diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2009-09-11 16:39:11 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2009-09-11 16:39:11 -0700 |
commit | 86d710146fb9975f04c505ec78caa43d227c1018 (patch) | |
tree | c7f95412b7760e6b7e3c15eab8b2ac944256d7ac | |
parent | 86373435d2299b722ec87c416005953215f049c1 (diff) | |
parent | ab3bbaa8b257845e248e9a01d12a69ca245f4197 (diff) | |
download | op-kernel-dev-86d710146fb9975f04c505ec78caa43d227c1018.zip op-kernel-dev-86d710146fb9975f04c505ec78caa43d227c1018.tar.gz |
Merge git://git.linux-nfs.org/projects/trondmy/nfs-2.6
* git://git.linux-nfs.org/projects/trondmy/nfs-2.6: (87 commits)
NFSv4: Disallow 'mount -t nfs4 -overs=2' and 'mount -t nfs4 -overs=3'
NFS: Allow the "nfs" file system type to support NFSv4
NFS: Move details of nfs4_get_sb() to a helper
NFS: Refactor NFSv4 text-based mount option validation
NFS: Mount option parser should detect missing "port="
NFS: out of date comment regarding O_EXCL above nfs3_proc_create()
NFS: Handle a zero-length auth flavor list
SUNRPC: Ensure that sunrpc gets initialised before nfs, lockd, etc...
nfs: fix compile error in rpc_pipefs.h
nfs: Remove reference to generic_osync_inode from a comment
SUNRPC: cache must take a reference to the cache detail's module on open()
NFS: Use the DNS resolver in the mount code.
NFS: Add a dns resolver for use with NFSv4 referrals and migration
SUNRPC: Fix a typo in cache_pipefs_files
nfs: nfs4xdr: optimize low level decoding
nfs: nfs4xdr: get rid of READ_BUF
nfs: nfs4xdr: simplify decode_exchange_id by reusing decode_opaque_inline
nfs: nfs4xdr: get rid of COPYMEM
nfs: nfs4xdr: introduce decode_sessionid helper
nfs: nfs4xdr: introduce decode_verifier helper
...
48 files changed, 4064 insertions, 1805 deletions
diff --git a/Documentation/filesystems/nfs.txt b/Documentation/filesystems/nfs.txt new file mode 100644 index 0000000..f50f26c --- /dev/null +++ b/Documentation/filesystems/nfs.txt @@ -0,0 +1,98 @@ + +The NFS client +============== + +The NFS version 2 protocol was first documented in RFC1094 (March 1989). +Since then two more major releases of NFS have been published, with NFSv3 +being documented in RFC1813 (June 1995), and NFSv4 in RFC3530 (April +2003). + +The Linux NFS client currently supports all the above published versions, +and work is in progress on adding support for minor version 1 of the NFSv4 +protocol. + +The purpose of this document is to provide information on some of the +upcall interfaces that are used in order to provide the NFS client with +some of the information that it requires in order to fully comply with +the NFS spec. + +The DNS resolver +================ + +NFSv4 allows for one server to refer the NFS client to data that has been +migrated onto another server by means of the special "fs_locations" +attribute. See + http://tools.ietf.org/html/rfc3530#section-6 +and + http://tools.ietf.org/html/draft-ietf-nfsv4-referrals-00 + +The fs_locations information can take the form of either an ip address and +a path, or a DNS hostname and a path. The latter requires the NFS client to +do a DNS lookup in order to mount the new volume, and hence the need for an +upcall to allow userland to provide this service. + +Assuming that the user has the 'rpc_pipefs' filesystem mounted in the usual +/var/lib/nfs/rpc_pipefs, the upcall consists of the following steps: + + (1) The process checks the dns_resolve cache to see if it contains a + valid entry. If so, it returns that entry and exits. + + (2) If no valid entry exists, the helper script '/sbin/nfs_cache_getent' + (may be changed using the 'nfs.cache_getent' kernel boot parameter) + is run, with two arguments: + - the cache name, "dns_resolve" + - the hostname to resolve + + (3) After looking up the corresponding ip address, the helper script + writes the result into the rpc_pipefs pseudo-file + '/var/lib/nfs/rpc_pipefs/cache/dns_resolve/channel' + in the following (text) format: + + "<ip address> <hostname> <ttl>\n" + + Where <ip address> is in the usual IPv4 (123.456.78.90) or IPv6 + (ffee:ddcc:bbaa:9988:7766:5544:3322:1100, ffee::1100, ...) format. + <hostname> is identical to the second argument of the helper + script, and <ttl> is the 'time to live' of this cache entry (in + units of seconds). + + Note: If <ip address> is invalid, say the string "0", then a negative + entry is created, which will cause the kernel to treat the hostname + as having no valid DNS translation. + + + + +A basic sample /sbin/nfs_cache_getent +===================================== + +#!/bin/bash +# +ttl=600 +# +cut=/usr/bin/cut +getent=/usr/bin/getent +rpc_pipefs=/var/lib/nfs/rpc_pipefs +# +die() +{ + echo "Usage: $0 cache_name entry_name" + exit 1 +} + +[ $# -lt 2 ] && die +cachename="$1" +cache_path=${rpc_pipefs}/cache/${cachename}/channel + +case "${cachename}" in + dns_resolve) + name="$2" + result="$(${getent} hosts ${name} | ${cut} -f1 -d\ )" + [ -z "${result}" ] && result="0" + ;; + *) + die + ;; +esac +echo "${result} ${name} ${ttl}" >${cache_path} + diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 8e91863..5d4427d 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1503,6 +1503,14 @@ and is between 256 and 4096 characters. It is defined in the file [NFS] set the TCP port on which the NFSv4 callback channel should listen. + nfs.cache_getent= + [NFS] sets the pathname to the program which is used + to update the NFS client cache entries. + + nfs.cache_getent_timeout= + [NFS] sets the timeout after which an attempt to + update a cache entry is deemed to have failed. + nfs.idmap_cache_timeout= [NFS] set the maximum lifetime for idmapper cache entries. @@ -2395,6 +2403,18 @@ and is between 256 and 4096 characters. It is defined in the file stifb= [HW] Format: bpp:<bpp1>[:<bpp2>[:<bpp3>...]] + sunrpc.min_resvport= + sunrpc.max_resvport= + [NFS,SUNRPC] + SunRPC servers often require that client requests + originate from a privileged port (i.e. a port in the + range 0 < portnr < 1024). + An administrator who wishes to reserve some of these + ports for other uses may adjust the range that the + kernel's sunrpc client considers to be privileged + using these two parameters to set the minimum and + maximum port values. + sunrpc.pool_mode= [NFS] Control how the NFS server code allocates CPUs to @@ -2411,6 +2431,15 @@ and is between 256 and 4096 characters. It is defined in the file pernode one pool for each NUMA node (equivalent to global on non-NUMA machines) + sunrpc.tcp_slot_table_entries= + sunrpc.udp_slot_table_entries= + [NFS,SUNRPC] + Sets the upper limit on the number of simultaneous + RPC calls that can be sent from the client to a + server. Increasing these values may allow you to + improve throughput, but will also increase the + amount of memory reserved for use by the client. + swiotlb= [IA-64] Number of I/O TLB slabs switches= [HW,M68k] diff --git a/fs/lockd/host.c b/fs/lockd/host.c index 99d737b..7cb076a 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -87,18 +87,6 @@ static unsigned int nlm_hash_address(const struct sockaddr *sap) return hash & (NLM_HOST_NRHASH - 1); } -static void nlm_clear_port(struct sockaddr *sap) -{ - switch (sap->sa_family) { - case AF_INET: - ((struct sockaddr_in *)sap)->sin_port = 0; - break; - case AF_INET6: - ((struct sockaddr_in6 *)sap)->sin6_port = 0; - break; - } -} - /* * Common host lookup routine for server & client */ @@ -177,7 +165,7 @@ static struct nlm_host *nlm_lookup_host(struct nlm_lookup_host_info *ni) host->h_addrbuf = nsm->sm_addrbuf; memcpy(nlm_addr(host), ni->sap, ni->salen); host->h_addrlen = ni->salen; - nlm_clear_port(nlm_addr(host)); + rpc_set_port(nlm_addr(host), 0); memcpy(nlm_srcaddr(host), ni->src_sap, ni->src_len); host->h_version = ni->version; host->h_proto = ni->protocol; diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 7fce1b5..30c9331 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -61,43 +61,6 @@ static inline struct sockaddr *nsm_addr(const struct nsm_handle *nsm) return (struct sockaddr *)&nsm->sm_addr; } -static void nsm_display_ipv4_address(const struct sockaddr *sap, char *buf, - const size_t len) -{ - const struct sockaddr_in *sin = (struct sockaddr_in *)sap; - snprintf(buf, len, "%pI4", &sin->sin_addr.s_addr); -} - -static void nsm_display_ipv6_address(const struct sockaddr *sap, char *buf, - const size_t len) -{ - const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap; - - if (ipv6_addr_v4mapped(&sin6->sin6_addr)) - snprintf(buf, len, "%pI4", &sin6->sin6_addr.s6_addr32[3]); - else if (sin6->sin6_scope_id != 0) - snprintf(buf, len, "%pI6%%%u", &sin6->sin6_addr, - sin6->sin6_scope_id); - else - snprintf(buf, len, "%pI6", &sin6->sin6_addr); -} - -static void nsm_display_address(const struct sockaddr *sap, - char *buf, const size_t len) -{ - switch (sap->sa_family) { - case AF_INET: - nsm_display_ipv4_address(sap, buf, len); - break; - case AF_INET6: - nsm_display_ipv6_address(sap, buf, len); - break; - default: - snprintf(buf, len, "unsupported address family"); - break; - } -} - static struct rpc_clnt *nsm_create(void) { struct sockaddr_in sin = { @@ -307,8 +270,11 @@ static struct nsm_handle *nsm_create_handle(const struct sockaddr *sap, memcpy(nsm_addr(new), sap, salen); new->sm_addrlen = salen; nsm_init_private(new); - nsm_display_address((const struct sockaddr *)&new->sm_addr, - new->sm_addrbuf, sizeof(new->sm_addrbuf)); + + if (rpc_ntop(nsm_addr(new), new->sm_addrbuf, + sizeof(new->sm_addrbuf)) == 0) + (void)snprintf(new->sm_addrbuf, sizeof(new->sm_addrbuf), + "unsupported address family"); memcpy(new->sm_name, hostname, hostname_len); new->sm_name[hostname_len] = '\0'; diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index 8451598..da7fda6 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -6,7 +6,8 @@ obj-$(CONFIG_NFS_FS) += nfs.o nfs-y := client.o dir.o file.o getroot.o inode.o super.o nfs2xdr.o \ direct.o pagelist.o proc.o read.o symlink.o unlink.o \ - write.o namespace.o mount_clnt.o + write.o namespace.o mount_clnt.o \ + dns_resolve.o cache_lib.o nfs-$(CONFIG_ROOT_NFS) += nfsroot.o nfs-$(CONFIG_NFS_V3) += nfs3proc.o nfs3xdr.o nfs-$(CONFIG_NFS_V3_ACL) += nfs3acl.o diff --git a/fs/nfs/cache_lib.c b/fs/nfs/cache_lib.c new file mode 100644 index 0000000..b4ffd01 --- /dev/null +++ b/fs/nfs/cache_lib.c @@ -0,0 +1,140 @@ +/* + * linux/fs/nfs/cache_lib.c + * + * Helper routines for the NFS client caches + * + * Copyright (c) 2009 Trond Myklebust <Trond.Myklebust@netapp.com> + */ +#include <linux/kmod.h> +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/mount.h> +#include <linux/namei.h> +#include <linux/sunrpc/cache.h> +#include <linux/sunrpc/rpc_pipe_fs.h> + +#include "cache_lib.h" + +#define NFS_CACHE_UPCALL_PATHLEN 256 +#define NFS_CACHE_UPCALL_TIMEOUT 15 + +static char nfs_cache_getent_prog[NFS_CACHE_UPCALL_PATHLEN] = + "/sbin/nfs_cache_getent"; +static unsigned long nfs_cache_getent_timeout = NFS_CACHE_UPCALL_TIMEOUT; + +module_param_string(cache_getent, nfs_cache_getent_prog, + sizeof(nfs_cache_getent_prog), 0600); +MODULE_PARM_DESC(cache_getent, "Path to the client cache upcall program"); +module_param_named(cache_getent_timeout, nfs_cache_getent_timeout, ulong, 0600); +MODULE_PARM_DESC(cache_getent_timeout, "Timeout (in seconds) after which " + "the cache upcall is assumed to have failed"); + +int nfs_cache_upcall(struct cache_detail *cd, char *entry_name) +{ + static char *envp[] = { "HOME=/", + "TERM=linux", + "PATH=/sbin:/usr/sbin:/bin:/usr/bin", + NULL + }; + char *argv[] = { + nfs_cache_getent_prog, + cd->name, + entry_name, + NULL + }; + int ret = -EACCES; + + if (nfs_cache_getent_prog[0] == '\0') + goto out; + ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC); + /* + * 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 to set the 'cache_getent' parameter once the problem + * has been fixed. + */ + if (ret == -ENOENT || ret == -EACCES) + nfs_cache_getent_prog[0] = '\0'; +out: + return ret > 0 ? 0 : ret; +} + +/* + * Deferred request handling + */ +void nfs_cache_defer_req_put(struct nfs_cache_defer_req *dreq) +{ + if (atomic_dec_and_test(&dreq->count)) + kfree(dreq); +} + +static void nfs_dns_cache_revisit(struct cache_deferred_req *d, int toomany) +{ + struct nfs_cache_defer_req *dreq; + + dreq = container_of(d, struct nfs_cache_defer_req, deferred_req); + + complete_all(&dreq->completion); + nfs_cache_defer_req_put(dreq); +} + +static struct cache_deferred_req *nfs_dns_cache_defer(struct cache_req *req) +{ + struct nfs_cache_defer_req *dreq; + + dreq = container_of(req, struct nfs_cache_defer_req, req); + dreq->deferred_req.revisit = nfs_dns_cache_revisit; + atomic_inc(&dreq->count); + + return &dreq->deferred_req; +} + +struct nfs_cache_defer_req *nfs_cache_defer_req_alloc(void) +{ + struct nfs_cache_defer_req *dreq; + + dreq = kzalloc(sizeof(*dreq), GFP_KERNEL); + if (dreq) { + init_completion(&dreq->completion); + atomic_set(&dreq->count, 1); + dreq->req.defer = nfs_dns_cache_defer; + } + return dreq; +} + +int nfs_cache_wait_for_upcall(struct nfs_cache_defer_req *dreq) +{ + if (wait_for_completion_timeout(&dreq->completion, + nfs_cache_getent_timeout * HZ) == 0) + return -ETIMEDOUT; + return 0; +} + +int nfs_cache_register(struct cache_detail *cd) +{ + struct nameidata nd; + struct vfsmount *mnt; + int ret; + + mnt = rpc_get_mount(); + if (IS_ERR(mnt)) + return PTR_ERR(mnt); + ret = vfs_path_lookup(mnt->mnt_root, mnt, "/cache", 0, &nd); + if (ret) + goto err; + ret = sunrpc_cache_register_pipefs(nd.path.dentry, + cd->name, 0600, cd); + path_put(&nd.path); + if (!ret) + return ret; +err: + rpc_put_mount(); + return ret; +} + +void nfs_cache_unregister(struct cache_detail *cd) +{ + sunrpc_cache_unregister_pipefs(cd); + rpc_put_mount(); +} + diff --git a/fs/nfs/cache_lib.h b/fs/nfs/cache_lib.h new file mode 100644 index 0000000..76f856e --- /dev/null +++ b/fs/nfs/cache_lib.h @@ -0,0 +1,27 @@ +/* + * Helper routines for the NFS client caches + * + * Copyright (c) 2009 Trond Myklebust <Trond.Myklebust@netapp.com> + */ + +#include <linux/completion.h> +#include <linux/sunrpc/cache.h> +#include <asm/atomic.h> + +/* + * Deferred request handling + */ +struct nfs_cache_defer_req { + struct cache_req req; + struct cache_deferred_req deferred_req; + struct completion completion; + atomic_t count; +}; + +extern int nfs_cache_upcall(struct cache_detail *cd, char *entry_name); +extern struct nfs_cache_defer_req *nfs_cache_defer_req_alloc(void); +extern void nfs_cache_defer_req_put(struct nfs_cache_defer_req *dreq); +extern int nfs_cache_wait_for_upcall(struct nfs_cache_defer_req *dreq); + +extern int nfs_cache_register(struct cache_detail *cd); +extern void nfs_cache_unregister(struct cache_detail *cd); diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 7f604c7..293fa05 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -43,21 +43,29 @@ static struct svc_program nfs4_callback_program; unsigned int nfs_callback_set_tcpport; unsigned short nfs_callback_tcpport; unsigned short nfs_callback_tcpport6; -static const int nfs_set_port_min = 0; -static const int nfs_set_port_max = 65535; +#define NFS_CALLBACK_MAXPORTNR (65535U) -static int param_set_port(const char *val, struct kernel_param *kp) +static int param_set_portnr(const char *val, struct kernel_param *kp) { - char *endp; - int num = simple_strtol(val, &endp, 0); - if (endp == val || *endp || num < nfs_set_port_min || num > nfs_set_port_max) + unsigned long num; + int ret; + + if (!val) + return -EINVAL; + ret = strict_strtoul(val, 0, &num); + if (ret == -EINVAL || num > NFS_CALLBACK_MAXPORTNR) return -EINVAL; - *((int *)kp->arg) = num; + *((unsigned int *)kp->arg) = num; return 0; } -module_param_call(callback_tcpport, param_set_port, param_get_int, - &nfs_callback_set_tcpport, 0644); +static int param_get_portnr(char *buffer, struct kernel_param *kp) +{ + return param_get_uint(buffer, kp); +} +#define param_check_portnr(name, p) __param_check(name, p, unsigned int); + +module_param_named(callback_tcpport, nfs_callback_set_tcpport, portnr, 0644); /* * This is the NFSv4 callback kernel thread. diff --git a/fs/nfs/client.c b/fs/nfs/client.c index c6be84a..e350bd6 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -809,6 +809,9 @@ static int nfs_init_server(struct nfs_server *server, /* Initialise the client representation from the mount data */ server->flags = data->flags; server->options = data->options; + server->caps |= NFS_CAP_HARDLINKS|NFS_CAP_SYMLINKS|NFS_CAP_FILEID| + NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|NFS_CAP_OWNER_GROUP| + NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME; if (data->rsize) server->rsize = nfs_block_size(data->rsize, NULL); @@ -1075,10 +1078,6 @@ struct nfs_server *nfs_create_server(const struct nfs_parsed_mount_data *data, (unsigned long long) server->fsid.major, (unsigned long long) server->fsid.minor); - BUG_ON(!server->nfs_client); - BUG_ON(!server->nfs_client->rpc_ops); - BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops); - spin_lock(&nfs_client_lock); list_add_tail(&server->client_link, &server->nfs_client->cl_superblocks); list_add_tail(&server->master_link, &nfs_volume_list); @@ -1275,7 +1274,7 @@ static int nfs4_init_server(struct nfs_server *server, /* Initialise the client representation from the mount data */ server->flags = data->flags; - server->caps |= NFS_CAP_ATOMIC_OPEN; + server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR; server->options = data->options; /* Get a client record */ @@ -1360,10 +1359,6 @@ struct nfs_server *nfs4_create_server(const struct nfs_parsed_mount_data *data, if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN) server->namelen = NFS4_MAXNAMLEN; - BUG_ON(!server->nfs_client); - BUG_ON(!server->nfs_client->rpc_ops); - BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops); - spin_lock(&nfs_client_lock); list_add_tail(&server->client_link, &server->nfs_client->cl_superblocks); list_add_tail(&server->master_link, &nfs_volume_list); @@ -1401,7 +1396,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, /* Initialise the client representation from the parent server */ nfs_server_copy_userdata(server, parent_server); - server->caps |= NFS_CAP_ATOMIC_OPEN; + server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR; /* Get a client representation. * Note: NFSv4 always uses TCP, */ diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index e4e089a..6c32100 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -934,9 +934,6 @@ out: * back into its cache. We let the server do generic write * parameter checking and report problems. * - * We also avoid an unnecessary invocation of generic_osync_inode(), - * as it is fairly meaningless to sync the metadata of an NFS file. - * * We eliminate local atime updates, see direct read above. * * We avoid unnecessary page cache invalidations for normal cached diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c new file mode 100644 index 0000000..f4d54ba --- /dev/null +++ b/fs/nfs/dns_resolve.c @@ -0,0 +1,335 @@ +/* + * linux/fs/nfs/dns_resolve.c + * + * Copyright (c) 2009 Trond Myklebust <Trond.Myklebust@netapp.com> + * + * Resolves DNS hostnames into valid ip addresses + */ + +#include <linux/hash.h> +#include <linux/string.h> +#include <linux/kmod.h> +#include <linux/module.h> +#include <linux/socket.h> +#include <linux/seq_file.h> +#include <linux/inet.h> +#include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/cache.h> +#include <linux/sunrpc/svcauth.h> + +#include "dns_resolve.h" +#include "cache_lib.h" + +#define NFS_DNS_HASHBITS 4 +#define NFS_DNS_HASHTBL_SIZE (1 << NFS_DNS_HASHBITS) + +static struct cache_head *nfs_dns_table[NFS_DNS_HASHTBL_SIZE]; + +struct nfs_dns_ent { + struct cache_head h; + + char *hostname; + size_t namelen; + + struct sockaddr_storage addr; + size_t addrlen; +}; + + +static void nfs_dns_ent_init(struct cache_head *cnew, + struct cache_head *ckey) +{ + struct nfs_dns_ent *new; + struct nfs_dns_ent *key; + + new = container_of(cnew, struct nfs_dns_ent, h); + key = container_of(ckey, struct nfs_dns_ent, h); + + kfree(new->hostname); + new->hostname = kstrndup(key->hostname, key->namelen, GFP_KERNEL); + if (new->hostname) { + new->namelen = key->namelen; + memcpy(&new->addr, &key->addr, key->addrlen); + new->addrlen = key->addrlen; + } else { + new->namelen = 0; + new->addrlen = 0; + } +} + +static void nfs_dns_ent_put(struct kref *ref) +{ + struct nfs_dns_ent *item; + + item = container_of(ref, struct nfs_dns_ent, h.ref); + kfree(item->hostname); + kfree(item); +} + +static struct cache_head *nfs_dns_ent_alloc(void) +{ + struct nfs_dns_ent *item = kmalloc(sizeof(*item), GFP_KERNEL); + + if (item != NULL) { + item->hostname = NULL; + item->namelen = 0; + item->addrlen = 0; + return &item->h; + } + return NULL; +}; + +static unsigned int nfs_dns_hash(const struct nfs_dns_ent *key) +{ + return hash_str(key->hostname, NFS_DNS_HASHBITS); +} + +static void nfs_dns_request(struct cache_detail *cd, + struct cache_head *ch, + char **bpp, int *blen) +{ + struct nfs_dns_ent *key = container_of(ch, struct nfs_dns_ent, h); + + qword_add(bpp, blen, key->hostname); + (*bpp)[-1] = '\n'; +} + +static int nfs_dns_upcall(struct cache_detail *cd, + struct cache_head *ch) +{ + struct nfs_dns_ent *key = container_of(ch, struct nfs_dns_ent, h); + int ret; + + ret = nfs_cache_upcall(cd, key->hostname); + if (ret) + ret = sunrpc_cache_pipe_upcall(cd, ch, nfs_dns_request); + return ret; +} + +static int nfs_dns_match(struct cache_head *ca, + struct cache_head *cb) +{ + struct nfs_dns_ent *a; + struct nfs_dns_ent *b; + + a = container_of(ca, struct nfs_dns_ent, h); + b = container_of(cb, struct nfs_dns_ent, h); + + if (a->namelen == 0 || a->namelen != b->namelen) + return 0; + return memcmp(a->hostname, b->hostname, a->namelen) == 0; +} + +static int nfs_dns_show(struct seq_file *m, struct cache_detail *cd, + struct cache_head *h) +{ + struct nfs_dns_ent *item; + long ttl; + + if (h == NULL) { + seq_puts(m, "# ip address hostname ttl\n"); + return 0; + } + item = container_of(h, struct nfs_dns_ent, h); + ttl = (long)item->h.expiry_time - (long)get_seconds(); + if (ttl < 0) + ttl = 0; + + if (!test_bit(CACHE_NEGATIVE, &h->flags)) { + char buf[INET6_ADDRSTRLEN+IPV6_SCOPE_ID_LEN+1]; + + rpc_ntop((struct sockaddr *)&item->addr, buf, sizeof(buf)); + seq_printf(m, "%15s ", buf); + } else + seq_puts(m, "<none> "); + seq_printf(m, "%15s %ld\n", item->hostname, ttl); + return 0; +} + +struct nfs_dns_ent *nfs_dns_lookup(struct cache_detail *cd, + struct nfs_dns_ent *key) +{ + struct cache_head *ch; + + ch = sunrpc_cache_lookup(cd, + &key->h, + nfs_dns_hash(key)); + if (!ch) + return NULL; + return container_of(ch, struct nfs_dns_ent, h); +} + +struct nfs_dns_ent *nfs_dns_update(struct cache_detail *cd, + struct nfs_dns_ent *new, + struct nfs_dns_ent *key) +{ + struct cache_head *ch; + + ch = sunrpc_cache_update(cd, + &new->h, &key->h, + nfs_dns_hash(key)); + if (!ch) + return NULL; + return container_of(ch, struct nfs_dns_ent, h); +} + +static int nfs_dns_parse(struct cache_detail *cd, char *buf, int buflen) +{ + char buf1[NFS_DNS_HOSTNAME_MAXLEN+1]; + struct nfs_dns_ent key, *item; + unsigned long ttl; + ssize_t len; + int ret = -EINVAL; + + if (buf[buflen-1] != '\n') + goto out; + buf[buflen-1] = '\0'; + + len = qword_get(&buf, buf1, sizeof(buf1)); + if (len <= 0) + goto out; + key.addrlen = rpc_pton(buf1, len, + (struct sockaddr *)&key.addr, + sizeof(key.addr)); + + len = qword_get(&buf, buf1, sizeof(buf1)); + if (len <= 0) + goto out; + + key.hostname = buf1; + key.namelen = len; + memset(&key.h, 0, sizeof(key.h)); + + ttl = get_expiry(&buf); + if (ttl == 0) + goto out; + key.h.expiry_time = ttl + get_seconds(); + + ret = -ENOMEM; + item = nfs_dns_lookup(cd, &key); + if (item == NULL) + goto out; + + if (key.addrlen == 0) + set_bit(CACHE_NEGATIVE, &key.h.flags); + + item = nfs_dns_update(cd, &key, item); + if (item == NULL) + goto out; + + ret = 0; + cache_put(&item->h, cd); +out: + return ret; +} + +static struct cache_detail nfs_dns_resolve = { + .owner = THIS_MODULE, + .hash_size = NFS_DNS_HASHTBL_SIZE, + .hash_table = nfs_dns_table, + .name = "dns_resolve", + .cache_put = nfs_dns_ent_put, + .cache_upcall = nfs_dns_upcall, + .cache_parse = nfs_dns_parse, + .cache_show = nfs_dns_show, + .match = nfs_dns_match, + .init = nfs_dns_ent_init, + .update = nfs_dns_ent_init, + .alloc = nfs_dns_ent_alloc, +}; + +static int do_cache_lookup(struct cache_detail *cd, + struct nfs_dns_ent *key, + struct nfs_dns_ent **item, + struct nfs_cache_defer_req *dreq) +{ + int ret = -ENOMEM; + + *item = nfs_dns_lookup(cd, key); + if (*item) { + ret = cache_check(cd, &(*item)->h, &dreq->req); + if (ret) + *item = NULL; + } + return ret; +} + +static int do_cache_lookup_nowait(struct cache_detail *cd, + struct nfs_dns_ent *key, + struct nfs_dns_ent **item) +{ + int ret = -ENOMEM; + + *item = nfs_dns_lookup(cd, key); + if (!*item) + goto out_err; + ret = -ETIMEDOUT; + if (!test_bit(CACHE_VALID, &(*item)->h.flags) + || (*item)->h.expiry_time < get_seconds() + || cd->flush_time > (*item)->h.last_refresh) + goto out_put; + ret = -ENOENT; + if (test_bit(CACHE_NEGATIVE, &(*item)->h.flags)) + goto out_put; + return 0; +out_put: + cache_put(&(*item)->h, cd); +out_err: + *item = NULL; + return ret; +} + +static int do_cache_lookup_wait(struct cache_detail *cd, + struct nfs_dns_ent *key, + struct nfs_dns_ent **item) +{ + struct nfs_cache_defer_req *dreq; + int ret = -ENOMEM; + + dreq = nfs_cache_defer_req_alloc(); + if (!dreq) + goto out; + ret = do_cache_lookup(cd, key, item, dreq); + if (ret == -EAGAIN) { + ret = nfs_cache_wait_for_upcall(dreq); + if (!ret) + ret = do_cache_lookup_nowait(cd, key, item); + } + nfs_cache_defer_req_put(dreq); +out: + return ret; +} + +ssize_t nfs_dns_resolve_name(char *name, size_t namelen, + struct sockaddr *sa, size_t salen) +{ + struct nfs_dns_ent key = { + .hostname = name, + .namelen = namelen, + }; + struct nfs_dns_ent *item = NULL; + ssize_t ret; + + ret = do_cache_lookup_wait(&nfs_dns_resolve, &key, &item); + if (ret == 0) { + if (salen >= item->addrlen) { + memcpy(sa, &item->addr, item->addrlen); + ret = item->addrlen; + } else + ret = -EOVERFLOW; + cache_put(&item->h, &nfs_dns_resolve); + } else if (ret == -ENOENT) + ret = -ESRCH; + return ret; +} + +int nfs_dns_resolver_init(void) +{ + return nfs_cache_register(&nfs_dns_resolve); +} + +void nfs_dns_resolver_destroy(void) +{ + nfs_cache_unregister(&nfs_dns_resolve); +} + diff --git a/fs/nfs/dns_resolve.h b/fs/nfs/dns_resolve.h new file mode 100644 index 0000000..a3f0938 --- /dev/null +++ b/fs/nfs/dns_resolve.h @@ -0,0 +1,14 @@ +/* + * Resolve DNS hostnames into valid ip addresses + */ +#ifndef __LINUX_FS_NFS_DNS_RESOLVE_H +#define __LINUX_FS_NFS_DNS_RESOLVE_H + +#define NFS_DNS_HOSTNAME_MAXLEN (128) + +extern int nfs_dns_resolver_init(void); +extern void nfs_dns_resolver_destroy(void); +extern ssize_t nfs_dns_resolve_name(char *name, size_t namelen, + struct sockaddr *sa, size_t salen); + +#endif diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 0506232..5021b75 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -328,6 +328,42 @@ nfs_file_fsync(struct file *file, struct dentry *dentry, int datasync) } /* + * Decide whether a read/modify/write cycle may be more efficient + * then a modify/write/read cycle when writing to a page in the + * page cache. + * + * The modify/write/read cycle may occur if a page is read before + * being completely filled by the writer. In this situation, the + * page must be completely written to stable storage on the server + * before it can be refilled by reading in the page from the server. + * This can lead to expensive, small, FILE_SYNC mode writes being + * done. + * + * It may be more efficient to read the page first if the file is + * open for reading in addition to writing, the page is not marked + * as Uptodate, it is not dirty or waiting to be committed, + * indicating that it was previously allocated and then modified, + * that there were valid bytes of data in that range of the file, + * and that the new data won't completely replace the old data in + * that range of the file. + */ +static int nfs_want_read_modify_write(struct file *file, struct page *page, + loff_t pos, unsigned len) +{ + unsigned int pglen = nfs_page_length(page); + unsigned int offset = pos & (PAGE_CACHE_SIZE - 1); + unsigned int end = offset + len; + + if ((file->f_mode & FMODE_READ) && /* open for read? */ + !PageUptodate(page) && /* Uptodate? */ + !PagePrivate(page) && /* i/o request already? */ + pglen && /* valid bytes of file? */ + (end < pglen || offset)) /* replace all valid bytes? */ + return 1; + return 0; +} + +/* * This does the "real" work of the write. We must allocate and lock the * page to be sent back to the generic routine, which then copies the * data from user space. @@ -340,15 +376,16 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping, struct page **pagep, void **fsdata) { int ret; - pgoff_t index; + pgoff_t index = pos >> PAGE_CACHE_SHIFT; struct page *page; - index = pos >> PAGE_CACHE_SHIFT; + int once_thru = 0; dfprintk(PAGECACHE, "NFS: write_begin(%s/%s(%ld), %u@%lld)\n", file->f_path.dentry->d_parent->d_name.name, file->f_path.dentry->d_name.name, mapping->host->i_ino, len, (long long) pos); +start: /* * Prevent starvation issues if someone is doing a consistency * sync-to-disk @@ -367,6 +404,13 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping, if (ret) { unlock_page(page); page_cache_release(page); + } else if (!once_thru && + nfs_want_read_modify_write(file, page, pos, len)) { + once_thru = 1; + ret = nfs_readpage(file, page); + page_cache_release(page); + if (!ret) + goto start; } return ret; } @@ -479,6 +523,7 @@ const struct address_space_operations nfs_file_aops = { .invalidatepage = nfs_invalidate_page, .releasepage = nfs_release_page, .direct_IO = nfs_direct_IO, + .migratepage = nfs_migrate_page, .launder_page = nfs_launder_page, }; diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index 86147b0..21a84d45 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -101,7 +101,7 @@ static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *); static unsigned int fnvhash32(const void *, size_t); -static struct rpc_pipe_ops idmap_upcall_ops = { +static const struct rpc_pipe_ops idmap_upcall_ops = { .upcall = idmap_pipe_upcall, .downcall = idmap_pipe_downcall, .destroy_msg = idmap_pipe_destroy_msg, @@ -119,8 +119,8 @@ nfs_idmap_new(struct nfs_client *clp) if (idmap == NULL) return -ENOMEM; - idmap->idmap_dentry = rpc_mkpipe(clp->cl_rpcclient->cl_dentry, "idmap", - idmap, &idmap_upcall_ops, 0); + idmap->idmap_dentry = rpc_mkpipe(clp->cl_rpcclient->cl_path.dentry, + "idmap", idmap, &idmap_upcall_ops, 0); if (IS_ERR(idmap->idmap_dentry)) { error = PTR_ERR(idmap->idmap_dentry); kfree(idmap); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index bd7938e..060022b 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -46,6 +46,7 @@ #include "iostat.h" #include "internal.h" #include "fscache.h" +#include "dns_resolve.h" #define NFSDBG_FACILITY NFSDBG_VFS @@ -286,6 +287,11 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) /* We can't support update_atime(), since the server will reset it */ inode->i_flags |= S_NOATIME|S_NOCMTIME; inode->i_mode = fattr->mode; + if ((fattr->valid & NFS_ATTR_FATTR_MODE) == 0 + && nfs_server_capable(inode, NFS_CAP_MODE)) + nfsi->cache_validity |= NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL; /* Why so? Because we want revalidate for devices/FIFOs, and * that's precisely what we have in nfs_file_inode_operations. */ @@ -330,20 +336,46 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) nfsi->attr_gencount = fattr->gencount; if (fattr->valid & NFS_ATTR_FATTR_ATIME) inode->i_atime = fattr->atime; + else if (nfs_server_capable(inode, NFS_CAP_ATIME)) + nfsi->cache_validity |= NFS_INO_INVALID_ATTR; if (fattr->valid & NFS_ATTR_FATTR_MTIME) inode->i_mtime = fattr->mtime; + else if (nfs_server_capable(inode, NFS_CAP_MTIME)) + nfsi->cache_validity |= NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_DATA; if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode->i_ctime = fattr->ctime; + else if (nfs_server_capable(inode, NFS_CAP_CTIME)) + nfsi->cache_validity |= NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL; if (fattr->valid & NFS_ATTR_FATTR_CHANGE) nfsi->change_attr = fattr->change_attr; + else if (nfs_server_capable(inode, NFS_CAP_CHANGE_ATTR)) + nfsi->cache_validity |= NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_DATA; if (fattr->valid & NFS_ATTR_FATTR_SIZE) inode->i_size = nfs_size_to_loff_t(fattr->size); + else + nfsi->cache_validity |= NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_DATA + | NFS_INO_REVAL_PAGECACHE; if (fattr->valid & NFS_ATTR_FATTR_NLINK) inode->i_nlink = fattr->nlink; + else if (nfs_server_capable(inode, NFS_CAP_NLINK)) + nfsi->cache_validity |= NFS_INO_INVALID_ATTR; if (fattr->valid & NFS_ATTR_FATTR_OWNER) inode->i_uid = fattr->uid; + else if (nfs_server_capable(inode, NFS_CAP_OWNER)) + nfsi->cache_validity |= NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL; if (fattr->valid & NFS_ATTR_FATTR_GROUP) inode->i_gid = fattr->gid; + else if (nfs_server_capable(inode, NFS_CAP_OWNER_GROUP)) + nfsi->cache_validity |= NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL; if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { @@ -1145,6 +1177,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) loff_t cur_isize, new_isize; unsigned long invalid = 0; unsigned long now = jiffies; + unsigned long save_cache_validity; dfprintk(VFS, "NFS: %s(%s/%ld ct=%d info=0x%x)\n", __func__, inode->i_sb->s_id, inode->i_ino, @@ -1171,10 +1204,11 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) */ nfsi->read_cache_jiffies = fattr->time_start; - if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) || (fattr->valid & (NFS_ATTR_FATTR_MTIME|NFS_ATTR_FATTR_CTIME))) - nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR - | NFS_INO_INVALID_ATIME - | NFS_INO_REVAL_PAGECACHE); + save_cache_validity = nfsi->cache_validity; + nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ATIME + | NFS_INO_REVAL_FORCED + | NFS_INO_REVAL_PAGECACHE); /* Do atomic weak cache consistency updates */ nfs_wcc_update_inode(inode, fattr); @@ -1189,7 +1223,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfs_force_lookup_revalidate(inode); nfsi->change_attr = fattr->change_attr; } - } + } else if (server->caps & NFS_CAP_CHANGE_ATTR) + invalid |= save_cache_validity; if (fattr->valid & NFS_ATTR_FATTR_MTIME) { /* NFSv2/v3: Check if the mtime agrees */ @@ -1201,7 +1236,12 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfs_force_lookup_revalidate(inode); memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime)); } - } + } else if (server->caps & NFS_CAP_MTIME) + invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_DATA + | NFS_INO_REVAL_PAGECACHE + | NFS_INO_REVAL_FORCED); + if (fattr->valid & NFS_ATTR_FATTR_CTIME) { /* If ctime has changed we should definitely clear access+acl caches */ if (!timespec_equal(&inode->i_ctime, &fattr->ctime)) { @@ -1215,7 +1255,11 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) } memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime)); } - } + } else if (server->caps & NFS_CAP_CTIME) + invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL + | NFS_INO_REVAL_FORCED); /* Check if our cached file size is stale */ if (fattr->valid & NFS_ATTR_FATTR_SIZE) { @@ -1231,30 +1275,50 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) dprintk("NFS: isize change on server for file %s/%ld\n", inode->i_sb->s_id, inode->i_ino); } - } + } else + invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + | NFS_INO_REVAL_PAGECACHE + | NFS_INO_REVAL_FORCED); if (fattr->valid & NFS_ATTR_FATTR_ATIME) memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime)); + else if (server->caps & NFS_CAP_ATIME) + invalid |= save_cache_validity & (NFS_INO_INVALID_ATIME + | NFS_INO_REVAL_FORCED); if (fattr->valid & NFS_ATTR_FATTR_MODE) { if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) { invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; inode->i_mode = fattr->mode; } - } + } else if (server->caps & NFS_CAP_MODE) + invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL + | NFS_INO_REVAL_FORCED); + if (fattr->valid & NFS_ATTR_FATTR_OWNER) { if (inode->i_uid != fattr->uid) { invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; inode->i_uid = fattr->uid; } - } + } else if (server->caps & NFS_CAP_OWNER) + invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL + | NFS_INO_REVAL_FORCED); + if (fattr->valid & NFS_ATTR_FATTR_GROUP) { if (inode->i_gid != fattr->gid) { invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; inode->i_gid = fattr->gid; } - } + } else if (server->caps & NFS_CAP_OWNER_GROUP) + invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL + | NFS_INO_REVAL_FORCED); if (fattr->valid & NFS_ATTR_FATTR_NLINK) { if (inode->i_nlink != fattr->nlink) { @@ -1263,7 +1327,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) invalid |= NFS_INO_INVALID_DATA; inode->i_nlink = fattr->nlink; } - } + } else if (server->caps & NFS_CAP_NLINK) + invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR + | NFS_INO_REVAL_FORCED); if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { /* @@ -1293,9 +1359,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) || S_ISLNK(inode->i_mode))) invalid &= ~NFS_INO_INVALID_DATA; if (!nfs_have_delegation(inode, FMODE_READ) || - (nfsi->cache_validity & NFS_INO_REVAL_FORCED)) + (save_cache_validity & NFS_INO_REVAL_FORCED)) nfsi->cache_validity |= invalid; - nfsi->cache_validity &= ~NFS_INO_REVAL_FORCED; return 0; out_changed: @@ -1442,6 +1507,10 @@ static int __init init_nfs_fs(void) { int err; + err = nfs_dns_resolver_init(); + if (err < 0) + goto out8; + err = nfs_fscache_register(); if (err < 0) goto out7; @@ -1500,6 +1569,8 @@ out5: out6: nfs_fscache_unregister(); out7: + nfs_dns_resolver_destroy(); +out8: return err; } @@ -1511,6 +1582,7 @@ static void __exit exit_nfs_fs(void) nfs_destroy_inodecache(); nfs_destroy_nfspagecache(); nfs_fscache_unregister(); + nfs_dns_resolver_destroy(); #ifdef CONFIG_PROC_FS rpc_proc_unregister("nfs"); #endif diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 7dd90a6..e21b1bb 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -49,6 +49,11 @@ struct nfs_clone_mount { #define NFS_MAX_SECFLAVORS (12) /* + * Value used if the user did not specify a port value. + */ +#define NFS_UNSPEC_PORT (-1) + +/* * In-kernel mount arguments */ struct nfs_parsed_mount_data { @@ -63,6 +68,7 @@ struct nfs_parsed_mount_data { unsigned int auth_flavor_len; rpc_authflavor_t auth_flavors[1]; char *client_address; + unsigned int version; unsigned int minorversion; char *fscache_uniq; @@ -71,7 +77,7 @@ struct nfs_parsed_mount_data { size_t addrlen; char *hostname; u32 version; - unsigned short port; + int port; unsigned short protocol; } mount_server; @@ -80,7 +86,7 @@ struct nfs_parsed_mount_data { size_t addrlen; char *hostname; char *export_path; - unsigned short port; + int port; unsigned short protocol; } nfs_server; @@ -102,6 +108,7 @@ struct nfs_mount_request { }; extern int nfs_mount(struct nfs_mount_request *info); +extern void nfs_umount(const struct nfs_mount_request *info); /* client.c */ extern struct rpc_program nfs_program; @@ -213,7 +220,6 @@ void nfs_zap_acl_cache(struct inode *inode); extern int nfs_wait_bit_killable(void *word); /* super.c */ -void nfs_parse_ip_address(char *, size_t, struct sockaddr *, size_t *); extern struct file_system_type nfs_xdev_fs_type; #ifdef CONFIG_NFS_V4 extern struct file_system_type nfs4_xdev_fs_type; @@ -248,6 +254,12 @@ extern void nfs_read_prepare(struct rpc_task *task, void *calldata); /* write.c */ extern void nfs_write_prepare(struct rpc_task *task, void *calldata); +#ifdef CONFIG_MIGRATION +extern int nfs_migrate_page(struct address_space *, + struct page *, struct page *); +#else +#define nfs_migrate_page NULL +#endif /* nfs4proc.c */ extern int _nfs4_call_sync(struct nfs_server *server, @@ -368,24 +380,3 @@ unsigned int nfs_page_array_len(unsigned int base, size_t len) return ((unsigned long)len + (unsigned long)base + PAGE_SIZE - 1) >> PAGE_SHIFT; } - -#define IPV6_SCOPE_DELIMITER '%' - -/* - * Set the port number in an address. Be agnostic about the address - * family. - */ -static inline void nfs_set_port(struct sockaddr *sap, unsigned short port) -{ - struct sockaddr_in *ap = (struct sockaddr_in *)sap; - struct sockaddr_in6 *ap6 = (struct sockaddr_in6 *)sap; - - switch (sap->sa_family) { - case AF_INET: - ap->sin_port = htons(port); - break; - case AF_INET6: - ap6->sin6_port = htons(port); - break; - } -} diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index 38ef9ea..0adefc4 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -209,6 +209,71 @@ out_mnt_err: goto out; } +/** + * nfs_umount - Notify a server that we have unmounted this export + * @info: pointer to umount request arguments + * + * MOUNTPROC_UMNT is advisory, so we set a short timeout, and always + * use UDP. + */ +void nfs_umount(const struct nfs_mount_request *info) +{ + static const struct rpc_timeout nfs_umnt_timeout = { + .to_initval = 1 * HZ, + .to_maxval = 3 * HZ, + .to_retries = 2, + }; + struct rpc_create_args args = { + .protocol = IPPROTO_UDP, + .address = info->sap, + .addrsize = info->salen, + .timeout = &nfs_umnt_timeout, + .servername = info->hostname, + .program = &mnt_program, + .version = info->version, + .authflavor = RPC_AUTH_UNIX, + .flags = RPC_CLNT_CREATE_NOPING, + }; + struct mountres result; + struct rpc_message msg = { + .rpc_argp = info->dirpath, + .rpc_resp = &result, + }; + struct rpc_clnt *clnt; + int status; + + if (info->noresvport) + args.flags |= RPC_CLNT_CREATE_NONPRIVPORT; + + clnt = rpc_create(&args); + if (unlikely(IS_ERR(clnt))) + goto out_clnt_err; + + dprintk("NFS: sending UMNT request for %s:%s\n", + (info->hostname ? info->hostname : "server"), info->dirpath); + + if (info->version == NFS_MNT3_VERSION) + msg.rpc_proc = &clnt->cl_procinfo[MOUNTPROC3_UMNT]; + else + msg.rpc_proc = &clnt->cl_procinfo[MOUNTPROC_UMNT]; + + status = rpc_call_sync(clnt, &msg, 0); + rpc_shutdown_client(clnt); + + if (unlikely(status < 0)) + goto out_call_err; + + return; + +out_clnt_err: + dprintk("NFS: failed to create UMNT RPC client, status=%ld\n", + PTR_ERR(clnt)); + return; + +out_call_err: + dprintk("NFS: UMNT request failed, status=%d\n", status); +} + /* * XDR encode/decode functions for MOUNT */ @@ -258,7 +323,7 @@ static int decode_status(struct xdr_stream *xdr, struct mountres *res) return -EIO; status = ntohl(*p); - for (i = 0; i <= ARRAY_SIZE(mnt_errtbl); i++) { + for (i = 0; i < ARRAY_SIZE(mnt_errtbl); i++) { if (mnt_errtbl[i].status == status) { res->errno = mnt_errtbl[i].errno; return 0; @@ -309,7 +374,7 @@ static int decode_fhs_status(struct xdr_stream *xdr, struct mountres *res) return -EIO; status = ntohl(*p); - for (i = 0; i <= ARRAY_SIZE(mnt3_errtbl); i++) { + for (i = 0; i < ARRAY_SIZE(mnt3_errtbl); i++) { if (mnt3_errtbl[i].status == status) { res->errno = mnt3_errtbl[i].errno; return 0; @@ -407,6 +472,13 @@ static struct rpc_procinfo mnt_procedures[] = { .p_statidx = MOUNTPROC_MNT, .p_name = "MOUNT", }, + [MOUNTPROC_UMNT] = { + .p_proc = MOUNTPROC_UMNT, + .p_encode = (kxdrproc_t)mnt_enc_dirpath, + .p_arglen = MNT_enc_dirpath_sz, + .p_statidx = MOUNTPROC_UMNT, + .p_name = "UMOUNT", + }, }; static struct rpc_procinfo mnt3_procedures[] = { @@ -419,6 +491,13 @@ static struct rpc_procinfo mnt3_procedures[] = { .p_statidx = MOUNTPROC3_MNT, .p_name = "MOUNT", }, + [MOUNTPROC3_UMNT] = { + .p_proc = MOUNTPROC3_UMNT, + .p_encode = (kxdrproc_t)mnt_enc_dirpath, + .p_arglen = MNT_enc_dirpath_sz, + .p_statidx = MOUNTPROC3_UMNT, + .p_name = "UMOUNT", + }, }; diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index d0cc5ce..ee6a13f 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -299,7 +299,6 @@ static void nfs3_free_createdata(struct nfs3_createdata *data) /* * Create a regular file. - * For now, we don't implement O_EXCL. */ static int nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index 2a2a0a7..2636c26 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -17,6 +17,7 @@ #include <linux/inet.h> #include "internal.h" #include "nfs4_fs.h" +#include "dns_resolve.h" #define NFSDBG_FACILITY NFSDBG_VFS @@ -95,6 +96,20 @@ static int nfs4_validate_fspath(const struct vfsmount *mnt_parent, return 0; } +static size_t nfs_parse_server_name(char *string, size_t len, + struct sockaddr *sa, size_t salen) +{ + ssize_t ret; + + ret = rpc_pton(string, len, sa, salen); + if (ret == 0) { + ret = nfs_dns_resolve_name(string, len, sa, salen); + if (ret < 0) + ret = 0; + } + return ret; +} + static struct vfsmount *try_location(struct nfs_clone_mount *mountdata, char *page, char *page2, const struct nfs4_fs_location *location) @@ -121,11 +136,12 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata, if (memchr(buf->data, IPV6_SCOPE_DELIMITER, buf->len)) continue; - nfs_parse_ip_address(buf->data, buf->len, - mountdata->addr, &mountdata->addrlen); - if (mountdata->addr->sa_family == AF_UNSPEC) + mountdata->addrlen = nfs_parse_server_name(buf->data, + buf->len, + mountdata->addr, mountdata->addrlen); + if (mountdata->addrlen == 0) continue; - nfs_set_port(mountdata->addr, NFS_PORT); + rpc_set_port(mountdata->addr, NFS_PORT); memcpy(page2, buf->data, buf->len); page2[buf->len] = '\0'; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 6917311..be6544a 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -61,6 +61,8 @@ #define NFS4_POLL_RETRY_MIN (HZ/10) #define NFS4_POLL_RETRY_MAX (15*HZ) +#define NFS4_MAX_LOOP_ON_RECOVER (10) + struct nfs4_opendata; static int _nfs4_proc_open(struct nfs4_opendata *data); static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); @@ -426,17 +428,19 @@ out: static int nfs4_recover_session(struct nfs4_session *session) { struct nfs_client *clp = session->clp; + unsigned int loop; int ret; - for (;;) { + for (loop = NFS4_MAX_LOOP_ON_RECOVER; loop != 0; loop--) { ret = nfs4_wait_clnt_recover(clp); if (ret != 0) - return ret; + break; if (!test_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state)) break; nfs4_schedule_state_manager(clp); + ret = -EIO; } - return 0; + return ret; } static int nfs41_setup_sequence(struct nfs4_session *session, @@ -1444,18 +1448,20 @@ static int _nfs4_proc_open(struct nfs4_opendata *data) static int nfs4_recover_expired_lease(struct nfs_server *server) { struct nfs_client *clp = server->nfs_client; + unsigned int loop; int ret; - for (;;) { + for (loop = NFS4_MAX_LOOP_ON_RECOVER; loop != 0; loop--) { ret = nfs4_wait_clnt_recover(clp); if (ret != 0) - return ret; + break; if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) && !test_bit(NFS4CLNT_CHECK_LEASE,&clp->cl_state)) break; nfs4_schedule_state_recovery(clp); + ret = -EIO; } - return 0; + return ret; } /* @@ -1997,12 +2003,34 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f status = nfs4_call_sync(server, &msg, &args, &res, 0); if (status == 0) { memcpy(server->attr_bitmask, res.attr_bitmask, sizeof(server->attr_bitmask)); + server->caps &= ~(NFS_CAP_ACLS|NFS_CAP_HARDLINKS| + NFS_CAP_SYMLINKS|NFS_CAP_FILEID| + NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER| + NFS_CAP_OWNER_GROUP|NFS_CAP_ATIME| + NFS_CAP_CTIME|NFS_CAP_MTIME); if (res.attr_bitmask[0] & FATTR4_WORD0_ACL) server->caps |= NFS_CAP_ACLS; if (res.has_links != 0) server->caps |= NFS_CAP_HARDLINKS; if (res.has_symlinks != 0) server->caps |= NFS_CAP_SYMLINKS; + if (res.attr_bitmask[0] & FATTR4_WORD0_FILEID) + server->caps |= NFS_CAP_FILEID; + if (res.attr_bitmask[1] & FATTR4_WORD1_MODE) + server->caps |= NFS_CAP_MODE; + if (res.attr_bitmask[1] & FATTR4_WORD1_NUMLINKS) + server->caps |= NFS_CAP_NLINK; + if (res.attr_bitmask[1] & FATTR4_WORD1_OWNER) + server->caps |= NFS_CAP_OWNER; + if (res.attr_bitmask[1] & FATTR4_WORD1_OWNER_GROUP) + server->caps |= NFS_CAP_OWNER_GROUP; + if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_ACCESS) + server->caps |= NFS_CAP_ATIME; + if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_METADATA) + server->caps |= NFS_CAP_CTIME; + if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_MODIFY) + server->caps |= NFS_CAP_MTIME; + memcpy(server->cache_consistency_bitmask, res.attr_bitmask, sizeof(server->cache_consistency_bitmask)); server->cache_consistency_bitmask[0] &= FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE; server->cache_consistency_bitmask[1] &= FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY; diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 617273e..cfc30d3 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -702,29 +702,12 @@ struct compound_hdr { u32 minorversion; }; -/* - * START OF "GENERIC" ENCODE ROUTINES. - * These may look a little ugly since they are imported from a "generic" - * set of XDR encode/decode routines which are intended to be shared by - * all of our NFSv4 implementations (OpenBSD, MacOS X...). - * - * If the pain of reading these is too great, it should be a straightforward - * task to translate them into Linux-specific versions which are more - * consistent with the style used in NFSv2/v3... - */ -#define WRITE32(n) *p++ = htonl(n) -#define WRITE64(n) do { \ - *p++ = htonl((uint32_t)((n) >> 32)); \ - *p++ = htonl((uint32_t)(n)); \ -} while (0) -#define WRITEMEM(ptr,nbytes) do { \ - p = xdr_encode_opaque_fixed(p, ptr, nbytes); \ -} while (0) - -#define RESERVE_SPACE(nbytes) do { \ - p = xdr_reserve_space(xdr, nbytes); \ - BUG_ON(!p); \ -} while (0) +static __be32 *reserve_space(struct xdr_stream *xdr, size_t nbytes) +{ + __be32 *p = xdr_reserve_space(xdr, nbytes); + BUG_ON(!p); + return p; +} static void encode_string(struct xdr_stream *xdr, unsigned int len, const char *str) { @@ -749,12 +732,11 @@ static void encode_compound_hdr(struct xdr_stream *xdr, dprintk("encode_compound: tag=%.*s\n", (int)hdr->taglen, hdr->tag); BUG_ON(hdr->taglen > NFS4_MAXTAGLEN); - RESERVE_SPACE(12+(XDR_QUADLEN(hdr->taglen)<<2)); - WRITE32(hdr->taglen); - WRITEMEM(hdr->tag, hdr->taglen); - WRITE32(hdr->minorversion); + p = reserve_space(xdr, 4 + hdr->taglen + 8); + p = xdr_encode_opaque(p, hdr->tag, hdr->taglen); + *p++ = cpu_to_be32(hdr->minorversion); hdr->nops_p = p; - WRITE32(hdr->nops); + *p = cpu_to_be32(hdr->nops); } static void encode_nops(struct compound_hdr *hdr) @@ -829,55 +811,53 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const len += 16; else if (iap->ia_valid & ATTR_MTIME) len += 4; - RESERVE_SPACE(len); + p = reserve_space(xdr, len); /* * We write the bitmap length now, but leave the bitmap and the attribute * buffer length to be backfilled at the end of this routine. */ - WRITE32(2); + *p++ = cpu_to_be32(2); q = p; p += 3; if (iap->ia_valid & ATTR_SIZE) { bmval0 |= FATTR4_WORD0_SIZE; - WRITE64(iap->ia_size); + p = xdr_encode_hyper(p, iap->ia_size); } if (iap->ia_valid & ATTR_MODE) { bmval1 |= FATTR4_WORD1_MODE; - WRITE32(iap->ia_mode & S_IALLUGO); + *p++ = cpu_to_be32(iap->ia_mode & S_IALLUGO); } if (iap->ia_valid & ATTR_UID) { bmval1 |= FATTR4_WORD1_OWNER; - WRITE32(owner_namelen); - WRITEMEM(owner_name, owner_namelen); + p = xdr_encode_opaque(p, owner_name, owner_namelen); } if (iap->ia_valid & ATTR_GID) { bmval1 |= FATTR4_WORD1_OWNER_GROUP; - WRITE32(owner_grouplen); - WRITEMEM(owner_group, owner_grouplen); + p = xdr_encode_opaque(p, owner_group, owner_grouplen); } if (iap->ia_valid & ATTR_ATIME_SET) { bmval1 |= FATTR4_WORD1_TIME_ACCESS_SET; - WRITE32(NFS4_SET_TO_CLIENT_TIME); - WRITE32(0); - WRITE32(iap->ia_mtime.tv_sec); - WRITE32(iap->ia_mtime.tv_nsec); + *p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME); + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(iap->ia_mtime.tv_sec); + *p++ = cpu_to_be32(iap->ia_mtime.tv_nsec); } else if (iap->ia_valid & ATTR_ATIME) { bmval1 |= FATTR4_WORD1_TIME_ACCESS_SET; - WRITE32(NFS4_SET_TO_SERVER_TIME); + *p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME); } if (iap->ia_valid & ATTR_MTIME_SET) { bmval1 |= FATTR4_WORD1_TIME_MODIFY_SET; - WRITE32(NFS4_SET_TO_CLIENT_TIME); - WRITE32(0); - WRITE32(iap->ia_mtime.tv_sec); - WRITE32(iap->ia_mtime.tv_nsec); + *p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME); + *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(iap->ia_mtime.tv_sec); + *p++ = cpu_to_be32(iap->ia_mtime.tv_nsec); } else if (iap->ia_valid & ATTR_MTIME) { bmval1 |= FATTR4_WORD1_TIME_MODIFY_SET; - WRITE32(NFS4_SET_TO_SERVER_TIME); + *p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME); } /* @@ -891,7 +871,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const len = (char *)p - (char *)q - 12; *q++ = htonl(bmval0); *q++ = htonl(bmval1); - *q++ = htonl(len); + *q = htonl(len); /* out: */ } @@ -900,9 +880,9 @@ static void encode_access(struct xdr_stream *xdr, u32 access, struct compound_hd { __be32 *p; - RESERVE_SPACE(8); - WRITE32(OP_ACCESS); - WRITE32(access); + p = reserve_space(xdr, 8); + *p++ = cpu_to_be32(OP_ACCESS); + *p = cpu_to_be32(access); hdr->nops++; hdr->replen += decode_access_maxsz; } @@ -911,10 +891,10 @@ static void encode_close(struct xdr_stream *xdr, const struct nfs_closeargs *arg { __be32 *p; - RESERVE_SPACE(8+NFS4_STATEID_SIZE); - WRITE32(OP_CLOSE); - WRITE32(arg->seqid->sequence->counter); - WRITEMEM(arg->stateid->data, NFS4_STATEID_SIZE); + p = reserve_space(xdr, 8+NFS4_STATEID_SIZE); + *p++ = cpu_to_be32(OP_CLOSE); + *p++ = cpu_to_be32(arg->seqid->sequence->counter); + xdr_encode_opaque_fixed(p, arg->stateid->data, NFS4_STATEID_SIZE); hdr->nops++; hdr->replen += decode_close_maxsz; } @@ -923,10 +903,10 @@ static void encode_commit(struct xdr_stream *xdr, const struct nfs_writeargs *ar { __be32 *p; - RESERVE_SPACE(16); - WRITE32(OP_COMMIT); - WRITE64(args->offset); - WRITE32(args->count); + p = reserve_space(xdr, 16); + *p++ = cpu_to_be32(OP_COMMIT); + p = xdr_encode_hyper(p, args->offset); + *p = cpu_to_be32(args->count); hdr->nops++; hdr->replen += decode_commit_maxsz; } @@ -935,30 +915,28 @@ static void encode_create(struct xdr_stream *xdr, const struct nfs4_create_arg * { __be32 *p; - RESERVE_SPACE(8); - WRITE32(OP_CREATE); - WRITE32(create->ftype); + p = reserve_space(xdr, 8); + *p++ = cpu_to_be32(OP_CREATE); + *p = cpu_to_be32(create->ftype); switch (create->ftype) { case NF4LNK: - RESERVE_SPACE(4); - WRITE32(create->u.symlink.len); + p = reserve_space(xdr, 4); + *p = cpu_to_be32(create->u.symlink.len); xdr_write_pages(xdr, create->u.symlink.pages, 0, create->u.symlink.len); break; case NF4BLK: case NF4CHR: - RESERVE_SPACE(8); - WRITE32(create->u.device.specdata1); - WRITE32(create->u.device.specdata2); + p = reserve_space(xdr, 8); + *p++ = cpu_to_be32(create->u.device.specdata1); + *p = cpu_to_be32(create->u.device.specdata2); break; default: break; } - RESERVE_SPACE(4 + create->name->len); - WRITE32(create->name->len); - WRITEMEM(create->name->name, create->name->len); + encode_string(xdr, create->name->len, create->name->name); hdr->nops++; hdr->replen += decode_create_maxsz; @@ -969,10 +947,10 @@ static void encode_getattr_one(struct xdr_stream *xdr, uint32_t bitmap, struct c { __be32 *p; - RESERVE_SPACE(12); - WRITE32(OP_GETATTR); - WRITE32(1); - WRITE32(bitmap); + p = reserve_space(xdr, 12); + *p++ = cpu_to_be32(OP_GETATTR); + *p++ = cpu_to_be32(1); + *p = cpu_to_be32(bitmap); hdr->nops++; hdr->replen += decode_getattr_maxsz; } @@ -981,11 +959,11 @@ static void encode_getattr_two(struct xdr_stream *xdr, uint32_t bm0, uint32_t bm { __be32 *p; - RESERVE_SPACE(16); - WRITE32(OP_GETATTR); - WRITE32(2); - WRITE32(bm0); - WRITE32(bm1); + p = reserve_space(xdr, 16); + *p++ = cpu_to_be32(OP_GETATTR); + *p++ = cpu_to_be32(2); + *p++ = cpu_to_be32(bm0); + *p = cpu_to_be32(bm1); hdr->nops++; hdr->replen += decode_getattr_maxsz; } @@ -1012,8 +990,8 @@ static void encode_getfh(struct xdr_stream *xdr, struct compound_hdr *hdr) { __be32 *p; - RESERVE_SPACE(4); - WRITE32(OP_GETFH); + p = reserve_space(xdr, 4); + *p = cpu_to_be32(OP_GETFH); hdr->nops++; hdr->replen += decode_getfh_maxsz; } @@ -1022,10 +1000,9 @@ static void encode_link(struct xdr_stream *xdr, const struct qstr *name, struct { __be32 *p; - RESERVE_SPACE(8 + name->len); - WRITE32(OP_LINK); - WRITE32(name->len); - WRITEMEM(name->name, name->len); + p = reserve_space(xdr, 8 + name->len); + *p++ = cpu_to_be32(OP_LINK); + xdr_encode_opaque(p, name->name, name->len); hdr->nops++; hdr->replen += decode_link_maxsz; } @@ -1052,27 +1029,27 @@ static void encode_lock(struct xdr_stream *xdr, const struct nfs_lock_args *args { __be32 *p; - RESERVE_SPACE(32); - WRITE32(OP_LOCK); - WRITE32(nfs4_lock_type(args->fl, args->block)); - WRITE32(args->reclaim); - WRITE64(args->fl->fl_start); - WRITE64(nfs4_lock_length(args->fl)); - WRITE32(args->new_lock_owner); + p = reserve_space(xdr, 32); + *p++ = cpu_to_be32(OP_LOCK); + *p++ = cpu_to_be32(nfs4_lock_type(args->fl, args->block)); + *p++ = cpu_to_be32(args->reclaim); + p = xdr_encode_hyper(p, args->fl->fl_start); + p = xdr_encode_hyper(p, nfs4_lock_length(args->fl)); + *p = cpu_to_be32(args->new_lock_owner); if (args->new_lock_owner){ - RESERVE_SPACE(4+NFS4_STATEID_SIZE+32); - WRITE32(args->open_seqid->sequence->counter); - WRITEMEM(args->open_stateid->data, NFS4_STATEID_SIZE); - WRITE32(args->lock_seqid->sequence->counter); - WRITE64(args->lock_owner.clientid); - WRITE32(16); - WRITEMEM("lock id:", 8); - WRITE64(args->lock_owner.id); + p = reserve_space(xdr, 4+NFS4_STATEID_SIZE+32); + *p++ = cpu_to_be32(args->open_seqid->sequence->counter); + p = xdr_encode_opaque_fixed(p, args->open_stateid->data, NFS4_STATEID_SIZE); + *p++ = cpu_to_be32(args->lock_seqid->sequence->counter); + p = xdr_encode_hyper(p, args->lock_owner.clientid); + *p++ = cpu_to_be32(16); + p = xdr_encode_opaque_fixed(p, "lock id:", 8); + xdr_encode_hyper(p, args->lock_owner.id); } else { - RESERVE_SPACE(NFS4_STATEID_SIZE+4); - WRITEMEM(args->lock_stateid->data, NFS4_STATEID_SIZE); - WRITE32(args->lock_seqid->sequence->counter); + p = reserve_space(xdr, NFS4_STATEID_SIZE+4); + p = xdr_encode_opaque_fixed(p, args->lock_stateid->data, NFS4_STATEID_SIZE); + *p = cpu_to_be32(args->lock_seqid->sequence->counter); } hdr->nops++; hdr->replen += decode_lock_maxsz; @@ -1082,15 +1059,15 @@ static void encode_lockt(struct xdr_stream *xdr, const struct nfs_lockt_args *ar { __be32 *p; - RESERVE_SPACE(52); - WRITE32(OP_LOCKT); - WRITE32(nfs4_lock_type(args->fl, 0)); - WRITE64(args->fl->fl_start); - WRITE64(nfs4_lock_length(args->fl)); - WRITE64(args->lock_owner.clientid); - WRITE32(16); - WRITEMEM("lock id:", 8); - WRITE64(args->lock_owner.id); + p = reserve_space(xdr, 52); + *p++ = cpu_to_be32(OP_LOCKT); + *p++ = cpu_to_be32(nfs4_lock_type(args->fl, 0)); + p = xdr_encode_hyper(p, args->fl->fl_start); + p = xdr_encode_hyper(p, nfs4_lock_length(args->fl)); + p = xdr_encode_hyper(p, args->lock_owner.clientid); + *p++ = cpu_to_be32(16); + p = xdr_encode_opaque_fixed(p, "lock id:", 8); + xdr_encode_hyper(p, args->lock_owner.id); hdr->nops++; hdr->replen += decode_lockt_maxsz; } @@ -1099,13 +1076,13 @@ static void encode_locku(struct xdr_stream *xdr, const struct nfs_locku_args *ar { __be32 *p; - RESERVE_SPACE(12+NFS4_STATEID_SIZE+16); - WRITE32(OP_LOCKU); - WRITE32(nfs4_lock_type(args->fl, 0)); - WRITE32(args->seqid->sequence->counter); - WRITEMEM(args->stateid->data, NFS4_STATEID_SIZE); - WRITE64(args->fl->fl_start); - WRITE64(nfs4_lock_length(args->fl)); + p = reserve_space(xdr, 12+NFS4_STATEID_SIZE+16); + *p++ = cpu_to_be32(OP_LOCKU); + *p++ = cpu_to_be32(nfs4_lock_type(args->fl, 0)); + *p++ = cpu_to_be32(args->seqid->sequence->counter); + p = xdr_encode_opaque_fixed(p, args->stateid->data, NFS4_STATEID_SIZE); + p = xdr_encode_hyper(p, args->fl->fl_start); + xdr_encode_hyper(p, nfs4_lock_length(args->fl)); hdr->nops++; hdr->replen += decode_locku_maxsz; } @@ -1115,10 +1092,9 @@ static void encode_lookup(struct xdr_stream *xdr, const struct qstr *name, struc int len = name->len; __be32 *p; - RESERVE_SPACE(8 + len); - WRITE32(OP_LOOKUP); - WRITE32(len); - WRITEMEM(name->name, len); + p = reserve_space(xdr, 8 + len); + *p++ = cpu_to_be32(OP_LOOKUP); + xdr_encode_opaque(p, name->name, len); hdr->nops++; hdr->replen += decode_lookup_maxsz; } @@ -1127,21 +1103,21 @@ static void encode_share_access(struct xdr_stream *xdr, fmode_t fmode) { __be32 *p; - RESERVE_SPACE(8); + p = reserve_space(xdr, 8); switch (fmode & (FMODE_READ|FMODE_WRITE)) { case FMODE_READ: - WRITE32(NFS4_SHARE_ACCESS_READ); + *p++ = cpu_to_be32(NFS4_SHARE_ACCESS_READ); break; case FMODE_WRITE: - WRITE32(NFS4_SHARE_ACCESS_WRITE); + *p++ = cpu_to_be32(NFS4_SHARE_ACCESS_WRITE); break; case FMODE_READ|FMODE_WRITE: - WRITE32(NFS4_SHARE_ACCESS_BOTH); + *p++ = cpu_to_be32(NFS4_SHARE_ACCESS_BOTH); break; default: - WRITE32(0); + *p++ = cpu_to_be32(0); } - WRITE32(0); /* for linux, share_deny = 0 always */ + *p = cpu_to_be32(0); /* for linux, share_deny = 0 always */ } static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_openargs *arg) @@ -1151,29 +1127,29 @@ static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_opena * opcode 4, seqid 4, share_access 4, share_deny 4, clientid 8, ownerlen 4, * owner 4 = 32 */ - RESERVE_SPACE(8); - WRITE32(OP_OPEN); - WRITE32(arg->seqid->sequence->counter); + p = reserve_space(xdr, 8); + *p++ = cpu_to_be32(OP_OPEN); + *p = cpu_to_be32(arg->seqid->sequence->counter); encode_share_access(xdr, arg->fmode); - RESERVE_SPACE(28); - WRITE64(arg->clientid); - WRITE32(16); - WRITEMEM("open id:", 8); - WRITE64(arg->id); + p = reserve_space(xdr, 28); + p = xdr_encode_hyper(p, arg->clientid); + *p++ = cpu_to_be32(16); + p = xdr_encode_opaque_fixed(p, "open id:", 8); + xdr_encode_hyper(p, arg->id); } static inline void encode_createmode(struct xdr_stream *xdr, const struct nfs_openargs *arg) { __be32 *p; - RESERVE_SPACE(4); + p = reserve_space(xdr, 4); switch(arg->open_flags & O_EXCL) { case 0: - WRITE32(NFS4_CREATE_UNCHECKED); + *p = cpu_to_be32(NFS4_CREATE_UNCHECKED); encode_attrs(xdr, arg->u.attrs, arg->server); break; default: - WRITE32(NFS4_CREATE_EXCLUSIVE); + *p = cpu_to_be32(NFS4_CREATE_EXCLUSIVE); encode_nfs4_verifier(xdr, &arg->u.verifier); } } @@ -1182,14 +1158,14 @@ static void encode_opentype(struct xdr_stream *xdr, const struct nfs_openargs *a { __be32 *p; - RESERVE_SPACE(4); + p = reserve_space(xdr, 4); switch (arg->open_flags & O_CREAT) { case 0: - WRITE32(NFS4_OPEN_NOCREATE); + *p = cpu_to_be32(NFS4_OPEN_NOCREATE); break; default: BUG_ON(arg->claim != NFS4_OPEN_CLAIM_NULL); - WRITE32(NFS4_OPEN_CREATE); + *p = cpu_to_be32(NFS4_OPEN_CREATE); encode_createmode(xdr, arg); } } @@ -1198,16 +1174,16 @@ static inline void encode_delegation_type(struct xdr_stream *xdr, fmode_t delega { __be32 *p; - RESERVE_SPACE(4); + p = reserve_space(xdr, 4); switch (delegation_type) { case 0: - WRITE32(NFS4_OPEN_DELEGATE_NONE); + *p = cpu_to_be32(NFS4_OPEN_DELEGATE_NONE); break; case FMODE_READ: - WRITE32(NFS4_OPEN_DELEGATE_READ); + *p = cpu_to_be32(NFS4_OPEN_DELEGATE_READ); break; case FMODE_WRITE|FMODE_READ: - WRITE32(NFS4_OPEN_DELEGATE_WRITE); + *p = cpu_to_be32(NFS4_OPEN_DELEGATE_WRITE); break; default: BUG(); @@ -1218,8 +1194,8 @@ static inline void encode_claim_null(struct xdr_stream *xdr, const struct qstr * { __be32 *p; - RESERVE_SPACE(4); - WRITE32(NFS4_OPEN_CLAIM_NULL); + p = reserve_space(xdr, 4); + *p = cpu_to_be32(NFS4_OPEN_CLAIM_NULL); encode_string(xdr, name->len, name->name); } @@ -1227,8 +1203,8 @@ static inline void encode_claim_previous(struct xdr_stream *xdr, fmode_t type) { __be32 *p; - RESERVE_SPACE(4); - WRITE32(NFS4_OPEN_CLAIM_PREVIOUS); + p = reserve_space(xdr, 4); + *p = cpu_to_be32(NFS4_OPEN_CLAIM_PREVIOUS); encode_delegation_type(xdr, type); } @@ -1236,9 +1212,9 @@ static inline void encode_claim_delegate_cur(struct xdr_stream *xdr, const struc { __be32 *p; - RESERVE_SPACE(4+NFS4_STATEID_SIZE); - WRITE32(NFS4_OPEN_CLAIM_DELEGATE_CUR); - WRITEMEM(stateid->data, NFS4_STATEID_SIZE); + p = reserve_space(xdr, 4+NFS4_STATEID_SIZE); + *p++ = cpu_to_be32(NFS4_OPEN_CLAIM_DELEGATE_CUR); + xdr_encode_opaque_fixed(p, stateid->data, NFS4_STATEID_SIZE); encode_string(xdr, name->len, name->name); } @@ -1267,10 +1243,10 @@ static void encode_open_confirm(struct xdr_stream *xdr, const struct nfs_open_co { __be32 *p; - RESERVE_SPACE(4+NFS4_STATEID_SIZE+4); - WRITE32(OP_OPEN_CONFIRM); - WRITEMEM(arg->stateid->data, NFS4_STATEID_SIZE); - WRITE32(arg->seqid->sequence->counter); + p = reserve_space(xdr, 4+NFS4_STATEID_SIZE+4); + *p++ = cpu_to_be32(OP_OPEN_CONFIRM); + p = xdr_encode_opaque_fixed(p, arg->stateid->data, NFS4_STATEID_SIZE); + *p = cpu_to_be32(arg->seqid->sequence->counter); hdr->nops++; hdr->replen += decode_open_confirm_maxsz; } @@ -1279,10 +1255,10 @@ static void encode_open_downgrade(struct xdr_stream *xdr, const struct nfs_close { __be32 *p; - RESERVE_SPACE(4+NFS4_STATEID_SIZE+4); - WRITE32(OP_OPEN_DOWNGRADE); - WRITEMEM(arg->stateid->data, NFS4_STATEID_SIZE); - WRITE32(arg->seqid->sequence->counter); + p = reserve_space(xdr, 4+NFS4_STATEID_SIZE+4); + *p++ = cpu_to_be32(OP_OPEN_DOWNGRADE); + p = xdr_encode_opaque_fixed(p, arg->stateid->data, NFS4_STATEID_SIZE); + *p = cpu_to_be32(arg->seqid->sequence->counter); encode_share_access(xdr, arg->fmode); hdr->nops++; hdr->replen += decode_open_downgrade_maxsz; @@ -1294,10 +1270,9 @@ encode_putfh(struct xdr_stream *xdr, const struct nfs_fh *fh, struct compound_hd int len = fh->size; __be32 *p; - RESERVE_SPACE(8 + len); - WRITE32(OP_PUTFH); - WRITE32(len); - WRITEMEM(fh->data, len); + p = reserve_space(xdr, 8 + len); + *p++ = cpu_to_be32(OP_PUTFH); + xdr_encode_opaque(p, fh->data, len); hdr->nops++; hdr->replen += decode_putfh_maxsz; } @@ -1306,8 +1281,8 @@ static void encode_putrootfh(struct xdr_stream *xdr, struct compound_hdr *hdr) { __be32 *p; - RESERVE_SPACE(4); - WRITE32(OP_PUTROOTFH); + p = reserve_space(xdr, 4); + *p = cpu_to_be32(OP_PUTROOTFH); hdr->nops++; hdr->replen += decode_putrootfh_maxsz; } @@ -1317,26 +1292,26 @@ static void encode_stateid(struct xdr_stream *xdr, const struct nfs_open_context nfs4_stateid stateid; __be32 *p; - RESERVE_SPACE(NFS4_STATEID_SIZE); + p = reserve_space(xdr, NFS4_STATEID_SIZE); if (ctx->state != NULL) { nfs4_copy_stateid(&stateid, ctx->state, ctx->lockowner); - WRITEMEM(stateid.data, NFS4_STATEID_SIZE); + xdr_encode_opaque_fixed(p, stateid.data, NFS4_STATEID_SIZE); } else - WRITEMEM(zero_stateid.data, NFS4_STATEID_SIZE); + xdr_encode_opaque_fixed(p, zero_stateid.data, NFS4_STATEID_SIZE); } static void encode_read(struct xdr_stream *xdr, const struct nfs_readargs *args, struct compound_hdr *hdr) { __be32 *p; - RESERVE_SPACE(4); - WRITE32(OP_READ); + p = reserve_space(xdr, 4); + *p = cpu_to_be32(OP_READ); encode_stateid(xdr, args->context); - RESERVE_SPACE(12); - WRITE64(args->offset); - WRITE32(args->count); + p = reserve_space(xdr, 12); + p = xdr_encode_hyper(p, args->offset); + *p = cpu_to_be32(args->count); hdr->nops++; hdr->replen += decode_read_maxsz; } @@ -1349,20 +1324,20 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg }; __be32 *p; - RESERVE_SPACE(12+NFS4_VERIFIER_SIZE+20); - WRITE32(OP_READDIR); - WRITE64(readdir->cookie); - WRITEMEM(readdir->verifier.data, NFS4_VERIFIER_SIZE); - WRITE32(readdir->count >> 1); /* We're not doing readdirplus */ - WRITE32(readdir->count); - WRITE32(2); + p = reserve_space(xdr, 12+NFS4_VERIFIER_SIZE+20); + *p++ = cpu_to_be32(OP_READDIR); + p = xdr_encode_hyper(p, readdir->cookie); + p = xdr_encode_opaque_fixed(p, readdir->verifier.data, NFS4_VERIFIER_SIZE); + *p++ = cpu_to_be32(readdir->count >> 1); /* We're not doing readdirplus */ + *p++ = cpu_to_be32(readdir->count); + *p++ = cpu_to_be32(2); /* Switch to mounted_on_fileid if the server supports it */ if (readdir->bitmask[1] & FATTR4_WORD1_MOUNTED_ON_FILEID) attrs[0] &= ~FATTR4_WORD0_FILEID; else attrs[1] &= ~FATTR4_WORD1_MOUNTED_ON_FILEID; - WRITE32(attrs[0] & readdir->bitmask[0]); - WRITE32(attrs[1] & readdir->bitmask[1]); + *p++ = cpu_to_be32(attrs[0] & readdir->bitmask[0]); + *p = cpu_to_be32(attrs[1] & readdir->bitmask[1]); hdr->nops++; hdr->replen += decode_readdir_maxsz; dprintk("%s: cookie = %Lu, verifier = %08x:%08x, bitmap = %08x:%08x\n", @@ -1378,8 +1353,8 @@ static void encode_readlink(struct xdr_stream *xdr, const struct nfs4_readlink * { __be32 *p; - RESERVE_SPACE(4); - WRITE32(OP_READLINK); + p = reserve_space(xdr, 4); + *p = cpu_to_be32(OP_READLINK); hdr->nops++; hdr->replen += decode_readlink_maxsz; } @@ -1388,10 +1363,9 @@ static void encode_remove(struct xdr_stream *xdr, const struct qstr *name, struc { __be32 *p; - RESERVE_SPACE(8 + name->len); - WRITE32(OP_REMOVE); - WRITE32(name->len); - WRITEMEM(name->name, name->len); + p = reserve_space(xdr, 8 + name->len); + *p++ = cpu_to_be32(OP_REMOVE); + xdr_encode_opaque(p, name->name, name->len); hdr->nops++; hdr->replen += decode_remove_maxsz; } @@ -1400,14 +1374,10 @@ static void encode_rename(struct xdr_stream *xdr, const struct qstr *oldname, co { __be32 *p; - RESERVE_SPACE(8 + oldname->len); - WRITE32(OP_RENAME); - WRITE32(oldname->len); - WRITEMEM(oldname->name, oldname->len); - - RESERVE_SPACE(4 + newname->len); - WRITE32(newname->len); - WRITEMEM(newname->name, newname->len); + p = reserve_space(xdr, 4); + *p = cpu_to_be32(OP_RENAME); + encode_string(xdr, oldname->len, oldname->name); + encode_string(xdr, newname->len, newname->name); hdr->nops++; hdr->replen += decode_rename_maxsz; } @@ -1416,9 +1386,9 @@ static void encode_renew(struct xdr_stream *xdr, const struct nfs_client *client { __be32 *p; - RESERVE_SPACE(12); - WRITE32(OP_RENEW); - WRITE64(client_stateid->cl_clientid); + p = reserve_space(xdr, 12); + *p++ = cpu_to_be32(OP_RENEW); + xdr_encode_hyper(p, client_stateid->cl_clientid); hdr->nops++; hdr->replen += decode_renew_maxsz; } @@ -1428,8 +1398,8 @@ encode_restorefh(struct xdr_stream *xdr, struct compound_hdr *hdr) { __be32 *p; - RESERVE_SPACE(4); - WRITE32(OP_RESTOREFH); + p = reserve_space(xdr, 4); + *p = cpu_to_be32(OP_RESTOREFH); hdr->nops++; hdr->replen += decode_restorefh_maxsz; } @@ -1439,16 +1409,16 @@ encode_setacl(struct xdr_stream *xdr, struct nfs_setaclargs *arg, struct compoun { __be32 *p; - RESERVE_SPACE(4+NFS4_STATEID_SIZE); - WRITE32(OP_SETATTR); - WRITEMEM(zero_stateid.data, NFS4_STATEID_SIZE); - RESERVE_SPACE(2*4); - WRITE32(1); - WRITE32(FATTR4_WORD0_ACL); + p = reserve_space(xdr, 4+NFS4_STATEID_SIZE); + *p++ = cpu_to_be32(OP_SETATTR); + xdr_encode_opaque_fixed(p, zero_stateid.data, NFS4_STATEID_SIZE); + p = reserve_space(xdr, 2*4); + *p++ = cpu_to_be32(1); + *p = cpu_to_be32(FATTR4_WORD0_ACL); if (arg->acl_len % 4) return -EINVAL; - RESERVE_SPACE(4); - WRITE32(arg->acl_len); + p = reserve_space(xdr, 4); + *p = cpu_to_be32(arg->acl_len); xdr_write_pages(xdr, arg->acl_pages, arg->acl_pgbase, arg->acl_len); hdr->nops++; hdr->replen += decode_setacl_maxsz; @@ -1460,8 +1430,8 @@ encode_savefh(struct xdr_stream *xdr, struct compound_hdr *hdr) { __be32 *p; - RESERVE_SPACE(4); - WRITE32(OP_SAVEFH); + p = reserve_space(xdr, 4); + *p = cpu_to_be32(OP_SAVEFH); hdr->nops++; hdr->replen += decode_savefh_maxsz; } @@ -1470,9 +1440,9 @@ static void encode_setattr(struct xdr_stream *xdr, const struct nfs_setattrargs { __be32 *p; - RESERVE_SPACE(4+NFS4_STATEID_SIZE); - WRITE32(OP_SETATTR); - WRITEMEM(arg->stateid.data, NFS4_STATEID_SIZE); + p = reserve_space(xdr, 4+NFS4_STATEID_SIZE); + *p++ = cpu_to_be32(OP_SETATTR); + xdr_encode_opaque_fixed(p, arg->stateid.data, NFS4_STATEID_SIZE); hdr->nops++; hdr->replen += decode_setattr_maxsz; encode_attrs(xdr, arg->iap, server); @@ -1482,17 +1452,17 @@ static void encode_setclientid(struct xdr_stream *xdr, const struct nfs4_setclie { __be32 *p; - RESERVE_SPACE(4 + NFS4_VERIFIER_SIZE); - WRITE32(OP_SETCLIENTID); - WRITEMEM(setclientid->sc_verifier->data, NFS4_VERIFIER_SIZE); + p = reserve_space(xdr, 4 + NFS4_VERIFIER_SIZE); + *p++ = cpu_to_be32(OP_SETCLIENTID); + xdr_encode_opaque_fixed(p, setclientid->sc_verifier->data, NFS4_VERIFIER_SIZE); encode_string(xdr, setclientid->sc_name_len, setclientid->sc_name); - RESERVE_SPACE(4); - WRITE32(setclientid->sc_prog); + p = reserve_space(xdr, 4); + *p = cpu_to_be32(setclientid->sc_prog); encode_string(xdr, setclientid->sc_netid_len, setclientid->sc_netid); encode_string(xdr, setclientid->sc_uaddr_len, setclientid->sc_uaddr); - RESERVE_SPACE(4); - WRITE32(setclientid->sc_cb_ident); + p = reserve_space(xdr, 4); + *p = cpu_to_be32(setclientid->sc_cb_ident); hdr->nops++; hdr->replen += decode_setclientid_maxsz; } @@ -1501,10 +1471,10 @@ static void encode_setclientid_confirm(struct xdr_stream *xdr, const struct nfs_ { __be32 *p; - RESERVE_SPACE(12 + NFS4_VERIFIER_SIZE); - WRITE32(OP_SETCLIENTID_CONFIRM); - WRITE64(client_state->cl_clientid); - WRITEMEM(client_state->cl_confirm.data, NFS4_VERIFIER_SIZE); + p = reserve_space(xdr, 12 + NFS4_VERIFIER_SIZE); + *p++ = cpu_to_be32(OP_SETCLIENTID_CONFIRM); + p = xdr_encode_hyper(p, client_state->cl_clientid); + xdr_encode_opaque_fixed(p, client_state->cl_confirm.data, NFS4_VERIFIER_SIZE); hdr->nops++; hdr->replen += decode_setclientid_confirm_maxsz; } @@ -1513,15 +1483,15 @@ static void encode_write(struct xdr_stream *xdr, const struct nfs_writeargs *arg { __be32 *p; - RESERVE_SPACE(4); - WRITE32(OP_WRITE); + p = reserve_space(xdr, 4); + *p = cpu_to_be32(OP_WRITE); encode_stateid(xdr, args->context); - RESERVE_SPACE(16); - WRITE64(args->offset); - WRITE32(args->stable); - WRITE32(args->count); + p = reserve_space(xdr, 16); + p = xdr_encode_hyper(p, args->offset); + *p++ = cpu_to_be32(args->stable); + *p = cpu_to_be32(args->count); xdr_write_pages(xdr, args->pages, args->pgbase, args->count); hdr->nops++; @@ -1532,10 +1502,10 @@ static void encode_delegreturn(struct xdr_stream *xdr, const nfs4_stateid *state { __be32 *p; - RESERVE_SPACE(4+NFS4_STATEID_SIZE); + p = reserve_space(xdr, 4+NFS4_STATEID_SIZE); - WRITE32(OP_DELEGRETURN); - WRITEMEM(stateid->data, NFS4_STATEID_SIZE); + *p++ = cpu_to_be32(OP_DELEGRETURN); + xdr_encode_opaque_fixed(p, stateid->data, NFS4_STATEID_SIZE); hdr->nops++; hdr->replen += decode_delegreturn_maxsz; } @@ -1548,16 +1518,16 @@ static void encode_exchange_id(struct xdr_stream *xdr, { __be32 *p; - RESERVE_SPACE(4 + sizeof(args->verifier->data)); - WRITE32(OP_EXCHANGE_ID); - WRITEMEM(args->verifier->data, sizeof(args->verifier->data)); + p = reserve_space(xdr, 4 + sizeof(args->verifier->data)); + *p++ = cpu_to_be32(OP_EXCHANGE_ID); + xdr_encode_opaque_fixed(p, args->verifier->data, sizeof(args->verifier->data)); encode_string(xdr, args->id_len, args->id); - RESERVE_SPACE(12); - WRITE32(args->flags); - WRITE32(0); /* zero length state_protect4_a */ - WRITE32(0); /* zero length implementation id array */ + p = reserve_space(xdr, 12); + *p++ = cpu_to_be32(args->flags); + *p++ = cpu_to_be32(0); /* zero length state_protect4_a */ + *p = cpu_to_be32(0); /* zero length implementation id array */ hdr->nops++; hdr->replen += decode_exchange_id_maxsz; } @@ -1571,55 +1541,43 @@ static void encode_create_session(struct xdr_stream *xdr, uint32_t len; struct nfs_client *clp = args->client; - RESERVE_SPACE(4); - WRITE32(OP_CREATE_SESSION); - - RESERVE_SPACE(8); - WRITE64(clp->cl_ex_clid); + len = scnprintf(machine_name, sizeof(machine_name), "%s", + clp->cl_ipaddr); - RESERVE_SPACE(8); - WRITE32(clp->cl_seqid); /*Sequence id */ - WRITE32(args->flags); /*flags */ + p = reserve_space(xdr, 20 + 2*28 + 20 + len + 12); + *p++ = cpu_to_be32(OP_CREATE_SESSION); + p = xdr_encode_hyper(p, clp->cl_ex_clid); + *p++ = cpu_to_be32(clp->cl_seqid); /*Sequence id */ + *p++ = cpu_to_be32(args->flags); /*flags */ - RESERVE_SPACE(2*28); /* 2 channel_attrs */ /* Fore Channel */ - WRITE32(args->fc_attrs.headerpadsz); /* header padding size */ - WRITE32(args->fc_attrs.max_rqst_sz); /* max req size */ - WRITE32(args->fc_attrs.max_resp_sz); /* max resp size */ - WRITE32(args->fc_attrs.max_resp_sz_cached); /* Max resp sz cached */ - WRITE32(args->fc_attrs.max_ops); /* max operations */ - WRITE32(args->fc_attrs.max_reqs); /* max requests */ - WRITE32(0); /* rdmachannel_attrs */ + *p++ = cpu_to_be32(args->fc_attrs.headerpadsz); /* header padding size */ + *p++ = cpu_to_be32(args->fc_attrs.max_rqst_sz); /* max req size */ + *p++ = cpu_to_be32(args->fc_attrs.max_resp_sz); /* max resp size */ + *p++ = cpu_to_be32(args->fc_attrs.max_resp_sz_cached); /* Max resp sz cached */ + *p++ = cpu_to_be32(args->fc_attrs.max_ops); /* max operations */ + *p++ = cpu_to_be32(args->fc_attrs.max_reqs); /* max requests */ + *p++ = cpu_to_be32(0); /* rdmachannel_attrs */ /* Back Channel */ - WRITE32(args->fc_attrs.headerpadsz); /* header padding size */ - WRITE32(args->bc_attrs.max_rqst_sz); /* max req size */ - WRITE32(args->bc_attrs.max_resp_sz); /* max resp size */ - WRITE32(args->bc_attrs.max_resp_sz_cached); /* Max resp sz cached */ - WRITE32(args->bc_attrs.max_ops); /* max operations */ - WRITE32(args->bc_attrs.max_reqs); /* max requests */ - WRITE32(0); /* rdmachannel_attrs */ - - RESERVE_SPACE(4); - WRITE32(args->cb_program); /* cb_program */ - - RESERVE_SPACE(4); /* # of security flavors */ - WRITE32(1); - - RESERVE_SPACE(4); - WRITE32(RPC_AUTH_UNIX); /* auth_sys */ + *p++ = cpu_to_be32(args->fc_attrs.headerpadsz); /* header padding size */ + *p++ = cpu_to_be32(args->bc_attrs.max_rqst_sz); /* max req size */ + *p++ = cpu_to_be32(args->bc_attrs.max_resp_sz); /* max resp size */ + *p++ = cpu_to_be32(args->bc_attrs.max_resp_sz_cached); /* Max resp sz cached */ + *p++ = cpu_to_be32(args->bc_attrs.max_ops); /* max operations */ + *p++ = cpu_to_be32(args->bc_attrs.max_reqs); /* max requests */ + *p++ = cpu_to_be32(0); /* rdmachannel_attrs */ + + *p++ = cpu_to_be32(args->cb_program); /* cb_program */ + *p++ = cpu_to_be32(1); + *p++ = cpu_to_be32(RPC_AUTH_UNIX); /* auth_sys */ /* authsys_parms rfc1831 */ - RESERVE_SPACE(4); - WRITE32((u32)clp->cl_boot_time.tv_nsec); /* stamp */ - len = scnprintf(machine_name, sizeof(machine_name), "%s", - clp->cl_ipaddr); - RESERVE_SPACE(16 + len); - WRITE32(len); - WRITEMEM(machine_name, len); - WRITE32(0); /* UID */ - WRITE32(0); /* GID */ - WRITE32(0); /* No more gids */ + *p++ = cpu_to_be32((u32)clp->cl_boot_time.tv_nsec); /* stamp */ + p = xdr_encode_opaque(p, machine_name, len); + *p++ = cpu_to_be32(0); /* UID */ + *p++ = cpu_to_be32(0); /* GID */ + *p = cpu_to_be32(0); /* No more gids */ hdr->nops++; hdr->replen += decode_create_session_maxsz; } @@ -1629,9 +1587,9 @@ static void encode_destroy_session(struct xdr_stream *xdr, struct compound_hdr *hdr) { __be32 *p; - RESERVE_SPACE(4 + NFS4_MAX_SESSIONID_LEN); - WRITE32(OP_DESTROY_SESSION); - WRITEMEM(session->sess_id.data, NFS4_MAX_SESSIONID_LEN); + p = reserve_space(xdr, 4 + NFS4_MAX_SESSIONID_LEN); + *p++ = cpu_to_be32(OP_DESTROY_SESSION); + xdr_encode_opaque_fixed(p, session->sess_id.data, NFS4_MAX_SESSIONID_LEN); hdr->nops++; hdr->replen += decode_destroy_session_maxsz; } @@ -1655,8 +1613,8 @@ static void encode_sequence(struct xdr_stream *xdr, WARN_ON(args->sa_slotid == NFS4_MAX_SLOT_TABLE); slot = tp->slots + args->sa_slotid; - RESERVE_SPACE(4); - WRITE32(OP_SEQUENCE); + p = reserve_space(xdr, 4 + NFS4_MAX_SESSIONID_LEN + 16); + *p++ = cpu_to_be32(OP_SEQUENCE); /* * Sessionid + seqid + slotid + max slotid + cache_this @@ -1670,12 +1628,11 @@ static void encode_sequence(struct xdr_stream *xdr, ((u32 *)session->sess_id.data)[3], slot->seq_nr, args->sa_slotid, tp->highest_used_slotid, args->sa_cache_this); - RESERVE_SPACE(NFS4_MAX_SESSIONID_LEN + 16); - WRITEMEM(session->sess_id.data, NFS4_MAX_SESSIONID_LEN); - WRITE32(slot->seq_nr); - WRITE32(args->sa_slotid); - WRITE32(tp->highest_used_slotid); - WRITE32(args->sa_cache_this); + p = xdr_encode_opaque_fixed(p, session->sess_id.data, NFS4_MAX_SESSIONID_LEN); + *p++ = cpu_to_be32(slot->seq_nr); + *p++ = cpu_to_be32(args->sa_slotid); + *p++ = cpu_to_be32(tp->highest_used_slotid); + *p = cpu_to_be32(args->sa_cache_this); hdr->nops++; hdr->replen += decode_sequence_maxsz; #endif /* CONFIG_NFS_V4_1 */ @@ -2466,68 +2423,53 @@ static int nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req, uint32_t *p, } #endif /* CONFIG_NFS_V4_1 */ -/* - * START OF "GENERIC" DECODE ROUTINES. - * These may look a little ugly since they are imported from a "generic" - * set of XDR encode/decode routines which are intended to be shared by - * all of our NFSv4 implementations (OpenBSD, MacOS X...). - * - * If the pain of reading these is too great, it should be a straightforward - * task to translate them into Linux-specific versions which are more - * consistent with the style used in NFSv2/v3... - */ -#define READ32(x) (x) = ntohl(*p++) -#define READ64(x) do { \ - (x) = (u64)ntohl(*p++) << 32; \ - (x) |= ntohl(*p++); \ -} while (0) -#define READTIME(x) do { \ - p++; \ - (x.tv_sec) = ntohl(*p++); \ - (x.tv_nsec) = ntohl(*p++); \ -} while (0) -#define COPYMEM(x,nbytes) do { \ - memcpy((x), p, nbytes); \ - p += XDR_QUADLEN(nbytes); \ -} while (0) - -#define READ_BUF(nbytes) do { \ - p = xdr_inline_decode(xdr, nbytes); \ - if (unlikely(!p)) { \ - dprintk("nfs: %s: prematurely hit end of receive" \ - " buffer\n", __func__); \ - dprintk("nfs: %s: xdr->p=%p, bytes=%u, xdr->end=%p\n", \ - __func__, xdr->p, nbytes, xdr->end); \ - return -EIO; \ - } \ -} while (0) +static void print_overflow_msg(const char *func, const struct xdr_stream *xdr) +{ + dprintk("nfs: %s: prematurely hit end of receive buffer. " + "Remaining buffer length is %tu words.\n", + func, xdr->end - xdr->p); +} static int decode_opaque_inline(struct xdr_stream *xdr, unsigned int *len, char **string) { __be32 *p; - READ_BUF(4); - READ32(*len); - READ_BUF(*len); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + *len = be32_to_cpup(p); + p = xdr_inline_decode(xdr, *len); + if (unlikely(!p)) + goto out_overflow; *string = (char *)p; return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_compound_hdr(struct xdr_stream *xdr, struct compound_hdr *hdr) { __be32 *p; - READ_BUF(8); - READ32(hdr->status); - READ32(hdr->taglen); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + hdr->status = be32_to_cpup(p++); + hdr->taglen = be32_to_cpup(p); - READ_BUF(hdr->taglen + 4); + p = xdr_inline_decode(xdr, hdr->taglen + 4); + if (unlikely(!p)) + goto out_overflow; hdr->tag = (char *)p; p += XDR_QUADLEN(hdr->taglen); - READ32(hdr->nops); + hdr->nops = be32_to_cpup(p); if (unlikely(hdr->nops < 1)) return nfs4_stat_to_errno(hdr->status); return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected) @@ -2536,18 +2478,23 @@ static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected) uint32_t opnum; int32_t nfserr; - READ_BUF(8); - READ32(opnum); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + opnum = be32_to_cpup(p++); if (opnum != expected) { dprintk("nfs: Server returned operation" " %d but we issued a request for %d\n", opnum, expected); return -EIO; } - READ32(nfserr); + nfserr = be32_to_cpup(p); if (nfserr != NFS_OK) return nfs4_stat_to_errno(nfserr); return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } /* Dummy routine */ @@ -2557,8 +2504,11 @@ static int decode_ace(struct xdr_stream *xdr, void *ace, struct nfs_client *clp) unsigned int strlen; char *str; - READ_BUF(12); - return decode_opaque_inline(xdr, &strlen, &str); + p = xdr_inline_decode(xdr, 12); + if (likely(p)) + return decode_opaque_inline(xdr, &strlen, &str); + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_bitmap(struct xdr_stream *xdr, uint32_t *bitmap) @@ -2566,27 +2516,39 @@ static int decode_attr_bitmap(struct xdr_stream *xdr, uint32_t *bitmap) uint32_t bmlen; __be32 *p; - READ_BUF(4); - READ32(bmlen); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + bmlen = be32_to_cpup(p); bitmap[0] = bitmap[1] = 0; - READ_BUF((bmlen << 2)); + p = xdr_inline_decode(xdr, (bmlen << 2)); + if (unlikely(!p)) + goto out_overflow; if (bmlen > 0) { - READ32(bitmap[0]); + bitmap[0] = be32_to_cpup(p++); if (bmlen > 1) - READ32(bitmap[1]); + bitmap[1] = be32_to_cpup(p); } return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static inline int decode_attr_length(struct xdr_stream *xdr, uint32_t *attrlen, __be32 **savep) { __be32 *p; - READ_BUF(4); - READ32(*attrlen); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + *attrlen = be32_to_cpup(p); *savep = xdr->p; return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_supported(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *bitmask) @@ -2609,8 +2571,10 @@ static int decode_attr_type(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t * if (unlikely(bitmap[0] & (FATTR4_WORD0_TYPE - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_TYPE)) { - READ_BUF(4); - READ32(*type); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + *type = be32_to_cpup(p); if (*type < NF4REG || *type > NF4NAMEDATTR) { dprintk("%s: bad type %d\n", __func__, *type); return -EIO; @@ -2620,6 +2584,9 @@ static int decode_attr_type(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t * } dprintk("%s: type=0%o\n", __func__, nfs_type2fmt[*type]); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_change(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *change) @@ -2631,14 +2598,19 @@ static int decode_attr_change(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t if (unlikely(bitmap[0] & (FATTR4_WORD0_CHANGE - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_CHANGE)) { - READ_BUF(8); - READ64(*change); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, change); bitmap[0] &= ~FATTR4_WORD0_CHANGE; ret = NFS_ATTR_FATTR_CHANGE; } dprintk("%s: change attribute=%Lu\n", __func__, (unsigned long long)*change); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_size(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *size) @@ -2650,13 +2622,18 @@ static int decode_attr_size(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t * if (unlikely(bitmap[0] & (FATTR4_WORD0_SIZE - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_SIZE)) { - READ_BUF(8); - READ64(*size); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, size); bitmap[0] &= ~FATTR4_WORD0_SIZE; ret = NFS_ATTR_FATTR_SIZE; } dprintk("%s: file size=%Lu\n", __func__, (unsigned long long)*size); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_link_support(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) @@ -2667,12 +2644,17 @@ static int decode_attr_link_support(struct xdr_stream *xdr, uint32_t *bitmap, ui if (unlikely(bitmap[0] & (FATTR4_WORD0_LINK_SUPPORT - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_LINK_SUPPORT)) { - READ_BUF(4); - READ32(*res); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + *res = be32_to_cpup(p); bitmap[0] &= ~FATTR4_WORD0_LINK_SUPPORT; } dprintk("%s: link support=%s\n", __func__, *res == 0 ? "false" : "true"); return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_symlink_support(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) @@ -2683,12 +2665,17 @@ static int decode_attr_symlink_support(struct xdr_stream *xdr, uint32_t *bitmap, if (unlikely(bitmap[0] & (FATTR4_WORD0_SYMLINK_SUPPORT - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_SYMLINK_SUPPORT)) { - READ_BUF(4); - READ32(*res); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + *res = be32_to_cpup(p); bitmap[0] &= ~FATTR4_WORD0_SYMLINK_SUPPORT; } dprintk("%s: symlink support=%s\n", __func__, *res == 0 ? "false" : "true"); return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_fsid(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_fsid *fsid) @@ -2701,9 +2688,11 @@ static int decode_attr_fsid(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs if (unlikely(bitmap[0] & (FATTR4_WORD0_FSID - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_FSID)) { - READ_BUF(16); - READ64(fsid->major); - READ64(fsid->minor); + p = xdr_inline_decode(xdr, 16); + if (unlikely(!p)) + goto out_overflow; + p = xdr_decode_hyper(p, &fsid->major); + xdr_decode_hyper(p, &fsid->minor); bitmap[0] &= ~FATTR4_WORD0_FSID; ret = NFS_ATTR_FATTR_FSID; } @@ -2711,6 +2700,9 @@ static int decode_attr_fsid(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs (unsigned long long)fsid->major, (unsigned long long)fsid->minor); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_lease_time(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) @@ -2721,12 +2713,17 @@ static int decode_attr_lease_time(struct xdr_stream *xdr, uint32_t *bitmap, uint if (unlikely(bitmap[0] & (FATTR4_WORD0_LEASE_TIME - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_LEASE_TIME)) { - READ_BUF(4); - READ32(*res); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + *res = be32_to_cpup(p); bitmap[0] &= ~FATTR4_WORD0_LEASE_TIME; } dprintk("%s: file size=%u\n", __func__, (unsigned int)*res); return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) @@ -2737,12 +2734,17 @@ static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint if (unlikely(bitmap[0] & (FATTR4_WORD0_ACLSUPPORT - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_ACLSUPPORT)) { - READ_BUF(4); - READ32(*res); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + *res = be32_to_cpup(p); bitmap[0] &= ~FATTR4_WORD0_ACLSUPPORT; } dprintk("%s: ACLs supported=%u\n", __func__, (unsigned int)*res); return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *fileid) @@ -2754,13 +2756,18 @@ static int decode_attr_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t if (unlikely(bitmap[0] & (FATTR4_WORD0_FILEID - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_FILEID)) { - READ_BUF(8); - READ64(*fileid); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, fileid); bitmap[0] &= ~FATTR4_WORD0_FILEID; ret = NFS_ATTR_FATTR_FILEID; } dprintk("%s: fileid=%Lu\n", __func__, (unsigned long long)*fileid); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_mounted_on_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *fileid) @@ -2772,13 +2779,18 @@ static int decode_attr_mounted_on_fileid(struct xdr_stream *xdr, uint32_t *bitma if (unlikely(bitmap[1] & (FATTR4_WORD1_MOUNTED_ON_FILEID - 1U))) return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_MOUNTED_ON_FILEID)) { - READ_BUF(8); - READ64(*fileid); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, fileid); bitmap[1] &= ~FATTR4_WORD1_MOUNTED_ON_FILEID; ret = NFS_ATTR_FATTR_FILEID; } dprintk("%s: fileid=%Lu\n", __func__, (unsigned long long)*fileid); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_files_avail(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) @@ -2790,12 +2802,17 @@ static int decode_attr_files_avail(struct xdr_stream *xdr, uint32_t *bitmap, uin if (unlikely(bitmap[0] & (FATTR4_WORD0_FILES_AVAIL - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_FILES_AVAIL)) { - READ_BUF(8); - READ64(*res); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, res); bitmap[0] &= ~FATTR4_WORD0_FILES_AVAIL; } dprintk("%s: files avail=%Lu\n", __func__, (unsigned long long)*res); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_files_free(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) @@ -2807,12 +2824,17 @@ static int decode_attr_files_free(struct xdr_stream *xdr, uint32_t *bitmap, uint if (unlikely(bitmap[0] & (FATTR4_WORD0_FILES_FREE - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_FILES_FREE)) { - READ_BUF(8); - READ64(*res); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, res); bitmap[0] &= ~FATTR4_WORD0_FILES_FREE; } dprintk("%s: files free=%Lu\n", __func__, (unsigned long long)*res); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_files_total(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) @@ -2824,12 +2846,17 @@ static int decode_attr_files_total(struct xdr_stream *xdr, uint32_t *bitmap, uin if (unlikely(bitmap[0] & (FATTR4_WORD0_FILES_TOTAL - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_FILES_TOTAL)) { - READ_BUF(8); - READ64(*res); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, res); bitmap[0] &= ~FATTR4_WORD0_FILES_TOTAL; } dprintk("%s: files total=%Lu\n", __func__, (unsigned long long)*res); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_pathname(struct xdr_stream *xdr, struct nfs4_pathname *path) @@ -2838,8 +2865,10 @@ static int decode_pathname(struct xdr_stream *xdr, struct nfs4_pathname *path) __be32 *p; int status = 0; - READ_BUF(4); - READ32(n); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + n = be32_to_cpup(p); if (n == 0) goto root_path; dprintk("path "); @@ -2873,6 +2902,9 @@ out_eio: dprintk(" status %d", status); status = -EIO; goto out; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs4_fs_locations *res) @@ -2890,8 +2922,10 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st status = decode_pathname(xdr, &res->fs_path); if (unlikely(status != 0)) goto out; - READ_BUF(4); - READ32(n); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + n = be32_to_cpup(p); if (n <= 0) goto out_eio; res->nlocations = 0; @@ -2899,8 +2933,10 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st u32 m; struct nfs4_fs_location *loc = &res->locations[res->nlocations]; - READ_BUF(4); - READ32(m); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + m = be32_to_cpup(p); loc->nservers = 0; dprintk("%s: servers ", __func__); @@ -2939,6 +2975,8 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st out: dprintk("%s: fs_locations done, error = %d\n", __func__, status); return status; +out_overflow: + print_overflow_msg(__func__, xdr); out_eio: status = -EIO; goto out; @@ -2953,12 +2991,17 @@ static int decode_attr_maxfilesize(struct xdr_stream *xdr, uint32_t *bitmap, uin if (unlikely(bitmap[0] & (FATTR4_WORD0_MAXFILESIZE - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_MAXFILESIZE)) { - READ_BUF(8); - READ64(*res); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, res); bitmap[0] &= ~FATTR4_WORD0_MAXFILESIZE; } dprintk("%s: maxfilesize=%Lu\n", __func__, (unsigned long long)*res); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_maxlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *maxlink) @@ -2970,12 +3013,17 @@ static int decode_attr_maxlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_ if (unlikely(bitmap[0] & (FATTR4_WORD0_MAXLINK - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_MAXLINK)) { - READ_BUF(4); - READ32(*maxlink); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + *maxlink = be32_to_cpup(p); bitmap[0] &= ~FATTR4_WORD0_MAXLINK; } dprintk("%s: maxlink=%u\n", __func__, *maxlink); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_maxname(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *maxname) @@ -2987,12 +3035,17 @@ static int decode_attr_maxname(struct xdr_stream *xdr, uint32_t *bitmap, uint32_ if (unlikely(bitmap[0] & (FATTR4_WORD0_MAXNAME - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_MAXNAME)) { - READ_BUF(4); - READ32(*maxname); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + *maxname = be32_to_cpup(p); bitmap[0] &= ~FATTR4_WORD0_MAXNAME; } dprintk("%s: maxname=%u\n", __func__, *maxname); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_maxread(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) @@ -3005,8 +3058,10 @@ static int decode_attr_maxread(struct xdr_stream *xdr, uint32_t *bitmap, uint32_ return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_MAXREAD)) { uint64_t maxread; - READ_BUF(8); - READ64(maxread); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, &maxread); if (maxread > 0x7FFFFFFF) maxread = 0x7FFFFFFF; *res = (uint32_t)maxread; @@ -3014,6 +3069,9 @@ static int decode_attr_maxread(struct xdr_stream *xdr, uint32_t *bitmap, uint32_ } dprintk("%s: maxread=%lu\n", __func__, (unsigned long)*res); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_maxwrite(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) @@ -3026,8 +3084,10 @@ static int decode_attr_maxwrite(struct xdr_stream *xdr, uint32_t *bitmap, uint32 return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_MAXWRITE)) { uint64_t maxwrite; - READ_BUF(8); - READ64(maxwrite); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, &maxwrite); if (maxwrite > 0x7FFFFFFF) maxwrite = 0x7FFFFFFF; *res = (uint32_t)maxwrite; @@ -3035,6 +3095,9 @@ static int decode_attr_maxwrite(struct xdr_stream *xdr, uint32_t *bitmap, uint32 } dprintk("%s: maxwrite=%lu\n", __func__, (unsigned long)*res); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_mode(struct xdr_stream *xdr, uint32_t *bitmap, umode_t *mode) @@ -3047,14 +3110,19 @@ static int decode_attr_mode(struct xdr_stream *xdr, uint32_t *bitmap, umode_t *m if (unlikely(bitmap[1] & (FATTR4_WORD1_MODE - 1U))) return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_MODE)) { - READ_BUF(4); - READ32(tmp); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + tmp = be32_to_cpup(p); *mode = tmp & ~S_IFMT; bitmap[1] &= ~FATTR4_WORD1_MODE; ret = NFS_ATTR_FATTR_MODE; } dprintk("%s: file mode=0%o\n", __func__, (unsigned int)*mode); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_nlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *nlink) @@ -3066,16 +3134,22 @@ static int decode_attr_nlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t if (unlikely(bitmap[1] & (FATTR4_WORD1_NUMLINKS - 1U))) return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_NUMLINKS)) { - READ_BUF(4); - READ32(*nlink); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + *nlink = be32_to_cpup(p); bitmap[1] &= ~FATTR4_WORD1_NUMLINKS; ret = NFS_ATTR_FATTR_NLINK; } dprintk("%s: nlink=%u\n", __func__, (unsigned int)*nlink); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } -static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_client *clp, uint32_t *uid) +static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, + struct nfs_client *clp, uint32_t *uid, int may_sleep) { uint32_t len; __be32 *p; @@ -3085,10 +3159,16 @@ static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nf if (unlikely(bitmap[1] & (FATTR4_WORD1_OWNER - 1U))) return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_OWNER)) { - READ_BUF(4); - READ32(len); - READ_BUF(len); - if (len < XDR_MAX_NETOBJ) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + len = be32_to_cpup(p); + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + goto out_overflow; + if (!may_sleep) { + /* do nothing */ + } else if (len < XDR_MAX_NETOBJ) { if (nfs_map_name_to_uid(clp, (char *)p, len, uid) == 0) ret = NFS_ATTR_FATTR_OWNER; else @@ -3101,9 +3181,13 @@ static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nf } dprintk("%s: uid=%d\n", __func__, (int)*uid); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } -static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_client *clp, uint32_t *gid) +static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, + struct nfs_client *clp, uint32_t *gid, int may_sleep) { uint32_t len; __be32 *p; @@ -3113,10 +3197,16 @@ static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nf if (unlikely(bitmap[1] & (FATTR4_WORD1_OWNER_GROUP - 1U))) return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_OWNER_GROUP)) { - READ_BUF(4); - READ32(len); - READ_BUF(len); - if (len < XDR_MAX_NETOBJ) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + len = be32_to_cpup(p); + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + goto out_overflow; + if (!may_sleep) { + /* do nothing */ + } else if (len < XDR_MAX_NETOBJ) { if (nfs_map_group_to_gid(clp, (char *)p, len, gid) == 0) ret = NFS_ATTR_FATTR_GROUP; else @@ -3129,6 +3219,9 @@ static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nf } dprintk("%s: gid=%d\n", __func__, (int)*gid); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_rdev(struct xdr_stream *xdr, uint32_t *bitmap, dev_t *rdev) @@ -3143,9 +3236,11 @@ static int decode_attr_rdev(struct xdr_stream *xdr, uint32_t *bitmap, dev_t *rde if (likely(bitmap[1] & FATTR4_WORD1_RAWDEV)) { dev_t tmp; - READ_BUF(8); - READ32(major); - READ32(minor); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + major = be32_to_cpup(p++); + minor = be32_to_cpup(p); tmp = MKDEV(major, minor); if (MAJOR(tmp) == major && MINOR(tmp) == minor) *rdev = tmp; @@ -3154,6 +3249,9 @@ static int decode_attr_rdev(struct xdr_stream *xdr, uint32_t *bitmap, dev_t *rde } dprintk("%s: rdev=(0x%x:0x%x)\n", __func__, major, minor); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_space_avail(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) @@ -3165,12 +3263,17 @@ static int decode_attr_space_avail(struct xdr_stream *xdr, uint32_t *bitmap, uin if (unlikely(bitmap[1] & (FATTR4_WORD1_SPACE_AVAIL - 1U))) return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_SPACE_AVAIL)) { - READ_BUF(8); - READ64(*res); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, res); bitmap[1] &= ~FATTR4_WORD1_SPACE_AVAIL; } dprintk("%s: space avail=%Lu\n", __func__, (unsigned long long)*res); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_space_free(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) @@ -3182,12 +3285,17 @@ static int decode_attr_space_free(struct xdr_stream *xdr, uint32_t *bitmap, uint if (unlikely(bitmap[1] & (FATTR4_WORD1_SPACE_FREE - 1U))) return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_SPACE_FREE)) { - READ_BUF(8); - READ64(*res); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, res); bitmap[1] &= ~FATTR4_WORD1_SPACE_FREE; } dprintk("%s: space free=%Lu\n", __func__, (unsigned long long)*res); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_space_total(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) @@ -3199,12 +3307,17 @@ static int decode_attr_space_total(struct xdr_stream *xdr, uint32_t *bitmap, uin if (unlikely(bitmap[1] & (FATTR4_WORD1_SPACE_TOTAL - 1U))) return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_SPACE_TOTAL)) { - READ_BUF(8); - READ64(*res); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, res); bitmap[1] &= ~FATTR4_WORD1_SPACE_TOTAL; } dprintk("%s: space total=%Lu\n", __func__, (unsigned long long)*res); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_space_used(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *used) @@ -3216,14 +3329,19 @@ static int decode_attr_space_used(struct xdr_stream *xdr, uint32_t *bitmap, uint if (unlikely(bitmap[1] & (FATTR4_WORD1_SPACE_USED - 1U))) return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_SPACE_USED)) { - READ_BUF(8); - READ64(*used); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, used); bitmap[1] &= ~FATTR4_WORD1_SPACE_USED; ret = NFS_ATTR_FATTR_SPACE_USED; } dprintk("%s: space used=%Lu\n", __func__, (unsigned long long)*used); return ret; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_time(struct xdr_stream *xdr, struct timespec *time) @@ -3232,12 +3350,17 @@ static int decode_attr_time(struct xdr_stream *xdr, struct timespec *time) uint64_t sec; uint32_t nsec; - READ_BUF(12); - READ64(sec); - READ32(nsec); + p = xdr_inline_decode(xdr, 12); + if (unlikely(!p)) + goto out_overflow; + p = xdr_decode_hyper(p, &sec); + nsec = be32_to_cpup(p); time->tv_sec = (time_t)sec; time->tv_nsec = (long)nsec; return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_attr_time_access(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec *time) @@ -3315,11 +3438,16 @@ static int decode_change_info(struct xdr_stream *xdr, struct nfs4_change_info *c { __be32 *p; - READ_BUF(20); - READ32(cinfo->atomic); - READ64(cinfo->before); - READ64(cinfo->after); + p = xdr_inline_decode(xdr, 20); + if (unlikely(!p)) + goto out_overflow; + cinfo->atomic = be32_to_cpup(p++); + p = xdr_decode_hyper(p, &cinfo->before); + xdr_decode_hyper(p, &cinfo->after); return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_access(struct xdr_stream *xdr, struct nfs4_accessres *access) @@ -3331,40 +3459,62 @@ static int decode_access(struct xdr_stream *xdr, struct nfs4_accessres *access) status = decode_op_hdr(xdr, OP_ACCESS); if (status) return status; - READ_BUF(8); - READ32(supp); - READ32(acc); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + supp = be32_to_cpup(p++); + acc = be32_to_cpup(p); access->supported = supp; access->access = acc; return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } -static int decode_close(struct xdr_stream *xdr, struct nfs_closeres *res) +static int decode_opaque_fixed(struct xdr_stream *xdr, void *buf, size_t len) { __be32 *p; + + p = xdr_inline_decode(xdr, len); + if (likely(p)) { + memcpy(buf, p, len); + return 0; + } + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid) +{ + return decode_opaque_fixed(xdr, stateid->data, NFS4_STATEID_SIZE); +} + +static int decode_close(struct xdr_stream *xdr, struct nfs_closeres *res) +{ int status; status = decode_op_hdr(xdr, OP_CLOSE); if (status != -EIO) nfs_increment_open_seqid(status, res->seqid); - if (status) - return status; - READ_BUF(NFS4_STATEID_SIZE); - COPYMEM(res->stateid.data, NFS4_STATEID_SIZE); - return 0; + if (!status) + status = decode_stateid(xdr, &res->stateid); + return status; +} + +static int decode_verifier(struct xdr_stream *xdr, void *verifier) +{ + return decode_opaque_fixed(xdr, verifier, 8); } static int decode_commit(struct xdr_stream *xdr, struct nfs_writeres *res) { - __be32 *p; int status; status = decode_op_hdr(xdr, OP_COMMIT); - if (status) - return status; - READ_BUF(8); - COPYMEM(res->verf->verifier, 8); - return 0; + if (!status) + status = decode_verifier(xdr, res->verf->verifier); + return status; } static int decode_create(struct xdr_stream *xdr, struct nfs4_change_info *cinfo) @@ -3378,10 +3528,16 @@ static int decode_create(struct xdr_stream *xdr, struct nfs4_change_info *cinfo) return status; if ((status = decode_change_info(xdr, cinfo))) return status; - READ_BUF(4); - READ32(bmlen); - READ_BUF(bmlen << 2); - return 0; + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + bmlen = be32_to_cpup(p); + p = xdr_inline_decode(xdr, bmlen << 2); + if (likely(p)) + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_server_caps(struct xdr_stream *xdr, struct nfs4_server_caps_res *res) @@ -3466,7 +3622,8 @@ xdr_error: return status; } -static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, const struct nfs_server *server) +static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, + const struct nfs_server *server, int may_sleep) { __be32 *savep; uint32_t attrlen, @@ -3538,12 +3695,14 @@ static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, cons goto xdr_error; fattr->valid |= status; - status = decode_attr_owner(xdr, bitmap, server->nfs_client, &fattr->uid); + status = decode_attr_owner(xdr, bitmap, server->nfs_client, + &fattr->uid, may_sleep); if (status < 0) goto xdr_error; fattr->valid |= status; - status = decode_attr_group(xdr, bitmap, server->nfs_client, &fattr->gid); + status = decode_attr_group(xdr, bitmap, server->nfs_client, + &fattr->gid, may_sleep); if (status < 0) goto xdr_error; fattr->valid |= status; @@ -3633,14 +3792,21 @@ static int decode_getfh(struct xdr_stream *xdr, struct nfs_fh *fh) if (status) return status; - READ_BUF(4); - READ32(len); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + len = be32_to_cpup(p); if (len > NFS4_FHSIZE) return -EIO; fh->size = len; - READ_BUF(len); - COPYMEM(fh->data, len); + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + goto out_overflow; + memcpy(fh->data, p, len); return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_link(struct xdr_stream *xdr, struct nfs4_change_info *cinfo) @@ -3662,10 +3828,12 @@ static int decode_lock_denied (struct xdr_stream *xdr, struct file_lock *fl) __be32 *p; uint32_t namelen, type; - READ_BUF(32); - READ64(offset); - READ64(length); - READ32(type); + p = xdr_inline_decode(xdr, 32); + if (unlikely(!p)) + goto out_overflow; + p = xdr_decode_hyper(p, &offset); + p = xdr_decode_hyper(p, &length); + type = be32_to_cpup(p++); if (fl != NULL) { fl->fl_start = (loff_t)offset; fl->fl_end = fl->fl_start + (loff_t)length - 1; @@ -3676,23 +3844,27 @@ static int decode_lock_denied (struct xdr_stream *xdr, struct file_lock *fl) fl->fl_type = F_RDLCK; fl->fl_pid = 0; } - READ64(clientid); - READ32(namelen); - READ_BUF(namelen); - return -NFS4ERR_DENIED; + p = xdr_decode_hyper(p, &clientid); + namelen = be32_to_cpup(p); + p = xdr_inline_decode(xdr, namelen); + if (likely(p)) + return -NFS4ERR_DENIED; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_lock(struct xdr_stream *xdr, struct nfs_lock_res *res) { - __be32 *p; int status; status = decode_op_hdr(xdr, OP_LOCK); if (status == -EIO) goto out; if (status == 0) { - READ_BUF(NFS4_STATEID_SIZE); - COPYMEM(res->stateid.data, NFS4_STATEID_SIZE); + status = decode_stateid(xdr, &res->stateid); + if (unlikely(status)) + goto out; } else if (status == -NFS4ERR_DENIED) status = decode_lock_denied(xdr, NULL); if (res->open_seqid != NULL) @@ -3713,16 +3885,13 @@ static int decode_lockt(struct xdr_stream *xdr, struct nfs_lockt_res *res) static int decode_locku(struct xdr_stream *xdr, struct nfs_locku_res *res) { - __be32 *p; int status; status = decode_op_hdr(xdr, OP_LOCKU); if (status != -EIO) nfs_increment_lock_seqid(status, res->seqid); - if (status == 0) { - READ_BUF(NFS4_STATEID_SIZE); - COPYMEM(res->stateid.data, NFS4_STATEID_SIZE); - } + if (status == 0) + status = decode_stateid(xdr, &res->stateid); return status; } @@ -3737,34 +3906,46 @@ static int decode_space_limit(struct xdr_stream *xdr, u64 *maxsize) __be32 *p; uint32_t limit_type, nblocks, blocksize; - READ_BUF(12); - READ32(limit_type); + p = xdr_inline_decode(xdr, 12); + if (unlikely(!p)) + goto out_overflow; + limit_type = be32_to_cpup(p++); switch (limit_type) { case 1: - READ64(*maxsize); + xdr_decode_hyper(p, maxsize); break; case 2: - READ32(nblocks); - READ32(blocksize); + nblocks = be32_to_cpup(p++); + blocksize = be32_to_cpup(p); *maxsize = (uint64_t)nblocks * (uint64_t)blocksize; } return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res) { __be32 *p; uint32_t delegation_type; + int status; - READ_BUF(4); - READ32(delegation_type); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + delegation_type = be32_to_cpup(p); if (delegation_type == NFS4_OPEN_DELEGATE_NONE) { res->delegation_type = 0; return 0; } - READ_BUF(NFS4_STATEID_SIZE+4); - COPYMEM(res->delegation.data, NFS4_STATEID_SIZE); - READ32(res->do_recall); + status = decode_stateid(xdr, &res->delegation); + if (unlikely(status)) + return status; + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + res->do_recall = be32_to_cpup(p); switch (delegation_type) { case NFS4_OPEN_DELEGATE_READ: @@ -3776,6 +3957,9 @@ static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res) return -EIO; } return decode_ace(xdr, NULL, res->server->nfs_client); +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res) @@ -3787,23 +3971,27 @@ static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res) status = decode_op_hdr(xdr, OP_OPEN); if (status != -EIO) nfs_increment_open_seqid(status, res->seqid); - if (status) + if (!status) + status = decode_stateid(xdr, &res->stateid); + if (unlikely(status)) return status; - READ_BUF(NFS4_STATEID_SIZE); - COPYMEM(res->stateid.data, NFS4_STATEID_SIZE); decode_change_info(xdr, &res->cinfo); - READ_BUF(8); - READ32(res->rflags); - READ32(bmlen); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + res->rflags = be32_to_cpup(p++); + bmlen = be32_to_cpup(p); if (bmlen > 10) goto xdr_error; - READ_BUF(bmlen << 2); + p = xdr_inline_decode(xdr, bmlen << 2); + if (unlikely(!p)) + goto out_overflow; savewords = min_t(uint32_t, bmlen, NFS4_BITMAP_SIZE); for (i = 0; i < savewords; ++i) - READ32(res->attrset[i]); + res->attrset[i] = be32_to_cpup(p++); for (; i < NFS4_BITMAP_SIZE; i++) res->attrset[i] = 0; @@ -3811,36 +3999,33 @@ static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res) xdr_error: dprintk("%s: Bitmap too large! Length = %u\n", __func__, bmlen); return -EIO; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_open_confirm(struct xdr_stream *xdr, struct nfs_open_confirmres *res) { - __be32 *p; int status; status = decode_op_hdr(xdr, OP_OPEN_CONFIRM); if (status != -EIO) nfs_increment_open_seqid(status, res->seqid); - if (status) - return status; - READ_BUF(NFS4_STATEID_SIZE); - COPYMEM(res->stateid.data, NFS4_STATEID_SIZE); - return 0; + if (!status) + status = decode_stateid(xdr, &res->stateid); + return status; } static int decode_open_downgrade(struct xdr_stream *xdr, struct nfs_closeres *res) { - __be32 *p; int status; status = decode_op_hdr(xdr, OP_OPEN_DOWNGRADE); if (status != -EIO) nfs_increment_open_seqid(status, res->seqid); - if (status) - return status; - READ_BUF(NFS4_STATEID_SIZE); - COPYMEM(res->stateid.data, NFS4_STATEID_SIZE); - return 0; + if (!status) + status = decode_stateid(xdr, &res->stateid); + return status; } static int decode_putfh(struct xdr_stream *xdr) @@ -3863,9 +4048,11 @@ static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_ status = decode_op_hdr(xdr, OP_READ); if (status) return status; - READ_BUF(8); - READ32(eof); - READ32(count); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + eof = be32_to_cpup(p++); + count = be32_to_cpup(p); hdrlen = (u8 *) p - (u8 *) iov->iov_base; recvd = req->rq_rcv_buf.len - hdrlen; if (count > recvd) { @@ -3878,6 +4065,9 @@ static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_ res->eof = eof; res->count = count; return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs4_readdir_res *readdir) @@ -3892,17 +4082,17 @@ static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct n int status; status = decode_op_hdr(xdr, OP_READDIR); - if (status) + if (!status) + status = decode_verifier(xdr, readdir->verifier.data); + if (unlikely(status)) return status; - READ_BUF(8); - COPYMEM(readdir->verifier.data, 8); dprintk("%s: verifier = %08x:%08x\n", __func__, ((u32 *)readdir->verifier.data)[0], ((u32 *)readdir->verifier.data)[1]); - hdrlen = (char *) p - (char *) iov->iov_base; + hdrlen = (char *) xdr->p - (char *) iov->iov_base; recvd = rcvbuf->len - hdrlen; if (pglen > recvd) pglen = recvd; @@ -3990,8 +4180,10 @@ static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req) return status; /* Convert length of symlink */ - READ_BUF(4); - READ32(len); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + len = be32_to_cpup(p); if (len >= rcvbuf->page_len || len <= 0) { dprintk("nfs: server returned giant symlink!\n"); return -ENAMETOOLONG; @@ -4015,6 +4207,9 @@ static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req) kaddr[len+rcvbuf->page_base] = '\0'; kunmap_atomic(kaddr, KM_USER0); return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_remove(struct xdr_stream *xdr, struct nfs4_change_info *cinfo) @@ -4112,10 +4307,16 @@ static int decode_setattr(struct xdr_stream *xdr) status = decode_op_hdr(xdr, OP_SETATTR); if (status) return status; - READ_BUF(4); - READ32(bmlen); - READ_BUF(bmlen << 2); - return 0; + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + bmlen = be32_to_cpup(p); + p = xdr_inline_decode(xdr, bmlen << 2); + if (likely(p)) + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_setclientid(struct xdr_stream *xdr, struct nfs_client *clp) @@ -4124,35 +4325,50 @@ static int decode_setclientid(struct xdr_stream *xdr, struct nfs_client *clp) uint32_t opnum; int32_t nfserr; - READ_BUF(8); - READ32(opnum); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + opnum = be32_to_cpup(p++); if (opnum != OP_SETCLIENTID) { dprintk("nfs: decode_setclientid: Server returned operation" " %d\n", opnum); return -EIO; } - READ32(nfserr); + nfserr = be32_to_cpup(p); if (nfserr == NFS_OK) { - READ_BUF(8 + NFS4_VERIFIER_SIZE); - READ64(clp->cl_clientid); - COPYMEM(clp->cl_confirm.data, NFS4_VERIFIER_SIZE); + p = xdr_inline_decode(xdr, 8 + NFS4_VERIFIER_SIZE); + if (unlikely(!p)) + goto out_overflow; + p = xdr_decode_hyper(p, &clp->cl_clientid); + memcpy(clp->cl_confirm.data, p, NFS4_VERIFIER_SIZE); } else if (nfserr == NFSERR_CLID_INUSE) { uint32_t len; /* skip netid string */ - READ_BUF(4); - READ32(len); - READ_BUF(len); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + len = be32_to_cpup(p); + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + goto out_overflow; /* skip uaddr string */ - READ_BUF(4); - READ32(len); - READ_BUF(len); + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + len = be32_to_cpup(p); + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + goto out_overflow; return -NFSERR_CLID_INUSE; } else return nfs4_stat_to_errno(nfserr); return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_setclientid_confirm(struct xdr_stream *xdr) @@ -4169,11 +4385,16 @@ static int decode_write(struct xdr_stream *xdr, struct nfs_writeres *res) if (status) return status; - READ_BUF(16); - READ32(res->count); - READ32(res->verf->committed); - COPYMEM(res->verf->verifier, 8); + p = xdr_inline_decode(xdr, 16); + if (unlikely(!p)) + goto out_overflow; + res->count = be32_to_cpup(p++); + res->verf->committed = be32_to_cpup(p++); + memcpy(res->verf->verifier, p, 8); return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_delegreturn(struct xdr_stream *xdr) @@ -4187,6 +4408,7 @@ static int decode_exchange_id(struct xdr_stream *xdr, { __be32 *p; uint32_t dummy; + char *dummy_str; int status; struct nfs_client *clp = res->client; @@ -4194,36 +4416,45 @@ static int decode_exchange_id(struct xdr_stream *xdr, if (status) return status; - READ_BUF(8); - READ64(clp->cl_ex_clid); - READ_BUF(12); - READ32(clp->cl_seqid); - READ32(clp->cl_exchange_flags); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, &clp->cl_ex_clid); + p = xdr_inline_decode(xdr, 12); + if (unlikely(!p)) + goto out_overflow; + clp->cl_seqid = be32_to_cpup(p++); + clp->cl_exchange_flags = be32_to_cpup(p++); /* We ask for SP4_NONE */ - READ32(dummy); + dummy = be32_to_cpup(p); if (dummy != SP4_NONE) return -EIO; /* Throw away minor_id */ - READ_BUF(8); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; /* Throw away Major id */ - READ_BUF(4); - READ32(dummy); - READ_BUF(dummy); + status = decode_opaque_inline(xdr, &dummy, &dummy_str); + if (unlikely(status)) + return status; /* Throw away server_scope */ - READ_BUF(4); - READ32(dummy); - READ_BUF(dummy); + status = decode_opaque_inline(xdr, &dummy, &dummy_str); + if (unlikely(status)) + return status; /* Throw away Implementation id array */ - READ_BUF(4); - READ32(dummy); - READ_BUF(dummy); + status = decode_opaque_inline(xdr, &dummy, &dummy_str); + if (unlikely(status)) + return status; return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_chan_attrs(struct xdr_stream *xdr, @@ -4232,22 +4463,35 @@ static int decode_chan_attrs(struct xdr_stream *xdr, __be32 *p; u32 nr_attrs; - READ_BUF(28); - READ32(attrs->headerpadsz); - READ32(attrs->max_rqst_sz); - READ32(attrs->max_resp_sz); - READ32(attrs->max_resp_sz_cached); - READ32(attrs->max_ops); - READ32(attrs->max_reqs); - READ32(nr_attrs); + p = xdr_inline_decode(xdr, 28); + if (unlikely(!p)) + goto out_overflow; + attrs->headerpadsz = be32_to_cpup(p++); + attrs->max_rqst_sz = be32_to_cpup(p++); + attrs->max_resp_sz = be32_to_cpup(p++); + attrs->max_resp_sz_cached = be32_to_cpup(p++); + attrs->max_ops = be32_to_cpup(p++); + attrs->max_reqs = be32_to_cpup(p++); + nr_attrs = be32_to_cpup(p); if (unlikely(nr_attrs > 1)) { printk(KERN_WARNING "%s: Invalid rdma channel attrs count %u\n", __func__, nr_attrs); return -EINVAL; } - if (nr_attrs == 1) - READ_BUF(4); /* skip rdma_attrs */ + if (nr_attrs == 1) { + p = xdr_inline_decode(xdr, 4); /* skip rdma_attrs */ + if (unlikely(!p)) + goto out_overflow; + } return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_sessionid(struct xdr_stream *xdr, struct nfs4_sessionid *sid) +{ + return decode_opaque_fixed(xdr, sid->data, NFS4_MAX_SESSIONID_LEN); } static int decode_create_session(struct xdr_stream *xdr, @@ -4259,24 +4503,26 @@ static int decode_create_session(struct xdr_stream *xdr, struct nfs4_session *session = clp->cl_session; status = decode_op_hdr(xdr, OP_CREATE_SESSION); - - if (status) + if (!status) + status = decode_sessionid(xdr, &session->sess_id); + if (unlikely(status)) return status; - /* sessionid */ - READ_BUF(NFS4_MAX_SESSIONID_LEN); - COPYMEM(&session->sess_id, NFS4_MAX_SESSIONID_LEN); - /* seqid, flags */ - READ_BUF(8); - READ32(clp->cl_seqid); - READ32(session->flags); + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + clp->cl_seqid = be32_to_cpup(p++); + session->flags = be32_to_cpup(p); /* Channel attributes */ status = decode_chan_attrs(xdr, &session->fc_attrs); if (!status) status = decode_chan_attrs(xdr, &session->bc_attrs); return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; } static int decode_destroy_session(struct xdr_stream *xdr, void *dummy) @@ -4300,7 +4546,9 @@ static int decode_sequence(struct xdr_stream *xdr, return 0; status = decode_op_hdr(xdr, OP_SEQUENCE); - if (status) + if (!status) + status = decode_sessionid(xdr, &id); + if (unlikely(status)) goto out_err; /* @@ -4309,36 +4557,43 @@ static int decode_sequence(struct xdr_stream *xdr, */ status = -ESERVERFAULT; - slot = &res->sr_session->fc_slot_table.slots[res->sr_slotid]; - READ_BUF(NFS4_MAX_SESSIONID_LEN + 20); - COPYMEM(id.data, NFS4_MAX_SESSIONID_LEN); if (memcmp(id.data, res->sr_session->sess_id.data, NFS4_MAX_SESSIONID_LEN)) { dprintk("%s Invalid session id\n", __func__); goto out_err; } + + p = xdr_inline_decode(xdr, 20); + if (unlikely(!p)) + goto out_overflow; + /* seqid */ - READ32(dummy); + slot = &res->sr_session->fc_slot_table.slots[res->sr_slotid]; + dummy = be32_to_cpup(p++); if (dummy != slot->seq_nr) { dprintk("%s Invalid sequence number\n", __func__); goto out_err; } /* slot id */ - READ32(dummy); + dummy = be32_to_cpup(p++); if (dummy != res->sr_slotid) { dprintk("%s Invalid slot id\n", __func__); goto out_err; } /* highest slot id - currently not processed */ - READ32(dummy); + dummy = be32_to_cpup(p++); /* target highest slot id - currently not processed */ - READ32(dummy); + dummy = be32_to_cpup(p++); /* result flags - currently not processed */ - READ32(dummy); + dummy = be32_to_cpup(p); status = 0; out_err: res->sr_status = status; return status; +out_overflow: + print_overflow_msg(__func__, xdr); + status = -EIO; + goto out_err; #else /* CONFIG_NFS_V4_1 */ return 0; #endif /* CONFIG_NFS_V4_1 */ @@ -4370,7 +4625,8 @@ static int nfs4_xdr_dec_open_downgrade(struct rpc_rqst *rqstp, __be32 *p, struct status = decode_open_downgrade(&xdr, res); if (status != 0) goto out; - decode_getfattr(&xdr, res->fattr, res->server); + decode_getfattr(&xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4397,7 +4653,8 @@ static int nfs4_xdr_dec_access(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_ac status = decode_access(&xdr, res); if (status != 0) goto out; - decode_getfattr(&xdr, res->fattr, res->server); + decode_getfattr(&xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4424,7 +4681,8 @@ static int nfs4_xdr_dec_lookup(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_lo goto out; if ((status = decode_getfh(&xdr, res->fh)) != 0) goto out; - status = decode_getfattr(&xdr, res->fattr, res->server); + status = decode_getfattr(&xdr, res->fattr, res->server + ,!RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4448,7 +4706,8 @@ static int nfs4_xdr_dec_lookup_root(struct rpc_rqst *rqstp, __be32 *p, struct nf if ((status = decode_putrootfh(&xdr)) != 0) goto out; if ((status = decode_getfh(&xdr, res->fh)) == 0) - status = decode_getfattr(&xdr, res->fattr, res->server); + status = decode_getfattr(&xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4473,7 +4732,8 @@ static int nfs4_xdr_dec_remove(struct rpc_rqst *rqstp, __be32 *p, struct nfs_rem goto out; if ((status = decode_remove(&xdr, &res->cinfo)) != 0) goto out; - decode_getfattr(&xdr, &res->dir_attr, res->server); + decode_getfattr(&xdr, &res->dir_attr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4503,11 +4763,13 @@ static int nfs4_xdr_dec_rename(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_re if ((status = decode_rename(&xdr, &res->old_cinfo, &res->new_cinfo)) != 0) goto out; /* Current FH is target directory */ - if (decode_getfattr(&xdr, res->new_fattr, res->server) != 0) + if (decode_getfattr(&xdr, res->new_fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)) != 0) goto out; if ((status = decode_restorefh(&xdr)) != 0) goto out; - decode_getfattr(&xdr, res->old_fattr, res->server); + decode_getfattr(&xdr, res->old_fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4540,11 +4802,13 @@ static int nfs4_xdr_dec_link(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_link * Note order: OP_LINK leaves the directory as the current * filehandle. */ - if (decode_getfattr(&xdr, res->dir_attr, res->server) != 0) + if (decode_getfattr(&xdr, res->dir_attr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)) != 0) goto out; if ((status = decode_restorefh(&xdr)) != 0) goto out; - decode_getfattr(&xdr, res->fattr, res->server); + decode_getfattr(&xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4573,11 +4837,13 @@ static int nfs4_xdr_dec_create(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_cr goto out; if ((status = decode_getfh(&xdr, res->fh)) != 0) goto out; - if (decode_getfattr(&xdr, res->fattr, res->server) != 0) + if (decode_getfattr(&xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)) != 0) goto out; if ((status = decode_restorefh(&xdr)) != 0) goto out; - decode_getfattr(&xdr, res->dir_fattr, res->server); + decode_getfattr(&xdr, res->dir_fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4609,7 +4875,8 @@ static int nfs4_xdr_dec_getattr(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_g status = decode_putfh(&xdr); if (status) goto out; - status = decode_getfattr(&xdr, res->fattr, res->server); + status = decode_getfattr(&xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4716,7 +4983,8 @@ static int nfs4_xdr_dec_close(struct rpc_rqst *rqstp, __be32 *p, struct nfs_clos * an ESTALE error. Shouldn't be a problem, * though, since fattr->valid will remain unset. */ - decode_getfattr(&xdr, res->fattr, res->server); + decode_getfattr(&xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4748,11 +5016,13 @@ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, __be32 *p, struct nfs_openr goto out; if (decode_getfh(&xdr, &res->fh) != 0) goto out; - if (decode_getfattr(&xdr, res->f_attr, res->server) != 0) + if (decode_getfattr(&xdr, res->f_attr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)) != 0) goto out; if (decode_restorefh(&xdr) != 0) goto out; - decode_getfattr(&xdr, res->dir_attr, res->server); + decode_getfattr(&xdr, res->dir_attr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4800,7 +5070,8 @@ static int nfs4_xdr_dec_open_noattr(struct rpc_rqst *rqstp, __be32 *p, struct nf status = decode_open(&xdr, res); if (status) goto out; - decode_getfattr(&xdr, res->f_attr, res->server); + decode_getfattr(&xdr, res->f_attr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -4827,7 +5098,8 @@ static int nfs4_xdr_dec_setattr(struct rpc_rqst *rqstp, __be32 *p, struct nfs_se status = decode_setattr(&xdr); if (status) goto out; - decode_getfattr(&xdr, res->fattr, res->server); + decode_getfattr(&xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -5001,7 +5273,8 @@ static int nfs4_xdr_dec_write(struct rpc_rqst *rqstp, __be32 *p, struct nfs_writ status = decode_write(&xdr, res); if (status) goto out; - decode_getfattr(&xdr, res->fattr, res->server); + decode_getfattr(&xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); if (!status) status = res->count; out: @@ -5030,7 +5303,8 @@ static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, __be32 *p, struct nfs_wri status = decode_commit(&xdr, res); if (status) goto out; - decode_getfattr(&xdr, res->fattr, res->server); + decode_getfattr(&xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -5194,7 +5468,8 @@ static int nfs4_xdr_dec_delegreturn(struct rpc_rqst *rqstp, __be32 *p, struct nf if (status != 0) goto out; status = decode_delegreturn(&xdr); - decode_getfattr(&xdr, res->fattr, res->server); + decode_getfattr(&xdr, res->fattr, res->server, + !RPC_IS_ASYNC(rqstp->rq_task)); out: return status; } @@ -5222,7 +5497,8 @@ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req, __be32 *p, goto out; xdr_enter_page(&xdr, PAGE_SIZE); status = decode_getfattr(&xdr, &res->fs_locations->fattr, - res->fs_locations->server); + res->fs_locations->server, + !RPC_IS_ASYNC(req->rq_task)); out: return status; } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 0b4cbdc..867f705 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -73,7 +73,7 @@ enum { Opt_cto, Opt_nocto, Opt_ac, Opt_noac, Opt_lock, Opt_nolock, - Opt_v2, Opt_v3, + Opt_v2, Opt_v3, Opt_v4, Opt_udp, Opt_tcp, Opt_rdma, Opt_acl, Opt_noacl, Opt_rdirplus, Opt_nordirplus, @@ -127,6 +127,7 @@ static const match_table_t nfs_mount_option_tokens = { { Opt_nolock, "nolock" }, { Opt_v2, "v2" }, { Opt_v3, "v3" }, + { Opt_v4, "v4" }, { Opt_udp, "udp" }, { Opt_tcp, "tcp" }, { Opt_rdma, "rdma" }, @@ -158,7 +159,7 @@ static const match_table_t nfs_mount_option_tokens = { { Opt_mountvers, "mountvers=%s" }, { Opt_nfsvers, "nfsvers=%s" }, { Opt_nfsvers, "vers=%s" }, - { Opt_minorversion, "minorversion=%u" }, + { Opt_minorversion, "minorversion=%s" }, { Opt_sec, "sec=%s" }, { Opt_proto, "proto=%s" }, @@ -272,6 +273,10 @@ static const struct super_operations nfs_sops = { }; #ifdef CONFIG_NFS_V4 +static int nfs4_validate_text_mount_data(void *options, + struct nfs_parsed_mount_data *args, const char *dev_name); +static int nfs4_try_mount(int flags, const char *dev_name, + struct nfs_parsed_mount_data *data, struct vfsmount *mnt); static int nfs4_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt); static int nfs4_remote_get_sb(struct file_system_type *fs_type, @@ -742,127 +747,23 @@ static int nfs_verify_server_address(struct sockaddr *addr) } } + dfprintk(MOUNT, "NFS: Invalid IP address specified\n"); return 0; } -static void nfs_parse_ipv4_address(char *string, size_t str_len, - struct sockaddr *sap, size_t *addr_len) -{ - struct sockaddr_in *sin = (struct sockaddr_in *)sap; - u8 *addr = (u8 *)&sin->sin_addr.s_addr; - - if (str_len <= INET_ADDRSTRLEN) { - dfprintk(MOUNT, "NFS: parsing IPv4 address %*s\n", - (int)str_len, string); - - sin->sin_family = AF_INET; - *addr_len = sizeof(*sin); - if (in4_pton(string, str_len, addr, '\0', NULL)) - return; - } - - sap->sa_family = AF_UNSPEC; - *addr_len = 0; -} - -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -static int nfs_parse_ipv6_scope_id(const char *string, const size_t str_len, - const char *delim, - struct sockaddr_in6 *sin6) -{ - char *p; - size_t len; - - if ((string + str_len) == delim) - return 1; - - if (*delim != IPV6_SCOPE_DELIMITER) - return 0; - - if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)) - return 0; - - len = (string + str_len) - delim - 1; - p = kstrndup(delim + 1, len, GFP_KERNEL); - if (p) { - unsigned long scope_id = 0; - struct net_device *dev; - - dev = dev_get_by_name(&init_net, p); - if (dev != NULL) { - scope_id = dev->ifindex; - dev_put(dev); - } else { - if (strict_strtoul(p, 10, &scope_id) == 0) { - kfree(p); - return 0; - } - } - - kfree(p); - - sin6->sin6_scope_id = scope_id; - dfprintk(MOUNT, "NFS: IPv6 scope ID = %lu\n", scope_id); - return 1; - } - - return 0; -} - -static void nfs_parse_ipv6_address(char *string, size_t str_len, - struct sockaddr *sap, size_t *addr_len) -{ - struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap; - u8 *addr = (u8 *)&sin6->sin6_addr.in6_u; - const char *delim; - - if (str_len <= INET6_ADDRSTRLEN) { - dfprintk(MOUNT, "NFS: parsing IPv6 address %*s\n", - (int)str_len, string); - - sin6->sin6_family = AF_INET6; - *addr_len = sizeof(*sin6); - if (in6_pton(string, str_len, addr, - IPV6_SCOPE_DELIMITER, &delim) != 0) { - if (nfs_parse_ipv6_scope_id(string, str_len, - delim, sin6) != 0) - return; - } - } - - sap->sa_family = AF_UNSPEC; - *addr_len = 0; -} -#else -static void nfs_parse_ipv6_address(char *string, size_t str_len, - struct sockaddr *sap, size_t *addr_len) -{ - sap->sa_family = AF_UNSPEC; - *addr_len = 0; -} -#endif - /* - * Construct a sockaddr based on the contents of a string that contains - * an IP address in presentation format. - * - * If there is a problem constructing the new sockaddr, set the address - * family to AF_UNSPEC. + * Select between a default port value and a user-specified port value. + * If a zero value is set, then autobind will be used. */ -void nfs_parse_ip_address(char *string, size_t str_len, - struct sockaddr *sap, size_t *addr_len) +static void nfs_set_default_port(struct sockaddr *sap, const int parsed_port, + const unsigned short default_port) { - unsigned int i, colons; + unsigned short port = default_port; - colons = 0; - for (i = 0; i < str_len; i++) - if (string[i] == ':') - colons++; + if (parsed_port != NFS_UNSPEC_PORT) + port = parsed_port; - if (colons >= 2) - nfs_parse_ipv6_address(string, str_len, sap, addr_len); - else - nfs_parse_ipv4_address(string, str_len, sap, addr_len); + rpc_set_port(sap, port); } /* @@ -904,8 +805,6 @@ static void nfs_set_mount_transport_protocol(struct nfs_parsed_mount_data *mnt) /* * Parse the value of the 'sec=' option. - * - * The flavor_len setting is for v4 mounts. */ static int nfs_parse_security_flavors(char *value, struct nfs_parsed_mount_data *mnt) @@ -916,53 +815,43 @@ static int nfs_parse_security_flavors(char *value, switch (match_token(value, nfs_secflavor_tokens, args)) { case Opt_sec_none: - mnt->auth_flavor_len = 0; mnt->auth_flavors[0] = RPC_AUTH_NULL; break; case Opt_sec_sys: - mnt->auth_flavor_len = 0; mnt->auth_flavors[0] = RPC_AUTH_UNIX; break; case Opt_sec_krb5: - mnt->auth_flavor_len = 1; mnt->auth_flavors[0] = RPC_AUTH_GSS_KRB5; break; case Opt_sec_krb5i: - mnt->auth_flavor_len = 1; mnt->auth_flavors[0] = RPC_AUTH_GSS_KRB5I; break; case Opt_sec_krb5p: - mnt->auth_flavor_len = 1; mnt->auth_flavors[0] = RPC_AUTH_GSS_KRB5P; break; case Opt_sec_lkey: - mnt->auth_flavor_len = 1; mnt->auth_flavors[0] = RPC_AUTH_GSS_LKEY; break; case Opt_sec_lkeyi: - mnt->auth_flavor_len = 1; mnt->auth_flavors[0] = RPC_AUTH_GSS_LKEYI; break; case Opt_sec_lkeyp: - mnt->auth_flavor_len = 1; mnt->auth_flavors[0] = RPC_AUTH_GSS_LKEYP; break; case Opt_sec_spkm: - mnt->auth_flavor_len = 1; mnt->auth_flavors[0] = RPC_AUTH_GSS_SPKM; break; case Opt_sec_spkmi: - mnt->auth_flavor_len = 1; mnt->auth_flavors[0] = RPC_AUTH_GSS_SPKMI; break; case Opt_sec_spkmp: - mnt->auth_flavor_len = 1; mnt->auth_flavors[0] = RPC_AUTH_GSS_SPKMP; break; default: return 0; } + mnt->auth_flavor_len = 1; return 1; } @@ -1001,7 +890,6 @@ static int nfs_parse_mount_options(char *raw, while ((p = strsep(&raw, ",")) != NULL) { substring_t args[MAX_OPT_ARGS]; unsigned long option; - int int_option; int token; if (!