diff options
Diffstat (limited to 'net')
114 files changed, 5480 insertions, 1376 deletions
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index a0b2d8b9def7..93eadf179123 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -580,6 +580,7 @@ static int vlan_dev_init(struct net_device *dev) dev->vlan_features = real_dev->vlan_features & ~NETIF_F_ALL_FCOE; dev->hw_enc_features = vlan_tnl_features(real_dev); + dev->mpls_features = real_dev->mpls_features; /* ipv6 shared card related stuff */ dev->dev_id = real_dev->dev_id; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index c05def8fd9cd..681b72862c16 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -52,6 +52,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) br_switchdev_frame_unmark(skb); BR_INPUT_SKB_CB(skb)->brdev = dev; + BR_INPUT_SKB_CB(skb)->frag_max_size = 0; skb_reset_mac_header(skb); eth = eth_hdr(skb); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 159a0e2cb0f6..e8cf03b43b7d 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -421,6 +421,7 @@ struct net_bridge { struct br_input_skb_cb { struct net_device *brdev; + u16 frag_max_size; #ifdef CONFIG_BRIDGE_IGMP_SNOOPING u8 igmp; u8 mrouters_only:1; diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig index c3ad90c43801..f4fb0b9b927d 100644 --- a/net/bridge/netfilter/Kconfig +++ b/net/bridge/netfilter/Kconfig @@ -19,6 +19,20 @@ config NF_LOG_BRIDGE tristate "Bridge packet logging" select NF_LOG_COMMON +config NF_CONNTRACK_BRIDGE + tristate "IPv4/IPV6 bridge connection tracking support" + depends on NF_CONNTRACK + default n + help + Connection tracking keeps a record of what packets have passed + through your machine, in order to figure out how they are related + into connections. This is used to enhance packet filtering via + stateful policies. Enable this if you want native tracking from + the bridge. This provides a replacement for the `br_netfilter' + infrastructure. + + To compile it as a module, choose M here. If unsure, say N. + endif # NF_TABLES_BRIDGE menuconfig BRIDGE_NF_EBTABLES diff --git a/net/bridge/netfilter/Makefile b/net/bridge/netfilter/Makefile index 9b868861f21a..9d7767322a64 100644 --- a/net/bridge/netfilter/Makefile +++ b/net/bridge/netfilter/Makefile @@ -5,6 +5,9 @@ obj-$(CONFIG_NFT_BRIDGE_REJECT) += nft_reject_bridge.o +# connection tracking +obj-$(CONFIG_NF_CONNTRACK_BRIDGE) += nf_conntrack_bridge.o + # packet logging obj-$(CONFIG_NF_LOG_BRIDGE) += nf_log_bridge.o diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c index eeae23a73c6a..ed91ea31978a 100644 --- a/net/bridge/netfilter/ebt_dnat.c +++ b/net/bridge/netfilter/ebt_dnat.c @@ -22,7 +22,7 @@ ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par) const struct ebt_nat_info *info = par->targinfo; struct net_device *dev; - if (!skb_make_writable(skb, 0)) + if (skb_ensure_writable(skb, ETH_ALEN)) return EBT_DROP; ether_addr_copy(eth_hdr(skb)->h_dest, info->mac); diff --git a/net/bridge/netfilter/ebt_redirect.c b/net/bridge/netfilter/ebt_redirect.c index 53ef08e6765f..0cad62a4052b 100644 --- a/net/bridge/netfilter/ebt_redirect.c +++ b/net/bridge/netfilter/ebt_redirect.c @@ -21,7 +21,7 @@ ebt_redirect_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_redirect_info *info = par->targinfo; - if (!skb_make_writable(skb, 0)) + if (skb_ensure_writable(skb, ETH_ALEN)) return EBT_DROP; if (xt_hooknum(par) != NF_BR_BROUTING) diff --git a/net/bridge/netfilter/ebt_snat.c b/net/bridge/netfilter/ebt_snat.c index 700d338d5ddb..27443bf229a3 100644 --- a/net/bridge/netfilter/ebt_snat.c +++ b/net/bridge/netfilter/ebt_snat.c @@ -22,7 +22,7 @@ ebt_snat_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_nat_info *info = par->targinfo; - if (!skb_make_writable(skb, 0)) + if (skb_ensure_writable(skb, ETH_ALEN * 2)) return EBT_DROP; ether_addr_copy(eth_hdr(skb)->h_source, info->mac); diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c new file mode 100644 index 000000000000..b675cd7c1a82 --- /dev/null +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -0,0 +1,433 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/types.h> +#include <linux/ip.h> +#include <linux/netfilter.h> +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter_bridge.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/icmp.h> +#include <linux/sysctl.h> +#include <net/route.h> +#include <net/ip.h> + +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_bridge.h> + +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> +#include <net/netfilter/nf_tables.h> + +#include "../br_private.h" + +/* Best effort variant of ip_do_fragment which preserves geometry, unless skbuff + * has been linearized or cloned. + */ +static int nf_br_ip_fragment(struct net *net, struct sock *sk, + struct sk_buff *skb, + struct nf_ct_bridge_frag_data *data, + int (*output)(struct net *, struct sock *sk, + const struct nf_ct_bridge_frag_data *data, + struct sk_buff *)) +{ + int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size; + unsigned int hlen, ll_rs, mtu; + struct ip_frag_state state; + struct iphdr *iph; + int err; + + /* for offloaded checksums cleanup checksum before fragmentation */ + if (skb->ip_summed == CHECKSUM_PARTIAL && + (err = skb_checksum_help(skb))) + goto blackhole; + + iph = ip_hdr(skb); + + /* + * Setup starting values + */ + + hlen = iph->ihl * 4; + frag_max_size -= hlen; + ll_rs = LL_RESERVED_SPACE(skb->dev); + mtu = skb->dev->mtu; + + if (skb_has_frag_list(skb)) { + unsigned int first_len = skb_pagelen(skb); + struct ip_fraglist_iter iter; + struct sk_buff *frag; + + if (first_len - hlen > mtu || + skb_headroom(skb) < ll_rs) + goto blackhole; + + if (skb_cloned(skb)) + goto slow_path; + + skb_walk_frags(skb, frag) { + if (frag->len > mtu || + skb_headroom(frag) < hlen + ll_rs) + goto blackhole; + + if (skb_shared(frag)) + goto slow_path; + } + + ip_fraglist_init(skb, iph, hlen, &iter); + + for (;;) { + if (iter.frag) + ip_fraglist_prepare(skb, &iter); + + err = output(net, sk, data, skb); + if (err || !iter.frag) + break; + + skb = ip_fraglist_next(&iter); + } + return err; + } +slow_path: + /* This is a linearized skbuff, the original geometry is lost for us. + * This may also be a clone skbuff, we could preserve the geometry for + * the copies but probably not worth the effort. + */ + ip_frag_init(skb, hlen, ll_rs, frag_max_size, &state); + + while (state.left > 0) { + struct sk_buff *skb2; + + skb2 = ip_frag_next(skb, &state); + if (IS_ERR(skb2)) { + err = PTR_ERR(skb2); + goto blackhole; + } + + err = output(net, sk, data, skb2); + if (err) + goto blackhole; + } + consume_skb(skb); + return err; + +blackhole: + kfree_skb(skb); + return 0; +} + +/* ip_defrag() expects IPCB() in place. */ +static void br_skb_cb_save(struct sk_buff *skb, struct br_input_skb_cb *cb, + size_t inet_skb_parm_size) +{ + memcpy(cb, skb->cb, sizeof(*cb)); + memset(skb->cb, 0, inet_skb_parm_size); +} + +static void br_skb_cb_restore(struct sk_buff *skb, + const struct br_input_skb_cb *cb, + u16 fragsz) +{ + memcpy(skb->cb, cb, sizeof(*cb)); + BR_INPUT_SKB_CB(skb)->frag_max_size = fragsz; +} + +static unsigned int nf_ct_br_defrag4(struct sk_buff *skb, + const struct nf_hook_state *state) +{ + u16 zone_id = NF_CT_DEFAULT_ZONE_ID; + enum ip_conntrack_info ctinfo; + struct br_input_skb_cb cb; + const struct nf_conn *ct; + int err; + + if (!ip_is_fragment(ip_hdr(skb))) + return NF_ACCEPT; + + ct = nf_ct_get(skb, &ctinfo); + if (ct) + zone_id = nf_ct_zone_id(nf_ct_zone(ct), CTINFO2DIR(ctinfo)); + + br_skb_cb_save(skb, &cb, sizeof(struct inet_skb_parm)); + local_bh_disable(); + err = ip_defrag(state->net, skb, + IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id); + local_bh_enable(); + if (!err) { + br_skb_cb_restore(skb, &cb, IPCB(skb)->frag_max_size); + skb->ignore_df = 1; + return NF_ACCEPT; + } + + return NF_STOLEN; +} + +static unsigned int nf_ct_br_defrag6(struct sk_buff *skb, + const struct nf_hook_state *state) +{ + u16 zone_id = NF_CT_DEFAULT_ZONE_ID; + enum ip_conntrack_info ctinfo; + struct br_input_skb_cb cb; + const struct nf_conn *ct; + int err; + + ct = nf_ct_get(skb, &ctinfo); + if (ct) + zone_id = nf_ct_zone_id(nf_ct_zone(ct), CTINFO2DIR(ctinfo)); + + br_skb_cb_save(skb, &cb, sizeof(struct inet6_skb_parm)); + + err = nf_ipv6_br_defrag(state->net, skb, + IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id); + /* queued */ + if (err == -EINPROGRESS) + return NF_STOLEN; + + br_skb_cb_restore(skb, &cb, IP6CB(skb)->frag_max_size); + return err == 0 ? NF_ACCEPT : NF_DROP; +} + +static int nf_ct_br_ip_check(const struct sk_buff *skb) +{ + const struct iphdr *iph; + int nhoff, len; + + nhoff = skb_network_offset(skb); + iph = ip_hdr(skb); + if (iph->ihl < 5 || + iph->version != 4) + return -1; + + len = ntohs(iph->tot_len); + if (skb->len < nhoff + len || + len < (iph->ihl * 4)) + return -1; + + return 0; +} + +static int nf_ct_br_ipv6_check(const struct sk_buff *skb) +{ + const struct ipv6hdr *hdr; + int nhoff, len; + + nhoff = skb_network_offset(skb); + hdr = ipv6_hdr(skb); + if (hdr->version != 6) + return -1; + + len = ntohs(hdr->payload_len) + sizeof(struct ipv6hdr) + nhoff; + if (skb->len < len) + return -1; + + return 0; +} + +static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct nf_hook_state bridge_state = *state; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + u32 len; + int ret; + + ct = nf_ct_get(skb, &ctinfo); + if ((ct && !nf_ct_is_template(ct)) || + ctinfo == IP_CT_UNTRACKED) + return NF_ACCEPT; + + switch (skb->protocol) { + case htons(ETH_P_IP): + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + return NF_ACCEPT; + + len = ntohs(ip_hdr(skb)->tot_len); + if (pskb_trim_rcsum(skb, len)) + return NF_ACCEPT; + + if (nf_ct_br_ip_check(skb)) + return NF_ACCEPT; + + bridge_state.pf = NFPROTO_IPV4; + ret = nf_ct_br_defrag4(skb, &bridge_state); + break; + case htons(ETH_P_IPV6): + if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) + return NF_ACCEPT; + + len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len); + if (pskb_trim_rcsum(skb, len)) + return NF_ACCEPT; + + if (nf_ct_br_ipv6_check(skb)) + return NF_ACCEPT; + + bridge_state.pf = NFPROTO_IPV6; + ret = nf_ct_br_defrag6(skb, &bridge_state); + break; + default: + nf_ct_set(skb, NULL, IP_CT_UNTRACKED); + return NF_ACCEPT; + } + + if (ret != NF_ACCEPT) + return ret; + + return nf_conntrack_in(skb, &bridge_state); +} + +static void nf_ct_bridge_frag_save(struct sk_buff *skb, + struct nf_ct_bridge_frag_data *data) +{ + if (skb_vlan_tag_present(skb)) { + data->vlan_present = true; + data->vlan_tci = skb->vlan_tci; + data->vlan_proto = skb->vlan_proto; + } else { + data->vlan_present = false; + } + skb_copy_from_linear_data_offset(skb, -ETH_HLEN, data->mac, ETH_HLEN); +} + +static unsigned int +nf_ct_bridge_refrag(struct sk_buff *skb, const struct nf_hook_state *state, + int (*output)(struct net *, struct sock *sk, + const struct nf_ct_bridge_frag_data *data, + struct sk_buff *)) +{ + struct nf_ct_bridge_frag_data data; + + if (!BR_INPUT_SKB_CB(skb)->frag_max_size) + return NF_ACCEPT; + + nf_ct_bridge_frag_save(skb, &data); + switch (skb->protocol) { + case htons(ETH_P_IP): + nf_br_ip_fragment(state->net, state->sk, skb, &data, output); + break; + case htons(ETH_P_IPV6): + nf_br_ip6_fragment(state->net, state->sk, skb, &data, output); + break; + default: + WARN_ON_ONCE(1); + return NF_DROP; + } + + return NF_STOLEN; +} + +/* Actually only slow path refragmentation needs this. */ +static int nf_ct_bridge_frag_restore(struct sk_buff *skb, + const struct nf_ct_bridge_frag_data *data) +{ + int err; + + err = skb_cow_head(skb, ETH_HLEN); + if (err) { + kfree_skb(skb); + return -ENOMEM; + } + if (data->vlan_present) + __vlan_hwaccel_put_tag(skb, data->vlan_proto, data->vlan_tci); + + skb_copy_to_linear_data_offset(skb, -ETH_HLEN, data->mac, ETH_HLEN); + skb_reset_mac_header(skb); + + return 0; +} + +static int nf_ct_bridge_refrag_post(struct net *net, struct sock *sk, + const struct nf_ct_bridge_frag_data *data, + struct sk_buff *skb) +{ + int err; + + err = nf_ct_bridge_frag_restore(skb, data); + if (err < 0) + return err; + + return br_dev_queue_push_xmit(net, sk, skb); +} + +static unsigned int nf_ct_bridge_confirm(struct sk_buff *skb) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + int protoff; + + ct = nf_ct_get(skb, &ctinfo); + if (!ct || ctinfo == IP_CT_RELATED_REPLY) + return nf_conntrack_confirm(skb); + + switch (skb->protocol) { + case htons(ETH_P_IP): + protoff = skb_network_offset(skb) + ip_hdrlen(skb); + break; + case htons(ETH_P_IPV6): { + unsigned char pnum = ipv6_hdr(skb)->nexthdr; + __be16 frag_off; + + protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, + &frag_off); + if (protoff < 0 || (frag_off & htons(~0x7)) != 0) + return nf_conntrack_confirm(skb); + } + break; + default: + return NF_ACCEPT; + } + return nf_confirm(skb, protoff, ct, ctinfo); +} + +static unsigned int nf_ct_bridge_post(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + int ret; + + ret = nf_ct_bridge_confirm(skb); + if (ret != NF_ACCEPT) + return ret; + + return nf_ct_bridge_refrag(skb, state, nf_ct_bridge_refrag_post); +} + +static struct nf_hook_ops nf_ct_bridge_hook_ops[] __read_mostly = { + { + .hook = nf_ct_bridge_pre, + .pf = NFPROTO_BRIDGE, + .hooknum = NF_BR_PRE_ROUTING, + .priority = NF_IP_PRI_CONNTRACK, + }, + { + .hook = nf_ct_bridge_post, + .pf = NFPROTO_BRIDGE, + .hooknum = NF_BR_POST_ROUTING, + .priority = NF_IP_PRI_CONNTRACK_CONFIRM, + }, +}; + +static struct nf_ct_bridge_info bridge_info = { + .ops = nf_ct_bridge_hook_ops, + .ops_size = ARRAY_SIZE(nf_ct_bridge_hook_ops), + .me = THIS_MODULE, +}; + +static int __init nf_conntrack_l3proto_bridge_init(void) +{ + nf_ct_bridge_register(&bridge_info); + + return 0; +} + +static void __exit nf_conntrack_l3proto_bridge_fini(void) +{ + nf_ct_bridge_unregister(&bridge_info); +} + +module_init(nf_conntrack_l3proto_bridge_init); +module_exit(nf_conntrack_l3proto_bridge_fini); + +MODULE_ALIAS("nf_conntrack-" __stringify(AF_BRIDGE)); +MODULE_LICENSE("GPL"); diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index cc9597a87770..f40e3d35fd9c 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -627,6 +627,7 @@ static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) unsigned int i; u32 nbuckets; u64 cost; + int ret; smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN); if (!smap) @@ -635,13 +636,21 @@ static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) smap->bucket_log = ilog2(roundup_pow_of_two(num_possible_cpus())); nbuckets = 1U << smap->bucket_log; + cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap); + + ret = bpf_map_charge_init(&smap->map.memory, cost); + if (ret < 0) { + kfree(smap); + return ERR_PTR(ret); + } + smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets, GFP_USER | __GFP_NOWARN); if (!smap->buckets) { + bpf_map_charge_finish(&smap->map.memory); kfree(smap); return ERR_PTR(-ENOMEM); } - cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap); for (i = 0; i < nbuckets; i++) { INIT_HLIST_HEAD(&smap->buckets[i].list); @@ -651,7 +660,6 @@ static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) smap->elem_size = sizeof(struct bpf_sk_storage_elem) + attr->value_size; smap->cache_idx = (unsigned int)atomic_inc_return(&cache_idx) % BPF_SK_STORAGE_CACHE_SIZE; - smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; return &smap->map; } diff --git a/net/core/devlink.c b/net/core/devlink.c index 132f4b757963..fd15a66c1d2f 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -17,6 +17,7 @@ #include <linux/netdevice.h> #include <linux/spinlock.h> #include <linux/refcount.h> +#include <linux/workqueue.h> #include <rdma/ib_verbs.h> #include <net/netlink.h> #include <net/genetlink.h> @@ -2668,6 +2669,108 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) return devlink->ops->reload(devlink, info->extack); } +static int devlink_nl_flash_update_fill(struct sk_buff *msg, + struct devlink *devlink, + enum devlink_command cmd, + const char *status_msg, + const char *component, + unsigned long done, unsigned long total) +{ + void *hdr; + + hdr = genlmsg_put(msg, 0, 0, &devlink_nl_family, 0, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + if (cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS) + goto out; + + if (status_msg && + nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_MSG, + status_msg)) + goto nla_put_failure; + if (component && + nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_COMPONENT, + component)) + goto nla_put_failure; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_DONE, + done, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TOTAL, + total, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + +out: + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static void __devlink_flash_update_notify(struct devlink *devlink, + enum devlink_command cmd, + const char *status_msg, + const char *component, + unsigned long done, + unsigned long total) +{ + struct sk_buff *msg; + int err; + + WARN_ON(cmd != DEVLINK_CMD_FLASH_UPDATE && + cmd != DEVLINK_CMD_FLASH_UPDATE_END && + cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_flash_update_fill(msg, devlink, cmd, status_msg, + component, done, total); + if (err) + goto out_free_msg; + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); + return; + +out_free_msg: + nlmsg_free(msg); +} + +void devlink_flash_update_begin_notify(struct devlink *devlink) +{ + __devlink_flash_update_notify(devlink, + DEVLINK_CMD_FLASH_UPDATE, + NULL, NULL, 0, 0); +} +EXPORT_SYMBOL_GPL(devlink_flash_update_begin_notify); + +void devlink_flash_update_end_notify(struct devlink *devlink) +{ + __devlink_flash_update_notify(devlink, + DEVLINK_CMD_FLASH_UPDATE_END, + NULL, NULL, 0, 0); +} +EXPORT_SYMBOL_GPL(devlink_flash_update_end_notify); + +void devlink_flash_update_status_notify(struct devlink *devlink, + const char *status_msg, + const char *component, + unsigned long done, + unsigned long total) +{ + __devlink_flash_update_notify(devlink, + DEVLINK_CMD_FLASH_UPDATE_STATUS, + status_msg, component, done, total); +} +EXPORT_SYMBOL_GPL(devlink_flash_update_status_notify); + static int devlink_nl_cmd_flash_update(struct sk_buff *skb, struct genl_info *info) { @@ -5386,6 +5489,38 @@ void devlink_free(struct devlink *devlink) } EXPORT_SYMBOL_GPL(devlink_free); +static void devlink_port_type_warn(struct work_struct *work) +{ + WARN(true, "Type was not set for devlink port."); +} + +static bool devlink_port_type_should_warn(struct devlink_port *devlink_port) +{ + /* Ignore CPU and DSA flavours. */ + return devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_CPU && + devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_DSA; +} + +#define DEVLINK_PORT_TYPE_WARN_TIMEOUT (HZ * 30) + +static void devlink_port_type_warn_schedule(struct devlink_port *devlink_port) +{ + if (!devlink_port_type_should_warn(devlink_port)) + return; + /* Schedule a work to WARN in case driver does not set port + * type within timeout. + */ + schedule_delayed_work(&devlink_port->type_warn_dw, + DEVLINK_PORT_TYPE_WARN_TIMEOUT); +} + +static void devlink_port_type_warn_cancel(struct devlink_port *devlink_port) +{ + if (!devlink_port_type_should_warn(devlink_port)) + return; + cancel_delayed_work_sync(&devlink_port->type_warn_dw); +} + /** * devlink_port_register - Register devlink port * @@ -5415,6 +5550,8 @@ int devlink_port_register(struct devlink *devlink, list_add_tail(&devlink_port->list, &devlink->port_list); INIT_LIST_HEAD(&devlink_port->param_list); mutex_unlock(&devlink->lock); + INIT_DELAYED_WORK(&devlink_port->type_warn_dw, &devlink_port_type_warn); + devlink_port_type_warn_schedule(devlink_port); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); return 0; } @@ -5429,6 +5566,7 @@ void devlink_port_unregister(struct devlink_port *devlink_port) { struct devlink *devlink = devlink_port->devlink; + devlink_port_type_warn_cancel(devlink_port); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); mutex_lock(&devlink->lock); list_del(&devlink_port->list); @@ -5442,6 +5580,7 @@ static void __devlink_port_type_set(struct devlink_port *devlink_port, { if (WARN_ON(!devlink_port->registered)) return; + devlink_port_type_warn_cancel(devlink_port); spin_lock(&devlink_port->type_lock); devlink_port->type = type; devlink_port->type_dev = type_dev; @@ -5515,6 +5654,7 @@ EXPORT_SYMBOL_GPL(devlink_port_type_ib_set); void devlink_port_type_clear(struct devlink_port *devlink_port) { __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_NOTSET, NULL); + devlink_port_type_warn_schedule(devlink_port); } EXPORT_SYMBOL_GPL(devlink_port_type_clear); diff --git a/net/core/filter.c b/net/core/filter.c index cd09bf5d21f4..88e92aae3e20 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -62,6 +62,7 @@ #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> #include <net/ip_fib.h> +#include <net/nexthop.h> #include <net/flow.h> #include <net/arp.h> #include <net/ipv6.h> @@ -4670,7 +4671,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (res.type != RTN_UNICAST) return BPF_FIB_LKUP_RET_NOT_FWDED; - if (res.fi->fib_nhs > 1) + if (fib_info_num_path(res.fi) > 1) fib_select_path(net, &res, &fl4, NULL); if (check_mtu) { diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index edd622956083..c0559af9e5e5 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -757,7 +757,7 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, * @nhoff: network header offset, if @data is NULL use skb_network_offset(skb) * @hlen: packet header length, if @data is NULL use skb_headlen(skb) * @flags: flags that control the dissection process, e.g. - * FLOW_DISSECTOR_F_STOP_AT_L3. + * FLOW_DISSECTOR_F_STOP_AT_ENCAP. * * The function will try to retrieve individual keys into target specified * by flow_dissector from either the skbuff or a raw buffer specified by the @@ -922,11 +922,6 @@ proto_again: __skb_flow_dissect_ipv4(skb, flow_dissector, target_container, data, iph); - if (flags & FLOW_DISSECTOR_F_STOP_AT_L3) { - fdret = FLOW_DISSECT_RET_OUT_GOOD; - break; - } - break; } case htons(ETH_P_IPV6): { @@ -975,9 +970,6 @@ proto_again: __skb_flow_dissect_ipv6(skb, flow_dissector, target_container, data, iph); - if (flags & FLOW_DISSECTOR_F_STOP_AT_L3) - fdret = FLOW_DISSECT_RET_OUT_GOOD; - break; } case htons(ETH_P_8021AD): diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index 5ce7d47a960e..3d93e51b83e0 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -7,8 +7,7 @@ struct flow_rule *flow_rule_alloc(unsigned int num_actions) { struct flow_rule *rule; - rule = kzalloc(sizeof(struct flow_rule) + - sizeof(struct flow_action_entry) * num_actions, + rule = kzalloc(struct_size(rule, action.entries, num_actions), GFP_KERNEL); if (!rule) return NULL; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 0e2c07355463..a4a6cf808792 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -583,6 +583,8 @@ static struct neighbour *___neigh_create(struct neigh_table *tbl, int error; struct neigh_hash_table *nht; + trace_neigh_create(tbl, dev, pkey, n, exempt_from_gc); + if (!n) { rc = ERR_PTR(-ENOBUFS); goto out; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index dd8b1a460d64..2cf27da1baeb 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -696,16 +696,22 @@ int netpoll_setup(struct netpoll *np) if (!np->local_ip.ip) { if (!np->ipv6) { + const struct in_ifaddr *ifa; + in_dev = __in_dev_get_rtnl(ndev); + if (!in_dev) + goto put_noaddr; - if (!in_dev || !in_dev->ifa_list) { + ifa = rtnl_dereference(in_dev->ifa_list); + if (!ifa) { +put_noaddr: np_err(np, "no IP address for %s, aborting\n", np->dev_name); err = -EDESTADDRREQ; goto put; } - np->local_ip.ip = in_dev->ifa_list->ifa_local; + np->local_ip.ip = ifa->ifa_local; np_info(np, "local IP %pI4\n", &np->local_ip.ip); } else { #if IS_ENABLED(CONFIG_IPV6) diff --git a/net/core/pktgen.c b/net/core/pktgen.c index f975c5e2a369..bb9915291644 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2118,9 +2118,11 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) rcu_read_lock(); in_dev = __in_dev_get_rcu(pkt_dev->odev); if (in_dev) { - if (in_dev->ifa_list) { - pkt_dev->saddr_min = - in_dev->ifa_list->ifa_address; + const struct in_ifaddr *ifa; + + ifa = rcu_dereference(in_dev->ifa_list); + if (ifa) { + pkt_dev->saddr_min = ifa->ifa_address; pkt_dev->saddr_max = pkt_dev->saddr_min; } } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 47c1aa9ee045..23c9bf8fc322 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -72,6 +72,7 @@ #include <linux/highmem.h> #include <linux/capability.h> #include <linux/user_namespace.h> +#include <linux/indirect_call_wrapper.h> #include "datagram.h" @@ -909,6 +910,31 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) } /** + * alloc_skb_for_msg() - allocate sk_buff to wrap frag list forming a msg + * @first: first sk_buff of the msg + */ +struct sk_buff *alloc_skb_for_msg(struct sk_buff *first) +{ + struct sk_buff *n; + + n = alloc_skb(0, GFP_ATOMIC); + if (!n) + return NULL; + + n->len = first->len; + n->data_len = first->len; + n->truesize = first->truesize; + + skb_shinfo(n)->frag_list = first; + + __copy_skb_header(n, first); + n->destructor = NULL; + + return n; +} +EXPORT_SYMBOL_GPL(alloc_skb_for_msg); + +/** * skb_morph - morph one skb into another * @dst: the skb to receive the contents * @src: the skb to supply the contents @@ -2507,7 +2533,8 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, if (copy > 0) { if (copy > len) copy = len; - csum = ops->update(skb->data + offset, copy, csum); + csum = INDIRECT_CALL_1(ops->update, csum_partial_ext, + skb->data + offset, copy, csum); if ((len -= copy) == 0) return csum; offset += copy; @@ -2534,9 +2561,13 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, frag->page_offset + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_atomic(p); - csum2 = ops->update(vaddr + p_off, p_len, 0); + csum2 = INDIRECT_CALL_1(ops->update, + csum_partial_ext, + vaddr + p_off, p_len, 0); kunmap_atomic(vaddr); - csum = ops->combine(csum, csum2, pos, p_len); + csum = INDIRECT_CALL_1(ops->combine, + csum_block_add_ext, csum, + csum2, pos, p_len); pos += p_len; } @@ -2559,7 +2590,8 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, copy = len; csum2 = __skb_checksum(frag_iter, offset - start, copy, 0, ops); - csum = ops->combine(csum, csum2, pos, copy); + csum = INDIRECT_CALL_1(ops->combine, csum_block_add_ext, + csum, csum2, pos, copy); if ((len -= copy) == 0) return csum; offset += copy; diff --git a/net/core/sock_map.c b/net/core/sock_map.c index be6092ac69f8..52d4faeee18b 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -44,13 +44,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) /* Make sure page count doesn't overflow. */ cost = (u64) stab->map.max_entries * sizeof(struct sock *); - if (cost >= U32_MAX - PAGE_SIZE) { - err = -EINVAL; - goto free_stab; - } - - stab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; - err = bpf_map_precharge_memlock(stab->map.pages); + err = bpf_map_charge_init(&stab->map.memory, cost); if (err) goto free_stab; @@ -60,6 +54,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) if (stab->sks) return &stab->map; err = -ENOMEM; + bpf_map_charge_finish(&stab->map.memory); free_stab: kfree(stab); return ERR_PTR(err); diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 820dd8da57fc..38d11c863b57 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -257,7 +257,7 @@ static int dsa_port_setup(struct dsa_port *dp) enum devlink_port_flavour flavour; struct dsa_switch *ds = dp->ds; struct dsa_switch_tree *dst = ds->dst; - int err; + int err = 0; if (dp->type == DSA_PORT_TYPE_UNUSED) return 0; @@ -295,19 +295,15 @@ static int dsa_port_setup(struct dsa_port *dp) break; case DSA_PORT_TYPE_CPU: err = dsa_port_link_register_of(dp); - if (err) { + if (err) dev_err(ds->dev, "failed to setup link for port %d.%d\n", ds->index, dp->index); - return err; - } break; case DSA_PORT_TYPE_DSA: err = dsa_port_link_register_of(dp); - if (err) { + if (err) dev_err(ds->dev, "failed to setup link for port %d.%d\n", ds->index, dp->index); - return err; - } break; case DSA_PORT_TYPE_USER: err = dsa_slave_create(dp); @@ -319,7 +315,10 @@ static int dsa_port_setup(struct dsa_port *dp) break; } - return 0; + if (err) + devlink_port_unregister(&dp->devlink_port); + + return err; } static void dsa_port_teardown(struct dsa_port *dp) @@ -347,7 +346,7 @@ static void dsa_port_teardown(struct dsa_port *dp) static int dsa_switch_setup(struct dsa_switch *ds) { - int err; + int err = 0; /* Initialize ds->phys_mii_mask before registering the slave MDIO bus * driver and before ops->setup() has run, since the switch drivers and @@ -365,29 +364,41 @@ static int dsa_switch_setup(struct dsa_switch *ds) err = devlink_register(ds->devlink, ds->dev); if (err) - return err; + goto free_devlink; err = dsa_switch_register_notifier(ds); if (err) - return err; + goto unregister_devlink; err = ds->ops->setup(ds); if (err < 0) - return err; + goto unregister_notifier; if (!ds->slave_mii_bus && ds->ops->phy_read) { ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev); - if (!ds->slave_mii_bus) - return -ENOMEM; + if (!ds->slave_mii_bus) { + err = -ENOMEM; + goto unregister_notifier; + } dsa_slave_mii_bus_init(ds); err = mdiobus_register(ds->slave_mii_bus); if (err < 0) - return err; + goto unregister_notifier; } return 0; + +unregister_notifier: + dsa_switch_unregister_notifier(ds); +unregister_devlink: + devlink_unregister(ds->devlink); +free_devlink: + devlink_free(ds->devlink); + ds->devlink = NULL; + + return err; } static void dsa_switch_teardown(struct dsa_switch *ds) @@ -409,8 +420,8 @@ static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) { struct dsa_switch *ds; struct dsa_port *dp; - int device, port; - int err; + int device, port, i; + int err = 0; for (device = 0; device < DSA_MAX_SWITCHES; device++) { ds = dst->ds[device]; @@ -419,18 +430,41 @@ static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) err = dsa_switch_setup(ds); if (err) - return err; + goto switch_teardown; for (port = 0; port < ds->num_ports; port++) { dp = &ds->ports[port]; err = dsa_port_setup(dp); if (err) - return err; + goto ports_teardown; } } return 0; + +ports_teardown: + for (i = 0; i < port; i++) + dsa_port_teardown(&ds->ports[i]); + + dsa_switch_teardown(ds); + +switch_teardown: + for (i = 0; i < device; i++) { + ds = dst->ds[i]; + if (!ds) + continue; + + for (port = 0; port < ds->num_ports; port++) { + dp = &ds->ports[port]; + + dsa_port_teardown(dp); + } + + dsa_switch_teardown(ds); + } + + return err; } static void dsa_tree_teardown_switches(struct dsa_switch_tree *dst) @@ -492,17 +526,24 @@ static int dsa_tree_setup(struct dsa_switch_tree *dst) err = dsa_tree_setup_switches(dst); if (err) - return err; + goto teardown_default_cpu; err = dsa_tree_setup_master(dst); if (err) - return err; + goto teardown_switches; dst->setup = true; pr_info("DSA: tree %d setup\n", dst->index); return 0; + +teardown_switches: + dsa_tree_teardown_switches(dst); +teardown_default_cpu: + dsa_tree_teardown_default_cpu(dst); + + return err; } static void dsa_tree_teardown(struct dsa_switch_tree *dst) @@ -543,8 +584,10 @@ static int dsa_tree_add_switch(struct dsa_switch_tree *dst, dst->ds[index] = ds; err = dsa_tree_setup(dst); - if (err) - dsa_tree_remove_switch(dst, index); + if (err) { + dst->ds[index] = NULL; + dsa_tree_put(dst); + } return err; } diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 3986cedfafc0..b2be53a13aa0 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -159,6 +159,23 @@ int dsa_port_vid_add(struct dsa_port *dp, u16 vid, u16 flags); int dsa_port_vid_del(struct dsa_port *dp, u16 vid); int dsa_port_link_register_of(struct dsa_port *dp); void dsa_port_link_unregister_of(struct dsa_port *dp); +void dsa_port_phylink_validate(struct phylink_config *config, + unsigned long *supported, + struct phylink_link_state *state); +int dsa_port_phylink_mac_link_state(struct phylink_config *config, + struct phylink_link_state *state); +void dsa_port_phylink_mac_config(struct phylink_config *config, + unsigned int mode, + const struct phylink_link_state *state); +void dsa_port_phylink_mac_an_restart(struct phylink_config *config); +void dsa_port_phylink_mac_link_down(struct phylink_config *config, + unsigned int mode, + phy_interface_t interface); +void dsa_port_phylink_mac_link_up(struct phylink_config *config, + unsigned int mode, + phy_interface_t interface, + struct phy_device *phydev); +extern const struct phylink_mac_ops dsa_port_phylink_mac_ops; /* slave.c */ extern const struct dsa_device_ops notag_netdev_ops; diff --git a/net/dsa/port.c b/net/dsa/port.c index 363eab6df51b..70744fec9717 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -418,6 +418,108 @@ static struct phy_device *dsa_port_get_phy_device(struct dsa_port *dp) return phydev; } +void dsa_port_phylink_validate(struct phylink_config *config, + unsigned long *supported, + struct phylink_link_state *state) +{ + struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); + struct dsa_switch *ds = dp->ds; + + if (!ds->ops->phylink_validate) + return; + + ds->ops->phylink_validate(ds, dp->index, supported, state); +} +EXPORT_SYMBOL_GPL(dsa_port_phylink_validate); + +int dsa_port_phylink_mac_link_state(struct phylink_config *config, + struct phylink_link_state *state) +{ + struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); + struct dsa_switch *ds = dp->ds; + + /* Only called for SGMII and 802.3z */ + if (!ds->ops->phylink_mac_link_state) + return -EOPNOTSUPP; + + return ds->ops->phylink_mac_link_state(ds, dp->index, state); +} +EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_link_state); + +void dsa_port_phylink_mac_config(struct phylink_config *config, + unsigned int mode, + const struct phylink_link_state *state) +{ + struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); + struct dsa_switch *ds = dp->ds; + + if (!ds->ops->phylink_mac_config) + return; + + ds->ops->phylink_mac_config(ds, dp->index, mode, state); +} +EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_config); + +void dsa_port_phylink_mac_an_restart(struct phylink_config *config) +{ + struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); + struct dsa_switch *ds = dp->ds; + + if (!ds->ops->phylink_mac_an_restart) + return; + + ds->ops->phylink_mac_an_restart(ds, dp->index); +} +EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_an_restart); + +void dsa_port_phylink_mac_link_down(struct phylink_config *config, + unsigned int mode, + phy_interface_t interface) +{ + struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); + struct phy_device *phydev = NULL; + struct dsa_switch *ds = dp->ds; + + if (dsa_is_user_port(ds, dp->index)) + phydev = dp->slave->phydev; + + if (!ds->ops->phylink_mac_link_down) { + if (ds->ops->adjust_link && phydev) + ds->ops->adjust_link(ds, dp->index, phydev); + return; + } + + ds->ops->phylink_mac_link_down(ds, dp->index, mode, interface); +} +EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_link_down); + +void dsa_port_phylink_mac_link_up(struct phylink_config *config, + unsigned int mode, + phy_interface_t interface, + struct phy_device *phydev) +{ + struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); + struct dsa_switch *ds = dp->ds; + + if (!ds->ops->phylink_mac_link_up) { + if (ds->ops->adjust_link && phydev) + ds->ops->adjust_link(ds, dp->index, phydev); + return; + } + + ds->ops->phylink_mac_link_up(ds, dp->index, mode, interface, phydev); +} +EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_link_up); + +const struct phylink_mac_ops dsa_port_phylink_mac_ops = { + .validate = dsa_port_phylink_validate, + .mac_link_state = dsa_port_phylink_mac_link_state, + .mac_config = dsa_port_phylink_mac_config, + .mac_an_restart = dsa_port_phylink_mac_an_restart, + .mac_link_down = dsa_port_phylink_mac_link_down, + .mac_link_up = dsa_port_phylink_mac_link_up, +}; + static int dsa_port_setup_phy_of(struct dsa_port *dp, bool enable) { struct dsa_switch *ds = dp->ds; @@ -495,8 +597,53 @@ static int dsa_port_fixed_link_register_of(struct dsa_port *dp) return 0; } +static int dsa_port_phylink_register(struct dsa_port *dp) +{ + struct dsa_switch *ds = dp->ds; + struct device_node *port_dn = dp->dn; + int mode, err; + + mode = of_get_phy_mode(port_dn); + if (mode < 0) + mode = PHY_INTERFACE_MODE_NA; + + dp->pl_config.dev = ds->dev; + dp->pl_config.type = PHYLINK_DEV; + + dp->pl = phylink_create(&dp->pl_config, of_fwnode_handle(port_dn), + mode, &dsa_port_phylink_mac_ops); + if (IS_ERR(dp->pl)) { + pr_err("error creating PHYLINK: %ld\n", PTR_ERR(dp->pl)); + return PTR_ERR(dp->pl); + } + + err = phylink_of_phy_connect(dp->pl, port_dn, 0); + if (err) { + pr_err("could not attach to PHY: %d\n", err); + goto err_phy_connect; + } + + rtnl_lock(); + phylink_start(dp->pl); + rtnl_unlock(); + + return 0; + +err_phy_connect: + phylink_destroy(dp->pl); + return err; +} + int dsa_port_link_register_of(struct dsa_port *dp) { + struct dsa_switch *ds = dp->ds; + + if (!ds->ops->adjust_link) + return dsa_port_phylink_register(dp); + + dev_warn(ds->dev, + "Using legacy PHYLIB callbacks. Please migrate to PHYLINK!