diff --git a/Makefile b/Makefile index bc4dd5b..3f23cb7 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 3 PATCHLEVEL = 4 -SUBLEVEL = 61 +SUBLEVEL = 62 EXTRAVERSION = NAME = Saber-toothed Squirrel diff --git a/arch/m32r/boot/compressed/Makefile b/arch/m32r/boot/compressed/Makefile index 177716b..01729c2 100644 --- a/arch/m32r/boot/compressed/Makefile +++ b/arch/m32r/boot/compressed/Makefile @@ -43,9 +43,9 @@ endif OBJCOPYFLAGS += -R .empty_zero_page -suffix_$(CONFIG_KERNEL_GZIP) = gz -suffix_$(CONFIG_KERNEL_BZIP2) = bz2 -suffix_$(CONFIG_KERNEL_LZMA) = lzma +suffix-$(CONFIG_KERNEL_GZIP) = gz +suffix-$(CONFIG_KERNEL_BZIP2) = bz2 +suffix-$(CONFIG_KERNEL_LZMA) = lzma $(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix-y) FORCE $(call if_changed,ld) diff --git a/arch/m32r/boot/compressed/misc.c b/arch/m32r/boot/compressed/misc.c index 370d608..28a0952 100644 --- a/arch/m32r/boot/compressed/misc.c +++ b/arch/m32r/boot/compressed/misc.c @@ -28,7 +28,7 @@ static unsigned long free_mem_ptr; static unsigned long free_mem_end_ptr; #ifdef CONFIG_KERNEL_BZIP2 -static void *memset(void *s, int c, size_t n) +void *memset(void *s, int c, size_t n) { char *ss = s; @@ -39,6 +39,16 @@ static void *memset(void *s, int c, size_t n) #endif #ifdef CONFIG_KERNEL_GZIP +void *memcpy(void *dest, const void *src, size_t n) +{ + char *d = dest; + const char *s = src; + while (n--) + *d++ = *s++; + + return dest; +} + #define BOOT_HEAP_SIZE 0x10000 #include "../../../../lib/decompress_inflate.c" #endif diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 8c45818..8375622 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3737,10 +3737,6 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op, break; case OpMem8: ctxt->memop.bytes = 1; - if (ctxt->memop.type == OP_REG) { - ctxt->memop.addr.reg = decode_register(ctxt, ctxt->modrm_rm, 1); - fetch_register_operand(&ctxt->memop); - } goto mem_common; case OpMem16: ctxt->memop.bytes = 2; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index d9f8358..80103bb 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3750,11 +3750,17 @@ static int bond_neigh_init(struct neighbour *n) * The bonding ndo_neigh_setup is called at init time beofre any * slave exists. So we must declare proxy setup function which will * be used at run time to resolve the actual slave neigh param setup. + * + * It's also called by master devices (such as vlans) to setup their + * underlying devices. In that case - do nothing, we're already set up from + * our init. */ static int bond_neigh_setup(struct net_device *dev, struct neigh_parms *parms) { - parms->neigh_setup = bond_neigh_init; + /* modify only our neigh_parms */ + if (parms->dev == dev) + parms->neigh_setup = bond_neigh_init; return 0; } diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c index 2205db7..1b44047 100644 --- a/drivers/net/ethernet/realtek/8139cp.c +++ b/drivers/net/ethernet/realtek/8139cp.c @@ -524,6 +524,7 @@ rx_status_loop: PCI_DMA_FROMDEVICE); if (dma_mapping_error(&cp->pdev->dev, new_mapping)) { dev->stats.rx_dropped++; + kfree_skb(new_skb); goto rx_next; } diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 5151f06..77ce8b2 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -642,6 +642,28 @@ static int macvtap_skb_to_vnet_hdr(const struct sk_buff *skb, return 0; } +static unsigned long iov_pages(const struct iovec *iv, int offset, + unsigned long nr_segs) +{ + unsigned long seg, base; + int pages = 0, len, size; + + while (nr_segs && (offset >= iv->iov_len)) { + offset -= iv->iov_len; + ++iv; + --nr_segs; + } + + for (seg = 0; seg < nr_segs; seg++) { + base = (unsigned long)iv[seg].iov_base + offset; + len = iv[seg].iov_len - offset; + size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT; + pages += size; + offset = 0; + } + + return pages; +} /* Get packet from user space buffer */ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, @@ -688,31 +710,15 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, if (unlikely(count > UIO_MAXIOV)) goto err; - if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) - zerocopy = true; - - if (zerocopy) { - /* Userspace may produce vectors