diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c index aedc47a264c1..1f3b0fc0d351 100644 --- a/fs/lockd/clntlock.c +++ b/fs/lockd/clntlock.c @@ -139,55 +139,6 @@ int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout) return 0; } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -static const struct in6_addr *nlmclnt_map_v4addr(const struct sockaddr *sap, - struct in6_addr *addr_mapped) -{ - const struct sockaddr_in *sin = (const struct sockaddr_in *)sap; - - switch (sap->sa_family) { - case AF_INET6: - return &((const struct sockaddr_in6 *)sap)->sin6_addr; - case AF_INET: - ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, addr_mapped); - return addr_mapped; - } - - return NULL; -} - -/* - * If lockd is using a PF_INET6 listener, all incoming requests appear - * to come from AF_INET6 remotes. The address of AF_INET remotes are - * mapped to AF_INET6 automatically by the network layer. In case the - * user passed an AF_INET server address at mount time, ensure both - * addresses are AF_INET6 before comparing them. - */ -static int nlmclnt_cmp_addr(const struct nlm_host *host, - const struct sockaddr *sap) -{ - const struct in6_addr *addr1; - const struct in6_addr *addr2; - struct in6_addr addr1_mapped; - struct in6_addr addr2_mapped; - - addr1 = nlmclnt_map_v4addr(nlm_addr(host), &addr1_mapped); - if (likely(addr1 != NULL)) { - addr2 = nlmclnt_map_v4addr(sap, &addr2_mapped); - if (likely(addr2 != NULL)) - return ipv6_addr_equal(addr1, addr2); - } - - return 0; -} -#else /* !(CONFIG_IPV6 || CONFIG_IPV6_MODULE) */ -static int nlmclnt_cmp_addr(const struct nlm_host *host, - const struct sockaddr *sap) -{ - return nlm_cmp_addr(nlm_addr(host), sap); -} -#endif /* !(CONFIG_IPV6 || CONFIG_IPV6_MODULE) */ - /* * The server lockd has called us back to tell us the lock was granted */ @@ -215,7 +166,7 @@ __be32 nlmclnt_grant(const struct sockaddr *addr, const struct nlm_lock *lock) */ if (fl_blocked->fl_u.nfs_fl.owner->pid != lock->svid) continue; - if (!nlmclnt_cmp_addr(block->b_host, addr)) + if (!nlm_cmp_addr(nlm_addr(block->b_host), addr)) continue; if (nfs_compare_fh(NFS_FH(fl_blocked->fl_file->f_path.dentry->d_inode) ,fh) != 0) continue; diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 5e2c4d5ac827..6d5d4a4169e5 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -16,6 +16,8 @@ #include #include +#include + #define NLMDBG_FACILITY NLMDBG_MONITOR #define NSM_PROGRAM 100024 #define NSM_VERSION 1 @@ -274,10 +276,12 @@ static void nsm_init_private(struct nsm_handle *nsm) { u64 *p = (u64 *)&nsm->sm_priv.data; struct timespec ts; + s64 ns; ktime_get_ts(&ts); - *p++ = timespec_to_ns(&ts); - *p = (unsigned long)nsm; + ns = timespec_to_ns(&ts); + put_unaligned(ns, p); + put_unaligned((unsigned long)nsm, p + 1); } static struct nsm_handle *nsm_create_handle(const struct sockaddr *sap, diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 64f1c31b5853..abf83881f68a 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -52,17 +52,6 @@ static struct task_struct *nlmsvc_task; static struct svc_rqst *nlmsvc_rqst; unsigned long nlmsvc_timeout; -/* - * If the kernel has IPv6 support available, always listen for - * both AF_INET and AF_INET6 requests. - */ -#if (defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)) && \ - defined(CONFIG_SUNRPC_REGISTER_V4) -static const sa_family_t nlmsvc_family = AF_INET6; -#else /* (CONFIG_IPV6 || CONFIG_IPV6_MODULE) && CONFIG_SUNRPC_REGISTER_V4 */ -static const sa_family_t nlmsvc_family = AF_INET; -#endif /* (CONFIG_IPV6 || CONFIG_IPV6_MODULE) && CONFIG_SUNRPC_REGISTER_V4 */ - /* * These can be set at insmod time (useful for NFS as root filesystem), * and also changed through the sysctl interface. -- Jamie Lokier, Aug 2003 @@ -204,19 +193,30 @@ lockd(void *vrqstp) return 0; } -static int create_lockd_listener(struct svc_serv *serv, char *name, - unsigned short port) +static int create_lockd_listener(struct svc_serv *serv, const char *name, + const int family, const unsigned short port) { struct svc_xprt *xprt; - xprt = svc_find_xprt(serv, name, 0, 0); + xprt = svc_find_xprt(serv, name, family, 0); if (xprt == NULL) - return svc_create_xprt(serv, name, port, SVC_SOCK_DEFAULTS); - + return svc_create_xprt(serv, name, family, port, + SVC_SOCK_DEFAULTS); svc_xprt_put(xprt); return 0; } +static int create_lockd_family(struct svc_serv *serv, const int family) +{ + int err; + + err = create_lockd_listener(serv, "udp", family, nlm_udpport); + if (err < 0) + return err; + + return create_lockd_listener(serv, "tcp", family, nlm_tcpport); +} + /* * Ensure there are active UDP and TCP listeners for lockd. * @@ -232,13 +232,15 @@ static int make_socks(struct svc_serv *serv) static int warned; int err; - err = create_lockd_listener(serv, "udp", nlm_udpport); + err = create_lockd_family(serv, PF_INET); if (err < 0) goto out_err; - err = create_lockd_listener(serv, "tcp", nlm_tcpport); - if (err < 0) +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + err = create_lockd_family(serv, PF_INET6); + if (err < 0 && err != -EAFNOSUPPORT) goto out_err; +#endif /* CONFIG_IPV6 || CONFIG_IPV6_MODULE */ warned = 0; return 0; @@ -274,7 +276,7 @@ int lockd_up(void) "lockd_up: no pid, %d users??\n", nlmsvc_users); error = -ENOMEM; - serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, nlmsvc_family, NULL); + serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, NULL); if (!serv) { printk(KERN_WARNING "lockd_up: create service failed\n"); goto out; diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 3e634f2a1083..a886e692ddd0 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -38,19 +38,10 @@ 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; -/* - * If the kernel has IPv6 support available, always listen for - * both AF_INET and AF_INET6 requests. - */ -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -static const sa_family_t nfs_callback_family = AF_INET6; -#else -static const sa_family_t nfs_callback_family = AF_INET; -#endif - static int param_set_port(const char *val, struct kernel_param *kp) { char *endp; @@ -116,19 +107,29 @@ int nfs_callback_up(void) mutex_lock(&nfs_callback_mutex); if (nfs_callback_info.users++ || nfs_callback_info.task != NULL) goto out; - serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, - nfs_callback_family, NULL); + serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, NULL); ret = -ENOMEM; if (!serv) goto out_err; - ret = svc_create_xprt(serv, "tcp", nfs_callback_set_tcpport, - SVC_SOCK_ANONYMOUS); + ret = svc_create_xprt(serv, "tcp", PF_INET, + nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS); if (ret <= 0) goto out_err; nfs_callback_tcpport = ret; dprintk("NFS: Callback listener port = %u (af %u)\n", - nfs_callback_tcpport, nfs_callback_family); + nfs_callback_tcpport, PF_INET); + +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + ret = svc_create_xprt(serv, "tcp", PF_INET6, + nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS); + if (ret > 0) { + nfs_callback_tcpport6 = ret; + dprintk("NFS: Callback listener port = %u (af %u)\n", + nfs_callback_tcpport6, PF_INET6); + } else if (ret != -EAFNOSUPPORT) + goto out_err; +#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */ nfs_callback_info.rqst = svc_prepare_thread(serv, &serv->sv_pools[0]); if (IS_ERR(nfs_callback_info.rqst)) { diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h index bb25d2135ff1..e110e286a262 100644 --- a/fs/nfs/callback.h +++ b/fs/nfs/callback.h @@ -72,5 +72,6 @@ extern void nfs_callback_down(void); extern unsigned int nfs_callback_set_tcpport; extern unsigned short nfs_callback_tcpport; +extern unsigned short nfs_callback_tcpport6; #endif /* __LINUX_FS_NFS_CALLBACK_H */ diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 2277421656e7..aba38017bdef 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -224,38 +224,6 @@ void nfs_put_client(struct nfs_client *clp) } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -static const struct in6_addr *nfs_map_ipv4_addr(const struct sockaddr *sa, struct in6_addr *addr_mapped) -{ - switch (sa->sa_family) { - default: - return NULL; - case AF_INET6: - return &((const struct sockaddr_in6 *)sa)->sin6_addr; - break; - case AF_INET: - ipv6_addr_set_v4mapped(((const struct sockaddr_in *)sa)->sin_addr.s_addr, - addr_mapped); - return addr_mapped; - } -} - -static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1, - const struct sockaddr *sa2) -{ - const struct in6_addr *addr1; - const struct in6_addr *addr2; - struct in6_addr addr1_mapped; - struct in6_addr addr2_mapped; - - addr1 = nfs_map_ipv4_addr(sa1, &addr1_mapped); - if (likely(addr1 != NULL)) { - addr2 = nfs_map_ipv4_addr(sa2, &addr2_mapped); - if (likely(addr2 != NULL)) - return ipv6_addr_equal(addr1, addr2); - } - return 0; -} - /* * Test if two ip6 socket addresses refer to the same socket by * comparing relevant fields. The padding bytes specifically, are not @@ -267,38 +235,21 @@ static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1, * * The caller should ensure both socket addresses are AF_INET6. */ -static int nfs_sockaddr_cmp_ip6(const struct sockaddr *sa1, - const struct sockaddr *sa2) +static int nfs_sockaddr_match_ipaddr6(const struct sockaddr *sa1, + const struct sockaddr *sa2) { - const struct sockaddr_in6 *saddr1 = (const struct sockaddr_in6 *)sa1; - const struct sockaddr_in6 *saddr2 = (const struct sockaddr_in6 *)sa2; + const struct sockaddr_in6 *sin1 = (const struct sockaddr_in6 *)sa1; + const struct sockaddr_in6 *sin2 = (const struct sockaddr_in6 *)sa2; - if (!ipv6_addr_equal(&saddr1->sin6_addr, - &saddr1->sin6_addr)) + if (ipv6_addr_scope(&sin1->sin6_addr) == IPV6_ADDR_SCOPE_LINKLOCAL && + sin1->sin6_scope_id != sin2->sin6_scope_id) return 0; - if (ipv6_addr_scope(&saddr1->sin6_addr) == IPV6_ADDR_SCOPE_LINKLOCAL && - saddr1->sin6_scope_id != saddr2->sin6_scope_id) - return 0; - return saddr1->sin6_port == saddr2->sin6_port; -} -#else -static int nfs_sockaddr_match_ipaddr4(const struct sockaddr_in *sa1, - const struct sockaddr_in *sa2) -{ - return sa1->sin_addr.s_addr == sa2->sin_addr.s_addr; -} -static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1, - const struct sockaddr *sa2) -{ - if (unlikely(sa1->sa_family != AF_INET || sa2->sa_family != AF_INET)) - return 0; - return nfs_sockaddr_match_ipaddr4((const struct sockaddr_in *)sa1, - (const struct sockaddr_in *)sa2); + return ipv6_addr_equal(&sin1->sin6_addr, &sin1->sin6_addr); } - -static int nfs_sockaddr_cmp_ip6(const struct sockaddr * sa1, - const struct sockaddr * sa2) +#else /* !defined(CONFIG_IPV6) && !defined(CONFIG_IPV6_MODULE) */ +static int nfs_sockaddr_match_ipaddr6(const struct sockaddr *sa1, + const struct sockaddr *sa2) { return 0; } @@ -311,20 +262,57 @@ static int nfs_sockaddr_cmp_ip6(const struct sockaddr * sa1, * * The caller should ensure both socket addresses are AF_INET. */ +static int nfs_sockaddr_match_ipaddr4(const struct sockaddr *sa1, + const struct sockaddr *sa2) +{ + const struct sockaddr_in *sin1 = (const struct sockaddr_in *)sa1; + const struct sockaddr_in *sin2 = (const struct sockaddr_in *)sa2; + + return sin1->sin_addr.s_addr == sin2->sin_addr.s_addr; +} + +static int nfs_sockaddr_cmp_ip6(const struct sockaddr *sa1, + const struct sockaddr *sa2) +{ + const struct sockaddr_in6 *sin1 = (const struct sockaddr_in6 *)sa1; + const struct sockaddr_in6 *sin2 = (const struct sockaddr_in6 *)sa2; + + return nfs_sockaddr_match_ipaddr6(sa1, sa2) && + (sin1->sin6_port == sin2->sin6_port); +} + static int nfs_sockaddr_cmp_ip4(const struct sockaddr *sa1, const struct sockaddr *sa2) { - const struct sockaddr_in *saddr1 = (const struct sockaddr_in *)sa1; - const struct sockaddr_in *saddr2 = (const struct sockaddr_in *)sa2; + const struct sockaddr_in *sin1 = (const struct sockaddr_in *)sa1; + const struct sockaddr_in *sin2 = (const struct sockaddr_in *)sa2; - if (saddr1->sin_addr.s_addr != saddr2->sin_addr.s_addr) - return 0; - return saddr1->sin_port == saddr2->sin_port; + return nfs_sockaddr_match_ipaddr4(sa1, sa2) && + (sin1->sin_port == sin2->sin_port); } /* * Test if two socket addresses represent the same actual socket, - * by comparing (only) relevant fields. + * by comparing (only) relevant fields, excluding the port number. + */ +static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1, + const struct sockaddr *sa2) +{ + if (sa1->sa_family != sa2->sa_family) + return 0; + + switch (sa1->sa_family) { + case AF_INET: + return nfs_sockaddr_match_ipaddr4(sa1, sa2); + case AF_INET6: + return nfs_sockaddr_match_ipaddr6(sa1, sa2); + } + return 0; +} + +/* + * Test if two socket addresses represent the same actual socket, + * by comparing (only) relevant fields, including the port number. */ static int nfs_sockaddr_cmp(const struct sockaddr *sa1, const struct sockaddr *sa2) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 78bf72fc1db3..370b190a09d1 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1624,8 +1624,7 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, } else if (atomic_read(&new_dentry->d_count) > 1) /* dentry still busy? */ goto out; - } else - nfs_drop_nlink(new_inode); + } go_ahead: /* @@ -1638,10 +1637,8 @@ go_ahead: } nfs_inode_return_delegation(old_inode); - if (new_inode != NULL) { + if (new_inode != NULL) nfs_inode_return_delegation(new_inode); - d_delete(new_dentry); - } error = NFS_PROTO(old_dir)->rename(old_dir, &old_dentry->d_name, new_dir, &new_dentry->d_name); @@ -1650,6 +1647,8 @@ out: if (rehash) d_rehash(rehash); if (!error) { + if (new_inode != NULL) + nfs_drop_nlink(new_inode); d_move(old_dentry, new_dentry); nfs_set_verifier(new_dentry, nfs_save_change_attribute(new_dir)); diff --git a/fs/nfs/file.c b/fs/nfs/file.c index cec79392e4ba..0abf3f331f56 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -64,11 +64,7 @@ const struct file_operations nfs_file_operations = { .write = do_sync_write, .aio_read = nfs_file_read, .aio_write = nfs_file_write, -#ifdef CONFIG_MMU .mmap = nfs_file_mmap, -#else - .mmap = generic_file_mmap, -#endif .open = nfs_file_open, .flush = nfs_file_flush, .release = nfs_file_release, @@ -141,9 +137,6 @@ nfs_file_release(struct inode *inode, struct file *filp) dentry->d_parent->d_name.name, dentry->d_name.name); - /* Ensure that dirty pages are flushed out with the right creds */ - if (filp->f_mode & FMODE_WRITE) - nfs_wb_all(dentry->d_inode); nfs_inc_stats(inode, NFSIOS_VFSRELEASE); return nfs_release(inode, filp); } @@ -235,7 +228,6 @@ nfs_file_flush(struct file *file, fl_owner_t id) struct nfs_open_context *ctx = nfs_file_open_context(file); struct dentry *dentry = file->f_path.dentry; struct inode *inode = dentry->d_inode; - int status; dprintk("NFS: flush(%s/%s)\n", dentry->d_parent->d_name.name, @@ -245,11 +237,8 @@ nfs_file_flush(struct file *file, fl_owner_t id) return 0; nfs_inc_stats(inode, NFSIOS_VFSFLUSH); - /* Ensure that data+attribute caches are up to date after close() */ - status = nfs_do_fsync(ctx, inode); - if (!status) - nfs_revalidate_inode(NFS_SERVER(inode), inode); - return status; + /* Flush writes to the server and return any errors */ + return nfs_do_fsync(ctx, inode); } static ssize_t @@ -304,11 +293,13 @@ nfs_file_mmap(struct file * file, struct vm_area_struct * vma) dprintk("NFS: mmap(%s/%s)\n", dentry->d_parent->d_name.name, dentry->d_name.name); - status = nfs_revalidate_mapping(inode, file->f_mapping); + /* Note: generic_file_mmap() returns ENOSYS on nommu systems + * so we call that before revalidating the mapping + */ + status = generic_file_mmap(file, vma); if (!status) { vma->vm_ops = &nfs_file_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; - file_accessed(file); + status = nfs_revalidate_mapping(inode, file->f_mapping); } return status; } @@ -354,6 +345,15 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping, file->f_path.dentry->d_name.name, mapping->host->i_ino, len, (long long) pos); + /* + * Prevent starvation issues if someone is doing a consistency + * sync-to-disk + */ + ret = wait_on_bit(&NFS_I(mapping->host)->flags, NFS_INO_FLUSHING, + nfs_wait_bit_killable, TASK_KILLABLE); + if (ret) + return ret; + page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index b7c9b2df1f29..46177cb87064 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -156,7 +156,7 @@ int nfs4_path_walk(struct nfs_server *server, return ret; } - if (fattr.type != NFDIR) { + if (!S_ISDIR(fattr.mode)) { printk(KERN_ERR "nfs4_get_root:" " getroot encountered non-directory\n"); return -ENOTDIR; @@ -213,7 +213,7 @@ eat_dot_dir: return ret; } - if (fattr.type != NFDIR) { + if (!S_ISDIR(fattr.mode)) { printk(KERN_ERR "nfs4_get_root:" " lookupfh encountered non-directory\n"); return -ENOTDIR; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 0c381686171e..a834d1d850b7 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -65,6 +65,18 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr) return nfs_fileid_to_ino_t(fattr->fileid); } +/** + * nfs_wait_bit_killable - helper for functions that are sleeping on bit locks + * @word: long word containing the bit lock + */ +int nfs_wait_bit_killable(void *word) +{ + if (fatal_signal_pending(current)) + return -ERESTARTSYS; + schedule(); + return 0; +} + /** * nfs_compat_user_ino64 - returns the user-visible inode number * @fileid: 64-bit fileid @@ -249,13 +261,10 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) struct inode *inode = ERR_PTR(-ENOENT); unsigned long hash; - if ((fattr->valid & NFS_ATTR_FATTR) == 0) + if ((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0) goto out_no_inode; - - if (!fattr->nlink) { - printk("NFS: Buggy server - nlink == 0!