\n"); + if (of_phy_is_fixed_link(dp->dn)) return dsa_port_fixed_link_register_of(dp); else @@ -505,6 +652,16 @@ int dsa_port_link_register_of(struct dsa_port *dp) void dsa_port_link_unregister_of(struct dsa_port *dp) { + struct dsa_switch *ds = dp->ds; + + if (!ds->ops->adjust_link) { + rtnl_lock(); + phylink_disconnect_phy(dp->pl); + rtnl_unlock(); + phylink_destroy(dp->pl); + return; + } + if (of_phy_is_fixed_link(dp->dn)) of_phy_deregister_fixed_link(dp->dn); else diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 8157be7e162d..5bab82d46f0c 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1160,98 +1160,6 @@ static struct device_type dsa_type = { .name = "dsa", }; -static void dsa_slave_phylink_validate(struct net_device *dev, - unsigned long *supported, - struct phylink_link_state *state) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - - if (!ds->ops->phylink_validate) - return; - - ds->ops->phylink_validate(ds, dp->index, supported, state); -} - -static int dsa_slave_phylink_mac_link_state(struct net_device *dev, - struct phylink_link_state *state) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - - /* Only called for SGMII and 802.3z */ - if (!ds->ops->phylink_mac_link_state) - return -EOPNOTSUPP; - - return ds->ops->phylink_mac_link_state(ds, dp->index, state); -} - -static void dsa_slave_phylink_mac_config(struct net_device *dev, - unsigned int mode, - const struct phylink_link_state *state) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - - if (!ds->ops->phylink_mac_config) - return; - - ds->ops->phylink_mac_config(ds, dp->index, mode, state); -} - -static void dsa_slave_phylink_mac_an_restart(struct net_device *dev) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - - if (!ds->ops->phylink_mac_an_restart) - return; - - ds->ops->phylink_mac_an_restart(ds, dp->index); -} - -static void dsa_slave_phylink_mac_link_down(struct net_device *dev, - unsigned int mode, - phy_interface_t interface) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - - if (!ds->ops->phylink_mac_link_down) { - if (ds->ops->adjust_link && dev->phydev) - ds->ops->adjust_link(ds, dp->index, dev->phydev); - return; - } - - ds->ops->phylink_mac_link_down(ds, dp->index, mode, interface); -} - -static void dsa_slave_phylink_mac_link_up(struct net_device *dev, - unsigned int mode, - phy_interface_t interface, - struct phy_device *phydev) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - - if (!ds->ops->phylink_mac_link_up) { - if (ds->ops->adjust_link && dev->phydev) - ds->ops->adjust_link(ds, dp->index, dev->phydev); - return; - } - - ds->ops->phylink_mac_link_up(ds, dp->index, mode, interface, phydev); -} - -static const struct phylink_mac_ops dsa_slave_phylink_mac_ops = { - .validate = dsa_slave_phylink_validate, - .mac_link_state = dsa_slave_phylink_mac_link_state, - .mac_config = dsa_slave_phylink_mac_config, - .mac_an_restart = dsa_slave_phylink_mac_an_restart, - .mac_link_down = dsa_slave_phylink_mac_link_down, - .mac_link_up = dsa_slave_phylink_mac_link_up, -}; - void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up) { const struct dsa_port *dp = dsa_to_port(ds, port); @@ -1299,8 +1207,11 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) if (mode < 0) mode = PHY_INTERFACE_MODE_NA; - dp->pl = phylink_create(slave_dev, of_fwnode_handle(port_dn), mode, - &dsa_slave_phylink_mac_ops); + dp->pl_config.dev = &slave_dev->dev; + dp->pl_config.type = PHYLINK_NETDEV; + + dp->pl = phylink_create(&dp->pl_config, of_fwnode_handle(port_dn), mode, + &dsa_port_phylink_mac_ops); if (IS_ERR(dp->pl)) { netdev_err(slave_dev, "error creating PHYLINK: %ld\n", PTR_ERR(dp->pl)); diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 20b0bcb7e9e3..17374afee28f 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -545,17 +545,10 @@ unsigned char * __weak arch_get_platform_mac_address(void) int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr) { - const unsigned char *addr; - struct device_node *dp; + const unsigned char *addr = NULL; - if (dev_is_pci(dev)) - dp = pci_device_to_OF_node(to_pci_dev(dev)); - else - dp = dev->of_node; - - addr = NULL; - if (dp) - addr = of_get_mac_address(dp); + if (dev->of_node) + addr = of_get_mac_address(dev->of_node); if (IS_ERR_OR_NULL(addr)) addr = arch_get_platform_mac_address(); @@ -563,6 +556,7 @@ int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr) return -ENODEV; ether_addr_copy(mac_addr, addr); + return 0; } EXPORT_SYMBOL(eth_platform_get_mac_address); diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index 9133e3cede77..a0ed13cd120e 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -74,7 +74,7 @@ fq_find(struct net *net, const struct lowpan_802154_cb *cb, key.src = *src; key.dst = *dst; - q = inet_frag_find(&ieee802154_lowpan->frags, &key); + q = inet_frag_find(ieee802154_lowpan->fqdir, &key); if (!q) return NULL; @@ -134,7 +134,7 @@ static int lowpan_frag_queue(struct lowpan_frag_queue *fq, fq->q.flags |= INET_FRAG_FIRST_IN; fq->q.meat += skb->len; - add_frag_mem_limit(fq->q.net, skb->truesize); + add_frag_mem_limit(fq->q.fqdir, skb->truesize); if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { @@ -321,23 +321,18 @@ err: static struct ctl_table lowpan_frags_ns_ctl_table[] = { { .procname = "6lowpanfrag_high_thresh", - .data = &init_net.ieee802154_lowpan.frags.high_thresh, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, - .extra1 = &init_net.ieee802154_lowpan.frags.low_thresh }, { .procname = "6lowpanfrag_low_thresh", - .data = &init_net.ieee802154_lowpan.frags.low_thresh, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, - .extra2 = &init_net.ieee802154_lowpan.frags.high_thresh }, { .procname = "6lowpanfrag_time", - .data = &init_net.ieee802154_lowpan.frags.timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -372,17 +367,17 @@ static int __net_init lowpan_frags_ns_sysctl_register(struct net *net) if (table == NULL) goto err_alloc; - table[0].data = &ieee802154_lowpan->frags.high_thresh; - table[0].extra1 = &ieee802154_lowpan->frags.low_thresh; - table[1].data = &ieee802154_lowpan->frags.low_thresh; - table[1].extra2 = &ieee802154_lowpan->frags.high_thresh; - table[2].data = &ieee802154_lowpan->frags.timeout; - /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) table[0].procname = NULL; } + table[0].data = &ieee802154_lowpan->fqdir->high_thresh; + table[0].extra1 = &ieee802154_lowpan->fqdir->low_thresh; + table[1].data = &ieee802154_lowpan->fqdir->low_thresh; + table[1].extra2 = &ieee802154_lowpan->fqdir->high_thresh; + table[2].data = &ieee802154_lowpan->fqdir->timeout; + hdr = register_net_sysctl(net, "net/ieee802154/6lowpan", table); if (hdr == NULL) goto err_reg; @@ -449,17 +444,18 @@ static int __net_init lowpan_frags_init_net(struct net *net) net_ieee802154_lowpan(net); int res; - ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH; - ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH; - ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT; - ieee802154_lowpan->frags.f = &lowpan_frags; - res = inet_frags_init_net(&ieee802154_lowpan->frags); + res = fqdir_init(&ieee802154_lowpan->fqdir, &lowpan_frags, net); if (res < 0) return res; + + ieee802154_lowpan->fqdir->high_thresh = IPV6_FRAG_HIGH_THRESH; + ieee802154_lowpan->fqdir->low_thresh = IPV6_FRAG_LOW_THRESH; + ieee802154_lowpan->fqdir->timeout = IPV6_FRAG_TIMEOUT; + res = lowpan_frags_ns_sysctl_register(net); if (res < 0) - inet_frags_exit_net(&ieee802154_lowpan->frags); + fqdir_exit(ieee802154_lowpan->fqdir); return res; } @@ -469,7 +465,7 @@ static void __net_exit lowpan_frags_exit_net(struct net *net) net_ieee802154_lowpan(net); lowpan_frags_ns_sysctl_unregister(net); - inet_frags_exit_net(&ieee802154_lowpan->frags); + fqdir_exit(ieee802154_lowpan->fqdir); } static struct pernet_operations lowpan_frags_ops = { @@ -539,7 +535,7 @@ err_sysctl: void lowpan_net_frag_exit(void) { - inet_frags_fini(&lowpan_frags); lowpan_frags_sysctl_unregister(); unregister_pernet_subsys(&lowpan_frags_ops); + inet_frags_fini(&lowpan_frags); } diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 000a61994c8f..d57ecfaf89d4 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -14,7 +14,7 @@ obj-y := route.o inetpeer.o protocol.o \ udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \ fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \ inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o \ - metrics.o netlink.o + metrics.o netlink.o nexthop.o obj-$(CONFIG_BPFILTER) += bpfilter/ diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index c6bd0f7a020a..925dffa915cb 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -190,7 +190,8 @@ static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32); static BLOCKING_NOTIFIER_HEAD(inetaddr_chain); static BLOCKING_NOTIFIER_HEAD(inetaddr_validator_chain); -static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, +static void inet_del_ifa(struct in_device *in_dev, + struct in_ifaddr __rcu **ifap, int destroy); #ifdef CONFIG_SYSCTL static int devinet_sysctl_register(struct in_device *idev); @@ -296,8 +297,8 @@ static void in_dev_rcu_put(struct rcu_head *head) static void inetdev_destroy(struct in_device *in_dev) { - struct in_ifaddr *ifa; struct net_device *dev; + struct in_ifaddr *ifa; ASSERT_RTNL(); @@ -307,7 +308,7 @@ static void inetdev_destroy(struct in_device *in_dev) ip_mc_destroy_dev(in_dev); - while ((ifa = in_dev->ifa_list) != NULL) { + while ((ifa = rtnl_dereference(in_dev->ifa_list)) != NULL) { inet_del_ifa(in_dev, &in_dev->ifa_list, 0); inet_free_ifa(ifa); } @@ -323,30 +324,35 @@ static void inetdev_destroy(struct in_device *in_dev) int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b) { + const struct in_ifaddr *ifa; + rcu_read_lock(); - for_primary_ifa(in_dev) { + in_dev_for_each_ifa_rcu(ifa, in_dev) { if (inet_ifa_match(a, ifa)) { if (!b || inet_ifa_match(b, ifa)) { rcu_read_unlock(); return 1; } } - } endfor_ifa(in_dev); + } rcu_read_unlock(); return 0; } -static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, - int destroy, struct nlmsghdr *nlh, u32 portid) +static void __inet_del_ifa(struct in_device *in_dev, + struct in_ifaddr __rcu **ifap, + int destroy, struct nlmsghdr *nlh, u32 portid) { struct in_ifaddr *promote = NULL; - struct in_ifaddr *ifa, *ifa1 = *ifap; - struct in_ifaddr *last_prim = in_dev->ifa_list; + struct in_ifaddr *ifa, *ifa1; + struct in_ifaddr *last_prim; struct in_ifaddr *prev_prom = NULL; int do_promote = IN_DEV_PROMOTE_SECONDARIES(in_dev); ASSERT_RTNL(); + ifa1 = rtnl_dereference(*ifap); + last_prim = rtnl_dereference(in_dev->ifa_list); if (in_dev->dead) goto no_promotions; @@ -355,9 +361,9 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, **/ if (!(ifa1->ifa_flags & IFA_F_SECONDARY)) { - struct in_ifaddr **ifap1 = &ifa1->ifa_next; + struct in_ifaddr __rcu **ifap1 = &ifa1->ifa_next; - while ((ifa = *ifap1) != NULL) { + while ((ifa = rtnl_dereference(*ifap1)) != NULL) { if (!(ifa->ifa_flags & IFA_F_SECONDARY) && ifa1->ifa_scope <= ifa->ifa_scope) last_prim = ifa; @@ -390,7 +396,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, * and later to add them back with new prefsrc. Do this * while all addresses are on the device list. */ - for (ifa = promote; ifa; ifa = ifa->ifa_next) { + for (ifa = promote; ifa; ifa = rtnl_dereference(ifa->ifa_next)) { if (ifa1->ifa_mask == ifa->ifa_mask && inet_ifa_match(ifa1->ifa_address, ifa)) fib_del_ifaddr(ifa, ifa1); @@ -416,19 +422,24 @@ no_promotions: blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa1); if (promote) { - struct in_ifaddr *next_sec = promote->ifa_next; + struct in_ifaddr *next_sec; + next_sec = rtnl_dereference(promote->ifa_next); if (prev_prom) { - prev_prom->ifa_next = promote->ifa_next; - promote->ifa_next = last_prim->ifa_next; - last_prim->ifa_next = promote; + struct in_ifaddr *last_sec; + + last_sec = rtnl_dereference(last_prim->ifa_next); + rcu_assign_pointer(prev_prom->ifa_next, next_sec); + rcu_assign_pointer(promote->ifa_next, last_sec); + rcu_assign_pointer(last_prim->ifa_next, promote); } promote->ifa_flags &= ~IFA_F_SECONDARY; rtmsg_ifa(RTM_NEWADDR, promote, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, promote); - for (ifa = next_sec; ifa; ifa = ifa->ifa_next) { + for (ifa = next_sec; ifa; + ifa = rtnl_dereference(ifa->ifa_next)) { if (ifa1->ifa_mask != ifa->ifa_mask || !inet_ifa_match(ifa1->ifa_address, ifa)) continue; @@ -440,7 +451,8 @@ no_promotions: inet_free_ifa(ifa1); } -static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, +static void inet_del_ifa(struct in_device *in_dev, + struct in_ifaddr __rcu **ifap, int destroy) { __inet_del_ifa(in_dev, ifap, destroy, NULL, 0); @@ -453,9 +465,10 @@ static DECLARE_DELAYED_WORK(check_lifetime_work, check_lifetime); static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 portid, struct netlink_ext_ack *extack) { + struct in_ifaddr __rcu **last_primary, **ifap; struct in_device *in_dev = ifa->ifa_dev; - struct in_ifaddr *ifa1, **ifap, **last_primary; struct in_validator_info ivi; + struct in_ifaddr *ifa1; int ret; ASSERT_RTNL(); @@ -468,8 +481,10 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, ifa->ifa_flags &= ~IFA_F_SECONDARY; last_primary = &in_dev->ifa_list; - for (ifap = &in_dev->ifa_list; (ifa1 = *ifap) != NULL; - ifap = &ifa1->ifa_next) { + ifap = &in_dev->ifa_list; + ifa1 = rtnl_dereference(*ifap); + + while (ifa1) { if (!(ifa1->ifa_flags & IFA_F_SECONDARY) && ifa->ifa_scope <= ifa1->ifa_scope) last_primary = &ifa1->ifa_next; @@ -485,6 +500,9 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, } ifa->ifa_flags |= IFA_F_SECONDARY; } + + ifap = &ifa1->ifa_next; + ifa1 = rtnl_dereference(*ifap); } /* Allow any devices that wish to register ifaddr validtors to weigh @@ -510,8 +528,8 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, ifap = last_primary; } - ifa->ifa_next = *ifap; - *ifap = ifa; + rcu_assign_pointer(ifa->ifa_next, *ifap); + rcu_assign_pointer(*ifap, ifa); inet_hash_insert(dev_net(in_dev->dev), ifa); @@ -576,12 +594,14 @@ EXPORT_SYMBOL(inetdev_by_index); struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask) { + struct in_ifaddr *ifa; + ASSERT_RTNL(); - for_primary_ifa(in_dev) { + in_dev_for_each_ifa_rtnl(ifa, in_dev) { if (ifa->ifa_mask == mask && inet_ifa_match(prefix, ifa)) return ifa; - } endfor_ifa(in_dev); + } return NULL; } @@ -609,10 +629,12 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); + struct in_ifaddr __rcu **ifap; struct nlattr *tb[IFA_MAX+1]; struct in_device *in_dev; struct ifaddrmsg *ifm; - struct in_ifaddr *ifa, **ifap; + struct in_ifaddr *ifa; + int err = -EINVAL; ASSERT_RTNL(); @@ -629,7 +651,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, goto errout; } - for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL; + for (ifap = &in_dev->ifa_list; (ifa = rtnl_dereference(*ifap)) != NULL; ifap = &ifa->ifa_next) { if (tb[IFA_LOCAL] && ifa->ifa_local != nla_get_in_addr(tb[IFA_LOCAL])) @@ -717,15 +739,20 @@ static void check_lifetime(struct work_struct *work) if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && age >= ifa->ifa_valid_lft) { - struct in_ifaddr **ifap; - - for (ifap = &ifa->ifa_dev->ifa_list; - *ifap != NULL; ifap = &(*ifap)->ifa_next) { - if (*ifap == ifa) { + struct in_ifaddr __rcu **ifap; + struct in_ifaddr *tmp; + + ifap = &ifa->ifa_dev->ifa_list; + tmp = rtnl_dereference(*ifap); + while (tmp) { + tmp = rtnl_dereference(tmp->ifa_next); + if (rtnl_dereference(*ifap) == ifa) { inet_del_ifa(ifa->ifa_dev, ifap, 1); break; } + ifap = &tmp->ifa_next; + tmp = rtnl_dereference(*ifap); } } else if (ifa->ifa_preferred_lft != INFINITY_LIFE_TIME && @@ -869,13 +896,12 @@ errout: static struct in_ifaddr *find_matching_ifa(struct in_ifaddr *ifa) { struct in_device *in_dev = ifa->ifa_dev; - struct in_ifaddr *ifa1, **ifap; + struct in_ifaddr *ifa1; if (!ifa->ifa_local) return NULL; - for (ifap = &in_dev->ifa_list; (ifa1 = *ifap) != NULL; - ifap = &ifa1->ifa_next) { + in_dev_for_each_ifa_rtnl(ifa1, in_dev) { if (ifa1->ifa_mask == ifa->ifa_mask && inet_ifa_match(ifa1->ifa_address, ifa) && ifa1->ifa_local == ifa->ifa_local) @@ -970,8 +996,8 @@ int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr) { struct sockaddr_in sin_orig; struct sockaddr_in *sin = (struct sockaddr_in *)&ifr->ifr_addr; + struct in_ifaddr __rcu **ifap = NULL; struct in_device *in_dev; - struct in_ifaddr **ifap = NULL; struct in_ifaddr *ifa = NULL; struct net_device *dev; char *colon; @@ -1042,7 +1068,9 @@ int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr) /* note: we only do this for a limited set of ioctls and only if the original address family was AF_INET. This is checked above. */ - for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL; + + for (ifap = &in_dev->ifa_list; + (ifa = rtnl_dereference(*ifap)) != NULL; ifap = &ifa->ifa_next) { if (!strcmp(ifr->ifr_name, ifa->ifa_label) && sin_orig.sin_addr.s_addr == @@ -1055,7 +1083,8 @@ int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr) 4.3BSD-style and passed in junk so we fall back to comparing just the label */ if (!ifa) { - for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL; + for (ifap = &in_dev->ifa_list; + (ifa = rtnl_dereference(*ifap)) != NULL; ifap = &ifa->ifa_next) if (!strcmp(ifr->ifr_name, ifa->ifa_label)) break; @@ -1204,7 +1233,7 @@ out: static int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) { struct in_device *in_dev = __in_dev_get_rtnl(dev); - struct in_ifaddr *ifa; + const struct in_ifaddr *ifa; struct ifreq ifr; int done = 0; @@ -1214,7 +1243,7 @@ static int inet_gifconf(struct net_device *dev, char __user *buf, int len, int s if (!in_dev) goto out; - for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) { + in_dev_for_each_ifa_rtnl(ifa, in_dev) { if (!buf) { done += size; continue; @@ -1242,17 +1271,22 @@ out: static __be32 in_dev_select_addr(const struct in_device *in_dev, int scope) { - for_primary_ifa(in_dev) { + const struct in_ifaddr *ifa; + + in_dev_for_each_ifa_rcu(ifa, in_dev) { + if (ifa->ifa_flags & IFA_F_SECONDARY) + continue; if (ifa->ifa_scope != RT_SCOPE_LINK && ifa->ifa_scope <= scope) return ifa->ifa_local; - } endfor_ifa(in_dev); + } return 0; } __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) { + const struct in_ifaddr *ifa; __be32 addr = 0; struct in_device *in_dev; struct net *net = dev_net(dev); @@ -1263,7 +1297,9 @@ __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) if (!in_dev) goto no_in_dev; - for_primary_ifa(in_dev) { + in_dev_for_each_ifa_rcu(ifa, in_dev) { + if (ifa->ifa_flags & IFA_F_SECONDARY) + continue; if (ifa->ifa_scope > scope) continue; if (!dst || inet_ifa_match(dst, ifa)) { @@ -1272,7 +1308,7 @@ __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) } if (!addr) addr = ifa->ifa_local; - } endfor_ifa(in_dev); + } if (addr) goto out_unlock; @@ -1317,10 +1353,11 @@ EXPORT_SYMBOL(inet_select_addr); static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst, __be32 local, int scope) { - int same = 0; + const struct in_ifaddr *ifa; __be32 addr = 0; + int same = 0; - for_ifa(in_dev) { + in_dev_for_each_ifa_rcu(ifa, in_dev) { if (!addr && (local == ifa->ifa_local || !local) && ifa->ifa_scope <= scope) { @@ -1346,7 +1383,7 @@ static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst, same = 0; } } - } endfor_ifa(in_dev); + } return same ? addr : 0; } @@ -1420,7 +1457,7 @@ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev) struct in_ifaddr *ifa; int named = 0; - for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) { + in_dev_for_each_ifa_rtnl(ifa, in_dev) { char old[IFNAMSIZ], *dot; memcpy(old, ifa->ifa_label, IFNAMSIZ); @@ -1450,10 +1487,9 @@ static void inetdev_send_gratuitous_arp(struct net_device *dev, struct in_device *in_dev) { - struct in_ifaddr *ifa; + const struct in_ifaddr *ifa; - for (ifa = in_dev->ifa_list; ifa; - ifa = ifa->ifa_next) { + in_dev_for_each_ifa_rtnl(ifa, in_dev) { arp_send(ARPOP_REQUEST, ETH_P_ARP, ifa->ifa_local, dev, ifa->ifa_local, NULL, @@ -1723,15 +1759,17 @@ static int in_dev_dump_addr(struct in_device *in_dev, struct sk_buff *skb, int ip_idx = 0; int err; - for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next, ip_idx++) { - if (ip_idx < s_ip_idx) + in_dev_for_each_ifa_rtnl(ifa, in_dev) { + if (ip_idx < s_ip_idx) { + ip_idx++; continue; - + } err = inet_fill_ifaddr(skb, ifa, fillargs); if (err < 0) goto done; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); + ip_idx++; } err = 0; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index e54c2bcbb465..33b0dbe84aa6 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -39,6 +39,7 @@ #include <net/sock.h> #include <net/arp.h> #include <net/ip_fib.h> +#include <net/nexthop.h> #include <net/rtnetlink.h> #include <net/xfrm.h> #include <net/l3mdev.h> @@ -188,7 +189,7 @@ int fib_unmerge(struct net *net) return 0; } -static void fib_flush(struct net *net) +void fib_flush(struct net *net) { int flushed = 0; unsigned int h; @@ -230,7 +231,9 @@ static inline unsigned int __inet_dev_addr_type(struct net *net, if (table) { ret = RTN_UNICAST; if (!fib_table_lookup(table, &fl4, &res, FIB_LOOKUP_NOREF)) { - if (!dev || dev == res.fi->fib_dev) + struct fib_nh_common *nhc = fib_info_nhc(res.fi, 0); + + if (!dev || dev == nhc->nhc_dev) ret = res.type; } } @@ -317,19 +320,19 @@ bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev) #ifdef CONFIG_IP_ROUTE_MULTIPATH int ret; - for (ret = 0; ret < fi->fib_nhs; ret++) { - struct fib_nh *nh = &fi->fib_nh[ret]; + for (ret = 0; ret < fib_info_num_path(fi); ret++) { + const struct fib_nh_common *nhc = fib_info_nhc(fi, ret); - if (nh->fib_nh_dev == dev) { + if (nhc->nhc_dev == dev) { dev_match = true; break; - } else if (l3mdev_master_ifindex_rcu(nh->fib_nh_dev) == dev->ifindex) { + } else if (l3mdev_master_ifindex_rcu(nhc->nhc_dev) == dev->ifindex) { dev_match = true; break; } } #else - if (fi->fib_nh[0].fib_nh_dev == dev) + if (fib_info_nhc(fi, 0)->nhc_dev == dev) dev_match = true; #endif @@ -536,14 +539,22 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, cfg->fc_oif = dev->ifindex; cfg->fc_table = l3mdev_fib_table(dev); if (colon) { - struct in_ifaddr *ifa; - struct in_device *in_dev = __in_dev_get_rtnl(dev); + const struct in_ifaddr *ifa; + struct in_device *in_dev; + + in_dev = __in_dev_get_rtnl(dev); if (!in_dev) return -ENODEV; + *colon = ':'; - for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) + + rcu_read_lock(); + in_dev_for_each_ifa_rcu(ifa, in_dev) { if (strcmp(ifa->ifa_label, devname) == 0) break; + } + rcu_read_unlock(); + if (!ifa) return -ENODEV; cfg->fc_prefsrc = ifa->ifa_local; @@ -641,6 +652,7 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, struct rtentry *rt) } const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = { + [RTA_UNSPEC] = { .strict_start_type = RTA_DPORT + 1 }, [RTA_DST] = { .type = NLA_U32 }, [RTA_SRC] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, @@ -1172,8 +1184,8 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) * * Scan address list to be sure that addresses are really gone. */ - - for (ifa1 = in_dev->ifa_list; ifa1; ifa1 = ifa1->ifa_next) { + rcu_read_lock(); + in_dev_for_each_ifa_rcu(ifa1, in_dev) { if (ifa1 == ifa) { /* promotion, keep the IP */ gone = 0; @@ -1241,6 +1253,7 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) } } } + rcu_read_unlock(); no_promotions: if (!(ok & BRD_OK)) @@ -1410,6 +1423,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo struct netdev_notifier_info_ext *info_ext = ptr; struct in_device *in_dev; struct net *net = dev_net(dev); + struct in_ifaddr *ifa; unsigned int flags; if (event == NETDEV_UNREGISTER) { @@ -1424,9 +1438,9 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo switch (event) { case NETDEV_UP: - for_ifa(in_dev) { + in_dev_for_each_ifa_rtnl(ifa, in_dev) { fib_add_ifaddr(ifa); - } endfor_ifa(in_dev); + } #ifdef CONFIG_IP_ROUTE_MULTIPATH fib_sync_up(dev, RTNH_F_DEAD); #endif diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index 7945f0534db7..a68b5e21ec51 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -5,6 +5,7 @@ #include <linux/types.h> #include <linux/list.h> #include <net/ip_fib.h> +#include <net/nexthop.h> struct fib_alias { struct hlist_node fa_list; diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index a38e86b98e4f..b43a7ba5c6a4 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -27,6 +27,7 @@ #include <net/route.h> #include <net/tcp.h> #include <net/ip_fib.h> +#include <net/nexthop.h> #include <net/fib_rules.h> struct fib4_rule { @@ -141,8 +142,11 @@ static bool fib4_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg struct fib_result *result = (struct fib_result *) arg->result; struct net_device *dev = NULL; - if (result->fi) - dev = result->fi->fib_dev; + if (result->fi) { + struct fib_nh_common *nhc = fib_info_nhc(result->fi, 0); + + dev = nhc->nhc_dev; + } /* do not accept result if the route does * not meet the required prefix length diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index b80410673915..afa4af1f9326 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -38,6 +38,7 @@ #include <net/sock.h> #include <net/ip_fib.h> #include <net/ip6_fib.h> +#include <net/nexthop.h> #include <net/netlink.h> #include <net/rtnh.h> #include <net/lwtunnel.h> @@ -56,18 +57,21 @@ static unsigned int fib_info_cnt; #define DEVINDEX_HASHSIZE (1U << DEVINDEX_HASHBITS) static struct hlist_head fib_info_devhash[DEVINDEX_HASHSIZE]; +/* for_nexthops and change_nexthops only used when nexthop object + * is not set in a fib_info. The logic within can reference fib_nh. + */ #ifdef CONFIG_IP_ROUTE_MULTIPATH #define for_nexthops(fi) { \ int nhsel; const struct fib_nh *nh; \ for (nhsel = 0, nh = (fi)->fib_nh; \ - nhsel < (fi)->fib_nhs; \ + nhsel < fib_info_num_path((fi)); \ nh++, nhsel++) #define change_nexthops(fi) { \ int nhsel; struct fib_nh *nexthop_nh; \ for (nhsel = 0, nexthop_nh = (struct fib_nh *)((fi)->fib_nh); \ - nhsel < (fi)->fib_nhs; \ + nhsel < fib_info_num_path((fi)); \ nexthop_nh++, nhsel++) #else /* CONFIG_IP_ROUTE_MULTIPATH */ @@ -228,9 +232,13 @@ static void free_fib_info_rcu(struct rcu_head *head) { struct fib_info *fi = container_of(head, struct fib_info, rcu); - change_nexthops(fi) { - fib_nh_release(fi->fib_net, nexthop_nh); - } endfor_nexthops(fi); + if (fi->nh) { + nexthop_put(fi->nh); + } else { + change_nexthops(fi) { + fib_nh_release(fi->fib_net, nexthop_nh); + } endfor_nexthops(fi); + } ip_fib_metrics_put(fi->fib_metrics); @@ -256,22 +264,34 @@ void fib_release_info(struct fib_info *fi) hlist_del(&fi->fib_hash); if (fi->fib_prefsrc) hlist_del(&fi->fib_lhash); - change_nexthops(fi) { - if (!nexthop_nh->fib_nh_dev) - continue; - hlist_del(&nexthop_nh->nh_hash); - } endfor_nexthops(fi) + if (fi->nh) { + list_del(&fi->nh_list); + } else { + change_nexthops(fi) { + if (!nexthop_nh->fib_nh_dev) + continue; + hlist_del(&nexthop_nh->nh_hash); + } endfor_nexthops(fi) + } fi->fib_dead = 1; fib_info_put(fi); } spin_unlock_bh(&fib_info_lock); } -static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi) +static inline int nh_comp(struct fib_info *fi, struct fib_info *ofi) { - const struct fib_nh *onh = ofi->fib_nh; + const struct fib_nh *onh; + + if (fi->nh || ofi->nh) + return nexthop_cmp(fi->nh, ofi->nh) ? 0 : -1; + + if (ofi->fib_nhs == 0) + return 0; for_nexthops(fi) { + onh = fib_info_nh(ofi, nhsel); + if (nh->fib_nh_oif != onh->fib_nh_oif || nh->fib_nh_gw_family != onh->fib_nh_gw_family || nh->fib_nh_scope != onh->fib_nh_scope || @@ -292,8 +312,6 @@ static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi) if (nh->fib_nh_gw_family == AF_INET6 && ipv6_addr_cmp(&nh->fib_nh_gw6, &onh->fib_nh_gw6)) return -1; - - onh++; } endfor_nexthops(fi); return 0; } @@ -315,14 +333,19 @@ static inline unsigned int fib_info_hashfn(const struct fib_info *fi) val ^= (fi->fib_protocol << 8) | fi->fib_scope; val ^= (__force u32)fi->fib_prefsrc; val ^= fi->fib_priority; - for_nexthops(fi) { - val ^= fib_devindex_hashfn(nh->fib_nh_oif); - } endfor_nexthops(fi) + + if (fi->nh) { + val ^= fib_devindex_hashfn(fi->nh->id); + } else { + for_nexthops(fi) { + val ^= fib_devindex_hashfn(nh->fib_nh_oif); + } endfor_nexthops(fi) + } return (val ^ (val >> 7) ^ (val >> 12)) & mask; } -static struct fib_info *fib_find_info(const struct fib_info *nfi) +static struct fib_info *fib_find_info(struct fib_info *nfi) { struct hlist_head *head; struct fib_info *fi; @@ -344,7 +367,7 @@ static struct fib_info *fib_find_info(const struct fib_info *nfi) memcmp(nfi->fib_metrics, fi->fib_metrics, sizeof(u32) * RTAX_MAX) == 0 && !((nfi->fib_flags ^ fi->fib_flags) & ~RTNH_COMPARE_MASK) && - (nfi->fib_nhs == 0 || nh_comp(fi, nfi) == 0)) + nh_comp(fi, nfi) == 0) return fi; } @@ -386,34 +409,40 @@ static inline size_t fib_nlmsg_size(struct fib_info *fi) + nla_total_size(4) /* RTA_PRIORITY */ + nla_total_size(4) /* RTA_PREFSRC */ + nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */ + unsigned int nhs = fib_info_num_path(fi); /* space for nested metrics */ payload += nla_total_size((RTAX_MAX * nla_total_size(4))); - if (fi->fib_nhs) { + if (fi->nh) + payload += nla_total_size(4); /* RTA_NH_ID */ + + if (nhs) { size_t nh_encapsize = 0; - /* Also handles the special case fib_nhs == 1 */ + /* Also handles the special case nhs == 1 */ /* each nexthop is packed in an attribute */ size_t nhsize = nla_total_size(sizeof(struct rtnexthop)); + unsigned int i; /* may contain flow and gateway attribute */ nhsize += 2 * nla_total_size(4); /* grab encap info */ - for_nexthops(fi) { - if (nh->fib_nh_lws) { + for (i = 0; i < fib_info_num_path(fi); i++) { + struct fib_nh_common *nhc = fib_info_nhc(fi, i); + + if (nhc->nhc_lwtstate) { /* RTA_ENCAP_TYPE */ nh_encapsize += lwtunnel_get_encap_size( - nh->fib_nh_lws); + nhc->nhc_lwtstate); /* RTA_ENCAP */ nh_encapsize += nla_total_size(2); } - } endfor_nexthops(fi); + } /* all nexthops are packed in a nested attribute */ - payload += nla_total_size((fi->fib_nhs * nhsize) + - nh_encapsize); + payload += nla_total_size((nhs * nhsize) + nh_encapsize); } @@ -574,12 +603,14 @@ static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining, return nhs; } +/* only called when fib_nh is integrated into fib_info */ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, int remaining, struct fib_config *cfg, struct netlink_ext_ack *extack) { struct net *net = fi->fib_net; struct fib_config fib_cfg; + struct fib_nh *nh; int ret; change_nexthops(fi) { @@ -642,24 +673,25 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, } endfor_nexthops(fi); ret = -EINVAL; - if (cfg->fc_oif && fi->fib_nh->fib_nh_oif != cfg->fc_oif) { + nh = fib_info_nh(fi, 0); + if (cfg->fc_oif && nh->fib_nh_oif != cfg->fc_oif) { NL_SET_ERR_MSG(extack, "Nexthop device index does not match RTA_OIF"); goto errout; } if (cfg->fc_gw_family) { - if (cfg->fc_gw_family != fi->fib_nh->fib_nh_gw_family || + if (cfg->fc_gw_family != nh->fib_nh_gw_family || (cfg->fc_gw_family == AF_INET && - fi->fib_nh->fib_nh_gw4 != cfg->fc_gw4) || + nh->fib_nh_gw4 != cfg->fc_gw4) || (cfg->fc_gw_family == AF_INET6 && - ipv6_addr_cmp(&fi->fib_nh->fib_nh_gw6, &cfg->fc_gw6))) { + ipv6_addr_cmp(&nh->fib_nh_gw6, &cfg->fc_gw6))) { NL_SET_ERR_MSG(extack, "Nexthop gateway does not match RTA_GATEWAY or RTA_VIA"); goto errout; } } #ifdef CONFIG_IP_ROUTE_CLASSID - if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow) { + if (cfg->fc_flow && nh->nh_tclassid != cfg->fc_flow) { NL_SET_ERR_MSG(extack, "Nexthop class id does not match RTA_FLOW"); goto errout; @@ -670,12 +702,13 @@ errout: return ret; } +/* only called when fib_nh is integrated into fib_info */ static void fib_rebalance(struct fib_info *fi) { int total; int w; - if (fi->fib_nhs < 2) + if (fib_info_num_path(fi) < 2) return; total = 0; @@ -757,27 +790,29 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi, return 1; if (cfg->fc_oif || cfg->fc_gw_family) { + struct fib_nh *nh = fib_info_nh(fi, 0); + if (cfg->fc_encap) { if (fib_encap_match(cfg->fc_encap_type, cfg->fc_encap, - fi->fib_nh, cfg, extack)) + nh, cfg, extack)) return 1; } #ifdef CONFIG_IP_ROUTE_CLASSID if (cfg->fc_flow && - cfg->fc_flow != fi->fib_nh->nh_tclassid) + cfg->fc_flow != nh->nh_tclassid) return 1; #endif - if ((cfg->fc_oif && cfg->fc_oif != fi->fib_nh->fib_nh_oif) || + if ((cfg->fc_oif && cfg->fc_oif != nh->fib_nh_oif) || (cfg->fc_gw_family && - cfg->fc_gw_family != fi->fib_nh->fib_nh_gw_family)) + cfg->fc_gw_family != nh->fib_nh_gw_family)) return 1; if (cfg->fc_gw_family == AF_INET && - cfg->fc_gw4 != fi->fib_nh->fib_nh_gw4) + cfg->fc_gw4 != nh->fib_nh_gw4) return 1; if (cfg->fc_gw_family == AF_INET6 && - ipv6_addr_cmp(&cfg->fc_gw6, &fi->fib_nh->fib_nh_gw6)) + ipv6_addr_cmp(&cfg->fc_gw6, &nh->fib_nh_gw6)) return 1; return 0; @@ -1088,15 +1123,13 @@ out: return err; } -static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh, - struct netlink_ext_ack *extack) +int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope, + struct netlink_ext_ack *extack) { - struct net *net = cfg->fc_nlinfo.nl_net; - u32 table = cfg->fc_table; int err; if (nh->fib_nh_gw_family == AF_INET) - err = fib_check_nh_v4_gw(net, nh, table, cfg->fc_scope, extack); + err = fib_check_nh_v4_gw(net, nh, table, scope, extack); else if (nh->fib_nh_gw_family == AF_INET6) err = fib_check_nh_v6_gw(net, nh, table, extack); else @@ -1187,11 +1220,16 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash, fib_info_hash_free(old_laddrhash, bytes); } -__be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh) +__be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc, + unsigned char scope) { - nh->nh_saddr = inet_select_addr(nh->fib_nh_dev, - nh->fib_nh_gw4, - nh->nh_parent->fib_scope); + struct fib_nh *nh; + + if (nhc->nhc_family != AF_INET) + return inet_select_addr(nhc->nhc_dev, 0, scope); + + nh = container_of(nhc, struct fib_nh, nh_common); + nh->nh_saddr = inet_select_addr(nh->fib_nh_dev, nh->fib_nh_gw4, scope); nh->nh_saddr_genid = atomic_read(&net->ipv4.dev_addr_genid); return nh->nh_saddr; @@ -1200,16 +1238,19 @@ __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh) __be32 fib_result_prefsrc(struct net *net, struct fib_result *res) { struct fib_nh_common *nhc = res->nhc; - struct fib_nh *nh; if (res->fi->fib_prefsrc) return res->fi->fib_prefsrc; - nh = container_of(nhc, struct fib_nh, nh_common); - if (nh->nh_saddr_genid == atomic_read(&net->ipv4.dev_addr_genid)) - return nh->nh_saddr; + if (nhc->nhc_family == AF_INET) { + struct fib_nh *nh; + + nh = container_of(nhc, struct fib_nh, nh_common); + if (nh->nh_saddr_genid == atomic_read(&net->ipv4.dev_addr_genid)) + return nh->nh_saddr; + } - return fib_info_update_nh_saddr(net, nh); + return fib_info_update_nhc_saddr(net, nhc, res->fi->fib_scope); } static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc) @@ -1241,6 +1282,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg, { int err; struct fib_info *fi = NULL; + struct nexthop *nh = NULL; struct fib_info *ofi; int nhs = 1; struct net *net = cfg->fc_nlinfo.nl_net; @@ -1295,7 +1337,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg, goto failure; fi->fib_metrics = ip_fib_metrics_init(fi->fib_net, cfg->fc_mx, cfg->fc_mx_len, extack); - if (unlikely(IS_ERR(fi->fib_metrics))) { + if (IS_ERR(fi->fib_metrics)) { err = PTR_ERR(fi->fib_metrics); kfree(fi); return ERR_PTR(err); @@ -1312,14 +1354,25 @@ struct fib_info *fib_create_info(struct fib_config *cfg, fi->fib_tb_id = cfg->fc_table; fi->fib_nhs = nhs; - change_nexthops(fi) { - nexthop_nh->nh_parent = fi; - } endfor_nexthops(fi) + if (nh) { + if (!nexthop_get(nh)) { + NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); + err = -EINVAL; + } else { + err = 0; + fi->nh = nh; + } + } else { + change_nexthops(fi) { + nexthop_nh->nh_parent = fi; + } endfor_nexthops(fi) - if (cfg->fc_mp) - err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg, extack); - else - err = fib_nh_init(net, fi->fib_nh, cfg, 1, extack); + if (cfg->fc_mp) + err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg, + extack); + else + err = fib_nh_init(net, fi->fib_nh, cfg, 1, extack); + } if (err != 0) goto failure; @@ -1350,7 +1403,11 @@ struct fib_info *fib_create_info(struct fib_config *cfg, goto err_inval; } - if (cfg->fc_scope == RT_SCOPE_HOST) { + if (fi->nh) { + err = fib_check_nexthop(fi->nh, cfg->fc_scope, extack); + if (err) + goto failure; + } else if (cfg->fc_scope == RT_SCOPE_HOST) { struct fib_nh *nh = fi->fib_nh; /* Local address is added. */ @@ -1365,7 +1422,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg, goto err_inval; } nh->fib_nh_scope = RT_SCOPE_NOWHERE; - nh->fib_nh_dev = dev_get_by_index(net, fi->fib_nh->fib_nh_oif); + nh->fib_nh_dev = dev_get_by_index(net, nh->fib_nh_oif); err = -ENODEV; if (!nh->fib_nh_dev) goto failure; @@ -1373,7 +1430,9 @@ struct fib_info *fib_create_info(struct fib_config *cfg, int linkdown = 0; change_nexthops(fi) { - err = fib_check_nh(cfg, nexthop_nh, extack); + err = fib_check_nh(cfg->fc_nlinfo.nl_net, nexthop_nh, + cfg->fc_table, cfg->fc_scope, + extack); if (err != 0) goto failure; if (nexthop_nh->fib_nh_flags & RTNH_F_LINKDOWN) @@ -1388,13 +1447,16 @@ struct fib_info *fib_create_info(struct fib_config *cfg, goto err_inval; } - change_nexthops(fi) { - fib_info_update_nh_saddr(net, nexthop_nh); - if (nexthop_nh->fib_nh_gw_family == AF_INET6) - fi->fib_nh_is_v6 = true; - } endfor_nexthops(fi) + if (!fi->nh) { + change_nexthops(fi) { + fib_info_update_nhc_saddr(net, &nexthop_nh->nh_common, + fi->fib_scope); + if (nexthop_nh->fib_nh_gw_family == AF_INET6) + fi->fib_nh_is_v6 = true; + } endfor_nexthops(fi) - fib_rebalance(fi); + fib_rebalance(fi); + } link_it: ofi = fib_find_info(fi); @@ -1416,16 +1478,20 @@ link_it: head = &fib_info_laddrhash[fib_laddr_hashfn(fi->fib_prefsrc)]; hlist_add_head(&fi->fib_lhash, head); } - change_nexthops(fi) { - struct hlist_head *head; - unsigned int hash; + if (fi->nh) { + list_add(&fi->nh_list, &nh->fi_list); + } else { + change_nexthops(fi) { + struct hlist_head *head; + unsigned int hash; - if (!nexthop_nh->fib_nh_dev) - continue; - hash = fib_devindex_hashfn(nexthop_nh->fib_nh_dev->ifindex); - head = &fib_info_devhash[hash]; - hlist_add_head(&nexthop_nh->nh_hash, head); - } endfor_nexthops(fi) + if (!nexthop_nh->fib_nh_dev) + continue; + hash = fib_devindex_hashfn(nexthop_nh->fib_nh_dev->ifindex); + head = &fib_info_devhash[hash]; + hlist_add_head(&nexthop_nh->nh_hash, head); + } endfor_nexthops(fi) + } spin_unlock_bh(&fib_info_lock); return fi; @@ -1552,6 +1618,12 @@ static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi) if (!mp) goto nla_put_failure; + if (unlikely(fi->nh)) { + if (nexthop_mpath_fill_node(skb, fi->nh) < 0) + goto nla_put_failure; + goto mp_end; + } + for_nexthops(fi) { if (fib_add_nexthop(skb, &nh->nh_common, nh->fib_nh_weight) < 0) goto nla_put_failure; @@ -1562,6 +1634,7 @@ static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi) #endif } endfor_nexthops(fi); +mp_end: nla_nest_end(skb, mp); return 0; @@ -1580,6 +1653,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos, struct fib_info *fi, unsigned int flags) { + unsigned int nhs = fib_info_num_path(fi); struct nlmsghdr *nlh; struct rtmsg *rtm; @@ -1615,18 +1689,31 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, if (fi->fib_prefsrc && nla_put_in_addr(skb, RTA_PREFSRC, fi->fib_prefsrc)) goto nla_put_failure; - if (fi->fib_nhs == 1) { - struct fib_nh *nh = &fi->fib_nh[0]; + + if (fi->nh) { + if (nla_put_u32(skb, RTA_NH_ID, fi->nh->id)) + goto nla_put_failure; + if (nexthop_is_blackhole(fi->nh)) + rtm->rtm_type = RTN_BLACKHOLE; + } + + if (nhs == 1) { + const struct fib_nh_common *nhc = fib_info_nhc(fi, 0); unsigned char flags = 0; - if (fib_nexthop_info(skb, &nh->nh_common, &flags, false) < 0) + if (fib_nexthop_info(skb, nhc, &flags, false) < 0) goto nla_put_failure; rtm->rtm_flags = flags; #ifdef CONFIG_IP_ROUTE_CLASSID - if (nh->nh_tclassid && - nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid)) - goto nla_put_failure; + if (nhc->nhc_family == AF_INET) { + struct fib_nh *nh; + + nh = container_of(nhc, struct fib_nh, nh_common); + if (nh->nh_tclassid && + nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid)) + goto nla_put_failure; + } #endif } else { if (fib_add_multipath(skb, fi) < 0) @@ -1709,7 +1796,7 @@ static int call_fib_nh_notifiers(struct fib_nh *nh, * - if the new MTU is greater than the PMTU, don't make any change * - otherwise, unlock and set PMTU */ -static void nh_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig) +void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig) { struct fnhe_hash_bucket *bucket; int i; @@ -1745,7 +1832,7 @@ void fib_sync_mtu(struct net_device *dev, u32 orig_mtu) hlist_for_each_entry(nh, head, nh_hash) { if (nh->fib_nh_dev == dev) - nh_update_mtu(&nh->nh_common, dev->mtu, orig_mtu); + fib_nhc_update_mtu(&nh->nh_common, dev->mtu, orig_mtu); } } @@ -1754,6 +1841,8 @@ void fib_sync_mtu(struct net_device *dev, u32 orig_mtu) * NETDEV_DOWN 0 LINKDOWN|DEAD Link down, not for scope host * NETDEV_DOWN 1 LINKDOWN|DEAD Last address removed * NETDEV_UNREGISTER 1 LINKDOWN|DEAD Device removed + * + * only used when fib_nh is built into fib_info */ int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force) { @@ -1835,6 +1924,7 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res) hlist_for_each_entry_rcu(fa, fa_head, fa_list) { struct fib_info *next_fi = fa->fa_info; + struct fib_nh *nh; if (fa->fa_slen != slen) continue; @@ -1856,8 +1946,9 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res) if (next_fi->fib_scope != res->scope || fa->fa_type != RTN_UNICAST) continue; - if (!next_fi->fib_nh[0].fib_nh_gw4 || - next_fi->fib_nh[0].fib_nh_scope != RT_SCOPE_LINK) + + nh = fib_info_nh(next_fi, 0); + if (!nh->fib_nh_gw4 || nh->fib_nh_scope != RT_SCOPE_LINK) continue; fib_alias_accessed(fa); @@ -1899,6 +1990,8 @@ out: /* * Dead device goes up. We wake up dead nexthops. * It takes sense only on multipath routes. + * + * only used when fib_nh is built into fib_info */ int fib_sync_up(struct net_device *dev, unsigned char nh_flags) { @@ -1993,6 +2086,11 @@ void fib_select_multipath(struct fib_result *res, int hash) struct net *net = fi->fib_net; bool first = false; + if (unlikely(res->fi->nh)) { + nexthop_path_fib_result(res, hash); + return; + } + change_nexthops(fi) { if (net->ipv4.sysctl_fib_multipath_use_neigh) { if (!fib_good_nh(nexthop_nh)) @@ -2021,7 +2119,7 @@ void fib_select_path(struct net *net, struct fib_result *res, goto check_saddr; #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (res->fi->fib_nhs > 1) { + if (fib_info_num_path(res->fi) > 1) { int h = fib_multipath_hash(net, fl4, skb, NULL); fib_select_multipath(res, h); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 868c74771fa9..94e5d83db4db 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1449,6 +1449,7 @@ found: fib_alias_accessed(fa); err = fib_props[fa->fa_type].error; if (unlikely(err < 0)) { +out_reject: #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_passed); #endif @@ -1457,7 +1458,13 @@ found: } if (fi->fib_flags & RTNH_F_DEAD) continue; - for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) { + + if (unlikely(fi->nh && nexthop_is_blackhole(fi->nh))) { + err = fib_props[RTN_BLACKHOLE].error; + goto out_reject; + } + + for (nhsel = 0; nhsel < fib_info_num_path(fi); nhsel++) { struct fib_nh_common *nhc = fib_info_nhc(fi, nhsel); if (nhc->nhc_flags & RTNH_F_DEAD) @@ -1931,6 +1938,77 @@ int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all) return found; } +/* derived from fib_trie_free */ +static void __fib_info_notify_update(struct net *net, struct fib_table *tb, + struct nl_info *info) +{ + struct trie *t = (struct trie *)tb->tb_data; + struct key_vector *pn = t->kv; + unsigned long cindex = 1; + struct fib_alias *fa; + + for (;;) { + struct key_vector *n; + + if (!