diff options
author | Ingo Molnar <mingo@elte.hu> | 2009-03-05 12:47:28 +0100 |
---|---|---|
committer | Ingo Molnar <mingo@elte.hu> | 2009-03-05 12:47:28 +0100 |
commit | 7df4edb07cf54a4868b9a750424c0d2aa68f8d66 (patch) | |
tree | 0ad0ad3f3dcb6f9edf26dde42ba625053dddf54f /net | |
parent | 0d688da5505d77bcef2441e0a22d8cc26459702d (diff) | |
parent | 559595a985e106d2fa9f0c79b7f5805453fed593 (diff) |
Merge branch 'linus' into core/iommu
Diffstat (limited to 'net')
51 files changed, 788 insertions, 311 deletions
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 6c132394026..2886d2fb9ab 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -1,12 +1,16 @@ #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/if_vlan.h> +#include <linux/netpoll.h> #include "vlan.h" /* VLAN rx hw acceleration helper. This acts like netif_{rx,receive_skb}(). */ int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp, u16 vlan_tci, int polling) { + if (netpoll_rx(skb)) + return NET_RX_DROP; + if (skb_bond_should_drop(skb)) goto drop; @@ -62,13 +66,13 @@ struct net_device *vlan_dev_real_dev(const struct net_device *dev) { return vlan_dev_info(dev)->real_dev; } -EXPORT_SYMBOL_GPL(vlan_dev_real_dev); +EXPORT_SYMBOL(vlan_dev_real_dev); u16 vlan_dev_vlan_id(const struct net_device *dev) { return vlan_dev_info(dev)->vlan_id; } -EXPORT_SYMBOL_GPL(vlan_dev_vlan_id); +EXPORT_SYMBOL(vlan_dev_vlan_id); static int vlan_gro_common(struct napi_struct *napi, struct vlan_group *grp, unsigned int vlan_tci, struct sk_buff *skb) @@ -100,6 +104,9 @@ int vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp, { int err = NET_RX_SUCCESS; + if (netpoll_receive_skb(skb)) + return NET_RX_DROP; + switch (vlan_gro_common(napi, grp, vlan_tci, skb)) { case -1: return netif_receive_skb(skb); @@ -126,6 +133,9 @@ int vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp, if (!skb) goto out; + if (netpoll_receive_skb(skb)) + goto out; + err = NET_RX_SUCCESS; switch (vlan_gro_common(napi, grp, vlan_tci, skb)) { diff --git a/net/9p/client.c b/net/9p/client.c index 821f1ec0b2c..1eb580c38fb 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -618,7 +618,7 @@ static struct p9_fid *p9_fid_create(struct p9_client *clnt) return ERR_PTR(-ENOMEM); ret = p9_idpool_get(clnt->fidpool); - if (fid->fid < 0) { + if (ret < 0) { ret = -ENOSPC; goto error; } diff --git a/net/9p/protocol.c b/net/9p/protocol.c index dcd7666824b..fc70147c771 100644 --- a/net/9p/protocol.c +++ b/net/9p/protocol.c @@ -29,6 +29,7 @@ #include <linux/errno.h> #include <linux/uaccess.h> #include <linux/sched.h> +#include <linux/types.h> #include <net/9p/9p.h> #include <net/9p/client.h> #include "protocol.h" @@ -160,29 +161,32 @@ p9pdu_vreadf(struct p9_fcall *pdu, int optional, const char *fmt, va_list ap) break; case 'w':{ int16_t *val = va_arg(ap, int16_t *); - if (pdu_read(pdu, val, sizeof(*val))) { + __le16 le_val; + if (pdu_read(pdu, &le_val, sizeof(le_val))) { errcode = -EFAULT; break; } - *val = cpu_to_le16(*val); + *val = le16_to_cpu(le_val); } break; case 'd':{ int32_t *val = va_arg(ap, int32_t *); - if (pdu_read(pdu, val, sizeof(*val))) { + __le32 le_val; + if (pdu_read(pdu, &le_val, sizeof(le_val))) { errcode = -EFAULT; break; } - *val = cpu_to_le32(*val); + *val = le32_to_cpu(le_val); } break; case 'q':{ int64_t *val = va_arg(ap, int64_t *); - if (pdu_read(pdu, val, sizeof(*val))) { + __le64 le_val; + if (pdu_read(pdu, &le_val, sizeof(le_val))) { errcode = -EFAULT; break; } - *val = cpu_to_le64(*val); + *val = le64_to_cpu(le_val); } break; case 's':{ @@ -362,19 +366,19 @@ p9pdu_vwritef(struct p9_fcall *pdu, int optional, const char *fmt, va_list ap) } break; case 'w':{ - int16_t val = va_arg(ap, int); + __le16 val = cpu_to_le16(va_arg(ap, int)); if (pdu_write(pdu, &val, sizeof(val))) errcode = -EFAULT; } break; case 'd':{ - int32_t val = va_arg(ap, int32_t); + __le32 val = cpu_to_le32(va_arg(ap, int32_t)); if (pdu_write(pdu, &val, sizeof(val))) errcode = -EFAULT; } break; case 'q':{ - int64_t val = va_arg(ap, int64_t); + __le64 val = cpu_to_le64(va_arg(ap, int64_t)); if (pdu_write(pdu, &val, sizeof(val))) errcode = -EFAULT; } diff --git a/net/Kconfig b/net/Kconfig index bf2776018f7..cdb8fdef6c4 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -24,14 +24,6 @@ if NET menu "Networking options" -config NET_NS - bool "Network namespace support" - default n - depends on EXPERIMENTAL && NAMESPACES - help - Allow user space to create what appear to be multiple instances - of the network stack. - config COMPAT_NET_DEV_OPS def_bool y diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index bdd9ccea17c..d2c27c808d3 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -67,6 +67,11 @@ static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb) { struct net_device *indev; + if (skb_warn_if_lro(skb)) { + kfree_skb(skb); + return; + } + indev = skb->dev; skb->dev = to->dev; skb_forward_csum(skb); @@ -89,7 +94,7 @@ void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb) /* called with rcu_read_lock */ void br_forward(const struct net_bridge_port *to, struct sk_buff *skb) { - if (!skb_warn_if_lro(skb) && should_deliver(to, skb)) { + if (should_deliver(to, skb)) { __br_forward(to, skb); return; } diff --git a/net/core/dev.c b/net/core/dev.c index 8d675975d85..72b0d26fd46 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1090,7 +1090,7 @@ int dev_open(struct net_device *dev) /* * Enable NET_DMA */ - dmaengine_get(); + net_dmaengine_get(); /* * Initialize multicasting status @@ -1172,7 +1172,7 @@ int dev_close(struct net_device *dev) /* * Shutdown NET_DMA */ - dmaengine_put(); + net_dmaengine_put(); return 0; } @@ -1534,7 +1534,19 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) skb->mac_len = skb->network_header - skb->mac_header; __skb_pull(skb, skb->mac_len); - if (WARN_ON(skb->ip_summed != CHECKSUM_PARTIAL)) { + if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { + struct net_device *dev = skb->dev; + struct ethtool_drvinfo info = {}; + + if (dev && dev->ethtool_ops && dev->ethtool_ops->get_drvinfo) + dev->ethtool_ops->get_drvinfo(dev, &info); + + WARN(1, "%s: caps=(0x%lx, 0x%lx) len=%d data_len=%d " + "ip_summed=%d", + info.driver, dev ? dev->features : 0L, + skb->sk ? skb->sk->sk_route_caps : 0L, + skb->len, skb->data_len, skb->ip_summed); + if (skb_header_cloned(skb) && (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) return ERR_PTR(err); @@ -2476,6 +2488,9 @@ static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { + if (netpoll_receive_skb(skb)) + return NET_RX_DROP; + switch (__napi_gro_receive(napi, skb)) { case -1: return netif_receive_skb(skb); @@ -2524,6 +2539,7 @@ struct sk_buff *napi_fraginfo_skb(struct napi_struct *napi, if (!pskb_may_pull(skb, ETH_HLEN)) { napi_reuse_skb(napi, skb); + skb = NULL; goto out; } @@ -2545,6 +2561,9 @@ int napi_gro_frags(struct napi_struct *napi, struct napi_gro_fraginfo *info) if (!skb) goto out; + if (netpoll_receive_skb(skb)) + goto out; + err = NET_RX_SUCCESS; switch (__napi_gro_receive(napi, skb)) { diff --git a/net/core/neighbour.c b/net/core/neighbour.c index f66c58df895..278a142d104 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1994,8 +1994,8 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) if (!net_eq(neigh_parms_net(p), net)) continue; - if (nidx++ < neigh_skip) - continue; + if (nidx < neigh_skip) + goto next; if (neightbl_fill_param_info(skb, tbl, p, NETLINK_CB(cb->skb).pid, @@ -2003,6 +2003,8 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) RTM_NEWNEIGHTBL, NLM_F_MULTI) <= 0) goto out; + next: + nidx++; } neigh_skip = 0; @@ -2082,12 +2084,10 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, if (h > s_h) s_idx = 0; for (n = tbl->hash_buckets[h], idx = 0; n; n = n->next) { - int lidx; if (dev_net(n->dev) != net) continue; - lidx = idx++; - if (lidx < s_idx) - continue; + if (idx < s_idx) + goto next; if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, @@ -2096,6 +2096,8 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, rc = -1; goto out; } + next: + idx++; } } read_unlock_bh(&tbl->lock); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 55cffad2f32..2adb1a7d361 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -32,24 +32,14 @@ static __net_init int setup_net(struct net *net) { /* Must be called with net_mutex held */ struct pernet_operations *ops; - int error; - struct net_generic *ng; + int error = 0; atomic_set(&net->count, 1); + #ifdef NETNS_REFCNT_DEBUG atomic_set(&net->use_count, 0); #endif - error = -ENOMEM; - ng = kzalloc(sizeof(struct net_generic) + - INITIAL_NET_GEN_PTRS * sizeof(void *), GFP_KERNEL); - if (ng == NULL) - goto out; - - ng->len = INITIAL_NET_GEN_PTRS; - rcu_assign_pointer(net->gen, ng); - - error = 0; list_for_each_entry(ops, &pernet_list, list) { if (ops->init) { error = ops->init(net); @@ -70,24 +60,50 @@ out_undo: } rcu_barrier(); - kfree(ng); goto out; } +static struct net_generic *net_alloc_generic(void) +{ + struct net_generic *ng; + size_t generic_size = sizeof(struct net_generic) + + INITIAL_NET_GEN_PTRS * sizeof(void *); + + ng = kzalloc(generic_size, GFP_KERNEL); + if (ng) + ng->len = INITIAL_NET_GEN_PTRS; + + return