\n"); + if ((fattr->valid & NFS_ATTR_FATTR_TYPE) == 0) goto out_no_inode; - } hash = nfs_fattr_to_ino_t(fattr); @@ -291,7 +300,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) && fattr->size <= NFS_LIMIT_READDIRPLUS) set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags); /* Deal with crossing mountpoints */ - if (!nfs_fsid_equal(&NFS_SB(sb)->fsid, &fattr->fsid)) { + if ((fattr->valid & NFS_ATTR_FATTR_FSID) + && !nfs_fsid_equal(&NFS_SB(sb)->fsid, &fattr->fsid)) { if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) inode->i_op = &nfs_referral_inode_operations; else @@ -304,28 +314,45 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) else init_special_inode(inode, inode->i_mode, fattr->rdev); + memset(&inode->i_atime, 0, sizeof(inode->i_atime)); + memset(&inode->i_mtime, 0, sizeof(inode->i_mtime)); + memset(&inode->i_ctime, 0, sizeof(inode->i_ctime)); + nfsi->change_attr = 0; + inode->i_size = 0; + inode->i_nlink = 0; + inode->i_uid = -2; + inode->i_gid = -2; + inode->i_blocks = 0; + memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf)); + nfsi->read_cache_jiffies = fattr->time_start; nfsi->attr_gencount = fattr->gencount; - inode->i_atime = fattr->atime; - inode->i_mtime = fattr->mtime; - inode->i_ctime = fattr->ctime; - if (fattr->valid & NFS_ATTR_FATTR_V4) + if (fattr->valid & NFS_ATTR_FATTR_ATIME) + inode->i_atime = fattr->atime; + if (fattr->valid & NFS_ATTR_FATTR_MTIME) + inode->i_mtime = fattr->mtime; + if (fattr->valid & NFS_ATTR_FATTR_CTIME) + inode->i_ctime = fattr->ctime; + if (fattr->valid & NFS_ATTR_FATTR_CHANGE) nfsi->change_attr = fattr->change_attr; - inode->i_size = nfs_size_to_loff_t(fattr->size); - inode->i_nlink = fattr->nlink; - inode->i_uid = fattr->uid; - inode->i_gid = fattr->gid; - if (fattr->valid & (NFS_ATTR_FATTR_V3 | NFS_ATTR_FATTR_V4)) { + if (fattr->valid & NFS_ATTR_FATTR_SIZE) + inode->i_size = nfs_size_to_loff_t(fattr->size); + if (fattr->valid & NFS_ATTR_FATTR_NLINK) + inode->i_nlink = fattr->nlink; + if (fattr->valid & NFS_ATTR_FATTR_OWNER) + inode->i_uid = fattr->uid; + if (fattr->valid & NFS_ATTR_FATTR_GROUP) + inode->i_gid = fattr->gid; + if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) + inode->i_blocks = fattr->du.nfs2.blocks; + if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { /* * report the blocks in 512byte units */ inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); - } else { - inode->i_blocks = fattr->du.nfs2.blocks; } nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = now; - memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf)); nfsi->access_cache = RB_ROOT; unlock_new_inode(inode); @@ -514,6 +541,32 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) return err; } +/** + * nfs_close_context - Common close_context() routine NFSv2/v3 + * @ctx: pointer to context + * @is_sync: is this a synchronous close + * + * always ensure that the attributes are up to date if we're mounted + * with close-to-open semantics + */ +void nfs_close_context(struct nfs_open_context *ctx, int is_sync) +{ + struct inode *inode; + struct nfs_server *server; + + if (!(ctx->mode & FMODE_WRITE)) + return; + if (!is_sync) + return; + inode = ctx->path.dentry->d_inode; + if (!list_empty(&NFS_I(inode)->open_files)) + return; + server = NFS_SERVER(inode); + if (server->flags & NFS_MOUNT_NOCTO) + return; + nfs_revalidate_inode(server, inode); +} + static struct nfs_open_context *alloc_nfs_open_context(struct vfsmount *mnt, struct dentry *dentry, struct rpc_cred *cred) { struct nfs_open_context *ctx; @@ -540,24 +593,15 @@ struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx) return ctx; } -static void __put_nfs_open_context(struct nfs_open_context *ctx, int wait) +static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync) { - struct inode *inode; + struct inode *inode = ctx->path.dentry->d_inode; - if (ctx == NULL) - return; - - inode = ctx->path.dentry->d_inode; if (!atomic_dec_and_lock(&ctx->count, &inode->i_lock)) return; list_del(&ctx->list); spin_unlock(&inode->i_lock); - if (ctx->state != NULL) { - if (wait) - nfs4_close_sync(&ctx->path, ctx->state, ctx->mode); - else - nfs4_close_state(&ctx->path, ctx->state, ctx->mode); - } + NFS_PROTO(inode)->close_context(ctx, is_sync); if (ctx->cred != NULL) put_rpccred(ctx->cred); path_put(&ctx->path); @@ -670,9 +714,6 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) if (NFS_STALE(inode)) goto out; - if (NFS_STALE(inode)) - goto out; - nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE); status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), &fattr); if (status != 0) { @@ -815,25 +856,31 @@ static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr) { struct nfs_inode *nfsi = NFS_I(inode); - if ((fattr->valid & NFS_ATTR_WCC_V4) != 0 && - nfsi->change_attr == fattr->pre_change_attr) { + if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE) + && (fattr->valid & NFS_ATTR_FATTR_CHANGE) + && nfsi->change_attr == fattr->pre_change_attr) { nfsi->change_attr = fattr->change_attr; if (S_ISDIR(inode->i_mode)) nfsi->cache_validity |= NFS_INO_INVALID_DATA; } /* If we have atomic WCC data, we may update some attributes */ - if ((fattr->valid & NFS_ATTR_WCC) != 0) { - if (timespec_equal(&inode->i_ctime, &fattr->pre_ctime)) + if ((fattr->valid & NFS_ATTR_FATTR_PRECTIME) + && (fattr->valid & NFS_ATTR_FATTR_CTIME) + && timespec_equal(&inode->i_ctime, &fattr->pre_ctime)) memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime)); - if (timespec_equal(&inode->i_mtime, &fattr->pre_mtime)) { + + if ((fattr->valid & NFS_ATTR_FATTR_PREMTIME) + && (fattr->valid & NFS_ATTR_FATTR_MTIME) + && timespec_equal(&inode->i_mtime, &fattr->pre_mtime)) { memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime)); if (S_ISDIR(inode->i_mode)) nfsi->cache_validity |= NFS_INO_INVALID_DATA; - } - if (i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size) && - nfsi->npages == 0) - i_size_write(inode, nfs_size_to_loff_t(fattr->size)); } + if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE) + && (fattr->valid & NFS_ATTR_FATTR_SIZE) + && i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size) + && nfsi->npages == 0) + i_size_write(inode, nfs_size_to_loff_t(fattr->size)); } /** @@ -853,35 +900,39 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat /* Has the inode gone and changed behind our back? */ - if (nfsi->fileid != fattr->fileid - || (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) { + if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid) + return -EIO; + if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) return -EIO; - } - if ((fattr->valid & NFS_ATTR_FATTR_V4) != 0 && + if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && nfsi->change_attr != fattr->change_attr) invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE; /* Verify a few of the more important attributes */ - if (!timespec_equal(&inode->i_mtime, &fattr->mtime)) + if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec_equal(&inode->i_mtime, &fattr->mtime)) invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE; - cur_size = i_size_read(inode); - new_isize = nfs_size_to_loff_t(fattr->size); - if (cur_size != new_isize && nfsi->npages == 0) - invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE; + if (fattr->valid & NFS_ATTR_FATTR_SIZE) { + cur_size = i_size_read(inode); + new_isize = nfs_size_to_loff_t(fattr->size); + if (cur_size != new_isize && nfsi->npages == 0) + invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE; + } /* Have any file permissions changed? */ - if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO) - || inode->i_uid != fattr->uid - || inode->i_gid != fattr->gid) + if ((fattr->valid & NFS_ATTR_FATTR_MODE) && (inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) + invalid |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL; + if ((fattr->valid & NFS_ATTR_FATTR_OWNER) && inode->i_uid != fattr->uid) + invalid |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL; + if ((fattr->valid & NFS_ATTR_FATTR_GROUP) && inode->i_gid != fattr->gid) invalid |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL; /* Has the link count changed? */ - if (inode->i_nlink != fattr->nlink) + if ((fattr->valid & NFS_ATTR_FATTR_NLINK) && inode->i_nlink != fattr->nlink) invalid |= NFS_INO_INVALID_ATTR; - if (!timespec_equal(&inode->i_atime, &fattr->atime)) + if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec_equal(&inode->i_atime, &fattr->atime)) invalid |= NFS_INO_INVALID_ATIME; if (invalid != 0) @@ -893,11 +944,15 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat static int nfs_ctime_need_update(const struct inode *inode, const struct nfs_fattr *fattr) { + if (!(fattr->valid & NFS_ATTR_FATTR_CTIME)) + return 0; return timespec_compare(&fattr->ctime, &inode->i_ctime) > 0; } static int nfs_size_need_update(const struct inode *inode, const struct nfs_fattr *fattr) { + if (!(fattr->valid & NFS_ATTR_FATTR_SIZE)) + return 0; return nfs_size_to_loff_t(fattr->size) > i_size_read(inode); } @@ -1033,20 +1088,31 @@ int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fa /* Don't do a WCC update if these attributes are already stale */ if ((fattr->valid & NFS_ATTR_FATTR) == 0 || !nfs_inode_attrs_need_update(inode, fattr)) { - fattr->valid &= ~(NFS_ATTR_WCC_V4|NFS_ATTR_WCC); + fattr->valid &= ~(NFS_ATTR_FATTR_PRECHANGE + | NFS_ATTR_FATTR_PRESIZE + | NFS_ATTR_FATTR_PREMTIME + | NFS_ATTR_FATTR_PRECTIME); goto out_noforce; } - if ((fattr->valid & NFS_ATTR_FATTR_V4) != 0 && - (fattr->valid & NFS_ATTR_WCC_V4) == 0) { + if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && + (fattr->valid & NFS_ATTR_FATTR_PRECHANGE) == 0) { fattr->pre_change_attr = NFS_I(inode)->change_attr; - fattr->valid |= NFS_ATTR_WCC_V4; + fattr->valid |= NFS_ATTR_FATTR_PRECHANGE; } - if ((fattr->valid & NFS_ATTR_FATTR) != 0 && - (fattr->valid & NFS_ATTR_WCC) == 0) { + if ((fattr->valid & NFS_ATTR_FATTR_CTIME) != 0 && + (fattr->valid & NFS_ATTR_FATTR_PRECTIME) == 0) { memcpy(&fattr->pre_ctime, &inode->i_ctime, sizeof(fattr->pre_ctime)); + fattr->valid |= NFS_ATTR_FATTR_PRECTIME; + } + if ((fattr->valid & NFS_ATTR_FATTR_MTIME) != 0 && + (fattr->valid & NFS_ATTR_FATTR_PREMTIME) == 0) { memcpy(&fattr->pre_mtime, &inode->i_mtime, sizeof(fattr->pre_mtime)); + fattr->valid |= NFS_ATTR_FATTR_PREMTIME; + } + if ((fattr->valid & NFS_ATTR_FATTR_SIZE) != 0 && + (fattr->valid & NFS_ATTR_FATTR_PRESIZE) == 0) { fattr->pre_size = i_size_read(inode); - fattr->valid |= NFS_ATTR_WCC; + fattr->valid |= NFS_ATTR_FATTR_PRESIZE; } out_noforce: status = nfs_post_op_update_inode_locked(inode, fattr); @@ -1078,18 +1144,18 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) __func__, inode->i_sb->s_id, inode->i_ino, atomic_read(&inode->i_count), fattr->valid); - if (nfsi->fileid != fattr->fileid) + if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid) goto out_fileid; /* * Make sure the inode's type hasn't changed. */ - if ((inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) + if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) goto out_changed; server = NFS_SERVER(inode); /* Update the fsid? */ - if (S_ISDIR(inode->i_mode) && + if (S_ISDIR(inode->i_mode) && (fattr->valid & NFS_ATTR_FATTR_FSID) && !nfs_fsid_equal(&server->fsid, &fattr->fsid) && !test_bit(NFS_INO_MOUNTPOINT, &nfsi->flags)) server->fsid = fattr->fsid; @@ -1099,14 +1165,27 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) */ nfsi->read_cache_jiffies = fattr->time_start; - nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ATIME - | NFS_INO_REVAL_PAGECACHE); + 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); /* Do atomic weak cache consistency updates */ nfs_wcc_update_inode(inode, fattr); /* More cache consistency checks */ - if (!