with count greater than - * MAX_SKB_FRAGS, so we need to linearize parts of the skb - * to let the rest of data to be fit in the frags. - */ - if (count > MAX_SKB_FRAGS) { - copylen = iov_length(iv, count - MAX_SKB_FRAGS); - if (copylen < vnet_hdr_len) - copylen = 0; - else - copylen -= vnet_hdr_len; - } - /* There are 256 bytes to be copied in skb, so there is enough - * room for skb expand head in case it is used. - * The rest buffer is mapped from userspace. - */ - if (copylen < vnet_hdr.hdr_len) - copylen = vnet_hdr.hdr_len; - if (!copylen) - copylen = GOODCOPY_LEN; + if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) { + copylen = vnet_hdr.hdr_len ? vnet_hdr.hdr_len : GOODCOPY_LEN; linear = copylen; - } else { + if (iov_pages(iv, vnet_hdr_len + copylen, count) + <= MAX_SKB_FRAGS) + zerocopy = true; + } + + if (!zerocopy) { copylen = len; linear = vnet_hdr.hdr_len; } @@ -724,9 +730,15 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, if (zerocopy) err = zerocopy_sg_from_iovec(skb, iv, vnet_hdr_len, count); - else + else { err = skb_copy_datagram_from_iovec(skb, 0, iv, vnet_hdr_len, len); + if (!err && m && m->msg_control) { + struct ubuf_info *uarg = m->msg_control; + uarg->callback(uarg); + } + } + if (err) goto err_kfree; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index c896b8f..194f879 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -615,8 +615,9 @@ static ssize_t tun_get_user(struct tun_struct *tun, int offset = 0; if (!(tun->flags & TUN_NO_PI)) { - if ((len -= sizeof(pi)) > count) + if (len < sizeof(pi)) return -EINVAL; + len -= sizeof(pi); if (memcpy_fromiovecend((void *)&pi, iv, 0, sizeof(pi))) return -EFAULT; @@ -624,8 +625,9 @@ static ssize_t tun_get_user(struct tun_struct *tun, } if (tun->flags & TUN_VNET_HDR) { - if ((len -= tun->vnet_hdr_sz) > count) + if (len < tun->vnet_hdr_sz) return -EINVAL; + len -= tun->vnet_hdr_sz; if (memcpy_fromiovecend((void *)&gso, iv, offset, sizeof(gso))) return -EFAULT; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 1a9e2a9..a50cb9c 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -1603,6 +1603,7 @@ void vhost_zerocopy_callback(struct ubuf_info *ubuf) struct vhost_ubuf_ref *ubufs = ubuf->ctx; struct vhost_virtqueue *vq = ubufs->vq; + vhost_poll_queue(&vq->poll); /* set len = 1 to mark this desc buffers done DMA */ vq->heads[ubuf->desc].len = VHOST_DMA_DONE_LEN; kref_put(&ubufs->kref, vhost_zerocopy_done_signal); diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index ba45e6b..f5a21d0 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -123,6 +123,8 @@ static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb) #define ICMPV6_NOT_NEIGHBOUR 2 #define ICMPV6_ADDR_UNREACH 3 #define ICMPV6_PORT_UNREACH 4 +#define ICMPV6_POLICY_FAIL 5 +#define ICMPV6_REJECT_ROUTE 6 /* * Codes for Time Exceeded diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 8260ef7..e6412ee 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -260,6 +260,7 @@ struct inet6_skb_parm { #define IP6SKB_XFRM_TRANSFORMED 1 #define IP6SKB_FORWARDED 2 #define IP6SKB_REROUTED 4 +#define IP6SKB_FRAGMENTED 16 }; #define IP6CB(skb) ((struct inet6_skb_parm*)((skb)->cb)) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 9069071..ca670d9 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1155,7 +1155,8 @@ static int br_ip6_multicast_query(struct net_bridge *br, mld2q = (struct mld2_query *)icmp6_hdr(skb); if (!mld2q->mld2q_nsrcs) group = &mld2q->mld2q_mca; - max_delay = mld2q->mld2q_mrc ? MLDV2_MRC(mld2q->mld2q_mrc) : 1; + + max_delay = max(msecs_to_jiffies(MLDV2_MRC(ntohs(mld2q->mld2q_mrc))), 1UL); } if (!group) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 69b7ca3..ebd4b21 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1442,16 +1442,18 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, atomic_set(&p->refcnt, 1); p->reachable_time = neigh_rand_reach_time(p->base_reachable_time); + dev_hold(dev); + p->dev = dev; + write_pnet(&p->net, hold_net(net)); + p->sysctl_table = NULL; if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) { + release_net(net); + dev_put(dev); kfree(p); return NULL; } - dev_hold(dev); - p->dev = dev; - write_pnet(&p->net, hold_net(net)); - p->sysctl_table = NULL; write_lock_bh(&tbl->lock); p->next = tbl->parms.next; tbl->parms.next = p; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 0c28508..77d1550 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -19,6 +19,9 @@ #include #include +static int zero = 0; +static int ushort_max = USHRT_MAX; + #ifdef CONFIG_RPS static int rps_sock_flow_sysctl(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -197,7 +200,9 @@ static struct ctl_table netns_core_table[] = { .data = &init_net.core.sysctl_somaxconn, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .extra1 = &zero, + .extra2 = &ushort_max, + .proc_handler = proc_dointvec_minmax }, { } }; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 30b88d7..424704a 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -71,7 +71,6 @@ #include #include #include -#include #include #include #include @@ -1772,10 +1771,8 @@ static struct leaf *leaf_walk_rcu(struct tnode *p, struct rt_trie_node *c) if (!c) continue; - if (IS_LEAF(c)) { - prefetch(rcu_dereference_rtnl(p->child[idx])); + if (IS_LEAF(c)) return (struct leaf *) c; - } /* Rescan start scanning in new node */ p = (struct tnode *) c; diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index a9077f4..b6ae92a 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -206,8 +206,8 @@ static u32 cubic_root(u64 a) */ static inline void bictcp_update(struct bictcp *ca, u32 cwnd) { - u64 offs; - u32 delta, t, bic_target, max_cnt; + u32 delta, bic_target, max_cnt; + u64 offs, t; ca->ack_cnt++; /* count the number of ACKs */ @@ -250,9 +250,11 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd) * if the cwnd < 1 million packets !!! */ + t = (s32)(tcp_time_stamp - ca->epoch_start); + t += msecs_to_jiffies(ca->delay_min >> 3); /* change the unit from HZ to bictcp_HZ */ - t = ((tcp_time_stamp + msecs_to_jiffies(ca->delay_min>>3) - - ca->epoch_start) << BICTCP_HZ) / HZ; + t <<= BICTCP_HZ; + do_div(t, HZ); if (t < ca->bic_K) /* t - K */ offs = ca->bic_K - t; @@ -414,7 +416,7 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us) return; /* Discard delay samples right after fast recovery */ - if ((s32)(tcp_time_stamp - ca->epoch_start) < HZ) + if (ca->epoch_start && (s32)(tcp_time_stamp - ca->epoch_start) < HZ) return; delay = (rtt_us << 3) / USEC_PER_MSEC; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index d427f1b..abfa007 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -910,12 +910,10 @@ retry: if (ifp->flags & IFA_F_OPTIMISTIC) addr_flags |= IFA_F_OPTIMISTIC; - ift = !max_addresses || - ipv6_count_addresses(idev) < max_addresses ? - ipv6_add_addr(idev, &addr, tmp_plen, - ipv6_addr_type(&addr)&IPV6_ADDR_SCOPE_MASK, - addr_flags) : NULL; - if (!ift || IS_ERR(ift)) { + ift = ipv6_add_addr(idev, &addr, tmp_plen, + ipv6_addr_type(&addr)&IPV6_ADDR_SCOPE_MASK, + addr_flags); + if (IS_ERR(ift)) { in6_ifa_put(ifp); in6_dev_put(idev); printk(KERN_INFO diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 27ac95a..dbf20f6 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -917,6 +917,14 @@ static const struct icmp6_err { .err = ECONNREFUSED, .fatal = 1, }, + { /* POLICY_FAIL */ + .err = EACCES, + .fatal = 1, + }, + { /* REJECT_ROUTE */ + .err = EACCES, + .fatal = 1, + }, }; int icmpv6_err_convert(u8 type, u8 code, int *err) @@ -928,7 +936,7 @@ int icmpv6_err_convert(u8 type, u8 code, int *err) switch (type) { case ICMPV6_DEST_UNREACH: fatal = 1; - if (code <= ICMPV6_PORT_UNREACH) { + if (code < ARRAY_SIZE(tab_unreach)) { *err = tab_unreach[code].err; fatal = tab_unreach[code].fatal; } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index c3a007d..5bb77a6 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -949,14 +949,22 @@ static struct fib6_node * fib6_lookup_1(struct fib6_node *root, if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) { #ifdef CONFIG_IPV6_SUBTREES - if (fn->subtree) - fn = fib6_lookup_1(fn->subtree, args + 1); + if (fn->subtree) { + struct fib6_node *sfn; + sfn = fib6_lookup_1(fn->subtree, + args + 1); + if (!sfn) + goto backtrack; + fn = sfn; + } #endif - if (!fn || fn->fn_flags & RTN_RTINFO) + if (fn->fn_flags & RTN_RTINFO) return fn; } } - +#ifdef CONFIG_IPV6_SUBTREES +backtrack: +#endif if (fn->fn_flags & RTN_ROOT) break; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 843d6eb..5cc78e6 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -441,7 +441,6 @@ struct sk_buff *ndisc_build_skb(struct net_device *dev, int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; int len; - int err; u8 *opt; if (!dev->addr_len) @@ -451,14 +450,12 @@ struct sk_buff *ndisc_build_skb(struct net_device *dev, if (llinfo) len += ndisc_opt_addr_space(dev); - skb = sock_alloc_send_skb(sk, - (MAX_HEADER + sizeof(struct ipv6hdr) + - len + hlen + tlen), - 1, &err); + skb = alloc_skb((MAX_HEADER + sizeof(struct ipv6hdr) + + len + hlen + tlen), GFP_ATOMIC); if (!skb) { ND_PRINTK0(KERN_ERR - "ICMPv6 ND: %s() failed to allocate an skb, err=%d.\n", - __func__, err); + "ICMPv6 ND: %s() failed to allocate an skb.\n", + __func__); return NULL; } @@ -486,6 +483,11 @@ struct sk_buff *ndisc_build_skb(struct net_device *dev, csum_partial(hdr, len, 0)); + /* Manually assign socket ownership as we avoid calling + * sock_alloc_send_pskb() to bypass wmem buffer limits + */ + skb_set_owner_w(skb, sk); + return skb; } diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 6bda7aa..ff900ac 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -516,6 +516,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, head->tstamp = fq->q.stamp; ipv6_hdr(head)->payload_len = htons(payload_len); IP6CB(head)->nhoff = nhoff; + IP6CB(head)->flags |= IP6SKB_FRAGMENTED; /* Yes, and fold redundant checksum back. 8) */ if (head->ip_summed == CHECKSUM_COMPLETE) @@ -551,6 +552,9 @@ static int ipv6_frag_rcv(struct sk_buff *skb) const struct ipv6hdr *hdr = ipv6_hdr(skb); struct net *net = dev_net(skb_dst(skb)->dev); + if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED) + goto fail_hdr; + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS); /* Jumbo payload inhibits frag. header */ @@ -571,6 +575,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMOKS); IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb); + IP6CB(skb)->flags |= IP6SKB_FRAGMENTED; return 1; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7ee7121..c4717e8 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1571,7 +1571,7 @@ ipv6_pktoptions: if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit; if (np->rxopt.bits.rxtclass) - np->rcv_tclass = ipv6_tclass(ipv6_hdr(skb)); + np->rcv_tclass = ipv6_tclass(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb)) { skb_set_owner_r(opt_skb, sk); opt_skb = xchg(&np->pktoptions, opt_skb); diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index f08b9166..caa5aff 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -86,7 +86,7 @@ struct htb_class { unsigned int children; struct htb_class *parent; /* parent class */ - int prio; /* these two are used only by leaves... */ + u32 prio; /* these two are used only by leaves... */ int quantum; /* but stored for parent-to-leaf return */ union { diff --git a/net/tipc/eth_media.c b/net/tipc/eth_media.c index 527e3f0..dd625af 100644 --- a/net/tipc/eth_media.c +++ b/net/tipc/eth_media.c @@ -53,6 +53,7 @@ struct eth_bearer { struct tipc_bearer *bearer; struct net_device *dev; struct packet_type tipc_packet_type; + struct work_struct setup; struct work_struct cleanup; }; @@ -138,6 +139,17 @@ static int recv_msg(struct sk_buff *buf, struct net_device *dev, } /** + * setup_bearer - setup association between Ethernet bearer and interface + */ +static void setup_bearer(struct work_struct *work) +{ + struct eth_bearer *eb_ptr = + container_of(work, struct eth_bearer, setup); + + dev_add_pack(&eb_ptr->tipc_packet_type); +} + +/** * enable_bearer - attach TIPC bearer to an Ethernet interface */ @@ -181,7 +193,8 @@ static int enable_bearer(struct tipc_bearer *tb_ptr) eb_ptr->tipc_packet_type.func = recv_msg; eb_ptr->tipc_packet_type.af_packet_priv = eb_ptr; INIT_LIST_HEAD(&(eb_ptr->tipc_packet_type.list)); - dev_add_pack(&eb_ptr->tipc_packet_type); + INIT_WORK(&eb_ptr->setup, setup_bearer); + schedule_work(&eb_ptr->setup); /* Associate TIPC bearer with Ethernet bearer */