diff options
Diffstat (limited to 'net')
122 files changed, 2655 insertions, 754 deletions
diff --git a/net/802/mrp.c b/net/802/mrp.c index 2cfdfbfbb2ed..bea6e43d45a0 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -523,7 +523,7 @@ int mrp_request_join(const struct net_device *dev, struct mrp_attr *attr; if (sizeof(struct mrp_skb_cb) + len > - FIELD_SIZEOF(struct sk_buff, cb)) + sizeof_field(struct sk_buff, cb)) return -ENOMEM; spin_lock_bh(&app->lock); @@ -548,7 +548,7 @@ void mrp_request_leave(const struct net_device *dev, struct mrp_attr *attr; if (sizeof(struct mrp_skb_cb) + len > - FIELD_SIZEOF(struct sk_buff, cb)) + sizeof_field(struct sk_buff, cb)) return; spin_lock_bh(&app->lock); @@ -692,7 +692,7 @@ static int mrp_pdu_parse_vecattr(struct mrp_applicant *app, * advance to the next event in its Vector. */ if (sizeof(struct mrp_skb_cb) + mrp_cb(skb)->mh->attrlen > - FIELD_SIZEOF(struct sk_buff, cb)) + sizeof_field(struct sk_buff, cb)) return -1; if (skb_copy_bits(skb, *offset, mrp_cb(skb)->attrvalue, mrp_cb(skb)->mh->attrlen) < 0) diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index e5bff5cc6f97..5ff8059837b4 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -646,8 +646,8 @@ static int vlan_ethtool_get_ts_info(struct net_device *dev, const struct ethtool_ops *ops = vlan->real_dev->ethtool_ops; struct phy_device *phydev = vlan->real_dev->phydev; - if (phydev && phydev->drv && phydev->drv->ts_info) { - return phydev->drv->ts_info(phydev, info); + if (phy_has_tsinfo(phydev)) { + return phy_ts_info(phydev, info); } else if (ops->get_ts_info) { return ops->get_ts_info(vlan->real_dev, info); } else { diff --git a/net/Kconfig b/net/Kconfig index bd191f978a23..52af65e5d28c 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -108,9 +108,10 @@ config NETWORK_PHY_TIMESTAMPING bool "Timestamping in PHY devices" select NET_PTP_CLASSIFY help - This allows timestamping of network packets by PHYs with - hardware timestamping capabilities. This option adds some - overhead in the transmit and receive paths. + This allows timestamping of network packets by PHYs (or + other MII bus snooping devices) with hardware timestamping + capabilities. This option adds some overhead in the transmit + and receive paths. If you are unsure how to answer this question, answer N. diff --git a/net/Makefile b/net/Makefile index 449fc0b221f8..848303d98d3d 100644 --- a/net/Makefile +++ b/net/Makefile @@ -13,7 +13,7 @@ obj-$(CONFIG_NET) += $(tmp-y) # LLC has to be linked before the files in net/802/ obj-$(CONFIG_LLC) += llc/ -obj-$(CONFIG_NET) += ethernet/ 802/ sched/ netlink/ bpf/ +obj-$(CONFIG_NET) += ethernet/ 802/ sched/ netlink/ bpf/ ethtool/ obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_INET) += ipv4/ obj-$(CONFIG_TLS) += tls/ diff --git a/net/atm/lec.c b/net/atm/lec.c index 5a77c235a212..b57368e70aab 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -194,7 +194,7 @@ lec_send(struct atm_vcc *vcc, struct sk_buff *skb) dev->stats.tx_bytes += skb->len; } -static void lec_tx_timeout(struct net_device *dev) +static void lec_tx_timeout(struct net_device *dev, unsigned int txqueue) { pr_info("%s\n", dev->name); netif_trans_update(dev); diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 4a89177def64..4811ec65bc43 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -548,7 +548,7 @@ static void batadv_recv_handler_init(void) BUILD_BUG_ON(sizeof(struct batadv_tvlv_tt_change) != 12); BUILD_BUG_ON(sizeof(struct batadv_tvlv_roam_adv) != 8); - i = FIELD_SIZEOF(struct sk_buff, cb); + i = sizeof_field(struct sk_buff, cb); BUILD_BUG_ON(sizeof(struct batadv_skb_cb) > i); /* broadcast packet */ diff --git a/net/bluetooth/bnep/netdev.c b/net/bluetooth/bnep/netdev.c index 1d4d7d415730..cc1cff63194f 100644 --- a/net/bluetooth/bnep/netdev.c +++ b/net/bluetooth/bnep/netdev.c @@ -112,7 +112,7 @@ static int bnep_net_set_mac_addr(struct net_device *dev, void *arg) return 0; } -static void bnep_net_timeout(struct net_device *dev) +static void bnep_net_timeout(struct net_device *dev, unsigned int txqueue) { BT_DBG("net_timeout"); netif_wake_queue(dev); diff --git a/net/bridge/br.c b/net/bridge/br.c index 8a8f9e5f264f..b6fe30e3768f 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -312,7 +312,7 @@ static int __init br_init(void) { int err; - BUILD_BUG_ON(sizeof(struct br_input_skb_cb) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct br_input_skb_cb) > sizeof_field(struct sk_buff, cb)); err = stp_proto_register(&br_stp_proto); if (err < 0) { diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index af7800103e51..59980ecfc962 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -662,6 +662,9 @@ static unsigned int br_nf_forward_arp(void *priv, nf_bridge_pull_encap_header(skb); } + if (unlikely(!pskb_may_pull(skb, sizeof(struct arphdr)))) + return NF_DROP; + if (arp_hdr(skb)->ar_pln != 4) { if (is_vlan_arp(skb, state->net)) nf_bridge_push_encap_header(skb); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index a0a54482aabc..60136575aea4 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -1607,6 +1607,19 @@ static int br_fill_linkxstats(struct sk_buff *skb, br_multicast_get_stats(br, p, nla_data(nla)); } #endif + + if (p) { + nla = nla_reserve_64bit(skb, BRIDGE_XSTATS_STP, + sizeof(p->stp_xstats), + BRIDGE_XSTATS_PAD); + if (!nla) + goto nla_put_failure; + + spin_lock_bh(&br->lock); + memcpy(nla_data(nla), &p->stp_xstats, sizeof(p->stp_xstats)); + spin_unlock_bh(&br->lock); + } + nla_nest_end(skb, nest); *prividx = 0; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 36b0367ca1e0..f540f3bdf294 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -283,6 +283,8 @@ struct net_bridge_port { #endif u16 group_fwd_mask; u16 backup_redirected_cnt; + + struct bridge_stp_xstats stp_xstats; }; #define kobj_to_brport(obj) container_of(obj, struct net_bridge_port, kobj) diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 1f1410f8d312..6856a6d9282b 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -45,6 +45,17 @@ void br_set_state(struct net_bridge_port *p, unsigned int state) br_info(p->br, "port %u(%s) entered %s state\n", (unsigned int) p->port_no, p->dev->name, br_port_state_names[p->state]); + + if (p->br->stp_enabled == BR_KERNEL_STP) { + switch (p->state) { + case BR_STATE_BLOCKING: + p->stp_xstats.transition_blk++; + break; + case BR_STATE_FORWARDING: + p->stp_xstats.transition_fwd++; + break; + } + } } /* called under bridge lock */ @@ -484,6 +495,8 @@ void br_received_config_bpdu(struct net_bridge_port *p, struct net_bridge *br; int was_root; + p->stp_xstats.rx_bpdu++; + br = p->br; was_root = br_is_root_bridge(br); @@ -517,6 +530,8 @@ void br_received_config_bpdu(struct net_bridge_port *p, /* called under bridge lock */ void br_received_tcn_bpdu(struct net_bridge_port *p) { + p->stp_xstats.rx_tcn++; + if (br_is_designated_port(p)) { br_info(p->br, "port %u(%s) received tcn bpdu\n", (unsigned int) p->port_no, p->dev->name); diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c index 7796dd9d42d7..0e4572f31330 100644 --- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -118,6 +118,8 @@ void br_send_config_bpdu(struct net_bridge_port *p, struct br_config_bpdu *bpdu) br_set_ticks(buf+33, bpdu->forward_delay); br_send_bpdu(p, buf, 35); + + p->stp_xstats.tx_bpdu++; } /* called under bridge lock */ @@ -133,6 +135,8 @@ void br_send_tcn_bpdu(struct net_bridge_port *p) buf[2] = 0; buf[3] = BPDU_TYPE_TCN; br_send_bpdu(p, buf, 4); + + p->stp_xstats.tx_tcn++; } /* diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index de09b0a65791..f7587428febd 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -423,9 +423,9 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct j1939_sock *jsk = j1939_sk(sock->sk); - struct j1939_priv *priv = jsk->priv; - struct sock *sk = sock->sk; - struct net *net = sock_net(sk); + struct j1939_priv *priv; + struct sock *sk; + struct net *net; int ret = 0; ret = j1939_sk_sanity_check(addr, len); @@ -434,6 +434,10 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) lock_sock(sock->sk); + priv = jsk->priv; + sk = sock->sk; + net = sock_net(sk); + /* Already bound to an interface? */ if (jsk->state & J1939_SOCK_BOUND) { /* A re-bind() to a different interface is not diff --git a/net/core/Makefile b/net/core/Makefile index a104dc8faafc..3e2c378e5f31 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -8,7 +8,7 @@ obj-y := sock.o request_sock.o skbuff.o datagram.o stream.o scm.o \ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o -obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \ +obj-y += dev.o dev_addr_lists.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o \ sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \ fib_notifier.o xdp.o flow_offload.o diff --git a/net/core/dev.c b/net/core/dev.c index 255d3cf35360..f1b8afcfbc0f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10182,7 +10182,7 @@ static struct hlist_head * __net_init netdev_create_hash(void) static int __net_init netdev_init(struct net *net) { BUILD_BUG_ON(GRO_HASH_BUCKETS > - 8 * FIELD_SIZEOF(struct napi_struct, gro_bitmask)); + 8 * sizeof_field(struct napi_struct, gro_bitmask)); if (net != &init_net) INIT_LIST_HEAD(&net->dev_base_head); diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 5163d900bb4f..dbaebbe573f0 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -187,6 +187,7 @@ static int net_hwtstamp_validate(struct ifreq *ifr) case HWTSTAMP_TX_OFF: case HWTSTAMP_TX_ON: case HWTSTAMP_TX_ONESTEP_SYNC: + case HWTSTAMP_TX_ONESTEP_P2P: tx_type_valid = 1; break; } diff --git a/net/core/filter.c b/net/core/filter.c index 217af9974c86..42fd17c48c5f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -274,7 +274,7 @@ static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, switch (skb_field) { case SKF_AD_MARK: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); + BUILD_BUG_ON(sizeof_field(struct sk_buff, mark) != 4); *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, offsetof(struct sk_buff, mark)); @@ -289,14 +289,14 @@ static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, break; case SKF_AD_QUEUE: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2); + BUILD_BUG_ON(sizeof_field(struct sk_buff, queue_mapping) != 2); *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, offsetof(struct sk_buff, queue_mapping)); break; case SKF_AD_VLAN_TAG: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); + BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_tci) != 2); /* dst_reg = *(u16 *) (src_reg + offsetof(vlan_tci)) */ *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, @@ -322,7 +322,7 @@ static bool convert_bpf_extensions(struct sock_filter *fp, switch (fp->k) { case SKF_AD_OFF + SKF_AD_PROTOCOL: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2); + BUILD_BUG_ON(sizeof_field(struct sk_buff, protocol) != 2); /* A = *(u16 *) (CTX + offsetof(protocol)) */ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, @@ -338,8 +338,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp, case SKF_AD_OFF + SKF_AD_IFINDEX: case SKF_AD_OFF + SKF_AD_HATYPE: - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2); + BUILD_BUG_ON(sizeof_field(struct net_device, ifindex) != 4); + BUILD_BUG_ON(sizeof_field(struct net_device, type) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), BPF_REG_TMP, BPF_REG_CTX, @@ -361,7 +361,7 @@ static bool convert_bpf_extensions(struct sock_filter *fp, break; case SKF_AD_OFF + SKF_AD_RXHASH: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); + BUILD_BUG_ON(sizeof_field(struct sk_buff, hash) != 4); *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, offsetof(struct sk_buff, hash)); @@ -385,7 +385,7 @@ static bool convert_bpf_extensions(struct sock_filter *fp, break; case SKF_AD_OFF + SKF_AD_VLAN_TPID: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_proto) != 2); + BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_proto) != 2); /* A = *(u16 *) (CTX + offsetof(vlan_proto)) */ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, @@ -2055,6 +2055,7 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) } skb->dev = dev; + skb->tstamp = 0; dev_xmit_recursion_inc(); ret = dev_queue_xmit(skb); @@ -5548,8 +5549,8 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, #define BPF_TCP_SOCK_GET_COMMON(FIELD) \ do { \ - BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, FIELD) > \ - FIELD_SIZEOF(struct bpf_tcp_sock, FIELD)); \ + BUILD_BUG_ON(sizeof_field(struct tcp_sock, FIELD) > \ + sizeof_field(struct bpf_tcp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_sock, FIELD),\ si->dst_reg, si->src_reg, \ offsetof(struct tcp_sock, FIELD)); \ @@ -5557,9 +5558,9 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, #define BPF_INET_SOCK_GET_COMMON(FIELD) \ do { \ - BUILD_BUG_ON(FIELD_SIZEOF(struct inet_connection_sock, \ + BUILD_BUG_ON(sizeof_field(struct inet_connection_sock, \ FIELD) > \ - FIELD_SIZEOF(struct bpf_tcp_sock, FIELD)); \ + sizeof_field(struct bpf_tcp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct inet_connection_sock, \ FIELD), \ @@ -5574,7 +5575,7 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, switch (si->off) { case offsetof(struct bpf_tcp_sock, rtt_min): - BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, rtt_min) != + BUILD_BUG_ON(sizeof_field(struct tcp_sock, rtt_min) != sizeof(struct minmax)); BUILD_BUG_ON(sizeof(struct minmax) < sizeof(struct minmax_sample)); @@ -5739,8 +5740,8 @@ u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, #define BPF_XDP_SOCK_GET(FIELD) \ do { \ - BUILD_BUG_ON(FIELD_SIZEOF(struct xdp_sock, FIELD) > \ - FIELD_SIZEOF(struct bpf_xdp_sock, FIELD)); \ + BUILD_BUG_ON(sizeof_field(struct xdp_sock, FIELD) > \ + sizeof_field(struct bpf_xdp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_sock, FIELD),\ si->dst_reg, si->src_reg, \ offsetof(struct xdp_sock, FIELD)); \ @@ -7303,7 +7304,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, case offsetof(struct __sk_buff, cb[0]) ... offsetofend(struct __sk_buff, cb[4]) - 1: - BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, data) < 20); + BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, data) < 20); BUILD_BUG_ON((offsetof(struct sk_buff, cb) + offsetof(struct qdisc_skb_cb, data)) % sizeof(__u64)); @@ -7322,7 +7323,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, tc_classid): - BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, tc_classid) != 2); + BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, tc_classid) != 2); off = si->off; off -= offsetof(struct __sk_buff, tc_classid); @@ -7393,7 +7394,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, #endif break; case offsetof(struct __sk_buff, family): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, @@ -7404,7 +7405,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, 2, target_size)); break; case offsetof(struct __sk_buff, remote_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, @@ -7415,7 +7416,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, 4, target_size)); break; case offsetof(struct __sk_buff, local_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), @@ -7429,7 +7430,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, case offsetof(struct __sk_buff, remote_ip6[0]) ... offsetof(struct __sk_buff, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; @@ -7449,7 +7450,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, case offsetof(struct __sk_buff, local_ip6[0]) ... offsetof(struct __sk_buff, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; @@ -7468,7 +7469,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, remote_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, @@ -7483,7 +7484,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, local_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, @@ -7494,7 +7495,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, tstamp): - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tstamp) != 8); + BUILD_BUG_ON(sizeof_field(struct sk_buff, tstamp) != 8); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_DW, @@ -7532,7 +7533,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, target_size)); break; case offsetof(struct __sk_buff, wire_len): - BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, pkt_len) != 4); + BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, pkt_len) != 4); off = si->off; off -= offsetof(struct __sk_buff, wire_len); @@ -7562,7 +7563,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, switch (si->off) { case offsetof(struct bpf_sock, bound_dev_if): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_bound_dev_if) != 4); + BUILD_BUG_ON(sizeof_field(struct sock, sk_bound_dev_if) != 4); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, @@ -7573,7 +7574,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock, mark): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_mark) != 4); + BUILD_BUG_ON(sizeof_field(struct sock, sk_mark) != 4); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, @@ -7584,7 +7585,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock, priority): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_priority) != 4); + BUILD_BUG_ON(sizeof_field(struct sock, sk_priority) != 4); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, @@ -7600,7 +7601,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_family, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_family), target_size)); break; @@ -7627,7 +7628,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_rcv_saddr, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_rcv_saddr), target_size)); break; @@ -7636,7 +7637,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_daddr, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_daddr), target_size)); break; @@ -7650,7 +7651,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, bpf_target_off( struct sock_common, skc_v6_rcv_saddr.s6_addr32[0], - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]), target_size) + off); #else @@ -7667,7 +7668,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_v6_daddr.s6_addr32[0], - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]), target_size) + off); #else @@ -7681,7 +7682,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, BPF_FIELD_SIZEOF(struct sock_common, skc_num), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_num, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_num), target_size)); break; @@ -7691,7 +7692,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, BPF_FIELD_SIZEOF(struct sock_common, skc_dport), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_dport, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_dport), target_size)); break; @@ -7701,7 +7702,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, BPF_FIELD_SIZEOF(struct sock_common, skc_state), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_state, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_state), target_size)); break; @@ -7796,7 +7797,7 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type, si->src_reg, offsetof(S, F)); \ *insn++ = BPF_LDX_MEM( \ SIZE, si->dst_reg, si->dst_reg, \ - bpf_target_off(NS, NF, FIELD_SIZEOF(NS, NF), \ + bpf_target_off(NS, NF, sizeof_field(NS, NF), \ target_size) \ + OFF); \ } while (0) @@ -7827,7 +7828,7 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(S, F), tmp_reg, \ si->dst_reg, offsetof(S, F)); \ *insn++ = BPF_STX_MEM(SIZE, tmp_reg, si->src_reg, \ - bpf_target_off(NS, NF, FIELD_SIZEOF(NS, NF), \ + bpf_target_off(NS, NF, sizeof_field(NS, NF), \ target_size) \ + OFF); \ *insn++ = BPF_LDX_MEM(BPF_DW, tmp_reg, si->dst_reg, \ @@ -7889,8 +7890,8 @@ static u32 sock_addr_convert_ctx_access(enum bpf_access_type type, */ BUILD_BUG_ON(offsetof(struct sockaddr_in, sin_port) != offsetof(struct sockaddr_in6, sin6_port)); - BUILD_BUG_ON(FIELD_SIZEOF(struct sockaddr_in, sin_port) != - FIELD_SIZEOF(struct sockaddr_in6, sin6_port)); + BUILD_BUG_ON(sizeof_field(struct sockaddr_in, sin_port) != + sizeof_field(struct sockaddr_in6, sin6_port)); SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD(struct bpf_sock_addr_kern, struct sockaddr_in6, uaddr, sin6_port, tmp_reg); @@ -7956,8 +7957,8 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, /* Helper macro for adding read access to tcp_sock or sock fields. */ #define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ - BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) > \ - FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD)); \ + BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) > \ + sizeof_field(struct bpf_sock_ops, BPF_FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_fullsock), \ @@ -7990,8 +7991,8 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, #define SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ int reg = BPF_REG_9; \ - BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) > \ - FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD)); \ + BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) > \ + sizeof_field(struct bpf_sock_ops, BPF_FIELD)); \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == reg || si->src_reg == reg) \ @@ -8032,12 +8033,12 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, switch (si->off) { case offsetof(struct bpf_sock_ops, op) ... offsetof(struct bpf_sock_ops, replylong[3]): - BUILD_BUG_ON(FIELD_SIZEOF(struct bpf_sock_ops, op) != - FIELD_SIZEOF(struct bpf_sock_ops_kern, op)); - BUILD_BUG_ON(FIELD_SIZEOF(struct bpf_sock_ops, reply) != - FIELD_SIZEOF(struct bpf_sock_ops_kern, reply)); - BUILD_BUG_ON(FIELD_SIZEOF(struct bpf_sock_ops, replylong) != - FIELD_SIZEOF(struct bpf_sock_ops_kern, replylong)); + BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, op) != + sizeof_field(struct bpf_sock_ops_kern, op)); + BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, reply) != + sizeof_field(struct bpf_sock_ops_kern, reply)); + BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, replylong) != + sizeof_field(struct bpf_sock_ops_kern, replylong)); off = si->off; off -= offsetof(struct bpf_sock_ops, op); off += offsetof(struct bpf_sock_ops_kern, op); @@ -8050,7 +8051,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, family): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@ -8061,7 +8062,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, remote_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@ -8072,7 +8073,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, local_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( @@ -8087,7 +8088,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, case offsetof(struct bpf_sock_ops, remote_ip6[0]) ... offsetof(struct bpf_sock_ops, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; @@ -8108,7 +8109,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, case offsetof(struct bpf_sock_ops, local_ip6[0]) ... offsetof(struct bpf_sock_ops, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; @@ -8127,7 +8128,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, remote_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@ -8141,7 +8142,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, local_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@ -8161,7 +8162,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, state): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_state) != 1); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_state) != 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@ -8172,7 +8173,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, rtt_min): - BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, rtt_min) != + BUILD_BUG_ON(sizeof_field(struct tcp_sock, rtt_min) != sizeof(struct minmax)); BUILD_BUG_ON(sizeof(struct minmax) < sizeof(struct minmax_sample)); @@ -8183,7 +8184,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct tcp_sock, rtt_min) + - FIELD_SIZEOF(struct minmax_sample, t)); + sizeof_field(struct minmax_sample, t)); break; case offsetof(struct bpf_sock_ops, bpf_sock_ops_cb_flags): @@ -8325,7 +8326,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, offsetof(struct sk_msg, data_end)); break; case offsetof(struct sk_msg_md, family): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), @@ -8336,7 +8337,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct sk_msg_md, remote_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), @@ -8347,7 +8348,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct sk_msg_md, local_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( @@ -8362,7 +8363,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, case offsetof(struct sk_msg_md, remote_ip6[0]) ... offsetof(struct sk_msg_md, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; @@ -8383,7 +8384,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, case offsetof(struct sk_msg_md, local_ip6[0]) ... offsetof(struct sk_msg_md, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; @@ -8402,7 +8403,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct sk_msg_md, remote_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), @@ -8416,7 +8417,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct sk_msg_md, local_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), @@ -8806,7 +8807,7 @@ sk_reuseport_is_valid_access(int off, int size, /* Fields that allow narrowing */ case bpf_ctx_range(struct sk_reuseport_md, eth_protocol): - if (size < FIELD_SIZEOF(struct sk_buff, protocol)) + if (size < sizeof_field(struct sk_buff, protocol)) return false; /* fall through */ case bpf_ctx_range(struct sk_reuseport_md, ip_protocol): @@ -8824,7 +8825,7 @@ sk_reuseport_is_valid_access(int off, int size, *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_reuseport_kern, F), \ si->dst_reg, si->src_reg, \ bpf_target_off(struct sk_reuseport_kern, F, \ - FIELD_SIZEOF(struct sk_reuseport_kern, F), \ + sizeof_field(struct sk_reuseport_kern, F), \ target_size)); \ }) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index d524a693e00f..2dbbb030fbed 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -599,8 +599,8 @@ __skb_flow_dissect_gre(const struct sk_buff *skb, offset += sizeof(struct gre_base_hdr); if (hdr->flags & GRE_CSUM) - offset += FIELD_SIZEOF(struct gre_full_hdr, csum) + - FIELD_SIZEOF(struct gre_full_hdr, reserved1); + offset += sizeof_field(struct gre_full_hdr, csum) + + sizeof_field(struct gre_full_hdr, reserved1); if (hdr->flags & GRE_KEY) { const __be32 *keyid; @@ -622,11 +622,11 @@ __skb_flow_dissect_gre(const struct sk_buff *skb, else key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK; } - offset += FIELD_SIZEOF(struct gre_full_hdr, key); + offset += sizeof_field(struct gre_full_hdr, key); } if (hdr->flags & GRE_SEQ) - offset += FIELD_SIZEOF(struct pptp_gre_header, seq); + offset += sizeof_field(struct pptp_gre_header, seq); if (gre_ver == 0) { if (*p_proto == htons(ETH_P_TEB)) { @@ -653,7 +653,7 @@ __skb_flow_dissect_gre(const struct sk_buff *skb, u8 *ppp_hdr; if (hdr->flags & GRE_ACK) - offset += FIELD_SIZEOF(struct pptp_gre_header, ack); + offset += sizeof_field(struct pptp_gre_header, ack); ppp_hdr = __skb_header_pointer(skb, *p_nhoff + offset, sizeof(_ppp_hdr), diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 652da6369037..920784a9b7ff 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -98,9 +98,6 @@ static int neigh_blackhole(struct neighbour *neigh, struct sk_buff *skb) static void neigh_cleanup_and_release(struct neighbour *neigh) { - if (neigh->parms->neigh_cleanup) - neigh->parms->neigh_cleanup(neigh); - trace_neigh_cleanup_and_release(neigh, 0); __neigh_notify(neigh, RTM_DELNEIGH, 0, 0); call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 5c4624298996..4c826b8bf9b1 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -919,14 +919,17 @@ static int rx_queue_add_kobject(struct net_device *dev, int index) struct kobject *kobj = &queue->kobj; int error = 0; + /* Kobject_put later will trigger rx_queue_release call which + * decreases dev refcount: Take that reference here + */ + dev_hold(queue->dev); + kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, "rx-%u", index); if (error) goto err; - dev_hold(queue->dev); - if (dev->sysfs_rx_queue_group) { error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group); if (error) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 02916f43bf63..20bc406f3871 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1041,6 +1041,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_MIN_MTU */ + nla_total_size(4) /* IFLA_MAX_MTU */ + rtnl_prop_list_size(dev) + + nla_total_size(MAX_ADDR_LEN) /* IFLA_PERM_ADDRESS */ + 0; } @@ -1757,6 +1758,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, nla_put_s32(skb, IFLA_NEW_IFINDEX, new_ifindex) < 0) goto nla_put_failure; + if (memchr_inv(dev->perm_addr, '\0', dev->addr_len) && + nla_put(skb, IFLA_PERM_ADDRESS, dev->addr_len, dev->perm_addr)) + goto nla_put_failure; rcu_read_lock(); if (rtnl_fill_link_af(skb, dev, ext_filter_mask)) @@ -1822,6 +1826,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_PROP_LIST] = { .type = NLA_NESTED }, [IFLA_ALT_IFNAME] = { .type = NLA_STRING, .len = ALTIFNAMSIZ - 1 }, + [IFLA_PERM_ADDRESS] = { .type = NLA_REJECT }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 973a71f4bc89..44b0894d8ae1 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5472,12 +5472,15 @@ static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr, } /** - * skb_mpls_push() - push a new MPLS header after the mac header + * skb_mpls_push() - push a new MPLS header after mac_len bytes from start of + * the packet * * @skb: buffer * @mpls_lse: MPLS label stack entry to push * @mpls_proto: ethertype of the new MPLS header (expects 0x8847 or 0x8848) * @mac_len: length of the MAC header + * @ethernet: flag to indicate if the resulting packet after skb_mpls_push is + * ethernet * * Expects skb->data at mac header. * @@ -5501,7 +5504,7 @@ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, return err; if (!skb->inner_protocol) { - skb_set_inner_network_header(skb, mac_len); + skb_set_inner_network_header(skb, skb_network_offset(skb)); skb_set_inner_protocol(skb, skb->protocol); } @@ -5510,6 +5513,7 @@ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, mac_len); skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); + skb_reset_mac_len(skb); lse = mpls_hdr(skb); lse->label_stack_entry = mpls_lse; @@ -5529,7 +5533,7 @@ EXPORT_SYMBOL_GPL(skb_mpls_push); * @skb: buffer * @next_proto: ethertype of header after popped MPLS header * @mac_len: length of the MAC header - * @ethernet: flag to indicate if ethernet header is present in packet + * @ethernet: flag to indicate if the packet is ethernet * * Expects skb->data at mac header. * diff --git a/net/core/sock.c b/net/core/sock.c index 043db3ce023e..8459ad579f73 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2916,7 +2916,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_max_pacing_rate = ~0UL; sk->sk_pacing_rate = ~0UL; - sk->sk_pacing_shift = 10; + WRITE_ONCE(sk->sk_pacing_shift, 10); sk->sk_incoming_cpu = -1; sk_rx_queue_clear(sk); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index eb29e5adc84d..9f9e00ba3ad7 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -288,6 +288,7 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write, return ret; } +# ifdef CONFIG_HAVE_EBPF_JIT static int proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, @@ -298,6 +299,7 @@ proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write, return proc_dointvec_minmax(table, write, buffer, lenp, ppos); } +# endif /* CONFIG_HAVE_EBPF_JIT */ static int proc_dolongvec_minmax_bpf_restricted(struct ctl_table *table, int write, diff --git a/net/core/timestamping.c b/net/core/timestamping.c index 7911235706a9..04840697fe79 100644 --- a/net/core/timestamping.c +++ b/net/core/timestamping.c @@ -13,7 +13,7 @@ static unsigned int classify(const struct sk_buff *skb) { if (likely(skb->dev && skb->dev->phydev && - skb->dev->phydev->drv)) + skb->dev->phydev->mii_ts)) return ptp_classify_raw(skb); else return PTP_CLASS_NONE; @@ -21,7 +21,7 @@ static unsigned int classify(const struct sk_buff *skb) void skb_clone_tx_timestamp(struct sk_buff *skb) { - struct phy_device *phydev; + struct mii_timestamper *mii_ts; struct sk_buff *clone; unsigned int type; @@ -32,22 +32,22 @@ void skb_clone_tx_timestamp(struct sk_buff *skb) if (type == PTP_CLASS_NONE) return; - phydev = skb->dev->phydev; - if (likely(phydev->drv->txtstamp)) { + mii_ts = skb->dev->phydev->mii_ts; + if (likely(mii_ts->txtstamp)) { clone = skb_clone_sk(skb); if (!clone) return; - phydev->drv->txtstamp(phydev, clone, type); + mii_ts->txtstamp(mii_ts, clone, type); } } EXPORT_SYMBOL_GPL(skb_clone_tx_timestamp); bool skb_defer_rx_timestamp(struct sk_buff *skb) { - struct phy_device *phydev; + struct mii_timestamper *mii_ts; unsigned int type; - if (!skb->dev || !skb->dev->phydev || !skb->dev->phydev->drv) + if (!skb->dev || !skb->dev->phydev || !skb->dev->phydev->mii_ts) return false; if (skb_headroom(skb) < ETH_HLEN) @@ -62,9 +62,9 @@ bool skb_defer_rx_timestamp(struct sk_buff *skb) if (type == PTP_CLASS_NONE) return false; - phydev = skb->dev->phydev; - if (likely(phydev->drv->rxtstamp)) - return phydev->drv->rxtstamp(phydev, skb, type); + mii_ts = skb->dev->phydev->mii_ts; + if (likely(mii_ts->rxtstamp)) + return mii_ts->rxtstamp(mii_ts, skb, type); return false; } diff --git a/net/core/xdp.c b/net/core/xdp.c index 7c8390ad4dc6..8310714c47fd 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -36,7 +36,7 @@ static u32 xdp_mem_id_hashfn(const void *data, u32 len, u32 seed) const u32 *k = data; const u32 key = *k; - BUILD_BUG_ON(FIELD_SIZEOF(struct xdp_mem_allocator, mem.id) + BUILD_BUG_ON(sizeof_field(struct xdp_mem_allocator, mem.id) != sizeof(u32)); /* Use cyclic increasing ID as direct hash key */ @@ -56,7 +56,7 @@ static const struct rhashtable_params mem_id_rht_params = { .nelem_hint = 64, .head_offset = offsetof(struct xdp_mem_allocator, node), .key_offset = offsetof(struct xdp_mem_allocator, mem.id), - .key_len = FIELD_SIZEOF(struct xdp_mem_allocator, mem.id), + .key_len = sizeof_field(struct xdp_mem_allocator, mem.id), .max_size = MEM_ID_MAX, .min_size = 8, .automatic_shrinking = true, diff --git a/net/dccp/proto.c b/net/dccp/proto.c index a52e8ba1ced0..4af8a98fe784 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -1132,7 +1132,7 @@ static int __init dccp_init(void) int rc; BUILD_BUG_ON(sizeof(struct dccp_skb_cb) > - FIELD_SIZEOF(struct sk_buff, cb)); + sizeof_field(struct sk_buff, cb)); rc = percpu_counter_init(&dccp_orphan_count, 0, GFP_KERNEL); if (rc) goto out_fail; diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 1e6c3cac11e6..92663dcb3aa2 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -29,6 +29,12 @@ config NET_DSA_TAG_8021Q Drivers which use these helpers should select this as dependency. +config NET_DSA_TAG_AR9331 + tristate "Tag driver for Atheros AR9331 SoC with built-in switch" + help + Say Y or M if you want to enable support for tagging frames for + the Atheros AR9331 SoC with built-in switch. + config NET_DSA_TAG_BRCM_COMMON tristate default n diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 9a482c38bdb1..108486cfdeef 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -5,6 +5,7 @@ dsa_core-y += dsa.o dsa2.o master.o port.o slave.o switch.o # tagging formats obj-$(CONFIG_NET_DSA_TAG_8021Q) += tag_8021q.o +obj-$(CONFIG_NET_DSA_TAG_AR9331) += tag_ar9331.o obj-$(CONFIG_NET_DSA_TAG_BRCM_COMMON) += tag_brcm.o obj-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o obj-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 9ef2caa13f27..c66abbed4daf 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -124,7 +124,8 @@ static struct dsa_port *dsa_tree_find_port_by_node(struct dsa_switch_tree *dst, return NULL; } -struct dsa_link *dsa_link_touch(struct dsa_port *dp, struct dsa_port *link_dp) +static struct dsa_link *dsa_link_touch(struct dsa_port *dp, + struct dsa_port *link_dp) { struct dsa_switch *ds = dp->ds; struct dsa_switch_tree *dst; diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 2dd86d9bcda9..09ea2fd78c74 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -150,22 +150,6 @@ int dsa_port_vid_add(struct dsa_port *dp, u16 vid, u16 flags); int dsa_port_vid_del(struct dsa_port *dp, u16 vid); int dsa_port_link_register_of(struct dsa_port *dp); void dsa_port_link_unregister_of(struct dsa_port *dp); -void dsa_port_phylink_validate(struct phylink_config *config, - unsigned long *supported, - struct phylink_link_state *state); -void dsa_port_phylink_mac_pcs_get_state(struct phylink_config *config, - struct phylink_link_state *state); -void dsa_port_phylink_mac_config(struct phylink_config *config, - unsigned int mode, - const struct phylink_link_state *state); -void dsa_port_phylink_mac_an_restart(struct phylink_config *config); -void dsa_port_phylink_mac_link_down(struct phylink_config *config, - unsigned int mode, - phy_interface_t interface); -void dsa_port_phylink_mac_link_up(struct phylink_config *config, - unsigned int mode, - phy_interface_t interface, - struct phy_device *phydev); extern const struct phylink_mac_ops dsa_port_phylink_mac_ops; /* slave.c */ diff --git a/net/dsa/port.c b/net/dsa/port.c index 46ac9ba21987..ffb5601f7ed6 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -415,9 +415,9 @@ static struct phy_device *dsa_port_get_phy_device(struct dsa_port *dp) return phydev; } -void dsa_port_phylink_validate(struct phylink_config *config, - unsigned long *supported, - struct phylink_link_state *state) +static void dsa_port_phylink_validate(struct phylink_config *config, + unsigned long *supported, + struct phylink_link_state *state) { struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct dsa_switch *ds = dp->ds; @@ -427,10 +427,9 @@ void dsa_port_phylink_validate(struct phylink_config *config, ds->ops->phylink_validate(ds, dp->index, supported, state); } -EXPORT_SYMBOL_GPL(dsa_port_phylink_validate); -void dsa_port_phylink_mac_pcs_get_state(struct phylink_config *config, - struct phylink_link_state *state) +static void dsa_port_phylink_mac_pcs_get_state(struct phylink_config *config, + struct phylink_link_state *state) { struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct dsa_switch *ds = dp->ds; @@ -444,11 +443,10 @@ void dsa_port_phylink_mac_pcs_get_state(struct phylink_config *config, if (ds->ops->phylink_mac_link_state(ds, dp->index, state) < 0) state->link = 0; } -EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_pcs_get_state); -void dsa_port_phylink_mac_config(struct phylink_config *config, - unsigned int mode, - const struct phylink_link_state *state) +static void dsa_port_phylink_mac_config(struct phylink_config *config, + unsigned int mode, + const struct phylink_link_state *state) { struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct dsa_switch *ds = dp->ds; @@ -458,9 +456,8 @@ void dsa_port_phylink_mac_config(struct phylink_config *config, ds->ops->phylink_mac_config(ds, dp->index, mode, state); } -EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_config); -void dsa_port_phylink_mac_an_restart(struct phylink_config *config) +static void dsa_port_phylink_mac_an_restart(struct phylink_config *config) { struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct dsa_switch *ds = dp->ds; @@ -470,11 +467,10 @@ void dsa_port_phylink_mac_an_restart(struct phylink_config *config) ds->ops->phylink_mac_an_restart(ds, dp->index); } -EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_an_restart); -void dsa_port_phylink_mac_link_down(struct phylink_config *config, - unsigned int mode, - phy_interface_t interface) +static void dsa_port_phylink_mac_link_down(struct phylink_config *config, + unsigned int mode, + phy_interface_t interface) { struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct phy_device *phydev = NULL; @@ -491,12 +487,11 @@ void dsa_port_phylink_mac_link_down(struct phylink_config *config, ds->ops->phylink_mac_link_down(ds, dp->index, mode, interface); } -EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_link_down); -void dsa_port_phylink_mac_link_up(struct phylink_config *config, - unsigned int mode, - phy_interface_t interface, - struct phy_device *phydev) +static void dsa_port_phylink_mac_link_up(struct phylink_config *config, + unsigned int mode, + phy_interface_t interface, + struct phy_device *phydev) { struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct dsa_switch *ds = dp->ds; @@ -509,7 +504,6 @@ void dsa_port_phylink_mac_link_up(struct phylink_config *config, ds->ops->phylink_mac_link_up(ds, dp->index, mode, interface, phydev); } -EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_link_up); const struct phylink_mac_ops dsa_port_phylink_mac_ops = { .validate = dsa_port_phylink_validate, diff --git a/net/dsa/tag_ar9331.c b/net/dsa/tag_ar9331.c new file mode 100644 index 000000000000..466ffa92a474 --- /dev/null +++ b/net/dsa/tag_ar9331.c @@ -0,0 +1,96 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2019 Pengutronix, Oleksij Rempel <kernel@pengutronix.de> + */ + + +#include <linux/bitfield.h> +#include <linux/etherdevice.h> + +#include "dsa_priv.h" + +#define AR9331_HDR_LEN 2 +#define AR9331_HDR_VERSION 1 + +#define AR9331_HDR_VERSION_MASK GENMASK(15, 14) +#define AR9331_HDR_PRIORITY_MASK GENMASK(13, 12) +#define AR9331_HDR_TYPE_MASK GENMASK(10, 8) +#define AR9331_HDR_BROADCAST BIT(7) +#define AR9331_HDR_FROM_CPU BIT(6) +/* AR9331_HDR_RESERVED - not used or may be version field. + * According to the AR8216 doc it should 0b10. On AR9331 it is 0b11 on RX path + * and should be set to 0b11 to make it work. + */ +#define AR9331_HDR_RESERVED_MASK GENMASK(5, 4) +#define AR9331_HDR_PORT_NUM_MASK GENMASK(3, 0) + +static struct sk_buff *ar9331_tag_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + __le16 *phdr; + u16 hdr; + + if (skb_cow_head(skb, 0) < 0) + return NULL; + + phdr = skb_push(skb, AR9331_HDR_LEN); + + hdr = FIELD_PREP(AR9331_HDR_VERSION_MASK, AR9331_HDR_VERSION); + hdr |= AR9331_HDR_FROM_CPU | dp->index; + /* 0b10 for AR8216 and 0b11 for AR9331 */ + hdr |= AR9331_HDR_RESERVED_MASK; + + phdr[0] = cpu_to_le16(hdr); + + return skb; +} + +static struct sk_buff *ar9331_tag_rcv(struct sk_buff *skb, + struct net_device *ndev, + struct packet_type *pt) +{ + u8 ver, port; + u16 hdr; + + if (unlikely(!pskb_may_pull(skb, AR9331_HDR_LEN))) + return NULL; + + hdr = le16_to_cpu(*(__le16 *)skb_mac_header(skb)); + + ver = FIELD_GET(AR9331_HDR_VERSION_MASK, hdr); + if (unlikely(ver != AR9331_HDR_VERSION)) { + netdev_warn_once(ndev, "%s:%i wrong header version 0x%2x\n", + __func__, __LINE__, hdr); + return NULL; + } + + if (unlikely(hdr & AR9331_HDR_FROM_CPU)) { + netdev_warn_once(ndev, "%s:%i packet should not be from cpu 0x%2x\n", + __func__, __LINE__, hdr); + return NULL; + } + + skb_pull_rcsum(skb, AR9331_HDR_LEN); + + /* Get source port information */ + port = FIELD_GET(AR9331_HDR_PORT_NUM_MASK, hdr); + + skb->dev = dsa_master_find_slave(ndev, 0, port); + if (!skb->dev) + return NULL; + + return skb; +} + +static const struct dsa_device_ops ar9331_netdev_ops = { + .name = "ar9331", + .proto = DSA_TAG_PROTO_AR9331, + .xmit = ar9331_tag_xmit, + .rcv = ar9331_tag_rcv, + .overhead = AR9331_HDR_LEN, +}; + +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_AR9331); +module_dsa_tag_driver(ar9331_netdev_ops); diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 73605bcbb385..90d055c4df9e 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -84,8 +84,6 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, * (eg, 0x00=port1, 0x02=port3, 0x06=port7) */ -#define KSZ8795_INGRESS_TAG_LEN 1 - #define KSZ8795_TAIL_TAG_OVERRIDE BIT(6) #define KSZ8795_TAIL_TAG_LOOKUP BIT(7) @@ -96,12 +94,12 @@ static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev) u8 *tag; u8 *addr; - nskb = ksz_common_xmit(skb, dev, KSZ8795_INGRESS_TAG_LEN); + nskb = ksz_common_xmit(skb, dev, KSZ_INGRESS_TAG_LEN); if (!nskb) return NULL; /* Tag encoding */ - tag = skb_put(nskb, KSZ8795_INGRESS_TAG_LEN); + tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN); addr = skb_mac_header(nskb); *tag = 1 << dp->index; @@ -124,7 +122,7 @@ static const struct dsa_device_ops ksz8795_netdev_ops = { .proto = DSA_TAG_PROTO_KSZ8795, .xmit = ksz8795_xmit, .rcv = ksz8795_rcv, - .overhead = KSZ8795_INGRESS_TAG_LEN, + .overhead = KSZ_INGRESS_TAG_LEN, }; DSA_TAG_DRIVER(ksz8795_netdev_ops); diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile new file mode 100644 index 000000000000..f68387618973 --- /dev/null +++ b/net/ethtool/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only + +obj-y += ioctl.o common.o diff --git a/net/ethtool/common.c b/net/ethtool/common.c new file mode 100644 index 000000000000..0a8728565356 --- /dev/null +++ b/net/ethtool/common.c @@ -0,0 +1,171 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "common.h" + +const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { + [NETIF_F_SG_BIT] = "tx-scatter-gather", + [NETIF_F_IP_CSUM_BIT] = "tx-checksum-ipv4", + [NETIF_F_HW_CSUM_BIT] = "tx-checksum-ip-generic", + [NETIF_F_IPV6_CSUM_BIT] = "tx-checksum-ipv6", + [NETIF_F_HIGHDMA_BIT] = "highdma", + [NETIF_F_FRAGLIST_BIT] = "tx-scatter-gather-fraglist", + [NETIF_F_HW_VLAN_CTAG_TX_BIT] = "tx-vlan-hw-insert", + + [NETIF_F_HW_VLAN_CTAG_RX_BIT] = "rx-vlan-hw-parse", + [NETIF_F_HW_VLAN_CTAG_FILTER_BIT] = "rx-vlan-filter", + [NETIF_F_HW_VLAN_STAG_TX_BIT] = "tx-vlan-stag-hw-insert", + [NETIF_F_HW_VLAN_STAG_RX_BIT] = "rx-vlan-stag-hw-parse", + [NETIF_F_HW_VLAN_STAG_FILTER_BIT] = "rx-vlan-stag-filter", + [NETIF_F_VLAN_CHALLENGED_BIT] = "vlan-challenged", + [NETIF_F_GSO_BIT] = "tx-generic-segmentation", + [NETIF_F_LLTX_BIT] = "tx-lockless", + [NETIF_F_NETNS_LOCAL_BIT] = "netns-local", + [NETIF_F_GRO_BIT] = "rx-gro", + [NETIF_F_GRO_HW_BIT] = "rx-gro-hw", + [NETIF_F_LRO_BIT] = "rx-lro", + + [NETIF_F_TSO_BIT] = "tx-tcp-segmentation", + [NETIF_F_GSO_ROBUST_BIT] = "tx-gso-robust", + [NETIF_F_TSO_ECN_BIT] = "tx-tcp-ecn-segmentation", + [NETIF_F_TSO_MANGLEID_BIT] = "tx-tcp-mangleid-segmentation", + [NETIF_F_TSO6_BIT] = "tx-tcp6-segmentation", + [NETIF_F_FSO_BIT] = "tx-fcoe-segmentation", + [NETIF_F_GSO_GRE_BIT] = "tx-gre-segmentation", + [NETIF_F_GSO_GRE_CSUM_BIT] = "tx-gre-csum-segmentation", + [NETIF_F_GSO_IPXIP4_BIT] = "tx-ipxip4-segmentation", + [NETIF_F_GSO_IPXIP6_BIT] = "tx-ipxip6-segmentation", + [NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation", + [NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT] = "tx-udp_tnl-csum-segmentation", + [NETIF_F_GSO_PARTIAL_BIT] = "tx-gso-partial", + [NETIF_F_GSO_SCTP_BIT] = "tx-sctp-segmentation", + [NETIF_F_GSO_ESP_BIT] = "tx-esp-segmentation", + [NETIF_F_GSO_UDP_L4_BIT] = "tx-udp-segmentation", + + [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", + [NETIF_F_SCTP_CRC_BIT] = "tx-checksum-sctp", + [NETIF_F_FCOE_MTU_BIT] = "fcoe-mtu", + [NETIF_F_NTUPLE_BIT] = "rx-ntuple-filter", + [NETIF_F_RXHASH_BIT] = "rx-hashing", + [NETIF_F_RXCSUM_BIT] = "rx-checksum", + [NETIF_F_NOCACHE_COPY_BIT] = "tx-nocache-copy", + [NETIF_F_LOOPBACK_BIT] = "loopback", + [NETIF_F_RXFCS_BIT] = "rx-fcs", + [NETIF_F_RXALL_BIT] = "rx-all", + [NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload", + [NETIF_F_HW_TC_BIT] = "hw-tc-offload", + [NETIF_F_HW_ESP_BIT] = "esp-hw-offload", + [NETIF_F_HW_ESP_TX_CSUM_BIT] = "esp-tx-csum-hw-offload", + [NETIF_F_RX_UDP_TUNNEL_PORT_BIT] = "rx-udp_tunnel-port-offload", + [NETIF_F_HW_TLS_RECORD_BIT] = "tls-hw-record", + [NETIF_F_HW_TLS_TX_BIT] = "tls-hw-tx-offload", + [NETIF_F_HW_TLS_RX_BIT] = "tls-hw-rx-offload", +}; + +const char +rss_hash_func_strings[ETH_RSS_HASH_FUNCS_COUNT][ETH_GSTRING_LEN] = { + [ETH_RSS_HASH_TOP_BIT] = "toeplitz", + [ETH_RSS_HASH_XOR_BIT] = "xor", + [ETH_RSS_HASH_CRC32_BIT] = "crc32", +}; + +const char +tunable_strings[__ETHTOOL_TUNABLE_COUNT][ETH_GSTRING_LEN] = { + [ETHTOOL_ID_UNSPEC] = "Unspec", + [ETHTOOL_RX_COPYBREAK] = "rx-copybreak", + [ETHTOOL_TX_COPYBREAK] = "tx-copybreak", + [ETHTOOL_PFC_PREVENTION_TOUT] = "pfc-prevention-tout", +}; + +const char +phy_tunable_strings[__ETHTOOL_PHY_TUNABLE_COUNT][ETH_GSTRING_LEN] = { + [ETHTOOL_ID_UNSPEC] = "Unspec", + [ETHTOOL_PHY_DOWNSHIFT] = "phy-downshift", + [ETHTOOL_PHY_FAST_LINK_DOWN] = "phy-fast-link-down", + [ETHTOOL_PHY_EDPD] = "phy-energy-detect-power-down", +}; + +#define __LINK_MODE_NAME(speed, type, duplex) \ + #speed "base" #type "/" #duplex +#define __DEFINE_LINK_MODE_NAME(speed, type, duplex) \ + [ETHTOOL_LINK_MODE(speed, type, duplex)] = \ + __LINK_MODE_NAME(speed, type, duplex) +#define __DEFINE_SPECIAL_MODE_NAME(_mode, _name) \ + [ETHTOOL_LINK_MODE_ ## _mode ## _BIT] = _name + +const char link_mode_names[][ETH_GSTRING_LEN] = { + __DEFINE_LINK_MODE_NAME(10, T, Half), + __DEFINE_LINK_MODE_NAME(10, T, Full), + __DEFINE_LINK_MODE_NAME(100, T, Half), + __DEFINE_LINK_MODE_NAME(100, T, Full), + __DEFINE_LINK_MODE_NAME(1000, T, Half), + __DEFINE_LINK_MODE_NAME(1000, T, Full), + __DEFINE_SPECIAL_MODE_NAME(Autoneg, "Autoneg"), + __DEFINE_SPECIAL_MODE_NAME(TP, "TP"), + __DEFINE_SPECIAL_MODE_NAME(AUI, "AUI"), + __DEFINE_SPECIAL_MODE_NAME(MII, "MII"), + __DEFINE_SPECIAL_MODE_NAME(FIBRE, "FIBRE"), + __DEFINE_SPECIAL_MODE_NAME(BNC, "BNC"), + __DEFINE_LINK_MODE_NAME(10000, T, Full), + __DEFINE_SPECIAL_MODE_NAME(Pause, "Pause"), + __DEFINE_SPECIAL_MODE_NAME(Asym_Pause, "Asym_Pause"), + __DEFINE_LINK_MODE_NAME(2500, X, Full), + __DEFINE_SPECIAL_MODE_NAME(Backplane, "Backplane"), + __DEFINE_LINK_MODE_NAME(1000, KX, Full), + __DEFINE_LINK_MODE_NAME(10000, KX4, Full), + __DEFINE_LINK_MODE_NAME(10000, KR, Full), + __DEFINE_SPECIAL_MODE_NAME(10000baseR_FEC, "10000baseR_FEC"), + __DEFINE_LINK_MODE_NAME(20000, MLD2, Full), + __DEFINE_LINK_MODE_NAME(20000, KR2, Full), + __DEFINE_LINK_MODE_NAME(40000, KR4, Full), + __DEFINE_LINK_MODE_NAME(40000, CR4, Full), + __DEFINE_LINK_MODE_NAME(40000, SR4, Full), + __DEFINE_LINK_MODE_NAME(40000, LR4, Full), + __DEFINE_LINK_MODE_NAME(56000, KR4, Full), + __DEFINE_LINK_MODE_NAME(56000, CR4, Full), + __DEFINE_LINK_MODE_NAME(56000, SR4, Full), + __DEFINE_LINK_MODE_NAME(56000, LR4, Full), + __DEFINE_LINK_MODE_NAME(25000, CR, Full), + __DEFINE_LINK_MODE_NAME(25000, KR, Full), + __DEFINE_LINK_MODE_NAME(25000, SR, Full), + __DEFINE_LINK_MODE_NAME(50000, CR2, Full), + __DEFINE_LINK_MODE_NAME(50000, KR2, Full), + __DEFINE_LINK_MODE_NAME(100000, KR4, Full), + __DEFINE_LINK_MODE_NAME(100000, SR4, Full), + __DEFINE_LINK_MODE_NAME(100000, CR4, Full), + __DEFINE_LINK_MODE_NAME(100000, LR4_ER4, Full), + __DEFINE_LINK_MODE_NAME(50000, SR2, Full), + __DEFINE_LINK_MODE_NAME(1000, X, Full), + __DEFINE_LINK_MODE_NAME(10000, CR, Full), + __DEFINE_LINK_MODE_NAME(10000, SR, Full), + __DEFINE_LINK_MODE_NAME(10000, LR, Full), + __DEFINE_LINK_MODE_NAME(10000, LRM, Full), + __DEFINE_LINK_MODE_NAME(10000, ER, Full), + __DEFINE_LINK_MODE_NAME(2500, T, Full), + __DEFINE_LINK_MODE_NAME(5000, T, Full), + __DEFINE_SPECIAL_MODE_NAME(FEC_NONE, "None"), + __DEFINE_SPECIAL_MODE_NAME(FEC_RS, "RS"), + __DEFINE_SPECIAL_MODE_NAME(FEC_BASER, "BASER"), + __DEFINE_LINK_MODE_NAME(50000, KR, Full), + __DEFINE_LINK_MODE_NAME(50000, SR, Full), + __DEFINE_LINK_MODE_NAME(50000, CR, Full), + __DEFINE_LINK_MODE_NAME(50000, LR_ER_FR, Full), + __DEFINE_LINK_MODE_NAME(50000, DR, Full), + __DEFINE_LINK_MODE_NAME(100000, KR2, Full), + __DEFINE_LINK_MODE_NAME(100000, SR2, Full), + __DEFINE_LINK_MODE_NAME(100000, CR2, Full), + __DEFINE_LINK_MODE_NAME(100000, LR2_ER2_FR2, Full), + __DEFINE_LINK_MODE_NAME(100000, DR2, Full), + __DEFINE_LINK_MODE_NAME(200000, KR4, Full), + __DEFINE_LINK_MODE_NAME(200000, SR4, Full), + __DEFINE_LINK_MODE_NAME(200000, LR4_ER4_FR4, Full), + __DEFINE_LINK_MODE_NAME(200000, DR4, Full), + __DEFINE_LINK_MODE_NAME(200000, CR4, Full), + __DEFINE_LINK_MODE_NAME(100, T1, Full), + __DEFINE_LINK_MODE_NAME(1000, T1, Full), + __DEFINE_LINK_MODE_NAME(400000, KR8, Full), + __DEFINE_LINK_MODE_NAME(400000, SR8, Full), + __DEFINE_LINK_MODE_NAME(400000, LR8_ER8_FR8, Full), + __DEFINE_LINK_MODE_NAME(400000, DR8, Full), + __DEFINE_LINK_MODE_NAME(400000, CR8, Full), +}; +static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); diff --git a/net/ethtool/common.h b/net/ethtool/common.h new file mode 100644 index 000000000000..bbb788908cb1 --- /dev/null +++ b/net/ethtool/common.