(fattr->valid & NFS_ATTR_FATTR_V4)) { + if (fattr->valid & NFS_ATTR_FATTR_CHANGE) { + if (nfsi->change_attr != fattr->change_attr) { + dprintk("NFS: change_attr change on server for file %s/%ld\n", + inode->i_sb->s_id, inode->i_ino); + invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; + if (S_ISDIR(inode->i_mode)) + nfs_force_lookup_revalidate(inode); + nfsi->change_attr = fattr->change_attr; + } + } + + if (fattr->valid & NFS_ATTR_FATTR_MTIME) { /* NFSv2/v3: Check if the mtime agrees */ if (!timespec_equal(&inode->i_mtime, &fattr->mtime)) { dprintk("NFS: mtime change on server for file %s/%ld\n", @@ -1114,59 +1193,80 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA; if (S_ISDIR(inode->i_mode)) nfs_force_lookup_revalidate(inode); + memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime)); } + } + 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)) + if (!timespec_equal(&inode->i_ctime, &fattr->ctime)) { invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; - } else if (nfsi->change_attr != fattr->change_attr) { - dprintk("NFS: change_attr change on server for file %s/%ld\n", - inode->i_sb->s_id, inode->i_ino); - invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; - if (S_ISDIR(inode->i_mode)) - nfs_force_lookup_revalidate(inode); + /* and probably clear data for a directory too as utimes can cause + * havoc with our cache. + */ + if (S_ISDIR(inode->i_mode)) { + invalid |= NFS_INO_INVALID_DATA; + nfs_force_lookup_revalidate(inode); + } + memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime)); + } } /* Check if our cached file size is stale */ - new_isize = nfs_size_to_loff_t(fattr->size); - cur_isize = i_size_read(inode); - if (new_isize != cur_isize) { - /* Do we perhaps have any outstanding writes, or has - * the file grown beyond our last write? */ - if (nfsi->npages == 0 || new_isize > cur_isize) { - i_size_write(inode, new_isize); - invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA; + if (fattr->valid & NFS_ATTR_FATTR_SIZE) { + new_isize = nfs_size_to_loff_t(fattr->size); + cur_isize = i_size_read(inode); + if (new_isize != cur_isize) { + /* Do we perhaps have any outstanding writes, or has + * the file grown beyond our last write? */ + if (nfsi->npages == 0 || new_isize > cur_isize) { + i_size_write(inode, new_isize); + invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA; + } + dprintk("NFS: isize change on server for file %s/%ld\n", + inode->i_sb->s_id, inode->i_ino); } - dprintk("NFS: isize change on server for file %s/%ld\n", - inode->i_sb->s_id, inode->i_ino); } - memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime)); - memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime)); - memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime)); - nfsi->change_attr = fattr->change_attr; + if (fattr->valid & NFS_ATTR_FATTR_ATIME) + memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime)); - if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO) || - inode->i_uid != fattr->uid || - inode->i_gid != fattr->gid) - invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; + 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; + } + } + 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; + } + } + 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; + } + } - if (inode->i_nlink != fattr->nlink) - invalid |= NFS_INO_INVALID_ATTR; + if (fattr->valid & NFS_ATTR_FATTR_NLINK) { + if (inode->i_nlink != fattr->nlink) { + invalid |= NFS_INO_INVALID_ATTR; + if (S_ISDIR(inode->i_mode)) + invalid |= NFS_INO_INVALID_DATA; + inode->i_nlink = fattr->nlink; + } + } - inode->i_mode = fattr->mode; - inode->i_nlink = fattr->nlink; - inode->i_uid = fattr->uid; - inode->i_gid = fattr->gid; - - if (fattr->valid & (NFS_ATTR_FATTR_V3 | NFS_ATTR_FATTR_V4)) { + if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { /* * report the blocks in 512byte units */ inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); - } else { - inode->i_blocks = fattr->du.nfs2.blocks; } + if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) + inode->i_blocks = fattr->du.nfs2.blocks; /* Update attrtimeo value if we're out of the unstable period */ if (invalid & NFS_INO_INVALID_ATTR) { @@ -1274,7 +1374,6 @@ static void init_once(void *foo) INIT_LIST_HEAD(&nfsi->access_cache_entry_lru); INIT_LIST_HEAD(&nfsi->access_cache_inode_lru); INIT_RADIX_TREE(&nfsi->nfs_page_tree, GFP_ATOMIC); - nfsi->ncommit = 0; nfsi->npages = 0; atomic_set(&nfsi->silly_count, 1); INIT_HLIST_HEAD(&nfsi->silly_list); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 340ede8f608f..2041f68ff1cc 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -152,6 +152,9 @@ extern __be32 *nfs4_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus); extern struct rpc_procinfo nfs4_procedures[]; #endif +/* proc.c */ +void nfs_close_context(struct nfs_open_context *ctx, int is_sync); + /* dir.c */ extern int nfs_access_cache_shrinker(int nr_to_scan, gfp_t gfp_mask); @@ -165,6 +168,7 @@ extern void nfs_clear_inode(struct inode *); extern void nfs4_clear_inode(struct inode *); #endif 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 *); diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index 28bab67d1519..c862c9340f9a 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -120,8 +120,8 @@ xdr_decode_time(__be32 *p, struct timespec *timep) static __be32 * xdr_decode_fattr(__be32 *p, struct nfs_fattr *fattr) { - u32 rdev; - fattr->type = (enum nfs_ftype) ntohl(*p++); + u32 rdev, type; + type = ntohl(*p++); fattr->mode = ntohl(*p++); fattr->nlink = ntohl(*p++); fattr->uid = ntohl(*p++); @@ -136,10 +136,9 @@ xdr_decode_fattr(__be32 *p, struct nfs_fattr *fattr) p = xdr_decode_time(p, &fattr->atime); p = xdr_decode_time(p, &fattr->mtime); p = xdr_decode_time(p, &fattr->ctime); - fattr->valid |= NFS_ATTR_FATTR; + fattr->valid |= NFS_ATTR_FATTR_V2; fattr->rdev = new_decode_dev(rdev); - if (fattr->type == NFCHR && rdev == NFS2_FIFO_DEV) { - fattr->type = NFFIFO; + if (type == NFCHR && rdev == NFS2_FIFO_DEV) { fattr->mode = (fattr->mode & ~S_IFMT) | S_IFIFO; fattr->rdev = 0; } diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index c55be7a7679e..b82fe6847f14 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -834,4 +834,5 @@ const struct nfs_rpc_ops nfs_v3_clientops = { .commit_done = nfs3_commit_done, .lock = nfs3_proc_lock, .clear_acl_cache = nfs3_forget_cached_acls, + .close_context = nfs_close_context, }; diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 6cdeacffde46..e6a1932c7110 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -91,19 +91,15 @@ /* * Map file type to S_IFMT bits */ -static struct { - unsigned int mode; - unsigned int nfs2type; -} nfs_type2fmt[] = { - { 0, NFNON }, - { S_IFREG, NFREG }, - { S_IFDIR, NFDIR }, - { S_IFBLK, NFBLK }, - { S_IFCHR, NFCHR }, - { S_IFLNK, NFLNK }, - { S_IFSOCK, NFSOCK }, - { S_IFIFO, NFFIFO }, - { 0, NFBAD } +static const umode_t nfs_type2fmt[] = { + [NF3BAD] = 0, + [NF3REG] = S_IFREG, + [NF3DIR] = S_IFDIR, + [NF3BLK] = S_IFBLK, + [NF3CHR] = S_IFCHR, + [NF3LNK] = S_IFLNK, + [NF3SOCK] = S_IFSOCK, + [NF3FIFO] = S_IFIFO, }; /* @@ -148,13 +144,12 @@ static __be32 * xdr_decode_fattr(__be32 *p, struct nfs_fattr *fattr) { unsigned int type, major, minor; - int fmode; + umode_t fmode; type = ntohl(*p++); - if (type >= NF3BAD) - type = NF3BAD; - fmode = nfs_type2fmt[type].mode; - fattr->type = nfs_type2fmt[type].nfs2type; + if (type > NF3FIFO) + type = NF3NON; + fmode = nfs_type2fmt[type]; fattr->mode = (ntohl(*p++) & ~S_IFMT) | fmode; fattr->nlink = ntohl(*p++); fattr->uid = ntohl(*p++); @@ -177,7 +172,7 @@ xdr_decode_fattr(__be32 *p, struct nfs_fattr *fattr) p = xdr_decode_time3(p, &fattr->ctime); /* Update the mode bits */ - fattr->valid |= (NFS_ATTR_FATTR | NFS_ATTR_FATTR_V3); + fattr->valid |= NFS_ATTR_FATTR_V3; return p; } @@ -233,7 +228,9 @@ xdr_decode_wcc_attr(__be32 *p, struct nfs_fattr *fattr) p = xdr_decode_hyper(p, &fattr->pre_size); p = xdr_decode_time3(p, &fattr->pre_mtime); p = xdr_decode_time3(p, &fattr->pre_ctime); - fattr->valid |= NFS_ATTR_WCC; + fattr->valid |= NFS_ATTR_FATTR_PRESIZE + | NFS_ATTR_FATTR_PREMTIME + | NFS_ATTR_FATTR_PRECTIME; return p; } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 8dde84b988d9..97bacccff579 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -193,14 +193,6 @@ static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dent kunmap_atomic(start, KM_USER0); } -static int nfs4_wait_bit_killable(void *word) -{ - if (fatal_signal_pending(current)) - return -ERESTARTSYS; - schedule(); - return 0; -} - static int nfs4_wait_clnt_recover(struct nfs_client *clp) { int res; @@ -208,7 +200,7 @@ static int nfs4_wait_clnt_recover(struct nfs_client *clp) might_sleep(); res = wait_on_bit(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING, - nfs4_wait_bit_killable, TASK_KILLABLE); + nfs_wait_bit_killable, TASK_KILLABLE); return res; } @@ -1439,7 +1431,7 @@ int nfs4_do_close(struct path *path, struct nfs4_state *state, int wait) if (calldata->arg.seqid == NULL) goto out_free_calldata; calldata->arg.fmode = 0; - calldata->arg.bitmask = server->attr_bitmask; + calldata->arg.bitmask = server->cache_consistency_bitmask; calldata->res.fattr = &calldata->fattr; calldata->res.seqid = calldata->arg.seqid; calldata->res.server = server; @@ -1580,6 +1572,15 @@ out_drop: return 0; } +void nfs4_close_context(struct nfs_open_context *ctx, int is_sync) +{ + if (ctx->state == NULL) + return; + if (is_sync) + nfs4_close_sync(&ctx->path, ctx->state, ctx->mode); + else + nfs4_close_state(&ctx->path, ctx->state, ctx->mode); +} static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle) { @@ -1600,6 +1601,9 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f server->caps |= NFS_CAP_HARDLINKS; if (res.has_symlinks != 0) server->caps |= NFS_CAP_SYMLINKS; + 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; server->acl_bitmask = res.acl_bitmask; } return status; @@ -2079,7 +2083,7 @@ static void nfs4_proc_unlink_setup(struct rpc_message *msg, struct inode *dir) struct nfs_removeargs *args = msg->rpc_argp; struct nfs_removeres *res = msg->rpc_resp; - args->bitmask = server->attr_bitmask; + args->bitmask = server->cache_consistency_bitmask; res->server = server; msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_REMOVE]; } @@ -2323,7 +2327,7 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, .pages = &page, .pgbase = 0, .count = count, - .bitmask = NFS_SERVER(dentry->d_inode)->attr_bitmask, + .bitmask = NFS_SERVER(dentry->d_inode)->cache_consistency_bitmask, }; struct nfs4_readdir_res res; struct rpc_message msg = { @@ -2552,7 +2556,7 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag { struct nfs_server *server = NFS_SERVER(data->inode); - data->args.bitmask = server->attr_bitmask; + data->args.bitmask = server->cache_consistency_bitmask; data->res.server = server; data->timestamp = jiffies; @@ -2575,7 +2579,7 @@ static void nfs4_proc_commit_setup(struct nfs_write_data *data, struct rpc_messa { struct nfs_server *server = NFS_SERVER(data->inode); - data->args.bitmask = server->attr_bitmask; + data->args.bitmask = server->cache_consistency_bitmask; data->res.server = server; msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COMMIT]; } @@ -3678,6 +3682,19 @@ ssize_t nfs4_listxattr(struct dentry *dentry, char *buf, size_t buflen) return len; } +static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr) +{ + if (!((fattr->valid & NFS_ATTR_FATTR_FILEID) && + (fattr->valid & NFS_ATTR_FATTR_FSID) && + (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL))) + return; + + fattr->valid |= NFS_ATTR_FATTR_TYPE | NFS_ATTR_FATTR_MODE | + NFS_ATTR_FATTR_NLINK; + fattr->mode = S_IFDIR | S_IRUGO | S_IXUGO; + fattr->nlink = 2; +} + int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name, struct nfs4_fs_locations *fs_locations, struct page *page) { @@ -3704,6 +3721,7 @@ int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name, fs_locations->server = server; fs_locations->nlocations = 0; status = rpc_call_sync(server->client, &msg, 0); + nfs_fixup_referral_attributes(&fs_locations->fattr); dprintk("%s: returned status = %d\n", __func__, status); return status; } @@ -3767,6 +3785,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .commit_done = nfs4_commit_done, .lock = nfs4_proc_lock, .clear_acl_cache = nfs4_zap_acl_attr, + .close_context = nfs4_close_context, }; /* diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 2022fe47966f..0298e909559f 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -62,8 +62,14 @@ static LIST_HEAD(nfs4_clientid_list); static int nfs4_init_client(struct nfs_client *clp, struct rpc_cred *cred) { - int status = nfs4_proc_setclientid(clp, NFS4_CALLBACK, - nfs_callback_tcpport, cred); + unsigned short port; + int status; + + port = nfs_callback_tcpport; + if (clp->cl_addr.ss_family == AF_INET6) + port = nfs_callback_tcpport6; + + status = nfs4_proc_setclientid(clp, NFS4_CALLBACK, port, cred); if (status == 0) status = nfs4_proc_setclientid_confirm(clp, cred); if (status == 0) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index d1e4c8f8a0a9..1690f0e44b91 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -522,20 +522,17 @@ static int nfs4_stat_to_errno(int); decode_lookup_maxsz + \ decode_fs_locations_maxsz) -static struct { - unsigned int mode; - unsigned int nfs2type; -} nfs_type2fmt[] = { - { 0, NFNON }, - { S_IFREG, NFREG }, - { S_IFDIR, NFDIR }, - { S_IFBLK, NFBLK }, - { S_IFCHR, NFCHR }, - { S_IFLNK, NFLNK }, - { S_IFSOCK, NFSOCK }, - { S_IFIFO, NFFIFO }, - { 0, NFNON }, - { 0, NFNON }, +static const umode_t nfs_type2fmt[] = { + [NF4BAD] = 0, + [NF4REG] = S_IFREG, + [NF4DIR] = S_IFDIR, + [NF4BLK] = S_IFBLK, + [NF4CHR] = S_IFCHR, + [NF4LNK] = S_IFLNK, + [NF4SOCK] = S_IFSOCK, + [NF4FIFO] = S_IFIFO, + [NF4ATTRDIR] = 0, + [NF4NAMEDATTR] = 0, }; struct compound_hdr { @@ -2160,6 +2157,7 @@ static int decode_attr_supported(struct xdr_stream *xdr, uint32_t *bitmap, uint3 static int decode_attr_type(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *type) { __be32 *p; + int ret = 0; *type = 0; if (unlikely(bitmap[0] & (FATTR4_WORD0_TYPE - 1U))) @@ -2172,14 +2170,16 @@ static int decode_attr_type(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t * return -EIO; } bitmap[0] &= ~FATTR4_WORD0_TYPE; + ret = NFS_ATTR_FATTR_TYPE; } - dprintk("%s: type=0%o\n", __func__, nfs_type2fmt[*type].nfs2type); - return 0; + dprintk("%s: type=0%o\n", __func__, nfs_type2fmt[*type]); + return ret; } static int decode_attr_change(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *change) { __be32 *p; + int ret = 0; *change = 0; if (unlikely(bitmap[0] & (FATTR4_WORD0_CHANGE - 1U))) @@ -2188,15 +2188,17 @@ static int decode_attr_change(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t READ_BUF(8); READ64(*change); bitmap[0] &= ~FATTR4_WORD0_CHANGE; + ret = NFS_ATTR_FATTR_CHANGE; } dprintk("%s: change attribute=%Lu\n", __func__, (unsigned long long)*change); - return 0; + return ret; } static int decode_attr_size(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *size) { __be32 *p; + int ret = 0; *size = 0; if (unlikely(bitmap[0] & (FATTR4_WORD0_SIZE - 1U))) @@ -2205,9 +2207,10 @@ static int decode_attr_size(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t * READ_BUF(8); READ64(*size); bitmap[0] &= ~FATTR4_WORD0_SIZE; + ret = NFS_ATTR_FATTR_SIZE; } dprintk("%s: file size=%Lu\n", __func__, (unsigned long long)*size); - return 0; + return ret; } static int decode_attr_link_support(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) @@ -2245,6 +2248,7 @@ static int decode_attr_symlink_support(struct xdr_stream *xdr, uint32_t *bitmap, static int decode_attr_fsid(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_fsid *fsid) { __be32 *p; + int ret = 0; fsid->major = 0; fsid->minor = 0; @@ -2255,11 +2259,12 @@ static int decode_attr_fsid(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs READ64(fsid->major); READ64(fsid->minor); bitmap[0] &= ~FATTR4_WORD0_FSID; + ret = NFS_ATTR_FATTR_FSID; } dprintk("%s: fsid=(0x%Lx/0x%Lx)\n", __func__, (unsigned long long)fsid->major, (unsigned long long)fsid->minor); - return 0; + return ret; } static int decode_attr_lease_time(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) @@ -2297,6 +2302,7 @@ static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint static int decode_attr_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *fileid) { __be32 *p; + int ret = 0; *fileid = 0; if (unlikely(bitmap[0] & (FATTR4_WORD0_FILEID - 1U))) @@ -2305,14 +2311,16 @@ static int decode_attr_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t READ_BUF(8); READ64(*fileid); bitmap[0] &= ~FATTR4_WORD0_FILEID; + ret = NFS_ATTR_FATTR_FILEID; } dprintk("%s: fileid=%Lu\n", __func__, (unsigned long long)*fileid); - return 0; + return ret; } static int decode_attr_mounted_on_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *fileid) { __be32 *p; + int ret = 0; *fileid = 0; if (unlikely(bitmap[1] & (FATTR4_WORD1_MOUNTED_ON_FILEID - 1U))) @@ -2321,9 +2329,10 @@ static int decode_attr_mounted_on_fileid(struct xdr_stream *xdr, uint32_t *bitma READ_BUF(8); READ64(*fileid); bitmap[1] &= ~FATTR4_WORD1_MOUNTED_ON_FILEID; + ret = NFS_ATTR_FATTR_FILEID; } dprintk("%s: fileid=%Lu\n", __func__, (unsigned long long)*fileid); - return 0; + return ret; } static int decode_attr_files_avail(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) @@ -2479,6 +2488,8 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st if (res->nlocations < NFS4_FS_LOCATIONS_MAXENTRIES) res->nlocations++; } + if (res->nlocations != 0) + status = NFS_ATTR_FATTR_V4_REFERRAL; out: dprintk("%s: fs_locations done, error = %d\n", __func__, status); return status; @@ -2580,26 +2591,30 @@ static int decode_attr_maxwrite(struct xdr_stream *xdr, uint32_t *bitmap, uint32 return status; } -static int decode_attr_mode(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *mode) +static int decode_attr_mode(struct xdr_stream *xdr, uint32_t *bitmap, umode_t *mode) { + uint32_t tmp; __be32 *p; + int ret = 0; *mode = 0; if (unlikely(bitmap[1] & (FATTR4_WORD1_MODE - 1U))) return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_MODE)) { READ_BUF(4); - READ32(*mode); - *mode &= ~S_IFMT; + READ32(tmp); + *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 0; + return ret; } static int decode_attr_nlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *nlink) { __be32 *p; + int ret = 0; *nlink = 1; if (unlikely(bitmap[1] & (FATTR4_WORD1_NUMLINKS - 1U))) @@ -2608,15 +2623,17 @@ static int decode_attr_nlink(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t READ_BUF(4); READ32(*nlink); bitmap[1] &= ~FATTR4_WORD1_NUMLINKS; + ret = NFS_ATTR_FATTR_NLINK; } dprintk("%s: nlink=%u\n", __func__, (unsigned int)*nlink); - return 0; + return ret; } static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_client *clp, uint32_t *uid) { uint32_t len; __be32 *p; + int ret = 0; *uid = -2; if (unlikely(bitmap[1] & (FATTR4_WORD1_OWNER - 1U))) @@ -2626,7 +2643,9 @@ static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nf READ32(len); READ_BUF(len); if (len < XDR_MAX_NETOBJ) { - if (nfs_map_name_to_uid(clp, (char *)p, len, uid) != 0) + if (nfs_map_name_to_uid(clp, (char *)p, len, uid) == 0) + ret = NFS_ATTR_FATTR_OWNER; + else dprintk("%s: nfs_map_name_to_uid failed!\n", __func__); } else @@ -2635,13 +2654,14 @@ static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap, struct nf bitmap[1] &= ~FATTR4_WORD1_OWNER; } dprintk("%s: uid=%d\n", __func__, (int)*uid); - return 0; + return ret; } static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_client *clp, uint32_t *gid) { uint32_t len; __be32 *p; + int ret = 0; *gid = -2; if (unlikely(bitmap[1] & (FATTR4_WORD1_OWNER_GROUP - 1U))) @@ -2651,7 +2671,9 @@ static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nf READ32(len); READ_BUF(len); if (len < XDR_MAX_NETOBJ) { - if (nfs_map_group_to_gid(clp, (char *)p, len, gid) != 0) + if (nfs_map_group_to_gid(clp, (char *)p, len, gid) == 0) + ret = NFS_ATTR_FATTR_GROUP; + else dprintk("%s: nfs_map_group_to_gid failed!\n", __func__); } else @@ -2660,13 +2682,14 @@ static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap, struct nf bitmap[1] &= ~FATTR4_WORD1_OWNER_GROUP; } dprintk("%s: gid=%d\n", __func__, (int)*gid); - return 0; + return ret; } static int decode_attr_rdev(struct xdr_stream *xdr, uint32_t *bitmap, dev_t *rdev) { uint32_t major = 0, minor = 0; __be32 *p; + int ret = 0; *rdev = MKDEV(0,0); if (unlikely(bitmap[1] & (FATTR4_WORD1_RAWDEV - 1U))) @@ -2681,9 +2704,10 @@ static int decode_attr_rdev(struct xdr_stream *xdr, uint32_t *bitmap, dev_t *rde if (MAJOR(tmp) == major && MINOR(tmp) == minor) *rdev = tmp; bitmap[1] &= ~ FATTR4_WORD1_RAWDEV; + ret = NFS_ATTR_FATTR_RDEV; } dprintk("%s: rdev=(0x%x:0x%x)\n", __func__, major, minor); - return 0; + return ret; } static int decode_attr_space_avail(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) @@ -2740,6 +2764,7 @@ static int decode_attr_space_total(struct xdr_stream *xdr, uint32_t *bitmap, uin static int decode_attr_space_used(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *used) { __be32 *p; + int ret = 0; *used = 0; if (unlikely(bitmap[1] & (FATTR4_WORD1_SPACE_USED - 1U))) @@ -2748,10 +2773,11 @@ static int decode_attr_space_used(struct xdr_stream *xdr, uint32_t *bitmap, uint READ_BUF(8); READ64(*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 0; + return ret; } static int decode_attr_time(struct xdr_stream *xdr, struct timespec *time) @@ -2778,6 +2804,8 @@ static int decode_attr_time_access(struct xdr_stream *xdr, uint32_t *bitmap, str return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_TIME_ACCESS)) { status = decode_attr_time(xdr, time); + if (status == 0) + status = NFS_ATTR_FATTR_ATIME; bitmap[1] &= ~FATTR4_WORD1_TIME_ACCESS; } dprintk("%s: atime=%ld\n", __func__, (long)time->tv_sec); @@ -2794,6 +2822,8 @@ static int decode_attr_time_metadata(struct xdr_stream *xdr, uint32_t *bitmap, s return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_TIME_METADATA)) { status = decode_attr_time(xdr, time); + if (status == 0) + status = NFS_ATTR_FATTR_CTIME; bitmap[1] &= ~FATTR4_WORD1_TIME_METADATA; } dprintk("%s: ctime=%ld\n", __func__, (long)time->tv_sec); @@ -2810,6 +2840,8 @@ static int decode_attr_time_modify(struct xdr_stream *xdr, uint32_t *bitmap, str return -EIO; if (likely(bitmap[1] & FATTR4_WORD1_TIME_MODIFY)) { status = decode_attr_time(xdr, time); + if (status == 0) + status = NFS_ATTR_FATTR_MTIME; bitmap[1] &= ~FATTR4_WORD1_TIME_MODIFY; } dprintk("%s: mtime=%ld\n", __func__, (long)time->tv_sec); @@ -2994,63 +3026,116 @@ static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, cons uint32_t attrlen, bitmap[2] = {0}, type; - int status, fmode = 0; + int status; + umode_t fmode = 0; uint64_t fileid; - if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0) - goto xdr_error; - if ((status = decode_attr_bitmap(xdr, bitmap)) != 0) + status = decode_op_hdr(xdr, OP_GETATTR); + if (status < 0) goto xdr_error; - fattr->bitmap[0] = bitmap[0]; - fattr->bitmap[1] = bitmap[1]; + status = decode_attr_bitmap(xdr, bitmap); + if (status < 0) + goto xdr_error; - if ((status = decode_attr_length(xdr, &attrlen, &savep)) != 0) + status = decode_attr_length(xdr, &attrlen, &savep); + if (status < 0) goto xdr_error; - if ((status = decode_attr_type(xdr, bitmap, &type)) != 0) + status = decode_attr_type(xdr, bitmap, &type); + if (status < 0) goto xdr_error; - fattr->type = nfs_type2fmt[type].nfs2type; - fmode = nfs_type2fmt[type].mode; + fattr->mode = 0; + if (status != 0) { + fattr->mode |= nfs_type2fmt[type]; + fattr->valid |= status; + } - if ((status = decode_attr_change(xdr, bitmap, &fattr->change_attr)) != 0) + status = decode_attr_change(xdr, bitmap, &fattr->change_attr); + if (status < 0) goto xdr_error; - if ((status = decode_attr_size(xdr, bitmap, &fattr->size)) != 0) + fattr->valid |= status; + + status = decode_attr_size(xdr, bitmap, &fattr->size); + if (status < 0) goto xdr_error; - if ((status = decode_attr_fsid(xdr, bitmap, &fattr->fsid)) != 0) + fattr->valid |= status; + + status = decode_attr_fsid(xdr, bitmap, &fattr->fsid); + if (status < 0) goto xdr_error; - if ((status = decode_attr_fileid(xdr, bitmap, &fattr->fileid)) != 0) + fattr->valid |= status; + + status = decode_attr_fileid(xdr, bitmap, &fattr->fileid); + if (status < 0) goto xdr_error; - if ((status = decode_attr_fs_locations(xdr, bitmap, container_of(fattr, + fattr->valid |= status; + + status = decode_attr_fs_locations(xdr, bitmap, container_of(fattr, struct nfs4_fs_locations, - fattr))) != 0) + fattr)); + if (status < 0) goto xdr_error; - if ((status = decode_attr_mode(xdr, bitmap, &fattr->mode)) != 0) + fattr->valid |= status; + + status = decode_attr_mode(xdr, bitmap, &fmode); + if (status < 0) goto xdr_error; - fattr->mode |= fmode; - if ((status = decode_attr_nlink(xdr, bitmap, &fattr->nlink)) != 0) + if (status != 0) { + fattr->mode |= fmode; + fattr->valid |= status; + } + + status = decode_attr_nlink(xdr, bitmap, &fattr->nlink); + if (status < 0) goto xdr_error; - if ((status = decode_attr_owner(xdr, bitmap, server->nfs_client, &fattr->uid)) != 0) + fattr->valid |= status; + + status = decode_attr_owner(xdr, bitmap, server->nfs_client, &fattr->uid); + if (status < 0) goto xdr_error; - if ((status = decode_attr_group(xdr, bitmap, server->nfs_client, &fattr->gid)) != 0) + fattr->valid |= status; + + status = decode_attr_group(xdr, bitmap, server->nfs_client, &fattr->gid); + if (status < 0) goto xdr_error; - if ((status = decode_attr_rdev(xdr, bitmap, &fattr->rdev)) != 0) + fattr->valid |= status; + + status = decode_attr_rdev(xdr, bitmap, &fattr->rdev); + if (status < 0) goto xdr_error; - if ((status = decode_attr_space_used(xdr, bitmap, &fattr->du.nfs3.used)) != 0) + fattr->valid |= status; + + status = decode_attr_space_used(xdr, bitmap, &fattr->du.nfs3.used); + if (status < 0) goto xdr_error; - if ((status = decode_attr_time_access(xdr, bitmap, &fattr->atime)) != 0) + fattr->valid |= status; + + status = decode_attr_time_access(xdr, bitmap, &fattr->atime); + if (status < 0) goto xdr_error; - if ((status = decode_attr_time_metadata(xdr, bitmap, &fattr->ctime)) != 0) + fattr->valid |= status; + + status = decode_attr_time_metadata(xdr, bitmap, &fattr->ctime); + if (status < 0) goto xdr_error; - if ((status = decode_attr_time_modify(xdr, bitmap, &fattr->mtime)) != 0) + fattr->valid |= status; + + status = decode_attr_time_modify(xdr, bitmap, &fattr->mtime); + if (status < 0) goto xdr_error; - if ((status = decode_attr_mounted_on_fileid(xdr, bitmap, &fileid)) != 0) + fattr->valid |= status; + + status = decode_attr_mounted_on_fileid(xdr, bitmap, &fileid); + if (status < 0) goto xdr_error; - if (fattr->fileid == 0 && fileid != 0) + if (status != 0 && !(fattr->valid & status)) { fattr->fileid = fileid; - if ((status = verify_attr_len(xdr, savep, attrlen)) == 0) - fattr->valid = NFS_ATTR_FATTR | NFS_ATTR_FATTR_V3 | NFS_ATTR_FATTR_V4; + fattr->valid |= status; + } + + status = verify_attr_len(xdr, savep, attrlen); xdr_error: dprintk("%s: xdr returned %d\n", __func__, -status); return status; @@ -4078,9 +4163,7 @@ static int nfs4_xdr_dec_setattr(struct rpc_rqst *rqstp, __be32 *p, struct nfs_se status = decode_setattr(&xdr, res); if (status) goto out; - status = decode_getfattr(&xdr, res->fattr, res->server); - if (status == NFS4ERR_DELAY) - status = 0; + decode_getfattr(&xdr, res->fattr, res->server); out: return status; } diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 7f079209d70a..e2975939126a 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -176,17 +176,6 @@ void nfs_release_request(struct nfs_page *req) kref_put(&req->wb_kref, nfs_free_request); } -static int nfs_wait_bit_killable(void *word) -{ - int ret = 0; - - if (fatal_signal_pending(current)) - ret = -ERESTARTSYS; - else - schedule(); - return ret; -} - /** * nfs_wait_on_request - Wait for a request to complete. * @req: request to wait upon. diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index 193465210d7c..7be72d90d49d 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -663,4 +663,5 @@ const struct nfs_rpc_ops nfs_v2_clientops = { .commit_setup = nfs_proc_commit_setup, .lock = nfs_proc_lock, .lock_check_bounds = nfs_lock_check_bounds, + .close_context = nfs_close_context, }; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index d6686f4786dc..0942fcbbad3c 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1018,6 +1018,7 @@ static int nfs_parse_mount_options(char *raw, case Opt_rdma: mnt->flags |= NFS_MOUNT_TCP; /* for side protocols */ mnt->nfs_server.protocol = XPRT_TRANSPORT_RDMA; + xprt_load_transport(p); break; case Opt_acl: mnt->flags &= ~NFS_MOUNT_NOACL; @@ -1205,12 +1206,14 @@ static int nfs_parse_mount_options(char *raw, /* vector side protocols to TCP */ mnt->flags |= NFS_MOUNT_TCP; mnt->nfs_server.protocol = XPRT_TRANSPORT_RDMA; + xprt_load_transport(string); break; default: errors++; dfprintk(MOUNT, "NFS: unrecognized " "transport protocol\n"); } + kfree(string); break; case Opt_mountproto: string = match_strdup(args); @@ -1218,7 +1221,6 @@ static int nfs_parse_mount_options(char *raw, goto out_nomem; token = match_token(string, nfs_xprt_protocol_tokens, args); - kfree(string); switch (token) { case Opt_xprt_udp: diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 9f9845859fc1..e560a78995a3 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -313,19 +313,34 @@ static int nfs_writepages_callback(struct page *page, struct writeback_control * int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct inode *inode = mapping->host; + unsigned long *bitlock = &NFS_I(inode)->flags; struct nfs_pageio_descriptor pgio; int err; + /* Stop dirtying of new pages while we sync */ + err = wait_on_bit_lock(bitlock, NFS_INO_FLUSHING, + nfs_wait_bit_killable, TASK_KILLABLE); + if (err) + goto out_err; + nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES); nfs_pageio_init_write(&pgio, inode, wb_priority(wbc)); err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio); nfs_pageio_complete(&pgio); + + clear_bit_unlock(NFS_INO_FLUSHING, bitlock); + smp_mb__after_clear_bit(); + wake_up_bit(bitlock, NFS_INO_FLUSHING); + if (err < 0) - return err; - if (pgio.pg_error < 0) - return pgio.pg_error; + goto out_err; + err = pgio.pg_error; + if (err < 0) + goto out_err; return 0; +out_err: + return err; } /* @@ -404,7 +419,6 @@ nfs_mark_request_commit(struct nfs_page *req) struct nfs_inode *nfsi = NFS_I(inode); spin_lock(&inode->i_lock); - nfsi->ncommit++; set_bit(PG_CLEAN, &(req)->wb_flags); radix_tree_tag_set(&nfsi->nfs_page_tree, req->wb_index, @@ -524,6 +538,12 @@ static void nfs_cancel_commit_list(struct list_head *head) } #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) +static int +nfs_need_commit(struct nfs_inode *nfsi) +{ + return radix_tree_tagged(&nfsi->nfs_page_tree, NFS_PAGE_TAG_COMMIT); +} + /* * nfs_scan_commit - Scan an inode for commit requests * @inode: NFS inode to scan @@ -538,16 +558,18 @@ static int nfs_scan_commit(struct inode *inode, struct list_head *dst, pgoff_t idx_start, unsigned int npages) { struct nfs_inode *nfsi = NFS_I(inode); - int res = 0; - if (nfsi->ncommit != 0) { - res = nfs_scan_list(nfsi, dst, idx_start, npages, - NFS_PAGE_TAG_COMMIT); - nfsi->ncommit -= res; - } - return res; + if (!nfs_need_commit(nfsi)) + return 0; + + return nfs_scan_list(nfsi, dst, idx_start, npages, NFS_PAGE_TAG_COMMIT); } #else +static inline int nfs_need_commit(struct nfs_inode *nfsi) +{ + return 0; +} + static inline int nfs_scan_commit(struct inode *inode, struct list_head *dst, pgoff_t idx_start, unsigned int npages) { return 0; @@ -820,7 +842,7 @@ static int nfs_write_rpcsetup(struct nfs_page *req, data->args.stable = NFS_UNSTABLE; if (how & FLUSH_STABLE) { data->args.stable = NFS_DATA_SYNC; - if (!NFS_I(inode)->ncommit) + if (!nfs_need_commit(NFS_I(inode))) data->args.stable = NFS_FILE_SYNC; } @@ -1425,18 +1447,13 @@ static int nfs_write_mapping(struct address_space *mapping, int how) { struct writeback_control wbc = { .bdi = mapping->backing_dev_info, - .sync_mode = WB_SYNC_NONE, + .sync_mode = WB_SYNC_ALL, .nr_to_write = LONG_MAX, .range_start = 0, .range_end = LLONG_MAX, .for_writepages = 1, }; - int ret; - ret = __nfs_write_mapping(mapping, &wbc, how); - if (ret < 0) - return ret; - wbc.sync_mode = WB_SYNC_ALL; return __nfs_write_mapping(mapping, &wbc, how); } diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 3d93b2064ce5..a4ed8644d69c 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -938,10 +938,12 @@ static ssize_t __write_ports(struct file *file, char *buf, size_t size) char transport[16]; int port; if (sscanf(buf, "%15s %4d", transport, &port) == 2) { + if (port < 1 || port > 65535) + return -EINVAL; err = nfsd_create_serv(); if (!err) { err = svc_create_xprt(nfsd_serv, - transport, port, + transport, PF_INET, port, SVC_SOCK_ANONYMOUS); if (err == -ENOENT) /* Give a reasonable perror msg for @@ -960,7 +962,7 @@ static ssize_t __write_ports(struct file *file, char *buf, size_t size) char transport[16]; int port; if (sscanf(&buf[1], "%15s %4d", transport, &port) == 2) { - if (port == 0) + if (port < 1 || port > 65535) return -EINVAL; if (nfsd_serv) { xprt = svc_find_xprt(nfsd_serv, transport, diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 07e4f5d7baa8..bc3567bab8c4 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -229,7 +229,6 @@ int nfsd_create_serv(void) atomic_set(&nfsd_busy, 0); nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize, - AF_INET, nfsd_last_thread, nfsd, THIS_MODULE); if (nfsd_serv == NULL) err = -ENOMEM; @@ -244,7 +243,7 @@ static int nfsd_init_socks(int port) if (!list_empty(&nfsd_serv->sv_permsocks)) return 0; - error = svc_create_xprt(nfsd_serv, "udp", port, + error = svc_create_xprt(nfsd_serv, "udp", PF_INET, port, SVC_SOCK_DEFAULTS); if (error < 0) return error; @@ -253,7 +252,7 @@ static int nfsd_init_socks(int port) if (error < 0) return error; - error = svc_create_xprt(nfsd_serv, "tcp", port, + error = svc_create_xprt(nfsd_serv, "tcp", PF_INET, port, SVC_SOCK_DEFAULTS); if (error < 0) return error; diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 8cc8807f77d6..bde2557c2a9c 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -166,8 +166,7 @@ struct nfs_inode { */ struct radix_tree_root nfs_page_tree; - unsigned long ncommit, - npages; + unsigned long npages; /* Open contexts for shared mmap writes */ struct list_head open_files; @@ -207,6 +206,7 @@ struct nfs_inode { #define NFS_INO_STALE (1) /* possible stale inode */ #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ #define NFS_INO_MOUNTPOINT (3) /* inode is remote mountpoint */ +#define NFS_INO_FLUSHING (4) /* inode is flushing out data */ static inline struct nfs_inode *NFS_I(const struct inode *inode) { diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 9bb81aec91cf..29b1e40dce99 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -106,6 +106,11 @@ struct nfs_server { u32 attr_bitmask[2];/* V4 bitmask representing the set of attributes supported on this filesystem */ + u32 cache_consistency_bitmask[2]; + /* V4 bitmask representing the subset + of change attribute, size, ctime + and mtime attributes supported by + the server */ u32 acl_bitmask; /* V4 bitmask representing the ACEs that are supported on this filesystem */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 43a713fce11c..b89c34e40bc2 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -27,12 +27,8 @@ static inline int nfs_fsid_equal(const struct nfs_fsid *a, const struct nfs_fsid } struct nfs_fattr { - unsigned short valid; /* which fields are valid */ - __u64 pre_size; /* pre_op_attr.size */ - struct timespec pre_mtime; /* pre_op_attr.mtime */ - struct timespec pre_ctime; /* pre_op_attr.ctime */ - enum nfs_ftype type; /* always use NFSv2 types */ - __u32 mode; + unsigned int valid; /* which fields are valid */ + umode_t mode; __u32 nlink; __u32 uid; __u32 gid; @@ -52,19 +48,55 @@ struct nfs_fattr { struct timespec atime; struct timespec mtime; struct timespec ctime; - __u32 bitmap[2]; /* NFSv4 returned attribute bitmap */ __u64 change_attr; /* NFSv4 change attribute */ __u64 pre_change_attr;/* pre-op NFSv4 change attribute */ + __u64 pre_size; /* pre_op_attr.size */ + struct timespec pre_mtime; /* pre_op_attr.mtime */ + struct timespec pre_ctime; /* pre_op_attr.ctime */ unsigned long time_start; unsigned long gencount; }; -#define NFS_ATTR_WCC 0x0001 /* pre-op WCC data */ -#define NFS_ATTR_FATTR 0x0002 /* post-op attributes */ -#define NFS_ATTR_FATTR_V3 0x0004 /* NFSv3 attributes */ -#define NFS_ATTR_FATTR_V4 0x0008 /* NFSv4 change attribute */ -#define NFS_ATTR_WCC_V4 0x0010 /* pre-op change attribute */ -#define NFS_ATTR_FATTR_V4_REFERRAL 0x0020 /* NFSv4 referral */ +#define NFS_ATTR_FATTR_TYPE (1U << 0) +#define NFS_ATTR_FATTR_MODE (1U << 1) +#define NFS_ATTR_FATTR_NLINK (1U << 2) +#define NFS_ATTR_FATTR_OWNER (1U << 3) +#define NFS_ATTR_FATTR_GROUP (1U << 4) +#define NFS_ATTR_FATTR_RDEV (1U << 5) +#define NFS_ATTR_FATTR_SIZE (1U << 6) +#define NFS_ATTR_FATTR_PRESIZE (1U << 7) +#define NFS_ATTR_FATTR_BLOCKS_USED (1U << 8) +#define NFS_ATTR_FATTR_SPACE_USED (1U << 9) +#define NFS_ATTR_FATTR_FSID (1U << 10) +#define NFS_ATTR_FATTR_FILEID (1U << 11) +#define NFS_ATTR_FATTR_ATIME (1U << 12) +#define NFS_ATTR_FATTR_MTIME (1U << 13) +#define NFS_ATTR_FATTR_CTIME (1U << 14) +#define NFS_ATTR_FATTR_PREMTIME (1U << 15) +#define NFS_ATTR_FATTR_PRECTIME (1U << 16) +#define NFS_ATTR_FATTR_CHANGE (1U << 17) +#define NFS_ATTR_FATTR_PRECHANGE (1U << 18) +#define NFS_ATTR_FATTR_V4_REFERRAL (1U << 19) /* NFSv4 referral */ + +#define NFS_ATTR_FATTR (NFS_ATTR_FATTR_TYPE \ + | NFS_ATTR_FATTR_MODE \ + | NFS_ATTR_FATTR_NLINK \ + | NFS_ATTR_FATTR_OWNER \ + | NFS_ATTR_FATTR_GROUP \ + | NFS_ATTR_FATTR_RDEV \ + | NFS_ATTR_FATTR_SIZE \ + | NFS_ATTR_FATTR_FSID \ + | NFS_ATTR_FATTR_FILEID \ + | NFS_ATTR_FATTR_ATIME \ + | NFS_ATTR_FATTR_MTIME \ + | NFS_ATTR_FATTR_CTIME) +#define NFS_ATTR_FATTR_V2 (NFS_ATTR_FATTR \ + | NFS_ATTR_FATTR_BLOCKS_USED) +#define NFS_ATTR_FATTR_V3 (NFS_ATTR_FATTR \ + | NFS_ATTR_FATTR_SPACE_USED) +#define NFS_ATTR_FATTR_V4 (NFS_ATTR_FATTR \ + | NFS_ATTR_FATTR_SPACE_USED \ + | NFS_ATTR_FATTR_CHANGE) /* * Info on the file system @@ -836,6 +868,7 @@ struct nfs_rpc_ops { int (*lock)(struct file *, int, struct file_lock *); int (*lock_check_bounds)(const struct file_lock *); void (*clear_acl_cache)(struct inode *); + void (*close_context)(struct nfs_open_context *ctx, int); }; /* diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 3435d24bfe55..d3a4c0231933 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -69,7 +69,6 @@ struct svc_serv { struct list_head sv_tempsocks; /* all temporary sockets */ int sv_tmpcnt; /* count of temporary sockets */ struct timer_list sv_temptimer; /* timer for aging temporary sockets */ - sa_family_t sv_family; /* listener's address family */ char * sv_name; /* service name */ @@ -385,19 +384,19 @@ struct svc_procedure { /* * Function prototypes. */ -struct svc_serv *svc_create(struct svc_program *, unsigned int, sa_family_t, +struct svc_serv *svc_create(struct svc_program *, unsigned int, void (*shutdown)(struct svc_serv *)); struct svc_rqst *svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool); void svc_exit_thread(struct svc_rqst *); struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, - sa_family_t, void (*shutdown)(struct svc_serv *), + void (*shutdown)(struct svc_serv *), svc_thread_fn, struct module *); int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); void svc_destroy(struct svc_serv *); int svc_process(struct svc_rqst *); -int svc_register(const struct svc_serv *, const unsigned short, - const unsigned short); +int svc_register(const struct svc_serv *, const int, + const unsigned short, const unsigned short); void svc_wake_up(struct svc_serv *); void svc_reserve(struct svc_rqst *rqstp, int space); diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 0127daca4354..0d9cb6ef28b0 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -71,7 +71,8 @@ int svc_reg_xprt_class(struct svc_xprt_class *); void svc_unreg_xprt_class(struct svc_xprt_class *); void svc_xprt_init(struct svc_xprt_class *, struct svc_xprt *, struct svc_serv *); -int svc_create_xprt(struct svc_serv *, char *, unsigned short, int); +int svc_create_xprt(struct svc_serv *, const char *, const int, + const unsigned short, int); void svc_xprt_enqueue(struct svc_xprt *xprt); void svc_xprt_received(struct svc_xprt *); void svc_xprt_put(struct svc_xprt *xprt); @@ -80,7 +81,8 @@ void svc_close_xprt(struct svc_xprt *xprt); void svc_delete_xprt(struct svc_xprt *xprt); int svc_port_is_privileged(struct sockaddr *sin); int svc_print_xprts(char *buf, int maxlen); -struct svc_xprt *svc_find_xprt(struct svc_serv *, char *, int, int); +struct svc_xprt *svc_find_xprt(struct svc_serv *serv, const char *xcl_name, + const sa_family_t af, const unsigned short port); int svc_xprt_names(struct svc_serv *serv, char *buf, int buflen); static inline void svc_xprt_get(struct svc_xprt *xprt) @@ -88,29 +90,32 @@ static inline void svc_xprt_get(struct svc_xprt *xprt) kref_get(&xprt->xpt_ref); } static inline void svc_xprt_set_local(struct svc_xprt *xprt, - struct sockaddr *sa, int salen) + const struct sockaddr *sa, + const size_t salen) { memcpy(&xprt->xpt_local, sa, salen); xprt->xpt_locallen = salen; } static inline void svc_xprt_set_remote(struct svc_xprt *xprt, - struct sockaddr *sa, int salen) + const struct sockaddr *sa, + const size_t salen) { memcpy(&xprt->xpt_remote, sa, salen); xprt->xpt_remotelen = salen; } -static inline unsigned short svc_addr_port(struct sockaddr *sa) +static inline unsigned short svc_addr_port(const struct sockaddr *sa) { - unsigned short ret = 0; + const struct sockaddr_in *sin = (const struct sockaddr_in *)sa; + const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)sa; + switch (sa->sa_family) { case AF_INET: - ret = ntohs(((struct sockaddr_in *)sa)->sin_port); - break; + return ntohs(sin->sin_port); case AF_INET6: - ret = ntohs(((struct sockaddr_in6 *)sa)->sin6_port); - break; + return ntohs(sin6->sin6_port); } - return ret; + + return 0; } static inline size_t svc_addr_len(struct sockaddr *sa) @@ -124,36 +129,39 @@ static inline size_t svc_addr_len(struct sockaddr *sa) return -EAFNOSUPPORT; } -static inline unsigned short svc_xprt_local_port(struct svc_xprt *xprt) +static inline unsigned short svc_xprt_local_port(const struct svc_xprt *xprt) { - return svc_addr_port((struct sockaddr *)&xprt->xpt_local); + return svc_addr_port((const struct sockaddr *)&xprt->xpt_local); } -static inline unsigned short svc_xprt_remote_port(struct svc_xprt *xprt) +static inline unsigned short svc_xprt_remote_port(const struct svc_xprt *xprt) { - return svc_addr_port((struct sockaddr *)&xprt->xpt_remote); + return svc_addr_port((const struct sockaddr *)&xprt->xpt_remote); } -static inline char *__svc_print_addr(struct sockaddr *addr, - char *buf, size_t len) +static inline char *__svc_print_addr(const struct sockaddr *addr, + char *buf, const size_t len) { + const struct sockaddr_in *sin = (const struct sockaddr_in *)addr; + const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)addr; + switch (addr->sa_family) { case AF_INET: - snprintf(buf, len, "%pI4, port=%u", - &((struct sockaddr_in *)addr)->sin_addr, - ntohs(((struct sockaddr_in *) addr)->sin_port)); + snprintf(buf, len, "%pI4, port=%u", &sin->sin_addr, + ntohs(sin->sin_port)); break; case AF_INET6: snprintf(buf, len, "%pI6, port=%u", - &((struct sockaddr_in6 *)addr)->sin6_addr, - ntohs(((struct sockaddr_in6 *) addr)->sin6_port)); + &sin6->sin6_addr, + ntohs(sin6->sin6_port)); break; default: snprintf(buf, len, "unknown address type: %d", addr->sa_family); break; } + return buf; } #endif /* SUNRPC_SVC_XPRT_H */ diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 11fc71d50c1e..1758d9f5b5c3 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -235,6 +235,7 @@ static inline __be32 *xprt_skip_transport_header(struct rpc_xprt *xprt, __be32 * */ int xprt_register_transport(struct xprt_class *type); int xprt_unregister_transport(struct xprt_class *type); +int xprt_load_transport(const char *); void xprt_set_retrans_timeout_def(struct rpc_task *task); void xprt_set_retrans_timeout_rtt(struct rpc_task *task); void xprt_wake_pending_tasks(struct rpc_xprt *xprt, int status); @@ -259,6 +260,7 @@ void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie); #define XPRT_BOUND (4) #define XPRT_BINDING (5) #define XPRT_CLOSING (6) +#define XPRT_CONNECTION_ABORT (7) static inline void xprt_set_connected(struct rpc_xprt *xprt) { diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig index 5592883e1e4a..afd91c78ce8e 100644 --- a/net/sunrpc/Kconfig +++ b/net/sunrpc/Kconfig @@ -17,28 +17,6 @@ config SUNRPC_XPRT_RDMA If unsure, say N. -config SUNRPC_REGISTER_V4 - bool "Register local RPC services via rpcbind v4 (EXPERIMENTAL)" - depends on SUNRPC && EXPERIMENTAL - default n - help - Sun added support for registering RPC services at an IPv6 - address by creating two new versions of the rpcbind protocol - (RFC 1833). - - This option enables support in the kernel RPC server for - registering kernel RPC services via version 4 of the rpcbind - protocol. If you enable this option, you must run a portmapper - daemon that supports rpcbind protocol version 4. - - Serving NFS over IPv6 from knfsd (the kernel's NFS server) - requires that you enable this option and use a portmapper that - supports rpcbind version 4. - - If unsure, say N to get traditional behavior (register kernel - RPC services using only rpcbind version 2). Distributions - using the legacy Linux portmapper daemon must say N here. - config RPCSEC_GSS_KRB5 tristate "Secure RPC: Kerberos V mechanism (EXPERIMENTAL)" depends on SUNRPC && EXPERIMENTAL diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 836f15c0c4a3..5abab094441f 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1032,27 +1032,20 @@ call_connect_status(struct rpc_task *task) dprint_status(task); task->tk_status = 0; - if (status >= 0) { + if (status >= 0 || status == -EAGAIN) { clnt->cl_stats->netreconn++; task->tk_action = call_transmit; return; } - /* Something failed: remote service port may have changed */ - rpc_force_rebind(clnt); - switch (status) { - case -ENOTCONN: - case -EAGAIN: - task->tk_action = call_bind; - if (!RPC_IS_SOFT(task)) - return; /* if soft mounted, test if we've timed out */ case -ETIMEDOUT: task->tk_action = call_timeout; - return; + break; + default: + rpc_exit(task, -EIO); } - rpc_exit(task, -EIO); } /* @@ -1105,14 +1098,26 @@ static void call_transmit_status(struct rpc_task *task) { task->tk_action = call_status; - /* - * Special case: if we've been waiting on the socket's write_space() - * callback, then don't call xprt_end_transmit(). - */ - if (task->tk_status == -EAGAIN) - return; - xprt_end_transmit(task); - rpc_task_force_reencode(task); + switch (task->tk_status) { + case -EAGAIN: + break; + default: + xprt_end_transmit(task); + /* + * Special cases: if we've been waiting on the + * socket's write_space() callback, or if the + * socket just returned a connection error, + * then hold onto the transport lock. + */ + case -ECONNREFUSED: + case -ECONNRESET: + case -ENOTCONN: + case -EHOSTDOWN: + case -EHOSTUNREACH: + case -ENETUNREACH: + case -EPIPE: + rpc_task_force_reencode(task); + } } /* @@ -1152,9 +1157,12 @@ call_status(struct rpc_task *task) xprt_conditional_disconnect(task->tk_xprt, req->rq_connect_cookie); break; + case -ECONNRESET: case -ECONNREFUSED: - case -ENOTCONN: rpc_force_rebind(clnt); + rpc_delay(task, 3*HZ); + case -EPIPE: + case -ENOTCONN: task->tk_action = call_bind; break; case -EAGAIN: diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 03ae007641e4..beee6da33035 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -63,9 +63,16 @@ enum { * r_owner * * The "owner" is allowed to unset a service in the rpcbind database. - * We always use the following (arbitrary) fixed string. + * + * For AF_LOCAL SET/UNSET requests, rpcbind treats this string as a + * UID which it maps to a local user name via a password lookup. + * In all other cases it is ignored. + * + * For SET/UNSET requests, user space provides a value, even for + * network requests, and GETADDR uses an empty string. We follow + * those precedents here. */ -#define RPCB_OWNER_STRING "rpcb" +#define RPCB_OWNER_STRING "0" #define RPCB_MAXOWNERLEN sizeof(RPCB_OWNER_STRING) static void rpcb_getport_done(struct rpc_task *, void *); @@ -124,12 +131,6 @@ static const struct sockaddr_in rpcb_inaddr_loopback = { .sin_port = htons(RPCBIND_PORT), }; -static const struct sockaddr_in6 rpcb_in6addr_loopback = { - .sin6_family = AF_INET6, - .sin6_addr = IN6ADDR_LOOPBACK_INIT, - .sin6_port = htons(RPCBIND_PORT), -}; - static struct rpc_clnt *rpcb_create_local(struct sockaddr *addr, size_t addrlen, u32 version) { @@ -176,9 +177,10 @@ static struct rpc_clnt *rpcb_create(char *hostname, struct sockaddr *srvaddr, return rpc_create(&args); } -static int rpcb_register_call(struct sockaddr *addr, size_t addrlen, - u32 version, struct rpc_message *msg) +static int rpcb_register_call(const u32 version, struct rpc_message *msg) { + struct sockaddr *addr = (struct sockaddr *)&rpcb_inaddr_loopback; + size_t addrlen = sizeof(rpcb_inaddr_loopback); struct rpc_clnt *rpcb_clnt; int result, error = 0; @@ -192,7 +194,7 @@ static int rpcb_register_call(struct sockaddr *addr, size_t addrlen, error = PTR_ERR(rpcb_clnt); if (error < 0) { - printk(KERN_WARNING "RPC: failed to contact local rpcbind " + dprintk("RPC: failed to contact local rpcbind " "server (errno %d).