diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-07-14 09:24:32 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-07-14 09:24:32 -0700 |
| commit | 8096acd7442e613fad0354fc8dfdb2003cceea0b (patch) | |
| tree | ad8b748475fa87fe7c3b6f9cd00da8d7b8d078bd /net | |
| parent | d1d488d813703618f0dd93f0e4c4a05928114aa8 (diff) | |
| parent | bcb9928a155444dbd212473e60241ca0a7f641e1 (diff) | |
| download | linux-8096acd7442e613fad0354fc8dfdb2003cceea0b.tar.gz linux-8096acd7442e613fad0354fc8dfdb2003cceea0b.tar.bz2 linux-8096acd7442e613fad0354fc8dfdb2003cceea0b.zip | |
Merge tag 'net-5.14-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski.
"Including fixes from bpf and netfilter.
Current release - regressions:
- sock: fix parameter order in sock_setsockopt()
Current release - new code bugs:
- netfilter: nft_last:
- fix incorrect arithmetic when restoring last used
- honor NFTA_LAST_SET on restoration
Previous releases - regressions:
- udp: properly flush normal packet at GRO time
- sfc: ensure correct number of XDP queues; don't allow enabling the
feature if there isn't sufficient resources to Tx from any CPU
- dsa: sja1105: fix address learning getting disabled on the CPU port
- mptcp: addresses a rmem accounting issue that could keep packets in
subflow receive buffers longer than necessary, delaying MPTCP-level
ACKs
- ip_tunnel: fix mtu calculation for ETHER tunnel devices
- do not reuse skbs allocated from skbuff_fclone_cache in the napi
skb cache, we'd try to return them to the wrong slab cache
- tcp: consistently disable header prediction for mptcp
Previous releases - always broken:
- bpf: fix subprog poke descriptor tracking use-after-free
- ipv6:
- allocate enough headroom in ip6_finish_output2() in case
iptables TEE is used
- tcp: drop silly ICMPv6 packet too big messages to avoid
expensive and pointless lookups (which may serve as a DDOS
vector)
- make sure fwmark is copied in SYNACK packets
- fix 'disable_policy' for forwarded packets (align with IPv4)
- netfilter: conntrack:
- do not renew entry stuck in tcp SYN_SENT state
- do not mark RST in the reply direction coming after SYN packet
for an out-of-sync entry
- mptcp: cleanly handle error conditions with MP_JOIN and syncookies
- mptcp: fix double free when rejecting a join due to port mismatch
- validate lwtstate->data before returning from skb_tunnel_info()
- tcp: call sk_wmem_schedule before sk_mem_charge in zerocopy path
- mt76: mt7921: continue to probe driver when fw already downloaded
- bonding: fix multiple issues with offloading IPsec to (thru?) bond
- stmmac: ptp: fix issues around Qbv support and setting time back
- bcmgenet: always clear wake-up based on energy detection
Misc:
- sctp: move 198 addresses from unusable to private scope
- ptp: support virtual clocks and timestamping
- openvswitch: optimize operation for key comparison"
* tag 'net-5.14-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (158 commits)
net: dsa: properly check for the bridge_leave methods in dsa_switch_bridge_leave()
sfc: add logs explaining XDP_TX/REDIRECT is not available
sfc: ensure correct number of XDP queues
sfc: fix lack of XDP TX queues - error XDP TX failed (-22)
net: fddi: fix UAF in fza_probe
net: dsa: sja1105: fix address learning getting disabled on the CPU port
net: ocelot: fix switchdev objects synced for wrong netdev with LAG offload
net: Use nlmsg_unicast() instead of netlink_unicast()
octeontx2-pf: Fix uninitialized boolean variable pps
ipv6: allocate enough headroom in ip6_finish_output2()
net: hdlc: rename 'mod_init' & 'mod_exit' functions to be module-specific
net: bridge: multicast: fix MRD advertisement router port marking race
net: bridge: multicast: fix PIM hello router port marking race
net: phy: marvell10g: fix differentiation of 88X3310 from 88X3340
dsa: fix for_each_child.cocci warnings
virtio_net: check virtqueue_add_sgs() return value
mptcp: properly account bulk freed memory
selftests: mptcp: fix case multiple subflows limited by server
mptcp: avoid processing packet if a subflow reset
mptcp: fix syncookie process if mptcp can not_accept new subflow
...
