper net to nfsd_destroy() from NFSd kthreads
  nfsd: simplify service shutdown
  nfsd: replace boolean nfsd_up flag by users counter
  nfsd: simplify NFSv4 state init and shutdown
  nfsd: introduce helpers for generic resources init and shutdown
  nfsd: make NFSd service structure allocated per net
  nfsd: make NFSd service boot time per-net
  nfsd: per-net NFSd up flag introduced
  nfsd: move per-net startup code to separated function
  nfsd: pass net to __write_ports() and down
  nfsd: pass net to nfsd_set_nrthreads()
  ...
This commit is contained in:
Linus Torvalds 2012-12-20 14:04:11 -08:00
parent 40889e8d9f 24ffb93872
commit 982197277c
32 changed files with 1933 additions and 1089 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
Documentation/filesystems/nfs/nfs41-server.txt
View File

@ -39,21 +39,10 @@ interoperability problems with future clients. Known issues:
from a linux client are possible, but we aren't really
conformant with the spec (for example, we don't use kerberos
on the backchannel correctly).
- Incomplete backchannel support: incomplete backchannel gss
support and no support for BACKCHANNEL_CTL mean that
callbacks (hence delegations and layouts) may not be
available and clients confused by the incomplete
implementation may fail.
- We do not support SSV, which provides security for shared
client-server state (thus preventing unauthorized tampering
with locks and opens, for example). It is mandatory for
servers to support this, though no clients use it yet.
- Mandatory operations which we do not support, such as
DESTROY_CLIENTID, are not currently used by clients, but will be
(and the spec recommends their uses in common cases), and
clients should not be expected to know how to recover from the
case where they are not supported. This will eventually cause
interoperability failures.
In addition, some limitations are inherited from the current NFSv4
implementation:
@ -89,7 +78,7 @@ Operations
| | MNI | or OPT) | |
+----------------------+------------+--------------+----------------+
| ACCESS | REQ | | Section 18.1 |
NS | BACKCHANNEL_CTL | REQ | | Section 18.33 |
I | BACKCHANNEL_CTL | REQ | | Section 18.33 |
I | BIND_CONN_TO_SESSION | REQ | | Section 18.34 |
| CLOSE | REQ | | Section 18.2 |
| COMMIT | REQ | | Section 18.3 |
@ -99,7 +88,7 @@ NS*| DELEGPURGE | OPT | FDELG (REQ) | Section 18.5 |
| DELEGRETURN | OPT | FDELG, | Section 18.6 |
| | | DDELG, pNFS | |
| | | (REQ) | |
NS | DESTROY_CLIENTID | REQ | | Section 18.50 |
I | DESTROY_CLIENTID | REQ | | Section 18.50 |
I | DESTROY_SESSION | REQ | | Section 18.37 |
I | EXCHANGE_ID | REQ | | Section 18.35 |
I | FREE_STATEID | REQ | | Section 18.38 |
@ -192,7 +181,6 @@ EXCHANGE_ID:
CREATE_SESSION:
* backchannel attributes are ignored
* backchannel security parameters are ignored
SEQUENCE:
* no support for dynamic slot table renegotiation (optional)
@ -202,7 +190,7 @@ Nonstandard compound limitations:
ca_maxrequestsize request and a ca_maxresponsesize reply, so we may
fail to live up to the promise we made in CREATE_SESSION fore channel
negotiation.
* No more than one IO operation (read, write, readdir) allowed per
compound.
* No more than one read-like operation allowed per compound; encoding
replies that cross page boundaries (except for read data) not handled.
See also http://wiki.linux-nfs.org/wiki/index.php/Server_4.0_and_4.1_issues.

4
fs/exportfs/expfs.c
View File

@ -322,10 +322,10 @@ static int export_encode_fh(struct inode *inode, struct fid *fid,
if (parent && (len < 4)) {
*max_len = 4;
return 255;
return FILEID_INVALID;
} else if (len < 2) {
*max_len = 2;
return 255;
return FILEID_INVALID;
}
len = 2;

2
fs/fhandle.c
View File

@ -52,7 +52,7 @@ static long do_sys_name_to_handle(struct path *path,
handle_bytes = handle_dwords * sizeof(u32);
handle->handle_bytes = handle_bytes;
if ((handle->handle_bytes > f_handle.handle_bytes) ||
(retval == 255) || (retval == -ENOSPC)) {
(retval == FILEID_INVALID) || (retval == -ENOSPC)) {
/* As per old exportfs_encode_fh documentation
* we could return ENOSPC to indicate overflow
* But file system returned 255 always. So handle

113
fs/nfsd/fault_inject.c
View File

@ -8,61 +8,144 @@
#include <linux/fs.h>
#include <linux/debugfs.h>
#include <linux/module.h>
#include <linux/nsproxy.h>
#include <linux/sunrpc/clnt.h>
#include <asm/uaccess.h>
#include "state.h"
#include "fault_inject.h"
#include "netns.h"
struct nfsd_fault_inject_op {
char *file;
void (*func)(u64);
u64 (*forget)(struct nfs4_client *, u64);
u64 (*print)(struct nfs4_client *, u64);
};
static struct nfsd_fault_inject_op inject_ops[] = {
{
.file = "forget_clients",
.func = nfsd_forget_clients,
.forget = nfsd_forget_client,
.print = nfsd_print_client,
},
{
.file = "forget_locks",
.func = nfsd_forget_locks,
.forget = nfsd_forget_client_locks,
.print = nfsd_print_client_locks,
},
{
.file = "forget_openowners",
.func = nfsd_forget_openowners,
.forget = nfsd_forget_client_openowners,
.print = nfsd_print_client_openowners,
},
{
.file = "forget_delegations",
.func = nfsd_forget_delegations,
.forget = nfsd_forget_client_delegations,
.print = nfsd_print_client_delegations,
},
{
.file = "recall_delegations",
.func = nfsd_recall_delegations,
.forget = nfsd_recall_client_delegations,
.print = nfsd_print_client_delegations,
},
};
static long int NUM_INJECT_OPS = sizeof(inject_ops) / sizeof(struct nfsd_fault_inject_op);
static struct dentry *debug_dir;
static int nfsd_inject_set(void *op_ptr, u64 val)
static void nfsd_inject_set(struct nfsd_fault_inject_op *op, u64 val)
{
struct nfsd_fault_inject_op *op = op_ptr;
u64 count = 0;
if (val == 0)
printk(KERN_INFO "NFSD Fault Injection: %s (all)", op->file);
else
printk(KERN_INFO "NFSD Fault Injection: %s (n = %llu)", op->file, val);
op->func(val);
return 0;
nfs4_lock_state();
count = nfsd_for_n_state(val, op->forget);
nfs4_unlock_state();
printk(KERN_INFO "NFSD: %s: found %llu", op->file, count);
}
static int nfsd_inject_get(void *data, u64 *val)
static void nfsd_inject_set_client(struct nfsd_fault_inject_op *op,
struct sockaddr_storage *addr,
size_t addr_size)
{
*val = 0;
return 0;
char buf[INET6_ADDRSTRLEN];
struct nfs4_client *clp;
u64 count;
nfs4_lock_state();
clp = nfsd_find_client(addr, addr_size);
if (clp) {
count = op->forget(clp, 0);
rpc_ntop((struct sockaddr *)&clp->cl_addr, buf, sizeof(buf));
printk(KERN_INFO "NFSD [%s]: Client %s had %llu state object(s)\n", op->file, buf, count);
}
nfs4_unlock_state();
}
DEFINE_SIMPLE_ATTRIBUTE(fops_nfsd, nfsd_inject_get, nfsd_inject_set, "%llu\n");
static void nfsd_inject_get(struct nfsd_fault_inject_op *op, u64 *val)
{
nfs4_lock_state();
*val = nfsd_for_n_state(0, op->print);
nfs4_unlock_state();
}
static ssize_t fault_inject_read(struct file *file, char __user *buf,
size_t len, loff_t *ppos)
{
static u64 val;
char read_buf[25];
size_t size, ret;
loff_t pos = *ppos;
if (!pos)
nfsd_inject_get(file->f_dentry->d_inode->i_private, &val);
size = scnprintf(read_buf, sizeof(read_buf), "%llu\n", val);
if (pos < 0)
return -EINVAL;
if (pos >= size || !len)
return 0;
if (len > size - pos)
len = size - pos;
ret = copy_to_user(buf, read_buf + pos, len);
if (ret == len)
return -EFAULT;
len -= ret;
*ppos = pos + len;
return len;
}
static ssize_t fault_inject_write(struct file *file, const char __user *buf,
size_t len, loff_t *ppos)
{
char write_buf[INET6_ADDRSTRLEN];
size_t size = min(sizeof(write_buf) - 1, len);
struct net *net = current->nsproxy->net_ns;
struct sockaddr_storage sa;
u64 val;
if (copy_from_user(write_buf, buf, size))
return -EFAULT;
write_buf[size] = '\0';
size = rpc_pton(net, write_buf, size, (struct sockaddr *)&sa, sizeof(sa));
if (size > 0)
nfsd_inject_set_client(file->f_dentry->d_inode->i_private, &sa, size);
else {
val = simple_strtoll(write_buf, NULL, 0);
nfsd_inject_set(file->f_dentry->d_inode->i_private, val);
}
return len; /* on success, claim we got the whole input */
}
static const struct file_operations fops_nfsd = {
.owner = THIS_MODULE,
.read = fault_inject_read,
.write = fault_inject_write,
};
void nfsd_fault_inject_cleanup(void)
{

28
fs/nfsd/fault_inject.h
View File

@ -1,28 +0,0 @@
/*
* Copyright (c) 2011 Bryan Schumaker <bjschuma@netapp.com>
*
* Function definitions for fault injection
*/
#ifndef LINUX_NFSD_FAULT_INJECT_H
#define LINUX_NFSD_FAULT_INJECT_H
#ifdef CONFIG_NFSD_FAULT_INJECTION
int nfsd_fault_inject_init(void);
void nfsd_fault_inject_cleanup(void);
void nfsd_forget_clients(u64);
void nfsd_forget_locks(u64);
void nfsd_forget_openowners(u64);
void nfsd_forget_delegations(u64);
void nfsd_recall_delegations(u64);
#else /* CONFIG_NFSD_FAULT_INJECTION */
static inline int nfsd_fault_inject_init(void) { return 0; }
static inline void nfsd_fault_inject_cleanup(void) {}
static inline void nfsd_forget_clients(u64 num) {}
static inline void nfsd_forget_locks(u64 num) {}
static inline void nfsd_forget_openowners(u64 num) {}
static inline void nfsd_forget_delegations(u64 num) {}
static inline void nfsd_recall_delegations(u64 num) {}
#endif /* CONFIG_NFSD_FAULT_INJECTION */
#endif /* LINUX_NFSD_FAULT_INJECT_H */

66
fs/nfsd/netns.h
View File

@ -24,7 +24,18 @@
#include <net/net_namespace.h>
#include <net/netns/generic.h>
/* Hash tables for nfs4_clientid state */
#define CLIENT_HASH_BITS 4
#define CLIENT_HASH_SIZE (1 << CLIENT_HASH_BITS)
#define CLIENT_HASH_MASK (CLIENT_HASH_SIZE - 1)
#define LOCKOWNER_INO_HASH_BITS 8
#define LOCKOWNER_INO_HASH_SIZE (1 << LOCKOWNER_INO_HASH_BITS)
#define SESSION_HASH_SIZE 512
struct cld_net;
struct nfsd4_client_tracking_ops;
struct nfsd_net {
struct cld_net *cld_net;
@ -38,7 +49,62 @@ struct nfsd_net {
struct lock_manager nfsd4_manager;
bool grace_ended;
time_t boot_time;
/*
* reclaim_str_hashtbl[] holds known client info from previous reset/reboot
* used in reboot/reset lease grace period processing
*
* conf_id_hashtbl[], and conf_name_tree hold confirmed
* setclientid_confirmed info.
*
* unconf_str_hastbl[] and unconf_name_tree hold unconfirmed
* setclientid info.
*/
struct list_head *reclaim_str_hashtbl;
int reclaim_str_hashtbl_size;
struct list_head *conf_id_hashtbl;
struct rb_root conf_name_tree;
struct list_head *unconf_id_hashtbl;
struct rb_root unconf_name_tree;
struct list_head *ownerstr_hashtbl;
struct list_head *lockowner_ino_hashtbl;
struct list_head *sessionid_hashtbl;
/*
* client_lru holds client queue ordered by nfs4_client.cl_time
* for lease renewal.
*
* close_lru holds (open) stateowner queue ordered by nfs4_stateowner.so_time
* for last close replay.
*
* All of the above fields are protected by the client_mutex.
*/
struct list_head client_lru;
struct list_head close_lru;
struct delayed_work laundromat_work;
/* client_lock protects the client lru list and session hash table */
spinlock_t client_lock;
struct file *rec_file;
bool in_grace;
struct nfsd4_client_tracking_ops *client_tracking_ops;
time_t nfsd4_lease;
time_t nfsd4_grace;
bool nfsd_net_up;
/*
* Time of server startup
*/
struct timeval nfssvc_boot;
struct svc_serv *nfsd_serv;
};
/* Simple check to find out if a given net was properly initialized */
#define nfsd_netns_ready(nn) ((nn)->sessionid_hashtbl)
extern int nfsd_net_id;
#endif /* __NFSD_NETNS_H__ */

2
fs/nfsd/nfs2acl.c
View File

@ -253,7 +253,7 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
(resp->mask & NFS_ACL) ? resp->acl_access : NULL,
(resp->mask & NFS_DFACL) ? resp->acl_default : NULL);
while (w > 0) {
if (!rqstp->rq_respages[rqstp->rq_resused++])
if (!*(rqstp->rq_next_page++))
return 0;
w -= PAGE_SIZE;
}

2
fs/nfsd/nfs3acl.c
View File

@ -184,7 +184,7 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
(resp->mask & NFS_ACL) ? resp->acl_access : NULL,
(resp->mask & NFS_DFACL) ? resp->acl_default : NULL);
while (w > 0) {
if (!rqstp->rq_respages[rqstp->rq_resused++])
if (!*(rqstp->rq_next_page++))
return 0;
w -= PAGE_SIZE;
}

6
fs/nfsd/nfs3proc.c
View File

@ -460,7 +460,7 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
__be32 nfserr;
int count = 0;
loff_t offset;
int i;
struct page **p;
caddr_t page_addr = NULL;
dprintk("nfsd: READDIR+(3) %s %d bytes at %d\n",
@ -484,8 +484,8 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
&resp->common,
nfs3svc_encode_entry_plus);
memcpy(resp->verf, argp->verf, 8);
for (i=1; i<rqstp->rq_resused ; i++) {
page_addr = page_address(rqstp->rq_respages[i]);
for (p = rqstp->rq_respages + 1; p < rqstp->rq_next_page; p++) {
page_addr = page_address(*p);
if (((caddr_t)resp->buffer >= page_addr) &&
((caddr_t)resp->buffer < page_addr + PAGE_SIZE)) {