*p) @@ -1047,10 +935,18 @@ static int nfs_parse_mount_options(char *raw, break; case Opt_v2: mnt->flags &= ~NFS_MOUNT_VER3; + mnt->version = 2; break; case Opt_v3: mnt->flags |= NFS_MOUNT_VER3; + mnt->version = 3; break; +#ifdef CONFIG_NFS_V4 + case Opt_v4: + mnt->flags &= ~NFS_MOUNT_VER3; + mnt->version = 4; + break; +#endif case Opt_udp: mnt->flags &= ~NFS_MOUNT_TCP; mnt->nfs_server.protocol = XPRT_TRANSPORT_UDP; @@ -1264,20 +1160,33 @@ static int nfs_parse_mount_options(char *raw, switch (option) { case NFS2_VERSION: mnt->flags &= ~NFS_MOUNT_VER3; + mnt->version = 2; break; case NFS3_VERSION: mnt->flags |= NFS_MOUNT_VER3; + mnt->version = 3; break; +#ifdef CONFIG_NFS_V4 + case NFS4_VERSION: + mnt->flags &= ~NFS_MOUNT_VER3; + mnt->version = 4; + break; +#endif default: goto out_invalid_value; } break; case Opt_minorversion: - if (match_int(args, &int_option)) - return 0; - if (int_option < 0 || int_option > NFS4_MAX_MINOR_VERSION) - return 0; - mnt->minorversion = int_option; + string = match_strdup(args); + if (string == NULL) + goto out_nomem; + rc = strict_strtoul(string, 10, &option); + kfree(string); + if (rc != 0) + goto out_invalid_value; + if (option > NFS4_MAX_MINOR_VERSION) + goto out_invalid_value; + mnt->minorversion = option; break; /* @@ -1352,11 +1261,14 @@ static int nfs_parse_mount_options(char *raw, string = match_strdup(args); if (string == NULL) goto out_nomem; - nfs_parse_ip_address(string, strlen(string), - (struct sockaddr *) - &mnt->nfs_server.address, - &mnt->nfs_server.addrlen); + mnt->nfs_server.addrlen = + rpc_pton(string, strlen(string), + (struct sockaddr *) + &mnt->nfs_server.address, + sizeof(mnt->nfs_server.address)); kfree(string); + if (mnt->nfs_server.addrlen == 0) + goto out_invalid_address; break; case Opt_clientaddr: string = match_strdup(args); @@ -1376,11 +1288,14 @@ static int nfs_parse_mount_options(char *raw, string = match_strdup(args); if (string == NULL) goto out_nomem; - nfs_parse_ip_address(string, strlen(string), - (struct sockaddr *) - &mnt->mount_server.address, - &mnt->mount_server.addrlen); + mnt->mount_server.addrlen = + rpc_pton(string, strlen(string), + (struct sockaddr *) + &mnt->mount_server.address, + sizeof(mnt->mount_server.address)); kfree(string); + if (mnt->mount_server.addrlen == 0) + goto out_invalid_address; break; case Opt_lookupcache: string = match_strdup(args); @@ -1432,8 +1347,11 @@ static int nfs_parse_mount_options(char *raw, return 1; +out_invalid_address: + printk(KERN_INFO "NFS: bad IP address specified: %s\n", p); + return 0; out_invalid_value: - printk(KERN_INFO "NFS: bad mount option value specified: %s \n", p); + printk(KERN_INFO "NFS: bad mount option value specified: %s\n", p); return 0; out_nomem: printk(KERN_INFO "NFS: not enough memory to parse option\n"); @@ -1445,13 +1363,60 @@ out_security_failure: } /* + * Match the requested auth flavors with the list returned by + * the server. Returns zero and sets the mount's authentication + * flavor on success; returns -EACCES if server does not support + * the requested flavor. + */ +static int nfs_walk_authlist(struct nfs_parsed_mount_data *args, + struct nfs_mount_request *request) +{ + unsigned int i, j, server_authlist_len = *(request->auth_flav_len); + + /* + * Certain releases of Linux's mountd return an empty + * flavor list. To prevent behavioral regression with + * these servers (ie. rejecting mounts that used to + * succeed), revert to pre-2.6.32 behavior (no checking) + * if the returned flavor list is empty. + */ + if (server_authlist_len == 0) + return 0; + + /* + * We avoid sophisticated negotiating here, as there are + * plenty of cases where we can get it wrong, providing + * either too little or too much security. + * + * RFC 2623, section 2.7 suggests we SHOULD prefer the + * flavor listed first. However, some servers list + * AUTH_NULL first. Our caller plants AUTH_SYS, the + * preferred default, in args->auth_flavors[0] if user + * didn't specify sec= mount option. + */ + for (i = 0; i < args->auth_flavor_len; i++) + for (j = 0; j < server_authlist_len; j++) + if (args->auth_flavors[i] == request->auth_flavs[j]) { + dfprintk(MOUNT, "NFS: using auth flavor %d\n", + request->auth_flavs[j]); + args->auth_flavors[0] = request->auth_flavs[j]; + return 0; + } + + dfprintk(MOUNT, "NFS: server does not support requested auth flavor\n"); + nfs_umount(request); + return -EACCES; +} + +/* * Use the remote server's MOUNT service to request the NFS file handle * corresponding to the provided path. */ static int nfs_try_mount(struct nfs_parsed_mount_data *args, struct nfs_fh *root_fh) { - unsigned int auth_flavor_len = 0; + rpc_authflavor_t server_authlist[NFS_MAX_SECFLAVORS]; + unsigned int server_authlist_len = ARRAY_SIZE(server_authlist); struct nfs_mount_request request = { .sap = (struct sockaddr *) &args->mount_server.address, @@ -1459,7 +1424,8 @@ static int nfs_try_mount(struct nfs_parsed_mount_data *args, .protocol = args->mount_server.protocol, .fh = root_fh, .noresvport = args->flags & NFS_MOUNT_NORESVPORT, - .auth_flav_len = &auth_flavor_len, + .auth_flav_len = &server_authlist_len, + .auth_flavs = server_authlist, }; int status; @@ -1485,23 +1451,25 @@ static int nfs_try_mount(struct nfs_parsed_mount_data *args, args->mount_server.addrlen = args->nfs_server.addrlen; } request.salen = args->mount_server.addrlen; - - /* - * autobind will be used if mount_server.port == 0 - */ - nfs_set_port(request.sap, args->mount_server.port); + nfs_set_default_port(request.sap, args->mount_server.port, 0); /* * Now ask the mount server to map our export path * to a file handle. */ status = nfs_mount(&request); - if (status == 0) - return 0; + if (status != 0) { + dfprintk(MOUNT, "NFS: unable to mount server %s, error %d\n", + request.hostname, status); + return status; + } - dfprintk(MOUNT, "NFS: unable to mount server %s, error %d\n", - request.hostname, status); - return status; + /* + * MNTv1 (NFSv2) does not support auth flavor negotiation. + */ + if (args->mount_server.version != NFS_MNT3_VERSION) + return 0; + return nfs_walk_authlist(args, &request); } static int nfs_parse_simple_hostname(const char *dev_name, @@ -1661,6 +1629,7 @@ static int nfs_validate_mount_data(void *options, const char *dev_name) { struct nfs_mount_data *data = (struct nfs_mount_data *)options; + struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address; if (data == NULL) goto out_no_data; @@ -1672,10 +1641,12 @@ static int nfs_validate_mount_data(void *options, args->acregmax = NFS_DEF_ACREGMAX; args->acdirmin = NFS_DEF_ACDIRMIN; args->acdirmax = NFS_DEF_ACDIRMAX; - args->mount_server.port = 0; /* autobind unless user sets port */ - args->nfs_server.port = 0; /* autobind unless user sets port */ + args->mount_server.port = NFS_UNSPEC_PORT; + args->nfs_server.port = NFS_UNSPEC_PORT; args->nfs_server.protocol = XPRT_TRANSPORT_TCP; args->auth_flavors[0] = RPC_AUTH_UNIX; + args->auth_flavor_len = 1; + args->minorversion = 0; switch (data->version) { case 1: @@ -1697,8 +1668,11 @@ static int nfs_validate_mount_data(void *options, if (data->root.size > NFS3_FHSIZE || data->root.size == 0) goto out_invalid_fh; mntfh->size = data->root.size; - } else + args->version = 3; + } else { mntfh->size = NFS2_FHSIZE; + args->version = 2; + } memcpy(mntfh->data, data->root.data, mntfh->size); @@ -1720,11 +1694,9 @@ static int nfs_validate_mount_data(void *options, args->acdirmin = data->acdirmin; args->acdirmax = data->acdirmax; - memcpy(&args->nfs_server.address, &data->addr, - sizeof(data->addr)); + memcpy(sap, &data->addr, sizeof(data->addr)); args->nfs_server.addrlen = sizeof(data->addr); - if (!nfs_verify_server_address((struct sockaddr *) - &args->nfs_server.address)) + if (!nfs_verify_server_address(sap)) goto out_no_address; if (!(data->flags & NFS_MOUNT_TCP)) @@ -1772,12 +1744,18 @@ static int nfs_validate_mount_data(void *options, if (nfs_parse_mount_options((char *)options, args) == 0) return -EINVAL; - if (!nfs_verify_server_address((struct sockaddr *) - &args->nfs_server.address)) + if (!nfs_verify_server_address(sap)) goto out_no_address; - nfs_set_port((struct sockaddr *)&args->nfs_server.address, - args->nfs_server.port); + if (args->version == 4) +#ifdef CONFIG_NFS_V4 + return nfs4_validate_text_mount_data(options, + args, dev_name); +#else + goto out_v4_not_compiled; +#endif + + nfs_set_default_port(sap, args->nfs_server.port, 0); nfs_set_mount_transport_protocol(args); @@ -1825,6 +1803,12 @@ out_v3_not_compiled: return -EPROTONOSUPPORT; #endif /* !CONFIG_NFS_V3 */ +#ifndef CONFIG_NFS_V4 +out_v4_not_compiled: + dfprintk(MOUNT, "NFS: NFSv4 is not compiled into kernel\n"); + return -EPROTONOSUPPORT; +#endif /* !CONFIG_NFS_V4 */ + out_nomem: dfprintk(MOUNT, "NFS: not enough memory to handle mount options\n"); return -ENOMEM; @@ -2120,6 +2104,14 @@ static int nfs_get_sb(struct file_system_type *fs_type, if (error < 0) goto out; +#ifdef CONFIG_NFS_V4 + if (data->version == 4) { + error = nfs4_try_mount(flags, dev_name, data, mnt); + kfree(data->client_address); + goto out; + } +#endif /* CONFIG_NFS_V4 */ + /* Get a volume representation */ server = nfs_create_server(data, mntfh); if (IS_ERR(server)) { @@ -2317,6 +2309,43 @@ static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *args) args->flags &= ~(NFS_MOUNT_NONLM|NFS_MOUNT_NOACL|NFS_MOUNT_VER3); } +static int nfs4_validate_text_mount_data(void *options, + struct nfs_parsed_mount_data *args, + const char *dev_name) +{ + struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address; + + nfs_set_default_port(sap, args->nfs_server.port, NFS_PORT); + + nfs_validate_transport_protocol(args); + + nfs4_validate_mount_flags(args); + + if (args->version != 4) { + dfprintk(MOUNT, + "NFS4: Illegal mount version\n"); + return -EINVAL; + } + + if (args->auth_flavor_len > 1) { + dfprintk(MOUNT, + "NFS4: Too many RPC auth flavours specified\n"); + return -EINVAL; + } + + if (args->client_address == NULL) { + dfprintk(MOUNT, + "NFS4: mount program didn't pass callback address\n"); + return -EINVAL; + } + + return nfs_parse_devname(dev_name, + &args->nfs_server.hostname, + NFS4_MAXNAMLEN, + &args->nfs_server.export_path, + NFS4_MAXPATHLEN); +} + /* * Validate NFSv4 mount options */ @@ -2324,7 +2353,7 @@ static int nfs4_validate_mount_data(void *options, struct nfs_parsed_mount_data *args, const char *dev_name) { - struct sockaddr_in *ap; + struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address; struct nfs4_mount_data *data = (struct nfs4_mount_data *)options; char *c; @@ -2337,23 +2366,22 @@ static int nfs4_validate_mount_data(void *options, args->acregmax = NFS_DEF_ACREGMAX; args->acdirmin = NFS_DEF_ACDIRMIN; args->acdirmax = NFS_DEF_ACDIRMAX; - args->nfs_server.port = NFS_PORT; /* 2049 unless user set port= */ + args->nfs_server.port = NFS_UNSPEC_PORT; args->auth_flavors[0] = RPC_AUTH_UNIX; - args->auth_flavor_len = 0; + args->auth_flavor_len = 1; + args->version = 4; args->minorversion = 0; switch (data->version) { case 1: - ap = (struct sockaddr_in *)&args->nfs_server.address; if (data->host_addrlen > sizeof(args->nfs_server.address)) goto out_no_address; if (data->host_addrlen == 0) goto out_no_address; args->nfs_server.addrlen = data->host_addrlen; - if (copy_from_user(ap, data->host_addr, data->host_addrlen)) + if (copy_from_user(sap, data->host_addr, data->host_addrlen)) return -EFAULT; - if (!nfs_verify_server_address((struct sockaddr *) - &args->nfs_server.address)) + if (!nfs_verify_server_address(sap)) goto out_no_address; if (data->auth_flavourlen) { @@ -2399,39 +2427,14 @@ static int nfs4_validate_mount_data(void *options, nfs_validate_transport_protocol(args); break; - default: { - int status; - + default: if (nfs_parse_mount_options((char *)options, args) == 0) return -EINVAL; - if (!nfs_verify_server_address((struct sockaddr *) - &args->nfs_server.address)) + if (!nfs_verify_server_address(sap)) return -EINVAL; - nfs_set_port((struct sockaddr *)&args->nfs_server.address, - args->nfs_server.port); - - nfs_validate_transport_protocol(args); - - nfs4_validate_mount_flags(args); - - if (args->auth_flavor_len > 1) - goto out_inval_auth; - - if (args->client_address == NULL) - goto out_no_client_address; - - status = nfs_parse_devname(dev_name, - &args->nfs_server.hostname, - NFS4_MAXNAMLEN, - &args->nfs_server.export_path, - NFS4_MAXPATHLEN); - if (status < 0) - return status; - - break; - } + return nfs4_validate_text_mount_data(options, args, dev_name); } return 0; @@ -2448,10 +2451,6 @@ out_inval_auth: out_no_address: dfprintk(MOUNT, "NFS4: mount program didn't pass remote address\n"); return -EINVAL; - -out_no_client_address: - dfprintk(MOUNT, "NFS4: mount program didn't pass callback address\n"); - return -EINVAL; } /* @@ -2618,6 +2617,34 @@ out_err: return ret; } +static int nfs4_try_mount(int flags, const char *dev_name, + struct nfs_parsed_mount_data *data, + struct vfsmount *mnt) +{ + char *export_path; + struct vfsmount *root_mnt; + int error; + + dfprintk(MOUNT, "--> nfs4_try_mount()\n"); + + export_path = data->nfs_server.export_path; + data->nfs_server.export_path = "/"; + root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, data, + data->nfs_server.hostname); + data->nfs_server.export_path = export_path; + + error = PTR_ERR(root_mnt); + if (IS_ERR(root_mnt)) + goto out; + + error = nfs_follow_remote_path(root_mnt, export_path, mnt); + +out: + dfprintk(MOUNT, "<-- nfs4_try_mount() = %d%s\n", error, + error != 0 ? " [error]" : ""); + return error; +} + /* * Get the superblock for an NFS4 mountpoint */ @@ -2625,8 +2652,6 @@ static int nfs4_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt) { struct nfs_parsed_mount_data *data; - char *export_path; - struct vfsmount *root_mnt; int error = -ENOMEM; data = kzalloc(sizeof(*data), GFP_KERNEL); @@ -2638,17 +2663,7 @@ static int nfs4_get_sb(struct file_system_type *fs_type, if (error < 0) goto out; - export_path = data->nfs_server.export_path; - data->nfs_server.export_path = "/"; - root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, data, - data->nfs_server.hostname); - data->nfs_server.export_path = export_path; - - error = PTR_ERR(root_mnt); - if (IS_ERR(root_mnt)) - goto out; - - error = nfs_follow_remote_path(root_mnt, export_path, mnt); + error = nfs4_try_mount(flags, dev_name, data, mnt); out: kfree(data->client_address); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index a34fae2..120acad 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -13,6 +13,7 @@ #include <linux/file.h> #include <linux/writeback.h> #include <linux/swap.h> +#include <linux/migrate.h> #include <linux/sunrpc/clnt.h> #include <linux/nfs_fs.h> @@ -26,6 +27,7 @@ #include "internal.h" #include "iostat.h" #include "nfs4_fs.h" +#include "fscache.h" #define NFSDBG_FACILITY NFSDBG_PAGECACHE @@ -218,24 +220,17 @@ static void nfs_end_page_writeback(struct page *page) clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC); } -/* - * Find an associated nfs write request, and prepare to flush it out - * May return an error if the user signalled nfs_wait_on_request(). - */ -static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, - struct page *page) +static struct nfs_page *nfs_find_and_lock_request(struct page *page) { struct inode *inode = page->mapping->host; struct nfs_page *req; int ret; spin_lock(&inode->i_lock); - for(;;) { + for (;;) { req = nfs_page_find_request_locked(page); - if (req == NULL) { - spin_unlock(&inode->i_lock); - return 0; - } + if (req == NULL) + break; if (nfs_set_page_tag_locked(req)) break; /* Note: If we hold the page lock, as is the case in nfs_writepage, @@ -247,23 +242,40 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, ret = nfs_wait_on_request(req); nfs_release_request(req); if (ret != 0) - return ret; + return ERR_PTR(ret); spin_lock(&inode->i_lock); } - if (test_bit(PG_CLEAN, &req->wb_flags)) { - spin_unlock(&inode->i_lock); - BUG(); - } - if (nfs_set_page_writeback(page) != 0) { - spin_unlock(&inode->i_lock); - BUG(); - } spin_unlock(&inode->i_lock); + return req; +} + +/* + * Find an associated nfs write request, and prepare to flush it out + * May return an error if the user signalled nfs_wait_on_request(). + */ +static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, + struct page *page) +{ + struct nfs_page *req; + int ret = 0; + + req = nfs_find_and_lock_request(page); + if (!req) + goto out; + ret = PTR_ERR(req); + if (IS_ERR(req)) + goto out; + + ret = nfs_set_page_writeback(page); + BUG_ON(ret != 0); + BUG_ON(test_bit(PG_CLEAN, &req->wb_flags)); + if (!nfs_pageio_add_request(pgio, req)) { nfs_redirty_request(req); - return pgio->pg_error; + ret = pgio->pg_error; } - return 0; +out: + return ret; } static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio) @@ -1580,6 +1592,41 @@ int nfs_wb_page(struct inode *inode, struct page* page) return nfs_wb_page_priority(inode, page, FLUSH_STABLE); } +#ifdef CONFIG_MIGRATION +int nfs_migrate_page(struct address_space *mapping, struct page *newpage, + struct page *page) +{ + struct nfs_page *req; + int ret; + + if (PageFsCache(page)) + nfs_fscache_release_page(page, GFP_KERNEL); + + req = nfs_find_and_lock_request(page); + ret = PTR_ERR(req); + if (IS_ERR(req)) + goto out; + + ret = migrate_page(mapping, newpage, page); + if (!req) + goto out; + if (ret) + goto out_unlock; + page_cache_get(newpage); + req->wb_page = newpage; + SetPagePrivate(newpage); + set_page_private(newpage, page_private(page)); + ClearPagePrivate(page); + set_page_private(page, 0); + page_cache_release(page); +out_unlock: + nfs_clear_page_tag_locked(req); + nfs_release_request(req); +out: + return ret; +} +#endif + int __init nfs_init_writepagecache(void) { nfs_wdata_cachep = kmem_cache_create("nfs_write_data", diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index b92a276..d946264 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -85,6 +85,11 @@ static void expkey_request(struct cache_detail *cd, (*bpp)[-1] = '\n'; } +static int expkey_upcall(struct cache_detail *cd, struct cache_head *h) +{ + return sunrpc_cache_pipe_upcall(cd, h, expkey_request); +} + static struct svc_expkey *svc_expkey_update(struct svc_expkey *new, struct svc_expkey *old); static struct svc_expkey *svc_expkey_lookup(struct svc_expkey *); static struct cache_detail svc_expkey_cache; @@ -259,7 +264,7 @@ static struct cache_detail svc_expkey_cache = { .hash_table = expkey_table, .name = "nfsd.fh", .cache_put = expkey_put, - .cache_request = expkey_request, + .cache_upcall = expkey_upcall, .cache_parse = expkey_parse, .cache_show = expkey_show, .match = expkey_match, @@ -355,6 +360,11 @@ static void svc_export_request(struct cache_detail *cd, (*bpp)[-1] = '\n'; } +static int svc_export_upcall(struct cache_detail *cd, struct cache_head *h) +{ + return sunrpc_cache_pipe_upcall(cd, h, svc_export_request); +} + static struct svc_export *svc_export_update(struct svc_export *new, struct svc_export *old); static struct svc_export *svc_export_lookup(struct svc_export *); @@ -724,7 +734,7 @@ struct cache_detail svc_export_cache = { .hash_table = export_table, .name = "nfsd.export", .cache_put = svc_export_put, - .cache_request = svc_export_request, + .cache_upcall = svc_export_upcall, .cache_parse = svc_export_parse, .cache_show = svc_export_show, .match = svc_export_match, diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index 5b39842..cdfa86f 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -146,6 +146,12 @@ idtoname_request(struct cache_detail *cd, struct cache_head *ch, char **bpp, } static int +idtoname_upcall(struct cache_detail *cd, struct cache_head *ch) +{ + return sunrpc_cache_pipe_upcall(cd, ch, idtoname_request); +} + +static int idtoname_match(struct cache_head *ca, struct cache_head *cb) { struct ent *a = container_of(ca, struct ent, h); @@ -175,10 +181,10 @@ idtoname_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h) } static void -warn_no_idmapd(struct cache_detail *detail) +warn_no_idmapd(struct cache_detail *detail, int has_died) { printk("nfsd: nfsv4 idmapping failing: has idmapd %s?\n", - detail->last_close? "died" : "not been started"); + has_died ? "died" : "not been started"); } @@ -192,7 +198,7 @@ static struct cache_detail idtoname_cache = { .hash_table = idtoname_table, .name = "nfs4.idtoname", .cache_put = ent_put, - .cache_request = idtoname_request, + .cache_upcall = idtoname_upcall, .cache_parse = idtoname_parse, .cache_show = idtoname_show, .warn_no_listener = warn_no_idmapd, @@ -325,6 +331,12 @@ nametoid_request(struct cache_detail *cd, struct cache_head *ch, char **bpp, } static int +nametoid_upcall(struct cache_detail *cd, struct cache_head *ch) +{ + return sunrpc_cache_pipe_upcall(cd, ch, nametoid_request); +} + +static int nametoid_match(struct cache_head *ca, struct cache_head *cb) { struct ent *a = container_of(ca, struct ent, h); @@ -363,7 +375,7 @@ static struct cache_detail nametoid_cache = { .hash_table = nametoid_table, .name = "nfs4.nametoid", .cache_put = ent_put, - .cache_request = nametoid_request, + .cache_upcall = nametoid_upcall, .cache_parse = nametoid_parse, .cache_show = nametoid_show, .warn_no_listener = warn_no_idmapd, diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 6d08475..7e906c5 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -37,6 +37,7 @@ #include <linux/nfsd/xdr.h> #include <linux/nfsd/syscall.h> #include <linux/lockd/lockd.h> +#include <linux/sunrpc/clnt.h> #include <asm/uaccess.h> #include <net/ipv6.h> @@ -490,22 +491,18 @@ static ssize_t write_getfd(struct file *file, char *buf, size_t size) * * Input: * buf: '\n'-terminated C string containing a - * presentation format IPv4 address + * presentation format IP address * size: length of C string in @buf * Output: * On success: returns zero if all specified locks were released; * returns one if one or more locks were not released * On error: return code is negative errno value - * - * Note: Only AF_INET client addresses are passed in */ static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size) { - struct sockaddr_in sin = { - .sin_family = AF_INET, - }; - int b1, b2, b3, b4; - char c; + struct sockaddr_storage address; + struct sockaddr *sap = (struct sockaddr *)&address; + size_t salen = sizeof(address); char *fo_path; /* sanity check */ @@ -519,14 +516,10 @@ static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size) if (qword_get(&buf, fo_path, size) < 0) return -EINVAL; - /* get ipv4 address */ - if (sscanf(fo_path, "%u.%u.%u.%u%c", &b1, &b2, &b3, &b4, &c) != 4) - return -EINVAL; - if (b1 > 255 || b2 > 255 || b3 > 255 || b4 > 255) + if (rpc_pton(fo_path, size, sap, salen) == 0) return -EINVAL; - sin.sin_addr.s_addr = htonl((b1 << 24) | (b2 << 16) | (b3 << 8) | b4); - return nlmsvc_unlock_all_by_ip((struct sockaddr *)&sin); + return nlmsvc_unlock_all_by_ip(sap); } /** diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index bd2eba5..33b2836 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -472,6 +472,7 @@ enum lock_type4 { #define NFSPROC4_NULL 0 #define NFSPROC4_COMPOUND 1 +#define NFS4_VERSION 4 #define NFS4_MINOR_VERSION 0 #if defined(CONFIG_NFS_V4_1) diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 19fe15d..320569e 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -167,6 +167,15 @@ struct nfs_server { #define NFS_CAP_SYMLINKS (1U << 2) #define NFS_CAP_ACLS (1U << 3) #define NFS_CAP_ATOMIC_OPEN (1U << 4) +#define NFS_CAP_CHANGE_ATTR (1U << 5) +#define NFS_CAP_FILEID (1U << 6) +#define NFS_CAP_MODE (1U << 7) +#define NFS_CAP_NLINK (1U << 8) +#define NFS_CAP_OWNER (1U << 9) +#define NFS_CAP_OWNER_GROUP (1U << 10) +#define NFS_CAP_ATIME (1U << 11) +#define NFS_CAP_CTIME (1U << 12) +#define NFS_CAP_MTIME (1U << 13) /* maximum number of slots to use */ diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 2d8b211..6f52b4d 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -59,6 +59,15 @@ struct cache_head { #define CACHE_NEW_EXPIRY 120 /* keep new things pending confirmation for 120 seconds */ +struct cache_detail_procfs { + struct proc_dir_entry *proc_ent; + struct proc_dir_entry *flush_ent, *channel_ent, *content_ent; +}; + +struct cache_detail_pipefs { + struct dentry *dir; +}; + struct cache_detail { struct module * owner; int hash_size; @@ -70,15 +79,17 @@ struct cache_detail { char *name; void (*cache_put)(struct kref *); - void (*cache_request)(struct cache_detail *cd, - struct cache_head *h, - char **bpp, int *blen); + int (*cache_upcall)(struct cache_detail *, + struct cache_head *); + int (*cache_parse)(struct cache_detail *, char *buf, int len); int (*cache_show)(struct seq_file *m, struct cache_detail *cd, struct cache_head *h); + void (*warn_no_listener)(struct cache_detail *cd, + int has_died); struct cache_head * (*alloc)(void); int (*match)(struct cache_head *orig, struct cache_head *new); @@ -96,13 +107,15 @@ struct cache_detail { /* fields for communication over channel */ struct list_head queue; - struct proc_dir_entry *proc_ent; - struct proc_dir_entry *flush_ent, *channel_ent, *content_ent; atomic_t readers; /* how many time is /chennel open */ time_t last_close; /* if no readers, when did last close */ time_t last_warn; /* when we last warned about no readers */ - void (*warn_no_listener)(struct cache_detail *cd); + + union { + struct cache_detail_procfs procfs; + struct cache_detail_pipefs pipefs; + } u; }; @@ -127,6 +140,10 @@ struct cache_deferred_req { }; +extern const struct file_operations cache_file_operations_pipefs; +extern const struct file_operations content_file_operations_pipefs; +extern const struct file_operations cache_flush_operations_pipefs; + extern struct cache_head * sunrpc_cache_lookup(struct cache_detail *detail, struct cache_head *key, int hash); @@ -134,6 +151,13 @@ extern struct cache_head * sunrpc_cache_update(struct cache_detail *detail, struct cache_head *new, struct cache_head *old, int hash); +extern int +sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h, + void (*cache_request)(struct cache_detail *, + struct cache_head *, + char **, + int *)); + extern void cache_clean_deferred(void *owner); @@ -171,6 +195,10 @@ extern void cache_purge(struct cache_detail *detail); extern int cache_register(struct cache_detail *cd); extern void cache_unregister(struct cache_detail *cd); +extern int sunrpc_cache_register_pipefs(struct dentry *parent, const char *, + mode_t, struct cache_detail *); +extern void sunrpc_cache_unregister_pipefs(struct cache_detail *); + extern void qword_add(char **bpp, int *lp, char *str); extern void qword_addhex(char **bpp, int *lp, char *buf, int blen); extern int qword_get(char **bpp, char *dest, int bufsize); diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 37881f1a..ab3f6e90 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -9,6 +9,10 @@ #ifndef _LINUX_SUNRPC_CLNT_H #define _LINUX_SUNRPC_CLNT_H +#include <linux/socket.h> +#include <linux/in.h> +#include <linux/in6.h> + #include <linux/sunrpc/msg_prot.h> #include <linux/sunrpc/sched.h> #include <linux/sunrpc/xprt.h> @@ -17,6 +21,7 @@ #include <linux/sunrpc/xdr.h> #include <linux/sunrpc/timer.h> #include <asm/signal.h> +#include <linux/path.h> struct rpc_inode; @@ -50,9 +55,7 @@ struct rpc_clnt { int cl_nodelen; /* nodename length */ char cl_nodename[UNX_MAXNODENAME]; - char cl_pathname[30];/* Path in rpc_pipe_fs */ - struct vfsmount * cl_vfsmnt; - struct dentry * cl_dentry; /* inode */ + struct path cl_path; struct rpc_clnt * cl_parent; /* Points to parent of clones */ struct rpc_rtt cl_rtt_default; struct rpc_timeout cl_timeout_default; @@ -151,5 +154,39 @@ void rpc_force_rebind(struct rpc_clnt *); size_t rpc_peeraddr(struct rpc_clnt *, struct sockaddr *, size_t); const char *rpc_peeraddr2str(struct rpc_clnt *, enum rpc_display_format_t); +size_t rpc_ntop(const struct sockaddr *, char *, const size_t); +size_t rpc_pton(const char *, const size_t, + struct sockaddr *, const size_t); +char * rpc_sockaddr2uaddr(const