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _ETHTOOL_COMMON_H +#define _ETHTOOL_COMMON_H + +#include <linux/ethtool.h> + +/* compose link mode index from speed, type and duplex */ +#define ETHTOOL_LINK_MODE(speed, type, duplex) \ + ETHTOOL_LINK_MODE_ ## speed ## base ## type ## _ ## duplex ## _BIT + +extern const char +netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]; +extern const char +rss_hash_func_strings[ETH_RSS_HASH_FUNCS_COUNT][ETH_GSTRING_LEN]; +extern const char +tunable_strings[__ETHTOOL_TUNABLE_COUNT][ETH_GSTRING_LEN]; +extern const char +phy_tunable_strings[__ETHTOOL_PHY_TUNABLE_COUNT][ETH_GSTRING_LEN]; +extern const char link_mode_names[][ETH_GSTRING_LEN]; + +#endif /* _ETHTOOL_COMMON_H */ diff --git a/net/core/ethtool.c b/net/ethtool/ioctl.c index cd9bc67381b2..88f7cddf5a6f 100644 --- a/net/core/ethtool.c +++ b/net/ethtool/ioctl.c @@ -27,6 +27,8 @@ #include <net/xdp_sock.h> #include <net/flow_offload.h> +#include "common.h" + /* * Some useful ethtool_ops methods that're device independent. * If we find that all drivers want to do the same thing here, @@ -54,88 +56,6 @@ EXPORT_SYMBOL(ethtool_op_get_ts_info); #define ETHTOOL_DEV_FEATURE_WORDS ((NETDEV_FEATURE_COUNT + 31) / 32) -static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { - [NETIF_F_SG_BIT] = "tx-scatter-gather", - [NETIF_F_IP_CSUM_BIT] = "tx-checksum-ipv4", - [NETIF_F_HW_CSUM_BIT] = "tx-checksum-ip-generic", - [NETIF_F_IPV6_CSUM_BIT] = "tx-checksum-ipv6", - [NETIF_F_HIGHDMA_BIT] = "highdma", - [NETIF_F_FRAGLIST_BIT] = "tx-scatter-gather-fraglist", - [NETIF_F_HW_VLAN_CTAG_TX_BIT] = "tx-vlan-hw-insert", - - [NETIF_F_HW_VLAN_CTAG_RX_BIT] = "rx-vlan-hw-parse", - [NETIF_F_HW_VLAN_CTAG_FILTER_BIT] = "rx-vlan-filter", - [NETIF_F_HW_VLAN_STAG_TX_BIT] = "tx-vlan-stag-hw-insert", - [NETIF_F_HW_VLAN_STAG_RX_BIT] = "rx-vlan-stag-hw-parse", - [NETIF_F_HW_VLAN_STAG_FILTER_BIT] = "rx-vlan-stag-filter", - [NETIF_F_VLAN_CHALLENGED_BIT] = "vlan-challenged", - [NETIF_F_GSO_BIT] = "tx-generic-segmentation", - [NETIF_F_LLTX_BIT] = "tx-lockless", - [NETIF_F_NETNS_LOCAL_BIT] = "netns-local", - [NETIF_F_GRO_BIT] = "rx-gro", - [NETIF_F_GRO_HW_BIT] = "rx-gro-hw", - [NETIF_F_LRO_BIT] = "rx-lro", - - [NETIF_F_TSO_BIT] = "tx-tcp-segmentation", - [NETIF_F_GSO_ROBUST_BIT] = "tx-gso-robust", - [NETIF_F_TSO_ECN_BIT] = "tx-tcp-ecn-segmentation", - [NETIF_F_TSO_MANGLEID_BIT] = "tx-tcp-mangleid-segmentation", - [NETIF_F_TSO6_BIT] = "tx-tcp6-segmentation", - [NETIF_F_FSO_BIT] = "tx-fcoe-segmentation", - [NETIF_F_GSO_GRE_BIT] = "tx-gre-segmentation", - [NETIF_F_GSO_GRE_CSUM_BIT] = "tx-gre-csum-segmentation", - [NETIF_F_GSO_IPXIP4_BIT] = "tx-ipxip4-segmentation", - [NETIF_F_GSO_IPXIP6_BIT] = "tx-ipxip6-segmentation", - [NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation", - [NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT] = "tx-udp_tnl-csum-segmentation", - [NETIF_F_GSO_PARTIAL_BIT] = "tx-gso-partial", - [NETIF_F_GSO_SCTP_BIT] = "tx-sctp-segmentation", - [NETIF_F_GSO_ESP_BIT] = "tx-esp-segmentation", - [NETIF_F_GSO_UDP_L4_BIT] = "tx-udp-segmentation", - - [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", - [NETIF_F_SCTP_CRC_BIT] = "tx-checksum-sctp", - [NETIF_F_FCOE_MTU_BIT] = "fcoe-mtu", - [NETIF_F_NTUPLE_BIT] = "rx-ntuple-filter", - [NETIF_F_RXHASH_BIT] = "rx-hashing", - [NETIF_F_RXCSUM_BIT] = "rx-checksum", - [NETIF_F_NOCACHE_COPY_BIT] = "tx-nocache-copy", - [NETIF_F_LOOPBACK_BIT] = "loopback", - [NETIF_F_RXFCS_BIT] = "rx-fcs", - [NETIF_F_RXALL_BIT] = "rx-all", - [NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload", - [NETIF_F_HW_TC_BIT] = "hw-tc-offload", - [NETIF_F_HW_ESP_BIT] = "esp-hw-offload", - [NETIF_F_HW_ESP_TX_CSUM_BIT] = "esp-tx-csum-hw-offload", - [NETIF_F_RX_UDP_TUNNEL_PORT_BIT] = "rx-udp_tunnel-port-offload", - [NETIF_F_HW_TLS_RECORD_BIT] = "tls-hw-record", - [NETIF_F_HW_TLS_TX_BIT] = "tls-hw-tx-offload", - [NETIF_F_HW_TLS_RX_BIT] = "tls-hw-rx-offload", -}; - -static const char -rss_hash_func_strings[ETH_RSS_HASH_FUNCS_COUNT][ETH_GSTRING_LEN] = { - [ETH_RSS_HASH_TOP_BIT] = "toeplitz", - [ETH_RSS_HASH_XOR_BIT] = "xor", - [ETH_RSS_HASH_CRC32_BIT] = "crc32", -}; - -static const char -tunable_strings[__ETHTOOL_TUNABLE_COUNT][ETH_GSTRING_LEN] = { - [ETHTOOL_ID_UNSPEC] = "Unspec", - [ETHTOOL_RX_COPYBREAK] = "rx-copybreak", - [ETHTOOL_TX_COPYBREAK] = "tx-copybreak", - [ETHTOOL_PFC_PREVENTION_TOUT] = "pfc-prevention-tout", -}; - -static const char -phy_tunable_strings[__ETHTOOL_PHY_TUNABLE_COUNT][ETH_GSTRING_LEN] = { - [ETHTOOL_ID_UNSPEC] = "Unspec", - [ETHTOOL_PHY_DOWNSHIFT] = "phy-downshift", - [ETHTOOL_PHY_FAST_LINK_DOWN] = "phy-fast-link-down", - [ETHTOOL_PHY_EDPD] = "phy-energy-detect-power-down", -}; - static int ethtool_get_features(struct net_device *dev, void __user *useraddr) { struct ethtool_gfeatures cmd = { @@ -234,6 +154,9 @@ static int __ethtool_get_sset_count(struct net_device *dev, int sset) !ops->get_ethtool_phy_stats) return phy_ethtool_get_sset_count(dev->phydev); + if (sset == ETH_SS_LINK_MODES) + return __ETHTOOL_LINK_MODE_MASK_NBITS; + if (ops->get_sset_count && ops->get_strings) return ops->get_sset_count(dev, sset); else @@ -258,6 +181,9 @@ static void __ethtool_get_strings(struct net_device *dev, else if (stringset == ETH_SS_PHY_STATS && dev->phydev && !ops->get_ethtool_phy_stats) phy_ethtool_get_strings(dev->phydev, data); + else if (stringset == ETH_SS_LINK_MODES) + memcpy(data, link_mode_names, + __ETHTOOL_LINK_MODE_MASK_NBITS * ETH_GSTRING_LEN); else /* ops->get_strings is valid because checked earlier */ ops->get_strings(dev, stringset, data); @@ -2170,8 +2096,8 @@ static int ethtool_get_ts_info(struct net_device *dev, void __user *useraddr) memset(&info, 0, sizeof(info)); info.cmd = ETHTOOL_GET_TS_INFO; - if (phydev && phydev->drv && phydev->drv->ts_info) { - err = phydev->drv->ts_info(phydev, &info); + if (phy_has_tsinfo(phydev)) { + err = phy_ts_info(phydev, &info); } else if (ops->get_ts_info) { err = ops->get_ts_info(dev, &info); } else { diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index b9df9c09b84e..b92a42433a7d 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -980,9 +980,12 @@ static struct key_vector *fib_find_node(struct trie *t, /* Return the first fib alias matching TOS with * priority less than or equal to PRIO. + * If 'find_first' is set, return the first matching + * fib alias, regardless of TOS and priority. */ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen, - u8 tos, u32 prio, u32 tb_id) + u8 tos, u32 prio, u32 tb_id, + bool find_first) { struct fib_alias *fa; @@ -998,6 +1001,8 @@ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen, continue; if (fa->tb_id != tb_id) break; + if (find_first) + return fa; if (fa->fa_tos > tos) continue; if (fa->fa_info->fib_priority >= prio || fa->fa_tos < tos) @@ -1063,9 +1068,6 @@ noleaf: return -ENOMEM; } -/* fib notifier for ADD is sent before calling fib_insert_alias with - * the expectation that the only possible failure ENOMEM - */ static int fib_insert_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *new, struct fib_alias *fa, t_key key) @@ -1118,11 +1120,13 @@ static bool fib_valid_key_len(u32 key, u8 plen, struct netlink_ext_ack *extack) return true; } +static void fib_remove_alias(struct trie *t, struct key_vector *tp, + struct key_vector *l, struct fib_alias *old); + /* Caller must hold RTNL. */ int fib_table_insert(struct net *net, struct fib_table *tb, struct fib_config *cfg, struct netlink_ext_ack *extack) { - enum fib_event_type event = FIB_EVENT_ENTRY_ADD; struct trie *t = (struct trie *)tb->tb_data; struct fib_alias *fa, *new_fa; struct key_vector *l, *tp; @@ -1149,7 +1153,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, l = fib_find_node(t, &tp, key); fa = l ? fib_find_alias(&l->leaf, slen, tos, fi->fib_priority, - tb->tb_id) : NULL; + tb->tb_id, false) : NULL; /* Now fa, if non-NULL, points to the first fib alias * with the same keys [prefix,tos,priority], if such key already @@ -1217,12 +1221,17 @@ int fib_table_insert(struct net *net, struct fib_table *tb, new_fa->tb_id = tb->tb_id; new_fa->fa_default = -1; - err = call_fib_entry_notifiers(net, - FIB_EVENT_ENTRY_REPLACE, - key, plen, new_fa, - extack); - if (err) - goto out_free_new_fa; + if (fib_find_alias(&l->leaf, fa->fa_slen, 0, 0, + tb->tb_id, true) == fa) { + enum fib_event_type fib_event; + + fib_event = FIB_EVENT_ENTRY_REPLACE; + err = call_fib_entry_notifiers(net, fib_event, + key, plen, + new_fa, extack); + if (err) + goto out_free_new_fa; + } rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, nlflags); @@ -1244,12 +1253,10 @@ int fib_table_insert(struct net *net, struct fib_table *tb, if (fa_match) goto out; - if (cfg->fc_nlflags & NLM_F_APPEND) { - event = FIB_EVENT_ENTRY_APPEND; + if (cfg->fc_nlflags & NLM_F_APPEND) nlflags |= NLM_F_APPEND; - } else { + else fa = fa_first; - } } err = -ENOENT; if (!(cfg->fc_nlflags & NLM_F_CREATE)) @@ -1269,14 +1276,26 @@ int fib_table_insert(struct net *net, struct fib_table *tb, new_fa->tb_id = tb->tb_id; new_fa->fa_default = -1; - err = call_fib_entry_notifiers(net, event, key, plen, new_fa, extack); - if (err) - goto out_free_new_fa; - /* Insert new entry to the list. */ err = fib_insert_alias(t, tp, l, new_fa, fa, key); if (err) - goto out_fib_notif; + goto out_free_new_fa; + + /* The alias was already inserted, so the node must exist. */ + l = l ? l : fib_find_node(t, &tp, key); + if (WARN_ON_ONCE(!l)) + goto out_free_new_fa; + + if (fib_find_alias(&l->leaf, new_fa->fa_slen, 0, 0, tb->tb_id, true) == + new_fa) { + enum fib_event_type fib_event; + + fib_event = FIB_EVENT_ENTRY_REPLACE; + err = call_fib_entry_notifiers(net, fib_event, key, plen, + new_fa, extack); + if (err) + goto out_remove_new_fa; + } if (!plen) tb->tb_num_default++; @@ -1287,14 +1306,8 @@ int fib_table_insert(struct net *net, struct fib_table *tb, succeeded: return 0; -out_fib_notif: - /* notifier was sent that entry would be added to trie, but - * the add failed and need to recover. Only failure for - * fib_insert_alias is ENOMEM. - */ - NL_SET_ERR_MSG(extack, "Failed to insert route into trie"); - call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, key, - plen, new_fa, NULL); +out_remove_new_fa: + fib_remove_alias(t, tp, l, new_fa); out_free_new_fa: kmem_cache_free(fn_alias_kmem, new_fa); out: @@ -1545,6 +1558,36 @@ static void fib_remove_alias(struct trie *t, struct key_vector *tp, node_pull_suffix(tp, fa->fa_slen); } +static void fib_notify_alias_delete(struct net *net, u32 key, + struct hlist_head *fah, + struct fib_alias *fa_to_delete, + struct netlink_ext_ack *extack) +{ + struct fib_alias *fa_next, *fa_to_notify; + u32 tb_id = fa_to_delete->tb_id; + u8 slen = fa_to_delete->fa_slen; + enum fib_event_type fib_event; + + /* Do not notify if we do not care about the route. */ + if (fib_find_alias(fah, slen, 0, 0, tb_id, true) != fa_to_delete) + return; + + /* Determine if the route should be replaced by the next route in the + * list. + */ + fa_next = hlist_entry_safe(fa_to_delete->fa_list.next, + struct fib_alias, fa_list); + if (fa_next && fa_next->fa_slen == slen && fa_next->tb_id == tb_id) { + fib_event = FIB_EVENT_ENTRY_REPLACE; + fa_to_notify = fa_next; + } else { + fib_event = FIB_EVENT_ENTRY_DEL; + fa_to_notify = fa_to_delete; + } + call_fib_entry_notifiers(net, fib_event, key, KEYLENGTH - slen, + fa_to_notify, extack); +} + /* Caller must hold RTNL. */ int fib_table_delete(struct net *net, struct fib_table *tb, struct fib_config *cfg, struct netlink_ext_ack *extack) @@ -1566,7 +1609,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb, if (!l) return -ESRCH; - fa = fib_find_alias(&l->leaf, slen, tos, 0, tb->tb_id); + fa = fib_find_alias(&l->leaf, slen, tos, 0, tb->tb_id, false); if (!fa) return -ESRCH; @@ -1598,8 +1641,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb, if (!fa_to_delete) return -ESRCH; - call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, key, plen, - fa_to_delete, extack); + fib_notify_alias_delete(net, key, &l->leaf, fa_to_delete, extack); rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id, &cfg->fc_nlinfo, 0); @@ -1923,10 +1965,8 @@ int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all) continue; } - call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, - n->key, - KEYLENGTH - fa->fa_slen, fa, - NULL); + fib_notify_alias_delete(net, n->key, &n->leaf, fa, + NULL); hlist_del_rcu(&fa->fa_list); fib_release_info(fa->fa_info); alias_free_mem_rcu(fa); @@ -2022,6 +2062,7 @@ static int fib_leaf_notify(struct key_vector *l, struct fib_table *tb, struct netlink_ext_ack *extack) { struct fib_alias *fa; + int last_slen = -1; int err; hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { @@ -2036,8 +2077,12 @@ static int fib_leaf_notify(struct key_vector *l, struct fib_table *tb, if (tb->tb_id != fa->tb_id) continue; - err = call_fib_entry_notifier(nb, FIB_EVENT_ENTRY_ADD, l->key, - KEYLENGTH - fa->fa_slen, + if (fa->fa_slen == last_slen) + continue; + + last_slen = fa->fa_slen; + err = call_fib_entry_notifier(nb, FIB_EVENT_ENTRY_REPLACE, + l->key, KEYLENGTH - fa->fa_slen, fa, extack); if (err) return err; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index af154977904c..f11e997e517b 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -911,11 +911,12 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, for (i = s_i; i < INET_LHTABLE_SIZE; i++) { struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; num = 0; ilb = &hashinfo->listening_hash[i]; spin_lock(&ilb->lock); - sk_for_each(sk, &ilb->head) { + sk_nulls_for_each(sk, node, &ilb->nulls_head) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 83fb00153018..2bbaaf0c7176 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -516,10 +516,11 @@ static int inet_reuseport_add_sock(struct sock *sk, struct inet_listen_hashbucket *ilb) { struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash; + const struct hlist_nulls_node *node; struct sock *sk2; kuid_t uid = sock_i_uid(sk); - sk_for_each_rcu(sk2, &ilb->head) { + sk_nulls_for_each_rcu(sk2, node, &ilb->nulls_head) { if (sk2 != sk && sk2->sk_family == sk->sk_family && ipv6_only_sock(sk2) == ipv6_only_sock(sk) && @@ -555,9 +556,9 @@ int __inet_hash(struct sock *sk, struct sock *osk) } if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && sk->sk_family == AF_INET6) - hlist_add_tail_rcu(&sk->sk_node, &ilb->head); + __sk_nulls_add_node_tail_rcu(sk, &ilb->nulls_head); else - hlist_add_head_rcu(&sk->sk_node, &ilb->head); + __sk_nulls_add_node_rcu(sk, &ilb->nulls_head); inet_hash2(hashinfo, sk); ilb->count++; sock_set_flag(sk, SOCK_RCU_FREE); @@ -606,11 +607,9 @@ void inet_unhash(struct sock *sk) reuseport_detach_sock(sk); if (ilb) { inet_unhash2(hashinfo, sk); - __sk_del_node_init(sk); - ilb->count--; - } else { - __sk_nulls_del_node_init_rcu(sk); + ilb->count--; } + __sk_nulls_del_node_init_rcu(sk); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); unlock: spin_unlock_bh(lock); @@ -750,7 +749,8 @@ void inet_hashinfo_init(struct inet_hashinfo *h) for (i = 0; i < INET_LHTABLE_SIZE; i++) { spin_lock_init(&h->listening_hash[i].lock); - INIT_HLIST_HEAD(&h->listening_hash[i].head); + INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].nulls_head, + i + LISTENING_NULLS_BASE); h->listening_hash[i].count = 0; } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 572b6307a2df..8274f98c511c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1464,8 +1464,8 @@ static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = { [IFLA_GRE_OFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_IKEY] = { .type = NLA_U32 }, [IFLA_GRE_OKEY] = { .type = NLA_U32 }, - [IFLA_GRE_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) }, - [IFLA_GRE_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_GRE_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, + [IFLA_GRE_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_GRE_TTL] = { .type = NLA_U8 }, [IFLA_GRE_TOS] = { .type = NLA_U8 }, [IFLA_GRE_PMTUDISC] = { .type = NLA_U8 }, diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index cfb025606793..9b153c7fcbb4 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -580,8 +580,8 @@ static const struct nla_policy vti_policy[IFLA_VTI_MAX + 1] = { [IFLA_VTI_LINK] = { .type = NLA_U32 }, [IFLA_VTI_IKEY] = { .type = NLA_U32 }, [IFLA_VTI_OKEY] = { .type = NLA_U32 }, - [IFLA_VTI_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) }, - [IFLA_VTI_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_VTI_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, + [IFLA_VTI_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_VTI_FWMARK] = { .type = NLA_U32 }, }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 09e2cae92956..f09fbc85b108 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1085,8 +1085,7 @@ do_error: goto out; out_err: /* make sure we wake any epoll edge trigger waiter */ - if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && - err == -EAGAIN)) { + if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } @@ -1417,8 +1416,7 @@ out_err: sock_zerocopy_put_abort(uarg, true); err = sk_stream_error(sk, flags, err); /* make sure we wake any epoll edge trigger waiter */ - if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && - err == -EAGAIN)) { + if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } @@ -1778,6 +1776,8 @@ static int tcp_zerocopy_receive(struct sock *sk, while (length + PAGE_SIZE <= zc->length) { if (zc->recv_skip_hint < PAGE_SIZE) { if (skb) { + if (zc->recv_skip_hint > 0) + break; skb = skb->next; offset = seq - TCP_SKB_CB(skb)->seq; } else { @@ -3947,7 +3947,7 @@ void __init tcp_init(void) BUILD_BUG_ON(TCP_MIN_SND_MSS <= MAX_TCP_OPTION_SPACE); BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > - FIELD_SIZEOF(struct sk_buff, cb)); + sizeof_field(struct sk_buff, cb)); percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL); percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL); diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 32772d6ded4e..a6545ef0d27b 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -306,7 +306,8 @@ static u32 bbr_tso_segs_goal(struct sock *sk) /* Sort of tcp_tso_autosize() but ignoring * driver provided sk_gso_max_size. */ - bytes = min_t(unsigned long, sk->sk_pacing_rate >> sk->sk_pacing_shift, + bytes = min_t(unsigned long, + sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift), GSO_MAX_SIZE - 1 - MAX_TCP_HEADER); segs = max_t(u32, bytes / tp->mss_cache, bbr_min_tso_segs(sk)); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 26637fce324d..6f52e5288a6f 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2147,13 +2147,14 @@ static void *listening_get_next(struct seq_file *seq, void *cur) struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; struct sock *sk = cur; if (!sk) { get_head: ilb = &tcp_hashinfo.listening_hash[st->bucket]; spin_lock(&ilb->lock); - sk = sk_head(&ilb->head); + sk = sk_nulls_head(&ilb->nulls_head); st->offset = 0; goto get_sk; } @@ -2161,9 +2162,9 @@ get_head: ++st->num; ++st->offset; - sk = sk_next(sk); + sk = sk_nulls_next(sk); get_sk: - sk_for_each_from(sk) { + sk_nulls_for_each_from(sk, node) { if (!net_eq(sock_net(sk), net)) continue; if (sk->sk_family == afinfo->family) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b184f03d7437..1f7735ca8f22 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1725,7 +1725,7 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, u32 bytes, segs; bytes = min_t(unsigned long, - sk->sk_pacing_rate >> sk->sk_pacing_shift, + sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift), sk->sk_gso_max_size - 1 - MAX_TCP_HEADER); /* Goal is to send at least one packet per ms, @@ -2260,7 +2260,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, limit = max_t(unsigned long, 2 * skb->truesize, - sk->sk_pacing_rate >> sk->sk_pacing_shift); + sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift)); if (sk->sk_pacing_status == SK_PACING_NONE) limit = min_t(unsigned long, limit, sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes); @@ -2438,6 +2438,14 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (tcp_small_queue_check(sk, skb, 0)) break; + /* Argh, we hit an empty skb(), presumably a thread + * is sleeping in sendmsg()/sk_stream_wait_memory(). + * We do not want to send a pure-ack packet and have + * a strange looking rtx queue with empty packet(s). + */ + if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) + break; + if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; @@ -3121,7 +3129,7 @@ void sk_forced_mem_schedule(struct sock *sk, int size) */ void tcp_send_fin(struct sock *sk) { - struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk); + struct sk_buff *skb, *tskb, *tail = tcp_write_queue_tail(sk); struct tcp_sock *tp = tcp_sk(sk); /* Optimization, tack on the FIN if we have one skb in write queue and @@ -3129,6 +3137,7 @@ void tcp_send_fin(struct sock *sk) * Note: in the latter case, FIN packet will be sent after a timeout, * as TCP stack thinks it has already been transmitted. */ + tskb = tail; if (!tskb && tcp_under_memory_pressure(sk)) tskb = skb_rb_last(&sk->tcp_rtx_queue); @@ -3136,7 +3145,7 @@ void tcp_send_fin(struct sock *sk) TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; TCP_SKB_CB(tskb)->end_seq++; tp->write_seq++; - if (tcp_write_queue_empty(sk)) { + if (!tail) { /* This means tskb was already sent. * Pretend we included the FIN on previous transmit. * We need to set tp->snd_nxt to the value it would have diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 98d82305d6de..39d861d00377 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5231,16 +5231,16 @@ static int inet6_rtm_valid_getaddr_req(struct sk_buff *skb, return -EINVAL; } + if (!netlink_strict_get_check(skb)) + return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, + ifa_ipv6_policy, extack); + ifm = nlmsg_data(nlh); if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get address request"); return -EINVAL; } - if (!netlink_strict_get_check(skb)) - return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, - ifa_ipv6_policy, extack); - err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, extack); if (err) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 7bae6a91b487..b1e9a10e1133 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -370,6 +370,21 @@ static int call_fib6_entry_notifier(struct notifier_block *nb, return call_fib6_notifier(nb, event_type, &info.info); } +static int call_fib6_multipath_entry_notifier(struct notifier_block *nb, + enum fib_event_type event_type, + struct fib6_info *rt, + unsigned int nsiblings, + struct netlink_ext_ack *extack) +{ + struct fib6_entry_notifier_info info = { + .info.extack = extack, + .rt = rt, + .nsiblings = nsiblings, + }; + + return call_fib6_notifier(nb, event_type, &info.info); +} + int call_fib6_entry_notifiers(struct net *net, enum fib_event_type event_type, struct fib6_info *rt, @@ -400,6 +415,17 @@ int call_fib6_multipath_entry_notifiers(struct net *net, return call_fib6_notifiers(net, event_type, &info.info); } +int call_fib6_entry_notifiers_replace(struct net *net, struct fib6_info *rt) +{ + struct fib6_entry_notifier_info info = { + .rt = rt, + .nsiblings = rt->fib6_nsiblings, + }; + + rt->fib6_table->fib_seq++; + return call_fib6_notifiers(net, FIB_EVENT_ENTRY_REPLACE, &info.info); +} + struct fib6_dump_arg { struct net *net; struct notifier_block *nb; @@ -408,22 +434,29 @@ struct fib6_dump_arg { static int fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg) { - if (rt == arg->net->ipv6.fib6_null_entry) + enum fib_event_type fib_event = FIB_EVENT_ENTRY_REPLACE; + int err; + + if (!rt || rt == arg->net->ipv6.fib6_null_entry) return 0; - return call_fib6_entry_notifier(arg->nb, FIB_EVENT_ENTRY_ADD, - rt, arg->extack); + + if (rt->fib6_nsiblings) + err = call_fib6_multipath_entry_notifier(arg->nb, fib_event, + rt, + rt->fib6_nsiblings, + arg->extack); + else + err = call_fib6_entry_notifier(arg->nb, fib_event, rt, + arg->extack); + + return