ng; +} + #ifdef CONFIG_NET_NS static struct kmem_cache *net_cachep; static struct workqueue_struct *netns_wq; static struct net *net_alloc(void) { - return kmem_cache_zalloc(net_cachep, GFP_KERNEL); + struct net *net = NULL; + struct net_generic *ng; + + ng = net_alloc_generic(); + if (!ng) + goto out; + + net = kmem_cache_zalloc(net_cachep, GFP_KERNEL); + if (!net) + goto out_free; + + rcu_assign_pointer(net->gen, ng); +out: + return net; + +out_free: + kfree(ng); + goto out; } static void net_free(struct net *net) { - if (!net) - return; - #ifdef NETNS_REFCNT_DEBUG if (unlikely(atomic_read(&net->use_count) != 0)) { printk(KERN_EMERG "network namespace not free! Usage: %d\n", @@ -112,27 +128,28 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net) err = -ENOMEM; new_net = net_alloc(); if (!new_net) - goto out; + goto out_err; mutex_lock(&net_mutex); err = setup_net(new_net); - if (err) - goto out_unlock; - - rtnl_lock(); - list_add_tail(&new_net->list, &net_namespace_list); - rtnl_unlock(); - - -out_unlock: + if (!err) { + rtnl_lock(); + list_add_tail(&new_net->list, &net_namespace_list); + rtnl_unlock(); + } mutex_unlock(&net_mutex); + + if (err) + goto out_free; out: put_net(old_net); - if (err) { - net_free(new_net); - new_net = ERR_PTR(err); - } return new_net; + +out_free: + net_free(new_net); +out_err: + new_net = ERR_PTR(err); + goto out; } static void cleanup_net(struct work_struct *work) @@ -188,6 +205,7 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net) static int __init net_ns_init(void) { + struct net_generic *ng; int err; printk(KERN_INFO "net_namespace: %zd bytes\n", sizeof(struct net)); @@ -202,6 +220,12 @@ static int __init net_ns_init(void) panic("Could not create netns workq"); #endif + ng = net_alloc_generic(); + if (!ng) + panic("Could not allocate generic netns"); + + rcu_assign_pointer(init_net.gen, ng); + mutex_lock(&net_mutex); err = setup_net(&init_net); @@ -341,8 +365,8 @@ again: rv = register_pernet_operations(first_device, ops); if (rv < 0) ida_remove(&net_generic_ids, *id); - mutex_unlock(&net_mutex); out: + mutex_unlock(&net_mutex); return rv; } EXPORT_SYMBOL_GPL(register_pernet_gen_subsys); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 65eac773903..c6a6b166f8d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -73,17 +73,13 @@ static struct kmem_cache *skbuff_fclone_cache __read_mostly; static void sock_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - struct sk_buff *skb = (struct sk_buff *) buf->private; - - kfree_skb(skb); + put_page(buf->page); } static void sock_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - struct sk_buff *skb = (struct sk_buff *) buf->private; - - skb_get(skb); + get_page(buf->page); } static int sock_pipe_buf_steal(struct pipe_inode_info *pipe, @@ -147,14 +143,6 @@ void skb_under_panic(struct sk_buff *skb, int sz, void *here) BUG(); } -void skb_truesize_bug(struct sk_buff *skb) -{ - WARN(net_ratelimit(), KERN_ERR "SKB BUG: Invalid truesize (%u) " - "len=%u, sizeof(sk_buff)=%Zd\n", - skb->truesize, skb->len, sizeof(struct sk_buff)); -} -EXPORT_SYMBOL(skb_truesize_bug); - /* Allocate a new skbuff. We do this ourselves so we can fill in a few * 'private' fields and also do memory statistics to find all the * [BEEP] leaks. @@ -1334,9 +1322,19 @@ fault: */ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i) { - struct sk_buff *skb = (struct sk_buff *) spd->partial[i].private; + put_page(spd->pages[i]); +} - kfree_skb(skb); +static inline struct page *linear_to_page(struct page *page, unsigned int len, + unsigned int offset) +{ + struct page *p = alloc_pages(GFP_KERNEL, 0); + + if (!p) + return NULL; + memcpy(page_address(p) + offset, page_address(page) + offset, len); + + return p; } /* @@ -1344,16 +1342,23 @@ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i) */ static inline int spd_fill_page(struct splice_pipe_desc *spd, struct page *page, unsigned int len, unsigned int offset, - struct sk_buff *skb) + struct sk_buff *skb, int linear) { if (unlikely(spd->nr_pages == PIPE_BUFFERS)) return 1; + if (linear) { + page = linear_to_page(page, len, offset); + if (!page) + return 1; + } else + get_page(page); + spd->pages[spd->nr_pages] = page; spd->partial[spd->nr_pages].len = len; spd->partial[spd->nr_pages].offset = offset; - spd->partial[spd->nr_pages].private = (unsigned long) skb_get(skb); spd->nr_pages++; + return 0; } @@ -1369,7 +1374,7 @@ static inline void __segment_seek(struct page **page, unsigned int *poff, static inline int __splice_segment(struct page *page, unsigned int poff, unsigned int plen, unsigned int *off, unsigned int *len, struct sk_buff *skb, - struct splice_pipe_desc *spd) + struct splice_pipe_desc *spd, int linear) { if (!*len) return 1; @@ -1392,7 +1397,7 @@ static inline int __splice_segment(struct page *page, unsigned int poff, /* the linear region may spread across several pages */ flen = min_t(unsigned int, flen, PAGE_SIZE - poff); - if (spd_fill_page(spd, page, flen, poff, skb)) + if (spd_fill_page(spd, page, flen, poff, skb, linear)) return 1; __segment_seek(&page, &poff, &plen, flen); @@ -1419,7 +1424,7 @@ static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset, if (__splice_segment(virt_to_page(skb->data), (unsigned long) skb->data & (PAGE_SIZE - 1), skb_headlen(skb), - offset, len, skb, spd)) + offset, len, skb, spd, 1)) return 1; /* @@ -1429,7 +1434,7 @@ static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset, const skb_frag_t *f = &skb_shinfo(skb)->frags[seg]; if (__splice_segment(f->page, f->page_offset, f->size, - offset, len, skb, spd)) + offset, len, skb, spd, 0)) return 1; } @@ -1442,7 +1447,7 @@ static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset, * the frag list, if such a thing exists. We'd probably need to recurse to * handle that cleanly. */ -int skb_splice_bits(struct sk_buff *__skb, unsigned int offset, +int skb_splice_bits(struct sk_buff *skb, unsigned int offset, struct pipe_inode_info *pipe, unsigned int tlen, unsigned int flags) { @@ -1455,16 +1460,6 @@ int skb_splice_bits(struct sk_buff *__skb, unsigned int offset, .ops = &sock_pipe_buf_ops, .spd_release = sock_spd_release, }; - struct sk_buff *skb; - - /* - * I'd love to avoid the clone here, but tcp_read_sock() - * ignores reference counts and unconditonally kills the sk_buff - * on return from the actor. - */ - skb = skb_clone(__skb, GFP_KERNEL); - if (unlikely(!skb)) - return -ENOMEM; /* * __skb_splice_bits() only fails if the output has no room left, @@ -1488,15 +1483,9 @@ int skb_splice_bits(struct sk_buff *__skb, unsigned int offset, } done: - /* - * drop our reference to the clone, the pipe consumption will - * drop the rest. - */ - kfree_skb(skb); - if (spd.nr_pages) { + struct sock *sk = skb->sk; int ret; - struct sock *sk = __skb->sk; /* * Drop the socket lock, otherwise we have reverse @@ -2215,10 +2204,10 @@ unsigned int skb_seq_read(unsigned int consumed, const u8 **data, return 0; next_skb: - block_limit = skb_headlen(st->cur_skb); + block_limit = skb_headlen(st->cur_skb) + st->stepped_offset; if (abs_offset < block_limit) { - *data = st->cur_skb->data + abs_offset; + *data = st->cur_skb->data + (abs_offset - st->stepped_offset); return block_limit - abs_offset; } @@ -2253,13 +2242,14 @@ next_skb: st->frag_data = NULL; } - if (st->cur_skb->next) { - st->cur_skb = st->cur_skb->next; + if (st->root_skb == st->cur_skb && + skb_shinfo(st->root_skb)->frag_list) { + st->cur_skb = skb_shinfo(st->root_skb)->frag_list; st->frag_idx = 0; goto next_skb; - } else if (st->root_skb == st->cur_skb && - skb_shinfo(st->root_skb)->frag_list) { - st->cur_skb = skb_shinfo(st->root_skb)->frag_list; + } else if (st->cur_skb->next) { + st->cur_skb = st->cur_skb->next; + st->frag_idx = 0; goto next_skb; } @@ -2588,8 +2578,9 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) struct sk_buff *nskb; unsigned int headroom; unsigned int hlen = p->data - skb_mac_header(p); + unsigned int len = skb->len; - if (hlen + p->len + skb->len >= 65536) + if (hlen + p->len + len >= 65536) return -E2BIG; if (skb_shinfo(p)->frag_list) @@ -2651,9 +2642,9 @@ merge: done: NAPI_GRO_CB(p)->count++; - p->data_len += skb->len; - p->truesize += skb->len; - p->len += skb->len; + p->data_len += len; + p->truesize += len; + p->len += len; NAPI_GRO_CB(skb)->same_flow = 1; return 0; diff --git a/net/core/sock.c b/net/core/sock.c index f3a0d08cbb4..5f97caa158e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -696,6 +696,8 @@ int sock_getsockopt(struct socket *sock, int level, int optname, if (len < 0) return -EINVAL; + memset(&v, 0, sizeof(v)); + switch(optname) { case SO_DEBUG: v.val = sock_flag(sk, SOCK_DBG); @@ -1135,7 +1137,6 @@ void sock_rfree(struct sk_buff *skb) { struct sock *sk = skb->sk; - skb_truesize_check(skb); atomic_sub(skb->truesize, &sk->sk_rmem_alloc); sk_mem_uncharge(skb->sk, skb->truesize); } diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 6bb2635b5de..7bc992976d2 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -3,11 +3,16 @@ * * This is an implementation of the CIPSO 2.2 protocol as specified in * draft-ietf-cipso-ipsecurity-01.txt with