\n", -error); return error; } @@ -254,25 +256,23 @@ int rpcb_register(u32 prog, u32 vers, int prot, unsigned short port) if (port) msg.rpc_proc = &rpcb_procedures2[RPCBPROC_SET]; - return rpcb_register_call((struct sockaddr *)&rpcb_inaddr_loopback, - sizeof(rpcb_inaddr_loopback), - RPCBVERS_2, &msg); + return rpcb_register_call(RPCBVERS_2, &msg); } /* * Fill in AF_INET family-specific arguments to register */ -static int rpcb_register_netid4(struct sockaddr_in *address_to_register, - struct rpc_message *msg) +static int rpcb_register_inet4(const struct sockaddr *sap, + struct rpc_message *msg) { + const struct sockaddr_in *sin = (const struct sockaddr_in *)sap; struct rpcbind_args *map = msg->rpc_argp; - unsigned short port = ntohs(address_to_register->sin_port); + unsigned short port = ntohs(sin->sin_port); char buf[32]; /* Construct AF_INET universal address */ snprintf(buf, sizeof(buf), "%pI4.%u.%u", - &address_to_register->sin_addr.s_addr, - port >> 8, port & 0xff); + &sin->sin_addr.s_addr, port >> 8, port & 0xff); map->r_addr = buf; dprintk("RPC: %sregistering [%u, %u, %s, '%s'] with " @@ -284,29 +284,27 @@ static int rpcb_register_netid4(struct sockaddr_in *address_to_register, if (port) msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; - return rpcb_register_call((struct sockaddr *)&rpcb_inaddr_loopback, - sizeof(rpcb_inaddr_loopback), - RPCBVERS_4, msg); + return rpcb_register_call(RPCBVERS_4, msg); } /* * Fill in AF_INET6 family-specific arguments to register */ -static int rpcb_register_netid6(struct sockaddr_in6 *address_to_register, - struct rpc_message *msg) +static int rpcb_register_inet6(const struct sockaddr *sap, + struct rpc_message *msg) { + const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)sap; struct rpcbind_args *map = msg->rpc_argp; - unsigned short port = ntohs(address_to_register->sin6_port); + unsigned short port = ntohs(sin6->sin6_port); char buf[64]; /* Construct AF_INET6 universal address */ - if (ipv6_addr_any(&address_to_register->sin6_addr)) + 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", - &address_to_register->sin6_addr, - port >> 8, port & 0xff); + &sin6->sin6_addr, port >> 8, port & 0xff); map->r_addr = buf; dprintk("RPC: %sregistering [%u, %u, %s, '%s'] with " @@ -318,9 +316,21 @@ static int rpcb_register_netid6(struct sockaddr_in6 *address_to_register, if (port) msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; - return rpcb_register_call((struct sockaddr *)&rpcb_in6addr_loopback, - sizeof(rpcb_in6addr_loopback), - RPCBVERS_4, msg); + return rpcb_register_call(RPCBVERS_4, msg); +} + +static int rpcb_unregister_all_protofamilies(struct rpc_message *msg) +{ + struct rpcbind_args *map = msg->rpc_argp; + + dprintk("RPC: unregistering [%u, %u, '%s'] with " + "local rpcbind\n", + map->r_prog, map->r_vers, map->r_netid); + + map->r_addr = ""; + msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET]; + + return rpcb_register_call(RPCBVERS_4, msg); } /** @@ -340,10 +350,11 @@ static int rpcb_register_netid6(struct sockaddr_in6 *address_to_register, * invoke this function once for each [program, version, address, * netid] tuple they wish to advertise. * - * Callers may also unregister RPC services that are no longer - * available by setting the port number in the passed-in address - * to zero. Callers pass a netid of "" to unregister all - * transport netids associated with [program, version, address]. + * Callers may also unregister RPC services that are registered at a + * specific address by setting the port number in @address to zero. + * They may unregister all registered protocol families at once for + * a service by passing a NULL @address argument. If @netid is "" + * then all netids for [program, version, address] are unregistered. * * This function uses rpcbind protocol version 4 to contact the * local rpcbind daemon. The local rpcbind daemon must support @@ -378,13 +389,14 @@ int rpcb_v4_register(const u32 program, const u32 version, .rpc_argp = &map, }; + if (address == NULL) + return rpcb_unregister_all_protofamilies(&msg); + switch (address->sa_family) { case AF_INET: - return rpcb_register_netid4((struct sockaddr_in *)address, - &msg); + return rpcb_register_inet4(address, &msg); case AF_INET6: - return rpcb_register_netid6((struct sockaddr_in6 *)address, - &msg); + return rpcb_register_inet6(address, &msg); } return -EAFNOSUPPORT; @@ -579,7 +591,7 @@ void rpcb_getport_async(struct rpc_task *task) 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 = RPCB_OWNER_STRING; /* ignored for GETADDR */ + map->r_owner = ""; map->r_status = -EIO; child = rpcb_call_async(rpcb_clnt, map, proc); @@ -703,11 +715,16 @@ static int rpcb_decode_getaddr(struct rpc_rqst *req, __be32 *p, *portp = 0; addr_len = ntohl(*p++); + if (addr_len == 0) { + dprintk("RPC: rpcb_decode_getaddr: " + "service is not registered\n"); + return 0; + } + /* - * Simple sanity check. The smallest possible universal - * address is an IPv4 address string containing 11 bytes. + * Simple sanity check. */ - if (addr_len < 11 || addr_len > RPCBIND_MAXUADDRLEN) + if (addr_len > RPCBIND_MAXUADDRLEN) goto out_err; /* diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index bb507e2bb94d..9f2f2412a2f3 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -359,7 +359,7 @@ svc_pool_for_cpu(struct svc_serv *serv, int cpu) */ static struct svc_serv * __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, - sa_family_t family, void (*shutdown)(struct svc_serv *serv)) + void (*shutdown)(struct svc_serv *serv)) { struct svc_serv *serv; unsigned int vers; @@ -368,7 +368,6 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, if (!(serv = kzalloc(sizeof(*serv), GFP_KERNEL))) return NULL; - serv->sv_family = family; serv->sv_name = prog->pg_name; serv->sv_program = prog; serv->sv_nrthreads = 1; @@ -427,21 +426,21 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, struct svc_serv * svc_create(struct svc_program *prog, unsigned int bufsize, - sa_family_t family, void (*shutdown)(struct svc_serv *serv)) + void (*shutdown)(struct svc_serv *serv)) { - return __svc_create(prog, bufsize, /*npools*/1, family, shutdown); + return __svc_create(prog, bufsize, /*npools*/1, shutdown); } EXPORT_SYMBOL_GPL(svc_create); struct svc_serv * svc_create_pooled(struct svc_program *prog, unsigned int bufsize, - sa_family_t family, void (*shutdown)(struct svc_serv *serv), + void (*shutdown)(struct svc_serv *serv), svc_thread_fn func, struct module *mod) { struct svc_serv *serv; unsigned int npools = svc_pool_map_get(); - serv = __svc_create(prog, bufsize, npools, family, shutdown); + serv = __svc_create(prog, bufsize, npools, shutdown); if (serv != NULL) { serv->sv_function = func; @@ -719,8 +718,6 @@ svc_exit_thread(struct svc_rqst *rqstp) } EXPORT_SYMBOL_GPL(svc_exit_thread); -#ifdef CONFIG_SUNRPC_REGISTER_V4 - /* * Register an "inet" protocol family netid with the local * rpcbind daemon via an rpcbind v4 SET request. @@ -735,12 +732,13 @@ static int __svc_rpcb_register4(const u32 program, const u32 version, const unsigned short protocol, const unsigned short port) { - struct sockaddr_in sin = { + const struct sockaddr_in sin = { .sin_family = AF_INET, .sin_addr.s_addr = htonl(INADDR_ANY), .sin_port = htons(port), }; - char *netid; + const char *netid; + int error; switch (protocol) { case IPPROTO_UDP: @@ -750,13 +748,23 @@ static int __svc_rpcb_register4(const u32 program, const u32 version, netid = RPCBIND_NETID_TCP; break; default: - return -EPROTONOSUPPORT; + return -ENOPROTOOPT; } - return rpcb_v4_register(program, version, - (struct sockaddr *)&sin, netid); + error = rpcb_v4_register(program, version, + (const struct sockaddr *)&sin, netid); + + /* + * User space didn't support rpcbind v4, so retry this + * registration request with the legacy rpcbind v2 protocol. + */ + if (error == -EPROTONOSUPPORT) + error = rpcb_register(program, version, protocol, port); + + return error; } +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) /* * Register an "inet6" protocol family netid with the local * rpcbind daemon via an rpcbind v4 SET request. @@ -771,12 +779,13 @@ static int __svc_rpcb_register6(const u32 program, const u32 version, const unsigned short protocol, const unsigned short port) { - struct sockaddr_in6 sin6 = { + const struct sockaddr_in6 sin6 = { .sin6_family = AF_INET6, .sin6_addr = IN6ADDR_ANY_INIT, .sin6_port = htons(port), }; - char *netid; + const char *netid; + int error; switch (protocol) { case IPPROTO_UDP: @@ -786,12 +795,22 @@ static int __svc_rpcb_register6(const u32 program, const u32 version, netid = RPCBIND_NETID_TCP6; break; default: - return -EPROTONOSUPPORT; + return -ENOPROTOOPT; } - return rpcb_v4_register(program, version, - (struct sockaddr *)&sin6, netid); + error = rpcb_v4_register(program, version, + (const struct sockaddr *)&sin6, netid); + + /* + * User space didn't support rpcbind version 4, so we won't + * use a PF_INET6 listener. + */ + if (error == -EPROTONOSUPPORT) + error = -EAFNOSUPPORT; + + return error; } +#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */ /* * Register a kernel RPC service via rpcbind version 4. @@ -799,69 +818,43 @@ static int __svc_rpcb_register6(const u32 program, const u32 version, * Returns zero on success; a negative errno value is returned * if any error occurs. */ -static int __svc_register(const u32 program, const u32 version, - const sa_family_t family, +static int __svc_register(const char *progname, + const u32 program, const u32 version, + const int family, const unsigned short protocol, const unsigned short port) { - int error; + int error = -EAFNOSUPPORT; switch (family) { - case AF_INET: - return __svc_rpcb_register4(program, version, + case PF_INET: + error = __svc_rpcb_register4(program, version, protocol, port); - case AF_INET6: + break; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + case PF_INET6: error = __svc_rpcb_register6(program, version, protocol, port); - if (error < 0) - return error; - - /* - * Work around bug in some versions of Linux rpcbind - * which don't allow registration of both inet and - * inet6 netids. - * - * Error return ignored for now. - */ - __svc_rpcb_register4(program, version, - protocol, port); - return 0; +#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */ } - return -EAFNOSUPPORT; + if (error < 0) + printk(KERN_WARNING "svc: failed to register %sv%u RPC " + "service (errno %d).\n", progname, version, -error); + return error; } -#else /* CONFIG_SUNRPC_REGISTER_V4 */ - -/* - * Register a kernel RPC service via rpcbind version 2. - * - * Returns zero on success; a negative errno value is returned - * if any error occurs. - */ -static int __svc_register(const u32 program, const u32 version, - sa_family_t family, - const unsigned short protocol, - const unsigned short port) -{ - if (family != AF_INET) - return -EAFNOSUPPORT; - - return rpcb_register(program, version, protocol, port); -} - -#endif /* CONFIG_SUNRPC_REGISTER_V4 */ - /** * svc_register - register an RPC service with the local portmapper * @serv: svc_serv struct for the service to register + * @family: protocol family of service's listener socket * @proto: transport protocol number to advertise * @port: port to advertise * - * Service is registered for any address in serv's address family + * Service is registered for any address in the passed-in protocol family */ -int svc_register(const struct svc_serv *serv, const unsigned short proto, - const unsigned short port) +int svc_register(const struct svc_serv *serv, const int family, + const unsigned short proto, const unsigned short port) { struct svc_program *progp; unsigned int i; @@ -879,15 +872,15 @@ int svc_register(const struct svc_serv *serv, const unsigned short proto, i, proto == IPPROTO_UDP? "udp" : "tcp", port, - serv->sv_family, + family, progp->pg_vers[i]->vs_hidden? " (but not telling portmap)" : ""); if (progp->pg_vers[i]->vs_hidden) continue; - error = __svc_register(progp->pg_prog, i, - serv->sv_family, proto, port); + error = __svc_register(progp->pg_name, progp->pg_prog, + i, family, proto, port); if (error < 0) break; } @@ -896,38 +889,31 @@ int svc_register(const struct svc_serv *serv, const unsigned short proto, return error; } -#ifdef CONFIG_SUNRPC_REGISTER_V4 - -static void __svc_unregister(const u32 program, const u32 version, - const char *progname) -{ - struct sockaddr_in6 sin6 = { - .sin6_family = AF_INET6, - .sin6_addr = IN6ADDR_ANY_INIT, - .sin6_port = 0, - }; - int error; - - error = rpcb_v4_register(program, version, - (struct sockaddr *)&sin6, ""); - dprintk("svc: %s(%sv%u), error %d\n", - __func__, progname, version, error); -} - -#else /* CONFIG_SUNRPC_REGISTER_V4 */ - +/* + * If user space is running rpcbind, it should take the v4 UNSET + * and clear everything for this [program, version]. If user space + * is running portmap, it will reject the v4 UNSET, but won't have + * any "inet6" entries anyway. So a PMAP_UNSET should be sufficient + * in this case to clear all existing entries for [program, version]. + */ static void __svc_unregister(const u32 program, const u32 version, const char *progname) { int error; - error = rpcb_register(program, version, 0, 0); + error = rpcb_v4_register(program, version, NULL, ""); + + /* + * User space didn't support rpcbind v4, so retry this + * request with the legacy rpcbind v2 protocol. + */ + if (error == -EPROTONOSUPPORT) + error = rpcb_register(program, version, 0, 0); + dprintk("svc: %s(%sv%u), error %d\n", __func__, progname, version, error); } -#endif /* CONFIG_SUNRPC_REGISTER_V4 */ - /* * All netids, bind addresses and ports registered for [program, version] * are removed from the local rpcbind database (if the service is not diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index e588df5d6b34..2819ee093f36 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -161,7 +161,9 @@ EXPORT_SYMBOL_GPL(svc_xprt_init); static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl, struct svc_serv *serv, - unsigned short port, int flags) + const int family, + const unsigned short port, + int flags) { struct sockaddr_in sin = { .sin_family = AF_INET, @@ -176,12 +178,12 @@ static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl, struct sockaddr *sap; size_t len; - switch (serv->sv_family) { - case AF_INET: + switch (family) { + case PF_INET: sap = (struct sockaddr *)&sin; len = sizeof(sin); break; - case AF_INET6: + case PF_INET6: sap = (struct sockaddr *)&sin6; len = sizeof(sin6); break; @@ -192,7 +194,8 @@ static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl, return xcl->xcl_ops->xpo_create(serv, sap, len, flags); } -int svc_create_xprt(struct svc_serv *serv, char *xprt_name, unsigned short port, +int svc_create_xprt(struct svc_serv *serv, const char *xprt_name, + const int family, const unsigned short port, int flags) { struct svc_xprt_class *xcl; @@ -209,7 +212,7 @@ int svc_create_xprt(struct svc_serv *serv, char *xprt_name, unsigned short port, goto err; spin_unlock(&svc_xprt_class_lock); - newxprt = __svc_xpo_create(xcl, serv, port, flags); + newxprt = __svc_xpo_create(xcl, serv, family, port, flags); if (IS_ERR(newxprt)) { module_put(xcl->xcl_owner); return PTR_ERR(newxprt); @@ -1033,7 +1036,13 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt) return dr; } -/* +/** + * svc_find_xprt - find an RPC transport instance + * @serv: pointer to svc_serv to search + * @xcl_name: C string containing transport's class name + * @af: Address family of transport's local address + * @port: transport's IP port number + * * Return the transport instance pointer for the endpoint accepting * connections/peer traffic from the specified transport class, * address family and port. @@ -1042,14 +1051,14 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt) * wild-card, and will result in matching the first transport in the * service's list that has a matching class name. */ -struct svc_xprt *svc_find_xprt(struct svc_serv *serv, char *xcl_name, - int af, int port) +struct svc_xprt *svc_find_xprt(struct svc_serv *serv, const char *xcl_name, + const sa_family_t af, const unsigned short port) { struct svc_xprt *xprt; struct svc_xprt *found = NULL; /* Sanity check the args */ - if (!serv || !xcl_name) + if (serv == NULL || xcl_name == NULL) return found; spin_lock_bh(&serv->sv_lock); @@ -1058,7 +1067,7 @@ struct svc_xprt *svc_find_xprt(struct svc_serv *serv, char *xcl_name, continue; if (af != AF_UNSPEC && af != xprt->xpt_local.ss_family) continue; - if (port && port != svc_xprt_local_port(xprt)) + if (port != 0 && port != svc_xprt_local_port(xprt)) continue; found = xprt; svc_xprt_get(xprt); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 5763e6460fea..9d504234af4a 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1110,7 +1110,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, struct svc_sock *svsk; struct sock *inet; int pmap_register = !(flags & SVC_SOCK_ANONYMOUS); - int val; dprintk("svc: svc_setup_socket %p\n", sock); if (!(svsk = kzalloc(sizeof(*svsk), GFP_KERNEL))) { @@ -1122,7 +1121,7 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, /* Register socket with portmapper */ if (*errp >= 0 && pmap_register) - *errp = svc_register(serv, inet->sk_protocol, + *errp = svc_register(serv, inet->sk_family, inet->sk_protocol, ntohs(inet_sk(inet)->sport)); if (*errp < 0) { @@ -1143,18 +1142,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, else svc_tcp_init(svsk, serv); - /* - * We start one listener per sv_serv. We want AF_INET - * requests to be automatically shunted to our AF_INET6 - * listener using a mapped IPv4 address. Make sure - * no-one starts an equivalent IPv4 listener, which - * would steal our incoming connections. - */ - val = 0; - if (serv->sv_family == AF_INET6) - kernel_setsockopt(sock, SOL_IPV6, IPV6_V6ONLY, - (char *)&val, sizeof(val)); - dprintk("svc: svc_setup_socket created %p (inet %p)\n", svsk, svsk->sk_sk); @@ -1222,6 +1209,8 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv, struct sockaddr_storage addr; struct sockaddr *newsin = (struct sockaddr *)&addr; int newlen; + int family; + int val; RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]); dprintk("svc: svc_create_socket(%s, %d, %s)\n", @@ -1233,14 +1222,35 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv, "sockets supported\n"); return ERR_PTR(-EINVAL); } - type = (protocol == IPPROTO_UDP)? SOCK_DGRAM : SOCK_STREAM; - error = sock_create_kern(sin->sa_family, type, protocol, &sock); + type = (protocol == IPPROTO_UDP)? SOCK_DGRAM : SOCK_STREAM; + switch (sin->sa_family) { + case AF_INET6: + family = PF_INET6; + break; + case AF_INET: + family = PF_INET; + break; + default: + return ERR_PTR(-EINVAL); + } + + error = sock_create_kern(family, type, protocol, &sock); if (error < 0) return ERR_PTR(error); svc_reclassify_socket(sock); + /* + * If this is an PF_INET6 listener, we want to avoid + * getting requests from IPv4 remotes. Those should + * be shunted to a PF_INET listener via rpcbind. + */ + val = 1; + if (family == PF_INET6) + kernel_setsockopt(sock, SOL_IPV6, IPV6_V6ONLY, + (char *)&val, sizeof(val)); + if (type == SOCK_STREAM) sock->sk->sk_reuse = 1; /* allow address reuse */ error = kernel_bind(sock, sin, len); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 62098d101a1f..a0bfe53f1621 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -151,6 +151,37 @@ out: } EXPORT_SYMBOL_GPL(xprt_unregister_transport); +/** + * xprt_load_transport - load a transport implementation + * @transport_name: transport to load + * + * Returns: + * 0: transport successfully loaded + * -ENOENT: transport module not available + */ +int xprt_load_transport(const char *transport_name) +{ + struct xprt_class *t; + char module_name[sizeof t->name + 5]; + int result; + + result = 0; + spin_lock(&xprt_list_lock); + list_for_each_entry(t, &xprt_list, list) { + if (strcmp(t->name, transport_name) == 0) { + spin_unlock(&xprt_list_lock); + goto out; + } + } + spin_unlock(&xprt_list_lock); + strcpy(module_name, "xprt"); + strncat(module_name, transport_name, sizeof t->name); + result = request_module(module_name); +out: + return result; +} +EXPORT_SYMBOL_GPL(xprt_load_transport); + /** * xprt_reserve_xprt - serialize write access to transports * @task: task that is requesting access to the transport @@ -580,7 +611,7 @@ void xprt_disconnect_done(struct rpc_xprt *xprt) dprintk("RPC: disconnected transport %p\n", xprt); spin_lock_bh(&xprt->transport_lock); xprt_clear_connected(xprt); - xprt_wake_pending_tasks(xprt, -ENOTCONN); + xprt_wake_pending_tasks(xprt, -EAGAIN); spin_unlock_bh(&xprt->transport_lock); } EXPORT_SYMBOL_GPL(xprt_disconnect_done); @@ -598,7 +629,7 @@ void xprt_force_disconnect(struct rpc_xprt *xprt) /* Try to schedule an autoclose RPC call */ if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0) queue_work(rpciod_workqueue, &xprt->task_cleanup); - xprt_wake_pending_tasks(xprt, -ENOTCONN); + xprt_wake_pending_tasks(xprt, -EAGAIN); spin_unlock_bh(&xprt->transport_lock); } @@ -625,7 +656,7 @@ void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie) /* Try to schedule an autoclose RPC call */ if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0) queue_work(rpciod_workqueue, &xprt->task_cleanup); - xprt_wake_pending_tasks(xprt, -ENOTCONN); + xprt_wake_pending_tasks(xprt, -EAGAIN); out: spin_unlock_bh(&xprt->transport_lock); } @@ -695,9 +726,8 @@ static void xprt_connect_status(struct rpc_task *task) } switch (task->tk_status) { - case -ENOTCONN: - dprintk("RPC: %5u xprt_connect_status: connection broken\n", - task->tk_pid); + case -EAGAIN: + dprintk("RPC: %5u xprt_connect_status: retrying\n", task->tk_pid); break; case -ETIMEDOUT: dprintk("RPC: %5u xprt_connect_status: connect attempt timed " @@ -818,15 +848,8 @@ int xprt_prepare_transmit(struct rpc_task *task) err = req->rq_received; goto out_unlock; } - if (!xprt->ops->reserve_xprt(task)) { + if (!xprt->ops->reserve_xprt(task)) err = -EAGAIN; - goto out_unlock; - } - - if (!xprt_connected(xprt)) { - err = -ENOTCONN; - goto out_unlock; - } out_unlock: spin_unlock_bh(&xprt->transport_lock); return err; @@ -870,32 +893,26 @@ void xprt_transmit(struct rpc_task *task) req->rq_connect_cookie = xprt->connect_cookie; req->rq_xtime = jiffies; status = xprt->ops->send_request(task); - if (status == 0) { - dprintk("RPC: %5u xmit complete\n", task->tk_pid); - spin_lock_bh(&xprt->transport_lock); - - xprt->ops->set_retrans_timeout(task); - - xprt->stat.sends++; - xprt->stat.req_u += xprt->stat.sends - xprt->stat.recvs; - xprt->stat.bklog_u += xprt->backlog.qlen; - - /* Don't race with disconnect */ - if (!xprt_connected(xprt)) - task->tk_status = -ENOTCONN; - else if (!req->rq_received) - rpc_sleep_on(&xprt->pending, task, xprt_timer); - spin_unlock_bh(&xprt->transport_lock); + if (status != 0) { + task->tk_status = status; return; } - /* Note: at this point, task->tk_sleeping has not yet been set, - * hence there is no danger of the waking up task being put on - * schedq, and being picked up by a parallel run of rpciod(). - */ - task->tk_status = status; - if (status == -ECONNREFUSED) - rpc_sleep_on(&xprt->sending, task, NULL); + dprintk("RPC: %5u xmit complete\n", task->tk_pid); + spin_lock_bh(&xprt->transport_lock); + + xprt->ops->set_retrans_timeout(task); + + xprt->stat.sends++; + xprt->stat.req_u += xprt->stat.sends - xprt->stat.recvs; + xprt->stat.bklog_u += xprt->backlog.qlen; + + /* Don't race with disconnect */ + if (!xprt_connected(xprt)) + task->tk_status = -ENOTCONN; + else if (!req->rq_received) + rpc_sleep_on(&xprt->pending, task, xprt_timer); + spin_unlock_bh(&xprt->transport_lock); } static inline void do_xprt_reserve(struct rpc_task *task) diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 14106d26bb95..e5e28d1946a4 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -310,6 +310,19 @@ rpcrdma_inline_pullup(struct rpc_rqst *rqst, int pad) __func__, pad, destp, rqst->rq_slen, curlen); copy_len = rqst->rq_snd_buf.page_len; + + if (rqst->rq_snd_buf.tail[0].iov_len) { + curlen = rqst->rq_snd_buf.tail[0].iov_len; + if (destp + copy_len != rqst->rq_snd_buf.tail[0].iov_base) { + memmove(destp + copy_len, + rqst->rq_snd_buf.tail[0].iov_base, curlen); + r_xprt->rx_stats.pullup_copy_count += curlen; + } + dprintk("RPC: %s: tail destp 0x%p len %d\n", + __func__, destp + copy_len, curlen); + rqst->rq_svec[0].iov_len += curlen; + } + r_xprt->rx_stats.pullup_copy_count += copy_len; npages = PAGE_ALIGN(rqst->rq_snd_buf.page_base+copy_len) >> PAGE_SHIFT; for (i = 0; copy_len && i < npages; i++) { @@ -332,17 +345,6 @@ rpcrdma_inline_pullup(struct rpc_rqst *rqst, int pad) destp += curlen; copy_len -= curlen; } - if (rqst->rq_snd_buf.tail[0].iov_len) { - curlen = rqst->rq_snd_buf.tail[0].iov_len; - if (destp != rqst->rq_snd_buf.tail[0].iov_base) { - memcpy(destp, - rqst->rq_snd_buf.tail[0].iov_base, curlen); - r_xprt->rx_stats.pullup_copy_count += curlen; - } - dprintk("RPC: %s: tail destp 0x%p len %d curlen %d\n", - __func__, destp, copy_len, curlen); - rqst->rq_svec[0].iov_len += curlen; - } /* header now contains entire send message */ return pad; } @@ -656,7 +658,7 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) if (curlen > rqst->rq_rcv_buf.tail[0].iov_len) curlen = rqst->rq_rcv_buf.tail[0].iov_len; if (rqst->rq_rcv_buf.tail[0].iov_base != srcp) - memcpy(rqst->rq_rcv_buf.tail[0].iov_base, srcp, curlen); + memmove(rqst->rq_rcv_buf.tail[0].iov_base, srcp, curlen); dprintk("RPC: %s: tail srcp 0x%p len %d curlen %d\n", __func__, srcp, copy_len, curlen); rqst->rq_rcv_buf.tail[0].iov_len = curlen; diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index a3334e3b73cc..6c26a675435a 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -191,7 +191,6 @@ static int map_xdr(struct svcxprt_rdma *xprt, struct xdr_buf *xdr, struct svc_rdma_req_map *vec) { - int sge_max = (xdr->len+PAGE_SIZE-1) / PAGE_SIZE + 3; int sge_no; u32 sge_bytes; u32 page_bytes; @@ -235,7 +234,11 @@ static int map_xdr(struct svcxprt_rdma *xprt, sge_no++; } - BUG_ON(sge_no > sge_max); + dprintk("svcrdma: map_xdr: sge_no %d page_no %d " + "page_base %u page_len %u head_len %zu tail_len %zu\n", + sge_no, page_no, xdr->page_base, xdr->page_len, + xdr->head[0].iov_len, xdr->tail[0].iov_len); + vec->count = sge_no; return 0; } @@ -579,7 +582,6 @@ static int send_reply(struct svcxprt_rdma *rdma, ctxt->sge[page_no+1].length = 0; } BUG_ON(sge_no > rdma->sc_max_sge); - BUG_ON(sge_no > ctxt->count); memset(&send_wr, 0, sizeof send_wr); ctxt->wr_op = IB_WR_SEND; send_wr.wr_id = (unsigned long)ctxt; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 568330eebbfe..d40ff50887aa 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -49,6 +49,9 @@ unsigned int xprt_tcp_slot_table_entries = RPC_DEF_SLOT_TABLE; unsigned int xprt_min_resvport = RPC_DEF_MIN_RESVPORT; unsigned int xprt_max_resvport = RPC_DEF_MAX_RESVPORT; +#define XS_TCP_LINGER_TO (15U * HZ) +static unsigned int xs_tcp_fin_timeout __read_mostly = XS_TCP_LINGER_TO; + /* * We can register our own files under /proc/sys/sunrpc by * calling register_sysctl_table() again. The files in that @@ -116,6 +119,14 @@ static ctl_table xs_tunables_table[] = { .extra1 = &xprt_min_resvport_limit, .extra2 = &xprt_max_resvport_limit }, + { + .procname = "tcp_fin_timeout", + .data = &xs_tcp_fin_timeout, + .maxlen = sizeof(xs_tcp_fin_timeout), + .mode = 0644, + .proc_handler = &proc_dointvec_jiffies, + .strategy = sysctl_jiffies + }, { .ctl_name = 0, }, @@ -521,11 +532,12 @@ static void xs_nospace_callback(struct rpc_task *task) * @task: task to put to sleep * */ -static void xs_nospace(struct rpc_task *task) +static int xs_nospace(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); + int ret = 0; dprintk("RPC: %5u xmit incomplete (%u left of %u)\n", task->tk_pid, req->rq_slen - req->rq_bytes_sent, @@ -537,6 +549,7 @@ static void xs_nospace(struct rpc_task *task) /* Don't race with disconnect */ if (xprt_connected(xprt)) { if (test_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags)) { + ret = -EAGAIN; /* * Notify TCP that we're limited by the application * window size @@ -548,10 +561,11 @@ static void xs_nospace(struct rpc_task *task) } } else { clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags); - task->tk_status = -ENOTCONN; + ret = -ENOTCONN; } spin_unlock_bh(&xprt->transport_lock); + return ret; } /** @@ -594,6 +608,8 @@ static int xs_udp_send_request(struct rpc_task *task) /* Still some bytes left; set up for a retry later. */ status = -EAGAIN; } + if (!transport->sock) + goto out; switch (status) { case -ENOTSOCK: @@ -601,21 +617,19 @@ static int xs_udp_send_request(struct rpc_task *task) /* Should we call xs_close() here? */ break; case -EAGAIN: - xs_nospace(task); + status = xs_nospace(task); break; + default: + dprintk("RPC: sendmsg returned unrecognized error %d\n", + -status); case -ENETUNREACH: case -EPIPE: case -ECONNREFUSED: /* When the server has died, an ICMP port unreachable message * prompts ECONNREFUSED. */ clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags); - break; - default: - clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags); - dprintk("RPC: sendmsg returned unrecognized error %d\n", - -status); } - +out: return status; } @@ -697,6 +711,8 @@ static int xs_tcp_send_request(struct rpc_task *task) status = -EAGAIN; break; } + if (!transport->sock) + goto out; switch (status) { case -ENOTSOCK: @@ -704,23 +720,19 @@ static int xs_tcp_send_request(struct rpc_task *task) /* Should we call xs_close() here? */ break; case -EAGAIN: - xs_nospace(task); - break; - case -ECONNRESET: - xs_tcp_shutdown(xprt); - case -ECONNREFUSED: - case -ENOTCONN: - case -EPIPE: - status = -ENOTCONN; - clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags); + status = xs_nospace(task); break; default: dprintk("RPC: sendmsg returned unrecognized error %d\n", -status); - clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags); + case -ECONNRESET: + case -EPIPE: xs_tcp_shutdown(xprt); + case -ECONNREFUSED: + case -ENOTCONN: + clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags); } - +out: return status; } @@ -767,23 +779,13 @@ static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *s sk->sk_error_report = transport->old_error_report; } -/** - * xs_close - close a socket - * @xprt: transport - * - * This is used when all requests are complete; ie, no DRC state remains - * on the server we want to save. - */ -static void xs_close(struct rpc_xprt *xprt) +static void xs_reset_transport(struct sock_xprt *transport) { - struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); struct socket *sock = transport->sock; struct sock *sk = transport->inet; - if (!sk) - goto clear_close_wait; - - dprintk("RPC: xs_close xprt %p\n", xprt); + if (sk == NULL) + return; write_lock_bh(&sk->sk_callback_lock); transport->inet = NULL; @@ -797,8 +799,25 @@ static void xs_close(struct rpc_xprt *xprt) sk->sk_no_check = 0; sock_release(sock); -clear_close_wait: +} + +/** + * xs_close - close a socket + * @xprt: transport + * + * This is used when all requests are complete; ie, no DRC state remains + * on the server we want to save. + */ +static void xs_close(struct rpc_xprt *xprt) +{ + struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); + + dprintk("RPC: xs_close xprt %p\n", xprt); + + xs_reset_transport(transport); + smp_mb__before_clear_bit(); + clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); clear_bit(XPRT_CLOSE_WAIT, &xprt->state); clear_bit(XPRT_CLOSING, &xprt->state); smp_mb__after_clear_bit(); @@ -1126,6 +1145,47 @@ out: read_unlock(&sk->sk_callback_lock); } +/* + * Do the equivalent of linger/linger2 handling for dealing with + * broken servers that don't close the socket in a timely + * fashion + */ +static void xs_tcp_schedule_linger_timeout(struct rpc_xprt *xprt, + unsigned long timeout) +{ + struct sock_xprt *transport; + + if (xprt_test_and_set_connecting(xprt)) + return; + set_bit(XPRT_CONNECTION_ABORT, &xprt->state); + transport = container_of(xprt, struct sock_xprt, xprt); + queue_delayed_work(rpciod_workqueue, &transport->connect_worker, + timeout); +} + +static void xs_tcp_cancel_linger_timeout(struct rpc_xprt *xprt) +{ + struct sock_xprt *transport; + + transport = container_of(xprt, struct sock_xprt, xprt); + + if (!test_bit(XPRT_CONNECTION_ABORT, &xprt->state) || + !cancel_delayed_work(&transport->connect_worker)) + return; + clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); + xprt_clear_connecting(xprt); +} + +static void xs_sock_mark_closed(struct rpc_xprt *xprt) +{ + smp_mb__before_clear_bit(); + clear_bit(XPRT_CLOSE_WAIT, &xprt->state); + clear_bit(XPRT_CLOSING, &xprt->state); + smp_mb__after_clear_bit(); + /* Mark transport as closed and wake up all pending tasks */ + xprt_disconnect_done(xprt); +} + /** * xs_tcp_state_change - callback to handle TCP socket state changes * @sk: socket whose state has changed @@ -1158,7 +1218,7 @@ static void xs_tcp_state_change(struct sock *sk) transport->tcp_flags = TCP_RCV_COPY_FRAGHDR | TCP_RCV_COPY_XID; - xprt_wake_pending_tasks(xprt, 0); + xprt_wake_pending_tasks(xprt, -EAGAIN); } spin_unlock_bh(&xprt->transport_lock); break; @@ -1171,10 +1231,10 @@ static void xs_tcp_state_change(struct sock *sk) clear_bit(XPRT_CONNECTED, &xprt->state); clear_bit(XPRT_CLOSE_WAIT, &xprt->state); smp_mb__after_clear_bit(); + xs_tcp_schedule_linger_timeout(xprt, xs_tcp_fin_timeout); break; case TCP_CLOSE_WAIT: /* The server initiated a shutdown of the socket */ - set_bit(XPRT_CLOSING, &xprt->state); xprt_force_disconnect(xprt); case TCP_SYN_SENT: xprt->connect_cookie++; @@ -1187,40 +1247,35 @@ static void xs_tcp_state_change(struct sock *sk) xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; break; case TCP_LAST_ACK: + set_bit(XPRT_CLOSING, &xprt->state); + xs_tcp_schedule_linger_timeout(xprt, xs_tcp_fin_timeout); smp_mb__before_clear_bit(); clear_bit(XPRT_CONNECTED, &xprt->state); smp_mb__after_clear_bit(); break; case TCP_CLOSE: - smp_mb__before_clear_bit(); - clear_bit(XPRT_CLOSE_WAIT, &xprt->state); - clear_bit(XPRT_CLOSING, &xprt->state); - smp_mb__after_clear_bit(); - /* Mark transport as closed and wake up all pending tasks */ - xprt_disconnect_done(xprt); + xs_tcp_cancel_linger_timeout(xprt); + xs_sock_mark_closed(xprt); } out: read_unlock(&sk->sk_callback_lock); } /** - * xs_tcp_error_report - callback mainly for catching RST events + * xs_error_report - callback mainly for catching socket errors * @sk: socket */ -static void xs_tcp_error_report(struct sock *sk) +static void xs_error_report(struct sock *sk) { struct rpc_xprt *xprt; read_lock(&sk->sk_callback_lock); - if (sk->sk_err != ECONNRESET || sk->sk_state != TCP_ESTABLISHED) - goto out; if (!(xprt = xprt_from_sock(sk))) goto out; dprintk("RPC: %s client %p...\n" "RPC: error %d\n", __func__, xprt, sk->sk_err); - - xprt_force_disconnect(xprt); + xprt_wake_pending_tasks(xprt, -EAGAIN); out: read_unlock(&sk->sk_callback_lock); } @@ -1494,6 +1549,7 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) sk->sk_user_data = xprt; sk->sk_data_ready = xs_udp_data_ready; sk->sk_write_space = xs_udp_write_space; + sk->sk_error_report = xs_error_report; sk->sk_no_check = UDP_CSUM_NORCV; sk->sk_allocation = GFP_ATOMIC; @@ -1526,9 +1582,10 @@ static void xs_udp_connect_worker4(struct work_struct *work) goto out; /* Start by resetting any existing state */ - xs_close(xprt); + xs_reset_transport(transport); - if ((err = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock)) < 0) { + err = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); + if (err < 0) { dprintk("RPC: can't create UDP transport socket (%d).\n", -err); goto out; } @@ -1545,8 +1602,8 @@ static void xs_udp_connect_worker4(struct work_struct *work) xs_udp_finish_connecting(xprt, sock); status = 0; out: - xprt_wake_pending_tasks(xprt, status); xprt_clear_connecting(xprt); + xprt_wake_pending_tasks(xprt, status); } /** @@ -1567,9 +1624,10 @@ static void xs_udp_connect_worker6(struct work_struct *work) goto out; /* Start by resetting any existing state */ - xs_close(xprt); + xs_reset_transport(transport); - if ((err = sock_create_kern(PF_INET6, SOCK_DGRAM, IPPROTO_UDP, &sock)) < 0) { + err = sock_create_kern(PF_INET6, SOCK_DGRAM, IPPROTO_UDP, &sock); + if (err < 0) { dprintk("RPC: can't create UDP transport socket (%d).\n", -err); goto out; } @@ -1586,18 +1644,17 @@ static void xs_udp_connect_worker6(struct work_struct *work) xs_udp_finish_connecting(xprt, sock); status = 0; out: - xprt_wake_pending_tasks(xprt, status); xprt_clear_connecting(xprt); + xprt_wake_pending_tasks(xprt, status); } /* * We need to preserve the port number so the reply cache on the server can * find our cached RPC replies when we get around to reconnecting. */ -static void xs_tcp_reuse_connection(struct rpc_xprt *xprt) +static void xs_abort_connection(struct rpc_xprt *xprt, struct sock_xprt *transport) { int result; - struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); struct sockaddr any; dprintk("RPC: disconnecting xprt %p to reuse port\n", xprt); @@ -1609,11 +1666,24 @@ static void xs_tcp_reuse_connection(struct rpc_xprt *xprt) memset(&any, 0, sizeof(any)); any.sa_family = AF_UNSPEC; result = kernel_connect(transport->sock, &any, sizeof(any), 0); - if (result) + if (!result) + xs_sock_mark_closed(xprt); + else dprintk("RPC: AF_UNSPEC connect return code %d\n", result); } +static void xs_tcp_reuse_connection(struct rpc_xprt *xprt, struct sock_xprt *transport) +{ + unsigned int state = transport->inet->sk_state; + + if (state == TCP_CLOSE && transport->sock->state == SS_UNCONNECTED) + return; + if ((1 << state) & (TCPF_ESTABLISHED|TCPF_SYN_SENT)) + return; + xs_abort_connection(xprt, transport); +} + static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); @@ -1629,7 +1699,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) sk->sk_data_ready = xs_tcp_data_ready; sk->sk_state_change = xs_tcp_state_change; sk->sk_write_space = xs_tcp_write_space; - sk->sk_error_report = xs_tcp_error_report; + sk->sk_error_report = xs_error_report; sk->sk_allocation = GFP_ATOMIC; /* socket options */ @@ -1656,6 +1726,97 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) return kernel_connect(sock, xs_addr(xprt), xprt->addrlen, O_NONBLOCK); } +/** + * xs_tcp_setup_socket - create a TCP socket and connect to a remote endpoint + * @xprt: RPC transport to connect + * @transport: socket transport to connect + * @create_sock: function to create a socket of the correct type + * + * Invoked by a work queue tasklet. + */ +static void xs_tcp_setup_socket(struct rpc_xprt *xprt, + struct sock_xprt *transport, + struct socket *(*create_sock)(struct rpc_xprt *, + struct sock_xprt *)) +{ + struct socket *sock = transport->sock; + int status = -EIO; + + if (xprt->shutdown) + goto out; + + if (!sock) { + clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); + sock = create_sock(xprt, transport); + if (IS_ERR(sock)) { + status = PTR_ERR(sock); + goto out; + } + } else { + int abort_and_exit; + + abort_and_exit = test_and_clear_bit(XPRT_CONNECTION_ABORT, + &xprt->state); + /* "close" the socket, preserving the local port */ + xs_tcp_reuse_connection(xprt, transport); + + if (abort_and_exit) + goto out_eagain; + } + + dprintk("RPC: worker connecting xprt %p to address: %s\n", + xprt, xprt->address_strings[RPC_DISPLAY_ALL]); + + status = xs_tcp_finish_connecting(xprt, sock); + dprintk("RPC: %p connect status %d connected %d sock state %d\n", + xprt, -status, xprt_connected(xprt), + sock->sk->sk_state); + switch (status) { + case -ECONNREFUSED: + case -ECONNRESET: + case -ENETUNREACH: + /* retry with existing socket, after a delay */ + case 0: + case -EINPROGRESS: + case -EALREADY: + xprt_clear_connecting(xprt); + return; + } + /* get rid of existing socket, and retry */ + xs_tcp_shutdown(xprt); + printk("%s: connect returned unhandled error %d\n", + __func__, status); +out_eagain: + status = -EAGAIN; +out: + xprt_clear_connecting(xprt); + xprt_wake_pending_tasks(xprt, status); +} + +static struct socket *xs_create_tcp_sock4(struct rpc_xprt *xprt, + struct sock_xprt *transport) +{ + struct socket *sock; + int err; + + /* start from scratch */ + err = sock_create_kern(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock); + if (err < 0) { + dprintk("RPC: can't create TCP transport socket (%d).\n", + -err); + goto out_err; + } + xs_reclassify_socket4(sock); + + if (xs_bind4(transport, sock) < 0) { + sock_release(sock); + goto out_err; + } + return sock; +out_err: + return ERR_PTR(-EIO); +} + /** * xs_tcp_connect_worker4 - connect a TCP socket to a remote endpoint * @work: RPC transport to connect @@ -1667,53 +1828,32 @@ static void xs_tcp_connect_worker4(struct work_struct *work) struct sock_xprt *transport = container_of(work, struct sock_xprt, connect_worker.work); struct rpc_xprt *xprt = &transport->xprt; - struct socket *sock = transport->sock; - int err, status = -EIO; - if (xprt->shutdown) - goto out; + xs_tcp_setup_socket(xprt, transport, xs_create_tcp_sock4); +} - if (!sock) { - /* start from scratch */ - if ((err = sock_create_kern(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock)) < 0) { - dprintk("RPC: can't create TCP transport socket (%d).\n", -err); - goto out; - } - xs_reclassify_socket4(sock); +static struct socket *xs_create_tcp_sock6(struct rpc_xprt *xprt, + struct sock_xprt *transport) +{ + struct socket *sock; + int err; - if (xs_bind4(transport, sock) < 0) { - sock_release(sock); - goto out; - } - } else - /* "close" the socket, preserving the local port */ - xs_tcp_reuse_connection(xprt); - - dprintk("RPC: worker connecting xprt %p to address: %s\n", - xprt, xprt->address_strings[RPC_DISPLAY_ALL]); - - status = xs_tcp_finish_connecting(xprt, sock); - dprintk("RPC: %p connect status %d connected %d sock state %d\n", - xprt, -status, xprt_connected(xprt), - sock->sk->sk_state); - if (status < 0) { - switch (status) { - case -EINPROGRESS: - case -EALREADY: - goto out_clear; - case -ECONNREFUSED: - case -ECONNRESET: - /* retry with existing socket, after a delay */ - break; - default: - /* get rid of existing socket, and retry */ - xs_tcp_shutdown(xprt); - } + /* start from scratch */ + err = sock_create_kern(PF_INET6, SOCK_STREAM, IPPROTO_TCP, &sock); + if (err < 0) { + dprintk("RPC: can't create TCP transport socket (%d).\n", + -err); + goto out_err; } -out: - xprt_wake_pending_tasks(xprt, status); -out_clear: - xprt_clear_connecting(xprt); + xs_reclassify_socket6(sock); + + if (xs_bind6(transport, sock) < 0) { + sock_release(sock); + goto out_err; + } + return sock; +out_err: + return ERR_PTR(-EIO); } /** @@ -1727,52 +1867,8 @@ static void xs_tcp_connect_worker6(struct work_struct *work) struct sock_xprt *transport = container_of(work, struct sock_xprt, connect_worker.work); struct rpc_xprt *xprt = &transport->xprt; - struct socket *sock = transport->sock; - int err, status = -EIO; - if (xprt->shutdown) - goto out; - - if (!sock) { - /* start from scratch */ - if ((err = sock_create_kern(PF_INET6, SOCK_STREAM, IPPROTO_TCP, &sock)) < 0) { - dprintk("RPC: can't create TCP transport socket (%d).\n", -err); - goto out; - } - xs_reclassify_socket6(sock); - - if (xs_bind6(transport, sock) < 0) { - sock_release(sock); - goto out; - } - } else - /* "close" the socket, preserving the local port */ - xs_tcp_reuse_connection(xprt); - - dprintk("RPC: worker connecting xprt %p to address: %s\n", - xprt, xprt->address_strings[RPC_DISPLAY_ALL]); - - status = xs_tcp_finish_connecting(xprt, sock); - dprintk("RPC: %p connect status %d connected %d sock state %d\n", - xprt, -status, xprt_connected(xprt), sock->sk->sk_state); - if (status < 0) { - switch (status) { - case -EINPROGRESS: - case -EALREADY: - goto out_clear; - case -ECONNREFUSED: - case -ECONNRESET: - /* retry with existing socket, after a delay */ - break; - default: - /* get rid of existing socket, and retry */ - xs_tcp_shutdown(xprt); - } - } -out: - xprt_wake_pending_tasks(xprt, status); -out_clear: - xprt_clear_connecting(xprt); + xs_tcp_setup_socket(xprt, transport, xs_create_tcp_sock6); } /** @@ -1817,9 +1913,6 @@ static void xs_tcp_connect(struct rpc_task *task) { struct rpc_xprt *xprt = task->tk_xprt; - /* Initiate graceful shutdown of the socket if not already done */ - if (test_bit(XPRT_CONNECTED, &xprt->state)) - xs_tcp_shutdown(xprt); /* Exit if we need to wait for socket shutdown to complete */ if (test_bit(XPRT_CLOSING, &xprt->state)) return;