err; } static int fib6_node_dump(struct fib6_walker *w) { - struct fib6_info *rt; - int err = 0; + int err; - for_each_fib6_walker_rt(w) { - err = fib6_rt_dump(rt, w->args); - if (err) - break; - } + err = fib6_rt_dump(w->leaf, w->args); w->leaf = NULL; return err; } @@ -1039,6 +1072,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, (info->nlh->nlmsg_flags & NLM_F_CREATE)); int found = 0; bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); + bool notify_sibling_rt = false; u16 nlflags = NLM_F_EXCL; int err; @@ -1130,6 +1164,7 @@ next_iter: /* Find the first route that have the same metric */ sibling = leaf; + notify_sibling_rt = true; while (sibling) { if (sibling->fib6_metric == rt->fib6_metric && rt6_qualify_for_ecmp(sibling)) { @@ -1139,6 +1174,7 @@ next_iter: } sibling = rcu_dereference_protected(sibling->fib6_next, lockdep_is_held(&rt->fib6_table->tb6_lock)); + notify_sibling_rt = false; } /* For each sibling in the list, increment the counter of * siblings. BUG() if counters does not match, list of siblings @@ -1165,10 +1201,21 @@ next_iter: add: nlflags |= NLM_F_CREATE; - if (!info->skip_notify_kernel) { + /* The route should only be notified if it is the first + * route in the node or if it is added as a sibling + * route to the first route in the node. + */ + if (!info->skip_notify_kernel && + (notify_sibling_rt || ins == &fn->leaf)) { + enum fib_event_type fib_event; + + if (notify_sibling_rt) + fib_event = FIB_EVENT_ENTRY_APPEND; + else + fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib6_entry_notifiers(info->nl_net, - FIB_EVENT_ENTRY_ADD, - rt, extack); + fib_event, rt, + extack); if (err) { struct fib6_info *sibling, *next_sibling; @@ -1212,7 +1259,7 @@ add: return -ENOENT; } - if (!info->skip_notify_kernel) { + if (!info->skip_notify_kernel && ins == &fn->leaf) { err = call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_REPLACE, rt, extack); @@ -1845,13 +1892,29 @@ static struct fib6_node *fib6_repair_tree(struct net *net, static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, struct fib6_info __rcu **rtp, struct nl_info *info) { + struct fib6_info *leaf, *replace_rt = NULL; struct fib6_walker *w; struct fib6_info *rt = rcu_dereference_protected(*rtp, lockdep_is_held(&table->tb6_lock)); struct net *net = info->nl_net; + bool notify_del = false; RT6_TRACE("fib6_del_route\n"); + /* If the deleted route is the first in the node and it is not part of + * a multipath route, then we need to replace it with the next route + * in the node, if exists. + */ + leaf = rcu_dereference_protected(fn->leaf, + lockdep_is_held(&table->tb6_lock)); + if (leaf == rt && !rt->fib6_nsiblings) { + if (rcu_access_pointer(rt->fib6_next)) + replace_rt = rcu_dereference_protected(rt->fib6_next, + lockdep_is_held(&table->tb6_lock)); + else + notify_del = true; + } + /* Unlink it */ *rtp = rt->fib6_next; rt->fib6_node = NULL; @@ -1869,6 +1932,14 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, if (rt->fib6_nsiblings) { struct fib6_info *sibling, *next_sibling; + /* The route is deleted from a multipath route. If this + * multipath route is the first route in the node, then we need + * to emit a delete notification. Otherwise, we need to skip + * the notification. + */ + if (rt->fib6_metric == leaf->fib6_metric && + rt6_qualify_for_ecmp(leaf)) + notify_del = true; list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) sibling->fib6_nsiblings--; @@ -1904,8 +1975,13 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, fib6_purge_rt(rt, fn, net); - if (!info->skip_notify_kernel) - call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, NULL); + if (!info->skip_notify_kernel) { + if (notify_del) + call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, + rt, NULL); + else if (replace_rt) + call_fib6_entry_notifiers_replace(net, replace_rt); + } if (!info->skip_notify) inet6_rt_notify(RTM_DELROUTE, rt, info, 0); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 923034c52ce4..9d0965252ddf 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -2170,8 +2170,8 @@ static const struct nla_policy ip6gre_policy[IFLA_GRE_MAX + 1] = { [IFLA_GRE_OFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_IKEY] = { .type = NLA_U32 }, [IFLA_GRE_OKEY] = { .type = NLA_U32 }, - [IFLA_GRE_LOCAL] = { .len = FIELD_SIZEOF(struct ipv6hdr, saddr) }, - [IFLA_GRE_REMOTE] = { .len = FIELD_SIZEOF(struct ipv6hdr, daddr) }, + [IFLA_GRE_LOCAL] = { .len = sizeof_field(struct ipv6hdr, saddr) }, + [IFLA_GRE_REMOTE] = { .len = sizeof_field(struct ipv6hdr, daddr) }, [IFLA_GRE_TTL] = { .type = NLA_U8 }, [IFLA_GRE_ENCAP_LIMIT] = { .type = NLA_U8 }, [IFLA_GRE_FLOWINFO] = { .type = NLA_U32 }, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b59940416cb5..4b8659e077d3 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3749,6 +3749,7 @@ static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg) if (rt->fib6_nsiblings && cfg->fc_delete_all_nh) { struct fib6_info *sibling, *next_sibling; + struct fib6_node *fn; /* prefer to send a single notification with all hops */ skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); @@ -3764,12 +3765,32 @@ static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg) info->skip_notify = 1; } + /* 'rt' points to the first sibling route. If it is not the + * leaf, then we do not need to send a notification. Otherwise, + * we need to check if the last sibling has a next route or not + * and emit a replace or delete notification, respectively. + */ info->skip_notify_kernel = 1; - call_fib6_multipath_entry_notifiers(net, - FIB_EVENT_ENTRY_DEL, - rt, - rt->fib6_nsiblings, - NULL); + fn = rcu_dereference_protected(rt->fib6_node, + lockdep_is_held(&table->tb6_lock)); + if (rcu_access_pointer(fn->leaf) == rt) { + struct fib6_info *last_sibling, *replace_rt; + + last_sibling = list_last_entry(&rt->fib6_siblings, + struct fib6_info, + fib6_siblings); + replace_rt = rcu_dereference_protected( + last_sibling->fib6_next, + lockdep_is_held(&table->tb6_lock)); + if (replace_rt) + call_fib6_entry_notifiers_replace(net, + replace_rt); + else + call_fib6_multipath_entry_notifiers(net, + FIB_EVENT_ENTRY_DEL, + rt, rt->fib6_nsiblings, + NULL); + } list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) { @@ -5017,12 +5038,37 @@ static void ip6_route_mpath_notify(struct fib6_info *rt, inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); } +static bool ip6_route_mpath_should_notify(const struct fib6_info *rt) +{ + bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); + bool should_notify = false; + struct fib6_info *leaf; + struct fib6_node *fn; + + rcu_read_lock(); + fn = rcu_dereference(rt->fib6_node); + if (!fn) + goto out; + + leaf = rcu_dereference(fn->leaf); + if (!leaf) + goto out; + + if (rt == leaf || + (rt_can_ecmp && rt->fib6_metric == leaf->fib6_metric && + rt6_qualify_for_ecmp(leaf))) + should_notify = true; +out: + rcu_read_unlock(); + + return should_notify; +} + static int ip6_route_multipath_add(struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct fib6_info *rt_notif = NULL, *rt_last = NULL; struct nl_info *info = &cfg->fc_nlinfo; - enum fib_event_type event_type; struct fib6_config r_cfg; struct rtnexthop *rtnh; struct fib6_info *rt; @@ -5147,13 +5193,27 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, nhn++; } - event_type = replace ? FIB_EVENT_ENTRY_REPLACE : FIB_EVENT_ENTRY_ADD; - err = call_fib6_multipath_entry_notifiers(info->nl_net, event_type, - rt_notif, nhn - 1, extack); - if (err) { - /* Delete all the siblings that were just added */ - err_nh = NULL; - goto add_errout; + /* An in-kernel notification should only be sent in case the new + * multipath route is added as the first route in the node, or if + * it was appended to it. We pass 'rt_notif' since it is the first + * sibling and might allow us to skip some checks in the replace case. + */ + if (ip6_route_mpath_should_notify(rt_notif)) { + enum fib_event_type fib_event; + + if (rt_notif->fib6_nsiblings != nhn - 1) + fib_event = FIB_EVENT_ENTRY_APPEND; + else + fib_event = FIB_EVENT_ENTRY_REPLACE; + + err = call_fib6_multipath_entry_notifiers(info->nl_net, + fib_event, rt_notif, + nhn - 1, extack); + if (err) { + /* Delete all the siblings that were just added */ + err_nh = NULL; + goto add_errout; + } } /* success ... tell user about new route */ diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index ebb62a4ebe30..c4bdcbc84b07 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -50,7 +50,7 @@ static struct iucv_interface *pr_iucv; static const u8 iprm_shutdown[8] = {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01}; -#define TRGCLS_SIZE FIELD_SIZEOF(struct iucv_message, class) +#define TRGCLS_SIZE sizeof_field(struct iucv_message, class) #define __iucv_sock_wait(sk, condition, timeo, ret) \ do { \ diff --git a/net/llc/llc_station.c b/net/llc/llc_station.c index 204a8351efff..c29170e767a8 100644 --- a/net/llc/llc_station.c +++ b/net/llc/llc_station.c @@ -32,7 +32,7 @@ static int llc_stat_ev_rx_null_dsap_xid_c(struct sk_buff *skb) return LLC_PDU_IS_CMD(pdu) && /* command PDU */ LLC_PDU_TYPE_IS_U(pdu) && /* U type PDU */ LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_XID && - !pdu->dsap ? 0 : 1; /* NULL DSAP value */ + !pdu->dsap; /* NULL DSAP value */ } static int llc_stat_ev_rx_null_dsap_test_c(struct sk_buff *skb) @@ -42,7 +42,7 @@ static int llc_stat_ev_rx_null_dsap_test_c(struct sk_buff *skb) return LLC_PDU_IS_CMD(pdu) && /* command PDU */ LLC_PDU_TYPE_IS_U(pdu) && /* U type PDU */ LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_TEST && - !pdu->dsap ? 0 : 1; /* NULL DSAP */ + !pdu->dsap; /* NULL DSAP */ } static int llc_station_ac_send_xid_r(struct sk_buff *skb) diff --git a/net/mac80211/airtime.c b/net/mac80211/airtime.c index 63cb0028b02d..9fc2968856c0 100644 --- a/net/mac80211/airtime.c +++ b/net/mac80211/airtime.c @@ -442,7 +442,7 @@ u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, return 0; sband = hw->wiphy->bands[status->band]; - if (!sband || status->rate_idx > sband->n_bitrates) + if (!sband || status->rate_idx >= sband->n_bitrates) return 0; rate = &sband->bitrates[status->rate_idx]; diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index b3c9001d1f43..c80b1e163ea4 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -201,8 +201,6 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf; u64 rx_airtime = 0, tx_airtime = 0; s64 deficit[IEEE80211_NUM_ACS]; - u32 q_depth[IEEE80211_NUM_ACS]; - u32 q_limit_l[IEEE80211_NUM_ACS], q_limit_h[IEEE80211_NUM_ACS]; ssize_t rv; int ac; @@ -214,6 +212,56 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, rx_airtime += sta->airtime[ac].rx_airtime; tx_airtime += sta->airtime[ac].tx_airtime; deficit[ac] = sta->airtime[ac].deficit; + spin_unlock_bh(&local->active_txq_lock[ac]); + } + + p += scnprintf(p, bufsz + buf - p, + "RX: %llu us\nTX: %llu us\nWeight: %u\n" + "Deficit: VO: %lld us VI: %lld us BE: %lld us BK: %lld us\n", + rx_airtime, tx_airtime, sta->airtime_weight, + deficit[0], deficit[1], deficit[2], deficit[3]); + + rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); + kfree(buf); + return rv; +} + +static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct sta_info *sta = file->private_data; + struct ieee80211_local *local = sta->sdata->local; + int ac; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + spin_lock_bh(&local->active_txq_lock[ac]); + sta->airtime[ac].rx_airtime = 0; + sta->airtime[ac].tx_airtime = 0; + sta->airtime[ac].deficit = sta->airtime_weight; + spin_unlock_bh(&local->active_txq_lock[ac]); + } + + return count; +} +STA_OPS_RW(airtime); + +static ssize_t sta_aql_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct sta_info *sta = file->private_data; + struct ieee80211_local *local = sta->sdata->local; + size_t bufsz = 400; + char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf; + u32 q_depth[IEEE80211_NUM_ACS]; + u32 q_limit_l[IEEE80211_NUM_ACS], q_limit_h[IEEE80211_NUM_ACS]; + ssize_t rv; + int ac; + + if (!buf) + return -ENOMEM; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + spin_lock_bh(&local->active_txq_lock[ac]); q_limit_l[ac] = sta->airtime[ac].aql_limit_low; q_limit_h[ac] = sta->airtime[ac].aql_limit_high; spin_unlock_bh(&local->active_txq_lock[ac]); @@ -221,12 +269,8 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, } p += scnprintf(p, bufsz + buf - p, - "RX: %llu us\nTX: %llu us\nWeight: %u\n" - "Deficit: VO: %lld us VI: %lld us BE: %lld us BK: %lld us\n" "Q depth: VO: %u us VI: %u us BE: %u us BK: %u us\n" "Q limit[low/high]: VO: %u/%u VI: %u/%u BE: %u/%u BK: %u/%u\n", - rx_airtime, tx_airtime, sta->airtime_weight, - deficit[0], deficit[1], deficit[2], deficit[3], q_depth[0], q_depth[1], q_depth[2], q_depth[3], q_limit_l[0], q_limit_h[0], q_limit_l[1], q_limit_h[1], q_limit_l[2], q_limit_h[2], q_limit_l[3], q_limit_h[3]), @@ -236,11 +280,10 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, return rv; } -static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, +static ssize_t sta_aql_write(struct file *file, const char __user *userbuf, size_t count, loff_t *ppos) { struct sta_info *sta = file->private_data; - struct ieee80211_local *local = sta->sdata->local; u32 ac, q_limit_l, q_limit_h; char _buf[100] = {}, *buf = _buf; @@ -251,7 +294,7 @@ static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, return -EFAULT; buf[sizeof(_buf) - 1] = '\0'; - if (sscanf(buf, "queue limit %u %u %u", &ac, &q_limit_l, &q_limit_h) + if (sscanf(buf, "limit %u %u %u", &ac, &q_limit_l, &q_limit_h) != 3) return -EINVAL; @@ -261,17 +304,10 @@ static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, sta->airtime[ac].aql_limit_low = q_limit_l; sta->airtime[ac].aql_limit_high = q_limit_h; - for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { - spin_lock_bh(&local->active_txq_lock[ac]); - sta->airtime[ac].rx_airtime = 0; - sta->airtime[ac].tx_airtime = 0; - sta->airtime[ac].deficit = sta->airtime_weight; - spin_unlock_bh(&local->active_txq_lock[ac]); - } - return count; } -STA_OPS_RW(airtime); +STA_OPS_RW(aql); + static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) @@ -996,6 +1032,10 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) DEBUGFS_ADD(airtime); + if (wiphy_ext_feature_isset(local->hw.wiphy, + NL80211_EXT_FEATURE_AQL)) + DEBUGFS_ADD(aql); + debugfs_create_xul("driver_buffered_tids", 0400, sta->debugfs_dir, &sta->driver_buffered_tids); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 6cca0853f183..4c2b5ba3ac09 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -672,9 +672,7 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, IEEE80211_DEFAULT_AQL_TXQ_LIMIT_H; } - local->airtime_flags = AIRTIME_USE_TX | - AIRTIME_USE_RX | - AIRTIME_USE_AQL; + local->airtime_flags = AIRTIME_USE_TX | AIRTIME_USE_RX; local->aql_threshold = IEEE80211_AQL_THRESHOLD; atomic_set(&local->aql_total_pending_airtime, 0); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 8eafd81e97b4..0f5f40678885 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1916,6 +1916,9 @@ void ieee80211_sta_update_pending_airtime(struct ieee80211_local *local, { int tx_pending; + if (!wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) + return; + if (!tx_completed) { if (sta) atomic_add(tx_airtime, diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index ad5d8a4ae56d..c00e28585f9d 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -127,7 +127,6 @@ enum ieee80211_agg_stop_reason { /* Debugfs flags to enable/disable use of RX/TX airtime in scheduler */ #define AIRTIME_USE_TX BIT(0) #define AIRTIME_USE_RX BIT(1) -#define AIRTIME_USE_AQL BIT(2) struct airtime_info { u64 rx_airtime; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index b696b9136f4c..a8a7306a1f56 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2256,6 +2256,15 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, payload[7]); } + /* + * Initialize skb->priority for QoS frames. This is put in the TID field + * of the frame before passing it to the driver. + */ + if (ieee80211_is_data_qos(hdr->frame_control)) { + u8 *p = ieee80211_get_qos_ctl(hdr); + skb->priority = *p & IEEE80211_QOS_CTL_TAG1D_MASK; + } + memset(info, 0, sizeof(*info)); info->flags = IEEE80211_TX_CTL_REQ_TX_STATUS | @@ -3668,7 +3677,7 @@ begin: IEEE80211_SKB_CB(skb)->control.vif = vif; - if (local->airtime_flags & AIRTIME_USE_AQL) { + if (wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) { u32 airtime; airtime = ieee80211_calc_expected_tx_airtime(hw, vif, txq->sta, @@ -3790,7 +3799,7 @@ bool ieee80211_txq_airtime_check(struct ieee80211_hw *hw, struct sta_info *sta; struct ieee80211_local *local = hw_to_local(hw); - if (!(local->airtime_flags & AIRTIME_USE_AQL)) + if (!wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) return true; if (!txq->sta) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 0af1898af2b8..f475fec84536 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -895,9 +895,10 @@ static void nf_ct_acct_merge(struct nf_conn *ct, enum ip_conntrack_info ctinfo, } /* Resolve race on insertion if this protocol allows this. */ -static int nf_ct_resolve_clash(struct net *net, struct sk_buff *skb, - enum ip_conntrack_info ctinfo, - struct nf_conntrack_tuple_hash *h) +static __cold noinline int +nf_ct_resolve_clash(struct net *net, struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + struct nf_conntrack_tuple_hash *h) { /* This is the conntrack entry already in hashes that won race. */ struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index d8d33ef52ce0..6a1c8f1f6171 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -3626,6 +3626,9 @@ static void __net_exit ctnetlink_net_exit_batch(struct list_head *net_exit_list) list_for_each_entry(net, net_exit_list, exit_list) ctnetlink_net_exit(net); + + /* wait for other cpus until they are done with ctnl_notifiers */ + synchronize_rcu(); } static struct pernet_operations ctnetlink_net_ops = { diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index c54c9a6cc981..de7a0d1e15c8 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -28,6 +28,7 @@ struct nf_flow_key { struct flow_dissector_key_basic basic; union { struct flow_dissector_key_ipv4_addrs ipv4; + struct flow_dissector_key_ipv6_addrs ipv6; }; struct flow_dissector_key_tcp tcp; struct flow_dissector_key_ports tp; @@ -57,6 +58,7 @@ static int nf_flow_rule_match(struct nf_flow_match *match, NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_CONTROL, control); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_BASIC, basic); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4); + NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_TCP, tcp); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_PORTS, tp); @@ -69,9 +71,18 @@ static int nf_flow_rule_match(struct nf_flow_match *match, key->ipv4.dst = tuple->dst_v4.s_addr; mask->ipv4.dst = 0xffffffff; break; + case AF_INET6: + key->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + key->basic.n_proto = htons(ETH_P_IPV6); + key->ipv6.src = tuple->src_v6; + memset(&mask->ipv6.src, 0xff, sizeof(mask->ipv6.src)); + key->ipv6.dst = tuple->dst_v6; + memset(&mask->ipv6.dst, 0xff, sizeof(mask->ipv6.dst)); + break; default: return -EOPNOTSUPP; } + match->dissector.used_keys |= BIT(key->control.addr_type); mask->basic.n_proto = 0xffff; switch (tuple->l4proto) { @@ -96,14 +107,13 @@ static int nf_flow_rule_match(struct nf_flow_match *match, match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | BIT(FLOW_DISSECTOR_KEY_PORTS); return 0; } static void flow_offload_mangle(struct flow_action_entry *entry, - enum flow_action_mangle_base htype, - u32 offset, u8 *value, u8 *mask) + enum flow_action_mangle_base htype, u32 offset, + const __be32 *value, const __be32 *mask) { entry->id = FLOW_ACTION_MANGLE; entry->mangle.htype = htype; @@ -140,12 +150,12 @@ static int flow_offload_eth_src(struct net *net, memcpy(&val16, dev->dev_addr, 2); val = val16 << 16; flow_offload_mangle(entry0, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 4, - (u8 *)&val, (u8 *)&mask); + &val, &mask); mask = ~0xffffffff; memcpy(&val, dev->dev_addr + 2, 4); flow_offload_mangle(entry1, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 8, - (u8 *)&val, (u8 *)&mask); + &val, &mask); dev_put(dev); return 0; @@ -170,13 +180,13 @@ static int flow_offload_eth_dst(struct net *net, mask = ~0xffffffff; memcpy(&val, n->ha, 4); flow_offload_mangle(entry0, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 0, - (u8 *)&val, (u8 *)&mask); + &val, &mask); mask = ~0x0000ffff; memcpy(&val16, n->ha + 4, 2); val = val16; flow_offload_mangle(entry1, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 4, - (u8 *)&val, (u8 *)&mask); + &val, &mask); neigh_release(n); return 0; @@ -206,7 +216,7 @@ static void flow_offload_ipv4_snat(struct net *net, } flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offset, - (u8 *)&addr, (u8 *)&mask); + &addr, &mask); } static void flow_offload_ipv4_dnat(struct net *net, @@ -233,12 +243,12 @@ static void flow_offload_ipv4_dnat(struct net *net, } flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offset, - (u8 *)&addr, (u8 *)&mask); + &addr, &mask); } static void flow_offload_ipv6_mangle(struct nf_flow_rule *flow_rule, unsigned int offset, - u8 *addr, u8 *mask) + const __be32 *addr, const __be32 *mask) { struct flow_action_entry *entry; int i; @@ -246,8 +256,7 @@ static void flow_offload_ipv6_mangle(struct nf_flow_rule *flow_rule, for (i = 0; i < sizeof(struct in6_addr) / sizeof(u32); i += sizeof(u32)) { entry = flow_action_entry_next(flow_rule); flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP6, - offset + i, - &addr[i], mask); + offset + i, &addr[i], mask); } } @@ -257,23 +266,23 @@ static void flow_offload_ipv6_snat(struct net *net, struct nf_flow_rule *flow_rule) { u32 mask = ~htonl(0xffffffff); - const u8 *addr; + const __be32 *addr; u32 offset; switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: - addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6.s6_addr; + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6.s6_addr32; offset = offsetof(struct ipv6hdr, saddr); break; case FLOW_OFFLOAD_DIR_REPLY: - addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6.s6_addr; + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6.s6_addr32; offset = offsetof(struct ipv6hdr, daddr); break; default: return; } - flow_offload_ipv6_mangle(flow_rule, offset, (u8 *)addr, (u8 *)&mask); + flow_offload_ipv6_mangle(flow_rule, offset, addr, &mask); } static void flow_offload_ipv6_dnat(struct net *net, @@ -282,23 +291,23 @@ static void flow_offload_ipv6_dnat(struct net *net, struct nf_flow_rule *flow_rule) { u32 mask = ~htonl(0xffffffff); - const u8 *addr; + const __be32 *addr; u32 offset; switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: - addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6.s6_addr; + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6.s6_addr32; offset = offsetof(struct ipv6hdr, daddr); break; case FLOW_OFFLOAD_DIR_REPLY: - addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6.s6_addr; + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6.s6_addr32; offset = offsetof(struct ipv6hdr, saddr); break; default: return; } - flow_offload_ipv6_mangle(flow_rule, offset, (u8 *)addr, (u8 *)&mask); + flow_offload_ipv6_mangle(flow_rule, offset, addr, &mask); } static int flow_offload_l4proto(const struct flow_offload *flow) @@ -326,25 +335,24 @@ static void flow_offload_port_snat(struct net *net, struct nf_flow_rule *flow_rule) { struct flow_action_entry *entry = flow_action_entry_next(flow_rule); - u32 mask = ~htonl(0xffff0000); - __be16 port; + u32 mask = ~htonl(0xffff0000), port; u32 offset; switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: - port = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port; + port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port); offset = 0; /* offsetof(struct tcphdr, source); */ break; case FLOW_OFFLOAD_DIR_REPLY: - port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port; + port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port); offset = 0; /* offsetof(struct tcphdr, dest); */ break; default: - break; + return; } - + port = htonl(port << 16); flow_offload_mangle(entry, flow_offload_l4proto(flow), offset, - (u8 *)&port, (u8 *)&mask); + &port, &mask); } static void flow_offload_port_dnat(struct net *net, @@ -353,25 +361,24 @@ static void flow_offload_port_dnat(struct net *net, struct nf_flow_rule *flow_rule) { struct flow_action_entry *entry = flow_action_entry_next(flow_rule); - u32 mask = ~htonl(0xffff); - __be16 port; + u32 mask = ~htonl(0xffff), port; u32 offset; switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: - port = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port; + port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port); offset = 0; /* offsetof(struct tcphdr, source); */ break; case FLOW_OFFLOAD_DIR_REPLY: - port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port; + port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port); offset = 0; /* offsetof(struct tcphdr, dest); */ break; default: - break; + return; } - + port = htonl(port); flow_offload_mangle(entry, flow_offload_l4proto(flow), offset, - (u8 *)&port, (u8 *)&mask); + &port, &mask); } static void flow_offload_ipv4_checksum(struct net *net, @@ -574,7 +581,7 @@ static int flow_offload_tuple_add(struct flow_offload_work *offload, cls_flow.rule = flow_rule->rule; list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) { - err = block_cb->cb(TC_SETUP_FT, &cls_flow, + err = block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow, block_cb->cb_priv); if (err < 0) continue; @@ -599,7 +606,7 @@ static void flow_offload_tuple_del(struct flow_offload_work *offload, &offload->flow->tuplehash[dir].tuple, &extack); list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) - block_cb->cb(TC_SETUP_FT, &cls_flow, block_cb->cb_priv); + block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow, block_cb->cb_priv); offload->flow->flags |= FLOW_OFFLOAD_HW_DEAD; } @@ -656,7 +663,7 @@ static void flow_offload_tuple_stats(struct flow_offload_work *offload, &offload->flow->tuplehash[dir].tuple, &extack); list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) - block_cb->cb(TC_SETUP_FT, &cls_flow, block_cb->cb_priv); + block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow, block_cb->cb_priv); memcpy(stats, &cls_flow.stats, sizeof(*stats)); } @@ -822,7 +829,7 @@ int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, bo.extack = &extack; INIT_LIST_HEAD(&bo.cb_list); - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_FT, &bo); if (err < 0) return err; diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index a2b58de82600..f8f52ff99cfb 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -189,7 +189,7 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state, goto err; } - if (!skb_dst_force(skb) && state->hook != NF_INET_PRE_ROUTING) { + if (skb_dst(skb) && !skb_dst_force(skb)) { status = -ENETDOWN; goto err; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 062b73a83af0..273f3838318b 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4519,8 +4519,10 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, return err; err = -EINVAL; - if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) + if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) { + nft_data_release(&elem.key.val, desc.type); return err; + } priv = set->ops->get(ctx->net, set, &elem, flags); if (IS_ERR(priv)) @@ -4756,14 +4758,20 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (nla[NFTA_SET_ELEM_DATA] == NULL && !