diff options
Diffstat (limited to 'net')
95 files changed, 5148 insertions, 2147 deletions
diff --git a/net/6lowpan/nhc_udp.c b/net/6lowpan/nhc_udp.c index 8a3507524f7b..33f17bd8cda7 100644 --- a/net/6lowpan/nhc_udp.c +++ b/net/6lowpan/nhc_udp.c @@ -5,7 +5,7 @@ * Authors: * Alexander Aring <aar@pengutronix.de> * - * Orignal written by: + * Original written by: * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> * Jon Smirl <jonsmirl@gmail.com> */ @@ -82,7 +82,7 @@ static int udp_uncompress(struct sk_buff *skb, size_t needed) if (fail) return -EINVAL; - /* UDP length needs to be infered from the lower layers + /* UDP length needs to be inferred from the lower layers * here, we obtain the hint from the remaining size of the * frame */ diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 78ec2e1b14d1..59bc13b5f14f 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -4,6 +4,7 @@ #include <linux/if_vlan.h> #include <linux/netpoll.h> #include <linux/export.h> +#include <net/gro.h> #include "vlan.h" bool vlan_do_receive(struct sk_buff **skbp) @@ -495,7 +496,10 @@ static struct sk_buff *vlan_gro_receive(struct list_head *head, skb_gro_pull(skb, sizeof(*vhdr)); skb_gro_postpull_rcsum(skb, vhdr, sizeof(*vhdr)); - pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); + + pp = indirect_call_gro_receive_inet(ptype->callbacks.gro_receive, + ipv6_gro_receive, inet_gro_receive, + head, skb); out_unlock: rcu_read_unlock(); @@ -515,7 +519,9 @@ static int vlan_gro_complete(struct sk_buff *skb, int nhoff) rcu_read_lock(); ptype = gro_find_complete_by_type(type); if (ptype) - err = ptype->callbacks.gro_complete(skb, nhoff + sizeof(*vhdr)); + err = INDIRECT_CALL_INET(ptype->callbacks.gro_complete, + ipv6_gro_complete, inet_gro_complete, + skb, nhoff + sizeof(*vhdr)); rcu_read_unlock(); return err; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index dc1a197792e6..4db3f0621959 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -776,6 +776,26 @@ static int vlan_dev_get_iflink(const struct net_device *dev) return real_dev->ifindex; } +static int vlan_dev_fill_forward_path(struct net_device_path_ctx *ctx, + struct net_device_path *path) +{ + struct vlan_dev_priv *vlan = vlan_dev_priv(ctx->dev); + + path->type = DEV_PATH_VLAN; + path->encap.id = vlan->vlan_id; + path->encap.proto = vlan->vlan_proto; + path->dev = ctx->dev; + ctx->dev = vlan->real_dev; + if (ctx->num_vlans >= ARRAY_SIZE(ctx->vlan)) + return -ENOSPC; + + ctx->vlan[ctx->num_vlans].id = vlan->vlan_id; + ctx->vlan[ctx->num_vlans].proto = vlan->vlan_proto; + ctx->num_vlans++; + + return 0; +} + static const struct ethtool_ops vlan_ethtool_ops = { .get_link_ksettings = vlan_ethtool_get_link_ksettings, .get_drvinfo = vlan_ethtool_get_drvinfo, @@ -814,6 +834,7 @@ static const struct net_device_ops vlan_netdev_ops = { #endif .ndo_fix_features = vlan_dev_fix_features, .ndo_get_iflink = vlan_dev_get_iflink, + .ndo_fill_forward_path = vlan_dev_fill_forward_path, }; static void vlan_dev_free(struct net_device *dev) diff --git a/net/Kconfig b/net/Kconfig index 8cea808ad9e8..9c456acc379e 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -245,6 +245,14 @@ source "net/l3mdev/Kconfig" source "net/qrtr/Kconfig" source "net/ncsi/Kconfig" +config PCPU_DEV_REFCNT + bool "Use percpu variables to maintain network device refcount" + depends on SMP + default y + help + network device refcount are using per cpu variables if this option is set. + This can be forced to N to detect underflows (with a performance drop). + config RPS bool depends on SMP && SYSFS @@ -317,13 +325,9 @@ config BPF_STREAM_PARSER select STREAM_PARSER select NET_SOCK_MSG help - Enabling this allows a stream parser to be used with + Enabling this allows a TCP stream parser to be used with BPF_MAP_TYPE_SOCKMAP. - BPF_MAP_TYPE_SOCKMAP provides a map type to use with network sockets. - It can be used to enforce socket policy, implement socket redirects, - etc. - config NET_FLOW_LIMIT bool depends on RPS diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 269ee89d2c2b..2631efc6e359 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -850,6 +850,7 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol, case AX25_P_ROSE: if (ax25_protocol_is_registered(AX25_P_ROSE)) return -ESOCKTNOSUPPORT; + break; #endif default: break; diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 360bdbf44748..bcd543ce835b 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -438,10 +438,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac, batadv_add_counter(bat_priv, BATADV_CNT_RX_BYTES, skb->len + ETH_HLEN); - if (in_interrupt()) - netif_rx(skb); - else - netif_rx_ni(skb); + netif_rx_any_context(skb); out: if (primary_if) batadv_hardif_put(primary_if); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 58bcb8c849d5..0abdd67f44b1 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -10,20 +10,86 @@ #include <net/bpf_sk_storage.h> #include <net/sock.h> #include <net/tcp.h> +#include <net/net_namespace.h> #include <linux/error-injection.h> #include <linux/smp.h> +#include <linux/sock_diag.h> #define CREATE_TRACE_POINTS #include <trace/events/bpf_test_run.h> +struct bpf_test_timer { + enum { NO_PREEMPT, NO_MIGRATE } mode; + u32 i; + u64 time_start, time_spent; +}; + +static void bpf_test_timer_enter(struct bpf_test_timer *t) + __acquires(rcu) +{ + rcu_read_lock(); + if (t->mode == NO_PREEMPT) + preempt_disable(); + else + migrate_disable(); + + t->time_start = ktime_get_ns(); +} + +static void bpf_test_timer_leave(struct bpf_test_timer *t) + __releases(rcu) +{ + t->time_start = 0; + + if (t->mode == NO_PREEMPT) + preempt_enable(); + else + migrate_enable(); + rcu_read_unlock(); +} + +static bool bpf_test_timer_continue(struct bpf_test_timer *t, u32 repeat, int *err, u32 *duration) + __must_hold(rcu) +{ + t->i++; + if (t->i >= repeat) { + /* We're done. */ + t->time_spent += ktime_get_ns() - t->time_start; + do_div(t->time_spent, t->i); + *duration = t->time_spent > U32_MAX ? U32_MAX : (u32)t->time_spent; + *err = 0; + goto reset; + } + + if (signal_pending(current)) { + /* During iteration: we've been cancelled, abort. */ + *err = -EINTR; + goto reset; + } + + if (need_resched()) { + /* During iteration: we need to reschedule between runs. */ + t->time_spent += ktime_get_ns() - t->time_start; + bpf_test_timer_leave(t); + cond_resched(); + bpf_test_timer_enter(t); + } + + /* Do another round. */ + return true; + +reset: + t->i = 0; + return false; +} + static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *retval, u32 *time, bool xdp) { struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = { NULL }; + struct bpf_test_timer t = { NO_MIGRATE }; enum bpf_cgroup_storage_type stype; - u64 time_start, time_spent = 0; - int ret = 0; - u32 i; + int ret; for_each_cgroup_storage_type(stype) { storage[stype] = bpf_cgroup_storage_alloc(prog, stype); @@ -38,40 +104,16 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, if (!repeat) repeat = 1; - rcu_read_lock(); - migrate_disable(); - time_start = ktime_get_ns(); - for (i = 0; i < repeat; i++) { + bpf_test_timer_enter(&t); + do { bpf_cgroup_storage_set(storage); if (xdp) *retval = bpf_prog_run_xdp(prog, ctx); else *retval = BPF_PROG_RUN(prog, ctx); - - if (signal_pending(current)) { - ret = -EINTR; - break; - } - - if (need_resched()) { - time_spent += ktime_get_ns() - time_start; - migrate_enable(); - rcu_read_unlock(); - - cond_resched(); - - rcu_read_lock(); - migrate_disable(); - time_start = ktime_get_ns(); - } - } - time_spent += ktime_get_ns() - time_start; - migrate_enable(); - rcu_read_unlock(); - - do_div(time_spent, repeat); - *time = time_spent > U32_MAX ? U32_MAX : (u32)time_spent; + } while (bpf_test_timer_continue(&t, repeat, &ret, time)); + bpf_test_timer_leave(&t); for_each_cgroup_storage_type(stype) bpf_cgroup_storage_free(storage[stype]); @@ -674,18 +716,17 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { + struct bpf_test_timer t = { NO_PREEMPT }; u32 size = kattr->test.data_size_in; struct bpf_flow_dissector ctx = {}; u32 repeat = kattr->test.repeat; struct bpf_flow_keys *user_ctx; struct bpf_flow_keys flow_keys; - u64 time_start, time_spent = 0; const struct ethhdr *eth; unsigned int flags = 0; u32 retval, duration; void *data; int ret; - u32 i; if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR) return -EINVAL; @@ -721,48 +762,127 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, ctx.data = data; ctx.data_end = (__u8 *)data + size; - rcu_read_lock(); - preempt_disable(); - time_start = ktime_get_ns(); - for (i = 0; i < repeat; i++) { + bpf_test_timer_enter(&t); + do { retval = bpf_flow_dissect(prog, &ctx, eth->h_proto, ETH_HLEN, size, flags); + } while (bpf_test_timer_continue(&t, repeat, &ret, &duration)); + bpf_test_timer_leave(&t); - if (signal_pending(current)) { - preempt_enable(); - rcu_read_unlock(); + if (ret < 0) + goto out; - ret = -EINTR; - goto out; - } + ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys), + retval, duration); + if (!ret) + ret = bpf_ctx_finish(kattr, uattr, user_ctx, + sizeof(struct bpf_flow_keys)); - if (need_resched()) { - time_spent += ktime_get_ns() - time_start; - preempt_enable(); - rcu_read_unlock(); +out: + kfree(user_ctx); + kfree(data); + return ret; +} - cond_resched(); +int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + struct bpf_test_timer t = { NO_PREEMPT }; + struct bpf_prog_array *progs = NULL; + struct bpf_sk_lookup_kern ctx = {}; + u32 repeat = kattr->test.repeat; + struct bpf_sk_lookup *user_ctx; + u32 retval, duration; + int ret = -EINVAL; - rcu_read_lock(); - preempt_disable(); - time_start = ktime_get_ns(); - } + if (prog->type != BPF_PROG_TYPE_SK_LOOKUP) + return -EINVAL; + + if (kattr->test.flags || kattr->test.cpu) + return -EINVAL; + + if (kattr->test.data_in || kattr->test.data_size_in || kattr->test.data_out || + kattr->test.data_size_out) + return -EINVAL; + + if (!repeat) + repeat = 1; + + user_ctx = bpf_ctx_init(kattr, sizeof(*user_ctx)); + if (IS_ERR(user_ctx)) + return PTR_ERR(user_ctx); + + if (!user_ctx) + return -EINVAL; + + if (user_ctx->sk) + goto out; + + if (!range_is_zero(user_ctx, offsetofend(typeof(*user_ctx), local_port), sizeof(*user_ctx))) + goto out; + + if (user_ctx->local_port > U16_MAX || user_ctx->remote_port > U16_MAX) { + ret = -ERANGE; + goto out; } - time_spent += ktime_get_ns() - time_start; - preempt_enable(); - rcu_read_unlock(); - do_div(time_spent, repeat); - duration = time_spent > U32_MAX ? U32_MAX : (u32)time_spent; + ctx.family = (u16)user_ctx->family; + ctx.protocol = (u16)user_ctx->protocol; + ctx.dport = (u16)user_ctx->local_port; + ctx.sport = (__force __be16)user_ctx->remote_port; - ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys), - retval, duration); + switch (ctx.family) { + case AF_INET: + ctx.v4.daddr = (__force __be32)user_ctx->local_ip4; + ctx.v4.saddr = (__force __be32)user_ctx->remote_ip4; + break; + +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + ctx.v6.daddr = (struct in6_addr *)user_ctx->local_ip6; + ctx.v6.saddr = (struct in6_addr *)user_ctx->remote_ip6; + break; +#endif + + default: + ret = -EAFNOSUPPORT; + goto out; + } + + progs = bpf_prog_array_alloc(1, GFP_KERNEL); + if (!progs) { + ret = -ENOMEM; + goto out; + } + + progs->items[0].prog = prog; + + bpf_test_timer_enter(&t); + do { + ctx.selected_sk = NULL; + retval = BPF_PROG_SK_LOOKUP_RUN_ARRAY(progs, ctx, BPF_PROG_RUN); + } while (bpf_test_timer_continue(&t, repeat, &ret, &duration)); + bpf_test_timer_leave(&t); + + if (ret < 0) + goto out; + + user_ctx->cookie = 0; + if (ctx.selected_sk) { + if (ctx.selected_sk->sk_reuseport && !ctx.no_reuseport) { + ret = -EOPNOTSUPP; + goto out; + } + + user_ctx->cookie = sock_gen_cookie(ctx.selected_sk); + } + + ret = bpf_test_finish(kattr, uattr, NULL, 0, retval, duration); if (!ret) - ret = bpf_ctx_finish(kattr, uattr, user_ctx, - sizeof(struct bpf_flow_keys)); + ret = bpf_ctx_finish(kattr, uattr, user_ctx, sizeof(*user_ctx)); out: + bpf_prog_array_free(progs); kfree(user_ctx); - kfree(data); return ret; } diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c index dfec65eca8a6..3db1def4437b 100644 --- a/net/bridge/br_arp_nd_proxy.c +++ b/net/bridge/br_arp_nd_proxy.c @@ -160,7 +160,9 @@ void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br, if (br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED)) { if (p && (p->flags & BR_NEIGH_SUPPRESS)) return; - if (ipv4_is_zeronet(sip) || sip == tip) { + if (parp->ar_op != htons(ARPOP_RREQUEST) && + parp->ar_op != htons(ARPOP_RREPLY) && + (ipv4_is_zeronet(sip) || sip == tip)) { /* prevent flooding to neigh suppress ports */ BR_INPUT_SKB_CB(skb)->proxyarp_replied = 1; return; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 3f2f06b4dd27..e8b626cc6bfd 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -385,6 +385,54 @@ static int br_del_slave(struct net_device *dev, struct net_device *slave_dev) return br_del_if(br, slave_dev); } +static int br_fill_forward_path(struct net_device_path_ctx *ctx, + struct net_device_path *path) +{ + struct net_bridge_fdb_entry *f; + struct net_bridge_port *dst; + struct net_bridge *br; + + if (netif_is_bridge_port(ctx->dev)) + return -1; + + br = netdev_priv(ctx->dev); + + br_vlan_fill_forward_path_pvid(br, ctx, path); + + f = br_fdb_find_rcu(br, ctx->daddr, path->bridge.vlan_id); + if (!f || !f->dst) + return -1; + + dst = READ_ONCE(f->dst); + if (!dst) + return -1; + + if (br_vlan_fill_forward_path_mode(br, dst, path)) + return -1; + + path->type = DEV_PATH_BRIDGE; + path->dev = dst->br->dev; + ctx->dev = dst->dev; + + switch (path->bridge.vlan_mode) { + case DEV_PATH_BR_VLAN_TAG: + if (ctx->num_vlans >= ARRAY_SIZE(ctx->vlan)) + return -ENOSPC; + ctx->vlan[ctx->num_vlans].id = path->bridge.vlan_id; + ctx->vlan[ctx->num_vlans].proto = path->bridge.vlan_proto; + ctx->num_vlans++; + break; + case DEV_PATH_BR_VLAN_UNTAG_HW: + case DEV_PATH_BR_VLAN_UNTAG: + ctx->num_vlans--; + break; + case DEV_PATH_BR_VLAN_KEEP: + break; + } + + return 0; +} + static const struct ethtool_ops br_ethtool_ops = { .get_drvinfo = br_getinfo, .get_link = ethtool_op_get_link, @@ -419,6 +467,7 @@ static const struct net_device_ops br_netdev_ops = { .ndo_bridge_setlink = br_setlink, .ndo_bridge_dellink = br_dellink, .ndo_features_check = passthru_features_check, + .ndo_fill_forward_path = br_fill_forward_path, }; static struct device_type br_type = { diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index b7490237f3fc..698b79747d32 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -726,6 +726,56 @@ static inline size_t fdb_nlmsg_size(void) + nla_total_size(sizeof(u8)); /* NFEA_ACTIVITY_NOTIFY */ } +static int br_fdb_replay_one(struct notifier_block *nb, + struct net_bridge_fdb_entry *fdb, + struct net_device *dev) +{ + struct switchdev_notifier_fdb_info item; + int err; + + item.addr = fdb->key.addr.addr; + item.vid = fdb->key.vlan_id; + item.added_by_user = test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags); + item.offloaded = test_bit(BR_FDB_OFFLOADED, &fdb->flags); + item.info.dev = dev; + + err = nb->notifier_call(nb, SWITCHDEV_FDB_ADD_TO_DEVICE, &item); + return notifier_to_errno(err); +} + +int br_fdb_replay(struct net_device *br_dev, struct net_device *dev, + struct notifier_block *nb) +{ + struct net_bridge_fdb_entry *fdb; + struct net_bridge *br; + int err = 0; + + if (!netif_is_bridge_master(br_dev) || !netif_is_bridge_port(dev)) + return -EINVAL; + + br = netdev_priv(br_dev); + + rcu_read_lock(); + + hlist_for_each_entry_rcu(fdb, &br->fdb_list, fdb_node) { + struct net_bridge_port *dst = READ_ONCE(fdb->dst); + struct net_device *dst_dev; + + dst_dev = dst ? dst->dev : br->dev; + if (dst_dev != br_dev && dst_dev != dev) + continue; + + err = br_fdb_replay_one(nb, fdb, dst_dev); + if (err) + break; + } + + rcu_read_unlock(); + + return err; +} +EXPORT_SYMBOL_GPL(br_fdb_replay); + static void fdb_notify(struct net_bridge *br, const struct net_bridge_fdb_entry *fdb, int type, bool swdev_notify) diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 222285d9dae2..8875e953ac53 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -144,6 +144,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb break; case BR_PKT_UNICAST: dst = br_fdb_find_rcu(br, eth_hdr(skb)->h_dest, vid); + break; default: break; } diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 8846c5bcd075..95fa4af0e8dd 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -506,6 +506,134 @@ err: kfree(priv); } +static void br_switchdev_mdb_populate(struct switchdev_obj_port_mdb *mdb, + const struct net_bridge_mdb_entry *mp) +{ + if (mp->addr.proto == htons(ETH_P_IP)) + ip_eth_mc_map(mp->addr.dst.ip4, mdb->addr); +#if IS_ENABLED(CONFIG_IPV6) + else if (mp->addr.proto == htons(ETH_P_IPV6)) + ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb->addr); +#endif + else + ether_addr_copy(mdb->addr, mp->addr.dst.mac_addr); + + mdb->vid = mp->addr.vid; +} + +static int br_mdb_replay_one(struct notifier_block *nb, struct net_device *dev, + struct switchdev_obj_port_mdb *mdb, + struct netlink_ext_ack *extack) +{ + struct switchdev_notifier_port_obj_info obj_info = { + .info = { + .dev = dev, + .extack = extack, + }, + .obj = &mdb->obj, + }; + int err; + + err = nb->notifier_call(nb, SWITCHDEV_PORT_OBJ_ADD, &obj_info); + return notifier_to_errno(err); +} + +static int br_mdb_queue_one(struct list_head *mdb_list, + enum switchdev_obj_id id, + const struct net_bridge_mdb_entry *mp, + struct net_device *orig_dev) +{ + struct switchdev_obj_port_mdb *mdb; + + mdb = kzalloc(sizeof(*mdb), GFP_ATOMIC); + if (!mdb) + return -ENOMEM; + + mdb->obj.id = id; + mdb->obj.orig_dev = orig_dev; + br_switchdev_mdb_populate(mdb, mp); + list_add_tail(&mdb->obj.list, mdb_list); + + return 0; +} + +int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, + struct notifier_block *nb, struct netlink_ext_ack *extack) +{ + struct net_bridge_mdb_entry *mp; + struct switchdev_obj *obj, *tmp; + struct net_bridge *br; + LIST_HEAD(mdb_list); + int err = 0; + + ASSERT_RTNL(); + + if (!netif_is_bridge_master(br_dev) || !netif_is_bridge_port(dev)) + return -EINVAL; + + br = netdev_priv(br_dev); + + if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) + return 0; + + /* We cannot walk over br->mdb_list protected just by the rtnl_mutex, + * because the write-side protection is br->multicast_lock. But we + * need to emulate the [ blocking ] calling context of a regular + * switchdev event, so since both br->multicast_lock and RCU read side + * critical sections are atomic, we have no choice but to pick the RCU + * read side lock, queue up all our events, leave the critical section + * and notify switchdev from blocking context. + */ + rcu_read_lock(); + + hlist_for_each_entry_rcu(mp, &br->mdb_list, mdb_node) { + struct net_bridge_port_group __rcu **pp; + struct net_bridge_port_group *p; + + if (mp->host_joined) { + err = br_mdb_queue_one(&mdb_list, + SWITCHDEV_OBJ_ID_HOST_MDB, + mp, br_dev); + if (err) { + rcu_read_unlock(); + goto out_free_mdb; + } + } + + for (pp = &mp->ports; (p = rcu_dereference(*pp)) != NULL; + pp = &p->next) { + if (p->key.port->dev != dev) + continue; + + err = br_mdb_queue_one(&mdb_list, + SWITCHDEV_OBJ_ID_PORT_MDB, + mp, dev); + if (err) { + rcu_read_unlock(); + goto out_free_mdb; + } + } + } + + rcu_read_unlock(); + + list_for_each_entry(obj, &mdb_list, list) { + err = br_mdb_replay_one(nb, dev, SWITCHDEV_OBJ_PORT_MDB(obj), + extack); + if (err) + goto out_free_mdb; + } + +out_free_mdb: + list_for_each_entry_safe(obj, tmp, &mdb_list, list) { + list_del(&obj->list); + kfree(SWITCHDEV_OBJ_PORT_MDB(obj)); + } + + return err; +} +EXPORT_SYMBOL_GPL(br_mdb_replay); + static void br_mdb_switchdev_host_port(struct net_device *dev, struct net_device *lower_dev, struct net_bridge_mdb_entry *mp, @@ -515,18 +643,12 @@ static void br_mdb_switchdev_host_port(struct net_device *dev, .obj = { .id = SWITCHDEV_OBJ_ID_HOST_MDB, .flags = SWITCHDEV_F_DEFER, + .orig_dev = dev, }, - .vid = mp->addr.vid, }; - if (mp->addr.proto == htons(ETH_P_IP)) - ip_eth_mc_map(mp->addr.dst.ip4, mdb.addr); -#if IS_ENABLED(CONFIG_IPV6) - else - ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb.addr); -#endif + br_switchdev_mdb_populate(&mdb, mp); - mdb.obj.orig_dev = dev; switch (type) { case RTM_NEWMDB: switchdev_port_obj_add(lower_dev, &mdb.obj, NULL); @@ -558,21 +680,13 @@ void br_mdb_notify(struct net_device *dev, .id = SWITCHDEV_OBJ_ID_PORT_MDB, .flags = SWITCHDEV_F_DEFER, }, - .vid = mp->addr.vid, }; struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOBUFS; if (pg) { - if (mp->addr.proto == htons(ETH_P_IP)) - ip_eth_mc_map(mp->addr.dst.ip4, mdb.addr); -#if IS_ENABLED(CONFIG_IPV6) - else if (mp->addr.proto == htons(ETH_P_IPV6)) - ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb.addr); -#endif - else - ether_addr_copy(mdb.addr, mp->addr.dst.mac_addr); + br_switchdev_mdb_populate(&mdb, mp); mdb.obj.orig_dev = pg->key.port->dev; switch (type) { diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c index 12487f6fe9b4..cd2b1e424e54 100644 --- a/net/bridge/br_mrp.c +++ b/net/bridge/br_mrp.c @@ -411,6 +411,13 @@ static void br_mrp_del_impl(struct net_bridge *br, struct br_mrp *mrp) cancel_delayed_work_sync(&mrp->in_test_work); br_mrp_switchdev_send_in_test(br, mrp, 0, 0, 0); + /* Disable the roles */ + br_mrp_switchdev_set_ring_role(br, mrp, BR_MRP_RING_ROLE_DISABLED); + p = rtnl_dereference(mrp->i_port); + if (p) + br_mrp_switchdev_set_in_role(br, mrp, mrp->in_id, mrp->ring_id, + BR_MRP_IN_ROLE_DISABLED); + br_mrp_switchdev_del(br, mrp); /* Reset the ports */ diff --git a/net/bridge/br_multicast_eht.c b/net/bridge/br_multicast_eht.c index fea38b9a7268..13290a749d09 100644 --- a/net/bridge/br_multicast_eht.c +++ b/net/bridge/br_multicast_eht.c @@ -498,11 +498,13 @@ static void br_multicast_del_eht_host(struct net_bridge_port_group *pg, &set_h->h_addr); } -static void __eht_allow_incl(struct net_bridge_port_group *pg, - union net_bridge_eht_addr *h_addr, - void *srcs, - u32 nsrcs, - size_t addr_size) +/* create new set entries from reports */ +static void __eht_create_set_entries(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *h_addr, + void *srcs, + u32 nsrcs, + size_t addr_size, + int filter_mode) { union net_bridge_eht_addr eht_src_addr; u32 src_idx; @@ -511,72 +513,17 @@ static void __eht_allow_incl(struct net_bridge_port_group *pg, for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&eht_src_addr, srcs + (src_idx * addr_size), addr_size); br_multicast_create_eht_set_entry(pg, &eht_src_addr, h_addr, - MCAST_INCLUDE, + filter_mode, false); } } -static bool __eht_allow_excl(struct net_bridge_port_group *pg, - union net_bridge_eht_addr *h_addr, - void *srcs, - u32 nsrcs, - size_t addr_size) -{ - bool changed = false, host_excl = false; - union net_bridge_eht_addr eht_src_addr; - struct net_bridge_group_src *src_ent; - struct br_ip src_ip; - u32 src_idx; - - host_excl = !!