47
fs/nfsd/nfs3xdr.c
View File

@ -7,8 +7,10 @@
*/
#include <linux/namei.h>
#include <linux/sunrpc/svc_xprt.h>
#include "xdr3.h"
#include "auth.h"
#include "netns.h"
#define NFSDDBG_FACILITY NFSDDBG_XDR
@ -323,7 +325,7 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd3_readargs *args)
{
unsigned int len;
int v,pn;
int v;
u32 max_blocksize = svc_max_payload(rqstp);
if (!(p = decode_fh(p, &args->fh)))
@ -338,8 +340,9 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
/* set up the kvec */
v=0;
while (len > 0) {
pn = rqstp->rq_resused++;
rqstp->rq_vec[v].iov_base = page_address(rqstp->rq_respages[pn]);
struct page *p = *(rqstp->rq_next_page++);
rqstp->rq_vec[v].iov_base = page_address(p);
rqstp->rq_vec[v].iov_len = len < PAGE_SIZE? len : PAGE_SIZE;
len -= rqstp->rq_vec[v].iov_len;
v++;
@ -461,8 +464,7 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
len = ntohl(*p++);
if (len == 0 || len > NFS3_MAXPATHLEN || len >= PAGE_SIZE)
return 0;
args->tname = new =
page_address(rqstp->rq_respages[rqstp->rq_resused++]);
args->tname = new = page_address(*(rqstp->rq_next_page++));
args->tlen = len;
/* first copy and check from the first page */
old = (char*)p;
@ -533,8 +535,7 @@ nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p,
{
if (!(p = decode_fh(p, &args->fh)))
return 0;
args->buffer =
page_address(rqstp->rq_respages[rqstp->rq_resused++]);
args->buffer = page_address(*(rqstp->rq_next_page++));
return xdr_argsize_check(rqstp, p);
}
@ -565,8 +566,7 @@ nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p,
if (args->count > PAGE_SIZE)
args->count = PAGE_SIZE;
args->buffer =
page_address(rqstp->rq_respages[rqstp->rq_resused++]);
args->buffer = page_address(*(rqstp->rq_next_page++));
return xdr_argsize_check(rqstp, p);
}
@ -575,7 +575,7 @@ int
nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd3_readdirargs *args)
{
int len, pn;
int len;
u32 max_blocksize = svc_max_payload(rqstp);
if (!(p = decode_fh(p, &args->fh)))
@ -590,9 +590,9 @@ nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p,
args->count = len;
while (len > 0) {
pn = rqstp->rq_resused++;
struct page *p = *(rqstp->rq_next_page++);
if (!args->buffer)
args->buffer = page_address(rqstp->rq_respages[pn]);
args->buffer = page_address(p);
len -= PAGE_SIZE;
}
@ -720,12 +720,14 @@ int
nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p,
struct nfsd3_writeres *resp)
{
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
p = encode_wcc_data(rqstp, p, &resp->fh);
if (resp->status == 0) {
*p++ = htonl(resp->count);
*p++ = htonl(resp->committed);
*p++ = htonl(nfssvc_boot.tv_sec);
*p++ = htonl(nfssvc_boot.tv_usec);
*p++ = htonl(nn->nfssvc_boot.tv_sec);
*p++ = htonl(nn->nfssvc_boot.tv_usec);
}
return xdr_ressize_check(rqstp, p);
}
@ -876,7 +878,7 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen,
common);
__be32 *p = cd->buffer;
caddr_t curr_page_addr = NULL;
int pn; /* current page number */
struct page ** page;
int slen; /* string (name) length */
int elen; /* estimated entry length in words */
int num_entry_words = 0; /* actual number of words */
@ -913,8 +915,9 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen,
}
/* determine which page in rq_respages[] we are currently filling */
for (pn=1; pn < cd->rqstp->rq_resused; pn++) {
curr_page_addr = page_address(cd->rqstp->rq_respages[pn]);
for (page = cd->rqstp->rq_respages + 1;
page < cd->rqstp->rq_next_page; page++) {
curr_page_addr = page_address(*page);
if (((caddr_t)cd->buffer >= curr_page_addr) &&
((caddr_t)cd->buffer < curr_page_addr + PAGE_SIZE))
@ -929,14 +932,14 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen,
if (plus)
p = encode_entryplus_baggage(cd, p, name, namlen);
num_entry_words = p - cd->buffer;
} else if (cd->rqstp->rq_respages[pn+1] != NULL) {
} else if (*(page+1) != NULL) {
/* temporarily encode entry into next page, then move back to
* current and next page in rq_respages[] */
__be32 *p1, *tmp;
int len1, len2;
/* grab next page for temporary storage of entry */
p1 = tmp = page_address(cd->rqstp->rq_respages[pn+1]);
p1 = tmp = page_address(*(page+1));
p1 = encode_entry_baggage(cd, p1, name, namlen, ino);
@ -1082,11 +1085,13 @@ int
nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p,
struct nfsd3_commitres *resp)
{
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
p = encode_wcc_data(rqstp, p, &resp->fh);
/* Write verifier */
if (resp->status == 0) {
*p++ = htonl(nfssvc_boot.tv_sec);
*p++ = htonl(nfssvc_boot.tv_usec);
*p++ = htonl(nn->nfssvc_boot.tv_sec);
*p++ = htonl(nn->nfssvc_boot.tv_usec);
}
return xdr_ressize_check(rqstp, p);
}

69
fs/nfsd/nfs4callback.c
View File

@ -36,6 +36,7 @@
#include <linux/slab.h>
#include "nfsd.h"
#include "state.h"
#include "netns.h"
#define NFSDDBG_FACILITY NFSDDBG_PROC
@ -625,20 +626,46 @@ static const struct rpc_program cb_program = {
.pipe_dir_name = "nfsd4_cb",
};
static int max_cb_time(void)
static int max_cb_time(struct net *net)
{
return max(nfsd4_lease/10, (time_t)1) * HZ;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
return max(nn->nfsd4_lease/10, (time_t)1) * HZ;
}
static struct rpc_cred *callback_cred;
int set_callback_cred(void)
{
if (callback_cred)
return 0;
callback_cred = rpc_lookup_machine_cred("nfs");
if (!callback_cred)
return -ENOMEM;
return 0;
}
static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc_clnt *client, struct nfsd4_session *ses)
{
if (clp->cl_minorversion == 0) {
return get_rpccred(callback_cred);
} else {
struct rpc_auth *auth = client->cl_auth;
struct auth_cred acred = {};
acred.uid = ses->se_cb_sec.uid;
acred.gid = ses->se_cb_sec.gid;
return auth->au_ops->lookup_cred(client->cl_auth, &acred, 0);
}
}
static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn, struct nfsd4_session *ses)
{
struct rpc_timeout timeparms = {
.to_initval = max_cb_time(),
.to_initval = max_cb_time(clp->net),
.to_retries = 0,
};
struct rpc_create_args args = {
.net = &init_net,
.net = clp->net,
.address = (struct sockaddr *) &conn->cb_addr,
.addrsize = conn->cb_addrlen,
.saddress = (struct sockaddr *) &conn->cb_saddr,
@ -648,6 +675,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
.flags = (RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_QUIET),
};
struct rpc_clnt *client;
struct rpc_cred *cred;
if (clp->cl_minorversion == 0) {
if (!clp->cl_cred.cr_principal &&
@ -666,7 +694,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
args.bc_xprt = conn->cb_xprt;
args.prognumber = clp->cl_cb_session->se_cb_prog;
args.protocol = XPRT_TRANSPORT_BC_TCP;
args.authflavor = RPC_AUTH_UNIX;
args.authflavor = ses->se_cb_sec.flavor;
}
/* Create RPC client */
client = rpc_create(&args);
@ -675,9 +703,14 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
PTR_ERR(client));
return PTR_ERR(client);
}
cred = get_backchannel_cred(clp, client, ses);
if (IS_ERR(cred)) {
rpc_shutdown_client(client);
return PTR_ERR(cred);
}
clp->cl_cb_client = client;
clp->cl_cb_cred = cred;
return 0;
}
static void warn_no_callback_path(struct nfs4_client *clp, int reason)
@ -714,18 +747,6 @@ static const struct rpc_call_ops nfsd4_cb_probe_ops = {
.rpc_call_done = nfsd4_cb_probe_done,
};
static struct rpc_cred *callback_cred;
int set_callback_cred(void)
{
if (callback_cred)
return 0;
callback_cred = rpc_lookup_machine_cred("nfs");
if (!callback_cred)
return -ENOMEM;
return 0;
}
static struct workqueue_struct *callback_wq;
static void run_nfsd4_cb(struct nfsd4_callback *cb)
@ -743,7 +764,6 @@ static void do_probe_callback(struct nfs4_client *clp)
cb->cb_msg.rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL];
cb->cb_msg.rpc_argp = NULL;
cb->cb_msg.rpc_resp = NULL;
cb->cb_msg.rpc_cred = callback_cred;
cb->cb_ops = &nfsd4_cb_probe_ops;
@ -962,6 +982,8 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
if (clp->cl_cb_client) {
rpc_shutdown_client(clp->cl_cb_client);
clp->cl_cb_client = NULL;
put_rpccred(clp->cl_cb_cred);
clp->cl_cb_cred = NULL;
}
if (clp->cl_cb_conn.cb_xprt) {
svc_xprt_put(clp->cl_cb_conn.cb_xprt);
@ -995,7 +1017,7 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
run_nfsd4_cb(cb);
}
void nfsd4_do_callback_rpc(struct work_struct *w)
static void nfsd4_do_callback_rpc(struct work_struct *w)
{
struct nfsd4_callback *cb = container_of(w, struct nfsd4_callback, cb_work);
struct nfs4_client *clp = cb->cb_clp;
@ -1010,10 +1032,16 @@ void nfsd4_do_callback_rpc(struct work_struct *w)
nfsd4_release_cb(cb);
return;
}
cb->cb_msg.rpc_cred = clp->cl_cb_cred;
rpc_call_async(clnt, &cb->cb_msg, RPC_TASK_SOFT | RPC_TASK_SOFTCONN,
cb->cb_ops, cb);
}
void nfsd4_init_callback(struct nfsd4_callback *cb)
{
INIT_WORK(&cb->cb_work, nfsd4_do_callback_rpc);
}
void nfsd4_cb_recall(struct nfs4_delegation *dp)
{
struct nfsd4_callback *cb = &dp->dl_recall;
@ -1025,7 +1053,6 @@ void nfsd4_cb_recall(struct nfs4_delegation *dp)
cb->cb_msg.rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_RECALL];
cb->cb_msg.rpc_argp = cb;
cb->cb_msg.rpc_resp = cb;
cb->cb_msg.rpc_cred = callback_cred;
cb->cb_ops = &nfsd4_cb_recall_ops;

74
fs/nfsd/nfs4proc.c
View File

@ -40,6 +40,7 @@
#include "xdr4.h"
#include "vfs.h"
#include "current_stateid.h"
#include "netns.h"
#define NFSDDBG_FACILITY NFSDDBG_PROC
@ -194,6 +195,7 @@ static __be32
do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open)
{
struct svc_fh *resfh;
int accmode;
__be32 status;
resfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL);
@ -253,9 +255,10 @@ do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_o
/* set reply cache */
fh_copy_shallow(&open->op_openowner->oo_owner.so_replay.rp_openfh,
&resfh->fh_handle);
if (!open->op_created)
status = do_open_permission(rqstp, resfh, open,
NFSD_MAY_NOP);
accmode = NFSD_MAY_NOP;
if (open->op_created)
accmode |= NFSD_MAY_OWNER_OVERRIDE;
status = do_open_permission(rqstp, resfh, open, accmode);
set_change_info(&open->op_cinfo, current_fh);
fh_dup2(current_fh, resfh);
out:
@ -304,6 +307,8 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
{
__be32 status;
struct nfsd4_compoundres *resp;
struct net *net = SVC_NET(rqstp);
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
dprintk("NFSD: nfsd4_open filename %.*s op_openowner %p\n",
(int)open->op_fname.len, open->op_fname.data,
@ -331,7 +336,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
/* check seqid for replay. set nfs4_owner */
resp = rqstp->rq_resp;
status = nfsd4_process_open1(&resp->cstate, open);
status = nfsd4_process_open1(&resp->cstate, open, nn);
if (status == nfserr_replay_me) {
struct nfs4_replay *rp = &open->op_openowner->oo_owner.so_replay;
fh_put(&cstate->current_fh);
@ -354,10 +359,10 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
/* Openowner is now set, so sequence id will get bumped. Now we need
* these checks before we do any creates: */
status = nfserr_grace;
if (locks_in_grace(SVC_NET(rqstp)) && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
if (locks_in_grace(net) && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
goto out;
status = nfserr_no_grace;
if (!locks_in_grace(SVC_NET(rqstp)) && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
if (!locks_in_grace(net) && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
goto out;
switch (open->op_claim_type) {
@ -370,7 +375,9 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
break;
case NFS4_OPEN_CLAIM_PREVIOUS:
open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
status = nfs4_check_open_reclaim(&open->op_clientid, cstate->minorversion);
status = nfs4_check_open_reclaim(&open->op_clientid,
cstate->minorversion,
nn);
if (status)
goto out;
case NFS4_OPEN_CLAIM_FH:
@ -490,12 +497,13 @@ nfsd4_access(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
&access->ac_supported);
}
static void gen_boot_verifier(nfs4_verifier *verifier)
static void gen_boot_verifier(nfs4_verifier *verifier, struct net *net)
{
__be32 verf[2];
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
verf[0] = (__be32)nfssvc_boot.tv_sec;
verf[1] = (__be32)nfssvc_boot.tv_usec;
verf[0] = (__be32)nn->nfssvc_boot.tv_sec;
verf[1] = (__be32)nn->nfssvc_boot.tv_usec;
memcpy(verifier->data, verf, sizeof(verifier->data));
}
@ -503,7 +511,7 @@ static __be32
nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_commit *commit)
{
gen_boot_verifier(&commit->co_verf);
gen_boot_verifier(&commit->co_verf, SVC_NET(rqstp));
return nfsd_commit(rqstp, &cstate->current_fh, commit->co_offset,
commit->co_count);
}
@ -684,6 +692,17 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (read->rd_offset >= OFFSET_MAX)
return nfserr_inval;
/*
* If we do a zero copy read, then a client will see read data
* that reflects the state of the file *after* performing the
* following compound.
*
* To ensure proper ordering, we therefore turn off zero copy if
* the client wants us to do more in this compound:
*/
if (!nfsd4_last_compound_op(rqstp))
rqstp->rq_splice_ok = false;
nfs4_lock_state();
/* check stateid */
if ((status = nfs4_preprocess_stateid_op(SVC_NET(rqstp),
@ -876,6 +895,24 @@ out:
return status;
}
static int fill_in_write_vector(struct kvec *vec, struct nfsd4_write *write)
{
int i = 1;
int buflen = write->wr_buflen;
vec[0].iov_base = write->wr_head.iov_base;
vec[0].iov_len = min_t(int, buflen, write->wr_head.iov_len);
buflen -= vec[0].iov_len;
while (buflen) {
vec[i].iov_base = page_address(write->wr_pagelist[i - 1]);
vec[i].iov_len = min_t(int, PAGE_SIZE, buflen);
buflen -= vec[i].iov_len;
i++;
}
return i;
}
static __be32
nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_write *write)
@ -884,6 +921,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct file *filp = NULL;
__be32 status = nfs_ok;
unsigned long cnt;
int nvecs;
/* no need to check permission - this will be done in nfsd_write() */
@ -904,10 +942,13 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
cnt = write->wr_buflen;
write->wr_how_written = write->wr_stable_how;
gen_boot_verifier(&write->wr_verifier);
gen_boot_verifier(&write->wr_verifier, SVC_NET(rqstp));
nvecs = fill_in_write_vector(rqstp->rq_vec, write);
WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec));
status = nfsd_write(rqstp, &cstate->current_fh, filp,
write->wr_offset, rqstp->rq_vec, write->wr_vlen,
write->wr_offset, rqstp->rq_vec, nvecs,
&cnt, &write->wr_how_written);
if (filp)
fput(filp);
@ -1666,6 +1707,12 @@ static struct nfsd4_operation nfsd4_ops[] = {
.op_name = "OP_EXCHANGE_ID",
.op_rsize_bop = (nfsd4op_rsize)nfsd4_exchange_id_rsize,
},
[OP_BACKCHANNEL_CTL] = {
.op_func = (nfsd4op_func)nfsd4_backchannel_ctl,
.op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING,
.op_name = "OP_BACKCHANNEL_CTL",
.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
},
[OP_BIND_CONN_TO_SESSION] = {
.op_func = (nfsd4op_func)nfsd4_bind_conn_to_session,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP
@ -1719,6 +1766,7 @@ static struct nfsd4_operation nfsd4_ops[] = {
.op_func = (nfsd4op_func)nfsd4_free_stateid,
.op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING,
.op_name = "OP_FREE_STATEID",
.op_get_currentstateid = (stateid_getter)nfsd4_get_freestateid,
.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
},
};