additional tag types as found in - * FIPS-188, copies of both documents can be found in the Documentation - * directory. While CIPSO never became a full IETF RFC standard many vendors + * FIPS-188. While CIPSO never became a full IETF RFC standard many vendors * have chosen to adopt the protocol and over the years it has become a * de-facto standard for labeled networking. * + * The CIPSO draft specification can be found in the kernel's Documentation + * directory as well as the following URL: + * http://netlabel.sourceforge.net/files/draft-ietf-cipso-ipsecurity-01.txt + * The FIPS-188 specification can be found at the following URL: + * http://www.itl.nist.gov/fipspubs/fip188.htm + * * Author: Paul Moore <paul.moore@hp.com> * */ diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 42a0f3dd3fd..d722013c1ca 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -1268,6 +1268,9 @@ __be32 __init root_nfs_parse_addr(char *name) static int __init ip_auto_config(void) { __be32 addr; +#ifdef IPCONFIG_DYNAMIC + int retries = CONF_OPEN_RETRIES; +#endif #ifdef CONFIG_PROC_FS proc_net_fops_create(&init_net, "pnp", S_IRUGO, &pnp_seq_fops); @@ -1304,9 +1307,6 @@ static int __init ip_auto_config(void) #endif ic_first_dev->next) { #ifdef IPCONFIG_DYNAMIC - - int retries = CONF_OPEN_RETRIES; - if (ic_dynamic() < 0) { ic_close_devs(); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0cd71b84e48..76b148bcb0d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -524,7 +524,8 @@ static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, struct tcp_splice_state *tss = rd_desc->arg.data; int ret; - ret = skb_splice_bits(skb, offset, tss->pipe, rd_desc->count, tss->flags); + ret = skb_splice_bits(skb, offset, tss->pipe, min(rd_desc->count, len), + tss->flags); if (ret > 0) rd_desc->count -= ret; return ret; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a6961d75c7e..c28976a7e59 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1374,7 +1374,8 @@ static u8 tcp_sacktag_one(struct sk_buff *skb, struct sock *sk, static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, struct tcp_sacktag_state *state, - unsigned int pcount, int shifted, int mss) + unsigned int pcount, int shifted, int mss, + int dup_sack) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *prev = tcp_write_queue_prev(sk, skb); @@ -1410,7 +1411,7 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, } /* We discard results */ - tcp_sacktag_one(skb, sk, state, 0, pcount); + tcp_sacktag_one(skb, sk, state, dup_sack, pcount); /* Difference in this won't matter, both ACKed by the same cumul. ACK */ TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS); @@ -1561,7 +1562,7 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, if (!skb_shift(prev, skb, len)) goto fallback; - if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss)) + if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss, dup_sack)) goto out; /* Hole filled allows collapsing with the next as well, this is very @@ -1580,7 +1581,7 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, len = skb->len; if (skb_shift(prev, skb, len)) { pcount += tcp_skb_pcount(skb); - tcp_shifted_skb(sk, skb, state, tcp_skb_pcount(skb), len, mss); + tcp_shifted_skb(sk, skb, state, tcp_skb_pcount(skb), len, mss, 0); } out: diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 557fe16cbfb..da2c3b8794f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -663,14 +663,10 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, th->urg_ptr = 0; /* The urg_mode check is necessary during a below snd_una win probe */ - if (unlikely(tcp_urg_mode(tp))) { - if (between(tp->snd_up, tcb->seq + 1, tcb->seq + 0xFFFF)) { - th->urg_ptr = htons(tp->snd_up - tcb->seq); - th->urg = 1; - } else if (after(tcb->seq + 0xFFFF, tp->snd_nxt)) { - th->urg_ptr = 0xFFFF; - th->urg = 1; - } + if (unlikely(tcp_urg_mode(tp) && + between(tp->snd_up, tcb->seq + 1, tcb->seq + 0xFFFF))) { + th->urg_ptr = htons(tp->snd_up - tcb->seq); + th->urg = 1; } tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location); @@ -2027,7 +2023,6 @@ void tcp_xmit_retransmit_queue(struct sock *sk) last_lost = tp->snd_una; } - /* First pass: retransmit lost packets. */ tcp_for_write_queue_from(skb, sk) { __u8 sacked = TCP_SKB_CB(skb)->sacked; diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c index 2747ec7bfb6..4660b088a8c 100644 --- a/net/ipv4/tcp_scalable.c +++ b/net/ipv4/tcp_scalable.c @@ -1,6 +1,6 @@ /* Tom Kelly's Scalable TCP * - * See htt://www-lce.eng.cam.ac.uk/~ctk21/scalable/ + * See http://www.deneholme.net/tom/scalable/ * * John Heffner <jheffner@sc.edu> */ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index cf5ab0581eb..c47c989cb1f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -120,8 +120,11 @@ EXPORT_SYMBOL(sysctl_udp_wmem_min); atomic_t udp_memory_allocated; EXPORT_SYMBOL(udp_memory_allocated); +#define PORTS_PER_CHAIN (65536 / UDP_HTABLE_SIZE) + static int udp_lib_lport_inuse(struct net *net, __u16 num, const struct udp_hslot *hslot, + unsigned long *bitmap, struct sock *sk, int (*saddr_comp)(const struct sock *sk1, const struct sock *sk2)) @@ -132,12 +135,17 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num, sk_nulls_for_each(sk2, node, &hslot->head) if (net_eq(sock_net(sk2), net) && sk2 != sk && - sk2->sk_hash == num && + (bitmap || sk2->sk_hash == num) && (!sk2->sk_reuse || !sk->sk_reuse) && (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && - (*saddr_comp)(sk, sk2)) - return 1; + (*saddr_comp)(sk, sk2)) { + if (bitmap) + __set_bit(sk2->sk_hash / UDP_HTABLE_SIZE, + bitmap); + else + return 1; + } return 0; } @@ -160,32 +168,47 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, if (!snum) { int low, high, remaining; unsigned rand; - unsigned short first; + unsigned short first, last; + DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN); inet_get_local_port_range(&low, &high); remaining = (high - low) + 1; rand = net_random(); - snum = first = rand % remaining + low; - rand |= 1; - for (;;) { - hslot = &udptable->hash[udp_hashfn(net, snum)]; + first = (((u64)rand * remaining) >> 32) + low; + /* + * force rand to be an odd multiple of UDP_HTABLE_SIZE + */ + rand = (rand | 1) * UDP_HTABLE_SIZE; + for (last = first + UDP_HTABLE_SIZE; first != last; first++) { + hslot = &udptable->hash[udp_hashfn(net, first)]; + bitmap_zero(bitmap, PORTS_PER_CHAIN); spin_lock_bh(&hslot->lock); - if (!udp_lib_lport_inuse(net, snum, hslot, sk, saddr_comp)) - break; - spin_unlock_bh(&hslot->lock); + udp_lib_lport_inuse(net, snum, hslot, bitmap, sk, + saddr_comp); + + snum = first; + /* + * Iterate on all possible values of snum for this hash. + * Using steps of an odd multiple of UDP_HTABLE_SIZE + * give us randomization and full range coverage. + */ do { - snum = snum + rand; - } while (snum < low || snum > high); - if (snum == first) - goto fail; + if (low <= snum && snum <= high && + !test_bit(snum / UDP_HTABLE_SIZE, bitmap)) + goto found; + snum += rand; + } while (snum != first); + spin_unlock_bh(&hslot->lock); } + goto fail; } else { hslot = &udptable->hash[udp_hashfn(net, snum)]; spin_lock_bh(&hslot->lock); - if (udp_lib_lport_inuse(net, snum, hslot, sk, saddr_comp)) + if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, saddr_comp)) goto fail_unlock; } +found: inet_sk(sk)->num = snum; sk->sk_hash = snum; if (sk_unhashed(sk)) { @@ -992,9 +1015,11 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if ((rc = sock_queue_rcv_skb(sk, skb)) < 0) { /* Note that an ENOMEM error is charged twice */ - if (rc == -ENOMEM) + if (rc == -ENOMEM) { UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS, is_udplite); + atomic_inc(&sk->sk_drops); + } goto drop; } @@ -1206,11 +1231,10 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { struct sock *sk; - struct udphdr *uh = udp_hdr(skb); + struct udphdr *uh; unsigned short ulen; struct rtable *rt = (struct rtable*)skb->dst; - __be32 saddr = ip_hdr(skb)->saddr; - __be32 daddr = ip_hdr(skb)->daddr; + __be32 saddr, daddr; struct net *net = dev_net(skb->dev); /* @@ -1219,6 +1243,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto drop; /* No space for header. */ + uh = udp_hdr(skb); ulen = ntohs(uh->len); if (ulen > skb->len) goto short_packet; @@ -1233,6 +1258,9 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (udp4_csum_init(skb, uh, proto)) goto csum_error; + saddr = ip_hdr(skb)->saddr; + daddr = ip_hdr(skb)->daddr; + if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST)) return __udp4_lib_mcast_deliver(net, skb, uh, saddr, daddr, udptable); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index e92ad8455c6..f9afb452249 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4250,7 +4250,7 @@ static struct addrconf_sysctl_table .procname = "mc_forwarding", .data = &ipv6_devconf.mc_forwarding, .maxlen = sizeof(int), - .mode = 0644, + .mode = 0444, .proc_handler = proc_dointvec, }, #endif diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 94f74f5b0cb..c802bc1658a 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -797,6 +797,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, unsigned int nlen; int flush = 1; int