(br_multicast_eht_host_filter_mode(pg, h_addr) == MCAST_EXCLUDE); - memset(&eht_src_addr, 0, sizeof(eht_src_addr)); - for (src_idx = 0; src_idx < nsrcs; src_idx++) { - memcpy(&eht_src_addr, srcs + (src_idx * addr_size), addr_size); - if (!host_excl) { - br_multicast_create_eht_set_entry(pg, &eht_src_addr, h_addr, - MCAST_INCLUDE, - false); - } else { - if (!br_multicast_del_eht_set_entry(pg, &eht_src_addr, - h_addr)) - continue; - memcpy(&src_ip, srcs + (src_idx * addr_size), addr_size); - src_ent = br_multicast_find_group_src(pg, &src_ip); - if (!src_ent) - continue; - br_multicast_del_group_src(src_ent, true); - changed = true; - } - } - - return changed; -} - -static bool br_multicast_eht_allow(struct net_bridge_port_group *pg, - union net_bridge_eht_addr *h_addr, - void *srcs, - u32 nsrcs, - size_t addr_size) -{ - bool changed = false; - - switch (br_multicast_eht_host_filter_mode(pg, h_addr)) { - case MCAST_INCLUDE: - __eht_allow_incl(pg, h_addr, srcs, nsrcs, addr_size); - break; - case MCAST_EXCLUDE: - changed = __eht_allow_excl(pg, h_addr, srcs, nsrcs, addr_size); - break; - } - - return changed; -} - -static bool __eht_block_incl(struct net_bridge_port_group *pg, - union net_bridge_eht_addr *h_addr, - void *srcs, - u32 nsrcs, - size_t addr_size) +/* delete existing set entries and their (S,G) entries if they were the last */ +static bool __eht_del_set_entries(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *h_addr, + void *srcs, + u32 nsrcs, + size_t addr_size) { union net_bridge_eht_addr eht_src_addr; struct net_bridge_group_src *src_ent; @@ -602,39 +549,23 @@ static bool __eht_block_incl(struct net_bridge_port_group *pg, return changed; } -static bool __eht_block_excl(struct net_bridge_port_group *pg, - union net_bridge_eht_addr *h_addr, - void *srcs, - u32 nsrcs, - size_t addr_size) +static bool br_multicast_eht_allow(struct net_bridge_port_group *pg, + union net_bridge_eht_addr *h_addr, + void *srcs, + u32 nsrcs, + size_t addr_size) { - bool changed = false, host_excl = false; - union net_bridge_eht_addr eht_src_addr; - struct net_bridge_group_src *src_ent; - struct br_ip src_ip; - u32 src_idx; + bool changed = false; - host_excl = !!(br_multicast_eht_host_filter_mode(pg, h_addr) == MCAST_EXCLUDE); - memset(&eht_src_addr, 0, sizeof(eht_src_addr)); - memset(&src_ip, 0, sizeof(src_ip)); - src_ip.proto = pg->key.addr.proto; - for (src_idx = 0; src_idx < nsrcs; src_idx++) { - memcpy(&eht_src_addr, srcs + (src_idx * addr_size), addr_size); - if (host_excl) { - br_multicast_create_eht_set_entry(pg, &eht_src_addr, h_addr, - MCAST_EXCLUDE, - false); - } else { - if (!br_multicast_del_eht_set_entry(pg, &eht_src_addr, - h_addr)) - continue; - memcpy(&src_ip, srcs + (src_idx * addr_size), addr_size); - src_ent = br_multicast_find_group_src(pg, &src_ip); - if (!src_ent) - continue; - br_multicast_del_group_src(src_ent, true); - changed = true; - } + switch (br_multicast_eht_host_filter_mode(pg, h_addr)) { + case MCAST_INCLUDE: + __eht_create_set_entries(pg, h_addr, srcs, nsrcs, addr_size, + MCAST_INCLUDE); + break; + case MCAST_EXCLUDE: + changed = __eht_del_set_entries(pg, h_addr, srcs, nsrcs, + addr_size); + break; } return changed; @@ -650,10 +581,12 @@ static bool br_multicast_eht_block(struct net_bridge_port_group *pg, switch (br_multicast_eht_host_filter_mode(pg, h_addr)) { case MCAST_INCLUDE: - changed = __eht_block_incl(pg, h_addr, srcs, nsrcs, addr_size); + changed = __eht_del_set_entries(pg, h_addr, srcs, nsrcs, + addr_size); break; case MCAST_EXCLUDE: - changed = __eht_block_excl(pg, h_addr, srcs, nsrcs, addr_size); + __eht_create_set_entries(pg, h_addr, srcs, nsrcs, addr_size, + MCAST_EXCLUDE); break; } @@ -671,7 +604,6 @@ static bool __eht_inc_exc(struct net_bridge_port_group *pg, { bool changed = false, flush_entries = to_report; union net_bridge_eht_addr eht_src_addr; - u32 src_idx; if (br_multicast_eht_host_filter_mode(pg, h_addr) != filter_mode) flush_entries = true; @@ -680,11 +612,8 @@ static bool __eht_inc_exc(struct net_bridge_port_group *pg, /* if we're changing mode del host and its entries */ if (flush_entries) br_multicast_del_eht_host(pg, h_addr); - for (src_idx = 0; src_idx < nsrcs; src_idx++) { - memcpy(&eht_src_addr, srcs + (src_idx * addr_size), addr_size); - br_multicast_create_eht_set_entry(pg, &eht_src_addr, h_addr, - filter_mode, false); - } + __eht_create_set_entries(pg, h_addr, srcs, nsrcs, addr_size, + filter_mode); /* we can be missing sets only if we've deleted some entries */ if (flush_entries) { struct net_bridge *br = pg->key.port->br; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index d7d167e10b70..50747990188e 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -1118,6 +1118,13 @@ void br_vlan_notify(const struct net_bridge *br, bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, const struct net_bridge_vlan *range_end); +void br_vlan_fill_forward_path_pvid(struct net_bridge *br, + struct net_device_path_ctx *ctx, + struct net_device_path *path); +int br_vlan_fill_forward_path_mode(struct net_bridge *br, + struct net_bridge_port *dst, + struct net_device_path *path); + static inline struct net_bridge_vlan_group *br_vlan_group( const struct net_bridge *br) { @@ -1277,6 +1284,19 @@ static inline int nbp_get_num_vlan_infos(struct net_bridge_port *p, return 0; } +static inline void br_vlan_fill_forward_path_pvid(struct net_bridge *br, + struct net_device_path_ctx *ctx, + struct net_device_path *path) +{ +} + +static inline int br_vlan_fill_forward_path_mode(struct net_bridge *br, + struct net_bridge_port *dst, + struct net_device_path *path) +{ + return 0; +} + static inline struct net_bridge_vlan_group *br_vlan_group( const struct net_bridge *br) { diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 21c6781906aa..3dafb6143cff 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -64,6 +64,20 @@ void br_set_state(struct net_bridge_port *p, unsigned int state) } } +u8 br_port_get_stp_state(const struct net_device *dev) +{ + struct net_bridge_port *p; + + ASSERT_RTNL(); + + p = br_port_get_rtnl(dev); + if (!p) + return BR_STATE_DISABLED; + + return p->state; +} +EXPORT_SYMBOL_GPL(br_port_get_stp_state); + /* called under bridge lock */ struct net_bridge_port *br_get_port(struct net_bridge *br, u16 port_no) { @@ -625,6 +639,19 @@ int br_set_ageing_time(struct net_bridge *br, clock_t ageing_time) return 0; } +clock_t br_get_ageing_time(struct net_device *br_dev) +{ + struct net_bridge *br; + + if (!netif_is_bridge_master(br_dev)) + return 0; + + br = netdev_priv(br_dev); + + return jiffies_to_clock_t(br->ageing_time); +} +EXPORT_SYMBOL_GPL(br_get_ageing_time); + /* called under bridge lock */ void __br_set_topology_change(struct net_bridge *br, unsigned char val) { diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 8829f621b8ec..da3256a3eed0 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1339,6 +1339,61 @@ int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid) } EXPORT_SYMBOL_GPL(br_vlan_get_pvid_rcu); +void br_vlan_fill_forward_path_pvid(struct net_bridge *br, + struct net_device_path_ctx *ctx, + struct net_device_path *path) +{ + struct net_bridge_vlan_group *vg; + int idx = ctx->num_vlans - 1; + u16 vid; + + path->bridge.vlan_mode = DEV_PATH_BR_VLAN_KEEP; + + if (!br_opt_get(br, BROPT_VLAN_ENABLED)) + return; + + vg = br_vlan_group(br); + + if (idx >= 0 && + ctx->vlan[idx].proto == br->vlan_proto) { + vid = ctx->vlan[idx].id; + } else { + path->bridge.vlan_mode = DEV_PATH_BR_VLAN_TAG; + vid = br_get_pvid(vg); + } + + path->bridge.vlan_id = vid; + path->bridge.vlan_proto = br->vlan_proto; +} + +int br_vlan_fill_forward_path_mode(struct net_bridge *br, + struct net_bridge_port *dst, + struct net_device_path *path) +{ + struct net_bridge_vlan_group *vg; + struct net_bridge_vlan *v; + + if (!br_opt_get(br, BROPT_VLAN_ENABLED)) + return 0; + + vg = nbp_vlan_group_rcu(dst); + v = br_vlan_find(vg, path->bridge.vlan_id); + if (!v || !br_vlan_should_use(v)) + return -EINVAL; + + if (!(v->flags & BRIDGE_VLAN_INFO_UNTAGGED)) + return 0; + + if (path->bridge.vlan_mode == DEV_PATH_BR_VLAN_TAG) + path->bridge.vlan_mode = DEV_PATH_BR_VLAN_KEEP; + else if (v->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) + path->bridge.vlan_mode = DEV_PATH_BR_VLAN_UNTAG_HW; + else + path->bridge.vlan_mode = DEV_PATH_BR_VLAN_UNTAG; + + return 0; +} + int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo) { @@ -1751,6 +1806,79 @@ out_kfree: kfree_skb(skb); } +static int br_vlan_replay_one(struct notifier_block *nb, + struct net_device *dev, + struct switchdev_obj_port_vlan *vlan, + struct netlink_ext_ack *extack) +{ + struct switchdev_notifier_port_obj_info obj_info = { + .info = { + .dev = dev, + .extack = extack, + }, + .obj = &vlan->obj, + }; + int err; + + err = nb->notifier_call(nb, SWITCHDEV_PORT_OBJ_ADD, &obj_info); + return notifier_to_errno(err); +} + +int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, + struct notifier_block *nb, struct netlink_ext_ack *extack) +{ + struct net_bridge_vlan_group *vg; + struct net_bridge_vlan *v; + struct net_bridge_port *p; + struct net_bridge *br; + int err = 0; + u16 pvid; + + ASSERT_RTNL(); + + if (!netif_is_bridge_master(br_dev)) + return -EINVAL; + + if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev)) + return -EINVAL; + + if (netif_is_bridge_master(dev)) { + br = netdev_priv(dev); + vg = br_vlan_group(br); + p = NULL; + } else { + p = br_port_get_rtnl(dev); + if (WARN_ON(!p)) + return -EINVAL; + vg = nbp_vlan_group(p); + br = p->br; + } + + if (!vg) + return 0; + + pvid = br_get_pvid(vg); + + list_for_each_entry(v, &vg->vlan_list, vlist) { + struct switchdev_obj_port_vlan vlan = { + .obj.orig_dev = dev, + .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, + .flags = br_vlan_flags(v, pvid), + .vid = v->vid, + }; + + if (!br_vlan_should_use(v)) + continue; + + err = br_vlan_replay_one(nb, dev, &vlan, extack); + if (err) + return err; + } + + return err; +} +EXPORT_SYMBOL_GPL(br_vlan_replay); + /* check if v_curr can enter a range ending in range_end */ bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, const struct net_bridge_vlan *range_end) diff --git a/net/bridge/br_vlan_tunnel.c b/net/bridge/br_vlan_tunnel.c index 169e005fbda2..0d3a8c01552e 100644 --- a/net/bridge/br_vlan_tunnel.c +++ b/net/bridge/br_vlan_tunnel.c @@ -35,7 +35,7 @@ static const struct rhashtable_params br_vlan_tunnel_rht_params = { }; static struct net_bridge_vlan *br_vlan_tunnel_lookup(struct rhashtable *tbl, - u64 tunnel_id) + __be64 tunnel_id) { return rhashtable_lookup_fast(tbl, &tunnel_id, br_vlan_tunnel_rht_params); diff --git a/net/core/Makefile b/net/core/Makefile index 3e2c378e5f31..0c2233c826fd 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -16,7 +16,6 @@ obj-y += dev.o dev_addr_lists.o dst.o netevent.o \ obj-y += net-sysfs.o obj-$(CONFIG_PAGE_POOL) += page_pool.o obj-$(CONFIG_PROC_FS) += net-procfs.o -obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o obj-$(CONFIG_NET_PKTGEN) += pktgen.o obj-$(CONFIG_NETPOLL) += netpoll.o obj-$(CONFIG_FIB_RULES) += fib_rules.o @@ -28,10 +27,13 @@ obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o obj-$(CONFIG_LWTUNNEL) += lwtunnel.o obj-$(CONFIG_LWTUNNEL_BPF) += lwt_bpf.o -obj-$(CONFIG_BPF_STREAM_PARSER) += sock_map.o obj-$(CONFIG_DST_CACHE) += dst_cache.o obj-$(CONFIG_HWBM) += hwbm.o obj-$(CONFIG_NET_DEVLINK) += devlink.o obj-$(CONFIG_GRO_CELLS) += gro_cells.o obj-$(CONFIG_FAILOVER) += failover.o +ifeq ($(CONFIG_INET),y) +obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o +obj-$(CONFIG_BPF_SYSCALL) += sock_map.o +endif obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 4edd033e899c..cc3712ad8716 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -89,7 +89,7 @@ static void bpf_sk_storage_map_free(struct bpf_map *map) smap = (struct bpf_local_storage_map *)map; bpf_local_storage_cache_idx_free(&sk_cache, smap->cache_idx); - bpf_local_storage_map_free(smap); + bpf_local_storage_map_free(smap, NULL); } static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) diff --git a/net/core/dev.c b/net/core/dev.c index 0f72ff5d34ba..48b529d59157 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -848,6 +848,52 @@ int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) } EXPORT_SYMBOL_GPL(dev_fill_metadata_dst); +static struct net_device_path *dev_fwd_path(struct net_device_path_stack *stack) +{ + int k = stack->num_paths++; + + if (WARN_ON_ONCE(k >= NET_DEVICE_PATH_STACK_MAX)) + return NULL; + + return &stack->path[k]; +} + +int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr, + struct net_device_path_stack *stack) +{ + const struct net_device *last_dev; + struct net_device_path_ctx ctx = { + .dev = dev, + .daddr = daddr, + }; + struct net_device_path *path; + int ret = 0; + + stack->num_paths = 0; + while (ctx.dev && ctx.dev->netdev_ops->ndo_fill_forward_path) { + last_dev = ctx.dev; + path = dev_fwd_path(stack); + if (!path) + return -1; + + memset(path, 0, sizeof(struct net_device_path)); + ret = ctx.dev->netdev_ops->ndo_fill_forward_path(&ctx, path); + if (ret < 0) + return -1; + + if (WARN_ON_ONCE(last_dev == ctx.dev)) + return -1; + } + path = dev_fwd_path(stack); + if (!path) + return -1; + path->type = DEV_PATH_ETHERNET; + path->dev = ctx.dev; + + return ret; +} +EXPORT_SYMBOL_GPL(dev_fill_forward_path); + /** * __dev_get_by_name - find a device by its name * @net: the applicable net namespace @@ -2463,16 +2509,14 @@ int netdev_txq_to_tc(struct net_device *dev, unsigned int txq) EXPORT_SYMBOL(netdev_txq_to_tc); #ifdef CONFIG_XPS -struct static_key xps_needed __read_mostly; -EXPORT_SYMBOL(xps_needed); -struct static_key xps_rxqs_needed __read_mostly; -EXPORT_SYMBOL(xps_rxqs_needed); +static struct static_key xps_needed __read_mostly; +static struct static_key xps_rxqs_needed __read_mostly; static DEFINE_MUTEX(xps_map_mutex); #define xmap_dereference(P) \ rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) static bool remove_xps_queue(struct xps_dev_maps *dev_maps, - int tci, u16 index) + struct xps_dev_maps *old_maps, int tci, u16 index) { struct xps_map *map = NULL; int pos; @@ -2491,6 +2535,8 @@ static bool remove_xps_queue(struct xps_dev_maps *dev_maps, break; } + if (old_maps) + RCU_INIT_POINTER(old_maps->attr_map[tci], NULL); RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL); kfree_rcu(map, rcu); return false; @@ -2503,7 +2549,7 @@ static bool remove_xps_queue_cpu(struct net_device *dev, struct xps_dev_maps *dev_maps, int cpu, u16 offset, u16 count) { - int num_tc = dev->num_tc ? : 1; + int num_tc = dev_maps->num_tc; bool active = false; int tci; @@ -2511,7 +2557,7 @@ static bool remove_xps_queue_cpu(struct net_device *dev, int i, j; for (i = count, j = offset; i--; j++) { - if (!remove_xps_queue(dev_maps, tci, j)) + if (!remove_xps_queue(dev_maps, NULL, tci, j)) break; } @@ -2523,74 +2569,54 @@ static bool remove_xps_queue_cpu(struct net_device *dev, static void reset_xps_maps(struct net_device *dev, struct xps_dev_maps *dev_maps, - bool is_rxqs_map) + enum xps_map_type type) { - if (is_rxqs_map) { - static_key_slow_dec_cpuslocked(&xps_rxqs_needed); - RCU_INIT_POINTER(dev->xps_rxqs_map, NULL); - } else { - RCU_INIT_POINTER(dev->xps_cpus_map, NULL); - } static_key_slow_dec_cpuslocked(&xps_needed); + if (type == XPS_RXQS) + static_key_slow_dec_cpuslocked(&xps_rxqs_needed); + + RCU_INIT_POINTER(dev->xps_maps[type], NULL); + kfree_rcu(dev_maps, rcu); } -static void clean_xps_maps(struct net_device *dev, const unsigned long *mask, - struct xps_dev_maps *dev_maps, unsigned int nr_ids, - u16 offset, u16 count, bool is_rxqs_map) +static void clean_xps_maps(struct net_device *dev, enum xps_map_type type, + u16 offset, u16 count) { + struct xps_dev_maps *dev_maps; bool active = false; int i, j; - for (j = -1; j = netif_attrmask_next(j, mask, nr_ids), - j < nr_ids;) - active |= remove_xps_queue_cpu(dev, dev_maps, j, offset, - count); + dev_maps = xmap_dereference(dev->xps_maps[type]); + if (!dev_maps) + return; + + for (j = 0; j < dev_maps->nr_ids; j++) + active |= remove_xps_queue_cpu(dev, dev_maps, j, offset, count); if (!active) - reset_xps_maps(dev, dev_maps, is_rxqs_map); + reset_xps_maps(dev, dev_maps, type); - if (!is_rxqs_map) { - for (i = offset + (count - 1); count--; i--) { + if (type == XPS_CPUS) { + for (i = offset + (count - 1); count--; i--) netdev_queue_numa_node_write( - netdev_get_tx_queue(dev, i), - NUMA_NO_NODE); - } + netdev_get_tx_queue(dev, i), NUMA_NO_NODE); } } static void netif_reset_xps_queues(struct net_device *dev, u16 offset, u16 count) { - const unsigned long *possible_mask = NULL; - struct xps_dev_maps *dev_maps; - unsigned int nr_ids; - if (!static_key_false(&xps_needed)) return; cpus_read_lock(); mutex_lock(&xps_map_mutex); - if (static_key_false(&xps_rxqs_needed)) { - dev_maps = xmap_dereference(dev->xps_rxqs_map); - if (dev_maps) { - nr_ids = dev->num_rx_queues; - clean_xps_maps(dev, possible_mask, dev_maps, nr_ids, - offset, count, true); - } - } - - dev_maps = xmap_dereference(dev->xps_cpus_map); - if (!dev_maps) - goto out_no_maps; + if (static_key_false(&xps_rxqs_needed)) + clean_xps_maps(dev, XPS_RXQS, offset, count); - if (num_possible_cpus() > 1) - possible_mask = cpumask_bits(cpu_possible_mask); - nr_ids = nr_cpu_ids; - clean_xps_maps(dev, possible_mask, dev_maps, nr_ids, offset, count, - false); + clean_xps_maps(dev, XPS_CPUS, offset, count); -out_no_maps: mutex_unlock(&xps_map_mutex); cpus_read_unlock(); } @@ -2640,16 +2666,35 @@ static struct xps_map *expand_xps_map(struct xps_map *map, int attr_index, return new_map; } +/* Copy xps maps at a given index */ +static void xps_copy_dev_maps(struct xps_dev_maps *dev_maps, + struct xps_dev_maps *new_dev_maps, int index, + int tc, bool skip_tc) +{ + int i, tci = index * dev_maps->num_tc; + struct xps_map *map; + + /* copy maps belonging to foreign traffic classes */ + for (i = 0; i < dev_maps->num_tc; i++, tci++) { + if (i == tc && skip_tc) + continue; + + /* fill in the new device map from the old device map */ + map = xmap_dereference(dev_maps->attr_map[tci]); + RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); + } +} + /* Must be called under cpus_read_lock */ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, - u16 index, bool is_rxqs_map) + u16 index, enum xps_map_type type) { - const unsigned long *online_mask = NULL, *possible_mask = NULL; - struct xps_dev_maps *dev_maps, *new_dev_maps = NULL; + struct xps_dev_maps *dev_maps, *new_dev_maps = NULL, *old_dev_maps = NULL; + const unsigned long *online_mask = NULL; + bool active = false, copy = false; int i, j, tci, numa_node_id = -2; int maps_sz, num_tc = 1, tc = 0; struct xps_map *map, *new_map; - bool active = false; unsigned int nr_ids; if (dev->num_tc) { @@ -2667,38 +2712,48 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, } mutex_lock(&xps_map_mutex); - if (is_rxqs_map) { + + dev_maps = xmap_dereference(dev->xps_maps[type]); + if (type == XPS_RXQS) { maps_sz = XPS_RXQ_DEV_MAPS_SIZE(num_tc, dev->num_rx_queues); - dev_maps = xmap_dereference(dev->xps_rxqs_map); nr_ids = dev->num_rx_queues; } else { maps_sz = XPS_CPU_DEV_MAPS_SIZE(num_tc); - if (num_possible_cpus() > 1) { + if (num_possible_cpus() > 1) online_mask = cpumask_bits(cpu_online_mask); - possible_mask = cpumask_bits(cpu_possible_mask); - } - dev_maps = xmap_dereference(dev->xps_cpus_map); nr_ids = nr_cpu_ids; } if (maps_sz < L1_CACHE_BYTES) maps_sz = L1_CACHE_BYTES; + /* The old dev_maps could be larger or smaller than the one we're + * setting up now, as dev->num_tc or nr_ids could have been updated in + * between. We could try to be smart, but let's be safe instead and only + * copy foreign traffic classes if the two map sizes match. + */ + if (dev_maps && + dev_maps->num_tc == num_tc && dev_maps->nr_ids == nr_ids) + copy = true; + /* allocate memory for queue storage */ for (j = -1; j = netif_attrmask_next_and(j, online_mask, mask, nr_ids), j < nr_ids;) { - if (!new_dev_maps) - new_dev_maps = kzalloc(maps_sz, GFP_KERNEL); if (!new_dev_maps) { - mutex_unlock(&xps_map_mutex); - return -ENOMEM; + new_dev_maps = kzalloc(maps_sz, GFP_KERNEL); + if (!new_dev_maps) { + mutex_unlock(&xps_map_mutex); + return -ENOMEM; + } + + new_dev_maps->nr_ids = nr_ids; + new_dev_maps->num_tc = num_tc; } tci = j * num_tc + tc; - map = dev_maps ? xmap_dereference(dev_maps->attr_map[tci]) : - NULL; + map = copy ? xmap_dereference(dev_maps->attr_map[tci]) : NULL; - map = expand_xps_map(map, j, index, is_rxqs_map); + map = expand_xps_map(map, j, index, type == XPS_RXQS); if (!map) goto error; @@ -2711,29 +2766,21 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, if (!dev_maps) { /* Increment static keys at most once per type */ static_key_slow_inc_cpuslocked(&xps_needed); - if (is_rxqs_map) + if (type == XPS_RXQS) static_key_slow_inc_cpuslocked(&xps_rxqs_needed); } - for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids), - j < nr_ids;) { - /* copy maps belonging to foreign traffic classes */ - for (i = tc, tci = j * num_tc; dev_maps && i--; tci++) { - /* fill in the new device map from the old device map */ - map = xmap_dereference(dev_maps->attr_map[tci]); - RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); - } + for (j = 0; j < nr_ids; j++) { + bool skip_tc = false; - /* We need to explicitly update tci as prevous loop - * could break out early if dev_maps is NULL. - */ tci = j * num_tc + tc; - if (netif_attr_test_mask(j, mask, nr_ids) && netif_attr_test_online(j, online_mask, nr_ids)) { /* add tx-queue to CPU/rx-queue maps */ int pos = 0; + skip_tc = true; + map = xmap_dereference(new_dev_maps->attr_map[tci]); while ((pos < map->len) && (map->queues[pos] != index)) pos++; @@ -2741,78 +2788,81 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, if (pos == map->len) map->queues[map->len++] = index; #ifdef CONFIG_NUMA - if (!is_rxqs_map) { + if (type == XPS_CPUS) { if (numa_node_id == -2) numa_node_id = cpu_to_node(j); else if (numa_node_id != cpu_to_node(j)) numa_node_id = -1; } #endif - } else if (dev_maps) { - /* fill in the new device map from the old device map */ - map = xmap_dereference(dev_maps->attr_map[tci]); - RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } - /* copy maps belonging to foreign traffic classes */ - for (i = num_tc - tc, tci++; dev_maps && --i; tci++) { - /* fill in the new device map from the old device map */ - map = xmap_dereference(dev_maps->attr_map[tci]); - RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); - } + if (copy) + xps_copy_dev_maps(dev_maps, new_dev_maps, j, tc, + skip_tc); } - if (is_rxqs_map) - rcu_assign_pointer(dev->xps_rxqs_map, new_dev_maps); - else - rcu_assign_pointer(dev->xps_cpus_map, new_dev_maps); + rcu_assign_pointer(dev->xps_maps[type], new_dev_maps); /* Cleanup old maps */ if (!dev_maps) goto out_no_old_maps; - for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids), - j < nr_ids;) { - for (i = num_tc, tci = j * num_tc; i--; tci++) { - new_map = xmap_dereference(new_dev_maps->attr_map[tci]); + for (j = 0; j < dev_maps->nr_ids; j++) { + for (i = num_tc, tci = j * dev_maps->num_tc; i--; tci++) { map = xmap_dereference(dev_maps->attr_map[tci]); - if (map && map != new_map) - kfree_rcu(map, rcu); + if (!map) + continue; + + if (copy) { + new_map = xmap_dereference(new_dev_maps->attr_map[tci]); + if (map == new_map) + continue; + } + + RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL); + kfree_rcu(map, rcu); } } - kfree_rcu(dev_maps, rcu); + old_dev_maps = dev_maps; out_no_old_maps: dev_maps = new_dev_maps; active = true; out_no_new_maps: - if (!is_rxqs_map) { + if (type == XPS_CPUS) /* update Tx queue numa node */ netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index), (numa_node_id >= 0) ? numa_node_id : NUMA_NO_NODE); - } if (!dev_maps) goto out_no_maps; /* removes tx-queue from unused CPUs/rx-queues */ - for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids), - j < nr_ids;) { - for (i = tc, tci = j * num_tc; i--; tci++) - active |= remove_xps_queue(dev_maps, tci, index); - if (!netif_attr_test_mask(j, mask, nr_ids) || - !netif_attr_test_online(j, online_mask, nr_ids)) - active |= remove_xps_queue(dev_maps, tci, index); - for (i = num_tc - tc, tci++; --i; tci++) - active |= remove_xps_queue(dev_maps, tci, index); + for (j = 0; j < dev_maps->nr_ids; j++) { + tci = j * dev_maps->num_tc; + + for (i = 0; i < dev_maps->num_tc; i++, tci++) { + if (i == tc && + netif_attr_test_mask(j, mask, dev_maps->nr_ids) && + netif_attr_test_online(j, online_mask, dev_maps->nr_ids)) + continue; + + active |= remove_xps_queue(dev_maps, + copy ? old_dev_maps : NULL, + tci, index); + } } + if (old_dev_maps) + kfree_rcu(old_dev_maps, rcu); + /* free map if not active */ if (!active) - reset_xps_maps(dev, dev_maps, is_rxqs_map); + reset_xps_maps(dev, dev_maps, type); out_no_maps: mutex_unlock(&xps_map_mutex); @@ -2820,11 +2870,10 @@ out_no_maps: return 0; error: /* remove any maps that we added */ - for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids), - j < nr_ids;) { + for (j = 0; j < nr_ids; j++) { for (i = num_tc, tci = j * num_tc; i--; tci++) { new_map = xmap_dereference(new_dev_maps->attr_map[tci]); - map = dev_maps ? + map = copy ? xmap_dereference(dev_maps->attr_map[tci]) : NULL; if (new_map && new_map != map) @@ -2845,7 +2894,7 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, int ret; cpus_read_lock(); - ret = __netif_set_xps_queue(dev, cpumask_bits(mask), index, false); + ret = __netif_set_xps_queue(dev, cpumask_bits(mask), index, XPS_CPUS); cpus_read_unlock(); return ret; @@ -3956,13 +4005,15 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) static int __get_xps_queue_idx(struct net_device *dev, struct sk_buff *skb, struct xps_dev_maps *dev_maps, unsigned int tci) { + int tc = netdev_get_prio_tc_map(dev, skb->priority); struct xps_map *map; int queue_index = -1; - if (dev->num_tc) { - tci *= dev->num_tc; - tci += netdev_get_prio_tc_map(dev, skb->priority); - } + if (tc >= dev_maps->num_tc || tci >= dev_maps->nr_ids) + return queue_index; + + tci *= dev_maps->num_tc; + tci += tc; map = rcu_dereference(dev_maps->attr_map[tci]); if (map) { @@ -3993,18 +4044,18 @@ static int get_xps_queue(struct net_device *dev, struct net_device *sb_dev, if (!static_key_false(&xps_rxqs_needed)) goto get_cpus_map; - dev_maps = rcu_dereference(sb_dev->xps_rxqs_map); + dev_maps = rcu_dereference(sb_dev->xps_maps[XPS_RXQS]); if (dev_maps) { int tci = sk_rx_queue_get(sk); - if (tci >= 0 && tci < dev->num_rx_queues) + if (tci >= 0) queue_index = __get_xps_queue_idx(dev, skb, dev_maps, tci); } get_cpus_map: if (queue_index < 0) { - dev_maps = rcu_dereference(sb_dev->xps_cpus_map); + dev_maps = rcu_dereference(sb_dev->xps_maps[XPS_CPUS]); if (dev_maps) { unsigned int tci = skb->sender_cpu - 1; @@ -5284,6 +5335,7 @@ skip_classify: goto another_round; case RX_HANDLER_EXACT: deliver_exact = true; + break; case RX_HANDLER_PASS: break; default: @@ -5876,15 +5928,13 @@ void napi_gro_flush(struct napi_struct *napi, bool flush_old) } EXPORT_SYMBOL(napi_gro_flush); -static struct list_head *gro_list_prepare(struct napi_struct *napi, - struct sk_buff *skb) +static void gro_list_prepare(const struct list_head *head, + const struct sk_buff *skb) { unsigned int maclen = skb->dev->hard_header_len; u32 hash = skb_get_hash_raw(skb); - struct list_head *head; struct sk_buff *p; - head = &napi->gro_hash[hash & (GRO_HASH_BUCKETS - 1)].list; list_for_each_entry(p, head, list) { unsigned long diffs; @@ -5910,8 +5960,6 @@ static struct list_head *gro_list_prepare(struct napi_struct *napi, maclen); NAPI_GRO_CB(p)->same_flow = !diffs; } - - return head; } static void skb_gro_reset_offset(struct sk_buff *skb) @@ -5974,11 +6022,11 @@ static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head) static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { - u32 hash = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1); + u32 bucket = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1); + struct gro_list *gro_list = &napi->gro_hash[bucket]; struct list_head *head = &offload_base; struct packet_offload *ptype; __be16 type = skb->protocol; - struct list_head *gro_head; struct sk_buff *pp = NULL; enum gro_result ret; int same_flow; @@ -5987,7 +6035,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (netif_elide_gro(skb->dev)) goto normal; - gro_head = gro_list_prepare(napi, skb); + gro_list_prepare(&gro_list->list, skb); rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { @@ -6023,7 +6071,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff pp = INDIRECT_CALL_INET(ptype->callbacks.gro_receive, ipv6_gro_receive, inet_gro_receive, - gro_head, skb); + &gro_list->list, skb); break; } rcu_read_unlock(); @@ -6042,7 +6090,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (pp) { skb_list_del_init(pp); napi_gro_complete(napi, pp); - napi->gro_hash[hash].count--; + gro_list->count--; } if (same_flow) @@ -6051,16 +6099,16 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (NAPI_GRO_CB(skb)->flush) goto normal; - if (unlikely(napi->gro_hash[hash].count >= MAX_GRO_SKBS)) { - gro_flush_oldest(napi, gro_head); - } else { - napi->gro_hash[hash].count++; - } + if (unlikely(gro_list->count >= MAX_GRO_SKBS)) + gro_flush_oldest(napi, &gro_list->list); + else + gro_list->count++; + NAPI_GRO_CB(skb)->count = 1; NAPI_GRO_CB(skb)->age = jiffies; NAPI_GRO_CB(skb)->last = skb; skb_shinfo(skb)->gso_size = skb_gro_len(skb); - list_add(&skb->list, gro_head); + list_add(&skb->list, &gro_list->list); ret = GRO_HELD; pull: @@ -6068,11 +6116,11 @@ pull: if (grow > 0) gro_pull_from_frag0(skb, grow); ok: - if (napi->gro_hash[hash].count) { - if (!test_bit(hash, &napi->gro_bitmask)) - __set_bit(hash, &napi->gro_bitmask); - } else if (test_bit(hash, &napi->gro_bitmask)) { - __clear_bit(hash, &napi->gro_bitmask); + if (gro_list->count) { + if (!test_bit(bucket, &napi->gro_bitmask)) + __set_bit(bucket, &napi->gro_bitmask); + } else if (test_bit(bucket, &napi->gro_bitmask)) { + __clear_bit(bucket, &napi->gro_bitmask); } return ret; @@ -6789,6 +6837,7 @@ int dev_set_threaded(struct net_device *dev, bool threaded) return err; } +EXPORT_SYMBOL(dev_set_threaded); void netif_napi_add(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) @@ -10336,14 +10385,20 @@ EXPORT_SYMBOL(register_netdev); int netdev_refcnt_read(const struct net_device *dev) { +#ifdef CONFIG_PCPU_DEV_REFCNT int i, refcnt = 0; for_each_possible_cpu(i) refcnt += *per_cpu_ptr(dev->pcpu_refcnt, i); return refcnt; +#else + return refcount_read(&dev->dev_refcnt); +#endif } EXPORT_SYMBOL(netdev_refcnt_read); +int netdev_unregister_timeout_secs __read_mostly = 10; + #define WAIT_REFS_MIN_MSECS 1 #define WAIT_REFS_MAX_MSECS 250 /** @@ -10368,7 +10423,7 @@ static void netdev_wait_allrefs(struct net_device *dev) rebroadcast_time = warning_time = jiffies; refcnt = netdev_refcnt_read(dev); - while (refcnt != 0) { + while (refcnt != 1) { if (time_after(jiffies, rebroadcast_time + 1 * HZ)) { rtnl_lock(); @@ -10405,7 +10460,9 @@ static void netdev_wait_allrefs(struct net_device *dev) refcnt = netdev_refcnt_read(dev); - if (refcnt && time_after(jiffies, warning_time + 10 * HZ)) { + if (refcnt && + time_after(jiffies, warning_time + + netdev_unregister_timeout_secs * HZ)) { pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n", dev->name, refcnt); warning_time = jiffies; @@ -10481,7 +10538,7 @@ void netdev_run_todo(void) netdev_wait_allrefs(dev); /* paranoia */ - BUG_ON(netdev_refcnt_read(dev)); + BUG_ON(netdev_refcnt_read(dev) != 1); BUG_ON(!list_empty(&dev->ptype_all)); BUG_ON(!list_empty(&dev->ptype_specific)); WARN_ON(rcu_access_pointer(dev->ip_ptr)); @@ -10698,9 +10755,14 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev = PTR_ALIGN(p, NETDEV_ALIGN); dev->padded = (char *)dev - (char *)p; +#ifdef CONFIG_PCPU_DEV_REFCNT dev->pcpu_refcnt = alloc_percpu(int); if (!dev->pcpu_refcnt) goto free_dev; + dev_hold(dev); +#else + refcount_set(&dev->dev_refcnt, 1); +#endif if (dev_addr_init(dev)) goto free_pcpu; @@ -10764,8 +10826,10 @@ free_all: return NULL; free_pcpu: +#ifdef CONFIG_PCPU_DEV_REFCNT free_percpu(dev->pcpu_refcnt); free_dev: +#endif netdev_freemem(dev); return NULL; } @@ -10807,8 +10871,10 @@ void free_netdev(struct net_device *dev) list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) netif_napi_del(p); +#ifdef CONFIG_PCPU_DEV_REFCNT free_percpu(dev->pcpu_refcnt); dev->pcpu_refcnt = NULL; +#endif free_percpu(dev->xdp_bulkq); dev->xdp_bulkq = NULL; diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index db65ce62b625..ead2a8aa57b4 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -1754,7 +1754,7 @@ static void exit_net_drop_monitor(void) /* * Because of the module_get/put we do in the trace state change path - * we are guarnateed not to have any current users when we get here + * we are guaranteed not to have any current users when we get here */ for_each_possible_cpu(cpu) { diff --git a/net/core/filter.c b/net/core/filter.c index 9323d34d34cc..f5eeebf6a16f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1863,10 +1863,7 @@ static const struct bpf_func_proto bpf_sk_fullsock_proto = { static inline int sk_skb_try_make_writable(struct sk_buff *skb, unsigned int write_len) { - int err = __bpf_try_make_writable(skb, write_len); - - bpf_compute_data_end_sk_skb(skb); - return err; + return __bpf_try_make_writable(skb, write_len); } BPF_CALL_2(sk_skb_pull_data, struct sk_buff *, skb, u32, len) @@ -3412,6 +3409,7 @@ static u32 bpf_skb_net_base_len(const struct sk_buff *skb) BPF_F_ADJ_ROOM_ENCAP_L3_MASK | \ BPF_F_ADJ_ROOM_ENCAP_L4_GRE | \ BPF_F_ADJ_ROOM_ENCAP_L4_UDP | \ + BPF_F_ADJ_ROOM_ENCAP_L2_ETH | \ BPF_F_ADJ_ROOM_ENCAP_L2( \ BPF_ADJ_ROOM_ENCAP_L2_MASK)) @@ -3448,6 +3446,10 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff, flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP) return -EINVAL; + if (flags & BPF_F_ADJ_ROOM_ENCAP_L2_ETH && + inner_mac_len < ETH_HLEN) + return -EINVAL; + if (skb->encapsulation) return -EALREADY; @@ -3466,7 +3468,11 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff, skb->inner_mac_header = inner_net - inner_mac_len; skb->inner_network_header = inner_net; skb->inner_transport_header = inner_trans; - skb_set_inner_protocol(skb, skb->protocol); + + if (flags & BPF_F_ADJ_ROOM_ENCAP_L2_ETH) + skb_set_inner_protocol(skb, htons(ETH_P_TEB)); + else + skb_set_inner_protocol(skb, skb->protocol); skb->encapsulation = 1; skb_set_network_header(skb, mac_len); @@ -3577,7 +3583,6 @@ BPF_CALL_4(sk_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, return -ENOMEM; __skb_pull(skb, len_diff_abs); } - bpf_compute_data_end_sk_skb(skb); if (tls_sw_has_ctx_rx(skb->sk)) { struct strp_msg *rxm = strp_msg(skb); @@ -3742,10 +3747,7 @@ static const struct bpf_func_proto bpf_skb_change_tail_proto = { BPF_CALL_3(sk_skb_change_tail, struct sk_buff *, skb, u32, new_len, u64, flags) { - int ret = __bpf_skb_change_tail(skb, new_len, flags); - - bpf_compute_data_end_sk_skb(skb); - return ret; + return __bpf_skb_change_tail(skb, new_len, flags); } static const struct bpf_func_proto sk_skb_change_tail_proto = { @@ -3808,10 +3810,7 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = { BPF_CALL_3(sk_skb_change_head, struct sk_buff *, skb, u32, head_room, u64, flags) { - int ret = __bpf_skb_change_head(skb, head_room, flags); - - bpf_compute_data_end_sk_skb(skb); - return ret; + return __bpf_skb_change_head(skb, head_room, flags); } static const struct bpf_func_proto sk_skb_change_head_proto = { @@ -3919,23 +3918,6 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = { .arg2_type = ARG_ANYTHING, }; -static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd, - struct bpf_map *map, struct xdp_buff *xdp) -{ - switch (map->map_type) { - case BPF_MAP_TYPE_DEVMAP: - case BPF_MAP_TYPE_DEVMAP_HASH: - return dev_map_enqueue(fwd, xdp, dev_rx); - case BPF_MAP_TYPE_CPUMAP: - return cpu_map_enqueue(fwd, xdp, dev_rx); - case BPF_MAP_TYPE_XSKMAP: - return __xsk_map_redirect(fwd, xdp); - default: - return -EBADRQC; - } - return 0; -} - void xdp_do_flush(void) { __dev_flush(); @@ -3944,71 +3926,52 @@ void xdp_do_flush(void) } EXPORT_SYMBOL_GPL(xdp_do_flush); -static inline void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index) -{ - switch (map->map_type) { - case BPF_MAP_TYPE_DEVMAP: - return __dev_map_lookup_elem(map, index); - case BPF_MAP_TYPE_DEVMAP_HASH: - return __dev_map_hash_lookup_elem(map, index); - case BPF_MAP_TYPE_CPUMAP: - return __cpu_map_lookup_elem(map, index); - case BPF_MAP_TYPE_XSKMAP: - return __xsk_map_lookup_elem(map, index); - default: - return NULL; - } -} - -void bpf_clear_redirect_map(struct bpf_map *map) -{ - struct bpf_redirect_info *ri; - int cpu; - - for_each_possible_cpu(cpu) { - ri = per_cpu_ptr(&bpf_redirect_info, cpu); - /* Avoid polluting remote cacheline due to writes if - * not needed. Once we pass this test, we need the - * cmpxchg() to make sure it hasn't been changed in - * the meantime by remote CPU. - */ - if (unlikely(READ_ONCE(ri->map) == map)) - cmpxchg(&ri->map, map, NULL); - } -} - int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); - struct bpf_map *map = READ_ONCE(ri->map); - u32 index = ri->tgt_index; + enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; + u32 map_id = ri->map_id; int err; - ri->tgt_index = 0; - ri->tgt_value = NULL; - WRITE_ONCE(ri->map, NULL); + ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ + ri->map_type = BPF_MAP_TYPE_UNSPEC; - if (unlikely(!map)) { - fwd = dev_get_by_index_rcu(dev_net(dev), index); - if (unlikely(!fwd)) { - err = -EINVAL; - goto err; + switch (map_type) { + case BPF_MAP_TYPE_DEVMAP: + fallthrough; + case BPF_MAP_TYPE_DEVMAP_HASH: + err = dev_map_enqueue(fwd, xdp, dev); + break; + case BPF_MAP_TYPE_CPUMAP: + err = cpu_map_enqueue(fwd, xdp, dev); + break; + case BPF_MAP_TYPE_XSKMAP: + err = __xsk_map_redirect(fwd, xdp); + break; + case BPF_MAP_TYPE_UNSPEC: + if (map_id == INT_MAX) { + fwd = dev_get_by_index_rcu(dev_net(dev), ri->tgt_index); + if (unlikely(!fwd)) { + err = -EINVAL; + break; + } + err = dev_xdp_enqueue(fwd, xdp, dev); + break; } - - err = dev_xdp_enqueue(fwd, xdp, dev); - } else { - err = __bpf_tx_xdp_map(dev, fwd, map, xdp); + fallthrough; + default: + err = -EBADRQC; } if (unlikely(err)) goto err; - _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index); + _trace_xdp_redirect_map(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index); return 0; err: - _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err); + _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err); return err; } EXPORT_SYMBOL_GPL(xdp_do_redirect); @@ -4017,41 +3980,36 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog, - struct bpf_map *map) + void *fwd, + enum bpf_map_type map_type, u32 map_id) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); - u32 index = ri->tgt_index; - void *fwd = ri->tgt_value; - int err = 0; - - ri->tgt_index = 0; - ri->tgt_value = NULL; - WRITE_ONCE(ri->map, NULL); - - if (map->map_type == BPF_MAP_TYPE_DEVMAP || - map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { - struct bpf_dtab_netdev *dst = fwd; + int err; - err = dev_map_generic_redirect(dst, skb, xdp_prog); + switch (map_type) { + case BPF_MAP_TYPE_DEVMAP: + fallthrough; + case BPF_MAP_TYPE_DEVMAP_HASH: + err = dev_map_generic_redirect(fwd, skb, xdp_prog); if (unlikely(err)) goto err; - } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { - struct xdp_sock *xs = fwd; - - err = xsk_generic_rcv(xs, xdp); + break; + case BPF_MAP_TYPE_XSKMAP: + err = xsk_generic_rcv(fwd, xdp); if (err) goto err; consume_skb(skb); - } else { + break; + default: /* TODO: Handle BPF_MAP_TYPE_CPUMAP */ err = -EBADRQC; goto err; } - _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index); + _trace_xdp_redirect_map(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index); return 0; err: - _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err); + _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err); return err; } @@ -4059,31 +4017,34 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); - struct bpf_map *map = READ_ONCE(ri->map); - u32 index = ri->tgt_index; - struct net_device *fwd; - int err = 0; - - if (map) - return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, - map); - ri->tgt_index = 0; - fwd = dev_get_by_index_rcu(dev_net(dev), index); - if (unlikely(!fwd)) { - err = -EINVAL; - goto err; - } + enum bpf_map_type map_type = ri->map_type; + void *fwd = ri->tgt_value; + u32 map_id = ri->map_id; + int err; - err = xdp_ok_fwd_dev(fwd, skb->len); - if (unlikely(err)) - goto err; + ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ + ri->map_type = BPF_MAP_TYPE_UNSPEC; - skb->dev = fwd; - _trace_xdp_redirect(dev, xdp_prog, index); - generic_xdp_tx(skb, xdp_prog); - return 0; + if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) { + fwd = dev_get_by_index_rcu(dev_net(dev), ri->tgt_index); + if (unlikely(!fwd)) { + err = -EINVAL; + goto err; + } + + err = xdp_ok_fwd_dev(fwd, skb->len); + if (unlikely(err)) + goto err; + + skb->dev = fwd; + _trace_xdp_redirect(dev, xdp_prog, ri->tgt_index); + generic_xdp_tx(skb, xdp_prog); + return 