561
fs/nfsd/nfs4recover.c
View File

@ -58,13 +58,11 @@ struct nfsd4_client_tracking_ops {
void (*create)(struct nfs4_client *);
void (*remove)(struct nfs4_client *);
int (*check)(struct nfs4_client *);
void (*grace_done)(struct net *, time_t);
void (*grace_done)(struct nfsd_net *, time_t);
};
/* Globals */
static struct file *rec_file;
static char user_recovery_dirname[PATH_MAX] = "/var/lib/nfs/v4recovery";
static struct nfsd4_client_tracking_ops *client_tracking_ops;
static int
nfs4_save_creds(const struct cred **original_creds)
@ -102,33 +100,39 @@ md5_to_hex(char *out, char *md5)
*out = '\0';
}
__be32
nfs4_make_rec_clidname(char *dname, struct xdr_netobj *clname)
static int
nfs4_make_rec_clidname(char *dname, const struct xdr_netobj *clname)
{
struct xdr_netobj cksum;
struct hash_desc desc;
struct scatterlist sg;
__be32 status = nfserr_jukebox;
int status;
dprintk("NFSD: nfs4_make_rec_clidname for %.*s\n",
clname->len, clname->data);
desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
desc.tfm = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
if (IS_ERR(desc.tfm))
if (IS_ERR(desc.tfm)) {
status = PTR_ERR(desc.tfm);
goto out_no_tfm;
}
cksum.len = crypto_hash_digestsize(desc.tfm);
cksum.data = kmalloc(cksum.len, GFP_KERNEL);
if (cksum.data == NULL)
if (cksum.data == NULL) {
status = -ENOMEM;
goto out;
}
sg_init_one(&sg, clname->data, clname->len);
if (crypto_hash_digest(&desc, &sg, sg.length, cksum.data))
status = crypto_hash_digest(&desc, &sg, sg.length, cksum.data);
if (status)
goto out;
md5_to_hex(dname, cksum.data);
status = nfs_ok;
status = 0;
out:
kfree(cksum.data);
crypto_free_hash(desc.tfm);
@ -136,29 +140,61 @@ out_no_tfm:
return status;
}
/*
* If we had an error generating the recdir name for the legacy tracker
* then warn the admin. If the error doesn't appear to be transient,
* then disable recovery tracking.
*/
static void
legacy_recdir_name_error(int error)
{
printk(KERN_ERR "NFSD: unable to generate recoverydir "
"name (%d).\n", error);
/*
* if the algorithm just doesn't exist, then disable the recovery
* tracker altogether. The crypto libs will generally return this if
* FIPS is enabled as well.
*/
if (error == -ENOENT) {
printk(KERN_ERR "NFSD: disabling legacy clientid tracking. "
"Reboot recovery will not function correctly!\n");
/* the argument is ignored by the legacy exit function */
nfsd4_client_tracking_exit(NULL);
}
}
static void
nfsd4_create_clid_dir(struct nfs4_client *clp)
{
const struct cred *original_cred;
char *dname = clp->cl_recdir;
char dname[HEXDIR_LEN];
struct dentry *dir, *dentry;
struct nfs4_client_reclaim *crp;
int status;
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
dprintk("NFSD: nfsd4_create_clid_dir for \"%s\"\n", dname);
if (test_and_set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
return;
if (!rec_file)
if (!nn->rec_file)
return;
status = nfs4_make_rec_clidname(dname, &clp->cl_name);
if (status)
return legacy_recdir_name_error(status);
status = nfs4_save_creds(&original_cred);
if (status < 0)
return;
status = mnt_want_write_file(rec_file);
status = mnt_want_write_file(nn->rec_file);
if (status)
return;
dir = rec_file->f_path.dentry;
dir = nn->rec_file->f_path.dentry;
/* lock the parent */
mutex_lock(&dir->d_inode->i_mutex);
@ -182,18 +218,24 @@ out_put:
dput(dentry);
out_unlock:
mutex_unlock(&dir->d_inode->i_mutex);
if (status == 0)
vfs_fsync(rec_file, 0);
else
if (status == 0) {
if (nn->in_grace) {
crp = nfs4_client_to_reclaim(dname, nn);
if (crp)
crp->cr_clp = clp;
}
vfs_fsync(nn->rec_file, 0);
} else {
printk(KERN_ERR "NFSD: failed to write recovery record"
" (err %d); please check that %s exists"
" and is writeable", status,
user_recovery_dirname);
mnt_drop_write_file(rec_file);
}
mnt_drop_write_file(nn->rec_file);
nfs4_reset_creds(original_cred);
}
typedef int (recdir_func)(struct dentry *, struct dentry *);
typedef int (recdir_func)(struct dentry *, struct dentry *, struct nfsd_net *);
struct name_list {
char name[HEXDIR_LEN];
@ -219,10 +261,10 @@ nfsd4_build_namelist(void *arg, const char *name, int namlen,
}
static int
nfsd4_list_rec_dir(recdir_func *f)
nfsd4_list_rec_dir(recdir_func *f, struct nfsd_net *nn)
{
const struct cred *original_cred;
struct dentry *dir = rec_file->f_path.dentry;
struct dentry *dir = nn->rec_file->f_path.dentry;
LIST_HEAD(names);
int status;
@ -230,13 +272,13 @@ nfsd4_list_rec_dir(recdir_func *f)
if (status < 0)
return status;
status = vfs_llseek(rec_file, 0, SEEK_SET);
status = vfs_llseek(nn->rec_file, 0, SEEK_SET);
if (status < 0) {
nfs4_reset_creds(original_cred);
return status;
}
status = vfs_readdir(rec_file, nfsd4_build_namelist, &names);
status = vfs_readdir(nn->rec_file, nfsd4_build_namelist, &names);
mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);
while (!list_empty(&names)) {
struct name_list *entry;
@ -248,7 +290,7 @@ nfsd4_list_rec_dir(recdir_func *f)
status = PTR_ERR(dentry);
break;
}
status = f(dir, dentry);
status = f(dir, dentry, nn);
dput(dentry);
}
list_del(&entry->list);
@ -260,14 +302,14 @@ nfsd4_list_rec_dir(recdir_func *f)
}
static int
nfsd4_unlink_clid_dir(char *name, int namlen)
nfsd4_unlink_clid_dir(char *name, int namlen, struct nfsd_net *nn)
{
struct dentry *dir, *dentry;
int status;
dprintk("NFSD: nfsd4_unlink_clid_dir. name %.*s\n", namlen, name);
dir = rec_file->f_path.dentry;
dir = nn->rec_file->f_path.dentry;
mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);
dentry = lookup_one_len(name, dir, namlen);
if (IS_ERR(dentry)) {
@ -289,37 +331,52 @@ static void
nfsd4_remove_clid_dir(struct nfs4_client *clp)
{
const struct cred *original_cred;
struct nfs4_client_reclaim *crp;
char dname[HEXDIR_LEN];
int status;
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
if (!rec_file || !test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
if (!nn->rec_file || !test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
return;
status = mnt_want_write_file(rec_file);
status = nfs4_make_rec_clidname(dname, &clp->cl_name);
if (status)
return legacy_recdir_name_error(status);
status = mnt_want_write_file(nn->rec_file);
if (status)
goto out;
clear_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
status = nfs4_save_creds(&original_cred);
if (status < 0)
goto out;
goto out_drop_write;
status = nfsd4_unlink_clid_dir(clp->cl_recdir, HEXDIR_LEN-1);
status = nfsd4_unlink_clid_dir(dname, HEXDIR_LEN-1, nn);
nfs4_reset_creds(original_cred);
if (status == 0)
vfs_fsync(rec_file, 0);
mnt_drop_write_file(rec_file);
if (status == 0) {
vfs_fsync(nn->rec_file, 0);
if (nn->in_grace) {
/* remove reclaim record */
crp = nfsd4_find_reclaim_client(dname, nn);
if (crp)
nfs4_remove_reclaim_record(crp, nn);
}
}
out_drop_write:
mnt_drop_write_file(nn->rec_file);
out:
if (status)
printk("NFSD: Failed to remove expired client state directory"
" %.*s\n", HEXDIR_LEN, clp->cl_recdir);
" %.*s\n", HEXDIR_LEN, dname);
}
static int
purge_old(struct dentry *parent, struct dentry *child)
purge_old(struct dentry *parent, struct dentry *child, struct nfsd_net *nn)
{
int status;
if (nfs4_has_reclaimed_state(child->d_name.name, false))
if (nfs4_has_reclaimed_state(child->d_name.name, nn))
return 0;
status = vfs_rmdir(parent->d_inode, child);
@ -331,27 +388,29 @@ purge_old(struct dentry *parent, struct dentry *child)
}
static void
nfsd4_recdir_purge_old(struct net *net, time_t boot_time)
nfsd4_recdir_purge_old(struct nfsd_net *nn, time_t boot_time)
{
int status;
if (!rec_file)
nn->in_grace = false;
if (!nn->rec_file)
return;
status = mnt_want_write_file(rec_file);
status = mnt_want_write_file(nn->rec_file);
if (status)
goto out;
status = nfsd4_list_rec_dir(purge_old);
status = nfsd4_list_rec_dir(purge_old, nn);
if (status == 0)
vfs_fsync(rec_file, 0);
mnt_drop_write_file(rec_file);
vfs_fsync(nn->rec_file, 0);
mnt_drop_write_file(nn->rec_file);
out:
nfs4_release_reclaim(nn);
if (status)
printk("nfsd4: failed to purge old clients from recovery"
" directory %s\n", rec_file->f_path.dentry->d_name.name);
" directory %s\n", nn->rec_file->f_path.dentry->d_name.name);
}
static int
load_recdir(struct dentry *parent, struct dentry *child)
load_recdir(struct dentry *parent, struct dentry *child, struct nfsd_net *nn)
{
if (child->d_name.len != HEXDIR_LEN - 1) {
printk("nfsd4: illegal name %s in recovery directory\n",
@ -359,21 +418,22 @@ load_recdir(struct dentry *parent, struct dentry *child)
/* Keep trying; maybe the others are OK: */
return 0;
}
nfs4_client_to_reclaim(child->d_name.name);
nfs4_client_to_reclaim(child->d_name.name, nn);
return 0;
}
static int
nfsd4_recdir_load(void) {
nfsd4_recdir_load(struct net *net) {
int status;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
if (!rec_file)
if (!nn->rec_file)
return 0;
status = nfsd4_list_rec_dir(load_recdir);
status = nfsd4_list_rec_dir(load_recdir, nn);
if (status)
printk("nfsd4: failed loading clients from recovery"
" directory %s\n", rec_file->f_path.dentry->d_name.name);
" directory %s\n", nn->rec_file->f_path.dentry->d_name.name);
return status;
}
@ -382,15 +442,16 @@ nfsd4_recdir_load(void) {
*/
static int
nfsd4_init_recdir(void)
nfsd4_init_recdir(struct net *net)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
const struct cred *original_cred;
int status;
printk("NFSD: Using %s as the NFSv4 state recovery directory\n",
user_recovery_dirname);
BUG_ON(rec_file);
BUG_ON(nn->rec_file);
status = nfs4_save_creds(&original_cred);
if (status < 0) {
@ -400,23 +461,65 @@ nfsd4_init_recdir(void)
return status;
}
rec_file = filp_open(user_recovery_dirname, O_RDONLY | O_DIRECTORY, 0);
if (IS_ERR(rec_file)) {
nn->rec_file = filp_open(user_recovery_dirname, O_RDONLY | O_DIRECTORY, 0);
if (IS_ERR(nn->rec_file)) {
printk("NFSD: unable to find recovery directory %s\n",
user_recovery_dirname);
status = PTR_ERR(rec_file);
rec_file = NULL;
status = PTR_ERR(nn->rec_file);
nn->rec_file = NULL;
}
nfs4_reset_creds(original_cred);
if (!status)
nn->in_grace = true;
return status;
}
static int
nfs4_legacy_state_init(struct net *net)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
int i;
nn->reclaim_str_hashtbl = kmalloc(sizeof(struct list_head) *
CLIENT_HASH_SIZE, GFP_KERNEL);
if (!nn->reclaim_str_hashtbl)
return -ENOMEM;
for (i = 0; i < CLIENT_HASH_SIZE; i++)
INIT_LIST_HEAD(&nn->reclaim_str_hashtbl[i]);
nn->reclaim_str_hashtbl_size = 0;
return 0;
}
static void
nfs4_legacy_state_shutdown(struct net *net)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
kfree(nn->reclaim_str_hashtbl);
}
static int
nfsd4_load_reboot_recovery_data(struct net *net)
{
int status;
status = nfsd4_init_recdir(net);
if (!status)
status = nfsd4_recdir_load(net);
if (status)
printk(KERN_ERR "NFSD: Failure reading reboot recovery data\n");
return status;
}
static int
nfsd4_legacy_tracking_init(struct net *net)
{
int status;
/* XXX: The legacy code won't work in a container */
if (net != &init_net) {
WARN(1, KERN_ERR "NFSD: attempt to initialize legacy client "
@ -424,30 +527,37 @@ nfsd4_load_reboot_recovery_data(struct net *net)
return -EINVAL;
}
nfs4_lock_state();
status = nfsd4_init_recdir();
if (!status)
status = nfsd4_recdir_load();
nfs4_unlock_state();
status = nfs4_legacy_state_init(net);
if (status)
printk(KERN_ERR "NFSD: Failure reading reboot recovery data\n");
return status;
status = nfsd4_load_reboot_recovery_data(net);
if (status)
goto err;
return 0;
err:
nfs4_legacy_state_shutdown(net);
return status;
}
static void
nfsd4_shutdown_recdir(void)
nfsd4_shutdown_recdir(struct nfsd_net *nn)
{
if (!rec_file)
if (!nn->rec_file)
return;
fput(rec_file);
rec_file = NULL;
fput(nn->rec_file);
nn->rec_file = NULL;
}
static void
nfsd4_legacy_tracking_exit(struct net *net)
{
nfs4_release_reclaim();
nfsd4_shutdown_recdir();
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
nfs4_release_reclaim(nn);
nfsd4_shutdown_recdir(nn);
nfs4_legacy_state_shutdown(net);
}
/*
@ -480,13 +590,26 @@ nfs4_recoverydir(void)
static int
nfsd4_check_legacy_client(struct nfs4_client *clp)
{
int status;
char dname[HEXDIR_LEN];
struct nfs4_client_reclaim *crp;
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
/* did we already find that this client is stable? */
if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
return 0;
status = nfs4_make_rec_clidname(dname, &clp->cl_name);
if (status) {
legacy_recdir_name_error(status);
return status;
}
/* look for it in the reclaim hashtable otherwise */
if (nfsd4_find_reclaim_client(clp)) {
crp = nfsd4_find_reclaim_client(dname, nn);
if (crp) {
set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
crp->cr_clp = clp;
return 0;
}
@ -494,7 +617,7 @@ nfsd4_check_legacy_client(struct nfs4_client *clp)
}
static struct nfsd4_client_tracking_ops nfsd4_legacy_tracking_ops = {
.init = nfsd4_load_reboot_recovery_data,
.init = nfsd4_legacy_tracking_init,
.exit = nfsd4_legacy_tracking_exit,
.create = nfsd4_create_clid_dir,
.remove = nfsd4_remove_clid_dir,
@ -785,8 +908,7 @@ nfsd4_cld_create(struct nfs4_client *clp)
{
int ret;
struct cld_upcall *cup;
/* FIXME: determine net from clp */
struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
struct cld_net *cn = nn->cld_net;
/* Don't upcall if it's already stored */
@ -823,8 +945,7 @@ nfsd4_cld_remove(struct nfs4_client *clp)
{
int ret;
struct cld_upcall *cup;
/* FIXME: determine net from clp */
struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
struct cld_net *cn = nn->cld_net;
/* Don't upcall if it's already removed */
@ -861,8 +982,7 @@ nfsd4_cld_check(struct nfs4_client *clp)
{
int ret;
struct cld_upcall *cup;
/* FIXME: determine net from clp */
struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
struct cld_net *cn = nn->cld_net;
/* Don't upcall if one was already stored during this grace pd */
@ -892,11 +1012,10 @@ nfsd4_cld_check(struct nfs4_client *clp)
}
static void
nfsd4_cld_grace_done(struct net *net, time_t boot_time)
nfsd4_cld_grace_done(struct nfsd_net *nn, time_t boot_time)
{
int ret;
struct cld_upcall *cup;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
struct cld_net *cn = nn->cld_net;
cup = alloc_cld_upcall(cn);
@ -926,28 +1045,261 @@ static struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops = {
.grace_done = nfsd4_cld_grace_done,
};
/* upcall via usermodehelper */
static char cltrack_prog[PATH_MAX] = "/sbin/nfsdcltrack";
module_param_string(cltrack_prog, cltrack_prog, sizeof(cltrack_prog),
S_IRUGO|S_IWUSR);
MODULE_PARM_DESC(cltrack_prog, "Path to the nfsdcltrack upcall program");
static bool cltrack_legacy_disable;
module_param(cltrack_legacy_disable, bool, S_IRUGO|S_IWUSR);
MODULE_PARM_DESC(cltrack_legacy_disable,
"Disable legacy recoverydir conversion. Default: false");
#define LEGACY_TOPDIR_ENV_PREFIX "NFSDCLTRACK_LEGACY_TOPDIR="
#define LEGACY_RECDIR_ENV_PREFIX "NFSDCLTRACK_LEGACY_RECDIR="
static char *
nfsd4_cltrack_legacy_topdir(void)
{
int copied;
size_t len;
char *result;
if (cltrack_legacy_disable)
return NULL;
len = strlen(LEGACY_TOPDIR_ENV_PREFIX) +
strlen(nfs4_recoverydir()) + 1;
result = kmalloc(len, GFP_KERNEL);
if (!result)
return result;
copied = snprintf(result, len, LEGACY_TOPDIR_ENV_PREFIX "%s",
nfs4_recoverydir());
if (copied >= len) {
/* just return nothing if output was truncated */
kfree(result);
return NULL;
}
return result;
}
static char *
nfsd4_cltrack_legacy_recdir(const struct xdr_netobj *name)
{
int copied;
size_t len;
char *result;
if (cltrack_legacy_disable)
return NULL;
/* +1 is for '/' between "topdir" and "recdir" */
len = strlen(LEGACY_RECDIR_ENV_PREFIX) +
strlen(nfs4_recoverydir()) + 1 + HEXDIR_LEN;
result = kmalloc(len, GFP_KERNEL);
if (!result)
return result;
copied = snprintf(result, len, LEGACY_RECDIR_ENV_PREFIX "%s/",
nfs4_recoverydir());
if (copied > (len - HEXDIR_LEN)) {
/* just return nothing if output will be truncated */
kfree(result);
return NULL;
}
copied = nfs4_make_rec_clidname(result + copied, name);
if (copied) {
kfree(result);
return NULL;
}
return result;
}
static int
nfsd4_umh_cltrack_upcall(char *cmd, char *arg, char *legacy)
{
char *envp[2];
char *argv[4];
int ret;
if (unlikely(!cltrack_prog[0])) {
dprintk("%s: cltrack_prog is disabled\n", __func__);
return -EACCES;
}
dprintk("%s: cmd: %s\n", __func__, cmd);
dprintk("%s: arg: %s\n", __func__, arg ? arg : "(null)");
dprintk("%s: legacy: %s\n", __func__, legacy ? legacy : "(null)");
envp[0] = legacy;
envp[1] = NULL;
argv[0] = (char *)cltrack_prog;
argv[1] = cmd;
argv[2] = arg;
argv[3] = NULL;
ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);
/*
* Disable the upcall mechanism if we're getting an ENOENT or EACCES
* error. The admin can re-enable it on the fly by using sysfs
* once the problem has been fixed.
*/
if (ret == -ENOENT || ret == -EACCES) {
dprintk("NFSD: %s was not found or isn't executable (%d). "
"Setting cltrack_prog to blank string!",
cltrack_prog, ret);
cltrack_prog[0] = '\0';
}
dprintk("%s: %s return value: %d\n", __func__, cltrack_prog, ret);
return ret;
}
static char *
bin_to_hex_dup(const unsigned char *src, int srclen)
{
int i;
char *buf, *hex;
/* +1 for terminating NULL */
buf = kmalloc((srclen * 2) + 1, GFP_KERNEL);
if (!buf)
return buf;
hex = buf;
for (i = 0; i < srclen; i++) {
sprintf(hex, "%2.2x", *src++);
hex += 2;
}
return buf;
}
static int
nfsd4_umh_cltrack_init(struct net __attribute__((unused)) *net)
{
return nfsd4_umh_cltrack_upcall("init", NULL, NULL);
}
static void
nfsd4_umh_cltrack_create(struct nfs4_client *clp)
{
char *hexid;
hexid = bin_to_hex_dup(clp->cl_name.data, clp->cl_name.len);
if (!hexid) {
dprintk("%s: can't allocate memory for upcall!\n", __func__);
return;
}
nfsd4_umh_cltrack_upcall("create", hexid, NULL);
kfree(hexid);
}
static void
nfsd4_umh_cltrack_remove(struct nfs4_client *clp)
{
char *hexid;
hexid = bin_to_hex_dup(clp->cl_name.data, clp->cl_name.len);
if (!hexid) {
dprintk("%s: can't allocate memory for upcall!\n", __func__);
return;
}
nfsd4_umh_cltrack_upcall("remove", hexid, NULL);
kfree(hexid);
}
static int
nfsd4_umh_cltrack_check(struct nfs4_client *clp)
{
int ret;
char *hexid, *legacy;
hexid = bin_to_hex_dup(clp->cl_name.data, clp->cl_name.len);
if (!hexid) {
dprintk("%s: can't allocate memory for upcall!\n", __func__);
return -ENOMEM;
}
legacy = nfsd4_cltrack_legacy_recdir(&clp->cl_name);
ret = nfsd4_umh_cltrack_upcall("check", hexid, legacy);
kfree(legacy);
kfree(hexid);
return ret;
}
static void
nfsd4_umh_cltrack_grace_done(struct nfsd_net __attribute__((unused)) *nn,
time_t boot_time)
{
char *legacy;
char timestr[22]; /* FIXME: better way to determine max size? */
sprintf(timestr, "%ld", boot_time);
legacy = nfsd4_cltrack_legacy_topdir();
nfsd4_umh_cltrack_upcall("gracedone", timestr, legacy);
kfree(legacy);
}
static struct nfsd4_client_tracking_ops nfsd4_umh_tracking_ops = {
.init = nfsd4_umh_cltrack_init,
.exit = NULL,
.create = nfsd4_umh_cltrack_create,
.remove = nfsd4_umh_cltrack_remove,
.check = nfsd4_umh_cltrack_check,
.grace_done = nfsd4_umh_cltrack_grace_done,
};
int
nfsd4_client_tracking_init(struct net *net)
{
int status;
struct path path;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
if (!client_tracking_ops) {
client_tracking_ops = &nfsd4_cld_tracking_ops;
status = kern_path(nfs4_recoverydir(), LOOKUP_FOLLOW, &path);
if (!status) {
if (S_ISDIR(path.dentry->d_inode->i_mode))
client_tracking_ops =
&nfsd4_legacy_tracking_ops;
path_put(&path);
}
/* just run the init if it the method is already decided */
if (nn->client_tracking_ops)
goto do_init;
/*
* First, try a UMH upcall. It should succeed or fail quickly, so
* there's little harm in trying that first.
*/
nn->client_tracking_ops = &nfsd4_umh_tracking_ops;
status = nn->client_tracking_ops->init(net);
if (!status)
return status;
/*
* See if the recoverydir exists and is a directory. If it is,
* then use the legacy ops.
*/
nn->client_tracking_ops = &nfsd4_legacy_tracking_ops;
status = kern_path(nfs4_recoverydir(), LOOKUP_FOLLOW, &path);
if (!status) {
status = S_ISDIR(path.dentry->d_inode->i_mode);
path_put(&path);
if (status)
goto do_init;
}
status = client_tracking_ops->init(net);
/* Finally, try to use nfsdcld */
nn->client_tracking_ops = &nfsd4_cld_tracking_ops;
printk(KERN_WARNING "NFSD: the nfsdcld client tracking upcall will be "
"removed in 3.10. Please transition to using "
"nfsdcltrack.\n");
do_init:
status = nn->client_tracking_ops->init(net);
if (status) {
printk(KERN_WARNING "NFSD: Unable to initialize client "
"recovery tracking! (%d)\n", status);
client_tracking_ops = NULL;
nn->client_tracking_ops = NULL;
}
return status;
}
@ -955,40 +1307,49 @@ nfsd4_client_tracking_init(struct net *net)
void
nfsd4_client_tracking_exit(struct net *net)
{
if (client_tracking_ops) {
client_tracking_ops->exit(net);
client_tracking_ops = NULL;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
if (nn->client_tracking_ops) {
if (nn->client_tracking_ops->exit)
nn->client_tracking_ops->exit(net);
nn->client_tracking_ops = NULL;
}
}
void
nfsd4_client_record_create(struct nfs4_client *clp)
{
if (client_tracking_ops)
client_tracking_ops->create(clp);
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
if (nn->client_tracking_ops)
nn->client_tracking_ops->create(clp);
}
void
nfsd4_client_record_remove(struct nfs4_client *clp)
{
if (client_tracking_ops)
client_tracking_ops->remove(clp);
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
if (nn->client_tracking_ops)
nn->client_tracking_ops->remove(clp);
}
int
nfsd4_client_record_check(struct nfs4_client *clp)
{
if (client_tracking_ops)
return client_tracking_ops->check(clp);
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
if (nn->client_tracking_ops)
return nn->client_tracking_ops->check(clp);
return -EOPNOTSUPP;
}
void
nfsd4_record_grace_done(struct net *net, time_t boot_time)
nfsd4_record_grace_done(struct nfsd_net *nn, time_t boot_time)
{
if (client_tracking_ops)
client_tracking_ops->grace_done(net, boot_time);
if (nn->client_tracking_ops)
nn->client_tracking_ops->grace_done(nn, boot_time);
}
static int

