diff options
Diffstat (limited to 'net')
109 files changed, 2184 insertions, 831 deletions
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 502f66349530..a56ed7f2a3a3 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -584,7 +584,7 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, unsigned long now = jiffies; /* fastpath: update of existing entry */ - if (unlikely(source != fdb->dst)) { + if (unlikely(source != fdb->dst && !fdb->is_sticky)) { fdb->dst = source; fdb_modified = true; /* Take over HW learned entry */ @@ -656,6 +656,8 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, ndm->ndm_flags |= NTF_OFFLOADED; if (fdb->added_by_external_learn) ndm->ndm_flags |= NTF_EXT_LEARNED; + if (fdb->is_sticky) + ndm->ndm_flags |= NTF_STICKY; if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->key.addr)) goto nla_put_failure; @@ -772,8 +774,10 @@ skip: /* Update (create or replace) forwarding database entry */ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, - const __u8 *addr, __u16 state, __u16 flags, __u16 vid) + const u8 *addr, u16 state, u16 flags, u16 vid, + u8 ndm_flags) { + u8 is_sticky = !!(ndm_flags & NTF_STICKY); struct net_bridge_fdb_entry *fdb; bool modified = false; @@ -789,6 +793,9 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, return -EINVAL; } + if (is_sticky && (state & NUD_PERMANENT)) + return -EINVAL; + fdb = br_fdb_find(br, addr, vid); if (fdb == NULL) { if (!(flags & NLM_F_CREATE)) @@ -832,6 +839,12 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, modified = true; } + + if (is_sticky != fdb->is_sticky) { + fdb->is_sticky = is_sticky; + modified = true; + } + fdb->added_by_user = 1; fdb->used = jiffies; @@ -865,7 +878,7 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, } else { spin_lock_bh(&br->hash_lock); err = fdb_add_entry(br, p, addr, ndm->ndm_state, - nlh_flags, vid); + nlh_flags, vid, ndm->ndm_flags); spin_unlock_bh(&br->hash_lock); } diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 0363f1bdc401..3bb66508f07d 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -394,8 +394,7 @@ static int find_portno(struct net_bridge *br) struct net_bridge_port *p; unsigned long *inuse; - inuse = kcalloc(BITS_TO_LONGS(BR_MAX_PORTS), sizeof(unsigned long), - GFP_KERNEL); + inuse = bitmap_zalloc(BR_MAX_PORTS, GFP_KERNEL); if (!inuse) return -ENOMEM; @@ -404,7 +403,7 @@ static int find_portno(struct net_bridge *br) set_bit(p->port_no, inuse); } index = find_first_zero_bit(inuse, BR_MAX_PORTS); - kfree(inuse); + bitmap_free(inuse); return (index >= BR_MAX_PORTS) ? -EXFULL : index; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 11ed2029985f..d21035a17f4c 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -181,6 +181,7 @@ struct net_bridge_fdb_entry { struct hlist_node fdb_node; unsigned char is_local:1, is_static:1, + is_sticky:1, added_by_user:1, added_by_external_learn:1, offloaded:1; diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 7df269092103..bb6ba794864f 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -877,8 +877,7 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) return 0; } - changed = kcalloc(BITS_TO_LONGS(BR_MAX_PORTS), sizeof(unsigned long), - GFP_KERNEL); + changed = bitmap_zalloc(BR_MAX_PORTS, GFP_KERNEL); if (!changed) return -ENOMEM; @@ -925,7 +924,7 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) br->default_pvid = pvid; out: - kfree(changed); + bitmap_free(changed); return err; err_port: diff --git a/net/caif/cfrfml.c b/net/caif/cfrfml.c index b82440e1fcb4..a931a71ef6df 100644 --- a/net/caif/cfrfml.c +++ b/net/caif/cfrfml.c @@ -264,9 +264,6 @@ static int cfrfml_transmit(struct cflayer *layr, struct cfpkt *pkt) frontpkt = rearpkt; rearpkt = NULL; - err = -ENOMEM; - if (frontpkt == NULL) - goto out; err = -EPROTO; if (cfpkt_add_head(frontpkt, head, 6) < 0) goto out; diff --git a/net/core/dev.c b/net/core/dev.c index 82114e1111e6..0b2d777e5b9e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1969,6 +1969,9 @@ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) rcu_read_lock(); again: list_for_each_entry_rcu(ptype, ptype_list, list) { + if (ptype->ignore_outgoing) + continue; + /* Never send packets back to the socket * they originated from - MvS (miquels@drinkel.ow.org) */ @@ -3228,7 +3231,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *de while (skb) { struct sk_buff *next = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); rc = xmit_one(skb, dev, txq, next != NULL); if (unlikely(!dev_xmit_complete(rc))) { skb->next = next; @@ -3328,7 +3331,7 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d for (; skb != NULL; skb = next) { next = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); /* in case skb wont be segmented, point to itself */ skb->prev = skb; @@ -5292,8 +5295,7 @@ static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, list_for_each_entry_safe_reverse(skb, p, head, list) { if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) return; - list_del(&skb->list); - skb->next = NULL; + skb_list_del_init(skb); napi_gro_complete(skb); napi->gro_hash[index].count--; } @@ -5478,8 +5480,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED; if (pp) { - list_del(&pp->list); - pp->next = NULL; + skb_list_del_init(pp); napi_gro_complete(pp); napi->gro_hash[hash].count--; } diff --git a/net/core/ethtool.c b/net/core/ethtool.c index c9993c6c2fd4..9d4e56d97080 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -539,47 +539,17 @@ struct ethtool_link_usettings { } link_modes; }; -/* Internal kernel helper to query a device ethtool_link_settings. - * - * Backward compatibility note: for compatibility with legacy drivers - * that implement only the ethtool_cmd API, this has to work with both - * drivers implementing get_link_ksettings API and drivers - * implementing get_settings API. When drivers implement get_settings - * and report ethtool_cmd deprecated fields - * (transceiver/maxrxpkt/maxtxpkt), these fields are silently ignored - * because the resulting struct ethtool_link_settings does not report them. - */ +/* Internal kernel helper to query a device ethtool_link_settings. */ int __ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *link_ksettings) { - int err; - struct ethtool_cmd cmd; - ASSERT_RTNL(); - if (dev->ethtool_ops->get_link_ksettings) { - memset(link_ksettings, 0, sizeof(*link_ksettings)); - return dev->ethtool_ops->get_link_ksettings(dev, - link_ksettings); - } - - /* driver doesn't support %ethtool_link_ksettings API. revert to - * legacy %ethtool_cmd API, unless it's not supported either. - * TODO: remove when ethtool_ops::get_settings disappears internally - */ - if (!dev->ethtool_ops->get_settings) + if (!dev->ethtool_ops->get_link_ksettings) return -EOPNOTSUPP; - memset(&cmd, 0, sizeof(cmd)); - cmd.cmd = ETHTOOL_GSET; - err = dev->ethtool_ops->get_settings(dev, &cmd); - if (err < 0) - return err; - - /* we ignore deprecated fields transceiver/maxrxpkt/maxtxpkt - */ - convert_legacy_settings_to_link_ksettings(link_ksettings, &cmd); - return err; + memset(link_ksettings, 0, sizeof(*link_ksettings)); + return dev->ethtool_ops->get_link_ksettings(dev, link_ksettings); } EXPORT_SYMBOL(__ethtool_get_link_ksettings); @@ -635,16 +605,7 @@ store_link_ksettings_for_user(void __user *to, return 0; } -/* Query device for its ethtool_link_settings. - * - * Backward compatibility note: this function must fail when driver - * does not implement ethtool::get_link_ksettings, even if legacy - * ethtool_ops::get_settings is implemented. This tells new versions - * of ethtool that they should use the legacy API %ETHTOOL_GSET for - * this driver, so that they can correctly access the ethtool_cmd - * deprecated fields (transceiver/maxrxpkt/maxtxpkt), until no driver - * implements ethtool_ops::get_settings anymore. - */ +/* Query device for its ethtool_link_settings. */ static int ethtool_get_link_ksettings(struct net_device *dev, void __user *useraddr) { @@ -652,7 +613,6 @@ static int ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings link_ksettings; ASSERT_RTNL(); - if (!dev->ethtool_ops->get_link_ksettings) return -EOPNOTSUPP; @@ -699,16 +659,7 @@ static int ethtool_get_link_ksettings(struct net_device *dev, return store_link_ksettings_for_user(useraddr, &link_ksettings); } -/* Update device ethtool_link_settings. - * - * Backward compatibility note: this function must fail when driver - * does not implement ethtool::set_link_ksettings, even if legacy - * ethtool_ops::set_settings is implemented. This tells new versions - * of ethtool that they should use the legacy API %ETHTOOL_SSET for - * this driver, so that they can correctly update the ethtool_cmd - * deprecated fields (transceiver/maxrxpkt/maxtxpkt), until no driver - * implements ethtool_ops::get_settings anymore. - */ +/* Update device ethtool_link_settings. */ static int ethtool_set_link_ksettings(struct net_device *dev, void __user *useraddr) { @@ -746,51 +697,31 @@ static int ethtool_set_link_ksettings(struct net_device *dev, /* Query device for its ethtool_cmd settings. * - * Backward compatibility note: for compatibility with legacy ethtool, - * this has to work with both drivers implementing get_link_ksettings - * API and drivers implementing get_settings API. When drivers - * implement get_link_ksettings and report higher link mode bits, a - * kernel warning is logged once (with name of 1st driver/device) to - * recommend user to upgrade ethtool, but the command is successful - * (only the lower link mode bits reported back to user). + * Backward compatibility note: for compatibility with legacy ethtool, this is + * now implemented via get_link_ksettings. When driver reports higher link mode + * bits, a kernel warning is logged once (with name of 1st driver/device) to + * recommend user to upgrade ethtool, but the command is successful (only the + * lower link mode bits reported back to user). Deprecated fields from + * ethtool_cmd (transceiver/maxrxpkt/maxtxpkt) are always set to zero. */ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) { + struct ethtool_link_ksettings link_ksettings; struct ethtool_cmd cmd; + int err; ASSERT_RTNL(); + if (!dev->ethtool_ops->get_link_ksettings) + return -EOPNOTSUPP; - if (dev->ethtool_ops->get_link_ksettings) { - /* First, use link_ksettings API if it is supported */ - int err; - struct ethtool_link_ksettings link_ksettings; - - memset(&link_ksettings, 0, sizeof(link_ksettings)); - err = dev->ethtool_ops->get_link_ksettings(dev, - &link_ksettings); - if (err < 0) - return err; - convert_link_ksettings_to_legacy_settings(&cmd, - &link_ksettings); - - /* send a sensible cmd tag back to user */ - cmd.cmd = ETHTOOL_GSET; - } else { - /* driver doesn't support %ethtool_link_ksettings - * API. revert to legacy %ethtool_cmd API, unless it's - * not supported either. - */ - int err; - - if (!dev->ethtool_ops->get_settings) - return -EOPNOTSUPP; + memset(&link_ksettings, 0, sizeof(link_ksettings)); + err = dev->ethtool_ops->get_link_ksettings(dev, &link_ksettings); + if (err < 0) + return err; + convert_link_ksettings_to_legacy_settings(&cmd, &link_ksettings); - memset(&cmd, 0, sizeof(cmd)); - cmd.cmd = ETHTOOL_GSET; - err = dev->ethtool_ops->get_settings(dev, &cmd); - if (err < 0) - return err; - } + /* send a sensible cmd tag back to user */ + cmd.cmd = ETHTOOL_GSET; if (copy_to_user(useraddr, &cmd, sizeof(cmd))) return -EFAULT; @@ -800,48 +731,29 @@ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) /* Update device link settings with given ethtool_cmd. * - * Backward compatibility note: for compatibility with legacy ethtool, - * this has to work with both drivers implementing set_link_ksettings - * API and drivers implementing set_settings API. When drivers - * implement set_link_ksettings and user's request updates deprecated - * ethtool_cmd fields (transceiver/maxrxpkt/maxtxpkt), a kernel - * warning is logged once (with name of 1st driver/device) to - * recommend user to upgrade ethtool, and the request is rejected. + * Backward compatibility note: for compatibility with legacy ethtool, this is + * now always implemented via set_link_settings. When user's request updates + * deprecated ethtool_cmd fields (transceiver/maxrxpkt/maxtxpkt), a kernel + * warning is logged once (with name of 1st driver/device) to recommend user to + * upgrade ethtool, and the request is rejected. */ static int ethtool_set_settings(struct net_device *dev, void __user *useraddr) { + struct ethtool_link_ksettings link_ksettings; struct ethtool_cmd cmd; ASSERT_RTNL(); if (copy_from_user(&cmd, useraddr, sizeof(cmd))) return -EFAULT; - - /* first, try new %ethtool_link_ksettings API. */ - if (dev->ethtool_ops->set_link_ksettings) { - struct ethtool_link_ksettings link_ksettings; - - if (!convert_legacy_settings_to_link_ksettings(&link_ksettings, - &cmd)) - return -EINVAL; - - link_ksettings.base.cmd = ETHTOOL_SLINKSETTINGS; - link_ksettings.base.link_mode_masks_nwords - = __ETHTOOL_LINK_MODE_MASK_NU32; - return dev->ethtool_ops->set_link_ksettings(dev, - &link_ksettings); - } - - /* legacy %ethtool_cmd API */ - - /* TODO: return -EOPNOTSUPP when ethtool_ops::get_settings - * disappears internally - */ - - if (!dev->ethtool_ops->set_settings) + if (!dev->ethtool_ops->set_link_ksettings) return -EOPNOTSUPP; - return dev->ethtool_ops->set_settings(dev, &cmd); + if (!convert_legacy_settings_to_link_ksettings(&link_ksettings, &cmd)) + return -EINVAL; + link_ksettings.base.link_mode_masks_nwords = + __ETHTOOL_LINK_MODE_MASK_NU32; + return dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings); } static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, diff --git a/net/core/filter.c b/net/core/filter.c index 5e00f2b85a56..0b40f95da21b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4013,6 +4013,12 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, tp->snd_ssthresh = val; } break; + case TCP_SAVE_SYN: + if (val < 0 || val > 1) + ret = -EINVAL; + else + tp->save_syn = val; + break; default: ret = -EINVAL; } @@ -4038,21 +4044,32 @@ static const struct bpf_func_proto bpf_setsockopt_proto = { BPF_CALL_5(bpf_getsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { + struct inet_connection_sock *icsk; struct sock *sk = bpf_sock->sk; + struct tcp_sock *tp; if (!sk_fullsock(sk)) goto err_clear; - #ifdef CONFIG_INET if (level == SOL_TCP && sk->sk_prot->getsockopt == tcp_getsockopt) { - if (optname == TCP_CONGESTION) { - struct inet_connection_sock *icsk = inet_csk(sk); + switch (optname) { + case TCP_CONGESTION: + icsk = inet_csk(sk); if (!icsk->icsk_ca_ops || optlen <= 1) goto err_clear; strncpy(optval, icsk->icsk_ca_ops->name, optlen); optval[optlen - 1] = 0; - } else { + break; + case TCP_SAVED_SYN: + tp = tcp_sk(sk); + + if (optlen <= 0 || !tp->saved_syn || + optlen > tp->saved_syn[0]) + goto err_clear; + memcpy(optval, tp->saved_syn + 1, optlen); + break; + default: goto err_clear; } } else if (level == SOL_IP) { diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 7f6938405fa1..6ac919847ce6 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3426,7 +3426,7 @@ xmit_more: net_info_ratelimited("%s xmit error: %d\n", pkt_dev->odevname, ret); pkt_dev->errors++; - /* fallthru */ + /* fall through */ case NETDEV_TX_BUSY: /* Retry it next time */ refcount_dec(&(pkt_dev->skb->users)); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 63ce2283a456..80a7e18c65fb 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1016,7 +1016,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_NEW_NETNSID */ + nla_total_size(4) /* IFLA_NEW_IFINDEX */ + nla_total_size(1) /* IFLA_PROTO_DOWN */ - + nla_total_size(4) /* IFLA_IF_NETNSID */ + + nla_total_size(4) /* IFLA_TARGET_NETNSID */ + nla_total_size(4) /* IFLA_CARRIER_UP_COUNT */ + nla_total_size(4) /* IFLA_CARRIER_DOWN_COUNT */ + nla_total_size(4) /* IFLA_MIN_MTU */ @@ -1598,7 +1598,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, ifm->ifi_flags = dev_get_flags(dev); ifm->ifi_change = change; - if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_IF_NETNSID, tgt_netnsid)) + if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_TARGET_NETNSID, tgt_netnsid)) goto nla_put_failure; if (nla_put_string(skb, IFLA_IFNAME, dev->name) || @@ -1737,7 +1737,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_XDP] = { .type = NLA_NESTED }, [IFLA_EVENT] = { .type = NLA_U32 }, [IFLA_GROUP] = { .type = NLA_U32 }, - [IFLA_IF_NETNSID] = { .type = NLA_S32 }, + [IFLA_TARGET_NETNSID] = { .type = NLA_S32 }, [IFLA_CARRIER_UP_COUNT] = { .type = NLA_U32 }, [IFLA_CARRIER_DOWN_COUNT] = { .type = NLA_U32 }, [IFLA_MIN_MTU] = { .type = NLA_U32 }, @@ -1845,7 +1845,15 @@ static bool link_dump_filtered(struct net_device *dev, return false; } -static struct net *get_target_net(struct sock *sk, int netnsid) +/** + * rtnl_get_net_ns_capable - Get netns if sufficiently privileged. + * @sk: netlink socket + * @netnsid: network namespace identifier + * + * Returns the network namespace identified by netnsid on success or an error + * pointer on failure. + */ +struct net *rtnl_get_net_ns_capable(struct sock *sk, int netnsid) { struct net *net; @@ -1862,6 +1870,7 @@ static struct net *get_target_net(struct sock *sk, int netnsid) } return net; } +EXPORT_SYMBOL_GPL(rtnl_get_net_ns_capable); static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { @@ -1895,9 +1904,9 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX, ifla_policy, NULL) >= 0) { - if (tb[IFLA_IF_NETNSID]) { - netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]); - tgt_net = get_target_net(skb->sk, netnsid); + if (tb[IFLA_TARGET_NETNSID]) { + netnsid = nla_get_s32(tb[IFLA_TARGET_NETNSID]); + tgt_net = rtnl_get_net_ns_capable(skb->sk, netnsid); if (IS_ERR(tgt_net)) { tgt_net = net; netnsid = -1; @@ -1984,7 +1993,7 @@ EXPORT_SYMBOL(rtnl_link_get_net); * * 1. IFLA_NET_NS_PID * 2. IFLA_NET_NS_FD - * 3. IFLA_IF_NETNSID + * 3. IFLA_TARGET_NETNSID */ static struct net *rtnl_link_get_net_by_nlattr(struct net *src_net, struct nlattr *tb[]) @@ -1994,10 +2003,10 @@ static struct net *rtnl_link_get_net_by_nlattr(struct net *src_net, if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD]) return rtnl_link_get_net(src_net, tb); - if (!tb[IFLA_IF_NETNSID]) + if (!tb[IFLA_TARGET_NETNSID]) return get_net(src_net); - net = get_net_ns_by_id(src_net, nla_get_u32(tb[IFLA_IF_NETNSID])); + net = get_net_ns_by_id(src_net, nla_get_u32(tb[IFLA_TARGET_NETNSID])); if (!net) return ERR_PTR(-EINVAL); @@ -2038,13 +2047,13 @@ static int rtnl_ensure_unique_netns(struct nlattr *tb[], return -EOPNOTSUPP; } - if (tb[IFLA_IF_NETNSID] && (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD])) + if (tb[IFLA_TARGET_NETNSID] && (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD])) goto invalid_attr; - if (tb[IFLA_NET_NS_PID] && (tb[IFLA_IF_NETNSID] || tb[IFLA_NET_NS_FD])) + if (tb[IFLA_NET_NS_PID] && (tb[IFLA_TARGET_NETNSID] || tb[IFLA_NET_NS_FD])) goto invalid_attr; - if (tb[IFLA_NET_NS_FD] && (tb[IFLA_IF_NETNSID] || tb[IFLA_NET_NS_PID])) + if (tb[IFLA_NET_NS_FD] && (tb[IFLA_TARGET_NETNSID] || tb[IFLA_NET_NS_PID])) goto invalid_attr; return 0; @@ -2320,7 +2329,7 @@ static int do_setlink(const struct sk_buff *skb, if (err < 0) return err; - if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD] || tb[IFLA_IF_NETNSID]) { + if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD] || tb[IFLA_TARGET_NETNSID]) { struct net *net = rtnl_link_get_net_capable(skb, dev_net(dev), tb, CAP_NET_ADMIN); if (IS_ERR(net)) { @@ -2763,9 +2772,9 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[IFLA_IFNAME]) nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); - if (tb[IFLA_IF_NETNSID]) { - netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]); - tgt_net = get_target_net(NETLINK_CB(skb).sk, netnsid); + if (tb[IFLA_TARGET_NETNSID]) { + netnsid = nla_get_s32(tb[IFLA_TARGET_NETNSID]); + tgt_net = rtnl_get_net_ns_capable(NETLINK_CB(skb).sk, netnsid); if (IS_ERR(tgt_net)) return PTR_ERR(tgt_net); } @@ -3173,9 +3182,9 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) return err; - if (tb[IFLA_IF_NETNSID]) { - netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]); - tgt_net = get_target_net(NETLINK_CB(skb).sk, netnsid); + if (tb[IFLA_TARGET_NETNSID]) { + netnsid = nla_get_s32(tb[IFLA_TARGET_NETNSID]); + tgt_net = rtnl_get_net_ns_capable(NETLINK_CB(skb).sk, netnsid); if (IS_ERR(tgt_net)) return PTR_ERR(tgt_net); } @@ -3260,13 +3269,13 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) { int idx; int s_idx = cb->family; + int type = cb->nlh->nlmsg_type - RTM_BASE; if (s_idx == 0) s_idx = 1; for (idx = 1; idx <= RTNL_FAMILY_MAX; idx++) { struct rtnl_link **tab; - int type = cb->nlh->nlmsg_type-RTM_BASE; struct rtnl_link *link; rtnl_dumpit_func dumpit; diff --git a/net/core/sock.c b/net/core/sock.c index 3730eb855095..8537b6ca72c5 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2332,7 +2332,7 @@ static void __release_sock(struct sock *sk) next = skb->next; prefetch(next); WARN_ON_ONCE(skb_dst_is_noref(skb)); - skb->next = NULL; + skb_mark_not_on_list(skb); sk_backlog_rcv(sk, skb); cond_resched(); diff --git a/net/core/xdp.c b/net/core/xdp.c index 89b6785cef2a..4b2b194f4f1f 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -94,11 +94,21 @@ static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu) kfree(xa); } -static void __xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) +void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) { struct xdp_mem_allocator *xa; int id = xdp_rxq->mem.id; + if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { + WARN(1, "Missing register, driver bug"); + return; + } + + if (xdp_rxq->mem.type != MEM_TYPE_PAGE_POOL && + xdp_rxq->mem.type != MEM_TYPE_ZERO_COPY) { + return; + } + if (id == 0) return; @@ -110,6 +120,7 @@ static void __xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) mutex_unlock(&mem_id_lock); } +EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg_mem_model); void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq) { @@ -119,7 +130,7 @@ void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq) WARN(!(xdp_rxq->reg_state == REG_STATE_REGISTERED), "Driver BUG"); - __xdp_rxq_info_unreg_mem_model(xdp_rxq); + xdp_rxq_info_unreg_mem_model(xdp_rxq); xdp_rxq->reg_state = REG_STATE_UNREGISTERED; xdp_rxq->dev = NULL; @@ -398,3 +409,41 @@ void xdp_attachment_setup(struct xdp_attachment_info *info, info->flags = bpf->flags; } EXPORT_SYMBOL_GPL(xdp_attachment_setup); + +struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp) +{ + unsigned int metasize, totsize; + void *addr, *data_to_copy; + struct xdp_frame *xdpf; + struct page *page; + + /* Clone into a MEM_TYPE_PAGE_ORDER0 xdp_frame. */ + metasize = xdp_data_meta_unsupported(xdp) ? 