diff options
author | J. Bruce Fields <bfields@citi.umich.edu> | 2009-08-21 17:27:29 +0200 |
---|---|---|
committer | J. Bruce Fields <bfields@citi.umich.edu> | 2009-08-21 17:27:29 +0200 |
commit | e9dc122166b8d863d3057a66ada04838e5548e52 (patch) | |
tree | 749e15bf719b64bf9113db7acd8e043d9742cb26 /net | |
parent | sunrpc: fix memory leak in unix_gid cache. (diff) | |
parent | SUNRPC: Ensure that sunrpc gets initialised before nfs, lockd, etc... (diff) | |
download | linux-e9dc122166b8d863d3057a66ada04838e5548e52.tar.xz linux-e9dc122166b8d863d3057a66ada04838e5548e52.zip |
Merge branch 'nfs-for-2.6.32' of git://git.linux-nfs.org/projects/trondmy/nfs-2.6 into for-2.6.32-incoming
Conflicts:
net/sunrpc/cache.c
Diffstat (limited to 'net')
94 files changed, 2245 insertions, 1077 deletions
diff --git a/net/9p/client.c b/net/9p/client.c index dd43a8289b0d..787ccddb85ea 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -117,9 +117,6 @@ static int parse_opts(char *opts, struct p9_client *clnt) } } - if (!clnt->trans_mod) - clnt->trans_mod = v9fs_get_default_trans(); - kfree(options); return ret; } @@ -689,6 +686,9 @@ struct p9_client *p9_client_create(const char *dev_name, char *options) if (err < 0) goto error; + if (!clnt->trans_mod) + clnt->trans_mod = v9fs_get_default_trans(); + if (clnt->trans_mod == NULL) { err = -EPROTONOSUPPORT; P9_DPRINTK(P9_DEBUG_ERROR, @@ -1098,7 +1098,6 @@ p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset, if (data) { memmove(data, dataptr, count); - data += count; } if (udata) { @@ -1192,9 +1191,9 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid) err = p9pdu_readf(req->rc, clnt->dotu, "wS", &ignored, ret); if (err) { - ret = ERR_PTR(err); p9pdu_dump(1, req->rc); - goto free_and_error; + p9_free_req(clnt, req); + goto error; } P9_DPRINTK(P9_DEBUG_9P, @@ -1211,8 +1210,6 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid) p9_free_req(clnt, req); return ret; -free_and_error: - p9_free_req(clnt, req); error: kfree(ret); return ERR_PTR(err); diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index a2a1814c7a8d..8c2588e4edc0 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -735,12 +735,14 @@ static int parse_opts(char *params, struct p9_fd_opts *opts) if (!*p) continue; token = match_token(p, tokens, args); - r = match_int(&args[0], &option); - if (r < 0) { - P9_DPRINTK(P9_DEBUG_ERROR, - "integer field, but no integer?\n"); - ret = r; - continue; + if (token != Opt_err) { + r = match_int(&args[0], &option); + if (r < 0) { + P9_DPRINTK(P9_DEBUG_ERROR, + "integer field, but no integer?\n"); + ret = r; + continue; + } } switch (token) { case Opt_port: diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 590b83963622..bfbe13786bb4 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -54,6 +54,7 @@ #include <linux/capability.h> #include <linux/module.h> #include <linux/if_arp.h> +#include <linux/smp_lock.h> #include <linux/termios.h> /* For TIOCOUTQ/INQ */ #include <net/datalink.h> #include <net/psnap.h> diff --git a/net/atm/common.c b/net/atm/common.c index c1c97936192c..8c4d843eb17f 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -92,7 +92,7 @@ static void vcc_sock_destruct(struct sock *sk) static void vcc_def_wakeup(struct sock *sk) { read_lock(&sk->sk_callback_lock); - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + if (sk_has_sleeper(sk)) wake_up(sk->sk_sleep); read_unlock(&sk->sk_callback_lock); } @@ -110,7 +110,7 @@ static void vcc_write_space(struct sock *sk) read_lock(&sk->sk_callback_lock); if (vcc_writable(sk)) { - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + if (sk_has_sleeper(sk)) wake_up_interruptible(sk->sk_sleep); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); @@ -594,7 +594,7 @@ unsigned int vcc_poll(struct file *file, struct socket *sock, poll_table *wait) struct atm_vcc *vcc; unsigned int mask; - poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk->sk_sleep, wait); mask = 0; vcc = ATM_SD(sock); diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index e50566ebf9f9..94b3388c188b 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -2080,28 +2080,41 @@ static CLASS_ATTR(rfcomm_dlc, S_IRUGO, rfcomm_dlc_sysfs_show, NULL); /* ---- Initialization ---- */ static int __init rfcomm_init(void) { + int ret; + l2cap_load(); hci_register_cb(&rfcomm_cb); rfcomm_thread = kthread_run(rfcomm_run, NULL, "krfcommd"); if (IS_ERR(rfcomm_thread)) { - hci_unregister_cb(&rfcomm_cb); - return PTR_ERR(rfcomm_thread); + ret = PTR_ERR(rfcomm_thread); + goto out_thread; } if (class_create_file(bt_class, &class_attr_rfcomm_dlc) < 0) BT_ERR("Failed to create RFCOMM info file"); - rfcomm_init_sockets(); + ret = rfcomm_init_ttys(); + if (ret) + goto out_tty; -#ifdef CONFIG_BT_RFCOMM_TTY - rfcomm_init_ttys(); -#endif + ret = rfcomm_init_sockets(); + if (ret) + goto out_sock; BT_INFO("RFCOMM ver %s", VERSION); return 0; + +out_sock: + rfcomm_cleanup_ttys(); +out_tty: + kthread_stop(rfcomm_thread); +out_thread: + hci_unregister_cb(&rfcomm_cb); + + return ret; } static void __exit rfcomm_exit(void) @@ -2112,9 +2125,7 @@ static void __exit rfcomm_exit(void) kthread_stop(rfcomm_thread); -#ifdef CONFIG_BT_RFCOMM_TTY rfcomm_cleanup_ttys(); -#endif rfcomm_cleanup_sockets(); } diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 7f482784e9f7..0b85e8116859 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -1132,7 +1132,7 @@ error: return err; } -void __exit rfcomm_cleanup_sockets(void) +void rfcomm_cleanup_sockets(void) { class_remove_file(bt_class, &class_attr_rfcomm); diff --git a/net/bridge/br.c b/net/bridge/br.c index 9aac5213105a..e1241c76239a 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -93,7 +93,7 @@ static void __exit br_deinit(void) unregister_pernet_subsys(&br_net_ops); - synchronize_net(); + rcu_barrier(); /* Wait for completion of call_rcu()'s */ br_netfilter_fini(); #if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE) diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 8a96672e2c5c..eb404dc3ed6e 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -424,7 +424,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) err2: br_fdb_delete_by_port(br, p, 1); err1: - kobject_del(&p->kobj); + kobject_put(&p->kobj); err0: dev_set_promiscuity(dev, -1); put_back: diff --git a/net/can/bcm.c b/net/can/bcm.c index 95d7f32643ae..72720c710351 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -75,6 +75,7 @@ static __initdata const char banner[] = KERN_INFO MODULE_DESCRIPTION("PF_CAN broadcast manager protocol"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>"); +MODULE_ALIAS("can-proto-2"); /* easy access to can_frame payload */ static inline u64 GET_U64(const struct can_frame *cp) @@ -1469,6 +1470,9 @@ static int bcm_release(struct socket *sock) bo->ifindex = 0; } + sock_orphan(sk); + sock->sk = NULL; + release_sock(sk); sock_put(sk); diff --git a/net/can/raw.c b/net/can/raw.c index 6aa154e806ae..f4cc44548bda 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -62,6 +62,7 @@ static __initdata const char banner[] = MODULE_DESCRIPTION("PF_CAN raw protocol"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Urs Thuermann <urs.thuermann@volkswagen.de>"); +MODULE_ALIAS("can-proto-1"); #define MASK_ALL 0 @@ -306,6 +307,9 @@ static int raw_release(struct socket *sock) ro->bound = 0; ro->count = 0; + sock_orphan(sk); + sock->sk = NULL; + release_sock(sk); sock_put(sk); diff --git a/net/core/datagram.c b/net/core/datagram.c index 58abee1f1df1..b0fe69211eef 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -712,7 +712,7 @@ unsigned int datagram_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; unsigned int mask; - poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk->sk_sleep, wait); mask = 0; /* exceptional events? */ diff --git a/net/core/dev.c b/net/core/dev.c index 60b572812278..6a94475aee85 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2823,9 +2823,11 @@ static void net_rx_action(struct softirq_action *h) * move the instance around on the list at-will. */ if (unlikely(work == weight)) { - if (unlikely(napi_disable_pending(n))) - __napi_complete(n); - else + if (unlikely(napi_disable_pending(n))) { + local_irq_enable(); + napi_complete(n); + local_irq_disable(); + } else list_move_tail(&n->poll_list, list); } @@ -3863,10 +3865,12 @@ int dev_unicast_delete(struct net_device *dev, void *addr) ASSERT_RTNL(); + netif_addr_lock_bh(dev); err = __hw_addr_del(&dev->uc, addr, dev->addr_len, NETDEV_HW_ADDR_T_UNICAST); if (!err) __dev_set_rx_mode(dev); + netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_unicast_delete); @@ -3887,10 +3891,12 @@ int dev_unicast_add(struct net_device *dev, void *addr) ASSERT_RTNL(); + netif_addr_lock_bh(dev); err = __hw_addr_add(&dev->uc, addr, dev->addr_len, NETDEV_HW_ADDR_T_UNICAST); if (!err) __dev_set_rx_mode(dev); + netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_unicast_add); @@ -3947,7 +3953,8 @@ void __dev_addr_unsync(struct dev_addr_list **to, int *to_count, * @from: source device * * Add newly added addresses to the destination device and release - * addresses that have no users left. + * addresses that have no users left. The source device must be + * locked by netif_tx_lock_bh. * * This function is intended to be called from the dev->set_rx_mode * function of layered software devices. @@ -3956,14 +3963,14 @@ int dev_unicast_sync(struct net_device *to, struct net_device *from) { int err = 0; - ASSERT_RTNL(); - if (to->addr_len != from->addr_len) return -EINVAL; + netif_addr_lock_bh(to); err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); + netif_addr_unlock_bh(to); return err; } EXPORT_SYMBOL(dev_unicast_sync); @@ -3979,27 +3986,27 @@ EXPORT_SYMBOL(dev_unicast_sync); */ void dev_unicast_unsync(struct net_device *to, struct net_device *from) { - ASSERT_RTNL(); - if (to->addr_len != from->addr_len) return; + netif_addr_lock_bh(from); + netif_addr_lock(to); __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); __dev_set_rx_mode(to); + netif_addr_unlock(to); + netif_addr_unlock_bh(from); } EXPORT_SYMBOL(dev_unicast_unsync); static void dev_unicast_flush(struct net_device *dev) { - /* rtnl_mutex must be held here */ - + netif_addr_lock_bh(dev); __hw_addr_flush(&dev->uc); + netif_addr_unlock_bh(dev); } static void dev_unicast_init(struct net_device *dev) { - /* rtnl_mutex must be held here */ - __hw_addr_init(&dev->uc); } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index b7292a2719dc..197283072cc8 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -488,7 +488,7 @@ int net_assign_generic(struct net *net, int id, void *data) */ ng->len = id; - memcpy(&ng->ptr, &old_ng->ptr, old_ng->len); + memcpy(&ng->ptr, &old_ng->ptr, old_ng->len * sizeof(void*)); rcu_assign_pointer(net->gen, ng); call_rcu(&old_ng->rcu, net_generic_release); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 9675f312830d..df30feb2fc72 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -740,7 +740,7 @@ int netpoll_setup(struct netpoll *np) np->name); break; } - cond_resched(); + msleep(1); } /* If carrier appears to come up instantly, we don't diff --git a/net/core/sock.c b/net/core/sock.c index b0ba569bc973..bbb25be7ddfe 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -631,7 +631,7 @@ set_rcvbuf: case SO_TIMESTAMPING: if (val & ~SOF_TIMESTAMPING_MASK) { - ret = EINVAL; + ret = -EINVAL; break; } sock_valbool_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE, @@ -919,13 +919,19 @@ static inline void sock_lock_init(struct sock *sk) af_family_keys + sk->sk_family); } +/* + * Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet, + * even temporarly, because of RCU lookups. sk_node should also be left as is. + */ static void sock_copy(struct sock *nsk, const struct sock *osk) { #ifdef CONFIG_SECURITY_NETWORK void *sptr = nsk->sk_security; #endif - - memcpy(nsk, osk, osk->sk_prot->obj_size); + BUILD_BUG_ON(offsetof(struct sock, sk_copy_start) != + sizeof(osk->sk_node) + sizeof(osk->sk_refcnt)); + memcpy(&nsk->sk_copy_start, &osk->sk_copy_start, + osk->sk_prot->obj_size - offsetof(struct sock, sk_copy_start)); #ifdef CONFIG_SECURITY_NETWORK nsk->sk_security = sptr; security_sk_clone(osk, nsk); @@ -939,8 +945,23 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, struct kmem_cache *slab; slab = prot->slab; - if (slab != NULL) - sk = kmem_cache_alloc(slab, priority); + if (slab != NULL) { + sk = kmem_cache_alloc(slab, priority & ~__GFP_ZERO); + if (!sk) + return sk; + if (priority & __GFP_ZERO) { + /* + * caches using SLAB_DESTROY_BY_RCU should let + * sk_node.next un-modified. Special care is taken + * when initializing object to zero. + */ + if (offsetof(struct sock, sk_node.next) != 0) + memset(sk, 0, offsetof(struct sock, sk_node.next)); + memset(&sk->sk_node.pprev, 0, + prot->obj_size - offsetof(struct sock, + sk_node.pprev)); + } + } else sk = kmalloc(prot->obj_size, priority); @@ -1125,6 +1146,11 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) newsk->sk_err = 0; newsk->sk_priority = 0; + /* + * Before updating sk_refcnt, we must commit prior changes to memory + * (Documentation/RCU/rculist_nulls.txt for details) + */ + smp_wmb(); atomic_set(&newsk->sk_refcnt, 2); /* @@ -1715,7 +1741,7 @@ EXPORT_SYMBOL(sock_no_sendpage); static void sock_def_wakeup(struct sock *sk) { read_lock(&sk->sk_callback_lock); - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + if (sk_has_sleeper(sk)) wake_up_interruptible_all(sk->sk_sleep); read_unlock(&sk->sk_callback_lock); } @@ -1723,7 +1749,7 @@ static void sock_def_wakeup(struct sock *sk) static void sock_def_error_report(struct sock *sk) { read_lock(&sk->sk_callback_lock); - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + if (sk_has_sleeper(sk)) wake_up_interruptible_poll(sk->sk_sleep, POLLERR); sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR); read_unlock(&sk->sk_callback_lock); @@ -1732,7 +1758,7 @@ static void sock_def_error_report(struct sock *sk) static void sock_def_readable(struct sock *sk, int len) { read_lock(&sk->sk_callback_lock); - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + if (sk_has_sleeper(sk)) wake_up_interruptible_sync_poll(sk->sk_sleep, POLLIN | POLLRDNORM | POLLRDBAND); sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); @@ -1747,7 +1773,7 @@ static void sock_def_write_space(struct sock *sk) * progress. --DaveM */ if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + if (sk_has_sleeper(sk)) wake_up_interruptible_sync_poll(sk->sk_sleep, POLLOUT | POLLWRNORM | POLLWRBAND); @@ -1840,6 +1866,11 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_stamp = ktime_set(-1L, 0); + /* + * Before updating sk_refcnt, we must commit prior changes to memory + * (Documentation/RCU/rculist_nulls.txt for details) + */ + smp_wmb(); atomic_set(&sk->sk_refcnt, 1); atomic_set(&sk->sk_wmem_alloc, 1); atomic_set(&sk->sk_drops, 0); diff --git a/net/dccp/output.c b/net/dccp/output.c index c0e88c16d088..c96119fda688 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -196,7 +196,7 @@ void dccp_write_space(struct sock *sk) { read_lock(&sk->sk_callback_lock); - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + if (sk_has_sleeper(sk)) wake_up_interruptible(sk->sk_sleep); /* Should agree with poll, otherwise some programs break */ if (sock_writeable(sk)) diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 314a1b5c033c..3281013ce038 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -311,7 +311,7 @@ unsigned int dccp_poll(struct file *file, struct socket *sock, unsigned int mask; struct sock *sk = sock->sk; - poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk->sk_sleep, wait); if (sk->sk_state == DCCP_LISTEN) return inet_csk_listen_poll(sk); @@ -1066,7 +1066,7 @@ static int __init dccp_init(void) (dccp_hashinfo.ehash_size - 1)) dccp_hashinfo.ehash_size--; dccp_hashinfo.ehash = (struct inet_ehash_bucket *) - __get_free_pages(GFP_ATOMIC, ehash_order); + __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, ehash_order); } while (!dccp_hashinfo.ehash && --ehash_order > 0); if (!dccp_hashinfo.ehash) { @@ -1091,7 +1091,7 @@ static int __init dccp_init(void) bhash_order > 0) continue; dccp_hashinfo.bhash = (struct inet_bind_hashbucket *) - __get_free_pages(GFP_ATOMIC, bhash_order); + __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, bhash_order); } while (!dccp_hashinfo.bhash && --bhash_order >= 0); if (!dccp_hashinfo.bhash) { diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index d351b8db0df5..77d40289653c 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -2413,6 +2413,8 @@ static void __exit decnet_exit(void) proc_net_remove(&init_net, "decnet"); proto_unregister(&dn_proto); + + rcu_barrier_bh(); /* Wait for completion of call_rcu_bh()'s */ } module_exit(decnet_exit); #endif diff --git a/net/dsa/mv88e6xxx.c b/net/dsa/mv88e6xxx.c index 4e4d8b5ad03d..efe661a9def4 100644 --- a/net/dsa/mv88e6xxx.c +++ b/net/dsa/mv88e6xxx.c @@ -418,7 +418,7 @@ static int mv88e6xxx_stats_wait(struct dsa_switch *ds) int i; for (i = 0; i < 10; i++) { - ret = REG_READ(REG_GLOBAL2, 0x1d); + ret = REG_READ(REG_GLOBAL, 0x1d); if ((ret & 0x8000) == 0) return 0; } diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c index 105ad10876af..27eda9fdf3c2 100644 --- a/net/ieee802154/netlink.c +++ b/net/ieee802154/netlink.c @@ -276,6 +276,9 @@ static struct net_device *ieee802154_nl_get_dev(struct genl_info *info) else return NULL; + if (!dev) + return NULL; + if (dev->type != ARPHRD_IEEE802154) { dev_put(dev); return NULL; @@ -521,3 +524,6 @@ static void __exit ieee802154_nl_exit(void) } module_exit(ieee802154_nl_exit); +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("ieee 802.15.4 configuration interface"); + diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 8a3881e28aca..090e9991ac2a 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -801,11 +801,8 @@ static int arp_process(struct sk_buff *skb) * cache. */ - /* - * Special case: IPv4 duplicate address detection packet (RFC2131) - * and Gratuitous ARP/ARP Announce. (RFC3927, Section 2.4) - */ - if (sip == 0 || tip == sip) { + /* Special case: IPv4 duplicate address detection packet (RFC2131) */ + if (sip == 0) { if (arp->ar_op == htons(ARPOP_REQUEST) && inet_addr_type(net, tip) == RTN_LOCAL && !arp_ignore(in_dev, sip, tip)) @@ -1307,7 +1304,9 @@ static void arp_format_neigh_entry(struct seq_file *seq, hbuffer[k++] = hex_asc_lo(n->ha[j]); hbuffer[k++] = ':'; } - hbuffer[--k] = 0; + if (k != 0) + --k; + hbuffer[k] = 0; #if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE) } #endif diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 012cf5a68581..63c2fa7b68c4 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -316,8 +316,8 @@ static inline void check_tnode(const struct tnode *tn) static const int halve_threshold = 25; static const int inflate_threshold = 50; -static const int halve_threshold_root = 8; -static const int inflate_threshold_root = 15; +static const int halve_threshold_root = 15; +static const int inflate_threshold_root = 25; static void __alias_free_mem(struct rcu_head *head) @@ -1021,6 +1021,9 @@ static void trie_rebalance(struct trie *t, struct tnode *tn) (struct node *)tn, wasfull); tp = node_parent((struct node *) tn); + if (!tp) + rcu_assign_pointer(t->trie, (struct node *)tn); + tnode_free_flush(); if (!tp) break; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 44e2a3d2359a..cb4a0f4bd5e5 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -735,10 +735,10 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) } tos = tiph->tos; - if (tos&1) { + if (tos == 1) { + tos = 0; if (skb->protocol == htons(ETH_P_IP)) tos = old_iph->tos; - tos &= ~1; } { diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 490ce20faf38..db46b4b5b2b9 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -440,6 +440,9 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, /* Remove any debris in the socket control block */ memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + /* Must drop socket now because of tproxy. */ + skb_orphan(skb); + return NF_HOOK(PF_INET, NF_INET_PRE_ROUTING, skb, dev, NULL, ip_rcv_finish); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 247026282669..7d0821054729 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1243,7 +1243,6 @@ int ip_push_pending_frames(struct