0; + } + + return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, fwd, map_type, map_id); err: - _trace_xdp_redirect_err(dev, xdp_prog, index, err); + _trace_xdp_redirect_err(dev, xdp_prog, ri->tgt_index, err); return err; } @@ -4094,10 +4055,12 @@ BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags) if (unlikely(flags)) return XDP_ABORTED; - ri->flags = flags; + /* NB! Map type UNSPEC and map_id == INT_MAX (never generated + * by map_idr) is used for ifindex based XDP redirect. + */ ri->tgt_index = ifindex; - ri->tgt_value = NULL; - WRITE_ONCE(ri->map, NULL); + ri->map_id = INT_MAX; + ri->map_type = BPF_MAP_TYPE_UNSPEC; return XDP_REDIRECT; } @@ -4113,28 +4076,7 @@ static const struct bpf_func_proto bpf_xdp_redirect_proto = { BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex, u64, flags) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); - - /* Lower bits of the flags are used as return code on lookup failure */ - if (unlikely(flags > XDP_TX)) - return XDP_ABORTED; - - ri->tgt_value = __xdp_map_lookup_elem(map, ifindex); - if (unlikely(!ri->tgt_value)) { - /* If the lookup fails we want to clear out the state in the - * redirect_info struct completely, so that if an eBPF program - * performs multiple lookups, the last one always takes - * precedence. - */ - WRITE_ONCE(ri->map, NULL); - return flags; - } - - ri->flags = flags; - ri->tgt_index = ifindex; - WRITE_ONCE(ri->map, map); - - return XDP_REDIRECT; + return map->ops->map_redirect(map, ifindex, flags); } static const struct bpf_func_proto bpf_xdp_redirect_map_proto = { @@ -9663,22 +9605,40 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; } +/* data_end = skb->data + skb_headlen() */ +static struct bpf_insn *bpf_convert_data_end_access(const struct bpf_insn *si, + struct bpf_insn *insn) +{ + /* si->dst_reg = skb->data */ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, data)); + /* AX = skb->len */ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len), + BPF_REG_AX, si->src_reg, + offsetof(struct sk_buff, len)); + /* si->dst_reg = skb->data + skb->len */ + *insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX); + /* AX = skb->data_len */ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data_len), + BPF_REG_AX, si->src_reg, + offsetof(struct sk_buff, data_len)); + /* si->dst_reg = skb->data + skb->len - skb->data_len */ + *insn++ = BPF_ALU64_REG(BPF_SUB, si->dst_reg, BPF_REG_AX); + + return insn; +} + static u32 sk_skb_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; - int off; switch (si->off) { case offsetof(struct __sk_buff, data_end): - off = si->off; - off -= offsetof(struct __sk_buff, data_end); - off += offsetof(struct sk_buff, cb); - off += offsetof(struct tcp_skb_cb, bpf.data_end); - *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, - si->src_reg, off); + insn = bpf_convert_data_end_access(si, insn); break; default: return bpf_convert_ctx_access(type, si, insn_buf, prog, @@ -10457,6 +10417,7 @@ static u32 sk_lookup_convert_ctx_access(enum bpf_access_type type, } const struct bpf_prog_ops sk_lookup_prog_ops = { + .test_run = bpf_prog_test_run_sk_lookup, }; const struct bpf_verifier_ops sk_lookup_verifier_ops = { diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index a96a4f5de0ce..5985029e43d4 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -114,7 +114,7 @@ int flow_dissector_bpf_prog_attach_check(struct net *net, * is the protocol port offset returned from proto_ports_offset */ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, - void *data, int hlen) + const void *data, int hlen) { int poff = proto_ports_offset(ip_proto); @@ -161,7 +161,7 @@ static bool icmp_has_id(u8 type) */ void skb_flow_get_icmp_tci(const struct sk_buff *skb, struct flow_dissector_key_icmp *key_icmp, - void *data, int thoff, int hlen) + const void *data, int thoff, int hlen) { struct icmphdr *ih, _ih; @@ -187,8 +187,8 @@ EXPORT_SYMBOL(skb_flow_get_icmp_tci); */ static void __skb_flow_dissect_icmp(const struct sk_buff *skb, struct flow_dissector *flow_dissector, - void *target_container, - void *data, int thoff, int hlen) + void *target_container, const void *data, + int thoff, int hlen) { struct flow_dissector_key_icmp *key_icmp; @@ -409,8 +409,8 @@ EXPORT_SYMBOL(skb_flow_dissect_hash); static enum flow_dissect_ret __skb_flow_dissect_mpls(const struct sk_buff *skb, struct flow_dissector *flow_dissector, - void *target_container, void *data, int nhoff, int hlen, - int lse_index, bool *entropy_label) + void *target_container, const void *data, int nhoff, + int hlen, int lse_index, bool *entropy_label) { struct mpls_label *hdr, _hdr; u32 entry, label, bos; @@ -467,7 +467,8 @@ __skb_flow_dissect_mpls(const struct sk_buff *skb, static enum flow_dissect_ret __skb_flow_dissect_arp(const struct sk_buff *skb, struct flow_dissector *flow_dissector, - void *target_container, void *data, int nhoff, int hlen) + void *target_container, const void *data, + int nhoff, int hlen) { struct flow_dissector_key_arp *key_arp; struct { @@ -523,7 +524,7 @@ static enum flow_dissect_ret __skb_flow_dissect_gre(const struct sk_buff *skb, struct flow_dissector_key_control *key_control, struct flow_dissector *flow_dissector, - void *target_container, void *data, + void *target_container, const void *data, __be16 *p_proto, int *p_nhoff, int *p_hlen, unsigned int flags) { @@ -663,8 +664,8 @@ __skb_flow_dissect_gre(const struct sk_buff *skb, static enum flow_dissect_ret __skb_flow_dissect_batadv(const struct sk_buff *skb, struct flow_dissector_key_control *key_control, - void *data, __be16 *p_proto, int *p_nhoff, int hlen, - unsigned int flags) + const void *data, __be16 *p_proto, int *p_nhoff, + int hlen, unsigned int flags) { struct { struct batadv_unicast_packet batadv_unicast; @@ -695,7 +696,8 @@ __skb_flow_dissect_batadv(const struct sk_buff *skb, static void __skb_flow_dissect_tcp(const struct sk_buff *skb, struct flow_dissector *flow_dissector, - void *target_container, void *data, int thoff, int hlen) + void *target_container, const void *data, + int thoff, int hlen) { struct flow_dissector_key_tcp *key_tcp; struct tcphdr *th, _th; @@ -719,8 +721,8 @@ __skb_flow_dissect_tcp(const struct sk_buff *skb, static void __skb_flow_dissect_ports(const struct sk_buff *skb, struct flow_dissector *flow_dissector, - void *target_container, void *data, int nhoff, - u8 ip_proto, int hlen) + void *target_container, const void *data, + int nhoff, u8 ip_proto, int hlen) { enum flow_dissector_key_id dissector_ports = FLOW_DISSECTOR_KEY_MAX; struct flow_dissector_key_ports *key_ports; @@ -744,7 +746,8 @@ __skb_flow_dissect_ports(const struct sk_buff *skb, static void __skb_flow_dissect_ipv4(const struct sk_buff *skb, struct flow_dissector *flow_dissector, - void *target_container, void *data, const struct iphdr *iph) + void *target_container, const void *data, + const struct iphdr *iph) { struct flow_dissector_key_ip *key_ip; @@ -761,7 +764,8 @@ __skb_flow_dissect_ipv4(const struct sk_buff *skb, static void __skb_flow_dissect_ipv6(const struct sk_buff *skb, struct flow_dissector *flow_dissector, - void *target_container, void *data, const struct ipv6hdr *iph) + void *target_container, const void *data, + const struct ipv6hdr *iph) { struct flow_dissector_key_ip *key_ip; @@ -908,9 +912,8 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, bool __skb_flow_dissect(const struct net *net, const struct sk_buff *skb, struct flow_dissector *flow_dissector, - void *target_container, - void *data, __be16 proto, int nhoff, int hlen, - unsigned int flags) + void *target_container, const void *data, + __be16 proto, int nhoff, int hlen, unsigned int flags) { struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; @@ -1642,7 +1645,7 @@ __u32 skb_get_hash_perturb(const struct sk_buff *skb, } EXPORT_SYMBOL(skb_get_hash_perturb); -u32 __skb_get_poff(const struct sk_buff *skb, void *data, +u32 __skb_get_poff(const struct sk_buff *skb, const void *data, const struct flow_keys_basic *keys, int hlen) { u32 poff = keys->control.thoff; diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index c714e6a9dad4..d8b9dbabd4a4 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -10,9 +10,6 @@ #define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1)) #define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o)) -extern struct list_head ptype_all __read_mostly; -extern struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; - static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 307628fdf380..f6197774048b 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1361,83 +1361,94 @@ static const struct attribute_group dql_group = { #endif /* CONFIG_BQL */ #ifdef CONFIG_XPS -static ssize_t xps_cpus_show(struct netdev_queue *queue, - char *buf) +static ssize_t xps_queue_show(struct net_device *dev, unsigned int index, + int tc, char *buf, enum xps_map_type type) { - int cpu, len, ret, num_tc = 1, tc = 0; - struct net_device *dev = queue->dev; struct xps_dev_maps *dev_maps; - cpumask_var_t mask; - unsigned long index; - - if (!netif_is_multiqueue(dev)) - return -ENOENT; + unsigned long *mask; + unsigned int nr_ids; + int j, len; - index = get_netdev_queue_index(queue); + rcu_read_lock(); + dev_maps = rcu_dereference(dev->xps_maps[type]); - if (!rtnl_trylock()) - return restart_syscall(); + /* Default to nr_cpu_ids/dev->num_rx_queues and do not just return 0 + * when dev_maps hasn't been allocated yet, to be backward compatible. + */ + nr_ids = dev_maps ? dev_maps->nr_ids : + (type == XPS_CPUS ? nr_cpu_ids : dev->num_rx_queues); - if (dev->num_tc) { - /* Do not allow XPS on subordinate device directly */ - num_tc = dev->num_tc; - if (num_tc < 0) { - ret = -EINVAL; - goto err_rtnl_unlock; - } + mask = bitmap_zalloc(nr_ids, GFP_NOWAIT); + if (!mask) { + rcu_read_unlock(); + return -ENOMEM; + } - /* If queue belongs to subordinate dev use its map */ - dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; + if (!dev_maps || tc >= dev_maps->num_tc) + goto out_no_maps; - tc = netdev_txq_to_tc(dev, index); - if (tc < 0) { - ret = -EINVAL; - goto err_rtnl_unlock; - } - } + for (j = 0; j < nr_ids; j++) { + int i, tci = j * dev_maps->num_tc + tc; + struct xps_map *map; - if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) { - ret = -ENOMEM; - goto err_rtnl_unlock; - } + map = rcu_dereference(dev_maps->attr_map[tci]); + if (!map) + continue; - rcu_read_lock(); - dev_maps = rcu_dereference(dev->xps_cpus_map); - if (dev_maps) { - for_each_possible_cpu(cpu) { - int i, tci = cpu * num_tc + tc; - struct xps_map *map; - - map = rcu_dereference(dev_maps->attr_map[tci]); - if (!map) - continue; - - for (i = map->len; i--;) { - if (map->queues[i] == index) { - cpumask_set_cpu(cpu, mask); - break; - } + for (i = map->len; i--;) { + if (map->queues[i] == index) { + set_bit(j, mask); + break; } } } +out_no_maps: rcu_read_unlock(); - rtnl_unlock(); + len = bitmap_print_to_pagebuf(false, buf, mask, nr_ids); + bitmap_free(mask); - len = snprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask)); - free_cpumask_var(mask); return len < PAGE_SIZE ? len : -EINVAL; +} + +static ssize_t xps_cpus_show(struct netdev_queue *queue, char *buf) +{ + struct net_device *dev = queue->dev; + unsigned int index; + int len, tc; + + if (!netif_is_multiqueue(dev)) + return -ENOENT; -err_rtnl_unlock: + index = get_netdev_queue_index(queue); + + if (!rtnl_trylock()) + return restart_syscall(); + + /* If queue belongs to subordinate dev use its map */ + dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; + + tc = netdev_txq_to_tc(dev, index); + if (tc < 0) { + rtnl_unlock(); + return -EINVAL; + } + + /* Make sure the subordinate device can't be freed */ + get_device(&dev->dev); rtnl_unlock(); - return ret; + + len = xps_queue_show(dev, index, tc, buf, XPS_CPUS); + + put_device(&dev->dev); + return len; } static ssize_t xps_cpus_store(struct netdev_queue *queue, const char *buf, size_t len) { struct net_device *dev = queue->dev; - unsigned long index; + unsigned int index; cpumask_var_t mask; int err; @@ -1476,64 +1487,21 @@ static struct netdev_queue_attribute xps_cpus_attribute __ro_after_init static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf) { - int j, len, ret, num_tc = 1, tc = 0; struct net_device *dev = queue->dev; - struct xps_dev_maps *dev_maps; - unsigned long *mask, index; + unsigned int index; + int tc; index = get_netdev_queue_index(queue); if (!rtnl_trylock()) return restart_syscall(); - if (dev->num_tc) { - num_tc = dev->num_tc; - tc = netdev_txq_to_tc(dev, index); - if (tc < 0) { - ret = -EINVAL; - goto err_rtnl_unlock; - } - } - mask = bitmap_zalloc(dev->num_rx_queues, GFP_KERNEL); - if (!mask) { - ret = -ENOMEM; - goto err_rtnl_unlock; - } - - rcu_read_lock(); - dev_maps = rcu_dereference(dev->xps_rxqs_map); - if (!dev_maps) - goto out_no_maps; - - for (j = -1; j = netif_attrmask_next(j, NULL, dev->num_rx_queues), - j < dev->num_rx_queues;) { - int i, tci = j * num_tc + tc; - struct xps_map *map; - - map = rcu_dereference(dev_maps->attr_map[tci]); - if (!map) - continue; - - for (i = map->len; i--;) { - if (map->queues[i] == index) { - set_bit(j, mask); - break; - } - } - } -out_no_maps: - rcu_read_unlock(); - + tc = netdev_txq_to_tc(dev, index); rtnl_unlock(); + if (tc < 0) + return -EINVAL; - len = bitmap_print_to_pagebuf(false, buf, mask, dev->num_rx_queues); - bitmap_free(mask); - - return len < PAGE_SIZE ? len : -EINVAL; - -err_rtnl_unlock: - rtnl_unlock(); - return ret; + return xps_queue_show(dev, index, tc, buf, XPS_RXQS); } static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf, @@ -1541,7 +1509,8 @@ static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf, { struct net_device *dev = queue->dev; struct net *net = dev_net(dev); - unsigned long *mask, index; + unsigned long *mask; + unsigned int index; int err; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) @@ -1565,7 +1534,7 @@ static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf, } cpus_read_lock(); - err = __netif_set_xps_queue(dev, mask, index, true); + err = __netif_set_xps_queue(dev, mask, index, XPS_RXQS); cpus_read_unlock(); rtnl_unlock(); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c421c8f80925..e8320b5d651a 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3732,13 +3732,13 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, unsigned int tnl_hlen = skb_tnl_header_len(skb); unsigned int delta_truesize = 0; unsigned int delta_len = 0; - struct sk_buff *tail = NULL; struct sk_buff *nskb, *tmp; int err; skb_push(skb, -skb_network_offset(skb) + offset); skb_shinfo(skb)->frag_list = NULL; + skb->next = list_skb; do { nskb = list_skb; @@ -3756,17 +3756,8 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, } } - if (!tail) - skb->next = nskb; - else - tail->next = nskb; - - if (unlikely(err)) { - nskb->next = list_skb; + if (unlikely(err)) goto err_linearize; - } - - tail = nskb; delta_len += nskb->len; delta_truesize += nskb->truesize; @@ -3793,7 +3784,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, skb_gso_reset(skb); - skb->prev = tail; + skb->prev = nskb; if (skb_needs_linearize(skb, features) && __skb_linearize(skb)) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 1261512d6807..07f54015238a 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -525,7 +525,8 @@ static void sk_psock_backlog(struct work_struct *work) len = skb->len; off = 0; start: - ingress = tcp_skb_bpf_ingress(skb); + ingress = skb_bpf_ingress(skb); + skb_bpf_redirect_clear(skb); do { ret = -EIO; if (likely(psock->sk->sk_socket)) @@ -618,7 +619,7 @@ struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock) return link; } -void __sk_psock_purge_ingress_msg(struct sk_psock *psock) +static void __sk_psock_purge_ingress_msg(struct sk_psock *psock) { struct sk_msg *msg, *tmp; @@ -631,7 +632,12 @@ void __sk_psock_purge_ingress_msg(struct sk_psock *psock) static void sk_psock_zap_ingress(struct sk_psock *psock) { - __skb_queue_purge(&psock->ingress_skb); + struct sk_buff *skb; + + while ((skb = __skb_dequeue(&psock->ingress_skb)) != NULL) { + skb_bpf_redirect_clear(skb); + kfree_skb(skb); + } __sk_psock_purge_ingress_msg(psock); } @@ -645,15 +651,15 @@ static void sk_psock_link_destroy(struct sk_psock *psock) } } +static void sk_psock_done_strp(struct sk_psock *psock); + static void sk_psock_destroy_deferred(struct work_struct *gc) { struct sk_psock *psock = container_of(gc, struct sk_psock, gc); /* No sk_callback_lock since already detached. */ - /* Parser has been stopped */ - if (psock->progs.skb_parser) - strp_done(&psock->parser.strp); + sk_psock_done_strp(psock); cancel_work_sync(&psock->work); @@ -685,9 +691,9 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock) write_lock_bh(&sk->sk_callback_lock); sk_psock_restore_proto(sk, psock); rcu_assign_sk_user_data(sk, NULL); - if (psock->progs.skb_parser) + if (psock->progs.stream_parser) sk_psock_stop_strp(sk, psock); - else if (psock->progs.skb_verdict) + else if (psock->progs.stream_verdict) sk_psock_stop_verdict(sk, psock); write_unlock_bh(&sk->sk_callback_lock); sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); @@ -743,27 +749,12 @@ out: } EXPORT_SYMBOL_GPL(sk_psock_msg_verdict); -static int sk_psock_bpf_run(struct sk_psock *psock, struct bpf_prog *prog, - struct sk_buff *skb) -{ - bpf_compute_data_end_sk_skb(skb); - return bpf_prog_run_pin_on_cpu(prog, skb); -} - -static struct sk_psock *sk_psock_from_strp(struct strparser *strp) -{ - struct sk_psock_parser *parser; - - parser = container_of(strp, struct sk_psock_parser, strp); - return container_of(parser, struct sk_psock, parser); -} - static void sk_psock_skb_redirect(struct sk_buff *skb) { struct sk_psock *psock_other; struct sock *sk_other; - sk_other = tcp_skb_bpf_redirect_fetch(skb); + sk_other = skb_bpf_redirect_fetch(skb); /* This error is a buggy BPF program, it returned a redirect * return code, but then didn't set a redirect interface. */ @@ -806,16 +797,17 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb) int ret = __SK_PASS; rcu_read_lock(); - prog = READ_ONCE(psock->progs.skb_verdict); + prog = READ_ONCE(psock->progs.stream_verdict); if (likely(prog)) { /* We skip full set_owner_r here because if we do a SK_PASS * or SK_DROP we can skip skb memory accounting and use the * TLS context. */ skb->sk = psock->sk; - tcp_skb_bpf_redirect_clear(skb); - ret = sk_psock_bpf_run(psock, prog, skb); - ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); + skb_dst_drop(skb); + skb_bpf_redirect_clear(skb); + ret = bpf_prog_run_pin_on_cpu(prog, skb); + ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); skb->sk = NULL; } sk_psock_tls_verdict_apply(skb, psock->sk, ret); @@ -827,7 +819,6 @@ EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read); static void sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, int verdict) { - struct tcp_skb_cb *tcp; struct sock *sk_other; int err = -EIO; @@ -839,8 +830,7 @@ static void sk_psock_verdict_apply(struct sk_psock *psock, goto out_free; } - tcp = TCP_SKB_CB(skb); - tcp->bpf.flags |= BPF_F_INGRESS; + skb_bpf_set_ingress(skb); /* If the queue is empty then we can submit directly * into the msg queue. If its not empty we have to @@ -866,6 +856,24 @@ out_free: } } +static void sk_psock_write_space(struct sock *sk) +{ + struct sk_psock *psock; + void (*write_space)(struct sock *sk) = NULL; + + rcu_read_lock(); + psock = sk_psock(sk); + if (likely(psock)) { + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + schedule_work(&psock->work); + write_space = psock->saved_write_space; + } + rcu_read_unlock(); + if (write_space) + write_space(sk); +} + +#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) { struct sk_psock *psock; @@ -881,11 +889,12 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) goto out; } skb_set_owner_r(skb, sk); - prog = READ_ONCE(psock->progs.skb_verdict); + prog = READ_ONCE(psock->progs.stream_verdict); if (likely(prog)) { - tcp_skb_bpf_redirect_clear(skb); - ret = sk_psock_bpf_run(psock, prog, skb); - ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); + skb_dst_drop(skb); + skb_bpf_redirect_clear(skb); + ret = bpf_prog_run_pin_on_cpu(prog, skb); + ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); } sk_psock_verdict_apply(psock, skb, ret); out: @@ -899,15 +908,15 @@ static int sk_psock_strp_read_done(struct strparser *strp, int err) static int sk_psock_strp_parse(struct strparser *strp, struct sk_buff *skb) { - struct sk_psock *psock = sk_psock_from_strp(strp); + struct sk_psock *psock = container_of(strp, struct sk_psock, strp); struct bpf_prog *prog; int ret = skb->len; rcu_read_lock(); - prog = READ_ONCE(psock->progs.skb_parser); + prog = READ_ONCE(psock->progs.stream_parser); if (likely(prog)) { skb->sk = psock->sk; - ret = sk_psock_bpf_run(psock, prog, skb); + ret = bpf_prog_run_pin_on_cpu(prog, skb); skb->sk = NULL; } rcu_read_unlock(); @@ -923,16 +932,59 @@ static void sk_psock_strp_data_ready(struct sock *sk) psock = sk_psock(sk); if (likely(psock)) { if (tls_sw_has_ctx_rx(sk)) { - psock->parser.saved_data_ready(sk); + psock->saved_data_ready(sk); } else { write_lock_bh(&sk->sk_callback_lock); - strp_data_ready(&psock->parser.strp); + strp_data_ready(&psock->strp); write_unlock_bh(&sk->sk_callback_lock); } } rcu_read_unlock(); } +int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) +{ + static const struct strp_callbacks cb = { + .rcv_msg = sk_psock_strp_read, + .read_sock_done = sk_psock_strp_read_done, + .parse_msg = sk_psock_strp_parse, + }; + + return strp_init(&psock->strp, sk, &cb); +} + +void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) +{ + if (psock->saved_data_ready) + return; + + psock->saved_data_ready = sk->sk_data_ready; + sk->sk_data_ready = sk_psock_strp_data_ready; + sk->sk_write_space = sk_psock_write_space; +} + +void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) +{ + if (!psock->saved_data_ready) + return; + + sk->sk_data_ready = psock->saved_data_ready; + psock->saved_data_ready = NULL; + strp_stop(&psock->strp); +} + +static void sk_psock_done_strp(struct sk_psock *psock) +{ + /* Parser has been stopped */ + if (psock->progs.stream_parser) + strp_done(&psock->strp); +} +#else +static void sk_psock_done_strp(struct sk_psock *psock) +{ +} +#endif /* CONFIG_BPF_STREAM_PARSER */ + static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb, unsigned int offset, size_t orig_len) { @@ -957,11 +1009,12 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb, goto out; } skb_set_owner_r(skb, sk); - prog = READ_ONCE(psock->progs.skb_verdict); + prog = READ_ONCE(psock->progs.stream_verdict); if (likely(prog)) { - tcp_skb_bpf_redirect_clear(skb); - ret = sk_psock_bpf_run(psock, prog, skb); - ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); + skb_dst_drop(skb); + skb_bpf_redirect_clear(skb); + ret = bpf_prog_run_pin_on_cpu(prog, skb); + ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); } sk_psock_verdict_apply(psock, skb, ret); out: @@ -984,82 +1037,21 @@ static void sk_psock_verdict_data_ready(struct sock *sk) sock->ops->read_sock(sk, &desc, sk_psock_verdict_recv); } -static void sk_psock_write_space(struct sock *sk) -{ - struct sk_psock *psock; - void (*write_space)(struct sock *sk) = NULL; - - rcu_read_lock(); - psock = sk_psock(sk); - if (likely(psock)) { - if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) - schedule_work(&psock->work); - write_space = psock->saved_write_space; - } - rcu_read_unlock(); - if (write_space) - write_space(sk); -} - -int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) -{ - static const struct strp_callbacks cb = { - .rcv_msg = sk_psock_strp_read, - .read_sock_done = sk_psock_strp_read_done, - .parse_msg = sk_psock_strp_parse, - }; - - psock->parser.enabled = false; - return strp_init(&psock->parser.strp, sk, &cb); -} - void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock) { - struct sk_psock_parser *parser = &psock->parser; - - if (parser->enabled) + if (psock->saved_data_ready) return; - parser->saved_data_ready = sk->sk_data_ready; + psock->saved_data_ready = sk->sk_data_ready; sk->sk_data_ready = sk_psock_verdict_data_ready; sk->sk_write_space = sk_psock_write_space; - parser->enabled = true; -} - -void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) -{ - struct sk_psock_parser *parser = &psock->parser; - - if (parser->enabled) - return; - - parser->saved_data_ready = sk->sk_data_ready; - sk->sk_data_ready = sk_psock_strp_data_ready; - sk->sk_write_space = sk_psock_write_space; - parser->enabled = true; -} - -void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) -{ - struct sk_psock_parser *parser = &psock->parser; - - if (!parser->enabled) - return; - - sk->sk_data_ready = parser->saved_data_ready; - parser->saved_data_ready = NULL; - strp_stop(&parser->strp); - parser->enabled = false; } void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock) { - struct sk_psock_parser *parser = &psock->parser; - - if (!parser->enabled) + if (!psock->saved_data_ready) return; - sk->sk_data_ready = parser->saved_data_ready; - parser->saved_data_ready = NULL; - parser->enabled = false; + sk->sk_data_ready = psock->saved_data_ready; + psock->saved_data_ready = NULL; } diff --git a/net/core/sock_map.c b/net/core/sock_map.c index d758fb83c884..dd53a7771d7e 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -24,6 +24,9 @@ struct bpf_stab { #define SOCK_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) +static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, + struct bpf_prog *old, u32 which); + static struct bpf_map *sock_map_alloc(union bpf_attr *attr) { struct bpf_stab *stab; @@ -148,9 +151,9 @@ static void sock_map_del_link(struct sock *sk, struct bpf_map *map = link->map; struct bpf_stab *stab = container_of(map, struct bpf_stab, map); - if (psock->parser.enabled && stab->progs.skb_parser) + if (psock->saved_data_ready && stab->progs.stream_parser) strp_stop = true; - if (psock->parser.enabled && stab->progs.skb_verdict) + if (psock->saved_data_ready && stab->progs.stream_verdict) verdict_stop = true; list_del(&link->list); sk_psock_free_link(link); @@ -224,23 +227,23 @@ out: static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs, struct sock *sk) { - struct bpf_prog *msg_parser, *skb_parser, *skb_verdict; + struct bpf_prog *msg_parser, *stream_parser, *stream_verdict; struct sk_psock *psock; int ret; - skb_verdict = READ_ONCE(progs->skb_verdict); - if (skb_verdict) { - skb_verdict = bpf_prog_inc_not_zero(skb_verdict); - if (IS_ERR(skb_verdict)) - return PTR_ERR(skb_verdict); + stream_verdict = READ_ONCE(progs->stream_verdict); + if (stream_verdict) { + stream_verdict = bpf_prog_inc_not_zero(stream_verdict); + if (IS_ERR(stream_verdict)) + return PTR_ERR(stream_verdict); } - skb_parser = READ_ONCE(progs->skb_parser); - if (skb_parser) { - skb_parser = bpf_prog_inc_not_zero(skb_parser); - if (IS_ERR(skb_parser)) { - ret = PTR_ERR(skb_parser); - goto out_put_skb_verdict; + stream_parser = READ_ONCE(progs->stream_parser); + if (stream_parser) { + stream_parser = bpf_prog_inc_not_zero(stream_parser); + if (IS_ERR(stream_parser)) { + ret = PTR_ERR(stream_parser); + goto out_put_stream_verdict; } } @@ -249,7 +252,7 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs, msg_parser = bpf_prog_inc_not_zero(msg_parser); if (IS_ERR(msg_parser)) { ret = PTR_ERR(msg_parser); - goto out_put_skb_parser; + goto out_put_stream_parser; } } @@ -261,8 +264,8 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs, if (psock) { if ((msg_parser && READ_ONCE(psock->progs.msg_parser)) || - (skb_parser && READ_ONCE(psock->progs.skb_parser)) || - (skb_verdict && READ_ONCE(psock->progs.skb_verdict))) { + (stream_parser && READ_ONCE(psock->progs.stream_parser)) || + (stream_verdict && READ_ONCE(psock->progs.stream_verdict))) { sk_psock_put(sk, psock); ret = -EBUSY; goto out_progs; @@ -283,15 +286,15 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs, goto out_drop; write_lock_bh(&sk->sk_callback_lock); - if (skb_parser && skb_verdict && !psock->parser.enabled) { + if (stream_parser && stream_verdict && !psock->saved_data_ready) { ret = sk_psock_init_strp(sk, psock); if (ret) goto out_unlock_drop; - psock_set_prog(&psock->progs.skb_verdict, skb_verdict); - psock_set_prog(&psock->progs.skb_parser, skb_parser); + psock_set_prog(&psock->progs.stream_verdict, stream_verdict); + psock_set_prog(&psock->progs.stream_parser, stream_parser); sk_psock_start_strp(sk, psock); - } else if (!skb_parser && skb_verdict && !psock->parser.enabled) { - psock_set_prog(&psock->progs.skb_verdict, skb_verdict); + } else if (!stream_parser && stream_verdict && !psock->saved_data_ready) { + psock_set_prog(&psock->progs.stream_verdict, stream_verdict); sk_psock_start_verdict(sk,psock); } write_unlock_bh(&sk->sk_callback_lock); @@ -303,12 +306,12 @@ out_drop: out_progs: if (msg_parser) bpf_prog_put(msg_parser); -out_put_skb_parser: - if (skb_parser) - bpf_prog_put(skb_parser); -out_put_skb_verdict: - if (skb_verdict) - bpf_prog_put(skb_verdict); +out_put_stream_parser: + if (stream_parser) + bpf_prog_put(stream_parser); +out_put_stream_verdict: + if (stream_verdict) + bpf_prog_put(stream_verdict); return ret; } @@ -657,7 +660,6 @@ const struct bpf_func_proto bpf_sock_map_update_proto = { BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb, struct bpf_map *, map, u32, key, u64, flags) { - struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); struct sock *sk; if (unlikely(flags & ~(BPF_F_INGRESS))) @@ -667,8 +669,7 @@ BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb, if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; - tcb->bpf.flags = flags; - tcb->bpf.sk_redir = sk; + skb_bpf_set_redir(skb, sk, flags & BPF_F_INGRESS); return SK_PASS; } @@ -1250,7 +1251,6 @@ const struct bpf_func_proto bpf_sock_hash_update_proto = { BPF_CALL_4(bpf_sk_redirect_hash, struct sk_buff *, skb, struct bpf_map *, map, void *, key, u64, flags) { - struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); struct sock *sk; if (unlikely(flags & ~(BPF_F_INGRESS))) @@ -1260,8 +1260,7 @@ BPF_CALL_4(bpf_sk_redirect_hash, struct sk_buff *, skb, if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; - tcb->bpf.flags = flags; - tcb->bpf.sk_redir = sk; + skb_bpf_set_redir(skb, sk, flags & BPF_F_INGRESS); return SK_PASS; } @@ -1448,8 +1447,8 @@ static struct sk_psock_progs *sock_map_progs(struct bpf_map *map) return NULL; } -int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, - struct bpf_prog *old, u32 which) +static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, + struct bpf_prog *old, u32 which) { struct sk_psock_progs *progs = sock_map_progs(map); struct bpf_prog **pprog; @@ -1461,11 +1460,13 @@ int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, case BPF_SK_MSG_VERDICT: pprog = &progs->msg_parser; break; +#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) case BPF_SK_SKB_STREAM_PARSER: - pprog = &progs->skb_parser; + pprog = &progs->stream_parser; break; +#endif case BPF_SK_SKB_STREAM_VERDICT: - pprog = &progs->skb_verdict; + pprog = &progs->stream_verdict; break; default: return -EOPNOTSUPP; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 4567de519603..d84c8a1b280e 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -24,6 +24,7 @@ static int two = 2; static int three = 3; +static int int_3600 = 3600; static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; static int max_skb_frags = MAX_SKB_FRAGS; @@ -570,6 +571,15 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, }, + { + .procname = "netdev_unregister_timeout_secs", + .data = &netdev_unregister_timeout_secs, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &int_3600, + }, { } }; diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 2193ae529e75..32b1bed8ae51 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -84,8 +84,7 @@ #include <net/dn_neigh.h> #include <net/dn_fib.h> -struct dn_rt_hash_bucket -{ +struct dn_rt_hash_bucket { struct dn_route __rcu *chain; spinlock_t lock; }; @@ -93,7 +92,7 @@ struct dn_rt_hash_bucket extern struct neigh_table dn_neigh_table; -static unsigned char dn_hiord_addr[6] = {0xAA,0x00,0x04,0x00,0x00,0x00}; +static unsigned char dn_hiord_addr[6] = {0xAA, 0x00, 0x04, 0x00, 0x00, 0x00}; static const int dn_rt_min_delay = 2 * HZ; static const int dn_rt_max_delay = 10 * HZ; @@ -359,10 +358,11 @@ static void dn_run_flush(struct timer_list *unused) for (i = 0; i < dn_rt_hash_mask; i++) { spin_lock_bh(&dn_rt_hash_table[i].lock); - if ((rt = xchg((struct dn_route **)&dn_rt_hash_table[i].chain, NULL)) == NULL) + rt = xchg((struct dn_route **)&dn_rt_hash_table[i].chain, NULL); + if (!rt) goto nothing_to_declare; - for(; rt; rt = next) { + for (; rt; rt = next) { next = rcu_dereference_raw(rt->dn_next); RCU_INIT_POINTER(rt->dn_next, NULL); dst_dev_put(&rt->dst); @@ -425,7 +425,8 @@ static int dn_return_short(struct sk_buff *skb) /* Add back headers */ skb_push(skb, skb->data - skb_network_header(skb)); - if ((skb = skb_unshare(skb, GFP_ATOMIC)) == NULL) + skb = skb_unshare(skb, GFP_ATOMIC); + if (!skb) return NET_RX_DROP; cb = DN_SKB_CB(skb); @@ -461,7 +462,8 @@ static int dn_return_long(struct sk_buff *skb) /* Add back all headers */ skb_push(skb, skb->data - skb_network_header(skb)); - if ((skb = skb_unshare(skb, GFP_ATOMIC)) == NULL) + skb = skb_unshare(skb, GFP_ATOMIC); + if (!skb) return NET_RX_DROP; cb = DN_SKB_CB(skb); @@ -505,7 +507,8 @@ static int dn_route_rx_packet(struct net *net, struct sock *sk, struct sk_buff * struct dn_skb_cb *cb; int err; - if ((err = dn_route_input(skb)) == 0) + err = dn_route_input(skb); + if (err == 0) return dst_input(skb); cb = DN_SKB_CB(skb); @@ -629,7 +632,8 @@ int dn_route_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type if (dn == NULL) goto dump_it; - if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) goto out; if (!pskb_may_pull(skb, 3)) @@ -898,7 +902,7 @@ static inline int dn_match_addr(__le16 addr1, __le16 addr2) { __u16 tmp = le16_to_cpu(addr1) ^ le16_to_cpu(addr2); int match = 16; - while(tmp) { + while (tmp) { tmp >>= 1; match--; } @@ -1324,7 +1328,8 @@ static int dn_route_input_slow(struct sk_buff *skb) dev_hold(in_dev); - if ((dn_db = rcu_dereference(in_dev->dn_ptr)) == NULL) + dn_db = rcu_dereference(in_dev->dn_ptr); + if (!dn_db) goto out; /* Zero source addresses are not allowed */ @@ -1383,7 +1388,7 @@ static int dn_route_input_slow(struct sk_buff *skb) fld.saddr = src_map; } - switch(res.type) { + switch (res.type) { case RTN_UNICAST: /* * Forwarding check here, we only check for forwarding @@ -1407,7 +1412,7 @@ static int dn_route_input_slow(struct sk_buff *skb) flags |= RTCF_DOREDIRECT; local_src = DN_FIB_RES_PREFSRC(res); - + break; case RTN_BLACKHOLE: case RTN_UNREACHABLE: break; @@ -1526,7 +1531,7 @@ static int dn_route_input(struct sk_buff *skb) return 0; rcu_read_lock(); - for(rt = rcu_dereference(dn_rt_hash_table[hash].chain); rt != NULL; + for (rt = rcu_dereference(dn_rt_hash_table[hash].chain); rt != NULL; rt = rcu_dereference(rt->dn_next)) { if ((rt->fld.saddr == cb->src) && (rt->fld.daddr == cb->dst) && @@ -1739,13 +1744,13 @@ int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb) s_h = cb->args[0]; s_idx = idx = cb->args[1]; - for(h = 0; h <= dn_rt_hash_mask; h++) { + for (h = 0; h <= dn_rt_hash_mask; h++) { if (h < s_h) continue; if (h > s_h) s_idx = 0; rcu_read_lock_bh(); - for(rt = rcu_dereference_bh(dn_rt_hash_table[h].chain), idx = 0; + for (rt = rcu_dereference_bh(dn_rt_hash_table[h].chain), idx = 0; rt; rt = rcu_dereference_bh(rt->dn_next), idx++) { if (idx < s_idx) @@ -1779,7 +1784,7 @@ static struct dn_route *dn_rt_cache_get_first(struct seq_file *seq) struct dn_route *rt = NULL; struct dn_rt_cache_iter_state *s = seq->private; - for(s->bucket = dn_rt_hash_mask; s->bucket >= 0; --s->bucket) { + for (s->bucket = dn_rt_hash_mask; s->bucket >= 0; --s->bucket) { rcu_read_lock_bh(); rt = rcu_dereference_bh(dn_rt_hash_table[s->bucket].chain); if (rt) @@ -1809,7 +1814,7 @@ static void *dn_rt_cache_seq_start(struct seq_file *seq, loff_t *pos) struct dn_route *rt = dn_rt_cache_get_first(seq); if (rt) { - while(*pos && (rt = dn_rt_cache_get_next(seq, rt))) + while (*pos && (rt = dn_rt_cache_get_next(seq, rt))) --*pos; } return *pos ? NULL : rt; @@ -1864,21 +1869,21 @@ void __init dn_route_init(void) goal = totalram_pages() >> (26 - PAGE_SHIFT); - for(order = 0; (1UL << order) < goal; order++) + for (order = 0; (1UL << order) < goal; order++) /* NOTHING */; /* * Only want 1024 entries max, since the table is very, very unlikely * to be larger than that. */ - while(order && ((((1UL << order) * PAGE_SIZE) / + while (order && ((((1UL << order) * PAGE_SIZE) / sizeof(struct dn_rt_hash_bucket)) >= 2048)) order--; do { dn_rt_hash_mask = (1UL << order) * PAGE_SIZE / sizeof(struct dn_rt_hash_bucket); - while(dn_rt_hash_mask & (dn_rt_hash_mask - 1)) + while (dn_rt_hash_mask & (dn_rt_hash_mask - 1)) dn_rt_hash_mask--; dn_rt_hash_table = (struct dn_rt_hash_bucket *) __get_free_pages(GFP_ATOMIC, order); @@ -1893,7 +1898,7 @@ void __init dn_route_init(void) (long)(dn_rt_hash_mask*sizeof(struct dn_rt_hash_bucket))/1024); dn_rt_hash_mask--; - for(i = 0; i <= dn_rt_hash_mask; i++) { + for (i = 0; i <= dn_rt_hash_mask; i++) { spin_lock_init(&dn_rt_hash_table[i].lock); dn_rt_hash_table[i].chain = NULL; } diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 58b8fc82cd3c..8746b07668ae 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -1,15 +1,10 @@ # SPDX-License-Identifier: GPL-2.0-only -config HAVE_NET_DSA - def_bool y - depends on INET && NETDEVICES && !S390 - -# Drivers must select NET_DSA and the appropriate tagging format menuconfig NET_DSA tristate "Distributed Switch Architecture" - depends on HAVE_NET_DSA depends on BRIDGE || BRIDGE=n depends on HSR || HSR=n + depends on INET && NETDEVICES select GRO_CELLS select NET_SWITCHDEV select PHYLINK @@ -20,7 +15,8 @@ menuconfig NET_DSA if NET_DSA -# tagging formats +# Drivers must select the appropriate tagging format(s) + config NET_DSA_TAG_8021Q tristate select VLAN_8021Q @@ -48,6 +44,13 @@ config NET_DSA_TAG_BRCM Say Y if you want to enable support for tagging frames for the Broadcom switches which place the tag after the MAC source address. +config NET_DSA_TAG_BRCM_LEGACY + tristate "Tag driver for Broadcom legacy switches using in-frame headers" + select NET_DSA_TAG_BRCM_COMMON + help + Say Y if you want to enable support for tagging frames for the + Broadcom legacy switches which place the tag after the MAC source + address. config NET_DSA_TAG_BRCM_PREPEND tristate "Tag driver for Broadcom switches using prepended headers" diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 9d4b0e9b1aa1..92282de54230 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -181,12 +181,14 @@ int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy); int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy); void dsa_port_disable_rt(struct dsa_port *dp); void dsa_port_disable(struct dsa_port *dp); -int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br); +int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, + struct netlink_ext_ack *extack); void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br); int dsa_port_lag_change(struct dsa_port *dp, struct netdev_lag_lower_state_info *linfo); int dsa_port_lag_join(struct dsa_port *dp, struct net_device *lag_dev, - struct netdev_lag_upper_info *uinfo); + struct netdev_lag_upper_info *uinfo, + struct netlink_ext_ack *extack); void dsa_port_lag_leave(struct dsa_port *dp, struct net_device *lag_dev); int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, struct netlink_ext_ack *extack); @@ -233,19 +235,7 @@ extern const struct phylink_mac_ops dsa_port_phylink_mac_ops; static inline bool dsa_port_offloads_bridge_port(struct dsa_port *dp, struct net_device *dev) { - /* Switchdev offloading can be configured on: */ - - if (dev == dp->slave) - /* DSA ports directly connected to a bridge, and event - * was emitted for the ports themselves. - */ - return true; - - if (dp->lag_dev == dev) - /* DSA ports connected to a bridge via a LAG */ - return true; - - return false; + return dsa_port_to_bridge_port(dp) == dev; } static inline bool dsa_port_offloads_bridge(struct dsa_port *dp, @@ -272,6 +262,9 @@ static inline bool dsa_tree_offloads_bridge_port(struct dsa_switch_tree *dst, /* slave.c */ extern const struct dsa_device_ops notag_netdev_ops; +extern struct notifier_block dsa_slave_switchdev_notifier; +extern struct notifier_block dsa_slave_switchdev_blocking_notifier; + void dsa_slave_mii_bus_init(struct dsa_switch *ds); int dsa_slave_create(struct dsa_port *dp); void dsa_slave_destroy(struct net_device *slave_dev); diff --git a/net/dsa/port.c b/net/dsa/port.c index c9c6d7ab3f47..01e30264b25b 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -122,29 +122,132 @@ void dsa_port_disable(struct dsa_port *dp) rtnl_unlock(); } -static void dsa_port_change_brport_flags(struct dsa_port *dp, - bool bridge_offload) +static int dsa_port_inherit_brport_flags(struct dsa_port *dp, + struct netlink_ext_ack *extack) { - struct switchdev_brport_flags flags; - int flag; + const unsigned long mask = BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD | + BR_BCAST_FLOOD; + struct net_device *brport_dev = dsa_port_to_bridge_port(dp); + int flag, err; - flags.mask = BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD | BR_BCAST_FLOOD; - if (bridge_offload) - flags.val = flags.mask; - else - flags.val = flags.mask & ~BR_LEARNING; + for_each_set_bit(flag, &mask, 32) { + struct switchdev_brport_flags flags = {0}; + + flags.mask = BIT(flag); + + if (br_port_flag_is_set(brport_dev, BIT(flag))) + flags.val = BIT(flag); - for_each_set_bit(flag, &flags.mask, 32) { - struct switchdev_brport_flags tmp; + err = dsa_port_bridge_flags(dp, flags, extack); + if (err && err != -EOPNOTSUPP) + return err; + } - tmp.val = flags.val & BIT(flag); - tmp.mask = BIT(flag); + return 0; +} - dsa_port_bridge_flags(dp, tmp, NULL); +static void dsa_port_clear_brport_flags(struct dsa_port *dp) +{ + const unsigned long val = BR_FLOOD | BR_MCAST_FLOOD | BR_BCAST_FLOOD; + const unsigned long mask = BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD | + BR_BCAST_FLOOD; + int flag, err; + + for_each_set_bit(flag, &mask, 32) { + struct switchdev_brport_flags flags = {0}; + + flags.mask = BIT(flag); + flags.val = val & BIT(flag); + + err = dsa_port_bridge_flags(dp, flags, NULL); + if (err && err != -EOPNOTSUPP) + dev_err(dp->ds->dev, + "failed to clear bridge port flag %lu: %pe\n", + flags.val, ERR_PTR(err)); } } -int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br) +static int dsa_port_switchdev_sync(struct