(flags & NFT_SET_ELEM_INTERVAL_END)) return -EINVAL; - if (nla[NFTA_SET_ELEM_DATA] != NULL && - flags & NFT_SET_ELEM_INTERVAL_END) - return -EINVAL; } else { if (nla[NFTA_SET_ELEM_DATA] != NULL) return -EINVAL; } + if ((flags & NFT_SET_ELEM_INTERVAL_END) && + (nla[NFTA_SET_ELEM_DATA] || + nla[NFTA_SET_ELEM_OBJREF] || + nla[NFTA_SET_ELEM_TIMEOUT] || + nla[NFTA_SET_ELEM_EXPIRATION] || + nla[NFTA_SET_ELEM_USERDATA] || + nla[NFTA_SET_ELEM_EXPR])) + return -EINVAL; + timeout = 0; if (nla[NFTA_SET_ELEM_TIMEOUT] != NULL) { if (!(set->flags & NFT_SET_TIMEOUT)) @@ -5476,7 +5484,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; - type = nft_obj_type_get(net, objtype); + type = __nft_obj_type_get(objtype); nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); return nf_tables_updobj(&ctx, type, nla[NFTA_OBJ_DATA], obj); @@ -7595,7 +7603,7 @@ int nft_validate_register_load(enum nft_registers reg, unsigned int len) return -EINVAL; if (len == 0) return -EINVAL; - if (reg * NFT_REG32_SIZE + len > FIELD_SIZEOF(struct nft_regs, data)) + if (reg * NFT_REG32_SIZE + len > sizeof_field(struct nft_regs, data)) return -ERANGE; return 0; @@ -7643,7 +7651,7 @@ int nft_validate_register_store(const struct nft_ctx *ctx, if (len == 0) return -EINVAL; if (reg * NFT_REG32_SIZE + len > - FIELD_SIZEOF(struct nft_regs, data)) + sizeof_field(struct nft_regs, data)) return -ERANGE; if (data != NULL && type != NFT_DATA_VALUE) diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 431f3b803bfb..a9ea29afb09f 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -44,6 +44,9 @@ struct nft_flow_rule *nft_flow_rule_create(struct net *net, expr = nft_expr_next(expr); } + if (num_actions == 0) + return ERR_PTR(-EOPNOTSUPP); + flow = nft_flow_rule_alloc(num_actions); if (!flow) return ERR_PTR(-ENOMEM); @@ -577,6 +580,9 @@ static int nft_offload_netdev_event(struct notifier_block *this, struct net *net = dev_net(dev); struct nft_chain *chain; + if (event != NETDEV_UNREGISTER) + return NOTIFY_DONE; + mutex_lock(&net->nft.commit_mutex); chain = __nft_offload_get_chain(dev); if (chain) diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 7525063c25f5..de3a9596b7f1 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -236,7 +236,7 @@ nfnl_cthelper_create(const struct nlattr * const tb[], nla_strlcpy(helper->name, tb[NFCTH_NAME], NF_CT_HELPER_NAME_LEN); size = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN])); - if (size > FIELD_SIZEOF(struct nf_conn_help, data)) { + if (size > sizeof_field(struct nf_conn_help, data)) { ret = -ENOMEM; goto err2; } diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index 02afa752dd2e..10e9d50e4e19 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -80,7 +80,7 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, tb[NFTA_BITWISE_MASK]); if (err < 0) return err; - if (d1.len != priv->len) { + if (d1.type != NFT_DATA_VALUE || d1.len != priv->len) { err = -EINVAL; goto err1; } @@ -89,7 +89,7 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, tb[NFTA_BITWISE_XOR]); if (err < 0) goto err1; - if (d2.len != priv->len) { + if (d2.type != NFT_DATA_VALUE || d2.len != priv->len) { err = -EINVAL; goto err2; } diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index b8092069f868..8a28c127effc 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -81,6 +81,12 @@ static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (err < 0) return err; + if (desc.type != NFT_DATA_VALUE) { + err = -EINVAL; + nft_data_release(&priv->data, desc.type); + return err; + } + priv->sreg = nft_parse_register(tb[NFTA_CMP_SREG]); err = nft_validate_register_load(priv->sreg, desc.len); if (err < 0) diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 46ca8bcca1bd..faea72c2df32 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -440,12 +440,12 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, switch (ctx->family) { case NFPROTO_IPV4: - len = FIELD_SIZEOF(struct nf_conntrack_tuple, + len = sizeof_field(struct nf_conntrack_tuple, src.u3.ip); break; case NFPROTO_IPV6: case NFPROTO_INET: - len = FIELD_SIZEOF(struct nf_conntrack_tuple, + len = sizeof_field(struct nf_conntrack_tuple, src.u3.ip6); break; default: @@ -457,20 +457,20 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, if (tb[NFTA_CT_DIRECTION] == NULL) return -EINVAL; - len = FIELD_SIZEOF(struct nf_conntrack_tuple, src.u3.ip); + len = sizeof_field(struct nf_conntrack_tuple, src.u3.ip); break; case NFT_CT_SRC_IP6: case NFT_CT_DST_IP6: if (tb[NFTA_CT_DIRECTION] == NULL) return -EINVAL; - len = FIELD_SIZEOF(struct nf_conntrack_tuple, src.u3.ip6); + len = sizeof_field(struct nf_conntrack_tuple, src.u3.ip6); break; case NFT_CT_PROTO_SRC: case NFT_CT_PROTO_DST: if (tb[NFTA_CT_DIRECTION] == NULL) return -EINVAL; - len = FIELD_SIZEOF(struct nf_conntrack_tuple, src.u.all); + len = sizeof_field(struct nf_conntrack_tuple, src.u.all); break; case NFT_CT_BYTES: case NFT_CT_PKTS: @@ -551,7 +551,7 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, case NFT_CT_MARK: if (tb[NFTA_CT_DIRECTION]) return -EINVAL; - len = FIELD_SIZEOF(struct nf_conn, mark); + len = sizeof_field(struct nf_conn, mark); break; #endif #ifdef CONFIG_NF_CONNTRACK_LABELS diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c index 39dc94f2491e..bc9fd98c5d6d 100644 --- a/net/netfilter/nft_masq.c +++ b/net/netfilter/nft_masq.c @@ -43,7 +43,7 @@ static int nft_masq_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { - u32 plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all); + u32 plen = sizeof_field(struct nf_nat_range, min_addr.all); struct nft_masq *priv = nft_expr_priv(expr); int err; diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index c3c93e95b46e..8b44a4de5329 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -141,10 +141,10 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, switch (family) { case NFPROTO_IPV4: - alen = FIELD_SIZEOF(struct nf_nat_range, min_addr.ip); + alen = sizeof_field(struct nf_nat_range, min_addr.ip); break; case NFPROTO_IPV6: - alen = FIELD_SIZEOF(struct nf_nat_range, min_addr.ip6); + alen = sizeof_field(struct nf_nat_range, min_addr.ip6); break; default: return -EAFNOSUPPORT; @@ -171,7 +171,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, } } - plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all); + plen = sizeof_field(struct nf_nat_range, min_addr.all); if (tb[NFTA_NAT_REG_PROTO_MIN]) { priv->sreg_proto_min = nft_parse_register(tb[NFTA_NAT_REG_PROTO_MIN]); diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c index 4701fa8a45e7..89efcc5a533d 100644 --- a/net/netfilter/nft_range.c +++ b/net/netfilter/nft_range.c @@ -66,11 +66,21 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr if (err < 0) return err; + if (desc_from.type != NFT_DATA_VALUE) { + err = -EINVAL; + goto err1; + } + err = nft_data_init(NULL, &priv->data_to, sizeof(priv->data_to), &desc_to, tb[NFTA_RANGE_TO_DATA]); if (err < 0) goto err1; + if (desc_to.type != NFT_DATA_VALUE) { + err = -EINVAL; + goto err2; + } + if (desc_from.len != desc_to.len) { err = -EINVAL; goto err2; diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index 43eeb1f609f1..5b779171565c 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -48,7 +48,7 @@ static int nft_redir_init(const struct nft_ctx *ctx, unsigned int plen; int err; - plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all); + plen = sizeof_field(struct nf_nat_range, min_addr.all); if (tb[NFTA_REDIR_REG_PROTO_MIN]) { priv->sreg_proto_min = nft_parse_register(tb[NFTA_REDIR_REG_PROTO_MIN]); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 57123259452f..a9f804f7a04a 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -74,8 +74,13 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set parent = rcu_dereference_raw(parent->rb_left); continue; } - if (nft_rbtree_interval_end(rbe)) - goto out; + if (nft_rbtree_interval_end(rbe)) { + if (nft_set_is_anonymous(set)) + return false; + parent = rcu_dereference_raw(parent->rb_left); + interval = NULL; + continue; + } *ext = &rbe->ext; return true; @@ -88,7 +93,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set *ext = &interval->ext; return true; } -out: + return false; } @@ -139,8 +144,10 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, if (flags & NFT_SET_ELEM_INTERVAL_END) interval = rbe; } else { - if (!nft_set_elem_active(&rbe->ext, genmask)) + if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = rcu_dereference_raw(parent->rb_left); + continue; + } if (!nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) || (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END) == @@ -148,7 +155,11 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, *elem = rbe; return true; } - return false; + + if (nft_rbtree_interval_end(rbe)) + interval = NULL; + + parent = rcu_dereference_raw(parent->rb_left); } } diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index f92a82c73880..4c33dfc9dab5 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -218,14 +218,14 @@ static int nft_tproxy_init(const struct nft_ctx *ctx, switch (priv->family) { case NFPROTO_IPV4: - alen = FIELD_SIZEOF(union nf_inet_addr, in); + alen = sizeof_field(union nf_inet_addr, in); err = nf_defrag_ipv4_enable(ctx->net); if (err) return err; break; #if IS_ENABLED(CONFIG_NF_TABLES_IPV6) case NFPROTO_IPV6: - alen = FIELD_SIZEOF(union nf_inet_addr, in6); + alen = sizeof_field(union nf_inet_addr, in6); err = nf_defrag_ipv6_enable(ctx->net); if (err) return err; diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index 2236455b10a3..37253d399c6b 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -30,7 +30,7 @@ static unsigned int jhash_rnd __read_mostly; static unsigned int xt_rateest_hash(const char *name) { - return jhash(name, FIELD_SIZEOF(struct xt_rateest, name), jhash_rnd) & + return jhash(name, sizeof_field(struct xt_rateest, name), jhash_rnd) & (RATEEST_HSIZE - 1); } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 90b2ab9dd449..4e31721e7293 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2755,7 +2755,7 @@ static int __init netlink_proto_init(void) if (err != 0) goto out; - BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > sizeof_field(struct sk_buff, cb)); nl_table = kcalloc(MAX_LINKS, sizeof(*nl_table), GFP_KERNEL); if (!nl_table) diff --git a/net/nfc/nci/uart.c b/net/nfc/nci/uart.c index 78fe622eba65..11b554ce07ff 100644 --- a/net/nfc/nci/uart.c +++ b/net/nfc/nci/uart.c @@ -346,7 +346,7 @@ static int nci_uart_default_recv_buf(struct nci_uart *nu, const u8 *data, nu->rx_packet_len = -1; nu->rx_skb = nci_skb_alloc(nu->ndev, NCI_MAX_PACKET_SIZE, - GFP_KERNEL); + GFP_ATOMIC); if (!nu->rx_skb) return -ENOMEM; } diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 4c8395462303..7fbfe2adfffa 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -161,16 +161,17 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, const struct nlattr *attr, int len); static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key, - const struct ovs_action_push_mpls *mpls) + __be32 mpls_lse, __be16 mpls_ethertype, __u16 mac_len) { int err; - err = skb_mpls_push(skb, mpls->mpls_lse, mpls->mpls_ethertype, - skb->mac_len, - ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET); + err = skb_mpls_push(skb, mpls_lse, mpls_ethertype, mac_len, !!mac_len); if (err) return err; + if (!mac_len) + key->mac_proto = MAC_PROTO_NONE; + invalidate_flow_key(key); return 0; } @@ -185,6 +186,9 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key, if (err) return err; + if (ethertype == htons(ETH_P_TEB)) + key->mac_proto = MAC_PROTO_ETHERNET; + invalidate_flow_key(key); return 0; } @@ -1229,10 +1233,24 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, execute_hash(skb, key, a); break; - case OVS_ACTION_ATTR_PUSH_MPLS: - err = push_mpls(skb, key, nla_data(a)); + case OVS_ACTION_ATTR_PUSH_MPLS: { + struct ovs_action_push_mpls *mpls = nla_data(a); + + err = push_mpls(skb, key, mpls->mpls_lse, + mpls->mpls_ethertype, skb->mac_len); break; + } + case OVS_ACTION_ATTR_ADD_MPLS: { + struct ovs_action_add_mpls *mpls = nla_data(a); + __u16 mac_len = 0; + + if (mpls->tun_flags & OVS_MPLS_L3_TUNNEL_FLAG_MASK) + mac_len = skb->mac_len; + err = push_mpls(skb, key, mpls->mpls_lse, + mpls->mpls_ethertype, mac_len); + break; + } case OVS_ACTION_ATTR_POP_MPLS: err = pop_mpls(skb, key, nla_get_be16(a)); break; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 1047e8043084..e3a37d22539c 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -2497,7 +2497,7 @@ static int __init dp_init(void) { int err; - BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > sizeof_field(struct sk_buff, cb)); pr_info("Open vSwitch switching datapath\n"); diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index fd8ed766bdd1..758a8c77f736 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -37,7 +37,7 @@ enum sw_flow_mac_proto { * matching for small options. */ #define TUN_METADATA_OFFSET(opt_len) \ - (FIELD_SIZEOF(struct sw_flow_key, tun_opts) - opt_len) + (sizeof_field(struct sw_flow_key, tun_opts) - opt_len) #define TUN_METADATA_OPTS(flow_key, opt_len) \ ((void *)((flow_key)->tun_opts + TUN_METADATA_OFFSET(opt_len))) @@ -52,7 +52,7 @@ struct vlan_head { #define OVS_SW_FLOW_KEY_METADATA_SIZE \ (offsetof(struct sw_flow_key, recirc_id) + \ - FIELD_SIZEOF(struct sw_flow_key, recirc_id)) + sizeof_field(struct sw_flow_key, recirc_id)) struct ovs_key_nsh { struct ovs_nsh_key_base base; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 65c2e3458ff5..7da4230627f5 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -79,6 +79,7 @@ static bool actions_may_change_flow(const struct nlattr *actions) case OVS_ACTION_ATTR_SET_MASKED: case OVS_ACTION_ATTR_METER: case OVS_ACTION_ATTR_CHECK_PKT_LEN: + case OVS_ACTION_ATTR_ADD_MPLS: default: return true; } @@ -3005,6 +3006,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, [OVS_ACTION_ATTR_METER] = sizeof(u32), [OVS_ACTION_ATTR_CLONE] = (u32)-1, [OVS_ACTION_ATTR_CHECK_PKT_LEN] = (u32)-1, + [OVS_ACTION_ATTR_ADD_MPLS] = sizeof(struct ovs_action_add_mpls), }; const struct ovs_action_push_vlan *vlan; int type = nla_type(a); @@ -3072,6 +3074,33 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, case OVS_ACTION_ATTR_RECIRC: break; + case OVS_ACTION_ATTR_ADD_MPLS: { + const struct ovs_action_add_mpls *mpls = nla_data(a); + + if (!eth_p_mpls(mpls->mpls_ethertype)) + return -EINVAL; + + if (mpls->tun_flags & OVS_MPLS_L3_TUNNEL_FLAG_MASK) { + if (vlan_tci & htons(VLAN_CFI_MASK) || + (eth_type != htons(ETH_P_IP) && + eth_type != htons(ETH_P_IPV6) && + eth_type != htons(ETH_P_ARP) && + eth_type != htons(ETH_P_RARP) && + !eth_p_mpls(eth_type))) + return -EINVAL; + mpls_label_count++; + } else { + if (mac_proto == MAC_PROTO_ETHERNET) { + mpls_label_count = 1; + mac_proto = MAC_PROTO_NONE; + } else { + mpls_label_count++; + } + } + eth_type = mpls->mpls_ethertype; + break; + } + case OVS_ACTION_ATTR_PUSH_MPLS: { const struct ovs_action_push_mpls *mpls = nla_data(a); @@ -3109,6 +3138,11 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, * recirculation. */ proto = nla_get_be16(a); + + if (proto == htons(ETH_P_TEB) && + mac_proto != MAC_PROTO_NONE) + return -EINVAL; + mpls_label_count--; if (!eth_p_mpls(proto) || !mpls_label_count) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 53c1d41fb1c9..3bec515ccde3 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -520,7 +520,7 @@ static int prb_calc_retire_blk_tmo(struct packet_sock *po, int blk_size_in_bytes) { struct net_device *dev; - unsigned int mbits = 0, msec = 0, div = 0, tmo = 0; + unsigned int mbits, div; struct ethtool_link_ksettings ecmd; int err; @@ -532,30 +532,25 @@ static int prb_calc_retire_blk_tmo(struct packet_sock *po, } err = __ethtool_get_link_ksettings(dev, &ecmd); rtnl_unlock(); - if (!err) { - /* - * If the link speed is so slow you don't really - * need to worry about perf anyways - */ - if (ecmd.base.speed < SPEED_1000 || - ecmd.base.speed == SPEED_UNKNOWN) { - return DEFAULT_PRB_RETIRE_TOV; - } else { - msec = 1; - div = ecmd.base.speed / 1000; - } - } + if (err) + return DEFAULT_PRB_RETIRE_TOV; + /* If the link speed is so slow you don't really + * need to worry about perf anyways + */ + if (ecmd.base.speed < SPEED_1000 || + ecmd.base.speed == SPEED_UNKNOWN) + return DEFAULT_PRB_RETIRE_TOV; + + div = ecmd.base.speed / 1000; mbits = (blk_size_in_bytes * 8) / (1024 * 1024); if (div) mbits /= div; - tmo = mbits * msec; - if (div) - return tmo+1; - return tmo; + return mbits + 1; + return mbits; } static void prb_init_ft_ops(struct tpacket_kbdq_core *p1, diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 461d75274fb3..971c73c7d34c 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -1002,10 +1002,13 @@ static void rfkill_sync_work(struct work_struct *work) int __must_check rfkill_register(struct rfkill *rfkill) { static unsigned long rfkill_no; - struct device *dev = &rfkill->dev; + struct device *dev; int error; - BUG_ON(!rfkill); + if (!rfkill) + return -EINVAL; + + dev = &rfkill->dev; mutex_lock(&rfkill_global_mutex); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index d72ddb67bb74..9d3c4d2d893a 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -972,7 +972,7 @@ static int __init af_rxrpc_init(void) int ret = -1; unsigned int tmp; - BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > sizeof_field(struct sk_buff, cb)); get_random_bytes(&tmp, sizeof(tmp)); tmp &= 0x3fffffff; diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 2985509147a2..b1e7ec726958 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -409,6 +409,23 @@ config NET_SCH_PLUG To compile this code as a module, choose M here: the module will be called sch_plug. +config NET_SCH_ETS + tristate "Enhanced transmission selection scheduler (ETS)" + help + The Enhanced Transmission Selection scheduler is a classful + queuing discipline that merges functionality of PRIO and DRR + qdiscs in one scheduler. ETS makes it easy to configure a set of + strict and bandwidth-sharing bands to implement the transmission + selection described in 802.1Qaz. + + Say Y here if you want to use the ETS packet scheduling + algorithm. + + To compile this driver as a module, choose M here: the module + will be called sch_ets. + + If unsure, say N. + menuconfig NET_SCH_DEFAULT bool "Allow override default queue discipline" ---help--- diff --git a/net/sched/Makefile b/net/sched/Makefile index 415d1e1f237e..bc8856b865ff 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -48,6 +48,7 @@ obj-$(CONFIG_NET_SCH_ATM) += sch_atm.o obj-$(CONFIG_NET_SCH_NETEM) += sch_netem.o obj-$(CONFIG_NET_SCH_DRR) += sch_drr.o obj-$(CONFIG_NET_SCH_PLUG) += sch_plug.o +obj-$(CONFIG_NET_SCH_ETS) += sch_ets.o obj-$(CONFIG_NET_SCH_MQPRIO) += sch_mqprio.o obj-$(CONFIG_NET_SCH_SKBPRIO) += sch_skbprio.o obj-$(CONFIG_NET_SCH_CHOKE) += sch_choke.o diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index bf2d69335d4b..f685c0d73708 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -312,7 +312,7 @@ static void tcf_ct_act_set_labels(struct nf_conn *ct, u32 *labels_m) { #if IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) - size_t labels_sz = FIELD_SIZEOF(struct tcf_ct_params, labels); + size_t labels_sz = sizeof_field(struct tcf_ct_params, labels); if (!memchr_inv(labels_m, 0, labels_sz)) return; @@ -936,7 +936,7 @@ static struct tc_action_ops act_ct_ops = { static __net_init int ct_init_net(struct net *net) { - unsigned int n_bits = FIELD_SIZEOF(struct tcf_ct_params, labels) * 8; + unsigned int n_bits = sizeof_field(struct tcf_ct_params, labels) * 8; struct tc_ct_action_net *tn = net_generic(net, ct_net_id); if (nf_connlabels_get(net, n_bits - 1)) { diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 6c68971d99df..0d125de54285 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1481,7 +1481,7 @@ static int fl_init_mask_hashtable(struct fl_flow_mask *mask) } #define FL_KEY_MEMBER_OFFSET(member) offsetof(struct fl_flow_key, member) -#define FL_KEY_MEMBER_SIZE(member) FIELD_SIZEOF(struct fl_flow_key, member) +#define FL_KEY_MEMBER_SIZE(member) sizeof_field(struct fl_flow_key, member) #define FL_KEY_IS_MASKED(mask, member) \ memchr_inv(((char *)mask) + FL_KEY_MEMBER_OFFSET(member), \ diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index a0e6fac613de..66c6bcec16cb 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -1108,10 +1108,33 @@ erridr: return err; } +static bool u32_hnode_empty(struct tc_u_hnode *ht, bool *non_root_ht) +{ + int i; + + if (!ht) + return true; + if (!ht->is_root) { + *non_root_ht = true; + return false; + } + if (*non_root_ht) + return false; + if (ht->refcnt < 2) + return true; + + for (i = 0; i <= ht->divisor; i++) { + if (rtnl_dereference(ht->ht[i])) + return false; + } + return true; +} + static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held) { struct tc_u_common *tp_c = tp->data; + bool non_root_ht = false; struct tc_u_hnode *ht; struct tc_u_knode *n; unsigned int h; @@ -1124,6 +1147,8 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, ht = rtnl_dereference(ht->next)) { if (ht->prio != tp->prio) continue; + if (u32_hnode_empty(ht, &non_root_ht)) + return; if (arg->count >= arg->skip) { if (arg->fn(tp, ht, arg) < 0) { arg->stop = 1; diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index e0f40400f679..6cc3ab145513 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -173,8 +173,7 @@ struct cake_tin_data { u64 tin_rate_bps; u16 tin_rate_shft; - u16 tin_quantum_prio; - u16 tin_quantum_band; + u16 tin_quantum; s32 tin_deficit; u32 tin_backlog; u32 tin_dropped; @@ -1919,7 +1918,7 @@ begin: while (b->tin_deficit < 0 || !