proto; + __wsum csum; if (unlikely(!pskb_may_pull(skb, sizeof(*iph)))) goto out; @@ -808,6 +809,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, rcu_read_lock(); proto = ipv6_gso_pull_exthdrs(skb, iph->nexthdr); + iph = ipv6_hdr(skb); IPV6_GRO_CB(skb)->proto = proto; ops = rcu_dereference(inet6_protos[proto]); if (!ops || !ops->gro_receive) @@ -839,8 +841,13 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, NAPI_GRO_CB(skb)->flush |= flush; + csum = skb->csum; + skb_postpull_rcsum(skb, iph, skb_network_header_len(skb)); + pp = ops->gro_receive(head, skb); + skb->csum = csum; + out_unlock: rcu_read_unlock(); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 4f433847d95..36dff880718 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -443,10 +443,10 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, if (xfrm_decode_session_reverse(skb, &fl2, AF_INET6)) goto relookup_failed; - if (ip6_dst_lookup(sk, &dst2, &fl)) + if (ip6_dst_lookup(sk, &dst2, &fl2)) goto relookup_failed; - err = xfrm_lookup(net, &dst2, &fl, sk, XFRM_LOOKUP_ICMP); + err = xfrm_lookup(net, &dst2, &fl2, sk, XFRM_LOOKUP_ICMP); switch (err) { case 0: dst_release(dst); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 8fe267feb81..1bcc3431859 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -258,11 +258,11 @@ unique: if (twp != NULL) { *twp = tw; - NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_TIMEWAITRECYCLED); + NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); } else if (tw != NULL) { /* Silly. Should hash-dance instead... */ inet_twsk_deschedule(tw, death_row); - NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_TIMEWAITRECYCLED); + NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); inet_twsk_put(tw); } diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index c62dd247774..7712578bdc6 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -323,17 +323,21 @@ static struct ip6_flowlabel * fl_create(struct net *net, struct in6_flowlabel_req *freq, char __user *optval, int optlen, int *err_p) { - struct ip6_flowlabel *fl; + struct ip6_flowlabel *fl = NULL; int olen; int addr_type; int err; + olen = optlen - CMSG_ALIGN(sizeof(*freq)); + err = -EINVAL; + if (olen > 64 * 1024) + goto done; + err = -ENOMEM; fl = kzalloc(sizeof(*fl), GFP_KERNEL); if (fl == NULL) goto done; - olen = optlen - CMSG_ALIGN(sizeof(*freq)); if (olen > 0) { struct msghdr msg; struct flowi flowi; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 936f48946e2..f171e8dbac9 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -255,6 +255,7 @@ int ip6_mc_input(struct sk_buff *skb) * IPv6 multicast router mode is now supported ;) */ if (dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding && + !(ipv6_addr_type(&hdr->daddr) & IPV6_ADDR_LINKLOCAL) && likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) { /* * Okay, we try to forward - split and duplicate @@ -316,7 +317,6 @@ int ip6_mc_input(struct sk_buff *skb) } if (skb2) { - skb2->dev = skb2->dst->dev; ip6_mr_input(skb2); } } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 4b15938bef4..9fb49c3b518 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1105,6 +1105,18 @@ static inline int ip6_ufo_append_data(struct sock *sk, return err; } +static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src, + gfp_t gfp) +{ + return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL; +} + +static inline struct ipv6_rt_hdr *ip6_rthdr_dup(struct ipv6_rt_hdr *src, + gfp_t gfp) +{ + return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL; +} + int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, @@ -1130,17 +1142,37 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, * setup for corking */ if (opt) { - if (np->cork.opt == NULL) { - np->cork.opt = kmalloc(opt->tot_len, - sk->sk_allocation); - if (unlikely(np->cork.opt == NULL)) - return -ENOBUFS; - } else if (np->cork.opt->tot_len < opt->tot_len) { - printk(KERN_DEBUG "ip6_append_data: invalid option length\n"); + if (WARN_ON(np->cork.opt)) return -EINVAL; - } - memcpy(np->cork.opt, opt, opt->tot_len); - inet->cork.flags |= IPCORK_OPT; + + np->cork.opt = kmalloc(opt->tot_len, sk->sk_allocation); + if (unlikely(np->cork.opt == NULL)) + return -ENOBUFS; + + np->cork.opt->tot_len = opt->tot_len; + np->cork.opt->opt_flen = opt->opt_flen; + np->cork.opt->opt_nflen = opt->opt_nflen; + + np->cork.opt->dst0opt = ip6_opt_dup(opt->dst0opt, + sk->sk_allocation); + if (opt->dst0opt && !np->cork.opt->dst0opt) + return -ENOBUFS; + + np->cork.opt->dst1opt = ip6_opt_dup(opt->dst1opt, + sk->sk_allocation); + if (opt->dst1opt && !np->cork.opt->dst1opt) + return -ENOBUFS; + + np->cork.opt->hopopt = ip6_opt_dup(opt->hopopt, + sk->sk_allocation); + if (opt->hopopt && !np->cork.opt->hopopt) + return -ENOBUFS; + + np->cork.opt->srcrt = ip6_rthdr_dup(opt->srcrt, + sk->sk_allocation); + if (opt->srcrt && !np->cork.opt->srcrt) + return -ENOBUFS; + /* need source address above miyazawa*/ } dst_hold(&rt->u.dst); @@ -1167,8 +1199,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, } else { rt = (struct rt6_info *)inet->cork.dst; fl = &inet->cork.fl; - if (inet->cork.flags & IPCORK_OPT) - opt = np->cork.opt; + opt = np->cork.opt; transhdrlen = 0; exthdrlen = 0; mtu = inet->cork.fragsize; @@ -1407,9 +1438,15 @@ error: static void ip6_cork_release(struct inet_sock *inet, struct ipv6_pinfo *np) { - inet->cork.flags &= ~IPCORK_OPT; - kfree(np->cork.opt); - np->cork.opt = NULL; + if (np->cork.opt) { + kfree(np->cork.opt->dst0opt); + kfree(np->cork.opt->dst1opt); + kfree(np->cork.opt->hopopt); + kfree(np->cork.opt->srcrt); + kfree(np->cork.opt); + np->cork.opt = NULL; + } + if (inet->cork.dst) { dst_release(inet->cork.dst); inet->cork.dst = NULL; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 58e2b0d9375..d994c55a5b1 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -249,8 +249,8 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p) } t = netdev_priv(dev); - ip6_tnl_dev_init(dev); t->parms = *p; + ip6_tnl_dev_init(dev); if ((err = register_netdevice(dev)) < 0) goto failed_free; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 3c51b2d827f..228be551e9c 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -48,6 +48,7 @@ #include <linux/pim.h> #include <net/addrconf.h> #include <linux/netfilter_ipv6.h> +#include <net/ip6_checksum.h> /* Big lock, protecting vif table, mrt cache and mroute socket state. Note that the changes are semaphored via rtnl_lock. @@ -365,7 +366,9 @@ static int pim6_rcv(struct sk_buff *skb) pim = (struct pimreghdr *)skb_transport_header(skb); if (pim->type != ((PIM_VERSION << 4) | PIM_REGISTER) || (pim->flags & PIM_NULL_REGISTER) || - (ip_compute_csum((void *)pim, sizeof(*pim)) != 0 && + (csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, + sizeof(*pim), IPPROTO_PIM, + csum_partial((void *)pim, sizeof(*pim), 0)) && csum_fold(skb_checksum(skb, 0, skb->len, 0)))) goto drop; @@ -392,7 +395,7 @@ static int pim6_rcv(struct sk_buff *skb) skb_pull(skb, (u8 *)encap - skb->data); skb_reset_network_header(skb); skb->dev = reg_dev; - skb->protocol = htons(ETH_P_IP); + skb->protocol = htons(ETH_P_IPV6); skb->ip_summed = 0; skb->pkt_type = PACKET_HOST; dst_release(skb->dst); @@ -481,6 +484,7 @@ static int mif6_delete(struct net *net, int vifi) { struct mif_device *v; struct net_device *dev; + struct inet6_dev *in6_dev; if (vifi < 0 || vifi >= net->ipv6.maxvif) return -EADDRNOTAVAIL; @@ -513,6 +517,10 @@ static int mif6_delete(struct net *net, int vifi) dev_set_allmulti(dev, -1); + in6_dev = __in6_dev_get(dev); + if (in6_dev) + in6_dev->cnf.mc_forwarding--; + if (v->flags & MIFF_REGISTER) unregister_netdevice(dev); @@ -622,6 +630,7 @@ static int mif6_add(struct net *net, struct mif6ctl *vifc, int mrtsock) int vifi = vifc->mif6c_mifi; struct mif_device *v = &net->ipv6.vif6_table[vifi]; struct net_device *dev; + struct inet6_dev *in6_dev; int err; /* Is vif busy ? */ @@ -662,6 +671,10 @@ static int mif6_add(struct net *net, struct mif6ctl *vifc, int mrtsock) return -EINVAL; } + in6_dev = __in6_dev_get(dev); + if (in6_dev) + in6_dev->cnf.mc_forwarding++; + /* * Fill in the VIF structures */ @@ -838,8 +851,6 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi, skb->dst = dst_clone(pkt->dst); skb->ip_summed = CHECKSUM_UNNECESSARY; - - skb_pull(skb, sizeof(struct ipv6hdr)); } if (net->ipv6.mroute6_sk == NULL) { @@ -1222,8 +1233,10 @@ static int ip6mr_sk_init(struct sock *sk) rtnl_lock(); write_lock_bh(&mrt_lock); - if (likely(net->ipv6.mroute6_sk == NULL)) + if (likely(net->ipv6.mroute6_sk == NULL)) { net->ipv6.mroute6_sk = sk; + net->ipv6.devconf_all->mc_forwarding++; + } else err = -EADDRINUSE; write_unlock_bh(&mrt_lock); @@ -1242,6 +1255,7 @@ int ip6mr_sk_done(struct sock *sk) if (sk == net->ipv6.mroute6_sk) { write_lock_bh(&mrt_lock); net->ipv6.mroute6_sk = NULL; + net->ipv6.devconf_all->mc_forwarding--; write_unlock_bh(&mrt_lock); mroute_clean_tables(net); diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index c455cf4ee75..72dbb6d1a6b 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -49,8 +49,19 @@ static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, static const