(cindex--)) { + t_key pkey = pn->key; + + if (IS_TRIE(pn)) + break; + + pn = node_parent(pn); + cindex = get_index(pkey, pn); + continue; + } + + /* grab the next available node */ + n = get_child(pn, cindex); + if (!n) + continue; + + if (IS_TNODE(n)) { + /* record pn and cindex for leaf walking */ + pn = n; + cindex = 1ul << n->bits; + + continue; + } + + hlist_for_each_entry(fa, &n->leaf, fa_list) { + struct fib_info *fi = fa->fa_info; + + if (!fi || !fi->nh_updated || fa->tb_id != tb->tb_id) + continue; + + rtmsg_fib(RTM_NEWROUTE, htonl(n->key), fa, + KEYLENGTH - fa->fa_slen, tb->tb_id, + info, NLM_F_REPLACE); + + /* call_fib_entry_notifiers will be removed when + * in-kernel notifier is implemented and supported + * for nexthop objects + */ + call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, + n->key, + KEYLENGTH - fa->fa_slen, fa, + NULL); + } + } +} + +void fib_info_notify_update(struct net *net, struct nl_info *info) +{ + unsigned int h; + + for (h = 0; h < FIB_TABLE_HASHSZ; h++) { + struct hlist_head *head = &net->ipv4.fib_table_hash[h]; + struct fib_table *tb; + + hlist_for_each_entry_rcu(tb, head, tb_hlist) + __fib_info_notify_update(net, tb, info); + } +} + static void fib_leaf_notify(struct net *net, struct key_vector *l, struct fib_table *tb, struct notifier_block *nb) { @@ -2634,14 +2712,18 @@ static void fib_route_seq_stop(struct seq_file *seq, void *v) rcu_read_unlock(); } -static unsigned int fib_flag_trans(int type, __be32 mask, const struct fib_info *fi) +static unsigned int fib_flag_trans(int type, __be32 mask, struct fib_info *fi) { unsigned int flags = 0; if (type == RTN_UNREACHABLE || type == RTN_PROHIBIT) flags = RTF_REJECT; - if (fi && fi->fib_nh->fib_nh_gw4) - flags |= RTF_GATEWAY; + if (fi) { + const struct fib_nh_common *nhc = fib_info_nhc(fi, 0); + + if (nhc->nhc_gw.ipv4) + flags |= RTF_GATEWAY; + } if (mask == htonl(0xFFFFFFFF)) flags |= RTF_HOST; flags |= RTF_UP; @@ -2672,7 +2754,7 @@ static int fib_route_seq_show(struct seq_file *seq, void *v) prefix = htonl(l->key); hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { - const struct fib_info *fi = fa->fa_info; + struct fib_info *fi = fa->fa_info; __be32 mask = inet_make_mask(KEYLENGTH - fa->fa_slen); unsigned int flags = fib_flag_trans(fa->fa_type, mask, fi); @@ -2685,26 +2767,31 @@ static int fib_route_seq_show(struct seq_file *seq, void *v) seq_setwidth(seq, 127); - if (fi) + if (fi) { + struct fib_nh_common *nhc = fib_info_nhc(fi, 0); + __be32 gw = 0; + + if (nhc->nhc_gw_family == AF_INET) + gw = nhc->nhc_gw.ipv4; + seq_printf(seq, "%s\t%08X\t%08X\t%04X\t%d\t%u\t" "%d\t%08X\t%d\t%u\t%u", - fi->fib_dev ? fi->fib_dev->name : "*", - prefix, - fi->fib_nh->fib_nh_gw4, flags, 0, 0, + nhc->nhc_dev ? nhc->nhc_dev->name : "*", + prefix, gw, flags, 0, 0, fi->fib_priority, mask, (fi->fib_advmss ? fi->fib_advmss + 40 : 0), fi->fib_window, fi->fib_rtt >> 3); - else + } else { seq_printf(seq, "*\t%08X\t%08X\t%04X\t%d\t%u\t" "%d\t%08X\t%d\t%u\t%u", prefix, 0, flags, 0, 0, 0, mask, 0, 0, 0); - + } seq_pad(seq, '\n'); } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 7c857c72aad1..1510e951f451 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -201,7 +201,7 @@ static const struct icmp_control icmp_pointers[NR_ICMP_TYPES+1]; */ static struct sock *icmp_sk(struct net *net) { - return *this_cpu_ptr(net->ipv4.icmp_sk); + return this_cpu_read(*net->ipv4.icmp_sk); } /* Called with BH disabled */ diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index a57f0d69eadb..9a206931a342 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -332,14 +332,15 @@ static __be32 igmpv3_get_srcaddr(struct net_device *dev, const struct flowi4 *fl4) { struct in_device *in_dev = __in_dev_get_rcu(dev); + const struct in_ifaddr *ifa; if (!in_dev) return htonl(INADDR_ANY); - for_ifa(in_dev) { + in_dev_for_each_ifa_rcu(ifa, in_dev) { if (fl4->saddr == ifa->ifa_local) return fl4->saddr; - } endfor_ifa(in_dev); + } return htonl(INADDR_ANY); } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 13ec7c3a9c49..fb0b4b0994ec 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -649,8 +649,7 @@ int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req) EXPORT_SYMBOL(inet_rtx_syn_ack); /* return true if req was found in the ehash table */ -static bool reqsk_queue_unlink(struct request_sock_queue *queue, - struct request_sock *req) +static bool reqsk_queue_unlink(struct request_sock *req) { struct inet_hashinfo *hashinfo = req_to_sk(req)->sk_prot->h.hashinfo; bool found = false; @@ -669,7 +668,7 @@ static bool reqsk_queue_unlink(struct request_sock_queue *queue, void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req) { - if (reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req)) { + if (reqsk_queue_unlink(req)) { reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); reqsk_put(req); } diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 5ce6969896f5..5c25727d491e 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -106,48 +106,101 @@ int inet_frags_init(struct inet_frags *f) if (!f->frags_cachep) return -ENOMEM; + refcount_set(&f->refcnt, 1); + init_completion(&f->completion); return 0; } EXPORT_SYMBOL(inet_frags_init); void inet_frags_fini(struct inet_frags *f) { - /* We must wait that all inet_frag_destroy_rcu() have completed. */ - rcu_barrier(); + if (refcount_dec_and_test(&f->refcnt)) + complete(&f->completion); + + wait_for_completion(&f->completion); kmem_cache_destroy(f->frags_cachep); f->frags_cachep = NULL; } EXPORT_SYMBOL(inet_frags_fini); +/* called from rhashtable_free_and_destroy() at netns_frags dismantle */ static void inet_frags_free_cb(void *ptr, void *arg) { struct inet_frag_queue *fq = ptr; + int count; - /* If we can not cancel the timer, it means this frag_queue - * is already disappearing, we have nothing to do. - * Otherwise, we own a refcount until the end of this function. - */ - if (!del_timer(&fq->timer)) - return; + count = del_timer_sync(&fq->timer) ? 1 : 0; spin_lock_bh(&fq->lock); if (!(fq->flags & INET_FRAG_COMPLETE)) { fq->flags |= INET_FRAG_COMPLETE; - refcount_dec(&fq->refcnt); + count++; + } else if (fq->flags & INET_FRAG_HASH_DEAD) { + count++; } spin_unlock_bh(&fq->lock); - inet_frag_put(fq); + if (refcount_sub_and_test(count, &fq->refcnt)) + inet_frag_destroy(fq); } -void inet_frags_exit_net(struct netns_frags *nf) +static void fqdir_rwork_fn(struct work_struct *work) { - nf->high_thresh = 0; /* prevent creation of new frags */ + struct fqdir *fqdir = container_of(to_rcu_work(work), + struct fqdir, destroy_rwork); + struct inet_frags *f = fqdir->f; + + rhashtable_free_and_destroy(&fqdir->rhashtable, inet_frags_free_cb, NULL); + + /* We need to make sure all ongoing call_rcu(..., inet_frag_destroy_rcu) + * have completed, since they need to dereference fqdir. + * Would it not be nice to have kfree_rcu_barrier() ? :) + */ + rcu_barrier(); + + if (refcount_dec_and_test(&f->refcnt)) + complete(&f->completion); - rhashtable_free_and_destroy(&nf->rhashtable, inet_frags_free_cb, NULL); + kfree(fqdir); } -EXPORT_SYMBOL(inet_frags_exit_net); + +int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net) +{ + struct fqdir *fqdir = kzalloc(sizeof(*fqdir), GFP_KERNEL); + int res; + + if (!fqdir) + return -ENOMEM; + fqdir->f = f; + fqdir->net = net; + res = rhashtable_init(&fqdir->rhashtable, &fqdir->f->rhash_params); + if (res < 0) { + kfree(fqdir); + return res; + } + refcount_inc(&f->refcnt); + *fqdirp = fqdir; + return 0; +} +EXPORT_SYMBOL(fqdir_init); + +void fqdir_exit(struct fqdir *fqdir) +{ + fqdir->high_thresh = 0; /* prevent creation of new frags */ + + fqdir->dead = true; + + /* call_rcu is supposed to provide memory barrier semantics, + * separating the setting of fqdir->dead with the destruction + * work. This implicit barrier is paired with inet_frag_kill(). + */ + + INIT_RCU_WORK(&fqdir->destroy_rwork, fqdir_rwork_fn); + queue_rcu_work(system_wq, &fqdir->destroy_rwork); + +} +EXPORT_SYMBOL(fqdir_exit); void inet_frag_kill(struct inet_frag_queue *fq) { @@ -155,11 +208,23 @@ void inet_frag_kill(struct inet_frag_queue *fq) refcount_dec(&fq->refcnt); if (!(fq->flags & INET_FRAG_COMPLETE)) { - struct netns_frags *nf = fq->net; + struct fqdir *fqdir = fq->fqdir; fq->flags |= INET_FRAG_COMPLETE; - rhashtable_remove_fast(&nf->rhashtable, &fq->node, nf->f->rhash_params); - refcount_dec(&fq->refcnt); + rcu_read_lock(); + /* The RCU read lock provides a memory barrier + * guaranteeing that if fqdir->dead is false then + * the hash table destruction will not start until + * after we unlock. Paired with inet_frags_exit_net(). + */ + if (!fqdir->dead) { + rhashtable_remove_fast(&fqdir->rhashtable, &fq->node, + fqdir->f->rhash_params); + refcount_dec(&fq->refcnt); + } else { + fq->flags |= INET_FRAG_HASH_DEAD; + } + rcu_read_unlock(); } } EXPORT_SYMBOL(inet_frag_kill); @@ -168,7 +233,7 @@ static void inet_frag_destroy_rcu(struct rcu_head *head) { struct inet_frag_queue *q = container_of(head, struct inet_frag_queue, rcu); - struct inet_frags *f = q->net->f; + struct inet_frags *f = q->fqdir->f; if (f->destructor) f->destructor(q); @@ -199,7 +264,7 @@ EXPORT_SYMBOL(inet_frag_rbtree_purge); void inet_frag_destroy(struct inet_frag_queue *q) { - struct netns_frags *nf; + struct fqdir *fqdir; unsigned int sum, sum_truesize = 0; struct inet_frags *f; @@ -207,18 +272,18 @@ void inet_frag_destroy(struct inet_frag_queue *q) WARN_ON(del_timer(&q->timer) != 0); /* Release all fragment data. */ - nf = q->net; - f = nf->f; + fqdir = q->fqdir; + f = fqdir->f; sum_truesize = inet_frag_rbtree_purge(&q->rb_fragments); sum = sum_truesize + f->qsize; call_rcu(&q->rcu, inet_frag_destroy_rcu); - sub_frag_mem_limit(nf, sum); + sub_frag_mem_limit(fqdir, sum); } EXPORT_SYMBOL(inet_frag_destroy); -static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, +static struct inet_frag_queue *inet_frag_alloc(struct fqdir *fqdir, struct inet_frags *f, void *arg) { @@ -228,9 +293,9 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, if (!q) return NULL; - q->net = nf; + q->fqdir = fqdir; f->constructor(q, arg); - add_frag_mem_limit(nf, f->qsize); + add_frag_mem_limit(fqdir, f->qsize); timer_setup(&q->timer, f->frag_expire, 0); spin_lock_init(&q->lock); @@ -239,21 +304,21 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, return q; } -static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, +static struct inet_frag_queue *inet_frag_create(struct fqdir *fqdir, void *arg, struct inet_frag_queue **prev) { - struct inet_frags *f = nf->f; + struct inet_frags *f = fqdir->f; struct inet_frag_queue *q; - q = inet_frag_alloc(nf, f, arg); + q = inet_frag_alloc(fqdir, f, arg); if (!q) { *prev = ERR_PTR(-ENOMEM); return NULL; } - mod_timer(&q->timer, jiffies + nf->timeout); + mod_timer(&q->timer, jiffies + fqdir->timeout); - *prev = rhashtable_lookup_get_insert_key(&nf->rhashtable, &q->key, + *prev = rhashtable_lookup_get_insert_key(&fqdir->rhashtable, &q->key, &q->node, f->rhash_params); if (*prev) { q->flags |= INET_FRAG_COMPLETE; @@ -265,18 +330,18 @@ static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, } /* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */ -struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key) +struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key) { struct inet_frag_queue *fq = NULL, *prev; - if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) + if (!fqdir->high_thresh || frag_mem_limit(fqdir) > fqdir->high_thresh) return NULL; rcu_read_lock(); - prev = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params); + prev = rhashtable_lookup(&fqdir->rhashtable, key, fqdir->f->rhash_params); if (!prev) - fq = inet_frag_create(nf, key, &prev); + fq = inet_frag_create(fqdir, key, &prev); if (prev && !IS_ERR(prev)) { fq = prev; if (!refcount_inc_not_zero(&fq->refcnt)) @@ -387,7 +452,7 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, delta += head->truesize; if (delta) - add_frag_mem_limit(q->net, delta); + add_frag_mem_limit(q->fqdir, delta); /* If the first fragment is fragmented itself, we split * it to two chunks: the first with data and paged part @@ -409,7 +474,7 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, head->truesize += clone->truesize; clone->csum = 0; clone->ip_summed = head->ip_summed; - add_frag_mem_limit(q->net, clone->truesize); + add_frag_mem_limit(q->fqdir, clone->truesize); skb_shinfo(head)->frag_list = clone; nextp = &clone->next; } else { @@ -462,7 +527,7 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, rbn = rbnext; } } - sub_frag_mem_limit(q->net, head->truesize); + sub_frag_mem_limit(q->fqdir, head->truesize); *nextp = NULL; skb_mark_not_on_list(head); @@ -490,7 +555,7 @@ struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q) if (head == q->fragments_tail) q->fragments_tail = NULL; - sub_frag_mem_limit(q->net, head->truesize); + sub_frag_mem_limit(q->fqdir, head->truesize); return head; } diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index c4503073248b..97824864e40d 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -316,7 +316,7 @@ struct sock *__inet_lookup_listener(struct net *net, saddr, sport, htonl(INADDR_ANY), hnum, dif, sdif); done: - if (unlikely(IS_ERR(result))) + if (IS_ERR(result)) return NULL; return result; } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index cf2b0a6a3337..1ffaec056821 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -82,15 +82,13 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, static void ip4_frag_init(struct inet_frag_queue *q, const void *a) { struct ipq *qp = container_of(q, struct ipq, q); - struct netns_ipv4 *ipv4 = container_of(q->net, struct netns_ipv4, - frags); - struct net *net = container_of(ipv4, struct net, ipv4); + struct net *net = q->fqdir->net; const struct frag_v4_compare_key *key = a; q->key.v4 = *key; qp->ecn = 0; - qp->peer = q->net->max_dist ? + qp->peer = q->fqdir->max_dist ? inet_getpeer_v4(net->ipv4.peers, key->saddr, key->vif, 1) : NULL; } @@ -142,7 +140,7 @@ static void ip_expire(struct timer_list *t) int err; qp = container_of(frag, struct ipq, q); - net = container_of(qp->q.net, struct net, ipv4.frags); + net = qp->q.fqdir->net; rcu_read_lock(); spin_lock(&qp->q.lock); @@ -211,7 +209,7 @@ static struct ipq *ip_find(struct net *net, struct iphdr *iph, }; struct inet_frag_queue *q; - q = inet_frag_find(&net->ipv4.frags, &key); + q = inet_frag_find(net->ipv4.fqdir, &key); if (!q) return NULL; @@ -222,7 +220,7 @@ static struct ipq *ip_find(struct net *net, struct iphdr *iph, static int ip_frag_too_far(struct ipq *qp) { struct inet_peer *peer = qp->peer; - unsigned int max = qp->q.net->max_dist; + unsigned int max = qp->q.fqdir->max_dist; unsigned int start, end; int rc; @@ -236,12 +234,8 @@ static int ip_frag_too_far(struct ipq *qp) rc = qp->q.fragments_tail && (end - start) > max; - if (rc) { - struct net *net; - - net = container_of(qp->q.net, struct net, ipv4.frags); - __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); - } + if (rc) + __IP_INC_STATS(qp->q.fqdir->net, IPSTATS_MIB_REASMFAILS); return rc; } @@ -250,13 +244,13 @@ static int ip_frag_reinit(struct ipq *qp) { unsigned int sum_truesize = 0; - if (!mod_timer(&qp->q.timer, jiffies + qp->q.net->timeout)) { + if (!mod_timer(&qp->q.timer, jiffies + qp->q.fqdir->timeout)) { refcount_inc(&qp->q.refcnt); return -ETIMEDOUT; } sum_truesize = inet_frag_rbtree_purge(&qp->q.rb_fragments); - sub_frag_mem_limit(qp->q.net, sum_truesize); + sub_frag_mem_limit(qp->q.fqdir, sum_truesize); qp->q.flags = 0; qp->q.len = 0; @@ -273,7 +267,7 @@ static int ip_frag_reinit(struct ipq *qp) /* Add new segment to existing queue. */ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) { - struct net *net = container_of(qp->q.net, struct net, ipv4.frags); + struct net *net = qp->q.fqdir->net; int ihl, end, flags, offset; struct sk_buff *prev_tail; struct net_device *dev; @@ -352,7 +346,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) qp->q.stamp = skb->tstamp; qp->q.meat += skb->len; qp->ecn |= ecn; - add_frag_mem_limit(qp->q.net, skb->truesize); + add_frag_mem_limit(qp->q.fqdir, skb->truesize); if (offset == 0) qp->q.flags |= INET_FRAG_FIRST_IN; @@ -399,7 +393,7 @@ err: static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, struct sk_buff *prev_tail, struct net_device *dev) { - struct net *net = container_of(qp->q.net, struct net, ipv4.frags); + struct net *net = qp->q.fqdir->net; struct iphdr *iph; void *reasm_data; int len, err; @@ -544,30 +538,24 @@ static int dist_min; static struct ctl_table ip4_frags_ns_ctl_table[] = { { .procname = "ipfrag_high_thresh", - .data = &init_net.ipv4.frags.high_thresh, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, - .extra1 = &init_net.ipv4.frags.low_thresh }, { .procname = "ipfrag_low_thresh", - .data = &init_net.ipv4.frags.low_thresh, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, - .extra2 = &init_net.ipv4.frags.high_thresh }, { .procname = "ipfrag_time", - .data = &init_net.ipv4.frags.timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "ipfrag_max_dist", - .data = &init_net.ipv4.frags.max_dist, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, @@ -600,13 +588,13 @@ static int __net_init ip4_frags_ns_ctl_register(struct net *net) if (!table) goto err_alloc; - table[0].data = &net->ipv4.frags.high_thresh; - table[0].extra1 = &net->ipv4.frags.low_thresh; - table[1].data = &net->ipv4.frags.low_thresh; - table[1].extra2 = &net->ipv4.frags.high_thresh; - table[2].data = &net->ipv4.frags.timeout; - table[3].data = &net->ipv4.frags.max_dist; } + table[0].data = &net->ipv4.fqdir->high_thresh; + table[0].extra1 = &net->ipv4.fqdir->low_thresh; + table[1].data = &net->ipv4.fqdir->low_thresh; + table[1].extra2 = &net->ipv4.fqdir->high_thresh; + table[2].data = &net->ipv4.fqdir->timeout; + table[3].data = &net->ipv4.fqdir->max_dist; hdr = register_net_sysctl(net, "net/ipv4", table); if (!hdr) @@ -654,6 +642,9 @@ static int __net_init ipv4_frags_init_net(struct net *net) { int res; + res = fqdir_init(&net->ipv4.fqdir, &ip4_frags, net); + if (res < 0) + return res; /* Fragment cache limits. * * The fragment memory accounting code, (tries to) account for @@ -668,31 +659,27 @@ static int __net_init ipv4_frags_init_net(struct net *net) * we will prune down to 3MB, making room for approx 8 big 64K * fragments 8x128k. */ - net->ipv4.frags.high_thresh = 4 * 1024 * 1024; - net->ipv4.frags.low_thresh = 3 * 1024 * 1024; + net->ipv4.fqdir->high_thresh = 4 * 1024 * 1024; + net->ipv4.fqdir->low_thresh = 3 * 1024 * 1024; /* * Important NOTE! Fragment queue must be destroyed before MSL expires. * RFC791 is wrong proposing to prolongate timer each fragment arrival * by TTL. */ - net->ipv4.frags.timeout = IP_FRAG_TIME; + net->ipv4.fqdir->timeout = IP_FRAG_TIME; - net->ipv4.frags.max_dist = 64; - net->ipv4.frags.f = &ip4_frags; + net->ipv4.fqdir->max_dist = 64; - res = inet_frags_init_net(&net->ipv4.frags); - if (res < 0) - return res; res = ip4_frags_ns_ctl_register(net); if (res < 0) - inet_frags_exit_net(&net->ipv4.frags); + fqdir_exit(net->ipv4.fqdir); return res; } static void __net_exit ipv4_frags_exit_net(struct net *net) { ip4_frags_ns_ctl_unregister(net); - inet_frags_exit_net(&net->ipv4.frags); + fqdir_exit(net->ipv4.fqdir); } static struct pernet_operations ip4_frags_ops = { diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 8c9189a41b13..f5636ab0b9c3 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -287,16 +287,9 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, return ret; } -static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) +static int __ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { unsigned int mtu; - int ret; - - ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); - if (ret) { - kfree_skb(skb); - return ret; - } #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ @@ -315,18 +308,37 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk return ip_finish_output2(net, sk, skb); } +static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + int ret; + + ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); + switch (ret) { + case NET_XMIT_SUCCESS: + return __ip_finish_output(net, sk, skb); + case NET_XMIT_CN: + return __ip_finish_output(net, sk, skb) ? : ret; + default: + kfree_skb(skb); + return ret; + } +} + static int ip_mc_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { int ret; ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); - if (ret) { + switch (ret) { + case NET_XMIT_SUCCESS: + return dev_loopback_xmit(net, sk, skb); + case NET_XMIT_CN: + return dev_loopback_xmit(net, sk, skb) ? : ret; + default: kfree_skb(skb); return ret; } - - return dev_loopback_xmit(net, sk, skb); } int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb) @@ -525,9 +537,6 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) skb_copy_hash(to, from); - /* Copy the flags to each fragment. */ - IPCB(to)->flags = IPCB(from)->flags; - #ifdef CONFIG_NET_SCHED to->tc_index = from->tc_index; #endif @@ -561,6 +570,175 @@ static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, return ip_do_fragment(net, sk, skb, output); } +void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph, + unsigned int hlen, struct ip_fraglist_iter *iter) +{ + unsigned int first_len = skb_pagelen(skb); + + iter->frag = skb_shinfo(skb)->frag_list; + skb_frag_list_init(skb); + + iter->offset = 0; + iter->iph = iph; + iter->hlen = hlen; + + skb->data_len = first_len - skb_headlen(skb); + skb->len = first_len; + iph->tot_len = htons(first_len); + iph->frag_off = htons(IP_MF); + ip_send_check(iph); +} +EXPORT_SYMBOL(ip_fraglist_init); + +static void ip_fraglist_ipcb_prepare(struct sk_buff *skb, + struct ip_fraglist_iter *iter) +{ + struct sk_buff *to = iter->frag; + + /* Copy the flags to each fragment. */ + IPCB(to)->flags = IPCB(skb)->flags; + + if (iter->offset == 0) + ip_options_fragment(to); +} + +void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter) +{ + unsigned int hlen = iter->hlen; + struct iphdr *iph = iter->iph; + struct sk_buff *frag; + + frag = iter->frag; + frag->ip_summed = CHECKSUM_NONE; + skb_reset_transport_header(frag); + __skb_push(frag, hlen); + skb_reset_network_header(frag); + memcpy(skb_network_header(frag), iph, hlen); + iter->iph = ip_hdr(frag); + iph = iter->iph; + iph->tot_len = htons(frag->len); + ip_copy_metadata(frag, skb); + iter->offset += skb->len - hlen; + iph->frag_off = htons(iter->offset >> 3); + if (frag->next) + iph->frag_off |= htons(IP_MF); + /* Ready, complete checksum */ + ip_send_check(iph); +} +EXPORT_SYMBOL(ip_fraglist_prepare); + +void ip_frag_init(struct sk_buff *skb, unsigned int hlen, + unsigned int ll_rs, unsigned int mtu, + struct ip_frag_state *state) +{ + struct iphdr *iph = ip_hdr(skb); + + state->hlen = hlen; + state->ll_rs = ll_rs; + state->mtu = mtu; + + state->left = skb->len - hlen; /* Space per frame */ + state->ptr = hlen; /* Where to start from */ + + state->offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3; + state->not_last_frag = iph->frag_off & htons(IP_MF); +} +EXPORT_SYMBOL(ip_frag_init); + +static void ip_frag_ipcb(struct sk_buff *from, struct sk_buff *to, + bool first_frag, struct ip_frag_state *state) +{ + /* Copy the flags to each fragment. */ + IPCB(to)->flags = IPCB(from)->flags; + + if (IPCB(from)->flags & IPSKB_FRAG_PMTU) + state->iph->frag_off |= htons(IP_DF); + + /* ANK: dirty, but effective trick. Upgrade options only if + * the segment to be fragmented was THE FIRST (otherwise, + * options are already fixed) and make it ONCE + * on the initial skb, so that all the following fragments + * will inherit fixed options. + */ + if (first_frag) + ip_options_fragment(from); +} + +struct sk_buff *ip_frag_next(struct sk_buff *skb, struct ip_frag_state *state) +{ + unsigned int len = state->left; + struct sk_buff *skb2; + struct iphdr *iph; + + len = state->left; + /* IF: it doesn't fit, use 'mtu' - the data space left */ + if (len > state->mtu) + len = state->mtu; + /* IF: we are not sending up to and including the packet end + then align the next start on an eight byte boundary */ + if (len < state->left) { + len &= ~7; + } + + /* Allocate buffer */ + skb2 = alloc_skb(len + state->hlen + state->ll_rs, GFP_ATOMIC); + if (!skb2) + return ERR_PTR(-ENOMEM); + + /* + * Set up data on packet + */ + + ip_copy_metadata(skb2, skb); + skb_reserve(skb2, state->ll_rs); + skb_put(skb2, len + state->hlen); + skb_reset_network_header(skb2); + skb2->transport_header = skb2->network_header + state->hlen; + + /* + * Charge the memory for the fragment to any owner + * it might possess + */ + + if (skb->sk) + skb_set_owner_w(skb2, skb->sk); + + /* + * Copy the packet header into the new buffer. + */ + + skb_copy_from_linear_data(skb, skb_network_header(skb2), state->hlen); + + /* + * Copy a block of the IP datagram. + */ + if (skb_copy_bits(skb, state->ptr, skb_transport_header(skb2), len)) + BUG(); + state->left -= len; + + /* + * Fill in the new header fields. + */ + iph = ip_hdr(skb2); + iph->frag_off = htons((state->offset >> 3)); + + /* + * Added AC : If we are fragmenting a fragment that's not the + * last fragment then keep MF on each bit + */ + if (state->left > 0 || state->not_last_frag) + iph->frag_off |= htons(IP_MF); + state->ptr += len; + state->offset += len; + + iph->tot_len = htons(len + state->hlen); + + ip_send_check(iph); + + return skb2; +} +EXPORT_SYMBOL(ip_frag_next); + /* * This IP datagram is too large to be sent in one piece. Break it up into * smaller pieces (each of size equal to IP header plus @@ -572,12 +750,11 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct iphdr *iph; - int ptr; struct sk_buff *skb2; - unsigned int mtu, hlen, left, len, ll_rs; - int offset; - __be16 not_last_frag; struct rtable *rt = skb_rtable(skb); + unsigned int mtu, hlen, ll_rs; + struct ip_fraglist_iter iter; + struct ip_frag_state state; int err = 0; /* for offloaded checksums cleanup checksum before fragmentation */ @@ -642,49 +819,24 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, } /* Everything is OK. Generate! */ - - err = 0; - offset = 0; - frag = skb_shinfo(skb)->frag_list; - skb_frag_list_init(skb); - skb->data_len = first_len - skb_headlen(skb); - skb->len = first_len; - iph->tot_len = htons(first_len); - iph->frag_off = htons(IP_MF); - ip_send_check(iph); + ip_fraglist_init(skb, iph, hlen, &iter); for (;;) { /* Prepare header of the next frame, * before previous one went down. */ - if (frag) { - frag->ip_summed = CHECKSUM_NONE; - skb_reset_transport_header(frag); - __skb_push(frag, hlen); - skb_reset_network_header(frag); - memcpy(skb_network_header(frag), iph, hlen); - iph = ip_hdr(frag); - iph->tot_len = htons(frag->len); - ip_copy_metadata(frag, skb); - if (offset == 0) - ip_options_fragment(frag); - offset += skb->len - hlen; - iph->frag_off = htons(offset>>3); - if (frag->next) - iph->frag_off |= htons(IP_MF); - /* Ready, complete checksum */ - ip_send_check(iph); + if (iter.frag) { + ip_fraglist_ipcb_prepare(skb, &iter); + ip_fraglist_prepare(skb, &iter); } err = output(net, sk, skb); if (!err) IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES); - if (err || !frag) + if (err || !iter.frag) break; - skb = frag; - frag = skb->next; - skb_mark_not_on_list(skb); + skb = ip_fraglist_next(&iter); } if (err == 0) { @@ -692,7 +844,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, return 0; } - kfree_skb_list(frag); + kfree_skb_list(iter.frag); IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); return err; @@ -708,105 +860,29 @@ slow_path_clean: } slow_path: - iph = ip_hdr(skb); - - left = skb->len - hlen; /* Space per frame */ - ptr = hlen; /* Where to start from */ - /* * Fragment the datagram. */ - offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3; - not_last_frag = iph->frag_off & htons(IP_MF); + ip_frag_init(skb, hlen, ll_rs, mtu, &state); /* * Keep copying data until we run out. */ - while (left > 0) { - len = left; - /* IF: it doesn't fit, use 'mtu' - the data space left */ - if (len > mtu) - len = mtu; - /* IF: we are not sending up to and including the packet end - then align the next start on an eight byte boundary */ - if (len < left) { - len &= ~7; - } + while (state.left > 0) { + bool first_frag = (state.offset == 0); - /* Allocate buffer */ - skb2 = alloc_skb(len + hlen + ll_rs, GFP_ATOMIC); - if (!skb2) { - err = -ENOMEM; + skb2 = ip_frag_next(skb, &state); + if (IS_ERR(skb2)) { + err = PTR_ERR(skb2); goto fail; } - - /* - * Set up data on packet - */ - - ip_copy_metadata(skb2, skb); - skb_reserve(skb2, ll_rs); - skb_put(skb2, len + hlen); - skb_reset_network_header(skb2); - skb2->transport_header = skb2->network_header + hlen; - - /* - * Charge the memory for the fragment to any owner - * it might possess - */ - - if (skb->sk) - skb_set_owner_w(skb2, skb->sk); - - /* - * Copy the packet header into the new buffer. - */ - - skb_copy_from_linear_data(skb, skb_network_header(skb2), hlen); - - /* - * Copy a block of the IP datagram. - */ - if (skb_copy_bits(skb, ptr, skb_transport_header(skb2), len)) - BUG(); - left -= len; - - /* - * Fill in the new header fields. - */ - iph = ip_hdr(skb2); - iph->frag_off = htons((offset >> 3)); - - if (IPCB(skb)->flags & IPSKB_FRAG_PMTU) - iph->frag_off |= htons(IP_DF); - - /* ANK: dirty, but effective trick. Upgrade options only if - * the segment to be fragmented was THE FIRST (otherwise, - * options are already fixed) and make it ONCE - * on the initial skb, so that all the following fragments - * will inherit fixed options. - */ - if (offset == 0) - ip_options_fragment(skb); - - /* - * Added AC : If we are fragmenting a fragment that's not the - * last fragment then keep MF on each bit - */ - if (left > 0 || not_last_frag) - iph->frag_off |= htons(IP_MF); - ptr += len; - offset += len; + ip_frag_ipcb(skb, skb2, first_frag, &state); /* * Put this fragment into the sending queue. */ - iph->tot_len = htons(len + hlen); - - ip_send_check(iph); - err = output(net, sk, skb2); if (err) goto fail; diff --git a/net/ipv4/netfilter/arpt_mangle.c b/net/ipv4/netfilter/arpt_mangle.c index 87ca2c42359b..a4e07e5e9c11 100644 --- a/net/ipv4/netfilter/arpt_mangle.c +++ b/net/ipv4/netfilter/arpt_mangle.c @@ -17,7 +17,7 @@ target(struct sk_buff *skb, const struct xt_action_param *par) unsigned char *arpptr; int pln, hln; - if (!skb_make_writable(skb, skb->len)) + if (skb_ensure_writable(skb, skb->len)) return NF_DROP; arp = arp_hdr(skb); diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c index aaaf9a81fbc9..9f6751893660 100644 --- a/net/ipv4/netfilter/ipt_ECN.c +++ b/net/ipv4/netfilter/ipt_ECN.c @@ -32,7 +32,7 @@ set_ect_ip(struct sk_buff *skb, const struct ipt_ECN_info *einfo) if ((iph->tos & IPT_ECN_IP_MASK) != (einfo->ip_ect & IPT_ECN_IP_MASK)) { __u8 oldtos; - if (!skb_make_writable(skb, sizeof(struct iphdr))) + if (skb_ensure_writable(skb, sizeof(struct iphdr))) return false; iph = ip_hdr(skb); oldtos = iph->tos; @@ -61,7 +61,7 @@ set_ect_tcp(struct sk_buff *skb, const struct ipt_ECN_info *einfo) tcph->cwr == einfo->proto.tcp.cwr)) return true; - if (!skb_make_writable(skb, ip_hdrlen(skb) + sizeof(*tcph))) + if (skb_ensure_writable(skb, ip_hdrlen(skb) + sizeof(*tcph))) return false; tcph = (void *)ip_hdr(skb) + ip_hdrlen(skb); diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index 7875c98072eb..15f2b2604890 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -59,7 +59,7 @@ static int set_addr(struct sk_buff *skb, unsigned int protoff, net_notice_ratelimited("nf_nat_h323: nf_nat_mangle_udp_packet error\n"); return -1; } - /* nf_nat_mangle_udp_packet uses skb_make_writable() to copy + /* nf_nat_mangle_udp_packet uses skb_ensure_writable() to copy * or pull everything in a linear buffer, so we can safely * use the skb pointers now */ *data = skb->data + ip_hdrlen(skb) + sizeof(struct udphdr); diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c index 657d2dcec3cc..717b726504fe 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c @@ -186,7 +186,7 @@ static int help(struct sk_buff *skb, unsigned int protoff, return NF_DROP; } - if (!skb_make_writable(skb, skb->len)) { + if (skb_ensure_writable(skb, skb->len)) { nf_ct_helper_log(skb, ct, "cannot mangle packet"); return NF_DROP; } diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c index 164714104965..40c93b3bd731 100644 --- a/net/ipv4/netfilter/nf_tproxy_ipv4.c +++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c @@ -53,6 +53,7 @@ EXPORT_SYMBOL_GPL(nf_tproxy_handle_time_wait4); __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr) { + const struct in_ifaddr *ifa; struct in_device *indev; __be32 laddr; @@ -61,10 +62,14 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr) laddr = 0; indev = __in_dev_get_rcu(skb->dev); - for_primary_ifa(indev) { + + in_dev_for_each_ifa_rcu(ifa, indev) { + if (ifa->ifa_flags & IFA_F_SECONDARY) + continue; + laddr = ifa->ifa_local; break; - } endfor_ifa(indev); + } return laddr ? laddr : daddr; } diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c new file mode 100644 index 000000000000..5e48762b6b5f --- /dev/null +++ b/net/ipv4/nexthop.c @@ -0,0 +1,1588 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Generic nexthop implementation + * + * Copyright (c) 2017-19 Cumulus Networks + * Copyright (c) 2017-19 David Ahern <dsa@cumulusnetworks.com> + */ + +#include <linux/nexthop.h> +#include <linux/rtnetlink.h> +#include <linux/slab.h> +#include <net/arp.h> +#include <net/ipv6_stubs.h> +#include <net/lwtunnel.h> +#include <net/ndisc.h> +#include <net/nexthop.h> +#include <net/route.h> +#include <net/sock.h> + +static void remove_nexthop(struct net *net, struct nexthop *nh, + struct nl_info *nlinfo); + +#define NH_DEV_HASHBITS 8 +#define NH_DEV_HASHSIZE (1U << NH_DEV_HASHBITS) + +static const struct nla_policy rtm_nh_policy[NHA_MAX + 1] = { + [NHA_UNSPEC] = { .strict_start_type = NHA_UNSPEC + 1 }, + [NHA_ID] = { .type = NLA_U32 }, + [NHA_GROUP] = { .type = NLA_BINARY }, + [NHA_GROUP_TYPE] = { .type = NLA_U16 }, + [NHA_BLACKHOLE] = { .type = NLA_FLAG }, + [NHA_OIF] = { .type = NLA_U32 }, + [NHA_GATEWAY] = { .type = NLA_BINARY }, + [NHA_ENCAP_TYPE] = { .type = NLA_U16 }, + [NHA_ENCAP] = { .type = NLA_NESTED }, + [NHA_GROUPS] = { .type = NLA_FLAG }, + [NHA_MASTER] = { .type = NLA_U32 }, +}; + +static unsigned int nh_dev_hashfn(unsigned int val) +{ + unsigned int mask = NH_DEV_HASHSIZE - 1; + + return (val ^ + (val >> NH_DEV_HASHBITS) ^ + (val >> (NH_DEV_HASHBITS * 2))) & mask; +} + +static void nexthop_devhash_add(struct net *net, struct nh_info *nhi) +{ + struct net_device *dev = nhi->fib_nhc.nhc_dev; + struct hlist_head *head; + unsigned int hash; + + WARN_ON(!dev); + + hash = nh_dev_hashfn(dev->ifindex); + head = &net->nexthop.devhash[hash]; + hlist_add_head(&nhi->dev_hash, head); +} + +static void nexthop_free_mpath(struct nexthop *nh) +{ + struct nh_group *nhg; + int i; + + nhg = rcu_dereference_raw(nh->nh_grp); + for (i = 0; i < nhg->num_nh; ++i) + WARN_ON(nhg->nh_entries[i].nh); + + kfree(nhg); +} + +static void nexthop_free_single(struct nexthop *nh) +{ + struct nh_info *nhi; + + nhi = rcu_dereference_raw(nh->nh_info); + switch (nhi->family) { + case AF_INET: + fib_nh_release(nh->net, &nhi->fib_nh); + break; + case AF_INET6: + ipv6_stub->fib6_nh_release(&nhi->fib6_nh); + break; + } + kfree(nhi); +} + +void nexthop_free_rcu(struct rcu_head *head) +{ + struct nexthop *nh = container_of(head, struct nexthop, rcu); + + if (nh->is_group) + nexthop_free_mpath(nh); + else + nexthop_free_single(nh); + + kfree(nh); +} +EXPORT_SYMBOL_GPL(nexthop_free_rcu); + +static struct nexthop *nexthop_alloc(void) +{ + struct nexthop *nh; + + nh = kzalloc(sizeof(struct nexthop), GFP_KERNEL); + if (nh) { + INIT_LIST_HEAD(&nh->fi_list); + INIT_LIST_HEAD(&nh->f6i_list); + INIT_LIST_HEAD(&nh->grp_list); + } + return nh; +} + +static struct nh_group *nexthop_grp_alloc(u16 num_nh) +{ + size_t sz = offsetof(struct