dsa_port *dp, + struct netlink_ext_ack *extack) +{ + struct net_device *brport_dev = dsa_port_to_bridge_port(dp); + struct net_device *br = dp->bridge_dev; + int err; + + err = dsa_port_inherit_brport_flags(dp, extack); + if (err) + return err; + + err = dsa_port_set_state(dp, br_port_get_stp_state(brport_dev)); + if (err && err != -EOPNOTSUPP) + return err; + + err = dsa_port_vlan_filtering(dp, br_vlan_enabled(br), extack); + if (err && err != -EOPNOTSUPP) + return err; + + err = dsa_port_mrouter(dp->cpu_dp, br_multicast_router(br), extack); + if (err && err != -EOPNOTSUPP) + return err; + + err = dsa_port_ageing_time(dp, br_get_ageing_time(br)); + if (err && err != -EOPNOTSUPP) + return err; + + err = br_mdb_replay(br, brport_dev, + &dsa_slave_switchdev_blocking_notifier, + extack); + if (err && err != -EOPNOTSUPP) + return err; + + err = br_fdb_replay(br, brport_dev, &dsa_slave_switchdev_notifier); + if (err && err != -EOPNOTSUPP) + return err; + + err = br_vlan_replay(br, brport_dev, + &dsa_slave_switchdev_blocking_notifier, + extack); + if (err && err != -EOPNOTSUPP) + return err; + + return 0; +} + +static void dsa_port_switchdev_unsync(struct dsa_port *dp) +{ + /* Configure the port for standalone mode (no address learning, + * flood everything). + * The bridge only emits SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS events + * when the user requests it through netlink or sysfs, but not + * automatically at port join or leave, so we need to handle resetting + * the brport flags ourselves. But we even prefer it that way, because + * otherwise, some setups might never get the notification they need, + * for example, when a port leaves a LAG that offloads the bridge, + * it becomes standalone, but as far as the bridge is concerned, no + * port ever left. + */ + dsa_port_clear_brport_flags(dp); + + /* Port left the bridge, put in BR_STATE_DISABLED by the bridge layer, + * so allow it to be in BR_STATE_FORWARDING to be kept functional + */ + dsa_port_set_state_now(dp, BR_STATE_FORWARDING); + + /* VLAN filtering is handled by dsa_switch_bridge_leave */ + + /* Some drivers treat the notification for having a local multicast + * router by allowing multicast to be flooded to the CPU, so we should + * allow this in standalone mode too. + */ + dsa_port_mrouter(dp->cpu_dp, true, NULL); + + /* Ageing time may be global to the switch chip, so don't change it + * here because we have no good reason (or value) to change it to. + */ +} + +int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, + struct netlink_ext_ack *extack) { struct dsa_notifier_bridge_info info = { .tree_index = dp->ds->dst->index, @@ -154,24 +257,25 @@ int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br) }; int err; - /* Notify the port driver to set its configurable flags in a way that - * matches the initial settings of a bridge port. - */ - dsa_port_change_brport_flags(dp, true); - /* Here the interface is already bridged. Reflect the current * configuration so that drivers can program their chips accordingly. */ dp->bridge_dev = br; err = dsa_broadcast(DSA_NOTIFIER_BRIDGE_JOIN, &info); + if (err) + goto out_rollback; - /* The bridging is rolled back on error */ - if (err) { - dsa_port_change_brport_flags(dp, false); - dp->bridge_dev = NULL; - } + err = dsa_port_switchdev_sync(dp, extack); + if (err) + goto out_rollback_unbridge; + return 0; + +out_rollback_unbridge: + dsa_broadcast(DSA_NOTIFIER_BRIDGE_LEAVE, &info); +out_rollback: + dp->bridge_dev = NULL; return err; } @@ -194,23 +298,7 @@ void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br) if (err) pr_err("DSA: failed to notify DSA_NOTIFIER_BRIDGE_LEAVE\n"); - /* Configure the port for standalone mode (no address learning, - * flood everything). - * The bridge only emits SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS events - * when the user requests it through netlink or sysfs, but not - * automatically at port join or leave, so we need to handle resetting - * the brport flags ourselves. But we even prefer it that way, because - * otherwise, some setups might never get the notification they need, - * for example, when a port leaves a LAG that offloads the bridge, - * it becomes standalone, but as far as the bridge is concerned, no - * port ever left. - */ - dsa_port_change_brport_flags(dp, false); - - /* Port left the bridge, put in BR_STATE_DISABLED by the bridge layer, - * so allow it to be in BR_STATE_FORWARDING to be kept functional - */ - dsa_port_set_state_now(dp, BR_STATE_FORWARDING); + dsa_port_switchdev_unsync(dp); } int dsa_port_lag_change(struct dsa_port *dp, @@ -241,7 +329,8 @@ int dsa_port_lag_change(struct dsa_port *dp, } int dsa_port_lag_join(struct dsa_port *dp, struct net_device *lag, - struct netdev_lag_upper_info *uinfo) + struct netdev_lag_upper_info *uinfo, + struct netlink_ext_ack *extack) { struct dsa_notifier_lag_info info = { .sw_index = dp->ds->index, @@ -249,17 +338,31 @@ int dsa_port_lag_join(struct dsa_port *dp, struct net_device *lag, .lag = lag, .info = uinfo, }; + struct net_device *bridge_dev; int err; dsa_lag_map(dp->ds->dst, lag); dp->lag_dev = lag; err = dsa_port_notify(dp, DSA_NOTIFIER_LAG_JOIN, &info); - if (err) { - dp->lag_dev = NULL; - dsa_lag_unmap(dp->ds->dst, lag); - } + if (err) + goto err_lag_join; + bridge_dev = netdev_master_upper_dev_get(lag); + if (!bridge_dev || !netif_is_bridge_master(bridge_dev)) + return 0; + + err = dsa_port_bridge_join(dp, bridge_dev, extack); + if (err) + goto err_bridge_join; + + return 0; + +err_bridge_join: + dsa_port_notify(dp, DSA_NOTIFIER_LAG_LEAVE, &info); +err_lag_join: + dp->lag_dev = NULL; + dsa_lag_unmap(dp->ds->dst, lag); return err; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 992fcab4b552..995e0e16f295 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1278,14 +1278,32 @@ static int dsa_slave_setup_tc_block(struct net_device *dev, } } +static int dsa_slave_setup_ft_block(struct dsa_switch *ds, int port, + void *type_data) +{ + struct dsa_port *cpu_dp = dsa_to_port(ds, port)->cpu_dp; + struct net_device *master = cpu_dp->master; + + if (!master->netdev_ops->ndo_setup_tc) + return -EOPNOTSUPP; + + return master->netdev_ops->ndo_setup_tc(master, TC_SETUP_FT, type_data); +} + static int dsa_slave_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_switch *ds = dp->ds; - if (type == TC_SETUP_BLOCK) + switch (type) { + case TC_SETUP_BLOCK: return dsa_slave_setup_tc_block(dev, type_data); + case TC_SETUP_FT: + return dsa_slave_setup_ft_block(ds, dp->index, type_data); + default: + break; + } if (!ds->ops->port_setup_tc) return -EOPNOTSUPP; @@ -1654,6 +1672,21 @@ static void dsa_slave_get_stats64(struct net_device *dev, dev_get_tstats64(dev, s); } +static int dsa_slave_fill_forward_path(struct net_device_path_ctx *ctx, + struct net_device_path *path) +{ + struct dsa_port *dp = dsa_slave_to_port(ctx->dev); + struct dsa_port *cpu_dp = dp->cpu_dp; + + path->dev = ctx->dev; + path->type = DEV_PATH_DSA; + path->dsa.proto = cpu_dp->tag_ops->proto; + path->dsa.port = dp->index; + ctx->dev = cpu_dp->master; + + return 0; +} + static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_open = dsa_slave_open, .ndo_stop = dsa_slave_close, @@ -1679,6 +1712,7 @@ static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_vlan_rx_kill_vid = dsa_slave_vlan_rx_kill_vid, .ndo_get_devlink_port = dsa_slave_get_devlink_port, .ndo_change_mtu = dsa_slave_change_mtu, + .ndo_fill_forward_path = dsa_slave_fill_forward_path, }; static struct device_type dsa_type = { @@ -1976,11 +2010,14 @@ static int dsa_slave_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct dsa_port *dp = dsa_slave_to_port(dev); + struct netlink_ext_ack *extack; int err = NOTIFY_DONE; + extack = netdev_notifier_info_to_extack(&info->info); + if (netif_is_bridge_master(info->upper_dev)) { if (info->linking) { - err = dsa_port_bridge_join(dp, info->upper_dev); + err = dsa_port_bridge_join(dp, info->upper_dev, extack); if (!err) dsa_bridge_mtu_normalization(dp); err = notifier_from_errno(err); @@ -1991,7 +2028,7 @@ static int dsa_slave_changeupper(struct net_device *dev, } else if (netif_is_lag_master(info->upper_dev)) { if (info->linking) { err = dsa_port_lag_join(dp, info->upper_dev, - info->upper_info); + info->upper_info, extack); if (err == -EOPNOTSUPP) { NL_SET_ERR_MSG_MOD(info->info.extack, "Offloading not supported"); @@ -2389,11 +2426,11 @@ static struct notifier_block dsa_slave_nb __read_mostly = { .notifier_call = dsa_slave_netdevice_event, }; -static struct notifier_block dsa_slave_switchdev_notifier = { +struct notifier_block dsa_slave_switchdev_notifier = { .notifier_call = dsa_slave_switchdev_event, }; -static struct notifier_block dsa_slave_switchdev_blocking_notifier = { +struct notifier_block dsa_slave_switchdev_blocking_notifier = { .notifier_call = dsa_slave_switchdev_blocking_event, }; diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index e2577a7dcbca..40e9f3098c8d 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -12,9 +12,26 @@ #include "dsa_priv.h" -/* This tag length is 4 bytes, older ones were 6 bytes, we do not - * handle them - */ +/* Legacy Broadcom tag (6 bytes) */ +#define BRCM_LEG_TAG_LEN 6 + +/* Type fields */ +/* 1st byte in the tag */ +#define BRCM_LEG_TYPE_HI 0x88 +/* 2nd byte in the tag */ +#define BRCM_LEG_TYPE_LO 0x74 + +/* Tag fields */ +/* 3rd byte in the tag */ +#define BRCM_LEG_UNICAST (0 << 5) +#define BRCM_LEG_MULTICAST (1 << 5) +#define BRCM_LEG_EGRESS (2 << 5) +#define BRCM_LEG_INGRESS (3 << 5) + +/* 6th byte in the tag */ +#define BRCM_LEG_PORT_ID (0xf) + +/* Newer Broadcom tag (4 bytes) */ #define BRCM_TAG_LEN 4 /* Tag is constructed and desconstructed using byte by byte access @@ -195,6 +212,87 @@ DSA_TAG_DRIVER(brcm_netdev_ops); MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM); #endif +#if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_LEGACY) +static struct sk_buff *brcm_leg_tag_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + u8 *brcm_tag; + + /* The Ethernet switch we are interfaced with needs packets to be at + * least 64 bytes (including FCS) otherwise they will be discarded when + * they enter the switch port logic. When Broadcom tags are enabled, we + * need to make sure that packets are at least 70 bytes + * (including FCS and tag) because the length verification is done after + * the Broadcom tag is stripped off the ingress packet. + * + * Let dsa_slave_xmit() free the SKB + */ + if (__skb_put_padto(skb, ETH_ZLEN + BRCM_LEG_TAG_LEN, false)) + return NULL; + + skb_push(skb, BRCM_LEG_TAG_LEN); + + memmove(skb->data, skb->data + BRCM_LEG_TAG_LEN, 2 * ETH_ALEN); + + brcm_tag = skb->data + 2 * ETH_ALEN; + + /* Broadcom tag type */ + brcm_tag[0] = BRCM_LEG_TYPE_HI; + brcm_tag[1] = BRCM_LEG_TYPE_LO; + + /* Broadcom tag value */ + brcm_tag[2] = BRCM_LEG_EGRESS; + brcm_tag[3] = 0; + brcm_tag[4] = 0; + brcm_tag[5] = dp->index & BRCM_LEG_PORT_ID; + + return skb; +} + +static struct sk_buff *brcm_leg_tag_rcv(struct sk_buff *skb, + struct net_device *dev, + struct packet_type *pt) +{ + int source_port; + u8 *brcm_tag; + + if (unlikely(!pskb_may_pull(skb, BRCM_LEG_PORT_ID))) + return NULL; + + brcm_tag = skb->data - 2; + + source_port = brcm_tag[5] & BRCM_LEG_PORT_ID; + + skb->dev = dsa_master_find_slave(dev, 0, source_port); + if (!skb->dev) + return NULL; + + /* Remove Broadcom tag and update checksum */ + skb_pull_rcsum(skb, BRCM_LEG_TAG_LEN); + + skb->offload_fwd_mark = 1; + + /* Move the Ethernet DA and SA */ + memmove(skb->data - ETH_HLEN, + skb->data - ETH_HLEN - BRCM_LEG_TAG_LEN, + 2 * ETH_ALEN); + + return skb; +} + +static const struct dsa_device_ops brcm_legacy_netdev_ops = { + .name = "brcm-legacy", + .proto = DSA_TAG_PROTO_BRCM_LEGACY, + .xmit = brcm_leg_tag_xmit, + .rcv = brcm_leg_tag_rcv, + .overhead = BRCM_LEG_TAG_LEN, +}; + +DSA_TAG_DRIVER(brcm_legacy_netdev_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM_LEGACY); +#endif /* CONFIG_NET_DSA_TAG_BRCM_LEGACY */ + #if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_PREPEND) static struct sk_buff *brcm_tag_xmit_prepend(struct sk_buff *skb, struct net_device *dev) @@ -227,6 +325,9 @@ static struct dsa_tag_driver *dsa_tag_driver_array[] = { #if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM) &DSA_TAG_DRIVER_NAME(brcm_netdev_ops), #endif +#if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_LEGACY) + &DSA_TAG_DRIVER_NAME(brcm_legacy_netdev_ops), +#endif #if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_PREPEND) &DSA_TAG_DRIVER_NAME(brcm_prepend_netdev_ops), #endif diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index 59748487664f..f9b2966d1936 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -24,9 +24,6 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, struct dsa_port *dp = dsa_slave_to_port(dev); u8 xmit_tpid; u8 *mtk_tag; - unsigned char *dest = eth_hdr(skb)->h_dest; - bool is_multicast_skb = is_multicast_ether_addr(dest) && - !is_broadcast_ether_addr(dest); /* Build the special tag after the MAC Source Address. If VLAN header * is present, it's required that VLAN header and special tag is @@ -55,10 +52,6 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, mtk_tag[0] = xmit_tpid; mtk_tag[1] = (1 << dp->index) & MTK_HDR_XMIT_DP_BIT_MASK; - /* Disable SA learning for multicast frames */ - if (unlikely(is_multicast_skb)) - mtk_tag[1] |= MTK_HDR_XMIT_SA_DIS; - /* Tag control information is kept for 802.1Q */ if (xmit_tpid == MTK_HDR_XMIT_UNTAGGED) { mtk_tag[2] = 0; @@ -74,9 +67,6 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, u16 hdr; int port; __be16 *phdr; - unsigned char *dest = eth_hdr(skb)->h_dest; - bool is_multicast_skb = is_multicast_ether_addr(dest) && - !is_broadcast_ether_addr(dest); if (unlikely(!pskb_may_pull(skb, MTK_HDR_LEN))) return NULL; @@ -102,9 +92,7 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, if (!skb->dev) return NULL; - /* Only unicast or broadcast frames are offloaded */ - if (likely(!is_multicast_skb)) - skb->offload_fwd_mark = 1; + skb->offload_fwd_mark = 1; return skb; } diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index 743809b5806b..f9df9cac81c5 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -83,7 +83,6 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, struct dsa_port *dp; u8 *extraction; u16 vlan_tpid; - u64 cpuq; /* Revert skb->data by the amount consumed by the DSA master, * so it points to the beginning of the frame. @@ -113,7 +112,6 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, ocelot_xfh_get_qos_class(extraction, &qos_class); ocelot_xfh_get_tag_type(extraction, &tag_type); ocelot_xfh_get_vlan_tci(extraction, &vlan_tci); - ocelot_xfh_get_cpuq(extraction, &cpuq); skb->dev = dsa_master_find_slave(netdev, 0, src_port); if (!skb->dev) @@ -128,12 +126,6 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, skb->offload_fwd_mark = 1; skb->priority = qos_class; -#if IS_ENABLED(CONFIG_BRIDGE_MRP) - if (eth_hdr(skb)->h_proto == cpu_to_be16(ETH_P_MRP) && - cpuq & BIT(OCELOT_MRP_CPUQ)) - skb->offload_fwd_mark = 0; -#endif - /* Ocelot switches copy frames unmodified to the CPU. However, it is * possible for the user to request a VLAN modification through * VCAP_IS1_ACT_VID_REPLACE_ENA. In this case, what will happen is that diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 4106373180c6..933b427122be 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -58,6 +58,7 @@ #include <net/ip.h> #include <net/dsa.h> #include <net/flow_dissector.h> +#include <net/gro.h> #include <linux/uaccess.h> #include <net/pkt_sched.h> @@ -122,7 +123,7 @@ EXPORT_SYMBOL(eth_header); * Make a best effort attempt to pull the length for all of the headers for * a given frame in a linear buffer. */ -u32 eth_get_headlen(const struct net_device *dev, void *data, unsigned int len) +u32 eth_get_headlen(const struct net_device *dev, const void *data, u32 len) { const unsigned int flags = FLOW_DISSECTOR_F_PARSE_1ST_FRAG; const struct ethhdr *eth = (const struct ethhdr *)data; @@ -449,7 +450,10 @@ struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb) skb_gro_pull(skb, sizeof(*eh)); skb_gro_postpull_rcsum(skb, eh, sizeof(*eh)); - pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); + + pp = indirect_call_gro_receive_inet(ptype->callbacks.gro_receive, + ipv6_gro_receive, inet_gro_receive, + head, skb); out_unlock: rcu_read_unlock(); @@ -473,8 +477,9 @@ int eth_gro_complete(struct sk_buff *skb, int nhoff) rcu_read_lock(); ptype = gro_find_complete_by_type(type); if (ptype != NULL) - err = ptype->callbacks.gro_complete(skb, nhoff + - sizeof(struct ethhdr)); + err = INDIRECT_CALL_INET(ptype->callbacks.gro_complete, + ipv6_gro_complete, inet_gro_complete, + skb, nhoff + sizeof(*eh)); rcu_read_unlock(); return err; diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 24783b71c584..0788cc3b3114 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1844,6 +1844,18 @@ out: return ret; } +__printf(2, 3) void ethtool_sprintf(u8 **data, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + vsnprintf(*data, ETH_GSTRING_LEN, fmt, args); + va_end(args); + + *data += ETH_GSTRING_LEN; +} +EXPORT_SYMBOL(ethtool_sprintf); + static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) { struct ethtool_value id; diff --git a/net/hsr/hsr_debugfs.c b/net/hsr/hsr_debugfs.c index 4cfd9e829c7b..99f3af1a9d4d 100644 --- a/net/hsr/hsr_debugfs.c +++ b/net/hsr/hsr_debugfs.c @@ -108,7 +108,7 @@ void hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev) /* hsr_debugfs_term - Tear down debugfs intrastructure * * Description: - * When Debufs is configured this routine removes debugfs file system + * When Debugfs is configured this routine removes debugfs file system * elements that are specific to hsr */ void diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 5b77a46885b9..bbdd9c44f14e 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -62,7 +62,7 @@ obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o obj-$(CONFIG_NET_SOCK_MSG) += tcp_bpf.o -obj-$(CONFIG_BPF_STREAM_PARSER) += udp_bpf.o +obj-$(CONFIG_BPF_SYSCALL) += udp_bpf.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 743777bce179..f09fe3a5608f 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -16,6 +16,9 @@ #include <net/route.h> #include <net/sock.h> +#define NH_RES_DEFAULT_IDLE_TIMER (120 * HZ) +#define NH_RES_DEFAULT_UNBALANCED_TIMER 0 /* No forced rebalancing. */ + static void remove_nexthop(struct net *net, struct nexthop *nh, struct nl_info *nlinfo); @@ -32,6 +35,7 @@ static const struct nla_policy rtm_nh_policy_new[] = { [NHA_ENCAP_TYPE] = { .type = NLA_U16 }, [NHA_ENCAP] = { .type = NLA_NESTED }, [NHA_FDB] = { .type = NLA_FLAG }, + [NHA_RES_GROUP] = { .type = NLA_NESTED }, }; static const struct nla_policy rtm_nh_policy_get[] = { @@ -45,6 +49,32 @@ static const struct nla_policy rtm_nh_policy_dump[] = { [NHA_FDB] = { .type = NLA_FLAG }, }; +static const struct nla_policy rtm_nh_res_policy_new[] = { + [NHA_RES_GROUP_BUCKETS] = { .type = NLA_U16 }, + [NHA_RES_GROUP_IDLE_TIMER] = { .type = NLA_U32 }, + [NHA_RES_GROUP_UNBALANCED_TIMER] = { .type = NLA_U32 }, +}; + +static const struct nla_policy rtm_nh_policy_dump_bucket[] = { + [NHA_ID] = { .type = NLA_U32 }, + [NHA_OIF] = { .type = NLA_U32 }, + [NHA_MASTER] = { .type = NLA_U32 }, + [NHA_RES_BUCKET] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy rtm_nh_res_bucket_policy_dump[] = { + [NHA_RES_BUCKET_NH_ID] = { .type = NLA_U32 }, +}; + +static const struct nla_policy rtm_nh_policy_get_bucket[] = { + [NHA_ID] = { .type = NLA_U32 }, + [NHA_RES_BUCKET] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy rtm_nh_res_bucket_policy_get[] = { + [NHA_RES_BUCKET_INDEX] = { .type = NLA_U16 }, +}; + static bool nexthop_notifiers_is_empty(struct net *net) { return !net->nexthop.notifier_chain.head; @@ -52,10 +82,8 @@ static bool nexthop_notifiers_is_empty(struct net *net) static void __nh_notifier_single_info_init(struct nh_notifier_single_info *nh_info, - const struct nexthop *nh) + const struct nh_info *nhi) { - struct nh_info *nhi = rtnl_dereference(nh->nh_info); - nh_info->dev = nhi->fib_nhc.nhc_dev; nh_info->gw_family = nhi->fib_nhc.nhc_gw_family; if (nh_info->gw_family == AF_INET) @@ -71,12 +99,14 @@ __nh_notifier_single_info_init(struct nh_notifier_single_info *nh_info, static int nh_notifier_single_info_init(struct nh_notifier_info *info, const struct nexthop *nh) { + struct nh_info *nhi = rtnl_dereference(nh->nh_info); + info->type = NH_NOTIFIER_INFO_TYPE_SINGLE; info->nh = kzalloc(sizeof(*info->nh), GFP_KERNEL); if (!info->nh) return -ENOMEM; - __nh_notifier_single_info_init(info->nh, nh); + __nh_notifier_single_info_init(info->nh, nhi); return 0; } @@ -103,11 +133,44 @@ static int nh_notifier_mp_info_init(struct nh_notifier_info *info, for (i = 0; i < num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; + struct nh_info *nhi; + nhi = rtnl_dereference(nhge->nh->nh_info); info->nh_grp->nh_entries[i].id = nhge->nh->id; info->nh_grp->nh_entries[i].weight = nhge->weight; __nh_notifier_single_info_init(&info->nh_grp->nh_entries[i].nh, - nhge->nh); + nhi); + } + + return 0; +} + +static int nh_notifier_res_table_info_init(struct nh_notifier_info *info, + struct nh_group *nhg) +{ + struct nh_res_table *res_table = rtnl_dereference(nhg->res_table); + u16 num_nh_buckets = res_table->num_nh_buckets; + unsigned long size; + u16 