u_int8_t invmap[] = { [ICMPV6_ECHO_REQUEST - 128] = ICMPV6_ECHO_REPLY + 1, [ICMPV6_ECHO_REPLY - 128] = ICMPV6_ECHO_REQUEST + 1, - [ICMPV6_NI_QUERY - 128] = ICMPV6_NI_QUERY + 1, - [ICMPV6_NI_REPLY - 128] = ICMPV6_NI_REPLY +1 + [ICMPV6_NI_QUERY - 128] = ICMPV6_NI_REPLY + 1, + [ICMPV6_NI_REPLY - 128] = ICMPV6_NI_QUERY +1 +}; + +static const u_int8_t noct_valid_new[] = { + [ICMPV6_MGM_QUERY - 130] = 1, + [ICMPV6_MGM_REPORT -130] = 1, + [ICMPV6_MGM_REDUCTION - 130] = 1, + [NDISC_ROUTER_SOLICITATION - 130] = 1, + [NDISC_ROUTER_ADVERTISEMENT - 130] = 1, + [NDISC_NEIGHBOUR_SOLICITATION - 130] = 1, + [NDISC_NEIGHBOUR_ADVERTISEMENT - 130] = 1, + [ICMPV6_MLD2_REPORT - 130] = 1 }; static bool icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple, @@ -178,6 +189,7 @@ icmpv6_error(struct net *net, struct sk_buff *skb, unsigned int dataoff, { const struct icmp6hdr *icmp6h; struct icmp6hdr _ih; + int type; icmp6h = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih); if (icmp6h == NULL) { @@ -189,11 +201,21 @@ icmpv6_error(struct net *net, struct sk_buff *skb, unsigned int dataoff, if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING && nf_ip6_checksum(skb, hooknum, dataoff, IPPROTO_ICMPV6)) { - nf_log_packet(PF_INET6, 0, skb, NULL, NULL, NULL, - "nf_ct_icmpv6: ICMPv6 checksum failed\n"); + if (LOG_INVALID(net, IPPROTO_ICMPV6)) + nf_log_packet(PF_INET6, 0, skb, NULL, NULL, NULL, + "nf_ct_icmpv6: ICMPv6 checksum failed "); return -NF_ACCEPT; } + type = icmp6h->icmp6_type - 130; + if (type >= 0 && type < sizeof(noct_valid_new) && + noct_valid_new[type]) { + skb->nfct = &nf_conntrack_untracked.ct_general; + skb->nfctinfo = IP_CT_NEW; + nf_conntrack_get(skb->nfct); + return NF_ACCEPT; + } + /* is not error message ? */ if (icmp6h->icmp6_type >= 128) return NF_ACCEPT; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c4a59824ac2..9c574235c90 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -794,7 +794,7 @@ void ip6_route_input(struct sk_buff *skb) .proto = iph->nexthdr, }; - if (rt6_need_strict(&iph->daddr)) + if (rt6_need_strict(&iph->daddr) && skb->dev->type != ARPHRD_PIMREG) flags |= RT6_LOOKUP_F_IFACE; skb->dst = fib6_rule_lookup(net, &fl, flags, ip6_pol_route_input); diff --git a/net/key/af_key.c b/net/key/af_key.c index f8bd8df5e25..7dcbde3ea7d 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1285,6 +1285,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, ext_hdrs[SADB_X_EXT_NAT_T_DPORT-1]; natt->encap_dport = n_port->sadb_x_nat_t_port_port; } + memset(&natt->encap_oa, 0, sizeof(natt->encap_oa)); } err = xfrm_init_state(x); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 5ba721b6a39..2b890af01ba 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -620,8 +620,8 @@ static u32 ieee80211_handle_bss_capability(struct ieee80211_sub_if_data *sdata, if (use_short_slot != bss_conf->use_short_slot) { #ifdef CONFIG_MAC80211_VERBOSE_DEBUG if (net_ratelimit()) { - printk(KERN_DEBUG "%s: switched to %s slot" - " (BSSID=%s)\n", + printk(KERN_DEBUG "%s: switched to %s slot time" + " (BSSID=%pM)\n", sdata->dev->name, use_short_slot ? "short" : "long", ifsta->bssid); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index dc2606d0ae7..e49a5b99cf1 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -195,7 +195,6 @@ struct sta_ampdu_mlme { * @tx_packets: number of RX/TX MSDUs * @tx_bytes: number of bytes transmitted to this STA * @tx_fragments: number of transmitted MPDUs - * @last_txrate: description of the last used transmit rate * @tid_seq: per-TID sequence numbers for sending to this STA * @ampdu_mlme: A-MPDU state machine state * @timer_to_tid: identity mapping to ID timers diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index a4af3a124cc..94de5033f0b 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1307,8 +1307,10 @@ int ieee80211_master_start_xmit(struct sk_buff *skb, struct net_device *dev) if (is_multicast_ether_addr(hdr->addr3)) memcpy(hdr->addr1, hdr->addr3, ETH_ALEN); else - if (mesh_nexthop_lookup(skb, osdata)) - return 0; + if (mesh_nexthop_lookup(skb, osdata)) { + dev_put(odev); + return 0; + } if (memcmp(odev->dev_addr, hdr->addr4, ETH_ALEN) != 0) IEEE80211_IFSTA_MESH_CTR_INC(&osdata->u.mesh, fwded_frames); @@ -1341,6 +1343,8 @@ int ieee80211_master_start_xmit(struct sk_buff *skb, struct net_device *dev) list) { if (!netif_running(sdata->dev)) continue; + if (sdata->vif.type != NL80211_IFTYPE_AP) + continue; if (compare_ether_addr(sdata->dev->dev_addr, hdr->addr2)) { dev_hold(sdata->dev); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 3dddec6d2f7..cb78aa00399 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -434,7 +434,7 @@ static int ctnetlink_conntrack_event(struct notifier_block *this, } else return NOTIFY_DONE; - if (!nfnetlink_has_listeners(group)) + if (!item->report && !nfnetlink_has_listeners(group)) return NOTIFY_DONE; skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); @@ -831,13 +831,16 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct, if (!parse_nat_setup) { #ifdef CONFIG_MODULES rcu_read_unlock(); + spin_unlock_bh(&nf_conntrack_lock); nfnl_unlock(); if (request_module("nf-nat-ipv4") < 0) { nfnl_lock(); + spin_lock_bh(&nf_conntrack_lock); rcu_read_lock(); return -EOPNOTSUPP; } nfnl_lock(); + spin_lock_bh(&nf_conntrack_lock); rcu_read_lock(); if (nfnetlink_parse_nat_setup_hook) return -EAGAIN; @@ -1212,6 +1215,16 @@ ctnetlink_create_conntrack(struct nlattr *cda[], } } +#ifdef CONFIG_NF_NAT_NEEDED + if (cda[CTA_NAT_SEQ_ADJ_ORIG] || cda[CTA_NAT_SEQ_ADJ_REPLY]) { + err = ctnetlink_change_nat_seq_adj(ct, cda); + if (err < 0) { + rcu_read_unlock(); + goto err; + } + } +#endif + if (cda[CTA_PROTOINFO]) { err = ctnetlink_change_protoinfo(ct, cda); if (err < 0) { @@ -1489,7 +1502,8 @@ static int ctnetlink_expect_event(struct notifier_block *this, } else return NOTIFY_DONE; - if (!nfnetlink_has_listeners(NFNLGRP_CONNTRACK_EXP_NEW)) + if (!item->report && + !nfnetlink_has_listeners(NFNLGRP_CONNTRACK_EXP_NEW)) return NOTIFY_DONE; skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index fa49dc7fe10..c712e9fc6bb 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -39,7 +39,7 @@ #endif #define NFULNL_NLBUFSIZ_DEFAULT NLMSG_GOODSIZE -#define NFULNL_TIMEOUT_DEFAULT HZ /* every second */ +#define NFULNL_TIMEOUT_DEFAULT 100 /* every second */ #define NFULNL_QTHRESH_DEFAULT 100 /* 100 packets */ #define NFULNL_COPY_RANGE_MAX 0xFFFF /* max packet size is limited by 16-bit struct nfattr nfa_len field */ @@ -590,8 +590,10 @@ nfulnl_log_packet(u_int8_t pf, qthreshold = inst->qthreshold; /* per-rule qthreshold overrides per-instance */ - if (qthreshold > li->u.ulog.qthreshold) - qthreshold = li->u.ulog.qthreshold; + if (li->u.ulog.qthreshold) + if (qthreshold > li->u.ulog.qthreshold) + qthreshold = li->u.ulog.qthreshold; + switch (inst->copy_mode) { case NFULNL_COPY_META: diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index bfbf521f6ea..5baccfa5a0d 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -827,59 +827,143 @@ static const struct file_operations xt_table_ops = { .release = seq_release_net, }; -static void *xt_match_seq_start(struct seq_file *seq, loff_t *pos) +/* + * Traverse state for ip{,6}_{tables,matches} for helping crossing + * the multi-AF mutexes. + */ +struct nf_mttg_trav { + struct list_head *head, *curr; + uint8_t class, nfproto; +}; + +enum { + MTTG_TRAV_INIT, + MTTG_TRAV_NFP_UNSPEC, + MTTG_TRAV_NFP_SPEC, + MTTG_TRAV_DONE, +}; + +static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos, + bool is_target) { - struct proc_dir_entry *pde = (struct proc_dir_entry *)seq->private; - u_int16_t af = (unsigned long)pde->data; + static const uint8_t next_class[] = { + [MTTG_TRAV_NFP_UNSPEC] = MTTG_TRAV_NFP_SPEC, + [MTTG_TRAV_NFP_SPEC] = MTTG_TRAV_DONE, + }; + struct nf_mttg_trav *trav = seq->private; + + switch (trav->class) { + case MTTG_TRAV_INIT: + trav->class = MTTG_TRAV_NFP_UNSPEC; + mutex_lock(&xt[NFPROTO_UNSPEC].mutex); + trav->head = trav->curr = is_target ? + &xt[NFPROTO_UNSPEC].target : &xt[NFPROTO_UNSPEC].match; + break; + case MTTG_TRAV_NFP_UNSPEC: + trav->curr = trav->curr->next; + if (trav->curr != trav->head) + break; + mutex_unlock(&xt[NFPROTO_UNSPEC].mutex); + mutex_lock(&xt[trav->nfproto].mutex); + trav->head = trav->curr = is_target ? + &xt[trav->nfproto].target : &xt[trav->nfproto].match; + trav->class = next_class[trav->class]; + break; + case MTTG_TRAV_NFP_SPEC: + trav->curr = trav->curr->next; + if (trav->curr != trav->head) + break; + /* fallthru, _stop will unlock */ + default: + return NULL; + } - mutex_lock(&xt[af].mutex); - return seq_list_start(&xt[af].match, *pos); + if (ppos != NULL) + ++*ppos; + return trav; } -static void *xt_match_seq_next(struct seq_file *seq, void *v, loff_t *pos) +static void *xt_mttg_seq_start(struct seq_file *seq, loff_t *pos, + bool is_target) { - struct proc_dir_entry *pde = (struct proc_dir_entry *)seq->private; - u_int16_t af = (unsigned long)pde->data; + struct nf_mttg_trav *trav = seq->private; + unsigned int j; - return seq_list_next(v, &xt[af].match, pos); + trav->class = MTTG_TRAV_INIT; + for (j = 0; j < *pos; ++j) + if (xt_mttg_seq_next(seq, NULL, NULL, is_target) == NULL) + return NULL; + return trav; } -static void xt_match_seq_stop(struct seq_file *seq, void *v) +static void xt_mttg_seq_stop(struct seq_file *seq, void *v) { - struct proc_dir_entry *pde = seq->private; - u_int16_t af = (unsigned long)pde->data; + struct nf_mttg_trav *trav = seq->private; + + switch (trav->class) { + case MTTG_TRAV_NFP_UNSPEC: + mutex_unlock(&xt[NFPROTO_UNSPEC].mutex); + break; + case MTTG_TRAV_NFP_SPEC: + mutex_unlock(&xt[trav->nfproto].mutex); + break; + } +} - mutex_unlock(&xt[af].mutex); +static void *xt_match_seq_start(struct seq_file *seq, loff_t *pos) +{ + return xt_mttg_seq_start(seq, pos, false); } -static int xt_match_seq_show(struct seq_file *seq, void *v) +static void *xt_match_seq_next(struct seq_file *seq, void *v, loff_t *ppos) { - struct xt_match *match = list_entry(v, struct xt_match, list); + return xt_mttg_seq_next(seq, v, ppos, false); +} - if (strlen(match->name)) - return seq_printf(seq, "%s\n", match->name); - else - return 0; +static int xt_match_seq_show(struct seq_file *seq, void *v) +{ + const struct nf_mttg_trav *trav = seq->private; + const struct xt_match *match; + + switch (trav->class) { + case MTTG_TRAV_NFP_UNSPEC: + case MTTG_TRAV_NFP_SPEC: + if (trav->curr == trav->head) + return 0; + match = list_entry(trav->curr, struct xt_match, list); + return (*match->name == '\0') ? 0 : + seq_printf(seq, "%s\n", match->name); + } + return 0; } static const struct seq_operations xt_match_seq_ops = { .start = xt_match_seq_start, .next = xt_match_seq_next, - .stop = xt_match_seq_stop, + .stop = xt_mttg_seq_stop, .show = xt_match_seq_show, }; static int xt_match_open(struct inode *inode, struct file *file) { + struct seq_file *seq; + struct nf_mttg_trav *trav; int ret; - ret = seq_open(file, &xt_match_seq_ops); - if (!ret) { - struct seq_file *seq = file->private_data; + trav = kmalloc(sizeof(*trav), GFP_KERNEL); + if (trav == NULL) + return -ENOMEM; - seq->private = PDE(inode); + ret = seq_open(file, &xt_match_seq_ops); + if (ret < 0) { + kfree(trav); + return ret; } - return ret; + + seq = file->private_data; + seq->private = trav; + trav->nfproto = (unsigned long)PDE(inode)->data; + return 0; } static const struct file_operations xt_match_ops = { @@ -887,62 +971,63 @@ static const struct file_operations xt_match_ops = { .open = xt_match_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_private, }; static void *xt_target_seq_start(struct seq_file *seq, loff_t *pos) { - struct proc_dir_entry *pde = (struct proc_dir_entry *)seq->private; - u_int16_t af = (unsigned long)pde->data; - - mutex_lock(&xt[af].mutex); - return seq_list_start(&xt[af].target, *pos); + return xt_mttg_seq_start(seq, pos, true); } -static void *xt_target_seq_next(struct seq_file *seq, void *v, loff_t *pos) +static void *xt_target_seq_next(struct seq_file *seq, void *v, loff_t *ppos) { - struct proc_dir_entry *pde = (struct proc_dir_entry *)seq->private; - u_int16_t af = (unsigned long)pde->data; - - return seq_list_next(v, &xt[af].target, pos); -} - -static void xt_target_seq_stop(struct seq_file *seq, void *v) -{ - struct proc_dir_entry *pde = seq->private; - u_int16_t af = (unsigned long)pde->data; - - mutex_unlock(&xt[af].mutex); + return xt_mttg_seq_next(seq, v, ppos, true); } static int xt_target_seq_show(struct seq_file *seq, void *v) { - struct xt_target *target = list_entry(v, struct xt_target, list); - - if (strlen(target->name)) - return seq_printf(seq, "%s\n", target->name); - else - return 0; + const struct nf_mttg_trav *trav = seq->private; + const struct xt_target *target; + + switch (trav->class) { + case MTTG_TRAV_NFP_UNSPEC: + case MTTG_TRAV_NFP_SPEC: + if (trav->curr == trav->head) + return 0; + target = list_entry(trav->curr, struct xt_target, list); + return (*target->name == '\0') ? 0 : + seq_printf(seq, "%s\n", target->name); + } + return 0; } static const struct seq_operations xt_target_seq_ops = { .start = xt_target_seq_start, .next = xt_target_seq_next, - .stop = xt_target_seq_stop, + .stop = xt_mttg_seq_stop, .show = xt_target_seq_show, }; static int xt_target_open(struct inode *inode, struct file *file) { + struct seq_file *seq; + struct nf_mttg_trav *trav; int ret; - ret = seq_open(file, &xt_target_seq_ops); - if (!ret) { - struct seq_file *seq = file->private_data; + trav = kmalloc(sizeof(*trav), GFP_KERNEL); + if (trav == NULL) + return -ENOMEM; - seq->private = PDE(inode); + ret = seq_open(file, &xt_target_seq_ops); + if (ret < 0) { + kfree(trav); + return ret; } - return ret; + + seq = file->private_data; + seq->private = trav; + trav->nfproto = (unsigned long)PDE(inode)->data; + return 0; } static const struct file_operations xt_target_ops = { @@ -950,7 +1035,7 @@ static const struct file_operations xt_target_ops = { .open = xt_target_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_private, }; #define FORMAT_TABLES "_tables_names" diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index fe80b614a40..791e030ea90 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -542,7 +542,7 @@ recent_mt_proc_write(struct file *file, const char __user *input, struct recent_entry *e; char buf[sizeof("+b335:1d35:1e55:dead:c0de:1715:5afe:c0de")]; const char *c = buf; - union nf_inet_addr addr; + union nf_inet_addr addr = {}; u_int16_t family; bool add, succ; diff --git a/net/netfilter/xt_sctp.c b/net/netfilter/xt_sctp.c index e223cb43ae8..a189ada9128 100644 --- a/net/netfilter/xt_sctp.c +++ b/net/netfilter/xt_sctp.c @@ -105,7 +105,7 @@ match_packet(const struct sk_buff *skb, switch (chunk_match_type) { case SCTP_CHUNK_MATCH_ALL: - return SCTP_CHUNKMAP_IS_CLEAR(info->chunkmap); + return SCTP_CHUNKMAP_IS_CLEAR(chunkmapcopy); case SCTP_CHUNK_MATCH_ANY: return false; case SCTP_CHUNK_MATCH_ONLY: diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 5f94db2f3e9..1fc4a7885c4 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -77,6 +77,7 @@ #include <linux/poll.h> #include <linux/module.h> #include <linux/init.h> +#include <linux/mutex.h> #ifdef CONFIG_INET #include <net/inet_common.h> @@ -175,6 +176,7 @@ struct packet_sock { #endif struct packet_type prot_hook; spinlock_t bind_lock; + struct mutex pg_vec_lock; unsigned int running:1, /* prot_hook is attached*/ auxdata:1, origdev:1; @@ -220,13 +222,13 @@ static void *packet_lookup_frame(struct packet_sock *po, unsigned int position, h.raw = po->pg_vec[pg_vec_pos] + (frame_offset * po->frame_size); switch (po->tp_version) { case TPACKET_V1: - if (status != h.h1->tp_status ? TP_STATUS_USER : - TP_STATUS_KERNEL) + if (status != (h.h1->tp_status ? TP_STATUS_USER : + TP_STATUS_KERNEL)) return NULL; break; case TPACKET_V2: - if (status != h.h2->tp_status ? TP_STATUS_USER : - TP_STATUS_KERNEL) + if (status != (h.h2->tp_status ? TP_STATUS_USER : + TP_STATUS_KERNEL)) return NULL; break; } @@ -1069,6 +1071,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol) */ spin_lock_init(&po->bind_lock); + mutex_init(&po->pg_vec_lock); po->prot_hook.func = packet_rcv; if (sock->type == SOCK_PACKET) @@ -1865,6 +1868,7 @@ static int packet_set_ring(struct sock *sk, struct tpacket_req *req, int closing synchronize_net(); err = -EBUSY; + mutex_lock(&po->pg_vec_lock); if (closing || atomic_read(&po->mapped) == 0) { err = 0; #define XC(a, b) ({ __typeof__ ((a)) __t; __t = (a); (a) = (b); __t; }) @@ -1886,6 +1890,7 @@ static int packet_set_ring(struct sock *sk, struct tpacket_req *req, int closing if (atomic_read(&po->mapped)) printk(KERN_DEBUG "packet_mmap: vma is busy: %d\n", atomic_read(&po->mapped)); } + mutex_unlock(&po->pg_vec_lock); spin_lock(&po->bind_lock); if (was_running && !po->running) { @@ -1918,7 +1923,7 @@ static int packet_mmap(struct file *file, struct socket *sock, struct vm_area_st size = vma->vm_end - vma->vm_start; - lock_sock(sk); + mutex_lock(&po->pg_vec_lock); if (po->pg_vec == NULL) goto out; if (size != po->pg_vec_len*po->pg_vec_pages*PAGE_SIZE) @@ -1941,7 +1946,7 @@ static int packet_mmap(struct file *file, struct socket *sock, struct vm_area_st err = 0; out: - release_sock(sk); + mutex_unlock(&po->pg_vec_lock); return err; } #endif diff --git a/net/phonet/pep-gprs.c b/net/phonet/pep-gprs.c index 6a91a32a80c..4aa888584d2 100644 --- a/net/phonet/pep-gprs.c +++ b/net/phonet/pep-gprs.c @@ -207,7 +207,6 @@ static int gprs_xmit(struct sk_buff *skb, struct net_device *dev) dev->name, err); dev->stats.tx_aborted_errors++; dev->stats.tx_errors++; - dev_kfree_skb(skb); } else { dev->stats.tx_packets++; dev->stats.tx_bytes += len; diff --git a/net/phonet/pep.c b/net/phonet/pep.c index bb3e67849b3..8ad2b533388 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -553,7 +553,7 @@ static int pep_do_rcv(struct sock *sk, struct sk_buff *skb) { struct pep_sock *pn = pep_sk(sk); struct sock *sknode; - struct pnpipehdr *hdr = pnp_hdr(skb); + struct pnpipehdr *hdr; struct sockaddr_pn dst; int err = NET_RX_SUCCESS; u8 pipe_handle; diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index d7d2bed7a69..eac5e7bb736 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -284,13 +284,13 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, if (IS_ERR(trans)) { call = ERR_CAST(trans); trans = NULL; - goto out; + goto out_notrans; } } else { trans = rx->trans; if (!trans) { call = ERR_PTR(-ENOTCONN); - goto out; + goto out_notrans; } atomic_inc(&trans->usage); } @@ -315,6 +315,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, rxrpc_put_bundle(trans, bundle); out: rxrpc_put_transport(trans); +out_notrans: release_sock(&rx->sk); _leave(" = %p", call); return call; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index f6b4fa97df7..e36e94ab4e1 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -66,11 +66,15 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, { struct drr_sched *q = qdisc_priv(sch); struct drr_class *cl = (struct drr_class *)*arg; + struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_DRR_MAX + 1]; u32 quantum; int err; - err = nla_parse_nested(tb, TCA_DRR_MAX, tca[TCA_OPTIONS], drr_policy); + if (!opt) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_DRR_MAX, opt, drr_policy); if (err < 0) return err; diff --git a/net/sctp/input.c b/net/sctp/input.c index bf612d954d4..2e4a8646dbc 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -249,6 +249,19 @@ int sctp_rcv(struct sk_buff *skb) */ sctp_bh_lock_sock(sk); + if (sk != rcvr->sk) { + /* Our cached sk is different from the rcvr->sk. This is + * because migrate()/accept() may have moved the association + * to a new socket and released all the sockets. So now we + * are holding a lock on the old socket while the user may + * be doing something with the new socket. Switch our veiw + * of the current sk. + */ + sctp_bh_unlock_sock(sk); + sk = rcvr->sk; + sctp_bh_lock_sock(sk); + } + if (sock_owned_by_user(sk)) { SCTP_INC_STATS_BH(SCTP_MIB_IN_PKT_BACKLOG); sctp_add_backlog(sk, skb); diff --git a/net/sctp/output.c b/net/sctp/output.c index c3f417f7ec6..73639355157 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -324,14 +324,16 @@ append: switch (chunk->chunk_hdr->type) { case SCTP_CID_DATA: retval = sctp_packet_append_data(packet, chunk); + if (SCTP_XMIT_OK != retval) + goto finish; /* Disallow SACK bundling after DATA. */ packet->has_sack = 1; /* Disallow AUTH bundling after DATA */ packet->has_auth = 1; /* Let it be knows that packet has DATA in it */ packet->has_data = 1; - if (SCTP_XMIT_OK != retval) - goto finish; + /* timestamp the chunk for rtx purposes */ + chunk->sent_at = jiffies; break; case SCTP_CID_COOKIE_ECHO: packet->has_cookie_echo = 1; @@ -470,7 +472,6 @@ int sctp_packet_transmit(struct sctp_packet *packet) } else chunk->resent = 1; - chunk->sent_at = jiffies; has_data = 1; } diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 247ebc95c1e..bc411c89621 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -929,7 +929,6 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) } /* Finally, transmit new packets. */ - start_timer = 0; while ((chunk = sctp_outq_dequeue_data(q)) != NULL) { /* RFC 2960 6.5 Every DATA chunk MUST carry a valid * stream identifier. @@ -1028,7 +1027,7 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) list_add_tail(&chunk->transmitted_list, &transport->transmitted); - sctp_transport_reset_timers(transport, start_timer-1); + sctp_transport_reset_timers(transport, 0); q->empty = 0; diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig new file mode 100644 index 00000000000..5592883e1e4 --- /dev/null +++ b/net/sunrpc/Kconfig @@ -0,0 +1,78 @@ +config SUNRPC + tristate + +config SUNRPC_GSS + tristate + +config SUNRPC_XPRT_RDMA + tristate + depends on SUNRPC && INFINIBAND && INFINIBAND_ADDR_TRANS && EXPERIMENTAL + default SUNRPC && INFINIBAND + help + This option allows the NFS client and server to support + an RDMA-enabled transport. + + To compile RPC client RDMA transport support as a module, + choose M here: the module will be called xprtrdma. + + If unsure, say N. + +config SUNRPC_REGISTER_V4 + bool "Register local RPC services via rpcbind v4 (EXPERIMENTAL)" + depends on SUNRPC && EXPERIMENTAL + default n + help + Sun added support for registering RPC services at an IPv6 + address by creating two new versions of the rpcbind protocol + (RFC 1833). + + This option enables support in the kernel RPC server for + registering kernel RPC services via version 4 of the rpcbind + protocol. If you enable this option, you must run a portmapper + daemon that supports rpcbind protocol version 4. + + Serving NFS over IPv6 from knfsd (the kernel's NFS server) + requires that you enable this option and use a portmapper that + supports rpcbind version 4. + + If unsure, say N to get traditional behavior (register kernel + RPC services using only rpcbind version 2). Distributions + using the legacy Linux portmapper daemon must say N here. + +config RPCSEC_GSS_KRB5 + tristate "Secure RPC: Kerberos V mechanism (EXPERIMENTAL)" + depends on SUNRPC && EXPERIMENTAL + select SUNRPC_GSS + select CRYPTO + select CRYPTO_MD5 + select CRYPTO_DES + select CRYPTO_CBC + help + Choose Y here to enable Secure RPC using the Kerberos version 5 + GSS-API mechanism (RFC 1964). + + Secure RPC calls with Kerberos require an auxiliary user-space + daemon which may be found in the Linux nfs-utils package + available from http://linux-nfs.org/. In addition, user-space + Kerberos support should be installed. + + If unsure, say N. + +config RPCSEC_GSS_SPKM3 + tristate "Secure RPC: SPKM3 mechanism (EXPERIMENTAL)" + depends on SUNRPC && EXPERIMENTAL + select SUNRPC_GSS + select CRYPTO + select CRYPTO_MD5 + select CRYPTO_DES + select CRYPTO_CAST5 + select CRYPTO_CBC + help + Choose Y here to enable Secure RPC using the SPKM3 public key + GSS-API mechansim (RFC 2025). + + Secure RPC calls with SPKM3 require an auxiliary userspace + daemon which may be found in the Linux nfs-utils package + available from http://linux-nfs.org/. + + If unsure, say N. diff --git a/net/wimax/debugfs.c b/net/wimax/debugfs.c index 87cf4430079..94d216a4640 100644 --- a/net/wimax/debugfs.c +++ b/net/wimax/debugfs.c @@ -28,17 +28,6 @@ #include "debug-levels.h" -/* Debug framework control of debug levels */ -struct d_level D_LEVEL[] = { - D_SUBMODULE_DEFINE(debugfs), - D_SUBMODULE_DEFINE(id_table), - D_SUBMODULE_DEFINE(op_msg), - D_SUBMODULE_DEFINE(op_reset), - D_SUBMODULE_DEFINE(op_rfkill), - D_SUBMODULE_DEFINE(stack), -}; -size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL); - #define __debugfs_register(prefix, name, parent) \ do { \ result = d_level_register_debugfs(prefix, name, parent); \ diff --git a/net/wimax/id-table.c b/net/wimax/id-table.c index 5e685f7eda9..72273abfcb1 100644 --- a/net/wimax/id-table.c +++ b/net/wimax/id-table.c @@ -94,12 +94,13 @@ struct wimax_dev *wimax_dev_get_by_genl_info( list_for_each_entry(wimax_dev, &wimax_id_table, id_table_node) { if (wimax_dev->net_dev->ifindex == ifindex) { dev_hold(wimax_dev->net_dev); - break; + goto found; } } - if (wimax_dev == NULL) - d_printf(1, NULL, "wimax: no devices found with ifindex %d\n", - ifindex); + wimax_dev = NULL; + d_printf(1, NULL, "wimax: no devices found with ifindex %d\n", + ifindex); +found: spin_unlock(&wimax_id_table_lock); d_fnend(3, NULL, "(info %p ifindex %d) = %p\n", info, ifindex, wimax_dev); diff --git a/net/wimax/stack.c b/net/wimax/stack.c index d4da92f8981..3869c032788 100644 --- a/net/wimax/stack.c +++ b/net/wimax/stack.c @@ -516,6 +516,19 @@ void wimax_dev_rm(struct wimax_dev *wimax_dev) } EXPORT_SYMBOL_GPL(wimax_dev_rm); + +/* Debug framework control of debug levels */ +struct d_level D_LEVEL[] = { + D_SUBMODULE_DEFINE(debugfs), + D_SUBMODULE_DEFINE(id_table), + D_SUBMODULE_DEFINE(op_msg), + D_SUBMODULE_DEFINE(op_reset), + D_SUBMODULE_DEFINE(op_rfkill), + D_SUBMODULE_DEFINE(stack), +}; +size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL); + + struct genl_family wimax_gnl_family = { .id = GENL_ID_GENERATE, .name = "WiMAX", diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 4f877535e66..85c9034c59b 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -421,6 +421,31 @@ static u32 freq_max_bandwidth(const struct ieee80211_freq_range *freq_range, return 0; } +/** + * freq_in_rule_band - tells us if a frequency is in a frequency band + * @freq_range: frequency rule we want to query + * @freq_khz: frequency we are inquiring about + * + * This lets us know if a specific frequency rule is or is not relevant to + * a specific frequency's band. Bands are device specific and artificial + * definitions (the "2.4 GHz band" and the "5 GHz band"), however it is + * safe for now to assume that a frequency rule should not be part of a + * frequency's band if the start freq or end freq are off by more than 2 GHz. + * This resolution can be lowered and should be considered as we add + * regulatory rule support for other "bands". + **/ +static bool freq_in_rule_band(const struct ieee80211_freq_range *freq_range, + u32 freq_khz) +{ +#define ONE_GHZ_IN_KHZ 1000000 + if (abs(freq_khz - freq_range->start_freq_khz) <= (2 * ONE_GHZ_IN_KHZ)) + return true; + if (abs(freq_khz - freq_range->end_freq_khz) <= (2 * ONE_GHZ_IN_KHZ)) + return true; + return false; +#undef ONE_GHZ_IN_KHZ +} + /* Converts a country IE to a regulatory domain. A regulatory domain * structure has a lot of information which the