diff options
Diffstat (limited to 'net')
31 files changed, 277 insertions, 156 deletions
diff --git a/net/Kconfig b/net/Kconfig index 2eeb0e55f7c9..df8d8c9bd021 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -52,6 +52,9 @@ config NET_INGRESS config NET_EGRESS bool +config NET_REDIRECT + bool + config SKB_EXTENSIONS bool diff --git a/net/core/dev.c b/net/core/dev.c index 402a986659cf..500bba8874b0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4516,7 +4516,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, /* Reinjected packets coming from act_mirred or similar should * not get XDP generic processing. */ - if (skb_is_tc_redirected(skb)) + if (skb_is_redirected(skb)) return XDP_PASS; /* XDP packets must be linear and must have sufficient headroom @@ -5063,7 +5063,7 @@ skip_taps: goto out; } #endif - skb_reset_tc(skb); + skb_reset_redirect(skb); skip_classify: if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) goto drop; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index acc849df60b5..d0641bba6b81 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3362,7 +3362,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) /* skb was 'freed' by stack, so clean few * bits and reuse it */ - skb_reset_tc(skb); + skb_reset_redirect(skb); } while (--burst > 0); goto out; /* Skips xmit_mode M_START_XMIT */ } else if (pkt_dev->xmit_mode == M_QUEUE_XMIT) { diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 2fb6c26294b5..b97ad93d1c1a 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -298,47 +298,4 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, } EXPORT_SYMBOL_GPL(dsa_8021q_xmit); -/* In the DSA packet_type handler, skb->data points in the middle of the VLAN - * tag, after tpid and before tci. This is because so far, ETH_HLEN - * (DMAC, SMAC, EtherType) bytes were pulled. - * There are 2 bytes of VLAN tag left in skb->data, and upper - * layers expect the 'real' EtherType to be consumed as well. - * Coincidentally, a VLAN header is also of the same size as - * the number of bytes that need to be pulled. - * - * skb_mac_header skb->data - * | | - * v v - * | | | | | | | | | | | | | | | | | | | - * +-----------------------+-----------------------+-------+-------+-------+ - * | Destination MAC | Source MAC | TPID | TCI | EType | - * +-----------------------+-----------------------+-------+-------+-------+ - * ^ | | - * |<--VLAN_HLEN-->to <---VLAN_HLEN---> - * from | - * >>>>>>> v - * >>>>>>> | | | | | | | | | | | | | | | - * >>>>>>> +-----------------------+-----------------------+-------+ - * >>>>>>> | Destination MAC | Source MAC | EType | - * +-----------------------+-----------------------+-------+ - * ^ ^ - * (now part of | | - * skb->head) skb_mac_header skb->data - */ -struct sk_buff *dsa_8021q_remove_header(struct sk_buff *skb) -{ - u8 *from = skb_mac_header(skb); - u8 *dest = from + VLAN_HLEN; - - memmove(dest, from, ETH_HLEN - VLAN_HLEN); - skb_pull(skb, VLAN_HLEN); - skb_push(skb, ETH_HLEN); - skb_reset_mac_header(skb); - skb_reset_mac_len(skb); - skb_pull_rcsum(skb, ETH_HLEN); - - return skb; -} -EXPORT_SYMBOL_GPL(dsa_8021q_remove_header); - MODULE_LICENSE("GPL v2"); diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index 9c3114179690..9169b63a89e3 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -140,6 +140,8 @@ static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb, /* Remove Broadcom tag and update checksum */ skb_pull_rcsum(skb, BRCM_TAG_LEN); + skb->offload_fwd_mark = 1; + return skb; } #endif diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 5366ea430349..d553bf36bd41 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -250,14 +250,14 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, { struct sja1105_meta meta = {0}; int source_port, switch_id; - struct vlan_ethhdr *hdr; + struct ethhdr *hdr; u16 tpid, vid, tci; bool is_link_local; bool is_tagged; bool is_meta; - hdr = vlan_eth_hdr(skb); - tpid = ntohs(hdr->h_vlan_proto); + hdr = eth_hdr(skb); + tpid = ntohs(hdr->h_proto); is_tagged = (tpid == ETH_P_SJA1105); is_link_local = sja1105_is_link_local(skb); is_meta = sja1105_is_meta_frame(skb); @@ -266,7 +266,12 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, if (is_tagged) { /* Normal traffic path. */ - tci = ntohs(hdr->h_vlan_TCI); + skb_push_rcsum(skb, ETH_HLEN); + __skb_vlan_pop(skb, &tci); + skb_pull_rcsum(skb, ETH_HLEN); + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + vid = tci & VLAN_VID_MASK; source_port = dsa_8021q_rx_source_port(vid); switch_id = dsa_8021q_rx_switch_id(vid); @@ -295,12 +300,6 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, return NULL; } - /* Delete/overwrite fake VLAN header, DSA expects to not find - * it there, see dsa_switch_rcv: skb_push(skb, ETH_HLEN). - */ - if (is_tagged) - skb = dsa_8021q_remove_header(skb); - return sja1105_rcv_meta_state_machine(skb, &meta, is_link_local, is_meta); } diff --git a/net/ethtool/debug.c b/net/ethtool/debug.c index aaef4843e6ba..92599ad7b3c2 100644 --- a/net/ethtool/debug.c +++ b/net/ethtool/debug.c @@ -107,8 +107,9 @@ int ethnl_set_debug(struct sk_buff *skb, struct genl_info *info) if (ret < 0) return ret; dev = req_info.dev; + ret = -EOPNOTSUPP; if (!dev->ethtool_ops->get_msglevel || !dev->ethtool_ops->set_msglevel) - return -EOPNOTSUPP; + goto out_dev; rtnl_lock(); ret = ethnl_ops_begin(dev); @@ -129,6 +130,7 @@ out_ops: ethnl_ops_complete(dev); out_rtnl: rtnl_unlock(); +out_dev: dev_put(dev); return ret; } diff --git a/net/ethtool/linkinfo.c b/net/ethtool/linkinfo.c index 5d16cb4e8693..6e9e0b590bb5 100644 --- a/net/ethtool/linkinfo.c +++ b/net/ethtool/linkinfo.c @@ -126,9 +126,10 @@ int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info) if (ret < 0) return ret; dev = req_info.dev; + ret = -EOPNOTSUPP; if (!dev->ethtool_ops->get_link_ksettings || !dev->ethtool_ops->set_link_ksettings) - return -EOPNOTSUPP; + goto out_dev; rtnl_lock(); ret = ethnl_ops_begin(dev); @@ -162,6 +163,7 @@ out_ops: ethnl_ops_complete(dev); out_rtnl: rtnl_unlock(); +out_dev: dev_put(dev); return ret; } diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c index 96f20be64553..18cc37be2d9c 100644 --- a/net/ethtool/linkmodes.c +++ b/net/ethtool/linkmodes.c @@ -338,9 +338,10 @@ int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info) if (ret < 0) return ret; dev = req_info.dev; + ret = -EOPNOTSUPP; if (!dev->ethtool_ops->get_link_ksettings || !dev->ethtool_ops->set_link_ksettings) - return -EOPNOTSUPP; + goto out_dev; rtnl_lock(); ret = ethnl_ops_begin(dev); @@ -370,6 +371,7 @@ out_ops: ethnl_ops_complete(dev); out_rtnl: rtnl_unlock(); +out_dev: dev_put(dev); return ret; } diff --git a/net/ethtool/wol.c b/net/ethtool/wol.c index e1b8a65b64c4..55e1ecaaf739 100644 --- a/net/ethtool/wol.c +++ b/net/ethtool/wol.c @@ -128,8 +128,9 @@ int ethnl_set_wol(struct sk_buff *skb, struct genl_info *info) if (ret < 0) return ret; dev = req_info.dev; + ret = -EOPNOTSUPP; if (!dev->ethtool_ops->get_wol || !dev->ethtool_ops->set_wol) - return -EOPNOTSUPP; + goto out_dev; rtnl_lock(); ret = ethnl_ops_begin(dev); @@ -172,6 +173,7 @@ out_ops: ethnl_ops_complete(dev); out_rtnl: rtnl_unlock(); +out_dev: dev_put(dev); return ret; } diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index fbfd0db182b7..a9104d42aafb 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -145,16 +145,16 @@ int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev, if (!port) return -ENOMEM; + port->hsr = hsr; + port->dev = dev; + port->type = type; + if (type != HSR_PT_MASTER) { res = hsr_portdev_setup(dev, port); if (res) goto fail_dev_setup; } - port->hsr = hsr; - port->dev = dev; - port->type = type; - list_add_tail_rcu(&port->port_list, &hsr->ports); synchronize_rcu(); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 577db1d50a24..213be9c050ad 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -997,7 +997,9 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) return -ENOENT; } + rcu_read_lock(); err = fib_table_dump(tb, skb, cb, &filter); + rcu_read_unlock(); return skb->len ? : err; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index eb2d80519f8e..dc77c303e6f7 