Diffstat (limited to 'net')
61 files changed, 671 insertions, 174 deletions
diff --git a/net/802/garp.c b/net/802/garp.c index 400bd857e5f5..f6012f8e59f0 100644 --- a/net/802/garp.c +++ b/net/802/garp.c @@ -203,6 +203,19 @@ static void garp_attr_destroy(struct garp_applicant *app, struct garp_attr *attr kfree(attr); } +static void garp_attr_destroy_all(struct garp_applicant *app) +{ + struct rb_node *node, *next; + struct garp_attr *attr; + + for (node = rb_first(&app->gid); + next = node ? rb_next(node) : NULL, node != NULL; + node = next) { + attr = rb_entry(node, struct garp_attr, node); + garp_attr_destroy(app, attr); + } +} + static int garp_pdu_init(struct garp_applicant *app) { struct sk_buff *skb; @@ -609,6 +622,7 @@ void garp_uninit_applicant(struct net_device *dev, struct garp_application *appl spin_lock_bh(&app->lock); garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU); + garp_attr_destroy_all(app); garp_pdu_queue(app); spin_unlock_bh(&app->lock); diff --git a/net/802/mrp.c b/net/802/mrp.c index bea6e43d45a0..35e04cc5390c 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -292,6 +292,19 @@ static void mrp_attr_destroy(struct mrp_applicant *app, struct mrp_attr *attr) kfree(attr); } +static void mrp_attr_destroy_all(struct mrp_applicant *app) +{ + struct rb_node *node, *next; + struct mrp_attr *attr; + + for (node = rb_first(&app->mad); + next = node ? rb_next(node) : NULL, node != NULL; + node = next) { + attr = rb_entry(node, struct mrp_attr, node); + mrp_attr_destroy(app, attr); + } +} + static int mrp_pdu_init(struct mrp_applicant *app) { struct sk_buff *skb; @@ -895,6 +908,7 @@ void mrp_uninit_applicant(struct net_device *dev, struct mrp_application *appl) spin_lock_bh(&app->lock); mrp_mad_event(app, MRP_EVENT_TX); + mrp_attr_destroy_all(app); mrp_pdu_queue(app); spin_unlock_bh(&app->lock); diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index f7d2f472ae24..6e4a32354a13 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -562,7 +562,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, struct net_bridge_port *p; int err = 0; unsigned br_hr, dev_hr; - bool changed_addr; + bool changed_addr, fdb_synced = false; /* Don't allow bridging non-ethernet like devices. */ if ((dev->flags & IFF_LOOPBACK) || @@ -652,6 +652,19 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, list_add_rcu(&p->list, &br->port_list); nbp_update_port_count(br); + if (!br_promisc_port(p) && (p->dev->priv_flags & IFF_UNICAST_FLT)) { + /* When updating the port count we also update all ports' + * promiscuous mode. + * A port leaving promiscuous mode normally gets the bridge's + * fdb synced to the unicast filter (if supported), however, + * `br_port_clear_promisc` does not distinguish between + * non-promiscuous ports and *new* ports, so we need to + * sync explicitly here. + */ + fdb_synced = br_fdb_sync_static(br, p) == 0; + if (!fdb_synced) + netdev_err(dev, "failed to sync bridge static fdb addresses to this port\n"); + } netdev_update_features(br->dev); @@ -701,6 +714,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, return 0; err7: + if (fdb_synced) + br_fdb_unsync_static(br, p); list_del_rcu(&p->list); br_fdb_delete_by_port(br, p, 0, 1); nbp_update_port_count(br); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 53c3a9d80d9c..d0434dc8c03b 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -3264,7 +3264,9 @@ static void br_multicast_pim(struct net_bridge *br, pim_hdr_type(pimhdr) != PIM_TYPE_HELLO) return; + spin_lock(&br->multicast_lock); br_ip4_multicast_mark_router(br, port); + spin_unlock(&br->multicast_lock); } static int br_ip4_multicast_mrd_rcv(struct