i; + + info->type = NH_NOTIFIER_INFO_TYPE_RES_TABLE; + size = struct_size(info->nh_res_table, nhs, num_nh_buckets); + info->nh_res_table = __vmalloc(size, GFP_KERNEL | __GFP_ZERO | + __GFP_NOWARN); + if (!info->nh_res_table) + return -ENOMEM; + + info->nh_res_table->num_nh_buckets = num_nh_buckets; + + for (i = 0; i < num_nh_buckets; i++) { + struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; + struct nh_grp_entry *nhge; + struct nh_info *nhi; + + nhge = rtnl_dereference(bucket->nh_entry); + nhi = rtnl_dereference(nhge->nh->nh_info); + __nh_notifier_single_info_init(&info->nh_res_table->nhs[i], + nhi); } return 0; @@ -120,6 +183,8 @@ static int nh_notifier_grp_info_init(struct nh_notifier_info *info, if (nhg->mpath) return nh_notifier_mp_info_init(info, nhg); + else if (nhg->resilient) + return nh_notifier_res_table_info_init(info, nhg); return -EINVAL; } @@ -130,6 +195,8 @@ static void nh_notifier_grp_info_fini(struct nh_notifier_info *info, if (nhg->mpath) kfree(info->nh_grp); + else if (nhg->resilient) + vfree(info->nh_res_table); } static int nh_notifier_info_init(struct nh_notifier_info *info, @@ -181,6 +248,178 @@ static int call_nexthop_notifiers(struct net *net, return notifier_to_errno(err); } +static int +nh_notifier_res_bucket_idle_timer_get(const struct nh_notifier_info *info, + bool force, unsigned int *p_idle_timer_ms) +{ + struct nh_res_table *res_table; + struct nh_group *nhg; + struct nexthop *nh; + int err = 0; + + /* When 'force' is false, nexthop bucket replacement is performed + * because the bucket was deemed to be idle. In this case, capable + * listeners can choose to perform an atomic replacement: The bucket is + * only replaced if it is inactive. However, if the idle timer interval + * is smaller than the interval in which a listener is querying + * buckets' activity from the device, then atomic replacement should + * not be tried. Pass the idle timer value to listeners, so that they + * could determine which type of replacement to perform. + */ + if (force) { + *p_idle_timer_ms = 0; + return 0; + } + + rcu_read_lock(); + + nh = nexthop_find_by_id(info->net, info->id); + if (!nh) { + err = -EINVAL; + goto out; + } + + nhg = rcu_dereference(nh->nh_grp); + res_table = rcu_dereference(nhg->res_table); + *p_idle_timer_ms = jiffies_to_msecs(res_table->idle_timer); + +out: + rcu_read_unlock(); + + return err; +} + +static int nh_notifier_res_bucket_info_init(struct nh_notifier_info *info, + u16 bucket_index, bool force, + struct nh_info *oldi, + struct nh_info *newi) +{ + unsigned int idle_timer_ms; + int err; + + err = nh_notifier_res_bucket_idle_timer_get(info, force, + &idle_timer_ms); + if (err) + return err; + + info->type = NH_NOTIFIER_INFO_TYPE_RES_BUCKET; + info->nh_res_bucket = kzalloc(sizeof(*info->nh_res_bucket), + GFP_KERNEL); + if (!info->nh_res_bucket) + return -ENOMEM; + + info->nh_res_bucket->bucket_index = bucket_index; + info->nh_res_bucket->idle_timer_ms = idle_timer_ms; + info->nh_res_bucket->force = force; + __nh_notifier_single_info_init(&info->nh_res_bucket->old_nh, oldi); + __nh_notifier_single_info_init(&info->nh_res_bucket->new_nh, newi); + return 0; +} + +static void nh_notifier_res_bucket_info_fini(struct nh_notifier_info *info) +{ + kfree(info->nh_res_bucket); +} + +static int __call_nexthop_res_bucket_notifiers(struct net *net, u32 nhg_id, + u16 bucket_index, bool force, + struct nh_info *oldi, + struct nh_info *newi, + struct netlink_ext_ack *extack) +{ + struct nh_notifier_info info = { + .net = net, + .extack = extack, + .id = nhg_id, + }; + int err; + + if (nexthop_notifiers_is_empty(net)) + return 0; + + err = nh_notifier_res_bucket_info_init(&info, bucket_index, force, + oldi, newi); + if (err) + return err; + + err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, + NEXTHOP_EVENT_BUCKET_REPLACE, &info); + nh_notifier_res_bucket_info_fini(&info); + + return notifier_to_errno(err); +} + +/* There are three users of RES_TABLE, and NHs etc. referenced from there: + * + * 1) a collection of callbacks for NH maintenance. This operates under + * RTNL, + * 2) the delayed work that gradually balances the resilient table, + * 3) and nexthop_select_path(), operating under RCU. + * + * Both the delayed work and the RTNL block are writers, and need to + * maintain mutual exclusion. Since there are only two and well-known + * writers for each table, the RTNL code can make sure it has exclusive + * access thus: + * + * - Have the DW operate without locking; + * - synchronously cancel the DW; + * - do the writing; + * - if the write was not actually a delete, call upkeep, which schedules + * DW again if necessary. + * + * The functions that are always called from the RTNL context use + * rtnl_dereference(). The functions that can also be called from the DW do + * a raw dereference and rely on the above mutual exclusion scheme. + */ +#define nh_res_dereference(p) (rcu_dereference_raw(p)) + +static int call_nexthop_res_bucket_notifiers(struct net *net, u32 nhg_id, + u16 bucket_index, bool force, + struct nexthop *old_nh, + struct nexthop *new_nh, + struct netlink_ext_ack *extack) +{ + struct nh_info *oldi = nh_res_dereference(old_nh->nh_info); + struct nh_info *newi = nh_res_dereference(new_nh->nh_info); + + return __call_nexthop_res_bucket_notifiers(net, nhg_id, bucket_index, + force, oldi, newi, extack); +} + +static int call_nexthop_res_table_notifiers(struct net *net, struct nexthop *nh, + struct netlink_ext_ack *extack) +{ + struct nh_notifier_info info = { + .net = net, + .extack = extack, + }; + struct nh_group *nhg; + int err; + + ASSERT_RTNL(); + + if (nexthop_notifiers_is_empty(net)) + return 0; + + /* At this point, the nexthop buckets are still not populated. Only + * emit a notification with the logical nexthops, so that a listener + * could potentially veto it in case of unsupported configuration. + */ + nhg = rtnl_dereference(nh->nh_grp); + err = nh_notifier_mp_info_init(&info, nhg); + if (err) { + NL_SET_ERR_MSG(extack, "Failed to initialize nexthop notifier info"); + return err; + } + + err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, + NEXTHOP_EVENT_RES_TABLE_PRE_REPLACE, + &info); + kfree(info.nh_grp); + + return notifier_to_errno(err); +} + static int call_nexthop_notifier(struct notifier_block *nb, struct net *net, enum nexthop_event_type event_type, struct nexthop *nh, @@ -239,6 +478,9 @@ static void nexthop_free_group(struct nexthop *nh) WARN_ON(nhg->spare == nhg); + if (nhg->resilient) + vfree(rcu_dereference_raw(nhg->res_table)); + kfree(nhg->spare); kfree(nhg); } @@ -297,6 +539,30 @@ static struct nh_group *nexthop_grp_alloc(u16 num_nh) return nhg; } +static void nh_res_table_upkeep_dw(struct work_struct *work); + +static struct nh_res_table * +nexthop_res_table_alloc(struct net *net, u32 nhg_id, struct nh_config *cfg) +{ + const u16 num_nh_buckets = cfg->nh_grp_res_num_buckets; + struct nh_res_table *res_table; + unsigned long size; + + size = struct_size(res_table, nh_buckets, num_nh_buckets); + res_table = __vmalloc(size, GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN); + if (!res_table) + return NULL; + + res_table->net = net; + res_table->nhg_id = nhg_id; + INIT_DELAYED_WORK(&res_table->upkeep_dw, &nh_res_table_upkeep_dw); + INIT_LIST_HEAD(&res_table->uw_nh_entries); + res_table->idle_timer = cfg->nh_grp_res_idle_timer; + res_table->unbalanced_timer = cfg->nh_grp_res_unbalanced_timer; + res_table->num_nh_buckets = num_nh_buckets; + return res_table; +} + static void nh_base_seq_inc(struct net *net) { while (++net->nexthop.seq == 0) @@ -345,6 +611,48 @@ static u32 nh_find_unused_id(struct net *net) return 0; } +static void nh_res_time_set_deadline(unsigned long next_time, + unsigned long *deadline) +{ + if (time_before(next_time, *deadline)) + *deadline = next_time; +} + +static clock_t nh_res_table_unbalanced_time(struct nh_res_table *res_table) +{ + if (list_empty(&res_table->uw_nh_entries)) + return 0; + return jiffies_delta_to_clock_t(jiffies - res_table->unbalanced_since); +} + +static int nla_put_nh_group_res(struct sk_buff *skb, struct nh_group *nhg) +{ + struct nh_res_table *res_table = rtnl_dereference(nhg->res_table); + struct nlattr *nest; + + nest = nla_nest_start(skb, NHA_RES_GROUP); + if (!nest) + return -EMSGSIZE; + + if (nla_put_u16(skb, NHA_RES_GROUP_BUCKETS, + res_table->num_nh_buckets) || + nla_put_u32(skb, NHA_RES_GROUP_IDLE_TIMER, + jiffies_to_clock_t(res_table->idle_timer)) || + nla_put_u32(skb, NHA_RES_GROUP_UNBALANCED_TIMER, + jiffies_to_clock_t(res_table->unbalanced_timer)) || + nla_put_u64_64bit(skb, NHA_RES_GROUP_UNBALANCED_TIME, + nh_res_table_unbalanced_time(res_table), + NHA_RES_GROUP_PAD)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + static int nla_put_nh_group(struct sk_buff *skb, struct nh_group *nhg) { struct nexthop_grp *p; @@ -355,6 +663,8 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nh_group *nhg) if (nhg->mpath) group_type = NEXTHOP_GRP_TYPE_MPATH; + else if (nhg->resilient) + group_type = NEXTHOP_GRP_TYPE_RES; if (nla_put_u16(skb, NHA_GROUP_TYPE, group_type)) goto nla_put_failure; @@ -370,6 +680,9 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nh_group *nhg) p += 1; } + if (nhg->resilient && nla_put_nh_group_res(skb, nhg)) + goto nla_put_failure; + return 0; nla_put_failure: @@ -457,13 +770,26 @@ nla_put_failure: return -EMSGSIZE; } +static size_t nh_nlmsg_size_grp_res(struct nh_group *nhg) +{ + return nla_total_size(0) + /* NHA_RES_GROUP */ + nla_total_size(2) + /* NHA_RES_GROUP_BUCKETS */ + nla_total_size(4) + /* NHA_RES_GROUP_IDLE_TIMER */ + nla_total_size(4) + /* NHA_RES_GROUP_UNBALANCED_TIMER */ + nla_total_size_64bit(8);/* NHA_RES_GROUP_UNBALANCED_TIME */ +} + static size_t nh_nlmsg_size_grp(struct nexthop *nh) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); size_t sz = sizeof(struct nexthop_grp) * nhg->num_nh; + size_t tot = nla_total_size(sz) + + nla_total_size(2); /* NHA_GROUP_TYPE */ + + if (nhg->resilient) + tot += nh_nlmsg_size_grp_res(nhg); - return nla_total_size(sz) + - nla_total_size(2); /* NHA_GROUP_TYPE */ + return tot; } static size_t nh_nlmsg_size_single(struct nexthop *nh) @@ -538,20 +864,144 @@ errout: rtnl_set_sk_err(info->nl_net, RTNLGRP_NEXTHOP, err); } +static unsigned long nh_res_bucket_used_time(const struct nh_res_bucket *bucket) +{ + return (unsigned long)atomic_long_read(&bucket->used_time); +} + +static unsigned long +nh_res_bucket_idle_point(const struct nh_res_table *res_table, + const struct nh_res_bucket *bucket, + unsigned long now) +{ + unsigned long time = nh_res_bucket_used_time(bucket); + + /* Bucket was not used since it was migrated. The idle time is now. */ + if (time == bucket->migrated_time) + return now; + + return time + res_table->idle_timer; +} + +static unsigned long +nh_res_table_unb_point(const struct nh_res_table *res_table) +{ + return res_table->unbalanced_since + res_table->unbalanced_timer; +} + +static void nh_res_bucket_set_idle(const struct nh_res_table *res_table, + struct nh_res_bucket *bucket) +{ + unsigned long now = jiffies; + + atomic_long_set(&bucket->used_time, (long)now); + bucket->migrated_time = now; +} + +static void nh_res_bucket_set_busy(struct nh_res_bucket *bucket) +{ + atomic_long_set(&bucket->used_time, (long)jiffies); +} + +static clock_t nh_res_bucket_idle_time(const struct nh_res_bucket *bucket) +{ + unsigned long used_time = nh_res_bucket_used_time(bucket); + + return jiffies_delta_to_clock_t(jiffies - used_time); +} + +static int nh_fill_res_bucket(struct sk_buff *skb, struct nexthop *nh, + struct nh_res_bucket *bucket, u16 bucket_index, + int event, u32 portid, u32 seq, + unsigned int nlflags, + struct netlink_ext_ack *extack) +{ + struct nh_grp_entry *nhge = nh_res_dereference(bucket->nh_entry); + struct nlmsghdr *nlh; + struct nlattr *nest; + struct nhmsg *nhm; + + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nhm), nlflags); + if (!nlh) + return -EMSGSIZE; + + nhm = nlmsg_data(nlh); + nhm->nh_family = AF_UNSPEC; + nhm->nh_flags = bucket->nh_flags; + nhm->nh_protocol = nh->protocol; + nhm->nh_scope = 0; + nhm->resvd = 0; + + if (nla_put_u32(skb, NHA_ID, nh->id)) + goto nla_put_failure; + + nest = nla_nest_start(skb, NHA_RES_BUCKET); + if (!nest) + goto nla_put_failure; + + if (nla_put_u16(skb, NHA_RES_BUCKET_INDEX, bucket_index) || + nla_put_u32(skb, NHA_RES_BUCKET_NH_ID, nhge->nh->id) || + nla_put_u64_64bit(skb, NHA_RES_BUCKET_IDLE_TIME, + nh_res_bucket_idle_time(bucket), + NHA_RES_BUCKET_PAD)) + goto nla_put_failure_nest; + + nla_nest_end(skb, nest); + nlmsg_end(skb, nlh); + return 0; + +nla_put_failure_nest: + nla_nest_cancel(skb, nest); +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static void nexthop_bucket_notify(struct nh_res_table *res_table, + u16 bucket_index) +{ + struct nh_res_bucket *bucket = &res_table->nh_buckets[bucket_index]; + struct nh_grp_entry *nhge = nh_res_dereference(bucket->nh_entry); + struct nexthop *nh = nhge->nh_parent; + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) + goto errout; + + err = nh_fill_res_bucket(skb, nh, bucket, bucket_index, + RTM_NEWNEXTHOPBUCKET, 0, 0, NLM_F_REPLACE, + NULL); + if (err < 0) { + kfree_skb(skb); + goto errout; + } + + rtnl_notify(skb, nh->net, 0, RTNLGRP_NEXTHOP, NULL, GFP_KERNEL); + return; +errout: + if (err < 0) + rtnl_set_sk_err(nh->net, RTNLGRP_NEXTHOP, err); +} + static bool valid_group_nh(struct nexthop *nh, unsigned int npaths, bool *is_fdb, struct netlink_ext_ack *extack) { if (nh->is_group) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); - /* nested multipath (group within a group) is not - * supported - */ + /* Nesting groups within groups is not supported. */ if (nhg->mpath) { NL_SET_ERR_MSG(extack, "Multipath group can not be a nexthop within a group"); return false; } + if (nhg->resilient) { + NL_SET_ERR_MSG(extack, + "Resilient group can not be a nexthop within a group"); + return false; + } *is_fdb = nhg->fdb_nh; } else { struct nh_info *nhi = rtnl_dereference(nh->nh_info); @@ -591,7 +1041,7 @@ static int nh_check_attr_fdb_group(struct nexthop *nh, u8 *nh_family, static int nh_check_attr_group(struct net *net, struct nlattr *tb[], size_t tb_size, - struct netlink_ext_ack *extack) + u16 nh_grp_type, struct netlink_ext_ack *extack) { unsigned int len = nla_len(tb[NHA_GROUP]); u8 nh_family = AF_UNSPEC; @@ -652,8 +1102,14 @@ static int nh_check_attr_group(struct net *net, for (i = NHA_GROUP_TYPE + 1; i < tb_size; ++i) { if (!tb[i]) continue; - if (i == NHA_FDB) + switch (i) { + case NHA_FDB: continue; + case NHA_RES_GROUP: + if (nh_grp_type == NEXTHOP_GRP_TYPE_RES) + continue; + break; + } NL_SET_ERR_MSG(extack, "No other attributes can be set in nexthop groups"); return -EINVAL; @@ -732,6 +1188,22 @@ static struct nexthop *nexthop_select_path_mp(struct nh_group *nhg, int hash) return rc; } +static struct nexthop *nexthop_select_path_res(struct nh_group *nhg, int hash) +{ + struct nh_res_table *res_table = rcu_dereference(nhg->res_table); + u16 bucket_index = hash % res_table->num_nh_buckets; + struct nh_res_bucket *bucket; + struct nh_grp_entry *nhge; + + /* nexthop_select_path() is expected to return a non-NULL value, so + * skip protocol validation and just hand out whatever there is. + */ + bucket = &res_table->nh_buckets[bucket_index]; + nh_res_bucket_set_busy(bucket); + nhge = rcu_dereference(bucket->nh_entry); + return nhge->nh; +} + struct nexthop *nexthop_select_path(struct nexthop *nh, int hash) { struct nh_group *nhg; @@ -742,6 +1214,8 @@ struct nexthop *nexthop_select_path(struct nexthop *nh, int hash) nhg = rcu_dereference(nh->nh_grp); if (nhg->mpath) return nexthop_select_path_mp(nhg, hash); + else if (nhg->resilient) + return nexthop_select_path_res(nhg, hash); /* Unreachable. */ return NULL; @@ -924,7 +1398,319 @@ static int fib_check_nh_list(struct nexthop *old, struct nexthop *new, return 0; } -static void nh_group_rebalance(struct nh_group *nhg) +static bool nh_res_nhge_is_balanced(const struct nh_grp_entry *nhge) +{ + return nhge->res.count_buckets == nhge->res.wants_buckets; +} + +static bool nh_res_nhge_is_ow(const struct nh_grp_entry *nhge) +{ + return nhge->res.count_buckets > nhge->res.wants_buckets; +} + +static bool nh_res_nhge_is_uw(const struct nh_grp_entry *nhge) +{ + return nhge->res.count_buckets < nhge->res.wants_buckets; +} + +static bool nh_res_table_is_balanced(const struct nh_res_table *res_table) +{ + return list_empty(&res_table->uw_nh_entries); +} + +static void nh_res_bucket_unset_nh(struct nh_res_bucket *bucket) +{ + struct nh_grp_entry *nhge; + + if (bucket->occupied) { + nhge = nh_res_dereference(bucket->nh_entry); + nhge->res.count_buckets--; + bucket->occupied = false; + } +} + +static void nh_res_bucket_set_nh(struct nh_res_bucket *bucket, + struct nh_grp_entry *nhge) +{ + nh_res_bucket_unset_nh(bucket); + + bucket->occupied = true; + rcu_assign_pointer(bucket->nh_entry, nhge); + nhge->res.count_buckets++; +} + +static bool nh_res_bucket_should_migrate(struct nh_res_table *res_table, + struct nh_res_bucket *bucket, + unsigned long *deadline, bool *force) +{ + unsigned long now = jiffies; + struct nh_grp_entry *nhge; + unsigned long idle_point; + + if (!bucket->occupied) { + /* The bucket is not occupied, its NHGE pointer is either + * NULL or obsolete. We _have to_ migrate: set force. + */ + *force = true; + return true; + } + + nhge = nh_res_dereference(bucket->nh_entry); + + /* If the bucket is populated by an underweight or balanced + * nexthop, do not migrate. + */ + if (!nh_res_nhge_is_ow(nhge)) + return false; + + /* At this point we know that the bucket is populated with an + * overweight nexthop. It needs to be migrated to a new nexthop if + * the idle timer of unbalanced timer expired. + */ + + idle_point = nh_res_bucket_idle_point(res_table, bucket, now); + if (time_after_eq(now, idle_point)) { + /* The bucket is idle. We _can_ migrate: unset force. */ + *force = false; + return true; + } + + /* Unbalanced timer of 0 means "never force". */ + if (res_table->unbalanced_timer) { + unsigned long unb_point; + + unb_point = nh_res_table_unb_point(res_table); + if (time_after(now, unb_point)) { + /* The bucket is not idle, but the unbalanced timer + * expired. We _can_ migrate, but set force anyway, + * so that drivers know to ignore activity reports + * from the HW. + */ + *force = true; + return true; + } + + nh_res_time_set_deadline(unb_point, deadline); + } + + nh_res_time_set_deadline(idle_point, deadline); + return false; +} + +static bool nh_res_bucket_migrate(struct nh_res_table *res_table, + u16 bucket_index, bool notify, + bool notify_nl, bool force) +{ + struct nh_res_bucket *bucket = &res_table->nh_buckets[bucket_index]; + struct nh_grp_entry *new_nhge; + struct netlink_ext_ack extack; + int err; + + new_nhge = list_first_entry_or_null(&res_table->uw_nh_entries, + struct nh_grp_entry, + res.uw_nh_entry); + if (WARN_ON_ONCE(!new_nhge)) + /* If this function is called, "bucket" is either not + * occupied, or it belongs to a next hop that is + * overweight. In either case, there ought to be a + * corresponding underweight next hop. + */ + return false; + + if (notify) { + struct nh_grp_entry *old_nhge; + + old_nhge = nh_res_dereference(bucket->nh_entry); + err = call_nexthop_res_bucket_notifiers(res_table->net, + res_table->nhg_id, + bucket_index, force, + old_nhge->nh, + new_nhge->nh, &extack); + if (err) { + pr_err_ratelimited("%s\n", extack._msg); + if (!force) + return false; + /* It is not possible to veto a forced replacement, so + * just clear the hardware flags from the nexthop + * bucket to indicate to user space that this bucket is + * not correctly populated in hardware. + */ + bucket->nh_flags &= ~(RTNH_F_OFFLOAD | RTNH_F_TRAP); + } + } + + nh_res_bucket_set_nh(bucket, new_nhge); + nh_res_bucket_set_idle(res_table, bucket); + + if (notify_nl) + nexthop_bucket_notify(res_table, bucket_index); + + if (nh_res_nhge_is_balanced(new_nhge)) + list_del(&new_nhge->res.uw_nh_entry); + return true; +} + +#define NH_RES_UPKEEP_DW_MINIMUM_INTERVAL (HZ / 2) + +static void nh_res_table_upkeep(struct nh_res_table *res_table, + bool notify, bool notify_nl) +{ + unsigned long now = jiffies; + unsigned long deadline; + u16 i; + + /* Deadline is the next time that upkeep should be run. It is the + * earliest time at which one of the buckets might be migrated. + * Start at the most pessimistic estimate: either unbalanced_timer + * from now, or if there is none, idle_timer from now. For each + * encountered time point, call nh_res_time_set_deadline() to + * refine the estimate. + */ + if (res_table->unbalanced_timer) + deadline = now + res_table->unbalanced_timer; + else + deadline = now + res_table->idle_timer; + + for (i = 0; i < res_table->num_nh_buckets; i++) { + struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; + bool force; + + if (nh_res_bucket_should_migrate(res_table, bucket, + &deadline, &force)) { + if (!nh_res_bucket_migrate(res_table, i, notify, + notify_nl, force)) { + unsigned long idle_point; + + /* A driver can override the migration + * decision if the HW reports that the + * bucket is actually not idle. Therefore + * remark the bucket as busy again and + * update the deadline. + */ + nh_res_bucket_set_busy(bucket); + idle_point = nh_res_bucket_idle_point(res_table, + bucket, + now); + nh_res_time_set_deadline(idle_point, &deadline); + } + } + } + + /* If