1055
fs/nfsd/nfs4state.c
View File

File diff suppressed because it is too large Load Diff

324
fs/nfsd/nfs4xdr.c
View File

@ -53,6 +53,7 @@
#include "vfs.h"
#include "state.h"
#include "cache.h"
#include "netns.h"
#define NFSDDBG_FACILITY NFSDDBG_XDR
@ -65,17 +66,17 @@
#define NFS4_REFERRAL_FSID_MINOR 0x8000000ULL
static __be32
check_filename(char *str, int len, __be32 err)
check_filename(char *str, int len)
{
int i;
if (len == 0)
return nfserr_inval;
if (isdotent(str, len))
return err;
return nfserr_badname;
for (i = 0; i < len; i++)
if (str[i] == '/')
return err;
return nfserr_badname;
return 0;
}
@ -422,6 +423,86 @@ nfsd4_decode_access(struct nfsd4_compoundargs *argp, struct nfsd4_access *access
DECODE_TAIL;
}
static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_cb_sec *cbs)
{
DECODE_HEAD;
u32 dummy, uid, gid;
char *machine_name;
int i;
int nr_secflavs;
/* callback_sec_params4 */
READ_BUF(4);
READ32(nr_secflavs);
cbs->flavor = (u32)(-1);
for (i = 0; i < nr_secflavs; ++i) {
READ_BUF(4);
READ32(dummy);
switch (dummy) {
case RPC_AUTH_NULL:
/* Nothing to read */
if (cbs->flavor == (u32)(-1))
cbs->flavor = RPC_AUTH_NULL;
break;
case RPC_AUTH_UNIX:
READ_BUF(8);
/* stamp */
READ32(dummy);
/* machine name */
READ32(dummy);
READ_BUF(dummy);
SAVEMEM(machine_name, dummy);
/* uid, gid */
READ_BUF(8);
READ32(uid);
READ32(gid);
/* more gids */
READ_BUF(4);
READ32(dummy);
READ_BUF(dummy * 4);
if (cbs->flavor == (u32)(-1)) {
cbs->uid = uid;
cbs->gid = gid;
cbs->flavor = RPC_AUTH_UNIX;
}
break;
case RPC_AUTH_GSS:
dprintk("RPC_AUTH_GSS callback secflavor "
"not supported!\n");
READ_BUF(8);
/* gcbp_service */
READ32(dummy);
/* gcbp_handle_from_server */
READ32(dummy);
READ_BUF(dummy);
p += XDR_QUADLEN(dummy);
/* gcbp_handle_from_client */
READ_BUF(4);
READ32(dummy);
READ_BUF(dummy);
break;
default:
dprintk("Illegal callback secflavor\n");
return nfserr_inval;
}
}
DECODE_TAIL;
}
static __be32 nfsd4_decode_backchannel_ctl(struct nfsd4_compoundargs *argp, struct nfsd4_backchannel_ctl *bc)
{
DECODE_HEAD;
READ_BUF(4);
READ32(bc->bc_cb_program);
nfsd4_decode_cb_sec(argp, &bc->bc_cb_sec);
DECODE_TAIL;
}
static __be32 nfsd4_decode_bind_conn_to_session(struct nfsd4_compoundargs *argp, struct nfsd4_bind_conn_to_session *bcts)
{
DECODE_HEAD;
@ -490,7 +571,7 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create
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)))
if ((status = check_filename(create->cr_name, create->cr_namelen)))
return status;
status = nfsd4_decode_fattr(argp, create->cr_bmval, &create->cr_iattr,
@ -522,7 +603,7 @@ nfsd4_decode_link(struct nfsd4_compoundargs *argp, struct nfsd4_link *link)
READ32(link->li_namelen);
READ_BUF(link->li_namelen);
SAVEMEM(link->li_name, link->li_namelen);
if ((status = check_filename(link->li_name, link->li_namelen, nfserr_inval)))
if ((status = check_filename(link->li_name, link->li_namelen)))
return status;
DECODE_TAIL;
@ -616,7 +697,7 @@ nfsd4_decode_lookup(struct nfsd4_compoundargs *argp, struct nfsd4_lookup *lookup
READ32(lookup->lo_len);
READ_BUF(lookup->lo_len);
SAVEMEM(lookup->lo_name, lookup->lo_len);
if ((status = check_filename(lookup->lo_name, lookup->lo_len, nfserr_noent)))
if ((status = check_filename(lookup->lo_name, lookup->lo_len)))
return status;
DECODE_TAIL;
@ -780,7 +861,7 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
READ32(open->op_fname.len);
READ_BUF(open->op_fname.len);
SAVEMEM(open->op_fname.data, open->op_fname.len);
if ((status = check_filename(open->op_fname.data, open->op_fname.len, nfserr_inval)))
if ((status = check_filename(open->op_fname.data, open->op_fname.len)))
return status;
break;
case NFS4_OPEN_CLAIM_PREVIOUS:
@ -795,7 +876,7 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
READ32(open->op_fname.len);
READ_BUF(open->op_fname.len);
SAVEMEM(open->op_fname.data, open->op_fname.len);
if ((status = check_filename(open->op_fname.data, open->op_fname.len, nfserr_inval)))
if ((status = check_filename(open->op_fname.data, open->op_fname.len)))
return status;
break;
case NFS4_OPEN_CLAIM_FH:
@ -907,7 +988,7 @@ nfsd4_decode_remove(struct nfsd4_compoundargs *argp, struct nfsd4_remove *remove
READ32(remove->rm_namelen);
READ_BUF(remove->rm_namelen);
SAVEMEM(remove->rm_name, remove->rm_namelen);
if ((status = check_filename(remove->rm_name, remove->rm_namelen, nfserr_noent)))
if ((status = check_filename(remove->rm_name, remove->rm_namelen)))
return status;
DECODE_TAIL;
@ -925,9 +1006,9 @@ nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename
READ32(rename->rn_tnamelen);
READ_BUF(rename->rn_tnamelen);
SAVEMEM(rename->rn_tname, rename->rn_tnamelen);
if ((status = check_filename(rename->rn_sname, rename->rn_snamelen, nfserr_noent)))
if ((status = check_filename(rename->rn_sname, rename->rn_snamelen)))
return status;
if ((status = check_filename(rename->rn_tname, rename->rn_tnamelen, nfserr_inval)))
if ((status = check_filename(rename->rn_tname, rename->rn_tnamelen)))
return status;
DECODE_TAIL;
@ -954,8 +1035,7 @@ nfsd4_decode_secinfo(struct nfsd4_compoundargs *argp,
READ32(secinfo->si_namelen);
READ_BUF(secinfo->si_namelen);
SAVEMEM(secinfo->si_name, secinfo->si_namelen);
status = check_filename(secinfo->si_name, secinfo->si_namelen,
nfserr_noent);
status = check_filename(secinfo->si_name, secinfo->si_namelen);
if (status)
return status;
DECODE_TAIL;
@ -1026,31 +1106,14 @@ nfsd4_decode_setclientid_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_s
static __be32
nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify)
{
#if 0
struct nfsd4_compoundargs save = {
.p = argp->p,
.end = argp->end,
.rqstp = argp->rqstp,
};
u32 ve_bmval[2];
struct iattr ve_iattr; /* request */
struct nfs4_acl *ve_acl; /* request */
#endif
DECODE_HEAD;
if ((status = nfsd4_decode_bitmap(argp, verify->ve_bmval)))
goto out;
/* For convenience's sake, we compare raw xdr'd attributes in
* nfsd4_proc_verify; however we still decode here just to return
* correct error in case of bad xdr. */
#if 0
status = nfsd4_decode_fattr(ve_bmval, &ve_iattr, &ve_acl);
if (status == nfserr_inval) {
status = nfserrno(status);
goto out;
}
#endif
* nfsd4_proc_verify */
READ_BUF(4);
READ32(verify->ve_attrlen);
READ_BUF(verify->ve_attrlen);
@ -1063,7 +1126,6 @@ static __be32
nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write)
{
int avail;
int v;
int len;
DECODE_HEAD;
@ -1087,27 +1149,26 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write)
__FILE__, __LINE__);
goto xdr_error;
}
argp->rqstp->rq_vec[0].iov_base = p;
argp->rqstp->rq_vec[0].iov_len = avail;
v = 0;
len = write->wr_buflen;
while (len > argp->rqstp->rq_vec[v].iov_len) {
len -= argp->rqstp->rq_vec[v].iov_len;
v++;
argp->rqstp->rq_vec[v].iov_base = page_address(argp->pagelist[0]);
argp->pagelist++;
if (argp->pagelen >= PAGE_SIZE) {
argp->rqstp->rq_vec[v].iov_len = PAGE_SIZE;
argp->pagelen -= PAGE_SIZE;
} else {
argp->rqstp->rq_vec[v].iov_len = argp->pagelen;
argp->pagelen -= len;
}
write->wr_head.iov_base = p;
write->wr_head.iov_len = avail;
WARN_ON(avail != (XDR_QUADLEN(avail) << 2));
write->wr_pagelist = argp->pagelist;
len = XDR_QUADLEN(write->wr_buflen) << 2;
if (len >= avail) {
int pages;
len -= avail;
pages = len >> PAGE_SHIFT;
argp->pagelist += pages;
argp->pagelen -= pages * PAGE_SIZE;
len -= pages * PAGE_SIZE;
argp->p = (__be32 *)page_address(argp->pagelist[0]);
argp->end = argp->p + XDR_QUADLEN(PAGE_SIZE);
}
argp->end = (__be32*) (argp->rqstp->rq_vec[v].iov_base + argp->rqstp->rq_vec[v].iov_len);
argp->p = (__be32*) (argp->rqstp->rq_vec[v].iov_base + (XDR_QUADLEN(len) << 2));
argp->rqstp->rq_vec[v].iov_len = len;
write->wr_vlen = v+1;
argp->p += XDR_QUADLEN(len);
DECODE_TAIL;
}
@ -1237,11 +1298,7 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp,
struct nfsd4_create_session *sess)
{
DECODE_HEAD;
u32 dummy;
char *machine_name;
int i;
int nr_secflavs;
READ_BUF(16);
COPYMEM(&sess->clientid, 8);
@ -1282,58 +1339,9 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp,
goto xdr_error;
}
READ_BUF(8);
READ_BUF(4);
READ32(sess->callback_prog);
/* callback_sec_params4 */
READ32(nr_secflavs);
for (i = 0; i < nr_secflavs; ++i) {
READ_BUF(4);
READ32(dummy);
switch (dummy) {
case RPC_AUTH_NULL:
/* Nothing to read */
break;
case RPC_AUTH_UNIX:
READ_BUF(8);
/* stamp */
READ32(dummy);
/* machine name */
READ32(dummy);
READ_BUF(dummy);
SAVEMEM(machine_name, dummy);
/* uid, gid */
READ_BUF(8);
READ32(sess->uid);
READ32(sess->gid);
/* more gids */
READ_BUF(4);
READ32(dummy);
READ_BUF(dummy * 4);
break;
case RPC_AUTH_GSS:
dprintk("RPC_AUTH_GSS callback secflavor "
"not supported!\n");
READ_BUF(8);
/* gcbp_service */
READ32(dummy);
/* gcbp_handle_from_server */
READ32(dummy);
READ_BUF(dummy);
p += XDR_QUADLEN(dummy);
/* gcbp_handle_from_client */
READ_BUF(4);
READ32(dummy);
READ_BUF(dummy);
break;
default:
dprintk("Illegal callback secflavor\n");
return nfserr_inval;
}
}
nfsd4_decode_cb_sec(argp, &sess->cb_sec);
DECODE_TAIL;
}
@ -1528,7 +1536,7 @@ static nfsd4_dec nfsd41_dec_ops[] = {
[OP_RELEASE_LOCKOWNER] = (nfsd4_dec)nfsd4_decode_notsupp,
/* new operations for NFSv4.1 */
[OP_BACKCHANNEL_CTL] = (nfsd4_dec)nfsd4_decode_notsupp,
[OP_BACKCHANNEL_CTL] = (nfsd4_dec)nfsd4_decode_backchannel_ctl,
[OP_BIND_CONN_TO_SESSION]= (nfsd4_dec)nfsd4_decode_bind_conn_to_session,
[OP_EXCHANGE_ID] = (nfsd4_dec)nfsd4_decode_exchange_id,
[OP_CREATE_SESSION] = (nfsd4_dec)nfsd4_decode_create_session,
@ -1568,12 +1576,6 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
bool cachethis = false;
int i;
/*
* XXX: According to spec, we should check the tag
* for UTF-8 compliance. I'm postponing this for
* now because it seems that some clients do use
* binary tags.
*/
READ_BUF(4);
READ32(argp->taglen);
READ_BUF(argp->taglen + 8);
@ -1603,38 +1605,8 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
op = &argp->ops[i];
op->replay = NULL;
/*
* We can't use READ_BUF() here because we need to handle
* a missing opcode as an OP_WRITE + 1. So we need to check
* to see if we're truly at the end of our buffer or if there
* is another page we need to flip to.
*/
if (argp->p == argp->end) {
if (argp->pagelen < 4) {
/* There isn't an opcode still on the wire */
op->opnum = OP_WRITE + 1;
op->status = nfserr_bad_xdr;
argp->opcnt = i+1;
break;
}
/*
* False alarm. We just hit a page boundary, but there
* is still data available. Move pointer across page
* boundary. *snip from READ_BUF*
*/
argp->p = page_address(argp->pagelist[0]);
argp->pagelist++;
if (argp->pagelen < PAGE_SIZE) {
argp->end = argp->p + (argp->pagelen>>2);
argp->pagelen = 0;
} else {
argp->end = argp->p + (PAGE_SIZE>>2);
argp->pagelen -= PAGE_SIZE;
}
}
op->opnum = ntohl(*argp->p++);
READ_BUF(4);
READ32(op->opnum);
if (op->opnum >= FIRST_NFS4_OP && op->opnum <= LAST_NFS4_OP)
op->status = ops->decoders[op->opnum](argp, &op->u);
@ -2014,6 +1986,22 @@ static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *rdattr_err)
return 0;
}
static int get_parent_attributes(struct svc_export *exp, struct kstat *stat)
{
struct path path = exp->ex_path;
int err;
path_get(&path);
while (follow_up(&path)) {
if (path.dentry != path.mnt->mnt_root)
break;
}
err = vfs_getattr(path.mnt, path.dentry, stat);
path_put(&path);
return err;
}
/*
* Note: @fhp can be NULL; in this case, we might have to compose the filehandle
* ourselves.
@ -2048,6 +2036,7 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
.mnt = exp->ex_path.mnt,
.dentry = dentry,
};
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
BUG_ON(bmval1 & NFSD_WRITEONLY_ATTRS_WORD1);
BUG_ON(bmval0 & ~nfsd_suppattrs0(minorversion));
@ -2208,7 +2197,7 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
if (bmval0 & FATTR4_WORD0_LEASE_TIME) {
if ((buflen -= 4) < 0)
goto out_resource;
WRITE32(nfsd4_lease);
WRITE32(nn->nfsd4_lease);