0 : + xdp->data - xdp->data_meta; + totsize = xdp->data_end - xdp->data + metasize; + + if (sizeof(*xdpf) + totsize > PAGE_SIZE) + return NULL; + + page = dev_alloc_page(); + if (!page) + return NULL; + + addr = page_to_virt(page); + xdpf = addr; + memset(xdpf, 0, sizeof(*xdpf)); + + addr += sizeof(*xdpf); + data_to_copy = metasize ? xdp->data_meta : xdp->data; + memcpy(addr, data_to_copy, totsize); + + xdpf->data = addr + metasize; + xdpf->len = totsize - metasize; + xdpf->headroom = 0; + xdpf->metasize = metasize; + xdpf->mem.type = MEM_TYPE_PAGE_ORDER0; + + xdp_return_buff(xdp); + return xdpf; +} +EXPORT_SYMBOL_GPL(xdp_convert_zc_to_xdp_frame); diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 4183e4ba27a5..48c41918fb35 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -38,6 +38,9 @@ config NET_DSA_TAG_DSA config NET_DSA_TAG_EDSA bool +config NET_DSA_TAG_GSWIP + bool + config NET_DSA_TAG_KSZ bool diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 9e4d3536f977..6e721f7a2947 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -9,6 +9,7 @@ dsa_core-$(CONFIG_NET_DSA_TAG_BRCM) += tag_brcm.o dsa_core-$(CONFIG_NET_DSA_TAG_BRCM_PREPEND) += tag_brcm.o dsa_core-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o dsa_core-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o +dsa_core-$(CONFIG_NET_DSA_TAG_GSWIP) += tag_gswip.o dsa_core-$(CONFIG_NET_DSA_TAG_KSZ) += tag_ksz.o dsa_core-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o dsa_core-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 9f3209ff7ffd..a69c1790bbfc 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -52,6 +52,9 @@ const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = { #ifdef CONFIG_NET_DSA_TAG_EDSA [DSA_TAG_PROTO_EDSA] = &edsa_netdev_ops, #endif +#ifdef CONFIG_NET_DSA_TAG_GSWIP + [DSA_TAG_PROTO_GSWIP] = &gswip_netdev_ops, +#endif #ifdef CONFIG_NET_DSA_TAG_KSZ [DSA_TAG_PROTO_KSZ] = &ksz_netdev_ops, #endif @@ -70,6 +73,52 @@ const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = { [DSA_TAG_PROTO_NONE] = &none_ops, }; +const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops) +{ + const char *protocol_name[DSA_TAG_LAST] = { +#ifdef CONFIG_NET_DSA_TAG_BRCM + [DSA_TAG_PROTO_BRCM] = "brcm", +#endif +#ifdef CONFIG_NET_DSA_TAG_BRCM_PREPEND + [DSA_TAG_PROTO_BRCM_PREPEND] = "brcm-prepend", +#endif +#ifdef CONFIG_NET_DSA_TAG_DSA + [DSA_TAG_PROTO_DSA] = "dsa", +#endif +#ifdef CONFIG_NET_DSA_TAG_EDSA + [DSA_TAG_PROTO_EDSA] = "edsa", +#endif +#ifdef CONFIG_NET_DSA_TAG_GSWIP + [DSA_TAG_PROTO_GSWIP] = "gswip", +#endif +#ifdef CONFIG_NET_DSA_TAG_KSZ + [DSA_TAG_PROTO_KSZ] = "ksz", +#endif +#ifdef CONFIG_NET_DSA_TAG_LAN9303 + [DSA_TAG_PROTO_LAN9303] = "lan9303", +#endif +#ifdef CONFIG_NET_DSA_TAG_MTK + [DSA_TAG_PROTO_MTK] = "mtk", +#endif +#ifdef CONFIG_NET_DSA_TAG_QCA + [DSA_TAG_PROTO_QCA] = "qca", +#endif +#ifdef CONFIG_NET_DSA_TAG_TRAILER + [DSA_TAG_PROTO_TRAILER] = "trailer", +#endif + [DSA_TAG_PROTO_NONE] = "none", + }; + unsigned int i; + + BUILD_BUG_ON(ARRAY_SIZE(protocol_name) != DSA_TAG_LAST); + + for (i = 0; i < ARRAY_SIZE(dsa_device_ops); i++) + if (ops == dsa_device_ops[i]) + return protocol_name[i]; + + return protocol_name[DSA_TAG_PROTO_NONE]; +}; + const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol) { const struct dsa_device_ops *ops; diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 3964c6f7a7c0..9e4fd04ab53c 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -86,6 +86,7 @@ struct dsa_slave_priv { /* dsa.c */ const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol); bool dsa_schedule_work(struct work_struct *work); +const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops); /* legacy.c */ #if IS_ENABLED(CONFIG_NET_DSA_LEGACY) @@ -205,6 +206,9 @@ extern const struct dsa_device_ops dsa_netdev_ops; /* tag_edsa.c */ extern const struct dsa_device_ops edsa_netdev_ops; +/* tag_gswip.c */ +extern const struct dsa_device_ops gswip_netdev_ops; + /* tag_ksz.c */ extern const struct dsa_device_ops ksz_netdev_ops; diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index 42a7b85b84e1..8aa92b09db76 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -392,8 +392,7 @@ static void dsa_of_free_platform_data(struct dsa_platform_data *pd) } /* Drop our reference to the MDIO bus device */ - if (pd->chip[i].host_dev) - put_device(pd->chip[i].host_dev); + put_device(pd->chip[i].host_dev); } kfree(pd->chip); } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 1c45c1d6d241..3f840b6eea69 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1058,6 +1058,27 @@ static struct device_type dsa_type = { .name = "dsa", }; +static ssize_t tagging_show(struct device *d, struct device_attribute *attr, + char *buf) +{ + struct net_device *dev = to_net_dev(d); + struct dsa_port *dp = dsa_slave_to_port(dev); + + return sprintf(buf, "%s\n", + dsa_tag_protocol_to_str(dp->cpu_dp->tag_ops)); +} +static DEVICE_ATTR_RO(tagging); + +static struct attribute *dsa_slave_attrs[] = { + &dev_attr_tagging.attr, + NULL +}; + +static const struct attribute_group dsa_group = { + .name = "dsa", + .attrs = dsa_slave_attrs, +}; + static void dsa_slave_phylink_validate(struct net_device *dev, unsigned long *supported, struct phylink_link_state *state) @@ -1353,8 +1374,14 @@ int dsa_slave_create(struct dsa_port *port) goto out_phy; } + ret = sysfs_create_group(&slave_dev->dev.kobj, &dsa_group); + if (ret) + goto out_unreg; + return 0; +out_unreg: + unregister_netdev(slave_dev); out_phy: rtnl_lock(); phylink_disconnect_phy(p->dp->pl); @@ -1378,6 +1405,7 @@ void dsa_slave_destroy(struct net_device *slave_dev) rtnl_unlock(); dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER); + sysfs_remove_group(&slave_dev->dev.kobj, &dsa_group); unregister_netdev(slave_dev); phylink_destroy(dp->pl); free_percpu(p->stats64); diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c new file mode 100644 index 000000000000..49e9b73f1be3 --- /dev/null +++ b/net/dsa/tag_gswip.c @@ -0,0 +1,109 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel / Lantiq GSWIP V2.0 PMAC tag support + * + * Copyright (C) 2017 - 2018 Hauke Mehrtens <hauke@hauke-m.de> + */ + +#include <linux/bitops.h> +#include <linux/etherdevice.h> +#include <linux/skbuff.h> +#include <net/dsa.h> + +#include "dsa_priv.h" + +#define GSWIP_TX_HEADER_LEN 4 + +/* special tag in TX path header */ +/* Byte 0 */ +#define GSWIP_TX_SLPID_SHIFT 0 /* source port ID */ +#define GSWIP_TX_SLPID_CPU 2 +#define GSWIP_TX_SLPID_APP1 3 +#define GSWIP_TX_SLPID_APP2 4 +#define GSWIP_TX_SLPID_APP3 5 +#define GSWIP_TX_SLPID_APP4 6 +#define GSWIP_TX_SLPID_APP5 7 + +/* Byte 1 */ +#define GSWIP_TX_CRCGEN_DIS BIT(7) +#define GSWIP_TX_DPID_SHIFT 0 /* destination group ID */ +#define GSWIP_TX_DPID_ELAN 0 +#define GSWIP_TX_DPID_EWAN 1 +#define GSWIP_TX_DPID_CPU 2 +#define GSWIP_TX_DPID_APP1 3 +#define GSWIP_TX_DPID_APP2 4 +#define GSWIP_TX_DPID_APP3 5 +#define GSWIP_TX_DPID_APP4 6 +#define GSWIP_TX_DPID_APP5 7 + +/* Byte 2 */ +#define GSWIP_TX_PORT_MAP_EN BIT(7) +#define GSWIP_TX_PORT_MAP_SEL BIT(6) +#define GSWIP_TX_LRN_DIS BIT(5) +#define GSWIP_TX_CLASS_EN BIT(4) +#define GSWIP_TX_CLASS_SHIFT 0 +#define GSWIP_TX_CLASS_MASK GENMASK(3, 0) + +/* Byte 3 */ +#define GSWIP_TX_DPID_EN BIT(0) +#define GSWIP_TX_PORT_MAP_SHIFT 1 +#define GSWIP_TX_PORT_MAP_MASK GENMASK(6, 1) + +#define GSWIP_RX_HEADER_LEN 8 + +/* special tag in RX path header */ +/* Byte 7 */ +#define GSWIP_RX_SPPID_SHIFT 4 +#define GSWIP_RX_SPPID_MASK GENMASK(6, 4) + +static struct sk_buff *gswip_tag_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + int err; + u8 *gswip_tag; + + err = skb_cow_head(skb, GSWIP_TX_HEADER_LEN); + if (err) + return NULL; + + skb_push(skb, GSWIP_TX_HEADER_LEN); + + gswip_tag = skb->data; + gswip_tag[0] = GSWIP_TX_SLPID_CPU; + gswip_tag[1] = GSWIP_TX_DPID_ELAN; + gswip_tag[2] = GSWIP_TX_PORT_MAP_EN | GSWIP_TX_PORT_MAP_SEL; + gswip_tag[3] = BIT(dp->index + GSWIP_TX_PORT_MAP_SHIFT) & GSWIP_TX_PORT_MAP_MASK; + gswip_tag[3] |= GSWIP_TX_DPID_EN; + + return skb; +} + +static struct sk_buff *gswip_tag_rcv(struct sk_buff *skb, + struct net_device *dev, + struct packet_type *pt) +{ + int port; + u8 *gswip_tag; + + if (unlikely(!pskb_may_pull(skb, GSWIP_RX_HEADER_LEN))) + return NULL; + + gswip_tag = skb->data - ETH_HLEN; + + /* Get source port information */ + port = (gswip_tag[7] & GSWIP_RX_SPPID_MASK) >> GSWIP_RX_SPPID_SHIFT; + skb->dev = dsa_master_find_slave(dev, 0, port); + if (!skb->dev) + return NULL; + + /* remove GSWIP tag */ + skb_pull_rcsum(skb, GSWIP_RX_HEADER_LEN); + + return skb; +} + +const struct dsa_device_ops gswip_netdev_ops = { + .xmit = gswip_tag_xmit, + .rcv = gswip_tag_rcv, +}; diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index e7857a8ac86d..09ffbf5ce8fa 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -260,7 +260,7 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev, } sub_frag_mem_limit(fq->q.net, sum_truesize); - head->next = NULL; + skb_mark_not_on_list(head); head->dev = ldev; head->tstamp = fq->q.stamp; diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 82178cc69c96..777fa3b7fb13 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1512,7 +1512,7 @@ static int cipso_v4_parsetag_loc(const struct cipso_v4_doi *doi_def, * * Description: * Parse the packet's IP header looking for a CIPSO option. Returns a pointer - * to the start of the CIPSO option on success, NULL if one if not found. + * to the start of the CIPSO option on success, NULL if one is not found. * */ unsigned char *cipso_v4_optptr(const struct sk_buff *skb) @@ -1522,10 +1522,8 @@ unsigned char *cipso_v4_optptr(const struct sk_buff *skb) int optlen; int taglen; - for (optlen = iph->ihl*4 - sizeof(struct iphdr); optlen > 0; ) { + for (optlen = iph->ihl*4 - sizeof(struct iphdr); optlen > 1; ) { switch (optptr[0]) { - case IPOPT_CIPSO: - return optptr; case IPOPT_END: return NULL; case IPOPT_NOOP: @@ -1534,6 +1532,11 @@ unsigned char *cipso_v4_optptr(const struct sk_buff *skb) default: taglen = optptr[1]; } + if (!taglen || taglen > optlen) + return NULL; + if (optptr[0] == IPOPT_CIPSO) + return optptr; + optlen -= taglen; optptr += taglen; } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index ea4bd8a52422..44d931a3cd50 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -100,6 +100,15 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, [IFA_FLAGS] = { .type = NLA_U32 }, [IFA_RT_PRIORITY] = { .type = NLA_U32 }, + [IFA_TARGET_NETNSID] = { .type = NLA_S32 }, +}; + +struct inet_fill_args { + u32 portid; + u32 seq; + int event; + unsigned int flags; + int netnsid; }; #define IN4_ADDR_HSIZE_SHIFT 8 @@ -1584,13 +1593,14 @@ static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp, } static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, - u32 portid, u32 seq, int event, unsigned int flags) + struct inet_fill_args *args) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; u32 preferred, valid; - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), flags); + nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(*ifm), + args->flags); if (!nlh) return -EMSGSIZE; @@ -1601,6 +1611,10 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, ifm->ifa_scope = ifa->ifa_scope; ifm->ifa_index = ifa->ifa_dev->dev->ifindex; + if (args->netnsid >= 0 && + nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) + goto nla_put_failure; + if (!(ifm->ifa_flags & IFA_F_PERMANENT)) { preferred = ifa->ifa_preferred_lft; valid = ifa->ifa_valid_lft; @@ -1647,7 +1661,16 @@ nla_put_failure: static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) { + struct inet_fill_args fillargs = { + .portid = NETLINK_CB(cb->skb).portid, + .seq = cb->nlh->nlmsg_seq, + .event = RTM_NEWADDR, + .flags = NLM_F_MULTI, + .netnsid = -1, + }; struct net *net = sock_net(skb->sk); + struct nlattr *tb[IFA_MAX+1]; + struct net *tgt_net = net; int h, s_h; int idx, s_idx; int ip_idx, s_ip_idx; @@ -1660,12 +1683,24 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) s_idx = idx = cb->args[1]; s_ip_idx = ip_idx = cb->args[2]; + if (nlmsg_parse(cb->nlh, sizeof(struct ifaddrmsg), tb, IFA_MAX, + ifa_ipv4_policy, NULL) >= 0) { + if (tb[IFA_TARGET_NETNSID]) { + fillargs.netnsid = nla_get_s32(tb[IFA_TARGET_NETNSID]); + + tgt_net = rtnl_get_net_ns_capable(skb->sk, + fillargs.netnsid); + if (IS_ERR(tgt_net)) + return PTR_ERR(tgt_net); + } + } + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; - head = &net->dev_index_head[h]; + head = &tgt_net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^ - net->dev_base_seq; + cb->seq = atomic_read(&tgt_net->ipv4.dev_addr_genid) ^ + tgt_net->dev_base_seq; hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; @@ -1679,10 +1714,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) ifa = ifa->ifa_next, ip_idx++) { if (ip_idx < s_ip_idx) continue; - if (inet_fill_ifaddr(skb, ifa, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWADDR, NLM_F_MULTI) < 0) { + if (inet_fill_ifaddr(skb, ifa, &fillargs) < 0) { rcu_read_unlock(); goto done; } @@ -1698,6 +1730,8 @@ done: cb->args[0] = h; cb->args[1] = idx; cb->args[2] = ip_idx; + if (fillargs.netnsid >= 0) + put_net(tgt_net); return skb->len; } @@ -1705,8 +1739,14 @@ done: static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 portid) { + struct inet_fill_args fillargs = { + .portid = portid, + .seq = nlh ? nlh->nlmsg_seq : 0, + .event = event, + .flags = 0, + .netnsid = -1, + }; struct sk_buff *skb; - u32 seq = nlh ? nlh->nlmsg_seq : 0; int err = -ENOBUFS; struct net *net; @@ -1715,7 +1755,7 @@ static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, if (!skb) goto errout; - err = inet_fill_ifaddr(skb, ifa, portid, seq, event, 0); + err = inet_fill_ifaddr(skb, ifa, &fillargs); if (err < 0) { /* -EMSGSIZE implies BUG in inet_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index f3c89ccf14c5..bee8db979195 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -797,8 +797,10 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh, return -EINVAL; } dev = __dev_get_by_index(net, nh->nh_oif); - if (!dev) + if (!dev) { + NL_SET_ERR_MSG(extack, "Nexthop device required for onlink"); return -ENODEV; + } if (!(dev->flags & IFF_UP)) { NL_SET_ERR_MSG(extack, "Nexthop device is not up"); diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index b798862b6be5..7efe740c06eb 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -86,13 +86,14 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, options = (__be32 *)(greh + 1); if (greh->flags & GRE_CSUM) { - if (skb_checksum_simple_validate(skb)) { + if (!skb_checksum_simple_validate(skb)) { + skb_checksum_try_convert(skb, IPPROTO_GRE, 0, + null_compute_pseudo); + } else if (csum_err) { *csum_err = true; return -EINVAL; } - skb_checksum_try_convert(skb, IPPROTO_GRE, 0, - null_compute_pseudo); options++; } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index e7227128df2c..da930b01a147 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -382,7 +382,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) */ if (end < qp->q.len || ((qp->q.flags & INET_FRAG_LAST_IN) && end != qp->q.len)) - goto err; + goto discard_qp; qp->q.flags |= INET_FRAG_LAST_IN; qp->q.len = end; } else { @@ -394,20 +394,20 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) if (end > qp->q.len) { /* Some bits beyond end -> corruption. */ if (qp->q.flags & INET_FRAG_LAST_IN) - goto err; + goto discard_qp; qp->q.len = end; } } if (end == offset) - goto err; + goto discard_qp; err = -ENOMEM; if (!pskb_pull(skb, skb_network_offset(skb) + ihl)) - goto err; + goto discard_qp; err = pskb_trim_rcsum(skb, end - offset); if (err) - goto err; + goto discard_qp; /* Note : skb->rbnode and skb->dev share the same location. */ dev = skb->dev; @@ -423,6 +423,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) * We do the same here for IPv4 (and increment an snmp counter). */ + err = -EINVAL; /* Find out where to put this fragment. */ prev_tail = qp->q.fragments_tail; if (!prev_tail) @@ -431,7 +432,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) /* This is the common case: skb goes to the end. */ /* Detect and discard overlaps. */ if (offset < prev_tail->ip_defrag_offset + prev_tail->len) - goto discard_qp; + goto overlap; if (offset == prev_tail->ip_defrag_offset + prev_tail->len) ip4_frag_append_to_last_run(&qp->q, skb); else @@ -450,7 +451,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) FRAG_CB(skb1)->frag_run_len) rbn = &parent->rb_right; else /* Found an overlap with skb1. */ - goto discard_qp; + goto overlap; } while (*rbn); /* Here we have parent properly set, and rbn pointing to * one of its NULL left/right children. Insert skb. @@ -487,16 +488,18 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) skb->_skb_refdst = 0UL; err = ip_frag_reasm(qp, skb, prev_tail, dev); skb->_skb_refdst = orefdst; + if (err) + inet_frag_kill(&qp->q); return err; } skb_dst_drop(skb); return -EINPROGRESS; +overlap: + __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); discard_qp: inet_frag_kill(&qp->q); - err = -EINVAL; - __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); err: kfree_skb(skb); return err; @@ -621,7 +624,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, sub_frag_mem_limit(qp->q.net, head->truesize); *nextp = NULL; - head->next = NULL; + skb_mark_not_on_list(head); head->prev = NULL; head->dev = dev; head->tstamp = qp->q.stamp; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 8cce0e9ea08c..c3385a84f8ff 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -232,13 +232,10 @@ static void gre_err(struct sk_buff *skb, u32 info) const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct tnl_ptk_info tpi; - bool csum_err = false; - if (gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP), - iph->ihl * 4) < 0) { - if (!csum_err) /* ignore csum errors. */ - return; - } + if (gre_parse_header(skb, &tpi, NULL, htons(ETH_P_IP), + iph->ihl * 4) < 0) + return; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 3196cf58f418..35a786c0aaa0 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -531,11 +531,7 @@ static void ip_sublist_rcv_finish(struct list_head *head) struct sk_buff *skb, *next; list_for_each_entry_safe(skb, next, head, list) { - list_del(&skb->list); - /* Handle ip{6}_forward case, as sch_direct_xmit have - * another kind of SKB-list usage (see validate_xmit_skb_list) - */ - skb->next = NULL; + skb_list_del_init(skb); dst_input(skb); } } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 9c4e72e9c60a..c09219e7f230 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -278,7 +278,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, struct sk_buff *nskb = segs->next; int err; - segs->next = NULL; + skb_mark_not_on_list(segs); err = ip_fragment(net, sk, segs, mtu, ip_finish_output2); if (err && ret == 0) @@ -684,7 +684,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, skb = frag; frag = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); } if (err == 0) { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 10c6246396cc..67670fac7c8d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2595,6 +2595,8 @@ int tcp_disconnect(struct sock *sk, int flags) tp->compressed_ack = 0; tp->bytes_sent = 0; tp->bytes_retrans = 0; + tp->duplicate_sack[0].start_seq = 0; + tp->duplicate_sack[0].end_seq = 0; tp->dsack_dups = 0; tp->reord_seen = 0; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 4cf2f7bb2802..d9034073138c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4199,6 +4199,17 @@ static void tcp_dsack_extend(struct sock *sk, u32 seq, u32 end_seq) tcp_sack_extend(tp->duplicate_sack, seq, end_seq); } +static void tcp_rcv_spurious_retrans(struct sock *sk, const struct sk_buff *skb) +{ + /* When the ACK path fails or drops most ACKs, the sender would + * timeout and spuriously retransmit the same segment repeatedly. + * The receiver remembers and reflects via DSACKs. Leverage the + * DSACK state and change the txhash to re-route speculatively. + */ + if (TCP_SKB_CB(skb)->seq == tcp_sk(sk)->duplicate_sack[0].start_seq) + sk_rethink_txhash(sk); +} + static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); @@ -4211,6 +4222,7 @@ static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb) if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) { u32 end_seq = TCP_SKB_CB(skb)->end_seq; + tcp_rcv_spurious_retrans(sk, skb); if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) end_seq = tp->rcv_nxt; tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, end_seq); @@ -4755,6 +4767,7 @@ queue_and_out: } if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) { + tcp_rcv_spurious_retrans(sk, skb); /* A retransmit, 2nd most common case. Force an immediate ack. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST); tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 44c09eddbb78..09547ef9c4c6 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2549,7 +2549,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_tw_reuse = 2; cnt = tcp_hashinfo.ehash_mask + 1; - net->ipv4.tcp_death_row.sysctl_max_tw_buckets = (cnt + 1) / 2; + net->ipv4.tcp_death_row.sysctl_max_tw_buckets = cnt / 2; net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo; net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 256); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index d51a8c0b3372..d4733160e6b7 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4491,6 +4491,7 @@ static const struct nla_policy ifa_ipv6_policy[IFA_MAX+1] = { [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, [IFA_FLAGS] = { .len = sizeof(u32) }, [IFA_RT_PRIORITY] = { .len = sizeof(u32) }, + [IFA_TARGET_NETNSID] = { .type = NLA_S32 }, }; static int @@ -4793,19 +4794,32 @@ static inline int inet6_ifaddr_msgsize(void) + nla_total_size(4) /* IFA_RT_PRIORITY */; } +struct inet6_fill_args { + u32 portid; + u32 seq; + int event; + unsigned int flags; + int netnsid; +}; + static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, - u32 portid, u32 seq, int event, unsigned int flags) + struct inet6_fill_args *args) { struct nlmsghdr *nlh; u32 preferred, valid; - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags); + nlh = nlmsg_put(skb, args->portid, args->seq, args->event, + sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; put_ifaddrmsg(nlh, ifa->prefix_len, ifa->flags, rt_scope(ifa->scope), ifa->idev->dev->ifindex); + if (args->netnsid >= 0 && + nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) + goto error; + if (!