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2948,8 +2948,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level, err = -EPERM; else if (tp->repair_queue == TCP_SEND_QUEUE) WRITE_ONCE(tp->write_seq, val); - else if (tp->repair_queue == TCP_RECV_QUEUE) + else if (tp->repair_queue == TCP_RECV_QUEUE) { WRITE_ONCE(tp->rcv_nxt, val); + WRITE_ONCE(tp->copied_seq, val); + } else err = -EINVAL; break; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 306e25d743e8..2f45cde168c4 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1109,6 +1109,10 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, if (unlikely(!skb)) return -ENOBUFS; + /* retransmit skbs might have a non zero value in skb->dev + * because skb->dev is aliased with skb->rbnode.rb_left + */ + skb->dev = NULL; } inet = inet_sk(sk); @@ -3037,8 +3041,12 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) tcp_skb_tsorted_save(skb) { nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); - err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : - -ENOBUFS; + if (nskb) { + nskb->dev = NULL; + err = tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC); + } else { + err = -ENOBUFS; + } } tcp_skb_tsorted_restore(skb); if (!err) { diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 8af28e10b4e6..70ebebaf5bc1 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -554,6 +554,9 @@ void nf_flow_table_free(struct nf_flowtable *flow_table) nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL); nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, flow_table); nf_flow_table_offload_flush(flow_table); + if (nf_flowtable_hw_offload(flow_table)) + nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, + flow_table); rhashtable_destroy(&flow_table->rhashtable); } EXPORT_SYMBOL_GPL(nf_flow_table_free); diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 9e563fd3da0f..ba775aecd89a 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -146,11 +146,13 @@ static int nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb, if (test_bit(NF_FLOW_SNAT, &flow->flags) && (nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir) < 0 || - nf_flow_snat_ip(flow, skb, iph, thoff, dir) < 0)) + nf_flow_snat_ip(flow, skb, ip_hdr(skb), thoff, dir) < 0)) return -1; + + iph = ip_hdr(skb); if (test_bit(NF_FLOW_DNAT, &flow->flags) && (nf_flow_dnat_port(flow, skb, thoff, iph->protocol, dir) < 0 || - nf_flow_dnat_ip(flow, skb, iph, thoff, dir) < 0)) + nf_flow_dnat_ip(flow, skb, ip_hdr(skb), thoff, dir) < 0)) return -1; return 0; @@ -189,6 +191,7 @@ static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev, if (!pskb_may_pull(skb, thoff + sizeof(*ports))) return -1; + iph = ip_hdr(skb); ports = (struct flow_ports *)(skb_network_header(skb) + thoff); tuple->src_v4.s_addr = iph->saddr; @@ -426,11 +429,13 @@ static int nf_flow_nat_ipv6(const struct flow_offload *flow, if (test_bit(NF_FLOW_SNAT, &flow->flags) && (nf_flow_snat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 || - nf_flow_snat_ipv6(flow, skb, ip6h, thoff, dir) < 0)) + nf_flow_snat_ipv6(flow, skb, ipv6_hdr(skb), thoff, dir) < 0)) return -1; + + ip6h = ipv6_hdr(skb); if (test_bit(NF_FLOW_DNAT, &flow->flags) && (nf_flow_dnat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 || - nf_flow_dnat_ipv6(flow, skb, ip6h, thoff, dir) < 0)) + nf_flow_dnat_ipv6(flow, skb, ipv6_hdr(skb), thoff, dir) < 0)) return -1; return 0; @@ -459,6 +464,7 @@ static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev, if (!pskb_may_pull(skb, thoff + sizeof(*ports))) return -1; + ip6h = ipv6_hdr(skb); ports = (struct flow_ports *)(skb_network_header(skb) + thoff); tuple->src_v6 = ip6h->saddr; diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 06f00cdc3891..f2c22c682851 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -87,6 +87,7 @@ static int nf_flow_rule_match(struct nf_flow_match *match, default: return -EOPNOTSUPP; } + mask->control.addr_type = 0xffff; match->dissector.used_keys |= BIT(key->control.addr_type); mask->basic.n_proto = 0xffff; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 38c680f28f15..d11f1a74d43c 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5082,6 +5082,11 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, err = -EBUSY; else if (!