diff options
Diffstat (limited to 'net')
42 files changed, 484 insertions, 253 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/bpfilter/main.c b/net/bpfilter/main.c index 77396a098fbe..efea4874743e 100644 --- a/net/bpfilter/main.c +++ b/net/bpfilter/main.c @@ -10,7 +10,7 @@ #include <asm/unistd.h> #include "msgfmt.h" -int debug_fd; +FILE *debug_f; static int handle_get_cmd(struct mbox_request *cmd) { @@ -35,9 +35,10 @@ static void loop(void) struct mbox_reply reply; int n; + fprintf(debug_f, "testing the buffer\n"); n = read(0, &req, sizeof(req)); if (n != sizeof(req)) { - dprintf(debug_fd, "invalid request %d\n", n); + fprintf(debug_f, "invalid request %d\n", n); return; } @@ -47,7 +48,7 @@ static void loop(void) n = write(1, &reply, sizeof(reply)); if (n != sizeof(reply)) { - dprintf(debug_fd, "reply failed %d\n", n); + fprintf(debug_f, "reply failed %d\n", n); return; } } @@ -55,9 +56,10 @@ static void loop(void) int main(void) { - debug_fd = open("/dev/kmsg", 00000002); - dprintf(debug_fd, "Started bpfilter\n"); + debug_f = fopen("/dev/kmsg", "w"); + setvbuf(debug_f, 0, _IOLBF, 0); + fprintf(debug_f, "Started bpfilter\n"); loop(); - close(debug_fd); + fclose(debug_f); return 0; } diff --git a/net/core/dev.c b/net/core/dev.c index 021e18251465..d760dcc47978 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; @@ -5195,7 +5195,7 @@ static int __netif_receive_skb_one_core(struct sk_buff *skb, bool pfmemalloc) * * More direct receive version of netif_receive_skb(). It should * only be used by callers that have a need to skip RPS and Generic XDP. - * Caller must also take care of handling if (page_is_)pfmemalloc. + * Caller must also take care of handling if ``(page_is_)pfmemalloc``. * * This function may only be called from softirq context and interrupts * should be enabled. diff --git a/net/core/pktgen.c b/net/core/pktgen.c index f2b3d8dd40f4..08e2811b5274 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/core/sock_map.c b/net/core/sock_map.c index a7075b3b4489..b08dfae10f88 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -299,8 +299,11 @@ static void sock_map_free(struct bpf_map *map) struct bpf_stab *stab = container_of(map, struct bpf_stab, map); int i; + /* After the sync no updates or deletes will be in-flight so it + * is safe to walk map and remove entries without risking a race + * in EEXIST update case. + */ synchronize_rcu(); - raw_spin_lock_bh(&stab->lock); for (i = 0; i < stab->map.max_entries; i++) { struct sock **psk = &stab->sks[i]; struct sock *sk; @@ -314,7 +317,6 @@ static void sock_map_free(struct bpf_map *map) release_sock(sk); } } - raw_spin_unlock_bh(&stab->lock); /* wait for psock readers accessing its map link */ synchronize_rcu(); @@ -1008,10 +1010,13 @@ static void sock_hash_free(struct bpf_map *map) struct hlist_node *node; int i; + /* After the sync no updates or deletes will be in-flight so it + * is safe to walk map and remove entries without risking a race + * in EEXIST update case. + */ synchronize_rcu(); for (i = 0; i < htab->buckets_num; i++) { bucket = sock_hash_select_bucket(htab, i); - raw_spin_lock_bh(&bucket->lock); hlist_for_each_entry_safe(elem, node, &bucket->head, node) { hlist_del_rcu(&elem->node); lock_sock(elem->sk); @@ -1020,7 +1025,6 @@ static void sock_hash_free(struct bpf_map *map) rcu_read_unlock(); release_sock(elem->sk); } - raw_spin_unlock_bh(&bucket->lock); } /* wait for psock readers accessing its map link */ 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 0d3f796d14a3..cc8512b5f9e2 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; } 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 87f288ee20c8..1bd026a29f3f 100644 --- a/net/ethtool/debug.c +++ b/net/ethtool/debug.c @@ -109,8 +109,9 @@ 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); @@ -131,6 +132,7 @@ 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 2df420068cbb..677068deb68c 100644 --- a/net/ethtool/linkinfo.c +++ b/net/ethtool/linkinfo.c @@ -128,9 +128,10 @@ 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); @@ -164,6 +165,7 @@ 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 cb29cc8c5960..452608c6d856 100644 --- a/net/ethtool/linkmodes.c +++ b/net/ethtool/linkmodes.c @@ -341,9 +341,10 @@ 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); @@ -373,6 +374,7 @@ out_ops: ethnl_ops_complete(dev); out_rtnl: rtnl_unlock(); +out_dev: dev_put(dev); return ret; } diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 55c8ce4019d9..71855bdd3b38 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -40,6 +40,7 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, struct nlattr *tb[ETHTOOL_A_HEADER_MAX + 1]; const struct nlattr *devname_attr; struct net_device *dev = NULL; + u32 flags = 0; int ret; if (!header) { @@ -50,8 +51,17 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, ethnl_header_policy, extack); if (ret < 0) return ret; - devname_attr = tb[ETHTOOL_A_HEADER_DEV_NAME]; + if (tb[ETHTOOL_A_HEADER_FLAGS]) { + flags = nla_get_u32(tb[ETHTOOL_A_HEADER_FLAGS]); + if (flags & ~ETHTOOL_FLAG_ALL) { + NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_HEADER_FLAGS], + "unrecognized request flags"); + nl_set_extack_cookie_u32(extack, ETHTOOL_FLAG_ALL); + return -EOPNOTSUPP; + } + } + devname_attr = tb[ETHTOOL_A_HEADER_DEV_NAME]; if (tb[ETHTOOL_A_HEADER_DEV_INDEX]) { u32 ifindex = nla_get_u32(tb[ETHTOOL_A_HEADER_DEV_INDEX]); @@ -90,9 +100,7 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, } req_info->dev = dev; - if (tb[ETHTOOL_A_HEADER_FLAGS]) - req_info->flags = nla_get_u32(tb[ETHTOOL_A_HEADER_FLAGS]); - + req_info->flags = flags; return 0; } diff --git a/net/ethtool/wol.c b/net/ethtool/wol.c index 1d2bcabee554..1798421e9f1c 100644 --- a/net/ethtool/wol.c +++ b/net/ethtool/wol.c @@ -129,8 +129,9 @@ 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); @@ -173,6 +174,7 @@ out_ops: ethnl_ops_complete(dev); out_rtnl: rtnl_unlock(); +out_dev: dev_put(dev); return ret; } diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index d46d22c7105c..03b891904314 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -483,12 +483,9 @@ int hsr_get_node_data(struct hsr_priv *hsr, struct hsr_port *port; unsigned long tdiff; - rcu_read_lock(); node = find_node_by_addr_A(&hsr->node_db, addr); - if (!node) { - rcu_read_unlock(); - return -ENOENT; /* No such entry */ - } + if (!node) + return -ENOENT; ether_addr_copy(addr_b, node->macaddress_B); @@ -523,7 +520,5 @@ int hsr_get_node_data(struct hsr_priv *hsr, *addr_b_ifindex = -1; } - rcu_read_unlock(); - return 0; } diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 64d39c1e93a2..5465a395da04 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -250,15 +250,16 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info) if (!na) goto invalid; - hsr_dev = __dev_get_by_index(genl_info_net(info), - nla_get_u32(info->attrs[HSR_A_IFINDEX])); + rcu_read_lock(); + hsr_dev = dev_get_by_index_rcu(genl_info_net(info), + nla_get_u32(info->attrs[HSR_A_IFINDEX])); if (!hsr_dev) - goto invalid; + goto rcu_unlock; if (!is_hsr_master(hsr_dev)) - goto invalid; + goto rcu_unlock; /* Send reply */ - skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb_out) { res = -ENOMEM; goto fail; @@ -312,12 +313,10 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info) res = nla_put_u16(skb_out, HSR_A_IF1_SEQ, hsr_node_if1_seq); if (res < 0) goto nla_put_failure; - rcu_read_lock(); port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); if (port) res = nla_put_u32(skb_out, HSR_A_IF1_IFINDEX, port->dev->ifindex); - rcu_read_unlock(); if (res < 0) goto nla_put_failure; @@ -327,20 +326,22 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info) res = nla_put_u16(skb_out, HSR_A_IF2_SEQ, hsr_node_if2_seq); if (res < 0) goto nla_put_failure; - rcu_read_lock(); port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); if (port) res = nla_put_u32(skb_out, HSR_A_IF2_IFINDEX, port->dev->ifindex); - rcu_read_unlock(); if (res < 0) goto nla_put_failure; + rcu_read_unlock(); + genlmsg_end(skb_out, msg_head); genlmsg_unicast(genl_info_net(info), skb_out, info->snd_portid); return 0; +rcu_unlock: + rcu_read_unlock(); invalid: netlink_ack(skb_in, nlmsg_hdr(skb_in), -EINVAL, NULL); return 0; @@ -350,6 +351,7 @@ nla_put_failure: /* Fall through */ fail: + rcu_read_unlock(); return res; } @@ -357,16 +359,14 @@ fail: */ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info) { - /* For receiving */ - struct nlattr *na; + unsigned char addr[ETH_ALEN]; struct net_device *hsr_dev; - - /* For sending */ struct sk_buff *skb_out; - void *msg_head; struct hsr_priv *hsr; - void *pos; - unsigned char addr[ETH_ALEN]; + bool restart = false; + struct nlattr *na; + void *pos = NULL; + void *msg_head; int res; if (!info) @@ -376,15 +376,17 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info) if (!na) goto invalid; - hsr_dev = __dev_get_by_index(genl_info_net(info), - nla_get_u32(info->attrs[HSR_A_IFINDEX])); + rcu_read_lock(); + hsr_dev = dev_get_by_index_rcu(genl_info_net(info), + nla_get_u32(info->attrs[HSR_A_IFINDEX])); if (!hsr_dev) - goto invalid; + goto rcu_unlock; if (!is_hsr_master(hsr_dev)) - goto invalid; + goto rcu_unlock; +restart: /* Send reply */ - skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + skb_out = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb_out) { res = -ENOMEM; goto fail; @@ -398,18 +400,26 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info) goto nla_put_failure; } - res = nla_put_u32(skb_out, HSR_A_IFINDEX, hsr_dev->ifindex); - if (res < 0) - goto nla_put_failure; + if (!restart) { + res = nla_put_u32(skb_out, HSR_A_IFINDEX, hsr_dev->ifindex); + if (res < 0) + goto nla_put_failure; + } hsr = netdev_priv(hsr_dev); - rcu_read_lock(); - pos = hsr_get_next_node(hsr, NULL, addr); + if (!pos) + pos = hsr_get_next_node(hsr, NULL, addr); while (pos) { res = nla_put(skb_out, HSR_A_NODE_ADDR, ETH_ALEN, addr); if (res < 0) { - rcu_read_unlock(); + if (res == -EMSGSIZE) { + genlmsg_end(skb_out, msg_head); + genlmsg_unicast(genl_info_net(info), skb_out, + info->snd_portid); + restart = true; + goto restart; + } goto nla_put_failure; } pos = hsr_get_next_node(hsr, pos, addr); @@ -421,15 +431,18 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info) return 0; +rcu_unlock: + rcu_read_unlock(); invalid: netlink_ack(skb_in, nlmsg_hdr(skb_in), -EINVAL, NULL); return 0; nla_put_failure: - kfree_skb(skb_out); + nlmsg_free(skb_out); /* Fall through */ fail: + rcu_read_unlock(); return res; } @@ -456,6 +469,7 @@ static struct genl_family hsr_genl_family __ro_after_init = { .version = 1, .maxattr = HSR_A_MAX, .policy = hsr_genl_policy, + .netnsok = true, .module = THIS_MODULE, .ops = hsr_ops, .n_ops = ARRAY_SIZE(hsr_ops), diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index d3547e8c6d5b..f4b9f7a3ce51 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -151,16 +151,16 @@ 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(hsr, dev, port, extack); 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/ip_gre.c b/net/ipv4/ip_gre.c index 8274f98c511c..029b24eeafba 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1153,6 +1153,24 @@ static int ipgre_netlink_parms(struct net_device *dev, if (data[IFLA_GRE_FWMARK]) *fwmark = nla_get_u32(data[IFLA_GRE_FWMARK]); + return 0; +} + +static int erspan_netlink_parms(struct net_device *dev, + struct nlattr *data[], + struct nlattr *tb[], + struct ip_tunnel_parm *parms, + __u32 *fwmark) +{ + struct ip_tunnel *t = netdev_priv(dev); + int err; + + err = ipgre_netlink_parms(dev, data, tb, parms, fwmark); + if (err) + return err; + if (!data) + return 0; + if (data[IFLA_GRE_ERSPAN_VER]) { t->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); @@ -1276,45 +1294,70 @@ static void ipgre_tap_setup(struct net_device *dev) ip_tunnel_setup(dev, gre_tap_net_id); } -static int ipgre_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], - struct netlink_ext_ack *extack) +static int +ipgre_newlink_encap_setup(struct net_device *dev, struct nlattr *data[]) { - struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; - __u32 fwmark = 0; - int err; if (ipgre_netlink_encap_parms(data, &ipencap)) { struct ip_tunnel *t = netdev_priv(dev); - err = ip_tunnel_encap_setup(t, &ipencap); + int err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) return err; } + return 0; +} + +static int ipgre_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct ip_tunnel_parm p; + __u32 fwmark = 0; + int err; + + err = ipgre_newlink_encap_setup(dev, data); + if (err) + return err; + err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; return ip_tunnel_newlink(dev, tb, &p, fwmark); } +static int erspan_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct ip_tunnel_parm p; + __u32 fwmark = 0; + int err; + + err = ipgre_newlink_encap_setup(dev, data); + if (err) + return err; + + err = erspan_netlink_parms(dev, data, tb, &p, &fwmark); + if (err) + return err; + return ip_tunnel_newlink(dev, tb, &p, fwmark); +} + static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); - struct ip_tunnel_encap ipencap; __u32 fwmark = t->fwmark; struct ip_tunnel_parm p; int err; - if (ipgre_netlink_encap_parms(data, &ipencap)) { - err = ip_tunnel_encap_setup(t, &ipencap); - - if (err < 0) - return err; - } + err = ipgre_newlink_encap_setup(dev, data); + if (err) + return err; err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) @@ -1327,8 +1370,34 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], t->parms.i_flags = p.i_flags; t->parms.o_flags = p.o_flags; - if (strcmp(dev->rtnl_link_ops->kind, "erspan")) - ipgre_link_update(dev, !tb[IFLA_MTU]); + ipgre_link_update(dev, !tb[IFLA_MTU]); + + return 0; +} + +static int erspan_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct ip_tunnel *t = netdev_priv(dev); + __u32 fwmark = t->fwmark; + struct ip_tunnel_parm p; + int err; + + err = ipgre_newlink_encap_setup(dev, data); + if (err) + return err; + + err = erspan_netlink_parms(dev, data, tb, &p, &fwmark); + if (err < 0) + return err; + + err = ip_tunnel_changelink(dev, tb, &p, fwmark); + if (err < 0) + return err; + + t->parms.i_flags = p.i_flags; + t->parms.o_flags = p.o_flags; return 0; } @@ -1519,8 +1588,8 @@ static struct rtnl_link_ops erspan_link_ops __read_mostly = { .priv_size = sizeof(struct ip_tunnel), .setup = erspan_setup, .validate = erspan_validate, - .newlink = ipgre_newlink, - .changelink = ipgre_changelink, + .newlink = erspan_newlink, + .changelink = erspan_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, .fill_info = ipgre_fill_info, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5c57850fab4b..6d87de434377 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 9a477bd563b7..d523c2a9312f 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -613,6 +613,9 @@ 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); mutex_destroy(&flow_table->flow_block_lock); } diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 5272721080f8..441fb0d7bead 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; @@ -417,11 +420,13 @@ 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; @@ -450,6 +455,7 @@ 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 ad549317af30..024a91645d9c 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -120,6 +120,7 @@ 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 f92fb6003745..1dc539729926 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5106,6 +5106,11 @@ 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 c1afb6c94edc..87aabf651cfe 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1164,21 +1164,41 @@ 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 172ef8189f99..3a5552e14f75 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/netlink/af_netlink.c b/net/netlink/af_netlink.c index ed77c75bf63f..5ded01ca8b20 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2392,19 +2392,14 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, if (nlk_has_extack && extack && extack->_msg) tlvlen += nla_total_size(strlen(extack->_msg) + 1); - if (err) { - if (!(nlk->flags & NETLINK_F_CAP_ACK)) - payload += nlmsg_len(nlh); - else - flags |= NLM_F_CAPPED; - if (nlk_has_extack && extack && extack->bad_attr) - tlvlen += nla_total_size(sizeof(u32)); - } else { + if (err && !(nlk->flags & NETLINK_F_CAP_ACK)) + payload += nlmsg_len(nlh); + else flags |= NLM_F_CAPPED; - - if (nlk_has_extack && extack && extack->cookie_len) - tlvlen += nla_total_size(extack->cookie_len); - } + if (err && nlk_has_extack && extack && extack->bad_attr) + tlvlen += nla_total_size(sizeof(u32)); + if (nlk_has_extack && extack && extack->cookie_len) + tlvlen += nla_total_size(extack->cookie_len); if (tlvlen) flags |= NLM_F_ACK_TLVS; @@ -2427,20 +2422,16 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, WARN_ON(nla_put_string(skb, NLMSGERR_ATTR_MSG, extack->_msg)); } - if (err) { - if (extack->bad_attr && - !WARN_ON((u8 *)extack->bad_attr < in_skb->data || - (u8 *)extack->bad_attr >= in_skb->data + - in_skb->len)) - WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_OFFS, - (u8 *)extack->bad_attr - - (u8 *)nlh)); - } else { - if (extack->cookie_len) - WARN_ON(nla_put(skb, NLMSGERR_ATTR_COOKIE, - extack->cookie_len, - extack->cookie)); - } + if (err && extack->bad_attr && + !WARN_ON((u8 *)extack->bad_attr < in_skb->data || + (u8 *)extack->bad_attr >= in_skb->data + + in_skb->len)) + WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_OFFS, + (u8 *)extack->bad_attr - + (u8 *)nlh)); + if (extack->cookie_len) + WARN_ON(nla_put(skb, NLMSGERR_ATTR_COOKIE, + extack->cookie_len, extack->cookie)); } nlmsg_end(skb, rep); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index e5b0986215d2..29bd405adbbd 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2173,6 +2173,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct timespec64 ts; __u32 ts_status; bool is_drop_n_account = false; + unsigned int slot_id = 0; bool do_vnet = false; /* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT. @@ -2275,6 +2276,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if (!h.raw) goto drop_n_account; + if (po->tp_version <= TPACKET_V2) { + slot_id = po->rx_ring.head; + if (test_bit(slot_id, po->rx_ring.rx_owner_map)) + goto drop_n_account; + __set_bit(slot_id, po->rx_ring.rx_owner_map); + } + if (do_vnet && virtio_net_hdr_from_skb(skb, h.raw + macoff - sizeof(struct virtio_net_hdr), @@ -2380,7 +2388,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, #endif if (po->tp_version <= TPACKET_V2) { + spin_lock(&sk->sk_receive_queue.lock); __packet_set_status(po, h.raw, status); + __clear_bit(slot_id, po->rx_ring.rx_owner_map); + spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk); } else { prb_clear_blk_fill_status(&po->rx_ring); @@ -4277,6 +4288,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, { struct pgv *pg_vec = NULL; struct packet_sock *po = pkt_sk(sk); + unsigned long *rx_owner_map = NULL; int was_running, order = 0; struct packet_ring_buffer *rb; struct sk_buff_head *rb_queue; @@ -4362,6 +4374,12 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, } break; default: + if (!tx_ring) { + rx_owner_map = bitmap_alloc(req->tp_frame_nr, + GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO); + if (!rx_owner_map) + goto out_free_pg_vec; + } break; } } @@ -4391,6 +4409,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, err = 0; spin_lock_bh(&rb_queue->lock); swap(rb->pg_vec, pg_vec); + if (po->tp_version <= TPACKET_V2) + swap(rb->rx_owner_map, rx_owner_map); rb->frame_max = (req->tp_frame_nr - 1); rb->head = 0; rb->frame_size = req->tp_frame_size; @@ -4422,6 +4442,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, } out_free_pg_vec: + bitmap_free(rx_owner_map); if (pg_vec) free_pg_vec(pg_vec, order, req->tp_block_nr); out: diff --git a/net/packet/internal.h b/net/packet/internal.h index 82fb2b10f790..907f4cd2a718 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -70,7 +70,10 @@ struct packet_ring_buffer { unsigned int __percpu *pending_refcnt; - struct tpacket_kbdq_core prb_bdqc; + union { + unsigned long *rx_owner_map; + struct tpacket_kbdq_core prb_bdqc; + }; }; extern struct mutex fanout_mutex; 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 56b66d215a89..1a766393be62 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1273,7 +1273,7 @@ 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/cls_route.c b/net/sched/cls_route.c index 6f8786b06bde..5efa3e7ace15 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -534,8 +534,8 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, fp = &b->ht[h]; for (pfp = rtnl_dereference(*fp); pfp; fp = &pfp->next, pfp = rtnl_dereference(*fp)) { - if (pfp == f) { - *fp = f->next; + if (pfp == fold) { + rcu_assign_pointer(*fp, fold->next); break; } } diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 09b7dc5fe7e0..9904299424a1 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -261,8 +261,10 @@ static void tcindex_partial_destroy_work(struct work_struct *work) struct tcindex_data, rwork); + rtnl_lock(); kfree(p->perfect); kfree(p); + rtnl_unlock(); } static void tcindex_free_perfect_hash(struct tcindex_data *cp) @@ -357,6 +359,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, if (tcindex_alloc_perfect_hash(net, cp) < 0) goto errout; + cp->alloc_hash = cp->hash; for (i = 0; i < min(cp->hash, p->hash); i++) cp->perfect[i].res = p->perfect[i].res; balloc = 1; 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); } |