((ifa->flags&IFA_F_PERMANENT) && (ifa->prefered_lft == INFINITY_LIFE_TIME))) { preferred = ifa->prefered_lft; @@ -4855,7 +4869,7 @@ error: } static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, - u32 portid, u32 seq, int event, u16 flags) + struct inet6_fill_args *args) { struct nlmsghdr *nlh; u8 scope = RT_SCOPE_UNIVERSE; @@ -4864,10 +4878,15 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, if (ipv6_addr_scope(&ifmca->mca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags); + nlh = nlmsg_put(skb, args->portid, args->seq, args->event, + sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; + if (args->netnsid >= 0 && + nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) + return -EMSGSIZE; + put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_MULTICAST, &ifmca->mca_addr) < 0 || put_cacheinfo(skb, ifmca->mca_cstamp, ifmca->mca_tstamp, @@ -4881,7 +4900,7 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, } static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, - u32 portid, u32 seq, int event, unsigned int flags) + struct inet6_fill_args *args) { struct net_device *dev = fib6_info_nh_dev(ifaca->aca_rt); int ifindex = dev ? dev->ifindex : 1; @@ -4891,10 +4910,15 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, if (ipv6_addr_scope(&ifaca->aca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags); + nlh = nlmsg_put(skb, args->portid, args->seq, args->event, + sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; + if (args->netnsid >= 0 && + nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) + return -EMSGSIZE; + put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_ANYCAST, &ifaca->aca_addr) < 0 || put_cacheinfo(skb, ifaca->aca_cstamp, ifaca->aca_tstamp, @@ -4916,8 +4940,14 @@ enum addr_type_t { /* called with rcu_read_lock() */ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, struct netlink_callback *cb, enum addr_type_t type, - int s_ip_idx, int *p_ip_idx) + int s_ip_idx, int *p_ip_idx, int netnsid) { + struct inet6_fill_args fillargs = { + .portid = NETLINK_CB(cb->skb).portid, + .seq = cb->nlh->nlmsg_seq, + .flags = NLM_F_MULTI, + .netnsid = netnsid, + }; struct ifmcaddr6 *ifmca; struct ifacaddr6 *ifaca; int err = 1; @@ -4927,16 +4957,13 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, switch (type) { case UNICAST_ADDR: { struct inet6_ifaddr *ifa; + fillargs.event = RTM_NEWADDR; /* unicast address incl. temp addr */ list_for_each_entry(ifa, &idev->addr_list, if_list) { if (++ip_idx < s_ip_idx) continue; - err = inet6_fill_ifaddr(skb, ifa, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWADDR, - NLM_F_MULTI); + err = inet6_fill_ifaddr(skb, ifa, &fillargs); if (err < 0) break; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -4944,31 +4971,26 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, break; } case MULTICAST_ADDR: + fillargs.event = RTM_GETMULTICAST; + /* multicast address */ for (ifmca = idev->mc_list; ifmca; ifmca = ifmca->next, ip_idx++) { if (ip_idx < s_ip_idx) continue; - err = inet6_fill_ifmcaddr(skb, ifmca, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_GETMULTICAST, - NLM_F_MULTI); + err = inet6_fill_ifmcaddr(skb, ifmca, &fillargs); if (err < 0) break; } break; case ANYCAST_ADDR: + fillargs.event = RTM_GETANYCAST; /* anycast address */ for (ifaca = idev->ac_list; ifaca; ifaca = ifaca->aca_next, ip_idx++) { if (ip_idx < s_ip_idx) continue; - err = inet6_fill_ifacaddr(skb, ifaca, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_GETANYCAST, - NLM_F_MULTI); + err = inet6_fill_ifacaddr(skb, ifaca, &fillargs); if (err < 0) break; } @@ -4985,6 +5007,9 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, enum addr_type_t type) { struct net *net = sock_net(skb->sk); + struct nlattr *tb[IFA_MAX+1]; + struct net *tgt_net = net; + int netnsid = -1; int h, s_h; int idx, ip_idx; int s_idx, s_ip_idx; @@ -4996,11 +5021,22 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, s_idx = idx = cb->args[1]; s_ip_idx = ip_idx = cb->args[2]; + if (nlmsg_parse(cb->nlh, sizeof(struct ifaddrmsg), tb, IFA_MAX, + ifa_ipv6_policy, NULL) >= 0) { + if (tb[IFA_TARGET_NETNSID]) { + netnsid = nla_get_s32(tb[IFA_TARGET_NETNSID]); + + tgt_net = rtnl_get_net_ns_capable(skb->sk, netnsid); + if (IS_ERR(tgt_net)) + return PTR_ERR(tgt_net); + } + } + rcu_read_lock(); - cb->seq = atomic_read(&net->ipv6.dev_addr_genid) ^ net->dev_base_seq; + cb->seq = atomic_read(&tgt_net->ipv6.dev_addr_genid) ^ tgt_net->dev_base_seq; for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; - head = &net->dev_index_head[h]; + head = &tgt_net->dev_index_head[h]; hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; @@ -5012,7 +5048,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, goto cont; if (in6_dump_addrs(idev, skb, cb, type, - s_ip_idx, &ip_idx) < 0) + s_ip_idx, &ip_idx, netnsid) < 0) goto done; cont: idx++; @@ -5023,6 +5059,8 @@ done: cb->args[0] = h; cb->args[1] = idx; cb->args[2] = ip_idx; + if (netnsid >= 0) + put_net(tgt_net); return skb->len; } @@ -5053,6 +5091,14 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); + struct inet6_fill_args fillargs = { + .portid = NETLINK_CB(in_skb).portid, + .seq = nlh->nlmsg_seq, + .event = RTM_NEWADDR, + .flags = 0, + .netnsid = -1, + }; + struct net *tgt_net = net; struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; struct in6_addr *addr = NULL, *peer; @@ -5066,15 +5112,24 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (err < 0) return err; + if (tb[IFA_TARGET_NETNSID]) { + fillargs.netnsid = nla_get_s32(tb[IFA_TARGET_NETNSID]); + + tgt_net = rtnl_get_net_ns_capable(NETLINK_CB(in_skb).sk, + fillargs.netnsid); + if (IS_ERR(tgt_net)) + return PTR_ERR(tgt_net); + } + addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer); if (!addr) return -EINVAL; ifm = nlmsg_data(nlh); if (ifm->ifa_index) - dev = dev_get_by_index(net, ifm->ifa_index); + dev = dev_get_by_index(tgt_net, ifm->ifa_index); - ifa = ipv6_get_ifaddr(net, addr, dev, 1); + ifa = ipv6_get_ifaddr(tgt_net, addr, dev, 1); if (!ifa) { err = -EADDRNOTAVAIL; goto errout; @@ -5086,20 +5141,22 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, goto errout_ifa; } - err = inet6_fill_ifaddr(skb, ifa, NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, RTM_NEWADDR, 0); + err = inet6_fill_ifaddr(skb, ifa, &fillargs); if (err < 0) { /* -EMSGSIZE implies BUG in inet6_ifaddr_msgsize() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout_ifa; } - err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); + err = rtnl_unicast(skb, tgt_net, NETLINK_CB(in_skb).portid); errout_ifa: in6_ifa_put(ifa); errout: if (dev) dev_put(dev); + if (fillargs.netnsid >= 0) + put_net(tgt_net); + return err; } @@ -5107,13 +5164,20 @@ static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa) { struct sk_buff *skb; struct net *net = dev_net(ifa->idev->dev); + struct inet6_fill_args fillargs = { + .portid = 0, + .seq = 0, + .event = event, + .flags = 0, + .netnsid = -1, + }; int err = -ENOBUFS; skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_ATOMIC); if (!skb) goto errout; - err = inet6_fill_ifaddr(skb, ifa, 0, 0, event, 0); + err = inet6_fill_ifaddr(skb, ifa, &fillargs); if (err < 0) { /* -EMSGSIZE implies BUG in inet6_ifaddr_msgsize() */ WARN_ON(err == -EMSGSIZE); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 9a4261e50272..77ef8478234f 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -209,6 +209,7 @@ lookup_protocol: np->hop_limit = -1; np->mcast_hops = IPV6_DEFAULT_MCASTHOPS; np->mc_loop = 1; + np->mc_all = 1; np->pmtudisc = IPV6_PMTUDISC_WANT; np->repflow = net->ipv6.sysctl.flowlabel_reflect; sk->sk_ipv6only = net->ipv6.sysctl.bindv6only; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index e493b041d4ac..515adbdba1d2 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -427,35 +427,17 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct net *net = dev_net(skb->dev); - const struct gre_base_hdr *greh; const struct ipv6hdr *ipv6h; - int grehlen = sizeof(*greh); + struct tnl_ptk_info tpi; struct ip6_tnl *t; - int key_off = 0; - __be16 flags; - __be32 key; - if (!pskb_may_pull(skb, offset + grehlen)) - return; - greh = (const struct gre_base_hdr *)(skb->data + offset); - flags = greh->flags; - if (flags & (GRE_VERSION | GRE_ROUTING)) + if (gre_parse_header(skb, &tpi, NULL, htons(ETH_P_IPV6), + offset) < 0) return; - if (flags & GRE_CSUM) - grehlen += 4; - if (flags & GRE_KEY) { - key_off = grehlen + offset; - grehlen += 4; - } - if (!pskb_may_pull(skb, offset + grehlen)) - return; ipv6h = (const struct ipv6hdr *)skb->data; - greh = (const struct gre_base_hdr *)(skb->data + offset); - key = key_off ? *(__be32 *)(skb->data + key_off) : 0; - t = ip6gre_tunnel_lookup(skb->dev, &ipv6h->daddr, &ipv6h->saddr, - key, greh->protocol); + tpi.key, tpi.proto); if (!t) return; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index f9f8f554d141..89e0d5118afe 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -725,7 +725,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, skb = frag; frag = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); } kfree(tmp_hdr); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index c0cac9cc3a28..381ce38940ae 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -674,6 +674,13 @@ done: retv = ipv6_sock_ac_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr); break; } + case IPV6_MULTICAST_ALL: + if (optlen < sizeof(int)) + goto e_inval; + np->mc_all = valbool; + retv = 0; + break; + case MCAST_JOIN_GROUP: case MCAST_LEAVE_GROUP: { @@ -1266,6 +1273,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, val = np->mcast_oif; break; + case IPV6_MULTICAST_ALL: + val = np->mc_all; + break; + case IPV6_UNICAST_IF: val = (__force int)htonl((__u32) np->ucast_oif); break; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 4ae54aaca373..6895e1dc0b03 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -636,7 +636,7 @@ bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr, } if (!mc) { rcu_read_unlock(); - return true; + return np->mc_all; } read_lock(&mc->sflock); psl = mc->sflist; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 8f68a518d9db..b8ac369f98ad 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -450,7 +450,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_devic sub_frag_mem_limit(fq->q.net, head->truesize); head->ignore_df = 1; - head->next = NULL; + skb_mark_not_on_list(head); head->dev = dev; head->tstamp = fq->q.stamp; ipv6_hdr(head)->payload_len = htons(payload_len); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 5c5b4f79296e..f1b1ff30fe5b 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -388,7 +388,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, } sub_frag_mem_limit(fq->q.net, sum_truesize); - head->next = NULL; + skb_mark_not_on_list(head); head->dev = dev; head->tstamp = fq->q.stamp; ipv6_hdr(head)->payload_len = htons(payload_len); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 480a79f47c52..21a919e74fbf 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -993,7 +993,6 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort) #ifdef CONFIG_IPV6_SUBTREES rt->rt6i_src = ort->fib6_src; #endif - rt->rt6i_prefsrc = ort->fib6_prefsrc; } static struct fib6_node* fib6_backtrack(struct fib6_node *fn, @@ -1447,11 +1446,6 @@ static int rt6_insert_exception(struct rt6_info *nrt, if (ort->fib6_src.plen) src_key = &nrt->rt6i_src.addr; #endif - - /* Update rt6i_prefsrc as it could be changed - * in rt6_remove_prefsrc() - */ - nrt->rt6i_prefsrc = ort->fib6_prefsrc; /* rt6_mtu_change() might lower mtu on ort. * Only insert this exception route if its mtu * is less than ort's mtu value. @@ -1633,25 +1627,6 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt) rcu_read_unlock(); } -static void rt6_exceptions_remove_prefsrc(struct fib6_info *rt) -{ - 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)); - - if (bucket) { - for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { - hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { - rt6_ex->rt6i->rt6i_prefsrc.plen = 0; - } - bucket++; - } - } -} - static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev, struct rt6_info *rt, int mtu) { @@ -3135,8 +3110,6 @@ install_route: rt->fib6_nh.nh_dev = dev; rt->fib6_table = table; - cfg->fc_nlinfo.nl_net = dev_net(dev); - if (idev) in6_dev_put(idev); @@ -3793,8 +3766,6 @@ static int fib6_remove_prefsrc(struct fib6_info *rt, void *arg) spin_lock_bh(&rt6_exception_lock); /* remove prefsrc entry */ rt->fib6_prefsrc.plen = 0; - /* need to update cache as well */ - rt6_exceptions_remove_prefsrc(rt); spin_unlock_bh(&rt6_exception_lock); } return 0; diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c index 260b3dc1b4a2..64d4bef04e73 100644 --- a/net/llc/llc_core.c +++ b/net/llc/llc_core.c @@ -127,9 +127,7 @@ void llc_sap_close(struct llc_sap *sap) list_del_rcu(&sap->node); spin_unlock_bh(&llc_sap_list_lock); - synchronize_rcu(); - - kfree(sap); + kfree_rcu(sap, rcu); } static struct packet_type llc_packet_type __read_mostly = { diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index d25da0e66da1..504627e2117f 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -158,12 +158,10 @@ static int ieee80211_change_iface(struct wiphy *wiphy, if (ret) return ret; - if (type == NL80211_IFTYPE_AP_VLAN && - params && params->use_4addr == 0) { + if (type == NL80211_IFTYPE_AP_VLAN && params->use_4addr == 0) { RCU_INIT_POINTER(sdata->u.vlan.sta, NULL); ieee80211_check_fast_rx_iface(sdata); - } else if (type == NL80211_IFTYPE_STATION && - params && params->use_4addr >= 0) { + } else if (type == NL80211_IFTYPE_STATION && params->use_4addr >= 0) { sdata->u.mgd.use_4addr = params->use_4addr; } @@ -911,6 +909,9 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, sdata->vif.bss_conf.beacon_int = params->beacon_interval; + if (params->he_cap) + sdata->vif.bss_conf.he_support = true; + mutex_lock(&local->mtx); err = ieee80211_vif_use_channel(sdata, ¶ms->chandef, IEEE80211_CHANCTX_SHARED); @@ -1092,50 +1093,6 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) return 0; } -/* Layer 2 Update frame (802.2 Type 1 LLC XID Update response) */ -struct iapp_layer2_update { - u8 da[ETH_ALEN]; /* broadcast */ - u8 sa[ETH_ALEN]; /* STA addr */ - __be16 len; /* 6 */ - u8 dsap; /* 0 */ - u8 ssap; /* 0 */ - u8 control; - u8 xid_info[3]; -} __packed; - -static void ieee80211_send_layer2_update(struct sta_info *sta) -{ - struct iapp_layer2_update *msg; - struct sk_buff *skb; - - /* Send Level 2 Update Frame to update forwarding tables in layer 2 - * bridge devices */ - - skb = dev_alloc_skb(sizeof(*msg)); - if (!skb) - return; - msg = skb_put(skb, sizeof(*msg)); - - /* 802.2 Type 1 Logical Link Control (LLC) Exchange Identifier (XID) - * Update response frame; IEEE Std 802.2-1998, 5.4.1.2.1 */ - - eth_broadcast_addr(msg->da); - memcpy(msg->sa, sta->sta.addr, ETH_ALEN); - msg->len = htons(6); - msg->dsap = 0; - msg->ssap = 0x01; /* NULL LSAP, CR Bit: Response */ - msg->control = 0xaf; /* XID response lsb.1111F101. - * F=0 (no poll command; unsolicited frame) */ - msg->xid_info[0] = 0x81; /* XID format identifier */ - msg->xid_info[1] = 1; /* LLC types/classes: Type 1 LLC */ - msg->xid_info[2] = 0; /* XID sender's receive window size (RW) */ - - skb->dev = sta->sdata->dev; - skb->protocol = eth_type_trans(skb, sta->sdata->dev); - memset(skb->cb, 0, sizeof(skb->cb)); - netif_rx_ni(skb); -} - static int sta_apply_auth_flags(struct ieee80211_local *local, struct sta_info *sta, u32 mask, u32 set) @@ -1499,7 +1456,7 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, } if (layer2_update) - ieee80211_send_layer2_update(sta); + cfg80211_send_layer2_update(sta->sdata->dev, sta->sta.addr); rcu_read_unlock(); @@ -1601,7 +1558,7 @@ static int ieee80211_change_station(struct wiphy *wiphy, if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) ieee80211_vif_inc_num_mcast(sta->sdata); - ieee80211_send_layer2_update(sta); + cfg80211_send_layer2_update(sta->sdata->dev, sta->sta.addr); } err = sta_apply_parameters(local, sta, params); diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index b5adf3625d16..3fe541e358f3 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -3,6 +3,7 @@ * * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH + * Copyright (C) 2018 Intel Corporation * * GPLv2 * @@ -214,6 +215,9 @@ static const char *hw_flag_names[] = { FLAG(SUPPORTS_TDLS_BUFFER_STA), FLAG(DEAUTH_NEED_MGD_TX_PREP), FLAG(DOESNT_SUPPORT_QOS_NDP), + FLAG(BUFF_MMPDU_TXQ), + FLAG(SUPPORTS_VHT_EXT_NSS_BW), + FLAG(STA_MMPDU_TXQ), #undef FLAG }; diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 4105081dc1df..af5185a836e5 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -4,6 +4,7 @@ * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2016 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -140,7 +141,7 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf, { struct sta_info *sta = file->private_data; struct ieee80211_local *local = sta->local; - size_t bufsz = AQM_TXQ_ENTRY_LEN*(IEEE80211_NUM_TIDS+1); + size_t bufsz = AQM_TXQ_ENTRY_LEN * (IEEE80211_NUM_TIDS + 2); char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf; struct txq_info *txqi; ssize_t rv; @@ -162,7 +163,9 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf, bufsz+buf-p, "tid ac backlog-bytes backlog-packets new-flows drops marks overlimit collisions tx-bytes tx-packets flags\n"); - for (i = 0; i < IEEE80211_NUM_TIDS; i++) { + for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { + if (!sta->sta.txq[i]) + continue; txqi = to_txq_info(sta->sta.txq[i]); p += scnprintf(p, bufsz+buf-p, "%d %d %u %u %u %u %u %u %u %u %u 0x%lx(%s%s%s)\n", @@ -487,12 +490,368 @@ static ssize_t sta_vht_capa_read(struct file *file, char __user *userbuf, p += scnprintf(p, sizeof(buf)+buf-p, "MCS TX highest: %d Mbps\n", le16_to_cpu(vhtc->vht_mcs.tx_highest)); +#undef PFLAG } return simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); } STA_OPS(vht_capa); +static ssize_t sta_he_capa_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) +{ + char *buf, *p; + size_t buf_sz = PAGE_SIZE; + struct sta_info *sta = file->private_data; + struct ieee80211_sta_he_cap *hec = &sta->sta.he_cap; + struct ieee80211_he_mcs_nss_supp *nss = &hec->he_mcs_nss_supp; + u8 ppe_size; + u8 *cap; + int i; + ssize_t ret; + + buf = kmalloc(buf_sz, GFP_KERNEL); + if (!buf) + return -ENOMEM; + p = buf; + + p += scnprintf(p, buf_sz + buf - p, "HE %ssupported\n", + hec->has_he ? "" : "not "); + if (!hec->has_he) + goto out; + + cap = hec->he_cap_elem.mac_cap_info; + p += scnprintf(p, buf_sz + buf - p, + "MAC-CAP: %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x\n", + cap[0], cap[1], cap[2], cap[3], cap[4], cap[5]); + +#define PRINT(fmt, ...) \ + p += scnprintf(p, buf_sz + buf - p, "\t\t" fmt "\n", \ + ##__VA_ARGS__) + +#define PFLAG(t, n, a, b) \ + do { \ + if (cap[n] & IEEE80211_HE_##t##_CAP##n##_##a) \ + PRINT("%s", b); \ + } while (0) + +#define PFLAG_RANGE(t, i, n, s, m, off, fmt) \ + do { \ + u8 msk = IEEE80211_HE_##t##_CAP##i##_##n##_MASK; \ + u8 idx = ((cap[i] & msk) >> (ffs(msk) - 1)) + off; \ + PRINT(fmt, (s << idx) + (m * idx)); \ + } while (0) + +#define PFLAG_RANGE_DEFAULT(t, i, n, s, m, off, fmt, a, b) \ + do { \ + if (cap[i] == IEEE80211_HE_##t ##_CAP##i##_##n##_##a) { \ + PRINT("%s", b); \ + break; \ + } \ + PFLAG_RANGE(t, i, n, s, m, off, fmt); \ + } while (0) + + PFLAG(MAC, 0, HTC_HE, "HTC-HE"); + PFLAG(MAC, 0, TWT_REQ, "TWT-REQ"); + PFLAG(MAC, 0, TWT_RES, "TWT-RES"); + PFLAG_RANGE_DEFAULT(MAC, 0, DYNAMIC_FRAG, 0, 1, 0, + "DYNAMIC-FRAG-LEVEL-%d", NOT_SUPP, "NOT-SUPP"); + PFLAG_RANGE_DEFAULT(MAC, 0, MAX_NUM_FRAG_MSDU, 1, 0, 0, + "MAX-NUM-FRAG-MSDU-%d", UNLIMITED, "UNLIMITED"); + + PFLAG_RANGE_DEFAULT(MAC, 1, MIN_FRAG_SIZE, 128, 0, -1, + "MIN-FRAG-SIZE-%d", UNLIMITED, "UNLIMITED"); + PFLAG_RANGE_DEFAULT(MAC, 1, TF_MAC_PAD_DUR, 0, 8, 0, + "TF-MAC-PAD-DUR-%dUS", MASK, "UNKNOWN"); + PFLAG_RANGE(MAC, 1, MULTI_TID_AGG_RX_QOS, 0, 1, 1, + "MULTI-TID-AGG-RX-QOS-%d"); + + if (cap[0] & IEEE80211_HE_MAC_CAP0_HTC_HE) { + switch (((cap[2] << 1) | (cap[1] >> 7)) & 0x3) { + case 0: + PRINT("LINK-ADAPTATION-NO-FEEDBACK"); + break; + case 1: + PRINT("LINK-ADAPTATION-RESERVED"); + break; + case 2: + PRINT("LINK-ADAPTATION-UNSOLICITED-FEEDBACK"); + break; + case 3: + PRINT("LINK-ADAPTATION-BOTH"); + break; + } + } + + PFLAG(MAC, 2, ALL_ACK, "ALL-ACK"); + PFLAG(MAC, 2, TRS, "TRS"); + PFLAG(MAC, 2, BSR, "BSR"); + PFLAG(MAC, 2, BCAST_TWT, "BCAST-TWT"); + PFLAG(MAC, 2, 32BIT_BA_BITMAP, "32BIT-BA-BITMAP"); + PFLAG(MAC, 2, MU_CASCADING, "MU-CASCADING"); + PFLAG(MAC, 2, ACK_EN, "ACK-EN"); + + PFLAG(MAC, 3, OMI_CONTROL, "OMI-CONTROL"); + PFLAG(MAC, 3, OFDMA_RA, "OFDMA-RA"); + + switch (cap[3] & IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK) { + case IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_USE_VHT: + PRINT("MAX-AMPDU-LEN-EXP-USE-VHT"); + break; + case IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_1: + PRINT("MAX-AMPDU-LEN-EXP-VHT-1"); + break; + case IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2: + PRINT("MAX-AMPDU-LEN-EXP-VHT-2"); + break; + case IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_RESERVED: + PRINT("MAX-AMPDU-LEN-EXP-RESERVED"); + break; + } + + PFLAG(MAC, 3, AMSDU_FRAG, "AMSDU-FRAG"); + PFLAG(MAC, 3, FLEX_TWT_SCHED, "FLEX-TWT-SCHED"); + PFLAG(MAC, 3, RX_CTRL_FRAME_TO_MULTIBSS, "RX-CTRL-FRAME-TO-MULTIBSS"); + + PFLAG(MAC, 4, BSRP_BQRP_A_MPDU_AGG, "BSRP-BQRP-A-MPDU-AGG"); + PFLAG(MAC, 4, QTP, "QTP"); + PFLAG(MAC, 4, BQR, "BQR"); + PFLAG(MAC, 4, SRP_RESP, "SRP-RESP"); + PFLAG(MAC, 4, NDP_FB_REP, "NDP-FB-REP"); + PFLAG(MAC, 4, OPS, "OPS"); + PFLAG(MAC, 4, AMDSU_IN_AMPDU, "AMSDU-IN-AMPDU"); + + PRINT("MULTI-TID-AGG-TX-QOS-%d", ((cap[5] << 1) | (cap[4] >> 7)) & 0x7); + + PFLAG(MAC, 5, SUBCHAN_SELECVITE_TRANSMISSION, + "SUBCHAN-SELECVITE-TRANSMISSION"); + PFLAG(MAC, 5, UL_2x996_TONE_RU, "UL-2x996-TONE-RU"); + PFLAG(MAC, 5, OM_CTRL_UL_MU_DATA_DIS_RX, "OM-CTRL-UL-MU-DATA-DIS-RX"); + + cap = hec->he_cap_elem.phy_cap_info; + p += scnprintf(p, buf_sz + buf - p, + "PHY CAP: %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x\n", + cap[0], cap[1], cap[2], cap[3], cap[4], cap[5], cap[6], + cap[7], cap[8], cap[9], cap[10]); + + PFLAG(PHY, 