(nlmsg_flags & NLM_F_EXCL)) err = 0; + } else if (err == -ENOTEMPTY) { + /* ENOTEMPTY reports overlapping between this element + * and an existing one. + */ + err = -EEXIST; } goto err_element_clash; } diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c index aba11c2333f3..3087e23297db 100644 --- a/net/netfilter/nft_fwd_netdev.c +++ b/net/netfilter/nft_fwd_netdev.c @@ -28,6 +28,9 @@ static void nft_fwd_netdev_eval(const struct nft_expr *expr, struct nft_fwd_netdev *priv = nft_expr_priv(expr); int oif = regs->data[priv->sreg_dev]; + /* This is used by ifb only. */ + skb_set_redirected(pkt->skb, true); + nf_fwd_netdev_egress(pkt, oif); regs->verdict.code = NF_STOLEN; } @@ -190,6 +193,13 @@ nla_put_failure: return -1; } +static int nft_fwd_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) +{ + return nft_chain_validate_hooks(ctx->chain, (1 << NF_NETDEV_INGRESS)); +} + static struct nft_expr_type nft_fwd_netdev_type; static const struct nft_expr_ops nft_fwd_neigh_netdev_ops = { .type = &nft_fwd_netdev_type, @@ -197,6 +207,7 @@ static const struct nft_expr_ops nft_fwd_neigh_netdev_ops = { .eval = nft_fwd_neigh_eval, .init = nft_fwd_neigh_init, .dump = nft_fwd_neigh_dump, + .validate = nft_fwd_validate, }; static const struct nft_expr_ops nft_fwd_netdev_ops = { @@ -205,6 +216,7 @@ static const struct nft_expr_ops nft_fwd_netdev_ops = { .eval = nft_fwd_netdev_eval, .init = nft_fwd_netdev_init, .dump = nft_fwd_netdev_dump, + .validate = nft_fwd_validate, .offload = nft_fwd_netdev_offload, }; diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 4fc0c924ed5d..ef7e8ad2e344 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1098,21 +1098,41 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, struct nft_pipapo_field *f; int i, bsize_max, err = 0; + if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END)) + end = (const u8 *)nft_set_ext_key_end(ext)->data; + else + end = start; + dup = pipapo_get(net, set, start, genmask); - if (PTR_ERR(dup) == -ENOENT) { - if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END)) { - end = (const u8 *)nft_set_ext_key_end(ext)->data; - dup = pipapo_get(net, set, end, nft_genmask_next(net)); - } else { - end = start; + if (!IS_ERR(dup)) { + /* Check if we already have the same exact entry */ + const struct nft_data *dup_key, *dup_end; + + dup_key = nft_set_ext_key(&dup->ext); + if (nft_set_ext_exists(&dup->ext, NFT_SET_EXT_KEY_END)) + dup_end = nft_set_ext_key_end(&dup->ext); + else + dup_end = dup_key; + + if (!memcmp(start, dup_key->data, sizeof(*dup_key->data)) && + !memcmp(end, dup_end->data, sizeof(*dup_end->data))) { + *ext2 = &dup->ext; + return -EEXIST; } + + return -ENOTEMPTY; + } + + if (PTR_ERR(dup) == -ENOENT) { + /* Look for partially overlapping entries */ + dup = pipapo_get(net, set, end, nft_genmask_next(net)); } if (PTR_ERR(dup) != -ENOENT) { if (IS_ERR(dup)) return PTR_ERR(dup); *ext2 = &dup->ext; - return -EEXIST; + return -ENOTEMPTY; } /* Validate */ diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 5000b938ab1e..8617fc16a1ed 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -33,6 +33,11 @@ static bool nft_rbtree_interval_end(const struct nft_rbtree_elem *rbe) (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END); } +static bool nft_rbtree_interval_start(const struct nft_rbtree_elem *rbe) +{ + return !nft_rbtree_interval_end(rbe); +} + static bool nft_rbtree_equal(const struct nft_set *set, const void *this, const struct nft_rbtree_elem *interval) { @@ -64,7 +69,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set if (interval && nft_rbtree_equal(set, this, interval) && nft_rbtree_interval_end(rbe) && - !nft_rbtree_interval_end(interval)) + nft_rbtree_interval_start(interval)) continue; interval = rbe; } else if (d > 0) @@ -89,7 +94,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && - !nft_rbtree_interval_end(interval)) { + nft_rbtree_interval_start(interval)) { *ext = &interval->ext; return true; } @@ -208,8 +213,43 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, u8 genmask = nft_genmask_next(net); struct nft_rbtree_elem *rbe; struct rb_node *parent, **p; + bool overlap = false; int d; + /* Detect overlaps as we descend the tree. Set the flag in these cases: + * + * a1. |__ _ _? >|__ _ _ (insert start after existing start) + * a2. _ _ __>| ?