sock *sk) skb->len += tmp_skb->len; skb->data_len += tmp_skb->len; skb->truesize += tmp_skb->truesize; - __sock_put(tmp_skb->sk); tmp_skb->destructor = NULL; tmp_skb->sk = NULL; } diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c index 155c008626c8..09172a65d9b6 100644 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -191,7 +191,8 @@ nf_nat_mangle_tcp_packet(struct sk_buff *skb, ct, ctinfo); /* Tell TCP window tracking about seq change */ nf_conntrack_tcp_update(skb, ip_hdrlen(skb), - ct, CTINFO2DIR(ctinfo)); + ct, CTINFO2DIR(ctinfo), + (int)rep_len - (int)match_len); nf_conntrack_event_cache(IPCT_NATSEQADJ, ct); } @@ -377,6 +378,7 @@ nf_nat_seq_adjust(struct sk_buff *skb, struct tcphdr *tcph; int dir; __be32 newseq, newack; + s16 seqoff, ackoff; struct nf_conn_nat *nat = nfct_nat(ct); struct nf_nat_seq *this_way, *other_way; @@ -390,15 +392,18 @@ nf_nat_seq_adjust(struct sk_buff *skb, tcph = (void *)skb->data + ip_hdrlen(skb); if (after(ntohl(tcph->seq), this_way->correction_pos)) - newseq = htonl(ntohl(tcph->seq) + this_way->offset_after); + seqoff = this_way->offset_after; else - newseq = htonl(ntohl(tcph->seq) + this_way->offset_before); + seqoff = this_way->offset_before; if (after(ntohl(tcph->ack_seq) - other_way->offset_before, other_way->correction_pos)) - newack = htonl(ntohl(tcph->ack_seq) - other_way->offset_after); + ackoff = other_way->offset_after; else - newack = htonl(ntohl(tcph->ack_seq) - other_way->offset_before); + ackoff = other_way->offset_before; + + newseq = htonl(ntohl(tcph->seq) + seqoff); + newack = htonl(ntohl(tcph->ack_seq) - ackoff); inet_proto_csum_replace4(&tcph->check, skb, tcph->seq, newseq, 0); inet_proto_csum_replace4(&tcph->check, skb, tcph->ack_seq, newack, 0); @@ -413,7 +418,7 @@ nf_nat_seq_adjust(struct sk_buff *skb, if (!nf_nat_sack_adjust(skb, tcph, ct, ctinfo)) return 0; - nf_conntrack_tcp_update(skb, ip_hdrlen(skb), ct, dir); + nf_conntrack_tcp_update(skb, ip_hdrlen(skb), ct, dir, seqoff); return 1; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 17b89c523f9d..91145244ea63 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -339,7 +339,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) struct sock *sk = sock->sk; struct tcp_sock *tp = tcp_sk(sk); - poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk->sk_sleep, wait); if (sk->sk_state == TCP_LISTEN) return inet_csk_listen_poll(sk); @@ -903,13 +903,17 @@ int tcp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, iov++; while (seglen > 0) { - int copy; + int copy = 0; + int max = size_goal; skb = tcp_write_queue_tail(sk); + if (tcp_send_head(sk)) { + if (skb->ip_summed == CHECKSUM_NONE) + max = mss_now; + copy = max - skb->len; + } - if (!tcp_send_head(sk) || - (copy = size_goal - skb->len) <= 0) { - + if (copy <= 0) { new_segment: /* Allocate new segment. If the interface is SG, * allocate skb fitting to single page. @@ -930,6 +934,7 @@ new_segment: skb_entail(sk, skb); copy = size_goal; + max = size_goal; } /* Try to append data to the end of skb. */ @@ -1028,7 +1033,7 @@ new_segment: if ((seglen -= copy) == 0 && iovlen == 0) goto out; - if (skb->len < size_goal || (flags & MSG_OOB)) + if (skb->len < max || (flags & MSG_OOB)) continue; if (forced_push(tp)) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5a1ca2698c88..6d88219c5e22 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1160,6 +1160,7 @@ struct request_sock_ops tcp_request_sock_ops __read_mostly = { #ifdef CONFIG_TCP_MD5SIG static struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { .md5_lookup = tcp_v4_reqsk_md5_lookup, + .calc_md5_hash = tcp_v4_md5_hash_skb, }; #endif @@ -1373,7 +1374,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, */ char *newkey = kmemdup(key->key, key->keylen, GFP_ATOMIC); if (newkey != NULL) - tcp_v4_md5_do_add(newsk, inet_sk(sk)->daddr, + tcp_v4_md5_do_add(newsk, newinet->daddr, newkey, key->keylen); newsk->sk_route_caps &= ~NETIF_F_GSO_MASK; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 43bbba7926ee..f8d67ccc64f3 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -128,7 +128,8 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, goto kill_with_rst; /* Dup ACK? */ - if (!after(TCP_SKB_CB(skb)->end_seq, tcptw->tw_rcv_nxt) || + if (!th->ack || + !after(TCP_SKB_CB(skb)->end_seq, tcptw->tw_rcv_nxt) || TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) { inet_twsk_put(tw); return TCP_TW_SUCCESS; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 416fc4c2e7eb..bd62712848fa 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -725,7 +725,8 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int mss_now) { - if (skb->len <= mss_now || !sk_can_gso(sk)) { + if (skb->len <= mss_now || !sk_can_gso(sk) || + skb->ip_summed == CHECKSUM_NONE) { /* Avoid the costly divide in the normal * non-TSO case. */ @@ -2260,7 +2261,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, #ifdef CONFIG_TCP_MD5SIG /* Okay, we have all we need - do the md5 hash if needed */ if (md5) { - tp->af_specific->calc_md5_hash(md5_hash_location, + tcp_rsk(req)->af_specific->calc_md5_hash(md5_hash_location, md5, NULL, req, skb); } #endif diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 60d918c96a4f..0071ee6f441f 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -136,7 +136,8 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) case IPPROTO_TCP: case IPPROTO_SCTP: case IPPROTO_DCCP: - if (pskb_may_pull(skb, xprth + 4 - skb->data)) { + if (xprth + 4 < skb->data || + pskb_may_pull(skb, xprth + 4 - skb->data)) { __be16 *ports = (__be16 *)xprth; fl->fl_ip_sport = ports[!!reverse]; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 8c1e86afbbf5..43b3c9f89c12 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1916,8 +1916,32 @@ ok: update_lft = 1; else if (stored_lft <= MIN_VALID_LIFETIME) { /* valid_lft <= stored_lft is always true */ - /* XXX: IPsec */ - update_lft = 0; + /* + * RFC 4862 Section 5.5.3e: + * "Note that the preferred lifetime of + * the corresponding address is always + * reset to the Preferred Lifetime in + * the received Prefix Information + * option, regardless of whether the + * valid lifetime is also reset or + * ignored." + * + * So if the preferred lifetime in + * this advertisement is different + * than what we have stored, but the + * valid lifetime is invalid, just + * reset prefered_lft. + * + * We must set the valid lifetime + * to the stored lifetime since we'll + * be updating the timestamp below, + * else we'll set it back to the + * minumum. + */ + if (prefered_lft != ifp->prefered_lft) { + valid_lft = stored_lft; + update_lft = 1; + } } else { valid_lft = MIN_VALID_LIFETIME; if (valid_lft < prefered_lft) @@ -3085,7 +3109,7 @@ restart: spin_unlock(&ifp->lock); continue; } else if (age >= ifp->prefered_lft) { - /* jiffies - ifp->tsamp > age >= ifp->prefered_lft */ + /* jiffies - ifp->tstamp > age >= ifp->prefered_lft */ int deprecate = 0; if (!(ifp->flags&IFA_F_DEPRECATED)) { @@ -3362,7 +3386,10 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, valid = ifa->valid_lft; if (preferred != INFINITY_LIFE_TIME) { long tval = (jiffies - ifa->tstamp)/HZ; - preferred -= tval; + if (preferred > tval) + preferred -= tval; + else + preferred = 0; if (valid != INFINITY_LIFE_TIME) valid -= tval; } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 85b3d0036afd..caa0278d30a9 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1284,6 +1284,8 @@ static void __exit inet6_exit(void) proto_unregister(&udplitev6_prot); proto_unregister(&udpv6_prot); proto_unregister(&tcpv6_prot); + + rcu_barrier(); /* Wait for completion of call_rcu()'s */ } module_exit(inet6_exit); diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index c3a07d75b5f5..6d6a4277c677 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -139,6 +139,9 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt rcu_read_unlock(); + /* Must drop socket now because of tproxy. */ + skb_orphan(skb); + return NF_HOOK(PF_INET6, NF_INET_PRE_ROUTING, skb, dev, NULL, ip6_rcv_finish); err: diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 7c76e3d18215..87f8419a68fd 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1484,7 +1484,6 @@ int ip6_push_pending_frames(struct sock *sk) skb->len += tmp_skb->len; skb->data_len += tmp_skb->len; skb->truesize += tmp_skb->truesize; - __sock_put(tmp_skb->sk); tmp_skb->destructor = NULL; tmp_skb->sk = NULL; } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 68e52308e552..98b7327d0949 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1018,6 +1018,7 @@ static void ipip6_tunnel_setup(struct net_device *dev) dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr); dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr); dev->flags = IFF_NOARP; + dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; dev->iflink = 0; dev->addr_len = 4; dev->features |= NETIF_F_NETNS_LOCAL; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 58810c65b635..d849dd53b788 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -896,6 +896,7 @@ struct request_sock_ops tcp6_request_sock_ops __read_mostly = { #ifdef CONFIG_TCP_MD5SIG static struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .md5_lookup = tcp_v6_reqsk_md5_lookup, + .calc_md5_hash = tcp_v6_md5_hash_skb, }; #endif @@ -1441,7 +1442,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, */ char *newkey = kmemdup(key->key, key->keylen, GFP_ATOMIC); if (newkey != NULL) - tcp_v6_md5_do_add(newsk, &inet6_sk(sk)->daddr, + tcp_v6_md5_do_add(newsk, &newnp->daddr, newkey, key->keylen); } #endif diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index b4b16a43f277..3a3c677bc0f2 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -157,7 +157,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) ipv6_addr_copy(&fl->fl6_dst, reverse ? &hdr->saddr : &hdr->daddr); ipv6_addr_copy(&fl->fl6_src, reverse ? &hdr->daddr : &hdr->saddr); - while (pskb_may_pull(skb, nh + offset + 1 - skb->data)) { + while (nh + offset + 1 < skb->data || + pskb_may_pull(skb, nh + offset + 1 - skb->data)) { nh = skb_network_header(skb); exthdr = (struct ipv6_opt_hdr *)(nh + offset); @@ -177,7 +178,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) case IPPROTO_TCP: case IPPROTO_SCTP: case IPPROTO_DCCP: - if (!onlyproto && pskb_may_pull(skb, nh + offset + 4 - skb->data)) { + if (!onlyproto && (nh + offset + 4 < skb->data || + pskb_may_pull(skb, nh + offset + 4 - skb->data))) { __be16 *ports = (__be16 *)exthdr; fl->fl_ip_sport = ports[!!reverse]; diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index 417b0e309495..f1118d92a191 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -41,6 +41,7 @@ #include <linux/netdevice.h> #include <linux/uio.h> #include <linux/skbuff.h> +#include <linux/smp_lock.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/string.h> diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index cb762c8723ea..80cf29aae096 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -45,6 +45,7 @@ #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> +#include <linux/smp_lock.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/init.h> diff --git a/net/irda/irnet/irnet.h b/net/irda/irnet/irnet.h index bccf4d0059f0..b001c361ad30 100644 --- a/net/irda/irnet/irnet.h +++ b/net/irda/irnet/irnet.h @@ -241,7 +241,6 @@ #include <linux/module.h> #include <linux/kernel.h> -#include <linux/smp_lock.h> #include <linux/skbuff.h> #include <linux/tty.h> #include <linux/proc_fs.h> diff --git a/net/irda/irnet/irnet_ppp.c b/net/irda/irnet/irnet_ppp.c index 6d8ae03c14f5..68cbcb19cbd8 100644 --- a/net/irda/irnet/irnet_ppp.c +++ b/net/irda/irnet/irnet_ppp.c @@ -13,6 +13,7 @@ * 2) as a control channel (write commands, read events) */ +#include <linux/smp_lock.h> #include "irnet_ppp.h" /* Private header */ /* Please put other headers in irnet.h - Thanks */ diff --git a/net/irda/irttp.c b/net/irda/irttp.c index ecf4eb2717cb..9cb79f95bf63 100644 --- a/net/irda/irttp.c +++ b/net/irda/irttp.c @@ -1453,6 +1453,7 @@ struct tsap_cb *irttp_dup(struct tsap_cb *orig, void *instance) } /* Dup */ memcpy(new, orig, sizeof(struct tsap_cb)); + spin_lock_init(&new->lock); /* We don't need the old instance any more */ spin_unlock_irqrestore(&irttp->tsaps->hb_spinlock, flags); diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 6be5f92d1094..49c15b48408e 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -306,7 +306,7 @@ static inline int iucv_below_msglim(struct sock *sk) static void iucv_sock_wake_msglim(struct sock *sk) { read_lock(&sk->sk_callback_lock); - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + if (sk_has_sleeper(sk)) wake_up_interruptible_all(sk->sk_sleep); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); read_unlock(&sk->sk_callback_lock); @@ -1256,7 +1256,7 @@ unsigned int iucv_sock_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; unsigned int mask = 0; - poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk->sk_sleep, wait); if (sk->sk_state == IUCV_LISTEN) return iucv_accept_poll(sk); diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig index ba2643a43c73..7836ee928983 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -83,6 +83,7 @@ endmenu config MAC80211_MESH bool "Enable mac80211 mesh networking (pre-802.11s) support" depends on MAC80211 && EXPERIMENTAL + depends on BROKEN ---help--- This options enables support of Draft 802.11s mesh networking. The implementation is based on Draft 1.08 of the Mesh Networking diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index fc712e60705d..11cf45bce38a 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -494,7 +494,7 @@ void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata) * should it be using the interface and enqueuing * frames at this very time on another CPU. */ - synchronize_rcu(); + rcu_barrier(); /* Wait for RX path and call_rcu()'s */ skb_queue_purge(&sdata->u.mesh.skb_queue); } diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 003cb470ac84..f49ef288e2e2 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -637,7 +637,7 @@ static void mesh_queue_preq(struct mesh_path *mpath, u8 flags) struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; struct mesh_preq_queue *preq_node; - preq_node = kmalloc(sizeof(struct mesh_preq_queue), GFP_KERNEL); + preq_node = kmalloc(sizeof(struct mesh_preq_queue), GFP_ATOMIC); if (!preq_node) { printk(KERN_DEBUG "Mesh HWMP: could not allocate PREQ node\n"); return; diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 3c72557df45a..479597e88583 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -175,6 +175,8 @@ int mesh_path_add(u8 *dst, struct ieee80211_sub_if_data *sdata) int err = 0; u32 hash_idx; + might_sleep(); + if (memcmp(dst, sdata->dev->dev_addr, ETH_ALEN) == 0) /* never add ourselves as neighbours */ return -ENOTSUPP; @@ -265,6 +267,7 @@ int mpp_path_add(u8 *dst, u8 *mpp, struct ieee80211_sub_if_data *sdata) int err = 0; u32 hash_idx; + might_sleep(); if (memcmp(dst, sdata->dev->dev_addr, ETH_ALEN) == 0) /* never add ourselves as neighbours */ @@ -491,8 +494,10 @@ void mesh_path_tx_pending(struct mesh_path *mpath) * @skb: frame to discard * @sdata: network subif the frame was to be sent through * - * If the frame was beign forwarded from another MP, a PERR frame will be sent - * to the precursor. + * If the frame was being forwarded from another MP, a PERR frame will be sent + * to the precursor. The precursor's address (i.e. the previous hop) was saved + * in addr1 of the frame-to-be-forwarded, and would only be overwritten once + * the destination is successfully resolved. * * Locking: the function must me called within a rcu_read_lock region */ @@ -507,7 +512,7 @@ void mesh_path_discard_frame(struct sk_buff *skb, u8 *ra, *da; da = hdr->addr3; - ra = hdr->addr2; + ra = hdr->addr1; mpath = mesh_path_lookup(da, sdata); if (mpath) dsn = ++mpath->dsn; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index aca22b00b6a3..07e7e41816be 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -721,7 +721,7 @@ void ieee80211_dynamic_ps_timer(unsigned long data) { struct ieee80211_local *local = (void *) data; - if (local->quiescing) + if (local->quiescing || local->suspended) return; queue_work(local->hw.workqueue, &local->dynamic_ps_enable_work); diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index 7a549f9deb96..5e3d476972f9 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -55,15 +55,6 @@ int __ieee80211_suspend(struct ieee80211_hw *hw) rcu_read_unlock(); - /* flush again, in case driver queued work */ - flush_workqueue(local->hw.workqueue); - - /* stop hardware - this must stop RX */ - if (local->open_count) { - ieee80211_led_radio(local, false); - drv_stop(local); - } - /* remove STAs */ spin_lock_irqsave(&local->sta_lock, flags); list_for_each_entry(sta, &local->sta_list, list) { @@ -111,7 +102,22 @@ int __ieee80211_suspend(struct ieee80211_hw *hw) drv_remove_interface(local, &conf); } + /* stop hardware - this must stop RX */ + if (local->open_count) { + ieee80211_led_radio(local, false); + drv_stop(local); + } + + /* + * flush again, in case driver queued work -- it + * shouldn't be doing (or cancel everything in the + * stop callback) that but better safe than sorry. + */ + flush_workqueue(local->hw.workqueue); + local->suspended = true; + /* need suspended to be visible before quiescing is false */ + barrier(); local->quiescing = false; return 0; diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index b218b98fba7f..37771abd8f5a 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -66,7 +66,7 @@ rix_to_ndx(struct minstrel_sta_info *mi, int rix) for (i = rix; i >= 0; i--) if (mi->r[i].rix == rix) break; - WARN_ON(mi->r[i].rix != rix); + WARN_ON(i < 0); return i; } @@ -181,6 +181,9 @@ minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband, break; ndx = rix_to_ndx(mi, ar[i].idx); + if (ndx < 0) + continue; + mi->r[ndx].attempts += ar[i].count; if ((i != IEEE80211_TX_MAX_RATES - 1) && (ar[i + 1].idx < 0)) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index de5bba7f910a..0936fc24942d 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2453,6 +2453,18 @@ void __ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb, return; } + /* + * If we're suspending, it is possible although not too likely + * that we'd be receiving frames after having already partially + * quiesced the stack. We can't process such frames then since + * that might, for example, cause stations to be added or other + * driver callbacks be invoked. + */ + if (unlikely(local->quiescing || local->suspended)) { + kfree_skb(skb); + return; + } + if (status->flag & RX_FLAG_HT) { /* rate_idx is MCS index */ if (WARN_ON(status->rate_idx < 0 || diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index d238a8939a09..3a8922cd1038 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1455,7 +1455,7 @@ int ieee80211_master_start_xmit(struct sk_buff *skb, struct net_device *dev) monitor_iface = UNKNOWN_ADDRESS; len_rthdr = ieee80211_get_radiotap_len(skb->data); - hdr = (struct ieee80211_hdr *)skb->data + len_rthdr; + hdr = (struct ieee80211_hdr *)(skb->data + len_rthdr); hdrlen = ieee80211_hdrlen(hdr->frame_control); /* check the header is complete in the frame */ diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 7508f11c5b39..b5869b9574b0 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -561,23 +561,38 @@ struct nf_conn *nf_conntrack_alloc(struct net *net, } } - ct = kmem_cache_zalloc(nf_conntrack_cachep, gfp); + /* + * Do not use kmem_cache_zalloc(), as this cache uses + * SLAB_DESTROY_BY_RCU. + */ + ct = kmem_cache_alloc(nf_conntrack_cachep, gfp); if (ct == NULL) { pr_debug("nf_conntrack_alloc: Can't alloc conntrack.