0, CHANNEL_WIDTH_SET_40MHZ_IN_2G, + "CHANNEL-WIDTH-SET-40MHZ-IN-2G"); + PFLAG(PHY, 0, CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G, + "CHANNEL-WIDTH-SET-40MHZ-80MHZ-IN-5G"); + PFLAG(PHY, 0, CHANNEL_WIDTH_SET_160MHZ_IN_5G, + "CHANNEL-WIDTH-SET-160MHZ-IN-5G"); + PFLAG(PHY, 0, CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G, + "CHANNEL-WIDTH-SET-80PLUS80-MHZ-IN-5G"); + PFLAG(PHY, 0, CHANNEL_WIDTH_SET_RU_MAPPING_IN_2G, + "CHANNEL-WIDTH-SET-RU-MAPPING-IN-2G"); + PFLAG(PHY, 0, CHANNEL_WIDTH_SET_RU_MAPPING_IN_5G, + "CHANNEL-WIDTH-SET-RU-MAPPING-IN-5G"); + + switch (cap[1] & IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK) { + case IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_20MHZ: + PRINT("PREAMBLE-PUNC-RX-80MHZ-ONLY-SECOND-20MHZ"); + break; + case IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_40MHZ: + PRINT("PREAMBLE-PUNC-RX-80MHZ-ONLY-SECOND-40MHZ"); + break; + case IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_20MHZ: + PRINT("PREAMBLE-PUNC-RX-160MHZ-ONLY-SECOND-20MHZ"); + break; + case IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_40MHZ: + PRINT("PREAMBLE-PUNC-RX-160MHZ-ONLY-SECOND-40MHZ"); + break; + } + + PFLAG(PHY, 1, DEVICE_CLASS_A, + "IEEE80211-HE-PHY-CAP1-DEVICE-CLASS-A"); + PFLAG(PHY, 1, LDPC_CODING_IN_PAYLOAD, + "LDPC-CODING-IN-PAYLOAD"); + PFLAG(PHY, 1, HE_LTF_AND_GI_FOR_HE_PPDUS_0_8US, + "HY-CAP1-HE-LTF-AND-GI-FOR-HE-PPDUS-0-8US"); + PRINT("MIDAMBLE-RX-MAX-NSTS-%d", ((cap[2] << 1) | (cap[1] >> 7)) & 0x3); + + PFLAG(PHY, 2, NDP_4x_LTF_AND_3_2US, "NDP-4X-LTF-AND-3-2US"); + PFLAG(PHY, 2, STBC_TX_UNDER_80MHZ, "STBC-TX-UNDER-80MHZ"); + PFLAG(PHY, 2, STBC_RX_UNDER_80MHZ, "STBC-RX-UNDER-80MHZ"); + PFLAG(PHY, 2, DOPPLER_TX, "DOPPLER-TX"); + PFLAG(PHY, 2, DOPPLER_RX, "DOPPLER-RX"); + PFLAG(PHY, 2, UL_MU_FULL_MU_MIMO, "UL-MU-FULL-MU-MIMO"); + PFLAG(PHY, 2, UL_MU_PARTIAL_MU_MIMO, "UL-MU-PARTIAL-MU-MIMO"); + + switch (cap[3] & IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_MASK) { + case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_NO_DCM: + PRINT("DCM-MAX-CONST-TX-NO-DCM"); + break; + case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK: + PRINT("DCM-MAX-CONST-TX-BPSK"); + break; + case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_QPSK: + PRINT("DCM-MAX-CONST-TX-QPSK"); + break; + case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_16_QAM: + PRINT("DCM-MAX-CONST-TX-16-QAM"); + break; + } + + PFLAG(PHY, 3, DCM_MAX_TX_NSS_1, "DCM-MAX-TX-NSS-1"); + PFLAG(PHY, 3, DCM_MAX_TX_NSS_2, "DCM-MAX-TX-NSS-2"); + + switch (cap[3] & IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_MASK) { + case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_NO_DCM: + PRINT("DCM-MAX-CONST-RX-NO-DCM"); + break; + case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK: + PRINT("DCM-MAX-CONST-RX-BPSK"); + break; + case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_QPSK: + PRINT("DCM-MAX-CONST-RX-QPSK"); + break; + case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_16_QAM: + PRINT("DCM-MAX-CONST-RX-16-QAM"); + break; + } + + PFLAG(PHY, 3, DCM_MAX_RX_NSS_1, "DCM-MAX-RX-NSS-1"); + PFLAG(PHY, 3, DCM_MAX_RX_NSS_2, "DCM-MAX-RX-NSS-2"); + PFLAG(PHY, 3, RX_HE_MU_PPDU_FROM_NON_AP_STA, + "RX-HE-MU-PPDU-FROM-NON-AP-STA"); + PFLAG(PHY, 3, SU_BEAMFORMER, "SU-BEAMFORMER"); + + PFLAG(PHY, 4, SU_BEAMFORMEE, "SU-BEAMFORMEE"); + PFLAG(PHY, 4, MU_BEAMFORMER, "MU-BEAMFORMER"); + + PFLAG_RANGE(PHY, 4, BEAMFORMEE_MAX_STS_UNDER_80MHZ, 0, 1, 4, + "BEAMFORMEE-MAX-STS-UNDER-%d"); + PFLAG_RANGE(PHY, 4, BEAMFORMEE_MAX_STS_ABOVE_80MHZ, 0, 1, 4, + "BEAMFORMEE-MAX-STS-ABOVE-%d"); + + PFLAG_RANGE(PHY, 5, BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ, 0, 1, 1, + "NUM-SND-DIM-UNDER-80MHZ-%d"); + PFLAG_RANGE(PHY, 5, BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ, 0, 1, 1, + "NUM-SND-DIM-ABOVE-80MHZ-%d"); + PFLAG(PHY, 5, NG16_SU_FEEDBACK, "NG16-SU-FEEDBACK"); + PFLAG(PHY, 5, NG16_MU_FEEDBACK, "NG16-MU-FEEDBACK"); + + PFLAG(PHY, 6, CODEBOOK_SIZE_42_SU, "CODEBOOK-SIZE-42-SU"); + PFLAG(PHY, 6, CODEBOOK_SIZE_75_MU, "CODEBOOK-SIZE-75-MU"); + PFLAG(PHY, 6, TRIG_SU_BEAMFORMER_FB, "TRIG-SU-BEAMFORMER-FB"); + PFLAG(PHY, 6, TRIG_MU_BEAMFORMER_FB, "TRIG-MU-BEAMFORMER-FB"); + PFLAG(PHY, 6, TRIG_CQI_FB, "TRIG-CQI-FB"); + PFLAG(PHY, 6, PARTIAL_BW_EXT_RANGE, "PARTIAL-BW-EXT-RANGE"); + PFLAG(PHY, 6, PARTIAL_BANDWIDTH_DL_MUMIMO, + "PARTIAL-BANDWIDTH-DL-MUMIMO"); + PFLAG(PHY, 6, PPE_THRESHOLD_PRESENT, "PPE-THRESHOLD-PRESENT"); + + PFLAG(PHY, 7, SRP_BASED_SR, "SRP-BASED-SR"); + PFLAG(PHY, 7, POWER_BOOST_FACTOR_AR, "POWER-BOOST-FACTOR-AR"); + PFLAG(PHY, 7, HE_SU_MU_PPDU_4XLTF_AND_08_US_GI, + "HE-SU-MU-PPDU-4XLTF-AND-08-US-GI"); + PFLAG_RANGE(PHY, 7, MAX_NC, 0, 1, 1, "MAX-NC-%d"); + PFLAG(PHY, 7, STBC_TX_ABOVE_80MHZ, "STBC-TX-ABOVE-80MHZ"); + PFLAG(PHY, 7, STBC_RX_ABOVE_80MHZ, "STBC-RX-ABOVE-80MHZ"); + + PFLAG(PHY, 8, HE_ER_SU_PPDU_4XLTF_AND_08_US_GI, + "HE-ER-SU-PPDU-4XLTF-AND-08-US-GI"); + PFLAG(PHY, 8, 20MHZ_IN_40MHZ_HE_PPDU_IN_2G, + "20MHZ-IN-40MHZ-HE-PPDU-IN-2G"); + PFLAG(PHY, 8, 20MHZ_IN_160MHZ_HE_PPDU, "20MHZ-IN-160MHZ-HE-PPDU"); + PFLAG(PHY, 8, 80MHZ_IN_160MHZ_HE_PPDU, "80MHZ-IN-160MHZ-HE-PPDU"); + PFLAG(PHY, 8, HE_ER_SU_1XLTF_AND_08_US_GI, + "HE-ER-SU-1XLTF-AND-08-US-GI"); + PFLAG(PHY, 8, MIDAMBLE_RX_TX_2X_AND_1XLTF, + "MIDAMBLE-RX-TX-2X-AND-1XLTF"); + + switch (cap[8] & IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_MASK) { + case IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_20MHZ: + PRINT("DDCM-MAX-BW-20MHZ"); + break; + case IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_40MHZ: + PRINT("DCM-MAX-BW-40MHZ"); + break; + case IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_80MHZ: + PRINT("DCM-MAX-BW-80MHZ"); + break; + case IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_160_OR_80P80_MHZ: + PRINT("DCM-MAX-BW-160-OR-80P80-MHZ"); + break; + } + + PFLAG(PHY, 9, LONGER_THAN_16_SIGB_OFDM_SYM, + "LONGER-THAN-16-SIGB-OFDM-SYM"); + PFLAG(PHY, 9, NON_TRIGGERED_CQI_FEEDBACK, + "NON-TRIGGERED-CQI-FEEDBACK"); + PFLAG(PHY, 9, TX_1024_QAM_LESS_THAN_242_TONE_RU, + "TX-1024-QAM-LESS-THAN-242-TONE-RU"); + PFLAG(PHY, 9, RX_1024_QAM_LESS_THAN_242_TONE_RU, + "RX-1024-QAM-LESS-THAN-242-TONE-RU"); + PFLAG(PHY, 9, RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB, + "RX-FULL-BW-SU-USING-MU-WITH-COMP-SIGB"); + PFLAG(PHY, 9, RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB, + "RX-FULL-BW-SU-USING-MU-WITH-NON-COMP-SIGB"); + +#undef PFLAG_RANGE_DEFAULT +#undef PFLAG_RANGE +#undef PFLAG + +#define PRINT_NSS_SUPP(f, n) \ + do { \ + int i; \ + u16 v = le16_to_cpu(nss->f); \ + p += scnprintf(p, buf_sz + buf - p, n ": %#.4x\n", v); \ + for (i = 0; i < 8; i += 2) { \ + switch ((v >> i) & 0x3) { \ + case 0: \ + PRINT(n "-%d-SUPPORT-0-7", i / 2); \ + break; \ + case 1: \ + PRINT(n "-%d-SUPPORT-0-9", i / 2); \ + break; \ + case 2: \ + PRINT(n "-%d-SUPPORT-0-11", i / 2); \ + break; \ + case 3: \ + PRINT(n "-%d-NOT-SUPPORTED", i / 2); \ + break; \ + } \ + } \ + } while (0) + + PRINT_NSS_SUPP(rx_mcs_80, "RX-MCS-80"); + PRINT_NSS_SUPP(tx_mcs_80, "TX-MCS-80"); + + if (cap[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) { + PRINT_NSS_SUPP(rx_mcs_160, "RX-MCS-160"); + PRINT_NSS_SUPP(tx_mcs_160, "TX-MCS-160"); + } + + if (cap[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G) { + PRINT_NSS_SUPP(rx_mcs_80p80, "RX-MCS-80P80"); + PRINT_NSS_SUPP(tx_mcs_80p80, "TX-MCS-80P80"); + } + +#undef PRINT_NSS_SUPP +#undef PRINT + + if (!(cap[6] & IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT)) + goto out; + + p += scnprintf(p, buf_sz + buf - p, "PPE-THRESHOLDS: %#.2x", + hec->ppe_thres[0]); + + ppe_size = ieee80211_he_ppe_size(hec->ppe_thres[0], cap); + for (i = 1; i < ppe_size; i++) { + p += scnprintf(p, buf_sz + buf - p, " %#.2x", + hec->ppe_thres[i]); + } + p += scnprintf(p, buf_sz + buf - p, "\n"); + +out: + ret = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); + kfree(buf); + return ret; +} +STA_OPS(he_capa); #define DEBUGFS_ADD(name) \ debugfs_create_file(#name, 0400, \ @@ -538,6 +897,7 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) DEBUGFS_ADD(agg_status); DEBUGFS_ADD(ht_capa); DEBUGFS_ADD(vht_capa); + DEBUGFS_ADD(he_capa); DEBUGFS_ADD_COUNTER(rx_duplicates, rx_stats.num_duplicates); DEBUGFS_ADD_COUNTER(rx_fragments, rx_stats.fragments); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 8f6998091d26..e42c641b6190 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1173,6 +1173,16 @@ static inline void drv_wake_tx_queue(struct ieee80211_local *local, local->ops->wake_tx_queue(&local->hw, &txq->txq); } +static inline int drv_can_aggregate_in_amsdu(struct ieee80211_local *local, + struct sk_buff *head, + struct sk_buff *skb) +{ + if (!local->ops->can_aggregate_in_amsdu) + return true; + + return local->ops->can_aggregate_in_amsdu(&local->hw, head, skb); +} + static inline int drv_start_nan(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct cfg80211_nan_conf *conf) diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index f0f5fedb8caa..0d704e8d7078 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -1070,7 +1070,9 @@ static void ieee80211_update_sta_info(struct ieee80211_sub_if_data *sdata, struct ieee80211_vht_cap cap_ie; struct ieee80211_sta_vht_cap cap = sta->sta.vht_cap; - ieee80211_chandef_vht_oper(elems->vht_operation, + ieee80211_chandef_vht_oper(&local->hw, + elems->vht_operation, + elems->ht_operation, &chandef); memcpy(&cap_ie, elems->vht_cap_elem, sizeof(cap_ie)); ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 172aeae21ae9..f40a2167935f 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -818,6 +818,7 @@ enum txq_info_flags { IEEE80211_TXQ_STOP, IEEE80211_TXQ_AMPDU, IEEE80211_TXQ_NO_AMSDU, + IEEE80211_TXQ_STOP_NETIF_TX, }; /** @@ -1198,6 +1199,9 @@ struct ieee80211_local { /* number of RX chains the hardware has */ u8 rx_chains; + /* bitmap of which sbands were copied */ + u8 sband_allocated; + int tx_headroom; /* required headroom for hardware/radiotap */ /* Tasklet and skb queue to process calls from IRQ mode. All frames @@ -1226,6 +1230,7 @@ struct ieee80211_local { struct sk_buff_head pending[IEEE80211_MAX_QUEUES]; struct tasklet_struct tx_pending_tasklet; + struct tasklet_struct wake_txqs_tasklet; atomic_t agg_queue_stop[IEEE80211_MAX_QUEUES]; @@ -2038,6 +2043,7 @@ void ieee80211_txq_remove_vlan(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata); void ieee80211_fill_txq_stats(struct cfg80211_txq_stats *txqstats, struct txq_info *txqi); +void ieee80211_wake_txqs(unsigned long data); void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, u16 transaction, u16 auth_alg, u16 status, const u8 *extra, size_t extra_len, const u8 *bssid, @@ -2106,7 +2112,9 @@ u8 *ieee80211_add_wmm_info_ie(u8 *buf, u8 qosinfo); /* channel management */ bool ieee80211_chandef_ht_oper(const struct ieee80211_ht_operation *ht_oper, struct cfg80211_chan_def *chandef); -bool ieee80211_chandef_vht_oper(const struct ieee80211_vht_operation *oper, +bool ieee80211_chandef_vht_oper(struct ieee80211_hw *hw, + const struct ieee80211_vht_operation *oper, + const struct ieee80211_ht_operation *htop, struct cfg80211_chan_def *chandef); u32 ieee80211_chandef_downgrade(struct cfg80211_chan_def *c); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index c054ac85793c..4700718e010f 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -248,6 +248,7 @@ static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key) (key->conf.flags & IEEE80211_KEY_FLAG_RESERVE_TAILROOM))) increment_tailroom_need_count(sdata); + key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE; ret = drv_set_key(key->local, DISABLE_KEY, sdata, sta ? &sta->sta : NULL, &key->conf); @@ -256,8 +257,65 @@ static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key) "failed to remove key (%d, %pM) from hardware (%d)\n", key->conf.keyidx, sta ? sta->sta.addr : bcast_addr, ret); +} - key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE; +static int ieee80211_hw_key_replace(struct ieee80211_key *old_key, + struct ieee80211_key *new_key, + bool ptk0rekey) +{ + struct ieee80211_sub_if_data *sdata; + struct ieee80211_local *local; + struct sta_info *sta; + int ret; + + /* Aggregation sessions are OK when running on SW crypto. + * A broken remote STA may cause issues not observed with HW + * crypto, though. + */ + if (!(old_key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) + return 0; + + assert_key_lock(old_key->local); + sta = old_key->sta; + + /* PTK only using key ID 0 needs special handling on rekey */ + if (new_key && sta && ptk0rekey) { + local = old_key->local; + sdata = old_key->sdata; + + /* Stop TX till we are on the new key */ + old_key->flags |= KEY_FLAG_TAINTED; + ieee80211_clear_fast_xmit(sta); + + /* Aggregation sessions during rekey are complicated due to the + * reorder buffer and retransmits. Side step that by blocking + * aggregation during rekey and tear down running sessions. + */ + if (ieee80211_hw_check(&local->hw, AMPDU_AGGREGATION)) { + set_sta_flag(sta, WLAN_STA_BLOCK_BA); + ieee80211_sta_tear_down_BA_sessions(sta, + AGG_STOP_LOCAL_REQUEST); + } + + if (!wiphy_ext_feature_isset(local->hw.wiphy, + NL80211_EXT_FEATURE_CAN_REPLACE_PTK0)) { + pr_warn_ratelimited("Rekeying PTK for STA %pM but driver can't safely do that.", + sta->sta.addr); + /* Flushing the driver queues *may* help prevent + * the clear text leaks and freezes. + */ + ieee80211_flush_queues(local, sdata, false); + } + } + + ieee80211_key_disable_hw_accel(old_key); + + if (new_key) + ret = ieee80211_key_enable_hw_accel(new_key); + else + ret = 0; + + return ret; } static void __ieee80211_set_default_key(struct ieee80211_sub_if_data *sdata, @@ -316,38 +374,57 @@ void ieee80211_set_default_mgmt_key(struct ieee80211_sub_if_data *sdata, } -static void ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, +static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, bool pairwise, struct ieee80211_key *old, struct ieee80211_key *new) { int idx; + int ret; bool defunikey, defmultikey, defmgmtkey; /* caller must provide at least one old/new */ if (WARN_ON(!new && !old)) - return; + return 0; if (new) list_add_tail_rcu(&new->list, &sdata->key_list); WARN_ON(new && old && new->conf.keyidx != old->conf.keyidx); - if (old) + if (old) { idx = old->conf.keyidx; - else + /* TODO: proper implement and test "Extended Key ID for + * Individually Addressed Frames" from IEEE 802.11-2016. + * Till then always assume only key ID 0 is used for + * pairwise keys.*/ + ret = ieee80211_hw_key_replace(old, new, pairwise); + } else { + /* new must be provided in case old is not */ idx = new->conf.keyidx; + if (!new->local->wowlan) + ret = ieee80211_key_enable_hw_accel(new); + else + ret = 0; + } + + if (ret) + return ret; if (sta) { if (pairwise) { rcu_assign_pointer(sta->ptk[idx], new); sta->ptk_idx = idx; - ieee80211_check_fast_xmit(sta); + if (new) { + clear_sta_flag(sta, WLAN_STA_BLOCK_BA); + ieee80211_check_fast_xmit(sta); + } } else { rcu_assign_pointer(sta->gtk[idx], new); } - ieee80211_check_fast_rx(sta); + if (new) + ieee80211_check_fast_rx(sta); } else { defunikey = old && old == key_mtx_dereference(sdata->local, @@ -380,6 +457,8 @@ static void ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, if (old) list_del_rcu(&old->list); + + return 0; } struct ieee80211_key * @@ -575,9 +654,6 @@ static void ieee80211_key_free_common(struct ieee80211_key *key) static void __ieee80211_key_destroy(struct ieee80211_key *key, bool delay_tailroom) { - if (key->local) - ieee80211_key_disable_hw_accel(key); - if (key->local) { struct ieee80211_sub_if_data *sdata = key->sdata; @@ -654,7 +730,6 @@ int ieee80211_key_link(struct ieee80211_key *key, struct ieee80211_sub_if_data *sdata, struct sta_info *sta) { - struct ieee80211_local *local = sdata->local; struct ieee80211_key *old_key; int idx = key->conf.keyidx; bool pairwise = key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE; @@ -691,17 +766,13 @@ int ieee80211_key_link(struct ieee80211_key *key, increment_tailroom_need_count(sdata); - ieee80211_key_replace(sdata, sta, pairwise, old_key, key); - ieee80211_key_destroy(old_key, delay_tailroom); - - ieee80211_debugfs_key_add(key); + ret = ieee80211_key_replace(sdata, sta, pairwise, old_key, key); - if (!local->wowlan) { - ret = ieee80211_key_enable_hw_accel(key); - if (ret) - ieee80211_key_free(key, delay_tailroom); + if (!ret) { + ieee80211_debugfs_key_add(key); + ieee80211_key_destroy(old_key, delay_tailroom); } else { - ret = 0; + ieee80211_key_free(key, delay_tailroom); } out: diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 513627896204..77381017bac7 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -4,6 +4,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2017 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -610,6 +611,18 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, local->ops = ops; local->use_chanctx = use_chanctx; + /* + * We need a bit of data queued to build aggregates properly, so + * instruct the TCP stack to allow more than a single ms of data + * to be queued in the stack. The value is a bit-shift of 1 + * second, so 8 is ~4ms of queued data. Only affects local TCP + * sockets. + * This is the default, anyhow - drivers may need to override it + * for local reasons (longer buffers, longer completion time, or + * similar). + */ + local->hw.tx_sk_pacing_shift = 8; + /* set up some defaults */ local->hw.queues = 1; local->hw.max_rates = 1; @@ -684,6 +697,10 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, tasklet_init(&local->tx_pending_tasklet, ieee80211_tx_pending, (unsigned long)local); + if (ops->wake_tx_queue) + tasklet_init(&local->wake_txqs_tasklet, ieee80211_wake_txqs, + (unsigned long)local); + tasklet_init(&local->tasklet, ieee80211_tasklet_handler, (unsigned long) local); @@ -1154,6 +1171,51 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) goto fail_rate; } + if (local->rate_ctrl) { + clear_bit(IEEE80211_HW_SUPPORTS_VHT_EXT_NSS_BW, hw->flags); + if (local->rate_ctrl->ops->capa & RATE_CTRL_CAPA_VHT_EXT_NSS_BW) + ieee80211_hw_set(hw, SUPPORTS_VHT_EXT_NSS_BW); + } + + /* + * If the VHT capabilities don't have IEEE80211_VHT_EXT_NSS_BW_CAPABLE, + * or have it when we don't, copy the sband structure and set/clear it. + * This is necessary because rate scaling algorithms could be switched + * and have different support values. + * Print a message so that in the common case the reallocation can be + * avoided. + */ + BUILD_BUG_ON(NUM_NL80211_BANDS > 8 * sizeof(local->sband_allocated)); + for (band = 0; band < NUM_NL80211_BANDS; band++) { + struct ieee80211_supported_band *sband; + bool local_cap, ie_cap; + + local_cap = ieee80211_hw_check(hw, SUPPORTS_VHT_EXT_NSS_BW); + + sband = local->hw.wiphy->bands[band]; + if (!sband || !sband->vht_cap.vht_supported) + continue; + + ie_cap = !!(sband->vht_cap.vht_mcs.tx_highest & + cpu_to_le16(IEEE80211_VHT_EXT_NSS_BW_CAPABLE)); + + if (local_cap == ie_cap) + continue; + + sband = kmemdup(sband, sizeof(*sband), GFP_KERNEL); + if (!sband) + goto fail_rate; + + wiphy_dbg(hw->wiphy, "copying sband (band %d) due to VHT EXT NSS BW flag\n", + band); + + sband->vht_cap.vht_mcs.tx_highest ^= + cpu_to_le16(IEEE80211_VHT_EXT_NSS_BW_CAPABLE); + + local->hw.wiphy->bands[band] = sband; + local->sband_allocated |= BIT(band); + } + /* add one default STA interface if supported */ if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_STATION) && !ieee80211_hw_check(hw, NO_AUTO_VIF)) { @@ -1272,6 +1334,7 @@ static int ieee80211_free_ack_frame(int id, void *p, void *data) void ieee80211_free_hw(struct ieee80211_hw *hw) { struct ieee80211_local *local = hw_to_local(hw); + enum nl80211_band band; mutex_destroy(&local->iflist_mtx); mutex_destroy(&local->mtx); @@ -1287,6 +1350,12 @@ void ieee80211_free_hw(struct ieee80211_hw *hw) ieee80211_free_led_names(local); + for (band = 0; band < NUM_NL80211_BANDS; band++) { + if (!