(b->sparse_flow_count + b->bulk_flow_count)) { if (b->tin_deficit <= 0) - b->tin_deficit += b->tin_quantum_band; + b->tin_deficit += b->tin_quantum; if (b->sparse_flow_count + b->bulk_flow_count) empty = false; @@ -2241,8 +2240,7 @@ static int cake_config_besteffort(struct Qdisc *sch) cake_set_rate(b, rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); - b->tin_quantum_band = 65535; - b->tin_quantum_prio = 65535; + b->tin_quantum = 65535; return 0; } @@ -2253,8 +2251,7 @@ static int cake_config_precedence(struct Qdisc *sch) struct cake_sched_data *q = qdisc_priv(sch); u32 mtu = psched_mtu(qdisc_dev(sch)); u64 rate = q->rate_bps; - u32 quantum1 = 256; - u32 quantum2 = 256; + u32 quantum = 256; u32 i; q->tin_cnt = 8; @@ -2267,18 +2264,14 @@ static int cake_config_precedence(struct Qdisc *sch) cake_set_rate(b, rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); - b->tin_quantum_prio = max_t(u16, 1U, quantum1); - b->tin_quantum_band = max_t(u16, 1U, quantum2); + b->tin_quantum = max_t(u16, 1U, quantum); /* calculate next class's parameters */ rate *= 7; rate >>= 3; - quantum1 *= 3; - quantum1 >>= 1; - - quantum2 *= 7; - quantum2 >>= 3; + quantum *= 7; + quantum >>= 3; } return 0; @@ -2347,8 +2340,7 @@ static int cake_config_diffserv8(struct Qdisc *sch) struct cake_sched_data *q = qdisc_priv(sch); u32 mtu = psched_mtu(qdisc_dev(sch)); u64 rate = q->rate_bps; - u32 quantum1 = 256; - u32 quantum2 = 256; + u32 quantum = 256; u32 i; q->tin_cnt = 8; @@ -2364,18 +2356,14 @@ static int cake_config_diffserv8(struct Qdisc *sch) cake_set_rate(b, rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); - b->tin_quantum_prio = max_t(u16, 1U, quantum1); - b->tin_quantum_band = max_t(u16, 1U, quantum2); + b->tin_quantum = max_t(u16, 1U, quantum); /* calculate next class's parameters */ rate *= 7; rate >>= 3; - quantum1 *= 3; - quantum1 >>= 1; - - quantum2 *= 7; - quantum2 >>= 3; + quantum *= 7; + quantum >>= 3; } return 0; @@ -2414,17 +2402,11 @@ static int cake_config_diffserv4(struct Qdisc *sch) cake_set_rate(&q->tins[3], rate >> 2, mtu, us_to_ns(q->target), us_to_ns(q->interval)); - /* priority weights */ - q->tins[0].tin_quantum_prio = quantum; - q->tins[1].tin_quantum_prio = quantum >> 4; - q->tins[2].tin_quantum_prio = quantum << 2; - q->tins[3].tin_quantum_prio = quantum << 4; - /* bandwidth-sharing weights */ - q->tins[0].tin_quantum_band = quantum; - q->tins[1].tin_quantum_band = quantum >> 4; - q->tins[2].tin_quantum_band = quantum >> 1; - q->tins[3].tin_quantum_band = quantum >> 2; + q->tins[0].tin_quantum = quantum; + q->tins[1].tin_quantum = quantum >> 4; + q->tins[2].tin_quantum = quantum >> 1; + q->tins[3].tin_quantum = quantum >> 2; return 0; } @@ -2455,15 +2437,10 @@ static int cake_config_diffserv3(struct Qdisc *sch) cake_set_rate(&q->tins[2], rate >> 2, mtu, us_to_ns(q->target), us_to_ns(q->interval)); - /* priority weights */ - q->tins[0].tin_quantum_prio = quantum; - q->tins[1].tin_quantum_prio = quantum >> 4; - q->tins[2].tin_quantum_prio = quantum << 4; - /* bandwidth-sharing weights */ - q->tins[0].tin_quantum_band = quantum; - q->tins[1].tin_quantum_band = quantum >> 4; - q->tins[2].tin_quantum_band = quantum >> 2; + q->tins[0].tin_quantum = quantum; + q->tins[1].tin_quantum = quantum >> 4; + q->tins[2].tin_quantum = quantum >> 2; return 0; } diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c new file mode 100644 index 000000000000..a87e9159338c --- /dev/null +++ b/net/sched/sch_ets.c @@ -0,0 +1,828 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * net/sched/sch_ets.c Enhanced Transmission Selection scheduler + * + * Description + * ----------- + * + * The Enhanced Transmission Selection scheduler is a classful queuing + * discipline that merges functionality of PRIO and DRR qdiscs in one scheduler. + * ETS makes it easy to configure a set of strict and bandwidth-sharing bands to + * implement the transmission selection described in 802.1Qaz. + * + * Although ETS is technically classful, it's not possible to add and remove + * classes at will. Instead one specifies number of classes, how many are + * PRIO-like and how many DRR-like, and quanta for the latter. + * + * Algorithm + * --------- + * + * The strict classes, if any, are tried for traffic first: first band 0, if it + * has no traffic then band 1, etc. + * + * When there is no traffic in any of the strict queues, the bandwidth-sharing + * ones are tried next. Each band is assigned a deficit counter, initialized to + * "quantum" of that band. ETS maintains a list of active bandwidth-sharing + * bands whose qdiscs are non-empty. A packet is dequeued from the band at the + * head of the list if the packet size is smaller or equal to the deficit + * counter. If the counter is too small, it is increased by "quantum" and the + * scheduler moves on to the next band in the active list. + */ + +#include <linux/module.h> +#include <net/gen_stats.h> +#include <net/netlink.h> +#include <net/pkt_cls.h> +#include <net/pkt_sched.h> +#include <net/sch_generic.h> + +struct ets_class { + struct list_head alist; /* In struct ets_sched.active. */ + struct Qdisc *qdisc; + u32 quantum; + u32 deficit; + struct gnet_stats_basic_packed bstats; + struct gnet_stats_queue qstats; +}; + +struct ets_sched { + struct list_head active; + struct tcf_proto __rcu *filter_list; + struct tcf_block *block; + unsigned int nbands; + unsigned int nstrict; + u8 prio2band[TC_PRIO_MAX + 1]; + struct ets_class classes[TCQ_ETS_MAX_BANDS]; +}; + +static const struct nla_policy ets_policy[TCA_ETS_MAX + 1] = { + [TCA_ETS_NBANDS] = { .type = NLA_U8 }, + [TCA_ETS_NSTRICT] = { .type = NLA_U8 }, + [TCA_ETS_QUANTA] = { .type = NLA_NESTED }, + [TCA_ETS_PRIOMAP] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy ets_priomap_policy[TCA_ETS_MAX + 1] = { + [TCA_ETS_PRIOMAP_BAND] = { .type = NLA_U8 }, +}; + +static const struct nla_policy ets_quanta_policy[TCA_ETS_MAX + 1] = { + [TCA_ETS_QUANTA_BAND] = { .type = NLA_U32 }, +}; + +static const struct nla_policy ets_class_policy[TCA_ETS_MAX + 1] = { + [TCA_ETS_QUANTA_BAND] = { .type = NLA_U32 }, +}; + +static int ets_quantum_parse(struct Qdisc *sch, const struct nlattr *attr, + unsigned int *quantum, + struct netlink_ext_ack *extack) +{ + *quantum = nla_get_u32(attr); + if (!*quantum) { + NL_SET_ERR_MSG(extack, "ETS quantum cannot be zero"); + return -EINVAL; + } + return 0; +} + +static struct ets_class * +ets_class_from_arg(struct Qdisc *sch, unsigned long arg) +{ + struct ets_sched *q = qdisc_priv(sch); + + return &q->classes[arg - 1]; +} + +static u32 ets_class_id(struct Qdisc *sch, const struct ets_class *cl) +{ + struct ets_sched *q = qdisc_priv(sch); + int band = cl - q->classes; + + return TC_H_MAKE(sch->handle, band + 1); +} + +static void ets_offload_change(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct ets_sched *q = qdisc_priv(sch); + struct tc_ets_qopt_offload qopt; + unsigned int w_psum_prev = 0; + unsigned int q_psum = 0; + unsigned int q_sum = 0; + unsigned int quantum; + unsigned int w_psum; + unsigned int weight; + unsigned int i; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + qopt.command = TC_ETS_REPLACE; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + qopt.replace_params.bands = q->nbands; + qopt.replace_params.qstats = &sch->qstats; + memcpy(&qopt.replace_params.priomap, + q->prio2band, sizeof(q->prio2band)); + + for (i = 0; i < q->nbands; i++) + q_sum += q->classes[i].quantum; + + for (i = 0; i < q->nbands; i++) { + quantum = q->classes[i].quantum; + q_psum += quantum; + w_psum = quantum ? q_psum * 100 / q_sum : 0; + weight = w_psum - w_psum_prev; + w_psum_prev = w_psum; + + qopt.replace_params.quanta[i] = quantum; + qopt.replace_params.weights[i] = weight; + } + + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETS, &qopt); +} + +static void ets_offload_destroy(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_ets_qopt_offload qopt; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + qopt.command = TC_ETS_DESTROY; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETS, &qopt); +} + +static void ets_offload_graft(struct Qdisc *sch, struct Qdisc *new, + struct Qdisc *old, unsigned long arg, + struct netlink_ext_ack *extack) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_ets_qopt_offload qopt; + + qopt.command = TC_ETS_GRAFT; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + qopt.graft_params.band = arg - 1; + qopt.graft_params.child_handle = new->handle; + + qdisc_offload_graft_helper(dev, sch, new, old, TC_SETUP_QDISC_ETS, + &qopt, extack); +} + +static int ets_offload_dump(struct Qdisc *sch) +{ + struct tc_ets_qopt_offload qopt; + + qopt.command = TC_ETS_STATS; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + qopt.stats.bstats = &sch->bstats; + qopt.stats.qstats = &sch->qstats; + + return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_ETS, &qopt); +} + +static bool ets_class_is_strict(struct ets_sched *q, const struct ets_class *cl) +{ + unsigned int band = cl - q->classes; + + return band < q->nstrict; +} + +static int ets_class_change(struct Qdisc *sch, u32 classid, u32 parentid, + struct nlattr **tca, unsigned long *arg, + struct netlink_ext_ack *extack) +{ + struct ets_class *cl = ets_class_from_arg(sch, *arg); + struct ets_sched *q = qdisc_priv(sch); + struct nlattr *opt = tca[TCA_OPTIONS]; + struct nlattr *tb[TCA_ETS_MAX + 1]; + unsigned int quantum; + int err; + + /* Classes can be added and removed only through Qdisc_ops.change + * interface. + */ + if (!cl) { + NL_SET_ERR_MSG(extack, "Fine-grained class addition and removal is not supported"); + return -EOPNOTSUPP; + } + + if (!opt) { + NL_SET_ERR_MSG(extack, "ETS options are required for this operation"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_ETS_MAX, opt, ets_class_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_ETS_QUANTA_BAND]) + /* Nothing to configure. */ + return 0; + + if (ets_class_is_strict(q, cl)) { + NL_SET_ERR_MSG(extack, "Strict bands do not have a configurable quantum"); + return -EINVAL; + } + + err = ets_quantum_parse(sch, tb[TCA_ETS_QUANTA_BAND], &quantum, + extack); + if (err) + return err; + + sch_tree_lock(sch); + cl->quantum = quantum; + sch_tree_unlock(sch); + + ets_offload_change(sch); + return 0; +} + +static int ets_class_graft(struct Qdisc *sch, unsigned long arg, + struct Qdisc *new, struct Qdisc **old, + struct netlink_ext_ack *extack) +{ + struct ets_class *cl = ets_class_from_arg(sch, arg); + + if (!new) { + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + ets_class_id(sch, cl), NULL); + if (!new) + new = &noop_qdisc; + else + qdisc_hash_add(new, true); + } + + *old = qdisc_replace(sch, new, &cl->qdisc); + ets_offload_graft(sch, new, *old, arg, extack); + return 0; +} + +static struct Qdisc *ets_class_leaf(struct Qdisc *sch, unsigned long arg) +{ + struct ets_class *cl = ets_class_from_arg(sch, arg); + + return cl->qdisc; +} + +static unsigned long ets_class_find(struct Qdisc *sch, u32 classid) +{ + unsigned long band = TC_H_MIN(classid); + struct ets_sched *q = qdisc_priv(sch); + + if (band - 1 >= q->nbands) + return 0; + return band; +} + +static void ets_class_qlen_notify(struct Qdisc *sch, unsigned long arg) +{ + struct ets_class *cl = ets_class_from_arg(sch, arg); + struct ets_sched *q = qdisc_priv(sch); + + /* We get notified about zero-length child Qdiscs as well if they are + * offloaded. Those aren't on the active list though, so don't attempt + * to remove them. + */ + if (!ets_class_is_strict(q, cl) && sch->q.qlen) + list_del(&cl->alist); +} + +static int ets_class_dump(struct Qdisc *sch, unsigned long arg, + struct sk_buff *skb, struct tcmsg *tcm) +{ + struct ets_class *cl = ets_class_from_arg(sch, arg); + struct ets_sched *q = qdisc_priv(sch); + struct nlattr *nest; + + tcm->tcm_parent = TC_H_ROOT; + tcm->tcm_handle = ets_class_id(sch, cl); + tcm->tcm_info = cl->qdisc->handle; + + nest = nla_nest_start_noflag(skb, TCA_OPTIONS); + if (!nest) + goto nla_put_failure; + if (!ets_class_is_strict(q, cl)) { + if (nla_put_u32(skb, TCA_ETS_QUANTA_BAND, cl->quantum)) + goto nla_put_failure; + } + return nla_nest_end(skb, nest); + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int ets_class_dump_stats(struct Qdisc *sch, unsigned long arg, + struct gnet_dump *d) +{ + struct ets_class *cl = ets_class_from_arg(sch, arg); + struct Qdisc *cl_q = cl->qdisc; + + if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), + d, NULL, &cl_q->bstats) < 0 || + qdisc_qstats_copy(d, cl_q) < 0) + return -1; + + return 0; +} + +static void ets_qdisc_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + struct ets_sched *q = qdisc_priv(sch); + int i; + + if (arg->stop) + return; + + for (i = 0; i < q->nbands; i++) { + if (arg->count < arg->skip) { + arg->count++; + continue; + } + if (arg->fn(sch, i + 1, arg) < 0) { + arg->stop = 1; + break; + } + arg->count++; + } +} + +static struct tcf_block * +ets_qdisc_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) +{ + struct ets_sched *q = qdisc_priv(sch); + + if (cl) { + NL_SET_ERR_MSG(extack, "ETS classid must be zero"); + return NULL; + } + + return q->block; +} + +static unsigned long ets_qdisc_bind_tcf(struct Qdisc *sch, unsigned long parent, + u32 classid) +{ + return ets_class_find(sch, classid); +} + +static void ets_qdisc_unbind_tcf(struct Qdisc *sch, unsigned long arg) +{ +} + +static struct ets_class *ets_classify(struct sk_buff *skb, struct Qdisc *sch, + int *qerr) +{ + struct ets_sched *q = qdisc_priv(sch); + u32 band = skb->priority; + struct tcf_result res; + struct tcf_proto *fl; + int err; + + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; + if (TC_H_MAJ(skb->priority) != sch->handle) { + fl = rcu_dereference_bh(q->filter_list); + err = tcf_classify(skb, fl, &res, false); +#ifdef CONFIG_NET_CLS_ACT + switch (err) { + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + case TC_ACT_TRAP: + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ + case TC_ACT_SHOT: + return NULL; + } +#endif + if (!fl || err < 0) { + if (TC_H_MAJ(band)) + band = 0; + return &q->classes[q->prio2band[band & TC_PRIO_MAX]]; + } + band = res.classid; + } + band = TC_H_MIN(band) - 1; + if (band >= q->nbands) + return &q->classes[q->prio2band[0]]; + return &q->classes[band]; +} + +static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + unsigned int len = qdisc_pkt_len(skb); + struct ets_sched *q = qdisc_priv(sch); + struct ets_class *cl; + int err = 0; + bool first; + + cl = ets_classify(skb, sch, &err); + if (!cl) { + if (err & __NET_XMIT_BYPASS) + qdisc_qstats_drop(sch); + __qdisc_drop(skb, to_free); + return err; + } + + first = !cl->qdisc->q.qlen; + err = qdisc_enqueue(skb, cl->qdisc, to_free); + if (unlikely(err != NET_XMIT_SUCCESS)) { + if (net_xmit_drop_count(err)) { + cl->qstats.drops++; + qdisc_qstats_drop(sch); + } + return err; + } + + if (first && !ets_class_is_strict(q, cl)) { + list_add_tail(&cl->alist, &q->active); + cl->deficit = cl->quantum; + } + + sch->qstats.backlog += len; + sch->q.qlen++; + return err; +} + +static struct sk_buff * +ets_qdisc_dequeue_skb(struct Qdisc *sch, struct sk_buff *skb) +{ + qdisc_bstats_update(sch, skb); + qdisc_qstats_backlog_dec(sch, skb); + sch->q.qlen--; + return skb; +} + +static struct sk_buff *ets_qdisc_dequeue(struct Qdisc *sch) +{ + struct ets_sched *q = qdisc_priv(sch); + struct ets_class *cl; + struct sk_buff *skb; + unsigned int band; + unsigned int len; + + while (1) { + for (band = 0; band < q->nstrict; band++) { + cl = &q->classes[band]; + skb = qdisc_dequeue_peeked(cl->qdisc); + if (skb) + return ets_qdisc_dequeue_skb(sch, skb); + } + + if (list_empty(&q->active)) + goto out; + + cl = list_first_entry(&q->active, struct ets_class, alist); + skb = cl->qdisc->ops->peek(cl->qdisc); + if (!skb) { + qdisc_warn_nonwc(__func__, cl->qdisc); + goto out; + } + + len = qdisc_pkt_len(skb); + if (len <= cl->deficit) { + cl->deficit -= len; + skb = qdisc_dequeue_peeked(cl->qdisc); + if (unlikely(!skb)) + goto out; + if (cl->qdisc->q.qlen == 0) + list_del(&cl->alist); + return ets_qdisc_dequeue_skb(sch, skb); + } + + cl->deficit += cl->quantum; + list_move_tail(&cl->alist, &q->active); + } +out: + return NULL; +} + +static int ets_qdisc_priomap_parse(struct nlattr *priomap_attr, + unsigned int nbands, u8 *priomap, + struct netlink_ext_ack *extack) +{ + const struct nlattr *attr; + int prio = 0; + u8 band; + int rem; + int err; + + err = __nla_validate_nested(priomap_attr, TCA_ETS_MAX, + ets_priomap_policy, NL_VALIDATE_STRICT, + extack); + if (err) + return err; + + nla_for_each_nested(attr, priomap_attr, rem) { + switch (nla_type(attr)) { + case TCA_ETS_PRIOMAP_BAND: + if (prio > TC_PRIO_MAX) { + NL_SET_ERR_MSG_MOD(extack, "Too many priorities in ETS priomap"); + return -EINVAL; + } + band = nla_get_u8(attr); + if (band >= nbands) { + NL_SET_ERR_MSG_MOD(extack, "Invalid band number in ETS priomap"); + return -EINVAL; + } + priomap[prio++] = band; + break; + default: + WARN_ON_ONCE(1); /* Validate should have caught this. */ + return -EINVAL; + } + } + + return 0; +} + +static int ets_qdisc_quanta_parse(struct Qdisc *sch, struct nlattr *quanta_attr, + unsigned int nbands, unsigned int nstrict, + unsigned int *quanta, + struct netlink_ext_ack *extack) +{ + const struct nlattr *attr; + int band = nstrict; + int rem; + int err; + + err = __nla_validate_nested(quanta_attr, TCA_ETS_MAX, + ets_quanta_policy, NL_VALIDATE_STRICT, + extack); + if (err < 0) + return err; + + nla_for_each_nested(attr, quanta_attr, rem) { + switch (nla_type(attr)) { + case TCA_ETS_QUANTA_BAND: + if (band >= nbands) { + NL_SET_ERR_MSG_MOD(extack, "ETS quanta has more values than bands"); + return -EINVAL; + } + err = ets_quantum_parse(sch, attr, &quanta[band++], + extack); + if (err) + return err; + break; + default: + WARN_ON_ONCE(1); /* Validate should have caught this. */ + return -EINVAL; + } + } + + return 0; +} + +static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + unsigned int quanta[TCQ_ETS_MAX_BANDS] = {0}; + struct Qdisc *queues[TCQ_ETS_MAX_BANDS]; + struct ets_sched *q = qdisc_priv(sch); + struct nlattr *tb[TCA_ETS_MAX + 1]; + unsigned int oldbands = q->nbands; + u8 priomap[TC_PRIO_MAX + 1]; + unsigned int nstrict = 0; + unsigned int nbands; + unsigned int i; + int err; + + if (!opt) { + NL_SET_ERR_MSG(extack, "ETS options are required for this operation"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_ETS_MAX, opt, ets_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_ETS_NBANDS]) { + NL_SET_ERR_MSG_MOD(extack, "Number of bands is a required argument"); + return -EINVAL; + } + nbands = nla_get_u8(tb[TCA_ETS_NBANDS]); + if (nbands < 1 || nbands > TCQ_ETS_MAX_BANDS) { + NL_SET_ERR_MSG_MOD(extack, "Invalid number of bands"); + return -EINVAL; + } + /* Unless overridden, traffic goes to the last band. */ + memset(priomap, nbands - 1, sizeof(priomap)); + + if (tb[TCA_ETS_NSTRICT]) { + nstrict = nla_get_u8(tb[TCA_ETS_NSTRICT]); + if (nstrict > nbands) { + NL_SET_ERR_MSG_MOD(extack, "Invalid number of strict bands"); + return -EINVAL; + } + } + + if (tb[TCA_ETS_PRIOMAP]) { + err = ets_qdisc_priomap_parse(tb[TCA_ETS_PRIOMAP], + nbands, priomap, extack); + if (err) + return err; + } + + if (tb[TCA_ETS_QUANTA]) { + err = ets_qdisc_quanta_parse(sch, tb[TCA_ETS_QUANTA], + nbands, nstrict, quanta, extack); + if (err) + return err; + } + /* If there are more bands than strict + quanta provided, the remaining + * ones are ETS with quantum of MTU. Initialize the missing values here. + */ + for (i = nstrict; i < nbands; i++) { + if (!quanta[i]) + quanta[i] = psched_mtu(qdisc_dev(sch)); + } + + /* Before commit, make sure we can allocate all new qdiscs */ + for (i = oldbands; i < nbands; i++) { + queues[i] = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + ets_class_id(sch, &q->classes[i]), + extack); + if (!queues[i]) { + while (i > oldbands) + qdisc_put(queues[--i]); + return -ENOMEM; + } + } + + sch_tree_lock(sch); + + q->nbands = nbands; + q->nstrict = nstrict; + memcpy(q->prio2band, priomap, sizeof(priomap)); + + for (i = q->nbands; i < oldbands; i++) + qdisc_tree_flush_backlog(q->classes[i].qdisc); + + for (i = 0; i < q->nbands; i++) + q->classes[i].quantum = quanta[i]; + + for (i = oldbands; i < q->nbands; i++) { + q->classes[i].qdisc = queues[i]; + if (q->classes[i].qdisc != &noop_qdisc) + qdisc_hash_add(q->classes[i].qdisc, true); + } + + sch_tree_unlock(sch); + + ets_offload_change(sch); + for (i = q->nbands; i < oldbands; i++) { + qdisc_put(q->classes[i].qdisc); + memset(&q->classes[i], 0, sizeof(q->classes[i])); + } + return 0; +} + +static int ets_qdisc_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct ets_sched *q = qdisc_priv(sch); + int err; + + if (!opt) + return -EINVAL; + + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); + if (err) + return err; + + INIT_LIST_HEAD(&q->active); + return ets_qdisc_change(sch, opt, extack); +} + +static void ets_qdisc_reset(struct Qdisc *sch) +{ + struct ets_sched *q = qdisc_priv(sch); + int band; + + for (band = q->nstrict; band < q->nbands; band++) { + if (q->classes[band].qdisc->q.qlen) + list_del(&q->classes[band].alist); + } + for (band = 0; band < q->nbands; band++) + qdisc_reset(q->classes[band].qdisc); + sch->qstats.backlog = 0; + sch->q.qlen = 0; +} + +static void ets_qdisc_destroy(struct Qdisc *sch) +{ + struct ets_sched *q = qdisc_priv(sch); + int band; + + ets_offload_destroy(sch); + tcf_block_put(q->block); + for (band = 0; band < q->nbands; band++) + qdisc_put(q->classes[band].qdisc); +} + +static int ets_qdisc_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct ets_sched *q = qdisc_priv(sch); + struct nlattr *opts; + struct nlattr *nest; + int band; + int prio; + int err; + + err = ets_offload_dump(sch); + if (err) + return err; + + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); + if (!opts) + goto nla_err; + + if (nla_put_u8(skb, TCA_ETS_NBANDS, q->nbands)) + goto nla_err; + + if (q->nstrict && + nla_put_u8(skb, TCA_ETS_NSTRICT, q->nstrict)) + goto nla_err; + + if (q->nbands > q->nstrict) { + nest = nla_nest_start(skb, TCA_ETS_QUANTA); + if (!nest) + goto nla_err; + + for (band = q->nstrict; band < q->nbands; band++) { + if (nla_put_u32(skb, TCA_ETS_QUANTA_BAND, + q->classes[band].quantum)) + goto nla_err; + } + + nla_nest_end(skb, nest); + } + + nest = nla_nest_start(skb, TCA_ETS_PRIOMAP); + if (!nest) + goto nla_err; + + for (prio = 0; prio <= TC_PRIO_MAX; prio++) { + if (nla_put_u8(skb, TCA_ETS_PRIOMAP_BAND, q->prio2band[prio])) + goto nla_err; + } + + nla_nest_end(skb, nest); + + return nla_nest_end(skb, opts); + +nla_err: + nla_nest_cancel(skb, opts); + return -EMSGSIZE; +} + +static const struct Qdisc_class_ops ets_class_ops = { + .change = ets_class_change, + .graft = ets_class_graft, + .leaf = ets_class_leaf, + .find = ets_class_find, + .qlen_notify = ets_class_qlen_notify, + .dump = ets_class_dump, + .dump_stats = ets_class_dump_stats, + .walk = ets_qdisc_walk, + .tcf_block = ets_qdisc_tcf_block, + .bind_tcf = ets_qdisc_bind_tcf, + .unbind_tcf = ets_qdisc_unbind_tcf, +}; + +static struct Qdisc_ops ets_qdisc_ops __read_mostly = { + .cl_ops = &ets_class_ops, + .id = "ets", + .priv_size = sizeof(struct ets_sched), + .enqueue = ets_qdisc_enqueue, + .dequeue = ets_qdisc_dequeue, + .peek = qdisc_peek_dequeued, + .change = ets_qdisc_change, + .init = ets_qdisc_init, + .reset = ets_qdisc_reset, + .destroy = ets_qdisc_destroy, + .dump = ets_qdisc_dump, + .owner = THIS_MODULE, +}; + +static int __init ets_init(void) +{ + return register_qdisc(&ets_qdisc_ops); +} + +static void __exit ets_exit(void) +{ + unregister_qdisc(&ets_qdisc_ops); +} + +module_init(ets_init); +module_exit(ets_exit); +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 5ab696efca95..6c9595f1048a 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -441,7 +441,7 @@ static void dev_watchdog(struct timer_list *t) trace_net_dev_xmit_timeout(dev, i); WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out\n", dev->name, netdev_drivername(dev), i); - dev->netdev_ops->ndo_tx_timeout(dev); + dev->netdev_ops->ndo_tx_timeout(dev, i); } if (!mod_timer(&dev->watchdog_timer, round_jiffies(jiffies + diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index a031d1134c60..6b0b3bad4daa 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -36,6 +36,7 @@ #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> +#include <trace/events/sctp.h> /* Declare internal functions here. */ static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn); @@ -1238,6 +1239,11 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_chunk *chunk) /* Grab the association's destination address list. */ transport_list = &asoc->peer.transport_addr_list; + /* SCTP path tracepoint for congestion control debugging. */ + list_for_each_entry(transport, transport_list, transports) { + trace_sctp_probe_path(transport, asoc); + } + sack_ctsn = ntohl(sack->cum_tsn_ack); gap_ack_blocks = ntohs(sack->num_gap_ack_blocks); asoc->stats.gapcnt += gap_ack_blocks; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index fbbf19128c2d..78af2fcf90cc 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -227,6 +227,7 @@ static void sctp_v4_from_skb(union sctp_addr *addr, struct sk_buff *skb, sa->sin_port = sh->dest; sa->sin_addr.s_addr = ip_hdr(skb)->daddr; } + memset(sa->sin_zero, 0, sizeof(sa->sin_zero)); } /* Initialize an sctp_addr from a socket. */ @@ -235,6 +236,7 @@ static void sctp_v4_from_sk(union sctp_addr *addr, struct sock *sk) addr->v4.sin_family = AF_INET; addr->v4.sin_port = 0; addr->v4.sin_addr.s_addr = inet_sk(sk)->inet_rcv_saddr; + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Initialize sk->sk_rcv_saddr from sctp_addr. */ @@ -257,6 +259,7 @@ static void sctp_v4_from_addr_param(union sctp_addr *addr, addr->v4.sin_family = AF_INET; addr->v4.sin_port = port; addr->v4.sin_addr.s_addr = param->v4.addr.s_addr; + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Initialize an address parameter from a sctp_addr and return the length @@ -281,6 +284,7 @@ static void sctp_v4_dst_saddr(union sctp_addr *saddr, struct flowi4 *fl4, saddr->v4.sin_family = AF_INET; saddr->v4.sin_port = port; saddr->v4.sin_addr.s_addr = fl4->saddr; + memset(saddr->v4.sin_zero, 0, sizeof(saddr->v4.sin_zero)); } /* Compare two addresses exactly. */ @@ -303,6 +307,7 @@ static void sctp_v4_inaddr_any(union sctp_addr *addr, __be16 port) addr->v4.sin_family = AF_INET; addr->v4.sin_addr.s_addr = htonl(INADDR_ANY); addr->v4.sin_port = port; + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Is this a wildcard address? */ diff --git a/net/sctp/stream.c b/net/sctp/stream.c index df60b5ef24cb..e0b01bf912b3 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -84,8 +84,10 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, return 0; ret = genradix_prealloc(&stream->out, outcnt, gfp); - if (ret) + if (ret) { + genradix_free(&stream->out); return ret; + } stream->outcnt = outcnt; return 0; @@ -100,8 +102,10 @@ static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt, return 0; ret = genradix_prealloc(&stream->in, incnt, gfp); - if (ret) + if (ret) { + genradix_free(&stream->in); return ret; + } stream->incnt = incnt; return 0; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index b997072c72e5..cee5bf4a9bb9 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -857,6 +857,8 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr, goto out; sock_hold(&smc->sk); /* sock put in passive closing */ + if (smc->use_fallback) + goto out; if (flags & O_NONBLOCK) { if (schedule_work(&smc->connect_work)) smc->connect_nonblock = 1; @@ -1721,8 +1723,6 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, sk->sk_err = smc->clcsock->sk->sk_err; sk->sk_error_report(sk); } - if (rc) - return rc; if (optlen < sizeof(int)) return -EINVAL; @@ -1730,6 +1730,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, return -EFAULT; lock_sock(sk); + if (rc || smc->use_fallback) + goto out; switch (optname) { case TCP_ULP: case TCP_FASTOPEN: @@ -1741,15 +1743,14 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, smc_switch_to_fallback(smc); smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; } else { - if (!smc->use_fallback) - rc = -EINVAL; + rc = -EINVAL; } break; case TCP_NODELAY: if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { - if (val && !smc->use_fallback) + if (val) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); } @@ -1758,7 +1759,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { - if (!val && !smc->use_fallback) + if (!val) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); } @@ -1769,6 +1770,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, default: break; } +out: release_sock(sk); return rc; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index bb92c7c6214c..2249de5379ee 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -41,7 +41,7 @@ static struct smc_lgr_list smc_lgr_list = { /* established link groups */ .num = 0, }; -static atomic_t lgr_cnt; /* number of existing link groups */ +static atomic_t lgr_cnt = ATOMIC_INIT(0); /* number of existing link groups */ static DECLARE_WAIT_QUEUE_HEAD(lgrs_deleted); static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb, @@ -1287,7 +1287,7 @@ static int smc_core_reboot_event(struct notifier_block *this, unsigned long event, void *ptr) { smc_lgrs_shutdown(); - + smc_ib_unregister_client(); return 0; } @@ -1297,7 +1297,6 @@ static struct notifier_block smc_reboot_notifier = { int __init smc_core_init(void) { - atomic_set(&lgr_cnt, 0); return register_reboot_notifier(&smc_reboot_notifier); } diff --git a/net/socket.c b/net/socket.c index 4d38d49d6ad9..51bf34995bcb 100644 --- a/net/socket.c +++ b/net/socket.c @@ -128,6 +128,7 @@ static ssize_t sock_sendpage(struct file *file, struct page *page, static ssize_t sock_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); +static void sock_show_fdinfo(struct seq_file *m, struct file *f); /* * Socket files have a set of 'special' operations as well as the generic file ones. These don't appear @@ -150,6 +151,9 @@ static const struct file_operations socket_file_ops = { .sendpage = sock_sendpage, .splice_write = generic_splice_sendpage, .splice_read = sock_splice_read, +#ifdef CONFIG_PROC_FS + .show_fdinfo = sock_show_fdinfo, +#endif }; /* @@ -957,7 +961,7 @@ static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to) .msg_iocb = iocb}; ssize_t res; - if (file->f_flags & O_NONBLOCK) + if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT)) msg.msg_flags = MSG_DONTWAIT; if (iocb->ki_pos != 0) @@ -982,7 +986,7 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) if (iocb->ki_pos != 0) return -ESPIPE; - if (file->f_flags & O_NONBLOCK) + if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT)) msg.msg_flags = MSG_DONTWAIT; if (sock->type == SOCK_SEQPACKET) @@ -993,6 +997,14 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) return res; } +static void sock_show_fdinfo(struct seq_file *m, struct file *f) +{ + struct socket *sock = f->private_data; + + if (sock->ops->show_fdinfo) + sock->ops->show_fdinfo(m, sock); +} + /* * Atomic setting of ioctl hooks to avoid race * with module unload. diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 42e01e9cf893..4c20be08b9c4 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -305,17 +305,17 @@ static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts, * @skb: socket buffer to copy * @method: send method to be used * @dests: destination nodes for message. - * @cong_link_cnt: returns number of encountered congested destination links * Returns 0 if success, otherwise errno */ static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb, struct tipc_mc_method *method, - struct tipc_nlist *dests, - u16 *cong_link_cnt) + struct tipc_nlist *dests) { struct tipc_msg *hdr, *_hdr; struct sk_buff_head tmpq; struct sk_buff *_skb; + u16 cong_link_cnt; + int rc = 0; /* Is a cluster supporting with new capabilities ? */ if (!(tipc_net(net)->capabilities & TIPC_MCAST_RBCTL)) @@ -343,18 +343,19 @@ static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb, _hdr = buf_msg(_skb); msg_set_size(_hdr, MCAST_H_SIZE); msg_set_is_rcast(_hdr, !msg_is_rcast(hdr)); + msg_set_errcode(_hdr, TIPC_ERR_NO_PORT); __skb_queue_head_init(&tmpq); __skb_queue_tail(&tmpq, _skb); if (method->rcast) - tipc_bcast_xmit(net, &tmpq, cong_link_cnt); + rc = tipc_bcast_xmit(net, &tmpq, &cong_link_cnt); else - tipc_rcast_xmit(net, &tmpq, dests, cong_link_cnt); + rc = tipc_rcast_xmit(net, &tmpq, dests, &cong_link_cnt); /* This queue should normally be empty by now */ __skb_queue_purge(&tmpq); - return 0; + return rc; } /* tipc_mcast_xmit - deliver message to indicated destination nodes @@ -396,9 +397,14 @@ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts, msg_set_is_rcast(hdr, method->rcast); /* Switch method ? */ - if (rcast != method->rcast) - tipc_mcast_send_sync(net, skb, method, - dests, cong_link_cnt); + if (rcast != method->rcast) { + rc = tipc_mcast_send_sync(net, skb, method, dests); + if (unlikely(rc)) { + pr_err("Unable to send SYN: method %d, rc %d\n", + rcast, rc); + goto exit; + } + } if (method->rcast) rc = tipc_rcast_xmit(net, pkts, dests, cong_link_cnt); diff --git a/net/tipc/discover.c b/net/tipc/discover.c index b043e8c6397a..bfe43da127c0 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -194,6 +194,7 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb, { struct tipc_net *tn = tipc_net(net); struct tipc_msg *hdr = buf_msg(skb); + u32 pnet_hash = msg_peer_net_hash(hdr); u16 caps = msg_node_capabilities(hdr); bool legacy = tn->legacy_addr_format; u32 sugg = msg_sugg_node_addr(hdr); @@ -242,9 +243,8 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb, return; if (!tipc_in_scope(legacy, b->domain, src)) return; - tipc_node_check_dest(net, src, peer_id, b, caps, signature, - msg_peer_net_hash(hdr), &maddr, &respond, - &dupl_addr); + tipc_node_check_dest(net, src, peer_id, b, caps, signature, pnet_hash, + &maddr, &respond, &dupl_addr); if (dupl_addr) disc_dupl_alert(b, src, &maddr); if (!respond) diff --git a/net/tipc/link.c b/net/tipc/link.c index 94dd48cd70a3..467c53a1fb5c 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -250,7 +250,7 @@ static int tipc_link_build_nack_msg(struct tipc_link *l, static void tipc_link_build_bc_init_msg(struct tipc_link *l, struct sk_buff_head *xmitq); static int tipc_link_release_pkts(struct tipc_link *l, u16 to); -static u16 tipc_build_gap_ack_blks(struct tipc_link *l, void *data); +static u16 tipc_build_gap_ack_blks(struct tipc_link *l, void *data, u16 gap); static int tipc_link_advance_transmq(struct tipc_link *l, u16 acked, u16 gap, struct tipc_gap_ack_blks *ga, struct sk_buff_head *xmitq); @@ -1423,14 +1423,14 @@ static int tipc_link_release_pkts(struct tipc_link *l, u16 acked) * * returns the actual allocated memory size */ -static u16 tipc_build_gap_ack_blks(struct tipc_link *l, void *data) +static u16 tipc_build_gap_ack_blks(struct tipc_link *l, void *data, u16 gap) { struct sk_buff *skb = skb_peek(&l->deferdq); struct tipc_gap_ack_blks *ga = data; u16 len, expect, seqno = 0; u8 n = 0; - if (!skb) + if (!skb || !gap) goto exit; expect = buf_seqno(skb); @@ -1739,7 +1739,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, msg_set_probe(hdr, probe); msg_set_is_keepalive(hdr, probe || probe_reply); if (l->peer_caps & TIPC_GAP_ACK_BLOCK) - glen = tipc_build_gap_ack_blks(l, data); + glen = tipc_build_gap_ack_blks(l, data, rcvgap); tipc_mon_prep(l->net, data + glen, &dlen, mstate, l->bearer_id); msg_set_size(hdr, INT_H_SIZE + glen + dlen); skb_trim(skb, INT_H_SIZE + glen + dlen); diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 92d04dc2a44b..359b2bc888cf 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -36,6 +36,7 @@ #include <net/sock.h> #include <linux/list_sort.h> +#include <linux/rbtree_augmented.h> #include "core.h" #include "netlink.h" #include "name_table.h" @@ -51,6 +52,7 @@ * @lower: service range lower bound * @upper: service range upper bound * @tree_node: member of service range RB tree + * @max: largest 'upper' in this node subtree * @local_publ: list of identical publications made from this node * Used by closest_first lookup and multicast lookup algorithm * @all_publ: all publications identical to this one, whatever node and scope @@ -60,6 +62,7 @@ struct service_range { u32 lower; u32 upper; struct rb_node tree_node; + u32 max; struct list_head local_publ; struct list_head all_publ; }; @@ -84,6 +87,130 @@ struct tipc_service { struct rcu_head rcu; }; +#define service_range_upper(sr) ((sr)->upper) +RB_DECLARE_CALLBACKS_MAX(static, sr_callbacks, + struct service_range, tree_node, u32, max, + service_range_upper) + +#define service_range_entry(rbtree_node) \ + (container_of(rbtree_node, struct service_range, tree_node)) + +#define service_range_overlap(sr, start, end) \ + ((sr)->lower <= (end) && (sr)->upper >= (start)) + +/** + * service_range_foreach_match - iterate over tipc service rbtree for each + * range match + * @sr: the service range pointer as a loop cursor + * @sc: the pointer to tipc service which holds the service range rbtree + * @start, end: the range (end >= start) for matching + */ +#define service_range_foreach_match(sr, sc, start, end) \ + for (sr = service_range_match_first((sc)->ranges.rb_node, \ + start, \ + end); \ + sr; \ + sr = service_range_match_next(&(sr)->tree_node, \ + start, \ + end)) + +/** + * service_range_match_first - find first service range matching a range + * @n: the root node of service range rbtree for searching + * @start, end: the range (end >= start) for matching + * + * Return: the leftmost service range node in the rbtree that overlaps the + * specific range if any. Otherwise, returns NULL. + */ +static struct service_range *service_range_match_first(struct rb_node *n, + u32 start, u32 end) +{ + struct service_range *sr; + struct rb_node *l, *r; + + /* Non overlaps in tree at all? */ + if (!n || service_range_entry(n)->max < start) + return NULL; + + while (n) { + l = n->rb_left; + if (l && service_range_entry(l)->max >= start) { + /* A leftmost overlap range node must be one in the left + * subtree. If not, it has lower > end, then nodes on + * the right side cannot satisfy the condition either. + */ + n = l; + continue; + } + + /* No one in the left subtree can match, return if this node is + * an overlap i.e. leftmost. + */ + sr = service_range_entry(n); + if (service_range_overlap(sr, start, end)) + return sr; + + /* Ok, try to lookup on the right side */ + r = n->rb_right; + if (sr->lower <= end && + r && service_range_entry(r)->max >= start) { + n = r; + continue; + } + break; + } + + return NULL; +} + +/** + * service_range_match_next - find next service range matching a range + * @n: a node in service range rbtree from which the searching starts + * @start, end: the range (end >= start) for matching + * + * Return: the next service range node to the given node in the rbtree that + * overlaps the specific range if any. Otherwise, returns NULL. + */ +static struct service_range *service_range_match_next(struct rb_node *n, + u32 start, u32 end) +{ + struct service_range *sr; + struct rb_node *p, *r; + + while (n) { + r = n->rb_right; + if (r && service_range_entry(r)->max >= start) + /* A next overlap range node must be one in the right + * subtree. If not, it has lower > end, then any next + * successor (- an ancestor) of this node cannot + * satisfy the condition either. + */ + return service_range_match_first(r, start, end); + + /* No one in the right subtree can match, go up to find an + * ancestor of this node which is parent of a left-hand child. + */ + while ((p = rb_parent(n)) && n == p->rb_right) + n = p; + if (!p) + break; + + /* Return if this ancestor is an overlap */ + sr = service_range_entry(p); + if (service_range_overlap(sr, start, end)) + return sr; + + /* Ok, try to lookup more from this ancestor */ + if (sr->lower <= end) { + n = p; + continue; + } + break; + } + + return NULL; +} + static int hash(int x) { return x & (TIPC_NAMETBL_SIZE - 1); @@ -139,84 +266,51 @@ static struct tipc_service *tipc_service_create(u32 type, struct hlist_head *hd) return service; } -/** - * tipc_service_first_range - find first service range in tree matching instance - * - * Very time-critical, so binary search through range rb tree - */ -static struct service_range *tipc_service_first_range(struct tipc_service *sc, - u32 instance) -{ - struct rb_node *n = sc->ranges.rb_node; - struct service_range *sr; - - while (n) { - sr = container_of(n, struct service_range, tree_node); - if (sr->lower > instance) - n = n->rb_left; - else if (sr->upper < instance) - n = n->rb_right; - else - return sr; - } - return NULL; -} - /* tipc_service_find_range - find service range matching publication parameters */ static struct service_range *tipc_service_find_range(struct tipc_service *sc, u32 lower, u32 upper) { - struct rb_node *n = sc->ranges.rb_node; struct service_range *sr; - sr = tipc_service_first_range(sc, lower); - if (!sr) - return NULL; - - /* Look for exact match */ - for (n = &sr->tree_node; n; n = rb_next(n)) { - sr = container_of(n, struct service_range, tree_node); - if (sr->upper == upper) - break; + service_range_foreach_match(sr, sc, lower, upper) { + /* Look for exact match */ + if (sr->lower == lower && sr->upper == upper) + return sr; } - if (!n || sr->lower != lower || sr->upper != upper) - return NULL; - return sr; + return NULL; } static struct service_range *tipc_service_create_range(struct tipc_service *sc, u32 lower, u32 upper) { struct rb_node **n, *parent = NULL; - struct service_range *sr, *tmp; + struct service_range *sr; n = &sc->ranges.rb_node; while (*n) { - tmp = container_of(*n, struct service_range, tree_node); parent = *n; - tmp = container_of(parent, struct service_range, tree_node); - if (lower < tmp->lower) - n = &(*n)->rb_left; - else if (lower > tmp->lower) - n = &(*n)->rb_right; - else if (upper < tmp->upper) - n = &(*n)->rb_left; - else if (upper > tmp->upper) - n = &(*n)->rb_right; + sr = service_range_entry(parent); + if (lower == sr->lower && upper == sr->upper) + return sr; + if (sr->max < upper) + sr->max = upper; + if (lower <= sr->lower) + n = &parent->rb_left; else - return tmp; + n = &parent->rb_right; } sr = kzalloc(sizeof(*sr), GFP_ATOMIC); if (!sr) return NULL; sr->lower = lower; sr->upper = upper; + sr->max = upper; INIT_LIST_HEAD(&sr->local_publ); INIT_LIST_HEAD(&sr->all_publ); rb_link_node(&sr->tree_node, parent, n); - rb_insert_color(&sr->tree_node, &sc->ranges); + rb_insert_augmented(&sr->tree_node, &sc->ranges, &sr_callbacks); return sr; } @@ -310,7 +404,6 @@ static void tipc_service_subscribe(struct tipc_service *service, struct list_head publ_list; struct service_range *sr; struct tipc_name_seq ns; - struct rb_node *n; u32 filter; ns.type = tipc_sub_read(sb, seq.type); @@ -325,13 +418,7 @@ static void tipc_service_subscribe(struct tipc_service *service, return; INIT_LIST_HEAD(&publ_list); - for (n = rb_first(&service->ranges); n; n = rb_next(n)) { - sr = container_of(n, struct service_range, tree_node); - if (sr->lower > ns.upper) - break; - if (!tipc_sub_check_overlap(&ns, sr->lower, sr->upper)) - continue; - + service_range_foreach_match(sr, service, ns.lower, ns.upper) { first = NULL; list_for_each_entry(p, &sr->all_publ, all_publ) { if (filter & TIPC_SUB_PORTS) @@ -425,7 +512,7 @@ struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type, /* Remove service range item if this was its last publication */ if (list_empty(&sr->all_publ)) { - rb_erase(&sr->tree_node, &sc->ranges); + rb_erase_augmented(&sr->tree_node, &sc->ranges, &sr_callbacks); kfree(sr); } @@ -473,34 +560,39 @@ u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, u32 *dnode) rcu_read_lock(); sc = tipc_service_find(net, type); if (unlikely(!sc)) - goto not_found; + goto exit; spin_lock_bh(&sc->lock); - sr = tipc_service_first_range(sc, instance); - if (unlikely(!sr)) - goto no_match; - - /* Select lookup algorithm: local, closest-first or round-robin */ - if (*dnode == self) { - list = &sr->local_publ; - if (list_empty(list)) - goto no_match; - p = list_first_entry(list, struct publication, local_publ); - list_move_tail(&p->local_publ, &sr->local_publ); - } else if (legacy && !*dnode && !list_empty(&sr->local_publ)) { - list = &sr->local_publ; - p = list_first_entry(list, struct publication, local_publ); - list_move_tail(&p->local_publ, &sr->local_publ); - } else { - list = &sr->all_publ; - p = list_first_entry(list, struct publication, all_publ); - list_move_tail(&p->all_publ, &sr->all_publ); + service_range_foreach_match(sr, sc, instance, instance) { + /* Select lookup algo: local, closest-first or round-robin */ + if (*dnode == self) { + list = &sr->local_publ; + if (list_empty(list)) + continue; + p = list_first_entry(list, struct publication, + local_publ); + list_move_tail(&p->local_publ, &sr->local_publ); + } else if (legacy && !*dnode && !list_empty(&sr->local_publ)) { + list = &sr->local_publ; + p = list_first_entry(list, struct publication, + local_publ); + list_move_tail(&p->local_publ, &sr->local_publ); + } else { + list = &sr->all_publ; + p = list_first_entry(list, struct publication, + all_publ); + list_move_tail(&p->all_publ, &sr->all_publ); + } + port = p->port; + node = p->node; + /* Todo: as for legacy, pick the first matching range only, a + * "true" round-robin will be performed as needed. + */ + break; } - port = p->port; - node = p->node; -no_match: spin_unlock_bh(&sc->lock); -not_found: + +exit: rcu_read_unlock(); *dnode = node; return port; @@ -523,7 +615,8 @@ bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 scope, spin_lock_bh(&sc->lock); - sr = tipc_service_first_range(sc, instance); + /* Todo: a full search i.e. service_range_foreach_match() instead? */ + sr = service_range_match_first(sc->ranges.rb_node, instance, instance); if (!sr) goto no_match; @@ -552,7 +645,6 @@ void tipc_nametbl_mc_lookup(struct net *net, u32 type, u32 lower, u32 upper, struct service_range *sr; struct tipc_service *sc; struct publication *p; - struct rb_node *n; rcu_read_lock(); sc = tipc_service_find(net, type); @@ -560,13 +652,7 @@ void tipc_nametbl_mc_lookup(struct net *net, u32 type, u32 lower, u32 upper, goto exit; spin_lock_bh(&sc->lock); - - for (n = rb_first(&sc->ranges); n; n = rb_next(n)) { - sr = container_of(n, struct service_range, tree_node); - if (sr->upper < lower) - continue; - if (sr->lower > upper) - break; + service_range_foreach_match(sr, sc, lower, upper) { list_for_each_entry(p, &sr->local_publ, local_publ) { if (p->scope == scope || (!exact && p->scope < scope)) tipc_dest_push(dports, 0, p->port); @@ -587,7 +673,6 @@ void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower, struct service_range *sr; struct tipc_service *sc; struct publication *p; - struct rb_node *n; rcu_read_lock(); sc = tipc_service_find(net, type); @@ -595,13 +680,7 @@ void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower, goto exit; spin_lock_bh(&sc->lock); - - for (n = rb_first(&sc->ranges); n; n = rb_next(n)) { - sr = container_of(n, struct service_range, tree_node); - if (sr->upper < lower) - continue; - if (sr->lower > upper) - break; + service_range_foreach_match(sr, sc, lower, upper) { list_for_each_entry(p, &sr->all_publ, all_publ) { tipc_nlist_add(nodes, p->node); } @@ -799,7 +878,7 @@ static void tipc_service_delete(struct net *net, struct tipc_service *sc) tipc_service_remove_publ(sr, p->node, p->key); kfree_rcu(p, rcu); } - rb_erase(&sr->tree_node, &sc->ranges); + rb_erase_augmented(&sr->tree_node, &sc->ranges, &sr_callbacks); kfree(sr); } hlist_del_init_rcu(&sc->service_list); diff --git a/net/tipc/net.c b/net/tipc/net.c index 2de3cec9929d..85400e4242de 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -302,3 +302,59 @@ int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info) return err; } + +static int __tipc_nl_addr_legacy_get(struct net *net, struct tipc_nl_msg *msg) +{ + struct tipc_net *tn = tipc_net(net); + struct nlattr *attrs; + void *hdr; + + hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, + 0, TIPC_NL_ADDR_LEGACY_GET); + if (!hdr) + return -EMSGSIZE; + + attrs = nla_nest_start(msg->skb, TIPC_NLA_NET); + if (!attrs) + goto msg_full; + + if (tn->legacy_addr_format) + if (nla_put_flag(msg->skb, TIPC_NLA_NET_ADDR_LEGACY)) + goto attr_msg_full; + + nla_nest_end(msg->skb, attrs); + genlmsg_end(msg->skb, hdr); + + return 0; + +attr_msg_full: + nla_nest_cancel(msg->skb, attrs); +msg_full: + genlmsg_cancel(msg->skb, hdr); + + return -EMSGSIZE; +} + +int tipc_nl_net_addr_legacy_get(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = sock_net(skb->sk); + struct tipc_nl_msg msg; + struct sk_buff *rep; + int err; + + rep = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (!rep) + return -ENOMEM; + + msg.skb = rep; + msg.portid = info->snd_portid; + msg.seq = info->snd_seq; + + err = __tipc_nl_addr_legacy_get(net, &msg); + if (err) { + nlmsg_free(msg.skb); + return err; + } + + return genlmsg_reply(msg.skb, info); +} diff --git a/net/tipc/net.h b/net/tipc/net.h index b7f2e364eb99..6740d97c706e 100644 --- a/net/tipc/net.h +++ b/net/tipc/net.h @@ -47,5 +47,6 @@ void tipc_net_stop(struct net *net); int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info); int __tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info); +int tipc_nl_net_addr_legacy_get(struct sk_buff *skb, struct genl_info *info); #endif diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index e53231bd23b4..7c35094c20b8 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -83,6 +83,7 @@ const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = { [TIPC_NLA_NET_ADDR] = { .type = NLA_U32 }, [TIPC_NLA_NET_NODEID] = { .type = NLA_U64 }, [TIPC_NLA_NET_NODEID_W1] = { .type = NLA_U64 }, + [TIPC_NLA_NET_ADDR_LEGACY] = { .type = NLA_FLAG } }; const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = { @@ -273,6 +274,11 @@ static const struct genl_ops tipc_genl_v2_ops[] = { .doit = tipc_nl_node_flush_key, }, #endif + { + .cmd = TIPC_NL_ADDR_LEGACY_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = tipc_nl_net_addr_legacy_get, + }, }; struct genl_family tipc_genl_family __ro_after_init = { diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 41688da233ab..6552f986774c 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1364,8 +1364,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) struct tipc_msg *hdr = &tsk->phdr; struct tipc_name_seq *seq; struct sk_buff_head pkts; - u32 dport, dnode = 0; - u32 type, inst; + u32 dport = 0, dnode = 0; + u32 type = 0, inst = 0; int mtu, rc; if (unlikely(dlen > TIPC_MAX_USER_MSG_SIZE)) @@ -1418,23 +1418,11 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) type = dest->addr.name.name.type; inst = dest->addr.name.name.instance; dnode = dest->addr.name.domain; - msg_set_type(hdr, TIPC_NAMED_MSG); - msg_set_hdr_sz(hdr, NAMED_H_SIZE); - msg_set_nametype(hdr, type); - msg_set_nameinst(hdr, inst); - msg_set_lookup_scope(hdr, tipc_node2scope(dnode)); dport = tipc_nametbl_translate(net, type, inst, &dnode); - msg_set_destnode(hdr, dnode); - msg_set_destport(hdr, dport); if (unlikely(!dport && !dnode)) return -EHOSTUNREACH; } else if (dest->addrtype == TIPC_ADDR_ID) { dnode = dest->addr.id.node; - msg_set_type(hdr, TIPC_DIRECT_MSG); - msg_set_lookup_scope(hdr, 0); - msg_set_destnode(hdr, dnode); - msg_set_destport(hdr, dest->addr.id.ref); - msg_set_hdr_sz(hdr, BASIC_H_SIZE); } else { return -EINVAL; } @@ -1445,6 +1433,22 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) if (unlikely(rc)) return rc; + if (dest->addrtype == TIPC_ADDR_NAME) { + msg_set_type(hdr, TIPC_NAMED_MSG); + msg_set_hdr_sz(hdr, NAMED_H_SIZE); + msg_set_nametype(hdr, type); + msg_set_nameinst(hdr, inst); + msg_set_lookup_scope(hdr, tipc_node2scope(dnode)); + msg_set_destnode(hdr, dnode); + msg_set_destport(hdr, dport); + } else { /* TIPC_ADDR_ID */ + msg_set_type(hdr, TIPC_DIRECT_MSG); + msg_set_lookup_scope(hdr, 0); + msg_set_destnode(hdr, dnode); + msg_set_destport(hdr, dest->addr.id.ref); + msg_set_hdr_sz(hdr, BASIC_H_SIZE); + } + __skb_queue_head_init(&pkts); mtu = tipc_node_get_mtu(net, dnode, tsk->portid, false); rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index cd91ad812291..1ba5a92832bb 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -178,7 +178,7 @@ static void tls_icsk_clean_acked(struct sock *sk, u32 acked_seq) * socket and no in-flight SKBs associated with this * socket, so it is safe to free all the resources. */ -static void tls_device_sk_destruct(struct sock *sk) +void tls_device_sk_destruct(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx); @@ -196,6 +196,7 @@ static void tls_device_sk_destruct(struct sock *sk) if (refcount_dec_and_test(&tls_ctx->refcount)) tls_device_queue_ctx_destruction(tls_ctx); } +EXPORT_SYMBOL_GPL(tls_device_sk_destruct); void tls_device_free_resources_tx(struct sock *sk) { @@ -903,7 +904,7 @@ static void tls_device_attach(struct tls_context *ctx, struct sock *sk, spin_unlock_irq(&tls_device_lock); ctx->sk_destruct = sk->sk_destruct; - sk->sk_destruct = tls_device_sk_destruct; + smp_store_release(&sk->sk_destruct, tls_device_sk_destruct); } } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 7cfdce10de36..6756a3ccc392 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -676,6 +676,16 @@ static int unix_set_peek_off(struct sock *sk, int val) return 0; } +static void unix_show_fdinfo(struct seq_file *m, struct socket *sock) +{ + struct sock *sk = sock->sk; + struct unix_sock *u; + + if (sk) { + u = unix_sk(sock->sk); + seq_printf(m, "scm_fds: %u\n", READ_ONCE(u->scm_stat.nr_fds)); + } +} static const struct proto_ops unix_stream_ops = { .family = PF_UNIX, @@ -701,6 +711,7 @@ static const struct proto_ops unix_stream_ops = { .sendpage = unix_stream_sendpage, .splice_read = unix_stream_splice_read, .set_peek_off = unix_set_peek_off, + .show_fdinfo = unix_show_fdinfo, }; static const struct proto_ops unix_dgram_ops = { @@ -726,6 +737,7 @@ static const struct proto_ops unix_dgram_ops = { .