nexthop, nh_grp) + + sizeof(struct nh_group) + + sizeof(struct nh_grp_entry) * num_nh; + struct nh_group *nhg; + + nhg = kzalloc(sz, GFP_KERNEL); + if (nhg) + nhg->num_nh = num_nh; + + return nhg; +} + +static void nh_base_seq_inc(struct net *net) +{ + while (++net->nexthop.seq == 0) + ; +} + +/* no reference taken; rcu lock or rtnl must be held */ +struct nexthop *nexthop_find_by_id(struct net *net, u32 id) +{ + struct rb_node **pp, *parent = NULL, *next; + + pp = &net->nexthop.rb_root.rb_node; + while (1) { + struct nexthop *nh; + + next = rcu_dereference_raw(*pp); + if (!next) + break; + parent = next; + + nh = rb_entry(parent, struct nexthop, rb_node); + if (id < nh->id) + pp = &next->rb_left; + else if (id > nh->id) + pp = &next->rb_right; + else + return nh; + } + return NULL; +} +EXPORT_SYMBOL_GPL(nexthop_find_by_id); + +/* used for auto id allocation; called with rtnl held */ +static u32 nh_find_unused_id(struct net *net) +{ + u32 id_start = net->nexthop.last_id_allocated; + + while (1) { + net->nexthop.last_id_allocated++; + if (net->nexthop.last_id_allocated == id_start) + break; + + if (!nexthop_find_by_id(net, net->nexthop.last_id_allocated)) + return net->nexthop.last_id_allocated; + } + return 0; +} + +static int nla_put_nh_group(struct sk_buff *skb, struct nh_group *nhg) +{ + struct nexthop_grp *p; + size_t len = nhg->num_nh * sizeof(*p); + struct nlattr *nla; + u16 group_type = 0; + int i; + + if (nhg->mpath) + group_type = NEXTHOP_GRP_TYPE_MPATH; + + if (nla_put_u16(skb, NHA_GROUP_TYPE, group_type)) + goto nla_put_failure; + + nla = nla_reserve(skb, NHA_GROUP, len); + if (!nla) + goto nla_put_failure; + + p = nla_data(nla); + for (i = 0; i < nhg->num_nh; ++i) { + p->id = nhg->nh_entries[i].nh->id; + p->weight = nhg->nh_entries[i].weight - 1; + p += 1; + } + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, + int event, u32 portid, u32 seq, unsigned int nlflags) +{ + struct fib6_nh *fib6_nh; + struct fib_nh *fib_nh; + struct nlmsghdr *nlh; + struct nh_info *nhi; + struct nhmsg *nhm; + + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nhm), nlflags); + if (!nlh) + return -EMSGSIZE; + + nhm = nlmsg_data(nlh); + nhm->nh_family = AF_UNSPEC; + nhm->nh_flags = nh->nh_flags; + nhm->nh_protocol = nh->protocol; + nhm->nh_scope = 0; + nhm->resvd = 0; + + if (nla_put_u32(skb, NHA_ID, nh->id)) + goto nla_put_failure; + + if (nh->is_group) { + struct nh_group *nhg = rtnl_dereference(nh->nh_grp); + + if (nla_put_nh_group(skb, nhg)) + goto nla_put_failure; + goto out; + } + + nhi = rtnl_dereference(nh->nh_info); + nhm->nh_family = nhi->family; + if (nhi->reject_nh) { + if (nla_put_flag(skb, NHA_BLACKHOLE)) + goto nla_put_failure; + goto out; + } else { + const struct net_device *dev; + + dev = nhi->fib_nhc.nhc_dev; + if (dev && nla_put_u32(skb, NHA_OIF, dev->ifindex)) + goto nla_put_failure; + } + + nhm->nh_scope = nhi->fib_nhc.nhc_scope; + switch (nhi->family) { + case AF_INET: + fib_nh = &nhi->fib_nh; + if (fib_nh->fib_nh_gw_family && + nla_put_u32(skb, NHA_GATEWAY, fib_nh->fib_nh_gw4)) + goto nla_put_failure; + break; + + case AF_INET6: + fib6_nh = &nhi->fib6_nh; + if (fib6_nh->fib_nh_gw_family && + nla_put_in6_addr(skb, NHA_GATEWAY, &fib6_nh->fib_nh_gw6)) + goto nla_put_failure; + break; + } + + if (nhi->fib_nhc.nhc_lwtstate && + lwtunnel_fill_encap(skb, nhi->fib_nhc.nhc_lwtstate, + NHA_ENCAP, NHA_ENCAP_TYPE) < 0) + goto nla_put_failure; + +out: + nlmsg_end(skb, nlh); + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static size_t nh_nlmsg_size_grp(struct nexthop *nh) +{ + struct nh_group *nhg = rtnl_dereference(nh->nh_grp); + size_t sz = sizeof(struct nexthop_grp) * nhg->num_nh; + + return nla_total_size(sz) + + nla_total_size(2); /* NHA_GROUP_TYPE */ +} + +static size_t nh_nlmsg_size_single(struct nexthop *nh) +{ + struct nh_info *nhi = rtnl_dereference(nh->nh_info); + size_t sz; + + /* covers NHA_BLACKHOLE since NHA_OIF and BLACKHOLE + * are mutually exclusive + */ + sz = nla_total_size(4); /* NHA_OIF */ + + switch (nhi->family) { + case AF_INET: + if (nhi->fib_nh.fib_nh_gw_family) + sz += nla_total_size(4); /* NHA_GATEWAY */ + break; + + case AF_INET6: + /* NHA_GATEWAY */ + if (nhi->fib6_nh.fib_nh_gw_family) + sz += nla_total_size(sizeof(const struct in6_addr)); + break; + } + + if (nhi->fib_nhc.nhc_lwtstate) { + sz += lwtunnel_get_encap_size(nhi->fib_nhc.nhc_lwtstate); + sz += nla_total_size(2); /* NHA_ENCAP_TYPE */ + } + + return sz; +} + +static size_t nh_nlmsg_size(struct nexthop *nh) +{ + size_t sz = nla_total_size(4); /* NHA_ID */ + + if (nh->is_group) + sz += nh_nlmsg_size_grp(nh); + else + sz += nh_nlmsg_size_single(nh); + + return sz; +} + +static void nexthop_notify(int event, struct nexthop *nh, struct nl_info *info) +{ + unsigned int nlflags = info->nlh ? info->nlh->nlmsg_flags : 0; + u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(nh_nlmsg_size(nh), gfp_any()); + if (!skb) + goto errout; + + err = nh_fill_node(skb, nh, event, info->portid, seq, nlflags); + if (err < 0) { + /* -EMSGSIZE implies BUG in nh_nlmsg_size() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + + rtnl_notify(skb, info->nl_net, info->portid, RTNLGRP_NEXTHOP, + info->nlh, gfp_any()); + return; +errout: + if (err < 0) + rtnl_set_sk_err(info->nl_net, RTNLGRP_NEXTHOP, err); +} + +static bool valid_group_nh(struct nexthop *nh, unsigned int npaths, + struct netlink_ext_ack *extack) +{ + if (nh->is_group) { + struct nh_group *nhg = rtnl_dereference(nh->nh_grp); + + /* nested multipath (group within a group) is not + * supported + */ + if (nhg->mpath) { + NL_SET_ERR_MSG(extack, + "Multipath group can not be a nexthop within a group"); + return false; + } + } else { + struct nh_info *nhi = rtnl_dereference(nh->nh_info); + + if (nhi->reject_nh && npaths > 1) { + NL_SET_ERR_MSG(extack, + "Blackhole nexthop can not be used in a group with more than 1 path"); + return false; + } + } + + return true; +} + +static int nh_check_attr_group(struct net *net, struct nlattr *tb[], + struct netlink_ext_ack *extack) +{ + unsigned int len = nla_len(tb[NHA_GROUP]); + struct nexthop_grp *nhg; + unsigned int i, j; + + if (len & (sizeof(struct nexthop_grp) - 1)) { + NL_SET_ERR_MSG(extack, + "Invalid length for nexthop group attribute"); + return -EINVAL; + } + + /* convert len to number of nexthop ids */ + len /= sizeof(*nhg); + + nhg = nla_data(tb[NHA_GROUP]); + for (i = 0; i < len; ++i) { + if (nhg[i].resvd1 || nhg[i].resvd2) { + NL_SET_ERR_MSG(extack, "Reserved fields in nexthop_grp must be 0"); + return -EINVAL; + } + if (nhg[i].weight > 254) { + NL_SET_ERR_MSG(extack, "Invalid value for weight"); + return -EINVAL; + } + for (j = i + 1; j < len; ++j) { + if (nhg[i].id == nhg[j].id) { + NL_SET_ERR_MSG(extack, "Nexthop id can not be used twice in a group"); + return -EINVAL; + } + } + } + + nhg = nla_data(tb[NHA_GROUP]); + for (i = 0; i < len; ++i) { + struct nexthop *nh; + + nh = nexthop_find_by_id(net, nhg[i].id); + if (!nh) { + NL_SET_ERR_MSG(extack, "Invalid nexthop id"); + return -EINVAL; + } + if (!valid_group_nh(nh, len, extack)) + return -EINVAL; + } + for (i = NHA_GROUP + 1; i < __NHA_MAX; ++i) { + if (!tb[i]) + continue; + + NL_SET_ERR_MSG(extack, + "No other attributes can be set in nexthop groups"); + return -EINVAL; + } + + return 0; +} + +static bool ipv6_good_nh(const struct fib6_nh *nh) +{ + int state = NUD_REACHABLE; + struct neighbour *n; + + rcu_read_lock_bh(); + + n = __ipv6_neigh_lookup_noref_stub(nh->fib_nh_dev, &nh->fib_nh_gw6); + if (n) + state = n->nud_state; + + rcu_read_unlock_bh(); + + return !!(state & NUD_VALID); +} + +static bool ipv4_good_nh(const struct fib_nh *nh) +{ + int state = NUD_REACHABLE; + struct neighbour *n; + + rcu_read_lock_bh(); + + n = __ipv4_neigh_lookup_noref(nh->fib_nh_dev, + (__force u32)nh->fib_nh_gw4); + if (n) + state = n->nud_state; + + rcu_read_unlock_bh(); + + return !!(state & NUD_VALID); +} + +struct nexthop *nexthop_select_path(struct nexthop *nh, int hash) +{ + struct nexthop *rc = NULL; + struct nh_group *nhg; + int i; + + if (!nh->is_group) + return nh; + + nhg = rcu_dereference(nh->nh_grp); + for (i = 0; i < nhg->num_nh; ++i) { + struct nh_grp_entry *nhge = &nhg->nh_entries[i]; + struct nh_info *nhi; + + if (hash > atomic_read(&nhge->upper_bound)) + continue; + + /* nexthops always check if it is good and does + * not rely on a sysctl for this behavior + */ + nhi = rcu_dereference(nhge->nh->nh_info); + switch (nhi->family) { + case AF_INET: + if (ipv4_good_nh(&nhi->fib_nh)) + return nhge->nh; + break; + case AF_INET6: + if (ipv6_good_nh(&nhi->fib6_nh)) + return nhge->nh; + break; + } + + if (!rc) + rc = nhge->nh; + } + + return rc; +} +EXPORT_SYMBOL_GPL(nexthop_select_path); + +int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg, + struct netlink_ext_ack *extack) +{ + struct nh_info *nhi; + + /* fib6_src is unique to a fib6_info and limits the ability to cache + * routes in fib6_nh within a nexthop that is potentially shared + * across multiple fib entries. If the config wants to use source + * routing it can not use nexthop objects. mlxsw also does not allow + * fib6_src on routes. + */ + if (!ipv6_addr_any(&cfg->fc_src)) { + NL_SET_ERR_MSG(extack, "IPv6 routes using source address can not use nexthop objects"); + return -EINVAL; + } + + if (nh->is_group) { + struct nh_group *nhg; + + nhg = rtnl_dereference(nh->nh_grp); + if (nhg->has_v4) + goto no_v4_nh; + } else { + nhi = rtnl_dereference(nh->nh_info); + if (nhi->family == AF_INET) + goto no_v4_nh; + } + + return 0; +no_v4_nh: + NL_SET_ERR_MSG(extack, "IPv6 routes can not use an IPv4 nexthop"); + return -EINVAL; +} +EXPORT_SYMBOL_GPL(fib6_check_nexthop); + +static int nexthop_check_scope(struct nexthop *nh, u8 scope, + struct netlink_ext_ack *extack) +{ + struct nh_info *nhi; + + nhi = rtnl_dereference(nh->nh_info); + if (scope == RT_SCOPE_HOST && nhi->fib_nhc.nhc_gw_family) { + NL_SET_ERR_MSG(extack, + "Route with host scope can not have a gateway"); + return -EINVAL; + } + + if (nhi->fib_nhc.nhc_flags & RTNH_F_ONLINK && scope >= RT_SCOPE_LINK) { + NL_SET_ERR_MSG(extack, "Scope mismatch with nexthop"); + return -EINVAL; + } + + return 0; +} + +/* Invoked by fib add code to verify nexthop by id is ok with + * config for prefix; parts of fib_check_nh not done when nexthop + * object is used. + */ +int fib_check_nexthop(struct nexthop *nh, u8 scope, + struct netlink_ext_ack *extack) +{ + int err = 0; + + if (nh->is_group) { + struct nh_group *nhg; + + if (scope == RT_SCOPE_HOST) { + NL_SET_ERR_MSG(extack, "Route with host scope can not have multiple nexthops"); + err = -EINVAL; + goto out; + } + + nhg = rtnl_dereference(nh->nh_grp); + /* all nexthops in a group have the same scope */ + err = nexthop_check_scope(nhg->nh_entries[0].nh, scope, extack); + } else { + err = nexthop_check_scope(nh, scope, extack); + } +out: + return err; +} + +static void nh_group_rebalance(struct nh_group *nhg) +{ + int total = 0; + int w = 0; + int i; + + for (i = 0; i < nhg->num_nh; ++i) + total += nhg->nh_entries[i].weight; + + for (i = 0; i < nhg->num_nh; ++i) { + struct nh_grp_entry *nhge = &nhg->nh_entries[i]; + int upper_bound; + + w += nhge->weight; + upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31, total) - 1; + atomic_set(&nhge->upper_bound, upper_bound); + } +} + +static void remove_nh_grp_entry(struct nh_grp_entry *nhge, + struct nh_group *nhg, + struct nl_info *nlinfo) +{ + struct nexthop *nh = nhge->nh; + struct nh_grp_entry *nhges; + bool found = false; + int i; + + WARN_ON(!nh); + + nhges = nhg->nh_entries; + for (i = 0; i < nhg->num_nh; ++i) { + if (found) { + nhges[i-1].nh = nhges[i].nh; + nhges[i-1].weight = nhges[i].weight; + list_del(&nhges[i].nh_list); + list_add(&nhges[i-1].nh_list, &nhges[i-1].nh->grp_list); + } else if (nhg->nh_entries[i].nh == nh) { + found = true; + } + } + + if (WARN_ON(!found)) + return; + + nhg->num_nh--; + nhg->nh_entries[nhg->num_nh].nh = NULL; + + nh_group_rebalance(nhg); + + nexthop_put(nh); + + if (nlinfo) + nexthop_notify(RTM_NEWNEXTHOP, nhge->nh_parent, nlinfo); +} + +static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh, + struct nl_info *nlinfo) +{ + struct nh_grp_entry *nhge, *tmp; + + list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list) { + struct nh_group *nhg; + + list_del(&nhge->nh_list); + nhg = rtnl_dereference(nhge->nh_parent->nh_grp); + remove_nh_grp_entry(nhge, nhg, nlinfo); + + /* if this group has no more entries then remove it */ + if (!nhg->num_nh) + remove_nexthop(net, nhge->nh_parent, nlinfo); + } +} + +static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo) +{ + struct nh_group *nhg = rcu_dereference_rtnl(nh->nh_grp); + int i, num_nh = nhg->num_nh; + + for (i = 0; i < num_nh; ++i) { + struct nh_grp_entry *nhge = &nhg->nh_entries[i]; + + if (WARN_ON(!nhge->nh)) + continue; + + list_del(&nhge->nh_list); + nexthop_put(nhge->nh); + nhge->nh = NULL; + nhg->num_nh--; + } +} + +static void __remove_nexthop_fib(struct net *net, struct nexthop *nh) +{ + struct fib6_info *f6i, *tmp; + bool do_flush = false; + struct fib_info *fi; + + list_for_each_entry(fi, &nh->fi_list, nh_list) { + fi->fib_flags |= RTNH_F_DEAD; + do_flush = true; + } + if (do_flush) + fib_flush(net); + + /* ip6_del_rt removes the entry from this list hence the _safe */ + list_for_each_entry_safe(f6i, tmp, &nh->f6i_list, nh_list) { + /* __ip6_del_rt does a release, so do a hold here */ + fib6_info_hold(f6i); + ipv6_stub->ip6_del_rt(net, f6i); + } +} + +static void __remove_nexthop(struct net *net, struct nexthop *nh, + struct nl_info *nlinfo) +{ + __remove_nexthop_fib(net, nh); + + if (nh->is_group) { + remove_nexthop_group(nh, nlinfo); + } else { + struct nh_info *nhi; + + nhi = rtnl_dereference(nh->nh_info); + if (nhi->fib_nhc.nhc_dev) + hlist_del(&nhi->dev_hash); + + remove_nexthop_from_groups(net, nh, nlinfo); + } +} + +static void remove_nexthop(struct net *net, struct nexthop *nh, + struct nl_info *nlinfo) +{ + /* remove from the tree */ + rb_erase(&nh->rb_node, &net->nexthop.rb_root); + + if (nlinfo) + nexthop_notify(RTM_DELNEXTHOP, nh, nlinfo); + + __remove_nexthop(net, nh, nlinfo); + nh_base_seq_inc(net); + + nexthop_put(nh); +} + +static int replace_nexthop(struct net *net, struct nexthop *old, + struct nexthop *new, struct netlink_ext_ack *extack) +{ + return -EEXIST; +} + +/* called with rtnl_lock held */ +static int insert_nexthop(struct net *net, struct nexthop *new_nh, + struct nh_config *cfg, struct netlink_ext_ack *extack) +{ + struct rb_node **pp, *parent = NULL, *next; + struct rb_root *root = &net->nexthop.rb_root; + bool replace = !!(cfg->nlflags & NLM_F_REPLACE); + bool create = !!(cfg->nlflags & NLM_F_CREATE); + u32 new_id = new_nh->id; + int rc = -EEXIST; + + pp = &root->rb_node; + while (1) { + struct nexthop *nh; + + next = rtnl_dereference(*pp); + if (!next) + break; + + parent = next; + + nh = rb_entry(parent, struct nexthop, rb_node); + if (new_id < nh->id) { + pp = &next->rb_left; + } else if (new_id > nh->id) { + pp = &next->rb_right; + } else if (replace) { + rc = replace_nexthop(net, nh, new_nh, extack); + if (!rc) + new_nh = nh; /* send notification with old nh */ + goto out; + } else { + /* id already exists and not a replace */ + goto out; + } + } + + if (replace && !create) { + NL_SET_ERR_MSG(extack, "Replace specified without create and no entry exists"); + rc = -ENOENT; + goto out; + } + + rb_link_node_rcu(&new_nh->rb_node, parent, pp); + rb_insert_color(&new_nh->rb_node, root); + rc = 0; +out: + if (!rc) { + nh_base_seq_inc(net); + nexthop_notify(RTM_NEWNEXTHOP, new_nh, &cfg->nlinfo); + } + + return rc; +} + +/* rtnl */ +/* remove all nexthops tied to a device being deleted */ +static void nexthop_flush_dev(struct net_device *dev) +{ + unsigned int hash = nh_dev_hashfn(dev->ifindex); + struct net *net = dev_net(dev); + struct hlist_head *head = &net->nexthop.devhash[hash]; + struct hlist_node *n; + struct nh_info *nhi; + + hlist_for_each_entry_safe(nhi, n, head, dev_hash) { + if (nhi->fib_nhc.nhc_dev != dev) + continue; + + remove_nexthop(net, nhi->nh_parent, NULL); + } +} + +/* rtnl; called when net namespace is deleted */ +static void flush_all_nexthops(struct net *net) +{ + struct rb_root *root = &net->nexthop.rb_root; + struct rb_node *node; + struct nexthop *nh; + + while ((node = rb_first(root))) { + nh = rb_entry(node, struct nexthop, rb_node); + remove_nexthop(net, nh, NULL); + cond_resched(); + } +} + +static struct nexthop *nexthop_create_group(struct net *net, + struct nh_config *cfg) +{ + struct nlattr *grps_attr = cfg->nh_grp; + struct nexthop_grp *entry = nla_data(grps_attr); + struct nh_group *nhg; + struct nexthop *nh; + int i; + + nh = nexthop_alloc(); + if (!nh) + return ERR_PTR(-ENOMEM); + + nh->is_group = 1; + + nhg = nexthop_grp_alloc(nla_len(grps_attr) / sizeof(*entry)); + if (!nhg) { + kfree(nh); + return ERR_PTR(-ENOMEM); + } + + for (i = 0; i < nhg->num_nh; ++i) { + struct nexthop *nhe; + struct nh_info *nhi; + + nhe = nexthop_find_by_id(net, entry[i].id); + if (!nexthop_get(nhe)) + goto out_no_nh; + + nhi = rtnl_dereference(nhe->nh_info); + if (nhi->family == AF_INET) + nhg->has_v4 = true; + + nhg->nh_entries[i].nh = nhe; + nhg->nh_entries[i].weight = entry[i].weight + 1; + list_add(&nhg->nh_entries[i].nh_list, &nhe->grp_list); + nhg->nh_entries[i].nh_parent = nh; + } + + if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_MPATH) { + nhg->mpath = 1; + nh_group_rebalance(nhg); + } + + rcu_assign_pointer(nh->nh_grp, nhg); + + return nh; + +out_no_nh: + for (; i >= 0; --i) + nexthop_put(nhg->nh_entries[i].nh); + + kfree(nhg); + kfree(nh); + + return ERR_PTR(-ENOENT); +} + +static int nh_create_ipv4(struct net *net, struct nexthop *nh, + struct nh_info *nhi, struct nh_config *cfg, + struct netlink_ext_ack *extack) +{ + struct fib_nh *fib_nh = &nhi->fib_nh; + struct fib_config fib_cfg = { + .fc_oif = cfg->nh_ifindex, + .fc_gw4 = cfg->gw.ipv4, + .fc_gw_family = cfg->gw.ipv4 ? AF_INET : 0, + .fc_flags = cfg->nh_flags, + .fc_encap = cfg->nh_encap, + .fc_encap_type = cfg->nh_encap_type, + }; + u32 tb_id = l3mdev_fib_table(cfg->dev); + int err = -EINVAL; + + err = fib_nh_init(net, fib_nh, &fib_cfg, 1, extack); + if (err) { + fib_nh_release(net, fib_nh); + goto out; + } + + /* sets nh_dev if successful */ + err = fib_check_nh(net, fib_nh, tb_id, 0, extack); + if (!err) { + nh->nh_flags = fib_nh->fib_nh_flags; + fib_info_update_nhc_saddr(net, &fib_nh->nh_common, + fib_nh->fib_nh_scope); + } else { + fib_nh_release(net, fib_nh); + } +out: + return err; +} + +static int nh_create_ipv6(struct net *net, struct nexthop *nh, + struct nh_info *nhi, struct nh_config *cfg, + struct netlink_ext_ack *extack) +{ + struct fib6_nh *fib6_nh = &nhi->fib6_nh; + struct fib6_config fib6_cfg = { + .fc_table = l3mdev_fib_table(cfg->dev), + .fc_ifindex = cfg->nh_ifindex, + .fc_gateway = cfg->gw.ipv6, + .fc_flags = cfg->nh_flags, + .fc_encap = cfg->nh_encap, + .fc_encap_type = cfg->nh_encap_type, + }; + int err; + + if (!ipv6_addr_any(&cfg->gw.ipv6)) + fib6_cfg.fc_flags |= RTF_GATEWAY; + + /* sets nh_dev if successful */ + err = ipv6_stub->fib6_nh_init(net, fib6_nh, &fib6_cfg, GFP_KERNEL, + extack); + if (err) + ipv6_stub->fib6_nh_release(fib6_nh); + else + nh->nh_flags = fib6_nh->fib_nh_flags; + + return err; +} + +static struct nexthop *nexthop_create(struct net *net, struct nh_config *cfg, + struct netlink_ext_ack *extack) +{ + struct nh_info *nhi; + struct nexthop *nh; + int err = 0; + + nh = nexthop_alloc(); + if (!nh) + return ERR_PTR(-ENOMEM); + + nhi = kzalloc(sizeof(*nhi), GFP_KERNEL); + if (!nhi) { + kfree(nh); + return ERR_PTR(-ENOMEM); + } + + nh->nh_flags = cfg->nh_flags; + nh->net = net; + + nhi->nh_parent = nh; + nhi->family = cfg->nh_family; + nhi->fib_nhc.nhc_scope = RT_SCOPE_LINK; + + if (cfg->nh_blackhole) { + nhi->reject_nh = 1; + cfg->nh_ifindex = net->loopback_dev->ifindex; + } + + switch (cfg->nh_family) { + case AF_INET: + err = nh_create_ipv4(net, nh, nhi, cfg, extack); + break; + case AF_INET6: + err = nh_create_ipv6(net, nh, nhi, cfg, extack); + break; + } + + if (err) { + kfree(nhi); + kfree(nh); + return ERR_PTR(err); + } + + /* add the entry to the device based hash */ + nexthop_devhash_add(net, nhi); + + rcu_assign_pointer(nh->nh_info, nhi); + + return nh; +} + +/* called with rtnl lock held */ +static struct nexthop *nexthop_add(struct net *net, struct nh_config *cfg, + struct netlink_ext_ack *extack) +{ + struct nexthop *nh; + int err; + + if (cfg->nlflags & NLM_F_REPLACE && !cfg->nh_id) { + NL_SET_ERR_MSG(extack, "Replace requires nexthop id"); + return ERR_PTR(-EINVAL); + } + + if (!cfg->nh_id) { + cfg->nh_id = nh_find_unused_id(net); + if (!cfg->nh_id) { + NL_SET_ERR_MSG(extack, "No unused id"); + return ERR_PTR(-EINVAL); + } + } + + if (cfg->nh_grp) + nh = nexthop_create_group(net, cfg); + else + nh = nexthop_create(net, cfg, extack); + + if (IS_ERR(nh)) + return nh; + + refcount_set(&nh->refcnt, 1); + nh->id = cfg->nh_id; + nh->protocol = cfg->nh_protocol; + nh->net = net; + + err = insert_nexthop(net, nh, cfg, extack); + if (err) { + __remove_nexthop(net, nh, NULL); + nexthop_put(nh); + nh = ERR_PTR(err); + } + + return nh; +} + +static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, + struct nlmsghdr *nlh, struct nh_config *cfg, + struct netlink_ext_ack *extack) +{ + struct nhmsg *nhm = nlmsg_data(nlh); + struct nlattr *tb[NHA_MAX + 1]; + int err; + + err = nlmsg_parse(nlh, sizeof(*nhm), tb, NHA_MAX, rtm_nh_policy, + extack); + if (err < 0) + return err; + + err = -EINVAL; + if (nhm->resvd || nhm->nh_scope) { + NL_SET_ERR_MSG(extack, "Invalid values in ancillary header"); + goto out; + } + if (nhm->nh_flags & ~NEXTHOP_VALID_USER_FLAGS) { + NL_SET_ERR_MSG(extack, "Invalid nexthop flags in ancillary header"); + goto out; + } + + switch (nhm->nh_family) { + case AF_INET: + case AF_INET6: + break; + case AF_UNSPEC: + if (tb[NHA_GROUP]) + break; + /* fallthrough */ + default: + NL_SET_ERR_MSG(extack, "Invalid address family"); + goto out; + } + + if (tb[NHA_GROUPS] || tb[NHA_MASTER]) { + NL_SET_ERR_MSG(extack, "Invalid attributes in request"); + goto out; + } + + memset(cfg, 0, sizeof(*cfg)); + cfg->nlflags = nlh->nlmsg_flags; + cfg->nlinfo.portid = NETLINK_CB(skb).portid; + cfg->nlinfo.nlh = nlh; + cfg->nlinfo.nl_net = net; + + cfg->nh_family = nhm->nh_family; + cfg->nh_protocol = nhm->nh_protocol; + cfg->nh_flags = nhm->nh_flags; + + if (tb[NHA_ID]) + cfg->nh_id = nla_get_u32(tb[NHA_ID]); + + if (tb[NHA_GROUP]) { + if (nhm->nh_family != AF_UNSPEC) { + NL_SET_ERR_MSG(extack, "Invalid family for group"); + goto out; + } + cfg->nh_grp = tb[NHA_GROUP]; + + cfg->nh_grp_type = NEXTHOP_GRP_TYPE_MPATH; + if (tb[NHA_GROUP_TYPE]) + cfg->nh_grp_type = nla_get_u16(tb[NHA_GROUP_TYPE]); + + if (cfg->nh_grp_type > NEXTHOP_GRP_TYPE_MAX) { + NL_SET_ERR_MSG(extack, "Invalid group type"); + goto out; + } + err = nh_check_attr_group(net, tb, extack); + + /* no other attributes should be set */ + goto out; + } + + if (tb[NHA_BLACKHOLE]) { + if (tb[NHA_GATEWAY] || tb[NHA_OIF] || + tb[NHA_ENCAP] || tb[NHA_ENCAP_TYPE]) { + NL_SET_ERR_MSG(extack, "Blackhole attribute can not be used with gateway or oif"); + goto out; + } + + cfg->nh_blackhole = 1; + err = 0; + goto out; + } + + if (!tb[NHA_OIF]) { + NL_SET_ERR_MSG(extack, "Device attribute required for non-blackhole nexthops"); + goto out; + } + + cfg->nh_ifindex = nla_get_u32(tb[NHA_OIF]); + if (cfg->nh_ifindex) + cfg->dev = __dev_get_by_index(net, cfg->nh_ifindex); + + if (!cfg->dev) { + NL_SET_ERR_MSG(extack, "Invalid device index"); + goto out; + } else if (!(cfg->dev->flags & IFF_UP)) { + NL_SET_ERR_MSG(extack, "Nexthop device is not up"); + err = -ENETDOWN; + goto out; + } else if (!netif_carrier_ok(cfg->dev)) { + NL_SET_ERR_MSG(extack, "Carrier for nexthop device is down"); + err = -ENETDOWN; + goto out; + } + + err = -EINVAL; + if (tb[NHA_GATEWAY]) { + struct nlattr *gwa = tb[NHA_GATEWAY]; + + switch (cfg->nh_family) { + case AF_INET: + if (nla_len(gwa) != sizeof(u32)) { + NL_SET_ERR_MSG(extack, "Invalid gateway"); + goto out; + } + cfg->gw.ipv4 = nla_get_be32(gwa); + break; + case AF_INET6: + if (nla_len(gwa) != sizeof(struct in6_addr)) { + NL_SET_ERR_MSG(extack, "Invalid gateway"); + goto out; + } + cfg->gw.ipv6 = nla_get_in6_addr(gwa); + break; + default: + NL_SET_ERR_MSG(extack, + "Unknown address family for gateway"); + goto out; + } + } else { + /* device only nexthop (no gateway) */ + if (cfg->nh_flags & RTNH_F_ONLINK) { + NL_SET_ERR_MSG(extack, + "ONLINK flag can not be set for nexthop without a gateway"); + goto out; + } + } + + if (tb[NHA_ENCAP]) { + cfg->nh_encap = tb[NHA_ENCAP]; + + if (!tb[NHA_ENCAP_TYPE]) { + NL_SET_ERR_MSG(extack, "LWT encapsulation type is missing"); + goto out; + } + + cfg->nh_encap_type = nla_get_u16(tb[NHA_ENCAP_TYPE]); + err = lwtunnel_valid_encap_type(cfg->nh_encap_type, extack); + if (err < 0) + goto out; + + } else if (tb[NHA_ENCAP_TYPE]) { + NL_SET_ERR_MSG(extack, "LWT encapsulation attribute is missing"); + goto out; + } + + + err = 0; +out: + return err; +} + +/* rtnl */ +static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(skb->sk); + struct nh_config cfg; + struct nexthop *nh; + int err; + + err = rtm_to_nh_config(net, skb, nlh, &cfg, extack); + if (!err) { + nh = nexthop_add(net, &cfg, extack); + if (IS_ERR(nh)) + err = PTR_ERR(nh); + } + + return err; +} + +static int nh_valid_get_del_req(struct nlmsghdr *nlh, u32 *id, + struct netlink_ext_ack *extack) +{ + struct nhmsg *nhm = nlmsg_data(nlh); + struct nlattr *tb[NHA_MAX + 1]; + int err, i; + + err = nlmsg_parse(nlh, sizeof(*nhm), tb, NHA_MAX, rtm_nh_policy, + extack); + if (err < 0) + return err; + + err = -EINVAL; + for (i = 0; i < __NHA_MAX; ++i) { + if (!tb[i]) + continue; + + switch (i) { + case NHA_ID: + break; + default: + NL_SET_ERR_MSG_ATTR(extack, tb[i], + "Unexpected attribute in request"); + goto out; + } + } + if (nhm->nh_protocol || nhm->resvd || nhm->nh_scope || nhm->nh_flags) { + NL_SET_ERR_MSG(extack, "Invalid values in header"); + goto out; + } + + if (!tb[NHA_ID]) { + NL_SET_ERR_MSG(extack, "Nexthop id is missing"); + goto out; + } + + *id = nla_get_u32(tb[NHA_ID]); + if (!(*id)) + NL_SET_ERR_MSG(extack, "Invalid nexthop id"); + else + err = 0; +out: + return err; +} + +/* rtnl */ +static int rtm_del_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(skb->sk); + struct nl_info nlinfo = { + .nlh = nlh, + .nl_net = net, + .portid = NETLINK_CB(skb).portid, + }; + struct nexthop *nh; + int err; + u32 id; + + err = nh_valid_get_del_req(nlh, &id, extack); + if (err) + return err; + + nh = nexthop_find_by_id(net, id); + if (!nh) + return -ENOENT; + + remove_nexthop(net, nh, &nlinfo); + + return 0; +} + +/* rtnl */ +static int rtm_get_nexthop(struct sk_buff *in_skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(in_skb->sk); + struct sk_buff *skb = NULL; + struct nexthop *nh; + int err; + u32 id; + + err = nh_valid_get_del_req(nlh, &id, extack); + if (err) + return err; + + err = -ENOBUFS; + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) + goto out; + + err = -ENOENT; + nh = nexthop_find_by_id(net, id); + if (!nh) + goto errout_free; + + err = nh_fill_node(skb, nh, RTM_NEWNEXTHOP, NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, 0); + if (err < 0) { + WARN_ON(err == -EMSGSIZE); + goto errout_free; + } + + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); +out: + return err; +errout_free: + kfree_skb(skb); + goto out; +} + +static bool nh_dump_filtered(struct nexthop *nh, int dev_idx, int master_idx, + bool group_filter, u8 family) +{ + const struct net_device *dev; + const struct nh_info *nhi; + + if (group_filter && !nh->is_group) + return true; + + if (!dev_idx && !master_idx && !family) + return false; + + if (nh->is_group) + return true; + + nhi = rtnl_dereference(nh->nh_info); + if (family && nhi->family != family) + return true; + + dev = nhi->fib_nhc.nhc_dev; + if (dev_idx && (!dev || dev->ifindex != dev_idx)) + return true; + + if (master_idx) { + struct net_device *master; + + if (!dev) + return true; + + master = netdev_master_upper_dev_get((struct net_device *)dev); + if (!master || master->ifindex != master_idx) + return true; + } + + return false; +} + +static int nh_valid_dump_req(const struct nlmsghdr *nlh, int *dev_idx, + int *master_idx, bool *group_filter, + struct netlink_callback *cb) +{ + struct netlink_ext_ack *extack = cb->extack; + struct nlattr *tb[NHA_MAX + 1]; + struct nhmsg *nhm; + int err, i; + u32 idx; + + err = nlmsg_parse(nlh, sizeof(*nhm), tb, NHA_MAX, rtm_nh_policy, + NULL); + if (err < 0) + return err; + + for (i = 0; i <= NHA_MAX; ++i) { + if (!tb[i]) + continue; + + switch (i) { + case NHA_OIF: + idx = nla_get_u32(tb[i]); + if (idx > INT_MAX) { + NL_SET_ERR_MSG(extack, "Invalid device index"); + return -EINVAL; + } + *dev_idx = idx; + break; + case NHA_MASTER: + idx = nla_get_u32(tb[i]); + if (idx > INT_MAX) { + NL_SET_ERR_MSG(extack, "Invalid master device index"); + return -EINVAL; + } + *master_idx = idx; + break; + case NHA_GROUPS: + *group_filter = true; + break; + default: + NL_SET_ERR_MSG(extack, "Unsupported attribute in dump request"); + return -EINVAL; + } + } + + nhm = nlmsg_data(nlh); + if (nhm->nh_protocol || nhm->resvd || nhm->nh_scope || nhm->nh_flags) { + NL_SET_ERR_MSG(extack, "Invalid values in header for nexthop dump request"); + return -EINVAL; + } + + return 0; +} + +/* rtnl */ +static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct nhmsg *nhm = nlmsg_data(cb->nlh); + int dev_filter_idx = 0, master_idx = 0; + struct net *net = sock_net(skb->sk); + struct rb_root *root = &net->nexthop.rb_root; + bool group_filter = false; + struct rb_node *node; + int idx = 0, s_idx; + int err; + + err = nh_valid_dump_req(cb->nlh, &dev_filter_idx, &master_idx, + &group_filter, cb); + if (err < 0) + return err; + + s_idx = cb->args[0]; + for (node = rb_first(root); node; node = rb_next(node)) { + struct nexthop *nh; + + if (idx < s_idx) + goto cont; + + nh = rb_entry(node, struct nexthop, rb_node); + if (nh_dump_filtered(nh, dev_filter_idx, master_idx, + group_filter, nhm->nh_family)) + goto cont; + + err = nh_fill_node(skb, nh, RTM_NEWNEXTHOP, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI); + if (err < 0) { + if (likely(skb->len)) + goto out; + + goto out_err; + } +cont: + idx++; + } + +out: + err = skb->len; +out_err: + cb->args[0] = idx; + cb->seq = net->nexthop.seq; + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); + + return err; +} + +static void nexthop_sync_mtu(struct net_device *dev, u32 orig_mtu) +{ + unsigned int hash = nh_dev_hashfn(dev->ifindex); + struct net *net = dev_net(dev); + struct hlist_head *head = &net->nexthop.devhash[hash]; + struct hlist_node *n; + struct nh_info *nhi; + + hlist_for_each_entry_safe(nhi, n, head, dev_hash) { + if (nhi->fib_nhc.nhc_dev == dev) { + if (nhi->family == AF_INET) + fib_nhc_update_mtu(&nhi->fib_nhc, dev->mtu, + orig_mtu); + } + } +} + +/* rtnl */ +static int nh_netdev_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_info_ext *info_ext; + + switch (event) { + case NETDEV_DOWN: + case NETDEV_UNREGISTER: + nexthop_flush_dev(dev); + break; + case NETDEV_CHANGE: + if (!(dev_get_flags(dev) & (IFF_RUNNING | IFF_LOWER_UP))) + nexthop_flush_dev(dev); + break; + case NETDEV_CHANGEMTU: + info_ext = ptr; + nexthop_sync_mtu(dev, info_ext->ext.mtu); + rt_cache_flush(dev_net(dev)); + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block nh_netdev_notifier = { + .notifier_call = nh_netdev_event, +}; + +static void __net_exit nexthop_net_exit(struct net *net) +{ + rtnl_lock(); + flush_all_nexthops(net); + rtnl_unlock(); + kfree(net->nexthop.devhash); +} + +static int __net_init nexthop_net_init(struct net *net) +{ + size_t sz = sizeof(struct hlist_head) * NH_DEV_HASHSIZE; + + net->nexthop.rb_root = RB_ROOT; + net->nexthop.devhash = kzalloc(sz, GFP_KERNEL); + if (!net->nexthop.devhash) + return -ENOMEM; + + return 0; +} + +static struct pernet_operations nexthop_net_ops = { + .init = nexthop_net_init, + .exit = nexthop_net_exit, +}; + +static int __init nexthop_init(void) +{ + register_pernet_subsys(&nexthop_net_ops); + + register_netdevice_notifier(&nh_netdev_notifier); + + rtnl_register(PF_UNSPEC, RTM_NEWNEXTHOP, rtm_new_nexthop, NULL, 0); + rtnl_register(PF_UNSPEC, RTM_DELNEXTHOP, rtm_del_nexthop, NULL, 0); + rtnl_register(PF_UNSPEC, RTM_GETNEXTHOP, rtm_get_nexthop, + rtm_dump_nexthop, 0); + + rtnl_register(PF_INET, RTM_NEWNEXTHOP, rtm_new_nexthop, NULL, 0); + rtnl_register(PF_INET, RTM_GETNEXTHOP, NULL, rtm_dump_nexthop, 0); + + rtnl_register(PF_INET6, RTM_NEWNEXTHOP, rtm_new_nexthop, NULL, 0); + rtnl_register(PF_INET6, RTM_GETNEXTHOP, NULL, rtm_dump_nexthop, 0); + + return 0; +} +subsys_initcall(nexthop_init); diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 4370f4246e86..80d2ba1b6299 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -68,8 +68,8 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "RAW: inuse %d\n", sock_prot_inuse_get(net, &raw_prot)); seq_printf(seq, "FRAG: inuse %u memory %lu\n", - atomic_read(&net->ipv4.frags.rhashtable.nelems), - frag_mem_limit(&net->ipv4.frags)); + atomic_read(&net->ipv4.fqdir->rhashtable.nelems), + frag_mem_limit(net->ipv4.fqdir)); return 0; } @@ -287,6 +287,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPAckCompressed", LINUX_MIB_TCPACKCOMPRESSED), SNMP_MIB_ITEM("TCPZeroWindowDrop", LINUX_MIB_TCPZEROWINDOWDROP), SNMP_MIB_ITEM("TCPRcvQDrop", LINUX_MIB_TCPRCVQDROP), + SNMP_MIB_ITEM("TCPFastOpenPassiveAltKey", LINUX_MIB_TCPFASTOPENPASSIVEALTKEY), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 6cb7cff22db9..0700a7d59811 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -95,6 +95,7 @@ #include <net/inetpeer.h> #include <net/sock.h> #include <net/ip_fib.h> +#include <net/nexthop.h> #include <net/arp.h> #include <net/tcp.h> #include <net/icmp.h> @@ -1580,7 +1581,7 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, ip_dst_init_metrics(&rt->dst, fi->fib_metrics); #ifdef CONFIG_IP_ROUTE_CLASSID - { + if (nhc->nhc_family == AF_INET) { struct fib_nh *nh; nh = container_of(nhc, struct fib_nh, nh_common); @@ -1946,7 +1947,7 @@ static int ip_mkroute_input(struct sk_buff *skb, struct flow_keys *hkeys) { #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (res->fi && res->fi->fib_nhs > 1) { + if (res->fi && fib_info_num_path(res->fi) > 1) { int h = fib_multipath_hash(res->fi->fib_net, NULL, skb, hkeys); fib_select_multipath(res, h); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 875867b64d6a..90f09e47198b 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -277,55 +277,97 @@ static int proc_allowed_congestion_control(struct ctl_table *ctl, return ret; } +static int sscanf_key(char *buf, __le32 *key) +{ + u32 user_key[4]; + int i, ret = 0; + + if (sscanf(buf, "%x-%x-%x-%x", user_key, user_key + 1, + user_key + 2, user_key + 3) != 4) { + ret = -EINVAL; + } else { + for (i = 0; i < ARRAY_SIZE(user_key); i++) + key[i] = cpu_to_le32(user_key[i]); + } + pr_debug("proc TFO key set 0x%x-%x-%x-%x <- 0x%s: %u\n", + user_key[0], user_key[1], user_key[2], user_key[3], buf, ret); + + return ret; +} + static int proc_tcp_fastopen_key(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(table->data, struct net, ipv4.sysctl_tcp_fastopen); - struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) }; - struct tcp_fastopen_context *ctxt; - u32 user_key[4]; /* 16 bytes, matching TCP_FASTOPEN_KEY_LENGTH */ - __le32 key[4]; - int ret, i; + /* maxlen to print the list of keys in hex (*2), with dashes + * separating doublewords and a comma in between keys. + */ + struct ctl_table tbl = { .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * + 2 * TCP_FASTOPEN_KEY_MAX) + + (TCP_FASTOPEN_KEY_MAX * 5)) }; + struct tcp_fastopen_context *ctx; + u32 user_key[TCP_FASTOPEN_KEY_MAX * 4]; + __le32 key[TCP_FASTOPEN_KEY_MAX * 4]; + char *backup_data; + int ret, i = 0, off = 0, n_keys = 0; tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL); if (!tbl.data) return -ENOMEM; rcu_read_lock(); - ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx); - if (ctxt) - memcpy(key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH); - else - memset(key, 0, sizeof(key)); + ctx = rcu_dereference(net->ipv4.tcp_fastopen_ctx); + if (ctx) { + n_keys = tcp_fastopen_context_len(ctx); + memcpy(&key[0], &ctx->key[0], TCP_FASTOPEN_KEY_LENGTH * n_keys); + } rcu_read_unlock(); - for (i = 0; i < ARRAY_SIZE(key); i++) + if (!n_keys) { + memset(&key[0], 0, TCP_FASTOPEN_KEY_LENGTH); + n_keys = 1; + } + + for (i = 0; i < n_keys * 4; i++) user_key[i] = le32_to_cpu(key[i]); - snprintf(tbl.data, tbl.maxlen, "%08x-%08x-%08x-%08x", - user_key[0], user_key[1], user_key[2], user_key[3]); + for (i = 0; i < n_keys; i++) { + off += snprintf(tbl.data + off, tbl.maxlen - off, + "%08x-%08x-%08x-%08x", + user_key[i * 4], + user_key[i * 4 + 1], + user_key[i * 4 + 2], + user_key[i * 4 + 3]); + if (i + 1 < n_keys) + off += snprintf(tbl.data + off, tbl.maxlen - off, ","); + } + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) { - if (sscanf(tbl.data, "%x-%x-%x-%x", user_key, user_key + 1, - user_key + 2, user_key + 3) != 4) { + backup_data = strchr(tbl.data, ','); + if (backup_data) { + *backup_data = '\0'; + backup_data++; + } + if (sscanf_key(tbl.data, key)) { ret = -EINVAL; goto bad_key; } - - for (i = 0; i < ARRAY_SIZE(user_key); i++) - key[i] = cpu_to_le32(user_key[i]); - + if (backup_data) { + if (sscanf_key(backup_data, key + 4)) { + ret = -EINVAL; + goto bad_key; + } + } tcp_fastopen_reset_cipher(net, NULL, key, + backup_data ? key + 4 : NULL, TCP_FASTOPEN_KEY_LENGTH); } bad_key: - pr_debug("proc FO key set 0x%x-%x-%x-%x <- 0x%s: %u\n", - user_key[0], user_key[1], user_key[2], user_key[3], - (char *)tbl.data, ret); kfree(tbl.data); return ret; } @@ -933,7 +975,12 @@ static struct ctl_table ipv4_net_table[] = { .procname = "tcp_fastopen_key", .mode = 0600, .data = &init_net.ipv4.sysctl_tcp_fastopen, - .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10), + /* maxlen to print the list of keys in hex (*2), with dashes + * separating doublewords and a comma in between keys. + */ + .