\n"); atomic_dec(&net->ct.count); return ERR_PTR(-ENOMEM); } - + /* + * Let ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.next + * and ct->tuplehash[IP_CT_DIR_REPLY].hnnode.next unchanged. + */ + memset(&ct->tuplehash[IP_CT_DIR_MAX], 0, + sizeof(*ct) - offsetof(struct nf_conn, tuplehash[IP_CT_DIR_MAX])); spin_lock_init(&ct->lock); - atomic_set(&ct->ct_general.use, 1); ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig; + ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.pprev = NULL; ct->tuplehash[IP_CT_DIR_REPLY].tuple = *repl; + ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev = NULL; /* Don't set timer yet: wait for confirmation */ setup_timer(&ct->timeout, death_by_timeout, (unsigned long)ct); #ifdef CONFIG_NET_NS ct->ct_net = net; #endif + /* + * changes to lookup keys must be done before setting refcnt to 1 + */ + smp_wmb(); + atomic_set(&ct->ct_general.use, 1); return ct; } EXPORT_SYMBOL_GPL(nf_conntrack_alloc); diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index afde8f991646..2032dfe25ca8 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -617,8 +617,10 @@ err1: void nf_conntrack_expect_fini(struct net *net) { exp_proc_remove(net); - if (net_eq(net, &init_net)) + if (net_eq(net, &init_net)) { + rcu_barrier(); /* Wait for call_rcu() before destroy */ kmem_cache_destroy(nf_ct_expect_cachep); + } nf_ct_free_hashtable(net->ct.expect_hash, net->ct.expect_vmalloc, nf_ct_expect_hsize); } diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 4b2c769d555f..fef95be334bd 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -186,6 +186,6 @@ void nf_ct_extend_unregister(struct nf_ct_ext_type *type) rcu_assign_pointer(nf_ct_ext_types[type->id], NULL); update_alloc_size(type); mutex_unlock(&nf_ct_ext_type_mutex); - synchronize_rcu(); + rcu_barrier(); /* Wait for completion of call_rcu()'s */ } EXPORT_SYMBOL_GPL(nf_ct_extend_unregister); diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 33fc0a443f3d..97a82ba75376 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -720,8 +720,8 @@ static bool tcp_in_window(const struct nf_conn *ct, /* Caller must linearize skb at tcp header. */ void nf_conntrack_tcp_update(const struct sk_buff *skb, unsigned int dataoff, - struct nf_conn *ct, - int dir) + struct nf_conn *ct, int dir, + s16 offset) { const struct tcphdr *tcph = (const void *)skb->data + dataoff; const struct ip_ct_tcp_state *sender = &ct->proto.tcp.seen[dir]; @@ -734,7 +734,7 @@ void nf_conntrack_tcp_update(const struct sk_buff *skb, /* * We have to worry for the ack in the reply packet only... */ - if (after(end, ct->proto.tcp.seen[dir].td_end)) + if (ct->proto.tcp.seen[dir].td_end + offset == end) ct->proto.tcp.seen[dir].td_end = end; ct->proto.tcp.last_end = end; spin_unlock_bh(&ct->lock); diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c index 0b7139f3dd78..fc581800698e 100644 --- a/net/netfilter/xt_conntrack.c +++ b/net/netfilter/xt_conntrack.c @@ -129,7 +129,7 @@ conntrack_addrcmp(const union nf_inet_addr *kaddr, static inline bool conntrack_mt_origsrc(const struct nf_conn *ct, - const struct xt_conntrack_mtinfo1 *info, + const struct xt_conntrack_mtinfo2 *info, u_int8_t family) { return conntrack_addrcmp(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3, @@ -138,7 +138,7 @@ conntrack_mt_origsrc(const struct nf_conn *ct, static inline bool conntrack_mt_origdst(const struct nf_conn *ct, - const struct xt_conntrack_mtinfo1 *info, + const struct xt_conntrack_mtinfo2 *info, u_int8_t family) { return conntrack_addrcmp(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3, @@ -147,7 +147,7 @@ conntrack_mt_origdst(const struct nf_conn *ct, static inline bool conntrack_mt_replsrc(const struct nf_conn *ct, - const struct xt_conntrack_mtinfo1 *info, + const struct xt_conntrack_mtinfo2 *info, u_int8_t family) { return conntrack_addrcmp(&ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3, @@ -156,7 +156,7 @@ conntrack_mt_replsrc(const struct nf_conn *ct, static inline bool conntrack_mt_repldst(const struct nf_conn *ct, - const struct xt_conntrack_mtinfo1 *info, + const struct xt_conntrack_mtinfo2 *info, u_int8_t family) { return conntrack_addrcmp(&ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3, @@ -164,7 +164,7 @@ conntrack_mt_repldst(const struct nf_conn *ct, } static inline bool -ct_proto_port_check(const struct xt_conntrack_mtinfo1 *info, +ct_proto_port_check(const struct xt_conntrack_mtinfo2 *info, const struct nf_conn *ct) { const struct nf_conntrack_tuple *tuple; @@ -204,7 +204,7 @@ ct_proto_port_check(const struct xt_conntrack_mtinfo1 *info, static bool conntrack_mt(const struct sk_buff *skb, const struct xt_match_param *par) { - const struct xt_conntrack_mtinfo1 *info = par->matchinfo; + const struct xt_conntrack_mtinfo2 *info = par->matchinfo; enum ip_conntrack_info ctinfo; const struct nf_conn *ct; unsigned int statebit; @@ -278,6 +278,16 @@ conntrack_mt(const struct sk_buff *skb, const struct xt_match_param *par) return true; } +static bool +conntrack_mt_v1(const struct sk_buff *skb, const struct xt_match_param *par) +{ + const struct xt_conntrack_mtinfo2 *const *info = par->matchinfo; + struct xt_match_param newpar = *par; + + newpar.matchinfo = *info; + return conntrack_mt(skb, &newpar); +} + static bool conntrack_mt_check(const struct xt_mtchk_param *par) { if (nf_ct_l3proto_try_module_get(par->family) < 0) { @@ -288,11 +298,45 @@ static bool conntrack_mt_check(const struct xt_mtchk_param *par) return true; } +static bool conntrack_mt_check_v1(const struct xt_mtchk_param *par) +{ + struct xt_conntrack_mtinfo1 *info = par->matchinfo; + struct xt_conntrack_mtinfo2 *up; + int ret = conntrack_mt_check(par); + + if (ret < 0) + return ret; + + up = kmalloc(sizeof(*up), GFP_KERNEL); + if (up == NULL) { + nf_ct_l3proto_module_put(par->family); + return -ENOMEM; + } + + /* + * The strategy here is to minimize the overhead of v1 matching, + * by prebuilding a v2 struct and putting the pointer into the + * v1 dataspace. + */ + memcpy(up, info, offsetof(typeof(*info), state_mask)); + up->state_mask = info->state_mask; + up->status_mask = info->status_mask; + *(void **)info = up; + return true; +} + static void conntrack_mt_destroy(const struct xt_mtdtor_param *par) { nf_ct_l3proto_module_put(par->family); } +static void conntrack_mt_destroy_v1(const struct xt_mtdtor_param *par) +{ + struct xt_conntrack_mtinfo2 **info = par->matchinfo; + kfree(*info); + conntrack_mt_destroy(par); +} + #ifdef CONFIG_COMPAT struct compat_xt_conntrack_info { @@ -363,6 +407,16 @@ static struct xt_match conntrack_mt_reg[] __read_mostly = { .revision = 1, .family = NFPROTO_UNSPEC, .matchsize = sizeof(struct xt_conntrack_mtinfo1), + .match = conntrack_mt_v1, + .checkentry = conntrack_mt_check_v1, + .destroy = conntrack_mt_destroy_v1, + .me = THIS_MODULE, + }, + { + .name = "conntrack", + .revision = 2, + .family = NFPROTO_UNSPEC, + .matchsize = sizeof(struct xt_conntrack_mtinfo2), .match = conntrack_mt, .checkentry = conntrack_mt_check, .destroy = conntrack_mt_destroy, diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index 863e40977a4d..0f482e2440b4 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -330,7 +330,8 @@ static bool xt_osf_match_packet(const struct sk_buff *skb, fcount++; if (info->flags & XT_OSF_LOG) - nf_log_packet(p->hooknum, 0, skb, p->in, p->out, NULL, + nf_log_packet(p->family, p->hooknum, skb, + p->in, p->out, NULL, "%s [%s:%s] : %pi4:%d -> %pi4:%d hops=%d\n", f->genre, f->version, f->subtype, &ip->saddr, ntohs(tcp->source), @@ -345,7 +346,7 @@ static bool xt_osf_match_packet(const struct sk_buff *skb, rcu_read_unlock(); if (!fcount && (info->flags & XT_OSF_LOG)) - nf_log_packet(p->hooknum, 0, skb, p->in, p->out, NULL, + nf_log_packet(p->family, p->hooknum, skb, p->in, p->out, NULL, "Remote OS is not known: %pi4:%u -> %pi4:%u\n", &ip->saddr, ntohs(tcp->source), &ip->daddr, ntohs(tcp->dest)); diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index b0e582f2d37a..16e6c4378ff1 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -151,7 +151,7 @@ int netlbl_cfg_unlbl_map_add(const char *domain, addr6 = addr; mask6 = mask; map6 = kzalloc(sizeof(*map6), GFP_ATOMIC); - if (map4 == NULL) + if (map6 == NULL) goto cfg_unlbl_map_add_failure; map6->type = NETLBL_NLTYPE_UNLABELED; ipv6_addr_copy(&map6->list.addr, addr6); diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index 80a322d77909..b0d6ddd82a9d 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -69,10 +69,27 @@ static struct phonet_device *__phonet_get(struct net_device *dev) return NULL; } -static void __phonet_device_free(struct phonet_device *pnd) +static void phonet_device_destroy(struct net_device *dev) { - list_del(&pnd->list); - kfree(pnd); + struct phonet_device_list *pndevs = phonet_device_list(dev_net(dev)); + struct phonet_device *pnd; + + ASSERT_RTNL(); + + spin_lock_bh(&pndevs->lock); + pnd = __phonet_get(dev); + if (pnd) + list_del(&pnd->list); + spin_unlock_bh(&pndevs->lock); + + if (pnd) { + u8 addr; + + for (addr = find_first_bit(pnd->addrs, 64); addr < 64; + addr = find_next_bit(pnd->addrs, 64, 1+addr)) + phonet_address_notify(RTM_DELADDR, dev, addr); + kfree(pnd); + } } struct net_device *phonet_device_get(struct net *net) @@ -126,8 +143,10 @@ int phonet_address_del(struct net_device *dev, u8 addr) pnd = __phonet_get(dev); if (!pnd || !test_and_clear_bit(addr >> 2, pnd->addrs)) err = -EADDRNOTAVAIL; - else if (bitmap_empty(pnd->addrs, 64)) - __phonet_device_free(pnd); + else if (bitmap_empty(pnd->addrs, 64)) { + list_del(&pnd->list); + kfree(pnd); + } spin_unlock_bh(&pndevs->lock); return err; } @@ -181,18 +200,8 @@ static int phonet_device_notify(struct notifier_block *me, unsigned long what, { struct net_device *dev = arg; - if (what == NETDEV_UNREGISTER) { - struct phonet_device_list *pndevs; - struct phonet_device *pnd; - - /* Destroy phonet-specific device data */ - pndevs = phonet_device_list(dev_net(dev)); - spin_lock_bh(&pndevs->lock); - pnd = __phonet_get(dev); - if (pnd) - __phonet_device_free(pnd); - spin_unlock_bh(&pndevs->lock); - } + if (what == NETDEV_UNREGISTER) + phonet_device_destroy(dev); return 0; } @@ -218,11 +227,12 @@ static int phonet_init_net(struct net *net) static void phonet_exit_net(struct net *net) { struct phonet_net *pnn = net_generic(net, phonet_net_id); - struct phonet_device *pnd, *n; - - list_for_each_entry_safe(pnd, n, &pnn->pndevs.list, list) - __phonet_device_free(pnd); + struct net_device *dev; + rtnl_lock(); + for_each_netdev(net, dev) + phonet_device_destroy(dev); + rtnl_unlock(); kfree(pnn); } diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index cec4e5951681..f8b4cee434c2 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -32,7 +32,7 @@ static int fill_addr(struct sk_buff *skb, struct net_device *dev, u8 addr, u32 pid, u32 seq, int event); -static void rtmsg_notify(int event, struct net_device *dev, u8 addr) +void phonet_address_notify(int event, struct net_device *dev, u8 addr) { struct sk_buff *skb; int err = -ENOBUFS; @@ -94,7 +94,7 @@ static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *attr) else err = phonet_address_del(dev, pnaddr); if (!err) - rtmsg_notify(nlh->nlmsg_type, dev, pnaddr); + phonet_address_notify(nlh->nlmsg_type, dev, pnaddr); return err; } diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 79693fe2001e..2fc4a1724eb8 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -549,6 +549,10 @@ void rfkill_set_states(struct rfkill *rfkill, bool sw, bool hw) swprev = !!(rfkill->state & RFKILL_BLOCK_SW); hwprev = !!(rfkill->state & RFKILL_BLOCK_HW); __rfkill_set_sw_state(rfkill, sw); + if (hw) + rfkill->state |= RFKILL_BLOCK_HW; + else + rfkill->state &= ~RFKILL_BLOCK_HW; spin_unlock_irqrestore(&rfkill->lock, flags); @@ -648,15 +652,26 @@ static ssize_t rfkill_state_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - /* - * The intention was that userspace can only take control over - * a given device when/if rfkill-input doesn't control it due - * to user_claim. Since user_claim is currently unsupported, - * we never support changing the state from userspace -- this - * can be implemented again later. - */ + struct rfkill *rfkill = to_rfkill(dev); + unsigned long state; + int err; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + err = strict_strtoul(buf, 0, &state); + if (err) + return err; + + if (state != RFKILL_USER_STATE_SOFT_BLOCKED && + state != RFKILL_USER_STATE_UNBLOCKED) + return -EINVAL; + + mutex_lock(&rfkill_global_mutex); + rfkill_set_block(rfkill, state == RFKILL_USER_STATE_SOFT_BLOCKED); + mutex_unlock(&rfkill_global_mutex); - return -EPERM; + return err ?: count; } static ssize_t rfkill_claim_show(struct device *dev, diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 6bd8e93869ed..f0a76f6bca71 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -92,23 +92,21 @@ static void rose_set_lockdep_key(struct net_device *dev) /* * Convert a ROSE address into text. */ -const char *rose2asc(const rose_address *addr) +char *rose2asc(char *buf, const rose_address *addr) { - static char buffer[11]; - if (addr->rose_addr[0] == 0x00 && addr->rose_addr[1] == 0x00 && addr->rose_addr[2] == 0x00 && addr->rose_addr[3] == 0x00 && addr->rose_addr[4] == 0x00) { - strcpy(buffer, "*"); + strcpy(buf, "*"); } else { - sprintf(buffer, "%02X%02X%02X%02X%02X", addr->rose_addr[0] & 0xFF, + sprintf(buf, "%02X%02X%02X%02X%02X", addr->rose_addr[0] & 0xFF, addr->rose_addr[1] & 0xFF, addr->rose_addr[2] & 0xFF, addr->rose_addr[3] & 0xFF, addr->rose_addr[4] & 0xFF); } - return buffer; + return buf; } /* @@ -1437,7 +1435,7 @@ static void rose_info_stop(struct seq_file *seq, void *v) static int rose_info_show(struct seq_file *seq, void *v) { - char buf[11]; + char buf[11], rsbuf[11]; if (v == SEQ_START_TOKEN) seq_puts(seq, @@ -1455,8 +1453,8 @@ static int rose_info_show(struct seq_file *seq, void *v) devname = dev->name; seq_printf(seq, "%-10s %-9s ", - rose2asc(&rose->dest_addr), - ax2asc(buf, &rose->dest_call)); + rose2asc(rsbuf, &rose->dest_addr), + ax2asc(buf, &rose->dest_call)); if (ax25cmp(&rose->source_call, &null_ax25_address) == 0) callsign = "??????-?"; @@ -1465,7 +1463,7 @@ static int rose_info_show(struct seq_file *seq, void *v) seq_printf(seq, "%-10s %-9s %-5s %3.3X %05d %d %d %d %d %3lu %3lu %3lu %3lu %3lu %3lu/%03lu %5d %5d %ld\n", - rose2asc(&rose->source_addr), + rose2asc(rsbuf, &rose->source_addr), callsign, devname, rose->lci & 0x0FFF, diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index a81066a1010a..9478d9b3d977 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -1104,6 +1104,7 @@ static void rose_node_stop(struct seq_file *seq, void *v) static int rose_node_show(struct seq_file *seq, void *v) { + char rsbuf[11]; int i; if (v == SEQ_START_TOKEN) @@ -1112,13 +1113,13 @@ static int rose_node_show(struct seq_file *seq, void *v) const struct rose_node *rose_node = v; /* if (rose_node->loopback) { seq_printf(seq, "%-10s %04d 1 loopback\n", - rose2asc(&rose_node->address), - rose_node->mask); + rose2asc(rsbuf, &rose_node->address), + rose_node->mask); } else { */ seq_printf(seq, "%-10s %04d %d", - rose2asc(&rose_node->address), - rose_node->mask, - rose_node->count); + rose2asc(rsbuf, &rose_node->address), + rose_node->mask, + rose_node->count); for (i = 0; i < rose_node->count; i++) seq_printf(seq, " %05d", @@ -1267,7 +1268,7 @@ static void rose_route_stop(struct seq_file *seq, void *v) static int rose_route_show(struct seq_file *seq, void *v) { - char buf[11]; + char buf[11], rsbuf[11]; if (v == SEQ_START_TOKEN) seq_puts(seq, @@ -1279,7 +1280,7 @@ static int rose_route_show(struct seq_file *seq, void *v) seq_printf(seq, "%3.3X %-10s %-9s %05d ", rose_route->lci1, - rose2asc(&rose_route->src_addr), + rose2asc(rsbuf, &rose_route->src_addr), ax2asc(buf, &rose_route->src_call), rose_route->neigh1->number); else @@ -1289,10 +1290,10 @@ static int rose_route_show(struct seq_file *seq, void *v) if (rose_route->neigh2) seq_printf(seq, "%3.3X %-10s %-9s %05d\n", - rose_route->lci2, - rose2asc(&rose_route->dest_addr), - ax2asc(buf, &rose_route->dest_call), - rose_route->neigh2->number); + rose_route->lci2, + rose2asc(rsbuf, &rose_route->dest_addr), + ax2asc(buf, &rose_route->dest_call), + rose_route->neigh2->number); else seq_puts(seq, "000 * * 00000\n"); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index eac5e7bb7365..bfe493ebf27c 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -63,7 +63,7 @@ static void rxrpc_write_space(struct sock *sk) _enter("%p", sk); read_lock(&sk->sk_callback_lock); if (rxrpc_writable(sk)) { - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + if (sk_has_sleeper(sk)) wake_up_interruptible(sk->sk_sleep); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } @@ -588,7 +588,7 @@ static unsigned int rxrpc_poll(struct file *file, struct socket *sock, unsigned int mask; struct sock *sk = sock->sk; - poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk->sk_sleep, wait); mask = 0; /* the socket is readable if there are any messages waiting on the Rx diff --git a/net/sctp/output.c b/net/sctp/output.c index b76411444515..b94c21190566 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -407,7 +407,7 @@ int sctp_packet_transmit(struct sctp_packet *packet) } dst = dst_clone(tp->dst); skb_dst_set(nskb, dst); - if (dst) + if (!dst) goto no_route; /* Build the SCTP header. */ diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 35ba035970a2..971890dbfea0 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -6652,21 +6652,6 @@ static void sctp_wait_for_close(struct sock *sk, long timeout) finish_wait(sk->sk_sleep, &wait); } -static void sctp_sock_rfree_frag(struct sk_buff *skb) -{ - struct sk_buff *frag; - - if (!skb->data_len) - goto done; - - /* Don't forget the fragments. */ - skb_walk_frags(skb, frag) - sctp_sock_rfree_frag(frag); - -done: - sctp_sock_rfree(skb); -} - static void sctp_skb_set_owner_r_frag(struct sk_buff *skb, struct sock *sk) { struct sk_buff *frag; @@ -6776,7 +6761,6 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, sctp_skb_for_each(skb, &oldsk->sk_receive_queue, tmp) { event = sctp_skb2event(skb); if (event->asoc == assoc) { - sctp_sock_rfree_frag(skb); __skb_unlink(skb, &oldsk->sk_receive_queue); __skb_queue_tail(&newsk->sk_receive_queue, skb); sctp_skb_set_owner_r_frag(skb, newsk); @@ -6807,7 +6791,6 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, sctp_skb_for_each(skb, &oldsp->pd_lobby, tmp) { event = sctp_skb2event(skb); if (event->asoc == assoc) { - sctp_sock_rfree_frag(skb); __skb_unlink(skb, &oldsp->pd_lobby); __skb_queue_tail(queue, skb); sctp_skb_set_owner_r_frag(skb, newsk); @@ -6822,15 +6805,11 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, } - sctp_skb_for_each(skb, &assoc->ulpq.reasm, tmp) { - sctp_sock_rfree_frag(skb); + sctp_skb_for_each(skb, &assoc->ulpq.reasm, tmp) sctp_skb_set_owner_r_frag(skb, newsk); - } - sctp_skb_for_each(skb, &assoc->ulpq.lobby, tmp) { - sctp_sock_rfree_frag(skb); + sctp_skb_for_each(skb, &assoc->ulpq.lobby, tmp) sctp_skb_set_owner_r_frag(skb, newsk); - } /* Set the type of socket to indicate that it is peeled off from the * original UDP-style socket or created with the accept() call on a diff --git a/net/socket.c b/net/socket.c index 791d71a36a93..6d4716559047 100644 --- a/net/socket.c +++ b/net/socket.c @@ -736,7 +736,7 @@ static ssize_t sock_sendpage(struct file *file, struct page *page, if (more) flags |= MSG_MORE; - return sock->ops->sendpage(sock, page, offset, size, flags); + return kernel_sendpage(sock, page, offset, size, flags); } static ssize_t sock_splice_read(struct file *file, loff_t *ppos, diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile index db73fd2a3f0e..9d2fca5ad14a 100644 --- a/net/sunrpc/Makefile +++ b/net/sunrpc/Makefile @@ -10,7 +10,7 @@ obj-$(CONFIG_SUNRPC_XPRT_RDMA) += xprtrdma/ sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \ auth.o auth_null.o auth_unix.o auth_generic.o \ svc.o svcsock.o svcauth.o svcauth_unix.o \ - rpcb_clnt.o timer.o xdr.o \ + addr.o rpcb_clnt.o timer.o xdr.o \ sunrpc_syms.o cache.o rpc_pipe.o \ svc_xprt.o sunrpc-$(CONFIG_NFS_V4_1) += backchannel_rqst.o bc_svc.o diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c new file mode 100644 index 000000000000..22e8fd89477f --- /dev/null +++ b/net/sunrpc/addr.c @@ -0,0 +1,364 @@ +/* + * Copyright 2009, Oracle. All rights reserved. + * + * Convert socket addresses to presentation addresses and universal + * addresses, and vice versa. + * + * Universal addresses are introduced by RFC 1833 and further refined by + * recent RFCs describing NFSv4. The universal address format is part + * of the external (network) interface provided by rpcbind version 3 + * and 4, and by NFSv4. Such an address is a string containing a + * presentation format IP address followed by a port number in + * "hibyte.lobyte" format. + * + * IPv6 addresses can also include a scope ID, typically denoted by + * a '%' followed by a device name or a non-negative integer. Refer to + * RFC 4291, Section 2.2 for details on IPv6 presentation formats. + */ + +#include <net/ipv6.h> +#include <linux/sunrpc/clnt.h> + +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + +static size_t rpc_ntop6_noscopeid(const struct sockaddr *sap, + char *buf, const int buflen) +{ + const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap; + const struct in6_addr *addr = &sin6->sin6_addr; + + /* + * RFC 4291, Section 2.2.2 + * + * Shorthanded ANY address + */ + if (ipv6_addr_any(addr)) + return snprintf(buf, buflen, "::"); + + /* + * RFC 4291, Section 2.2.2 + * + * Shorthanded loopback address + */ + if (ipv6_addr_loopback(addr)) + return snprintf(buf, buflen, "::1"); + + /* + * RFC 4291, Section 2.2.3 + * + * Special presentation address format for mapped v4 + * addresses. + */ + if (ipv6_addr_v4mapped(addr)) + return snprintf(buf, buflen, "::ffff:%pI4", + &addr->s6_addr32[3]); + + /* + * RFC 4291, Section 2.2.1 + * + * To keep the result as short as possible, especially + * since we don't shorthand, we don't want leading zeros + * in each halfword, so avoid %pI6. + */ + return snprintf(buf, buflen, "%x:%x:%x:%x:%x:%x:%x:%x", + ntohs(addr->s6_addr16[0]), ntohs(addr->s6_addr16[1]), + ntohs(addr->s6_addr16[2]), ntohs(addr->s6_addr16[3]), + ntohs(addr->s6_addr16[4]), ntohs(addr->s6_addr16[5]), + ntohs(addr->s6_addr16[6]), ntohs(addr->s6_addr16[7])); +} + +static size_t rpc_ntop6(const struct sockaddr *sap, + char *buf, const size_t buflen) +{ + const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap; + char scopebuf[IPV6_SCOPE_ID_LEN]; + size_t len; + int rc; + + len = rpc_ntop6_noscopeid(sap, buf, buflen); + if (unlikely(len == 0)) + return len; + + if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) && + !