(local->sband_allocated & BIT(band))) + continue; + kfree(local->hw.wiphy->bands[band]); + } + wiphy_free(local->hw.wiphy); } EXPORT_SYMBOL(ieee80211_free_hw); diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index d51da26e9c18..8bad414c52ad 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -1,5 +1,6 @@ /* * Copyright (c) 2008, 2009 open80211s Ltd. + * Copyright (C) 2018 Intel Corporation * Authors: Luis Carlos Cobo <luisca@cozybit.com> * Javier Cardona <javier@cozybit.com> * @@ -98,7 +99,9 @@ bool mesh_matches_local(struct ieee80211_sub_if_data *sdata, cfg80211_chandef_create(&sta_chan_def, sdata->vif.bss_conf.chandef.chan, NL80211_CHAN_NO_HT); ieee80211_chandef_ht_oper(ie->ht_operation, &sta_chan_def); - ieee80211_chandef_vht_oper(ie->vht_operation, &sta_chan_def); + ieee80211_chandef_vht_oper(&sdata->local->hw, + ie->vht_operation, ie->ht_operation, + &sta_chan_def); if (!cfg80211_chandef_compatible(&sdata->vif.bss_conf.chandef, &sta_chan_def)) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 3dbecae4be73..89dac799a85f 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -220,7 +220,8 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, memcpy(&he_oper_vht_cap, he_oper->optional, 3); he_oper_vht_cap.basic_mcs_set = cpu_to_le16(0); - if (!ieee80211_chandef_vht_oper(&he_oper_vht_cap, + if (!ieee80211_chandef_vht_oper(&sdata->local->hw, + &he_oper_vht_cap, ht_oper, &vht_chandef)) { if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE)) sdata_info(sdata, @@ -228,7 +229,8 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, ret = IEEE80211_STA_DISABLE_HE; goto out; } - } else if (!ieee80211_chandef_vht_oper(vht_oper, &vht_chandef)) { + } else if (!ieee80211_chandef_vht_oper(&sdata->local->hw, vht_oper, + ht_oper, &vht_chandef)) { if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT)) sdata_info(sdata, "AP VHT information is invalid, disable VHT\n"); @@ -3237,19 +3239,16 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, } if (bss_conf->he_support) { - u32 he_oper_params = - le32_to_cpu(elems.he_operation->he_oper_params); + bss_conf->bss_color = + le32_get_bits(elems.he_operation->he_oper_params, + IEEE80211_HE_OPERATION_BSS_COLOR_MASK); - bss_conf->bss_color = he_oper_params & - IEEE80211_HE_OPERATION_BSS_COLOR_MASK; bss_conf->htc_trig_based_pkt_ext = - (he_oper_params & - IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK) << - IEEE80211_HE_OPERATION_DFLT_PE_DURATION_OFFSET; + le32_get_bits(elems.he_operation->he_oper_params, + IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK); bss_conf->frame_time_rts_th = - (he_oper_params & - IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK) << - IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET; + le32_get_bits(elems.he_operation->he_oper_params, + IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK); bss_conf->multi_sta_back_32bit = sta->sta.he_cap.he_cap_elem.mac_cap_info[2] & diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 96611d5dfadb..a0ca27aeb732 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -115,7 +115,8 @@ static inline bool should_drop_frame(struct sk_buff *skb, int present_fcs_len, if (status->flag & (RX_FLAG_FAILED_FCS_CRC | RX_FLAG_FAILED_PLCP_CRC | - RX_FLAG_ONLY_MONITOR)) + RX_FLAG_ONLY_MONITOR | + RX_FLAG_NO_PSDU)) return true; if (unlikely(skb->len < 16 + present_fcs_len + rtap_space)) @@ -189,6 +190,15 @@ ieee80211_rx_radiotap_hdrlen(struct ieee80211_local *local, BUILD_BUG_ON(sizeof(struct ieee80211_radiotap_he_mu) != 12); } + if (status->flag & RX_FLAG_NO_PSDU) + len += 1; + + if (status->flag & RX_FLAG_RADIOTAP_LSIG) { + len = ALIGN(len, 2); + len += 4; + BUILD_BUG_ON(sizeof(struct ieee80211_radiotap_lsig) != 4); + } + if (status->chains) { /* antenna and antenna signal fields */ len += 2 * hweight8(status->chains); @@ -279,6 +289,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, struct ieee80211_vendor_radiotap rtap = {}; struct ieee80211_radiotap_he he = {}; struct ieee80211_radiotap_he_mu he_mu = {}; + struct ieee80211_radiotap_lsig lsig = {}; if (status->flag & RX_FLAG_RADIOTAP_HE) { he = *(struct ieee80211_radiotap_he *)skb->data; @@ -291,6 +302,11 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, skb_pull(skb, sizeof(he_mu)); } + if (status->flag & RX_FLAG_RADIOTAP_LSIG) { + lsig = *(struct ieee80211_radiotap_lsig *)skb->data; + skb_pull(skb, sizeof(lsig)); + } + if (status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA) { rtap = *(struct ieee80211_vendor_radiotap *)skb->data; /* rtap.len and rtap.pad are undone immediately */ @@ -549,7 +565,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, if (status->encoding == RX_ENC_HE && status->flag & RX_FLAG_RADIOTAP_HE) { -#define HE_PREP(f, val) cpu_to_le16(FIELD_PREP(IEEE80211_RADIOTAP_HE_##f, val)) +#define HE_PREP(f, val) le16_encode_bits(val, IEEE80211_RADIOTAP_HE_##f) if (status->enc_flags & RX_ENC_FLAG_STBC_MASK) { he.data6 |= HE_PREP(DATA6_NSTS, @@ -630,6 +646,21 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, pos += sizeof(he_mu); } + if (status->flag & RX_FLAG_NO_PSDU) { + rthdr->it_present |= + cpu_to_le32(1 << IEEE80211_RADIOTAP_ZERO_LEN_PSDU); + *pos++ = status->zero_length_psdu_type; + } + + if (status->flag & RX_FLAG_RADIOTAP_LSIG) { + /* ensure 2 byte alignment */ + while ((pos - (u8 *)rthdr) & 1) + pos++; + rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_LSIG); + memcpy(pos, &lsig, sizeof(lsig)); + pos += sizeof(lsig); + } + for_each_set_bit(chain, &chains, IEEE80211_MAX_CHAINS) { *pos++ = status->chain_signal[chain]; *pos++ = chain; @@ -1505,7 +1536,7 @@ static void sta_ps_start(struct sta_info *sta) if (!sta->sta.txq[0]) return; - for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) { + for (tid = 0; tid < IEEE80211_NUM_TIDS; tid++) { if (txq_has_queue(sta->sta.txq[tid])) set_bit(tid, &sta->txq_buffered_tids); else @@ -2046,6 +2077,7 @@ ieee80211_reassemble_find(struct ieee80211_sub_if_data *sdata, idx = sdata->fragment_next; for (i = 0; i < IEEE80211_FRAGMENT_MAX; i++) { struct ieee80211_hdr *f_hdr; + struct sk_buff *f_skb; idx--; if (idx < 0) @@ -2057,7 +2089,8 @@ ieee80211_reassemble_find(struct ieee80211_sub_if_data *sdata, entry->last_frag + 1 != frag) continue; - f_hdr = (struct ieee80211_hdr *)entry->skb_list.next->data; + f_skb = __skb_peek(&entry->skb_list); + f_hdr = (struct ieee80211_hdr *) f_skb->data; /* * Check ftype and addresses are equal, else check next fragment @@ -2314,7 +2347,7 @@ __ieee80211_data_to_8023(struct ieee80211_rx_data *rx, bool *port_control) if (!sdata->u.mgd.use_4addr) return -1; - else + else if (!ether_addr_equal(hdr->addr1, sdata->vif.addr)) check_port_control = true; } diff --git a/net/mac80211/spectmgmt.c b/net/mac80211/spectmgmt.c index 029334835747..4e4902bdbef8 100644 --- a/net/mac80211/spectmgmt.c +++ b/net/mac80211/spectmgmt.c @@ -144,6 +144,7 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, wide_bw_chansw_ie->new_center_freq_seg1, /* .basic_mcs_set doesn't matter */ }; + struct ieee80211_ht_operation ht_oper = {}; /* default, for the case of IEEE80211_VHT_CHANWIDTH_USE_HT, * to the previously parsed chandef @@ -151,7 +152,9 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, new_vht_chandef = csa_ie->chandef; /* ignore if parsing fails */ - if (!ieee80211_chandef_vht_oper(&vht_oper, &new_vht_chandef)) + if (!ieee80211_chandef_vht_oper(&sdata->local->hw, + &vht_oper, &ht_oper, + &new_vht_chandef)) new_vht_chandef.chan = NULL; if (sta_flags & IEEE80211_STA_DISABLE_80P80MHZ && diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index f34202242d24..fb8c2252ac0e 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -113,7 +113,12 @@ static void __cleanup_single_sta(struct sta_info *sta) if (sta->sta.txq[0]) { for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { - struct txq_info *txqi = to_txq_info(sta->sta.txq[i]); + struct txq_info *txqi; + + if (!sta->sta.txq[i]) + continue; + + txqi = to_txq_info(sta->sta.txq[i]); spin_lock_bh(&fq->lock); ieee80211_txq_purge(local, txqi); @@ -374,6 +379,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { struct txq_info *txq = txq_data + i * size; + /* might not do anything for the bufferable MMPDU TXQ */ ieee80211_txq_init(sdata, sta, txq, i); } } @@ -1239,13 +1245,11 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) if (!ieee80211_hw_check(&local->hw, AP_LINK_PS)) drv_sta_notify(local, sdata, STA_NOTIFY_AWAKE, &sta->sta); - if (sta->sta.txq[0]) { - for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { - if (!txq_has_queue(sta->sta.txq[i])) - continue; + for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { + if (!sta->sta.txq[i] || !txq_has_queue(sta->sta.txq[i])) + continue; - drv_wake_tx_queue(local, to_txq_info(sta->sta.txq[i])); - } + drv_wake_tx_queue(local, to_txq_info(sta->sta.txq[i])); } skb_queue_head_init(&pending); @@ -1683,7 +1687,8 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, return; for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) { - if (!(driver_release_tids & BIT(tid)) || + if (!sta->sta.txq[tid] || + !(driver_release_tids & BIT(tid)) || txq_has_queue(sta->sta.txq[tid])) continue; @@ -2323,13 +2328,13 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, sinfo->filled |= BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL); } - if (ieee80211_hw_check(&sta->local->hw, REPORTS_TX_ACK_STATUS) && - !(sinfo->filled & BIT_ULL(NL80211_STA_INFO_DATA_ACK_SIGNAL_AVG))) { + if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL_AVG)) && + sta->status_stats.ack_signal_filled) { sinfo->avg_ack_signal = -(s8)ewma_avg_signal_read( &sta->status_stats.avg_ack_signal); sinfo->filled |= - BIT_ULL(NL80211_STA_INFO_DATA_ACK_SIGNAL_AVG); + BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL_AVG); } } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index f353d9db54bc..c42bfa1dcd2c 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1249,10 +1249,18 @@ static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local, (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE)) return NULL; - if (!ieee80211_is_data_present(hdr->frame_control)) - return NULL; - - if (sta) { + if (unlikely(!ieee80211_is_data_present(hdr->frame_control))) { + if ((!ieee80211_is_mgmt(hdr->frame_control) || + ieee80211_is_bufferable_mmpdu(hdr->frame_control) || + vif->type == NL80211_IFTYPE_STATION) && + sta && sta->uploaded) { + /* + * This will be NULL if the driver didn't set the + * opt-in hardware flag. + */ + txq = sta->sta.txq[IEEE80211_NUM_TIDS]; + } + } else if (sta) { u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK; if (!sta->uploaded) @@ -1440,16 +1448,33 @@ void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata, txqi->txq.vif = &sdata->vif; - if (sta) { - txqi->txq.sta = &sta->sta; - sta->sta.txq[tid] = &txqi->txq; - txqi->txq.tid = tid; - txqi->txq.ac = ieee80211_ac_from_tid(tid); - } else { + if (!sta) { sdata->vif.txq = &txqi->txq; txqi->txq.tid = 0; txqi->txq.ac = IEEE80211_AC_BE; + + return; + } + + if (tid == IEEE80211_NUM_TIDS) { + if (sdata->vif.type == NL80211_IFTYPE_STATION) { + /* Drivers need to opt in to the management MPDU TXQ */ + if (!ieee80211_hw_check(&sdata->local->hw, + STA_MMPDU_TXQ)) + return; + } else if (!ieee80211_hw_check(&sdata->local->hw, + BUFF_MMPDU_TXQ)) { + /* Drivers need to opt in to the bufferable MMPDU TXQ */ + return; + } + txqi->txq.ac = IEEE80211_AC_VO; + } else { + txqi->txq.ac = ieee80211_ac_from_tid(tid); } + + txqi->txq.sta = &sta->sta; + txqi->txq.tid = tid; + sta->sta.txq[tid] = &txqi->txq; } void ieee80211_txq_purge(struct ieee80211_local *local, @@ -2951,6 +2976,10 @@ void ieee80211_check_fast_xmit(struct sta_info *sta) if (!(build.key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) goto out; + /* Key is being removed */ + if (build.key->flags & KEY_FLAG_TAINTED) + goto out; + switch (build.key->conf.cipher) { case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: @@ -3196,6 +3225,10 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, max_amsdu_len = min_t(int, max_amsdu_len, sta->sta.max_rc_amsdu_len); + if (sta->sta.max_tid_amsdu_len[tid]) + max_amsdu_len = min_t(int, max_amsdu_len, + sta->sta.max_tid_amsdu_len[tid]); + spin_lock_bh(&fq->lock); /* TODO: Ideally aggregation should be done on dequeue to remain @@ -3228,6 +3261,9 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, if (max_frags && nfrags > max_frags) goto out; + if (!drv_can_aggregate_in_amsdu(local, head, skb)) + goto out; + if (!ieee80211_amsdu_prepare_head(sdata, fast_tx, head)) goto out; @@ -3472,13 +3508,19 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, struct ieee80211_tx_info *info; struct ieee80211_tx_data tx; ieee80211_tx_result r; - struct ieee80211_vif *vif; + struct ieee80211_vif *vif = txq->vif; spin_lock_bh(&fq->lock); - if (test_bit(IEEE80211_TXQ_STOP, &txqi->flags)) + if (test_bit(IEEE80211_TXQ_STOP, &txqi->flags) || + test_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags)) goto out; + if (vif->txqs_stopped[ieee80211_ac_from_tid(txq->tid)]) { + set_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags); + goto out; + } + /* Make sure fragments stay together. */ skb = __skb_dequeue(&txqi->frags); if (skb) @@ -3573,6 +3615,7 @@ begin: } IEEE80211_SKB_CB(skb)->control.vif = vif; + out: spin_unlock_bh(&fq->lock); @@ -3601,13 +3644,7 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, if (!IS_ERR_OR_NULL(sta)) { struct ieee80211_fast_tx *fast_tx; - /* We need a bit of data queued to build aggregates properly, so - * instruct the TCP stack to allow more than a single ms of data - * to be queued in the stack. The value is a bit-shift of 1 - * second, so 8 is ~4ms of queued data. Only affects local TCP - * sockets. - */ - sk_pacing_shift_update(skb->sk, 8); + sk_pacing_shift_update(skb->sk, sdata->local->hw.tx_sk_pacing_shift); fast_tx = rcu_dereference(sta->fast_tx); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 716cd6442d86..36a3c2ada515 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -240,6 +240,99 @@ __le16 ieee80211_ctstoself_duration(struct ieee80211_hw *hw, } EXPORT_SYMBOL(ieee80211_ctstoself_duration); +static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_vif *vif = &sdata->vif; + struct fq *fq = &local->fq; + struct ps_data *ps = NULL; + struct txq_info *txqi; + struct sta_info *sta; + int i; + + spin_lock_bh(&fq->lock); + + if (sdata->vif.type == NL80211_IFTYPE_AP) + ps = &sdata->bss->ps; + + sdata->vif.txqs_stopped[ac] = false; + + list_for_each_entry_rcu(sta, &local->sta_list, list) { + if (sdata != sta->sdata) + continue; + + for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { + struct ieee80211_txq *txq = sta->sta.txq[i]; + + txqi = to_txq_info(txq); + + if (ac != txq->ac) + continue; + + if (!test_and_clear_bit(IEEE80211_TXQ_STOP_NETIF_TX, + &txqi->flags)) + continue; + + spin_unlock_bh(&fq->lock); + drv_wake_tx_queue(local, txqi); + spin_lock_bh(&fq->lock); + } + } + + if (!vif->txq) + goto out; + + txqi = to_txq_info(vif->txq); + + if (!test_and_clear_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags) || + (ps && atomic_read(&ps->num_sta_ps)) || ac != vif->txq->ac) + goto out; + + spin_unlock_bh(&fq->lock); + + drv_wake_tx_queue(local, txqi); + return; +out: + spin_unlock_bh(&fq->lock); +} + +void ieee80211_wake_txqs(unsigned long data) +{ + struct ieee80211_local *local = (struct ieee80211_local *)data; + struct ieee80211_sub_if_data *sdata; + int n_acs = IEEE80211_NUM_ACS; + unsigned long flags; + int i; + + rcu_read_lock(); + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); + + if (local->hw.queues < IEEE80211_NUM_ACS) + n_acs = 1; + + for (i = 0; i < local->hw.queues; i++) { + if (local->queue_stop_reasons[i]) + continue; + + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + list_for_each_entry_rcu(sdata, &local->interfaces, list) { + int ac; + + for (ac = 0; ac < n_acs; ac++) { + int ac_queue = sdata->vif.hw_queue[ac]; + + if (ac_queue == i || + sdata->vif.cab_queue == i) + __ieee80211_wake_txqs(sdata, ac); + } + } + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); + } + + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + rcu_read_unlock(); +} + void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue) { struct ieee80211_sub_if_data *sdata; @@ -308,6 +401,9 @@ static void __ieee80211_wake_queue(struct ieee80211_hw *hw, int queue, rcu_read_unlock(); } else tasklet_schedule(&local->tx_pending_tasklet); + + if (local->ops->wake_tx_queue) + tasklet_schedule(&local->wake_txqs_tasklet); } void ieee80211_wake_queue_by_reason(struct ieee80211_hw *hw, int queue, @@ -351,9 +447,6 @@ static void __ieee80211_stop_queue(struct ieee80211_hw *hw, int queue, if (__test_and_set_bit(reason, &local->queue_stop_reasons[queue])) return; - if (local->ops->wake_tx_queue) - return; - if (local->hw.queues < IEEE80211_NUM_ACS) n_acs = 1; @@ -366,8 +459,15 @@ static void __ieee80211_stop_queue(struct ieee80211_hw *hw, int queue, for (ac = 0; ac < n_acs; ac++) { if (sdata->vif.hw_queue[ac] == queue || - sdata->vif.cab_queue == queue) - netif_stop_subqueue(sdata->dev, ac); + sdata->vif.cab_queue == queue) { + if (!local->ops->wake_tx_queue) { + netif_stop_subqueue(sdata->dev, ac); + continue; + } + spin_lock(&local->fq.lock); + sdata->vif.txqs_stopped[ac] = true; + spin_unlock(&local->fq.lock); + } } } rcu_read_unlock(); @@ -2657,49 +2757,65 @@ bool ieee80211_chandef_ht_oper(const struct ieee80211_ht_operation *ht_oper, return true; } -bool ieee80211_chandef_vht_oper(const struct ieee80211_vht_operation *oper, +bool ieee80211_chandef_vht_oper(struct ieee80211_hw *hw, + const struct ieee80211_vht_operation *oper, + const struct ieee80211_ht_operation *htop, struct cfg80211_chan_def *chandef) { struct cfg80211_chan_def new = *chandef; - int cf1, cf2; + int cf0, cf1; + int ccfs0, ccfs1, ccfs2; + int ccf0, ccf1; - if (!oper) + if (!oper || !htop) return false; - cf1 = ieee80211_channel_to_frequency(oper->center_freq_seg0_idx, - chandef->chan->band); - cf2 = ieee80211_channel_to_frequency(oper->center_freq_seg1_idx, - chandef->chan->band); + ccfs0 = oper->center_freq_seg0_idx; + ccfs1 = oper->center_freq_seg1_idx; + ccfs2 = (le16_to_cpu(htop->operation_mode) & + IEEE80211_HT_OP_MODE_CCFS2_MASK) + >> IEEE80211_HT_OP_MODE_CCFS2_SHIFT; + + /* when parsing (and we know how to) CCFS1 and CCFS2 are equivalent */ + ccf0 = ccfs0; + ccf1 = ccfs1; + if (!ccfs1 && ieee80211_hw_check(hw, SUPPORTS_VHT_EXT_NSS_BW)) + ccf1 = ccfs2; + + cf0 = ieee80211_channel_to_frequency(ccf0, chandef->chan->band); + cf1 = ieee80211_channel_to_frequency(ccf1, chandef->chan->band); switch (oper->chan_width) { case IEEE80211_VHT_CHANWIDTH_USE_HT: + /* just use HT information directly */ break; case IEEE80211_VHT_CHANWIDTH_80MHZ: new.width = NL80211_CHAN_WIDTH_80; - new.center_freq1 = cf1; + new.center_freq1 = cf0; /* If needed, adjust based on the newer interop workaround. */ - if (oper->center_freq_seg1_idx) { + if (ccf1) { unsigned int diff; - diff = abs(oper->center_freq_seg1_idx - - oper->center_freq_seg0_idx); + diff = abs(ccf1 - ccf0); if (diff == 8) { new.width = NL80211_CHAN_WIDTH_160; - new.center_freq1 = cf2; + new.center_freq1 = cf1; } else if (diff > 8) { new.width = NL80211_CHAN_WIDTH_80P80; - new.center_freq2 = cf2; + new.center_freq2 = cf1; } } break; case IEEE80211_VHT_CHANWIDTH_160MHZ: + /* deprecated encoding */ new.width = NL80211_CHAN_WIDTH_160; - new.center_freq1 = cf1; + new.center_freq1 = cf0; break; case IEEE80211_VHT_CHANWIDTH_80P80MHZ: + /* deprecated encoding */ new.width = NL80211_CHAN_WIDTH_80P80; - new.center_freq1 = cf1; - new.center_freq2 = cf2; + new.center_freq1 = cf0; + new.center_freq2 = cf1; break; default: return false; diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index 259325cbcc31..006d82e4a397 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -3,6 +3,7 @@ * * Portions of this file * Copyright(c) 2015 - 2016 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -231,6 +232,13 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, memcpy(&vht_cap->vht_mcs, &vht_cap_ie->supp_mcs, sizeof(struct ieee80211_vht_mcs_info)); + /* copy EXT_NSS_BW Support value or remove the capability */ + if (ieee80211_hw_check(&sdata->local->hw, SUPPORTS_VHT_EXT_NSS_BW)) + vht_cap->cap |= (cap_info & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK); + else + vht_cap->vht_mcs.tx_highest &= + ~cpu_to_le16(IEEE80211_VHT_EXT_NSS_BW_CAPABLE); + /* but also restrict MCSes */ for (i = 0; i < 8; i++) { u16 own_rx, own_tx, peer_rx, peer_tx; @@ -294,6 +302,18 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, break; default: sta->cur_max_bandwidth = IEEE80211_STA_RX_BW_80; + + if (!(vht_cap->vht_mcs.tx_highest & + cpu_to_le16(IEEE80211_VHT_EXT_NSS_BW_CAPABLE))) + break; + + /* + * If this is non-zero, then it does support 160 MHz after all, + * in one form or the other. We don't distinguish here (or even + * above) between 160 and 80+80 yet. + */ + if (cap_info & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) + sta->cur_max_bandwidth = IEEE80211_STA_RX_BW_160; } sta->sta.bandwidth = ieee80211_sta_cur_vht_bw(sta); diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index 45f33d6dedf7..32cb7751d216 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -12,7 +12,6 @@ #include <linux/if_arp.h> #include <linux/rtnetlink.h> #include <linux/etherdevice.h> -#include <linux/module.h> #include <net/genetlink.h> #include <net/ncsi.h> #include <linux/skbuff.h> diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index d33094f4ec41..43041f087eb3 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -765,7 +765,7 @@ __nfqnl_enqueue_packet_gso(struct net *net, struct nfqnl_instance *queue, return ret; } - skb->next = NULL; + skb_mark_not_on_list(skb); entry_seg = nf_queue_entry_dup(entry); if (entry_seg) { diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 930d17fa906c..e3a0538ec0be 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -574,11 +574,6 @@ static int netlink_insert(struct sock *sk, u32 portid) if (nlk_sk(sk)->bound) goto err; - err = -ENOMEM; - if (BITS_PER_LONG > 32 && - unlikely(atomic_read(&table->hash.nelems) >= UINT_MAX)) - goto err; - nlk_sk(sk)->portid = portid; sock_hold(sk); @@ -993,7 +988,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, struct netlink_sock *nlk = nlk_sk(sk); struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; int err = 0; - long unsigned int groups = nladdr->nl_groups; + unsigned long groups = nladdr->nl_groups; bool bound; if (addr_len < sizeof(struct sockaddr_nl)) @@ -1011,9 +1006,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, return err; } - if (nlk->ngroups == 0) - groups = 0; - else if (nlk->ngroups < 8*sizeof(groups)) + if (nlk->ngroups < BITS_PER_LONG) groups &= (1UL << nlk->ngroups) - 1; bound = nlk->bound; diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 56b8e7167790..35966da84769 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -254,21 +254,18 @@ static bool icmphdr_ok(struct sk_buff *skb) static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key) { + unsigned short frag_off; + unsigned int payload_ofs = 0; unsigned int nh_ofs = skb_network_offset(skb); unsigned int nh_len; - int payload_ofs; struct ipv6hdr *nh; - uint8_t nexthdr; - __be16 frag_off; - int err; + int err, nexthdr, flags = 0; err = check_header(skb, nh_ofs + sizeof(*nh)); if (unlikely(err)) return err; nh = ipv6_hdr(skb); - nexthdr = nh->nexthdr; - payload_ofs = (u8 *)(nh + 1) - skb->data; key->ip.proto = NEXTHDR_NONE; key->ip.tos = ipv6_get_dsfield(nh); @@ -277,10 +274,9 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key) key->ipv6.addr.src = nh->saddr; key->ipv6.addr.dst = nh->daddr; - payload_ofs = ipv6_skip_exthdr(skb, payload_ofs, &nexthdr, &frag_off); - - if (frag_off) { - if (frag_off & htons(~0x7)) + nexthdr = ipv6_find_hdr(skb, &payload_ofs, -1, &frag_off, &flags); + if (flags & IP6_FH_F_FRAG) { + if (frag_off) key->ip.frag = OVS_FRAG_TYPE_LATER; else key->ip.frag = OVS_FRAG_TYPE_FIRST; @@ -288,11 +284,11 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key) key->ip.frag = OVS_FRAG_TYPE_NONE; } - /* Delayed handling of error in ipv6_skip_exthdr() as it - * always sets frag_off to a valid value which may be + /* Delayed handling of error in ipv6_find_hdr() as it + * always sets flags and frag_off to a valid value which may be * used to set key->ip.frag above. */ - if (unlikely(payload_ofs < 0)) + if (unlikely(nexthdr < 0)) return -EPROTO; nh_len = payload_ofs - nh_ofs; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 75c92a87e7b2..f85f67b5c1f4 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3805,6 +3805,20 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv return fanout_set_data(po, optval, optlen); } + case PACKET_IGNORE_OUTGOING: + { + int val; + + if (optlen != sizeof(val)) + return -EINVAL; + if (copy_from_user(&val, optval, sizeof(val))) + return -EFAULT; + if (val < 0 || val > 1) + return -EINVAL; + + po->prot_hook.ignore_outgoing = !!val; + return 0; + } case