net_bridge *br, @@ -3275,7 +3277,9 @@ static int br_ip4_multicast_mrd_rcv(struct net_bridge *br, igmp_hdr(skb)->type != IGMP_MRDISC_ADV) return -ENOMSG; + spin_lock(&br->multicast_lock); br_ip4_multicast_mark_router(br, port); + spin_unlock(&br->multicast_lock); return 0; } @@ -3343,7 +3347,9 @@ static void br_ip6_multicast_mrd_rcv(struct net_bridge *br, if (icmp6_hdr(skb)->icmp6_type != ICMPV6_MRDISC_ADV) return; + spin_lock(&br->multicast_lock); br_ip6_multicast_mark_router(br, port); + spin_unlock(&br->multicast_lock); } static int br_multicast_ipv6_rcv(struct net_bridge *br, diff --git a/net/core/dev.c b/net/core/dev.c index c253c2aafe97..64b21f0a2048 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6008,6 +6008,19 @@ static void gro_list_prepare(const struct list_head *head, diffs = memcmp(skb_mac_header(p), skb_mac_header(skb), maclen); + + diffs |= skb_get_nfct(p) ^ skb_get_nfct(skb); +#if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT) + if (!diffs) { + struct tc_skb_ext *skb_ext = skb_ext_find(skb, TC_SKB_EXT); + struct tc_skb_ext *p_ext = skb_ext_find(p, TC_SKB_EXT); + + diffs |= (!!p_ext) ^ (!!skb_ext); + if (!diffs && unlikely(skb_ext)) + diffs |= p_ext->chain ^ skb_ext->chain; + } +#endif + NAPI_GRO_CB(p)->same_flow = !diffs; } } @@ -6221,6 +6234,8 @@ static gro_result_t napi_skb_finish(struct napi_struct *napi, case GRO_MERGED_FREE: if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) napi_skb_free_stolen_head(skb); + else if (skb->fclone != SKB_FCLONE_UNAVAILABLE) + __kfree_skb(skb); else __kfree_skb_defer(skb); break; @@ -6270,6 +6285,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb_shinfo(skb)->gso_type = 0; skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); skb_ext_reset(skb); + nf_reset_ct(skb); napi->skb = skb; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 12aabcda6db2..f63de967ac25 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -943,6 +943,7 @@ void __kfree_skb_defer(struct sk_buff *skb) void napi_skb_free_stolen_head(struct sk_buff *skb) { + nf_reset_ct(skb); skb_dst_drop(skb); skb_ext_put(skb); napi_skb_cache_put(skb); diff --git a/net/core/sock.c b/net/core/sock.c index ba1c0f75cd45..a3eea6e0b30a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -139,6 +139,8 @@ #include <net/tcp.h> #include <net/busy_poll.h> +#include <linux/ethtool.h> + static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); @@ -810,8 +812,47 @@ void sock_set_timestamp(struct sock *sk, int optname, bool valbool) } } -int sock_set_timestamping(struct sock *sk, int optname, int val) +static int sock_timestamping_bind_phc(struct sock *sk, int phc_index) +{ + struct net *net = sock_net(sk); + struct net_device *dev = NULL; + bool match = false; + int *vclock_index; + int i, num; + + if (sk->sk_bound_dev_if) + dev = dev_get_by_index(net, sk->sk_bound_dev_if); + + if (!dev) { + pr_err("%s: sock not bind to device\n", __func__); + return -EOPNOTSUPP; + } + + num = ethtool_get_phc_vclocks(dev, &vclock_index); + for (i = 0; i < num; i++) { + if (*(vclock_index + i) == phc_index) { + match = true; + break; + } + } + + if (num > 0) + kfree(vclock_index); + + if (!match) + return -EINVAL; + + sk->sk_bind_phc = phc_index; + + return 0; +} + +int sock_set_timestamping(struct sock *sk, int optname, + struct so_timestamping timestamping) { + int val = timestamping.flags; + int ret; + if (val & ~SOF_TIMESTAMPING_MASK) return -EINVAL; @@ -832,6 +873,12 @@ int sock_set_timestamping(struct sock *sk, int optname, int val) !