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * + 2 * TCP_FASTOPEN_KEY_MAX) + + (TCP_FASTOPEN_KEY_MAX * 5)), .proc_handler = proc_tcp_fastopen_key, }, { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f12d500ec85c..bd0856ac680a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2786,15 +2786,24 @@ static int do_tcp_setsockopt(struct sock *sk, int level, return err; } case TCP_FASTOPEN_KEY: { - __u8 key[TCP_FASTOPEN_KEY_LENGTH]; + __u8 key[TCP_FASTOPEN_KEY_BUF_LENGTH]; + __u8 *backup_key = NULL; - if (optlen != sizeof(key)) + /* Allow a backup key as well to facilitate key rotation + * First key is the active one. + */ + if (optlen != TCP_FASTOPEN_KEY_LENGTH && + optlen != TCP_FASTOPEN_KEY_BUF_LENGTH) return -EINVAL; if (copy_from_user(key, optval, optlen)) return -EFAULT; - return tcp_fastopen_reset_cipher(net, sk, key, sizeof(key)); + if (optlen == TCP_FASTOPEN_KEY_BUF_LENGTH) + backup_key = key + TCP_FASTOPEN_KEY_LENGTH; + + return tcp_fastopen_reset_cipher(net, sk, key, backup_key, + TCP_FASTOPEN_KEY_LENGTH); } default: /* fallthru */ @@ -3448,21 +3457,23 @@ static int do_tcp_getsockopt(struct sock *sk, int level, return 0; case TCP_FASTOPEN_KEY: { - __u8 key[TCP_FASTOPEN_KEY_LENGTH]; + __u8 key[TCP_FASTOPEN_KEY_BUF_LENGTH]; struct tcp_fastopen_context *ctx; + unsigned int key_len = 0; if (get_user(len, optlen)) return -EFAULT; rcu_read_lock(); ctx = rcu_dereference(icsk->icsk_accept_queue.fastopenq.ctx); - if (ctx) - memcpy(key, ctx->key, sizeof(key)); - else - len = 0; + if (ctx) { + key_len = tcp_fastopen_context_len(ctx) * + TCP_FASTOPEN_KEY_LENGTH; + memcpy(&key[0], &ctx->key[0], key_len); + } rcu_read_unlock(); - len = min_t(unsigned int, len, sizeof(key)); + len = min_t(unsigned int, len, key_len); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, key, len)) diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 018a48477355..8e1580485c9e 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -30,14 +30,20 @@ void tcp_fastopen_init_key_once(struct net *net) * for a valid cookie, so this is an acceptable risk. */ get_random_bytes(key, sizeof(key)); - tcp_fastopen_reset_cipher(net, NULL, key, sizeof(key)); + tcp_fastopen_reset_cipher(net, NULL, key, NULL, sizeof(key)); } static void tcp_fastopen_ctx_free(struct rcu_head *head) { struct tcp_fastopen_context *ctx = container_of(head, struct tcp_fastopen_context, rcu); - crypto_free_cipher(ctx->tfm); + int i; + + /* We own ctx, thus no need to hold the Fastopen-lock */ + for (i = 0; i < TCP_FASTOPEN_KEY_MAX; i++) { + if (ctx->tfm[i]) + crypto_free_cipher(ctx->tfm[i]); + } kfree(ctx); } @@ -66,33 +72,54 @@ void tcp_fastopen_ctx_destroy(struct net *net) call_rcu(&ctxt->rcu, tcp_fastopen_ctx_free); } +struct tcp_fastopen_context *tcp_fastopen_alloc_ctx(void *primary_key, + void *backup_key, + unsigned int len) +{ + struct tcp_fastopen_context *new_ctx; + void *key = primary_key; + int err, i; + + new_ctx = kmalloc(sizeof(*new_ctx), GFP_KERNEL); + if (!new_ctx) + return ERR_PTR(-ENOMEM); + for (i = 0; i < TCP_FASTOPEN_KEY_MAX; i++) + new_ctx->tfm[i] = NULL; + for (i = 0; i < (backup_key ? 2 : 1); i++) { + new_ctx->tfm[i] = crypto_alloc_cipher("aes", 0, 0); + if (IS_ERR(new_ctx->tfm[i])) { + err = PTR_ERR(new_ctx->tfm[i]); + new_ctx->tfm[i] = NULL; + pr_err("TCP: TFO aes cipher alloc error: %d\n", err); + goto out; + } + err = crypto_cipher_setkey(new_ctx->tfm[i], key, len); + if (err) { + pr_err("TCP: TFO cipher key error: %d\n", err); + goto out; + } + memcpy(&new_ctx->key[i * TCP_FASTOPEN_KEY_LENGTH], key, len); + key = backup_key; + } + return new_ctx; +out: + tcp_fastopen_ctx_free(&new_ctx->rcu); + return ERR_PTR(err); +} + int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk, - void *key, unsigned int len) + void *primary_key, void *backup_key, + unsigned int len) { struct tcp_fastopen_context *ctx, *octx; struct fastopen_queue *q; - int err; + int err = 0; - ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); - if (!ctx) - return -ENOMEM; - ctx->tfm = crypto_alloc_cipher("aes", 0, 0); - - if (IS_ERR(ctx->tfm)) { - err = PTR_ERR(ctx->tfm); -error: kfree(ctx); - pr_err("TCP: TFO aes cipher alloc error: %d\n", err); - return err; + ctx = tcp_fastopen_alloc_ctx(primary_key, backup_key, len); + if (IS_ERR(ctx)) { + err = PTR_ERR(ctx); + goto out; } - err = crypto_cipher_setkey(ctx->tfm, key, len); - if (err) { - pr_err("TCP: TFO cipher key error: %d\n", err); - crypto_free_cipher(ctx->tfm); - goto error; - } - memcpy(ctx->key, key, len); - - spin_lock(&net->ipv4.tcp_fastopen_ctx_lock); if (sk) { q = &inet_csk(sk)->icsk_accept_queue.fastopenq; @@ -108,28 +135,42 @@ error: kfree(ctx); if (octx) call_rcu(&octx->rcu, tcp_fastopen_ctx_free); +out: return err; } -static bool __tcp_fastopen_cookie_gen(struct sock *sk, const void *path, - struct tcp_fastopen_cookie *foc) +static bool __tcp_fastopen_cookie_gen_cipher(struct request_sock *req, + struct sk_buff *syn, + struct crypto_cipher *tfm, + struct tcp_fastopen_cookie *foc) { - struct tcp_fastopen_context *ctx; - bool ok = false; - - rcu_read_lock(); + if (req->rsk_ops->family == AF_INET) { + const struct iphdr *iph = ip_hdr(syn); + __be32 path[4] = { iph->saddr, iph->daddr, 0, 0 }; - ctx = rcu_dereference(inet_csk(sk)->icsk_accept_queue.fastopenq.ctx); - if (!ctx) - ctx = rcu_dereference(sock_net(sk)->ipv4.tcp_fastopen_ctx); + crypto_cipher_encrypt_one(tfm, foc->val, (void *)path); + foc->len = TCP_FASTOPEN_COOKIE_SIZE; + return true; + } - if (ctx) { - crypto_cipher_encrypt_one(ctx->tfm, foc->val, path); +#if IS_ENABLED(CONFIG_IPV6) + if (req->rsk_ops->family == AF_INET6) { + const struct ipv6hdr *ip6h = ipv6_hdr(syn); + struct tcp_fastopen_cookie tmp; + struct in6_addr *buf; + int i; + + crypto_cipher_encrypt_one(tfm, tmp.val, + (void *)&ip6h->saddr); + buf = &tmp.addr; + for (i = 0; i < 4; i++) + buf->s6_addr32[i] ^= ip6h->daddr.s6_addr32[i]; + crypto_cipher_encrypt_one(tfm, foc->val, (void *)buf); foc->len = TCP_FASTOPEN_COOKIE_SIZE; - ok = true; + return true; } - rcu_read_unlock(); - return ok; +#endif + return false; } /* Generate the fastopen cookie by doing aes128 encryption on both @@ -138,37 +179,20 @@ static bool __tcp_fastopen_cookie_gen(struct sock *sk, const void *path, * * XXX (TFO) - refactor when TCP_FASTOPEN_COOKIE_SIZE != AES_BLOCK_SIZE. */ -static bool tcp_fastopen_cookie_gen(struct sock *sk, +static void tcp_fastopen_cookie_gen(struct sock *sk, struct request_sock *req, struct sk_buff *syn, struct tcp_fastopen_cookie *foc) { - if (req->rsk_ops->family == AF_INET) { - const struct iphdr *iph = ip_hdr(syn); - - __be32 path[4] = { iph->saddr, iph->daddr, 0, 0 }; - return __tcp_fastopen_cookie_gen(sk, path, foc); - } - -#if IS_ENABLED(CONFIG_IPV6) - if (req->rsk_ops->family == AF_INET6) { - const struct ipv6hdr *ip6h = ipv6_hdr(syn); - struct tcp_fastopen_cookie tmp; - - if (__tcp_fastopen_cookie_gen(sk, &ip6h->saddr, &tmp)) { - struct in6_addr *buf = &tmp.addr; - int i; + struct tcp_fastopen_context *ctx; - for (i = 0; i < 4; i++) - buf->s6_addr32[i] ^= ip6h->daddr.s6_addr32[i]; - return __tcp_fastopen_cookie_gen(sk, buf, foc); - } - } -#endif - return false; + rcu_read_lock(); + ctx = tcp_fastopen_get_ctx(sk); + if (ctx) + __tcp_fastopen_cookie_gen_cipher(req, syn, ctx->tfm[0], foc); + rcu_read_unlock(); } - /* If an incoming SYN or SYNACK frame contains a payload and/or FIN, * queue this additional data / FIN. */ @@ -212,6 +236,35 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb) tcp_fin(sk); } +/* returns 0 - no key match, 1 for primary, 2 for backup */ +static int tcp_fastopen_cookie_gen_check(struct sock *sk, + struct request_sock *req, + struct sk_buff *syn, + struct tcp_fastopen_cookie *orig, + struct tcp_fastopen_cookie *valid_foc) +{ + struct tcp_fastopen_cookie search_foc = { .len = -1 }; + struct tcp_fastopen_cookie *foc = valid_foc; + struct tcp_fastopen_context *ctx; + int i, ret = 0; + + rcu_read_lock(); + ctx = tcp_fastopen_get_ctx(sk); + if (!ctx) + goto out; + for (i = 0; i < tcp_fastopen_context_len(ctx); i++) { + __tcp_fastopen_cookie_gen_cipher(req, syn, ctx->tfm[i], foc); + if (tcp_fastopen_cookie_match(foc, orig)) { + ret = i + 1; + goto out; + } + foc = &search_foc; + } +out: + rcu_read_unlock(); + return ret; +} + static struct sock *tcp_fastopen_create_child(struct sock *sk, struct sk_buff *skb, struct request_sock *req) @@ -331,6 +384,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, int tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen; struct tcp_fastopen_cookie valid_foc = { .len = -1 }; struct sock *child; + int ret = 0; if (foc->len == 0) /* Client requests a cookie */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENCOOKIEREQD); @@ -346,31 +400,44 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, tcp_fastopen_no_cookie(sk, dst, TFO_SERVER_COOKIE_NOT_REQD)) goto fastopen; - if (foc->len >= 0 && /* Client presents or requests a cookie */ - tcp_fastopen_cookie_gen(sk, req, skb, &valid_foc) && - foc->len == TCP_FASTOPEN_COOKIE_SIZE && - foc->len == valid_foc.len && - !memcmp(foc->val, valid_foc.val, foc->len)) { - /* Cookie is valid. Create a (full) child socket to accept - * the data in SYN before returning a SYN-ACK to ack the - * data. If we fail to create the socket, fall back and - * ack the ISN only but includes the same cookie. - * - * Note: Data-less SYN with valid cookie is allowed to send - * data in SYN_RECV state. - */ + if (foc->len == 0) { + /* Client requests a cookie. */ + tcp_fastopen_cookie_gen(sk, req, skb, &valid_foc); + } else if (foc->len > 0) { + ret = tcp_fastopen_cookie_gen_check(sk, req, skb, foc, + &valid_foc); + if (!ret) { + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPFASTOPENPASSIVEFAIL); + } else { + /* Cookie is valid. Create a (full) child socket to + * accept the data in SYN before returning a SYN-ACK to + * ack the data. If we fail to create the socket, fall + * back and ack the ISN only but includes the same + * cookie. + * + * Note: Data-less SYN with valid cookie is allowed to + * send data in SYN_RECV state. + */ fastopen: - child = tcp_fastopen_create_child(sk, skb, req); - if (child) { - foc->len = -1; + child = tcp_fastopen_create_child(sk, skb, req); + if (child) { + if (ret == 2) { + valid_foc.exp = foc->exp; + *foc = valid_foc; + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPFASTOPENPASSIVEALTKEY); + } else { + foc->len = -1; + } + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPFASTOPENPASSIVE); + return child; + } NET_INC_STATS(sock_net(sk), - LINUX_MIB_TCPFASTOPENPASSIVE); - return child; + LINUX_MIB_TCPFASTOPENPASSIVEFAIL); } - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL); - } else if (foc->len > 0) /* Client presents an invalid cookie */ - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL); - + } valid_foc.exp = foc->exp; *foc = valid_foc; return NULL; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index bc86f9735f45..f059fbd81a84 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -766,7 +766,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) arg.tos = ip_hdr(skb)->tos; arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); local_bh_disable(); - ctl_sk = *this_cpu_ptr(net->ipv4.tcp_sk); + ctl_sk = this_cpu_read(*net->ipv4.tcp_sk); if (sk) ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : sk->sk_mark; @@ -858,7 +858,7 @@ static void tcp_v4_send_ack(const struct sock *sk, arg.tos = tos; arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL); local_bh_disable(); - ctl_sk = *this_cpu_ptr(net->ipv4.tcp_sk); + ctl_sk = this_cpu_read(*net->ipv4.tcp_sk); if (sk) ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : sk->sk_mark; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 7c6228fbf5dd..86de412f1820 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -478,7 +478,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, htonl(INADDR_ANY), hnum, dif, sdif, exact_dif, hslot2, skb); } - if (unlikely(IS_ERR(result))) + if (IS_ERR(result)) return NULL; return result; } diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 06b3e2c1fcdc..0112f64faf69 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -208,7 +208,7 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, gso_skb->destructor = NULL; segs = skb_segment(gso_skb, features); - if (unlikely(IS_ERR_OR_NULL(segs))) { + if (IS_ERR_OR_NULL(segs)) { if (copy_dtor) gso_skb->destructor = sock_wfree; return segs; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 081bb517e40d..521e3203e83a 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2417,9 +2417,13 @@ static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, goto out; for_each_fib6_node_rt_rcu(fn) { - if (rt->fib6_nh.fib_nh_dev->ifindex != dev->ifindex) + /* prefix routes only use builtin fib6_nh */ + if (rt->nh) continue; - if (no_gw && rt->fib6_nh.fib_nh_gw_family) + + if (rt->fib6_nh->fib_nh_dev->ifindex != dev->ifindex) + continue; + if (no_gw && rt->fib6_nh->fib_nh_gw_family) continue; if ((rt->fib6_flags & flags) != flags) continue; @@ -3123,11 +3127,9 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) struct in_device *in_dev = __in_dev_get_rtnl(dev); if (in_dev && (dev->flags & IFF_UP)) { struct in_ifaddr *ifa; - int flag = scope; - for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) { - + in_dev_for_each_ifa_rtnl(ifa, in_dev) { addr.s6_addr32[3] = ifa->ifa_local; if (ifa->ifa_scope == RT_SCOPE_LINK) @@ -6350,16 +6352,17 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val) list_for_each_entry(ifa, &idev->addr_list, if_list) { spin_lock(&ifa->lock); if (ifa->rt) { - struct fib6_info *rt = ifa->rt; + /* host routes only use builtin fib6_nh */ + struct fib6_nh *nh = ifa->rt->fib6_nh; int cpu; rcu_read_lock(); ifa->rt->dst_nopolicy = val ? true : false; - if (rt->rt6i_pcpu) { + if (nh->rt6i_pcpu) { for_each_possible_cpu(cpu) { struct rt6_info **rtp; - rtp = per_cpu_ptr(rt->rt6i_pcpu, cpu); + rtp = per_cpu_ptr(nh->rt6i_pcpu, cpu); addrconf_set_nopolicy(*rtp, val); } } diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 5b1246635e02..783f3c1466da 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -183,6 +183,11 @@ static int eafnosupport_fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, return -EAFNOSUPPORT; } +static int eafnosupport_ip6_del_rt(struct net *net, struct fib6_info *rt) +{ + return -EAFNOSUPPORT; +} + const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { .ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup, .ipv6_route_input = eafnosupport_ipv6_route_input, @@ -192,6 +197,7 @@ const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { .fib6_select_path = eafnosupport_fib6_select_path, .ip6_mtu_from_fib6 = eafnosupport_ip6_mtu_from_fib6, .fib6_nh_init = eafnosupport_fib6_nh_init, + .ip6_del_rt = eafnosupport_ip6_del_rt, }; EXPORT_SYMBOL_GPL(ipv6_stub); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 5352708b7b2d..7382a927d1eb 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -208,7 +208,7 @@ lookup_protocol: np->mc_loop = 1; np->mc_all = 1; np->pmtudisc = IPV6_PMTUDISC_WANT; - np->repflow = net->ipv6.sysctl.flowlabel_reflect; + np->repflow = net->ipv6.sysctl.flowlabel_reflect & 1; sk->sk_ipv6only = net->ipv6.sysctl.bindv6only; /* Init the ipv4 part of the socket since we can have sockets @@ -922,6 +922,9 @@ static const struct ipv6_stub ipv6_stub_impl = { .ip6_mtu_from_fib6 = ip6_mtu_from_fib6, .fib6_nh_init = fib6_nh_init, .fib6_nh_release = fib6_nh_release, + .fib6_update_sernum = fib6_update_sernum_stub, + .fib6_rt_update = fib6_rt_update, + .ip6_del_rt = ip6_del_rt, .udpv6_encap_enable = udpv6_encap_enable, .ndisc_send_na = ndisc_send_na, .nd_tbl = &nd_tbl, diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index bafdd04a768d..3c2c5ef101c7 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -75,9 +75,9 @@ * * On SMP we have one ICMP socket per-cpu. */ -static inline struct sock *icmpv6_sk(struct net *net) +static struct sock *icmpv6_sk(struct net *net) { - return *this_cpu_ptr(net->ipv6.icmp_sk); + return this_cpu_read(*net->ipv6.icmp_sk); } static int icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index b2a55f300318..cf60fae9533b 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -174,7 +174,7 @@ struct sock *inet6_lookup_listener(struct net *net, saddr, sport, &in6addr_any, hnum, dif, sdif); done: - if (unlikely(IS_ERR(result))) + if (IS_ERR(result)) return NULL; return result; } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 9180c8b6f764..17dcc916eb63 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -143,20 +143,19 @@ static __be32 addr_bit_set(const void *token, int fn_bit) addr[fn_bit >> 5]; } -struct fib6_info *fib6_info_alloc(gfp_t gfp_flags) +struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh) { struct fib6_info *f6i; + size_t sz = sizeof(*f6i); - f6i = kzalloc(sizeof(*f6i), gfp_flags); - if (!f6i) - return NULL; + if (with_fib6_nh) + sz += sizeof(struct fib6_nh); - f6i->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, gfp_flags); - if (!f6i->rt6i_pcpu) { - kfree(f6i); + f6i = kzalloc(sz, gfp_flags); + if (!f6i) return NULL; - } + /* fib6_siblings is a union with nh_list, so this initializes both */ INIT_LIST_HEAD(&f6i->fib6_siblings); refcount_set(&f6i->fib6_ref, 1); @@ -166,36 +165,15 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags) void fib6_info_destroy_rcu(struct rcu_head *head) { struct fib6_info *f6i = container_of(head, struct fib6_info, rcu); - struct rt6_exception_bucket *bucket; WARN_ON(f6i->fib6_node); - bucket = rcu_dereference_protected(f6i->rt6i_exception_bucket, 1); - kfree(bucket); - - if (f6i->rt6i_pcpu) { - int cpu; - - for_each_possible_cpu(cpu) { - struct rt6_info **ppcpu_rt; - struct rt6_info *pcpu_rt; - - ppcpu_rt = per_cpu_ptr(f6i->rt6i_pcpu, cpu); - pcpu_rt = *ppcpu_rt; - if (pcpu_rt) { - dst_dev_put(&pcpu_rt->dst); - dst_release(&pcpu_rt->dst); - *ppcpu_rt = NULL; - } - } - - free_percpu(f6i->rt6i_pcpu); - } - - fib6_nh_release(&f6i->fib6_nh); + if (f6i->nh) + nexthop_put(f6i->nh); + else + fib6_nh_release(f6i->fib6_nh); ip_fib_metrics_put(f6i->fib6_metrics); - kfree(f6i); } EXPORT_SYMBOL_GPL(fib6_info_destroy_rcu); @@ -389,10 +367,10 @@ static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net, return call_fib6_notifier(nb, net, event_type, &info.info); } -static int call_fib6_entry_notifiers(struct net *net, - enum fib_event_type event_type, - struct fib6_info *rt, - struct netlink_ext_ack *extack) +int call_fib6_entry_notifiers(struct net *net, + enum fib_event_type event_type, + struct fib6_info *rt, + struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { .info.extack = extack, @@ -895,16 +873,14 @@ insert_above: return ln; } -static void fib6_drop_pcpu_from(struct fib6_info *f6i, - const struct fib6_table *table) +static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh, + const struct fib6_info *match, + const struct fib6_table *table) { int cpu; - /* Make sure rt6_make_pcpu_route() wont add other percpu routes - * while we are cleaning them here. - */ - f6i->fib6_destroying = 1; - mb(); /* paired with the cmpxchg() in rt6_make_pcpu_route() */ + if (!fib6_nh->rt6i_pcpu) + return; /* release the reference to this fib entry from * all of its cached pcpu routes @@ -913,9 +889,15 @@ static void fib6_drop_pcpu_from(struct fib6_info *f6i, struct rt6_info **ppcpu_rt; struct rt6_info *pcpu_rt; - ppcpu_rt = per_cpu_ptr(f6i->rt6i_pcpu, cpu); + ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu); pcpu_rt = *ppcpu_rt; - if (pcpu_rt) { + + /* only dropping the 'from' reference if the cached route + * is using 'match'. The cached pcpu_rt->from only changes + * from a fib6_info to NULL (ip6_dst_destroy); it can never + * change from one fib6_info reference to another + */ + if (pcpu_rt && rcu_access_pointer(pcpu_rt->from) == match) { struct fib6_info *from; from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL); @@ -924,13 +906,30 @@ static void fib6_drop_pcpu_from(struct fib6_info *f6i, } } +static void fib6_drop_pcpu_from(struct fib6_info *f6i, + const struct fib6_table *table) +{ + struct fib6_nh *fib6_nh; + + /* Make sure rt6_make_pcpu_route() wont add other percpu routes + * while we are cleaning them here. + */ + f6i->fib6_destroying = 1; + mb(); /* paired with the cmpxchg() in rt6_make_pcpu_route() */ + + fib6_nh = f6i->fib6_nh; + __fib6_drop_pcpu_from(fib6_nh, f6i, table); +} + static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn, struct net *net) { struct fib6_table *table = rt->fib6_table; - if (rt->rt6i_pcpu) - fib6_drop_pcpu_from(rt, table); + fib6_drop_pcpu_from(rt, table); + + if (rt->nh && !list_empty(&rt->nh_list)) + list_del_init(&rt->nh_list); if (refcount_read(&rt->fib6_ref) != 1) { /* This route is used as dummy address holder in some split @@ -1218,6 +1217,14 @@ void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt) __fib6_update_sernum_upto_root(rt, fib6_new_sernum(net)); } +/* allow ipv4 to update sernum via ipv6_stub */ +void fib6_update_sernum_stub(struct net *net, struct fib6_info *f6i) +{ + spin_lock_bh(&f6i->fib6_table->tb6_lock); + fib6_update_sernum_upto_root(net, f6i); + spin_unlock_bh(&f6i->fib6_table->tb6_lock); +} + /* * Add routing information to the routing tree. * <destination addr>/<source addr> @@ -1331,6 +1338,8 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, err = fib6_add_rt2node(fn, rt, info, extack); if (!err) { + if (rt->nh) + list_add(&rt->nh_list, &rt->nh->f6i_list); __fib6_update_sernum_upto_root(rt, sernum); fib6_start_gc(info->nl_net, rt); } @@ -2292,9 +2301,13 @@ static int ipv6_route_seq_show(struct seq_file *seq, void *v) { struct fib6_info *rt = v; struct ipv6_route_iter *iter = seq->private; + struct fib6_nh *fib6_nh = rt->fib6_nh; unsigned int flags = rt->fib6_flags; const struct net_device *dev; + if (rt->nh) + fib6_nh = nexthop_fib6_nh(rt->nh); + seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen); #ifdef CONFIG_IPV6_SUBTREES @@ -2302,14 +2315,14 @@ static int ipv6_route_seq_show(struct seq_file *seq, void *v) #else seq_puts(seq, "00000000000000000000000000000000 00 "); #endif - if (rt->fib6_nh.fib_nh_gw_family) { + if (fib6_nh->fib_nh_gw_family) { flags |= RTF_GATEWAY; - seq_printf(seq, "%pi6", &rt->fib6_nh.fib_nh_gw6); + seq_printf(seq, "%pi6", &fib6_nh->fib_nh_gw6); } else { seq_puts(seq, "00000000000000000000000000000000"); } - dev = rt->fib6_nh.fib_nh_dev; + dev = fib6_nh->fib_nh_dev; seq_printf(seq, " %08x %08x %08x %08x %8s\n", rt->fib6_metric, refcount_read(&rt->fib6_ref), 0, flags, dev ? dev->name : ""); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 934c88f128ab..0eb88d1cd61a 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -124,16 +124,8 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * return -EINVAL; } -static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) +static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - int ret; - - ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); - if (ret) { - kfree_skb(skb); - return ret; - } - #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ if (skb_dst(skb)->xfrm) { @@ -150,6 +142,22 @@ static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *s return ip6_finish_output2(net, sk, skb); } +static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + int ret; + + ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); + switch (ret) { + case NET_XMIT_SUCCESS: + return __ip6_finish_output(net, sk, skb); + case NET_XMIT_CN: + return __ip6_finish_output(net, sk, skb) ? : ret; + default: + kfree_skb(skb); + return ret; + } +} + int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; @@ -588,6 +596,169 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) skb_copy_secmark(to, from); } +int ip6_fraglist_init(struct sk_buff *skb, unsigned int hlen, u8 *prevhdr, + u8 nexthdr, __be32 frag_id, + struct ip6_fraglist_iter *iter) +{ + unsigned int first_len; + struct frag_hdr *fh; + + /* BUILD HEADER */ + *prevhdr = NEXTHDR_FRAGMENT; + iter->tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC); + if (!iter->tmp_hdr) + return -ENOMEM; + + iter->frag = skb_shinfo(skb)->frag_list; + skb_frag_list_init(skb); + + iter->offset = 0; + iter->hlen = hlen; + iter->frag_id = frag_id; + iter->nexthdr = nexthdr; + + __skb_pull(skb, hlen); + fh = __skb_push(skb, sizeof(struct frag_hdr)); + __skb_push(skb, hlen); + skb_reset_network_header(skb); + memcpy(skb_network_header(skb), iter->tmp_hdr, hlen); + + fh->nexthdr = nexthdr; + fh->reserved = 0; + fh->frag_off = htons(IP6_MF); + fh->identification = frag_id; + + first_len = skb_pagelen(skb); + skb->data_len = first_len - skb_headlen(skb); + skb->len = first_len; + ipv6_hdr(skb)->payload_len = htons(first_len - sizeof(struct ipv6hdr)); + + return 0; +} +EXPORT_SYMBOL(ip6_fraglist_init); + +void ip6_fraglist_prepare(struct sk_buff *skb, + struct ip6_fraglist_iter *iter) +{ + struct sk_buff *frag = iter->frag; + unsigned int hlen = iter->hlen; + struct frag_hdr *fh; + + frag->ip_summed = CHECKSUM_NONE; + skb_reset_transport_header(frag); + fh = __skb_push(frag, sizeof(struct frag_hdr)); + __skb_push(frag, hlen); + skb_reset_network_header(frag); + memcpy(skb_network_header(frag), iter->tmp_hdr, hlen); + iter->offset += skb->len - hlen - sizeof(struct frag_hdr); + fh->nexthdr = iter->nexthdr; + fh->reserved = 0; + fh->frag_off = htons(iter->offset); + if (frag->next) + fh->frag_off |= htons(IP6_MF); + fh->identification = iter->frag_id; + ipv6_hdr(frag)->payload_len = htons(frag->len - sizeof(struct ipv6hdr)); + ip6_copy_metadata(frag, skb); +} +EXPORT_SYMBOL(ip6_fraglist_prepare); + +void ip6_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int mtu, + unsigned short needed_tailroom, int hdr_room, u8 *prevhdr, + u8 nexthdr, __be32 frag_id, struct ip6_frag_state *state) +{ + state->prevhdr = prevhdr; + state->nexthdr = nexthdr; + state->frag_id = frag_id; + + state->hlen = hlen; + state->mtu = mtu; + + state->left = skb->len - hlen; /* Space per frame */ + state->ptr = hlen; /* Where to start from */ + + state->hroom = hdr_room; + state->troom = needed_tailroom; + + state->offset = 0; +} +EXPORT_SYMBOL(ip6_frag_init); + +struct sk_buff *ip6_frag_next(struct sk_buff *skb, struct ip6_frag_state *state) +{ + u8 *prevhdr = state->prevhdr, *fragnexthdr_offset; + struct sk_buff *frag; + struct frag_hdr *fh; + unsigned int len; + + len = state->left; + /* IF: it doesn't fit, use 'mtu' - the data space left */ + if (len > state->mtu) + len = state->mtu; + /* IF: we are not sending up to and including the packet end + then align the next start on an eight byte boundary */ + if (len < state->left) + len &= ~7; + + /* Allocate buffer */ + frag = alloc_skb(len + state->hlen + sizeof(struct frag_hdr) + + state->hroom + state->troom, GFP_ATOMIC); + if (!frag) + return ERR_PTR(-ENOMEM); + + /* + * Set up data on packet + */ + + ip6_copy_metadata(frag, skb); + skb_reserve(frag, state->hroom); + skb_put(frag, len + state->hlen + sizeof(struct frag_hdr)); + skb_reset_network_header(frag); + fh = (struct frag_hdr *)(skb_network_header(frag) + state->hlen); + frag->transport_header = (frag->network_header + state->hlen + + sizeof(struct frag_hdr)); + + /* + * Charge the memory for the fragment to any owner + * it might possess + */ + if (skb->sk) + skb_set_owner_w(frag, skb->sk); + + /* + * Copy the packet header into the new buffer. + */ + skb_copy_from_linear_data(skb, skb_network_header(frag), state->hlen); + + fragnexthdr_offset = skb_network_header(frag); + fragnexthdr_offset += prevhdr - skb_network_header(skb); + *fragnexthdr_offset = NEXTHDR_FRAGMENT; + + /* + * Build fragment header. + */ + fh->nexthdr = state->nexthdr; + fh->reserved = 0; + fh->identification = state->frag_id; + + /* + * Copy a block of the IP datagram. + */ + BUG_ON(skb_copy_bits(skb, state->ptr, skb_transport_header(frag), + len)); + state->left -= len; + + fh->frag_off = htons(state->offset); + if (state->left > 0) + fh->frag_off |= htons(IP6_MF); + ipv6_hdr(frag)->payload_len = htons(frag->len - sizeof(struct ipv6hdr)); + + state->ptr += len; + state->offset += len; + + return frag; +} +EXPORT_SYMBOL(ip6_frag_next); + int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) { @@ -595,12 +766,10 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? inet6_sk(skb->sk) : NULL; - struct ipv6hdr *tmp_hdr; - struct frag_hdr *fh; - unsigned int mtu, hlen, left, len, nexthdr_offset; - int hroom, troom; + struct ip6_frag_state state; + unsigned int mtu, hlen, nexthdr_offset; + int hroom, err = 0; __be32 frag_id; - int ptr, offset = 0, err = 0; u8 *prevhdr, nexthdr = 0; err = ip6_find_1stfragopt(skb, &prevhdr); @@ -647,6 +816,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, hroom = LL_RESERVED_SPACE(rt->dst.dev); if (skb_has_frag_list(skb)) { unsigned int first_len = skb_pagelen(skb); + struct ip6_fraglist_iter iter; struct sk_buff *frag2; if (first_len - hlen > mtu || @@ -674,74 +844,29 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, skb->truesize -= frag->truesize; } - err = 0; - offset = 0; - /* BUILD HEADER */ - - *prevhdr = NEXTHDR_FRAGMENT; - tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC); - if (!tmp_hdr) { - err = -ENOMEM; + err = ip6_fraglist_init(skb, hlen, prevhdr, nexthdr, frag_id, + &iter); + if (err < 0) goto fail; - } - frag = skb_shinfo(skb)->frag_list; - skb_frag_list_init(skb); - - __skb_pull(skb, hlen); - fh = __skb_push(skb, sizeof(struct frag_hdr)); - __skb_push(skb, hlen); - skb_reset_network_header(skb); - memcpy(skb_network_header(skb), tmp_hdr, hlen); - - fh->nexthdr = nexthdr; - fh->reserved = 0; - fh->frag_off = htons(IP6_MF); - fh->identification = frag_id; - - first_len = skb_pagelen(skb); - skb->data_len = first_len - skb_headlen(skb); - skb->len = first_len; - ipv6_hdr(skb)->payload_len = htons(first_len - - sizeof(struct ipv6hdr)); for (;;) { /* Prepare header of the next frame, * before previous one went down. */ - if (frag) { - frag->ip_summed = CHECKSUM_NONE; - skb_reset_transport_header(frag); - fh = __skb_push(frag, sizeof(struct frag_hdr)); - __skb_push(frag, hlen); - skb_reset_network_header(frag); - memcpy(skb_network_header(frag), tmp_hdr, - hlen); - offset += skb->len - hlen - sizeof(struct frag_hdr); - fh->nexthdr = nexthdr; - fh->reserved = 0; - fh->frag_off = htons(offset); - if (frag->next) - fh->frag_off |= htons(IP6_MF); - fh->identification = frag_id; - ipv6_hdr(frag)->payload_len = - htons(frag->len - - sizeof(struct ipv6hdr)); - ip6_copy_metadata(frag, skb); - } + if (iter.frag) + ip6_fraglist_prepare(skb, &iter); err = output(net, sk, skb); if (!err) IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGCREATES); - if (err || !frag) + if (err || !iter.frag) break; - skb = frag; - frag = skb->next; - skb_mark_not_on_list(skb); + skb = ip6_fraglist_next(&iter); } - kfree(tmp_hdr); + kfree(iter.tmp_hdr); if (err == 0) { IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), @@ -749,7 +874,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, return 0; } - kfree_skb_list(frag); + kfree_skb_list(iter.frag); IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGFAILS); @@ -766,91 +891,26 @@ slow_path_clean: } slow_path: - left = skb->len - hlen; /* Space per frame */ - ptr = hlen; /* Where to start from */ - /* * Fragment the datagram. */ - troom = rt->dst.dev->needed_tailroom; + ip6_frag_init(skb, hlen, mtu, rt->dst.dev->needed_tailroom, + LL_RESERVED_SPACE(rt->dst.dev), prevhdr, nexthdr, frag_id, + &state); /* * Keep copying data until we run out. */ - while (left > 0) { - u8 *fragnexthdr_offset; - - len = left; - /* IF: it doesn't fit, use 'mtu' - the data space left */ - if (len > mtu) - len = mtu; - /* IF: we are not sending up to and including the packet end - then align the next start on an eight byte boundary */ - if (len < left) { - len &= ~7; - } - /* Allocate buffer */ - frag = alloc_skb(len + hlen + sizeof(struct frag_hdr) + - hroom + troom, GFP_ATOMIC); - if (!frag) { - err = -ENOMEM; + while (state.left > 0) { + frag = ip6_frag_next(skb, &state); + if (IS_ERR(frag)) { + err = PTR_ERR(frag); goto fail; } /* - * Set up data on packet - */ - - ip6_copy_metadata(frag, skb); - skb_reserve(frag, hroom); - skb_put(frag, len + hlen + sizeof(struct frag_hdr)); - skb_reset_network_header(frag); - fh = (struct frag_hdr *)(skb_network_header(frag) + hlen); - frag->transport_header = (frag->network_header + hlen + - sizeof(struct frag_hdr)); - - /* - * Charge the memory for the fragment to any owner - * it might possess - */ - if (skb->sk) - skb_set_owner_w(frag, skb->sk); - - /* - * Copy the packet header into the new buffer. - */ - skb_copy_from_linear_data(skb, skb_network_header(frag), hlen); - - fragnexthdr_offset = skb_network_header(frag); - fragnexthdr_offset += prevhdr - skb_network_header(skb); - *fragnexthdr_offset = NEXTHDR_FRAGMENT; - - /* - * Build fragment header. - */ - fh->nexthdr = nexthdr; - fh->reserved = 0; - fh->identification = frag_id; - - /* - * Copy a block of the IP datagram. - */ - BUG_ON(skb_copy_bits(skb, ptr, skb_transport_header(frag), - len)); - left -= len; - - fh->frag_off = htons(offset); - if (left > 0) - fh->frag_off |= htons(IP6_MF); - ipv6_hdr(frag)->payload_len = htons(frag->len - - sizeof(struct ipv6hdr)); - - ptr += len; - offset += len; - - /* * Put this fragment into the sending queue. */ err = output(net, sk, frag); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 09dd2edfb868..083cc1c94cd3 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1285,12 +1285,11 @@ static void ndisc_router_discovery(struct sk_buff *skb) !in6_dev->cnf.accept_ra_rtr_pref) pref = ICMPV6_ROUTER_PREF_MEDIUM; #endif - + /* routes added from RAs do not use nexthop objects */ rt = rt6_get_dflt_router(net, &ipv6_hdr(skb)->saddr, skb->dev); - if (rt) { - neigh = ip6_neigh_lookup(&rt->fib6_nh.fib_nh_gw6, - rt->fib6_nh.fib_nh_dev, NULL, + neigh = ip6_neigh_lookup(&rt->fib6_nh->fib_nh_gw6, + rt->fib6_nh->fib_nh_dev, NULL, &ipv6_hdr(skb)->saddr); if (!neigh) { ND_PRINTK(0, err, @@ -1319,8 +1318,8 @@ static void ndisc_router_discovery(struct sk_buff *skb) return; } - neigh = ip6_neigh_lookup(&rt->fib6_nh.fib_nh_gw6, - rt->fib6_nh.fib_nh_dev, NULL, + neigh = ip6_neigh_lookup(&rt->fib6_nh->fib_nh_gw6, + rt->fib6_nh->fib_nh_dev, NULL, &ipv6_hdr(skb)->saddr); if (!neigh) { ND_PRINTK(0, err, diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 1240ccd57f39..d9673e10c60c 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -16,6 +16,9 @@ #include <net/ip6_route.h> #include <net/xfrm.h> #include <net/netfilter/nf_queue.h> +#include <net/netfilter/nf_conntrack_bridge.