PACKET_TX_HAS_OFF: { unsigned int val; @@ -3928,6 +3942,9 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, ((u32)po->fanout->flags << 24)) : 0); break; + case PACKET_IGNORE_OUTGOING: + val = po->prot_hook.ignore_outgoing; + break; case PACKET_ROLLOVER_STATS: if (!po->rollover) return -EINVAL; diff --git a/net/rds/rds.h b/net/rds/rds.h index c4dcf654d8fe..6bfaf05b63b2 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -278,7 +278,7 @@ struct rds_incoming { struct in6_addr i_saddr; rds_rdma_cookie_t i_rdma_cookie; - struct timeval i_rx_tstamp; + ktime_t i_rx_tstamp; u64 i_rx_lat_trace[RDS_RX_MAX_TRACES]; }; diff --git a/net/rds/recv.c b/net/rds/recv.c index 504cd6bcc54c..727639dac8a7 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -43,18 +43,14 @@ void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn, struct in6_addr *saddr) { - int i; - refcount_set(&inc->i_refcount, 1); INIT_LIST_HEAD(&inc->i_item); inc->i_conn = conn; inc->i_saddr = *saddr; inc->i_rdma_cookie = 0; - inc->i_rx_tstamp.tv_sec = 0; - inc->i_rx_tstamp.tv_usec = 0; + inc->i_rx_tstamp = ktime_set(0, 0); - for (i = 0; i < RDS_RX_MAX_TRACES; i++) - inc->i_rx_lat_trace[i] = 0; + memset(inc->i_rx_lat_trace, 0, sizeof(inc->i_rx_lat_trace)); } EXPORT_SYMBOL_GPL(rds_inc_init); @@ -67,8 +63,7 @@ void rds_inc_path_init(struct rds_incoming *inc, struct rds_conn_path *cp, inc->i_conn_path = cp; inc->i_saddr = *saddr; inc->i_rdma_cookie = 0; - inc->i_rx_tstamp.tv_sec = 0; - inc->i_rx_tstamp.tv_usec = 0; + inc->i_rx_tstamp = ktime_set(0, 0); } EXPORT_SYMBOL_GPL(rds_inc_path_init); @@ -385,7 +380,7 @@ void rds_recv_incoming(struct rds_connection *conn, struct in6_addr *saddr, be32_to_cpu(inc->i_hdr.h_len), inc->i_hdr.h_dport); if (sock_flag(sk, SOCK_RCVTSTAMP)) - do_gettimeofday(&inc->i_rx_tstamp); + inc->i_rx_tstamp = ktime_get_real(); rds_inc_addref(inc); inc->i_rx_lat_trace[RDS_MSG_RX_END] = local_clock(); list_add_tail(&inc->i_item, &rs->rs_recv_queue); @@ -552,11 +547,11 @@ static int rds_cmsg_recv(struct rds_incoming *inc, struct msghdr *msg, goto out; } - if ((inc->i_rx_tstamp.tv_sec != 0) && + if ((inc->i_rx_tstamp != 0) && sock_flag(rds_rs_to_sk(rs), SOCK_RCVTSTAMP)) { + struct timeval tv = ktime_to_timeval(inc->i_rx_tstamp); ret = put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMP, - sizeof(struct timeval), - &inc->i_rx_tstamp); + sizeof(tv), &tv); if (ret) goto out; } diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 1355f5ca8d22..abca57040f37 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -510,8 +510,8 @@ void rfkill_remove_epo_lock(void) /** * rfkill_is_epo_lock_active - returns true EPO is active * - * Returns 0 (false) if there is NOT an active EPO contidion, - * and 1 (true) if there is an active EPO contition, which + * Returns 0 (false) if there is NOT an active EPO condition, + * and 1 (true) if there is an active EPO condition, which * locks all radios in one of the BLOCKED states. * * Can be called in atomic context. diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index cfdc199c6351..ee8e7e1d5c0f 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -259,7 +259,7 @@ static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, while (list) { skb = list; list = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); rxrpc_free_skb(skb, rxrpc_skb_tx_freed); } } diff --git a/net/sched/act_api.c b/net/sched/act_api.c index e12f8ef7baa4..6f118d62c731 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -1073,12 +1073,14 @@ static struct tc_action *tcf_action_get_1(struct net *net, struct nlattr *nla, err = -EINVAL; ops = tc_lookup_action(tb[TCA_ACT_KIND]); if (!ops) { /* could happen in batch of actions */ - NL_SET_ERR_MSG(extack, "Specified TC action not found"); + NL_SET_ERR_MSG(extack, "Specified TC action kind not found"); goto err_out; } err = -ENOENT; - if (ops->lookup(net, &a, index, extack) == 0) + if (ops->lookup(net, &a, index) == 0) { + NL_SET_ERR_MSG(extack, "TC action with specified index not found"); goto err_mod; + } module_put(ops->owner); return a; diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 0c68bc9cf0b4..c7633843e223 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -387,8 +387,7 @@ static int tcf_bpf_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, bpf_net_id); diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 6f0f273f1139..8475913f2070 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -143,8 +143,10 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, return -EEXIST; } /* replacing action and zone */ + spin_lock_bh(&ci->tcf_lock); ci->tcf_action = parm->action; ci->zone = parm->zone; + spin_unlock_bh(&ci->tcf_lock); ret = 0; } @@ -156,16 +158,16 @@ static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a, { unsigned char *b = skb_tail_pointer(skb); struct tcf_connmark_info *ci = to_connmark(a); - struct tc_connmark opt = { .index = ci->tcf_index, .refcnt = refcount_read(&ci->tcf_refcnt) - ref, .bindcnt = atomic_read(&ci->tcf_bindcnt) - bind, - .action = ci->tcf_action, - .zone = ci->zone, }; struct tcf_t t; + spin_lock_bh(&ci->tcf_lock); + opt.action = ci->tcf_action; + opt.zone = ci->zone; if (nla_put(skb, TCA_CONNMARK_PARMS, sizeof(opt), &opt)) goto nla_put_failure; @@ -173,9 +175,12 @@ static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a, if (nla_put_64bit(skb, TCA_CONNMARK_TM, sizeof(t), &t, TCA_CONNMARK_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; } @@ -190,8 +195,7 @@ static int tcf_connmark_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, connmark_net_id); diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index b8a67ae3105a..3dc25b7806d7 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -646,8 +646,7 @@ static int tcf_csum_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_csum_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_csum_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, csum_net_id); diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index cd1d9bd32ef9..aa44d14b43c7 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -222,8 +222,7 @@ static int tcf_gact_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_gact_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_gact_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, gact_net_id); diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 06a3d4801878..30b63fa23ee2 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -855,8 +855,7 @@ static int tcf_ife_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, ife_net_id); diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 23273b5303fd..1efbfb10b1fc 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -329,8 +329,7 @@ static int tcf_ipt_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_ipt_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_ipt_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, ipt_net_id); @@ -379,8 +378,7 @@ static int tcf_xt_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_xt_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_xt_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, xt_net_id); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 8bf66d0a6800..a9d64bfe5a2a 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -338,8 +338,7 @@ static int tcf_mirred_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_mirred_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_mirred_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, mirred_net_id); diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 4313aa102440..c5c1e23add77 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -256,28 +256,31 @@ static int tcf_nat_dump(struct sk_buff *skb, struct tc_action *a, unsigned char *b = skb_tail_pointer(skb); struct tcf_nat *p = to_tcf_nat(a); struct tc_nat opt = { - .old_addr = p->old_addr, - .new_addr = p->new_addr, - .mask = p->mask, - .flags = p->flags, - .index = p->tcf_index, - .action = p->tcf_action, .refcnt = refcount_read(&p->tcf_refcnt) - ref, .bindcnt = atomic_read(&p->tcf_bindcnt) - bind, }; struct tcf_t t; + spin_lock_bh(&p->tcf_lock); + opt.old_addr = p->old_addr; + opt.new_addr = p->new_addr; + opt.mask = p->mask; + opt.flags = p->flags; + opt.action = p->tcf_action; + if (nla_put(skb, TCA_NAT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; tcf_tm_dump(&t, &p->tcf_tm); if (nla_put_64bit(skb, TCA_NAT_TM, sizeof(t), &t, TCA_NAT_PAD)) goto nla_put_failure; + spin_unlock_bh(&p->tcf_lock); return skb->len; nla_put_failure: + spin_unlock_bh(&p->tcf_lock); nlmsg_trim(skb, b); return -1; } @@ -292,8 +295,7 @@ static int tcf_nat_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, nat_net_id); diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index ad99a99f11f6..da3dd0f68cc2 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -460,8 +460,7 @@ static int tcf_pedit_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, pedit_net_id); diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 5d8bfa878477..92649d2667ed 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -22,8 +22,7 @@ #include <net/act_api.h> #include <net/netlink.h> -struct tcf_police { - struct tc_action common; +struct tcf_police_params { int tcfp_result; u32 tcfp_ewma_rate; s64 tcfp_burst; @@ -36,6 +35,12 @@ struct tcf_police { bool rate_present; struct psched_ratecfg peak; bool peak_present; + struct rcu_head rcu; +}; + +struct tcf_police { + struct tc_action common; + struct tcf_police_params __rcu *params; }; #define to_police(pc) ((struct tcf_police *)pc) @@ -84,6 +89,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, struct tcf_police *police; struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL; struct tc_action_net *tn = net_generic(net, police_net_id); + struct tcf_police_params *new; bool exists = false; int size; @@ -110,7 +116,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, parm->index, NULL, a, - &act_police_ops, bind, false); + &act_police_ops, bind, true); if (ret) { tcf_idr_cleanup(tn, parm->index); return ret; @@ -137,7 +143,8 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, } if (est) { - err = gen_replace_estimator(&police->tcf_bstats, NULL, + err = gen_replace_estimator(&police->tcf_bstats, + police->common.cpu_bstats, &police->tcf_rate_est, &police->tcf_lock, NULL, est); @@ -150,50 +157,60 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, goto failure; } - spin_lock_bh(&police->tcf_lock); + new = kzalloc(sizeof(*new), GFP_KERNEL); + if (unlikely(!new)) { + err = -ENOMEM; + goto failure; + } + /* No failure allowed after this point */ - police->tcfp_mtu = parm->mtu; - if (police->tcfp_mtu == 0) { - police->tcfp_mtu = ~0; + new->tcfp_mtu = parm->mtu; + if (!new->tcfp_mtu) { + new->tcfp_mtu = ~0; if (R_tab) - police->tcfp_mtu = 255 << R_tab->rate.cell_log; + new->tcfp_mtu = 255 << R_tab->rate.cell_log; } if (R_tab) { - police->rate_present = true; - psched_ratecfg_precompute(&police->rate, &R_tab->rate, 0); + new->rate_present = true; + psched_ratecfg_precompute(&new->rate, &R_tab->rate, 0); qdisc_put_rtab(R_tab); } else { - police->rate_present = false; + new->rate_present = false; } if (P_tab) { - police->peak_present = true; - psched_ratecfg_precompute(&police->peak, &P_tab->rate, 0); + new->peak_present = true; + psched_ratecfg_precompute(&new->peak, &P_tab->rate, 0); qdisc_put_rtab(P_tab); } else { - police->peak_present = false; + new->peak_present = false; } if (tb[TCA_POLICE_RESULT]) - police->tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]); - police->tcfp_burst = PSCHED_TICKS2NS(parm->burst); - police->tcfp_toks = police->tcfp_burst; - if (police->peak_present) { - police->tcfp_mtu_ptoks = (s64) psched_l2t_ns(&police->peak, - police->tcfp_mtu); - police->tcfp_ptoks = police->tcfp_mtu_ptoks; + new->tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]); + new->tcfp_burst = PSCHED_TICKS2NS(parm->burst); + new->tcfp_toks = new->tcfp_burst; + if (new->peak_present) { + new->tcfp_mtu_ptoks = (s64)psched_l2t_ns(&new->peak, + new->tcfp_mtu); + new->tcfp_ptoks = new->tcfp_mtu_ptoks; } - police->tcf_action = parm->action; if (tb[TCA_POLICE_AVRATE]) - police->tcfp_ewma_rate = nla_get_u32(tb[TCA_POLICE_AVRATE]); + new->tcfp_ewma_rate = nla_get_u32(tb[TCA_POLICE_AVRATE]); + spin_lock_bh(&police->tcf_lock); + new->tcfp_t_c = ktime_get_ns(); + police->tcf_action = parm->action; + rcu_swap_protected(police->params, + new, + lockdep_is_held(&police->tcf_lock)); spin_unlock_bh(&police->tcf_lock); - if (ret != ACT_P_CREATED) - return ret; - police->tcfp_t_c = ktime_get_ns(); - tcf_idr_insert(tn, *a); + if (new) + kfree_rcu(new, rcu); + if (ret == ACT_P_CREATED) + tcf_idr_insert(tn, *a); return ret; failure: @@ -207,64 +224,69 @@ static int tcf_police_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_police *police = to_police(a); - s64 now; - s64 toks; - s64 ptoks = 0; - - spin_lock(&police->tcf_lock); + struct tcf_police_params *p; + s64 now, toks, ptoks = 0; + int ret; - bstats_update(&police->tcf_bstats, skb); tcf_lastuse_update(&police->tcf_tm); + bstats_cpu_update(this_cpu_ptr(police->common.cpu_bstats), skb); - if (police->tcfp_ewma_rate) { + ret = READ_ONCE(police->tcf_action); + p = rcu_dereference_bh(police->params); + + if (p->tcfp_ewma_rate) { struct gnet_stats_rate_est64 sample; if (!gen_estimator_read(&police->tcf_rate_est, &sample) || - sample.bps >= police->tcfp_ewma_rate) { - police->tcf_qstats.overlimits++; - if (police->tcf_action == TC_ACT_SHOT) - police->tcf_qstats.drops++; - spin_unlock(&police->tcf_lock); - return police->tcf_action; - } + sample.bps >= p->tcfp_ewma_rate) + goto inc_overlimits; } - if (qdisc_pkt_len(skb) <= police->tcfp_mtu) { - if (!police->rate_present) { - spin_unlock(&police->tcf_lock); - return police->tcfp_result; + if (qdisc_pkt_len(skb) <= p->tcfp_mtu) { + if (!p->rate_present) { + ret = p->tcfp_result; + goto end; } now = ktime_get_ns(); - toks = min_t(s64, now - police->tcfp_t_c, - police->tcfp_burst); - if (police->peak_present) { - ptoks = toks + police->tcfp_ptoks; - if (ptoks > police->tcfp_mtu_ptoks) - ptoks = police->tcfp_mtu_ptoks; - ptoks -= (s64) psched_l2t_ns(&police->peak, - qdisc_pkt_len(skb)); + toks = min_t(s64, now - p->tcfp_t_c, p->tcfp_burst); + if (p->peak_present) { + ptoks = toks + p->tcfp_ptoks; + if (ptoks > p->tcfp_mtu_ptoks) + ptoks = p->tcfp_mtu_ptoks; + ptoks -= (s64)psched_l2t_ns(&p->peak, + qdisc_pkt_len(skb)); } - toks += police->tcfp_toks; - if (toks > police->tcfp_burst) - toks = police->tcfp_burst; - toks -= (s64) psched_l2t_ns(&police->rate, qdisc_pkt_len(skb)); + toks += p->tcfp_toks; + if (toks > p->tcfp_burst) + toks = p->tcfp_burst; + toks -= (s64)psched_l2t_ns(&p->rate, qdisc_pkt_len(skb)); if ((toks|ptoks) >= 0) { - police->tcfp_t_c = now; - police->tcfp_toks = toks; - police->tcfp_ptoks = ptoks; - if (police->tcfp_result == TC_ACT_SHOT) - police->tcf_qstats.drops++; - spin_unlock(&police->tcf_lock); - return police->tcfp_result; + p->tcfp_t_c = now; + p->tcfp_toks = toks; + p->tcfp_ptoks = ptoks; + ret = p->tcfp_result; + goto inc_drops; } } - police->tcf_qstats.overlimits++; - if (police->tcf_action == TC_ACT_SHOT) - police->tcf_qstats.drops++; - spin_unlock(&police->tcf_lock); - return police->tcf_action; +inc_overlimits: + qstats_overlimit_inc(this_cpu_ptr(police->common.cpu_qstats)); +inc_drops: + if (ret == TC_ACT_SHOT) + qstats_drop_inc(this_cpu_ptr(police->common.cpu_qstats)); +end: + return ret; +} + +static void tcf_police_cleanup(struct tc_action *a) +{ + struct tcf_police *police = to_police(a); + struct tcf_police_params *p; + + p = rcu_dereference_protected(police->params, 1); + if (p) + kfree_rcu(p, rcu); } static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a, @@ -272,6 +294,7 @@ static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a, { unsigned char *b = skb_tail_pointer(skb); struct tcf_police *police = to_police(a); + struct tcf_police_params *p; struct tc_police opt = { .index = police->tcf_index, .refcnt = refcount_read(&police->tcf_refcnt) - ref, @@ -281,19 +304,21 @@ static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a, spin_lock_bh(&police->tcf_lock); opt.action = police->tcf_action; - opt.mtu = police->tcfp_mtu; - opt.burst = PSCHED_NS2TICKS(police->tcfp_burst); - if (police->rate_present) - psched_ratecfg_getrate(&opt.rate, &police->rate); - if (police->peak_present) - psched_ratecfg_getrate(&opt.peakrate, &police->peak); + p = rcu_dereference_protected(police->params, + lockdep_is_held(&police->tcf_lock)); + opt.mtu = p->tcfp_mtu; + opt.burst = PSCHED_NS2TICKS(p->tcfp_burst); + if (p->rate_present) + psched_ratecfg_getrate(&opt.rate, &p->rate); + if (p->peak_present) + psched_ratecfg_getrate(&opt.peakrate, &p->peak); if (nla_put(skb, TCA_POLICE_TBF, sizeof(opt), &opt)) goto nla_put_failure; - if (police->tcfp_result && - nla_put_u32(skb, TCA_POLICE_RESULT, police->tcfp_result)) + if (p->tcfp_result && + nla_put_u32(skb, TCA_POLICE_RESULT, p->tcfp_result)) goto nla_put_failure; - if (police->tcfp_ewma_rate && - nla_put_u32(skb, TCA_POLICE_AVRATE, police->tcfp_ewma_rate)) + if (p->tcfp_ewma_rate && + nla_put_u32(skb, TCA_POLICE_AVRATE, p->tcfp_ewma_rate)) goto nla_put_failure; t.install = jiffies_to_clock_t(jiffies - police->tcf_tm.install); @@ -312,8 +337,7 @@ nla_put_failure: return -1; } -static int tcf_police_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_police_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, police_net_id); @@ -333,6 +357,7 @@ static struct tc_action_ops act_police_ops = { .init = tcf_police_init, .walk = tcf_police_walker, .lookup = tcf_police_search, + .cleanup = tcf_police_cleanup, .size = sizeof(struct tcf_police), }; diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 6b67aa13d2dd..1a0c682fd734 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -224,8 +224,7 @@ static int tcf_sample_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, sample_net_id); diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 52400d49f81f..902957beceb3 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -188,8 +188,7 @@ static int tcf_simp_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_simp_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_simp_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, simp_net_id); diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 73e44ce2a883..64dba3708fce 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -99,7 +99,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbedit_net_id); - struct tcf_skbedit_params *params_old, *params_new; + struct tcf_skbedit_params *params_new; struct nlattr *tb[TCA_SKBEDIT_MAX + 1]; struct tc_skbedit *parm; struct tcf_skbedit *d; @@ -187,8 +187,6 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, } } - ASSERT_RTNL(); - params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); if (unlikely(!params_new)) { if (ret == ACT_P_CREATED) @@ -210,11 +208,13 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, if (flags & SKBEDIT_F_MASK) params_new->mask = *mask; + spin_lock_bh(&d->tcf_lock); d->tcf_action = parm->action; - params_old = rtnl_dereference(d->params); - rcu_assign_pointer(d->params, params_new); - if (params_old) - kfree_rcu(params_old, rcu); + rcu_swap_protected(d->params, params_new, + lockdep_is_held(&d->tcf_lock)); + spin_unlock_bh(&d->tcf_lock); + if (params_new) + kfree_rcu(params_new, rcu); if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); @@ -231,12 +231,14 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, .index = d->tcf_index, .refcnt = refcount_read(&d->tcf_refcnt) - ref, .bindcnt = atomic_read(&d->tcf_bindcnt) - bind, - .action = d->tcf_action, }; u64 pure_flags = 0; struct tcf_t t; - params = rtnl_dereference(d->params); + spin_lock_bh(&d->tcf_lock); + params = rcu_dereference_protected(d->params, + lockdep_is_held(&d->tcf_lock)); + opt.action = d->tcf_action; if (nla_put(skb, TCA_SKBEDIT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; @@ -264,9 +266,12 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, tcf_tm_dump(&t, &d->tcf_tm); if (nla_put_64bit(skb, TCA_SKBEDIT_TM, sizeof(t), &t, TCA_SKBEDIT_PAD)) goto nla_put_failure; + spin_unlock_bh(&d->tcf_lock); + return skb->len; nla_put_failure: + spin_unlock_bh(&d->tcf_lock); nlmsg_trim(skb, b); return -1; } @@ -291,8 +296,7 @@ static int tcf_skbedit_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, skbedit_net_id); diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 588077fafd6c..59710a183bd3 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -251,8 +251,7 @@ static int tcf_skbmod_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, skbmod_net_id); diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 681f6f04e7da..4cca8f274662 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -548,8 +548,7 @@ static int tunnel_key_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 033d273afe50..ba677d54a7af 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -288,8 +288,7 @@ static int tcf_vlan_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, vlan_net_id); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 6fd9bdd93796..4b8dd37dd4f8 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -98,7 +98,7 @@ struct cls_fl_filter { struct list_head list; u32 handle; u32 flags; - unsigned int in_hw_count; + u32 in_hw_count; struct rcu_work rwork; struct net_device *hw_dev; }; @@ -1880,6 +1880,9 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh, if (f->flags && nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags)) goto nla_put_failure; + if (nla_put_u32(skb, TCA_FLOWER_IN_HW_COUNT, f->in_hw_count)) + goto nla_put_failure; + if (tcf_exts_dump(skb, &f->exts)) goto nla_put_failure; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 98541c6399db..411c40344b77 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -27,7 +27,6 @@ #include <linux/kmod.h> #include <linux/list.h> #include <linux/hrtimer.h> -#include <linux/lockdep.h> #include <linux/slab.h> #include <linux/hashtable.h> @@ -1053,10 +1052,6 @@ static int qdisc_block_indexes_set(struct Qdisc *sch, struct nlattr **tca, return 0; } -/* lockdep annotation is needed for ingress; egress gets it only for name */ -static struct lock_class_key qdisc_tx_lock; -static struct lock_class_key qdisc_rx_lock; - /* Allocate and initialize new qdisc. @@ -1121,7 +1116,6 @@ static struct Qdisc *qdisc_create(struct net_device *dev, if (handle == TC_H_INGRESS) { sch->flags |= TCQ_F_INGRESS; handle = TC_H_MAKE(TC_H_INGRESS, 