_ _ __| (insert end before existing end) + * a3. _ _ ___| ?_ _ _>| (insert end after existing end) + * a4. >|__ _ _ _ _ __| (insert start before existing end) + * + * and clear it later on, as we eventually reach the points indicated by + * '?' above, in the cases described below. We'll always meet these + * later, locally, due to tree ordering, and overlaps for the intervals + * that are the closest together are always evaluated last. + * + * b1. |__ _ _! >|__ _ _ (insert start after existing end) + * b2. _ _ __>| !_ _ __| (insert end before existing start) + * b3. !_____>| (insert end after existing start) + * + * Case a4. resolves to b1.: + * - if the inserted start element is the leftmost, because the '0' + * element in the tree serves as end element + * - otherwise, if an existing end is found. Note that end elements are + * always inserted after corresponding start elements. + * + * For a new, rightmost pair of elements, we'll hit cases b1. and b3., + * in that order. + * + * The flag is also cleared in two special cases: + * + * b4. |__ _ _!|<_ _ _ (insert start right before existing end) + * b5. |__ _ >|!__ _ _ (insert end right after existing start) + * + * which always happen as last step and imply that no further + * overlapping is possible. + */ + parent = NULL; p = &priv->root.rb_node; while (*p != NULL) { @@ -218,17 +258,42 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, d = memcmp(nft_set_ext_key(&rbe->ext), nft_set_ext_key(&new->ext), set->klen); - if (d < 0) + if (d < 0) { p = &parent->rb_left; - else if (d > 0) + + if (nft_rbtree_interval_start(new)) { + overlap = nft_rbtree_interval_start(rbe) && + nft_set_elem_active(&rbe->ext, + genmask); + } else { + overlap = nft_rbtree_interval_end(rbe) && + nft_set_elem_active(&rbe->ext, + genmask); + } + } else if (d > 0) { p = &parent->rb_right; - else { + + if (nft_rbtree_interval_end(new)) { + overlap = nft_rbtree_interval_end(rbe) && + nft_set_elem_active(&rbe->ext, + genmask); + } else if (nft_rbtree_interval_end(rbe) && + nft_set_elem_active(&rbe->ext, genmask)) { + overlap = true; + } + } else { if (nft_rbtree_interval_end(rbe) && - !nft_rbtree_interval_end(new)) { + nft_rbtree_interval_start(new)) { p = &parent->rb_left; - } else if (!nft_rbtree_interval_end(rbe) && + + if (nft_set_elem_active(&rbe->ext, genmask)) + overlap = false; + } else if (nft_rbtree_interval_start(rbe) && nft_rbtree_interval_end(new)) { p = &parent->rb_right; + + if (nft_set_elem_active(&rbe->ext, genmask)) + overlap = false; } else if (nft_set_elem_active(&rbe->ext, genmask)) { *ext = &rbe->ext; return -EEXIST; @@ -237,6 +302,10 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, } } } + + if (overlap) + return -ENOTEMPTY; + rb_link_node_rcu(&new->node, parent, p); rb_insert_color(&new->node, &priv->root); return 0; @@ -317,10 +386,10 @@ static void *nft_rbtree_deactivate(const struct net *net, parent = parent->rb_right; else { if (nft_rbtree_interval_end(rbe) && - !nft_rbtree_interval_end(this)) { + nft_rbtree_interval_start(this)) { parent = parent->rb_left; continue; - } else if (!nft_rbtree_interval_end(rbe) && + } else if (nft_rbtree_interval_start(rbe) && nft_rbtree_interval_end(this)) { parent = parent->rb_right; continue; diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index fe42f986cd94..15ee92d79581 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -285,7 +285,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, gfp_t gfp, rxrpc_notify_rx_t notify_rx, bool upgrade, - bool intr, + enum rxrpc_interruptibility interruptibility, unsigned int debug_id) { struct rxrpc_conn_parameters cp; @@ -310,7 +310,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, memset(&p, 0, sizeof(p)); p.user_call_ID = user_call_ID; p.tx_total_len = tx_total_len; - p.intr = intr; + p.interruptibility = interruptibility; memset(&cp, 0, sizeof(cp)); cp.local = rx->local; @@ -371,45 +371,18 @@ EXPORT_SYMBOL(rxrpc_kernel_end_call); * rxrpc_kernel_check_life - Check to see whether a call is still alive * @sock: The socket the call is on * @call: The call to check - * @_life: Where to store the life value * - * Allow a kernel service to find out whether a call is still alive - ie. we're - * getting ACKs from the server. Passes back in *_life a number representing - * the life state which can be compared to that returned by a previous call and - * return true if the call is still alive. - * - * If the life state stalls, rxrpc_kernel_probe_life() should be called and - * then 2RTT waited. + * Allow a kernel service to find out whether a call is still alive - + * ie. whether it has completed. */ bool rxrpc_kernel_check_life(const struct socket *sock, - const struct rxrpc_call *call, - u32 *_life) + const struct rxrpc_call *call) { - *_life = call->acks_latest; return call->state != RXRPC_CALL_COMPLETE; } EXPORT_SYMBOL(rxrpc_kernel_check_life); /** - * rxrpc_kernel_probe_life - Poke the peer to see if it's still alive - * @sock: The socket the call is on - * @call: The call to check - * - * In conjunction with rxrpc_kernel_check_life(), allow a kernel service to - * find out whether a call is still alive by pinging it. This should cause the - * life state to be bumped in about 2*RTT. - * - * The must be called in TASK_RUNNING state on pain of might_sleep() objecting. - */ -void rxrpc_kernel_probe_life(struct socket *sock, struct rxrpc_call *call) -{ - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false, - rxrpc_propose_ack_ping_for_check_life); - rxrpc_send_ack_packet(call, true, NULL); -} -EXPORT_SYMBOL(rxrpc_kernel_probe_life); - -/** * rxrpc_kernel_get_epoch - Retrieve the epoch value from a call. * @sock: The socket the call is on * @call: The call to query diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 7d730c438404..3eb1ab40ca5c 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -489,7 +489,6 @@ enum rxrpc_call_flag { RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */ RXRPC_CALL_RX_HEARD, /* The peer responded at least once to this call */ RXRPC_CALL_RX_UNDERRUN, /* Got data underrun */ - RXRPC_CALL_IS_INTR, /* The call is interruptible */ RXRPC_CALL_DISCONNECTED, /* The call has been disconnected */ }; @@ -598,6 +597,7 @@ struct rxrpc_call { atomic_t usage; u16 service_id; /* service ID */ u8 security_ix; /* Security type */ + enum rxrpc_interruptibility interruptibility; /* At what point call may be interrupted */ u32 call_id; /* call ID on connection */ u32 cid; /* connection ID plus channel index */ int debug_id; /* debug ID for printks */ @@ -675,7 +675,6 @@ struct rxrpc_call { /* transmission-phase ACK management */ ktime_t acks_latest_ts; /* Timestamp of latest ACK received */ - rxrpc_serial_t acks_latest; /* serial number of latest ACK received */ rxrpc_seq_t acks_lowest_nak; /* Lowest NACK in the buffer (or ==tx_hard_ack) */ rxrpc_seq_t acks_lost_top; /* tx_top at the time lost-ack ping sent */ rxrpc_serial_t acks_lost_ping; /* Serial number of probe ACK */ @@ -721,7 +720,7 @@ struct rxrpc_call_params { u32 normal; /* Max time since last call packet (msec) */ } timeouts; u8 nr_timeouts; /* Number of timeouts specified */ - bool intr; /* The call is interruptible */ + enum rxrpc_interruptibility interruptibility; /* How is interruptible is the call? */ }; struct rxrpc_send_params { diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index c9f34b0a11df..f07970207b54 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -237,8 +237,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, return call; } - if (p->intr) - __set_bit(RXRPC_CALL_IS_INTR, &call->flags); + call->interruptibility = p->interruptibility; call->tx_total_len = p->tx_total_len; trace_rxrpc_call(call->debug_id, rxrpc_call_new_client, atomic_read(&call->usage), diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index ea7d4c21f889..f2a1a5dbb5a7 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -655,13 +655,20 @@ static int rxrpc_wait_for_channel(struct rxrpc_call *call, gfp_t gfp) add_wait_queue_exclusive(&call->waitq, &myself); for (;;) { - if (test_bit(RXRPC_CALL_IS_INTR, &call->flags)) + switch (call->interruptibility) { + case RXRPC_INTERRUPTIBLE: + case RXRPC_PREINTERRUPTIBLE: set_current_state(TASK_INTERRUPTIBLE); - else + break; + case RXRPC_UNINTERRUPTIBLE: + default: set_current_state(TASK_UNINTERRUPTIBLE); + break; + } if (call->call_id) break; - if (test_bit(RXRPC_CALL_IS_INTR, &call->flags) && + if ((call->interruptibility == RXRPC_INTERRUPTIBLE || + call->interruptibility == RXRPC_PREINTERRUPTIBLE) && signal_pending(current)) { ret = -ERESTARTSYS; break; diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index ef10fbf71b15..69e09d69c896 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -882,7 +882,6 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) before(prev_pkt, call->ackr_prev_seq)) goto out; call->acks_latest_ts = skb->tstamp; - call->acks_latest = sp->hdr.serial; call->ackr_first_seq = first_soft_ack; call->ackr_prev_seq = prev_pkt; diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 813fd6888142..0fcf157aa09f 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -18,6 +18,21 @@ #include "ar-internal.h" /* + * Return true if there's sufficient Tx queue space. + */ +static bool rxrpc_check_tx_space(struct rxrpc_call *call, rxrpc_seq_t *_tx_win) +{ + unsigned int win_size = + min_t(unsigned int, call->tx_winsize, + call->cong_cwnd + call->cong_extra); + rxrpc_seq_t tx_win = READ_ONCE(call->tx_hard_ack); + + if (_tx_win) + *_tx_win = tx_win; + return call->tx_top - tx_win < win_size; +} + +/* * Wait for space to appear in the Tx queue or a signal to occur. */ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx, @@ -26,9 +41,7 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx, { for (;;) { set_current_state(TASK_INTERRUPTIBLE); - if (call->tx_top - call->tx_hard_ack < - min_t(unsigned int, call->tx_winsize, - call->cong_cwnd + call->cong_extra)) + if (rxrpc_check_tx_space(call, NULL)) return 0; if (call->state >= RXRPC_CALL_COMPLETE) @@ -49,7 +62,7 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx, * Wait for space to appear in the Tx queue uninterruptibly, but with * a timeout of 2*RTT if no progress was made and a signal occurred. */ -static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx, +static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx, struct rxrpc_call *call) { rxrpc_seq_t tx_start, tx_win; @@ -58,8 +71,8 @@ static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx, rtt = READ_ONCE(call->peer->rtt); rtt2 = nsecs_to_jiffies64(rtt) * 2; - if (rtt2 < 1) - rtt2 = 1; + if (rtt2 < 2) + rtt2 = 2; timeout = rtt2; tx_start = READ_ONCE(call->tx_hard_ack); @@ -68,16 +81,13 @@ static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx, set_current_state(TASK_UNINTERRUPTIBLE); tx_win = READ_ONCE(call->tx_hard_ack); - if (call->tx_top - tx_win < - min_t(unsigned int, call->tx_winsize, - call->cong_cwnd + call->cong_extra)) + if (rxrpc_check_tx_space(call, &tx_win)) return 0; if (call->state >= RXRPC_CALL_COMPLETE) return call->error; - if (test_bit(RXRPC_CALL_IS_INTR, &call->flags) && - timeout == 0 && + if (timeout == 0 && tx_win == tx_start && signal_pending(current)) return -EINTR; @@ -92,6 +102,26 @@ static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx, } /* + * Wait for space to appear in the Tx queue uninterruptibly. + */ +static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx, + struct rxrpc_call *call, + long *timeo) +{ + for (;;) { + set_current_state(TASK_UNINTERRUPTIBLE); + if (rxrpc_check_tx_space(call, NULL)) + return 0; + + if (call->state >= RXRPC_CALL_COMPLETE) + return call->error; + + trace_rxrpc_transmit(call, rxrpc_transmit_wait); + *timeo = schedule_timeout(*timeo); + } +} + +/* * wait for space to