(val & SOF_TIMESTAMPING_OPT_TSONLY)) return -EINVAL; + if (val & SOF_TIMESTAMPING_BIND_PHC) { + ret = sock_timestamping_bind_phc(sk, timestamping.bind_phc); + if (ret) + return ret; + } + sk->sk_tsflags = val; sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW); @@ -907,6 +954,7 @@ EXPORT_SYMBOL(sock_set_mark); int sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { + struct so_timestamping timestamping; struct sock_txtime sk_txtime; struct sock *sk = sock->sk; int val; @@ -1068,12 +1116,22 @@ set_sndbuf: case SO_TIMESTAMP_NEW: case SO_TIMESTAMPNS_OLD: case SO_TIMESTAMPNS_NEW: - sock_set_timestamp(sk, valbool, optname); + sock_set_timestamp(sk, optname, valbool); break; case SO_TIMESTAMPING_NEW: case SO_TIMESTAMPING_OLD: - ret = sock_set_timestamping(sk, optname, val); + if (optlen == sizeof(timestamping)) { + if (copy_from_sockptr(×tamping, optval, + sizeof(timestamping))) { + ret = -EFAULT; + break; + } + } else { + memset(×tamping, 0, sizeof(timestamping)); + timestamping.flags = val; + } + ret = sock_set_timestamping(sk, optname, timestamping); break; case SO_RCVLOWAT: @@ -1201,7 +1259,7 @@ set_sndbuf: if (val < 0) ret = -EINVAL; else - sk->sk_ll_usec = val; + WRITE_ONCE(sk->sk_ll_usec, val); } break; case SO_PREFER_BUSY_POLL: @@ -1348,6 +1406,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, struct __kernel_old_timeval tm; struct __kernel_sock_timeval stm; struct sock_txtime txtime; + struct so_timestamping timestamping; } v; int lv = sizeof(int); @@ -1451,7 +1510,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_TIMESTAMPING_OLD: - v.val = sk->sk_tsflags; + lv = sizeof(v.timestamping); + v.timestamping.flags = sk->sk_tsflags; + v.timestamping.bind_phc = sk->sk_bind_phc; break; case SO_RCVTIMEO_OLD: diff --git a/net/dsa/switch.c b/net/dsa/switch.c index af71b8638098..5ece05dfd8f2 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -113,11 +113,11 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, int err, port; if (dst->index == info->tree_index && ds->index == info->sw_index && - ds->ops->port_bridge_join) + ds->ops->port_bridge_leave) ds->ops->port_bridge_leave(ds, info->port, info->br); if ((dst->index != info->tree_index || ds->index != info->sw_index) && - ds->ops->crosschip_bridge_join) + ds->ops->crosschip_bridge_leave) ds->ops->crosschip_bridge_leave(ds, info->tree_index, info->sw_index, info->port, info->br); @@ -427,7 +427,7 @@ static int dsa_switch_lag_join(struct dsa_switch *ds, info->port, info->lag, info->info); - return 0; + return -EOPNOTSUPP; } static int dsa_switch_lag_leave(struct dsa_switch *ds, @@ -440,7 +440,7 @@ static int dsa_switch_lag_leave(struct dsa_switch *ds, return ds->ops->crosschip_lag_leave(ds, info->sw_index, info->port, info->lag); - return 0; + return -EOPNOTSUPP; } static int dsa_switch_mdb_add(struct dsa_switch *ds, diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 723c9a8a8cdf..0a19470efbfb 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -7,4 +7,4 @@ obj-$(CONFIG_ETHTOOL_NETLINK) += ethtool_nl.o ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o \ linkstate.o debug.o wol.o features.o privflags.o rings.o \ channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \ - tunnels.o fec.o eeprom.o stats.o + tunnels.o fec.o eeprom.o stats.o phc_vclocks.o diff --git a/net/ethtool/common.c b/net/ethtool/common.c index f9dcbad84788..c63e0739dc6a 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -4,6 +4,7 @@ #include <linux/net_tstamp.h> #include <linux/phy.h> #include <linux/rtnetlink.h> +#include <linux/ptp_clock_kernel.h> #include "common.h" @@ -397,6 +398,7 @@ const char sof_timestamping_names[][ETH_GSTRING_LEN] = { [const_ilog2(SOF_TIMESTAMPING_OPT_STATS)] = "option-stats", [const_ilog2(SOF_TIMESTAMPING_OPT_PKTINFO)] = "option-pktinfo", [const_ilog2(SOF_TIMESTAMPING_OPT_TX_SWHW)] = "option-tx-swhw", + [const_ilog2(SOF_TIMESTAMPING_BIND_PHC)] = "bind-phc", }; static_assert(ARRAY_SIZE(sof_timestamping_names) == __SOF_TIMESTAMPING_CNT); @@ -554,6 +556,18 @@ int __ethtool_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) return 0; } +int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index) +{ + struct ethtool_ts_info info = { }; + int num = 0; + + if (!