0); - lockdep_set_class(qdisc_lock(sch), &qdisc_rx_lock); } else { if (handle == 0) { handle = qdisc_alloc_handle(dev); @@ -1129,7 +1123,6 @@ static struct Qdisc *qdisc_create(struct net_device *dev, if (handle == 0) goto err_out3; } - lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock); if (!netif_is_multiqueue(dev)) sch->flags |= TCQ_F_ONETXQUEUE; } diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index c07c30b916d5..dc539295ae65 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -812,7 +812,7 @@ static struct sk_buff *dequeue_head(struct cake_flow *flow) if (skb) { flow->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); } return skb; @@ -1252,7 +1252,7 @@ found: else flow->head = elig_ack->next; - elig_ack->next = NULL; + skb_mark_not_on_list(elig_ack); return elig_ack; } @@ -1675,7 +1675,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, while (segs) { nskb = segs->next; - segs->next = NULL; + skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; cobalt_set_enqueue_time(segs, now); get_cobalt_cb(segs)->adjusted_len = cake_overhead(q, diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 4808713c73b9..b27ba36a269c 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -319,7 +319,7 @@ static struct sk_buff *fq_dequeue_head(struct Qdisc *sch, struct fq_flow *flow) if (skb) { flow->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); flow->qlen--; qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 6c0a9d5dbf94..cd04d40c30b6 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -124,7 +124,7 @@ static inline struct sk_buff *dequeue_head(struct fq_codel_flow *flow) struct sk_buff *skb = flow->head; flow->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); return skb; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 69078c82963e..a64132a5db36 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -184,7 +184,7 @@ static void try_bulk_dequeue_skb(struct Qdisc *q, skb = nskb; (*packets)++; /* GSO counts as one pkt */ } - skb->next = NULL; + skb_mark_not_on_list(skb); } /* This variant of try_bulk_dequeue_skb() makes sure @@ -210,7 +210,7 @@ static void try_bulk_dequeue_skb_slow(struct Qdisc *q, skb = nskb; } while (++cnt < 8); (*packets) += cnt; - skb->next = NULL; + skb_mark_not_on_list(skb); } /* Note that dequeue_skb can possibly return a SKB list (via skb->next). diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index c3a8388dcdf6..9d6a47697406 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -330,7 +330,7 @@ static struct sk_buff *dequeue_head(struct wdrr_bucket *bucket) struct sk_buff *skb = bucket->head; bucket->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); return skb; } diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 43c4bfe625a9..18ac2d6ca294 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -132,7 +132,7 @@ struct htb_class { struct htb_class_inner { struct htb_prio clprio[TC_HTB_NUMPRIO]; } inner; - } un; + }; s64 pq_key; int prio_activity; /* for which prios are we active */ @@ -411,13 +411,13 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl) int prio = ffz(~m); m &= ~(1 << prio); - if (p->un.inner.clprio[prio].feed.rb_node) + if (p->inner.clprio[prio].feed.rb_node) /* parent already has its feed in use so that * reset bit in mask as parent is already ok */ mask &= ~(1 << prio); - htb_add_to_id_tree(&p->un.inner.clprio[prio].feed, cl, prio); + htb_add_to_id_tree(&p->inner.clprio[prio].feed, cl, prio); } p->prio_activity |= mask; cl = p; @@ -447,19 +447,19 @@ static void htb_deactivate_prios(struct htb_sched *q, struct htb_class *cl) int prio = ffz(~m); m &= ~(1 << prio); - if (p->un.inner.clprio[prio].ptr == cl->node + prio) { + if (p->inner.clprio[prio].ptr == cl->node + prio) { /* we are removing child which is pointed to from * parent feed - forget the pointer but remember * classid */ - p->un.inner.clprio[prio].last_ptr_id = cl->common.classid; - p->un.inner.clprio[prio].ptr = NULL; + p->inner.clprio[prio].last_ptr_id = cl->common.classid; + p->inner.clprio[prio].ptr = NULL; } htb_safe_rb_erase(cl->node + prio, - &p->un.inner.clprio[prio].feed); + &p->inner.clprio[prio].feed); - if (!p->un.inner.clprio[prio].feed.rb_node) + if (!p->inner.clprio[prio].feed.rb_node) mask |= 1 << prio; } @@ -555,7 +555,7 @@ htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff) */ static inline void htb_activate(struct htb_sched *q, struct htb_class *cl) { - WARN_ON(cl->level || !cl->un.leaf.q || !cl->un.leaf.q->q.qlen); + WARN_ON(cl->level || !cl->leaf.q || !cl->leaf.q->q.qlen); if (!cl->prio_activity) { cl->prio_activity = 1 << cl->prio; @@ -577,22 +577,6 @@ static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl) cl->prio_activity = 0; } -static void htb_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch, - struct qdisc_skb_head *qh) -{ - struct sk_buff *last = qh->tail; - - if (last) { - skb->next = NULL; - last->next = skb; - qh->tail = skb; - } else { - qh->tail = skb; - qh->head = skb; - } - qh->qlen++; -} - static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { @@ -603,7 +587,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (cl == HTB_DIRECT) { /* enqueue to helper queue */ if (q->direct_queue.qlen < q->direct_qlen) { - htb_enqueue_tail(skb, sch, &q->direct_queue); + __qdisc_enqueue_tail(skb, &q->direct_queue); q->direct_pkts++; } else { return qdisc_drop(skb, sch, to_free); @@ -615,7 +599,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, __qdisc_drop(skb, to_free); return ret; #endif - } else if ((ret = qdisc_enqueue(skb, cl->un.leaf.q, + } else if ((ret = qdisc_enqueue(skb, cl->leaf.q, to_free)) != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(ret)) { qdisc_qstats_drop(sch); @@ -823,7 +807,7 @@ static struct htb_class *htb_lookup_leaf(struct htb_prio *hprio, const int prio) cl = rb_entry(*sp->pptr, struct htb_class, node[prio]); if (!cl->level) return cl; - clp = &cl->un.inner.clprio[prio]; + clp = &cl->inner.clprio[prio]; (++sp)->root = clp->feed.rb_node; sp->pptr = &clp->ptr; sp->pid = &clp->last_ptr_id; @@ -857,7 +841,7 @@ next: * graft operation on the leaf since last dequeue; * simply deactivate and skip such class */ - if (unlikely(cl->un.leaf.q->q.qlen == 0)) { + if (unlikely(cl->leaf.q->q.qlen == 0)) { struct htb_class *next; htb_deactivate(q, cl); @@ -873,12 +857,12 @@ next: goto next; } - skb = cl->un.leaf.q->dequeue(cl->un.leaf.q); + skb = cl->leaf.q->dequeue(cl->leaf.q); if (likely(skb != NULL)) break; - qdisc_warn_nonwc("htb", cl->un.leaf.q); - htb_next_rb_node(level ? &cl->parent->un.inner.clprio[prio].ptr: + qdisc_warn_nonwc("htb", cl->leaf.q); + htb_next_rb_node(level ? &cl->parent->inner.clprio[prio].ptr: &q->hlevel[0].hprio[prio].ptr); cl = htb_lookup_leaf(hprio, prio); @@ -886,16 +870,16 @@ next: if (likely(skb != NULL)) { bstats_update(&cl->bstats, skb); - cl->un.leaf.deficit[level] -= qdisc_pkt_len(skb); - if (cl->un.leaf.deficit[level] < 0) { - cl->un.leaf.deficit[level] += cl->quantum; - htb_next_rb_node(level ? &cl->parent->un.inner.clprio[prio].ptr : + cl->leaf.deficit[level] -= qdisc_pkt_len(skb); + if (cl->leaf.deficit[level] < 0) { + cl->leaf.deficit[level] += cl->quantum; + htb_next_rb_node(level ? &cl->parent->inner.clprio[prio].ptr : &q->hlevel[0].hprio[prio].ptr); } /* this used to be after charge_class but this constelation * gives us slightly better performance */ - if (!cl->un.leaf.q->q.qlen) + if (!cl->leaf.q->q.qlen) htb_deactivate(q, cl); htb_charge_class(q, cl, level, skb); } @@ -972,10 +956,10 @@ static void htb_reset(struct Qdisc *sch) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { if (cl->level) - memset(&cl->un.inner, 0, sizeof(cl->un.inner)); + memset(&cl->inner, 0, sizeof(cl->inner)); else { - if (cl->un.leaf.q) - qdisc_reset(cl->un.leaf.q); + if (cl->leaf.q) + qdisc_reset(cl->leaf.q); } cl->prio_activity = 0; cl->cmode = HTB_CAN_SEND; @@ -1098,8 +1082,8 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg, */ tcm->tcm_parent = cl->parent ? cl->parent->common.classid : TC_H_ROOT; tcm->tcm_handle = cl->common.classid; - if (!cl->level && cl->un.leaf.q) - tcm->tcm_info = cl->un.leaf.q->handle; + if (!cl->level && cl->leaf.q) + tcm->tcm_info = cl->leaf.q->handle; nest = nla_nest_start(skb, TCA_OPTIONS); if (nest == NULL) @@ -1142,9 +1126,9 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) }; __u32 qlen = 0; - if (!cl->level && cl->un.leaf.q) { - qlen = cl->un.leaf.q->q.qlen; - qs.backlog = cl->un.leaf.q->qstats.backlog; + if (!cl->level && cl->leaf.q) { + qlen = cl->leaf.q->q.qlen; + qs.backlog = cl->leaf.q->qstats.backlog; } cl->xstats.tokens = clamp_t(s64, PSCHED_NS2TICKS(cl->tokens), INT_MIN, INT_MAX); @@ -1172,14 +1156,14 @@ static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, cl->common.classid, extack)) == NULL) return -ENOBUFS; - *old = qdisc_replace(sch, new, &cl->un.leaf.q); + *old = qdisc_replace(sch, new, &cl->leaf.q); return 0; } static struct Qdisc *htb_leaf(struct Qdisc *sch, unsigned long arg) { struct htb_class *cl = (struct htb_class *)arg; - return !cl->level ? cl->un.leaf.q : NULL; + return !cl->level ? cl->leaf.q : NULL; } static void htb_qlen_notify(struct Qdisc *sch, unsigned long arg) @@ -1205,15 +1189,15 @@ static void htb_parent_to_leaf(struct htb_sched *q, struct htb_class *cl, { struct htb_class *parent = cl->parent; - WARN_ON(cl->level || !cl->un.leaf.q || cl->prio_activity); + WARN_ON(cl->level || !cl->leaf.q || cl->prio_activity); if (parent->cmode != HTB_CAN_SEND) htb_safe_rb_erase(&parent->pq_node, &q->hlevel[parent->level].wait_pq); parent->level = 0; - memset(&parent->un.inner, 0, sizeof(parent->un.inner)); - parent->un.leaf.q = new_q ? new_q : &noop_qdisc; + memset(&parent->inner, 0, sizeof(parent->inner)); + parent->leaf.q = new_q ? new_q : &noop_qdisc; parent->tokens = parent->buffer; parent->ctokens = parent->cbuffer; parent->t_c = ktime_get_ns(); @@ -1223,8 +1207,8 @@ static void htb_parent_to_leaf(struct htb_sched *q, struct htb_class *cl, static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl) { if (!cl->level) { - WARN_ON(!cl->un.leaf.q); - qdisc_destroy(cl->un.leaf.q); + WARN_ON(!cl->leaf.q); + qdisc_destroy(cl->leaf.q); } gen_kill_estimator(&cl->rate_est); tcf_block_put(cl->block); @@ -1286,11 +1270,11 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg) sch_tree_lock(sch); if (!cl->level) { - unsigned int qlen = cl->un.leaf.q->q.qlen; - unsigned int backlog = cl->un.leaf.q->qstats.backlog; + unsigned int qlen = cl->leaf.q->q.qlen; + unsigned int backlog = cl->leaf.q->qstats.backlog; - qdisc_reset(cl->un.leaf.q); - qdisc_tree_reduce_backlog(cl->un.leaf.q, qlen, backlog); + qdisc_reset(cl->leaf.q); + qdisc_tree_reduce_backlog(cl->leaf.q, qlen, backlog); } /* delete from hash and active; remainder in destroy_class */ @@ -1419,13 +1403,13 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, classid, NULL); sch_tree_lock(sch); if (parent && !parent->level) { - unsigned int qlen = parent->un.leaf.q->q.qlen; - unsigned int backlog = parent->un.leaf.q->qstats.backlog; + unsigned int qlen = parent->leaf.q->q.qlen; + unsigned int backlog = parent->leaf.q->qstats.backlog; /* turn parent into inner node */ - qdisc_reset(parent->un.leaf.q); - qdisc_tree_reduce_backlog(parent->un.leaf.q, qlen, backlog); - qdisc_destroy(parent->un.leaf.q); + qdisc_reset(parent->leaf.q); + qdisc_tree_reduce_backlog(parent->leaf.q, qlen, backlog); + qdisc_destroy(parent->leaf.q); if (parent->prio_activity) htb_deactivate(q, parent); @@ -1436,10 +1420,10 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, } parent->level = (parent->parent ? parent->parent->level : TC_HTB_MAXDEPTH) - 1; - memset(&parent->un.inner, 0, sizeof(parent->un.inner)); + memset(&parent->inner, 0, sizeof(parent->inner)); } /* leaf (we) needs elementary qdisc */ - cl->un.leaf.q = new_q ? new_q : &noop_qdisc; + cl->leaf.q = new_q ? new_q : &noop_qdisc; cl->common.classid = classid; cl->parent = parent; @@ -1455,8 +1439,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, qdisc_class_hash_insert(&q->clhash, &cl->common); if (parent) parent->children++; - if (cl->un.leaf.q != &noop_qdisc) - qdisc_hash_add(cl->un.leaf.q, true); + if (cl->leaf.q != &noop_qdisc) + qdisc_hash_add(cl->leaf.q, true); } else { if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, @@ -1478,7 +1462,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, psched_ratecfg_precompute(&cl->ceil, &hopt->ceil, ceil64); /* it used to be a nasty bug here, we have to check that node - * is really leaf before changing cl->un.leaf ! + * is really leaf before changing cl->leaf ! */ if (!cl->level) { u64 quantum = cl->rate.rate_bytes_ps; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index ad18a2052416..506e1960ed7f 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -412,16 +412,6 @@ static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch, return segs; } -static void netem_enqueue_skb_head(struct qdisc_skb_head *qh, struct sk_buff *skb) -{ - skb->next = qh->head; - - if (!qh->head) - qh->tail = skb; - qh->head = skb; - qh->qlen++; -} - /* * Insert one skb into qdisc. * Note: parent depends on return value to account for queue length. @@ -570,7 +560,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, cb->time_to_send = ktime_get_ns(); q->counter = 0; - netem_enqueue_skb_head(&sch->q, skb); + __qdisc_enqueue_head(skb, &sch->q); sch->qstats.requeues++; } @@ -578,7 +568,7 @@ finish_segs: if (segs) { while (segs) { skb2 = segs->next; - segs->next = NULL; + skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; last_len = segs->len; rc = qdisc_enqueue(segs, sch, to_free); diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 6f74a426f159..a4530e85bd02 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -162,7 +162,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch, nb = 0; while (segs) { nskb = segs->next; - segs->next = NULL; + skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; len += segs->len; ret = qdisc_enqueue(segs, q->qdisc, to_free); diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 0b427100b0d4..331cc734e3db 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -459,7 +459,7 @@ static struct sctp_ulpevent *sctp_ulpq_retrieve_reassembled(struct sctp_ulpq *ul * element in the queue, then count it towards * possible PD. */ - if (pos == ulpq->reasm.next) { + if (skb_queue_is_first(&ulpq->reasm, pos)) { pd_first = pos; pd_last = pos; pd_len = pos->len; diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 418f03d0be90..91891041e5e1 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -577,7 +577,7 @@ static int tipc_l2_rcv_msg(struct sk_buff *skb, struct net_device *dev, rcu_dereference_rtnl(orig_dev->tipc_ptr); if (likely(b && test_bit(0, &b->up) && (skb->pkt_type <= PACKET_MULTICAST))) { - skb->next = NULL; + skb_mark_not_on_list(skb); tipc_rcv(dev_net(b->pt.dev), skb, b); rcu_read_unlock(); return NET_RX_SUCCESS; diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 2627b5d812e9..d8956f7daac4 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -57,16 +57,12 @@ * @idr_lock: protect the connection identifier set * @idr_in_use: amount of allocated identifier entry * @net: network namspace instance - * @rcvbuf_cache: memory cache of server receive buffer + * @awork: accept work item * @rcv_wq: receive workqueue * @send_wq: send workqueue * @max_rcvbuf_size: maximum permitted receive message length - * @tipc_conn_new: callback will be called when new connection is incoming - * @tipc_conn_release: callback will be called before releasing the connection - * @tipc_conn_recvmsg: callback will be called when message arrives + * @listener: topsrv listener socket * @name: server name - * @imp: message importance - * @type: socket type */ struct tipc_topsrv { struct idr conn_idr; @@ -90,9 +86,7 @@ struct tipc_topsrv { * @server: pointer to connected server * @sub_list: lsit to all pertaing subscriptions * @sub_lock: lock protecting the subscription list - * @outqueue_lock: control access to the outqueue * @rwork: receive work item - * @rx_action: what to do when connection socket is active * @outqueue: pointer to first outbound message in queue * @outqueue_lock: control access to the outqueue * @swork: send work item diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index b9c6ecfbcfea..5ff51bac8b46 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -43,12 +43,133 @@ #define MAX_IV_SIZE TLS_CIPHER_AES_GCM_128_IV_SIZE +static int __skb_nsg(struct sk_buff *skb, int offset, int len, + unsigned int recursion_level) +{ + int start = skb_headlen(skb); + int i, chunk = start - offset; + struct sk_buff *frag_iter; + int elt = 0; + + if (unlikely(recursion_level >= 24)) + return -EMSGSIZE; + + if (chunk > 0) { + if (chunk > len) + chunk = len; + elt++; + len -= chunk; + if (len == 0) + return elt; + offset += chunk; + } + + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + int end; + + WARN_ON(start > offset + len); + + end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); + chunk = end - offset; + if (chunk > 0) { + if (chunk > len) + chunk = len; + elt++; + len -= chunk; + if (len == 0) + return elt; + offset += chunk; + } + start = end; + } + + if (unlikely(skb_has_frag_list(skb))) { + skb_walk_frags(skb, frag_iter) { + int end, ret; + + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + chunk = end - offset; + if (chunk > 0) { + if (chunk > len) + chunk = len; + ret = __skb_nsg(frag_iter, offset - start, chunk, + recursion_level + 1); + if (unlikely(ret < 0)) + return ret; + elt += ret; + len -= chunk; + if (len == 0) + return elt; + offset += chunk; + } + start = end; + } + } + BUG_ON(len); + return elt; +} + +/* Return the number of scatterlist elements required to completely map the + * skb, or -EMSGSIZE if the recursion depth is exceeded. + */ +static int skb_nsg(struct sk_buff *skb, int offset, int len) +{ + return __skb_nsg(skb, offset, len, 0); +} + +static void tls_decrypt_done(struct crypto_async_request *req, int err) +{ + struct aead_request *aead_req = (struct aead_request *)req; + struct scatterlist *sgout = aead_req->dst; + struct tls_sw_context_rx *ctx; + struct tls_context *tls_ctx; + struct scatterlist *sg; + struct sk_buff *skb; + unsigned int pages; + int pending; + + skb = (struct sk_buff *)req->data; + tls_ctx = tls_get_ctx(skb->sk); + ctx = tls_sw_ctx_rx(tls_ctx); + pending = atomic_dec_return(&ctx->decrypt_pending); + + /* Propagate if there was an err */ + if (err) { + ctx->async_wait.err = err; + tls_err_abort(skb->sk, err); + } + + /* After using skb->sk to propagate sk through crypto async callback + * we need to NULL it again. + */ + skb->sk = NULL; + + /* Release the skb, pages and memory allocated for crypto req */ + kfree_skb(skb); + + /* Skip the first S/G entry as it points to AAD */ + for_each_sg(sg_next(sgout), sg, UINT_MAX, pages) { + if (!sg) + break; + put_page(sg_page(sg)); + } + + kfree(aead_req); + + if (!pending && READ_ONCE(ctx->async_notify)) + complete(&ctx->async_wait.completion); +} + static int tls_do_decryption(struct sock *sk, + struct sk_buff *skb, struct scatterlist *sgin, struct scatterlist *sgout, char *iv_recv, size_t data_len, - struct aead_request *aead_req) + struct aead_request *aead_req, + bool async) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); @@ -59,10 +180,36 @@ static int tls_do_decryption(struct sock *sk, aead_request_set_crypt(aead_req, sgin, sgout, data_len + tls_ctx->rx.tag_size, (u8 *)iv_recv); - aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG, - crypto_req_done, &ctx->async_wait); - ret = crypto_wait_req(crypto_aead_decrypt(aead_req), &ctx->async_wait); + if (async) { + /* Using skb->sk to push sk through to crypto async callback + * handler. This allows propagating errors up to the socket + * if needed. It _must_ be cleared in the async handler + * before kfree_skb is called. We _know_ skb->sk is NULL + * because it is a clone from strparser. + */ + skb->sk = sk; + aead_request_set_callback(aead_req, + CRYPTO_TFM_REQ_MAY_BACKLOG, + tls_decrypt_done, skb); + atomic_inc(&ctx->decrypt_pending); + } else { + aead_request_set_callback(aead_req, + CRYPTO_TFM_REQ_MAY_BACKLOG, + crypto_req_done, &ctx->async_wait); + } + + ret = crypto_aead_decrypt(aead_req); + if (ret == -EINPROGRESS) { + if (async) + return ret; + + ret = crypto_wait_req(ret, &ctx->async_wait); + } + + if (async) + atomic_dec(&ctx->decrypt_pending); + return ret; } @@ -354,7 +501,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); - int ret = 0; + int ret; int required_size; long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); bool eor = !(msg->msg_flags & MSG_MORE); @@ -370,7 +517,8 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) lock_sock(sk); - if (tls_complete_pending_work(sk, tls_ctx, msg->msg_flags, &timeo)) + ret = tls_complete_pending_work(sk, tls_ctx, msg->msg_flags, &timeo); + if (ret) goto send_end; if (unlikely(msg->msg_controllen)) { @@ -505,7 +653,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); - int ret = 0; + int ret; long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); bool eor; size_t orig_size = size; @@ -525,7 +673,8 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); - if (tls_complete_pending_work(sk, tls_ctx, flags, &timeo)) + ret = tls_complete_pending_work(sk, tls_ctx, flags, &timeo); + if (ret) goto sendpage_end; /* Call the sk_stream functions to manage the sndbuf mem. */ @@ -684,12 +833,14 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, n_sgout = iov_iter_npages(out_iov, INT_MAX) + 1; else n_sgout = sg_nents(out_sg); + n_sgin = skb_nsg(skb, rxm->offset + tls_ctx->rx.prepend_size, + rxm->full_len - tls_ctx->rx.prepend_size); } else { n_sgout = 0; *zc = false; + n_sgin = skb_cow_data(skb, 0, &unused); } - n_sgin = skb_cow_data(skb, 0, &unused); if (n_sgin < 1) return -EBADMSG; @@ -769,7 +920,10 @@ fallback_to_reg_recv: } /* Prepare and submit AEAD request */ - err = tls_do_decryption(sk, sgin, sgout, iv, data_len, aead_req); + err = tls_do_decryption(sk, skb, sgin, sgout, iv, + data_len, aead_req, *zc); + if (err == -EINPROGRESS) + return err; /* Release the pages in case iov was mapped to pages */ for (; pages > 0; pages--) @@ -794,8 +948,12 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, #endif if (!ctx->decrypted) { err = decrypt_internal(sk, skb, dest, NULL, chunk, zc); - if (err < 0) + if (err < 0) { + if (err == -EINPROGRESS) + tls_advance_record_sn(sk, &tls_ctx->rx); + return err; + } } else { *zc = false; } @@ -823,18 +981,20 @@ static bool tls_sw_advance_skb(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 strp_msg *rxm = strp_msg(skb); - if (len < rxm->full_len) { - rxm->offset += len; - rxm->full_len -= len; + if (skb) { + struct strp_msg *rxm = strp_msg(skb); - return false; + if (len < rxm->full_len) { + rxm->offset += len; + rxm->full_len -= len; + return false; + } + kfree_skb(skb); } /* Finished with message */ ctx->recv_pkt = NULL; - kfree_skb(skb); __strp_unpause(&ctx->strp); return true; @@ -857,6 +1017,7 @@ int tls_sw_recvmsg(struct sock *sk, int target, err = 0; long timeo; bool is_kvec = msg->msg_iter.type & ITER_KVEC; + int num_async = 0; flags |= nonblock; @@ -869,6 +1030,7 @@ int tls_sw_recvmsg(struct sock *sk, timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); do { bool zc = false; + bool async = false; int chunk = 0; skb = tls_wait_data(sk, flags, timeo, &err); @@ -876,6 +1038,7 @@ int tls_sw_recvmsg(struct sock *sk, goto recv_end; rxm = strp_msg(skb); + if (!cmsg) { int cerr; @@ -902,26 +1065,39 @@ int tls_sw_recvmsg(struct sock *sk, err = decrypt_skb_update(sk, skb, &msg->msg_iter, &chunk, &zc); - if (err < 0) { + if (err < 0 && err != -EINPROGRESS) { tls_err_abort(sk, EBADMSG); goto recv_end; } + + if (err == -EINPROGRESS) { + async = true; + num_async++; + goto pick_next_record; + } + ctx->decrypted = true; } if (!zc) { chunk = min_t(unsigned int, rxm->full_len, len); + err = skb_copy_datagram_msg(skb, rxm->offset, msg, chunk); if (err < 0) goto recv_end; } +pick_next_record: copied += chunk; len -= chunk; if (likely(!