}
if (bmval0 & FATTR4_WORD0_RDATTR_ERROR) {
if ((buflen -= 4) < 0)
@ -2430,18 +2419,8 @@ out_acl:
* and this is the root of a cross-mounted filesystem.
*/
if (ignore_crossmnt == 0 &&
dentry == exp->ex_path.mnt->mnt_root) {
struct path path = exp->ex_path;
path_get(&path);
while (follow_up(&path)) {
if (path.dentry != path.mnt->mnt_root)
break;
}
err = vfs_getattr(path.mnt, path.dentry, &stat);
path_put(&path);
if (err)
goto out_nfserr;
}
dentry == exp->ex_path.mnt->mnt_root)
get_parent_attributes(exp, &stat);
WRITE64(stat.ino);
}
if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) {
@ -2927,7 +2906,8 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_read *read)
{
u32 eof;
int v, pn;
int v;
struct page *page;
unsigned long maxcount;
long len;
__be32 *p;
@ -2946,11 +2926,15 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
len = maxcount;
v = 0;
while (len > 0) {
pn = resp->rqstp->rq_resused++;
resp->rqstp->rq_vec[v].iov_base =
page_address(resp->rqstp->rq_respages[pn]);
page = *(resp->rqstp->rq_next_page);
if (!page) { /* ran out of pages */
maxcount -= len;
break;
}
resp->rqstp->rq_vec[v].iov_base = page_address(page);
resp->rqstp->rq_vec[v].iov_len =
len < PAGE_SIZE ? len : PAGE_SIZE;
resp->rqstp->rq_next_page++;
v++;
len -= PAGE_SIZE;
}
@ -2996,8 +2980,10 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd
return nfserr;
if (resp->xbuf->page_len)
return nfserr_resource;
if (!*resp->rqstp->rq_next_page)
return nfserr_resource;
page = page_address(resp->rqstp->rq_respages[resp->rqstp->rq_resused++]);
page = page_address(*(resp->rqstp->rq_next_page++));
maxcount = PAGE_SIZE;
RESERVE_SPACE(4);
@ -3045,6 +3031,8 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
return nfserr;
if (resp->xbuf->page_len)
return nfserr_resource;
if (!*resp->rqstp->rq_next_page)
return nfserr_resource;
RESERVE_SPACE(NFS4_VERIFIER_SIZE);
savep = p;
@ -3071,7 +3059,7 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
goto err_no_verf;
}
page = page_address(resp->rqstp->rq_respages[resp->rqstp->rq_resused++]);
page = page_address(*(resp->rqstp->rq_next_page++));
readdir->common.err = 0;
readdir->buflen = maxcount;
readdir->buffer = page;
@ -3094,8 +3082,8 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
p = readdir->buffer;
*p++ = 0; /* no more entries */
*p++ = htonl(readdir->common.err == nfserr_eof);
resp->xbuf->page_len = ((char*)p) - (char*)page_address(
resp->rqstp->rq_respages[resp->rqstp->rq_resused-1]);
resp->xbuf->page_len = ((char*)p) -
(char*)page_address(*(resp->rqstp->rq_next_page-1));
/* Use rest of head for padding and remaining ops: */
resp->xbuf->tail[0].iov_base = tailbase;

100
fs/nfsd/nfsctl.c
View File

@ -19,7 +19,7 @@
#include "idmap.h"
#include "nfsd.h"
#include "cache.h"
#include "fault_inject.h"
#include "state.h"
#include "netns.h"
/*
@ -186,9 +186,6 @@ static struct file_operations supported_enctypes_ops = {
};
#endif /* CONFIG_SUNRPC_GSS or CONFIG_SUNRPC_GSS_MODULE */
extern int nfsd_pool_stats_open(struct inode *inode, struct file *file);
extern int nfsd_pool_stats_release(struct inode *inode, struct file *file);
static const struct file_operations pool_stats_operations = {
.open = nfsd_pool_stats_open,
.read = seq_read,
@ -399,6 +396,8 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size)
{
char *mesg = buf;
int rv;
struct net *net = &init_net;
if (size > 0) {
int newthreads;
rv = get_int(&mesg, &newthreads);
@ -406,11 +405,11 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size)
return rv;
if (newthreads < 0)
return -EINVAL;
rv = nfsd_svc(newthreads);
rv = nfsd_svc(newthreads, net);
if (rv < 0)
return rv;
} else
rv = nfsd_nrthreads();
rv = nfsd_nrthreads(net);
return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%d\n", rv);
}
@ -448,9 +447,10 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size)
int len;
int npools;
int *nthreads;
struct net *net = &init_net;
mutex_lock(&nfsd_mutex);
npools = nfsd_nrpools();
npools = nfsd_nrpools(net);
if (npools == 0) {
/*
* NFS is shut down. The admin can start it by
@ -478,12 +478,12 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size)
if (nthreads[i] < 0)
goto out_free;
}
rv = nfsd_set_nrthreads(i, nthreads);
rv = nfsd_set_nrthreads(i, nthreads, net);
if (rv)
goto out_free;
}
rv = nfsd_get_nrthreads(npools, nthreads);
rv = nfsd_get_nrthreads(npools, nthreads, net);
if (rv)
goto out_free;
@ -510,11 +510,13 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
unsigned minor;
ssize_t tlen = 0;
char *sep;
struct net *net = &init_net;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
if (size>0) {
if (nfsd_serv)
if (nn->nfsd_serv)
/* Cannot change versions without updating
* nfsd_serv->sv_xdrsize, and reallocing
* nn->nfsd_serv->sv_xdrsize, and reallocing
* rq_argp and rq_resp
*/
return -EBUSY;
@ -645,11 +647,13 @@ static ssize_t write_versions(struct file *file, char *buf, size_t size)
* Zero-length write. Return a list of NFSD's current listener
* transports.
*/
static ssize_t __write_ports_names(char *buf)
static ssize_t __write_ports_names(char *buf, struct net *net)
{
if (nfsd_serv == NULL)
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
if (nn->nfsd_serv == NULL)
return 0;
return svc_xprt_names(nfsd_serv, buf, SIMPLE_TRANSACTION_LIMIT);
return svc_xprt_names(nn->nfsd_serv, buf, SIMPLE_TRANSACTION_LIMIT);
}
/*
@ -657,28 +661,28 @@ static ssize_t __write_ports_names(char *buf)
* a socket of a supported family/protocol, and we use it as an
* nfsd listener.
*/
static ssize_t __write_ports_addfd(char *buf)
static ssize_t __write_ports_addfd(char *buf, struct net *net)
{
char *mesg = buf;
int fd, err;
struct net *net = &init_net;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
err = get_int(&mesg, &fd);
if (err != 0 || fd < 0)
return -EINVAL;
err = nfsd_create_serv();
err = nfsd_create_serv(net);
if (err != 0)
return err;
err = svc_addsock(nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT);
err = svc_addsock(nn->nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT);
if (err < 0) {
nfsd_destroy(net);
return err;
}
/* Decrease the count, but don't shut down the service */
nfsd_serv->sv_nrthreads--;
nn->nfsd_serv->sv_nrthreads--;
return err;
}
@ -686,12 +690,12 @@ static ssize_t __write_ports_addfd(char *buf)
* A transport listener is added by writing it's transport name and
* a port number.
*/
static ssize_t __write_ports_addxprt(char *buf)
static ssize_t __write_ports_addxprt(char *buf, struct net *net)
{
char transport[16];
struct svc_xprt *xprt;
int port, err;
struct net *net = &init_net;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
if (sscanf(buf, "%15s %5u", transport, &port) != 2)
return -EINVAL;
@ -699,25 +703,25 @@ static ssize_t __write_ports_addxprt(char *buf)
if (port < 1 || port > USHRT_MAX)
return -EINVAL;
err = nfsd_create_serv();
err = nfsd_create_serv(net);
if (err != 0)
return err;
err = svc_create_xprt(nfsd_serv, transport, net,
err = svc_create_xprt(nn->nfsd_serv, transport, net,
PF_INET, port, SVC_SOCK_ANONYMOUS);
if (err < 0)
goto out_err;
err = svc_create_xprt(nfsd_serv, transport, net,
err = svc_create_xprt(nn->nfsd_serv, transport, net,
PF_INET6, port, SVC_SOCK_ANONYMOUS);
if (err < 0 && err != -EAFNOSUPPORT)
goto out_close;
/* Decrease the count, but don't shut down the service */
nfsd_serv->sv_nrthreads--;
nn->nfsd_serv->sv_nrthreads--;
return 0;
out_close:
xprt = svc_find_xprt(nfsd_serv, transport, net, PF_INET, port);
xprt = svc_find_xprt(nn->nfsd_serv, transport, net, PF_INET, port);
if (xprt != NULL) {
svc_close_xprt(xprt);
svc_xprt_put(xprt);
@ -727,16 +731,17 @@ out_err:
return err;
}
static ssize_t __write_ports(struct file *file, char *buf, size_t size)
static ssize_t __write_ports(struct file *file, char *buf, size_t size,
struct net *net)
{
if (size == 0)
return __write_ports_names(buf);
return __write_ports_names(buf, net);
if (isdigit(buf[0]))
return __write_ports_addfd(buf);
return __write_ports_addfd(buf, net);
if (isalpha(buf[0]))
return __write_ports_addxprt(buf);
return __write_ports_addxprt(buf, net);
return -EINVAL;
}
@ -787,9 +792,10 @@ static ssize_t __write_ports(struct file *file, char *buf, size_t size)
static ssize_t write_ports(struct file *file, char *buf, size_t size)
{
ssize_t rv;
struct net *net = &init_net;
mutex_lock(&nfsd_mutex);
rv = __write_ports(file, buf, size);
rv = __write_ports(file, buf, size, net);
mutex_unlock(&nfsd_mutex);
return rv;
}
@ -821,6 +827,9 @@ int nfsd_max_blksize;
static ssize_t write_maxblksize(struct file *file, char *buf, size_t size)
{
char *mesg = buf;
struct net *net = &init_net;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
if (size > 0) {
int bsize;
int rv = get_int(&mesg, &bsize);
@ -835,7 +844,7 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size)
bsize = NFSSVC_MAXBLKSIZE;
bsize &= ~(1024-1);
mutex_lock(&nfsd_mutex);
if (nfsd_serv) {
if (nn->nfsd_serv) {
mutex_unlock(&nfsd_mutex);
return -EBUSY;
}
@ -848,13 +857,14 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size)
}
#ifdef CONFIG_NFSD_V4
static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size, time_t *time)
static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size,
time_t *time, struct nfsd_net *nn)
{
char *mesg = buf;
int rv, i;
if (size > 0) {
if (nfsd_serv)
if (nn->nfsd_serv)
return -EBUSY;
rv = get_int(&mesg, &i);
if (rv)
@ -879,12 +889,13 @@ static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size, tim
return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%ld\n", *time);
}
static ssize_t nfsd4_write_time(struct file *file, char *buf, size_t size, time_t *time)
static ssize_t nfsd4_write_time(struct file *file, char *buf, size_t size,
time_t *time, struct nfsd_net *nn)
{
ssize_t rv;
mutex_lock(&nfsd_mutex);
rv = __nfsd4_write_time(file, buf, size, time);
rv = __nfsd4_write_time(file, buf, size, time, nn);
mutex_unlock(&nfsd_mutex);
return rv;
}
@ -912,7 +923,8 @@ static ssize_t nfsd4_write_time(struct file *file, char *buf, size_t size, time_
*/
static ssize_t write_leasetime(struct file *file, char *buf, size_t size)
{
return nfsd4_write_time(file, buf, size, &nfsd4_lease);
struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
return nfsd4_write_time(file, buf, size, &nn->nfsd4_lease, nn);
}
/**
@ -927,17 +939,19 @@ static ssize_t write_leasetime(struct file *file, char *buf, size_t size)
*/
static ssize_t write_gracetime(struct file *file, char *buf, size_t size)
{
return nfsd4_write_time(file, buf, size, &nfsd4_grace);
struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
return nfsd4_write_time(file, buf, size, &nn->nfsd4_grace, nn);
}
static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size)
static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size,
struct nfsd_net *nn)
{
char *mesg = buf;
char *recdir;
int len, status;
if (size > 0) {
if (nfsd_serv)
if (nn->nfsd_serv)
return -EBUSY;
if (size > PATH_MAX || buf[size-1] != '\n')
return -EINVAL;
@ -981,9 +995,10 @@ static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size)
static ssize_t write_recoverydir(struct file *file, char *buf, size_t size)
{
ssize_t rv;
struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
mutex_lock(&nfsd_mutex);
rv = __write_recoverydir(file, buf, size);
rv = __write_recoverydir(file, buf, size, nn);
mutex_unlock(&nfsd_mutex);
return rv;
}
@ -1063,6 +1078,7 @@ int nfsd_net_id;
static __net_init int nfsd_init_net(struct net *net)
{
int retval;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
retval = nfsd_export_init(net);
if (retval)
@ -1070,6 +1086,8 @@ static __net_init int nfsd_init_net(struct net *net)
retval = nfsd_idmap_init(net);
if (retval)
goto out_idmap_error;
nn->nfsd4_lease = 90; /* default lease time */
nn->nfsd4_grace = 90;
return 0;
out_idmap_error:

36
fs/nfsd/nfsd.h
View File

@ -55,7 +55,6 @@ extern struct svc_version nfsd_version2, nfsd_version3,
nfsd_version4;
extern u32 nfsd_supported_minorversion;
extern struct mutex nfsd_mutex;
extern struct svc_serv *nfsd_serv;
extern spinlock_t nfsd_drc_lock;
extern unsigned int nfsd_drc_max_mem;
extern unsigned int nfsd_drc_mem_used;
@ -65,26 +64,17 @@ extern const struct seq_operations nfs_exports_op;
/*
* Function prototypes.
*/
int nfsd_svc(int nrservs);
int nfsd_svc(int nrservs, struct net *net);
int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp);
int nfsd_nrthreads(void);
int nfsd_nrpools(void);
int nfsd_get_nrthreads(int n, int *);
int nfsd_set_nrthreads(int n, int *);
int nfsd_nrthreads(struct net *);
int nfsd_nrpools(struct net *);
int nfsd_get_nrthreads(int n, int *, struct net *);
int nfsd_set_nrthreads(int n, int *, struct net *);
int nfsd_pool_stats_open(struct inode *, struct file *);
int nfsd_pool_stats_release(struct inode *, struct file *);
static inline void nfsd_destroy(struct net *net)
{
int destroy = (nfsd_serv->sv_nrthreads == 1);
if (destroy)
svc_shutdown_net(nfsd_serv, net);
svc_destroy(nfsd_serv);
if (destroy)
nfsd_serv = NULL;
}
void nfsd_destroy(struct net *net);
#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
#ifdef CONFIG_NFSD_V2_ACL
@ -103,7 +93,7 @@ enum vers_op {NFSD_SET, NFSD_CLEAR, NFSD_TEST, NFSD_AVAIL };
int nfsd_vers(int vers, enum vers_op change);
int nfsd_minorversion(u32 minorversion, enum vers_op change);
void nfsd_reset_versions(void);
int nfsd_create_serv(void);
int nfsd_create_serv(struct net *net);
extern int nfsd_max_blksize;
@ -121,7 +111,9 @@ void nfs4_state_init(void);
int nfsd4_init_slabs(void);
void nfsd4_free_slabs(void);
int nfs4_state_start(void);
int nfs4_state_start_net(struct net *net);
void nfs4_state_shutdown(void);
void nfs4_state_shutdown_net(struct net *net);
void nfs4_reset_lease(time_t leasetime);
int nfs4_reset_recoverydir(char *recdir);
char * nfs4_recoverydir(void);
@ -130,7 +122,9 @@ static inline void nfs4_state_init(void) { }
static inline int nfsd4_init_slabs(void) { return 0; }
static inline void nfsd4_free_slabs(void) { }
static inline int nfs4_state_start(void) { return 0; }
static inline int nfs4_state_start_net(struct net *net) { return 0; }
static inline void nfs4_state_shutdown(void) { }
static inline void nfs4_state_shutdown_net(struct net *net) { }
static inline void nfs4_reset_lease(time_t leasetime) { }
static inline int nfs4_reset_recoverydir(char *recdir) { return 0; }
static inline char * nfs4_recoverydir(void) {return NULL; }
@ -265,16 +259,8 @@ void nfsd_lockd_shutdown(void);
/* Check for dir entries '.' and '..' */
#define isdotent(n, l) (l < 3 && n[0] == '.' && (l == 1 || n[1] == '.'))
/*
* Time of server startup
*/
extern struct timeval nfssvc_boot;
#ifdef CONFIG_NFSD_V4
extern time_t nfsd4_lease;
extern time_t nfsd4_grace;
/* before processing a COMPOUND operation, we have to check that there
* is enough space in the buffer for XDR encode to succeed. otherwise,
* we might process an operation with side effects, and be unable to

4
fs/nfsd/nfsfh.c
View File

@ -572,7 +572,7 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
if (inode)
_fh_update(fhp, exp, dentry);
if (fhp->fh_handle.fh_fileid_type == 255) {
if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) {
fh_put(fhp);
return nfserr_opnotsupp;
}
@ -603,7 +603,7 @@ fh_update(struct svc_fh *fhp)
goto out;
_fh_update(fhp, fhp->fh_export, dentry);
if (fhp->fh_handle.fh_fileid_type == 255)
if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID)
return nfserr_opnotsupp;
}
out:

207
fs/nfsd/nfssvc.c
View File

@ -11,7 +11,6 @@
#include <linux/module.h>
#include <linux/fs_struct.h>
#include <linux/swap.h>
#include <linux/nsproxy.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/svcsock.h>
@ -22,19 +21,19 @@
#include "nfsd.h"
#include "cache.h"
#include "vfs.h"
#include "netns.h"
#define NFSDDBG_FACILITY NFSDDBG_SVC
extern struct svc_program nfsd_program;
static int nfsd(void *vrqstp);
struct timeval nfssvc_boot;
/*
* nfsd_mutex protects nfsd_serv -- both the pointer itself and the members
* nfsd_mutex protects nn->nfsd_serv -- both the pointer itself and the members
* of the svc_serv struct. In particular, ->sv_nrthreads but also to some
* extent ->sv_temp_socks and ->sv_permsocks. It also protects nfsdstats.th_cnt
*
* If (out side the lock) nfsd_serv is non-NULL, then it must point to a
* If (out side the lock) nn->nfsd_serv is non-NULL, then it must point to a
* properly initialised 'struct svc_serv' with ->sv_nrthreads > 0. That number
* of nfsd threads must exist and each must listed in ->sp_all_threads in each
* entry of ->sv_pools[].
@ -52,7 +51,6 @@ struct timeval nfssvc_boot;
* nfsd_versions
*/
DEFINE_MUTEX(nfsd_mutex);
struct svc_serv *nfsd_serv;
/*
* nfsd_drc_lock protects nfsd_drc_max_pages and nfsd_drc_pages_used.
@ -173,28 +171,32 @@ int nfsd_minorversion(u32 minorversion, enum vers_op change)
*/
#define NFSD_MAXSERVS 8192
int nfsd_nrthreads(void)
int nfsd_nrthreads(struct net *net)
{
int rv = 0;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
mutex_lock(&nfsd_mutex);
if (nfsd_serv)
rv = nfsd_serv->sv_nrthreads;
if (nn->nfsd_serv)
rv = nn->nfsd_serv->sv_nrthreads;
mutex_unlock(&nfsd_mutex);
return rv;
}
static int nfsd_init_socks(void)
static int nfsd_init_socks(struct net *net)
{
int error;
if (!list_empty(&nfsd_serv->sv_permsocks))
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
if (!list_empty(&nn->nfsd_serv->sv_permsocks))
return 0;
error = svc_create_xprt(nfsd_serv, "udp", &init_net, PF_INET, NFS_PORT,
error = svc_create_xprt(nn->nfsd_serv, "udp", net, PF_INET, NFS_PORT,
SVC_SOCK_DEFAULTS);
if (error < 0)
return error;
error = svc_create_xprt(nfsd_serv, "tcp", &init_net, PF_INET, NFS_PORT,
error = svc_create_xprt(nn->nfsd_serv, "tcp", net, PF_INET, NFS_PORT,
SVC_SOCK_DEFAULTS);
if (error < 0)
return error;
@ -202,14 +204,15 @@ static int nfsd_init_socks(void)
return 0;
}
static bool nfsd_up = false;
static int nfsd_users = 0;
static int nfsd_startup(int nrservs)
static int nfsd_startup_generic(int nrservs)
{
int ret;
if (nfsd_up)
if (nfsd_users++)
return 0;
/*
* Readahead param cache - will no-op if it already exists.
* (Note therefore results will be suboptimal if number of
@ -218,43 +221,79 @@ static int nfsd_startup(int nrservs)
ret = nfsd_racache_init(2*nrservs);
if (ret)
return ret;
ret = nfsd_init_socks();
if (ret)
goto out_racache;
ret = lockd_up(&init_net);
if (ret)
goto out_racache;
ret = nfs4_state_start();
if (ret)
goto out_lockd;
nfsd_up = true;
goto out_racache;
return 0;
out_lockd:
lockd_down(&init_net);
out_racache:
nfsd_racache_shutdown();
return ret;
}
static void nfsd_shutdown(void)
static void nfsd_shutdown_generic(void)
{
if (--nfsd_users)
return;
nfs4_state_shutdown();
nfsd_racache_shutdown();
}
static int nfsd_startup_net(int nrservs, struct net *net)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
int ret;
if (nn->nfsd_net_up)
return 0;
ret = nfsd_startup_generic(nrservs);
if (ret)
return ret;
ret = nfsd_init_socks(net);
if (ret)
goto out_socks;
ret = lockd_up(net);
if (ret)
goto out_socks;
ret = nfs4_state_start_net(net);
if (ret)
goto out_lockd;
nn->nfsd_net_up = true;
return 0;
out_lockd:
lockd_down(net);
out_socks:
nfsd_shutdown_generic();
return ret;
}
static void nfsd_shutdown_net(struct net *net)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
nfs4_state_shutdown_net(net);
lockd_down(net);
nn->nfsd_net_up = false;
nfsd_shutdown_generic();
}
static void nfsd_last_thread(struct svc_serv *serv, struct net *net)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
/*
* write_ports can create the server without actually starting
* any threads--if we get shut down before any threads are
* started, then nfsd_last_thread will be run before any of this
* other initialization has been done.
*/
if (!nfsd_up)
if (!nn->nfsd_net_up)
return;
nfs4_state_shutdown();
lockd_down(&init_net);
nfsd_racache_shutdown();
nfsd_up = false;
}
static void nfsd_last_thread(struct svc_serv *serv, struct net *net)
{
nfsd_shutdown();
nfsd_shutdown_net(net);
svc_rpcb_cleanup(serv, net);
@ -327,69 +366,84 @@ static int nfsd_get_default_max_blksize(void)
return ret;
}
int nfsd_create_serv(void)
int nfsd_create_serv(struct net *net)
{
int error;
struct net *net = current->nsproxy->net_ns;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
WARN_ON(!mutex_is_locked(&nfsd_mutex));
if (nfsd_serv) {
svc_get(nfsd_serv);
if (nn->nfsd_serv) {
svc_get(nn->nfsd_serv);
return 0;
}
if (nfsd_max_blksize == 0)
nfsd_max_blksize = nfsd_get_default_max_blksize();
nfsd_reset_versions();
nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize,
nn->nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize,
nfsd_last_thread, nfsd, THIS_MODULE);
if (nfsd_serv == NULL)
if (nn->nfsd_serv == NULL)
return -ENOMEM;
error = svc_bind(nfsd_serv, net);
error = svc_bind(nn->nfsd_serv, net);
if (error < 0) {
svc_destroy(nfsd_serv);
svc_destroy(nn->nfsd_serv);
return error;
}
set_max_drc();
do_gettimeofday(&nfssvc_boot); /* record boot time */
do_gettimeofday(&nn->nfssvc_boot); /* record boot time */
return 0;
}
int nfsd_nrpools(void)
int nfsd_nrpools(struct net *net)
{
if (nfsd_serv == NULL)
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
if (nn->nfsd_serv == NULL)
return 0;
else
return nfsd_serv->sv_nrpools;
return nn->nfsd_serv->sv_nrpools;
}
int nfsd_get_nrthreads(int n, int *nthreads)
int nfsd_get_nrthreads(int n, int *nthreads, struct net *net)
{
int i = 0;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
if (nfsd_serv != NULL) {
for (i = 0; i < nfsd_serv->sv_nrpools && i < n; i++)
nthreads[i] = nfsd_serv->sv_pools[i].sp_nrthreads;
if (nn->nfsd_serv != NULL) {
for (i = 0; i < nn->nfsd_serv->sv_nrpools && i < n; i++)
nthreads[i] = nn->nfsd_serv->sv_pools[i].sp_nrthreads;
}
return 0;
}
int nfsd_set_nrthreads(int n, int *nthreads)
void nfsd_destroy(struct net *net)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
int destroy = (nn->nfsd_serv->sv_nrthreads == 1);
if (destroy)
svc_shutdown_net(nn->nfsd_serv, net);
svc_destroy(nn->nfsd_serv);
if (destroy)
nn->nfsd_serv = NULL;
}
int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
{
int i = 0;
int tot = 0;
int err = 0;
struct net *net = &init_net;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
WARN_ON(!mutex_is_locked(&nfsd_mutex));
if (nfsd_serv == NULL || n <= 0)
if (nn->nfsd_serv == NULL || n <= 0)
return 0;
if (n > nfsd_serv->sv_nrpools)
n = nfsd_serv->sv_nrpools;
if (n > nn->nfsd_serv->sv_nrpools)
n = nn->nfsd_serv->sv_nrpools;
/* enforce a global maximum number of threads */
tot = 0;
@ -419,9 +473,9 @@ int nfsd_set_nrthreads(int n, int *nthreads)
nthreads[0] = 1;
/* apply the new numbers */
svc_get(nfsd_serv);
svc_get(nn->nfsd_serv);
for (i = 0; i < n; i++) {
err = svc_set_num_threads(nfsd_serv, &nfsd_serv->sv_pools[i],
err = svc_set_num_threads(nn->nfsd_serv, &nn->nfsd_serv->sv_pools[i],
nthreads[i]);
if (err)
break;
@ -436,11 +490,11 @@ int nfsd_set_nrthreads(int n, int *nthreads)
* this is the first time nrservs is nonzero.
*/
int
nfsd_svc(int nrservs)
nfsd_svc(int nrservs, struct net *net)
{
int error;
bool nfsd_up_before;
struct net *net = &init_net;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
mutex_lock(&nfsd_mutex);
dprintk("nfsd: creating service\n");
@ -449,29 +503,29 @@ nfsd_svc(int nrservs)
if (nrservs > NFSD_MAXSERVS)
nrservs = NFSD_MAXSERVS;
error = 0;
if (nrservs == 0 && nfsd_serv == NULL)
if (nrservs == 0 && nn->nfsd_serv == NULL)
goto out;
error = nfsd_create_serv();
error = nfsd_create_serv(net);
if (error)
goto out;
nfsd_up_before = nfsd_up;
nfsd_up_before = nn->nfsd_net_up;
error = nfsd_startup(nrservs);
error = nfsd_startup_net(nrservs, net);
if (error)
goto out_destroy;
error = svc_set_num_threads(nfsd_serv, NULL, nrservs);
error = svc_set_num_threads(nn->nfsd_serv, NULL, nrservs);
if (error)
goto out_shutdown;
/* We are holding a reference to nfsd_serv which
/* We are holding a reference to nn->nfsd_serv which
* we don't want to count in the return value,
* so subtract 1
*/
error = nfsd_serv->sv_nrthreads - 1;
error = nn->nfsd_serv->sv_nrthreads - 1;
out_shutdown:
if (error < 0 && !nfsd_up_before)
nfsd_shutdown();
nfsd_shutdown_net(net);
out_destroy:
nfsd_destroy(net); /* Release server */
out:
@ -487,6 +541,8 @@ static int
nfsd(void *vrqstp)
{
struct svc_rqst *rqstp = (struct svc_rqst *) vrqstp;
struct svc_xprt *perm_sock = list_entry(rqstp->rq_server->sv_permsocks.next, typeof(struct svc_xprt), xpt_list);
struct net *net = perm_sock->xpt_net;
int err;
/* Lock module and set up kernel thread */
@ -551,7 +607,7 @@ out:
/* Release the thread */
svc_exit_thread(rqstp);
nfsd_destroy(&init_net);
nfsd_destroy(net);
/* Release module */
mutex_unlock(&nfsd_mutex);
@ -640,21 +696,24 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
}
/* Store reply in cache. */
nfsd_cache_update(rqstp, proc->pc_cachetype, statp + 1);
nfsd_cache_update(rqstp, rqstp->rq_cachetype, statp + 1);
return 1;
}
int nfsd_pool_stats_open(struct inode *inode, struct file *file)
{
int ret;
struct net *net = &init_net;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
mutex_lock(&nfsd_mutex);
if (nfsd_serv == NULL) {
if (nn->nfsd_serv == NULL) {
mutex_unlock(&nfsd_mutex);
return -ENODEV;
}
/* bump up the psudo refcount while traversing */
svc_get(nfsd_serv);
ret = svc_pool_stats_open(nfsd_serv, file);
svc_get(nn->nfsd_serv);
ret = svc_pool_stats_open(nn->nfsd_serv, file);
mutex_unlock(&nfsd_mutex);
return ret;
}