(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_SITELOCAL)) + return len; + + rc = snprintf(scopebuf, sizeof(scopebuf), "%c%u", + IPV6_SCOPE_DELIMITER, sin6->sin6_scope_id); + if (unlikely((size_t)rc > sizeof(scopebuf))) + return 0; + + len += rc; + if (unlikely(len > buflen)) + return 0; + + strcat(buf, scopebuf); + return len; +} + +#else /* !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)) */ + +static size_t rpc_ntop6_noscopeid(const struct sockaddr *sap, + char *buf, const int buflen) +{ + return 0; +} + +static size_t rpc_ntop6(const struct sockaddr *sap, + char *buf, const size_t buflen) +{ + return 0; +} + +#endif /* !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)) */ + +static int rpc_ntop4(const struct sockaddr *sap, + char *buf, const size_t buflen) +{ + const struct sockaddr_in *sin = (struct sockaddr_in *)sap; + + return snprintf(buf, buflen, "%pI4", &sin->sin_addr); +} + +/** + * rpc_ntop - construct a presentation address in @buf + * @sap: socket address + * @buf: construction area + * @buflen: size of @buf, in bytes + * + * Plants a %NUL-terminated string in @buf and returns the length + * of the string, excluding the %NUL. Otherwise zero is returned. + */ +size_t rpc_ntop(const struct sockaddr *sap, char *buf, const size_t buflen) +{ + switch (sap->sa_family) { + case AF_INET: + return rpc_ntop4(sap, buf, buflen); + case AF_INET6: + return rpc_ntop6(sap, buf, buflen); + } + + return 0; +} +EXPORT_SYMBOL_GPL(rpc_ntop); + +static size_t rpc_pton4(const char *buf, const size_t buflen, + struct sockaddr *sap, const size_t salen) +{ + struct sockaddr_in *sin = (struct sockaddr_in *)sap; + u8 *addr = (u8 *)&sin->sin_addr.s_addr; + + if (buflen > INET_ADDRSTRLEN || salen < sizeof(struct sockaddr_in)) + return 0; + + memset(sap, 0, sizeof(struct sockaddr_in)); + + if (in4_pton(buf, buflen, addr, '\0', NULL) == 0) + return 0; + + sin->sin_family = AF_INET; + return sizeof(struct sockaddr_in);; +} + +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +static int rpc_parse_scope_id(const char *buf, const size_t buflen, + const char *delim, struct sockaddr_in6 *sin6) +{ + char *p; + size_t len; + + if ((buf + buflen) == delim) + return 1; + + if (*delim != IPV6_SCOPE_DELIMITER) + return 0; + + if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) && + !(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_SITELOCAL)) + return 0; + + len = (buf + buflen) - delim - 1; + p = kstrndup(delim + 1, len, GFP_KERNEL); + if (p) { + unsigned long scope_id = 0; + struct net_device *dev; + + dev = dev_get_by_name(&init_net, p); + if (dev != NULL) { + scope_id = dev->ifindex; + dev_put(dev); + } else { + if (strict_strtoul(p, 10, &scope_id) == 0) { + kfree(p); + return 0; + } + } + + kfree(p); + + sin6->sin6_scope_id = scope_id; + return 1; + } + + return 0; +} + +static size_t rpc_pton6(const char *buf, const size_t buflen, + struct sockaddr *sap, const size_t salen) +{ + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap; + u8 *addr = (u8 *)&sin6->sin6_addr.in6_u; + const char *delim; + + if (buflen > (INET6_ADDRSTRLEN + IPV6_SCOPE_ID_LEN) || + salen < sizeof(struct sockaddr_in6)) + return 0; + + memset(sap, 0, sizeof(struct sockaddr_in6)); + + if (in6_pton(buf, buflen, addr, IPV6_SCOPE_DELIMITER, &delim) == 0) + return 0; + + if (!rpc_parse_scope_id(buf, buflen, delim, sin6)) + return 0; + + sin6->sin6_family = AF_INET6; + return sizeof(struct sockaddr_in6); +} +#else +static size_t rpc_pton6(const char *buf, const size_t buflen, + struct sockaddr *sap, const size_t salen) +{ + return 0; +} +#endif + +/** + * rpc_pton - Construct a sockaddr in @sap + * @buf: C string containing presentation format IP address + * @buflen: length of presentation address in bytes + * @sap: buffer into which to plant socket address + * @salen: size of buffer in bytes + * + * Returns the size of the socket address if successful; otherwise + * zero is returned. + * + * Plants a socket address in @sap and returns the size of the + * socket address, if successful. Returns zero if an error + * occurred. + */ +size_t rpc_pton(const char *buf, const size_t buflen, + struct sockaddr *sap, const size_t salen) +{ + unsigned int i; + + for (i = 0; i < buflen; i++) + if (buf[i] == ':') + return rpc_pton6(buf, buflen, sap, salen); + return rpc_pton4(buf, buflen, sap, salen); +} +EXPORT_SYMBOL_GPL(rpc_pton); + +/** + * rpc_sockaddr2uaddr - Construct a universal address string from @sap. + * @sap: socket address + * + * Returns a %NUL-terminated string in dynamically allocated memory; + * otherwise NULL is returned if an error occurred. Caller must + * free the returned string. + */ +char *rpc_sockaddr2uaddr(const struct sockaddr *sap) +{ + char portbuf[RPCBIND_MAXUADDRPLEN]; + char addrbuf[RPCBIND_MAXUADDRLEN]; + unsigned short port; + + switch (sap->sa_family) { + case AF_INET: + if (rpc_ntop4(sap, addrbuf, sizeof(addrbuf)) == 0) + return NULL; + port = ntohs(((struct sockaddr_in *)sap)->sin_port); + break; + case AF_INET6: + if (rpc_ntop6_noscopeid(sap, addrbuf, sizeof(addrbuf)) == 0) + return NULL; + port = ntohs(((struct sockaddr_in6 *)sap)->sin6_port); + break; + default: + return NULL; + } + + if (snprintf(portbuf, sizeof(portbuf), + ".%u.%u", port >> 8, port & 0xff) > (int)sizeof(portbuf)) + return NULL; + + if (strlcat(addrbuf, portbuf, sizeof(addrbuf)) > sizeof(addrbuf)) + return NULL; + + return kstrdup(addrbuf, GFP_KERNEL); +} +EXPORT_SYMBOL_GPL(rpc_sockaddr2uaddr); + +/** + * rpc_uaddr2sockaddr - convert a universal address to a socket address. + * @uaddr: C string containing universal address to convert + * @uaddr_len: length of universal address string + * @sap: buffer into which to plant socket address + * @salen: size of buffer + * + * Returns the size of the socket address if successful; otherwise + * zero is returned. + */ +size_t rpc_uaddr2sockaddr(const char *uaddr, const size_t uaddr_len, + struct sockaddr *sap, const size_t salen) +{ + char *c, buf[RPCBIND_MAXUADDRLEN]; + unsigned long portlo, porthi; + unsigned short port; + + if (uaddr_len > sizeof(buf)) + return 0; + + memcpy(buf, uaddr, uaddr_len); + + buf[uaddr_len] = '\n'; + buf[uaddr_len + 1] = '\0'; + + c = strrchr(buf, '.'); + if (unlikely(c == NULL)) + return 0; + if (unlikely(strict_strtoul(c + 1, 10, &portlo) != 0)) + return 0; + if (unlikely(portlo > 255)) + return 0; + + c[0] = '\n'; + c[1] = '\0'; + + c = strrchr(buf, '.'); + if (unlikely(c == NULL)) + return 0; + if (unlikely(strict_strtoul(c + 1, 10, &porthi) != 0)) + return 0; + if (unlikely(porthi > 255)) + return 0; + + port = (unsigned short)((porthi << 8) | portlo); + + c[0] = '\0'; + + if (rpc_pton(buf, strlen(buf), sap, salen) == 0) + return 0; + + switch (sap->sa_family) { + case AF_INET: + ((struct sockaddr_in *)sap)->sin_port = htons(port); + return sizeof(struct sockaddr_in); + case AF_INET6: + ((struct sockaddr_in6 *)sap)->sin6_port = htons(port); + return sizeof(struct sockaddr_in6); + } + + return 0; +} +EXPORT_SYMBOL_GPL(rpc_uaddr2sockaddr); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 66d458fc6920..fc6a43ccd950 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -89,8 +89,8 @@ static struct rpc_wait_queue pipe_version_rpc_waitqueue; static DECLARE_WAIT_QUEUE_HEAD(pipe_version_waitqueue); static void gss_free_ctx(struct gss_cl_ctx *); -static struct rpc_pipe_ops gss_upcall_ops_v0; -static struct rpc_pipe_ops gss_upcall_ops_v1; +static const struct rpc_pipe_ops gss_upcall_ops_v0; +static const struct rpc_pipe_ops gss_upcall_ops_v1; static inline struct gss_cl_ctx * gss_get_ctx(struct gss_cl_ctx *ctx) @@ -777,7 +777,7 @@ gss_create(struct rpc_clnt *clnt, rpc_authflavor_t flavor) * that we supported only the old pipe. So we instead create * the new pipe first. */ - gss_auth->dentry[1] = rpc_mkpipe(clnt->cl_dentry, + gss_auth->dentry[1] = rpc_mkpipe(clnt->cl_path.dentry, "gssd", clnt, &gss_upcall_ops_v1, RPC_PIPE_WAIT_FOR_OPEN); @@ -786,7 +786,7 @@ gss_create(struct rpc_clnt *clnt, rpc_authflavor_t flavor) goto err_put_mech; } - gss_auth->dentry[0] = rpc_mkpipe(clnt->cl_dentry, + gss_auth->dentry[0] = rpc_mkpipe(clnt->cl_path.dentry, gss_auth->mech->gm_name, clnt, &gss_upcall_ops_v0, RPC_PIPE_WAIT_FOR_OPEN); @@ -1507,7 +1507,7 @@ static const struct rpc_credops gss_nullops = { .crunwrap_resp = gss_unwrap_resp, }; -static struct rpc_pipe_ops gss_upcall_ops_v0 = { +static const struct rpc_pipe_ops gss_upcall_ops_v0 = { .upcall = gss_pipe_upcall, .downcall = gss_pipe_downcall, .destroy_msg = gss_pipe_destroy_msg, @@ -1515,7 +1515,7 @@ static struct rpc_pipe_ops gss_upcall_ops_v0 = { .release_pipe = gss_pipe_release, }; -static struct rpc_pipe_ops gss_upcall_ops_v1 = { +static const struct rpc_pipe_ops gss_upcall_ops_v1 = { .upcall = gss_pipe_upcall, .downcall = gss_pipe_downcall, .destroy_msg = gss_pipe_destroy_msg, diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 2278a50c6444..2e6a148d277c 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -181,6 +181,11 @@ static void rsi_request(struct cache_detail *cd, (*bpp)[-1] = '\n'; } +static int rsi_upcall(struct cache_detail *cd, struct cache_head *h) +{ + return sunrpc_cache_pipe_upcall(cd, h, rsi_request); +} + static int rsi_parse(struct cache_detail *cd, char *mesg, int mlen) @@ -270,7 +275,7 @@ static struct cache_detail rsi_cache = { .hash_table = rsi_table, .name = "auth.rpcsec.init", .cache_put = rsi_put, - .cache_request = rsi_request, + .cache_upcall = rsi_upcall, .cache_parse = rsi_parse, .match = rsi_match, .init = rsi_init, diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index bbd31f1215e7..ade8a7e99cd3 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -27,10 +27,12 @@ #include <linux/net.h> #include <linux/workqueue.h> #include <linux/mutex.h> +#include <linux/pagemap.h> #include <asm/ioctls.h> #include <linux/sunrpc/types.h> #include <linux/sunrpc/cache.h> #include <linux/sunrpc/stats.h> +#include <linux/sunrpc/rpc_pipe_fs.h> #define RPCDBG_FACILITY RPCDBG_CACHE @@ -175,7 +177,12 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail, } EXPORT_SYMBOL_GPL(sunrpc_cache_update); -static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h); +static int cache_make_upcall(struct cache_detail *cd, struct cache_head *h) +{ + if (!cd->cache_upcall) + return -EINVAL; + return cd->cache_upcall(cd, h); +} static inline int cache_is_valid(struct cache_detail *detail, struct cache_head *h) { @@ -192,6 +199,7 @@ static inline int cache_is_valid(struct cache_detail *detail, struct cache_head return 0; } } + /* * This is the generic cache management routine for all * the authentication caches. @@ -297,76 +305,11 @@ static DEFINE_SPINLOCK(cache_list_lock); static struct cache_detail *current_detail; static int current_index; -static const struct file_operations cache_file_operations; -static const struct file_operations content_file_operations; -static const struct file_operations cache_flush_operations; - static void do_cache_clean(struct work_struct *work); static DECLARE_DELAYED_WORK(cache_cleaner, do_cache_clean); -static void remove_cache_proc_entries(struct cache_detail *cd) -{ - if (cd->proc_ent == NULL) - return; - if (cd->flush_ent) - remove_proc_entry("flush", cd->proc_ent); - if (cd->channel_ent) - remove_proc_entry("channel", cd->proc_ent); - if (cd->content_ent) - remove_proc_entry("content", cd->proc_ent); - cd->proc_ent = NULL; - remove_proc_entry(cd->name, proc_net_rpc); -} - -#ifdef CONFIG_PROC_FS -static int create_cache_proc_entries(struct cache_detail *cd) -{ - struct proc_dir_entry *p; - - cd->proc_ent = proc_mkdir(cd->name, proc_net_rpc); - if (cd->proc_ent == NULL) - goto out_nomem; - cd->channel_ent = cd->content_ent = NULL; - - p = proc_create_data("flush", S_IFREG|S_IRUSR|S_IWUSR, - cd->proc_ent, &cache_flush_operations, cd); - cd->flush_ent = p; - if (p == NULL) - goto out_nomem; - - if (cd->cache_request || cd->cache_parse) { - p = proc_create_data("channel", S_IFREG|S_IRUSR|S_IWUSR, - cd->proc_ent, &cache_file_operations, cd); - cd->channel_ent = p; - if (p == NULL) - goto out_nomem; - } - if (cd->cache_show) { - p = proc_create_data("content", S_IFREG|S_IRUSR|S_IWUSR, - cd->proc_ent, &content_file_operations, cd); - cd->content_ent = p; - if (p == NULL) - goto out_nomem; - } - return 0; -out_nomem: - remove_cache_proc_entries(cd); - return -ENOMEM; -} -#else /* CONFIG_PROC_FS */ -static int create_cache_proc_entries(struct cache_detail *cd) -{ - return 0; -} -#endif - -int cache_register(struct cache_detail *cd) +static void sunrpc_init_cache_detail(struct cache_detail *cd) { - int ret; - - ret = create_cache_proc_entries(cd); - if (ret) - return ret; rwlock_init(&cd->hash_lock); INIT_LIST_HEAD(&cd->queue); spin_lock(&cache_list_lock); @@ -380,11 +323,9 @@ int cache_register(struct cache_detail *cd) /* start the cleaning process */ schedule_delayed_work(&cache_cleaner, 0); - return 0; } -EXPORT_SYMBOL_GPL(cache_register); -void cache_unregister(struct cache_detail *cd) +static void sunrpc_destroy_cache_detail(struct cache_detail *cd) { cache_purge(cd); spin_lock(&cache_list_lock); @@ -399,7 +340,6 @@ void cache_unregister(struct cache_detail *cd) list_del_init(&cd->others); write_unlock(&cd->hash_lock); spin_unlock(&cache_list_lock); - remove_cache_proc_entries(cd); if (list_empty(&cache_list)) { /* module must be being unloaded so its safe to kill the worker */ cancel_delayed_work_sync(&cache_cleaner); @@ -408,7 +348,6 @@ void cache_unregister(struct cache_detail *cd) out: printk(KERN_ERR "nfsd: failed to unregister %s cache\n", cd->name); } -EXPORT_SYMBOL_GPL(cache_unregister); /* clean cache tries to find something to clean * and cleans it. @@ -703,18 +642,18 @@ struct cache_reader { int offset; /* if non-0, we have a refcnt on next request */ }; -static ssize_t -cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) +static ssize_t cache_read(struct file *filp, char __user *buf, size_t count, + loff_t *ppos, struct cache_detail *cd) { struct cache_reader *rp = filp->private_data; struct cache_request *rq; - struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + struct inode *inode = filp->f_path.dentry->d_inode; int err; if (count == 0) return 0; - mutex_lock(&queue_io_mutex); /* protect against multiple concurrent + mutex_lock(&inode->i_mutex); /* protect against multiple concurrent * readers on this file */ again: spin_lock(&queue_lock); @@ -727,7 +666,7 @@ cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) } if (rp->q.list.next == &cd->queue) { spin_unlock(&queue_lock); - mutex_unlock(&queue_io_mutex); + mutex_unlock(&inode->i_mutex); BUG_ON(rp->offset); return 0; } @@ -774,49 +713,90 @@ cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) } if (err == -EAGAIN) goto again; - mutex_unlock(&queue_io_mutex); + mutex_unlock(&inode->i_mutex); return err ? err : count; } -static char write_buf[8192]; /* protected by queue_io_mutex */ +static ssize_t cache_do_downcall(char *kaddr, const char __user *buf, + size_t count, struct cache_detail *cd) +{ + ssize_t ret; -static ssize_t -cache_write(struct file *filp, const char __user *buf, size_t count, - loff_t *ppos) + if (copy_from_user(kaddr, buf, count)) + return -EFAULT; + kaddr[count] = '\0'; + ret = cd->cache_parse(cd, kaddr, count); + if (!ret) + ret = count; + return ret; +} + +static ssize_t cache_slow_downcall(const char __user *buf, + size_t count, struct cache_detail *cd) { - int err; - struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + static char write_buf[8192]; /* protected by queue_io_mutex */ + ssize_t ret = -EINVAL; - if (count == 0) - return 0; if (count >= sizeof(write_buf)) - return -EINVAL; - + goto out; mutex_lock(&queue_io_mutex); + ret = cache_do_downcall(write_buf, buf, count, cd); + mutex_unlock(&queue_io_mutex); +out: + return ret; +} - if (copy_from_user(write_buf, buf, count)) { - mutex_unlock(&queue_io_mutex); - return -EFAULT; - } - write_buf[count] = '\0'; - if (cd->cache_parse) - err = cd->cache_parse(cd, write_buf, count); - else - err = -EINVAL; +static ssize_t cache_downcall(struct address_space *mapping, + const char __user *buf, + size_t count, struct cache_detail *cd) +{ + struct page *page; + char *kaddr; + ssize_t ret = -ENOMEM; + + if (count >= PAGE_CACHE_SIZE) + goto out_slow; + + page = find_or_create_page(mapping, 0, GFP_KERNEL); + if (!page) + goto out_slow; + + kaddr = kmap(page); + ret = cache_do_downcall(kaddr, buf, count, cd); + kunmap(page); + unlock_page(page); + page_cache_release(page); + return ret; +out_slow: + return cache_slow_downcall(buf, count, cd); +} - mutex_unlock(&queue_io_mutex); - return err ? err : count; +static ssize_t cache_write(struct file *filp, const char __user *buf, + size_t count, loff_t *ppos, + struct cache_detail *cd) +{ + struct address_space *mapping = filp->f_mapping; + struct inode *inode = filp->f_path.dentry->d_inode; + ssize_t ret = -EINVAL; + + if (!cd->cache_parse) + goto out; + + mutex_lock(&inode->i_mutex); + ret = cache_downcall(mapping, buf, count, cd); + mutex_unlock(&inode->i_mutex); +out: + return ret; } static DECLARE_WAIT_QUEUE_HEAD(queue_wait); -static unsigned int -cache_poll(struct file *filp, poll_table *wait) +static unsigned int cache_poll(struct file *filp, poll_table *wait, + struct cache_detail *cd) { unsigned int mask; struct cache_reader *rp = filp->private_data; struct cache_queue *cq; - struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; poll_wait(filp, &queue_wait, wait); @@ -838,14 +818,13 @@ cache_poll(struct file *filp, poll_table *wait) return mask; } -static int -cache_ioctl(struct inode *ino, struct file *filp, - unsigned int cmd, unsigned long arg) +static int cache_ioctl(struct inode *ino, struct file *filp, + unsigned int cmd, unsigned long arg, + struct cache_detail *cd) { int len = 0; struct cache_reader *rp = filp->private_data; struct cache_queue *cq; - struct cache_detail *cd = PDE(ino)->data; if (cmd != FIONREAD || !rp) return -EINVAL; @@ -868,15 +847,15 @@ cache_ioctl(struct inode *ino, struct file *filp, return put_user(len, (int __user *)arg); } -static int -cache_open(struct inode *inode, struct file *filp) +static int cache_open(struct inode *inode, struct file *filp, + struct cache_detail *cd) { struct cache_reader *rp = NULL; + if (!cd || !try_module_get(cd->owner)) + return -EACCES; nonseekable_open(inode, filp); if (filp->f_mode & FMODE_READ) { - struct cache_detail *cd = PDE(inode)->data; - rp = kmalloc(sizeof(*rp), GFP_KERNEL); if (!rp) return -ENOMEM; @@ -891,11 +870,10 @@ cache_open(struct inode *inode, struct file *filp) return 0; } -static int -cache_release(struct inode *inode, struct file *filp) +static int cache_release(struct inode *inode, struct file *filp, + struct cache_detail *cd) { struct cache_reader *rp = filp->private_data; - struct cache_detail *cd = PDE(inode)->data; if (rp) { spin_lock(&queue_lock); @@ -919,23 +897,12 @@ cache_release(struct inode *inode, struct file *filp) cd->last_close = get_seconds(); atomic_dec(&cd->readers); } + module_put(cd->owner); return 0; } -static const struct file_operations cache_file_operations = { - .owner = THIS_MODULE, - .llseek = no_llseek, - .read = cache_read, - .write = cache_write, - .poll = cache_poll, - .ioctl = cache_ioctl, /* for FIONREAD */ - .open = cache_open, - .release = cache_release, -}; - - static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch) { struct cache_queue *cq; @@ -1036,15 +1003,21 @@ static void warn_no_listener(struct cache_detail *detail) if (detail->last_warn != detail->last_close) { detail->last_warn = detail->last_close; if (detail->warn_no_listener) - detail->warn_no_listener(detail); + detail->warn_no_listener(detail, detail->last_close != 0); } } /* - * register an upcall request to user-space. + * register an upcall request to user-space and queue it up for read() by the + * upcall daemon. + * * Each request is at most one page long. */ -static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h) +int sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h, + void (*cache_request)(struct cache_detail *, + struct cache_head *, + char **, + int *)) { char *buf; @@ -1052,9 +1025,6 @@ static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h) char *bp; int len; - if (detail->cache_request == NULL) - return -EINVAL; - if (atomic_read(&detail->readers) == 0 && detail->last_close < get_seconds() - 30) { warn_no_listener(detail); @@ -1073,7 +1043,7 @@ static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h) bp = buf; len = PAGE_SIZE; - detail->cache_request(detail, h, &bp, &len); + cache_request(detail, h, &bp, &len); if (len < 0) { kfree(buf); @@ -1091,6 +1061,7 @@ static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h) wake_up(&queue_wait); return 0; } +EXPORT_SYMBOL_GPL(sunrpc_cache_pipe_upcall); /* * parse a message from user-space and pass it @@ -1258,11 +1229,13 @@ static const struct seq_operations cache_content_op = { .show = c_show, }; -static int content_open(struct inode *inode, struct file *file) +static int content_open(struct inode *inode, struct file *file, + struct cache_detail *cd) { struct handle *han; - struct cache_detail *cd = PDE(inode)->data; + if (!cd || !try_module_get(cd->owner)) + return -EACCES; han = __seq_open_private(file, &cache_content_op, sizeof(*han)); if (han == NULL) return -ENOMEM; @@ -1271,17 +1244,33 @@ static int content_open(struct inode *inode, struct file *file) return 0; } -static const struct file_operations content_file_operations = { - .open = content_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_private, -}; +static int content_release(struct inode *inode, struct file *file, + struct cache_detail *cd) +{ + int ret = seq_release_private(inode, file); + module_put(cd->owner); + return ret; +} + +static int open_flush(struct inode *inode, struct file *file, + struct cache_detail *cd) +{ + if (!cd || !try_module_get(cd->owner)) + return -EACCES; + return nonseekable_open(inode, file); +} + +static int release_flush(struct inode *inode, struct file *file, + struct cache_detail *cd) +{ + module_put(cd->owner); + return 0; +} static ssize_t read_flush(struct file *file, char __user *buf, - size_t count, loff_t *ppos) + size_t count, loff_t *ppos, + struct cache_detail *cd) { - struct cache_detail *cd = PDE(file->f_path.dentry->d_inode)->data; char tbuf[20]; unsigned long p = *ppos; size_t len; @@ -1299,10 +1288,10 @@ static ssize_t read_flush(struct file *file, char __user *buf, return len; } -static ssize_t write_flush(struct file * file, const char __user * buf, - size_t count, loff_t *ppos) +static ssize_t write_flush(struct file *file, const char __user *buf, + size_t count, loff_t *ppos, + struct cache_detail *cd) { - struct cache_detail *cd = PDE(file->f_path.dentry->d_inode)->data; char tbuf[20]; char *ep; long flushtime; @@ -1323,8 +1312,343 @@ static ssize_t write_flush(struct file * file, const char __user * buf, return count; } -static const struct file_operations cache_flush_operations = { - .open = nonseekable_open, - .read = read_flush, - .write = write_flush, +static ssize_t cache_read_procfs(struct file *filp, char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + + return cache_read(filp, buf, count, ppos, cd); +} + +static ssize_t cache_write_procfs(struct file *filp, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + + return cache_write(filp, buf, count, ppos, cd); +} + +static unsigned int cache_poll_procfs(struct file *filp, poll_table *wait) +{ + struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + + return cache_poll(filp, wait, cd); +} + +static int cache_ioctl_procfs(struct inode *inode, struct file *filp, + unsigned int cmd, unsigned long arg) +{ + struct cache_detail *cd = PDE(inode)->data; + + return cache_ioctl(inode, filp, cmd, arg, cd); +} + +static int cache_open_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return cache_open(inode, filp, cd); +} + +static int cache_release_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return cache_release(inode, filp, cd); +} + +static const struct file_operations cache_file_operations_procfs = { + .owner = THIS_MODULE, + .llseek = no_llseek, + .read = cache_read_procfs, + .write = cache_write_procfs, + .poll = cache_poll_procfs, + .ioctl = cache_ioctl_procfs, /* for FIONREAD */ + .open = cache_open_procfs, + .release = cache_release_procfs, }; + +static int content_open_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return content_open(inode, filp, cd); +} + +static int content_release_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return content_release(inode, filp, cd); +} + +static const struct file_operations content_file_operations_procfs = { + .open = content_open_procfs, + .read = seq_read, + .llseek = seq_lseek, + .release = content_release_procfs, +}; + +static int open_flush_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return open_flush(inode, filp, cd); +} + +static int release_flush_procfs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = PDE(inode)->data; + + return release_flush(inode, filp, cd); +} + +static ssize_t read_flush_procfs(struct file *filp, char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + + return read_flush(filp, buf, count, ppos, cd); +} + +static ssize_t write_flush_procfs(struct file *filp, + const char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + + return write_flush(filp, buf, count, ppos, cd); +} + +static const struct file_operations cache_flush_operations_procfs = { + .open = open_flush_procfs, + .read = read_flush_procfs, + .write = write_flush_procfs, + .release = release_flush_procfs, +}; + +static void remove_cache_proc_entries(struct cache_detail *cd) +{ + if (cd->u.procfs.proc_ent == NULL) + return; + if (cd->u.procfs.flush_ent) + remove_proc_entry("flush", cd->u.procfs.proc_ent); + if (cd->u.procfs.channel_ent) + remove_proc_entry("channel", cd->u.procfs.proc_ent); + if (cd->u.procfs.content_ent) + remove_proc_entry("content", cd->u.procfs.proc_ent); + cd->u.procfs.proc_ent = NULL; + remove_proc_entry(cd->name, proc_net_rpc); +} + +#ifdef CONFIG_PROC_FS +static int create_cache_proc_entries(struct cache_detail *cd) +{ + struct proc_dir_entry *p; + + cd->u.procfs.proc_ent = proc_mkdir(cd->name, proc_net_rpc); + if (cd->u.procfs.proc_ent == NULL) + goto out_nomem; + cd->u.procfs.channel_ent = NULL; + cd->u.procfs.content_ent = NULL; + + p = proc_create_data("flush", S_IFREG|S_IRUSR|S_IWUSR, + cd->u.procfs.proc_ent, + &cache_flush_operations_procfs, cd); + cd->u.procfs.flush_ent = p; + if (p == NULL) + goto out_nomem; + + if (cd->cache_upcall || cd->cache_parse) { + p = proc_create_data("channel", S_IFREG|S_IRUSR|S_IWUSR, + cd->u.procfs.proc_ent, + &cache_file_operations_procfs, cd); + cd->u.procfs.channel_ent = p; + if (p == NULL) + goto out_nomem; + } + if (cd->cache_show) { + p = proc_create_data("content", S_IFREG|S_IRUSR|S_IWUSR, + cd->u.procfs.proc_ent, + &content_file_operations_procfs, cd); + cd->u.procfs.content_ent = p; + if (p == NULL) + goto out_nomem; + } + return 0; +out_nomem: + remove_cache_proc_entries(cd); + return -ENOMEM; +} +#else /* CONFIG_PROC_FS */ +static int create_cache_proc_entries(struct cache_detail *cd) +{ + return 0; +} +#endif + +int cache_register(struct cache_detail *cd) +{ + int ret; + + sunrpc_init_cache_detail(cd); + ret = create_cache_proc_entries(cd); + if (ret) + sunrpc_destroy_cache_detail(cd); + return ret; +} +EXPORT_SYMBOL_GPL(cache_register); + +void cache_unregister(struct cache_detail *cd) +{ + remove_cache_proc_entries(cd); + sunrpc_destroy_cache_detail(cd); +} +EXPORT_SYMBOL_GPL(cache_unregister); + +static ssize_t cache_read_pipefs(struct file *filp, char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + + return cache_read(filp, buf, count, ppos, cd); +} + +static ssize_t cache_write_pipefs(struct file *filp, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + + return cache_write(filp, buf, count, ppos, cd); +} + +static unsigned int cache_poll_pipefs(struct file *filp, poll_table *wait) +{ + struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + + return cache_poll(filp, wait, cd); +} + +static int cache_ioctl_pipefs(struct inode *inode, struct file *filp, + unsigned int cmd, unsigned long arg) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return cache_ioctl(inode, filp, cmd, arg, cd); +} + +static int cache_open_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return cache_open(inode, filp, cd); +} + +static int cache_release_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return cache_release(inode, filp, cd); +} + +const struct file_operations cache_file_operations_pipefs = { + .owner = THIS_MODULE, + .llseek = no_llseek, + .read = cache_read_pipefs, + .write = cache_write_pipefs, + .poll = cache_poll_pipefs, + .ioctl = cache_ioctl_pipefs, /* for FIONREAD */ + .open = cache_open_pipefs, + .release = cache_release_pipefs, +}; + +static int content_open_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return content_open(inode, filp, cd); +} + +static int content_release_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return content_release(inode, filp, cd); +} + +const struct file_operations content_file_operations_pipefs = { + .open = content_open_pipefs, + .read = seq_read, + .llseek = seq_lseek, + .release = content_release_pipefs, +}; + +static int open_flush_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return open_flush(inode, filp, cd); +} + +static int release_flush_pipefs(struct inode *inode, struct file *filp) +{ + struct cache_detail *cd = RPC_I(inode)->private; + + return release_flush(inode, filp, cd); +} + +static ssize_t read_flush_pipefs(struct file *filp, char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + + return read_flush(filp, buf, count, ppos, cd); +} + +static ssize_t write_flush_pipefs(struct file *filp, + const char __user *buf, + size_t count, loff_t *ppos) +{ + struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + + return write_flush(filp, buf, count, ppos, cd); +} + +const struct file_operations cache_flush_operations_pipefs = { + .open = open_flush_pipefs, + .read = read_flush_pipefs, + .write = write_flush_pipefs, + .release = release_flush_pipefs, +}; + +int sunrpc_cache_register_pipefs(struct dentry *parent, + const char *name, mode_t umode, + struct cache_detail *cd) +{ + struct qstr q; + struct dentry *dir; + int ret = 0; + + sunrpc_init_cache_detail(cd); + q.name = name; + q.len = strlen(name); + q.hash = full_name_hash(q.name, q.len); + dir = rpc_create_cache_dir(parent, &q, umode, cd); + if (!IS_ERR(dir)) + cd->u.pipefs.dir = dir; + else { + sunrpc_destroy_cache_detail(cd); + ret = PTR_ERR(dir); + } + return ret; +} +EXPORT_SYMBOL_GPL(sunrpc_cache_register_pipefs); + +void sunrpc_cache_unregister_pipefs(struct cache_detail *cd) +{ + rpc_remove_cache_dir(cd->u.pipefs.dir); + cd->u.pipefs.dir = NULL; + sunrpc_destroy_cache_detail(cd); +} +EXPORT_SYMBOL_GPL(sunrpc_cache_unregister_pipefs); + diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 5bc2f45bddf0..c1e467e1b07d 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -27,8 +27,9 @@ #include <linux/types.h> #include <linux/kallsyms.h> #include <linux/mm.h> +#include <linux/namei.h> +#include <linux/mount.h> #include <linux/slab.h> -#include <linux/smp_lock.h> #include <linux/utsname.h> #include <linux/workqueue.h> #include <linux/in6.h> @@ -98,33 +99,49 @@ static int rpc_setup_pipedir(struct rpc_clnt *clnt, char *dir_name) { static uint32_t clntid; + struct nameidata nd; + struct path path; + char name[15]; + struct qstr q = { + .name = name, + }; int error; - clnt->cl_vfsmnt = ERR_PTR(-ENOENT); - clnt->cl_dentry = ERR_PTR(-ENOENT); + clnt->cl_path.mnt = ERR_PTR(-ENOENT); + clnt->cl_path.dentry = ERR_PTR(-ENOENT); if (dir_name == NULL) return 0; - clnt->cl_vfsmnt = rpc_get_mount(); - if (IS_ERR(clnt->cl_vfsmnt)) - return PTR_ERR(clnt->cl_vfsmnt); + path.mnt = rpc_get_mount(); + if (IS_ERR(path.mnt)) + return PTR_ERR(path.mnt); + error = vfs_path_lookup(path.mnt->mnt_root, path.mnt, dir_name, 0, &nd); + if (error) + goto err; for (;;) { - snprintf(clnt->cl_pathname, sizeof(clnt->cl_pathname), - "%s/clnt%x", dir_name, - (unsigned int)clntid++); - clnt->cl_pathname[sizeof(clnt->cl_pathname) - 1] = '\0'; - clnt->cl_dentry = rpc_mkdir(clnt->cl_pathname, clnt); - if (!IS_ERR(clnt->cl_dentry)) - return 0; - error = PTR_ERR(clnt->cl_dentry); + q.len = snprintf(name, sizeof(name), "clnt%x", (unsigned int)clntid++); + name[sizeof(name) - 1] = '\0'; + q.hash = full_name_hash(q.name, q.len); + path.dentry = rpc_create_client_dir(nd.path.dentry, &q, clnt); + if (!IS_ERR(path.dentry)) + break; + error = PTR_ERR(path.dentry); if (error != -EEXIST) { - printk(KERN_INFO "RPC: Couldn't create pipefs entry %s, error %d\n", - clnt->cl_pathname, error); - rpc_put_mount(); - return error; + printk(KERN_INFO "RPC: Couldn't create pipefs entry" + " %s/%s, error %d\n", + dir_name, name, error); + goto err_path_put; } } + path_put(&nd.path); + clnt->cl_path = path; + return 0; +err_path_put: + path_put(&nd.path); +err: + rpc_put_mount(); + return error; } static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, struct rpc_xprt *xprt) @@ -232,8 +249,8 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, stru return clnt; out_no_auth: - if (!IS_ERR(clnt->cl_dentry)) { - rpc_rmdir(clnt->cl_dentry); + if (!IS_ERR(clnt->cl_path.dentry)) { + rpc_remove_client_dir(clnt->cl_path.dentry); rpc_put_mount(); } out_no_path: @@ -424,8 +441,8 @@ rpc_free_client(struct kref *kref) dprintk("RPC: destroying %s client for %s\n", clnt->cl_protname, clnt->cl_server); - if (!IS_ERR(clnt->cl_dentry)) { - rpc_rmdir(clnt->cl_dentry); + if (!IS_ERR(clnt->cl_path.dentry)) { + rpc_remove_client_dir(clnt->cl_path.dentry); rpc_put_mount(); } if (clnt->cl_parent != clnt) { diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 9ced0628d69c..7f676bdf70d3 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -26,6 +26,7 @@ #include <linux/sunrpc/clnt.h> #include <linux/workqueue.h> #include <linux/sunrpc/rpc_pipe_fs.h> +#include <linux/sunrpc/cache.h> static struct vfsmount *rpc_mount __read_mostly; static int rpc_mount_count; @@ -125,7 +126,7 @@ static void rpc_close_pipes(struct inode *inode) { struct rpc_inode *rpci = RPC_I(inode); - struct rpc_pipe_ops *ops; + const struct rpc_pipe_ops *ops; int need_release; mutex_lock(&inode->i_mutex); @@ -398,66 +399,12 @@ static const struct file_operations rpc_info_operations = { /* - * We have a single directory with 1 node in it. - */ -enum { - RPCAUTH_Root = 1, - RPCAUTH_lockd, - RPCAUTH_mount, - RPCAUTH_nfs, - RPCAUTH_portmap, - RPCAUTH_statd, - RPCAUTH_nfsd4_cb, - RPCAUTH_RootEOF -}; - -/* * Description of fs contents. */ struct rpc_filelist { - char *name; + const char *name; const struct file_operations *i_fop; - int mode; -}; - -static struct rpc_filelist files[] = { - [RPCAUTH_lockd] = { - .name = "lockd", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, - [RPCAUTH_mount] = { - .name = "mount", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, - [RPCAUTH_nfs] = { - .name = "nfs", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, - [RPCAUTH_portmap] = { - .name = "portmap", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, - [RPCAUTH_statd] = { - .name = "statd", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, - [RPCAUTH_nfsd4_cb] = { - .name = "nfsd4_cb", - .mode = S_IFDIR | S_IRUGO | S_IXUGO, - }, -}; - -enum { - RPCAUTH_info = 2, - RPCAUTH_EOF -}; - -static struct rpc_filelist authfiles[] = { - [RPCAUTH_info] = { - .name = "info", - .i_fop = &rpc_info_operations, - .mode = S_IFREG | S_IRUSR, - }, + umode_t mode; }; struct vfsmount *rpc_get_mount(void) @@ -469,11 +416,13 @@ struct vfsmount *rpc_get_mount(void) return ERR_PTR(err); return rpc_mount; } +EXPORT_SYMBOL_GPL(rpc_get_mount); void rpc_put_mount(void) { simple_release_fs(&rpc_mount, &rpc_mount_count); } +EXPORT_SYMBOL_GPL(rpc_put_mount); static int rpc_delete_dentry(struct dentry *dentry) { @@ -484,39 +433,8 @@ static const struct dentry_operations rpc_dentry_operations = { .d_delete = rpc_delete_dentry, }; -static int -rpc_lookup_parent(char *path, struct nameidata *nd) -{ - struct vfsmount *mnt; - - if (path[0] == '\0') - return -ENOENT; - - mnt = rpc_get_mount(); - if (IS_ERR(mnt)) { - printk(KERN_WARNING "%s: %s failed to mount " - "pseudofilesystem \n", __FILE__, __func__); - return PTR_ERR(mnt); - } - - if (vfs_path_lookup(mnt->mnt_root, mnt, path, LOOKUP_PARENT, nd)) { - printk(KERN_WARNING "%s: %s failed to find path %s\n", - __FILE__, __func__, path); - rpc_put_mount(); - return -ENOENT; - } - return 0; -} - -static void -rpc_release_path(struct nameidata *nd) -{ - path_put(&nd->path); - rpc_put_mount(); -} - static struct inode * -rpc_get_inode(struct super_block *sb, int mode) +rpc_get_inode(struct super_block *sb, umode_t mode) { struct inode *inode = new_inode(sb); if (!inode) @@ -534,212 +452,274 @@ rpc_get_inode(struct super_block *sb, int mode) return inode; } -/* - * FIXME: This probably has races. - */ -static void rpc_depopulate(struct dentry *parent, - unsigned long start, unsigned long eof) +static int __rpc_create_common(struct inode *dir, struct dentry *dentry, + umode_t mode, + const struct file_operations *i_fop, + void *private) { - struct inode *dir = parent->d_inode; - struct list_head *pos, *next; - struct dentry *dentry, *dvec[10]; - int n = 0; + struct inode *inode; - mutex_lock_nested(&dir->i_mutex, I_MUTEX_CHILD); -repeat: - spin_lock(&dcache_lock); - list_for_each_safe(pos, next, &parent->d_subdirs) { - dentry = list_entry(pos, struct dentry, d_u.d_child); - if (!dentry->d_inode || - dentry->d_inode->i_ino < start || - dentry->d_inode->i_ino >= eof) - continue; - spin_lock(&dentry->d_lock); - if (!d_unhashed(dentry)) { - dget_locked(dentry); - __d_drop(dentry); - spin_unlock(&dentry->d_lock); - dvec[n++] = dentry; - if (n == ARRAY_SIZE(dvec)) - break; - } else - spin_unlock(&dentry->d_lock); - } - spin_unlock(&dcache_lock); - if (n) { - do { - dentry = dvec[--n]; - if (S_ISREG(dentry->d_inode->i_mode)) - simple_unlink(dir, dentry); - else if (S_ISDIR(dentry->d_inode->i_mode)) - simple_rmdir(dir, dentry); - d_delete(dentry); - dput(dentry); - } while (n); - goto repeat; - } - mutex_unlock(&dir->i_mutex); + BUG_ON(!d_unhashed(dentry)); + inode = rpc_get_inode(dir->i_sb, mode); + if (!inode) + goto out_err; + inode->i_ino = iunique(dir->i_sb, 100); + if (i_fop) + inode->i_fop = i_fop; + if (private) + rpc_inode_setowner(inode, private); + d_add(dentry, inode); + return 0; +out_err: + printk(KERN_WARNING "%s: %s failed to allocate inode for dentry %s\n", + __FILE__, __func__, dentry->d_name.name); + dput(dentry); + return -ENOMEM; } -static int -rpc_populate(struct dentry *parent, - struct rpc_filelist *files, - int start, int eof) +static int __rpc_create(struct inode *dir, struct dentry *dentry, + umode_t mode, + const struct file_operations *i_fop, + void *private) { - struct inode *inode, *dir = parent->d_inode; - void *private = RPC_I(dir)->private; - struct dentry *dentry; - int mode, i; + int err; - mutex_lock(&dir->i_mutex); - for (i = start; i < eof; i++) { - dentry = d_alloc_name(parent, files[i].name); - if (!dentry) - goto out_bad; - dentry->d_op = &rpc_dentry_operations; - mode = files[i].mode; - inode = rpc_get_inode(dir->i_sb, mode); - if (!inode) { - dput(dentry); - goto out_bad; - } - inode->i_ino = i; - if (files[i].i_fop) - inode->i_fop = files[i].i_fop; - if (private) - rpc_inode_setowner(inode, private); - if (S_ISDIR(mode)) - inc_nlink(dir); - d_add(dentry, inode); - fsnotify_create(dir, dentry); - } - mutex_unlock(&dir->i_mutex); + err = __rpc_create_common(dir, dentry, S_IFREG | mode, i_fop, private); + if (err) + return err; + fsnotify_create(dir, dentry); return 0; -out_bad: - mutex_unlock(&dir->i_mutex); - printk(KERN_WARNING "%s: %s failed to populate directory %s\n", - __FILE__, __func__, parent->d_name.name); - return -ENOMEM; } -static int -__rpc_mkdir(struct inode *dir, struct dentry *dentry) +static int __rpc_mkdir(struct inode *dir, struct dentry *dentry, + umode_t mode, + const struct file_operations *i_fop, + void *private) { - struct inode *inode; + int err; - inode = rpc_get_inode(dir->i_sb, S_IFDIR | S_IRUGO | S_IXUGO); - if (!inode) - goto out_err; - inode->i_ino = iunique(dir->i_sb, 100); - d_instantiate(dentry, inode); + err = __rpc_create_common(dir, dentry, S_IFDIR | mode, i_fop, private); + if (err) + return err; inc_nlink(dir); fsnotify_mkdir(dir, dentry); return 0; -out_err: - printk(KERN_WARNING "%s: %s failed to allocate inode for dentry %s\n", - __FILE__, __func__, dentry->d_name.name); - return -ENOMEM; } -static int -__rpc_rmdir(struct inode *dir, struct dentry *dentry) +static int __rpc_mkpipe(struct inode *dir, struct dentry *dentry, + umode_t mode, + const struct file_operations *i_fop, + void *private, + const struct rpc_pipe_ops *ops, + int flags) { - int error; - error = simple_rmdir(dir, dentry); - if (!error) - d_delete(dentry); - return error; + struct rpc_inode *rpci; + int err; + + err = __rpc_create_common(dir, dentry, S_IFIFO | mode, i_fop, private); + if (err) + return err; + rpci = RPC_I(dentry->d_inode); + rpci->nkern_readwriters = 1; + rpci->private = private; + rpci->flags = flags; + rpci->ops = ops; + fsnotify_create(dir, dentry); + return 0; } -static struct dentry * -rpc_lookup_create(struct dentry *parent, const char *name, int len, int exclusive) +static int __rpc_rmdir(struct inode *dir, struct dentry *dentry) +{ + int ret; + + dget(dentry); + ret = simple_rmdir(dir, dentry); + d_delete(dentry); + dput(dentry); + return ret; +} + +static int __rpc_unlink(struct inode *dir, struct dentry *dentry) +{ + int ret; + + dget(dentry); + ret = simple_unlink(dir, dentry); + d_delete(dentry); + dput(dentry); + return ret; +} + +static int __rpc_rmpipe(struct inode *dir, struct dentry *dentry) +{ + struct inode *inode = dentry->d_inode; + struct rpc_inode *rpci = RPC_I(inode); + + rpci->nkern_readwriters--; + if (rpci->nkern_readwriters != 0) + return 0; + rpc_close_pipes(inode); + return __rpc_unlink(dir, dentry); +} + +static struct dentry *__rpc_lookup_create(struct dentry *parent, + struct qstr *name) { - struct inode *dir = parent->d_inode; struct dentry *dentry; - mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); - dentry = lookup_one_len(name, parent, len); - if (IS_ERR(dentry)) - goto out_err; + dentry = d_lookup(parent, name); + if (!dentry) { + dentry = d_alloc(parent, name); + if (!dentry) { + dentry = ERR_PTR(-ENOMEM); + goto out_err; + } + } if (!dentry->d_inode) dentry->d_op = &rpc_dentry_operations; - else if (exclusive) { - dput(dentry); - dentry = ERR_PTR(-EEXIST); - goto out_err; - } - return dentry; out_err: - mutex_unlock(&dir->i_mutex); return dentry; } -static struct dentry * -rpc_lookup_negative(char *path, struct nameidata *nd) +static struct dentry *__rpc_lookup_create_exclusive(struct dentry *parent, + struct qstr *name) { struct dentry *dentry; - int error; - if ((error = rpc_lookup_parent(path, nd)) != 0) - return ERR_PTR(error); - dentry = rpc_lookup_create(nd->path.dentry, nd->last.name, nd->last.len, - 1); - if (IS_ERR(dentry)) - rpc_release_path(nd); - return dentry; + dentry = __rpc_lookup_create(parent, name); + if (dentry->d_inode == NULL) + return dentry; + dput(dentry); + return ERR_PTR(-EEXIST); } -/** - * rpc_mkdir - Create a new directory in rpc_pipefs - * @path: path from the rpc_pipefs root to the new directory - * @rpc_client: rpc client to associate with this directory - * - * This creates a directory at the given @path associated with - * @rpc_clnt, which will contain a file named "info" with some basic - * information about the client, together with any "pipes" that may - * later be created using rpc_mkpipe(). +/* + * FIXME: This probably has races. */ -struct dentry * -rpc_mkdir(char *path, struct rpc_clnt *rpc_client) +static void __rpc_depopulate(struct dentry *parent, + const struct rpc_filelist *files, + int start, int eof) { - struct nameidata nd; + struct inode *dir = parent->d_inode; struct dentry *dentry; - struct inode *dir; + struct qstr name; + int i; + + for (i = start; i < eof; i++) { + name.name = files[i].name; + name.len = strlen(files[i].name); + name.hash = full_name_hash(name.name, name.len); + dentry = d_lookup(parent, &name); + + if (dentry == NULL) + continue; + if (dentry->d_inode == NULL) + goto next; + switch (dentry->d_inode->i_mode & S_IFMT) { + default: + BUG(); + case S_IFREG: + __rpc_unlink(dir, dentry); + break; + case S_IFDIR: + __rpc_rmdir(dir, dentry); + } +next: + dput(dentry); + } +} + +static void rpc_depopulate(struct dentry *parent, + const struct rpc_filelist *files, + int start, int eof) +{ + struct inode *dir = parent->d_inode; + + mutex_lock_nested(&dir->i_mutex, I_MUTEX_CHILD); + __rpc_depopulate(parent, files, start, eof); + mutex_unlock(&dir->i_mutex); +} + +static int rpc_populate(struct dentry *parent, + const struct rpc_filelist *files, + int start, int eof, + void *private) +{ + struct inode *dir = parent->d_inode; + struct dentry *dentry; + int i, err; + + mutex_lock(&dir->i_mutex); + for (i = start; i < eof; i++) { + struct qstr q; + + q.name = files[i].name; + q.len = strlen(files[i].name); + q.hash = full_name_hash(q.name, q.len); + dentry = __rpc_lookup_create_exclusive(parent, &q); + err = PTR_ERR(dentry); + if (IS_ERR(dentry)) + goto out_bad; + switch (files[i].mode & S_IFMT) { + default: + BUG(); + case S_IFREG: + err = __rpc_create(dir, dentry, + files[i].mode, + files[i].i_fop, + private); + break; + case S_IFDIR: + err = __rpc_mkdir(dir, dentry, + files[i].mode, + NULL, + private); + } + if (err != 0) + goto out_bad; + } + mutex_unlock(&dir->i_mutex); + return 0; +out_bad: + __rpc_depopulate(parent, files, start, eof); + mutex_unlock(&dir->i_mutex); + printk(KERN_WARNING "%s: %s failed to populate directory %s\n", + __FILE__, __func__, parent->d_name.name); + return err; +} + +static struct dentry *rpc_mkdir_populate(struct dentry *parent, + struct qstr *name, umode_t mode, void *private, + int (*populate)(struct dentry *, void *), void *args_populate) +{ + struct dentry *dentry; + struct inode *dir = parent->d_inode; int error; - dentry = rpc_lookup_negative(path, &nd); + mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); + dentry = __rpc_lookup_create_exclusive(parent, name); if (IS_ERR(dentry)) - return dentry; - dir = nd.path.dentry->d_inode; - if ((error = __rpc_mkdir(dir, dentry)) != 0) - goto err_dput; - RPC_I(dentry->d_inode)->private = rpc_client; - error = rpc_populate(dentry, authfiles, - RPCAUTH_info, RPCAUTH_EOF); - if (error) - goto err_depopulate; - dget(dentry); + goto out; + error = __rpc_mkdir(dir, dentry, mode, NULL, private); + if (error != 0) + goto out_err; + if (populate != NULL) { + error = populate(dentry, args_populate); + if (error) + goto err_rmdir; + } out: mutex_unlock(&dir->i_mutex); - rpc_release_path(&nd); return dentry; -err_depopulate: - rpc_depopulate(dentry, RPCAUTH_info, RPCAUTH_EOF); +err_rmdir: __rpc_rmdir(dir, dentry); -err_dput: - dput(dentry); - printk(KERN_WARNING "%s: %s() failed to create directory %s (errno = %d)\n", - __FILE__, __func__, path, error); +out_err: dentry = ERR_PTR(error); goto out; } -/** - * rpc_rmdir - Remove a directory created with rpc_mkdir() - * @dentry: directory to remove - */ -int -rpc_rmdir(struct dentry *dentry) +static int rpc_rmdir_depopulate(struct dentry *dentry, + void (*depopulate)(struct dentry *)) { struct dentry *parent; struct inode *dir; @@ -748,9 +728,9 @@ rpc_rmdir(struct dentry *dentry) parent = dget_parent(dentry); dir = parent->d_inode; mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); - rpc_depopulate(dentry, RPCAUTH_info, RPCAUTH_EOF); + if (depopulate != NULL) + depopulate(dentry); error = __rpc_rmdir(dir, dentry); - dput(dentry); mutex_unlock(&dir->i_mutex); dput(parent); return error; @@ -776,50 +756,54 @@ rpc_rmdir(struct dentry *dentry) * The @private argument passed here will be available to all these methods * from the file pointer, via RPC_I(file->f_dentry->d_inode)->private. */ -struct dentry * -rpc_mkpipe(struct dentry *parent, const char *name, void *private, struct rpc_pipe_ops *ops, int flags) +struct dentry *rpc_mkpipe(struct dentry *parent, const char *name, + void *private, const struct rpc_pipe_ops *ops, + int flags) { struct dentry *dentry; - struct inode *dir, *inode; - struct rpc_inode *rpci; + struct inode *dir = parent->d_inode; + umode_t umode = S_IFIFO | S_IRUSR | S_IWUSR; + struct qstr q; + int err; + + if (ops->upcall == NULL) + umode &= ~S_IRUGO; + if (ops->downcall == NULL) + umode &= ~S_IWUGO; + + q.name = name; + q.len = strlen(name); + q.hash = full_name_hash(q.name, q.len), - dentry = rpc_lookup_create(parent, name, strlen(name), 0); + mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); + dentry = __rpc_lookup_create(parent, &q); if (IS_ERR(dentry)) - return dentry; - dir = parent->d_inode; + goto out; if (dentry->d_inode) { - rpci = RPC_I(dentry->d_inode); + struct rpc_inode *rpci = RPC_I(dentry->d_inode); if (rpci->private != private || rpci->ops != ops || rpci->flags != flags) { dput (dentry); - dentry = ERR_PTR(-EBUSY); + err = -EBUSY; + goto out_err; } rpci->nkern_readwriters++; goto out; } - inode = rpc_get_inode(dir->i_sb, S_IFIFO | S_IRUSR | S_IWUSR); - if (!inode) - goto err_dput; - inode->i_ino = iunique(dir->i_sb, 100); - inode->i_fop = &rpc_pipe_fops; - d_instantiate(dentry, inode); - rpci = RPC_I(inode); - rpci->private = private; - rpci->flags = flags; - rpci->ops = ops; - rpci->nkern_readwriters = 1; - fsnotify_create(dir, dentry); - dget(dentry); + + err = __rpc_mkpipe(dir, dentry, umode, &rpc_pipe_fops, + private, ops, flags); + if (err) + goto out_err; out: mutex_unlock(&dir->i_mutex); return dentry; -err_dput: - dput(dentry); - dentry = ERR_PTR(-ENOMEM); +out_err: + dentry = ERR_PTR(err); printk(KERN_WARNING "%s: %s() failed to create pipe %s/%s (errno = %d)\n", __FILE__, __func__, parent->d_name.name, name, - -ENOMEM); + err); goto out; } EXPORT_SYMBOL_GPL(rpc_mkpipe); @@ -842,19 +826,107 @@ rpc_unlink(struct dentry *dentry) parent = dget_parent(dentry); dir = parent->d_inode; mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); - if (--RPC_I(dentry->d_inode)->nkern_readwriters == 0) { - rpc_close_pipes(dentry->d_inode); - error = simple_unlink(dir, dentry); - if (!error) - d_delete(dentry); - } - dput(dentry); + error = __rpc_rmpipe(dir, dentry); mutex_unlock(&dir->i_mutex); dput(parent); return error; } EXPORT_SYMBOL_GPL(rpc_unlink); +enum { + RPCAUTH_info, + RPCAUTH_EOF +}; + +static const struct rpc_filelist authfiles[] = { + [RPCAUTH_info] = { + .name = "info", + .i_fop = &rpc_info_operations, + .mode = S_IFREG | S_IRUSR, + }, +}; + +static int rpc_clntdir_populate(struct dentry *dentry, void *private) +{ + return rpc_populate(dentry, + authfiles, RPCAUTH_info, RPCAUTH_EOF, + private); +} + +static void rpc_clntdir_depopulate(struct dentry *dentry) +{ + rpc_depopulate(dentry, authfiles, RPCAUTH_info, RPCAUTH_EOF); +} + +/** + * rpc_create_client_dir - Create a new rpc_client directory in rpc_pipefs + * @path: path from the rpc_pipefs root to the new directory + * @rpc_client: rpc client to associate with this directory + * + * This creates a directory at the given @path associated with + * @rpc_clnt, which will contain a file named "info" with some basic + * information about the client, together with any "pipes" that may + * later be created using rpc_mkpipe(). + */ +struct dentry *rpc_create_client_dir(struct dentry *dentry, + struct qstr *name, + struct rpc_clnt *rpc_client) +{ + return rpc_mkdir_populate(dentry, name, S_IRUGO | S_IXUGO, NULL, + rpc_clntdir_populate, rpc_client); +} + +/** + * rpc_remove_client_dir - Remove a directory created with rpc_create_client_dir() + * @dentry: directory to remove + */ +int rpc_remove_client_dir(struct dentry *dentry) +{ + return rpc_rmdir_depopulate(dentry, rpc_clntdir_depopulate); +} + +static const struct rpc_filelist cache_pipefs_files[3] = { + [0] = { + .name = "channel", + .i_fop = &cache_file_operations_pipefs, + .mode = S_IFREG|S_IRUSR|S_IWUSR, + }, + [1] = { + .name = "content", + .i_fop = &content_file_operations_pipefs, + .mode = S_IFREG|S_IRUSR, + }, + [2] = { + .name = "flush", + .i_fop = &cache_flush_operations_pipefs, + .mode = S_IFREG|S_IRUSR|S_IWUSR, + }, +}; + +static int rpc_cachedir_populate(struct dentry *dentry, void *private) +{ + return rpc_populate(dentry, + cache_pipefs_files, 0, 3, + private); +} + +static void rpc_cachedir_depopulate(struct dentry *dentry) +{ + rpc_depopulate(dentry, cache_pipefs_files, 0, 3); +} + +struct dentry *rpc_create_cache_dir(struct dentry *parent, struct qstr *name, + mode_t umode, struct cache_detail *cd) +{ + return rpc_mkdir_populate(parent, name, umode, NULL, + rpc_cachedir_populate, cd); +} + +void rpc_remove_cache_dir(struct dentry *dentry) +{ + rpc_rmdir_depopulate(dentry, rpc_cachedir_depopulate); +} + /* * populate the filesystem */ @@ -866,6 +938,51 @@ static struct super_operations s_ops = { #define RPCAUTH_GSSMAGIC 0x67596969 +/* + * We have a single directory with 1 node in it. + */ +enum { + RPCAUTH_lockd, + RPCAUTH_mount, + RPCAUTH_nfs, + RPCAUTH_portmap, + RPCAUTH_statd, + RPCAUTH_nfsd4_cb, + RPCAUTH_cache, + RPCAUTH_RootEOF +}; + +static const struct rpc_filelist files[] = { + [RPCAUTH_lockd] = { + .name = "lockd", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_mount] = { + .name = "mount", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_nfs] = { + .name = "nfs", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_portmap] = { + .name = "portmap", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_statd] = { + .name = "statd", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_nfsd4_cb] = { + .name = "nfsd4_cb", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, + [RPCAUTH_cache] = { + .name = "cache", + .mode = S_IFDIR | S_IRUGO | S_IXUGO, + }, +}; + static int rpc_fill_super(struct super_block *sb, void *data, int silent) { @@ -886,7 +1003,7 @@ rpc_fill_super(struct super_block *sb, void *data, int silent) iput(inode); return -ENOMEM; } - if (rpc_populate(root, files, RPCAUTH_Root + 1, RPCAUTH_RootEOF)) + if (rpc_populate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF, NULL)) goto out; sb->s_root = root; return 0; diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index beee6da33035..830faf4d9997 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -75,6 +75,37 @@ enum { #define RPCB_OWNER_STRING "0" #define RPCB_MAXOWNERLEN sizeof(RPCB_OWNER_STRING) +/* + * XDR data type sizes + */ +#define RPCB_program_sz (1) +#define RPCB_version_sz (1) +#define RPCB_protocol_sz (1) +#define RPCB_port_sz (1) +#define RPCB_boolean_sz (1) + +#define RPCB_netid_sz (1 + XDR_QUADLEN(RPCBIND_MAXNETIDLEN)) +#define RPCB_addr_sz (1 + XDR_QUADLEN(RPCBIND_MAXUADDRLEN)) +#define RPCB_ownerstring_sz (1 + XDR_QUADLEN(RPCB_MAXOWNERLEN)) + +/* + * XDR argument and result sizes + */ +#define RPCB_mappingargs_sz (RPCB_program_sz + RPCB_version_sz + \ + RPCB_protocol_sz + RPCB_port_sz) +#define RPCB_getaddrargs_sz (RPCB_program_sz + RPCB_version_sz + \ + RPCB_netid_sz + RPCB_addr_sz + \ + RPCB_ownerstring_sz) + +#define RPCB_getportres_sz RPCB_port_sz +#define RPCB_setres_sz RPCB_boolean_sz + +/* + * Note that RFC 1833 does not put any size restrictions on the + * address string returned by the remote rpcbind database. + */ +#define RPCB_getaddrres_sz RPCB_addr_sz + static void rpcb_getport_done(struct rpc_task *, void *); static void rpcb_map_release(void *data); static struct rpc_program rpcb_program; @@ -122,6 +153,7 @@ static void rpcb_map_release(void *data) rpcb_wake_rpcbind_waiters(map->r_xprt, map->r_status); xprt_put(map->r_xprt); + kfree(map->r_addr); kfree(map); } @@ -268,12 +300,9 @@ static int rpcb_register_inet4(const struct sockaddr *sap, const struct sockaddr_in *sin = (const struct sockaddr_in *)sap; struct rpcbind_args *map = msg->rpc_argp; unsigned short port = ntohs(sin->sin_port); - char buf[32]; + int result; - /* Construct AF_INET universal address */ - snprintf(buf, sizeof(buf), "%pI4.%u.%u", - &sin->sin_addr.s_addr, port >> 8, port & 0xff); - map->r_addr = buf; + map->r_addr = rpc_sockaddr2uaddr(sap); dprintk("RPC: %sregistering [%u, %u, %s, '%s'] with " "local rpcbind\n", (port ? "" : "un"), @@ -284,7 +313,9 @@ static int rpcb_register_inet4(const struct sockaddr *sap, if (port) msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; - return rpcb_register_call(RPCBVERS_4, msg); + result = rpcb_register_call(RPCBVERS_4, msg); + kfree(map->r_addr); + return result; } /* @@ -296,16 +327,9 @@ static int rpcb_register_inet6(const struct sockaddr *sap, const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)sap; struct rpcbind_args *map = msg->rpc_argp; unsigned short port = ntohs(sin6->sin6_port); - char buf[64]; + int result; - /* Construct AF_INET6 universal address */ - if (ipv6_addr_any(&sin6->sin6_addr)) - snprintf(buf, sizeof(buf), "::.%u.%u", - port >> 8, port & 0xff); - else - snprintf(buf, sizeof(buf), "%pI6.%u.