IE doesn't yet have, * so for the other values we use upper max values as we will intersect @@ -473,6 +498,7 @@ static struct ieee80211_regdomain *country_ie_2_rd( * calculate the number of reg rules we will need. We will need one * for each channel subband */ while (country_ie_len >= 3) { + int end_channel = 0; struct ieee80211_country_ie_triplet *triplet = (struct ieee80211_country_ie_triplet *) country_ie; int cur_sub_max_channel = 0, cur_channel = 0; @@ -484,9 +510,25 @@ static struct ieee80211_regdomain *country_ie_2_rd( continue; } + /* 2 GHz */ + if (triplet->chans.first_channel <= 14) + end_channel = triplet->chans.first_channel + + triplet->chans.num_channels; + else + /* + * 5 GHz -- For example in country IEs if the first + * channel given is 36 and the number of channels is 4 + * then the individual channel numbers defined for the + * 5 GHz PHY by these parameters are: 36, 40, 44, and 48 + * and not 36, 37, 38, 39. + * + * See: http://tinyurl.com/11d-clarification + */ + end_channel = triplet->chans.first_channel + + (4 * (triplet->chans.num_channels - 1)); + cur_channel = triplet->chans.first_channel; - cur_sub_max_channel = ieee80211_channel_to_frequency( - cur_channel + triplet->chans.num_channels); + cur_sub_max_channel = end_channel; /* Basic sanity check */ if (cur_sub_max_channel < cur_channel) @@ -538,6 +580,7 @@ static struct ieee80211_regdomain *country_ie_2_rd( /* This time around we fill in the rd */ while (country_ie_len >= 3) { + int end_channel = 0; struct ieee80211_country_ie_triplet *triplet = (struct ieee80211_country_ie_triplet *) country_ie; struct ieee80211_reg_rule *reg_rule = NULL; @@ -559,6 +602,14 @@ static struct ieee80211_regdomain *country_ie_2_rd( reg_rule->flags = flags; + /* 2 GHz */ + if (triplet->chans.first_channel <= 14) + end_channel = triplet->chans.first_channel + + triplet->chans.num_channels; + else + end_channel = triplet->chans.first_channel + + (4 * (triplet->chans.num_channels - 1)); + /* The +10 is since the regulatory domain expects * the actual band edge, not the center of freq for * its start and end freqs, assuming 20 MHz bandwidth on @@ -568,8 +619,7 @@ static struct ieee80211_regdomain *country_ie_2_rd( triplet->chans.first_channel) - 10); freq_range->end_freq_khz = MHZ_TO_KHZ(ieee80211_channel_to_frequency( - triplet->chans.first_channel + - triplet->chans.num_channels) + 10); + end_channel) + 10); /* Large arbitrary values, we intersect later */ /* Increment this if we ever support >= 40 MHz channels @@ -748,12 +798,23 @@ static u32 map_regdom_flags(u32 rd_flags) * this value to the maximum allowed bandwidth. * @reg_rule: the regulatory rule which we have for this frequency * - * Use this function to get the regulatory rule for a specific frequency. + * Use this function to get the regulatory rule for a specific frequency on + * a given wireless device. If the device has a specific regulatory domain + * it wants to follow we respect that unless a country IE has been received + * and processed already. + * + * Returns 0 if it was able to find a valid regulatory rule which does + * apply to the given center_freq otherwise it returns non-zero. It will + * also return -ERANGE if we determine the given center_freq does not even have + * a regulatory rule for a frequency range in the center_freq's band. See + * freq_in_rule_band() for our current definition of a band -- this is purely + * subjective and right now its 802.11 specific. */ static int freq_reg_info(u32 center_freq, u32 *bandwidth, const struct ieee80211_reg_rule **reg_rule) { int i; + bool band_rule_found = false; u32 max_bandwidth = 0; if (!cfg80211_regdomain) @@ -767,7 +828,15 @@ static int freq_reg_info(u32 center_freq, u32 *bandwidth, rr = &cfg80211_regdomain->reg_rules[i]; fr = &rr->freq_range; pr = &rr->power_rule; + + /* We only need to know if one frequency rule was + * was in center_freq's band, that's enough, so lets + * not overwrite it once found */ + if (!band_rule_found) + band_rule_found = freq_in_rule_band(fr, center_freq); + max_bandwidth = freq_max_bandwidth(fr, center_freq); + if (max_bandwidth && *bandwidth <= max_bandwidth) { *reg_rule = rr; *bandwidth = max_bandwidth; @@ -775,23 +844,64 @@ static int freq_reg_info(u32 center_freq, u32 *bandwidth, } } + if (!band_rule_found) + return -ERANGE; + return !max_bandwidth; } -static void handle_channel(struct ieee80211_channel *chan) +static void handle_channel(struct wiphy *wiphy, enum ieee80211_band band, + unsigned int chan_idx) { int r; - u32 flags = chan->orig_flags; + u32 flags; u32 max_bandwidth = 0; const struct ieee80211_reg_rule *reg_rule = NULL; const struct ieee80211_power_rule *power_rule = NULL; + struct ieee80211_supported_band *sband; + struct ieee80211_channel *chan; + + sband = wiphy->bands[band]; + BUG_ON(chan_idx >= sband->n_channels); + chan = &sband->channels[chan_idx]; + + flags = chan->orig_flags; r = freq_reg_info(MHZ_TO_KHZ(chan->center_freq), &max_bandwidth, ®_rule); if (r) { - flags |= IEEE80211_CHAN_DISABLED; - chan->flags = flags; + /* This means no regulatory rule was found in the country IE + * with a frequency range on the center_freq's band, since + * IEEE-802.11 allows for a country IE to have a subset of the + * regulatory information provided in a country we ignore + * disabling the channel unless at least one reg rule was + * found on the center_freq's band. For details see this + * clarification: + * + * http://tinyurl.com/11d-clarification + */ + if (r == -ERANGE && + last_request->initiator == REGDOM_SET_BY_COUNTRY_IE) { +#ifdef CONFIG_CFG80211_REG_DEBUG + printk(KERN_DEBUG "cfg80211: Leaving channel %d MHz " + "intact on %s - no rule found in band on " + "Country IE\n", + chan->center_freq, wiphy_name(wiphy)); +#endif + } else { + /* In this case we know the country IE has at least one reg rule + * for the band so we respect its band definitions */ +#ifdef CONFIG_CFG80211_REG_DEBUG + if (last_request->initiator == REGDOM_SET_BY_COUNTRY_IE) + printk(KERN_DEBUG "cfg80211: Disabling " + "channel %d MHz on %s due to " + "Country IE\n", + chan->center_freq, wiphy_name(wiphy)); +#endif + flags |= IEEE80211_CHAN_DISABLED; + chan->flags = flags; + } return; } @@ -808,12 +918,16 @@ static void handle_channel(struct ieee80211_channel *chan) chan->max_power = (int) MBM_TO_DBM(power_rule->max_eirp); } -static void handle_band(struct ieee80211_supported_band *sband) +static void handle_band(struct wiphy *wiphy, enum ieee80211_band band) { - int i; + unsigned int i; + struct ieee80211_supported_band *sband; + + BUG_ON(!wiphy->bands[band]); + sband = wiphy->bands[band]; for (i = 0; i < sband->n_channels; i++) - handle_channel(&sband->channels[i]); + handle_channel(wiphy, band, i); } static bool ignore_reg_update(struct wiphy *wiphy, enum reg_set_by setby) @@ -840,7 +954,7 @@ void wiphy_update_regulatory(struct wiphy *wiphy, enum reg_set_by setby) enum ieee80211_band band; for (band = 0; band < IEEE80211_NUM_BANDS; band++) { if (wiphy->bands[band]) - handle_band(wiphy->bands[band]); + handle_band(wiphy, band); if (wiphy->reg_notifier) wiphy->reg_notifier(wiphy, setby); } @@ -1170,7 +1284,7 @@ static void reg_country_ie_process_debug( if (intersected_rd) { printk(KERN_DEBUG "cfg80211: We intersect both of these " "and get:\n"); - print_regdomain_info(rd); + print_regdomain_info(intersected_rd); return; } printk(KERN_DEBUG "cfg80211: Intersection between both failed\n"); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 7877e7975da..b95a2d64eb5 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1914,17 +1914,10 @@ static int xfrm_send_migrate(struct xfrm_selector *sel, u8 dir, u8 type, } #endif -/* For the xfrm_usersa_info cases we have to work around some 32-bit vs. - * 64-bit compatability issues. On 32-bit the structure is 220 bytes, but - * for 64-bit it gets padded out to 224 bytes. Those bytes are just - * padding and don't have any content we care about. Therefore as long - * as we have enough bytes for the content we can make both cases work. - */ - #define XMSGSIZE(type) sizeof(struct type) static const int xfrm_msg_min[XFRM_NR_MSGTYPES] = { - [XFRM_MSG_NEWSA - XFRM_MSG_BASE] = 220, /* see above */ + [XFRM_MSG_NEWSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_info), [XFRM_MSG_DELSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id), [XFRM_MSG_GETSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id), [XFRM_MSG_NEWPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_info), @@ -1934,7 +1927,7 @@ static const int xfrm_msg_min[XFRM_NR_MSGTYPES] = { [XFRM_MSG_ACQUIRE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_acquire), [XFRM_MSG_EXPIRE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_expire), [XFRM_MSG_UPDPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_info), - [XFRM_MSG_UPDSA - XFRM_MSG_BASE] = 220, /* see above */ + [XFRM_MSG_UPDSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_info), [XFRM_MSG_POLEXPIRE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_polexpire), [XFRM_MSG_FLUSHSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_flush), [XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = 0, |