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> +#include "../bridge/br_private.h" int ip6_route_me_harder(struct net *net, struct sk_buff *skb) { @@ -109,6 +112,122 @@ int __nf_ip6_route(struct net *net, struct dst_entry **dst, } EXPORT_SYMBOL_GPL(__nf_ip6_route); +int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, + struct nf_ct_bridge_frag_data *data, + int (*output)(struct net *, struct sock *sk, + const struct nf_ct_bridge_frag_data *data, + struct sk_buff *)) +{ + int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size; + struct ip6_frag_state state; + u8 *prevhdr, nexthdr = 0; + unsigned int mtu, hlen; + int hroom, err = 0; + __be32 frag_id; + + err = ip6_find_1stfragopt(skb, &prevhdr); + if (err < 0) + goto blackhole; + hlen = err; + nexthdr = *prevhdr; + + mtu = skb->dev->mtu; + if (frag_max_size > mtu || + frag_max_size < IPV6_MIN_MTU) + goto blackhole; + + mtu = frag_max_size; + if (mtu < hlen + sizeof(struct frag_hdr) + 8) + goto blackhole; + mtu -= hlen + sizeof(struct frag_hdr); + + frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr, + &ipv6_hdr(skb)->saddr); + + if (skb->ip_summed == CHECKSUM_PARTIAL && + (err = skb_checksum_help(skb))) + goto blackhole; + + hroom = LL_RESERVED_SPACE(skb->dev); + if (skb_has_frag_list(skb)) { + unsigned int first_len = skb_pagelen(skb); + struct ip6_fraglist_iter iter; + struct sk_buff *frag2; + + if (first_len - hlen > mtu || + skb_headroom(skb) < (hroom + sizeof(struct frag_hdr))) + goto blackhole; + + if (skb_cloned(skb)) + goto slow_path; + + skb_walk_frags(skb, frag2) { + if (frag2->len > mtu || + skb_headroom(frag2) < (hlen + hroom + sizeof(struct frag_hdr))) + goto blackhole; + + /* Partially cloned skb? */ + if (skb_shared(frag2)) + goto slow_path; + } + + err = ip6_fraglist_init(skb, hlen, prevhdr, nexthdr, frag_id, + &iter); + if (err < 0) + goto blackhole; + + for (;;) { + /* Prepare header of the next frame, + * before previous one went down. + */ + if (iter.frag) + ip6_fraglist_prepare(skb, &iter); + + err = output(net, sk, data, skb); + if (err || !iter.frag) + break; + + skb = ip6_fraglist_next(&iter); + } + + kfree(iter.tmp_hdr); + if (!err) + return 0; + + kfree_skb_list(iter.frag); + return err; + } +slow_path: + /* This is a linearized skbuff, the original geometry is lost for us. + * This may also be a clone skbuff, we could preserve the geometry for + * the copies but probably not worth the effort. + */ + ip6_frag_init(skb, hlen, mtu, skb->dev->needed_tailroom, + LL_RESERVED_SPACE(skb->dev), prevhdr, nexthdr, frag_id, + &state); + + while (state.left > 0) { + struct sk_buff *skb2; + + skb2 = ip6_frag_next(skb, &state); + if (IS_ERR(skb2)) { + err = PTR_ERR(skb2); + goto blackhole; + } + + err = output(net, sk, data, skb2); + if (err) + goto blackhole; + } + consume_skb(skb); + return err; + +blackhole: + kfree_skb(skb); + return 0; +} +EXPORT_SYMBOL_GPL(br_ip6_fragment); + static const struct nf_ipv6_ops ipv6ops = { #if IS_MODULE(CONFIG_IPV6) .chk_addr = ipv6_chk_addr, @@ -119,6 +238,10 @@ static const struct nf_ipv6_ops ipv6ops = { .route_input = ip6_route_input, .fragment = ip6_fragment, .reroute = nf_ip6_reroute, +#if IS_MODULE(CONFIG_IPV6) + .br_defrag = nf_ct_frag6_gather, + .br_fragment = br_ip6_fragment, +#endif }; int __init ipv6_netfilter_init(void) diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 6f3abbb9e093..b8962d4d6ae6 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -54,26 +54,21 @@ static struct inet_frags nf_frags; static struct ctl_table nf_ct_frag6_sysctl_table[] = { { .procname = "nf_conntrack_frag6_timeout", - .data = &init_net.nf_frag.frags.timeout, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "nf_conntrack_frag6_low_thresh", - .data = &init_net.nf_frag.frags.low_thresh, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, - .extra2 = &init_net.nf_frag.frags.high_thresh }, { .procname = "nf_conntrack_frag6_high_thresh", - .data = &init_net.nf_frag.frags.high_thresh, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, - .extra1 = &init_net.nf_frag.frags.low_thresh }, { } }; @@ -89,15 +84,15 @@ static int nf_ct_frag6_sysctl_register(struct net *net) GFP_KERNEL); if (table == NULL) goto err_alloc; - - table[0].data = &net->nf_frag.frags.timeout; - table[1].data = &net->nf_frag.frags.low_thresh; - table[1].extra2 = &net->nf_frag.frags.high_thresh; - table[2].data = &net->nf_frag.frags.high_thresh; - table[2].extra1 = &net->nf_frag.frags.low_thresh; - table[2].extra2 = &init_net.nf_frag.frags.high_thresh; } + table[0].data = &net->nf_frag.fqdir->timeout; + table[1].data = &net->nf_frag.fqdir->low_thresh; + table[1].extra2 = &net->nf_frag.fqdir->high_thresh; + table[2].data = &net->nf_frag.fqdir->high_thresh; + table[2].extra1 = &net->nf_frag.fqdir->low_thresh; + table[2].extra2 = &init_net.nf_frag.fqdir->high_thresh; + hdr = register_net_sysctl(net, "net/netfilter", table); if (hdr == NULL) goto err_reg; @@ -144,12 +139,10 @@ static void nf_ct_frag6_expire(struct timer_list *t) { struct inet_frag_queue *frag = from_timer(frag, t, timer); struct frag_queue *fq; - struct net *net; fq = container_of(frag, struct frag_queue, q); - net = container_of(fq->q.net, struct net, nf_frag.frags); - ip6frag_expire_frag_queue(net, fq); + ip6frag_expire_frag_queue(fq->q.fqdir->net, fq); } /* Creation primitives. */ @@ -165,7 +158,7 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user, }; struct inet_frag_queue *q; - q = inet_frag_find(&net->nf_frag.frags, &key); + q = inet_frag_find(net->nf_frag.fqdir, &key); if (!q) return NULL; @@ -272,7 +265,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, fq->ecn |= ecn; if (payload_len > fq->q.max_size) fq->q.max_size = payload_len; - add_frag_mem_limit(fq->q.net, skb->truesize); + add_frag_mem_limit(fq->q.fqdir, skb->truesize); /* The first fragment. * nhoffset is obtained from the first fragment, of course. @@ -492,24 +485,24 @@ static int nf_ct_net_init(struct net *net) { int res; - net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH; - net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH; - net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT; - net->nf_frag.frags.f = &nf_frags; - - res = inet_frags_init_net(&net->nf_frag.frags); + res = fqdir_init(&net->nf_frag.fqdir, &nf_frags, net); if (res < 0) return res; + + net->nf_frag.fqdir->high_thresh = IPV6_FRAG_HIGH_THRESH; + net->nf_frag.fqdir->low_thresh = IPV6_FRAG_LOW_THRESH; + net->nf_frag.fqdir->timeout = IPV6_FRAG_TIMEOUT; + res = nf_ct_frag6_sysctl_register(net); if (res < 0) - inet_frags_exit_net(&net->nf_frag.frags); + fqdir_exit(net->nf_frag.fqdir); return res; } static void nf_ct_net_exit(struct net *net) { nf_ct_frags6_sysctl_unregister(net); - inet_frags_exit_net(&net->nf_frag.frags); + fqdir_exit(net->nf_frag.fqdir); } static struct pernet_operations nf_ct_net_ops = { diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 4a8da679866e..bbff3e02e302 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -44,8 +44,8 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "RAW6: inuse %d\n", sock_prot_inuse_get(net, &rawv6_prot)); seq_printf(seq, "FRAG6: inuse %u memory %lu\n", - atomic_read(&net->ipv6.frags.rhashtable.nelems), - frag_mem_limit(&net->ipv6.frags)); + atomic_read(&net->ipv6.fqdir->rhashtable.nelems), + frag_mem_limit(net->ipv6.fqdir)); return 0; } diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 22369694b2fb..3f1f170cc9e8 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -72,12 +72,10 @@ static void ip6_frag_expire(struct timer_list *t) { struct inet_frag_queue *frag = from_timer(frag, t, timer); struct frag_queue *fq; - struct net *net; fq = container_of(frag, struct frag_queue, q); - net = container_of(fq->q.net, struct net, ipv6.frags); - ip6frag_expire_frag_queue(net, fq); + ip6frag_expire_frag_queue(fq->q.fqdir->net, fq); } static struct frag_queue * @@ -96,7 +94,7 @@ fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif) IPV6_ADDR_LINKLOCAL))) key.iif = 0; - q = inet_frag_find(&net->ipv6.frags, &key); + q = inet_frag_find(net->ipv6.fqdir, &key); if (!q) return NULL; @@ -196,7 +194,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, fq->q.stamp = skb->tstamp; fq->q.meat += skb->len; fq->ecn |= ecn; - add_frag_mem_limit(fq->q.net, skb->truesize); + add_frag_mem_limit(fq->q.fqdir, skb->truesize); fragsize = -skb_network_offset(skb) + skb->len; if (fragsize > fq->q.max_size) @@ -250,7 +248,7 @@ err: static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb, struct sk_buff *prev_tail, struct net_device *dev) { - struct net *net = container_of(fq->q.net, struct net, ipv6.frags); + struct net *net = fq->q.fqdir->net; unsigned int nhoff; void *reasm_data; int payload_len; @@ -397,23 +395,18 @@ static const struct inet6_protocol frag_protocol = { static struct ctl_table ip6_frags_ns_ctl_table[] = { { .procname = "ip6frag_high_thresh", - .data = &init_net.ipv6.frags.high_thresh, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, - .extra1 = &init_net.ipv6.frags.low_thresh }, { .procname = "ip6frag_low_thresh", - .data = &init_net.ipv6.frags.low_thresh, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, - .extra2 = &init_net.ipv6.frags.high_thresh }, { .procname = "ip6frag_time", - .data = &init_net.ipv6.frags.timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -445,12 +438,12 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net) if (!table) goto err_alloc; - table[0].data = &net->ipv6.frags.high_thresh; - table[0].extra1 = &net->ipv6.frags.low_thresh; - table[1].data = &net->ipv6.frags.low_thresh; - table[1].extra2 = &net->ipv6.frags.high_thresh; - table[2].data = &net->ipv6.frags.timeout; } + table[0].data = &net->ipv6.fqdir->high_thresh; + table[0].extra1 = &net->ipv6.fqdir->low_thresh; + table[1].data = &net->ipv6.fqdir->low_thresh; + table[1].extra2 = &net->ipv6.fqdir->high_thresh; + table[2].data = &net->ipv6.fqdir->timeout; hdr = register_net_sysctl(net, "net/ipv6", table); if (!hdr) @@ -513,25 +506,24 @@ static int __net_init ipv6_frags_init_net(struct net *net) { int res; - net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH; - net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH; - net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT; - net->ipv6.frags.f = &ip6_frags; - - res = inet_frags_init_net(&net->ipv6.frags); + res = fqdir_init(&net->ipv6.fqdir, &ip6_frags, net); if (res < 0) return res; + net->ipv6.fqdir->high_thresh = IPV6_FRAG_HIGH_THRESH; + net->ipv6.fqdir->low_thresh = IPV6_FRAG_LOW_THRESH; + net->ipv6.fqdir->timeout = IPV6_FRAG_TIMEOUT; + res = ip6_frags_ns_sysctl_register(net); if (res < 0) - inet_frags_exit_net(&net->ipv6.frags); + fqdir_exit(net->ipv6.fqdir); return res; } static void __net_exit ipv6_frags_exit_net(struct net *net) { ip6_frags_ns_sysctl_unregister(net); - inet_frags_exit_net(&net->ipv6.frags); + fqdir_exit(net->ipv6.fqdir); } static struct pernet_operations ip6_frags_ops = { @@ -587,8 +579,8 @@ err_protocol: void ipv6_frag_exit(void) { - inet_frags_fini(&ip6_frags); ip6_frags_sysctl_unregister(); unregister_pernet_subsys(&ip6_frags_ops); inet6_del_protocol(&frag_protocol, IPPROTO_FRAGMENT); + inet_frags_fini(&ip6_frags); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 0f60eb3a2873..fd0dc18ec574 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -428,21 +428,27 @@ void fib6_select_path(const struct net *net, struct fib6_result *res, struct fib6_info *sibling, *next_sibling; struct fib6_info *match = res->f6i; - if (!match->fib6_nsiblings || have_oif_match) + if ((!match->fib6_nsiblings && !match->nh) || have_oif_match) goto out; /* We might have already computed the hash for ICMPv6 errors. In such * case it will always be non-zero. Otherwise now is the time to do it. */ - if (!fl6->mp_hash) + if (!fl6->mp_hash && + (!match->nh || nexthop_is_multipath(match->nh))) fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL); - if (fl6->mp_hash <= atomic_read(&match->fib6_nh.fib_nh_upper_bound)) + if (unlikely(match->nh)) { + nexthop_path_fib6_result(res, fl6->mp_hash); + return; + } + + if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound)) goto out; list_for_each_entry_safe(sibling, next_sibling, &match->fib6_siblings, fib6_siblings) { - const struct fib6_nh *nh = &sibling->fib6_nh; + const struct fib6_nh *nh = sibling->fib6_nh; int nh_upper_bound; nh_upper_bound = atomic_read(&nh->fib_nh_upper_bound); @@ -456,7 +462,7 @@ void fib6_select_path(const struct net *net, struct fib6_result *res, out: res->f6i = match; - res->nh = &match->fib6_nh; + res->nh = match->fib6_nh; } /* @@ -492,13 +498,19 @@ static void rt6_device_match(struct net *net, struct fib6_result *res, struct fib6_nh *nh; if (!oif && ipv6_addr_any(saddr)) { - nh = &f6i->fib6_nh; + if (unlikely(f6i->nh)) { + nh = nexthop_fib6_nh(f6i->nh); + if (nexthop_is_blackhole(f6i->nh)) + goto out_blackhole; + } else { + nh = f6i->fib6_nh; + } if (!(nh->fib_nh_flags & RTNH_F_DEAD)) goto out; } for (spf6i = f6i; spf6i; spf6i = rcu_dereference(spf6i->fib6_next)) { - nh = &spf6i->fib6_nh; + nh = spf6i->fib6_nh; if (__rt6_device_match(net, nh, saddr, oif, flags)) { res->f6i = spf6i; goto out; @@ -507,19 +519,32 @@ static void rt6_device_match(struct net *net, struct fib6_result *res, if (oif && flags & RT6_LOOKUP_F_IFACE) { res->f6i = net->ipv6.fib6_null_entry; - nh = &res->f6i->fib6_nh; + nh = res->f6i->fib6_nh; goto out; } - nh = &f6i->fib6_nh; + if (unlikely(f6i->nh)) { + nh = nexthop_fib6_nh(f6i->nh); + if (nexthop_is_blackhole(f6i->nh)) + goto out_blackhole; + } else { + nh = f6i->fib6_nh; + } + if (nh->fib_nh_flags & RTNH_F_DEAD) { res->f6i = net->ipv6.fib6_null_entry; - nh = &res->f6i->fib6_nh; + nh = res->f6i->fib6_nh; } out: res->nh = nh; res->fib6_type = res->f6i->fib6_type; res->fib6_flags = res->f6i->fib6_flags; + return; + +out_blackhole: + res->fib6_flags |= RTF_REJECT; + res->fib6_type = RTN_BLACKHOLE; + res->nh = nh; } #ifdef CONFIG_IPV6_ROUTER_PREF @@ -710,7 +735,7 @@ static void __find_rr_leaf(struct fib6_info *f6i_start, if (fib6_check_expired(f6i)) continue; - nh = &f6i->fib6_nh; + nh = f6i->fib6_nh; if (find_match(nh, f6i->fib6_flags, oif, strict, mpri, do_rr)) { res->f6i = f6i; res->nh = nh; @@ -792,7 +817,7 @@ static void rt6_select(struct net *net, struct fib6_node *fn, int oif, out: if (!res->f6i) { res->f6i = net->ipv6.fib6_null_entry; - res->nh = &res->f6i->fib6_nh; + res->nh = res->f6i->fib6_nh; res->fib6_flags = res->f6i->fib6_flags; res->fib6_type = res->f6i->fib6_type; } @@ -1113,6 +1138,8 @@ restart: rt = net->ipv6.ip6_null_entry; dst_hold(&rt->dst); goto out; + } else if (res.fib6_flags & RTF_REJECT) { + goto do_create; } fib6_select_path(net, &res, fl6, fl6->flowi6_oif, @@ -1124,6 +1151,7 @@ restart: if (ip6_hold_safe(net, &rt)) dst_use_noref(&rt->dst, jiffies); } else { +do_create: rt = ip6_create_rt_rcu(&res); } @@ -1264,10 +1292,9 @@ static struct rt6_info *ip6_rt_pcpu_alloc(const struct fib6_result *res) /* It should be called with rcu_read_lock() acquired */ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res) { - struct rt6_info *pcpu_rt, **p; + struct rt6_info *pcpu_rt; - p = this_cpu_ptr(res->f6i->rt6i_pcpu); - pcpu_rt = *p; + pcpu_rt = this_cpu_read(*res->nh->rt6i_pcpu); if (pcpu_rt) ip6_hold_safe(NULL, &pcpu_rt); @@ -1287,7 +1314,7 @@ static struct rt6_info *rt6_make_pcpu_route(struct net *net, } dst_hold(&pcpu_rt->dst); - p = this_cpu_ptr(res->f6i->rt6i_pcpu); + p = this_cpu_ptr(res->nh->rt6i_pcpu); prev = cmpxchg(p, NULL, pcpu_rt); BUG_ON(prev); @@ -1457,25 +1484,74 @@ static unsigned int fib6_mtu(const struct fib6_result *res) return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu); } +#define FIB6_EXCEPTION_BUCKET_FLUSHED 0x1UL + +/* used when the flushed bit is not relevant, only access to the bucket + * (ie., all bucket users except rt6_insert_exception); + * + * called under rcu lock; sometimes called with rt6_exception_lock held + */ +static +struct rt6_exception_bucket *fib6_nh_get_excptn_bucket(const struct fib6_nh *nh, + spinlock_t *lock) +{ + struct rt6_exception_bucket *bucket; + + if (lock) + bucket = rcu_dereference_protected(nh->rt6i_exception_bucket, + lockdep_is_held(lock)); + else + bucket = rcu_dereference(nh->rt6i_exception_bucket); + + /* remove bucket flushed bit if set */ + if (bucket) { + unsigned long p = (unsigned long)bucket; + + p &= ~FIB6_EXCEPTION_BUCKET_FLUSHED; + bucket = (struct rt6_exception_bucket *)p; + } + + return bucket; +} + +static bool fib6_nh_excptn_bucket_flushed(struct rt6_exception_bucket *bucket) +{ + unsigned long p = (unsigned long)bucket; + + return !!(p & FIB6_EXCEPTION_BUCKET_FLUSHED); +} + +/* called with rt6_exception_lock held */ +static void fib6_nh_excptn_bucket_set_flushed(struct fib6_nh *nh, + spinlock_t *lock) +{ + struct rt6_exception_bucket *bucket; + unsigned long p; + + bucket = rcu_dereference_protected(nh->rt6i_exception_bucket, + lockdep_is_held(lock)); + + p = (unsigned long)bucket; + p |= FIB6_EXCEPTION_BUCKET_FLUSHED; + bucket = (struct rt6_exception_bucket *)p; + rcu_assign_pointer(nh->rt6i_exception_bucket, bucket); +} + static int rt6_insert_exception(struct rt6_info *nrt, const struct fib6_result *res) { struct net *net = dev_net(nrt->dst.dev); struct rt6_exception_bucket *bucket; + struct fib6_info *f6i = res->f6i; struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; - struct fib6_info *f6i = res->f6i; + struct fib6_nh *nh = res->nh; int err = 0; spin_lock_bh(&rt6_exception_lock); - if (f6i->exception_bucket_flushed) { - err = -EINVAL; - goto out; - } - - bucket = rcu_dereference_protected(f6i->rt6i_exception_bucket, - lockdep_is_held(&rt6_exception_lock)); + bucket = rcu_dereference_protected(nh->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); if (!bucket) { bucket = kcalloc(FIB6_EXCEPTION_BUCKET_SIZE, sizeof(*bucket), GFP_ATOMIC); @@ -1483,7 +1559,10 @@ static int rt6_insert_exception(struct rt6_info *nrt, err = -ENOMEM; goto out; } - rcu_assign_pointer(f6i->rt6i_exception_bucket, bucket); + rcu_assign_pointer(nh->rt6i_exception_bucket, bucket); + } else if (fib6_nh_excptn_bucket_flushed(bucket)) { + err = -EINVAL; + goto out; } #ifdef CONFIG_IPV6_SUBTREES @@ -1538,7 +1617,7 @@ out: return err; } -void rt6_flush_exceptions(struct fib6_info *rt) +static void fib6_nh_flush_exceptions(struct fib6_nh *nh, struct fib6_info *from) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; @@ -1546,25 +1625,33 @@ void rt6_flush_exceptions(struct fib6_info *rt) int i; spin_lock_bh(&rt6_exception_lock); - /* Prevent rt6_insert_exception() to recreate the bucket list */ - rt->exception_bucket_flushed = 1; - bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, - lockdep_is_held(&rt6_exception_lock)); + bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (!bucket) goto out; + /* Prevent rt6_insert_exception() to recreate the bucket list */ + if (!from) + fib6_nh_excptn_bucket_set_flushed(nh, &rt6_exception_lock); + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { - hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) - rt6_remove_exception(bucket, rt6_ex); - WARN_ON_ONCE(bucket->depth); + hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) { + if (!from || + rcu_access_pointer(rt6_ex->rt6i->from) == from) + rt6_remove_exception(bucket, rt6_ex); + } + WARN_ON_ONCE(!from && bucket->depth); bucket++; } - out: spin_unlock_bh(&rt6_exception_lock); } +void rt6_flush_exceptions(struct fib6_info *f6i) +{ + fib6_nh_flush_exceptions(f6i->fib6_nh, f6i); +} + /* Find cached rt in the hash table inside passed in rt * Caller has to hold rcu_read_lock() */ @@ -1593,7 +1680,7 @@ static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res, src_key = saddr; find_ex: #endif - bucket = rcu_dereference(res->f6i->rt6i_exception_bucket); + bucket = fib6_nh_get_excptn_bucket(res->nh, NULL); rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key); if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i)) @@ -1611,25 +1698,20 @@ find_ex: } /* Remove the passed in cached rt from the hash table that contains it */ -static int rt6_remove_exception_rt(struct rt6_info *rt) +static int fib6_nh_remove_exception(const struct fib6_nh *nh, int plen, + const struct rt6_info *rt) { + const struct in6_addr *src_key = NULL; struct rt6_exception_bucket *bucket; - struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; - struct fib6_info *from; int err; - from = rcu_dereference(rt->from); - if (!from || - !(rt->rt6i_flags & RTF_CACHE)) - return -EINVAL; - - if (!rcu_access_pointer(from->rt6i_exception_bucket)) + if (!rcu_access_pointer(nh->rt6i_exception_bucket)) return -ENOENT; spin_lock_bh(&rt6_exception_lock); - bucket = rcu_dereference_protected(from->rt6i_exception_bucket, - lockdep_is_held(&rt6_exception_lock)); + bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); + #ifdef CONFIG_IPV6_SUBTREES /* rt6i_src.plen != 0 indicates 'from' is in subtree * and exception table is indexed by a hash of @@ -1637,7 +1719,7 @@ static int rt6_remove_exception_rt(struct rt6_info *rt) * Otherwise, the exception table is indexed by * a hash of only rt6i_dst. */ - if (from->fib6_src.plen) + if (plen) src_key = &rt->rt6i_src.addr; #endif rt6_ex = __rt6_find_exception_spinlock(&bucket, @@ -1654,23 +1736,29 @@ static int rt6_remove_exception_rt(struct rt6_info *rt) return err; } -/* Find rt6_ex which contains the passed in rt cache and - * refresh its stamp - */ -static void rt6_update_exception_stamp_rt(struct rt6_info *rt) +static int rt6_remove_exception_rt(struct rt6_info *rt) { - struct rt6_exception_bucket *bucket; - struct in6_addr *src_key = NULL; - struct rt6_exception *rt6_ex; struct fib6_info *from; - rcu_read_lock(); from = rcu_dereference(rt->from); if (!from || !(rt->rt6i_flags & RTF_CACHE)) - goto unlock; + return -EINVAL; + + return fib6_nh_remove_exception(from->fib6_nh, + from->fib6_src.plen, rt); +} - bucket = rcu_dereference(from->rt6i_exception_bucket); +/* Find rt6_ex which contains the passed in rt cache and + * refresh its stamp + */ +static void fib6_nh_update_exception(const struct fib6_nh *nh, int plen, + const struct rt6_info *rt) +{ + const struct in6_addr *src_key = NULL; + struct rt6_exception_bucket *bucket; + struct rt6_exception *rt6_ex; + bucket = fib6_nh_get_excptn_bucket(nh, NULL); #ifdef CONFIG_IPV6_SUBTREES /* rt6i_src.plen != 0 indicates 'from' is in subtree * and exception table is indexed by a hash of @@ -1678,15 +1766,25 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt) * Otherwise, the exception table is indexed by * a hash of only rt6i_dst. */ - if (from->fib6_src.plen) + if (plen) src_key = &rt->rt6i_src.addr; #endif - rt6_ex = __rt6_find_exception_rcu(&bucket, - &rt->rt6i_dst.addr, - src_key); + rt6_ex = __rt6_find_exception_rcu(&bucket, &rt->rt6i_dst.addr, src_key); if (rt6_ex) rt6_ex->stamp = jiffies; +} +static void rt6_update_exception_stamp_rt(struct rt6_info *rt) +{ + struct fib6_info *from; + + rcu_read_lock(); + + from = rcu_dereference(rt->from); + if (!from || !(rt->rt6i_flags & RTF_CACHE)) + goto unlock; + + fib6_nh_update_exception(from->fib6_nh, from->fib6_src.plen, rt); unlock: rcu_read_unlock(); } @@ -1714,15 +1812,13 @@ static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev, } static void rt6_exceptions_update_pmtu(struct inet6_dev *idev, - struct fib6_info *rt, int mtu) + const struct fib6_nh *nh, int mtu) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; int i; - bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, - lockdep_is_held(&rt6_exception_lock)); - + bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (!bucket) return; @@ -1744,21 +1840,19 @@ static void rt6_exceptions_update_pmtu(struct inet6_dev *idev, #define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE) -static void rt6_exceptions_clean_tohost(struct fib6_info *rt, - struct in6_addr *gateway) +static void fib6_nh_exceptions_clean_tohost(const struct fib6_nh *nh, + const struct in6_addr *gateway) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; struct hlist_node *tmp; int i; - if (!rcu_access_pointer(rt->rt6i_exception_bucket)) + if (!rcu_access_pointer(nh->rt6i_exception_bucket)) return; spin_lock_bh(&rt6_exception_lock); - bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, - lockdep_is_held(&rt6_exception_lock)); - + bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (bucket) { for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry_safe(rt6_ex, tmp, @@ -1823,23 +1917,21 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket, gc_args->more++; } -void rt6_age_exceptions(struct fib6_info *rt, - struct fib6_gc_args *gc_args, - unsigned long now) +static void fib6_nh_age_exceptions(const struct fib6_nh *nh, + struct fib6_gc_args *gc_args, + unsigned long now) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; struct hlist_node *tmp; int i; - if (!rcu_access_pointer(rt->rt6i_exception_bucket)) + if (!rcu_access_pointer(nh->rt6i_exception_bucket)) return; rcu_read_lock_bh(); spin_lock(&rt6_exception_lock); - bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, - lockdep_is_held(&rt6_exception_lock)); - + bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (bucket) { for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry_safe(rt6_ex, tmp, @@ -1854,6 +1946,13 @@ void rt6_age_exceptions(struct fib6_info *rt, rcu_read_unlock_bh(); } +void rt6_age_exceptions(struct fib6_info *f6i, + struct fib6_gc_args *gc_args, + unsigned long now) +{ + fib6_nh_age_exceptions(f6i->fib6_nh, gc_args, now); +} + /* must be called with rcu lock held */ int fib6_table_lookup(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, struct fib6_result *res, int strict) @@ -2380,7 +2479,7 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, rcu_read_unlock(); return; } - res.nh = &res.f6i->fib6_nh; + res.nh = res.f6i->fib6_nh; res.fib6_flags = res.f6i->fib6_flags; res.fib6_type = res.f6i->fib6_type; @@ -2529,7 +2628,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net, restart: for_each_fib6_node_rt_rcu(fn) { res.f6i = rt; - res.nh = &rt->fib6_nh; + res.nh = rt->fib6_nh; if (fib6_check_expired(rt)) continue; @@ -2553,7 +2652,7 @@ restart: } res.f6i = rt; - res.nh = &rt->fib6_nh; + res.nh = rt->fib6_nh; out: if (ret) { ip6_hold_safe(net, &ret); @@ -3038,7 +3137,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, goto out; } } - goto set_dev; + goto pcpu_alloc; } if (cfg->fc_flags & RTF_GATEWAY) { @@ -3074,7 +3173,14 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, cfg->fc_encap_type, cfg, gfp_flags, extack); if (err) goto out; -set_dev: + +pcpu_alloc: + fib6_nh->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, gfp_flags); + if (!fib6_nh->rt6i_pcpu) { + err = -ENOMEM; + goto out; + } + fib6_nh->fib_nh_dev = dev; fib6_nh->fib_nh_oif = dev->ifindex; err = 0; @@ -3094,6 +3200,38 @@ out: void fib6_nh_release(struct fib6_nh *fib6_nh) { + struct rt6_exception_bucket *bucket; + + rcu_read_lock(); + + fib6_nh_flush_exceptions(fib6_nh, NULL); + bucket = fib6_nh_get_excptn_bucket(fib6_nh, NULL); + if (bucket) { + rcu_assign_pointer(fib6_nh->rt6i_exception_bucket, NULL); + kfree(bucket); + } + + rcu_read_unlock(); + + if (fib6_nh->rt6i_pcpu) { + int cpu; + + for_each_possible_cpu(cpu) { + struct rt6_info **ppcpu_rt; + struct rt6_info *pcpu_rt; + + ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu); + pcpu_rt = *ppcpu_rt; + if (pcpu_rt) { + dst_dev_put(&pcpu_rt->dst); + dst_release(&pcpu_rt->dst); + *ppcpu_rt = NULL; + } + } + + free_percpu(fib6_nh->rt6i_pcpu); + } + fib_nh_common_release(&fib6_nh->nh_common); } @@ -3103,7 +3241,9 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, { struct net *net = cfg->fc_nlinfo.nl_net; struct fib6_info *rt = NULL; + struct nexthop *nh = NULL; struct fib6_table *table; + struct fib6_nh *fib6_nh; int err = -EINVAL; int addr_type; @@ -3156,7 +3296,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, goto out; err = -ENOMEM; - rt = fib6_info_alloc(gfp_flags); + rt = fib6_info_alloc(gfp_flags, !nh); if (!rt) goto out; @@ -3196,19 +3336,35 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, ipv6_addr_prefix(&rt->fib6_src.addr, &cfg->fc_src, cfg->fc_src_len); rt->fib6_src.plen = cfg->fc_src_len; #endif - err = fib6_nh_init(net, &rt->fib6_nh, cfg, gfp_flags, extack); - if (err) - goto out; + if (nh) { + if (!nexthop_get(nh)) { + NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); + goto out; + } + if (rt->fib6_src.plen) { + NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing"); + goto out; + } + rt->nh = nh; + fib6_nh = nexthop_fib6_nh(rt->nh); + } else { + err = fib6_nh_init(net, rt->fib6_nh, cfg, gfp_flags, extack); + if (err) + goto out; - /* We cannot add true routes via loopback here, - * they would result in kernel looping; promote them to reject routes - */ - addr_type = ipv6_addr_type(&cfg->fc_dst); - if (fib6_is_reject(cfg->fc_flags, rt->fib6_nh.fib_nh_dev, addr_type)) - rt->fib6_flags = RTF_REJECT | RTF_NONEXTHOP; + fib6_nh = rt->fib6_nh; + + /* We cannot add true routes via loopback here, they would + * result in kernel looping; promote them to reject routes + */ + addr_type = ipv6_addr_type(&cfg->fc_dst); + if (fib6_is_reject(cfg->fc_flags, rt->fib6_nh->fib_nh_dev, + addr_type)) + rt->fib6_flags = RTF_REJECT | RTF_NONEXTHOP; + } if (!ipv6_addr_any(&cfg->fc_prefsrc)) { - struct net_device *dev = fib6_info_nh_dev(rt); + struct net_device *dev = fib6_nh->fib_nh_dev; if (!ipv6_chk_addr(net, &cfg->fc_prefsrc, dev, 0)) { NL_SET_ERR_MSG(extack, "Invalid source address"); @@ -3322,7 +3478,7 @@ out_put: return err; } -static int ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg) +static int __ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg) { int rc = -ESRCH; @@ -3338,10 +3494,25 @@ out: return rc; } +static int ip6_del_cached_rt(struct fib6_config *cfg, struct fib6_info *rt, + struct fib6_nh *nh) +{ + struct fib6_result res = { + .f6i = rt, + .nh = nh, + }; + struct rt6_info *rt_cache; + + rt_cache = rt6_find_cached_rt(&res, &cfg->fc_dst, &cfg->fc_src); + if (rt_cache) + return __ip6_del_cached_rt(rt_cache, cfg); + + return 0; +} + static int ip6_route_del(struct fib6_config *cfg, struct netlink_ext_ack *extack) { - struct rt6_info *rt_cache; struct fib6_table *table; struct fib6_info *rt; struct fib6_node *fn; @@ -3364,26 +3535,18 @@ static int ip6_route_del(struct fib6_config *cfg, for_each_fib6_node_rt_rcu(fn) { struct fib6_nh *nh; + nh = rt->fib6_nh; if (cfg->fc_flags & RTF_CACHE) { - struct fib6_result res = { - .f6i = rt, - }; int rc; - rt_cache = rt6_find_cached_rt(&res, - &cfg->fc_dst, - &cfg->fc_src); - if (rt_cache) { - rc = ip6_del_cached_rt(rt_cache, cfg); - if (rc != -ESRCH) { - rcu_read_unlock(); - return rc; - } + rc = ip6_del_cached_rt(cfg, rt, nh); + if (rc != -ESRCH) { + rcu_read_unlock(); + return rc; } continue; } - nh = &rt->fib6_nh; if (cfg->fc_ifindex && (!nh->fib_nh_dev || nh->fib_nh_dev->ifindex != cfg->fc_ifindex)) @@ -3505,7 +3668,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu if (!res.f6i) goto out; - res.nh = &res.f6i->fib6_nh; + res.nh = res.f6i->fib6_nh; res.fib6_flags = res.f6i->fib6_flags; res.fib6_type = res.f6i->fib6_type; nrt = ip6_rt_cache_alloc(&res, &msg->dest, NULL); @@ -3557,12 +3720,15 @@ static struct fib6_info *rt6_get_route_info(struct net *net, goto out; for_each_fib6_node_rt_rcu(fn) { - if (rt->fib6_nh.fib_nh_dev->ifindex != ifindex) + /* these routes do not use nexthops */ + if (rt->nh) + continue; + if (rt->fib6_nh->fib_nh_dev->ifindex != ifindex) continue; if (!(rt->fib6_flags & RTF_ROUTEINFO) || - !rt->fib6_nh.fib_nh_gw_family) + !rt->fib6_nh->fib_nh_gw_family) continue; - if (!ipv6_addr_equal(&rt->fib6_nh.fib_nh_gw6, gwaddr)) + if (!ipv6_addr_equal(&rt->fib6_nh->fib_nh_gw6, gwaddr)) continue; if (!fib6_info_hold_safe(rt)) continue; @@ -3620,8 +3786,13 @@ struct fib6_info *rt6_get_dflt_router(struct net *net, rcu_read_lock(); for_each_fib6_node_rt_rcu(&table->tb6_root) { - struct fib6_nh *nh = &rt->fib6_nh; + struct fib6_nh *nh; + /* RA routes do not use nexthops */ + if (rt->nh) + continue; + + nh = rt->fib6_nh; if (dev == nh->fib_nh_dev && ((rt->fib6_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) && ipv6_addr_equal(&nh->fib_nh_gw6, addr)) @@ -3872,7 +4043,8 @@ static int fib6_remove_prefsrc(struct fib6_info *rt, void *arg) struct net *net = ((struct arg_dev_net_ip *)arg)->net; struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr; - if (((void *)rt->fib6_nh.fib_nh_dev == dev || !dev) && + if (!rt->nh && + ((void *)rt->fib6_nh->fib_nh_dev == dev || !dev) && rt != net->ipv6.fib6_null_entry && ipv6_addr_equal(addr, &rt->fib6_prefsrc.addr)) { spin_lock_bh(&rt6_exception_lock); @@ -3900,18 +4072,22 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp) static int fib6_clean_tohost(struct fib6_info *rt, void *arg) { struct in6_addr *gateway = (struct in6_addr *)arg; + struct fib6_nh *nh; + /* RA routes do not use nexthops */ + if (rt->nh) + return 0; + + nh = rt->fib6_nh; if (((rt->fib6_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) && - rt->fib6_nh.fib_nh_gw_family && - ipv6_addr_equal(gateway, &rt->fib6_nh.fib_nh_gw6)) { + nh->fib_nh_gw_family && ipv6_addr_equal(gateway, &nh->fib_nh_gw6)) return -1; - } /* Further clean up cached routes in exception table. * This is needed because cached route may have a different * gateway than its 'parent' in the case of an ip redirect. */ - rt6_exceptions_clean_tohost(rt, gateway); + fib6_nh_exceptions_clean_tohost(nh, gateway); return 0; } @@ -3949,11 +4125,12 @@ static struct fib6_info *rt6_multipath_first_sibling(const struct fib6_info *rt) return NULL; } +/* only called for fib entries with builtin fib6_nh */ static bool rt6_is_dead(const struct fib6_info *rt) { - if (rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD || - (rt->fib6_nh.fib_nh_flags & RTNH_F_LINKDOWN && - ip6_ignore_linkdown(rt->fib6_nh.fib_nh_dev))) + if (rt->fib6_nh->fib_nh_flags & RTNH_F_DEAD || + (rt->fib6_nh->fib_nh_flags & RTNH_F_LINKDOWN && + ip6_ignore_linkdown(rt->fib6_nh->fib_nh_dev))) return true; return false; @@ -3965,11 +4142,11 @@ static int rt6_multipath_total_weight(const struct fib6_info *rt) int total = 0; if (!rt6_is_dead(rt)) - total += rt->fib6_nh.fib_nh_weight; + total += rt->fib6_nh->fib_nh_weight; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) { if (!rt6_is_dead(iter)) - total += iter->fib6_nh.fib_nh_weight; + total += iter->fib6_nh->fib_nh_weight; } return total; @@ -3980,11 +4157,11 @@ static void rt6_upper_bound_set(struct fib6_info *rt, int *weight, int total) int upper_bound = -1; if (!rt6_is_dead(rt)) { - *weight += rt->fib6_nh.fib_nh_weight; + *weight += rt->fib6_nh->fib_nh_weight; upper_bound = DIV_ROUND_CLOSEST_ULL((u64) (*weight) << 31, total) - 1; } - atomic_set(&rt->fib6_nh.fib_nh_upper_bound, upper_bound); + atomic_set(&rt->fib6_nh->fib_nh_upper_bound, upper_bound); } static void rt6_multipath_upper_bound_set(struct fib6_info *rt, int total) @@ -4027,9 +4204,9 @@ static int fib6_ifup(struct fib6_info *rt, void *p_arg) const struct arg_netdev_event *arg = p_arg; struct net *net = dev_net(arg->dev); - if (rt != net->ipv6.fib6_null_entry && - rt->fib6_nh.fib_nh_dev == arg->dev) { - rt->fib6_nh.fib_nh_flags &= ~arg->nh_flags; + if (rt != net->ipv6.fib6_null_entry && !rt->nh && + rt->fib6_nh->fib_nh_dev == arg->dev) { + rt->fib6_nh->fib_nh_flags &= ~arg->nh_flags; fib6_update_sernum_upto_root(net, rt); rt6_multipath_rebalance(rt); } @@ -4052,15 +4229,16 @@ void rt6_sync_up(struct net_device *dev, unsigned char nh_flags) fib6_clean_all(dev_net(dev), fib6_ifup, &arg); } +/* only called for fib entries with inline fib6_nh */ static bool rt6_multipath_uses_dev(const struct fib6_info *rt, const struct net_device *dev) { struct fib6_info *iter; - if (rt->fib6_nh.fib_nh_dev == dev) + if (rt->fib6_nh->fib_nh_dev == dev) return true; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) - if (iter->fib6_nh.fib_nh_dev == dev) + if (iter->fib6_nh->fib_nh_dev == dev) return true; return false; @@ -4081,12 +4259,12 @@ static unsigned int rt6_multipath_dead_count(const struct fib6_info *rt, struct fib6_info *iter; unsigned int dead = 0; - if (rt->fib6_nh.fib_nh_dev == down_dev || - rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD) + if (rt->fib6_nh->fib_nh_dev == down_dev || + rt->fib6_nh->fib_nh_flags & RTNH_F_DEAD) dead++; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) - if (iter->fib6_nh.fib_nh_dev == down_dev || - iter->fib6_nh.fib_nh_flags & RTNH_F_DEAD) + if (iter->fib6_nh->fib_nh_dev == down_dev || + iter->fib6_nh->fib_nh_flags & RTNH_F_DEAD) dead++; return dead; @@ -4098,11 +4276,11 @@ static void rt6_multipath_nh_flags_set(struct fib6_info *rt, { struct fib6_info *iter; - if (rt->fib6_nh.fib_nh_dev == dev) - rt->fib6_nh.fib_nh_flags |= nh_flags; + if (rt->fib6_nh->fib_nh_dev == dev) + rt->fib6_nh->fib_nh_flags |= nh_flags; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) - if (iter->fib6_nh.fib_nh_dev == dev) - iter->fib6_nh.fib_nh_flags |= nh_flags; + if (iter->fib6_nh->fib_nh_dev == dev) + iter->fib6_nh->fib_nh_flags |= nh_flags; } /* called with write lock held for table with rt */ @@ -4112,17 +4290,17 @@ static int fib6_ifdown(struct fib6_info *rt, void *p_arg) const struct net_device *dev = arg->dev; struct net *net = dev_net(dev); - if (rt == net->ipv6.fib6_null_entry) + if (rt == net->ipv6.fib6_null_entry || rt->nh) return 0; switch (arg->event) { case NETDEV_UNREGISTER: - return rt->fib6_nh.fib_nh_dev == dev ? -1 : 0; + return rt->fib6_nh->fib_nh_dev == dev ? -1 : 0; case NETDEV_DOWN: if (rt->should_flush) return -1; if (!rt->fib6_nsiblings) - return rt->fib6_nh.fib_nh_dev == dev ? -1 : 0; + return rt->fib6_nh->fib_nh_dev == dev ? -1 : 0; if (rt6_multipath_uses_dev(rt, dev)) { unsigned int count; @@ -4138,10 +4316,10 @@ static int fib6_ifdown(struct fib6_info *rt, void *p_arg) } return -2; case NETDEV_CHANGE: - if (rt->fib6_nh.fib_nh_dev != dev || + if (rt->fib6_nh->fib_nh_dev != dev || rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) break; - rt->fib6_nh.fib_nh_flags |= RTNH_F_LINKDOWN; + rt->fib6_nh->fib_nh_flags |= RTNH_F_LINKDOWN; rt6_multipath_rebalance(rt); break; } @@ -4175,9 +4353,36 @@ void rt6_disable_ip(struct net_device *dev, unsigned long event) struct rt6_mtu_change_arg { struct net_device *dev; unsigned int mtu; + struct fib6_info *f6i; }; -static int rt6_mtu_change_route(struct fib6_info *rt, void *p_arg) +static int fib6_nh_mtu_change(struct fib6_nh *nh, void *_arg) +{ + struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *)_arg; + struct fib6_info *f6i = arg->f6i; + + /* For administrative MTU increase, there is no way to discover + * IPv6 PMTU increase, so PMTU increase should be updated here. + * Since RFC 1981 doesn't include administrative MTU increase + * update PMTU increase is a MUST. (i.e. jumbo frame) + */ + if (nh->fib_nh_dev == arg->dev) { + struct inet6_dev *idev = __in6_dev_get(arg->dev); + u32 mtu = f6i->fib6_pmtu; + + if (mtu >= arg->mtu || + (mtu < arg->mtu && mtu == idev->cnf.mtu6)) + fib6_metric_set(f6i, RTAX_MTU, arg->mtu); + + spin_lock_bh(&rt6_exception_lock); + rt6_exceptions_update_pmtu(idev, nh, arg->mtu); + spin_unlock_bh(&rt6_exception_lock); + } + + return 0; +} + +static int rt6_mtu_change_route(struct fib6_info *f6i, void *p_arg) { struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *) p_arg; struct inet6_dev *idev; @@ -4192,24 +4397,11 @@ static int rt6_mtu_change_route(struct fib6_info *rt, void *p_arg) if (!idev) return 0; - /* For administrative MTU increase, there is no way to discover - IPv6 PMTU increase, so PMTU increase should be updated here. - Since RFC 1981 doesn't include administrative MTU increase - update PMTU increase is a MUST. (i.e. jumbo frame) - */ - if (rt->fib6_nh.fib_nh_dev == arg->dev && - !fib6_metric_locked(rt, RTAX_MTU)) { - u32 mtu = rt->fib6_pmtu; - - if (mtu >= arg->mtu || - (mtu < arg->mtu && mtu == idev->cnf.mtu6)) - fib6_metric_set(rt, RTAX_MTU, arg->mtu); + if (fib6_metric_locked(f6i, RTAX_MTU)) + return 0; - spin_lock_bh(&rt6_exception_lock); - rt6_exceptions_update_pmtu(idev, rt, arg->mtu); - spin_unlock_bh(&rt6_exception_lock); - } - return 0; + arg->f6i = f6i; + return fib6_nh_mtu_change(f6i->fib6_nh, arg); } void rt6_mtu_change(struct net_device *dev, unsigned int mtu) @@ -4223,6 +4415,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned int mtu) } static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { + [RTA_UNSPEC] = { .strict_start_type = RTA_DPORT + 1 }, [RTA_GATEWAY] = { .len = sizeof(struct in6_addr) }, [RTA_PREFSRC] = { .len = sizeof(struct in6_addr) }, [RTA_OIF] = { .type = NLA_U32 }, @@ -4488,7 +4681,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, goto cleanup; } - rt->fib6_nh.fib_nh_weight = rtnh->rtnh_hops + 1; + rt->fib6_nh->fib_nh_weight = rtnh->rtnh_hops + 1; err = ip6_route_info_append(info->nl_net, &rt6_nh_list, rt, &r_cfg); @@ -4651,11 +4844,14 @@ static size_t rt6_nlmsg_size(struct fib6_info *rt) { int nexthop_len = 0; + if (rt->nh) + nexthop_len += nla_total_size(4); /* RTA_NH_ID */ + if (rt->fib6_nsiblings) { nexthop_len = nla_total_size(0) /* RTA_MULTIPATH */ + NLA_ALIGN(sizeof(struct rtnexthop)) + nla_total_size(16) /* RTA_GATEWAY */ - + lwtunnel_get_encap_size(rt->fib6_nh.fib_nh_lws); + + lwtunnel_get_encap_size(rt->fib6_nh->fib_nh_lws); nexthop_len *= rt->fib6_nsiblings; } @@ -4673,10 +4869,39 @@ static size_t rt6_nlmsg_size(struct fib6_info *rt) + nla_total_size(sizeof(struct rta_cacheinfo)) + nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */ + nla_total_size(1) /* RTA_PREF */ - + lwtunnel_get_encap_size(rt->fib6_nh.fib_nh_lws) + + lwtunnel_get_encap_size(rt->fib6_nh->fib_nh_lws) + nexthop_len; } +static int rt6_fill_node_nexthop(struct sk_buff *skb, struct nexthop *nh, + unsigned char *flags) +{ + if (nexthop_is_multipath(nh)) { + struct nlattr *mp; + + mp = nla_nest_start(skb, RTA_MULTIPATH); + if (!mp) + goto nla_put_failure; + + if (nexthop_mpath_fill_node(skb, nh)) + goto nla_put_failure; + + nla_nest_end(skb, mp); + } else { + struct fib6_nh *fib6_nh; + + fib6_nh = nexthop_fib6_nh(nh); + if (fib_nexthop_info(skb, &fib6_nh->nh_common, + flags, false) < 0) + goto nla_put_failure; + } + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + static int rt6_fill_node(struct net *net, struct sk_buff *skb, struct fib6_info *rt, struct dst_entry *dst, struct in6_addr *dest, struct in6_addr *src, @@ -4686,6 +4911,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, struct rt6_info *rt6 = (struct rt6_info *)dst; struct rt6key *rt6_dst, *rt6_src; u32 *pmetrics, table, rt6_flags; + unsigned char nh_flags = 0; struct nlmsghdr *nlh; struct rtmsg *rtm; long expires = 0; @@ -4793,22 +5019,31 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, if (!mp) goto nla_put_failure; - if (fib_add_nexthop(skb, &rt->fib6_nh.nh_common, - rt->fib6_nh.fib_nh_weight) < 0) + if (fib_add_nexthop(skb, &rt->fib6_nh->nh_common, + rt->fib6_nh->fib_nh_weight) < 0) goto nla_put_failure; list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) { - if (fib_add_nexthop(skb, &sibling->fib6_nh.nh_common, - sibling->fib6_nh.fib_nh_weight) < 0) + if (fib_add_nexthop(skb, &sibling->fib6_nh->nh_common, + sibling->fib6_nh->fib_nh_weight) < 0) goto nla_put_failure; } nla_nest_end(skb, mp); - } else { - unsigned char nh_flags = 0; + } else if (rt->nh) { + if (nla_put_u32(skb, RTA_NH_ID, rt->nh->id)) + goto nla_put_failure; - if (fib_nexthop_info(skb, &rt->fib6_nh.nh_common, + if (nexthop_is_blackhole(rt->nh)) + rtm->rtm_type = RTN_BLACKHOLE; + + if (rt6_fill_node_nexthop(skb, rt->nh, &nh_flags) < 0) + goto nla_put_failure; + + rtm->rtm_flags |= nh_flags; + } else { + if (fib_nexthop_info(skb, &rt->fib6_nh->nh_common, &nh_flags, false) < 0) goto nla_put_failure; @@ -4838,7 +5073,7 @@ nla_put_failure: static bool fib6_info_uses_dev(const struct fib6_info *f6i, const struct net_device *dev) { - if (f6i->fib6_nh.fib_nh_dev == dev) + if (f6i->fib6_nh->fib_nh_dev == dev) return true; if (f6i->fib6_nsiblings) { @@ -4846,7 +5081,7 @@ static bool fib6_info_uses_dev(const struct fib6_info *f6i, list_for_each_entry_safe(sibling, next_sibling, &f6i->fib6_siblings, fib6_siblings) { - if (sibling->fib6_nh.fib_nh_dev == dev) + if (sibling->fib6_nh->fib_nh_dev == dev) return