%u", - &sin6->sin6_addr, port >> 8, port & 0xff); - map->r_addr = buf; + map->r_addr = rpc_sockaddr2uaddr(sap); dprintk("RPC: %sregistering [%u, %u, %s, '%s'] with " "local rpcbind\n", (port ? "" : "un"), @@ -316,7 +340,9 @@ static int rpcb_register_inet6(const struct sockaddr *sap, if (port) msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; - return rpcb_register_call(RPCBVERS_4, msg); + result = rpcb_register_call(RPCBVERS_4, msg); + kfree(map->r_addr); + return result; } static int rpcb_unregister_all_protofamilies(struct rpc_message *msg) @@ -428,7 +454,7 @@ int rpcb_getport_sync(struct sockaddr_in *sin, u32 prog, u32 vers, int prot) struct rpc_message msg = { .rpc_proc = &rpcb_procedures2[RPCBPROC_GETPORT], .rpc_argp = &map, - .rpc_resp = &map.r_port, + .rpc_resp = &map, }; struct rpc_clnt *rpcb_clnt; int status; @@ -458,7 +484,7 @@ static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, struct rpcbi struct rpc_message msg = { .rpc_proc = proc, .rpc_argp = map, - .rpc_resp = &map->r_port, + .rpc_resp = map, }; struct rpc_task_setup task_setup_data = { .rpc_client = rpcb_clnt, @@ -539,6 +565,7 @@ void rpcb_getport_async(struct rpc_task *task) goto bailout_nofree; } + /* Parent transport's destination address */ salen = rpc_peeraddr(clnt, sap, sizeof(addr)); /* Don't ever use rpcbind v2 for AF_INET6 requests */ @@ -589,11 +616,22 @@ void rpcb_getport_async(struct rpc_task *task) map->r_prot = xprt->prot; map->r_port = 0; map->r_xprt = xprt_get(xprt); - map->r_netid = rpc_peeraddr2str(clnt, RPC_DISPLAY_NETID); - map->r_addr = rpc_peeraddr2str(rpcb_clnt, RPC_DISPLAY_UNIVERSAL_ADDR); - map->r_owner = ""; map->r_status = -EIO; + switch (bind_version) { + case RPCBVERS_4: + case RPCBVERS_3: + map->r_netid = rpc_peeraddr2str(clnt, RPC_DISPLAY_NETID); + map->r_addr = rpc_sockaddr2uaddr(sap); + map->r_owner = ""; + break; + case RPCBVERS_2: + map->r_addr = NULL; + break; + default: + BUG(); + } + child = rpcb_call_async(rpcb_clnt, map, proc); rpc_release_client(rpcb_clnt); if (IS_ERR(child)) { @@ -656,176 +694,278 @@ static void rpcb_getport_done(struct rpc_task *child, void *data) * XDR functions for rpcbind */ -static int rpcb_encode_mapping(struct rpc_rqst *req, __be32 *p, - struct rpcbind_args *rpcb) +static int rpcb_enc_mapping(struct rpc_rqst *req, __be32 *p, + const struct rpcbind_args *rpcb) { - dprintk("RPC: encoding rpcb request (%u, %u, %d, %u)\n", + struct rpc_task *task = req->rq_task; + struct xdr_stream xdr; + + dprintk("RPC: %5u encoding PMAP_%s call (%u, %u, %d, %u)\n", + task->tk_pid, task->tk_msg.rpc_proc->p_name, rpcb->r_prog, rpcb->r_vers, rpcb->r_prot, rpcb->r_port); + + xdr_init_encode(&xdr, &req->rq_snd_buf, p); + + p = xdr_reserve_space(&xdr, sizeof(__be32) * RPCB_mappingargs_sz); + if (unlikely(p == NULL)) + return -EIO; + *p++ = htonl(rpcb->r_prog); *p++ = htonl(rpcb->r_vers); *p++ = htonl(rpcb->r_prot); - *p++ = htonl(rpcb->r_port); + *p = htonl(rpcb->r_port); - req->rq_slen = xdr_adjust_iovec(req->rq_svec, p); return 0; } -static int rpcb_decode_getport(struct rpc_rqst *req, __be32 *p, - unsigned short *portp) +static int rpcb_dec_getport(struct rpc_rqst *req, __be32 *p, + struct rpcbind_args *rpcb) { - *portp = (unsigned short) ntohl(*p++); - dprintk("RPC: rpcb getport result: %u\n", - *portp); + struct rpc_task *task = req->rq_task; + struct xdr_stream xdr; + unsigned long port; + + xdr_init_decode(&xdr, &req->rq_rcv_buf, p); + + rpcb->r_port = 0; + + p = xdr_inline_decode(&xdr, sizeof(__be32)); + if (unlikely(p == NULL)) + return -EIO; + + port = ntohl(*p); + dprintk("RPC: %5u PMAP_%s result: %lu\n", task->tk_pid, + task->tk_msg.rpc_proc->p_name, port); + if (unlikely(port > USHORT_MAX)) + return -EIO; + + rpcb->r_port = port; return 0; } -static int rpcb_decode_set(struct rpc_rqst *req, __be32 *p, - unsigned int *boolp) +static int rpcb_dec_set(struct rpc_rqst *req, __be32 *p, + unsigned int *boolp) { - *boolp = (unsigned int) ntohl(*p++); - dprintk("RPC: rpcb set/unset call %s\n", + struct rpc_task *task = req->rq_task; + struct xdr_stream xdr; + + xdr_init_decode(&xdr, &req->rq_rcv_buf, p); + + p = xdr_inline_decode(&xdr, sizeof(__be32)); + if (unlikely(p == NULL)) + return -EIO; + + *boolp = 0; + if (*p) + *boolp = 1; + + dprintk("RPC: %5u RPCB_%s call %s\n", + task->tk_pid, task->tk_msg.rpc_proc->p_name, (*boolp ? "succeeded" : "failed")); return 0; } -static int rpcb_encode_getaddr(struct rpc_rqst *req, __be32 *p, - struct rpcbind_args *rpcb) +static int encode_rpcb_string(struct xdr_stream *xdr, const char *string, + const u32 maxstrlen) { - dprintk("RPC: encoding rpcb request (%u, %u, %s)\n", - rpcb->r_prog, rpcb->r_vers, rpcb->r_addr); - *p++ = htonl(rpcb->r_prog); - *p++ = htonl(rpcb->r_vers); + u32 len; + __be32 *p; - p = xdr_encode_string(p, rpcb->r_netid); - p = xdr_encode_string(p, rpcb->r_addr); - p = xdr_encode_string(p, rpcb->r_owner); + if (unlikely(string == NULL)) + return -EIO; + len = strlen(string); + if (unlikely(len > maxstrlen)) + return -EIO; - req->rq_slen = xdr_adjust_iovec(req->rq_svec, p); + p = xdr_reserve_space(xdr, sizeof(__be32) + len); + if (unlikely(p == NULL)) + return -EIO; + xdr_encode_opaque(p, string, len); return 0; } -static int rpcb_decode_getaddr(struct rpc_rqst *req, __be32 *p, - unsigned short *portp) +static int rpcb_enc_getaddr(struct rpc_rqst *req, __be32 *p, + const struct rpcbind_args *rpcb) { - char *addr; - u32 addr_len; - int c, i, f, first, val; + struct rpc_task *task = req->rq_task; + struct xdr_stream xdr; - *portp = 0; - addr_len = ntohl(*p++); + dprintk("RPC: %5u encoding RPCB_%s call (%u, %u, '%s', '%s')\n", + task->tk_pid, task->tk_msg.rpc_proc->p_name, + rpcb->r_prog, rpcb->r_vers, + rpcb->r_netid, rpcb->r_addr); - if (addr_len == 0) { - dprintk("RPC: rpcb_decode_getaddr: " - "service is not registered\n"); - return 0; - } + xdr_init_encode(&xdr, &req->rq_snd_buf, p); - /* - * Simple sanity check. - */ - if (addr_len > RPCBIND_MAXUADDRLEN) - goto out_err; - - /* - * Start at the end and walk backwards until the first dot - * is encountered. When the second dot is found, we have - * both parts of the port number. - */ - addr = (char *)p; - val = 0; - first = 1; - f = 1; - for (i = addr_len - 1; i > 0; i--) { - c = addr[i]; - if (c >= '0' && c <= '9') { - val += (c - '0') * f; - f *= 10; - } else if (c == '.') { - if (first) { - *portp = val; - val = first = 0; - f = 1; - } else { - *portp |= (val << 8); - break; - } - } - } + p = xdr_reserve_space(&xdr, + sizeof(__be32) * (RPCB_program_sz + RPCB_version_sz)); + if (unlikely(p == NULL)) + return -EIO; + *p++ = htonl(rpcb->r_prog); + *p = htonl(rpcb->r_vers); - /* - * Simple sanity check. If we never saw a dot in the reply, - * then this was probably just garbage. - */ - if (first) - goto out_err; + if (encode_rpcb_string(&xdr, rpcb->r_netid, RPCBIND_MAXNETIDLEN)) + return -EIO; + if (encode_rpcb_string(&xdr, rpcb->r_addr, RPCBIND_MAXUADDRLEN)) + return -EIO; + if (encode_rpcb_string(&xdr, rpcb->r_owner, RPCB_MAXOWNERLEN)) + return -EIO; - dprintk("RPC: rpcb_decode_getaddr port=%u\n", *portp); return 0; - -out_err: - dprintk("RPC: rpcbind server returned malformed reply\n"); - return -EIO; } -#define RPCB_program_sz (1u) -#define RPCB_version_sz (1u) -#define RPCB_protocol_sz (1u) -#define RPCB_port_sz (1u) -#define RPCB_boolean_sz (1u) +static int rpcb_dec_getaddr(struct rpc_rqst *req, __be32 *p, + struct rpcbind_args *rpcb) +{ + struct sockaddr_storage address; + struct sockaddr *sap = (struct sockaddr *)&address; + struct rpc_task *task = req->rq_task; + struct xdr_stream xdr; + u32 len; -#define RPCB_netid_sz (1+XDR_QUADLEN(RPCBIND_MAXNETIDLEN)) -#define RPCB_addr_sz (1+XDR_QUADLEN(RPCBIND_MAXUADDRLEN)) -#define RPCB_ownerstring_sz (1+XDR_QUADLEN(RPCB_MAXOWNERLEN)) + rpcb->r_port = 0; -#define RPCB_mappingargs_sz RPCB_program_sz+RPCB_version_sz+ \ - RPCB_protocol_sz+RPCB_port_sz -#define RPCB_getaddrargs_sz RPCB_program_sz+RPCB_version_sz+ \ - RPCB_netid_sz+RPCB_addr_sz+ \ - RPCB_ownerstring_sz + xdr_init_decode(&xdr, &req->rq_rcv_buf, p); -#define RPCB_setres_sz RPCB_boolean_sz -#define RPCB_getportres_sz RPCB_port_sz - -/* - * Note that RFC 1833 does not put any size restrictions on the - * address string returned by the remote rpcbind database. - */ -#define RPCB_getaddrres_sz RPCB_addr_sz + p = xdr_inline_decode(&xdr, sizeof(__be32)); + if (unlikely(p == NULL)) + goto out_fail; + len = ntohl(*p); -#define PROC(proc, argtype, restype) \ - [RPCBPROC_##proc] = { \ - .p_proc = RPCBPROC_##proc, \ - .p_encode = (kxdrproc_t) rpcb_encode_##argtype, \ - .p_decode = (kxdrproc_t) rpcb_decode_##restype, \ - .p_arglen = RPCB_##argtype##args_sz, \ - .p_replen = RPCB_##restype##res_sz, \ - .p_statidx = RPCBPROC_##proc, \ - .p_timer = 0, \ - .p_name = #proc, \ + /* + * If the returned universal address is a null string, + * the requested RPC service was not registered. + */ + if (len == 0) { + dprintk("RPC: %5u RPCB reply: program not registered\n", + task->tk_pid); + return 0; } + if (unlikely(len > RPCBIND_MAXUADDRLEN)) + goto out_fail; + + p = xdr_inline_decode(&xdr, len); + if (unlikely(p == NULL)) + goto out_fail; + dprintk("RPC: %5u RPCB_%s reply: %s\n", task->tk_pid, + task->tk_msg.rpc_proc->p_name, (char *)p); + + if (rpc_uaddr2sockaddr((char *)p, len, sap, sizeof(address)) == 0) + goto out_fail; + rpcb->r_port = rpc_get_port(sap); + + return 0; + +out_fail: + dprintk("RPC: %5u malformed RPCB_%s reply\n", + task->tk_pid, task->tk_msg.rpc_proc->p_name); + return -EIO; +} + /* * Not all rpcbind procedures described in RFC 1833 are implemented * since the Linux kernel RPC code requires only these. */ + static struct rpc_procinfo rpcb_procedures2[] = { - PROC(SET, mapping, set), - PROC(UNSET, mapping, set), - PROC(GETPORT, mapping, getport), + [RPCBPROC_SET] = { + .p_proc = RPCBPROC_SET, + .p_encode = (kxdrproc_t)rpcb_enc_mapping, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_mappingargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_SET, + .p_timer = 0, + .p_name = "SET", + }, + [RPCBPROC_UNSET] = { + .p_proc = RPCBPROC_UNSET, + .p_encode = (kxdrproc_t)rpcb_enc_mapping, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_mappingargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_UNSET, + .p_timer = 0, + .p_name = "UNSET", + }, + [RPCBPROC_GETPORT] = { + .p_proc = RPCBPROC_GETPORT, + .p_encode = (kxdrproc_t)rpcb_enc_mapping, + .p_decode = (kxdrproc_t)rpcb_dec_getport, + .p_arglen = RPCB_mappingargs_sz, + .p_replen = RPCB_getportres_sz, + .p_statidx = RPCBPROC_GETPORT, + .p_timer = 0, + .p_name = "GETPORT", + }, }; static struct rpc_procinfo rpcb_procedures3[] = { - PROC(SET, getaddr, set), - PROC(UNSET, getaddr, set), - PROC(GETADDR, getaddr, getaddr), + [RPCBPROC_SET] = { + .p_proc = RPCBPROC_SET, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_SET, + .p_timer = 0, + .p_name = "SET", + }, + [RPCBPROC_UNSET] = { + .p_proc = RPCBPROC_UNSET, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_UNSET, + .p_timer = 0, + .p_name = "UNSET", + }, + [RPCBPROC_GETADDR] = { + .p_proc = RPCBPROC_GETADDR, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_getaddr, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_getaddrres_sz, + .p_statidx = RPCBPROC_GETADDR, + .p_timer = 0, + .p_name = "GETADDR", + }, }; static struct rpc_procinfo rpcb_procedures4[] = { - PROC(SET, getaddr, set), - PROC(UNSET, getaddr, set), - PROC(GETADDR, getaddr, getaddr), - PROC(GETVERSADDR, getaddr, getaddr), + [RPCBPROC_SET] = { + .p_proc = RPCBPROC_SET, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_SET, + .p_timer = 0, + .p_name = "SET", + }, + [RPCBPROC_UNSET] = { + .p_proc = RPCBPROC_UNSET, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_set, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_setres_sz, + .p_statidx = RPCBPROC_UNSET, + .p_timer = 0, + .p_name = "UNSET", + }, + [RPCBPROC_GETADDR] = { + .p_proc = RPCBPROC_GETADDR, + .p_encode = (kxdrproc_t)rpcb_enc_getaddr, + .p_decode = (kxdrproc_t)rpcb_dec_getaddr, + .p_arglen = RPCB_getaddrargs_sz, + .p_replen = RPCB_getaddrres_sz, + .p_statidx = RPCBPROC_GETADDR, + .p_timer = 0, + .p_name = "GETADDR", + }, }; static struct rpcb_info rpcb_next_version[] = { diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 1102ce1251f7..8f459abe97cf 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -16,7 +16,6 @@ #include <linux/slab.h> #include <linux/mempool.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/spinlock.h> #include <linux/mutex.h> diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index 843629f55763..8cce92189019 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -66,7 +66,8 @@ cleanup_sunrpc(void) #ifdef CONFIG_PROC_FS rpc_proc_exit(); #endif + rcu_barrier(); /* Wait for completion of call_rcu()'s */ } MODULE_LICENSE("GPL"); -module_init(init_sunrpc); +fs_initcall(init_sunrpc); /* Ensure we're initialised before nfs */ module_exit(cleanup_sunrpc); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 6f33d33cc064..27d44332f017 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -5,6 +5,7 @@ */ #include <linux/sched.h> +#include <linux/smp_lock.h> #include <linux/errno.h> #include <linux/freezer.h> #include <linux/kthread.h> diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 799ff6ef28b8..117f68a8aa40 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -171,6 +171,11 @@ static void ip_map_request(struct cache_detail *cd, (*bpp)[-1] = '\n'; } +static int ip_map_upcall(struct cache_detail *cd, struct cache_head *h) +{ + return sunrpc_cache_pipe_upcall(cd, h, ip_map_request); +} + static struct ip_map *ip_map_lookup(char *class, struct in6_addr *addr); static int ip_map_update(struct ip_map *ipm, struct unix_domain *udom, time_t expiry); @@ -289,7 +294,7 @@ struct cache_detail ip_map_cache = { .hash_table = ip_table, .name = "auth.unix.ip", .cache_put = ip_map_put, - .cache_request = ip_map_request, + .cache_upcall = ip_map_upcall, .cache_parse = ip_map_parse, .cache_show = ip_map_show, .match = ip_map_match, @@ -523,6 +528,11 @@ static void unix_gid_request(struct cache_detail *cd, (*bpp)[-1] = '\n'; } +static int unix_gid_upcall(struct cache_detail *cd, struct cache_head *h) +{ + return sunrpc_cache_pipe_upcall(cd, h, unix_gid_request); +} + static struct unix_gid *unix_gid_lookup(uid_t uid); extern struct cache_detail unix_gid_cache; @@ -622,7 +632,7 @@ struct cache_detail unix_gid_cache = { .hash_table = gid_table, .name = "auth.unix.gid", .cache_put = unix_gid_put, - .cache_request = unix_gid_request, + .cache_upcall = unix_gid_upcall, .cache_parse = unix_gid_parse, .cache_show = unix_gid_show, .match = unix_gid_match, diff --git a/net/sunrpc/timer.c b/net/sunrpc/timer.c index 31becbf09263..dd824341c349 100644 --- a/net/sunrpc/timer.c +++ b/net/sunrpc/timer.c @@ -25,8 +25,13 @@ #define RPC_RTO_INIT (HZ/5) #define RPC_RTO_MIN (HZ/10) -void -rpc_init_rtt(struct rpc_rtt *rt, unsigned long timeo) +/** + * rpc_init_rtt - Initialize an RPC RTT estimator context + * @rt: context to initialize + * @timeo: initial timeout value, in jiffies + * + */ +void rpc_init_rtt(struct rpc_rtt *rt, unsigned long timeo) { unsigned long init = 0; unsigned i; @@ -43,12 +48,16 @@ rpc_init_rtt(struct rpc_rtt *rt, unsigned long timeo) } EXPORT_SYMBOL_GPL(rpc_init_rtt); -/* +/** + * rpc_update_rtt - Update an RPC RTT estimator context + * @rt: context to update + * @timer: timer array index (request type) + * @m: recent actual RTT, in jiffies + * * NB: When computing the smoothed RTT and standard deviation, * be careful not to produce negative intermediate results. */ -void -rpc_update_rtt(struct rpc_rtt *rt, unsigned timer, long m) +void rpc_update_rtt(struct rpc_rtt *rt, unsigned timer, long m) { long *srtt, *sdrtt; @@ -79,21 +88,25 @@ rpc_update_rtt(struct rpc_rtt *rt, unsigned timer, long m) } EXPORT_SYMBOL_GPL(rpc_update_rtt); -/* - * Estimate rto for an nfs rpc sent via. an unreliable datagram. - * Use the mean and mean deviation of rtt for the appropriate type of rpc - * for the frequent rpcs and a default for the others. - * The justification for doing "other" this way is that these rpcs - * happen so infrequently that timer est. would probably be stale. - * Also, since many of these rpcs are - * non-idempotent, a conservative timeout is desired. +/** + * rpc_calc_rto - Provide an estimated timeout value + * @rt: context to use for calculation + * @timer: timer array index (request type) + * + * Estimate RTO for an NFS RPC sent via an unreliable datagram. Use + * the mean and mean deviation of RTT for the appropriate type of RPC + * for frequently issued RPCs, and a fixed default for the others. + * + * The justification for doing "other" this way is that these RPCs + * happen so infrequently that timer estimation would probably be + * stale. Also, since many of these RPCs are non-idempotent, a + * conservative timeout is desired. + * * getattr, lookup, * read, write, commit - A+4D * other - timeo */ - -unsigned long -rpc_calc_rto(struct rpc_rtt *rt, unsigned timer) +unsigned long rpc_calc_rto(struct rpc_rtt *rt, unsigned timer) { unsigned long res; diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 406e26de584e..8bd690c48b69 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -24,7 +24,7 @@ xdr_encode_netobj(__be32 *p, const struct xdr_netobj *obj) unsigned int quadlen = XDR_QUADLEN(obj->len); p[quadlen] = 0; /* zero trailing bytes */ - *p++ = htonl(obj->len); + *p++ = cpu_to_be32(obj->len); memcpy(p, obj->data, obj->len); return p + XDR_QUADLEN(obj->len); } @@ -35,7 +35,7 @@ xdr_decode_netobj(__be32 *p, struct xdr_netobj *obj) { unsigned int len; - if ((len = ntohl(*p++)) > XDR_MAX_NETOBJ) + if ((len = be32_to_cpu(*p++)) > XDR_MAX_NETOBJ) return NULL; obj->len = len; obj->data = (u8 *) p; @@ -83,7 +83,7 @@ EXPORT_SYMBOL_GPL(xdr_encode_opaque_fixed); */ __be32 *xdr_encode_opaque(__be32 *p, const void *ptr, unsigned int nbytes) { - *p++ = htonl(nbytes); + *p++ = cpu_to_be32(nbytes); return xdr_encode_opaque_fixed(p, ptr, nbytes); } EXPORT_SYMBOL_GPL(xdr_encode_opaque); @@ -101,7 +101,7 @@ xdr_decode_string_inplace(__be32 *p, char **sp, { u32 len; - len = ntohl(*p++); + len = be32_to_cpu(*p++); if (len > maxlen) return NULL; *lenp = len; @@ -771,7 +771,7 @@ xdr_decode_word(struct xdr_buf *buf, unsigned int base, u32 *obj) status = read_bytes_from_xdr_buf(buf, base, &raw, sizeof(*obj)); if (status) return status; - *obj = ntohl(raw); + *obj = be32_to_cpu(raw); return 0; } EXPORT_SYMBOL_GPL(xdr_decode_word); @@ -779,7 +779,7 @@ EXPORT_SYMBOL_GPL(xdr_decode_word); int xdr_encode_word(struct xdr_buf *buf, unsigned int base, u32 obj) { - __be32 raw = htonl(obj); + __be32 raw = cpu_to_be32(obj); return write_bytes_to_xdr_buf(buf, base, &raw, sizeof(obj)); } diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 1dd6123070e9..9a63f669ece4 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -168,47 +168,25 @@ static struct rpc_xprt_ops xprt_rdma_procs; /* forward reference */ static void xprt_rdma_format_addresses(struct rpc_xprt *xprt) { - struct sockaddr_in *addr = (struct sockaddr_in *) + struct sockaddr *sap = (struct sockaddr *) &rpcx_to_rdmad(xprt).addr; - char *buf; + struct sockaddr_in *sin = (struct sockaddr_in *)sap; + char buf[64]; - buf = kzalloc(20, GFP_KERNEL); - if (buf) - snprintf(buf, 20, "%pI4", &addr->sin_addr.s_addr); - xprt->address_strings[RPC_DISPLAY_ADDR] = buf; + (void)rpc_ntop(sap, buf, sizeof(buf)); + xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL); - buf = kzalloc(8, GFP_KERNEL); - if (buf) - snprintf(buf, 8, "%u", ntohs(addr->sin_port)); - xprt->address_strings[RPC_DISPLAY_PORT] = buf; + (void)snprintf(buf, sizeof(buf), "%u", rpc_get_port(sap)); + xprt->address_strings[RPC_DISPLAY_PORT] = kstrdup(buf, GFP_KERNEL); xprt->address_strings[RPC_DISPLAY_PROTO] = "rdma"; - buf = kzalloc(48, GFP_KERNEL); - if (buf) - snprintf(buf, 48, "addr=%pI4 port=%u proto=%s", - &addr->sin_addr.s_addr, - ntohs(addr->sin_port), "rdma"); - xprt->address_strings[RPC_DISPLAY_ALL] = buf; - - buf = kzalloc(10, GFP_KERNEL); - if (buf) - snprintf(buf, 10, "%02x%02x%02x%02x", - NIPQUAD(addr->sin_addr.s_addr)); - xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = buf; - - buf = kzalloc(8, GFP_KERNEL); - if (buf) - snprintf(buf, 8, "%4hx", ntohs(addr->sin_port)); - xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf; - - buf = kzalloc(30, GFP_KERNEL); - if (buf) - snprintf(buf, 30, "%pI4.%u.%u", - &addr->sin_addr.s_addr, - ntohs(addr->sin_port) >> 8, - ntohs(addr->sin_port) & 0xff); - xprt->address_strings[RPC_DISPLAY_UNIVERSAL_ADDR] = buf; + (void)snprintf(buf, sizeof(buf), "%02x%02x%02x%02x", + NIPQUAD(sin->sin_addr.s_addr)); + xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL); + + (void)snprintf(buf, sizeof(buf), "%4hx", rpc_get_port(sap)); + xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL); /* netid */ xprt->address_strings[RPC_DISPLAY_NETID] = "rdma"; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 83c73c4d017a..62438f3a914d 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -248,8 +248,8 @@ struct sock_xprt { * Connection of transports */ struct delayed_work connect_worker; - struct sockaddr_storage addr; - unsigned short port; + struct sockaddr_storage srcaddr; + unsigned short srcport; /* * UDP socket buffer size parameters @@ -296,117 +296,60 @@ static inline struct sockaddr_in6 *xs_addr_in6(struct rpc_xprt *xprt) return (struct sockaddr_in6 *) &xprt->addr; } -static void xs_format_ipv4_peer_addresses(struct rpc_xprt *xprt, - const char *protocol, - const char *netid) +static void xs_format_common_peer_addresses(struct rpc_xprt *xprt) { - struct sockaddr_in *addr = xs_addr_in(xprt); - char *buf; + struct sockaddr *sap = xs_addr(xprt); + struct sockaddr_in6 *sin6; + struct sockaddr_in *sin; + char buf[128]; - buf = kzalloc(20, GFP_KERNEL); - if (buf) { - snprintf(buf, 20, "%pI4", &addr->sin_addr.s_addr); - } - xprt->address_strings[RPC_DISPLAY_ADDR] = buf; - - buf = kzalloc(8, GFP_KERNEL); - if (buf) { - snprintf(buf, 8, "%u", - ntohs(addr->sin_port)); - } - xprt->address_strings[RPC_DISPLAY_PORT] = buf; - - xprt->address_strings[RPC_DISPLAY_PROTO] = protocol; - - buf = kzalloc(48, GFP_KERNEL); - if (buf) { - snprintf(buf, 48, "addr=%pI4 port=%u proto=%s", - &addr->sin_addr.s_addr, - ntohs(addr->sin_port), - protocol); - } - xprt->address_strings[RPC_DISPLAY_ALL] = buf; - - buf = kzalloc(10, GFP_KERNEL); - if (buf) { - snprintf(buf, 10, "%02x%02x%02x%02x", - NIPQUAD(addr->sin_addr.s_addr)); - } - xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = buf; + (void)rpc_ntop(sap, buf, sizeof(buf)); + xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL); - buf = kzalloc(8, GFP_KERNEL); - if (buf) { - snprintf(buf, 8, "%4hx", - ntohs(addr->sin_port)); - } - xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf; - - buf = kzalloc(30, GFP_KERNEL); - if (buf) { - snprintf(buf, 30, "%pI4.