11
fs/nfsd/nfsxdr.c
View File

@ -246,7 +246,7 @@ nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd_readargs *args)
{
unsigned int len;
int v,pn;
int v;
if (!(p = decode_fh(p, &args->fh)))
return 0;
@ -262,8 +262,9 @@ nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
*/
v=0;
while (len > 0) {
pn = rqstp->rq_resused++;
rqstp->rq_vec[v].iov_base = page_address(rqstp->rq_respages[pn]);
struct page *p = *(rqstp->rq_next_page++);
rqstp->rq_vec[v].iov_base = page_address(p);
rqstp->rq_vec[v].iov_len = len < PAGE_SIZE?len:PAGE_SIZE;
len -= rqstp->rq_vec[v].iov_len;
v++;
@ -355,7 +356,7 @@ nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readli
{
if (!(p = decode_fh(p, &args->fh)))
return 0;
args->buffer = page_address(rqstp->rq_respages[rqstp->rq_resused++]);
args->buffer = page_address(*(rqstp->rq_next_page++));
return xdr_argsize_check(rqstp, p);
}
@ -396,7 +397,7 @@ nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p,
if (args->count > PAGE_SIZE)
args->count = PAGE_SIZE;
args->buffer = page_address(rqstp->rq_respages[rqstp->rq_resused++]);
args->buffer = page_address(*(rqstp->rq_next_page++));
return xdr_argsize_check(rqstp, p);
}

64
fs/nfsd/state.h
View File

@ -150,6 +150,12 @@ struct nfsd4_channel_attrs {
u32 rdma_attrs;
};
struct nfsd4_cb_sec {
u32 flavor; /* (u32)(-1) used to mean "no valid flavor" */
u32 uid;
u32 gid;
};
struct nfsd4_create_session {
clientid_t clientid;
struct nfs4_sessionid sessionid;
@ -158,8 +164,12 @@ struct nfsd4_create_session {
struct nfsd4_channel_attrs fore_channel;
struct nfsd4_channel_attrs back_channel;
u32 callback_prog;
u32 uid;
u32 gid;
struct nfsd4_cb_sec cb_sec;
};
struct nfsd4_backchannel_ctl {
u32 bc_cb_program;
struct nfsd4_cb_sec bc_cb_sec;
};
struct nfsd4_bind_conn_to_session {
@ -192,6 +202,7 @@ struct nfsd4_session {
struct nfs4_sessionid se_sessionid;
struct nfsd4_channel_attrs se_fchannel;
struct nfsd4_channel_attrs se_bchannel;
struct nfsd4_cb_sec se_cb_sec;
struct list_head se_conns;
u32 se_cb_prog;
u32 se_cb_seq_nr;
@ -221,13 +232,12 @@ struct nfsd4_sessionid {
*/
struct nfs4_client {
struct list_head cl_idhash; /* hash by cl_clientid.id */
struct list_head cl_strhash; /* hash by cl_name */
struct rb_node cl_namenode; /* link into by-name trees */
struct list_head cl_openowners;
struct idr cl_stateids; /* stateid lookup */
struct list_head cl_delegations;
struct list_head cl_lru; /* tail queue */
struct xdr_netobj cl_name; /* id generated by client */
char cl_recdir[HEXDIR_LEN]; /* recovery dir */
nfs4_verifier cl_verifier; /* generated by client */
time_t cl_time; /* time of last lease renewal */
struct sockaddr_storage cl_addr; /* client ipaddress */
@ -242,9 +252,11 @@ struct nfs4_client {
#define NFSD4_CLIENT_CB_KILL (1)
#define NFSD4_CLIENT_STABLE (2) /* client on stable storage */
#define NFSD4_CLIENT_RECLAIM_COMPLETE (3) /* reclaim_complete done */
#define NFSD4_CLIENT_CONFIRMED (4) /* client is confirmed */
#define NFSD4_CLIENT_CB_FLAG_MASK (1 << NFSD4_CLIENT_CB_UPDATE | \
1 << NFSD4_CLIENT_CB_KILL)
unsigned long cl_flags;
struct rpc_cred *cl_cb_cred;
struct rpc_clnt *cl_cb_client;
u32 cl_cb_ident;
#define NFSD4_CB_UP 0
@ -271,6 +283,7 @@ struct nfs4_client {
unsigned long cl_cb_slot_busy;
struct rpc_wait_queue cl_cb_waitq; /* backchannel callers may */
/* wait here for slots */
struct net *net;
};
static inline void
@ -292,6 +305,7 @@ is_client_expired(struct nfs4_client *clp)
*/
struct nfs4_client_reclaim {
struct list_head cr_strhash; /* hash by cr_name */
struct nfs4_client *cr_clp; /* pointer to associated clp */
char cr_recdir[HEXDIR_LEN]; /* recover dir */
};
@ -452,25 +466,26 @@ extern __be32 nfs4_preprocess_stateid_op(struct net *net,
stateid_t *stateid, int flags, struct file **filp);
extern void nfs4_lock_state(void);
extern void nfs4_unlock_state(void);
extern int nfs4_in_grace(void);
extern void nfs4_release_reclaim(void);
extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(struct nfs4_client *crp);
extern __be32 nfs4_check_open_reclaim(clientid_t *clid, bool sessions);
void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *, struct nfsd_net *);
extern void nfs4_release_reclaim(struct nfsd_net *);
extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir,
struct nfsd_net *nn);
extern __be32 nfs4_check_open_reclaim(clientid_t *clid, bool sessions, struct nfsd_net *nn);
extern void nfs4_free_openowner(struct nfs4_openowner *);
extern void nfs4_free_lockowner(struct nfs4_lockowner *);
extern int set_callback_cred(void);
extern void nfsd4_init_callback(struct nfsd4_callback *);
extern void nfsd4_probe_callback(struct nfs4_client *clp);
extern void nfsd4_probe_callback_sync(struct nfs4_client *clp);
extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *);
extern void nfsd4_do_callback_rpc(struct work_struct *);
extern void nfsd4_cb_recall(struct nfs4_delegation *dp);
extern int nfsd4_create_callback_queue(void);
extern void nfsd4_destroy_callback_queue(void);
extern void nfsd4_shutdown_callback(struct nfs4_client *);
extern void nfs4_put_delegation(struct nfs4_delegation *dp);
extern __be32 nfs4_make_rec_clidname(char *clidname, struct xdr_netobj *clname);
extern int nfs4_client_to_reclaim(const char *name);
extern int nfs4_has_reclaimed_state(const char *name, bool use_exchange_id);
extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(const char *name,
struct nfsd_net *nn);
extern bool nfs4_has_reclaimed_state(const char *name, struct nfsd_net *nn);
extern void release_session_client(struct nfsd4_session *);
extern void nfsd4_purge_closed_stateid(struct nfs4_stateowner *);
@ -480,5 +495,28 @@ extern void nfsd4_client_tracking_exit(struct net *net);
extern void nfsd4_client_record_create(struct nfs4_client *clp);
extern void nfsd4_client_record_remove(struct nfs4_client *clp);
extern int nfsd4_client_record_check(struct nfs4_client *clp);
extern void nfsd4_record_grace_done(struct net *net, time_t boot_time);
extern void nfsd4_record_grace_done(struct nfsd_net *nn, time_t boot_time);
/* nfs fault injection functions */
#ifdef CONFIG_NFSD_FAULT_INJECTION
int nfsd_fault_inject_init(void);
void nfsd_fault_inject_cleanup(void);
u64 nfsd_for_n_state(u64, u64 (*)(struct nfs4_client *, u64));
struct nfs4_client *nfsd_find_client(struct sockaddr_storage *, size_t);
u64 nfsd_forget_client(struct nfs4_client *, u64);
u64 nfsd_forget_client_locks(struct nfs4_client*, u64);
u64 nfsd_forget_client_openowners(struct nfs4_client *, u64);
u64 nfsd_forget_client_delegations(struct nfs4_client *, u64);
u64 nfsd_recall_client_delegations(struct nfs4_client *, u64);
u64 nfsd_print_client(struct nfs4_client *, u64);
u64 nfsd_print_client_locks(struct nfs4_client *, u64);
u64 nfsd_print_client_openowners(struct nfs4_client *, u64);
u64 nfsd_print_client_delegations(struct nfs4_client *, u64);
#else /* CONFIG_NFSD_FAULT_INJECTION */
static inline int nfsd_fault_inject_init(void) { return 0; }
static inline void nfsd_fault_inject_cleanup(void) {}
#endif /* CONFIG_NFSD_FAULT_INJECTION */
#endif /* NFSD4_STATE_H */

53
fs/nfsd/vfs.c
View File

@ -886,7 +886,7 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
struct splice_desc *sd)
{
struct svc_rqst *rqstp = sd->u.data;
struct page **pp = rqstp->rq_respages + rqstp->rq_resused;
struct page **pp = rqstp->rq_next_page;
struct page *page = buf->page;
size_t size;
@ -894,17 +894,15 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
if (rqstp->rq_res.page_len == 0) {
get_page(page);
put_page(*pp);
*pp = page;
rqstp->rq_resused++;
put_page(*rqstp->rq_next_page);
*(rqstp->rq_next_page++) = page;
rqstp->rq_res.page_base = buf->offset;
rqstp->rq_res.page_len = size;
} else if (page != pp[-1]) {
get_page(page);
if (*pp)
put_page(*pp);
*pp = page;
rqstp->rq_resused++;
if (*rqstp->rq_next_page)
put_page(*rqstp->rq_next_page);
*(rqstp->rq_next_page++) = page;
rqstp->rq_res.page_len += size;
} else
rqstp->rq_res.page_len += size;
@ -936,7 +934,8 @@ nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
.u.data = rqstp,
};
rqstp->rq_resused = 1;
WARN_ON_ONCE(rqstp->rq_next_page != rqstp->rq_respages + 1);
rqstp->rq_next_page = rqstp->rq_respages + 1;
host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor);
} else {
oldfs = get_fs();
@ -1020,28 +1019,10 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
inode = dentry->d_inode;
exp = fhp->fh_export;
/*
* Request sync writes if
* - the sync export option has been set, or
* - the client requested O_SYNC behavior (NFSv3 feature).
* - The file system doesn't support fsync().
* When NFSv2 gathered writes have been configured for this volume,
* flushing the data to disk is handled separately below.
*/
use_wgather = (rqstp->rq_vers == 2) && EX_WGATHER(exp);
if (!file->f_op->fsync) {/* COMMIT3 cannot work */
stable = 2;
*stablep = 2; /* FILE_SYNC */
}
if (!EX_ISSYNC(exp))
stable = 0;
if (stable && !use_wgather) {
spin_lock(&file->f_lock);
file->f_flags |= O_SYNC;
spin_unlock(&file->f_lock);
}
/* Write the data. */
oldfs = get_fs(); set_fs(KERNEL_DS);
@ -1057,8 +1038,12 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
if (inode->i_mode & (S_ISUID | S_ISGID))
kill_suid(dentry);
if (stable && use_wgather)
host_err = wait_for_concurrent_writes(file);
if (stable) {
if (use_wgather)
host_err = wait_for_concurrent_writes(file);
else
host_err = vfs_fsync_range(file, offset, offset+*cnt, 0);
}
out_nfserr:
dprintk("nfsd: write complete host_err=%d\n", host_err);
@ -1485,13 +1470,19 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
case NFS3_CREATE_EXCLUSIVE:
if ( dchild->d_inode->i_mtime.tv_sec == v_mtime
&& dchild->d_inode->i_atime.tv_sec == v_atime
&& dchild->d_inode->i_size == 0 )
&& dchild->d_inode->i_size == 0 ) {
if (created)
*created = 1;
break;
}
case NFS4_CREATE_EXCLUSIVE4_1:
if ( dchild->d_inode->i_mtime.tv_sec == v_mtime
&& dchild->d_inode->i_atime.tv_sec == v_atime
&& dchild->d_inode->i_size == 0 )
&& dchild->d_inode->i_size == 0 ) {
if (created)
*created = 1;
goto set_attr;
}
/* fallthru */
case NFS3_CREATE_GUARDED:
err = nfserr_exist;