__ethtool_get_ts_info(dev, &info)) + num = ptp_get_vclocks_index(info.phc_index, vclock_index); + + return num; +} +EXPORT_SYMBOL(ethtool_get_phc_vclocks); + const struct ethtool_phy_ops *ethtool_phy_ops; void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops) diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index a7346346114f..73e0f5b626bf 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -248,6 +248,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_TSINFO_GET] = ðnl_tsinfo_request_ops, [ETHTOOL_MSG_MODULE_EEPROM_GET] = ðnl_module_eeprom_request_ops, [ETHTOOL_MSG_STATS_GET] = ðnl_stats_request_ops, + [ETHTOOL_MSG_PHC_VCLOCKS_GET] = ðnl_phc_vclocks_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) @@ -958,6 +959,15 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_stats_get_policy, .maxattr = ARRAY_SIZE(ethnl_stats_get_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + .policy = ethnl_phc_vclocks_get_policy, + .maxattr = ARRAY_SIZE(ethnl_phc_vclocks_get_policy) - 1, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 3e25a47fd482..3fc395c86702 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -347,6 +347,7 @@ extern const struct ethnl_request_ops ethnl_tsinfo_request_ops; extern const struct ethnl_request_ops ethnl_fec_request_ops; extern const struct ethnl_request_ops ethnl_module_eeprom_request_ops; extern const struct ethnl_request_ops ethnl_stats_request_ops; +extern const struct ethnl_request_ops ethnl_phc_vclocks_request_ops; extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; @@ -382,6 +383,7 @@ extern const struct nla_policy ethnl_fec_get_policy[ETHTOOL_A_FEC_HEADER + 1]; extern const struct nla_policy ethnl_fec_set_policy[ETHTOOL_A_FEC_AUTO + 1]; extern const struct nla_policy ethnl_module_eeprom_get_policy[ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS + 1]; extern const struct nla_policy ethnl_stats_get_policy[ETHTOOL_A_STATS_GROUPS + 1]; +extern const struct nla_policy ethnl_phc_vclocks_get_policy[ETHTOOL_A_PHC_VCLOCKS_HEADER + 1]; int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info); int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info); diff --git a/net/ethtool/phc_vclocks.c b/net/ethtool/phc_vclocks.c new file mode 100644 index 000000000000..637b2f5297d5 --- /dev/null +++ b/net/ethtool/phc_vclocks.c @@ -0,0 +1,94 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2021 NXP + */ +#include "netlink.h" +#include "common.h" + +struct phc_vclocks_req_info { + struct ethnl_req_info base; +}; + +struct phc_vclocks_reply_data { + struct ethnl_reply_data base; + int num; + int *index; +}; + +#define PHC_VCLOCKS_REPDATA(__reply_base) \ + container_of(__reply_base, struct phc_vclocks_reply_data, base) + +const struct nla_policy ethnl_phc_vclocks_get_policy[] = { + [ETHTOOL_A_PHC_VCLOCKS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), +}; + +static int phc_vclocks_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct phc_vclocks_reply_data *data = PHC_VCLOCKS_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + int ret; + + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + data->num = ethtool_get_phc_vclocks(dev, &data->index); + ethnl_ops_c |