appear in the transmit/ACK window * - caller holds the socket locked */ @@ -108,10 +138,19 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx, add_wait_queue(&call->waitq, &myself); - if (waitall) - ret = rxrpc_wait_for_tx_window_nonintr(rx, call); - else - ret = rxrpc_wait_for_tx_window_intr(rx, call, timeo); + switch (call->interruptibility) { + case RXRPC_INTERRUPTIBLE: + if (waitall) + ret = rxrpc_wait_for_tx_window_waitall(rx, call); + else + ret = rxrpc_wait_for_tx_window_intr(rx, call, timeo); + break; + case RXRPC_PREINTERRUPTIBLE: + case RXRPC_UNINTERRUPTIBLE: + default: + ret = rxrpc_wait_for_tx_window_nonintr(rx, call, timeo); + break; + } remove_wait_queue(&call->waitq, &myself); set_current_state(TASK_RUNNING); @@ -302,9 +341,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, _debug("alloc"); - if (call->tx_top - call->tx_hard_ack >= - min_t(unsigned int, call->tx_winsize, - call->cong_cwnd + call->cong_extra)) { + if (!rxrpc_check_tx_space(call, NULL)) { ret = -EAGAIN; if (msg->msg_flags & MSG_DONTWAIT) goto maybe_error; @@ -619,7 +656,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) .call.tx_total_len = -1, .call.user_call_ID = 0, .call.nr_timeouts = 0, - .call.intr = true, + .call.interruptibility = RXRPC_INTERRUPTIBLE, .abort_code = 0, .command = RXRPC_CMD_SEND_DATA, .exclusive = false, diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index f685c0d73708..41114b463161 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -739,7 +739,7 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); if (params) - kfree_rcu(params, rcu); + call_rcu(¶ms->rcu, tcf_ct_params_free); if (res == ACT_P_CREATED) tcf_idr_insert(tn, *a); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 1ad300e6dbc0..83dd82fc9f40 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -284,10 +284,8 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, /* mirror is always swallowed */ if (is_redirect) { - skb2->tc_redirected = 1; - skb2->tc_from_ingress = skb2->tc_at_ingress; - if (skb2->tc_from_ingress) - skb2->tstamp = 0; + skb_set_redirected(skb2, skb2->tc_at_ingress); + /* let's the caller reinsert the packet, if possible */ if (use_reinsert) { res->ingress = want_ingress; diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index b2905b03a432..2eaac2ff380f 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -181,6 +181,11 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch) s64 credits; int len; + /* The previous packet is still being sent */ + if (now < q->last) { + qdisc_watchdog_schedule_ns(&q->watchdog, q->last); + return NULL; + } if (q->credits < 0) { credits = timediff_to_credits(now - q->last, q->idleslope); @@ -212,7 +217,12 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch) credits += q->credits; q->credits = max_t(s64, credits, q->locredit); - q->last = now; + /* Estimate of the transmission of the last byte of the packet in ns */ + if (unlikely(atomic64_read(&q->port_rate) == 0)) + q->last = now; + else + q->last = now + div64_s64(len * NSEC_PER_SEC, + atomic64_read(&q->port_rate)); return skb; } diff --git a/net/socket.c b/net/socket.c index b79a05de7c6e..2eecf1517f76 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1707,7 +1707,8 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog) int __sys_accept4_file(struct file *file, unsigned file_flags, struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen, int flags) + int __user *upeer_addrlen, int flags, + unsigned long nofile) { struct socket *sock, *newsock; struct file *newfile; @@ -1738,7 +1739,7 @@ int __sys_accept4_file(struct file *file, unsigned file_flags, */ __module_get(newsock->ops->owner); - newfd = get_unused_fd_flags(flags); + newfd = __get_unused_fd_flags(flags, nofile); if (unlikely(newfd < 0)) { err = newfd; sock_release(newsock); @@ -1807,7 +1808,8 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, f = fdget(fd); if (f.file) { ret = __sys_accept4_file(f.file, 0, upeer_sockaddr, - upeer_addrlen, flags); + upeer_addrlen, flags, + rlimit(RLIMIT_NOFILE)); if (f.flags) fput(f.file); } |