15
fs/nfsd/xdr4.h
View File

@ -385,7 +385,8 @@ struct nfsd4_write {
u64 wr_offset; /* request */
u32 wr_stable_how; /* request */
u32 wr_buflen; /* request */
int wr_vlen;
struct kvec wr_head;
struct page ** wr_pagelist; /* request */
u32 wr_bytes_written; /* response */
u32 wr_how_written; /* response */
@ -462,6 +463,7 @@ struct nfsd4_op {
/* NFSv4.1 */
struct nfsd4_exchange_id exchange_id;
struct nfsd4_backchannel_ctl backchannel_ctl;
struct nfsd4_bind_conn_to_session bind_conn_to_session;
struct nfsd4_create_session create_session;
struct nfsd4_destroy_session destroy_session;
@ -526,6 +528,14 @@ static inline bool nfsd4_not_cached(struct nfsd4_compoundres *resp)
|| nfsd4_is_solo_sequence(resp);
}
static inline bool nfsd4_last_compound_op(struct svc_rqst *rqstp)
{
struct nfsd4_compoundres *resp = rqstp->rq_resp;
struct nfsd4_compoundargs *argp = rqstp->rq_argp;
return argp->opcnt == resp->opcnt;
}
#define NFS4_SVC_XDRSIZE sizeof(struct nfsd4_compoundargs)
static inline void
@ -566,6 +576,7 @@ extern __be32 nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
struct nfsd4_sequence *seq);
extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp,
struct nfsd4_compound_state *, struct nfsd4_exchange_id *);
extern __be32 nfsd4_backchannel_ctl(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_backchannel_ctl *);
extern __be32 nfsd4_bind_conn_to_session(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_bind_conn_to_session *);
extern __be32 nfsd4_create_session(struct svc_rqst *,
struct nfsd4_compound_state *,
@ -579,7 +590,7 @@ extern __be32 nfsd4_destroy_session(struct svc_rqst *,
extern __be32 nfsd4_destroy_clientid(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_destroy_clientid *);
__be32 nfsd4_reclaim_complete(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_reclaim_complete *);
extern __be32 nfsd4_process_open1(struct nfsd4_compound_state *,
struct nfsd4_open *open);
struct nfsd4_open *open, struct nfsd_net *nn);
extern __be32 nfsd4_process_open2(struct svc_rqst *rqstp,
struct svc_fh *current_fh, struct nfsd4_open *open);
extern void nfsd4_cleanup_open_state(struct nfsd4_open *open, __be32 status);

5
include/linux/exportfs.h
View File

@ -83,6 +83,11 @@ enum fid_type {
* 64 bit parent inode number.
*/
FILEID_NILFS_WITH_PARENT = 0x62,
/*
* Filesystems must not use 0xff file ID.
*/
FILEID_INVALID = 0xff,
};
struct fid {

6
include/linux/sunrpc/cache.h
View File

@ -217,6 +217,8 @@ extern int qword_get(char **bpp, char *dest, int bufsize);
static inline int get_int(char **bpp, int *anint)
{
char buf[50];
char *ep;
int rv;
int len = qword_get(bpp, buf, sizeof(buf));
if (len < 0)
@ -224,9 +226,11 @@ static inline int get_int(char **bpp, int *anint)
if (len == 0)
return -ENOENT;
if (kstrtoint(buf, 0, anint))
rv = simple_strtol(buf, &ep, 0);
if (*ep)
return -EINVAL;
*anint = rv;
return 0;
}

6
include/linux/sunrpc/svc.h
View File

@ -243,6 +243,7 @@ struct svc_rqst {
struct page * rq_pages[RPCSVC_MAXPAGES];
struct page * *rq_respages; /* points into rq_pages */
int rq_resused; /* number of pages used for result */
struct page * *rq_next_page; /* next reply page to use */
struct kvec rq_vec[RPCSVC_MAXPAGES]; /* generally useful.. */
@ -338,9 +339,8 @@ xdr_ressize_check(struct svc_rqst *rqstp, __be32 *p)
static inline void svc_free_res_pages(struct svc_rqst *rqstp)
{
while (rqstp->rq_resused) {
struct page **pp = (rqstp->rq_respages +
--rqstp->rq_resused);
while (rqstp->rq_next_page != rqstp->rq_respages) {
struct page **pp = --rqstp->rq_next_page;
if (*pp) {
put_page(*pp);
*pp = NULL;

21
include/linux/sunrpc/svcsock.h
View File

@ -26,11 +26,28 @@ struct svc_sock {
void (*sk_owspace)(struct sock *);
/* private TCP part */
u32 sk_reclen; /* length of record */
u32 sk_tcplen; /* current read length */
/* On-the-wire fragment header: */
__be32 sk_reclen;
/* As we receive a record, this includes the length received so
* far (including the fragment header): */
u32 sk_tcplen;
/* Total length of the data (not including fragment headers)
* received so far in the fragments making up this rpc: */
u32 sk_datalen;
struct page * sk_pages[RPCSVC_MAXPAGES]; /* received data */
};
static inline u32 svc_sock_reclen(struct svc_sock *svsk)
{
return ntohl(svsk->sk_reclen) & RPC_FRAGMENT_SIZE_MASK;
}
static inline u32 svc_sock_final_rec(struct svc_sock *svsk)
{
return ntohl(svsk->sk_reclen) & RPC_LAST_STREAM_FRAGMENT;
}
/*
* Function prototypes.
*/

1
net/sunrpc/rpcb_clnt.c
View File

@ -23,7 +23,6 @@
#include <linux/errno.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/nsproxy.h>
#include <net/ipv6.h>
#include <linux/sunrpc/clnt.h>

8
net/sunrpc/svc.c
View File

@ -20,7 +20,6 @@
#include <linux/module.h>
#include <linux/kthread.h>
#include <linux/slab.h>
#include <linux/nsproxy.h>
#include <linux/sunrpc/types.h>
#include <linux/sunrpc/xdr.h>
@ -1041,7 +1040,7 @@ static void svc_unregister(const struct svc_serv *serv, struct net *net)
}
/*
* Printk the given error with the address of the client that caused it.
* dprintk the given error with the address of the client that caused it.
*/
static __printf(2, 3)
void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...)
@ -1055,8 +1054,7 @@ void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...)
vaf.fmt = fmt;
vaf.va = &args;
net_warn_ratelimited("svc: %s: %pV",
svc_print_addr(rqstp, buf, sizeof(buf)), &vaf);
dprintk("svc: %s: %pV", svc_print_addr(rqstp, buf, sizeof(buf)), &vaf);
va_end(args);
}
@ -1305,7 +1303,7 @@ svc_process(struct svc_rqst *rqstp)
* Setup response xdr_buf.
* Initially it has just one page
*/
rqstp->rq_resused = 1;
rqstp->rq_next_page = &rqstp->rq_respages[1];
resv->iov_base = page_address(rqstp->rq_respages[0]);
resv->iov_len = 0;
rqstp->rq_res.pages = rqstp->rq_respages + 1;

98
net/sunrpc/svcsock.c
View File

@ -605,6 +605,7 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp)
rqstp->rq_respages = rqstp->rq_pages + 1 +
DIV_ROUND_UP(rqstp->rq_arg.page_len, PAGE_SIZE);
}
rqstp->rq_next_page = rqstp->rq_respages+1;
if (serv->sv_stats)
serv->sv_stats->netudpcnt++;
@ -878,9 +879,9 @@ static unsigned int svc_tcp_restore_pages(struct svc_sock *svsk, struct svc_rqst
{
unsigned int i, len, npages;
if (svsk->sk_tcplen <= sizeof(rpc_fraghdr))
if (svsk->sk_datalen == 0)
return 0;
len = svsk->sk_tcplen - sizeof(rpc_fraghdr);
len = svsk->sk_datalen;
npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
for (i = 0; i < npages; i++) {
if (rqstp->rq_pages[i] != NULL)
@ -897,9 +898,9 @@ static void svc_tcp_save_pages(struct svc_sock *svsk, struct svc_rqst *rqstp)
{
unsigned int i, len, npages;
if (svsk->sk_tcplen <= sizeof(rpc_fraghdr))
if (svsk->sk_datalen == 0)
return;
len = svsk->sk_tcplen - sizeof(rpc_fraghdr);
len = svsk->sk_datalen;
npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
for (i = 0; i < npages; i++) {
svsk->sk_pages[i] = rqstp->rq_pages[i];
@ -911,9 +912,9 @@ static void svc_tcp_clear_pages(struct svc_sock *svsk)
{
unsigned int i, len, npages;
if (svsk->sk_tcplen <= sizeof(rpc_fraghdr))
if (svsk->sk_datalen == 0)
goto out;
len = svsk->sk_tcplen - sizeof(rpc_fraghdr);
len = svsk->sk_datalen;
npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
for (i = 0; i < npages; i++) {
BUG_ON(svsk->sk_pages[i] == NULL);
@ -922,13 +923,12 @@ static void svc_tcp_clear_pages(struct svc_sock *svsk)
}
out:
svsk->sk_tcplen = 0;
svsk->sk_datalen = 0;
}
/*
* Receive data.
* Receive fragment record header.
* If we haven't gotten the record length yet, get the next four bytes.
* Otherwise try to gobble up as much as possible up to the complete
* record length.
*/
static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
{
@ -954,32 +954,16 @@ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
return -EAGAIN;
}
svsk->sk_reclen = ntohl(svsk->sk_reclen);
if (!(svsk->sk_reclen & RPC_LAST_STREAM_FRAGMENT)) {
/* FIXME: technically, a record can be fragmented,
* and non-terminal fragments will not have the top
* bit set in the fragment length header.
* But apparently no known nfs clients send fragmented
* records. */
net_notice_ratelimited("RPC: multiple fragments per record not supported\n");
goto err_delete;
}
svsk->sk_reclen &= RPC_FRAGMENT_SIZE_MASK;
dprintk("svc: TCP record, %d bytes\n", svsk->sk_reclen);
if (svsk->sk_reclen > serv->sv_max_mesg) {
net_notice_ratelimited("RPC: fragment too large: 0x%08lx\n",
(unsigned long)svsk->sk_reclen);
dprintk("svc: TCP record, %d bytes\n", svc_sock_reclen(svsk));
if (svc_sock_reclen(svsk) + svsk->sk_datalen >
serv->sv_max_mesg) {
net_notice_ratelimited("RPC: fragment too large: %d\n",
svc_sock_reclen(svsk));
goto err_delete;
}
}
if (svsk->sk_reclen < 8)
goto err_delete; /* client is nuts. */
len = svsk->sk_reclen;
return len;
return svc_sock_reclen(svsk);
error:
dprintk("RPC: TCP recv_record got %d\n", len);
return len;
@ -1023,7 +1007,7 @@ static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp)
if (dst->iov_len < src->iov_len)
return -EAGAIN; /* whatever; just giving up. */
memcpy(dst->iov_base, src->iov_base, src->iov_len);
xprt_complete_rqst(req->rq_task, svsk->sk_reclen);
xprt_complete_rqst(req->rq_task, rqstp->rq_arg.len);
rqstp->rq_arg.len = 0;
return 0;
}
@ -1042,6 +1026,17 @@ static int copy_pages_to_kvecs(struct kvec *vec, struct page **pages, int len)
return i;
}
static void svc_tcp_fragment_received(struct svc_sock *svsk)
{
/* If we have more data, signal svc_xprt_enqueue() to try again */
if (svc_recv_available(svsk) > sizeof(rpc_fraghdr))
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
dprintk("svc: TCP %s record (%d bytes)\n",
svc_sock_final_rec(svsk) ? "final" : "nonfinal",
svc_sock_reclen(svsk));
svsk->sk_tcplen = 0;
svsk->sk_reclen = 0;
}
/*
* Receive data from a TCP socket.
@ -1068,29 +1063,39 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
goto error;
base = svc_tcp_restore_pages(svsk, rqstp);
want = svsk->sk_reclen - base;
want = svc_sock_reclen(svsk) - (svsk->sk_tcplen - sizeof(rpc_fraghdr));
vec = rqstp->rq_vec;
pnum = copy_pages_to_kvecs(&vec[0], &rqstp->rq_pages[0],
svsk->sk_reclen);
svsk->sk_datalen + want);
rqstp->rq_respages = &rqstp->rq_pages[pnum];
rqstp->rq_next_page = rqstp->rq_respages + 1;
/* Now receive data */
len = svc_partial_recvfrom(rqstp, vec, pnum, want, base);
if (len >= 0)
if (len >= 0) {
svsk->sk_tcplen += len;
if (len != want) {
svsk->sk_datalen += len;
}
if (len != want || !svc_sock_final_rec(svsk)) {
svc_tcp_save_pages(svsk, rqstp);
if (len < 0 && len != -EAGAIN)
goto err_other;
dprintk("svc: incomplete TCP record (%d of %d)\n",
svsk->sk_tcplen, svsk->sk_reclen);
goto err_delete;
if (len == want)
svc_tcp_fragment_received(svsk);
else
dprintk("svc: incomplete TCP record (%d of %d)\n",
(int)(svsk->sk_tcplen - sizeof(rpc_fraghdr)),
svc_sock_reclen(svsk));
goto err_noclose;
}
rqstp->rq_arg.len = svsk->sk_reclen;
if (svc_sock_reclen(svsk) < 8)
goto err_delete; /* client is nuts. */
rqstp->rq_arg.len = svsk->sk_datalen;
rqstp->rq_arg.page_base = 0;
if (rqstp->rq_arg.len <= rqstp->rq_arg.head[0].iov_len) {
rqstp->rq_arg.head[0].iov_len = rqstp->rq_arg.len;
@ -1107,11 +1112,8 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
len = receive_cb_reply(svsk, rqstp);
/* Reset TCP read info */
svsk->sk_reclen = 0;
svsk->sk_tcplen = 0;
/* If we have more data, signal svc_xprt_enqueue() to try again */
if (svc_recv_available(svsk) > sizeof(rpc_fraghdr))
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
svsk->sk_datalen = 0;
svc_tcp_fragment_received(svsk);
if (len < 0)
goto error;
@ -1120,15 +1122,14 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
if (serv->sv_stats)
serv->sv_stats->nettcpcnt++;
dprintk("svc: TCP complete record (%d bytes)\n", rqstp->rq_arg.len);
return rqstp->rq_arg.len;
error:
if (len != -EAGAIN)
goto err_other;
goto err_delete;
dprintk("RPC: TCP recvfrom got EAGAIN\n");
return 0;
err_other:
err_delete:
printk(KERN_NOTICE "%s: recvfrom returned errno %d\n",
svsk->sk_xprt.xpt_server->sv_name, -len);
set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
@ -1305,6 +1306,7 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv)
svsk->sk_reclen = 0;
svsk->sk_tcplen = 0;
svsk->sk_datalen = 0;
memset(&svsk->sk_pages[0], 0, sizeof(svsk->sk_pages));
tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF;

10
net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
View File

@ -521,11 +521,11 @@ next_sge:
rqstp->rq_pages[ch_no] = NULL;
/*
* Detach res pages. svc_release must see a resused count of
* zero or it will attempt to put them.
* Detach res pages. If svc_release sees any it will attempt to
* put them.
*/
while (rqstp->rq_resused)
rqstp->rq_respages[--rqstp->rq_resused] = NULL;
while (rqstp->rq_next_page != rqstp->rq_respages)
*(--rqstp->rq_next_page) = NULL;
return err;
}
@ -550,7 +550,7 @@ static int rdma_read_complete(struct svc_rqst *rqstp,
/* rq_respages starts after the last arg page */
rqstp->rq_respages = &rqstp->rq_arg.pages[page_no];
rqstp->rq_resused = 0;
rqstp->rq_next_page = &rqstp->rq_arg.pages[page_no];
/* Rebuild rq_arg head and tail. */
rqstp->rq_arg.head[0] = head->arg.head[0];

4
net/sunrpc/xprtrdma/svc_rdma_sendto.c
View File

@ -548,6 +548,7 @@ static int send_reply(struct svcxprt_rdma *rdma,
int sge_no;
int sge_bytes;
int page_no;
int pages;
int ret;
/* Post a recv buffer to handle another request. */
@ -611,7 +612,8 @@ static int send_reply(struct svcxprt_rdma *rdma,
* respages array. They are our pages until the I/O
* completes.
*/
for (page_no = 0; page_no < rqstp->rq_resused; page_no++) {
pages = rqstp->rq_next_page - rqstp->rq_respages;
for (page_no = 0; page_no < pages; page_no++) {
ctxt->pages[page_no+1] = rqstp->rq_respages[page_no];
ctxt->count++;
rqstp->rq_respages[page_no] = NULL;