true; } } @@ -5125,6 +5360,38 @@ errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } +void fib6_rt_update(struct net *net, struct fib6_info *rt, + struct nl_info *info) +{ + u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; + struct sk_buff *skb; + int err = -ENOBUFS; + + /* call_fib6_entry_notifiers will be removed when in-kernel notifier + * is implemented and supported for nexthop objects + */ + call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, rt, NULL); + + skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); + if (!skb) + goto errout; + + err = rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0, + RTM_NEWROUTE, info->portid, seq, NLM_F_REPLACE); + if (err < 0) { + /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, + info->nlh, gfp_any()); + return; +errout: + if (err < 0) + rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); +} + static int ip6_route_dev_notify(struct notifier_block *this, unsigned long event, void *ptr) { @@ -5135,7 +5402,7 @@ static int ip6_route_dev_notify(struct notifier_block *this, return NOTIFY_OK; if (event == NETDEV_REGISTER) { - net->ipv6.fib6_null_entry->fib6_nh.fib_nh_dev = dev; + net->ipv6.fib6_null_entry->fib6_nh->fib_nh_dev = dev; net->ipv6.ip6_null_entry->dst.dev = dev; net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES @@ -5329,11 +5596,11 @@ static int __net_init ip6_route_net_init(struct net *net) if (dst_entries_init(&net->ipv6.ip6_dst_ops) < 0) goto out_ip6_dst_ops; - net->ipv6.fib6_null_entry = kmemdup(&fib6_null_entry_template, - sizeof(*net->ipv6.fib6_null_entry), - GFP_KERNEL); + net->ipv6.fib6_null_entry = fib6_info_alloc(GFP_KERNEL, true); if (!net->ipv6.fib6_null_entry) goto out_ip6_dst_entries; + memcpy(net->ipv6.fib6_null_entry, &fib6_null_entry_template, + sizeof(*net->ipv6.fib6_null_entry)); net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template, sizeof(*net->ipv6.ip6_null_entry), @@ -5470,7 +5737,7 @@ void __init ip6_route_init_special_entries(void) /* Registering of the loopback is done before this portion of code, * the loopback reference in rt6_info will not be taken, do it * manually for init_net */ - init_net.ipv6.fib6_null_entry->fib6_nh.fib_nh_dev = init_net.loopback_dev; + init_net.ipv6.fib6_null_entry->fib6_nh->fib_nh_dev = init_net.loopback_dev; init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev; init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index e15cd37024fd..6d86fac472e7 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -23,6 +23,7 @@ static int zero; static int one = 1; +static int three = 3; static int auto_flowlabels_min; static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX; @@ -114,6 +115,8 @@ static struct ctl_table ipv6_table_template[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &three, }, { .procname = "max_dst_opts_number", diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7a14ea37d2df..d8d18386c99a 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -912,15 +912,17 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); + struct ipv6hdr *ipv6h = ipv6_hdr(skb); u32 seq = 0, ack_seq = 0; struct tcp_md5sig_key *key = NULL; #ifdef CONFIG_TCP_MD5SIG const __u8 *hash_location = NULL; - struct ipv6hdr *ipv6h = ipv6_hdr(skb); unsigned char newhash[16]; int genhash; struct sock *sk1 = NULL; #endif + __be32 label = 0; + struct net *net; int oif = 0; if (th->rst) @@ -932,6 +934,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) if (!sk && !ipv6_unicast_destination(skb)) return; + net = dev_net(skb_dst(skb)->dev); #ifdef CONFIG_TCP_MD5SIG rcu_read_lock(); hash_location = tcp_parse_md5sig_option(th); @@ -945,7 +948,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) * Incoming packet is checked with md5 hash with finding key, * no RST generated if md5 hash doesn't match. */ - sk1 = inet6_lookup_listener(dev_net(skb_dst(skb)->dev), + sk1 = inet6_lookup_listener(net, &tcp_hashinfo, NULL, 0, &ipv6h->saddr, th->source, &ipv6h->daddr, @@ -975,9 +978,15 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) oif = sk->sk_bound_dev_if; if (sk_fullsock(sk)) trace_tcp_send_reset(sk, skb); + if (sk->sk_state == TCP_TIME_WAIT) + label = cpu_to_be32(inet_twsk(sk)->tw_flowlabel); + } else { + if (net->ipv6.sysctl.flowlabel_reflect & 2) + label = ip6_flowlabel(ipv6h); } - tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0); + tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, + label); #ifdef CONFIG_TCP_MD5SIG out: diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index b3418a7c5c74..693518350f79 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -215,7 +215,7 @@ struct sock *__udp6_lib_lookup(struct net *net, exact_dif, hslot2, skb); } - if (unlikely(IS_ERR(result))) + if (IS_ERR(result)) return NULL; return result; } diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 2b608044ae23..1f11907dc528 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -354,11 +354,11 @@ static int ieee80211_ifa_changed(struct notifier_block *nb, sdata_lock(sdata); /* Copy the addresses to the bss_conf list */ - ifa = idev->ifa_list; + ifa = rtnl_dereference(idev->ifa_list); while (ifa) { if (c < IEEE80211_BSS_ARP_ADDR_LIST_LEN) bss_conf->arp_addr_list[c] = ifa->ifa_address; - ifa = ifa->ifa_next; + ifa = rtnl_dereference(ifa->ifa_next); c++; } diff --git a/net/netfilter/core.c b/net/netfilter/core.c index b96fd3f54705..817a9e5d16e4 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -536,28 +536,6 @@ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, } EXPORT_SYMBOL(nf_hook_slow); - -int skb_make_writable(struct sk_buff *skb, unsigned int writable_len) -{ - if (writable_len > skb->len) - return 0; - - /* Not exclusive use of packet? Must copy. */ - if (!skb_cloned(skb)) { - if (writable_len <= skb_headlen(skb)) - return 1; - } else if (skb_clone_writable(skb, writable_len)) - return 1; - - if (writable_len <= skb_headlen(skb)) - writable_len = 0; - else - writable_len -= skb_headlen(skb); - - return !!__pskb_pull_tail(skb, writable_len); -} -EXPORT_SYMBOL(skb_make_writable); - /* This needs to be compiled in any case to avoid dependencies between the * nfnetlink_queue code and nf_conntrack. */ diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index bfd4365a8d73..4515056ef1c2 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -358,7 +358,7 @@ static inline int app_tcp_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb, struct tcphdr *th; __u32 seq; - if (!skb_make_writable(skb, tcp_offset + sizeof(*th))) + if (skb_ensure_writable(skb, tcp_offset + sizeof(*th))) return 0; th = (struct tcphdr *)(skb_network_header(skb) + tcp_offset); @@ -435,7 +435,7 @@ static inline int app_tcp_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb, struct tcphdr *th; __u32 seq; - if (!skb_make_writable(skb, tcp_offset + sizeof(*th))) + if (skb_ensure_writable(skb, tcp_offset + sizeof(*th))) return 0; th = (struct tcphdr *)(skb_network_header(skb) + tcp_offset); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 7138556b206b..e8651fd621ef 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -34,6 +34,7 @@ #include <net/tcp.h> #include <net/udp.h> #include <net/icmp.h> /* for icmp_send */ +#include <net/gue.h> #include <net/route.h> #include <net/ip6_checksum.h> #include <net/netns/generic.h> /* net_generic() */ @@ -892,7 +893,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb, if (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol || IPPROTO_SCTP == protocol) offset += 2 * sizeof(__u16); - if (!skb_make_writable(skb, offset)) + if (skb_ensure_writable(skb, offset)) goto out; #ifdef CONFIG_IP_VS_IPV6 @@ -1282,7 +1283,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, IP_VS_DBG_PKT(11, af, pp, skb, iph->off, "Outgoing packet"); - if (!skb_make_writable(skb, iph->len)) + if (skb_ensure_writable(skb, iph->len)) goto drop; /* mangle the packet */ @@ -1574,6 +1575,41 @@ ip_vs_try_to_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, return 1; } +/* Check the UDP tunnel and return its header length */ +static int ipvs_udp_decap(struct netns_ipvs *ipvs, struct sk_buff *skb, + unsigned int offset, __u16 af, + const union nf_inet_addr *daddr, __u8 *proto) +{ + struct udphdr _udph, *udph; + struct ip_vs_dest *dest; + + udph = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); + if (!udph) + goto unk; + offset += sizeof(struct udphdr); + dest = ip_vs_find_tunnel(ipvs, af, daddr, udph->dest); + if (!dest) + goto unk; + if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { + struct guehdr _gueh, *gueh; + + gueh = skb_header_pointer(skb, offset, sizeof(_gueh), &_gueh); + if (!gueh) + goto unk; + if (gueh->control != 0 || gueh->version != 0) + goto unk; + /* Later we can support also IPPROTO_IPV6 */ + if (gueh->proto_ctype != IPPROTO_IPIP) + goto unk; + *proto = gueh->proto_ctype; + return sizeof(struct udphdr) + sizeof(struct guehdr) + + (gueh->hlen << 2); + } + +unk: + return 0; +} + /* * Handle ICMP messages in the outside-to-inside direction (incoming). * Find any that might be relevant, check against existing connections, @@ -1593,6 +1629,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, struct ip_vs_proto_data *pd; unsigned int offset, offset2, ihl, verdict; bool ipip, new_cp = false; + union nf_inet_addr *raddr; *related = 1; @@ -1631,20 +1668,51 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ + raddr = (union nf_inet_addr *)&cih->daddr; /* Special case for errors for IPIP packets */ ipip = false; if (cih->protocol == IPPROTO_IPIP) { + struct ip_vs_dest *dest; + if (unlikely(cih->frag_off & htons(IP_OFFSET))) return NF_ACCEPT; /* Error for our IPIP must arrive at LOCAL_IN */ if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL)) return NF_ACCEPT; + dest = ip_vs_find_tunnel(ipvs, AF_INET, raddr, 0); + /* Only for known tunnel */ + if (!dest || dest->tun_type != IP_VS_CONN_F_TUNNEL_TYPE_IPIP) + return NF_ACCEPT; offset += cih->ihl * 4; cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ ipip = true; + } else if (cih->protocol == IPPROTO_UDP && /* Can be UDP encap */ + /* Error for our tunnel must arrive at LOCAL_IN */ + (skb_rtable(skb)->rt_flags & RTCF_LOCAL)) { + __u8 iproto; + int ulen; + + /* Non-first fragment has no UDP header */ + if (unlikely(cih->frag_off & htons(IP_OFFSET))) + return NF_ACCEPT; + offset2 = offset + cih->ihl * 4; + ulen = ipvs_udp_decap(ipvs, skb, offset2, AF_INET, raddr, + &iproto); + if (ulen > 0) { + /* Skip IP and UDP tunnel headers */ + offset = offset2 + ulen; + /* Now we should be at the original IP header */ + cih = skb_header_pointer(skb, offset, sizeof(_ciph), + &_ciph); + if (cih && cih->version == 4 && cih->ihl >= 5 && + iproto == IPPROTO_IPIP) + ipip = true; + else + return NF_ACCEPT; + } } pd = ip_vs_proto_data_get(ipvs, cih->protocol); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 776c87ed4813..84384d896e29 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -510,15 +510,36 @@ static inline unsigned int ip_vs_rs_hashkey(int af, static void ip_vs_rs_hash(struct netns_ipvs *ipvs, struct ip_vs_dest *dest) { unsigned int hash; + __be16 port; if (dest->in_rs_table) return; + switch (IP_VS_DFWD_METHOD(dest)) { + case IP_VS_CONN_F_MASQ: + port = dest->port; + break; + case IP_VS_CONN_F_TUNNEL: + switch (dest->tun_type) { + case IP_VS_CONN_F_TUNNEL_TYPE_GUE: + port = dest->tun_port; + break; + case IP_VS_CONN_F_TUNNEL_TYPE_IPIP: + port = 0; + break; + default: + return; + } + break; + default: + return; + } + /* * Hash by proto,addr,port, * which are the parameters of the real service. */ - hash = ip_vs_rs_hashkey(dest->af, &dest->addr, dest->port); + hash = ip_vs_rs_hashkey(dest->af, &dest->addr, port); hlist_add_head_rcu(&dest->d_list, &ipvs->rs_table[hash]); dest->in_rs_table = 1; @@ -550,7 +571,8 @@ bool ip_vs_has_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol, if (dest->port == dport && dest->af == af && ip_vs_addr_equal(af, &dest->addr, daddr) && - (dest->protocol == protocol || dest->vfwmark)) { + (dest->protocol == protocol || dest->vfwmark) && + IP_VS_DFWD_METHOD(dest) == IP_VS_CONN_F_MASQ) { /* HIT */ return true; } @@ -580,7 +602,37 @@ struct ip_vs_dest *ip_vs_find_real_service(struct netns_ipvs *ipvs, int af, if (dest->port == dport && dest->af == af && ip_vs_addr_equal(af, &dest->addr, daddr) && - (dest->protocol == protocol || dest->vfwmark)) { + (dest->protocol == protocol || dest->vfwmark) && + IP_VS_DFWD_METHOD(dest) == IP_VS_CONN_F_MASQ) { + /* HIT */ + return dest; + } + } + + return NULL; +} + +/* Find real service record by <af,addr,tun_port>. + * In case of multiple records with the same <af,addr,tun_port>, only + * the first found record is returned. + * + * To be called under RCU lock. + */ +struct ip_vs_dest *ip_vs_find_tunnel(struct netns_ipvs *ipvs, int af, + const union nf_inet_addr *daddr, + __be16 tun_port) +{ + struct ip_vs_dest *dest; + unsigned int hash; + + /* Check for "full" addressed entries */ + hash = ip_vs_rs_hashkey(af, daddr, tun_port); + + hlist_for_each_entry_rcu(dest, &ipvs->rs_table[hash], d_list) { + if (dest->tun_port == tun_port && + dest->af == af && + ip_vs_addr_equal(af, &dest->addr, daddr) && + IP_VS_DFWD_METHOD(dest) == IP_VS_CONN_F_TUNNEL) { /* HIT */ return dest; } @@ -826,24 +878,29 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, conn_flags = udest->conn_flags & IP_VS_CONN_F_DEST_MASK; conn_flags |= IP_VS_CONN_F_INACTIVE; + /* Need to rehash? */ + if ((udest->conn_flags & IP_VS_CONN_F_FWD_MASK) != + IP_VS_DFWD_METHOD(dest) || + udest->tun_type != dest->tun_type || + udest->tun_port != dest->tun_port) + ip_vs_rs_unhash(dest); + /* set the tunnel info */ dest->tun_type = udest->tun_type; dest->tun_port = udest->tun_port; + dest->tun_flags = udest->tun_flags; /* set the IP_VS_CONN_F_NOOUTPUT flag if not masquerading/NAT */ if ((conn_flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ) { conn_flags |= IP_VS_CONN_F_NOOUTPUT; } else { - /* - * Put the real service in rs_table if not present. - * For now only for NAT! - */ - ip_vs_rs_hash(ipvs, dest); /* FTP-NAT requires conntrack for mangling */ if (svc->port == FTPPORT) ip_vs_register_conntrack(svc); } atomic_set(&dest->conn_flags, conn_flags); + /* Put the real service in rs_table if not present. */ + ip_vs_rs_hash(ipvs, dest); /* bind the service */ old_svc = rcu_dereference_protected(dest->svc, 1); @@ -2906,6 +2963,7 @@ static const struct nla_policy ip_vs_dest_policy[IPVS_DEST_ATTR_MAX + 1] = { [IPVS_DEST_ATTR_ADDR_FAMILY] = { .type = NLA_U16 }, [IPVS_DEST_ATTR_TUN_TYPE] = { .type = NLA_U8 }, [IPVS_DEST_ATTR_TUN_PORT] = { .type = NLA_U16 }, + [IPVS_DEST_ATTR_TUN_FLAGS] = { .type = NLA_U16 }, }; static int ip_vs_genl_fill_stats(struct sk_buff *skb, int container_type, @@ -3212,6 +3270,8 @@ static int ip_vs_genl_fill_dest(struct sk_buff *skb, struct ip_vs_dest *dest) dest->tun_type) || nla_put_be16(skb, IPVS_DEST_ATTR_TUN_PORT, dest->tun_port) || + nla_put_u16(skb, IPVS_DEST_ATTR_TUN_FLAGS, + dest->tun_flags) || nla_put_u32(skb, IPVS_DEST_ATTR_U_THRESH, dest->u_threshold) || nla_put_u32(skb, IPVS_DEST_ATTR_L_THRESH, dest->l_threshold) || nla_put_u32(skb, IPVS_DEST_ATTR_ACTIVE_CONNS, @@ -3332,7 +3392,8 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest, /* If a full entry was requested, check for the additional fields */ if (full_entry) { struct nlattr *nla_fwd, *nla_weight, *nla_u_thresh, - *nla_l_thresh, *nla_tun_type, *nla_tun_port; + *nla_l_thresh, *nla_tun_type, *nla_tun_port, + *nla_tun_flags; nla_fwd = attrs[IPVS_DEST_ATTR_FWD_METHOD]; nla_weight = attrs[IPVS_DEST_ATTR_WEIGHT]; @@ -3340,6 +3401,7 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest, nla_l_thresh = attrs[IPVS_DEST_ATTR_L_THRESH]; nla_tun_type = attrs[IPVS_DEST_ATTR_TUN_TYPE]; nla_tun_port = attrs[IPVS_DEST_ATTR_TUN_PORT]; + nla_tun_flags = attrs[IPVS_DEST_ATTR_TUN_FLAGS]; if (!(nla_fwd && nla_weight && nla_u_thresh && nla_l_thresh)) return -EINVAL; @@ -3355,6 +3417,9 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest, if (nla_tun_port) udest->tun_port = nla_get_be16(nla_tun_port); + + if (nla_tun_flags) + udest->tun_flags = nla_get_u16(nla_tun_flags); } return 0; diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index c244b2545e24..cf925906f59b 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -267,7 +267,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, return 1; /* Linear packets are much easier to deal with. */ - if (!skb_make_writable(skb, skb->len)) + if (skb_ensure_writable(skb, skb->len)) return 0; if (cp->app_data == (void *) IP_VS_FTP_PASV) { @@ -433,7 +433,7 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, return 1; /* Linear packets are much easier to deal with. */ - if (!skb_make_writable(skb, skb->len)) + if (skb_ensure_writable(skb, skb->len)) return 0; data = data_start = ip_vs_ftp_data_ptr(skb, ipvsh); diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index b58ddb7dffd1..a0921adc31a9 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -101,7 +101,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, #endif /* csum_check requires unshared skb */ - if (!skb_make_writable(skb, sctphoff + sizeof(*sctph))) + if (skb_ensure_writable(skb, sctphoff + sizeof(*sctph))) return 0; if (unlikely(cp->app != NULL)) { @@ -148,7 +148,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, #endif /* csum_check requires unshared skb */ - if (!skb_make_writable(skb, sctphoff + sizeof(*sctph))) + if (skb_ensure_writable(skb, sctphoff + sizeof(*sctph))) return 0; if (unlikely(cp->app != NULL)) { diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 915ac8206076..000d961b97e4 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -159,7 +159,7 @@ tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, oldlen = skb->len - tcphoff; /* csum_check requires unshared skb */ - if (!skb_make_writable(skb, tcphoff+sizeof(*tcph))) + if (skb_ensure_writable(skb, tcphoff + sizeof(*tcph))) return 0; if (unlikely(cp->app != NULL)) { @@ -237,7 +237,7 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, oldlen = skb->len - tcphoff; /* csum_check requires unshared skb */ - if (!skb_make_writable(skb, tcphoff+sizeof(*tcph))) + if (skb_ensure_writable(skb, tcphoff + sizeof(*tcph))) return 0; if (unlikely(cp->app != NULL)) { diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index 379140075e95..153d89647c87 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -148,7 +148,7 @@ udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, oldlen = skb->len - udphoff; /* csum_check requires unshared skb */ - if (!skb_make_writable(skb, udphoff+sizeof(*udph))) + if (skb_ensure_writable(skb, udphoff + sizeof(*udph))) return 0; if (unlikely(cp->app != NULL)) { @@ -231,7 +231,7 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, oldlen = skb->len - udphoff; /* csum_check requires unshared skb */ - if (!skb_make_writable(skb, udphoff+sizeof(*udph))) + if (skb_ensure_writable(skb, udphoff + sizeof(*udph))) return 0; if (unlikely(cp->app != NULL)) { diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index e101eda05d55..71fc6d63a67f 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -36,6 +36,7 @@ #include <net/ipv6.h> #include <net/ip6_route.h> #include <net/ip_tunnels.h> +#include <net/ip6_checksum.h> #include <net/addrconf.h> #include <linux/icmpv6.h> #include <linux/netfilter.h> @@ -275,7 +276,7 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs, } /* don't propagate ttl change to cloned packets */ - if (!skb_make_writable(skb, sizeof(struct ipv6hdr))) + if (skb_ensure_writable(skb, sizeof(struct ipv6hdr))) return false; ipv6_hdr(skb)->hop_limit--; @@ -290,7 +291,7 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs, } /* don't propagate ttl change to cloned packets */ - if (!skb_make_writable(skb, sizeof(struct iphdr))) + if (skb_ensure_writable(skb, sizeof(struct iphdr))) return false; /* Decrease ttl */ @@ -381,8 +382,13 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr); if (!dest) goto err_put; - if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) + if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { mtu -= sizeof(struct udphdr) + sizeof(struct guehdr); + if ((dest->tun_flags & + IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) && + skb->ip_summed == CHECKSUM_PARTIAL) + mtu -= GUE_PLEN_REMCSUM + GUE_LEN_PRIV; + } if (mtu < 68) { IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__); goto err_put; @@ -536,8 +542,13 @@ __ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr); if (!dest) goto err_put; - if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) + if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { mtu -= sizeof(struct udphdr) + sizeof(struct guehdr); + if ((dest->tun_flags & + IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) && + skb->ip_summed == CHECKSUM_PARTIAL) + mtu -= GUE_PLEN_REMCSUM + GUE_LEN_PRIV; + } if (mtu < IPV6_MIN_MTU) { IP_VS_DBG_RL("%s(): mtu less than %d\n", __func__, IPV6_MIN_MTU); @@ -792,7 +803,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, } /* copy-on-write the packet before mangling it */ - if (!skb_make_writable(skb, sizeof(struct iphdr))) + if (skb_ensure_writable(skb, sizeof(struct iphdr))) goto tx_error; if (skb_cow(skb, rt->dst.dev->hard_header_len)) @@ -881,7 +892,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, } /* copy-on-write the packet before mangling it */ - if (!skb_make_writable(skb, sizeof(struct ipv6hdr))) + if (skb_ensure_writable(skb, sizeof(struct ipv6hdr))) goto tx_error; if (skb_cow(skb, rt->dst.dev->hard_header_len)) @@ -1002,17 +1013,56 @@ ipvs_gue_encap(struct net *net, struct sk_buff *skb, __be16 sport = udp_flow_src_port(net, skb, 0, 0, false); struct udphdr *udph; /* Our new UDP header */ struct guehdr *gueh; /* Our new GUE header */ + size_t hdrlen, optlen = 0; + void *data; + bool need_priv = false; + + if ((cp->dest->tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) && + skb->ip_summed == CHECKSUM_PARTIAL) { + optlen += GUE_PLEN_REMCSUM + GUE_LEN_PRIV; + need_priv = true; + } - skb_push(skb, sizeof(struct guehdr)); + hdrlen = sizeof(struct guehdr) + optlen; + + skb_push(skb, hdrlen); gueh = (struct guehdr *)skb->data; gueh->control = 0; gueh->version = 0; - gueh->hlen = 0; + gueh->hlen = optlen >> 2; gueh->flags = 0; gueh->proto_ctype = *next_protocol; + data = &gueh[1]; + + if (need_priv) { + __be32 *flags = data; + u16 csum_start = skb_checksum_start_offset(skb); + __be16 *pd; + + gueh->flags |= GUE_FLAG_PRIV; + *flags = 0; + data += GUE_LEN_PRIV; + + if (csum_start < hdrlen) + return -EINVAL; + + csum_start -= hdrlen; + pd = data; + pd[0] = htons(csum_start); + pd[1] = htons(csum_start + skb->csum_offset); + + if (!skb_is_gso(skb)) { + skb->ip_summed = CHECKSUM_NONE; + skb->encapsulation = 0; + } + + *flags |= GUE_PFLAG_REMCSUM; + data += GUE_PLEN_REMCSUM; + } + skb_push(skb, sizeof(struct udphdr)); skb_reset_transport_header(skb); @@ -1066,6 +1116,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, unsigned int max_headroom; /* The extra header space needed */ int ret, local; int tun_type, gso_type; + int tun_flags; EnterFunction(10); @@ -1088,9 +1139,19 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr); tun_type = cp->dest->tun_type; + tun_flags = cp->dest->tun_flags; - if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) - max_headroom += sizeof(struct udphdr) + sizeof(struct guehdr); + if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { + size_t gue_hdrlen, gue_optlen = 0; + + if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) && + skb->ip_summed == CHECKSUM_PARTIAL) { + gue_optlen += GUE_PLEN_REMCSUM + GUE_LEN_PRIV; + } + gue_hdrlen = sizeof(struct guehdr) + gue_optlen; + + max_headroom += sizeof(struct udphdr) + gue_hdrlen; + } /* We only care about the df field if sysctl_pmtu_disc(ipvs) is set */ dfp = sysctl_pmtu_disc(ipvs) ? &df : NULL; @@ -1101,8 +1162,17 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error; gso_type = __tun_gso_type_mask(AF_INET, cp->af); - if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) - gso_type |= SKB_GSO_UDP_TUNNEL; + if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { + if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) || + (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM)) + gso_type |= SKB_GSO_UDP_TUNNEL_CSUM; + else + gso_type |= SKB_GSO_UDP_TUNNEL; + if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) && + skb->ip_summed == CHECKSUM_PARTIAL) { + gso_type |= SKB_GSO_TUNNEL_REMCSUM; + } + } if (iptunnel_handle_offloads(skb, gso_type)) goto tx_error; @@ -1111,8 +1181,19 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, skb_set_inner_ipproto(skb, next_protocol); - if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) - ipvs_gue_encap(net, skb, cp, &next_protocol); + if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { + bool check = false; + + if (ipvs_gue_encap(net, skb, cp, &next_protocol)) + goto tx_error; + + if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) || + (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM)) + check = true; + + udp_set_csum(!check, skb, saddr, cp->daddr.ip, skb->len); + } + skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); @@ -1170,6 +1251,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, unsigned int max_headroom; /* The extra header space needed */ int ret, local; int tun_type, gso_type; + int tun_flags; EnterFunction(10); @@ -1193,9 +1275,19 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr); tun_type = cp->dest->tun_type; + tun_flags = cp->dest->tun_flags; - if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) - max_headroom += sizeof(struct udphdr) + sizeof(struct guehdr); + if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { + size_t gue_hdrlen, gue_optlen = 0; + + if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) && + skb->ip_summed == CHECKSUM_PARTIAL) { + gue_optlen += GUE_PLEN_REMCSUM + GUE_LEN_PRIV; + } + gue_hdrlen = sizeof(struct guehdr) + gue_optlen; + + max_headroom += sizeof(struct udphdr) + gue_hdrlen; + } skb = ip_vs_prepare_tunneled_skb(skb, cp->af, max_headroom, &next_protocol, &payload_len, @@ -1204,8 +1296,17 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error; gso_type = __tun_gso_type_mask(AF_INET6, cp->af); - if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) - gso_type |= SKB_GSO_UDP_TUNNEL; + if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { + if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) || + (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM)) + gso_type |= SKB_GSO_UDP_TUNNEL_CSUM; + else + gso_type |= SKB_GSO_UDP_TUNNEL; + if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM) && + skb->ip_summed == CHECKSUM_PARTIAL) { + gso_type |= SKB_GSO_TUNNEL_REMCSUM; + } + } if (iptunnel_handle_offloads(skb, gso_type)) goto tx_error; @@ -1214,8 +1315,18 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, skb_set_inner_ipproto(skb, next_protocol); - if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) - ipvs_gue_encap(net, skb, cp, &next_protocol); + if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { + bool check = false; + + if (ipvs_gue_encap(net, skb, cp, &next_protocol)) + goto tx_error; + + if ((tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) || + (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_REMCSUM)) + check = true; + + udp6_set_csum(!check, skb, &saddr, &cp->daddr.in6, skb->len); + } skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); @@ -1400,7 +1511,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, } /* copy-on-write the packet before mangling it */ - if (!skb_make_writable(skb, offset)) + if (skb_ensure_writable(skb, offset)) goto tx_error; if (skb_cow(skb, rt->dst.dev->hard_header_len)) @@ -1489,7 +1600,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, } /* copy-on-write the packet before mangling it */ - if (!skb_make_writable(skb, offset)) + if (skb_ensure_writable(skb, offset)) goto tx_error; if (skb_cow(skb, rt->dst.dev->hard_header_len)) diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c index e52fcb9c9a96..921a7b95be68 100644 --- a/net/netfilter/nf_conntrack_broadcast.c +++ b/net/netfilter/nf_conntrack_broadcast.c @@ -37,12 +37,17 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb, in_dev = __in_dev_get_rcu(rt->dst.dev); if (in_dev != NULL) { - for_primary_ifa(in_dev) { + const struct in_ifaddr *ifa; + + in_dev_for_each_ifa_rcu(ifa, in_dev) { + if (ifa->ifa_flags & IFA_F_SECONDARY) + continue; + if (ifa->ifa_broadcast == iph->daddr) { mask = ifa->ifa_mask; break; } - } endfor_ifa(in_dev); + } } if (mask == 0) diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 37bb530d848f..a0560d175a7f 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -16,6 +16,7 @@ #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_bridge.h> #include <net/netfilter/nf_log.h> #include <linux/ip.h> @@ -120,10 +121,8 @@ const struct nf_conntrack_l4proto *nf_ct_l4proto_find(u8 l4proto) }; EXPORT_SYMBOL_GPL(nf_ct_l4proto_find); -static unsigned int nf_confirm(struct sk_buff *skb, - unsigned int protoff, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo) +unsigned int nf_confirm(struct sk_buff *skb, unsigned int protoff, + struct nf_conn *ct, enum ip_conntrack_info ctinfo) { const struct nf_conn_help *help; @@ -154,6 +153,7 @@ static unsigned int nf_confirm(struct sk_buff *skb, /* We've seen it coming out the other side: confirm it */ return nf_conntrack_confirm(skb); } +EXPORT_SYMBOL_GPL(nf_confirm); static unsigned int ipv4_confirm(void *priv, struct sk_buff *skb, @@ -442,12 +442,14 @@ static int nf_ct_tcp_fixup(struct nf_conn *ct, void *_nfproto) return 0; } +static struct nf_ct_bridge_info *nf_ct_bridge_info; + static int nf_ct_netns_do_get(struct net *net, u8 nfproto) { struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); - bool fixup_needed = false; + bool fixup_needed = false, retry = true; int err = 0; - +retry: mutex_lock(&nf_ct_proto_mutex); switch (nfproto) { @@ -487,6 +489,32 @@ static int nf_ct_netns_do_get(struct net *net, u8 nfproto) fixup_needed = true; break; #endif + case NFPROTO_BRIDGE: + if (!nf_ct_bridge_info) { + if (!retry) { + err = -EPROTO; + goto out_unlock; + } + mutex_unlock(&nf_ct_proto_mutex); + request_module("nf_conntrack_bridge"); + retry = false; + goto retry; + } + if (!try_module_get(nf_ct_bridge_info->me)) { + err = -EPROTO; + goto out_unlock; + } + cnet->users_bridge++; + if (cnet->users_bridge > 1) + goto out_unlock; + + err = nf_register_net_hooks(net, nf_ct_bridge_info->ops, + nf_ct_bridge_info->ops_size); + if (err) + cnet->users_bridge = 0; + else + fixup_needed = true; + break; default: err = -EPROTO; break; @@ -519,47 +547,99 @@ static void nf_ct_netns_do_put(struct net *net, u8 nfproto) ARRAY_SIZE(ipv6_conntrack_ops)); break; #endif + case NFPROTO_BRIDGE: + if (!nf_ct_bridge_info) + break; + if (cnet->users_bridge && (--cnet->users_bridge == 0)) + nf_unregister_net_hooks(net, nf_ct_bridge_info->ops, + nf_ct_bridge_info->ops_size); + + module_put(nf_ct_bridge_info->me); + break; } - mutex_unlock(&nf_ct_proto_mutex); } -int nf_ct_netns_get(struct net *net, u8 nfproto) +static int nf_ct_netns_inet_get(struct net *net) { int err; - if (nfproto == NFPROTO_INET) { - err = nf_ct_netns_do_get(net, NFPROTO_IPV4); - if (err < 0) - goto err1; - err = nf_ct_netns_do_get(net, NFPROTO_IPV6); - if (err < 0) - goto err2; - } else { - err = nf_ct_netns_do_get(net, nfproto); - if (err < 0) - goto err1; - } - return 0; + err = nf_ct_netns_do_get(net, NFPROTO_IPV4); + if (err < 0) + goto err1; + err = nf_ct_netns_do_get(net, NFPROTO_IPV6); + if (err < 0) + goto err2; + return err; err2: nf_ct_netns_put(net, NFPROTO_IPV4); err1: return err; } + +int nf_ct_netns_get(struct net *net, u8 nfproto) +{ + int err; + + switch (nfproto) { + case NFPROTO_INET: + err = nf_ct_netns_inet_get(net); + break; + case NFPROTO_BRIDGE: + err = nf_ct_netns_do_get(net, NFPROTO_BRIDGE); + if (err < 0) + return err; + + err = nf_ct_netns_inet_get(net); + if (err < 0) { + nf_ct_netns_put(net, NFPROTO_BRIDGE); + return err; + } + break; + default: + err = nf_ct_netns_do_get(net, nfproto); + break; + } + return err; +} EXPORT_SYMBOL_GPL(nf_ct_netns_get); void nf_ct_netns_put(struct net *net, uint8_t nfproto) { - if (nfproto == NFPROTO_INET) { + switch (nfproto) { + case NFPROTO_BRIDGE: + nf_ct_netns_do_put(net, NFPROTO_BRIDGE); + /* fall through */ + case NFPROTO_INET: nf_ct_netns_do_put(net, NFPROTO_IPV4); nf_ct_netns_do_put(net, NFPROTO_IPV6); - } else { + break; + default: nf_ct_netns_do_put(net, nfproto); + break; } } EXPORT_SYMBOL_GPL(nf_ct_netns_put); +void nf_ct_bridge_register(struct nf_ct_bridge_info *info) +{ + WARN_ON(nf_ct_bridge_info); + mutex_lock(&nf_ct_proto_mutex); + nf_ct_bridge_info = info; + mutex_unlock(&nf_ct_proto_mutex); +} +EXPORT_SYMBOL_GPL(nf_ct_bridge_register); + +void nf_ct_bridge_unregister(struct nf_ct_bridge_info *info) +{ + WARN_ON(!nf_ct_bridge_info); + mutex_lock(&nf_ct_proto_mutex); + nf_ct_bridge_info = NULL; + mutex_unlock(&nf_ct_proto_mutex); +} +EXPORT_SYMBOL_GPL(nf_ct_bridge_unregister); + int nf_conntrack_proto_init(void) { int ret; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 5b8dde266412..07c5208a4ea0 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -339,7 +339,7 @@ static bool sctp_error(struct sk_buff *skb, if (state->hook == NF_INET_PRE_ROUTING && state->net->ct.sysctl_checksum && skb->ip_summed == CHECKSUM_NONE) { - if (!skb_make_writable(skb, dataoff + sizeof(struct sctphdr))) { + if (skb_ensure_writable(skb, dataoff + sizeof(*sh))) { logmsg = "nf_ct_sctp: failed to read header "; goto out_invalid; } diff --git a/net/netfilter/nf_conntrack_seqadj.c b/net/netfilter/nf_conntrack_seqadj.c index dc21a43cd145..3066449f8bd8 100644 --- a/net/netfilter/nf_conntrack_seqadj.c +++ b/net/netfilter/nf_conntrack_seqadj.c @@ -126,7 +126,7 @@ static unsigned int nf_ct_sack_adjust(struct sk_buff *skb, optoff = protoff + sizeof(struct tcphdr); optend = protoff + tcph->doff * 4; - if (!skb_make_writable(skb, optend)) + if (skb_ensure_writable(skb, optend)) return 0; tcph = (void *)skb->data + protoff; @@ -176,7 +176,7 @@ int nf_ct_seq_adjust(struct sk_buff *skb, this_way = &seqadj->seq[dir]; other_way = &seqadj->seq[!dir]; - if (!skb_make_writable(skb, protoff + sizeof(*tcph))) + if (skb_ensure_writable(skb, protoff + sizeof(*tcph))) return 0; tcph = (void *)skb->data + protoff; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 948b4ebbe3fb..e3d797252a98 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -53,7 +53,6 @@ flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct, ft->dst_port = ctt->dst.u.tcp.port; ft->iifidx = other_dst->dev->ifindex; - ft->oifidx = dst->dev->ifindex; ft->dst_cache = dst; } diff --git a/net/netfilter/nf_nat_helper.c b/net/netfilter/nf_nat_helper.c index 53aeb12b70fb..e85423fd7b3c 100644 --- a/net/netfilter/nf_nat_helper.c +++ b/net/netfilter/nf_nat_helper.c @@ -98,7 +98,7 @@ bool __nf_nat_mangle_tcp_packet(struct sk_buff *skb, struct tcphdr *tcph; int oldlen, datalen; - if (!skb_make_writable(skb, skb->len)) + if (skb_ensure_writable(skb, skb->len)) return false; if (rep_len > match_len && @@ -148,7 +148,7 @@ nf_nat_mangle_udp_packet(struct sk_buff *skb, struct udphdr *udph; int datalen, oldlen; - if (!skb_make_writable(skb, skb->len)) + if (skb_ensure_writable(skb, skb->len)) return false; if (rep_len > match_len && diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c index 84f5c90a7f21..04a6c1ac2526 100644 --- a/net/netfilter/nf_nat_proto.c +++ b/net/netfilter/nf_nat_proto.c @@ -73,7 +73,7 @@ static bool udp_manip_pkt(struct sk_buff *skb, struct udphdr *hdr; bool do_csum; - if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct udphdr *)(skb->data + hdroff); @@ -91,7 +91,7 @@ static bool udplite_manip_pkt(struct sk_buff *skb, #ifdef CONFIG_NF_CT_PROTO_UDPLITE struct udphdr *hdr; - if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct udphdr *)(skb->data + hdroff); @@ -117,7 +117,7 @@ sctp_manip_pkt(struct sk_buff *skb, if (skb->len >= hdroff + sizeof(*hdr)) hdrsize = sizeof(*hdr); - if (!skb_make_writable(skb, hdroff + hdrsize)) + if (skb_ensure_writable(skb, hdroff + hdrsize)) return false; hdr = (struct sctphdr *)(skb->data + hdroff); @@ -158,7 +158,7 @@ tcp_manip_pkt(struct sk_buff *skb, if (skb->len >= hdroff + sizeof(struct tcphdr)) hdrsize = sizeof(struct tcphdr); - if (!skb_make_writable(skb, hdroff + hdrsize)) + if (skb_ensure_writable(skb, hdroff + hdrsize)) return false; hdr = (struct tcphdr *)(skb->data + hdroff); @@ -198,7 +198,7 @@ dccp_manip_pkt(struct sk_buff *skb, if (skb->len >= hdroff + sizeof(struct dccp_hdr)) hdrsize = sizeof(struct dccp_hdr); - if (!skb_make_writable(skb, hdroff + hdrsize)) + if (skb_ensure_writable(skb, hdroff + hdrsize)) return false; hdr = (struct dccp_hdr *)(skb->data + hdroff); @@ -232,7 +232,7 @@ icmp_manip_pkt(struct sk_buff *skb, { struct icmphdr *hdr; - if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct icmphdr *)(skb->data + hdroff); @@ -250,7 +250,7 @@ icmpv6_manip_pkt(struct sk_buff *skb, { struct icmp6hdr *hdr; - if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct icmp6hdr *)(skb->data + hdroff); @@ -278,7 +278,7 @@ gre_manip_pkt(struct sk_buff *skb, /* pgreh includes two optional 32bit fields which are not required * to be there. That's where the magic '8' comes from */ - if (!skb_make_writable(skb, hdroff + sizeof(*pgreh) - 8)) + if (skb_ensure_writable(skb, hdroff + sizeof(*pgreh) - 8)) return false; greh = (void *)skb->data + hdroff; @@ -350,7 +350,7 @@ static bool nf_nat_ipv4_manip_pkt(struct sk_buff *skb, struct iphdr *iph; unsigned int hdroff; - if (!skb_make_writable(skb, iphdroff + sizeof(*iph))) + if (skb_ensure_writable(skb, iphdroff + sizeof(*iph))) return false; iph = (void *)skb->data + iphdroff; @@ -381,7 +381,7 @@ static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb, int hdroff; u8 nexthdr; - if (!skb_make_writable(skb, iphdroff + sizeof(*ipv6h))) + if (skb_ensure_writable(skb, iphdroff + sizeof(*ipv6h))) return false; ipv6h = (void *)skb->data + iphdroff; @@ -565,7 +565,7 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb, WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY); - if (!skb_make_writable(skb, hdrlen + sizeof(*inside))) + if (skb_ensure_writable(skb, hdrlen + sizeof(*inside))) return 0; if (nf_ip_checksum(skb, hooknum, hdrlen, 0)) return 0; @@ -787,7 +787,7 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY); - if (!skb_make_writable(skb, hdrlen + sizeof(*inside))) + if (skb_ensure_writable(skb, hdrlen + sizeof(*inside))) return 0; if (nf_ip6_checksum(skb, hooknum, hdrlen, IPPROTO_ICMPV6)) return 0; diff --git a/net/netfilter/nf_nat_redirect.c b/net/netfilter/nf_nat_redirect.c index 78a9e6454ff3..8598e80968e0 100644 --- a/net/netfilter/nf_nat_redirect.c +++ b/net/netfilter/nf_nat_redirect.c @@ -47,15 +47,17 @@ nf_nat_redirect_ipv4(struct sk_buff *skb, if (hooknum == NF_INET_LOCAL_OUT) { newdst = htonl(0x7F000001); } else { - struct in_device *indev; - struct in_ifaddr *ifa; + const struct in_device *indev; newdst = 0; indev = __in_dev_get_rcu(skb->dev); - if (indev && indev->ifa_list) { - ifa = indev->ifa_list; - newdst = ifa->ifa_local; + if (indev) { + const struct in_ifaddr *ifa; + + ifa = rcu_dereference(indev->ifa_list); + if (ifa) + newdst = ifa->ifa_local; } if (!newdst) diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c index 464387b3600f..07805bf4d62a 100644 --- a/net/netfilter/nf_nat_sip.c +++ b/net/netfilter/nf_nat_sip.c @@ -285,7 +285,7 @@ next: if (dir == IP_CT_DIR_REPLY && ct_sip_info->forced_dport) { struct udphdr *uh; - if (!skb_make_writable(skb, skb->len)) { + if (skb_ensure_writable(skb, skb->len)) { nf_ct_helper_log(skb, ct, "cannot mangle packet"); return NF_DROP; } diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 8ff4d22f10b2..3d58a9e93e5a 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -196,7 +196,7 @@ unsigned int synproxy_tstamp_adjust(struct sk_buff *skb, optoff = protoff + sizeof(struct tcphdr); optend = protoff + th->doff * 4; - if (!skb_make_writable(skb, optend)) + if (skb_ensure_writable(skb, optend)) return 0; while (optoff < optend) { diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 4b5159936034..d444405211c5 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1449,25 +1449,18 @@ static struct nft_stats __percpu *nft_stats_alloc(const struct nlattr *attr) return newstats; } -static void nft_chain_stats_replace(struct net *net, - struct nft_base_chain *chain, - struct nft_stats __percpu *newstats) +static void nft_chain_stats_replace(struct nft_trans *trans) { - struct nft_stats __percpu *oldstats; + struct nft_base_chain *chain = nft_base_chain(trans->ctx.chain); - if (newstats == NULL) + if (!nft_trans_chain_stats(trans)) return; - if (rcu_access_pointer(chain->stats)) { - oldstats = rcu_dereference_protected(chain->stats, - lockdep_commit_lock_is_held(net)); - rcu_assign_pointer(chain->stats, newstats); - synchronize_rcu(); - free_percpu(oldstats); - } else { - rcu_assign_pointer(chain->stats, newstats); + rcu_swap_protected(chain->stats, nft_trans_chain_stats(trans), + lockdep_commit_lock_is_held(trans->ctx.net)); + + if (!nft_trans_chain_stats(trans)) static_branch_inc(&nft_counters_enabled); - } } static void nf_tables_chain_free_chain_rules(struct nft_chain *chain) @@ -6362,9 +6355,9 @@ static void nft_chain_commit_update(struct nft_trans *trans) if (!nft_is_base_chain(trans->ctx.chain)) return; + nft_chain_stats_replace(trans); + basechain = nft_base_chain(trans->ctx.chain); - nft_chain_stats_replace(trans->ctx.net, basechain, - nft_trans_chain_stats(trans)); switch (nft_trans_chain_policy(trans)) { case NF_DROP: @@ -6381,6 +6374,7 @@ static void nft_commit_release(struct nft_trans *trans) nf_tables_table_destroy(&trans->ctx); break; case NFT_MSG_NEWCHAIN: + free_percpu(nft_trans_chain_stats(trans)); kfree(nft_trans_chain_name(trans)); break; case NFT_MSG_DELCHAIN: diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index f42326b40d6f..9f5dea0064ea 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -33,6 +33,7 @@ static inline int nf_osf_ttl(const struct sk_buff *skb, { struct in_device *in_dev = __in_dev_get_rcu(skb->dev); const struct iphdr *ip = ip_hdr(skb); + const struct in_ifaddr *ifa; int ret = 0; if (ttl_check == NF_OSF_TTL_TRUE) @@ -42,15 +43,13 @@ static inline int nf_osf_ttl(const struct sk_buff *skb, else if (ip->ttl <= f_ttl) return 1; - for_ifa(in_dev) { + in_dev_for_each_ifa_rcu(ifa, in_dev) { if (inet_ifa_match(ip->saddr, ifa)) { ret = (ip->ttl == f_ttl); break; } } - endfor_ifa(in_dev); - return ret; } diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 27dac47b29c2..831f57008d78 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -863,7 +863,7 @@ nfqnl_mangle(void *data, int data_len, struct nf_queue_entry *e, int diff) } skb_put(e->skb, diff); } - if (!skb_make_writable(e->skb, data_len)) + if (skb_ensure_writable(e->skb, data_len)) return -ENOMEM; skb_copy_to_linear_data(e->skb, data, data_len); e->skb->ip_summed = CHECKSUM_NONE; diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index a940c9fd9045..45c8a6c07783 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -156,7 +156,8 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr, if (i + optl > tcphdr_len || priv->len + priv->offset > optl) return; - if (!skb_make_writable(pkt->skb, pkt->xt.thoff + i + priv->len)) + if (skb_ensure_writable(pkt->skb, + pkt->xt.thoff + i + priv->len)) return; tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff, diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 54e15de4b79a..1465b7d6d2b0 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -243,7 +243,7 @@ static int nft_payload_l4csum_update(const struct nft_pktinfo *pkt, tsum)); } - if (!skb_make_writable(skb, l4csum_offset + sizeof(sum)) || + if (skb_ensure_writable(skb, l4csum_offset + sizeof(sum)) || skb_store_bits(skb, l4csum_offset, &sum, sizeof(sum)) < 0) return -1; @@ -259,7 +259,7 @@ static int nft_payload_csum_inet(struct sk_buff *skb, const u32 *src, return -1; nft_csum_replace(&sum, fsum, tsum); - if (!skb_make_writable(skb, csum_offset + sizeof(sum)) || + if (skb_ensure_writable(skb, csum_offset + sizeof(sum)) || skb_store_bits(skb, csum_offset, &sum, sizeof(sum)) < 0) return -1; @@ -312,7 +312,7 @@ static void nft_payload_set_eval(const struct nft_expr *expr, goto err; } - if (!skb_make_writable(skb, max(offset + priv->len, 0)) || + if (skb_ensure_writable(skb, max(offset + priv->len, 0)) || skb_store_bits(skb, offset, src, priv->len) < 0) goto err; diff --git a/net/netfilter/xt_DSCP.c b/net/netfilter/xt_DSCP.c index 098ed851b7a7..30d554d6c213 100644 --- a/net/netfilter/xt_DSCP.c +++ b/net/netfilter/xt_DSCP.c @@ -34,7 +34,7 @@ dscp_tg(struct sk_buff *skb, const struct xt_action_param *par) u_int8_t dscp = ipv4_get_dsfield(ip_hdr(skb)) >> XT_DSCP_SHIFT; if (dscp != dinfo->dscp) { - if (!skb_make_writable(skb, sizeof(struct iphdr))) + if (skb_ensure_writable(skb, sizeof(struct iphdr))) return NF_DROP; ipv4_change_dsfield(ip_hdr(skb), @@ -52,7 +52,7 @@ dscp_tg6(struct sk_buff *skb, const struct xt_action_param *par) u_int8_t dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> XT_DSCP_SHIFT; if (dscp != dinfo->dscp) { - if (!skb_make_writable(skb, sizeof(struct ipv6hdr))) + if (skb_ensure_writable(skb, sizeof(struct ipv6hdr))) return NF_DROP; ipv6_change_dsfield(ipv6_hdr(skb), @@ -82,7 +82,7 @@ tos_tg(struct sk_buff *skb, const struct xt_action_param *par) nv = (orig & ~info->tos_mask) ^ info->tos_value; if (orig != nv) { - if (!skb_make_writable(skb, sizeof(struct iphdr))) + if (skb_ensure_writable(skb, sizeof(struct iphdr))) return NF_DROP; iph = ip_hdr(skb); ipv4_change_dsfield(iph, 0, nv); @@ -102,7 +102,7 @@ tos_tg6(struct sk_buff *skb, const struct xt_action_param *par) nv = (orig & ~info->tos_mask) ^ info->tos_value; if (orig != nv) { - if (!skb_make_writable(skb, sizeof(struct iphdr))) + if (skb_ensure_writable(skb, sizeof(struct iphdr))) return NF_DROP; iph = ipv6_hdr(skb); ipv6_change_dsfield(iph, 0, nv); diff --git a/net/netfilter/xt_HL.c b/net/netfilter/xt_HL.c index 4653b071bed4..a37b8824221f 100644 --- a/net/netfilter/xt_HL.c +++ b/net/netfilter/xt_HL.c @@ -32,7 +32,7 @@ ttl_tg(struct sk_buff *skb, const struct xt_action_param *par) const struct ipt_TTL_info *info = par->targinfo; int new_ttl; - if (!skb_make_writable(skb, skb->len)) + if (skb_ensure_writable(skb, sizeof(*iph))) return NF_DROP; iph = ip_hdr(skb); @@ -72,7 +72,7 @@ hl_tg6(struct sk_buff *skb, const struct xt_action_param *par) const struct ip6t_HL_info *info = par->targinfo; int new_hl; - if (!skb_make_writable(skb, skb->len)) + if (skb_ensure_writable(skb, sizeof(*ip6h))) return NF_DROP; ip6h = ipv6_hdr(skb); diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 98efb202f8b4..3e24443ab81c 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -89,7 +89,7 @@ tcpmss_mangle_packet(struct sk_buff *skb, if (par->fragoff != 0) return 0; - if (!skb_make_writable(skb, skb->len)) + if (skb_ensure_writable(skb, skb->len)) return -1; len = skb->len - tcphoff; diff --git a/net/netfilter/xt_TCPOPTSTRIP.c b/net/netfilter/xt_TCPOPTSTRIP.c index eb92bffff11c..5a274813076a 100644 --- a/net/netfilter/xt_TCPOPTSTRIP.c +++ b/net/netfilter/xt_TCPOPTSTRIP.c @@ -31,33 +31,33 @@ static inline unsigned int optlen(const u_int8_t *opt, unsigned int offset) static unsigned int tcpoptstrip_mangle_packet(struct sk_buff *skb, const struct xt_action_param *par, - unsigned int tcphoff, unsigned int minlen) + unsigned int tcphoff) { const struct xt_tcpoptstrip_target_info *info = par->targinfo; + struct tcphdr *tcph, _th; unsigned int optl, i, j; - struct tcphdr *tcph; u_int16_t n, o; u_int8_t *opt; - int len, tcp_hdrlen; + int tcp_hdrlen; /* This is a fragment, no TCP header is available */ if (par->fragoff != 0) return XT_CONTINUE; - if (!skb_make_writable(skb, skb->len)) + tcph = skb_header_pointer(skb, tcphoff, sizeof(_th), &_th); + if (!tcph) return NF_DROP; - len = skb->len - tcphoff; - if (len < (int)sizeof(struct tcphdr)) - return NF_DROP; - - tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff); tcp_hdrlen = tcph->doff * 4; + if (tcp_hdrlen < sizeof(struct tcphdr)) + return NF_DROP; - if (len < tcp_hdrlen) + if (skb_ensure_writable(skb, tcphoff + tcp_hdrlen)) return NF_DROP; - opt = (u_int8_t *)tcph; + /* must reload tcph, might have been moved */ + tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff); + opt = (u8 *)tcph; /* * Walk through all TCP options - if we find some option to remove, @@ -91,8 +91,7 @@ tcpoptstrip_mangle_packet(struct sk_buff *skb, static unsigned int tcpoptstrip_tg4(struct sk_buff *skb, const struct xt_action_param *par) { - return tcpoptstrip_mangle_packet(skb, par, ip_hdrlen(skb), - sizeof(struct iphdr) + sizeof(struct tcphdr)); + return tcpoptstrip_mangle_packet(skb, par, ip_hdrlen(skb)); } #if IS_ENABLED(CONFIG_IP6_NF_MANGLE) @@ -109,8 +108,7 @@ tcpoptstrip_tg6(struct sk_buff *skb, const struct xt_action_param *par) if (tcphoff < 0) return NF_DROP; - return tcpoptstrip_mangle_packet(skb, par, tcphoff, - sizeof(*ipv6h) + sizeof(struct tcphdr)); + return tcpoptstrip_mangle_packet(skb, par, tcphoff); } #endif diff --git a/net/netfilter/xt_owner.c b/net/netfilter/xt_owner.c index 46686fb73784..a8784502aca6 100644 --- a/net/netfilter/xt_owner.c +++ b/net/netfilter/xt_owner.c @@ -91,11 +91,28 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par) } if (info->match & XT_OWNER_GID) { + unsigned int i, match = false; kgid_t gid_min = make_kgid(net->user_ns, info->gid_min); kgid_t gid_max = make_kgid(net->user_ns, info->gid_max); - if ((gid_gte(filp->f_cred->fsgid, gid_min) && - gid_lte(filp->f_cred->fsgid, gid_max)) ^ - !(info->invert & XT_OWNER_GID)) + struct group_info *gi = filp->f_cred->group_info; + + if (gid_gte(filp->f_cred->fsgid, gid_min) && + gid_lte(filp->f_cred->fsgid, gid_max)) + match = true; + + if (!match && (info->match & XT_OWNER_SUPPL_GROUPS) && gi) { + for (i = 0; i < gi->ngroups; ++i) { + kgid_t group = gi->gid[i]; + + if (gid_gte(group, gid_min) && + gid_lte(group, gid_max)) { + match = true; + break; + } + } + } + + if (match ^ !(info->invert & XT_OWNER_GID)) return false; } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index dc9ff9367221..4076e080914a 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1347,7 +1347,7 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) reply = ovs_flow_cmd_alloc_info((const struct sw_flow_actions __force *) flow->sf_acts, &flow->id, info, false, ufid_flags); if (likely(reply)) { - if (likely(!IS_ERR(reply))) { + if (!IS_ERR(reply)) { rcu_read_lock(); /*To keep RCU checker happy. */ err = ovs_flow_cmd_fill_info(flow, ovs_header->dp_ifindex, reply, info->snd_portid, diff --git a/net/rds/ib.c b/net/rds/ib.c index b8d581b779b2..ec05d91aa9a2 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -318,6 +318,7 @@ static int rds_ib_conn_info_visitor(struct rds_connection *conn, iinfo->max_recv_wr = ic->i_recv_ring.w_nr; iinfo->max_send_sge = rds_ibdev->max_sge; rds_ib_get_mr_info(rds_ibdev, iinfo); + iinfo->cache_allocs = atomic_read(&ic->i_cache_allocs); } return 1; } @@ -351,6 +352,7 @@ static int rds6_ib_conn_info_visitor(struct rds_connection *conn, iinfo6->max_recv_wr = ic->i_recv_ring.w_nr; iinfo6->max_send_sge = rds_ibdev->max_sge; rds6_ib_get_mr_info(rds_ibdev, iinfo6); + iinfo6->cache_allocs = atomic_read(&ic->i_cache_allocs); } return 1; } diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 2c72d95c3050..d104f7ee26c7 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -877,6 +877,23 @@ config NET_ACT_CONNMARK To compile this code as a module, choose M here: the module will be called act_connmark. +config NET_ACT_CTINFO + tristate "Netfilter Connection Mark Actions" + depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES + depends on NF_CONNTRACK && NF_CONNTRACK_MARK + help + Say Y here to allow transfer of a connmark stored information. + Current actions transfer connmark stored DSCP into + ipv4/v6 diffserv and/or to transfer connmark to packet + mark. Both are useful for restoring egress based marks + back onto ingress connections for qdisc priority mapping + purposes. + + If unsure, say N. + + To compile this code as a module, choose M here: the + module will be called act_ctinfo. + config NET_ACT_SKBMOD tristate "skb data modification action" depends on NET_CLS_ACT diff --git a/net/sched/Makefile b/net/sched/Makefile index 8a40431d7b5c..d54bfcbd7981 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -21,6 +21,7 @@ obj-$(CONFIG_NET_ACT_CSUM) += act_csum.o obj-$(CONFIG_NET_ACT_VLAN) += act_vlan.o obj-$(CONFIG_NET_ACT_BPF) += act_bpf.o obj-$(CONFIG_NET_ACT_CONNMARK) += act_connmark.o +obj-$(CONFIG_NET_ACT_CTINFO) += act_ctinfo.o obj-$(CONFIG_NET_ACT_SKBMOD) += act_skbmod.o obj-$(CONFIG_NET_ACT_IFE) += act_ife.o obj-$(CONFIG_NET_IFE_SKBMARK) += act_meta_mark.o diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c new file mode 100644 index 000000000000..e78b60e47c0f --- /dev/null +++ b/net/sched/act_ctinfo.c @@ -0,0 +1,392 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* net/sched/act_ctinfo.c netfilter ctinfo connmark actions + * + * Copyright (c) 2019 Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk> + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/skbuff.h> +#include <linux/rtnetlink.h> +#include <linux/pkt_cls.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <net/netlink.h> +#include <net/pkt_sched.h> +#include <net/act_api.h> +#include <net/pkt_cls.h> +#include <uapi/linux/tc_act/tc_ctinfo.h> +#include <net/tc_act/tc_ctinfo.h> + +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_ecache.h> +#include <net/netfilter/nf_conntrack_zones.h> + +static struct tc_action_ops act_ctinfo_ops; +static unsigned int ctinfo_net_id; + +static void tcf_ctinfo_dscp_set(struct nf_conn *ct, struct tcf_ctinfo *ca, + struct tcf_ctinfo_params *cp, + struct sk_buff *skb, int wlen, int proto) +{ + u8 dscp, newdscp; + + newdscp = (((ct->mark & cp->dscpmask) >> cp->dscpmaskshift) << 2) & + ~INET_ECN_MASK; + + switch (proto) { + case NFPROTO_IPV4: + dscp = ipv4_get_dsfield(ip_hdr(skb)) & ~INET_ECN_MASK; + if (dscp != newdscp) { + if (likely(!skb_try_make_writable(skb, wlen))) { + ipv4_change_dsfield(ip_hdr(skb), + INET_ECN_MASK, + newdscp); + ca->stats_dscp_set++; + } else { + ca->stats_dscp_error++; + } + } + break; + case NFPROTO_IPV6: + dscp = ipv6_get_dsfield(ipv6_hdr(skb)) & ~INET_ECN_MASK; + if (dscp != newdscp) { + if (likely(!skb_try_make_writable(skb, wlen))) { + ipv6_change_dsfield(ipv6_hdr(skb), + INET_ECN_MASK, + newdscp); + ca->stats_dscp_set++; + } else { + ca->stats_dscp_error++; + } + } + break; + default: + break; + } +} + +static void tcf_ctinfo_cpmark_set(struct nf_conn *ct, struct tcf_ctinfo *ca, + struct tcf_ctinfo_params *cp, + struct sk_buff *skb) +{ + ca->stats_cpmark_set++; + skb->mark = ct->mark & cp->cpmarkmask; +} + +static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a, + struct tcf_result *res) +{ + const struct nf_conntrack_tuple_hash *thash = NULL; + struct tcf_ctinfo *ca = to_ctinfo(a); + struct nf_conntrack_tuple tuple; + struct nf_conntrack_zone zone; + enum ip_conntrack_info ctinfo; + struct tcf_ctinfo_params *cp; + struct nf_conn *ct; + int proto, wlen; + int action; + + cp = rcu_dereference_bh(ca->params); + + tcf_lastuse_update(&ca->tcf_tm); + bstats_update(&ca->tcf_bstats, skb); + action = READ_ONCE(ca->tcf_action); + + wlen = skb_network_offset(skb); + if (tc_skb_protocol(skb) == htons(ETH_P_IP)) { + wlen += sizeof(struct iphdr); + if (!pskb_may_pull(skb, wlen)) + goto out; + + proto = NFPROTO_IPV4; + } else if (tc_skb_protocol(skb) == htons(ETH_P_IPV6)) { + wlen += sizeof(struct ipv6hdr); + if (!pskb_may_pull(skb, wlen)) + goto out; + + proto = NFPROTO_IPV6; + } else { + goto out; + } + + ct = nf_ct_get(skb, &ctinfo); + if (!ct) { /* look harder, usually ingress */ + if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), + proto, cp->net, &tuple)) + goto out; + zone.id = cp->zone; + zone.dir = NF_CT_DEFAULT_ZONE_DIR; + + thash = nf_conntrack_find_get(cp->net, &zone, &tuple); + if (!thash) + goto out; + + ct = nf_ct_tuplehash_to_ctrack(thash); + } + + if (cp->mode & CTINFO_MODE_DSCP) + if (!cp->dscpstatemask || (ct->mark & cp->dscpstatemask)) + tcf_ctinfo_dscp_set(ct, ca, cp, skb, wlen, proto); + + if (cp->mode & CTINFO_MODE_CPMARK) + tcf_ctinfo_cpmark_set(ct, ca, cp, skb); + + if (thash) + nf_ct_put(ct); +out: + return action; +} + +static const struct nla_policy ctinfo_policy[TCA_CTINFO_MAX + 1] = { + [TCA_CTINFO_ACT] = { .len = sizeof(struct + tc_ctinfo) }, + [TCA_CTINFO_ZONE] = { .type = NLA_U16 }, + [TCA_CTINFO_PARMS_DSCP_MASK] = { .type = NLA_U32 }, + [TCA_CTINFO_PARMS_DSCP_STATEMASK] = { .type = NLA_U32 }, + [TCA_CTINFO_PARMS_CPMARK_MASK] = { .type = NLA_U32 }, +}; + +static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action **a, + int ovr, int bind, bool rtnl_held, + struct tcf_proto *tp, + struct netlink_ext_ack *extack) +{ + struct tc_action_net *tn = net_generic(net, ctinfo_net_id); + struct nlattr *tb[TCA_CTINFO_MAX + 1]; + struct tcf_ctinfo_params *cp_new; + struct tcf_chain *goto_ch = NULL; + u32 dscpmask = 0, dscpstatemask; + struct tc_ctinfo *actparm; + struct tcf_ctinfo *ci; + u8 dscpmaskshift; + int ret = 0, err; + + if (!nla) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_CTINFO_MAX, nla, ctinfo_policy, NULL); + if (err < 0) + return err; + + if (!tb[TCA_CTINFO_ACT]) + return -EINVAL; + actparm = nla_data(tb[TCA_CTINFO_ACT]); + + /* do some basic validation here before dynamically allocating things */ + /* that we would otherwise have to clean up. */ + if (tb[TCA_CTINFO_PARMS_DSCP_MASK]) { + dscpmask = nla_get_u32(tb[TCA_CTINFO_PARMS_DSCP_MASK]); + /* need contiguous 6 bit mask */ + dscpmaskshift = dscpmask ? __ffs(dscpmask) : 0; + if ((~0 & (dscpmask >> dscpmaskshift)) != 0x3f) + return -EINVAL; + dscpstatemask = tb[TCA_CTINFO_PARMS_DSCP_STATEMASK] ? + nla_get_u32(tb[TCA_CTINFO_PARMS_DSCP_STATEMASK]) : 0; + /* mask & statemask must not overlap */ + if (dscpmask & dscpstatemask) + return -EINVAL; + } + + /* done the validation:now to the actual action allocation */ + err = tcf_idr_check_alloc(tn, &actparm->index, a, bind); + if (!err) { + ret = tcf_idr_create(tn, actparm->index, est, a, + &act_ctinfo_ops, bind, false); + if (ret) { + tcf_idr_cleanup(tn, actparm->index); + return ret; + } + } else if (err > 0) { + if (bind) /* don't override defaults */ + return 0; + if (!ovr) { + tcf_idr_release(*a, bind); + return -EEXIST; + } + } else { + return err; + } + + err = tcf_action_check_ctrlact(actparm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; + + ci = to_ctinfo(*a); + + cp_new = kzalloc(sizeof(*cp_new), GFP_KERNEL); + if (unlikely(!cp_new)) { + err = -ENOMEM; + goto put_chain; + } + + cp_new->net = net; + cp_new->zone = tb[TCA_CTINFO_ZONE] ? + nla_get_u16(tb[TCA_CTINFO_ZONE]) : 0; + if (dscpmask) { + cp_new->dscpmask = dscpmask; + cp_new->dscpmaskshift = dscpmaskshift; + cp_new->dscpstatemask = dscpstatemask; + cp_new->mode |= CTINFO_MODE_DSCP; + } + + if (tb[TCA_CTINFO_PARMS_CPMARK_MASK]) { + cp_new->cpmarkmask = + nla_get_u32(tb[TCA_CTINFO_PARMS_CPMARK_MASK]); + cp_new->mode |= CTINFO_MODE_CPMARK; + } + + spin_lock_bh(&ci->tcf_lock); + goto_ch = tcf_action_set_ctrlact(*a, actparm->action, goto_ch); + rcu_swap_protected(ci->params, cp_new, + lockdep_is_held(&ci->tcf_lock)); + spin_unlock_bh(&ci->tcf_lock); + + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + if (cp_new) + kfree_rcu(cp_new, rcu); + + if (ret == ACT_P_CREATED) + tcf_idr_insert(tn, *a); + + return ret; + +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + tcf_idr_release(*a, bind); + return err; +} + +static int tcf_ctinfo_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) +{ + struct tcf_ctinfo *ci = to_ctinfo(a); + struct tc_ctinfo opt = { + .index = ci->tcf_index, + .refcnt = refcount_read(&ci->tcf_refcnt) - ref, + .bindcnt = atomic_read(&ci->tcf_bindcnt) - bind, + }; + unsigned char *b = skb_tail_pointer(skb); + struct tcf_ctinfo_params *cp; + struct tcf_t t; + + spin_lock_bh(&ci->tcf_lock); + cp = rcu_dereference_protected(ci->params, + lockdep_is_held(&ci->tcf_lock)); + + tcf_tm_dump(&t, &ci->tcf_tm); + if (nla_put_64bit(skb, TCA_CTINFO_TM, sizeof(t), &t, TCA_CTINFO_PAD)) + goto nla_put_failure; + + opt.action = ci->tcf_action; + if (nla_put(skb, TCA_CTINFO_ACT, sizeof(opt), &opt)) + goto nla_put_failure; + + if (nla_put_u16(skb, TCA_CTINFO_ZONE, cp->zone)) + goto nla_put_failure; + + if (cp->mode & CTINFO_MODE_DSCP) { + if (nla_put_u32(skb, TCA_CTINFO_PARMS_DSCP_MASK, + cp->dscpmask)) + goto nla_put_failure; + if (nla_put_u32(skb, TCA_CTINFO_PARMS_DSCP_STATEMASK, + cp->dscpstatemask)) + goto nla_put_failure; + } + + if (cp->mode & CTINFO_MODE_CPMARK) { + if (nla_put_u32(skb, TCA_CTINFO_PARMS_CPMARK_MASK, + cp->cpmarkmask)) + goto nla_put_failure; + } + + if (nla_put_u64_64bit(skb, TCA_CTINFO_STATS_DSCP_SET, + ci->stats_dscp_set, TCA_CTINFO_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(skb, TCA_CTINFO_STATS_DSCP_ERROR, + ci->stats_dscp_error, TCA_CTINFO_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(skb, TCA_CTINFO_STATS_CPMARK_SET, + ci->stats_cpmark_set, TCA_CTINFO_PAD)) + goto nla_put_failure; + + spin_unlock_bh(&ci->tcf_lock); + return skb->len; + +nla_put_failure: + spin_unlock_bh(&ci->tcf_lock); + nlmsg_trim(skb, b); + return -1; +} + +static int tcf_ctinfo_walker(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, int type, + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) +{ + struct tc_action_net *tn = net_generic(net, ctinfo_net_id); + + return tcf_generic_walker(tn, skb, cb, type, ops, extack); +} + +static int tcf_ctinfo_search(struct net *net, struct tc_action **a, u32 index) +{ + struct tc_action_net *tn = net_generic(net, ctinfo_net_id); + + return tcf_idr_search(tn, a, index); +} + +static struct tc_action_ops act_ctinfo_ops = { + .kind = "ctinfo", + .id = TCA_ID_CTINFO, + .owner = THIS_MODULE, + .act = tcf_ctinfo_act, + .dump = tcf_ctinfo_dump, + .init = tcf_ctinfo_init, + .walk = tcf_ctinfo_walker, + .lookup = tcf_ctinfo_search, + .size = sizeof(struct tcf_ctinfo), +}; + +static __net_init int ctinfo_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, ctinfo_net_id); + + return tc_action_net_init(tn, &act_ctinfo_ops); +} + +static void __net_exit ctinfo_exit_net(struct list_head *net_list) +{ + tc_action_net_exit(net_list, ctinfo_net_id); +} + +static struct pernet_operations ctinfo_net_ops = { + .init = ctinfo_init_net, + .exit_batch = ctinfo_exit_net, + .id = &ctinfo_net_id, + .size = sizeof(struct tc_action_net), +}; + +static int __init ctinfo_init_module(void) +{ + return tcf_register_action(&act_ctinfo_ops, &ctinfo_net_ops); +} + +static void __exit ctinfo_cleanup_module(void) +{ + tcf_unregister_action(&act_ctinfo_ops, &ctinfo_net_ops); +} + +module_init(ctinfo_init_module); +module_exit(ctinfo_cleanup_module); +MODULE_AUTHOR("Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>"); +MODULE_DESCRIPTION("Connection tracking mark actions"); +MODULE_LICENSE("GPL"); diff --git a/net/sctp/offload.c b/net/sctp/offload.c index 2cae7440349c..74847d613835 100644 --- a/net/sctp/offload.c +++ b/net/sctp/offload.c @@ -94,11 +94,6 @@ static const struct net_offload sctp6_offload = { }, }; -static const struct skb_checksum_ops crc32c_csum_ops = { - .update = sctp_csum_update, - .combine = sctp_csum_combine, -}; - int __init sctp_offload_init(void) { int ret; @@ -111,7 +106,7 @@ int __init sctp_offload_init(void) if (ret) goto ipv4; - crc32c_csum_stub = &crc32c_csum_ops; + crc32c_csum_stub = &sctp_csum_ops; return ret; ipv4: diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 23af232c0a25..2d47adcb4cbe 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -81,7 +81,7 @@ static void sctp_v4_copy_addrlist(struct list_head *addrlist, return; } - for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) { + in_dev_for_each_ifa_rcu(ifa, in_dev) { /* Add the address to the local list. */ addr = kzalloc(sizeof(*addr), GFP_ATOMIC); if (addr) { diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 745afd82f281..49bcebff6378 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -97,17 +97,19 @@ static int smc_clc_prfx_set4_rcu(struct dst_entry *dst, __be32 ipv4, struct smc_clc_msg_proposal_prefix *prop) { struct in_device *in_dev = __in_dev_get_rcu(dst->dev); + const struct in_ifaddr *ifa; if (!in_dev) return -ENODEV; - for_ifa(in_dev) { + + in_dev_for_each_ifa_rcu(ifa, in_dev) { if (!inet_ifa_match(ipv4, ifa)) continue; prop->prefix_len = inet_mask_len(ifa->ifa_mask); prop->outgoing_subnet = ifa->ifa_address & ifa->ifa_mask; /* prop->ipv6_prefixes_cnt = 0; already done by memset before */ return 0; - } endfor_ifa(in_dev); + } return -ENOENT; } @@ -190,14 +192,15 @@ static int smc_clc_prfx_match4_rcu(struct net_device *dev, struct smc_clc_msg_proposal_prefix *prop) { struct in_device *in_dev = __in_dev_get_rcu(dev); + const struct in_ifaddr *ifa; if (!in_dev) return -ENODEV; - for_ifa(in_dev) { + in_dev_for_each_ifa_rcu(ifa, in_dev) { if (prop->prefix_len == inet_mask_len(ifa->ifa_mask) && inet_ifa_match(prop->outgoing_subnet, ifa)) return 0; - } endfor_ifa(in_dev); + } return -ENOENT; } diff --git a/net/socket.c b/net/socket.c index 38eec1583f6d..963df5dbdd54 100644 --- a/net/socket.c +++ b/net/socket.c @@ -429,7 +429,7 @@ static int sock_map_fd(struct socket *sock, int flags) } newfile = sock_alloc_file(sock, flags, NULL); - if (likely(!IS_ERR(newfile))) { + if (!IS_ERR(newfile)) { fd_install(fd, newfile); return fd; } diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index e137698e8aef..3fe541b746b0 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -160,18 +160,14 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, return 0; } - skb = alloc_skb(0, GFP_ATOMIC); + skb = alloc_skb_for_msg(head); if (!skb) { STRP_STATS_INCR(strp->stats.mem_fail); desc->error = -ENOMEM; return 0; } - skb->len = head->len; - skb->data_len = head->len; - skb->truesize = head->truesize; - *_strp_msg(skb) = *_strp_msg(head); + strp->skb_nextp = &head->next; - skb_shinfo(skb)->frag_list = head; strp->skb_head = skb; head = skb; } else { diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 1f9cf57d9754..43f2deb57078 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -252,7 +252,7 @@ static int tls_push_record(struct sock *sk, skb_frag_address(frag), record->len - prot->prepend_size, record_type, - ctx->crypto_send.info.version); + prot->version); /* HW doesn't care about the data in the tag, because it fills it. */ dummy_tag_frag.page = skb_frag_page(frag); @@ -264,7 +264,7 @@ static int tls_push_record(struct sock *sk, list_add_tail(&record->list, &offload_ctx->records_list); spin_unlock_irq(&offload_ctx->lock); offload_ctx->open_record = NULL; - tls_advance_record_sn(sk, &ctx->tx, ctx->crypto_send.info.version); + tls_advance_record_sn(sk, prot, &ctx->tx); for (i = 0; i < record->num_frags; i++) { frag = &record->frags[i]; @@ -610,8 +610,10 @@ static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb) sg_set_buf(&sg[0], buf, rxm->full_len + TLS_HEADER_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE); - skb_copy_bits(skb, offset, buf, - TLS_HEADER_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE); + err = skb_copy_bits(skb, offset, buf, + TLS_HEADER_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE); + if (err) + goto free_buf; /* We are interested only in the decrypted data not the auth */ err = decrypt_skb(sk, skb, sg); @@ -625,8 +627,11 @@ static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb) if (skb_pagelen(skb) > offset) { copy = min_t(int, skb_pagelen(skb) - offset, data_len); - if (skb->decrypted) - skb_store_bits(skb, offset, buf, copy); + if (skb->decrypted) { + err = skb_store_bits(skb, offset, buf, copy); + if (err) + goto free_buf; + } offset += copy; buf += copy; @@ -649,8 +654,11 @@ static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb) copy = min_t(int, skb_iter->len - frag_pos, data_len + rxm->offset - offset); - if (skb_iter->decrypted) - skb_store_bits(skb_iter, frag_pos, buf, copy); + if (skb_iter->decrypted) { + err = skb_store_bits(skb_iter, frag_pos, buf, copy); + if (err) + goto free_buf; + } offset += copy; buf += copy; @@ -671,10 +679,6 @@ int tls_device_decrypted(struct sock *sk, struct sk_buff *skb) int is_encrypted = !is_decrypted; struct sk_buff *skb_iter; - /* Skip if it is already decrypted */ - if (ctx->sw.decrypted) - return 0; - /* Check if all the data is decrypted already */ skb_walk_frags(skb, skb_iter) { is_decrypted &= skb_iter->decrypted; diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index c3a5fe624b4e..1d2d804ac633 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -240,7 +240,6 @@ static int fill_sg_in(struct scatterlist *sg_in, record = tls_get_record(ctx, tcp_seq, rcd_sn); if (!record) { spin_unlock_irqrestore(&ctx->lock, flags); - WARN(1, "Record not found for seq %u\n", tcp_seq); return -EINVAL; } @@ -409,7 +408,10 @@ put_sg: put_page(sg_page(&sg_in[--resync_sgs])); kfree(sg_in); free_orig: - kfree_skb(skb); + if (nskb) + consume_skb(skb); + else + kfree_skb(skb); return nskb; } @@ -424,6 +426,12 @@ struct sk_buff *tls_validate_xmit_skb(struct sock *sk, } EXPORT_SYMBOL_GPL(tls_validate_xmit_skb); +struct sk_buff *tls_encrypt_skb(struct sk_buff *skb) +{ + return tls_sw_fallback(skb->sk, skb); +} +EXPORT_SYMBOL_GPL(tls_encrypt_skb); + int tls_sw_fallback_init(struct sock *sk, struct tls_offload_context_tx *offload_ctx, struct tls_crypto_info *crypto_info) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 960494f437ac..bef71e54fad0 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -534,7 +534,7 @@ static int tls_do_encryption(struct sock *sk, /* Unhook the record from context if encryption is not failure */ ctx->open_rec = NULL; - tls_advance_record_sn(sk, &tls_ctx->tx, prot->version); + tls_advance_record_sn(sk, prot, &tls_ctx->tx); return rc; } @@ -1486,15 +1486,16 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); struct tls_prot_info *prot = &tls_ctx->prot_info; - int version = prot->version; struct strp_msg *rxm = strp_msg(skb); int pad, err = 0; if (!ctx->decrypted) { #ifdef CONFIG_TLS_DEVICE - err = tls_device_decrypted(sk, skb); - if (err < 0) - return err; + if (tls_ctx->rx_conf == TLS_HW) { + err = tls_device_decrypted(sk, skb); + if (err < 0) + return err; + } #endif /* Still not decrypted after tls_device */ if (!ctx->decrypted) { @@ -1502,8 +1503,8 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, async); if (err < 0) { if (err == -EINPROGRESS) - tls_advance_record_sn(sk, &tls_ctx->rx, - version); + tls_advance_record_sn(sk, prot, + &tls_ctx->rx); return err; } @@ -1518,7 +1519,7 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, rxm->full_len -= pad; rxm->offset += prot->prepend_size; rxm->full_len -= prot->overhead_size; - tls_advance_record_sn(sk, &tls_ctx->rx, version); + tls_advance_record_sn(sk, prot, &tls_ctx->rx); ctx->decrypted = true; ctx->saved_data_ready(sk); } else { diff --git a/net/unix/diag.c b/net/unix/diag.c index c51a707260fa..9ff64f9df1f3 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -5,9 +5,11 @@ #include <linux/unix_diag.h> #include <linux/skbuff.h> #include <linux/module.h> +#include <linux/uidgid.h> #include <net/netlink.h> #include <net/af_unix.h> #include <net/tcp_states.h> +#include <net/sock.h> static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb) { @@ -111,6 +113,12 @@ static int sk_diag_show_rqlen(struct sock *sk, struct sk_buff *nlskb) return nla_put(nlskb, UNIX_DIAG_RQLEN, sizeof(rql), &rql); } +static int sk_diag_dump_uid(struct sock *sk, struct sk_buff *nlskb) +{ + uid_t uid = from_kuid_munged(sk_user_ns(nlskb->sk), sock_i_uid(sk)); + return nla_put(nlskb, UNIX_DIAG_UID, sizeof(uid_t), &uid); +} + static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req, u32 portid, u32 seq, u32 flags, int sk_ino) { @@ -157,6 +165,10 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r if (nla_put_u8(skb, UNIX_DIAG_SHUTDOWN, sk->sk_shutdown)) goto out_nlmsg_trim; + if ((req->udiag_show & UDIAG_SHOW_UID) && + sk_diag_dump_uid(sk, skb)) + goto out_nlmsg_trim; + nlmsg_end(skb, nlh); return 0; diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index 982a8dc49e03..063073fd4952 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -23,14 +23,14 @@ #include <net/sock.h> #include <net/af_vsock.h> -/* The host side's design of the feature requires 6 exact 4KB pages for - * recv/send rings respectively -- this is suboptimal considering memory - * consumption, however unluckily we have to live with it, before the - * host comes up with a better design in the future. +/* Older (VMBUS version 'VERSION_WIN10' or before) Windows hosts have some + * stricter requirements on the hv_sock ring buffer size of six 4K pages. Newer + * hosts don't have this limitation; but, keep the defaults the same for compat. */ #define PAGE_SIZE_4K 4096 #define RINGBUFFER_HVS_RCV_SIZE (PAGE_SIZE_4K * 6) #define RINGBUFFER_HVS_SND_SIZE (PAGE_SIZE_4K * 6) +#define RINGBUFFER_HVS_MAX_SIZE (PAGE_SIZE_4K * 64) /* The MTU is 16KB per the host side's design */ #define HVS_MTU_SIZE (1024 * 16) @@ -55,8 +55,9 @@ struct hvs_recv_buf { }; /* We can send up to HVS_MTU_SIZE bytes of payload to the host, but let's use - * a small size, i.e. HVS_SEND_BUF_SIZE, to minimize the dynamically-allocated - * buffer, because tests show there is no significant performance difference. + * a smaller size, i.e. HVS_SEND_BUF_SIZE, to maximize concurrency between the + * guest and the host processing as one VMBUS packet is the smallest processing + * unit. * * Note: the buffer can be eliminated in the future when we add new VMBus * ringbuffer APIs that allow us to directly copy data from userspace buffer @@ -344,9 +345,12 @@ static void hvs_open_connection(struct vmbus_channel *chan) struct sockaddr_vm addr; struct sock *sk, *new = NULL; - struct vsock_sock *vnew; - struct hvsock *hvs, *hvs_new; + struct vsock_sock *vnew = NULL; + struct hvsock *hvs = NULL; + struct hvsock *hvs_new = NULL; + int rcvbuf; int ret; + int sndbuf; if_type = &chan->offermsg.offer.if_type; if_instance = &chan->offermsg.offer.if_instance; @@ -388,9 +392,34 @@ static void hvs_open_connection(struct vmbus_channel *chan) } set_channel_read_mode(chan, HV_CALL_DIRECT); - ret = vmbus_open(chan, RINGBUFFER_HVS_SND_SIZE, - RINGBUFFER_HVS_RCV_SIZE, NULL, 0, - hvs_channel_cb, conn_from_host ? new : sk); + + /* Use the socket buffer sizes as hints for the VMBUS ring size. For + * server side sockets, 'sk' is the parent socket and thus, this will + * allow the child sockets to inherit the size from the parent. Keep + * the mins to the default value and align to page size as per VMBUS + * requirements. + * For the max, the socket core library will limit the socket buffer + * size that can be set by the user, but, since currently, the hv_sock + * VMBUS ring buffer is physically contiguous allocation, restrict it + * further. + * Older versions of hv_sock host side code cannot handle bigger VMBUS + * ring buffer size. Use the version number to limit the change to newer + * versions. + */ + if (vmbus_proto_version < VERSION_WIN10_V5) { + sndbuf = RINGBUFFER_HVS_SND_SIZE; + rcvbuf = RINGBUFFER_HVS_RCV_SIZE; + } else { + sndbuf = max_t(int, sk->sk_sndbuf, RINGBUFFER_HVS_SND_SIZE); + sndbuf = min_t(int, sndbuf, RINGBUFFER_HVS_MAX_SIZE); + sndbuf = ALIGN(sndbuf, PAGE_SIZE); + rcvbuf = max_t(int, sk->sk_rcvbuf, RINGBUFFER_HVS_RCV_SIZE); + rcvbuf = min_t(int, rcvbuf, RINGBUFFER_HVS_MAX_SIZE); + rcvbuf = ALIGN(rcvbuf, PAGE_SIZE); + } + + ret = vmbus_open(chan, sndbuf, rcvbuf, NULL, 0, hvs_channel_cb, + conn_from_host ? new : sk); if (ret != 0) { if (conn_from_host) { hvs_new->chan = NULL; @@ -441,6 +470,7 @@ static u32 hvs_get_local_cid(void) static int hvs_sock_init(struct vsock_sock *vsk, struct vsock_sock *psk) { struct hvsock *hvs; + struct sock *sk = sk_vsock(vsk); hvs = kzalloc(sizeof(*hvs), GFP_KERNEL); if (!hvs) @@ -448,7 +478,8 @@ static int hvs_sock_init(struct vsock_sock *vsk, struct vsock_sock *psk) vsk->trans = hvs; hvs->vsk = vsk; - + sk->sk_sndbuf = RINGBUFFER_HVS_SND_SIZE; + sk->sk_rcvbuf = RINGBUFFER_HVS_RCV_SIZE; return 0; } @@ -644,7 +675,9 @@ static ssize_t hvs_stream_enqueue(struct vsock_sock *vsk, struct msghdr *msg, struct hvsock *hvs = vsk->trans; struct vmbus_channel *chan = hvs->chan; struct hvs_send_buf *send_buf; - ssize_t to_write, max_writable, ret; + ssize_t to_write, max_writable; + ssize_t ret = 0; + ssize_t bytes_written = 0; BUILD_BUG_ON(sizeof(*send_buf) != PAGE_SIZE_4K); @@ -652,20 +685,34 @@ static ssize_t hvs_stream_enqueue(struct vsock_sock *vsk, struct msghdr *msg, if (!send_buf) return -ENOMEM; - max_writable = hvs_channel_writable_bytes(chan); - to_write = min_t(ssize_t, len, max_writable); - to_write = min_t(ssize_t, to_write, HVS_SEND_BUF_SIZE); - - ret = memcpy_from_msg(send_buf->data, msg, to_write); - if (ret < 0) - goto out; + /* Reader(s) could be draining data from the channel as we write. + * Maximize bandwidth, by iterating until the channel is found to be + * full. + */ + while (len) { + max_writable = hvs_channel_writable_bytes(chan); + if (!max_writable) + break; + to_write = min_t(ssize_t, len, max_writable); + to_write = min_t(ssize_t, to_write, HVS_SEND_BUF_SIZE); + /* memcpy_from_msg is safe for loop as it advances the offsets + * within the message iterator. + */ + ret = memcpy_from_msg(send_buf->data, msg, to_write); + if (ret < 0) + goto out; - ret = hvs_send_data(hvs->chan, send_buf, to_write); - if (ret < 0) - goto out; + ret = hvs_send_data(hvs->chan, send_buf, to_write); + if (ret < 0) + goto out; - ret = to_write; + bytes_written += to_write; + len -= to_write; + } out: + /* If any data has been sent, return that */ + if (bytes_written) + ret = bytes_written; kfree(send_buf); return ret; } |