struct sockaddr *); +size_t rpc_uaddr2sockaddr(const char *, const size_t, + struct sockaddr *, const size_t); + +static inline unsigned short rpc_get_port(const struct sockaddr *sap) +{ + switch (sap->sa_family) { + case AF_INET: + return ntohs(((struct sockaddr_in *)sap)->sin_port); + case AF_INET6: + return ntohs(((struct sockaddr_in6 *)sap)->sin6_port); + } + return 0; +} + +static inline void rpc_set_port(struct sockaddr *sap, + const unsigned short port) +{ + switch (sap->sa_family) { + case AF_INET: + ((struct sockaddr_in *)sap)->sin_port = htons(port); + break; + case AF_INET6: + ((struct sockaddr_in6 *)sap)->sin6_port = htons(port); + break; + } +} + +#define IPV6_SCOPE_DELIMITER '%' +#define IPV6_SCOPE_ID_LEN sizeof("%nnnnnnnnnn") + #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_CLNT_H */ diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h index 70df4f1..77e6248 100644 --- a/include/linux/sunrpc/msg_prot.h +++ b/include/linux/sunrpc/msg_prot.h @@ -189,7 +189,22 @@ typedef __be32 rpc_fraghdr; * Additionally, the two alternative forms specified in Section 2.2 of * [RFC2373] are also acceptable. */ -#define RPCBIND_MAXUADDRLEN (56u) + +#include <linux/inet.h> + +/* Maximum size of the port number part of a universal address */ +#define RPCBIND_MAXUADDRPLEN sizeof(".255.255") + +/* Maximum size of an IPv4 universal address */ +#define RPCBIND_MAXUADDR4LEN \ + (INET_ADDRSTRLEN + RPCBIND_MAXUADDRPLEN) + +/* Maximum size of an IPv6 universal address */ +#define RPCBIND_MAXUADDR6LEN \ + (INET6_ADDRSTRLEN + RPCBIND_MAXUADDRPLEN) + +/* Assume INET6_ADDRSTRLEN will always be larger than INET_ADDRSTRLEN... */ +#define RPCBIND_MAXUADDRLEN RPCBIND_MAXUADDR6LEN #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_MSGPROT_H_ */ diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index cea764c..cf14db9 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -3,6 +3,8 @@ #ifdef __KERNEL__ +#include <linux/workqueue.h> + struct rpc_pipe_msg { struct list_head list; void *data; @@ -32,8 +34,8 @@ struct rpc_inode { wait_queue_head_t waitq; #define RPC_PIPE_WAIT_FOR_OPEN 1 int flags; - struct rpc_pipe_ops *ops; struct delayed_work queue_timeout; + const struct rpc_pipe_ops *ops; }; static inline struct rpc_inode * @@ -44,9 +46,19 @@ RPC_I(struct inode *inode) extern int rpc_queue_upcall(struct inode *, struct rpc_pipe_msg *); -extern struct dentry *rpc_mkdir(char *, struct rpc_clnt *); -extern int rpc_rmdir(struct dentry *); -extern struct dentry *rpc_mkpipe(struct dentry *, const char *, void *, struct rpc_pipe_ops *, int flags); +struct rpc_clnt; +extern struct dentry *rpc_create_client_dir(struct dentry *, struct qstr *, struct rpc_clnt *); +extern int rpc_remove_client_dir(struct dentry *); + +struct cache_detail; +extern struct dentry *rpc_create_cache_dir(struct dentry *, + struct qstr *, + mode_t umode, + struct cache_detail *); +extern void rpc_remove_cache_dir(struct dentry *); + +extern struct dentry *rpc_mkpipe(struct dentry *, const char *, void *, + const struct rpc_pipe_ops *, int flags); extern int rpc_unlink(struct dentry *); extern struct vfsmount *rpc_get_mount(void); extern void rpc_put_mount(void); diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index b99c625..7da466b 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -117,17 +117,15 @@ static inline __be32 *xdr_encode_array(__be32 *p, const void *s, unsigned int le static inline __be32 * xdr_encode_hyper(__be32 *p, __u64 val) { - *p++ = htonl(val >> 32); - *p++ = htonl(val & 0xFFFFFFFF); - return p; + *(__be64 *)p = cpu_to_be64(val); + return p + 2; } static inline __be32 * xdr_decode_hyper(__be32 *p, __u64 *valp) { - *valp = ((__u64) ntohl(*p++)) << 32; - *valp |= ntohl(*p++); - return p; + *valp = be64_to_cpup((__be64 *)p); + return p + 2; } /* diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 1175d58..c090df4 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -38,10 +38,8 @@ enum rpc_display_format_t { RPC_DISPLAY_ADDR = 0, RPC_DISPLAY_PORT, RPC_DISPLAY_PROTO, - RPC_DISPLAY_ALL, RPC_DISPLAY_HEX_ADDR, RPC_DISPLAY_HEX_PORT, - RPC_DISPLAY_UNIVERSAL_ADDR, RPC_DISPLAY_NETID, RPC_DISPLAY_MAX, }; diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile index db73fd2..9d2fca5 100644 --- a/net/sunrpc/Makefile +++ b/net/sunrpc/Makefile @@ -10,7 +10,7 @@ obj-$(CONFIG_SUNRPC_XPRT_RDMA) += xprtrdma/ sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \ auth.o auth_null.o auth_unix.o auth_generic.o \ svc.o svcsock.o svcauth.o svcauth_unix.o \ - rpcb_clnt.o timer.o xdr.o \ + addr.o rpcb_clnt.o timer.o xdr.o \ sunrpc_syms.o cache.o rpc_pipe.o \ svc_xprt.o sunrpc-$(CONFIG_NFS_V4_1) += backchannel_rqst.o bc_svc.o diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c new file mode 100644 index 0000000..22e8fd8 --- /dev/null +++ b/net/sunrpc/addr.c @@ -0,0 +1,364 @@ +/* + * Copyright 2009, Oracle. All rights reserved. + * + * Convert socket addresses to presentation addresses and universal + * addresses, and vice versa. + * + * Universal addresses are introduced by RFC 1833 and further refined by + * recent RFCs describing NFSv4. The universal address format is part + * of the external (network) interface provided by rpcbind version 3 + * and 4, and by NFSv4. Such an address is a string containing a + * presentation format IP address followed by a port number in + * "hibyte.lobyte" format. + * + * IPv6 addresses can also include a scope ID, typically denoted by + * a '%' followed by a device name or a non-negative integer. Refer to + * RFC 4291, Section 2.2 for details on IPv6 presentation formats. + */ + +#include <net/ipv6.h> +#include <linux/sunrpc/clnt.h> + +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + +static size_t rpc_ntop6_noscopeid(const struct sockaddr *sap, + char *buf, const int buflen) +{ + const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap; + const struct in6_addr *addr = &sin6->sin6_addr; + + /* + * RFC 4291, Section 2.2.2 + * + * Shorthanded ANY address + */ + if (ipv6_addr_any(addr)) + return snprintf(buf, buflen, "::"); + + /* + * RFC 4291, Section 2.2.2 + * + * Shorthanded loopback address + */ + if (ipv6_addr_loopback(addr)) + return snprintf(buf, buflen, "::1"); + + /* + * RFC 4291, Section 2.2.3 + * + * Special presentation address format for mapped v4 + * addresses. + */ + if (ipv6_addr_v4mapped(addr)) + return snprintf(buf, buflen, "::ffff:%pI4", + &addr->s6_addr32[3]); + + /* + * RFC 4291, Section 2.2.1 + * + * To keep the result as short as possible, especially + * since we don't shorthand, we don't want leading zeros + * in each halfword, so avoid %pI6. + */ + return snprintf(buf, buflen, "%x:%x:%x:%x:%x:%x:%x:%x", + ntohs(addr->s6_addr16[0]), ntohs(addr->s6_addr16[1]), + ntohs(addr->s6_addr16[2]), ntohs(addr->s6_addr16[3]), + ntohs(addr->s6_addr16[4]), ntohs(addr->s6_addr16[5]), + ntohs(addr->s6_addr16[6]), ntohs(addr->s6_addr16[7])); +} + +static size_t rpc_ntop6(const struct sockaddr *sap, + char *buf, const size_t buflen) +{ + const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap; + char scopebuf[IPV6_SCOPE_ID_LEN]; + size_t len; + int rc; + + len = rpc_ntop6_noscopeid(sap, buf, buflen); + if (unlikely(len == 0)) + return len; + + if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) && + !(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_SITELOCAL)) + return len; + + rc = snprintf(scopebuf, sizeof(scopebuf), "%c%u", + IPV6_SCOPE_DELIMITER, sin6->sin6_scope_id); + if (unlikely((size_t)rc > sizeof(scopebuf))) + return 0; + + len += rc; + if (unlikely(len > buflen)) + return 0; + + strcat(buf, scopebuf); + return len; +} + +#else /* !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)) */ + +static size_t rpc_ntop6_noscopeid(const struct sockaddr *sap, + char *buf, const int buflen) +{ + return 0; +} + +static size_t rpc_ntop6(const struct sockaddr *sap, + char *buf, const size_t buflen) +{ + return 0; +} + +#endif /* !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)) */ + +static int rpc_ntop4(const struct sockaddr *sap, + char *buf, const size_t buflen) +{ + const struct sockaddr_in *sin = (struct sockaddr_in *)sap; + + return snprintf(buf, buflen, "%pI4", &sin->sin_addr); +} + +/** + * rpc_ntop - construct a presentation address in @buf + * @sap: socket address + * @buf: construction area + * @buflen: size of @buf, in bytes + * + * Plants a %NUL-terminated string in @buf and returns the length + * of the string, excluding the %NUL. Otherwise zero is returned. + */ +size_t rpc_ntop(const struct sockaddr *sap, char *buf, const size_t buflen) +{ + switch (sap->sa_family) { + case AF_INET: + return rpc_ntop4(sap, buf, buflen); + case AF_INET6: + return rpc_ntop6(sap, buf, buflen); + } + + return 0; +} +EXPORT_SYMBOL_GPL(rpc_ntop); + +static size_t rpc_pton4(const char *buf, const size_t buflen, + struct sockaddr *sap, const size_t salen) +{ + struct sockaddr_in *sin = (struct sockaddr_in *)sap; + u8 *addr = (u8 *)&sin->sin_addr.s_addr; + + if (buflen > INET_ADDRSTRLEN || salen < sizeof(struct sockaddr_in)) + return 0; + + memset(sap, 0, sizeof(struct sockaddr_in)); + + if (in4_pton(buf, buflen, addr, '\0', NULL) == 0) + return 0; + + sin->sin_family = AF_INET; + return sizeof(struct sockaddr_in);; +} + +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +static int rpc_parse_scope_id(const char *buf, const size_t buflen, + const char *delim, struct sockaddr_in6 *sin6) +{ + char *p; + size_t len; + + if ((buf + buflen) == delim) + return 1; + + if (*delim != IPV6_SCOPE_DELIMITER) + return 0; + + if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) && + !(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_SITELOCAL)) + return 0; + + len = (buf + buflen) - delim - 1; + p = kstrndup(delim + 1, len, GFP_KERNEL); + if (p) { + unsigned long scope_id = 0; + struct net_device *dev; + + dev = dev_get_by_name(&init_net, p); + if (dev != NULL) { + scope_id = dev->ifindex; + dev_put(dev); + } else { + if (strict_strtoul(p, 10, &scope_id) == 0) { + kfree(p); + return 0; + } + } + + kfree(p); + + sin6->sin6_scope_id = scope_id; + return 1; + } + + return 0; +} + +static size_t rpc_pton6(const char *buf, const size_t buflen, + struct sockaddr *sap, const size_t salen) +{ + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap; + u8 *addr = (u8 *)&sin6->sin6_addr.in6_u; + const char *delim; + + if (buflen > (INET6_ADDRSTRLEN + IPV6_SCOPE_ID_LEN) || + salen < sizeof(struct sockaddr_in6)) + return 0; + + memset(sap, 0, sizeof(struct sockaddr_in6)); + + if (in6_pton(buf, buflen, addr, IPV6_SCOPE_DELIMITER, &delim) == 0) + return 0; + + if (!rpc_parse_scope_id(buf, buflen, delim, sin6)) + return 0; + + sin6->sin6_family = AF_INET6; + return sizeof(struct sockaddr_in6); +} +#else +static size_t rpc_pton6(const char *buf, const size_t buflen, + struct sockaddr *sap, const size_t salen) +{ + return 0; +} +#endif + +/** + * rpc_pton - Construct a sockaddr in @sap + * @buf: C string containing presentation format IP address + * @buflen: length of presentation address in bytes + * @sap: buffer into which to plant socket address + * @salen: size of buffer in bytes + * + * Returns the size of the socket address if successful; otherwise + * zero is returned. + * + * Plants a socket address in @sap and returns the size of the + * socket address, if successful. Returns zero if an error + * occurred. + */ +size_t rpc_pton(const char *buf, const size_t buflen, + struct sockaddr *sap, const size_t salen) +{ + unsigned int i; + + for (i = 0; i < buflen; i++) + if (buf[i] == ':') + return rpc_pton6(buf, buflen, sap, salen); + return rpc_pton4(buf, buflen, sap, salen); +} +EXPORT_SYMBOL_GPL(rpc_pton); + +/** + * rpc_sockaddr2uaddr - Construct a universal address string from @sap. + * @sap: socket address + * + * Returns a %NUL-terminated string in dynamically allocated memory; + * otherwise NULL is returned if an error occurred. Caller must + * free the returned string. + */ +char *rpc_sockaddr2uaddr(const struct sockaddr *sap) +{ + char portbuf[RPCBIND_MAXUADDRPLEN]; + char addrbuf[RPCBIND_MAXUADDRLEN]; + unsigned short port; + + switch (sap->sa_family) { + case AF_INET: + if (rpc_ntop4(sap, addrbuf, sizeof(addrbuf)) == 0) + return NULL; + port = ntohs(((struct sockaddr_in *)sap)->sin_port); + break; + case AF_INET6: + if (rpc_ntop6_noscopeid(sap, addrbuf, sizeof(addrbuf)) == 0) + return NULL; + port = ntohs(((struct sockaddr_in6 *)sap)->sin6_port); + break; + default: + return NULL; + } + + if (snprintf(portbuf, sizeof(portbuf), + ".%u.%u", port >> 8, port & 0xff) > (int)sizeof(portbuf)) + return NULL; + + if (strlcat(addrbuf, portbuf, sizeof(addrbuf)) > sizeof(addrbuf)) + return NULL; + + return kstrdup(addrbuf, GFP_KERNEL); +} +EXPORT_SYMBOL_GPL(rpc_sockaddr2uaddr); + +/** + * rpc_uaddr2sockaddr - convert a universal address to a socket address. + * @uaddr: C string containing universal address to convert + * @uaddr_len: length of universal address string + * @sap: buffer into which to plant socket address + * @salen: size of buffer + * + * Returns the size of the socket address if successful; otherwise + * zero is returned. + */ +size_t rpc_uaddr2sockaddr(const char *uaddr, const size_t uaddr_len, + struct sockaddr *sap, const size_t salen) +{ + char *c, buf[RPCBIND_MAXUADDRLEN]; + unsigned long portlo, porthi; + unsigned short port; + + if (uaddr_len > sizeof(buf)) + return 0; + + memcpy(buf, uaddr, uaddr_len); + + buf[uaddr_len] = '\n'; + buf[uaddr_len + 1] = '\0'; + + c = strrchr(buf, '.'); + if (unlikely(c == NULL)) + return 0; + if (unlikely(strict_strtoul(c + 1, 10, &portlo) != 0)) + return 0; + if (unlikely(portlo > 255)) + return 0; + + c[0] = '\n'; + c[1] = '\0'; + + c = strrchr(buf, '.'); + if (unlikely(c == NULL)) + return 0; + if (unlikely(strict_strtoul(c + 1, 10, &porthi) != 0)) + return 0; + if (unlikely(porthi > 255)) + return 0; + + port = (unsigned short)((porthi << 8) | portlo); + + c[0] = '\0'; + + if (rpc_pton(buf, strlen(buf), sap, salen) == 0) + return 0; + + switch (sap->sa_family) { + case AF_INET: + ((struct sockaddr_in *)sap)->sin_port = htons(port); + return sizeof(struct sockaddr_in); + case AF_INET6: + ((struct sockaddr_in6 *)sap)->sin6_port = htons(port); + return sizeof(struct sockaddr_in6); + } + + return 0; +} +EXPORT_SYMBOL_GPL(rpc_uaddr2sockaddr); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 66d458f..fc6a43c 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -89,8 +89,8 @@ static struct rpc_wait_queue pipe_version_rpc_waitqueue; static DECLARE_WAIT_QUEUE_HEAD(pipe_version_waitqueue); static void gss_free_ctx(struct gss_cl_ctx *); -static struct rpc_pipe_ops gss_upcall_ops_v0; -static struct rpc_pipe_ops gss_upcall_ops_v1; +static const struct rpc_pipe_ops gss_upcall_ops_v0; +static const struct rpc_pipe_ops gss_upcall_ops_v1; static inline struct gss_cl_ctx * gss_get_ctx(struct gss_cl_ctx *ctx) @@ -777,7 +777,7 @@ gss_create(struct rpc_clnt *clnt, rpc_authflavor_t flavor) * that we supported only the old pipe. So we instead create * the new pipe first. */ - gss_auth->dentry[1] = rpc_mkpipe(clnt->cl_dentry, + gss_auth->dentry[1] = rpc_mkpipe(clnt->cl_path.dentry, "gssd", clnt, &gss_upcall_ops_v1, RPC_PIPE_WAIT_FOR_OPEN); @@ -786,7 +786,7 @@ gss_create(struct rpc_clnt *clnt, rpc_authflavor_t flavor) goto err_put_mech; } - gss_auth->dentry[0] = rpc_mkpipe(clnt->cl_dentry, + gss_auth->dentry[0] = rpc_mkpipe(clnt->cl_path.dentry, gss_auth->mech->gm_name, clnt, &gss_upcall_ops_v0, RPC_PIPE_WAIT_FOR_OPEN); @@ -1507,7 +1507,7 @@ static const struct rpc_credops gss_nullops = { .crunwrap_resp = gss_unwrap_resp, }; -static struct rpc_pipe_ops gss_upcall_ops_v0 = { +static const struct rpc_pipe_ops gss_upcall_ops_v0 = { .upcall = gss_pipe_upcall, .downcall = gss_pipe_downcall, .destroy_msg = gss_pipe_destroy_msg, @@ -1515,7 +1515,7 @@ static struct rpc_pipe_ops gss_upcall_ops_v0 = { .release_pipe = gss_pipe_release, }; -static struct rpc_pipe_ops gss_upcall_ops_v1 = { +static const struct rpc_pipe_ops gss_upcall_ops_v1 = { .upcall = gss_pipe_upcall, .downcall = gss_pipe_downcall, .destroy_msg = gss_pipe_destroy_msg, diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 2278a50..2e6a148 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -181,6 +181,11 @@ static void rsi_request(struct cache_detail *cd, (*bpp)[-1] = '\n'; } +static int rsi_upcall(struct cache_detail *cd, struct cache_head *h) +{ + return sunrpc_cache_pipe_upcall(cd, h, rsi_request); +} + static int rsi_parse(struct cache_detail *cd, char *mesg, int mlen) @@ -270,7 +275,7 @@ static struct cache_detail rsi_cache = { .hash_table = rsi_table, .name = "auth.rpcsec.init", .cache_put = rsi_put, - .cache_request = rsi_request, + .cache_upcall = rsi_upcall, .cache_parse = rsi_parse, .match = rsi_match, .init = rsi_init, diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index ff0c230..45cdaff 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -27,10 +27,12 @@ #include <linux/net.h> #include <linux/workqueue.h> #include <linux/mutex.h> +#include <linux/pagemap.h> #include <asm/ioctls.h> #include <linux/sunrpc/types.h> #include <linux/sunrpc/cache.h> #include <linux/sunrpc/stats.h> +#include <linux/sunrpc/rpc_pipe_fs.h> #define RPCDBG_FACILITY RPCDBG_CACHE @@ -175,7 +177,13 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail, } EXPORT_SYMBOL_GPL(sunrpc_cache_update); -static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h); +static int cache_make_upcall(struct cache_detail *cd, struct cache_head *h) +{ + if (!cd->cache_upcall) + return -EINVAL; + return cd->cache_upcall(cd, h); +} + /* * This is the generic cache management routine for all * the authentication caches. @@ -284,76 +292,11 @@ static DEFINE_SPINLOCK(cache_list_lock); static struct cache_detail *current_detail; static int current_index; -static const struct file_operations cache_file_operations; -static const struct file_operations content_file_operations; -static const struct file_operations cache_flush_operations; - static void do_cache_clean(struct work_struct *work); static DECLARE_DELAYED_WORK(cache_cleaner, do_cache_clean); -static void remove_cache_proc_entries(struct cache_detail *cd) -{ - if (cd->proc_ent == NULL) - return; - if (cd->flush_ent) - remove_proc_entry("flush", cd->proc_ent); - if (cd->channel_ent) - remove_proc_entry("channel", cd->proc_ent); - if (cd->content_ent) - remove_proc_entry("content", cd->proc_ent); - cd->proc_ent = NULL; - remove_proc_entry(cd->name, proc_net_rpc); -} - -#ifdef CONFIG_PROC_FS -static int create_cache_proc_entries(struct cache_detail *cd) -{ - struct proc_dir_entry *p; - - cd->proc_ent = proc_mkdir(cd->name, proc_net_rpc); - if (cd->proc_ent == NULL) - goto out_nomem; - cd->channel_ent = cd->content_ent = NULL; - - p = proc_create_data("flush", S_IFREG|S_IRUSR|S_IWUSR, - cd->proc_ent, &cache_flush_operations, cd); - cd->flush_ent = p; - if (p == NULL) - goto out_nomem; - - if (cd->cache_request || cd->cache_parse) { - p = proc_create_data("channel", S_IFREG|S_IRUSR|S_IWUSR, - cd->proc_ent, &cache_file_operations, cd); - cd->channel_ent = p; - if (p == NULL) - goto out_nomem; - } - if (cd->cache_show) { - p = proc_create_data("content", S_IFREG|S_IRUSR|S_IWUSR, - cd->proc_ent, &content_file_operations, cd); - cd->content_ent = p; - if (p == NULL) - goto out_nomem; - } - return 0; -out_nomem: - remove_cache_proc_entries(cd); - return -ENOMEM; -} -#else /* CONFIG_PROC_FS */ -static int create_cache_proc_entries(struct cache_detail *cd) -{ - return 0; -} -#endif - -int cache_register(struct cache_detail *cd) +static void sunrpc_init_cache_detail(struct cache_detail *cd) { - int ret; - - ret = create_cache_proc_entries(cd); - if (ret) - return ret; rwlock_init(&cd->hash_lock); INIT_LIST_HEAD(&cd->queue); spin_lock(&cache_list_lock); @@ -367,11 +310,9 @@ int cache_register(struct cache_detail *cd) /* start the cleaning process */ schedule_delayed_work(&cache_cleaner, 0); - return 0; } -EXPORT_SYMBOL_GPL(cache_register); -void cache_unregister(struct cache_detail *cd) +static void sunrpc_destroy_cache_detail(struct cache_detail *cd) { cache_purge(cd); spin_lock(&cache_list_lock); @@ -386,7 +327,6 @@ void cache_unregister(struct cache_detail *cd) list_del_init(&cd->others); write_unlock(&cd->hash_lock); spin_unlock(&cache_list_lock); - remove_cache_proc_entries(cd); if (list_empty(&cache_list)) { /* module must be being unloaded so its safe to kill the worker */ cancel_delayed_work_sync(&cache_cleaner); @@ -395,7 +335,6 @@ void cache_unregister(struct cache_detail *cd) out: printk(KERN_ERR "nfsd: failed to unregister %s cache\n", cd->name); } -EXPORT_SYMBOL_GPL(cache_unregister); /* clean cache tries to find something to clean * and cleans it. @@ -687,18 +626,18 @@ struct cache_reader { int offset; /* if non-0, we have a refcnt on next request */ }; -static ssize_t -cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) +static ssize_t cache_read(struct file *filp, char __user *buf, size_t count, + loff_t *ppos, struct cache_detail *cd) { struct cache_reader *rp = filp->private_data; struct cache_request *rq; - struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + struct inode *inode = filp->f_path.dentry->d_inode; int err; if (count == 0) return 0; - mutex_lock(&queue_io_mutex); /* protect against multiple concurrent + mutex_lock(&inode->i_mutex); /* protect against multiple concurrent * readers on this file */ again: spin_lock(&queue_lock); @@ -711,7 +650,7 @@ cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) } if (rp->q.list.next == &cd->queue) { spin_unlock(&queue_lock); - mutex_unlock(&queue_io_mutex); + mutex_unlock(&inode->i_mutex); BUG_ON(rp->offset); return 0; } @@ -758,49 +697,90 @@ cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) } if (err == -EAGAIN) goto again; - mutex_unlock(&queue_io_mutex); + mutex_unlock(&inode->i_mutex); return err ? err : count; } -static char write_buf[8192]; /* protected by queue_io_mutex */ +static ssize_t cache_do_downcall(char *kaddr, const char __user *buf, + size_t count, struct cache_detail *cd) +{ + ssize_t ret; -static ssize_t -cache_write(struct file *filp, const char __user *buf, size_t count, - loff_t *ppos) + if (copy_from_user(kaddr, buf, count)) + return -EFAULT; + kaddr[count] = '\0'; + ret = cd->cache_parse(cd, kaddr, count); + if (!ret) + ret = count; + return ret; +} + +static ssize_t cache_slow_downcall(const char __user *buf, + size_t count, struct cache_detail *cd) { - int err; - struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + static char write_buf[8192]; /* protected by queue_io_mutex */ + ssize_t ret = -EINVAL; - if (count == 0) - return 0; if (count >= sizeof(write_buf)) - return -EINVAL; - + goto out; mutex_lock(&queue_io_mutex); + ret = cache_do_downcall(write_buf, buf, count, cd); + mutex_unlock(&queue_io_mutex); +out: + return ret; +} - if (copy_from_user(write_buf, buf, count)) { - mutex_unlock(&queue_io_mutex); - return -EFAULT; - } - write_buf[count] = '\0'; - if (cd->cache_parse) - err = cd->cache_parse(cd, write_buf, count); - else - err = -EINVAL; +static ssize_t cache_downcall(struct address_space *mapping, + const char __user *buf, + size_t count, struct cache_detail *cd) +{ + struct page *page; + char *kaddr; + ssize_t ret = -ENOMEM; + + if (count >= PAGE_CACHE_SIZE) + goto out_slow; + + page = find_or_create_page(mapping, 0, GFP_KERNEL); + if (!page) + goto out_slow; + + kaddr = kmap(page); + ret = cache_do_downcall(kaddr, buf, count, cd); + kunmap(page); + unlock_page(page); + page_cache_release(page); + return ret; +out_slow: + return cache_slow_downcall(buf, count, cd); +} - mutex_unlock(&queue_io_mutex); - return err ? err : count; +static ssize_t cache_write(struct file *filp, const char __user *buf, + size_t count, loff_t *ppos, + struct cache_detail *cd) +{ + struct address_space *mapping = filp->f_mapping; + struct inode *inode = filp->f_path.dentry->d_inode; + ssize_t ret = -EINVAL; + + if (!cd->cache_parse) + goto out; + + mutex_lock(&inode->i_mutex); + ret = cache_downcall(mapping, buf, count, cd); + mutex_unlock(&inode->i_mutex); +out: + return ret; } static DECLARE_WAIT_QUEUE_HEAD(queue_wait); -static unsigned int -cache_poll(struct file *filp, poll_table *wait) +static unsigned int cache_poll(struct file *filp, poll_table *wait, + struct cache_detail *cd) { unsigned int mask; struct cache_reader *rp = filp->private_data; struct cache_queue *cq; - struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; poll_wait(filp, &queue_wait, wait); @@ -822,14 +802,13 @@ cache_poll(struct file *filp, poll_table *wait) return mask; } -static int -cache_ioctl(struct inode *ino, struct file *filp, - unsigned int cmd, unsigned long arg) +static int cache_ioctl(struct inode *ino, struct file *filp, + unsigned int cmd, unsigned long arg, + struct cache_detail *cd) { int len = 0; struct cache_reader *rp = filp->private_data; struct cache_queue *cq; - struct cache_detail *cd = PDE(ino)->data; if (cmd != FIONREAD || !rp) return -EINVAL; @@ -852,15 +831,15 @@ cache_ioctl(struct inode *ino, struct file *filp, return put_user(len, (int __user *)arg); } -static int -cache_open(struct inode *inode, struct file *filp) +static int cache_open(struct inode *inode, struct file *filp, + struct cache_detail *cd) { struct cache_reader *rp = NULL; + if (!cd || !try_module_get(cd->owner)) + return -EACCES; nonseekable_open(inode, filp); if (filp->f_mode & FMODE_READ) { - struct cache_detail *cd = PDE(inode)->data; - rp = kmalloc(sizeof(*rp), GFP_KERNEL); if (!rp) return -ENOMEM; @@ -875,11 +854,10 @@ cache_open(struct inode *inode, struct file *filp) return 0; } -static int -cache_release(struct inode *inode, struct file *filp) +static int cache_release(struct inode *inode, struct file *filp, + struct cache_detail *cd) { struct cache_reader *rp = filp->private_data; - struct cache_detail *cd = PDE(inode)->data; if (rp) { spin_lock(&queue_lock); @@ -903,23 +881,12 @@ cache_release(struct inode *inode, struct file *filp) cd->last_close = get_seconds(); atomic_dec(&cd->readers); } + module_put(cd->owner); return 0; } -static const struct file_operations cache_file_operations = { - .owner = THIS_MODULE, - .llseek = no_llseek, - .read = cache_read, - .write = cache_write, - .poll = cache_poll, - .ioctl = cache_ioctl, /* for FIONREAD */ - .open = cache_open, - .release = cache_release, -}; - - static void queue_loose(struct cache_detail *detail, struct cache_head *ch) { struct cache_queue *cq; @@ -1020,15 +987,21 @@ static void warn_no_listener(struct cache_detail *detail) if (detail->last_warn != detail->last_close) { detail->last_warn = detail->last_close; if (detail->warn_no_listener) - detail->warn_no_listener(detail); + detail->warn_no_listener(detail, detail->last_close != 0); } } /* - * register an upcall request to user-space. + * register an upcall request to user-space and queue it up for read() by the + * upcall daemon. + * * Each request is at most one page long. */ -static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h) +int sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h, + void (*cache_request)(struct cache_detail *, + struct cache_head *, + char **, + int *)) { char *buf; @@ -1036,9 +1009,6 @@ static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h) char *bp; int len; - if (detail->cache_request == NULL) - return -EINVAL; - if (atomic_read(&detail->readers) == 0 && detail->last_close < get_seconds() - 30) { warn_no_listener(detail); @@ -1057,7 +1027,7 @@ static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h) bp = buf; len = PAGE_SIZE; - detail->cache_request(detail, h, &bp, &len); + cache_request(detail, h, &bp, &len); if (len < 0) { kfree(buf); @@ -1075,6 +1045,7 @@ static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h) wake_up(&queue_wait); return 0; } +EXPORT_SYMBOL_GPL(sunrpc_cache_pipe_upcall); /* * parse a message from user-space and pass it @@ -1242,11 +1213,13 @@ static const struct seq_operations cache_content_op = { .show = c_show, }; -static int content_open(struct inode *inode, struct file *file) +static int content_open(struct inode *inode, struct file *file, + struct cache_detail *cd) { struct handle *han; - struct cache_detail *cd = PDE(inode)->data; + if (!cd || !try_module_get(cd->owner)) + return -EACCES; han = __seq_open_private(file, &cache_content_op, sizeof(*han)); if (han == NULL) return -ENOMEM; @@ -1255,17 +1228,33 @@ static int content_open(struct inode *inode, struct file *file) return 0; } -static const struct file_operations content_file_operations = { - .open = content_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_private, -}; +static int content_release(struct inode *inode, struct file *file, + struct cache_detail *cd) +{ + int ret = seq_release_private(inode, file); + module_put(cd->owner); + return ret; +} + +static int open_flush(struct inode *inode, struct file *file, + struct cache_detail *cd) +{ + if (!cd || !try_module_get(cd->owner)) + return -EACCES; + return nonseekable_open(inode, file); +} + +static int release_flush(struct inode *inode, struct file *file, + struct cache_detail *cd) +{ + module_put(cd->owner); + return 0; +} static ssize_t read_flush(struct file *file, char __user *buf, - size_t count, loff_t *ppos) + size_t count, loff_t *ppos, + struct cache_detail *cd) { - struct cache_detail *cd = PDE(file->f_path.dentry->d_inode)->data; char tbuf[20]; unsigned long p = *ppos; size_t len; @@ -1283,10 +1272,10 @@ static ssize_t read_flush(struct file *file, char __user *buf, return len; } -static ssize_t write_flush(struct file * file, const char __user * buf, - size_t count, loff_t *ppos) +static ssize_t write_flush(struct file *file, const char __user *buf, + size_t count, loff_t *ppos, + struct cache_detail *cd) { - struct cache_detail *cd = PDE(file->f_path.dentry->d_inode)->data; char tbuf[20]; char *ep; long flushtime; @@ -1307,8 +1296,343 @@ static ssize_t write_flush(struct file * file, const char __user * buf, return count; } -static const struct file_operations cache_flush_operations = { - .open = nonseekable_open, - .read = read_flush, - .write = write_flush, +static ssize_t cache_read_procfs(struct file *filp, char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + + return cache_read(filp, buf, count, ppos, cd); +} + +static ssize_t cache_write_procfs(struct file *filp, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + + return cache_write(filp, buf, count, ppos, cd); +} + +static unsigned int cache_poll_procfs(struct file *filp, poll_table *wait) +{ + struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + + return cache_poll(filp, wait, cd); +} + +static int cache_ioctl_procfs(struct inode *inode, struct file *filp, + unsigned int cmd, unsigned long arg) +{ + struct cache_detail *cd = PDE(inode)->data; + + return cache_ioctl(inode, filp, cmd, arg, cd); +} + +static int cache_open_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return cache_open(inode, filp, cd); +} + +static int cache_release_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return cache_release(inode, filp, cd); +} + +static const struct file_operations cache_file_operations_procfs = { + .owner = THIS_MODULE, + .llseek = no_llseek, + .read = cache_read_procfs, + .write = cache_write_procfs, + .poll = cache_poll_procfs, + .ioctl = cache_ioctl_procfs, /* for FIONREAD */ + .open = cache_open_procfs, + .release = cache_release_procfs, }; + +static int content_open_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return content_open(inode, filp, cd); +} + +static int content_release_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return content_release(inode, filp, cd); +} + +static const struct file_operations content_file_operations_procfs = { + .open = content_open_procfs, + .read = seq_read, + .llseek = seq_lseek, + .release = content_release_procfs, +}; + +static int open_flush_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return open_flush(inode, filp, cd); +} + +static int release_flush_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return release_flush(inode, filp, cd); +} + +static ssize_t read_flush_procfs(struct file *filp, char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + + return read_flush(filp, buf, count, ppos, cd); +} + +static ssize_t write_flush_procfs(struct file *filp, + const char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + + return write_flush(filp, buf, count, ppos, cd); +} + +static const struct file_operations cache_flush_operations_procfs = { + .open = open_flush_procfs, + .read = read_flush_procfs, + .write = write_flush_procfs, + .release = release_flush_procfs, +}; + +static void remove_cache_proc_entries(struct cache_detail *cd) +{ + if (cd->u.procfs.proc_ent == NULL) + return; + if (cd->u.procfs.flush_ent) + remove_proc_entry("flush", cd->u.procfs.proc_ent); + if (cd->u.procfs.channel_ent) + remove_proc_entry("channel", cd->u.procfs.proc_ent); + if (cd->u.procfs.content_ent) + remove_proc_entry("content", cd->u.procfs.proc_ent); + cd->u.procfs.proc_ent = NULL; + remove_proc_entry(cd->name, proc_net_rpc); +} + +#ifdef CONFIG_PROC_FS +static int create_cache_proc_entries(struct cache_detail *cd) +{ + struct proc_dir_entry *p; + + cd->u.procfs.proc_ent = proc_mkdir(cd->name, proc_net_rpc); + if (cd->u.procfs.proc_ent == NULL) + goto out_nomem; + cd->u.procfs.channel_ent = NULL; + cd->u.procfs.content_ent = NULL; + + p = proc_create_data("flush", S_IFREG|S_IRUSR|S_IWUSR, + cd->u.procfs.proc_ent, + &cache_flush_operations_procfs, cd); + cd->u.procfs.flush_ent = p; + if (p == NULL) + goto out_nomem; + + if (cd->cache_upcall || cd->cache_parse) { + p = proc_create_data("channel", S_IFREG|S_IRUSR|S_IWUSR, + cd->u.procfs.proc_ent, + &cache_file_operations_procfs, cd); + cd->u.procfs.channel_ent = p; + if (p == NULL) + goto out_nomem; + } + if (cd->cache_show) { + p = proc_create_data("content", S_IFREG|S_IRUSR|S_IWUSR, + cd->u.procfs.proc_ent, + &content_file_operations_procfs, cd); + cd->u.procfs.content_ent = p; + if (p == NULL) + goto out_nomem; + } + return 0; +out_nomem: + remove_cache_proc_entries(cd); + return -ENOMEM; +} +#else /* CONFIG_PROC_FS */ +static int create_cache_proc_entries(struct cache_detail *cd) +{ + return 0; +} +#endif + +int cache_register(struct cache_detail *cd) +{ + int ret; + + sunrpc_init_cache_detail(cd); + ret = create_cache_proc_entries(cd); + if (ret) + sunrpc_destroy_cache_detail(cd); + return ret; +} +EXPORT_SYMBOL_GPL(cache_register); + +void cache_unregister(struct cache_detail *cd) +{ + remove_cache_proc_entries(cd); + sunrpc_destroy_cache_detail(cd); +} +EXPORT_SYMBOL_GPL(cache_unregister); + +static ssize_t cache_read_pipefs(struct file *filp, char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + + return cache_read(filp, buf, count, ppos, cd); +} + +static ssize_t cache_write_pipefs(struct file *filp, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + + return cache_write(filp, buf, count, ppos, cd); +} + +static unsigned int cache_poll_pipefs(struct file *filp, poll_table *wait) +{ + struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + + return cache_poll(filp, wait, cd); +} + +static int cache_ioctl_pipefs(struct inode *inode, struct file *filp, + unsigned int cmd, unsigned long arg) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return cache_ioctl(inode, filp, cmd, arg, cd); +} + +static int cache_open_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return cache_open(inode, filp, cd); +} + +static int cache_release_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return cache_release(inode, filp, cd); +} + +const struct file_operations cache_file_operations_pipefs = { + .owner = THIS_MODULE, + .llseek = no_llseek, + .read = cache_read_pipefs, + .write = cache_write_pipefs, + .poll = cache_poll_pipefs, + .ioctl = cache_ioctl_pipefs, /* for FIONREAD */ + .open = cache_open_pipefs, + .release = cache_release_pipefs, +}; + +static int content_open_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return content_open(inode, filp, cd); +} + +static int content_release_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return content_release(inode, filp, cd); +} + +const struct file_operations content_file_operations_pipefs = { + .open = content_open_pipefs, + .read = seq_read, + .llseek = seq_lseek, + .release = content_release_pipefs, +}; + +static int open_flush_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return open_flush(inode, filp, cd); +} + +static int release_flush_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return release_flush(inode, filp, cd); +} + +static ssize_t read_flush_pipefs(struct file *filp, char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + + return read_flush(filp, buf, count, ppos, cd); +} + +static ssize_t write_flush_pipefs(struct file *filp, + const char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + + return write_flush(filp, buf, count, ppos, cd); +} + +const struct file_operations cache_flush_operations_pipefs = { + .open = open_flush_pipefs, + .read = read_flush_pipefs, + .write = write_flush_pipefs, + .release = release_flush_pipefs, +}; + +int sunrpc_cache_register_pipefs(struct dentry *parent, + const char *name, mode_t umode, + struct cache_detail *cd) +{ + struct qstr q; + struct dentry *dir; + int ret = 0; + + sunrpc_init_cache_detail(cd); + q.name = name; + q.len = strlen(name); + q.hash = full_name_hash(q.name, q.len); + dir = rpc_create_cache_dir(parent, &q, umode, cd); + if (!IS_ERR(dir)) + cd->u.pipefs.dir = dir; + else { + sunrpc_destroy_cache_detail(cd); + ret = PTR_ERR(dir); + } + return ret; +} +EXPORT_SYMBOL_GPL(sunrpc_cache_register_pipefs); + +void sunrpc_cache_unregister_pipefs(struct cache_detail *cd) +{ + rpc_remove_cache_dir(cd->u.pipefs.dir); + cd->u.pipefs.dir = NULL; + sunrpc_destroy_cache_detail(cd); +} +EXPORT_SYMBOL_GPL(sunrpc_cache_unregister_pipefs); + diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index df1039f..fac0ca9 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -27,6 +27,8 @@ #include <linux/types.h> #include <linux/kallsyms.h> #include <linux/mm.h> +#include <linux/namei.h> +#include <linux/mount.h> #include <linux/slab.h> #include <linux/utsname.h> #include <linux/workqueue.h> @@ -97,33 +99,49 @@ static int rpc_setup_pipedir(struct rpc_clnt *clnt, char *dir_name) { static uint32_t clntid; + struct nameidata nd; + struct path path; + char name[15]; + struct qstr q = { + .name = name, + }; int error; - clnt->cl_vfsmnt = ERR_PTR(-ENOENT); - clnt->cl_dentry = ERR_PTR(-ENOENT); + clnt->cl_path.mnt = ERR_PTR(-ENOENT); + clnt->cl_path.dentry = ERR_PTR(-ENOENT); if (dir_name == NULL) return 0; - clnt->cl_vfsmnt = rpc_get_mount(); - if (IS_ERR(clnt->cl_vfsmnt)) - return PTR_ERR(clnt->cl_vfsmnt); + path.mnt = rpc_get_mount(); + if (IS_ERR(path.mnt)) + return PTR_ERR(path.mnt); + error = vfs_path_lookup(path.mnt->mnt_root, path.mnt, dir_name, 0, &nd); + if (error) + goto err; for (;;) { - snprintf(clnt->cl_pathname, sizeof(clnt->cl_pathname), - "%s/clnt%x", dir_name, - (unsigned int)clntid++); - clnt->cl_pathname[sizeof(clnt->cl_pathname) - 1] = '\0'; - clnt->cl_dentry = rpc_mkdir(clnt->cl_pathname, clnt); - if (!IS_ERR(clnt->cl_dentry)) - return 0; - error = PTR_ERR(clnt->cl_dentry); + q.len = snprintf(name, sizeof(name), "clnt%x", (unsigned int)clntid++); + name[sizeof(name) - 1] = '\0'; + q.hash = full_name_hash(q.name, q.len); + path.dentry = rpc_create_client_dir(nd.path.dentry, &q, clnt); + if (!IS_ERR(path.dentry)) + break; + error = PTR_ERR(path.dentry); if (error != -EEXIST) { - printk(KERN_INFO "RPC: Couldn't create pipefs entry %s, error %d\n", - clnt->cl_pathname, error); - rpc_put_mount(); - return error; + printk(KERN_INFO "RPC: Couldn't create pipefs entry" + " %s/%s, error %d\n", + dir_name, name, error); + goto err_path_put; } } + path_put(&nd.path); + clnt->cl_path = path; + return 0; +err_path_put: + path_put(&nd.path); +err: + rpc_put_mount(); + return error; } static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, struct rpc_xprt *xprt) @@ -231,8 +249,8 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, stru return clnt; out_no_auth: - if (!IS_ERR(clnt->cl_dentry)) { - rpc_rmdir(clnt->cl_dentry); + if (!IS_ERR(clnt->cl_path.dentry)) { + rpc_remove_client_dir(clnt->cl_path.dentry); rpc_put_mount(); } out_no_path: @@ -423,8 +441,8 @@ rpc_free_client(struct kref *kref) dprintk("RPC: destroying %s client for %s\n", clnt->cl_protname, clnt->cl_server); - if (!IS_ERR(clnt->cl_dentry)) { - rpc_rmdir(clnt->cl_dentry); + if (!IS_ERR(clnt->cl_path.dentry)) { + rpc_remove_client_dir(clnt->cl_path.dentry); rpc_put_mount(); } if (clnt->cl_parent != clnt) { diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 9ced062..7f676bd 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -26,6 +26,7 @@ #include <linux/sunrpc/clnt.h> #include <linux/workqueue.h> #include <linux/sunrpc/rpc_pipe_fs.h> +#include <linux/sunrpc/cache.h> static struct vfsmount *rpc_mount __read_mostly; static int rpc_mount_count; @@ -125,7 +126,7 @@ static void rpc_close_pipes(struct inode *inode) { struct rpc_inode *rpci = RPC_I(inode); - struct rpc_pipe_ops *ops; + const struct rpc_pipe_ops *ops; int need_release; mutex_lock(&inode->i_mutex); @@ -398,66 +399,12 @@ static const struct file_operations rpc_info_operations = { /* - * We have a single directory with 1 node in it. - */ -enum { - RPCAUTH_Root = 1, - RPCAUTH_lockd, - RPCAUTH_mount, - RPCAUTH_nfs, - RPCAUTH_portmap, - RPCAUTH_statd, - RPCAUTH_nfsd4_cb, - RPCAUTH_RootEOF -}; - -/* * Description of fs contents. */ struct rpc_filelist { - char *name; + const char *name; const struct file_operations *i_fop; - int mode; -}; - -static struct rpc_filelist files[] = { - [RPCAUTH_lockd] = { - .name = "lockd", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, - [RPCAUTH_mount] = { - .name = "mount", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, - [RPCAUTH_nfs] = { - .name = "nfs", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, - [RPCAUTH_portmap] = { - .name = "portmap", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, - [RPCAUTH_statd] = { - .name = "statd", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, - [RPCAUTH_nfsd4_cb] = { - .name = "nfsd4_cb", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, -}; - -enum { - RPCAUTH_info = 2, - RPCAUTH_EOF -}; - -static struct rpc_filelist authfiles[] = { - [RPCAUTH_info] = { - .name = "info", - .i_fop = &rpc_info_operations, - .mode = S_IFREG | S_IRUSR, - }, + umode_t mode; }; struct vfsmount *rpc_get_mount(void) @@ -469,11 +416,13 @@ struct vfsmount *rpc_get_mount(void) return ERR_PTR(err); return rpc_mount; } +EXPORT_SYMBOL_GPL(rpc_get_mount); void rpc_put_mount(void) { simple_release_fs(&rpc_mount, &rpc_mount_count); } +EXPORT_SYMBOL_GPL(rpc_put_mount); static int rpc_delete_dentry(struct dentry *dentry) { @@ -484,39 +433,8 @@ static const struct dentry_operations rpc_dentry_operations = { .d_delete = rpc_delete_dentry, }; -static int -rpc_lookup_parent(char *path, struct nameidata *nd) -{ - struct vfsmount *mnt; - - if (path[0] == '\0') - return -ENOENT; - - mnt = rpc_get_mount(); - if (IS_ERR(mnt)) { - printk(KERN_WARNING "%s: %s failed to mount " - "pseudofilesystem \n", __FILE__, __func__); - return PTR_ERR(mnt); - } - - if (vfs_path_lookup(mnt->mnt_root, mnt, path, LOOKUP_PARENT, nd)) { - printk(KERN_WARNING "%s: %s failed to find path %s\n", - __FILE__, __func__, path); - rpc_put_mount(); - return -ENOENT; - } - return 0; -} - -static void -rpc_release_path(struct nameidata *nd) -{ - path_put(&nd->path); - rpc_put_mount(); -} - static struct inode * -rpc_get_inode(struct super_block *sb, int mode) +rpc_get_inode(struct super_block *sb, umode_t mode) { struct inode *inode = new_inode(sb); if (!inode) @@ -534,212 +452,274 @@ rpc_get_inode(struct super_block *sb, int mode) return inode; } -/* - * FIXME: This probably has races. - */ -static void rpc_depopulate(struct dentry *parent, - unsigned long start, unsigned long eof) +static int __rpc_create_common(struct inode *dir, struct dentry *dentry, + umode_t mode, + const struct file_operations *i_fop, + void *private) { - struct inode *dir = parent->d_inode; - struct list_head *pos, *next; - struct dentry *dentry, *dvec[10]; - int n = 0; + struct inode *inode; - mutex_lock_nested(&dir->i_mutex, I_MUTEX_CHILD); -repeat: - spin_lock(&dcache_lock); - list_for_each_safe(pos, next, &parent->d_subdirs) { - dentry = list_entry(pos, struct dentry, d_u.d_child); - if (!dentry->d_inode || - dentry->d_inode->i_ino < start || - dentry->d_inode->i_ino >= eof) - continue; - spin_lock(&dentry->d_lock); - if (!d_unhashed(dentry)) { - dget_locked(dentry); - __d_drop(dentry); - spin_unlock(&dentry->d_lock); - dvec[n++] = dentry; - if (n == ARRAY_SIZE(dvec)) - break; - } else - spin_unlock(&dentry->d_lock); - } - spin_unlock(&dcache_lock); - if (n) { - do { - dentry = dvec[--n]; - if (S_ISREG(dentry->d_inode->i_mode)) - simple_unlink(dir, dentry); - else if (S_ISDIR(dentry->d_inode->i_mode)) - simple_rmdir(dir, dentry); - d_delete(dentry); - dput(dentry); - } while (n); - goto repeat; - } - mutex_unlock(&dir->i_mutex); + BUG_ON(!d_unhashed(dentry)); + inode = rpc_get_inode(dir->i_sb, mode); + if (!inode) + goto out_err; + inode->i_ino = iunique(dir->i_sb, 100); + if (i_fop) + inode->i_fop = i_fop; + if (private) + rpc_inode_setowner(inode, private); + d_add(dentry, inode); + return 0; +out_err: + printk(KERN_WARNING "%s: %s failed to allocate inode for dentry %s\n", + __FILE__, __func__, dentry->d_name.name); + dput(dentry); + return -ENOMEM; } -static int -rpc_populate(struct dentry *parent, - struct rpc_filelist *files, - int start, int eof) +static int __rpc_create(struct inode *dir, struct dentry *dentry, + umode_t mode, + const struct file_operations *i_fop, + void *private) { - struct inode *inode, *dir = parent->d_inode; - void *private = RPC_I(dir)->private; - struct dentry *dentry; - int mode, i; + int err; - mutex_lock(&dir->i_mutex); - for (i = start; i < eof; i++) { - dentry = d_alloc_name(parent, files[i].name); - if (!dentry) - goto out_bad; - dentry->d_op = &rpc_dentry_operations; - mode = files[i].mode; - inode = rpc_get_inode(dir->i_sb, mode); - if (!inode) { - dput(dentry); - goto out_bad; - } - inode->i_ino = i; - if (files[i].i_fop) - inode->i_fop = files[i].i_fop; - if (private) - rpc_inode_setowner(inode, private); - if (S_ISDIR(mode)) - inc_nlink(dir); - d_add(dentry, inode); - fsnotify_create(dir, dentry); - } - mutex_unlock(&dir->i_mutex); + err = __rpc_create_common(dir, dentry, S_IFREG | mode, i_fop, private); + if (err) + return err; + fsnotify_create(dir, dentry); return 0; -out_bad: - mutex_unlock(&dir->i_mutex); - printk(KERN_WARNING "%s: %s failed to populate directory %s\n", - __FILE__, __func__, parent->d_name.name); - return -ENOMEM; } -static int -__rpc_mkdir(struct inode *dir, struct dentry *dentry) +static int __rpc_mkdir(struct inode *dir, struct dentry *dentry, + umode_t mode, + const struct file_operations *i_fop, + void *private) { - struct inode *inode; + int err; - inode = rpc_get_inode(dir->i_sb, S_IFDIR | S_IRUGO | S_IXUGO); - if (!inode) - goto out_err; - inode->i_ino = iunique(dir->i_sb, 100); - d_instantiate(dentry, inode); + err = __rpc_create_common(dir, dentry, S_IFDIR | mode, i_fop, private); + if (err) + return err; inc_nlink(dir); fsnotify_mkdir(dir, dentry); return 0; -out_err: - printk(KERN_WARNING "%s: %s failed to allocate inode for dentry %s\n", - __FILE__, __func__, dentry->d_name.name); - return -ENOMEM; } -static int -__rpc_rmdir(struct inode *dir, struct dentry *dentry) +static int __rpc_mkpipe(struct inode *dir, struct dentry *dentry, + umode_t mode, + const struct file_operations *i_fop, + void *private, + const struct rpc_pipe_ops *ops, + int flags) { - int error; - error = simple_rmdir(dir, dentry); - if (!error) - d_delete(dentry); - return error; + struct rpc_inode *rpci; + int err; + + err = __rpc_create_common(dir, dentry, S_IFIFO | mode, i_fop, private); + if (err) + return err; + rpci = RPC_I(dentry->d_inode); + rpci->nkern_readwriters = 1; + rpci->private = private; + rpci->flags = flags; + rpci->ops = ops; + fsnotify_create(dir, dentry); + return 0; } -static struct dentry * -rpc_lookup_create(struct dentry *parent, const char *name, int len, int exclusive) +static int __rpc_rmdir(struct inode *dir, struct dentry *dentry) +{ + int ret; + + dget(dentry); + ret = simple_rmdir(dir, dentry); + d_delete(dentry); + dput(dentry); + return ret; +} + +static int __rpc_unlink(struct inode *dir, struct dentry *dentry) +{ + int ret; + + dget(dentry); + ret = simple_unlink(dir, dentry); + d_delete(dentry); + dput(dentry); + return ret; +} + +static int __rpc_rmpipe(struct inode *dir, struct dentry *dentry) +{ + struct inode *inode = dentry->d_inode; + struct rpc_inode *rpci = RPC_I(inode); + + rpci->nkern_readwriters--; + if (rpci->nkern_readwriters != 0) + return 0; + rpc_close_pipes(inode); + return __rpc_unlink(dir, dentry); +} + +static struct dentry *__rpc_lookup_create(struct dentry *parent, + struct qstr *name) { - struct inode *dir = parent->d_inode; struct dentry *dentry; - mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); - dentry = lookup_one_len(name, parent, len); - if (IS_ERR(dentry)) - goto out_err; + dentry = d_lookup(parent, name); + if (!dentry) { + dentry = d_alloc(parent, name); + if (!dentry) { + dentry = ERR_PTR(-ENOMEM); + goto out_err; + } + } if (!dentry->d_inode) dentry->d_op = &rpc_dentry_operations; - else if (exclusive) { - dput(dentry); - dentry = ERR_PTR(-EEXIST); - goto out_err; - } - return dentry; out_err: - mutex_unlock(&dir->i_mutex); return dentry; } -static struct dentry * -rpc_lookup_negative(char *path, struct nameidata *nd) +static struct dentry *__rpc_lookup_create_exclusive(struct dentry *parent, + struct qstr *name) { struct dentry *dentry; - int error; - if ((error = rpc_lookup_parent(path, nd)) != 0) - return ERR_PTR(error); - dentry = rpc_lookup_create(nd->path.dentry, nd->last.name, nd->last.len, - 1); - if (IS_ERR(dentry)) - rpc_release_path(nd); - return dentry; + dentry = __rpc_lookup_create(parent, name); + if (dentry->d_inode == NULL) + return dentry; + dput(dentry); + return ERR_PTR(-EEXIST); } -/** - * rpc_mkdir - Create a new directory in rpc_pipefs - * @path: path from the rpc_pipefs root to the new directory - * @rpc_client: rpc client to associate with this directory - * - * This creates a directory at the given @path associated with - * @rpc_clnt, which will contain a file named "info" with some basic - * information about the client, together with any "pipes" that may - * later be created using rpc_mkpipe(). +/* + * FIXME: This probably has races. */ -struct dentry * -rpc_mkdir(char *path, struct rpc_clnt *rpc_client) +static void __rpc_depopulate(struct dentry *parent, + const struct rpc_filelist *files, + int start, int eof) { - struct nameidata nd; + struct inode *dir = parent->d_inode; struct dentry *dentry; - struct inode *dir; + struct qstr name; + int i; + + for (i = start; i < eof; i++) { + name.name = files[i].name; + name.len = strlen(files[i].name); + name.hash = full_name_hash(name.name, name.len); + dentry = d_lookup(parent, &name); + + if (dentry == NULL) + continue; + if (dentry->d_inode == NULL) + goto next; + switch (dentry->d_inode->i_mode & S_IFMT) { + default: + BUG(); + case S_IFREG: + __rpc_unlink(dir, dentry); + break; + case S_IFDIR: + __rpc_rmdir(dir, dentry); + } +next: + dput(dentry); + } +} + +static void rpc_depopulate(struct dentry *parent, + const struct rpc_filelist *files, + int start, int eof) +{ + struct inode *dir = parent->d_inode; + + mutex_lock_nested(&dir->i_mutex, I_MUTEX_CHILD); + __rpc_depopulate(parent, files, start, eof); + mutex_unlock(&dir->i_mutex); +} + +static int rpc_populate(struct dentry *parent, + const struct rpc_filelist *files, + int start, int eof, + void *private) +{ + struct inode *dir = parent->d_inode; + struct dentry *dentry; + int i, err; + + mutex_lock(&dir->i_mutex); + for (i = start; i < eof; i++) { + struct qstr q; + + q.name = files[i].name; + q.len = strlen(files[i].name); + q.hash = full_name_hash(q.name, q.len); + dentry = __rpc_lookup_create_exclusive(parent, &q); + err = PTR_ERR(dentry); + if (IS_ERR(dentry)) + goto out_bad; + switch (files[i].mode & S_IFMT) { + default: + BUG(); + case S_IFREG: + err = __rpc_create(dir, dentry, + files[i].mode, + files[i].i_fop, + private); + break; + case S_IFDIR: + err = __rpc_mkdir(dir, dentry, + files[i].mode, + NULL, + private); + } + if (err != 0) + goto out_bad; + } + mutex_unlock(&dir->i_mutex); + return 0; +out_bad: + __rpc_depopulate(parent, files, start, eof); + mutex_unlock(&dir->i_mutex); + printk(KERN_WARNING "%s: %s failed to populate directory %s\n", + __FILE__, __func__, parent->d_name.name); + return err; +} + +static struct dentry *rpc_mkdir_populate(struct dentry *parent, + struct qstr *name, umode_t mode, void *private, + int (*populate)(struct dentry *, void *), void *args_populate) +{ + struct dentry *dentry; + struct inode *dir = parent->d_inode; int error; - dentry = rpc_lookup_negative(path, &nd); + mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); + dentry = __rpc_lookup_create_exclusive(parent, name); if (IS_ERR(dentry)) - return dentry; - dir = nd.path.dentry->d_inode; - if ((error = __rpc_mkdir(dir, dentry)) != 0) - goto err_dput; - RPC_I(dentry->d_inode)->private = rpc_client; - error = rpc_populate(dentry, authfiles, - RPCAUTH_info, RPCAUTH_EOF); - if (error) - goto err_depopulate; - dget(dentry); + goto out; + error = __rpc_mkdir(dir, dentry, mode, NULL, private); + if (error != 0) + goto out_err; + if (populate != NULL) { + error = populate(dentry, args_populate); + if (error) + goto err_rmdir; + } out: mutex_unlock(&dir->i_mutex); - rpc_release_path(&nd); return dentry; -err_depopulate: - rpc_depopulate(dentry, RPCAUTH_info, RPCAUTH_EOF); +err_rmdir: __rpc_rmdir(dir, dentry); -err_dput: - dput(dentry); - printk(KERN_WARNING "%s: %s() failed to create directory %s (errno = %d)\n", - __FILE__, __func__, path, error); +out_err: dentry = ERR_PTR(error); goto out; } -/** - * rpc_rmdir - Remove a directory created with rpc_mkdir() - * @dentry: directory to remove - */ -int -rpc_rmdir(struct dentry *dentry) +static int rpc_rmdir_depopulate(struct dentry *dentry, + void (*depopulate)(struct dentry *)) { struct dentry *parent; struct inode *dir; @@ -748,9 +728,9 @@ rpc_rmdir(struct dentry *dentry) parent = dget_parent(dentry); dir = parent->d_inode; mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); - rpc_depopulate(dentry, RPCAUTH_info, RPCAUTH_EOF); + if (depopulate != NULL) + depopulate(dentry); error = __rpc_rmdir(dir, dentry); - dput(dentry); mutex_unlock(&dir->i_mutex); dput(parent); return error; @@ -776,50 +756,54 @@ rpc_rmdir(struct dentry *dentry) * The @private argument passed here will be available to all these methods * from the file pointer, via RPC_I(file->f_dentry->d_inode)->private. */ -struct dentry * -rpc_mkpipe(struct dentry *parent, const char *name, void *private, struct rpc_pipe_ops *ops, int flags) +struct dentry *rpc_mkpipe(struct dentry *parent, const char *name, + void *private, const struct rpc_pipe_ops *ops, + int flags) { struct dentry *dentry; - struct inode *dir, *inode; - struct rpc_inode *rpci; + struct inode *dir = parent->d_inode; + umode_t umode = S_IFIFO | S_IRUSR | S_IWUSR; + struct qstr q; + int err; + + if (ops->upcall == NULL) + umode &= ~S_IRUGO; + if (ops->downcall == NULL) + umode &= ~S_IWUGO; + + q.name = name; + q.len = strlen(name); + q.hash = full_name_hash(q.name, q.len), - dentry = rpc_lookup_create(parent, name, strlen(name), 0); + mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); + dentry = __rpc_lookup_create(parent, &q); if (IS_ERR(dentry)) - return dentry; - dir = parent->d_inode; + goto out; if (dentry->d_inode) { - rpci = RPC_I(dentry->d_inode); + struct rpc_inode *rpci = RPC_I(dentry->d_inode); if (rpci->private != private || rpci->ops != ops || rpci->flags != flags) { dput (dentry); - dentry = ERR_PTR(-EBUSY); + err = -EBUSY; + goto out_err; } rpci->nkern_readwriters++; goto out; } - inode = rpc_get_inode(dir->i_sb, S_IFIFO | S_IRUSR | S_IWUSR); - if (!inode) - goto err_dput; - inode->i_ino = iunique(dir->i_sb, 100); - inode->i_fop = &rpc_pipe_fops; - d_instantiate(dentry, inode); - rpci = RPC_I(inode); - rpci->private = private; - rpci->flags = flags; - rpci->ops = ops; - rpci->nkern_readwriters = 1; - fsnotify_create(dir, dentry); - dget(dentry); + + err = __rpc_mkpipe(dir, dentry, umode, &rpc_pipe_fops, + private, ops, flags); + if (err) + goto out_err; out: mutex_unlock(&dir->i_mutex); return dentry; -err_dput: - dput(dentry); - dentry = ERR_PTR(-ENOMEM); +out_err: + dentry = ERR_PTR(err); printk(KERN_WARNING "%s: %s() failed to create pipe %s/%s (errno = %d)\n", __FILE__, __func__, parent->d_name.name, name, - -ENOMEM); + err); goto out; } EXPORT_SYMBOL_GPL(rpc_mkpipe); @@ -842,19 +826,107 @@ rpc_unlink(struct dentry *dentry) parent = dget_parent(dentry); dir = parent->d_inode; mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); - if (--RPC_I(dentry->d_inode)->nkern_readwriters == 0) { - rpc_close_pipes(dentry->d_inode); - error = simple_unlink(dir, dentry); - if (!error) - d_delete(dentry); - } - dput(dentry); + error = __rpc_rmpipe(dir, dentry); mutex_unlock(&dir->i_mutex); dput(parent); return error; } EXPORT_SYMBOL_GPL(rpc_unlink); +enum { + RPCAUTH_info, + RPCAUTH_EOF +}; + +static const struct rpc_filelist authfiles[] = { + [RPCAUTH_info] = { + .name = "info", + .i_fop = &rpc_info_operations, + .mode = S_IFREG | S_IRUSR, + }, +}; + +static int rpc_clntdir_populate(struct dentry *dentry, void *private) +{ + return rpc_populate(dentry, + authfiles, RPCAUTH_info, RPCAUTH_EOF, + private); +} + +static void rpc_clntdir_depopulate(struct dentry *dentry) +{ + rpc_depopulate(dentry, authfiles, RPCAUTH_info, RPCAUTH_EOF); +} + +/** + * rpc_create_client_dir - Create a new rpc_client directory in rpc_pipefs + * @path: path from the rpc_pipefs root to the new directory + * @rpc_client: rpc client to associate with this directory + * + * This creates a directory at the given @path associated with + * @rpc_clnt, which will contain a file named "info" with some basic + * information about the client, together with any "pipes" that may + * later be created using rpc_mkpipe(). + */ +struct dentry *rpc_create_client_dir(struct dentry *dentry, + struct qstr *name, + struct rpc_clnt *rpc_client) +{ + return rpc_mkdir_populate(dentry, name, S_IRUGO | S_IXUGO, NULL, + rpc_clntdir_populate, rpc_client); +} + +/** + * rpc_remove_client_dir - Remove a directory created with rpc_create_client_dir() + * @dentry: directory to remove + */ +int rpc_remove_client_dir(struct dentry *dentry) +{ + return rpc_rmdir_depopulate(dentry, rpc_clntdir_depopulate); +} + +static const struct rpc_filelist cache_pipefs_files[3] = { + [0] = { + .name = "channel", + .i_fop = &cache_file_operations_pipefs, + .mode = S_IFREG|S_IRUSR|S_IWUSR, + }, + [1] = { + .name = "content", + .i_fop = &content_file_operations_pipefs, + .mode = S_IFREG|S_IRUSR, + }, + [2] = { + .name = "flush", + .i_fop = &cache_flush_operations_pipefs, + .mode = S_IFREG|S_IRUSR|S_IWUSR, + }, +}; + +static int rpc_cachedir_populate(struct dentry *dentry, void *private) +{ + return rpc_populate(dentry, + cache_pipefs_files, 0, 3, + private); +} + +static void rpc_cachedir_depopulate(struct dentry *dentry) +{ + rpc_depopulate(dentry, cache_pipefs_files, 0, 3); +} + +struct dentry *rpc_create_cache_dir(struct dentry *parent, struct qstr *name, + mode_t umode, struct cache_detail *cd) +{ + return rpc_mkdir_populate(parent, name, umode, NULL, + rpc_cachedir_populate, cd); +} + +void rpc_remove_cache_dir(struct dentry *dentry) +{ + rpc_rmdir_depopulate(dentry, rpc_cachedir_depopulate); +} + /* * populate the filesystem */ @@ -866,6 +938,51 @@ static struct super_operations s_ops = { #define RPCAUTH_GSSMAGIC 0x67596969 +/* + * We have a single directory with 1 node in it. + */ +enum { + RPCAUTH_lockd, + RPCAUTH_mount, + RPCAUTH_nfs, + RPCAUTH_portmap, + RPCAUTH_statd, + RPCAUTH_nfsd4_cb, + RPCAUTH_cache, + RPCAUTH_RootEOF +}; + +static const struct rpc_filelist files[] = { + [RPCAUTH_lockd] = { + .name = "lockd", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_mount] = { + .name = "mount", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_nfs] = { + .name = "nfs", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_portmap] = { + .name = "portmap", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_statd] = { + .name = "statd", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_nfsd4_cb] = { + .name = "nfsd4_cb", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_cache] = { + .name = "cache", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, +}; + static int rpc_fill_super(struct super_block *sb, void *data, int silent) { @@ -886,7 +1003,7 @@ rpc_fill_super(struct super_block *sb, void *data, int silent) iput(inode); return -ENOMEM; } - if (rpc_populate(root, files, RPCAUTH_Root + 1, RPCAUTH_RootEOF)) + if (rpc_populate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF, NULL)) goto out; sb->s_root = root; return 0; diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index beee6da..830faf4 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -75,6 +75,37 @@ enum { #define RPCB_OWNER_STRING "0" #define RPCB_MAXOWNERLEN sizeof(RPCB_OWNER_STRING) +/* + * XDR data type sizes + */ +#define RPCB_program_sz (1) +#define RPCB_version_sz (1) +#define RPCB_protocol_sz (1) +#define RPCB_port_sz (1) +#define RPCB_boolean_sz (1) + +#define RPCB_netid_sz (1 + XDR_QUADLEN(RPCBIND_MAXNETIDLEN)) +#define RPCB_addr_sz (1 + XDR_QUADLEN(RPCBIND_MAXUADDRLEN)) +#define RPCB_ownerstring_sz (1 + XDR_QUADLEN(RPCB_MAXOWNERLEN)) + +/* + * XDR argument and result sizes + */ +#define RPCB_mappingargs_sz (RPCB_program_sz + RPCB_version_sz + \ + RPCB_protocol_sz + RPCB_port_sz) +#define RPCB_getaddrargs_sz (RPCB_program_sz + RPCB_version_sz + \ + RPCB_netid_sz + RPCB_addr_sz + \ + RPCB_ownerstring_sz) + +#define RPCB_getportres_sz RPCB_port_sz +#define RPCB_setres_sz RPCB_boolean_sz + +/* + * Note that RFC 1833 does not put any size restrictions on the + * address string returned by the remote rpcbind database. + */ +#define RPCB_getaddrres_sz RPCB_addr_sz + static void rpcb_getport_done(struct rpc_task *, void *); static void rpcb_map_release(void *data); static struct rpc_program rpcb_program; @@ -122,6 +153,7 @@ static void rpcb_map_release(void *data) rpcb_wake_rpcbind_waiters(map->r_xprt, map->r_status); xprt_put(map->r_xprt); + kfree(map->r_addr); kfree(map); } @@ -268,12 +300,9 @@ static int rpcb_register_inet4(const struct sockaddr *sap, const struct sockaddr_in *sin = (const struct sockaddr_in *)sap; struct rpcbind_args *map = msg->rpc_argp; unsigned short port = ntohs(sin->sin_port); - char buf[32]; + int result; - /* Construct AF_INET universal address */ - snprintf(buf, sizeof(buf), "%pI4.%u.%u", - &sin->sin_addr.s_addr, port >> 8, port & 0xff); - map->r_addr = buf; + map->r_addr = rpc_sockaddr2uaddr(sap); dprintk("RPC: %sregistering [%u, %u, %s, '%s'] with " "local rpcbind\n", (port ? "" : "un"), @@ -284,7 +313,9 @@ static int rpcb_register_inet4(const struct sockaddr *sap, if (port) msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; - return rpcb_register_call(RPCBVERS_4, msg); + result = rpcb_register_call(RPCBVERS_4, msg); + kfree(map->r_addr); + return result; } /* @@ -296,16 +327,9 @@ static int rpcb_register_inet6(const struct sockaddr *sap, const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)sap; struct rpcbind_args *map = msg->rpc_argp; unsigned short port = ntohs(sin6->sin6_port); - char buf[64]; + int result; - /* Construct AF_INET6 universal address */ - if (ipv6_addr_any(&sin6->sin6_addr)) - snprintf(buf, sizeof(buf), "::.%u.%u", - port >> 8, port & 0xff); - else - snprintf(buf, sizeof(buf), "%pI6.%u.