(flags & MSG_PEEK))) { u8 control = ctx->control; + /* For async, drop current skb reference */ + if (async) + skb = NULL; + if (tls_sw_advance_skb(sk, skb, chunk)) { /* Return full control message to * userspace before trying to parse @@ -930,6 +1106,8 @@ int tls_sw_recvmsg(struct sock *sk, msg->msg_flags |= MSG_EOR; if (control != TLS_RECORD_TYPE_DATA) goto recv_end; + } else { + break; } } else { /* MSG_PEEK right now cannot look beyond current skb @@ -946,6 +1124,22 @@ int tls_sw_recvmsg(struct sock *sk, } while (len); recv_end: + if (num_async) { + /* Wait for all previously submitted records to be decrypted */ + smp_store_mb(ctx->async_notify, true); + if (atomic_read(&ctx->decrypt_pending)) { + err = crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + if (err) { + /* one of async decrypt failed */ + tls_err_abort(sk, err); + copied = 0; + } + } else { + reinit_completion(&ctx->async_wait.completion); + } + WRITE_ONCE(ctx->async_notify, false); + } + release_sock(sk); return copied ? : err; } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 4b8ec659e797..d5f9b5235cdd 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4095,6 +4095,9 @@ static void nl80211_calculate_ap_params(struct cfg80211_ap_settings *params) cap = cfg80211_find_ie(WLAN_EID_VHT_CAPABILITY, ies, ies_len); if (cap && cap[1] >= sizeof(*params->vht_cap)) params->vht_cap = (void *)(cap + 2); + cap = cfg80211_find_ext_ie(WLAN_EID_EXT_HE_CAPABILITY, ies, ies_len); + if (cap && cap[1] >= sizeof(*params->he_cap) + 1) + params->he_cap = (void *)(cap + 3); } static bool nl80211_get_ap_channel(struct cfg80211_registered_device *rdev, @@ -4724,10 +4727,11 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, PUT_SINFO_U64(RX_DROP_MISC, rx_dropped_misc); PUT_SINFO_U64(BEACON_RX, rx_beacon); PUT_SINFO(BEACON_SIGNAL_AVG, rx_beacon_signal_avg, u8); - PUT_SINFO(ACK_SIGNAL, ack_signal, u8); if (wiphy_ext_feature_isset(&rdev->wiphy, - NL80211_EXT_FEATURE_DATA_ACK_SIGNAL_SUPPORT)) - PUT_SINFO(DATA_ACK_SIGNAL_AVG, avg_ack_signal, s8); + NL80211_EXT_FEATURE_ACK_SIGNAL_SUPPORT)) { + PUT_SINFO(ACK_SIGNAL, ack_signal, u8); + PUT_SINFO(ACK_SIGNAL_AVG, avg_ack_signal, s8); + } #undef PUT_SINFO #undef PUT_SINFO_U64 diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 2f702adf2912..56be68a27bb9 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -847,22 +847,36 @@ static bool valid_regdb(const u8 *data, unsigned int size) return true; } -static void set_wmm_rule(struct ieee80211_reg_rule *rrule, - struct fwdb_wmm_rule *wmm) -{ - struct ieee80211_wmm_rule *rule = &rrule->wmm_rule; - unsigned int i; +static void set_wmm_rule(const struct fwdb_header *db, + const struct fwdb_country *country, + const struct fwdb_rule *rule, + struct ieee80211_reg_rule *rrule) +{ + struct ieee80211_wmm_rule *wmm_rule = &rrule->wmm_rule; + struct fwdb_wmm_rule *wmm; + unsigned int i, wmm_ptr; + + wmm_ptr = be16_to_cpu(rule->wmm_ptr) << 2; + wmm = (void *)((u8 *)db + wmm_ptr); + + if (!valid_wmm(wmm)) { + pr_err("Invalid regulatory WMM rule %u-%u in domain %c%c\n", + be32_to_cpu(rule->start), be32_to_cpu(rule->end), + country->alpha2[0], country->alpha2[1]); + return; + } for (i = 0; i < IEEE80211_NUM_ACS; i++) { - rule->client[i].cw_min = + wmm_rule->client[i].cw_min = ecw2cw((wmm->client[i].ecw & 0xf0) >> 4); - rule->client[i].cw_max = ecw2cw(wmm->client[i].ecw & 0x0f); - rule->client[i].aifsn = wmm->client[i].aifsn; - rule->client[i].cot = 1000 * be16_to_cpu(wmm->client[i].cot); - rule->ap[i].cw_min = ecw2cw((wmm->ap[i].ecw & 0xf0) >> 4); - rule->ap[i].cw_max = ecw2cw(wmm->ap[i].ecw & 0x0f); - rule->ap[i].aifsn = wmm->ap[i].aifsn; - rule->ap[i].cot = 1000 * be16_to_cpu(wmm->ap[i].cot); + wmm_rule->client[i].cw_max = ecw2cw(wmm->client[i].ecw & 0x0f); + wmm_rule->client[i].aifsn = wmm->client[i].aifsn; + wmm_rule->client[i].cot = + 1000 * be16_to_cpu(wmm->client[i].cot); + wmm_rule->ap[i].cw_min = ecw2cw((wmm->ap[i].ecw & 0xf0) >> 4); + wmm_rule->ap[i].cw_max = ecw2cw(wmm->ap[i].ecw & 0x0f); + wmm_rule->ap[i].aifsn = wmm->ap[i].aifsn; + wmm_rule->ap[i].cot = 1000 * be16_to_cpu(wmm->ap[i].cot); } rrule->has_wmm = true; @@ -870,7 +884,7 @@ static void set_wmm_rule(struct ieee80211_reg_rule *rrule, static int __regdb_query_wmm(const struct fwdb_header *db, const struct fwdb_country *country, int freq, - struct ieee80211_reg_rule *rule) + struct ieee80211_reg_rule *rrule) { unsigned int ptr = be16_to_cpu(country->coll_ptr) << 2; struct fwdb_collection *coll = (void *)((u8 *)db + ptr); @@ -879,18 +893,14 @@ static int __regdb_query_wmm(const struct fwdb_header *db, for (i = 0; i < coll->n_rules; i++) { __be16 *rules_ptr = (void *)((u8 *)coll + ALIGN(coll->len, 2)); unsigned int rule_ptr = be16_to_cpu(rules_ptr[i]) << 2; - struct fwdb_rule *rrule = (void *)((u8 *)db + rule_ptr); - struct fwdb_wmm_rule *wmm; - unsigned int wmm_ptr; + struct fwdb_rule *rule = (void *)((u8 *)db + rule_ptr); - if (rrule->len < offsetofend(struct fwdb_rule, wmm_ptr)) + if (rule->len < offsetofend(struct fwdb_rule, wmm_ptr)) continue; - if (freq >= KHZ_TO_MHZ(be32_to_cpu(rrule->start)) && - freq <= KHZ_TO_MHZ(be32_to_cpu(rrule->end))) { - wmm_ptr = be16_to_cpu(rrule->wmm_ptr) << 2; - wmm = (void *)((u8 *)db + wmm_ptr); - set_wmm_rule(rule, wmm); + if (freq >= KHZ_TO_MHZ(be32_to_cpu(rule->start)) && + freq <= KHZ_TO_MHZ(be32_to_cpu(rule->end))) { + set_wmm_rule(db, country, rule, rrule); return 0; } } @@ -972,12 +982,8 @@ static int regdb_query_country(const struct fwdb_header *db, if (rule->len >= offsetofend(struct fwdb_rule, cac_timeout)) rrule->dfs_cac_ms = 1000 * be16_to_cpu(rule->cac_timeout); - if (rule->len >= offsetofend(struct fwdb_rule, wmm_ptr)) { - u32 wmm_ptr = be16_to_cpu(rule->wmm_ptr) << 2; - struct fwdb_wmm_rule *wmm = (void *)((u8 *)db + wmm_ptr); - - set_wmm_rule(rrule, wmm); - } + if (rule->len >= offsetofend(struct fwdb_rule, wmm_ptr)) + set_wmm_rule(db, country, rule, rrule); } return reg_schedule_apply(regdom); @@ -3184,13 +3190,59 @@ static void restore_regulatory_settings(bool reset_user) schedule_work(®_work); } +static bool is_wiphy_all_set_reg_flag(enum ieee80211_regulatory_flags flag) +{ + struct cfg80211_registered_device *rdev; + struct wireless_dev *wdev; + + list_for_each_entry(rdev, &cfg80211_rdev_list, list) { + list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { + wdev_lock(wdev); + if (!(wdev->wiphy->regulatory_flags & flag)) { + wdev_unlock(wdev); + return false; + } + wdev_unlock(wdev); + } + } + + return true; +} + void regulatory_hint_disconnect(void) { + /* Restore of regulatory settings is not required when wiphy(s) + * ignore IE from connected access point but clearance of beacon hints + * is required when wiphy(s) supports beacon hints. + */ + if (is_wiphy_all_set_reg_flag(REGULATORY_COUNTRY_IE_IGNORE)) { + struct reg_beacon *reg_beacon, *btmp; + + if (is_wiphy_all_set_reg_flag(REGULATORY_DISABLE_BEACON_HINTS)) + return; + + spin_lock_bh(®_pending_beacons_lock); + list_for_each_entry_safe(reg_beacon, btmp, + ®_pending_beacons, list) { + list_del(®_beacon->list); + kfree(reg_beacon); + } + spin_unlock_bh(®_pending_beacons_lock); + + list_for_each_entry_safe(reg_beacon, btmp, + ®_beacon_list, list) { + list_del(®_beacon->list); + kfree(reg_beacon); + } + + return; + } + pr_debug("All devices are disconnected, going to restore regulatory settings\n"); restore_regulatory_settings(false); } -static bool freq_is_chan_12_13_14(u16 freq) +static bool freq_is_chan_12_13_14(u32 freq) { if (freq == ieee80211_channel_to_frequency(12, NL80211_BAND_2GHZ) || freq == ieee80211_channel_to_frequency(13, NL80211_BAND_2GHZ) || diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 7c73510b161f..5e7eec849200 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -112,7 +112,7 @@ } while (0) #define CHAN_ENTRY __field(enum nl80211_band, band) \ - __field(u16, center_freq) + __field(u32, center_freq) #define CHAN_ASSIGN(chan) \ do { \ if (chan) { \ diff --git a/net/wireless/util.c b/net/wireless/util.c index 959ed3acd240..ef14d80ca03e 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -5,17 +5,20 @@ * Copyright 2007-2009 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2017 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation */ #include <linux/export.h> #include <linux/bitops.h> #include <linux/etherdevice.h> #include <linux/slab.h> +#include <linux/ieee80211.h> #include <net/cfg80211.h> #include <net/ip.h> #include <net/dsfield.h> #include <linux/if_vlan.h> #include <linux/mpls.h> #include <linux/gcd.h> +#include <linux/bitfield.h> #include "core.h" #include "rdev-ops.h" @@ -88,7 +91,7 @@ int ieee80211_channel_to_frequency(int chan, enum nl80211_band band) return 5000 + chan * 5; break; case NL80211_BAND_60GHZ: - if (chan < 5) + if (chan < 7) return 56160 + chan * 2160; break; default: @@ -109,7 +112,7 @@ int ieee80211_frequency_to_channel(int freq) return (freq - 4000) / 5; else if (freq <= 45000) /* DMG band lower limit */ return (freq - 5000) / 5; - else if (freq >= 58320 && freq <= 64800) + else if (freq >= 58320 && freq <= 70200) return (freq - 56160) / 2160; else return 0; @@ -1568,7 +1571,7 @@ bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef, } /* 56.16 GHz, channel 1..4 */ - if (freq >= 56160 + 2160 * 1 && freq <= 56160 + 2160 * 4) { + if (freq >= 56160 + 2160 * 1 && freq <= 56160 + 2160 * 6) { if (chandef->width >= NL80211_CHAN_WIDTH_40) return false; @@ -1893,3 +1896,154 @@ EXPORT_SYMBOL(rfc1042_header); const unsigned char bridge_tunnel_header[] __aligned(2) = { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0xf8 }; EXPORT_SYMBOL(bridge_tunnel_header); + +/* Layer 2 Update frame (802.2 Type 1 LLC XID Update response) */ +struct iapp_layer2_update { + u8 da[ETH_ALEN]; /* broadcast */ + u8 sa[ETH_ALEN]; /* STA addr */ + __be16 len; /* 6 */ + u8 dsap; /* 0 */ + u8 ssap; /* 0 */ + u8 control; + u8 xid_info[3]; +} __packed; + +void cfg80211_send_layer2_update(struct net_device *dev, const u8 *addr) +{ + struct iapp_layer2_update *msg; + struct sk_buff *skb; + + /* Send Level 2 Update Frame to update forwarding tables in layer 2 + * bridge devices */ + + skb = dev_alloc_skb(sizeof(*msg)); + if (!skb) + return; + msg = skb_put(skb, sizeof(*msg)); + + /* 802.2 Type 1 Logical Link Control (LLC) Exchange Identifier (XID) + * Update response frame; IEEE Std 802.2-1998, 5.4.1.2.1 */ + + eth_broadcast_addr(msg->da); + ether_addr_copy(msg->sa, addr); + msg->len = htons(6); + msg->dsap = 0; + msg->ssap = 0x01; /* NULL LSAP, CR Bit: Response */ + msg->control = 0xaf; /* XID response lsb.1111F101. + * F=0 (no poll command; unsolicited frame) */ + msg->xid_info[0] = 0x81; /* XID format identifier */ + msg->xid_info[1] = 1; /* LLC types/classes: Type 1 LLC */ + msg->xid_info[2] = 0; /* XID sender's receive window size (RW) */ + + skb->dev = dev; + skb->protocol = eth_type_trans(skb, dev); + memset(skb->cb, 0, sizeof(skb->cb)); + netif_rx_ni(skb); +} +EXPORT_SYMBOL(cfg80211_send_layer2_update); + +int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, + enum ieee80211_vht_chanwidth bw, + int mcs, bool ext_nss_bw_capable) +{ + u16 map = le16_to_cpu(cap->supp_mcs.rx_mcs_map); + int max_vht_nss = 0; + int ext_nss_bw; + int supp_width; + int i, mcs_encoding; + + if (map == 0xffff) + return 0; + + if (WARN_ON(mcs > 9)) + return 0; + if (mcs <= 7) + mcs_encoding = 0; + else if (mcs == 8) + mcs_encoding = 1; + else + mcs_encoding = 2; + + /* find max_vht_nss for the given MCS */ + for (i = 7; i >= 0; i--) { + int supp = (map >> (2 * i)) & 3; + + if (supp == 3) + continue; + + if (supp >= mcs_encoding) { + max_vht_nss = i; + break; + } + } + + if (!(cap->supp_mcs.tx_mcs_map & + cpu_to_le16(IEEE80211_VHT_EXT_NSS_BW_CAPABLE))) + return max_vht_nss; + + ext_nss_bw = le32_get_bits(cap->vht_cap_info, + IEEE80211_VHT_CAP_EXT_NSS_BW_MASK); + supp_width = le32_get_bits(cap->vht_cap_info, + IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK); + + /* if not capable, treat ext_nss_bw as 0 */ + if (!ext_nss_bw_capable) + ext_nss_bw = 0; + + /* This is invalid */ + if (supp_width == 3) + return 0; + + /* This is an invalid combination so pretend nothing is supported */ + if (supp_width == 2 && (ext_nss_bw == 1 || ext_nss_bw == 2)) + return 0; + + /* + * Cover all the special cases according to IEEE 802.11-2016 + * Table 9-250. All other cases are either factor of 1 or not + * valid/supported. + */ + switch (bw) { + case IEEE80211_VHT_CHANWIDTH_USE_HT: + case IEEE80211_VHT_CHANWIDTH_80MHZ: + if ((supp_width == 1 || supp_width == 2) && + ext_nss_bw == 3) + return 2 * max_vht_nss; + break; + case IEEE80211_VHT_CHANWIDTH_160MHZ: + if (supp_width == 0 && + (ext_nss_bw == 1 || ext_nss_bw == 2)) + return DIV_ROUND_UP(max_vht_nss, 2); + if (supp_width == 0 && + ext_nss_bw == 3) + return DIV_ROUND_UP(3 * max_vht_nss, 4); + if (supp_width == 1 && + ext_nss_bw == 3) + return 2 * max_vht_nss; + break; + case IEEE80211_VHT_CHANWIDTH_80P80MHZ: + if (supp_width == 0 && + (ext_nss_bw == 1 || ext_nss_bw == 2)) + return 0; /* not possible */ + if (supp_width == 0 && + ext_nss_bw == 2) + return DIV_ROUND_UP(max_vht_nss, 2); + if (supp_width == 0 && + ext_nss_bw == 3) + return DIV_ROUND_UP(3 * max_vht_nss, 4); + if (supp_width == 1 && + ext_nss_bw == 0) + return 0; /* not possible */ + if (supp_width == 1 && + ext_nss_bw == 1) + return DIV_ROUND_UP(max_vht_nss, 2); + if (supp_width == 1 && + ext_nss_bw == 2) + return DIV_ROUND_UP(3 * max_vht_nss, 4); + break; + } + + /* not covered or invalid combination received */ + return max_vht_nss; +} +EXPORT_SYMBOL(ieee80211_get_vht_max_nss); diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index bfe2dbea480b..b3b632c5aeae 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -76,8 +76,6 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_async_xmit) return force_zc ? -EOPNOTSUPP : 0; /* fail or fallback */ - bpf.command = XDP_QUERY_XSK_UMEM; - rtnl_lock(); err = xdp_umem_query(dev, queue_id); if (err) { @@ -314,8 +312,8 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) umem->pid = get_task_pid(current, PIDTYPE_PID); umem->address = (unsigned long)addr; - umem->props.chunk_mask = ~((u64)chunk_size - 1); - umem->props.size = size; + umem->chunk_mask = ~((u64)chunk_size - 1); + umem->size = size; umem->headroom = headroom; umem->chunk_size_nohr = chunk_size - headroom; umem->npgs = size / PAGE_SIZE; diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h index f11560334f88..c8be1ad3eb88 100644 --- a/net/xdp/xdp_umem.h +++ b/net/xdp/xdp_umem.h @@ -8,16 +8,6 @@ #include <net/xdp_sock.h> -static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr) -{ - return umem->pages[addr >> PAGE_SHIFT].addr + (addr & (PAGE_SIZE - 1)); -} - -static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr) -{ - return umem->pages[addr >> PAGE_SHIFT].dma + (addr & (PAGE_SIZE - 1)); -} - int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, u32 queue_id, u16 flags); bool xdp_umem_validate_queues(struct xdp_umem *umem); diff --git a/net/xdp/xdp_umem_props.h b/net/xdp/xdp_umem_props.h deleted file mode 100644 index 40eab10dfc49..000000000000 --- a/net/xdp/xdp_umem_props.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* XDP user-space packet buffer - * Copyright(c) 2018 Intel Corporation. - */ - -#ifndef XDP_UMEM_PROPS_H_ -#define XDP_UMEM_PROPS_H_ - -struct xdp_umem_props { - u64 chunk_mask; - u64 size; -}; - -#endif /* XDP_UMEM_PROPS_H_ */ diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 4e937cd7c17d..5a432dfee4ee 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -55,20 +55,30 @@ EXPORT_SYMBOL(xsk_umem_discard_addr); static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) { - void *buffer; + void *to_buf, *from_buf; + u32 metalen; u64 addr; int err; if (!xskq_peek_addr(xs->umem->fq, &addr) || - len > xs->umem->chunk_size_nohr) { + len > xs->umem->chunk_size_nohr - XDP_PACKET_HEADROOM) { xs->rx_dropped++; return -ENOSPC; } addr += xs->umem->headroom; - buffer = xdp_umem_get_data(xs->umem, addr); - memcpy(buffer, xdp->data, len); + if (unlikely(xdp_data_meta_unsupported(xdp))) { + from_buf = xdp->data; + metalen = 0; + } else { + from_buf = xdp->data_meta; + metalen = xdp->data - xdp->data_meta; + } + + to_buf = xdp_umem_get_data(xs->umem, addr); + memcpy(to_buf, from_buf, len + metalen); + addr += metalen; err = xskq_produce_batch_desc(xs->rx, addr, len); if (!err) { xskq_discard_addr(xs->umem->fq); @@ -111,6 +121,7 @@ void xsk_flush(struct xdp_sock *xs) int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) { + u32 metalen = xdp->data - xdp->data_meta; u32 len = xdp->data_end - xdp->data; void *buffer; u64 addr; @@ -120,7 +131,7 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) return -EINVAL; if (!xskq_peek_addr(xs->umem->fq, &addr) || - len > xs->umem->chunk_size_nohr) { + len > xs->umem->chunk_size_nohr - XDP_PACKET_HEADROOM) { xs->rx_dropped++; return -ENOSPC; } @@ -128,7 +139,8 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) addr += xs->umem->headroom; buffer = xdp_umem_get_data(xs->umem, addr); - memcpy(buffer, xdp->data, len); + memcpy(buffer, xdp->data_meta, len + metalen); + addr += metalen; err = xskq_produce_batch_desc(xs->rx, addr, len); if (!err) { xskq_discard_addr(xs->umem->fq); @@ -458,8 +470,10 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) goto out_unlock; } else { /* This xsk has its own umem. */ - xskq_set_umem(xs->umem->fq, &xs->umem->props); - xskq_set_umem(xs->umem->cq, &xs->umem->props); + xskq_set_umem(xs->umem->fq, xs->umem->size, + xs->umem->chunk_mask); + xskq_set_umem(xs->umem->cq, xs->umem->size, + xs->umem->chunk_mask); err = xdp_umem_assign_dev(xs->umem, dev, qid, flags); if (err) @@ -469,8 +483,8 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) xs->dev = dev; xs->zc = xs->umem->zc; xs->queue_id = qid; - xskq_set_umem(xs->rx, &xs->umem->props); - xskq_set_umem(xs->tx, &xs->umem->props); + xskq_set_umem(xs->rx, xs->umem->size, xs->umem->chunk_mask); + xskq_set_umem(xs->tx, xs->umem->size, xs->umem->chunk_mask); xdp_add_sk_umem(xs->umem, xs); out_unlock: diff --git a/net/xdp/xsk_queue.c b/net/xdp/xsk_queue.c index 6c32e92e98fc..2dc1384d9f27 100644 --- a/net/xdp/xsk_queue.c +++ b/net/xdp/xsk_queue.c @@ -7,12 +7,13 @@ #include "xsk_queue.h" -void xskq_set_umem(struct xsk_queue *q, struct xdp_umem_props *umem_props) +void xskq_set_umem(struct xsk_queue *q, u64 size, u64 chunk_mask) { if (!q) return; - q->umem_props = *umem_props; + q->size = size; + q->chunk_mask = chunk_mask; } static u32 xskq_umem_get_ring_size(struct xsk_queue *q) diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 8a64b150be54..82252cccb4e0 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -31,7 +31,8 @@ struct xdp_umem_ring { }; struct xsk_queue { - struct xdp_umem_props umem_props; + u64 chunk_mask; + u64 size; u32 ring_mask; u32 nentries; u32 prod_head; @@ -78,7 +79,7 @@ static inline u32 xskq_nb_free(struct xsk_queue *q, u32 producer, u32 dcnt) static inline bool xskq_is_valid_addr(struct xsk_queue *q, u64 addr) { - if (addr >= q->umem_props.size) { + if (addr >= q->size) { q->invalid_descs++; return false; } @@ -92,7 +93,7 @@ static inline u64 *xskq_validate_addr(struct xsk_queue *q, u64 *addr) struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; unsigned int idx = q->cons_tail & q->ring_mask; - *addr = READ_ONCE(ring->desc[idx]) & q->umem_props.chunk_mask; + *addr = READ_ONCE(ring->desc[idx]) & q->chunk_mask; if (xskq_is_valid_addr(q, *addr)) return addr; @@ -173,8 +174,8 @@ static inline bool xskq_is_valid_desc(struct xsk_queue *q, struct xdp_desc *d) if (!xskq_is_valid_addr(q, d->addr)) return false; - if (((d->addr + d->len) & q->umem_props.chunk_mask) != - (d->addr & q->umem_props.chunk_mask)) { + if (((d->addr + d->len) & q->chunk_mask) != + (d->addr & q->chunk_mask)) { q->invalid_descs++; return false; } @@ -253,7 +254,7 @@ static inline bool xskq_empty_desc(struct xsk_queue *q) return xskq_nb_free(q, q->prod_tail, q->nentries) == q->nentries; } -void xskq_set_umem(struct xsk_queue *q, struct xdp_umem_props *umem_props); +void xskq_set_umem(struct xsk_queue *q, u64 size, u64 chunk_mask); struct xsk_queue *xskq_create(u32 nentries, bool umem_queue); void xskq_destroy(struct xsk_queue *q_ops); diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 5611b7521020..260fbba4f03e 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -99,7 +99,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur do { struct sk_buff *nskb = skb2->next; - skb2->next = NULL; + skb_mark_not_on_list(skb2); xo = xfrm_offload(skb2); xo->flags |= XFRM_DEV_RESUME; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 45ba07ab3e4f..2d42cb0c94b8 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -189,7 +189,7 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb struct sk_buff *nskb = segs->next; int err; - segs->next = NULL; + skb_mark_not_on_list(segs); err = xfrm_output2(net, sk, segs); if (unlikely(err)) { |