%u.%u", - &addr->sin_addr.s_addr, - ntohs(addr->sin_port) >> 8, - ntohs(addr->sin_port) & 0xff); + switch (sap->sa_family) { + case AF_INET: + sin = xs_addr_in(xprt); + (void)snprintf(buf, sizeof(buf), "%02x%02x%02x%02x", + NIPQUAD(sin->sin_addr.s_addr)); + break; + case AF_INET6: + sin6 = xs_addr_in6(xprt); + (void)snprintf(buf, sizeof(buf), "%pi6", &sin6->sin6_addr); + break; + default: + BUG(); } - xprt->address_strings[RPC_DISPLAY_UNIVERSAL_ADDR] = buf; - - xprt->address_strings[RPC_DISPLAY_NETID] = netid; + xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL); } -static void xs_format_ipv6_peer_addresses(struct rpc_xprt *xprt, - const char *protocol, - const char *netid) +static void xs_format_common_peer_ports(struct rpc_xprt *xprt) { - struct sockaddr_in6 *addr = xs_addr_in6(xprt); - char *buf; + struct sockaddr *sap = xs_addr(xprt); + char buf[128]; - buf = kzalloc(40, GFP_KERNEL); - if (buf) { - snprintf(buf, 40, "%pI6",&addr->sin6_addr); - } - xprt->address_strings[RPC_DISPLAY_ADDR] = buf; + (void)snprintf(buf, sizeof(buf), "%u", rpc_get_port(sap)); + xprt->address_strings[RPC_DISPLAY_PORT] = kstrdup(buf, GFP_KERNEL); - buf = kzalloc(8, GFP_KERNEL); - if (buf) { - snprintf(buf, 8, "%u", - ntohs(addr->sin6_port)); - } - xprt->address_strings[RPC_DISPLAY_PORT] = buf; + (void)snprintf(buf, sizeof(buf), "%4hx", rpc_get_port(sap)); + xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL); +} +static void xs_format_peer_addresses(struct rpc_xprt *xprt, + const char *protocol, + const char *netid) +{ xprt->address_strings[RPC_DISPLAY_PROTO] = protocol; + xprt->address_strings[RPC_DISPLAY_NETID] = netid; + xs_format_common_peer_addresses(xprt); + xs_format_common_peer_ports(xprt); +} - buf = kzalloc(64, GFP_KERNEL); - if (buf) { - snprintf(buf, 64, "addr=%pI6 port=%u proto=%s", - &addr->sin6_addr, - ntohs(addr->sin6_port), - protocol); - } - xprt->address_strings[RPC_DISPLAY_ALL] = buf; - - buf = kzalloc(36, GFP_KERNEL); - if (buf) - snprintf(buf, 36, "%pi6", &addr->sin6_addr); - - xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = buf; - - buf = kzalloc(8, GFP_KERNEL); - if (buf) { - snprintf(buf, 8, "%4hx", - ntohs(addr->sin6_port)); - } - xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf; - - buf = kzalloc(50, GFP_KERNEL); - if (buf) { - snprintf(buf, 50, "%pI6.%u.%u", - &addr->sin6_addr, - ntohs(addr->sin6_port) >> 8, - ntohs(addr->sin6_port) & 0xff); - } - xprt->address_strings[RPC_DISPLAY_UNIVERSAL_ADDR] = buf; +static void xs_update_peer_port(struct rpc_xprt *xprt) +{ + kfree(xprt->address_strings[RPC_DISPLAY_HEX_PORT]); + kfree(xprt->address_strings[RPC_DISPLAY_PORT]); - xprt->address_strings[RPC_DISPLAY_NETID] = netid; + xs_format_common_peer_ports(xprt); } static void xs_free_peer_addresses(struct rpc_xprt *xprt) @@ -1587,25 +1530,15 @@ static unsigned short xs_get_random_port(void) */ static void xs_set_port(struct rpc_xprt *xprt, unsigned short port) { - struct sockaddr *addr = xs_addr(xprt); - dprintk("RPC: setting port for xprt %p to %u\n", xprt, port); - switch (addr->sa_family) { - case AF_INET: - ((struct sockaddr_in *)addr)->sin_port = htons(port); - break; - case AF_INET6: - ((struct sockaddr_in6 *)addr)->sin6_port = htons(port); - break; - default: - BUG(); - } + rpc_set_port(xs_addr(xprt), port); + xs_update_peer_port(xprt); } static unsigned short xs_get_srcport(struct sock_xprt *transport, struct socket *sock) { - unsigned short port = transport->port; + unsigned short port = transport->srcport; if (port == 0 && transport->xprt.resvport) port = xs_get_random_port(); @@ -1614,8 +1547,8 @@ static unsigned short xs_get_srcport(struct sock_xprt *transport, struct socket static unsigned short xs_next_srcport(struct sock_xprt *transport, struct socket *sock, unsigned short port) { - if (transport->port != 0) - transport->port = 0; + if (transport->srcport != 0) + transport->srcport = 0; if (!transport->xprt.resvport) return 0; if (port <= xprt_min_resvport || port > xprt_max_resvport) @@ -1633,7 +1566,7 @@ static int xs_bind4(struct sock_xprt *transport, struct socket *sock) unsigned short port = xs_get_srcport(transport, sock); unsigned short last; - sa = (struct sockaddr_in *)&transport->addr; + sa = (struct sockaddr_in *)&transport->srcaddr; myaddr.sin_addr = sa->sin_addr; do { myaddr.sin_port = htons(port); @@ -1642,7 +1575,7 @@ static int xs_bind4(struct sock_xprt *transport, struct socket *sock) if (port == 0) break; if (err == 0) { - transport->port = port; + transport->srcport = port; break; } last = port; @@ -1666,7 +1599,7 @@ static int xs_bind6(struct sock_xprt *transport, struct socket *sock) unsigned short port = xs_get_srcport(transport, sock); unsigned short last; - sa = (struct sockaddr_in6 *)&transport->addr; + sa = (struct sockaddr_in6 *)&transport->srcaddr; myaddr.sin6_addr = sa->sin6_addr; do { myaddr.sin6_port = htons(port); @@ -1675,7 +1608,7 @@ static int xs_bind6(struct sock_xprt *transport, struct socket *sock) if (port == 0) break; if (err == 0) { - transport->port = port; + transport->srcport = port; break; } last = port; @@ -1780,8 +1713,11 @@ static void xs_udp_connect_worker4(struct work_struct *work) goto out; } - dprintk("RPC: worker connecting xprt %p to address: %s\n", - xprt, xprt->address_strings[RPC_DISPLAY_ALL]); + dprintk("RPC: worker connecting xprt %p via %s to " + "%s (port %s)\n", xprt, + xprt->address_strings[RPC_DISPLAY_PROTO], + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT]); xs_udp_finish_connecting(xprt, sock); status = 0; @@ -1822,8 +1758,11 @@ static void xs_udp_connect_worker6(struct work_struct *work) goto out; } - dprintk("RPC: worker connecting xprt %p to address: %s\n", - xprt, xprt->address_strings[RPC_DISPLAY_ALL]); + dprintk("RPC: worker connecting xprt %p via %s to " + "%s (port %s)\n", xprt, + xprt->address_strings[RPC_DISPLAY_PROTO], + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT]); xs_udp_finish_connecting(xprt, sock); status = 0; @@ -1948,8 +1887,11 @@ static void xs_tcp_setup_socket(struct rpc_xprt *xprt, goto out_eagain; } - dprintk("RPC: worker connecting xprt %p to address: %s\n", - xprt, xprt->address_strings[RPC_DISPLAY_ALL]); + dprintk("RPC: worker connecting xprt %p via %s to " + "%s (port %s)\n", xprt, + xprt->address_strings[RPC_DISPLAY_PROTO], + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT]); status = xs_tcp_finish_connecting(xprt, sock); dprintk("RPC: %p connect status %d connected %d sock state %d\n", @@ -2120,7 +2062,7 @@ static void xs_udp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); seq_printf(seq, "\txprt:\tudp %u %lu %lu %lu %lu %Lu %Lu\n", - transport->port, + transport->srcport, xprt->stat.bind_count, xprt->stat.sends, xprt->stat.recvs, @@ -2144,7 +2086,7 @@ static void xs_tcp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) idle_time = (long)(jiffies - xprt->last_used) / HZ; seq_printf(seq, "\txprt:\ttcp %u %lu %lu %lu %ld %lu %lu %lu %Lu %Lu\n", - transport->port, + transport->srcport, xprt->stat.bind_count, xprt->stat.connect_count, xprt->stat.connect_time, @@ -2223,7 +2165,7 @@ static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args, memcpy(&xprt->addr, args->dstaddr, args->addrlen); xprt->addrlen = args->addrlen; if (args->srcaddr) - memcpy(&new->addr, args->srcaddr, args->addrlen); + memcpy(&new->srcaddr, args->srcaddr, args->addrlen); return xprt; } @@ -2272,7 +2214,7 @@ static struct rpc_xprt *xs_setup_udp(struct xprt_create *args) INIT_DELAYED_WORK(&transport->connect_worker, xs_udp_connect_worker4); - xs_format_ipv4_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP); + xs_format_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP); break; case AF_INET6: if (((struct sockaddr_in6 *)addr)->sin6_port != htons(0)) @@ -2280,15 +2222,22 @@ static struct rpc_xprt *xs_setup_udp(struct xprt_create *args) INIT_DELAYED_WORK(&transport->connect_worker, xs_udp_connect_worker6); - xs_format_ipv6_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP6); + xs_format_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP6); break; default: kfree(xprt); return ERR_PTR(-EAFNOSUPPORT); } - dprintk("RPC: set up transport to address %s\n", - xprt->address_strings[RPC_DISPLAY_ALL]); + if (xprt_bound(xprt)) + dprintk("RPC: set up xprt to %s (port %s) via %s\n", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT], + xprt->address_strings[RPC_DISPLAY_PROTO]); + else + dprintk("RPC: set up xprt to %s (autobind) via %s\n", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PROTO]); if (try_module_get(THIS_MODULE)) return xprt; @@ -2337,23 +2286,33 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args) if (((struct sockaddr_in *)addr)->sin_port != htons(0)) xprt_set_bound(xprt); - INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_connect_worker4); - xs_format_ipv4_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP); + INIT_DELAYED_WORK(&transport->connect_worker, + xs_tcp_connect_worker4); + xs_format_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP); break; case AF_INET6: if (((struct sockaddr_in6 *)addr)->sin6_port != htons(0)) xprt_set_bound(xprt); - INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_connect_worker6); - xs_format_ipv6_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP6); + INIT_DELAYED_WORK(&transport->connect_worker, + xs_tcp_connect_worker6); + xs_format_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP6); break; default: kfree(xprt); return ERR_PTR(-EAFNOSUPPORT); } - dprintk("RPC: set up transport to address %s\n", - xprt->address_strings[RPC_DISPLAY_ALL]); + if (xprt_bound(xprt)) + dprintk("RPC: set up xprt to %s (port %s) via %s\n", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT], + xprt->address_strings[RPC_DISPLAY_PROTO]); + else + dprintk("RPC: set up xprt to %s (autobind) via %s\n", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PROTO]); + if (try_module_get(THIS_MODULE)) return xprt; @@ -2412,3 +2371,55 @@ void cleanup_socket_xprt(void) xprt_unregister_transport(&xs_udp_transport); xprt_unregister_transport(&xs_tcp_transport); } + +static int param_set_uint_minmax(const char *val, struct kernel_param *kp, + unsigned int min, unsigned int max) +{ + unsigned long num; + int ret; + + if (!val) + return -EINVAL; + ret = strict_strtoul(val, 0, &num); + if (ret == -EINVAL || num < min || num > max) + return -EINVAL; + *((unsigned int *)kp->arg) = num; + return 0; +} + +static int param_set_portnr(const char *val, struct kernel_param *kp) +{ + return param_set_uint_minmax(val, kp, + RPC_MIN_RESVPORT, + RPC_MAX_RESVPORT); +} + +static int param_get_portnr(char *buffer, struct kernel_param *kp) +{ + return param_get_uint(buffer, kp); +} +#define param_check_portnr(name, p) \ + __param_check(name, p, unsigned int); + +module_param_named(min_resvport, xprt_min_resvport, portnr, 0644); +module_param_named(max_resvport, xprt_max_resvport, portnr, 0644); + +static int param_set_slot_table_size(const char *val, struct kernel_param *kp) +{ + return param_set_uint_minmax(val, kp, + RPC_MIN_SLOT_TABLE, + RPC_MAX_SLOT_TABLE); +} + +static int param_get_slot_table_size(char *buffer, struct kernel_param *kp) +{ + return param_get_uint(buffer, kp); +} +#define param_check_slot_table_size(name, p) \ + __param_check(name, p, unsigned int); + +module_param_named(tcp_slot_table_entries, xprt_tcp_slot_table_entries, + slot_table_size, 0644); +module_param_named(udp_slot_table_entries, xprt_udp_slot_table_entries, + slot_table_size, 0644); + diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 36d4e44d6233..fc3ebb906911 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -315,7 +315,7 @@ static void unix_write_space(struct sock *sk) { read_lock(&sk->sk_callback_lock); if (unix_writable(sk)) { - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) + if (sk_has_sleeper(sk)) wake_up_interruptible_sync(sk->sk_sleep); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } @@ -1985,7 +1985,7 @@ static unsigned int unix_poll(struct file *file, struct socket *sock, poll_table struct sock *sk = sock->sk; unsigned int mask; - poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk->sk_sleep, wait); mask = 0; /* exceptional events? */ @@ -2022,7 +2022,7 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk, *other; unsigned int mask, writable; - poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk->sk_sleep, wait); mask = 0; /* exceptional events? */ @@ -2053,7 +2053,7 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock, other = unix_peer_get(sk); if (other) { if (unix_peer(other) != sk) { - poll_wait(file, &unix_sk(other)->peer_wait, + sock_poll_wait(file, &unix_sk(other)->peer_wait, wait); if (unix_recvq_full(other)) writable = 0; diff --git a/net/wanrouter/wanmain.c b/net/wanrouter/wanmain.c index 466e2d22d256..258daa80ad92 100644 --- a/net/wanrouter/wanmain.c +++ b/net/wanrouter/wanmain.c @@ -48,6 +48,7 @@ #include <linux/kernel.h> #include <linux/module.h> /* support for loadable modules */ #include <linux/slab.h> /* kmalloc(), kfree() */ +#include <linux/smp_lock.h> #include <linux/mm.h> #include <linux/string.h> /* inline mem*, str* functions */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 241bddd0b4f1..634496b3ed77 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -447,6 +447,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) rdev = __cfg80211_drv_from_info(info); if (IS_ERR(rdev)) { + mutex_unlock(&cfg80211_mutex); result = PTR_ERR(rdev); goto unlock; } @@ -996,7 +997,7 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) if (IS_ERR(hdr)) { err = PTR_ERR(hdr); - goto out; + goto free_msg; } cookie.msg = msg; @@ -1010,7 +1011,7 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) &cookie, get_key_callback); if (err) - goto out; + goto free_msg; if (cookie.error) goto nla_put_failure; @@ -1021,6 +1022,7 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) nla_put_failure: err = -ENOBUFS; + free_msg: nlmsg_free(msg); out: cfg80211_put_dev(drv); diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 5e14371cda70..75a406d33619 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1089,17 +1089,18 @@ static void handle_reg_beacon(struct wiphy *wiphy, chan->beacon_found = true; + if (wiphy->disable_beacon_hints) + return; + chan_before.center_freq = chan->center_freq; chan_before.flags = chan->flags; - if ((chan->flags & IEEE80211_CHAN_PASSIVE_SCAN) && - !(chan->orig_flags & IEEE80211_CHAN_PASSIVE_SCAN)) { + if (chan->flags & IEEE80211_CHAN_PASSIVE_SCAN) { chan->flags &= ~IEEE80211_CHAN_PASSIVE_SCAN; channel_changed = true; } - if ((chan->flags & IEEE80211_CHAN_NO_IBSS) && - !(chan->orig_flags & IEEE80211_CHAN_NO_IBSS)) { + if (chan->flags & IEEE80211_CHAN_NO_IBSS) { chan->flags &= ~IEEE80211_CHAN_NO_IBSS; channel_changed = true; } diff --git a/net/wireless/reg.h b/net/wireless/reg.h index e37829a49dc4..4e167a8e11be 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -30,7 +30,8 @@ int set_regdom(const struct ieee80211_regdomain *rd); * non-radar 5 GHz channels. * * Drivers do not need to call this, cfg80211 will do it for after a scan - * on a newly found BSS. + * on a newly found BSS. If you cannot make use of this feature you can + * set the wiphy->disable_beacon_hints to true. */ int regulatory_hint_found_beacon(struct wiphy *wiphy, struct ieee80211_channel *beacon_chan, diff --git a/net/wireless/scan.c b/net/wireless/scan.c index e95b638b919f..7e595ce24eeb 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -35,8 +35,6 @@ void cfg80211_scan_done(struct cfg80211_scan_request *request, bool aborted) else nl80211_send_scan_done(wiphy_to_dev(request->wiphy), dev); - wiphy_to_dev(request->wiphy)->scan_req = NULL; - #ifdef CONFIG_WIRELESS_EXT if (!aborted) { memset(&wrqu, 0, sizeof(wrqu)); @@ -48,6 +46,7 @@ void cfg80211_scan_done(struct cfg80211_scan_request *request, bool aborted) dev_put(dev); out: + wiphy_to_dev(request->wiphy)->scan_req = NULL; kfree(request); } EXPORT_SYMBOL(cfg80211_scan_done); @@ -119,7 +118,7 @@ static int cmp_ies(u8 num, u8 *ies1, size_t len1, u8 *ies2, size_t len2) if (!ie1 && !ie2) return 0; - if (!ie1) + if (!ie1 || !ie2) return -1; r = memcmp(ie1 + 2, ie2 + 2, min(ie1[1], ie2[1])); @@ -172,6 +171,8 @@ static bool is_mesh(struct cfg80211_bss *a, ie = find_ie(WLAN_EID_MESH_CONFIG, a->information_elements, a->len_information_elements); + if (!ie) + return false; if (ie[1] != IEEE80211_MESH_CONFIG_LEN) return false; @@ -366,7 +367,6 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev, found = rb_find_bss(dev, res); if (found) { - kref_get(&found->ref); found->pub.beacon_interval = res->pub.beacon_interval; found->pub.tsf = res->pub.tsf; found->pub.signal = res->pub.signal; diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 21cdc872004e..5e6c072c64d3 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -40,6 +40,7 @@ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/smp_lock.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/net.h> diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c index d31ccb487730..faf54c6bf96b 100644 --- a/net/xfrm/xfrm_algo.c +++ b/net/xfrm/xfrm_algo.c @@ -292,8 +292,8 @@ static struct xfrm_algo_desc ealg_list[] = { } }, { - .name = "cbc(cast128)", - .compat = "cast128", + .name = "cbc(cast5)", + .compat = "cast5", .uinfo = { .encr = { diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 5f1f86565f16..f2f7c638083e 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -668,22 +668,10 @@ static struct xfrm_state *__xfrm_state_lookup(struct net *net, xfrm_address_t *d hlist_for_each_entry(x, entry, net->xfrm.state_byspi+h, byspi) { if (x->props.family != family || x->id.spi != spi || - x->id.proto != proto) + x->id.proto != proto || + xfrm_addr_cmp(&x->id.daddr, daddr, family)) continue; - switch (family) { - case AF_INET: - if (x->id.daddr.a4 != daddr->a4) - continue; - break; - case AF_INET6: - if (!ipv6_addr_equal((struct in6_addr *)daddr, - (struct in6_addr *) - x->id.daddr.a6)) - continue; - break; - } - xfrm_state_hold(x); return x; } @@ -699,26 +687,11 @@ static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, xfrm_addre hlist_for_each_entry(x, entry, net->xfrm.state_bysrc+h, bysrc) { if (x->props.family != family || - x->id.proto != proto) + x->id.proto != proto || + xfrm_addr_cmp(&x->id.daddr, daddr, family) || + xfrm_addr_cmp(&x->props.saddr, saddr, family)) continue; - switch (family) { - case AF_INET: - if (x->id.daddr.a4 != daddr->a4 || - x->props.saddr.a4 != saddr->a4) - continue; - break; - case AF_INET6: - if (!ipv6_addr_equal((struct in6_addr *)daddr, - (struct in6_addr *) - x->id.daddr.a6) || - !ipv6_addr_equal((struct in6_addr *)saddr, - (struct in6_addr *) - x->props.saddr.a6)) - continue; - break; - } - xfrm_state_hold(x); return x; } @@ -1001,25 +974,11 @@ static struct xfrm_state *__find_acq_core(struct net *net, unsigned short family x->props.family != family || x->km.state != XFRM_STATE_ACQ || x->id.spi != 0 || - x->id.proto != proto) + x->id.proto != proto || + xfrm_addr_cmp(&x->id.daddr, daddr, family) || + xfrm_addr_cmp(&x->props.saddr, saddr, family)) continue; - switch (family) { - case AF_INET: - if (x->id.daddr.a4 != daddr->a4 || - x->props.saddr.a4 != saddr->a4) - continue; - break; - case AF_INET6: - if (!ipv6_addr_equal((struct in6_addr *)x->id.daddr.a6, - (struct in6_addr *)daddr) || - !ipv6_addr_equal((struct in6_addr *) - x->props.saddr.a6, - (struct in6_addr *)saddr)) - continue; - break; - } - xfrm_state_hold(x); return x; } |