%u", - &sin6->sin6_addr, port >> 8, port & 0xff); - map->r_addr = buf; + map->r_addr = rpc_sockaddr2uaddr(sap); dprintk("RPC: %sregistering [%u, %u, %s, '%s'] with " "local rpcbind\n", (port ? "" : "un"), @@ -316,7 +340,9 @@ static int rpcb_register_inet6(const struct sockaddr *sap, if (port) msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; - return rpcb_register_call(RPCBVERS_4, msg); + result = rpcb_register_call(RPCBVERS_4, msg); + kfree(map->r_addr); + return result; } static int rpcb_unregister_all_protofamilies(struct rpc_message *msg) @@ -428,7 +454,7 @@ int rpcb_getport_sync(struct sockaddr_in *sin, u32 prog, u32 vers, int prot) struct rpc_message msg = { .rpc_proc = &rpcb_procedures2[RPCBPROC_GETPORT], .rpc_argp = &map, - .rpc_resp = &map.r_port, + .rpc_resp = &map, }; struct rpc_clnt *rpcb_clnt; int status; @@ -458,7 +484,7 @@ static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, struct rpcbi struct rpc_message msg = { .rpc_proc = proc, .rpc_argp = map, - .rpc_resp = &map->r_port, + .rpc_resp = map, }; struct rpc_task_setup task_setup_data = { .rpc_client = rpcb_clnt, @@ -539,6 +565,7 @@ void rpcb_getport_async(struct rpc_task *task) goto bailout_nofree; } + /* Parent transport's destination address */ salen = rpc_peeraddr(clnt, sap, sizeof(addr)); /* Don't ever use rpcbind v2 for AF_INET6 requests */ @@ -589,11 +616,22 @@ void rpcb_getport_async(struct rpc_task *task) map->r_prot = xprt->prot; map->r_port = 0; map->r_xprt = xprt_get(xprt); - map->r_netid = rpc_peeraddr2str(clnt, RPC_DISPLAY_NETID); - map->r_addr = rpc_peeraddr2str(rpcb_clnt, RPC_DISPLAY_UNIVERSAL_ADDR); - map->r_owner = ""; map->r_status = -EIO; + switch (bind_version) { + case RPCBVERS_4: + case RPCBVERS_3: + map->r_netid = rpc_peeraddr2str(clnt, RPC_DISPLAY_NETID); + map->r_addr = rpc_sockaddr2uaddr(sap); + map->r_owner = ""; + break; + case RPCBVERS_2: + map->r_addr = NULL; + break; + default: + BUG(); + } + child = rpcb_call_async(rpcb_clnt, map, proc); rpc_release_client(rpcb_clnt); if (IS_ERR(child)) { @@ -656,176 +694,278 @@ static void rpcb_getport_done(struct rpc_task *child, void *data) * XDR functions for rpcbind */ -static int rpcb_encode_mapping(struct rpc_rqst *req, __be32 *p, - struct rpcbind_args *rpcb) +static int rpcb_enc_mapping(struct rpc_rqst *req, __be32 *p, + const struct rpcbind_args *rpcb) { - dprintk("RPC: encoding rpcb request (%u, %u, %d, %u)\n", + struct rpc_task *task = req->rq_task; + struct xdr_stream xdr; + + dprintk("RPC: %5u encoding PMAP_%s call (%u, %u, %d, %u)\n", + task->tk_pid, task->tk_msg.rpc_proc->p_name, rpcb->r_prog, rpcb->r_vers, rpcb->r_prot, rpcb->r_port); + + xdr_init_encode(&xdr, &req->rq_snd_buf, p); + + p = xdr_reserve_space(&xdr, sizeof(__be32) * RPCB_mappingargs_sz); + if (unlikely(p == NULL)) + return -EIO; + *p++ = htonl(rpcb->r_prog); *p++ = htonl(rpcb->r_vers); *p++ = htonl(rpcb->r_prot); - *p++ = htonl(rpcb->r_port); + *p = htonl(rpcb->r_port); - req->rq_slen = xdr_adjust_iovec(req->rq_svec, p); return 0; } -static int rpcb_decode_getport(struct rpc_rqst *req, __be32 *p, - unsigned short *portp) +static int rpcb_dec_getport(struct rpc_rqst *req, __be32 *p, + struct rpcbind_args *rpcb) { - *portp = (unsigned short) ntohl(*p++); - dprintk("RPC: rpcb getport result: %u\n", - *portp); + struct rpc_task *task = req->rq_task; + struct xdr_stream xdr; + unsigned long port; + + xdr_init_decode(&xdr, &req->rq_rcv_buf, p); + + rpcb->r_port = 0; + + p = xdr_inline_decode(&xdr, sizeof(__be32)); + if (unlikely(p == NULL)) + return -EIO; + + port = ntohl(*p); + dprintk("RPC: %5u PMAP_%s result: %lu\n", task->tk_pid, + task->tk_msg.rpc_proc->p_name, port); + if (unlikely(port > USHORT_MAX)) + return -EIO; + + rpcb->r_port = port; return 0; } -static int rpcb_decode_set(struct rpc_rqst *req, __be32 *p, - unsigned int *boolp) +static int rpcb_dec_set(struct rpc_rqst *req, __be32 *p, + unsigned int *boolp) { - *boolp = (unsigned int) ntohl(*p++); - dprintk("RPC: rpcb set/unset call %s\n", + struct rpc_task *task = req->rq_task; + struct xdr_stream xdr; + + xdr_init_decode(&xdr, &req->rq_rcv_buf, p); + + p = xdr_inline_decode(&xdr, sizeof(__be32)); + if (unlikely(p == NULL)) + return -EIO; + + *boolp = 0; + if (*p) + *boolp = 1; + + dprintk("RPC: %5u RPCB_%s call %s\n", + task->tk_pid, task->tk_msg.rpc_proc->p_name, (*boolp ? "succeeded" : "failed")); return 0; } -static int rpcb_encode_getaddr(struct rpc_rqst *req, __be32 *p, - struct rpcbind_args *rpcb) +static int encode_rpcb_string(struct xdr_stream *xdr, const char *string, + const u32 maxstrlen) { - dprintk("RPC: encoding rpcb request (%u, %u, %s)\n", - rpcb->r_prog, rpcb->r_vers, rpcb->r_addr); - *p++ = htonl(rpcb->r_prog); - *p++ = htonl(rpcb->r_vers); + u32 len; + __be32 *p; - p = xdr_encode_string(p, rpcb->r_netid); - p = xdr_encode_string(p, rpcb->r_addr); - p = xdr_encode_string(p, rpcb->r_owner); + if (unlikely(string == NULL)) + return -EIO; + len = strlen(string); + if (unlikely(len > maxstrlen)) + return -EIO; - req->rq_slen = xdr_adjust_iovec(req->rq_svec, p); + p = xdr_reserve_space(xdr, sizeof(__be32) + len); + if (unlikely(p == NULL)) + return -EIO; + xdr_encode_opaque(p, string, len); return 0; } -static int rpcb_decode_getaddr(struct rpc_rqst *req, __be32 *p, - unsigned short *portp) +static int rpcb_enc_getaddr(struct rpc_rqst *req, __be32 *p, + const struct rpcbind_args *rpcb) { - char *addr; - u32 addr_len; - int c, i, f, first, val; + struct rpc_task *task = req->rq_task; + struct xdr_stream xdr; - *portp = 0; - addr_len = ntohl(*p++); + dprintk("RPC: %5u encoding RPCB_%s call (%u, %u, '%s', '%s')\n", + task->tk_pid, task->tk_msg.rpc_proc->p_name, + rpcb->r_prog, rpcb->r_vers, + rpcb->r_netid, rpcb->r_addr); - if (addr_len == 0) { - dprintk("RPC: rpcb_decode_getaddr: " - "service is not registered\n"); - return 0; - } + xdr_init_encode(&xdr, &req->rq_snd_buf, p); - /* - * Simple sanity check. - */ - if (addr_len > RPCBIND_MAXUADDRLEN) - goto out_err; - - /* - * Start at the end and walk backwards until the first dot - * is encountered. When the second dot is found, we have - * both parts of the port number. - */ - addr = (char *)p; - val = 0; - first = 1; - f = 1; - for (i = addr_len - 1; i > 0; i--) { - c = addr[i]; - if (c >= '0' && c <= '9') { - val += (c - '0') * f; - f *= 10; - } else if (c == '.') { - if (first) { - *portp = val; - val = first = 0; - f = 1; - } else { - *portp |= (val << 8); - break; - } - } - } + p = xdr_reserve_space(&xdr, + sizeof(__be32) * (RPCB_program_sz + RPCB_version_sz)); + if (unlikely(p == NULL)) + return -EIO; + *p++ = htonl(rpcb->r_prog); + *p = htonl(rpcb->r_vers); - /* - * Simple sanity check. If we never saw a dot in the reply, - * then this was probably just garbage. - */ - if (first) - goto out_err; + if (encode_rpcb_string(&xdr, rpcb->r_netid, RPCBIND_MAXNETIDLEN)) + return -EIO; + if (encode_rpcb_string(&xdr, rpcb->r_addr, RPCBIND_MAXUADDRLEN)) + return -EIO; + if (encode_rpcb_string(&xdr, rpcb->r_owner, RPCB_MAXOWNERLEN)) + return -EIO; - dprintk("RPC: rpcb_decode_getaddr port=%u\n", *portp); return 0; - -out_err: - dprintk("RPC: rpcbind server returned malformed reply\n"); - return -EIO; } -#define RPCB_program_sz (1u) -#define RPCB_version_sz (1u) -#define RPCB_protocol_sz (1u) -#define RPCB_port_sz (1u) -#define RPCB_boolean_sz (1u) +static int rpcb_dec_getaddr(struct rpc_rqst *req, __be32 *p, + struct rpcbind_args *rpcb) +{ + struct sockaddr_storage address; + struct sockaddr *sap = (struct sockaddr *)&address; + struct rpc_task *task = req->rq_task; + struct xdr_stream xdr; + u32 len; -#define RPCB_netid_sz (1+XDR_QUADLEN(RPCBIND_MAXNETIDLEN)) -#define RPCB_addr_sz (1+XDR_QUADLEN(RPCBIND_MAXUADDRLEN)) -#define RPCB_ownerstring_sz (1+XDR_QUADLEN(RPCB_MAXOWNERLEN)) + rpcb->r_port = 0; -#define RPCB_mappingargs_sz RPCB_program_sz+RPCB_version_sz+ \ - RPCB_protocol_sz+RPCB_port_sz -#define RPCB_getaddrargs_sz RPCB_program_sz+RPCB_version_sz+ \ - RPCB_netid_sz+RPCB_addr_sz+ \ - RPCB_ownerstring_sz + xdr_init_decode(&xdr, &req->rq_rcv_buf, p); -#define RPCB_setres_sz RPCB_boolean_sz -#define RPCB_getportres_sz RPCB_port_sz - -/* - * Note that RFC 1833 does not put any size restrictions on the - * address string returned by the remote rpcbind database. - */ -#define RPCB_getaddrres_sz RPCB_addr_sz + p = xdr_inline_decode(&xdr, sizeof(__be32)); + if (unlikely(p == NULL)) + goto out_fail; + len = ntohl(*p); -#define PROC(proc, argtype, restype) \ - [RPCBPROC_##proc] = { \ - .p_proc = RPCBPROC_##proc, \ - .p_encode = (kxdrproc_t) rpcb_encode_##argtype, \ - .p_decode = (kxdrproc_t) rpcb_decode_##restype, \ - .p_arglen = RPCB_##argtype##args_sz, \ - .p_replen = RPCB_##restype##res_sz, \ - .p_statidx = RPCBPROC_##proc, \ - .p_timer = 0, \ - .p_name = #proc, \ + /* + * If the returned universal address is a null string, + * the requested RPC service was not registered. + */ + if (len == 0) { + dprintk("RPC: %5u RPCB reply: program not registered\n", + task->tk_pid); + return 0; } + if (unlikely(len > RPCBIND_MAXUADDRLEN)) + goto out_fail; + + p = xdr_inline_decode(&xdr, len); + if (unlikely(p == NULL)) + goto out_fail; + dprintk("RPC: %5u RPCB_%s reply: %s\n", task->tk_pid, + task->tk_msg.rpc_proc->p_name, (char *)p); + + if (rpc_uaddr2sockaddr((char *)p, len, sap, sizeof(address)) == 0) + goto out_fail; + rpcb->r_port = rpc_get_port(sap); + + return 0; + +out_fail: + dprintk("RPC: %5u malformed RPCB_%s reply\n", + task->tk_pid, task->tk_msg.rpc_proc->p_name); + return -EIO; +} + /* * Not all rpcbind procedures described in RFC 1833 are implemented * since the Linux kernel RPC code requires only these. */ + static struct rpc_procinfo rpcb_procedures2[] = { - PROC(SET, mapping, set), - PROC(UNSET, mapping, set), - PROC(GETPORT, mapping, getport), + [RPCBPROC_SET] = { + .p_proc = RPCBPROC_SET, + .p_encode = (kxdrproc_t)rpcb_enc_mapping, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_mappingargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_SET, + .p_timer = 0, + .p_name = "SET", + }, + [RPCBPROC_UNSET] = { + .p_proc = RPCBPROC_UNSET, + .p_encode = (kxdrproc_t)rpcb_enc_mapping, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_mappingargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_UNSET, + .p_timer = 0, + .p_name = "UNSET", + }, + [RPCBPROC_GETPORT] = { + .p_proc = RPCBPROC_GETPORT, + .p_encode = (kxdrproc_t)rpcb_enc_mapping, + .p_decode = (kxdrproc_t)rpcb_dec_getport, + .p_arglen = RPCB_mappingargs_sz, + .p_replen = RPCB_getportres_sz, + .p_statidx = RPCBPROC_GETPORT, + .p_timer = 0, + .p_name = "GETPORT", + }, }; static struct rpc_procinfo rpcb_procedures3[] = { - PROC(SET, getaddr, set), - PROC(UNSET, getaddr, set), - PROC(GETADDR, getaddr, getaddr), + [RPCBPROC_SET] = { + .p_proc = RPCBPROC_SET, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_SET, + .p_timer = 0, + .p_name = "SET", + }, + [RPCBPROC_UNSET] = { + .p_proc = RPCBPROC_UNSET, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_UNSET, + .p_timer = 0, + .p_name = "UNSET", + }, + [RPCBPROC_GETADDR] = { + .p_proc = RPCBPROC_GETADDR, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_getaddr, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_getaddrres_sz, + .p_statidx = RPCBPROC_GETADDR, + .p_timer = 0, + .p_name = "GETADDR", + }, }; static struct rpc_procinfo rpcb_procedures4[] = { - PROC(SET, getaddr, set), - PROC(UNSET, getaddr, set), - PROC(GETADDR, getaddr, getaddr), - PROC(GETVERSADDR, getaddr, getaddr), + [RPCBPROC_SET] = { + .p_proc = RPCBPROC_SET, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_SET, + .p_timer = 0, + .p_name = "SET", + }, + [RPCBPROC_UNSET] = { + .p_proc = RPCBPROC_UNSET, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_UNSET, + .p_timer = 0, + .p_name = "UNSET", + }, + [RPCBPROC_GETADDR] = { + .p_proc = RPCBPROC_GETADDR, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_getaddr, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_getaddrres_sz, + .p_statidx = RPCBPROC_GETADDR, + .p_timer = 0, + .p_name = "GETADDR", + }, }; static struct rpcb_info rpcb_next_version[] = { diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index adaa819..8cce921 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -69,5 +69,5 @@ cleanup_sunrpc(void) rcu_barrier(); /* Wait for completion of call_rcu()'s */ } MODULE_LICENSE("GPL"); -module_init(init_sunrpc); +fs_initcall(init_sunrpc); /* Ensure we're initialised before nfs */ module_exit(cleanup_sunrpc); diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 5c865e2..6caffa3 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -171,6 +171,11 @@ static void ip_map_request(struct cache_detail *cd, (*bpp)[-1] = '\n'; } +static int ip_map_upcall(struct cache_detail *cd, struct cache_head *h) +{ + return sunrpc_cache_pipe_upcall(cd, h, ip_map_request); +} + static struct ip_map *ip_map_lookup(char *class, struct in6_addr *addr); static int ip_map_update(struct ip_map *ipm, struct unix_domain *udom, time_t expiry); @@ -289,7 +294,7 @@ struct cache_detail ip_map_cache = { .hash_table = ip_table, .name = "auth.unix.ip", .cache_put = ip_map_put, - .cache_request = ip_map_request, + .cache_upcall = ip_map_upcall, .cache_parse = ip_map_parse, .cache_show = ip_map_show, .match = ip_map_match, @@ -523,6 +528,11 @@ static void unix_gid_request(struct cache_detail *cd, (*bpp)[-1] = '\n'; } +static int unix_gid_upcall(struct cache_detail *cd, struct cache_head *h) +{ + return sunrpc_cache_pipe_upcall(cd, h, unix_gid_request); +} + static struct unix_gid *unix_gid_lookup(uid_t uid); extern struct cache_detail unix_gid_cache; @@ -622,7 +632,7 @@ struct cache_detail unix_gid_cache = { .hash_table = gid_table, .name = "auth.unix.gid", .cache_put = unix_gid_put, - .cache_request = unix_gid_request, + .cache_upcall = unix_gid_upcall, .cache_parse = unix_gid_parse, .cache_show = unix_gid_show, .match = unix_gid_match, diff --git a/net/sunrpc/timer.c b/net/sunrpc/timer.c index 31becbf..dd82434 100644 --- a/net/sunrpc/timer.c +++ b/net/sunrpc/timer.c @@ -25,8 +25,13 @@ #define RPC_RTO_INIT (HZ/5) #define RPC_RTO_MIN (HZ/10) -void -rpc_init_rtt(struct rpc_rtt *rt, unsigned long timeo) +/** + * rpc_init_rtt - Initialize an RPC RTT estimator context + * @rt: context to initialize + * @timeo: initial timeout value, in jiffies + * + */ +void rpc_init_rtt(struct rpc_rtt *rt, unsigned long timeo) { unsigned long init = 0; unsigned i; @@ -43,12 +48,16 @@ rpc_init_rtt(struct rpc_rtt *rt, unsigned long timeo) } EXPORT_SYMBOL_GPL(rpc_init_rtt); -/* +/** + * rpc_update_rtt - Update an RPC RTT estimator context + * @rt: context to update + * @timer: timer array index (request type) + * @m: recent actual RTT, in jiffies + * * NB: When computing the smoothed RTT and standard deviation, * be careful not to produce negative intermediate results. */ -void -rpc_update_rtt(struct rpc_rtt *rt, unsigned timer, long m) +void rpc_update_rtt(struct rpc_rtt *rt, unsigned timer, long m) { long *srtt, *sdrtt; @@ -79,21 +88,25 @@ rpc_update_rtt(struct rpc_rtt *rt, unsigned timer, long m) } EXPORT_SYMBOL_GPL(rpc_update_rtt); -/* - * Estimate rto for an nfs rpc sent via. an unreliable datagram. - * Use the mean and mean deviation of rtt for the appropriate type of rpc - * for the frequent rpcs and a default for the others. - * The justification for doing "other" this way is that these rpcs - * happen so infrequently that timer est. would probably be stale. - * Also, since many of these rpcs are - * non-idempotent, a conservative timeout is desired. +/** + * rpc_calc_rto - Provide an estimated timeout value + * @rt: context to use for calculation + * @timer: timer array index (request type) + * + * Estimate RTO for an NFS RPC sent via an unreliable datagram. Use + * the mean and mean deviation of RTT for the appropriate type of RPC + * for frequently issued RPCs, and a fixed default for the others. + * + * The justification for doing "other" this way is that these RPCs + * happen so infrequently that timer estimation would probably be + * stale. Also, since many of these RPCs are non-idempotent, a + * conservative timeout is desired. + * * getattr, lookup, * read, write, commit - A+4D * other - timeo */ - -unsigned long -rpc_calc_rto(struct rpc_rtt *rt, unsigned timer) +unsigned long rpc_calc_rto(struct rpc_rtt *rt, unsigned timer) { unsigned long res; diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 406e26d..8bd690c 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -24,7 +24,7 @@ xdr_encode_netobj(__be32 *p, const struct xdr_netobj *obj) unsigned int quadlen = XDR_QUADLEN(obj->len); p[quadlen] = 0; /* zero trailing bytes */ - *p++ = htonl(obj->len); + *p++ = cpu_to_be32(obj->len); memcpy(p, obj->data, obj->len); return p + XDR_QUADLEN(obj->len); } @@ -35,7 +35,7 @@ xdr_decode_netobj(__be32 *p, struct xdr_netobj *obj) { unsigned int len; - if ((len = ntohl(*p++)) > XDR_MAX_NETOBJ) + if ((len = be32_to_cpu(*p++)) > XDR_MAX_NETOBJ) return NULL; obj->len = len; obj->data = (u8 *) p; @@ -83,7 +83,7 @@ EXPORT_SYMBOL_GPL(xdr_encode_opaque_fixed); */ __be32 *xdr_encode_opaque(__be32 *p, const void *ptr, unsigned int nbytes) { - *p++ = htonl(nbytes); + *p++ = cpu_to_be32(nbytes); return xdr_encode_opaque_fixed(p, ptr, nbytes); } EXPORT_SYMBOL_GPL(xdr_encode_opaque); @@ -101,7 +101,7 @@ xdr_decode_string_inplace(__be32 *p, char **sp, { u32 len; - len = ntohl(*p++); + len = be32_to_cpu(*p++); if (len > maxlen) return NULL; *lenp = len; @@ -771,7 +771,7 @@ xdr_decode_word(struct xdr_buf *buf, unsigned int base, u32 *obj) status = read_bytes_from_xdr_buf(buf, base, &raw, sizeof(*obj)); if (status) return status; - *obj = ntohl(raw); + *obj = be32_to_cpu(raw); return 0; } EXPORT_SYMBOL_GPL(xdr_decode_word); @@ -779,7 +779,7 @@ EXPORT_SYMBOL_GPL(xdr_decode_word); int xdr_encode_word(struct xdr_buf *buf, unsigned int base, u32 obj) { - __be32 raw = htonl(obj); + __be32 raw = cpu_to_be32(obj); return write_bytes_to_xdr_buf(buf, base, &raw, sizeof(obj)); } diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 1dd6123..9a63f66 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -168,47 +168,25 @@ static struct rpc_xprt_ops xprt_rdma_procs; /* forward reference */ static void xprt_rdma_format_addresses(struct rpc_xprt *xprt) { - struct sockaddr_in *addr = (struct sockaddr_in *) + struct sockaddr *sap = (struct sockaddr *) &rpcx_to_rdmad(xprt).addr; - char *buf; + struct sockaddr_in *sin = (struct sockaddr_in *)sap; + char buf[64]; - buf = kzalloc(20, GFP_KERNEL); - if (buf) - snprintf(buf, 20, "%pI4", &addr->sin_addr.s_addr); - xprt->address_strings[RPC_DISPLAY_ADDR] = buf; + (void)rpc_ntop(sap, buf, sizeof(buf)); + xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL); - buf = kzalloc(8, GFP_KERNEL); - if (buf) - snprintf(buf, 8, "%u", ntohs(addr->sin_port)); - xprt->address_strings[RPC_DISPLAY_PORT] = buf; + (void)snprintf(buf, sizeof(buf), "%u", rpc_get_port(sap)); + xprt->address_strings[RPC_DISPLAY_PORT] = kstrdup(buf, GFP_KERNEL); xprt->address_strings[RPC_DISPLAY_PROTO] = "rdma"; - buf = kzalloc(48, GFP_KERNEL); - if (buf) - snprintf(buf, 48, "addr=%pI4 port=%u proto=%s", - &addr->sin_addr.s_addr, - ntohs(addr->sin_port), "rdma"); - xprt->address_strings[RPC_DISPLAY_ALL] = buf; - - buf = kzalloc(10, GFP_KERNEL); - if (buf) - snprintf(buf, 10, "%02x%02x%02x%02x", - NIPQUAD(addr->sin_addr.s_addr)); - xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = buf; - - buf = kzalloc(8, GFP_KERNEL); - if (buf) - snprintf(buf, 8, "%4hx", ntohs(addr->sin_port)); - xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf; - - buf = kzalloc(30, GFP_KERNEL); - if (buf) - snprintf(buf, 30, "%pI4.%u.%u", - &addr->sin_addr.s_addr, - ntohs(addr->sin_port) >> 8, - ntohs(addr->sin_port) & 0xff); - xprt->address_strings[RPC_DISPLAY_UNIVERSAL_ADDR] = buf; + (void)snprintf(buf, sizeof(buf), "%02x%02x%02x%02x", + NIPQUAD(sin->sin_addr.s_addr)); + xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL); + + (void)snprintf(buf, sizeof(buf), "%4hx", rpc_get_port(sap)); + xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL); /* netid */ xprt->address_strings[RPC_DISPLAY_NETID] = "rdma"; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 83c73c4..62438f3 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -248,8 +248,8 @@ struct sock_xprt { * Connection of transports */ struct delayed_work connect_worker; - struct sockaddr_storage addr; - unsigned short port; + struct sockaddr_storage srcaddr; + unsigned short srcport; /* * UDP socket buffer size parameters @@ -296,117 +296,60 @@ static inline struct sockaddr_in6 *xs_addr_in6(struct rpc_xprt *xprt) return (struct sockaddr_in6 *) &xprt->addr; } -static void xs_format_ipv4_peer_addresses(struct rpc_xprt *xprt, - const char *protocol, - const char *netid) +static void xs_format_common_peer_addresses(struct rpc_xprt *xprt) { - struct sockaddr_in *addr = xs_addr_in(xprt); - char *buf; + struct sockaddr *sap = xs_addr(xprt); + struct sockaddr_in6 *sin6; + struct sockaddr_in *sin; + char buf[128]; - buf = kzalloc(20, GFP_KERNEL); - if (buf) { - snprintf(buf, 20, "%pI4", &addr->sin_addr.s_addr); - } - xprt->address_strings[RPC_DISPLAY_ADDR] = buf; - - buf = kzalloc(8, GFP_KERNEL); - if (buf) { - snprintf(buf, 8, "%u", - ntohs(addr->sin_port)); - } - xprt->address_strings[RPC_DISPLAY_PORT] = buf; - - xprt->address_strings[RPC_DISPLAY_PROTO] = protocol; - - buf = kzalloc(48, GFP_KERNEL); - if (buf) { - snprintf(buf, 48, "addr=%pI4 port=%u proto=%s", - &addr->sin_addr.s_addr, - ntohs(addr->sin_port), - protocol); - } - xprt->address_strings[RPC_DISPLAY_ALL] = buf; - - buf = kzalloc(10, GFP_KERNEL); - if (buf) { - snprintf(buf, 10, "%02x%02x%02x%02x", - NIPQUAD(addr->sin_addr.s_addr)); - } - xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = buf; + (void)rpc_ntop(sap, buf, sizeof(buf)); + xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL); - buf = kzalloc(8, GFP_KERNEL); - if (buf) { - snprintf(buf, 8, "%4hx", - ntohs(addr->sin_port)); - } - xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf; - - buf = kzalloc(30, GFP_KERNEL); - if (buf) { - snprintf(buf, 30, "%pI4.%u.%u", - &addr->sin_addr.s_addr, - ntohs(addr->sin_port) >> 8, - ntohs(addr->sin_port) & 0xff); + switch (sap->sa_family) { + case AF_INET: + sin = xs_addr_in(xprt); + (void)snprintf(buf, sizeof(buf), "%02x%02x%02x%02x", + NIPQUAD(sin->sin_addr.s_addr)); + break; + case AF_INET6: + sin6 = xs_addr_in6(xprt); + (void)snprintf(buf, sizeof(buf), "%pi6", &sin6->sin6_addr); + break; + default: + BUG(); } - xprt->address_strings[RPC_DISPLAY_UNIVERSAL_ADDR] = buf; - - xprt->address_strings[RPC_DISPLAY_NETID] = netid; + xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL); } -static void xs_format_ipv6_peer_addresses(struct rpc_xprt *xprt, - const char *protocol, - const char *netid) +static void xs_format_common_peer_ports(struct rpc_xprt *xprt) { - struct sockaddr_in6 *addr = xs_addr_in6(xprt); - char *buf; + struct sockaddr *sap = xs_addr(xprt); + char buf[128]; - buf = kzalloc(40, GFP_KERNEL); - if (buf) { - snprintf(buf, 40, "%pI6",&addr->sin6_addr); - } - xprt->address_strings[RPC_DISPLAY_ADDR] = buf; + (void)snprintf(buf, sizeof(buf), "%u", rpc_get_port(sap)); + xprt->address_strings[RPC_DISPLAY_PORT] = kstrdup(buf, GFP_KERNEL); - buf = kzalloc(8, GFP_KERNEL); - if (buf) { - snprintf(buf, 8, "%u", - ntohs(addr->sin6_port)); - } - xprt->address_strings[RPC_DISPLAY_PORT] = buf; + (void)snprintf(buf, sizeof(buf), "%4hx", rpc_get_port(sap)); + xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL); +} +static void xs_format_peer_addresses(struct rpc_xprt *xprt, + const char *protocol, + const char *netid) +{ xprt->address_strings[RPC_DISPLAY_PROTO] = protocol; + xprt->address_strings[RPC_DISPLAY_NETID] = netid; + xs_format_common_peer_addresses(xprt); + xs_format_common_peer_ports(xprt); +} - buf = kzalloc(64, GFP_KERNEL); - if (buf) { - snprintf(buf, 64, "addr=%pI6 port=%u proto=%s", - &addr->sin6_addr, - ntohs(addr->sin6_port), - protocol); - } - xprt->address_strings[RPC_DISPLAY_ALL] = buf; - - buf = kzalloc(36, GFP_KERNEL); - if (buf) - snprintf(buf, 36, "%pi6", &addr->sin6_addr); - - xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = buf; - - buf = kzalloc(8, GFP_KERNEL); - if (buf) { - snprintf(buf, 8, "%4hx", - ntohs(addr->sin6_port)); - } - xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf; - - buf = kzalloc(50, GFP_KERNEL); - if (buf) { - snprintf(buf, 50, "%pI6.%u.%u", - &addr->sin6_addr, - ntohs(addr->sin6_port) >> 8, - ntohs(addr->sin6_port) & 0xff); - } - xprt->address_strings[RPC_DISPLAY_UNIVERSAL_ADDR] = buf; +static void xs_update_peer_port(struct rpc_xprt *xprt) +{ + kfree(xprt->address_strings[RPC_DISPLAY_HEX_PORT]); + kfree(xprt->address_strings[RPC_DISPLAY_PORT]); - xprt->address_strings[RPC_DISPLAY_NETID] = netid; + xs_format_common_peer_ports(xprt); } static void xs_free_peer_addresses(struct rpc_xprt *xprt) @@ -1587,25 +1530,15 @@ static unsigned short xs_get_random_port(void) */ static void xs_set_port(struct rpc_xprt *xprt, unsigned short port) { - struct sockaddr *addr = xs_addr(xprt); - dprintk("RPC: setting port for xprt %p to %u\n", xprt, port); - switch (addr->sa_family) { - case AF_INET: - ((struct sockaddr_in *)addr)->sin_port = htons(port); - break; - case AF_INET6: - ((struct sockaddr_in6 *)addr)->sin6_port = htons(port); - break; - default: - BUG(); - } + rpc_set_port(xs_addr(xprt), port); + xs_update_peer_port(xprt); } static unsigned short xs_get_srcport(struct sock_xprt *transport, struct socket *sock) { - unsigned short port = transport->port; + unsigned short port = transport->srcport; if (port == 0 && transport->xprt.resvport) port = xs_get_random_port(); @@ -1614,8 +1547,8 @@ static unsigned short xs_get_srcport(struct sock_xprt *transport, struct socket static unsigned short xs_next_srcport(struct sock_xprt *transport, struct socket *sock, unsigned short port) { - if (transport->port != 0) - transport->port = 0; + if (transport->srcport != 0) + transport->srcport = 0; if (!transport->xprt.resvport) return 0; if (port <= xprt_min_resvport || port > xprt_max_resvport) @@ -1633,7 +1566,7 @@ static int xs_bind4(struct sock_xprt *transport, struct socket *sock) unsigned short port = xs_get_srcport(transport, sock); unsigned short last; - sa = (struct sockaddr_in *)&transport->addr; + sa = (struct sockaddr_in *)&transport->srcaddr; myaddr.sin_addr = sa->sin_addr; do { myaddr.sin_port = htons(port); @@ -1642,7 +1575,7 @@ static int xs_bind4(struct sock_xprt *transport, struct socket *sock) if (port == 0) break; if (err == 0) { - transport->port = port; + transport->srcport = port; break; } last = port; @@ -1666,7 +1599,7 @@ static int xs_bind6(struct sock_xprt *transport, struct socket *sock) unsigned short port = xs_get_srcport(transport, sock); unsigned short last; - sa = (struct sockaddr_in6 *)&transport->addr; + sa = (struct sockaddr_in6 *)&transport->srcaddr; myaddr.sin6_addr = sa->sin6_addr; do { myaddr.sin6_port = htons(port); @@ -1675,7 +1608,7 @@ static int xs_bind6(struct sock_xprt *transport, struct socket *sock) if (port == 0) break; if (err == 0) { - transport->port = port; + transport->srcport = port; break; } last = port; @@ -1780,8 +1713,11 @@ static void xs_udp_connect_worker4(struct work_struct *work) goto out; } - dprintk("RPC: worker connecting xprt %p to address: %s\n", - xprt, xprt->address_strings[RPC_DISPLAY_ALL]); + dprintk("RPC: worker connecting xprt %p via %s to " + "%s (port %s)\n", xprt, + xprt->address_strings[RPC_DISPLAY_PROTO], + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT]); xs_udp_finish_connecting(xprt, sock); status = 0; @@ -1822,8 +1758,11 @@ static void xs_udp_connect_worker6(struct work_struct *work) goto out; } - dprintk("RPC: worker connecting xprt %p to address: %s\n", - xprt, xprt->address_strings[RPC_DISPLAY_ALL]); + dprintk("RPC: worker connecting xprt %p via %s to " + "%s (port %s)\n", xprt, + xprt->address_strings[RPC_DISPLAY_PROTO], + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT]); xs_udp_finish_connecting(xprt, sock); status = 0; @@ -1948,8 +1887,11 @@ static void xs_tcp_setup_socket(struct rpc_xprt *xprt, goto out_eagain; } - dprintk("RPC: worker connecting xprt %p to address: %s\n", - xprt, xprt->address_strings[RPC_DISPLAY_ALL]); + dprintk("RPC: worker connecting xprt %p via %s to " + "%s (port %s)\n", xprt, + xprt->address_strings[RPC_DISPLAY_PROTO], + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT]); status = xs_tcp_finish_connecting(xprt, sock); dprintk("RPC: %p connect status %d connected %d sock state %d\n", @@ -2120,7 +2062,7 @@ static void xs_udp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); seq_printf(seq, "\txprt:\tudp %u %lu %lu %lu %lu %Lu %Lu\n", - transport->port, + transport->srcport, xprt->stat.bind_count, xprt->stat.sends, xprt->stat.recvs, @@ -2144,7 +2086,7 @@ static void xs_tcp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) idle_time = (long)(jiffies - xprt->last_used) / HZ; seq_printf(seq, "\txprt:\ttcp %u %lu %lu %lu %ld %lu %lu %lu %Lu %Lu\n", - transport->port, + transport->srcport, xprt->stat.bind_count, xprt->stat.connect_count, xprt->stat.connect_time, @@ -2223,7 +2165,7 @@ static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args, memcpy(&xprt->addr, args->dstaddr, args->addrlen); xprt->addrlen = args->addrlen; if (args->srcaddr) - memcpy(&new->addr, args->srcaddr, args->addrlen); + memcpy(&new->srcaddr, args->srcaddr, args->addrlen); return xprt; } @@ -2272,7 +2214,7 @@ static struct rpc_xprt *xs_setup_udp(struct xprt_create *args) INIT_DELAYED_WORK(&transport->connect_worker, xs_udp_connect_worker4); - xs_format_ipv4_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP); + xs_format_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP); break; case AF_INET6: if (((struct sockaddr_in6 *)addr)->sin6_port != htons(0)) @@ -2280,15 +2222,22 @@ static struct rpc_xprt *xs_setup_udp(struct xprt_create *args) INIT_DELAYED_WORK(&transport->connect_worker, xs_udp_connect_worker6); - xs_format_ipv6_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP6); + xs_format_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP6); break; default: kfree(xprt); return ERR_PTR(-EAFNOSUPPORT); } - dprintk("RPC: set up transport to address %s\n", - xprt->address_strings[RPC_DISPLAY_ALL]); + if (xprt_bound(xprt)) + dprintk("RPC: set up xprt to %s (port %s) via %s\n", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT], + xprt->address_strings[RPC_DISPLAY_PROTO]); + else + dprintk("RPC: set up xprt to %s (autobind) via %s\n", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PROTO]); if (try_module_get(THIS_MODULE)) return xprt; @@ -2337,23 +2286,33 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args) if (((struct sockaddr_in *)addr)->sin_port != htons(0)) xprt_set_bound(xprt); - INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_connect_worker4); - xs_format_ipv4_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP); + INIT_DELAYED_WORK(&transport->connect_worker, + xs_tcp_connect_worker4); + xs_format_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP); break; case AF_INET6: if (((struct sockaddr_in6 *)addr)->sin6_port != htons(0)) xprt_set_bound(xprt); - INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_connect_worker6); - xs_format_ipv6_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP6); + INIT_DELAYED_WORK(&transport->connect_worker, + xs_tcp_connect_worker6); + xs_format_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP6); break; default: kfree(xprt); return ERR_PTR(-EAFNOSUPPORT); } - dprintk("RPC: set up transport to address %s\n", - xprt->address_strings[RPC_DISPLAY_ALL]); + if (xprt_bound(xprt)) + dprintk("RPC: set up xprt to %s (port %s) via %s\n", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT], + xprt->address_strings[RPC_DISPLAY_PROTO]); + else + dprintk("RPC: set up xprt to %s (autobind) via %s\n", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PROTO]); + if (try_module_get(THIS_MODULE)) return xprt; @@ -2412,3 +2371,55 @@ void cleanup_socket_xprt(void) xprt_unregister_transport(&xs_udp_transport); xprt_unregister_transport(&xs_tcp_transport); } + +static int param_set_uint_minmax(const char *val, struct kernel_param *kp, + unsigned int min, unsigned int max) +{ + unsigned long num; + int ret; + + if (!val) + return -EINVAL; + ret = strict_strtoul(val, 0, &num); + if (ret == -EINVAL || num < min || num > max) + return -EINVAL; + *((unsigned int *)kp->arg) = num; + return 0; +} + +static int param_set_portnr(const char *val, struct kernel_param *kp) +{ + return param_set_uint_minmax(val, kp, + RPC_MIN_RESVPORT, + RPC_MAX_RESVPORT); +} + +static int param_get_portnr(char *buffer, struct kernel_param *kp) +{ + return param_get_uint(buffer, kp); +} +#define param_check_portnr(name, p) \ + __param_check(name, p, unsigned int); + +module_param_named(min_resvport, xprt_min_resvport, portnr, 0644); +module_param_named(max_resvport, xprt_max_resvport, portnr, 0644); + +static int param_set_slot_table_size(const char *val, struct kernel_param *kp) +{ + return param_set_uint_minmax(val, kp, + RPC_MIN_SLOT_TABLE, + RPC_MAX_SLOT_TABLE); +} + +static int param_get_slot_table_size(char *buffer, struct kernel_param *kp) +{ + return param_get_uint(buffer, kp); +} +#define param_check_slot_table_size(name, p) \ + __param_check(name, p, unsigned int); + +module_param_named(tcp_slot_table_entries, xprt_tcp_slot_table_entries, + slot_table_size, 0644); +module_param_named(udp_slot_table_entries, xprt_udp_slot_table_entries, + slot_table_size, 0644); + |