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, .set_peek_off = unix_set_peek_off, + .show_fdinfo = unix_show_fdinfo, }; static const struct proto_ops unix_seqpacket_ops = { @@ -751,6 +763,7 @@ static const struct proto_ops unix_seqpacket_ops = { .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, .set_peek_off = unix_set_peek_off, + .show_fdinfo = unix_show_fdinfo, }; static struct proto unix_proto = { @@ -788,6 +801,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern) mutex_init(&u->bindlock); /* single task binding lock */ init_waitqueue_head(&u->peer_wait); init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay); + memset(&u->scm_stat, 0, sizeof(struct scm_stat)); unix_insert_socket(unix_sockets_unbound(sk), sk); out: if (sk == NULL) @@ -1572,6 +1586,28 @@ static bool unix_skb_scm_eq(struct sk_buff *skb, unix_secdata_eq(scm, skb); } +static void scm_stat_add(struct sock *sk, struct sk_buff *skb) +{ + struct scm_fp_list *fp = UNIXCB(skb).fp; + struct unix_sock *u = unix_sk(sk); + + lockdep_assert_held(&sk->sk_receive_queue.lock); + + if (unlikely(fp && fp->count)) + u->scm_stat.nr_fds += fp->count; +} + +static void scm_stat_del(struct sock *sk, struct sk_buff *skb) +{ + struct scm_fp_list *fp = UNIXCB(skb).fp; + struct unix_sock *u = unix_sk(sk); + + lockdep_assert_held(&sk->sk_receive_queue.lock); + + if (unlikely(fp && fp->count)) + u->scm_stat.nr_fds -= fp->count; +} + /* * Send AF_UNIX data. */ @@ -1757,7 +1793,10 @@ restart_locked: if (sock_flag(other, SOCK_RCVTSTAMP)) __net_timestamp(skb); maybe_add_creds(skb, sock, other); - skb_queue_tail(&other->sk_receive_queue, skb); + spin_lock(&other->sk_receive_queue.lock); + scm_stat_add(other, skb); + __skb_queue_tail(&other->sk_receive_queue, skb); + spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); other->sk_data_ready(other); sock_put(other); @@ -1859,7 +1898,10 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, goto pipe_err_free; maybe_add_creds(skb, sock, other); - skb_queue_tail(&other->sk_receive_queue, skb); + spin_lock(&other->sk_receive_queue.lock); + scm_stat_add(other, skb); + __skb_queue_tail(&other->sk_receive_queue, skb); + spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); other->sk_data_ready(other); sent += size; @@ -2058,8 +2100,8 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, mutex_lock(&u->iolock); skip = sk_peek_offset(sk, flags); - skb = __skb_try_recv_datagram(sk, flags, NULL, &skip, &err, - &last); + skb = __skb_try_recv_datagram(sk, flags, scm_stat_del, + &skip, &err, &last); if (skb) break; @@ -2353,8 +2395,12 @@ unlock: sk_peek_offset_bwd(sk, chunk); - if (UNIXCB(skb).fp) + if (UNIXCB(skb).fp) { + spin_lock(&sk->sk_receive_queue.lock); + scm_stat_del(sk, skb); + spin_unlock(&sk->sk_receive_queue.lock); unix_detach_fds(&scm, skb); + } if (unix_skb_len(skb)) break; @@ -2865,7 +2911,7 @@ static int __init af_unix_init(void) { int rc = -1; - BUILD_BUG_ON(sizeof(struct unix_skb_parms) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct unix_skb_parms) > sizeof_field(struct sk_buff, cb)); rc = proto_register(&unix_proto, 1); if (rc != 0) { diff --git a/net/vmw_vsock/Kconfig b/net/vmw_vsock/Kconfig index 8abcb815af2d..56356d2980c8 100644 --- a/net/vmw_vsock/Kconfig +++ b/net/vmw_vsock/Kconfig @@ -26,6 +26,18 @@ config VSOCKETS_DIAG Enable this module so userspace applications can query open sockets. +config VSOCKETS_LOOPBACK + tristate "Virtual Sockets loopback transport" + depends on VSOCKETS + default y + select VIRTIO_VSOCKETS_COMMON + help + This module implements a loopback transport for Virtual Sockets, + using vmw_vsock_virtio_transport_common. + + To compile this driver as a module, choose M here: the module + will be called vsock_loopback. If unsure, say N. + config VMWARE_VMCI_VSOCKETS tristate "VMware VMCI transport for Virtual Sockets" depends on VSOCKETS && VMWARE_VMCI diff --git a/net/vmw_vsock/Makefile b/net/vmw_vsock/Makefile index 7c6f9a0b67b0..6a943ec95c4a 100644 --- a/net/vmw_vsock/Makefile +++ b/net/vmw_vsock/Makefile @@ -5,6 +5,7 @@ obj-$(CONFIG_VMWARE_VMCI_VSOCKETS) += vmw_vsock_vmci_transport.o obj-$(CONFIG_VIRTIO_VSOCKETS) += vmw_vsock_virtio_transport.o obj-$(CONFIG_VIRTIO_VSOCKETS_COMMON) += vmw_vsock_virtio_transport_common.o obj-$(CONFIG_HYPERV_VSOCKETS) += hv_sock.o +obj-$(CONFIG_VSOCKETS_LOOPBACK) += vsock_loopback.o vsock-y += af_vsock.o af_vsock_tap.o vsock_addr.o diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 74db4cd637a7..9c5b2a91baad 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -136,6 +136,8 @@ static const struct vsock_transport *transport_h2g; static const struct vsock_transport *transport_g2h; /* Transport used for DGRAM communication */ static const struct vsock_transport *transport_dgram; +/* Transport used for local communication */ +static const struct vsock_transport *transport_local; static DEFINE_MUTEX(vsock_register_mutex); /**** UTILS ****/ @@ -386,6 +388,21 @@ void vsock_enqueue_accept(struct sock *listener, struct sock *connected) } EXPORT_SYMBOL_GPL(vsock_enqueue_accept); +static bool vsock_use_local_transport(unsigned int remote_cid) +{ + if (!transport_local) + return false; + + if (remote_cid == VMADDR_CID_LOCAL) + return true; + + if (transport_g2h) { + return remote_cid == transport_g2h->get_local_cid(); + } else { + return remote_cid == VMADDR_CID_HOST; + } +} + static void vsock_deassign_transport(struct vsock_sock *vsk) { if (!vsk->transport) @@ -402,9 +419,9 @@ static void vsock_deassign_transport(struct vsock_sock *vsk) * (e.g. during the connect() or when a connection request on a listener * socket is received). * The vsk->remote_addr is used to decide which transport to use: + * - remote CID == VMADDR_CID_LOCAL or g2h->local_cid or VMADDR_CID_HOST if + * g2h is not loaded, will use local transport; * - remote CID <= VMADDR_CID_HOST will use guest->host transport; - * - remote CID == local_cid (guest->host transport) will use guest->host - * transport for loopback (host->guest transports don't support loopback); * - remote CID > VMADDR_CID_HOST will use host->guest transport; */ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) @@ -419,9 +436,9 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) new_transport = transport_dgram; break; case SOCK_STREAM: - if (remote_cid <= VMADDR_CID_HOST || - (transport_g2h && - remote_cid == transport_g2h->get_local_cid())) + if (vsock_use_local_transport(remote_cid)) + new_transport = transport_local; + else if (remote_cid <= VMADDR_CID_HOST) new_transport = transport_g2h; else new_transport = transport_h2g; @@ -464,6 +481,9 @@ bool vsock_find_cid(unsigned int cid) if (transport_h2g && cid == VMADDR_CID_HOST) return true; + if (transport_local && cid == VMADDR_CID_LOCAL) + return true; + return false; } EXPORT_SYMBOL_GPL(vsock_find_cid); @@ -2137,7 +2157,7 @@ EXPORT_SYMBOL_GPL(vsock_core_get_transport); int vsock_core_register(const struct vsock_transport *t, int features) { - const struct vsock_transport *t_h2g, *t_g2h, *t_dgram; + const struct vsock_transport *t_h2g, *t_g2h, *t_dgram, *t_local; int err = mutex_lock_interruptible(&vsock_register_mutex); if (err) @@ -2146,6 +2166,7 @@ int vsock_core_register(const struct vsock_transport *t, int features) t_h2g = transport_h2g; t_g2h = transport_g2h; t_dgram = transport_dgram; + t_local = transport_local; if (features & VSOCK_TRANSPORT_F_H2G) { if (t_h2g) { @@ -2171,9 +2192,18 @@ int vsock_core_register(const struct vsock_transport *t, int features) t_dgram = t; } + if (features & VSOCK_TRANSPORT_F_LOCAL) { + if (t_local) { + err = -EBUSY; + goto err_busy; + } + t_local = t; + } + transport_h2g = t_h2g; transport_g2h = t_g2h; transport_dgram = t_dgram; + transport_local = t_local; err_busy: mutex_unlock(&vsock_register_mutex); @@ -2194,6 +2224,9 @@ void vsock_core_unregister(const struct vsock_transport *t) if (transport_dgram == t) transport_dgram = NULL; + if (transport_local == t) + transport_local = NULL; + mutex_unlock(&vsock_register_mutex); } EXPORT_SYMBOL_GPL(vsock_core_unregister); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 1458c5c8b64d..dfbaf6bd8b1c 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -44,10 +44,6 @@ struct virtio_vsock { spinlock_t send_pkt_list_lock; struct list_head send_pkt_list; - struct work_struct loopback_work; - spinlock_t loopback_list_lock; /* protects loopback_list */ - struct list_head loopback_list; - atomic_t queued_replies; /* The following fields are protected by rx_lock. vqs[VSOCK_VQ_RX] @@ -86,20 +82,6 @@ out_rcu: return ret; } -static int virtio_transport_send_pkt_loopback(struct virtio_vsock *vsock, - struct virtio_vsock_pkt *pkt) -{ - int len = pkt->len; - - spin_lock_bh(&vsock->loopback_list_lock); - list_add_tail(&pkt->list, &vsock->loopback_list); - spin_unlock_bh(&vsock->loopback_list_lock); - - queue_work(virtio_vsock_workqueue, &vsock->loopback_work); - - return len; -} - static void virtio_transport_send_pkt_work(struct work_struct *work) { @@ -194,7 +176,8 @@ virtio_transport_send_pkt(struct virtio_vsock_pkt *pkt) } if (le64_to_cpu(pkt->hdr.dst_cid) == vsock->guest_cid) { - len = virtio_transport_send_pkt_loopback(vsock, pkt); + virtio_transport_free_pkt(pkt); + len = -ENODEV; goto out_rcu; } @@ -502,33 +485,6 @@ static struct virtio_transport virtio_transport = { .send_pkt = virtio_transport_send_pkt, }; -static void virtio_transport_loopback_work(struct work_struct *work) -{ - struct virtio_vsock *vsock = - container_of(work, struct virtio_vsock, loopback_work); - LIST_HEAD(pkts); - - spin_lock_bh(&vsock->loopback_list_lock); - list_splice_init(&vsock->loopback_list, &pkts); - spin_unlock_bh(&vsock->loopback_list_lock); - - mutex_lock(&vsock->rx_lock); - - if (!vsock->rx_run) - goto out; - - while (!list_empty(&pkts)) { - struct virtio_vsock_pkt *pkt; - - pkt = list_first_entry(&pkts, struct virtio_vsock_pkt, list); - list_del_init(&pkt->list); - - virtio_transport_recv_pkt(&virtio_transport, pkt); - } -out: - mutex_unlock(&vsock->rx_lock); -} - static void virtio_transport_rx_work(struct work_struct *work) { struct virtio_vsock *vsock = @@ -633,13 +589,10 @@ static int virtio_vsock_probe(struct virtio_device *vdev) mutex_init(&vsock->event_lock); spin_lock_init(&vsock->send_pkt_list_lock); INIT_LIST_HEAD(&vsock->send_pkt_list); - spin_lock_init(&vsock->loopback_list_lock); - INIT_LIST_HEAD(&vsock->loopback_list); INIT_WORK(&vsock->rx_work, virtio_transport_rx_work); INIT_WORK(&vsock->tx_work, virtio_transport_tx_work); INIT_WORK(&vsock->event_work, virtio_transport_event_work); INIT_WORK(&vsock->send_pkt_work, virtio_transport_send_pkt_work); - INIT_WORK(&vsock->loopback_work, virtio_transport_loopback_work); mutex_lock(&vsock->tx_lock); vsock->tx_run = true; @@ -720,22 +673,12 @@ static void virtio_vsock_remove(struct virtio_device *vdev) } spin_unlock_bh(&vsock->send_pkt_list_lock); - spin_lock_bh(&vsock->loopback_list_lock); - while (!list_empty(&vsock->loopback_list)) { - pkt = list_first_entry(&vsock->loopback_list, - struct virtio_vsock_pkt, list); - list_del(&pkt->list); - virtio_transport_free_pkt(pkt); - } - spin_unlock_bh(&vsock->loopback_list_lock); - /* Delete virtqueues and flush outstanding callbacks if any */ vdev->config->del_vqs(vdev); /* Other works can be queued before 'config->del_vqs()', so we flush * all works before to free the vsock object to avoid use after free. */ - flush_work(&vsock->loopback_work); flush_work(&vsock->rx_work); flush_work(&vsock->tx_work); flush_work(&vsock->event_work); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index e5ea29c6bca7..d9f0c9c5425a 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -11,9 +11,6 @@ #include <linux/sched/signal.h> #include <linux/ctype.h> #include <linux/list.h> -#include <linux/virtio.h> -#include <linux/virtio_ids.h> -#include <linux/virtio_config.h> #include <linux/virtio_vsock.h> #include <uapi/linux/vsockmon.h> @@ -34,6 +31,9 @@ virtio_transport_get_ops(struct vsock_sock *vsk) { const struct vsock_transport *t = vsock_core_get_transport(vsk); + if (WARN_ON(!t)) + return NULL; + return container_of(t, struct virtio_transport, transport); } @@ -161,15 +161,25 @@ void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt) } EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt); +/* This function can only be used on connecting/connected sockets, + * since a socket assigned to a transport is required. + * + * Do not use on listener sockets! + */ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, struct virtio_vsock_pkt_info *info) { u32 src_cid, src_port, dst_cid, dst_port; + const struct virtio_transport *t_ops; struct virtio_vsock_sock *vvs; struct virtio_vsock_pkt *pkt; u32 pkt_len = info->pkt_len; - src_cid = virtio_transport_get_ops(vsk)->transport.get_local_cid(); + t_ops = virtio_transport_get_ops(vsk); + if (unlikely(!t_ops)) + return -EFAULT; + + src_cid = t_ops->transport.get_local_cid(); src_port = vsk->local_addr.svm_port; if (!info->remote_cid) { dst_cid = vsk->remote_addr.svm_cid; @@ -202,7 +212,7 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, virtio_transport_inc_tx_pkt(vvs, pkt); - return virtio_transport_get_ops(vsk)->send_pkt(pkt); + return t_ops->send_pkt(pkt); } static bool virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs, @@ -1021,18 +1031,18 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt, int ret; if (le16_to_cpu(pkt->hdr.op) != VIRTIO_VSOCK_OP_REQUEST) { - virtio_transport_reset(vsk, pkt); + virtio_transport_reset_no_sock(t, pkt); return -EINVAL; } if (sk_acceptq_is_full(sk)) { - virtio_transport_reset(vsk, pkt); + virtio_transport_reset_no_sock(t, pkt); return -ENOMEM; } child = vsock_create_connected(sk); if (!child) { - virtio_transport_reset(vsk, pkt); + virtio_transport_reset_no_sock(t, pkt); return -ENOMEM; } @@ -1054,7 +1064,7 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt, */ if (ret || vchild->transport != &t->transport) { release_sock(child); - virtio_transport_reset(vsk, pkt); + virtio_transport_reset_no_sock(t, pkt); sock_put(child); return ret; } diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 644d32e43d23..4b8b1150a738 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -648,7 +648,7 @@ static int vmci_transport_recv_dgram_cb(void *data, struct vmci_datagram *dg) static bool vmci_transport_stream_allow(u32 cid, u32 port) { static const u32 non_socket_contexts[] = { - VMADDR_CID_RESERVED, + VMADDR_CID_LOCAL, }; int i; diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c new file mode 100644 index 000000000000..a45f7ffca8c5 --- /dev/null +++ b/net/vmw_vsock/vsock_loopback.c @@ -0,0 +1,180 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* loopback transport for vsock using virtio_transport_common APIs + * + * Copyright (C) 2013-2019 Red Hat, Inc. + * Authors: Asias He <asias@redhat.com> + * Stefan Hajnoczi <stefanha@redhat.com> + * Stefano Garzarella <sgarzare@redhat.com> + * + */ +#include <linux/spinlock.h> +#include <linux/module.h> +#include <linux/list.h> +#include <linux/virtio_vsock.h> + +struct vsock_loopback { + struct workqueue_struct *workqueue; + + spinlock_t pkt_list_lock; /* protects pkt_list */ + struct list_head pkt_list; + struct work_struct pkt_work; +}; + +static struct vsock_loopback the_vsock_loopback; + +static u32 vsock_loopback_get_local_cid(void) +{ + return VMADDR_CID_LOCAL; +} + +static int vsock_loopback_send_pkt(struct virtio_vsock_pkt *pkt) +{ + struct vsock_loopback *vsock = &the_vsock_loopback; + int len = pkt->len; + + spin_lock_bh(&vsock->pkt_list_lock); + list_add_tail(&pkt->list, &vsock->pkt_list); + spin_unlock_bh(&vsock->pkt_list_lock); + + queue_work(vsock->workqueue, &vsock->pkt_work); + + return len; +} + +static int vsock_loopback_cancel_pkt(struct vsock_sock *vsk) +{ + struct vsock_loopback *vsock = &the_vsock_loopback; + struct virtio_vsock_pkt *pkt, *n; + LIST_HEAD(freeme); + + spin_lock_bh(&vsock->pkt_list_lock); + list_for_each_entry_safe(pkt, n, &vsock->pkt_list, list) { + if (pkt->vsk != vsk) + continue; + list_move(&pkt->list, &freeme); + } + spin_unlock_bh(&vsock->pkt_list_lock); + + list_for_each_entry_safe(pkt, n, &freeme, list) { + list_del(&pkt->list); + virtio_transport_free_pkt(pkt); + } + + return 0; +} + +static struct virtio_transport loopback_transport = { + .transport = { + .module = THIS_MODULE, + + .get_local_cid = vsock_loopback_get_local_cid, + + .init = virtio_transport_do_socket_init, + .destruct = virtio_transport_destruct, + .release = virtio_transport_release, + .connect = virtio_transport_connect, + .shutdown = virtio_transport_shutdown, + .cancel_pkt = vsock_loopback_cancel_pkt, + + .dgram_bind = virtio_transport_dgram_bind, + .dgram_dequeue = virtio_transport_dgram_dequeue, + .dgram_enqueue = virtio_transport_dgram_enqueue, + .dgram_allow = virtio_transport_dgram_allow, + + .stream_dequeue = virtio_transport_stream_dequeue, + .stream_enqueue = virtio_transport_stream_enqueue, + .stream_has_data = virtio_transport_stream_has_data, + .stream_has_space = virtio_transport_stream_has_space, + .stream_rcvhiwat = virtio_transport_stream_rcvhiwat, + .stream_is_active = virtio_transport_stream_is_active, + .stream_allow = virtio_transport_stream_allow, + + .notify_poll_in = virtio_transport_notify_poll_in, + .notify_poll_out = virtio_transport_notify_poll_out, + .notify_recv_init = virtio_transport_notify_recv_init, + .notify_recv_pre_block = virtio_transport_notify_recv_pre_block, + .notify_recv_pre_dequeue = virtio_transport_notify_recv_pre_dequeue, + .notify_recv_post_dequeue = virtio_transport_notify_recv_post_dequeue, + .notify_send_init = virtio_transport_notify_send_init, + .notify_send_pre_block = virtio_transport_notify_send_pre_block, + .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue, + .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue, + .notify_buffer_size = virtio_transport_notify_buffer_size, + }, + + .send_pkt = vsock_loopback_send_pkt, +}; + +static void vsock_loopback_work(struct work_struct *work) +{ + struct vsock_loopback *vsock = + container_of(work, struct vsock_loopback, pkt_work); + LIST_HEAD(pkts); + + spin_lock_bh(&vsock->pkt_list_lock); + list_splice_init(&vsock->pkt_list, &pkts); + spin_unlock_bh(&vsock->pkt_list_lock); + + while (!list_empty(&pkts)) { + struct virtio_vsock_pkt *pkt; + + pkt = list_first_entry(&pkts, struct virtio_vsock_pkt, list); + list_del_init(&pkt->list); + + virtio_transport_deliver_tap_pkt(pkt); + virtio_transport_recv_pkt(&loopback_transport, pkt); + } +} + +static int __init vsock_loopback_init(void) +{ + struct vsock_loopback *vsock = &the_vsock_loopback; + int ret; + + vsock->workqueue = alloc_workqueue("vsock-loopback", 0, 0); + if (!vsock->workqueue) + return -ENOMEM; + + spin_lock_init(&vsock->pkt_list_lock); + INIT_LIST_HEAD(&vsock->pkt_list); + INIT_WORK(&vsock->pkt_work, vsock_loopback_work); + + ret = vsock_core_register(&loopback_transport.transport, + VSOCK_TRANSPORT_F_LOCAL); + if (ret) + goto out_wq; + + return 0; + +out_wq: + destroy_workqueue(vsock->workqueue); + return ret; +} + +static void __exit vsock_loopback_exit(void) +{ + struct vsock_loopback *vsock = &the_vsock_loopback; + struct virtio_vsock_pkt *pkt; + + vsock_core_unregister(&loopback_transport.transport); + + flush_work(&vsock->pkt_work); + + spin_lock_bh(&vsock->pkt_list_lock); + while (!list_empty(&vsock->pkt_list)) { + pkt = list_first_entry(&vsock->pkt_list, + struct virtio_vsock_pkt, list); + list_del(&pkt->list); + virtio_transport_free_pkt(pkt); + } + spin_unlock_bh(&vsock->pkt_list_lock); + + destroy_workqueue(vsock->workqueue); +} + +module_init(vsock_loopback_init); +module_exit(vsock_loopback_exit); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Stefano Garzarella <sgarzare@redhat.com>"); +MODULE_DESCRIPTION("loopback transport for vsock"); +MODULE_ALIAS_NETPROTO(PF_VSOCK); diff --git a/net/wireless/core.c b/net/wireless/core.c index 350513744575..3e25229a059d 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1102,6 +1102,7 @@ static void __cfg80211_unregister_wdev(struct wireless_dev *wdev, bool sync) #ifdef CONFIG_CFG80211_WEXT kzfree(wdev->wext.keys); + wdev->wext.keys = NULL; #endif /* only initialized if we have a netdev */ if (wdev->netdev) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index da5262b2298b..fa3526592c51 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -12900,8 +12900,7 @@ static int nl80211_vendor_check_policy(const struct wiphy_vendor_command *vcmd, return -EINVAL; } - return nl80211_validate_nested(attr, vcmd->maxattr, vcmd->policy, - extack); + return nla_validate_nested(attr, vcmd->maxattr, vcmd->policy, extack); } static int nl80211_vendor_cmd(struct sk_buff *skb, struct genl_info *info) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index c34f7d077604..2efe44a34644 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -659,6 +659,12 @@ static int x25_release(struct socket *sock) sock_set_flag(sk, SOCK_DEAD); sock_set_flag(sk, SOCK_DESTROY); break; + + case X25_STATE_5: + x25_write_internal(sk, X25_CLEAR_REQUEST); + x25_disconnect(sk, 0, 0, 0); + __x25_destroy_socket(sk); + goto out; } sock_orphan(sk); @@ -1054,6 +1060,8 @@ int x25_rx_call_request(struct sk_buff *skb, struct x25_neigh *nb, if (test_bit(X25_ACCPT_APPRV_FLAG, &makex25->flags)) { x25_write_internal(make, X25_CALL_ACCEPTED); makex25->state = X25_STATE_3; + } else { + makex25->state = X25_STATE_5; } /* diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c index f97c43344e95..4d3bb46aaae0 100644 --- a/net/x25/x25_in.c +++ b/net/x25/x25_in.c @@ -382,6 +382,35 @@ out_clear: return 0; } +/* + * State machine for state 5, Call Accepted / Call Connected pending (X25_ACCPT_APPRV_FLAG). + * The handling of the timer(s) is in file x25_timer.c + * Handling of state 0 and connection release is in af_x25.c. + */ +static int x25_state5_machine(struct sock *sk, struct sk_buff *skb, int frametype) +{ + struct x25_sock *x25 = x25_sk(sk); + + switch (frametype) { + case X25_CLEAR_REQUEST: + if (!pskb_may_pull(skb, X25_STD_MIN_LEN + 2)) { + x25_write_internal(sk, X25_CLEAR_REQUEST); + x25->state = X25_STATE_2; + x25_start_t23timer(sk); + return 0; + } + + x25_write_internal(sk, X25_CLEAR_CONFIRMATION); + x25_disconnect(sk, 0, skb->data[3], skb->data[4]); + break; + + default: + break; + } + + return 0; +} + /* Higher level upcall for a LAPB frame */ int x25_process_rx_frame(struct sock *sk, struct sk_buff *skb) { @@ -406,6 +435,9 @@ int x25_process_rx_frame(struct sock *sk, struct sk_buff *skb) case X25_STATE_4: queued = x25_state4_machine(sk, skb, frametype); break; + case X25_STATE_5: + queued = x25_state5_machine(sk, skb, frametype); + break; } x25_kick(sk); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 5560d60c1ff5..02ada7ab8c6e 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -338,12 +338,21 @@ out: } EXPORT_SYMBOL(xsk_umem_consume_tx); -static int xsk_zc_xmit(struct xdp_sock *xs) +static int xsk_wakeup(struct xdp_sock *xs, u8 flags) { struct net_device *dev = xs->dev; + int err; + + rcu_read_lock(); + err = dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, flags); + rcu_read_unlock(); + + return err; +} - return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, - XDP_WAKEUP_TX); +static int xsk_zc_xmit(struct xdp_sock *xs) +{ + return xsk_wakeup(xs, XDP_WAKEUP_TX); } static void xsk_destruct_skb(struct sk_buff *skb) @@ -462,19 +471,16 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, __poll_t mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); - struct net_device *dev; struct xdp_umem *umem; if (unlikely(!xsk_is_bound(xs))) return mask; - dev = xs->dev; umem = xs->umem; if (umem->need_wakeup) { - if (dev->netdev_ops->ndo_xsk_wakeup) - dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, - umem->need_wakeup); + if (xs->zc) + xsk_wakeup(xs, umem->need_wakeup); else /* Poll needs to drive Tx also in copy mode */ __xsk_sendmsg(sk); |