the group is still unbalanced, schedule the next upkeep to + * either the deadline computed above, or the minimum deadline, + * whichever comes later. + */ + if (!nh_res_table_is_balanced(res_table)) { + unsigned long now = jiffies; + unsigned long min_deadline; + + min_deadline = now + NH_RES_UPKEEP_DW_MINIMUM_INTERVAL; + if (time_before(deadline, min_deadline)) + deadline = min_deadline; + + queue_delayed_work(system_power_efficient_wq, + &res_table->upkeep_dw, deadline - now); + } +} + +static void nh_res_table_upkeep_dw(struct work_struct *work) +{ + struct delayed_work *dw = to_delayed_work(work); + struct nh_res_table *res_table; + + res_table = container_of(dw, struct nh_res_table, upkeep_dw); + nh_res_table_upkeep(res_table, true, true); +} + +static void nh_res_table_cancel_upkeep(struct nh_res_table *res_table) +{ + cancel_delayed_work_sync(&res_table->upkeep_dw); +} + +static void nh_res_group_rebalance(struct nh_group *nhg, + struct nh_res_table *res_table) +{ + int prev_upper_bound = 0; + int total = 0; + int w = 0; + int i; + + INIT_LIST_HEAD(&res_table->uw_nh_entries); + + for (i = 0; i < nhg->num_nh; ++i) + total += nhg->nh_entries[i].weight; + + for (i = 0; i < nhg->num_nh; ++i) { + struct nh_grp_entry *nhge = &nhg->nh_entries[i]; + int upper_bound; + + w += nhge->weight; + upper_bound = DIV_ROUND_CLOSEST(res_table->num_nh_buckets * w, + total); + nhge->res.wants_buckets = upper_bound - prev_upper_bound; + prev_upper_bound = upper_bound; + + if (nh_res_nhge_is_uw(nhge)) { + if (list_empty(&res_table->uw_nh_entries)) + res_table->unbalanced_since = jiffies; + list_add(&nhge->res.uw_nh_entry, + &res_table->uw_nh_entries); + } + } +} + +/* Migrate buckets in res_table so that they reference NHGE's from NHG with + * the right NH ID. Set those buckets that do not have a corresponding NHGE + * entry in NHG as not occupied. + */ +static void nh_res_table_migrate_buckets(struct nh_res_table *res_table, + struct nh_group *nhg) +{ + u16 i; + + for (i = 0; i < res_table->num_nh_buckets; i++) { + struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; + u32 id = rtnl_dereference(bucket->nh_entry)->nh->id; + bool found = false; + int j; + + for (j = 0; j < nhg->num_nh; j++) { + struct nh_grp_entry *nhge = &nhg->nh_entries[j]; + + if (nhge->nh->id == id) { + nh_res_bucket_set_nh(bucket, nhge); + found = true; + break; + } + } + + if (!found) + nh_res_bucket_unset_nh(bucket); + } +} + +static void replace_nexthop_grp_res(struct nh_group *oldg, + struct nh_group *newg) +{ + /* For NH group replacement, the new NHG might only have a stub + * hash table with 0 buckets, because the number of buckets was not + * specified. For NH removal, oldg and newg both reference the same + * res_table. So in any case, in the following, we want to work + * with oldg->res_table. + */ + struct nh_res_table *old_res_table = rtnl_dereference(oldg->res_table); + unsigned long prev_unbalanced_since = old_res_table->unbalanced_since; + bool prev_has_uw = !list_empty(&old_res_table->uw_nh_entries); + + nh_res_table_cancel_upkeep(old_res_table); + nh_res_table_migrate_buckets(old_res_table, newg); + nh_res_group_rebalance(newg, old_res_table); + if (prev_has_uw && !list_empty(&old_res_table->uw_nh_entries)) + old_res_table->unbalanced_since = prev_unbalanced_since; + nh_res_table_upkeep(old_res_table, true, false); +} + +static void nh_mp_group_rebalance(struct nh_group *nhg) { int total = 0; int w = 0; @@ -965,7 +1751,9 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, } newg->has_v4 = false; + newg->is_multipath = nhg->is_multipath; newg->mpath = nhg->mpath; + newg->resilient = nhg->resilient; newg->fdb_nh = nhg->fdb_nh; newg->num_nh = nhg->num_nh; @@ -993,15 +1781,25 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, j++; } - nh_group_rebalance(newg); + if (newg->mpath) + nh_mp_group_rebalance(newg); + else if (newg->resilient) + replace_nexthop_grp_res(nhg, newg); + rcu_assign_pointer(nhp->nh_grp, newg); list_del(&nhge->nh_list); nexthop_put(nhge->nh); - err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, nhp, &extack); - if (err) - pr_err("%s\n", extack._msg); + /* Removal of a NH from a resilient group is notified through + * bucket notifications. + */ + if (newg->mpath) { + err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, nhp, + &extack); + if (err) + pr_err("%s\n", extack._msg); + } if (nlinfo) nexthop_notify(RTM_NEWNEXTHOP, nhp, nlinfo); @@ -1022,6 +1820,7 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh, static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo) { struct nh_group *nhg = rcu_dereference_rtnl(nh->nh_grp); + struct nh_res_table *res_table; int i, num_nh = nhg->num_nh; for (i = 0; i < num_nh; ++i) { @@ -1032,6 +1831,11 @@ static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo) list_del_init(&nhge->nh_list); } + + if (nhg->resilient) { + res_table = rtnl_dereference(nhg->res_table); + nh_res_table_cancel_upkeep(res_table); + } } /* not called for nexthop replace */ @@ -1107,9 +1911,12 @@ static void nh_rt_cache_flush(struct net *net, struct nexthop *nh) } static int replace_nexthop_grp(struct net *net, struct nexthop *old, - struct nexthop *new, + struct nexthop *new, const struct nh_config *cfg, struct netlink_ext_ack *extack) { + struct nh_res_table *tmp_table = NULL; + struct nh_res_table *new_res_table; + struct nh_res_table *old_res_table; struct nh_group *oldg, *newg; int i, err; @@ -1118,19 +1925,67 @@ static int replace_nexthop_grp(struct net *net, struct nexthop *old, return -EINVAL; } - err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new, extack); - if (err) - return err; - oldg = rtnl_dereference(old->nh_grp); newg = rtnl_dereference(new->nh_grp); + if (newg->mpath != oldg->mpath) { + NL_SET_ERR_MSG(extack, "Can not replace a nexthop group with one of a different type."); + return -EINVAL; + } + + if (newg->mpath) { + err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new, + extack); + if (err) + return err; + } else if (newg->resilient) { + new_res_table = rtnl_dereference(newg->res_table); + old_res_table = rtnl_dereference(oldg->res_table); + + /* Accept if num_nh_buckets was not given, but if it was + * given, demand that the value be correct. + */ + if (cfg->nh_grp_res_has_num_buckets && + cfg->nh_grp_res_num_buckets != + old_res_table->num_nh_buckets) { + NL_SET_ERR_MSG(extack, "Can not change number of buckets of a resilient nexthop group."); + return -EINVAL; + } + + /* Emit a pre-replace notification so that listeners could veto + * a potentially unsupported configuration. Otherwise, + * individual bucket replacement notifications would need to be + * vetoed, which is something that should only happen if the + * bucket is currently active. + */ + err = call_nexthop_res_table_notifiers(net, new, extack); + if (err) + return err; + + if (cfg->nh_grp_res_has_idle_timer) + old_res_table->idle_timer = cfg->nh_grp_res_idle_timer; + if (cfg->nh_grp_res_has_unbalanced_timer) + old_res_table->unbalanced_timer = + cfg->nh_grp_res_unbalanced_timer; + + replace_nexthop_grp_res(oldg, newg); + + tmp_table = new_res_table; + rcu_assign_pointer(newg->res_table, old_res_table); + rcu_assign_pointer(newg->spare->res_table, old_res_table); + } + /* update parents - used by nexthop code for cleanup */ for (i = 0; i < newg->num_nh; i++) newg->nh_entries[i].nh_parent = old; rcu_assign_pointer(old->nh_grp, newg); + if (newg->resilient) { + rcu_assign_pointer(oldg->res_table, tmp_table); + rcu_assign_pointer(oldg->spare->res_table, tmp_table); + } + for (i = 0; i < oldg->num_nh; i++) oldg->nh_entries[i].nh_parent = new; @@ -1156,6 +2011,71 @@ static void nh_group_v4_update(struct nh_group *nhg) nhg->has_v4 = has_v4; } +static int replace_nexthop_single_notify_res(struct net *net, + struct nh_res_table *res_table, + struct nexthop *old, + struct nh_info *oldi, + struct nh_info *newi, + struct netlink_ext_ack *extack) +{ + u32 nhg_id = res_table->nhg_id; + int err; + u16 i; + + for (i = 0; i < res_table->num_nh_buckets; i++) { + struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; + struct nh_grp_entry *nhge; + + nhge = rtnl_dereference(bucket->nh_entry); + if (nhge->nh == old) { + err = __call_nexthop_res_bucket_notifiers(net, nhg_id, + i, true, + oldi, newi, + extack); + if (err) + goto err_notify; + } + } + + return 0; + +err_notify: + while (i-- > 0) { + struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; + struct nh_grp_entry *nhge; + + nhge = rtnl_dereference(bucket->nh_entry); + if (nhge->nh == old) + __call_nexthop_res_bucket_notifiers(net, nhg_id, i, + true, newi, oldi, + extack); + } + return err; +} + +static int replace_nexthop_single_notify(struct net *net, + struct nexthop *group_nh, + struct nexthop *old, + struct nh_info *oldi, + struct nh_info *newi, + struct netlink_ext_ack *extack) +{ + struct nh_group *nhg = rtnl_dereference(group_nh->nh_grp); + struct nh_res_table *res_table; + + if (nhg->mpath) { + return call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, + group_nh, extack); + } else if (nhg->resilient) { + res_table = rtnl_dereference(nhg->res_table); + return replace_nexthop_single_notify_res(net, res_table, + old, oldi, newi, + extack); + } + + return -EINVAL; +} + static int replace_nexthop_single(struct net *net, struct nexthop *old, struct nexthop *new, struct netlink_ext_ack *extack) @@ -1198,8 +2118,8 @@ static int replace_nexthop_single(struct net *net, struct nexthop *old, list_for_each_entry(nhge, &old->grp_list, nh_list) { struct nexthop *nhp = nhge->nh_parent; - err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, nhp, - extack); + err = replace_nexthop_single_notify(net, nhp, old, oldi, newi, + extack); if (err) goto err_notify; } @@ -1229,7 +2149,7 @@ err_notify: list_for_each_entry_continue_reverse(nhge, &old->grp_list, nh_list) { struct nexthop *nhp = nhge->nh_parent; - call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, nhp, extack); + replace_nexthop_single_notify(net, nhp, old, newi, oldi, NULL); } call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, old, extack); return err; @@ -1276,7 +2196,8 @@ static void nexthop_replace_notify(struct net *net, struct nexthop *nh, } static int replace_nexthop(struct net *net, struct nexthop *old, - struct nexthop *new, struct netlink_ext_ack *extack) + struct nexthop *new, const struct nh_config *cfg, + struct netlink_ext_ack *extack) { bool new_is_reject = false; struct nh_grp_entry *nhge; @@ -1319,7 +2240,7 @@ static int replace_nexthop(struct net *net, struct nexthop *old, } if (old->is_group) - err = replace_nexthop_grp(net, old, new, extack); + err = replace_nexthop_grp(net, old, new, cfg, extack); else err = replace_nexthop_single(net, old, new, extack); @@ -1361,7 +2282,7 @@ static int insert_nexthop(struct net *net, struct nexthop *new_nh, } else if (new_id > nh->id) { pp = &next->rb_right; } else if (replace) { - rc = replace_nexthop(net, nh, new_nh, extack); + rc = replace_nexthop(net, nh, new_nh, cfg, extack); if (!rc) { new_nh = nh; /* send notification with old nh */ replace_notify = 1; @@ -1379,9 +2300,37 @@ static int insert_nexthop(struct net *net, struct nexthop *new_nh, goto out; } + if (new_nh->is_group) { + struct nh_group *nhg = rtnl_dereference(new_nh->nh_grp); + struct nh_res_table *res_table; + + if (nhg->resilient) { + res_table = rtnl_dereference(nhg->res_table); + + /* Not passing the number of buckets is OK when + * replacing, but not when creating a new group. + */ + if (!cfg->nh_grp_res_has_num_buckets) { + NL_SET_ERR_MSG(extack, "Number of buckets not specified for nexthop group insertion"); + rc = -EINVAL; + goto out; + } + + nh_res_group_rebalance(nhg, res_table); + + /* Do not send bucket notifications, we do full + * notification below. + */ + nh_res_table_upkeep(res_table, false, false); + } + } + rb_link_node_rcu(&new_nh->rb_node, parent, pp); rb_insert_color(&new_nh->rb_node, root); + /* The initial insertion is a full notification for mpath as well + * as resilient groups. + */ rc = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new_nh, extack); if (rc) rb_erase(&new_nh->rb_node, &net->nexthop.rb_root); @@ -1441,6 +2390,7 @@ static struct nexthop *nexthop_create_group(struct net *net, u16 num_nh = nla_len(grps_attr) / sizeof(*entry); struct nh_group *nhg; struct nexthop *nh; + int err; int i; if (WARN_ON(!num_nh)) @@ -1472,8 +2422,10 @@ static struct nexthop *nexthop_create_group(struct net *net, struct nh_info *nhi; nhe = nexthop_find_by_id(net, entry[i].id); - if (!nexthop_get(nhe)) + if (!nexthop_get(nhe)) { + err = -ENOENT; goto out_no_nh; + } nhi = rtnl_dereference(nhe->nh_info); if (nhi->family == AF_INET) @@ -1485,13 +2437,28 @@ static struct nexthop *nexthop_create_group(struct net *net, nhg->nh_entries[i].nh_parent = nh; } - if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_MPATH) + if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_MPATH) { nhg->mpath = 1; + nhg->is_multipath = true; + } else if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_RES) { + struct nh_res_table *res_table; + + res_table = nexthop_res_table_alloc(net, cfg->nh_id, cfg); + if (!res_table) { + err = -ENOMEM; + goto out_no_nh; + } + + rcu_assign_pointer(nhg->spare->res_table, res_table); + rcu_assign_pointer(nhg->res_table, res_table); + nhg->resilient = true; + nhg->is_multipath = true; + } - WARN_ON_ONCE(nhg->mpath != 1); + WARN_ON_ONCE(nhg->mpath + nhg->resilient != 1); if (nhg->mpath) - nh_group_rebalance(nhg); + nh_mp_group_rebalance(nhg); if (cfg->nh_fdb) nhg->fdb_nh = 1; @@ -1510,7 +2477,7 @@ out_no_nh: kfree(nhg); kfree(nh); - return ERR_PTR(-ENOENT); + return ERR_PTR(err); } static int nh_create_ipv4(struct net *net, struct nexthop *nh, @@ -1680,6 +2647,70 @@ static struct nexthop *nexthop_add(struct net *net, struct nh_config *cfg, return nh; } +static int rtm_nh_get_timer(struct nlattr *attr, unsigned long fallback, + unsigned long *timer_p, bool *has_p, + struct netlink_ext_ack *extack) +{ + unsigned long timer; + u32 value; + + if (!attr) { + *timer_p = fallback; + *has_p = false; + return 0; + } + + value = nla_get_u32(attr); + timer = clock_t_to_jiffies(value); + if (timer == ~0UL) { + NL_SET_ERR_MSG(extack, "Timer value too large"); + return -EINVAL; + } + + *timer_p = timer; + *has_p = true; + return 0; +} + +static int rtm_to_nh_config_grp_res(struct nlattr *res, struct nh_config *cfg, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[ARRAY_SIZE(rtm_nh_res_policy_new)] = {}; + int err; + + if (res) { + err = nla_parse_nested(tb, + ARRAY_SIZE(rtm_nh_res_policy_new) - 1, + res, rtm_nh_res_policy_new, extack); + if (err < 0) + return err; + } + + if (tb[NHA_RES_GROUP_BUCKETS]) { + cfg->nh_grp_res_num_buckets = + nla_get_u16(tb[NHA_RES_GROUP_BUCKETS]); + cfg->nh_grp_res_has_num_buckets = true; + if (!cfg->nh_grp_res_num_buckets) { + NL_SET_ERR_MSG(extack, "Number of buckets needs to be non-0"); + return -EINVAL; + } + } + + err = rtm_nh_get_timer(tb[NHA_RES_GROUP_IDLE_TIMER], + NH_RES_DEFAULT_IDLE_TIMER, + &cfg->nh_grp_res_idle_timer, + &cfg->nh_grp_res_has_idle_timer, + extack); + if (err) + return err; + + return rtm_nh_get_timer(tb[NHA_RES_GROUP_UNBALANCED_TIMER], + NH_RES_DEFAULT_UNBALANCED_TIMER, + &cfg->nh_grp_res_unbalanced_timer, + &cfg->nh_grp_res_has_unbalanced_timer, + extack); +} + static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, struct nh_config *cfg, struct netlink_ext_ack *extack) @@ -1758,7 +2789,14 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, NL_SET_ERR_MSG(extack, "Invalid group type"); goto out; } - err = nh_check_attr_group(net, tb, ARRAY_SIZE(tb), extack); + err = nh_check_attr_group(net, tb, ARRAY_SIZE(tb), + cfg->nh_grp_type, extack); + if (err) + goto out; + + if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_RES) + err = rtm_to_nh_config_grp_res(tb[NHA_RES_GROUP], + cfg, extack); /* no other attributes should be set */ goto out; @@ -1983,10 +3021,12 @@ errout_free: } struct nh_dump_filter { + u32 nh_id; int dev_idx; int master_idx; bool group_filter; bool fdb_filter; + u32 res_bucket_nh_id; }; static bool nh_dump_filtered(struct nexthop *nh, @@ -2166,6 +3206,318 @@ out_err: return err; } +static struct nexthop * +nexthop_find_group_resilient(struct net *net, u32 id, + struct netlink_ext_ack *extack) +{ + struct nh_group *nhg; + struct nexthop *nh; + + nh = nexthop_find_by_id(net, id); + if (!nh) + return ERR_PTR(-ENOENT); + + if (!nh->is_group) { + NL_SET_ERR_MSG(extack, "Not a nexthop group"); + return ERR_PTR(-EINVAL); + } + + nhg = rtnl_dereference(nh->nh_grp); + if (!nhg->resilient) { + NL_SET_ERR_MSG(extack, "Nexthop group not of type resilient"); + return ERR_PTR(-EINVAL); + } + + return nh; +} + +static int nh_valid_dump_nhid(struct nlattr *attr, u32 *nh_id_p, + struct netlink_ext_ack *extack) +{ + u32 idx; + + if (attr) { + idx = nla_get_u32(attr); + if (!idx) { + NL_SET_ERR_MSG(extack, "Invalid nexthop id"); + return -EINVAL; + } + *nh_id_p = idx; + } else { + *nh_id_p = 0; + } + + return 0; +} + +static int nh_valid_dump_bucket_req(const struct nlmsghdr *nlh, + struct nh_dump_filter *filter, + struct netlink_callback *cb) +{ + struct nlattr *res_tb[ARRAY_SIZE(rtm_nh_res_bucket_policy_dump)]; + struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_dump_bucket)]; + int err; + + err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, + ARRAY_SIZE(rtm_nh_policy_dump_bucket) - 1, + rtm_nh_policy_dump_bucket, NULL); + if (err < 0) + return err; + + err = nh_valid_dump_nhid(tb[NHA_ID], &filter->nh_id, cb->extack); + if (err) + return err; + + if (tb[NHA_RES_BUCKET]) { + size_t max = ARRAY_SIZE(rtm_nh_res_bucket_policy_dump) - 1; + + err = nla_parse_nested(res_tb, max, + tb[NHA_RES_BUCKET], + rtm_nh_res_bucket_policy_dump, + cb->extack); + if (err < 0) + return err; + + err = nh_valid_dump_nhid(res_tb[NHA_RES_BUCKET_NH_ID], + &filter->res_bucket_nh_id, + cb->extack); + if (err) + return err; + } + + return __nh_valid_dump_req(nlh, tb, filter, cb->extack); +} + +struct rtm_dump_res_bucket_ctx { + struct rtm_dump_nh_ctx nh; + u16 bucket_index; + u32 done_nh_idx; /* 1 + the index of the last fully processed NH. */ +}; + +static struct rtm_dump_res_bucket_ctx * +rtm_dump_res_bucket_ctx(struct netlink_callback *cb) +{ + struct rtm_dump_res_bucket_ctx *ctx = (void *)cb->ctx; + + BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); + return ctx; +} + +struct rtm_dump_nexthop_bucket_data { + struct rtm_dump_res_bucket_ctx *ctx; + struct nh_dump_filter filter; +}; + +static int rtm_dump_nexthop_bucket_nh(struct sk_buff *skb, + struct netlink_callback *cb, + struct nexthop *nh, + struct rtm_dump_nexthop_bucket_data *dd) +{ + u32 portid = NETLINK_CB(cb->skb).portid; + struct nhmsg *nhm = nlmsg_data(cb->nlh); + struct nh_res_table *res_table; + struct nh_group *nhg; + u16 bucket_index; + int err; + + if (dd->ctx->nh.idx < dd->ctx->done_nh_idx) + return 0; + + nhg = rtnl_dereference(nh->nh_grp); + res_table = rtnl_dereference(nhg->res_table); + for (bucket_index = dd->ctx->bucket_index; + bucket_index < res_table->num_nh_buckets; + bucket_index++) { + struct nh_res_bucket *bucket; + struct nh_grp_entry *nhge; + + bucket = &res_table->nh_buckets[bucket_index]; + nhge = rtnl_dereference(bucket->nh_entry); + if (nh_dump_filtered(nhge->nh, &dd->filter, nhm->nh_family)) + continue; + + if (dd->filter.res_bucket_nh_id && + dd->filter.res_bucket_nh_id != nhge->nh->id) + continue; + + err = nh_fill_res_bucket(skb, nh, bucket, bucket_index, + RTM_NEWNEXTHOPBUCKET, portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + cb->extack); + if (err < 0) { + if (likely(skb->len)) + goto out; + goto out_err; + } + } + + dd->ctx->done_nh_idx = dd->ctx->nh.idx + 1; + bucket_index = 0; + +out: + err = skb->len; +out_err: + dd->ctx->bucket_index = bucket_index; + return err; +} + +static int rtm_dump_nexthop_bucket_cb(struct sk_buff *skb, + struct netlink_callback *cb, + struct nexthop *nh, void *data) +{ + struct rtm_dump_nexthop_bucket_data *dd = data; + struct nh_group *nhg; + + if (!nh->is_group) + return 0; + + nhg = rtnl_dereference(nh->nh_grp); + if (!nhg->resilient) + return 0; + + return rtm_dump_nexthop_bucket_nh(skb, cb, nh, dd); +} + +/* rtnl */ +static int rtm_dump_nexthop_bucket(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct rtm_dump_res_bucket_ctx *ctx = rtm_dump_res_bucket_ctx(cb); + struct rtm_dump_nexthop_bucket_data dd = { .ctx = ctx }; + struct net *net = sock_net(skb->sk); + struct nexthop *nh; + int err; + + err = nh_valid_dump_bucket_req(cb->nlh, &dd.filter, cb); + if (err) + return err; + + if (dd.filter.nh_id) { + nh = nexthop_find_group_resilient(net, dd.filter.nh_id, + cb->extack); + if (IS_ERR(nh)) + return PTR_ERR(nh); + err = rtm_dump_nexthop_bucket_nh(skb, cb, nh, &dd); + } else { + struct rb_root *root = &net->nexthop.rb_root; + + err = rtm_dump_walk_nexthops(skb, cb, root, &ctx->nh, + &rtm_dump_nexthop_bucket_cb, &dd); + } + + if (err < 0) { + if (likely(skb->len)) + goto out; + goto out_err; + } + +out: + err = skb->len; +out_err: + cb->seq = net->nexthop.seq; + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); + return err; +} + +static int nh_valid_get_bucket_req_res_bucket(struct nlattr *res, + u16 *bucket_index, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[ARRAY_SIZE(rtm_nh_res_bucket_policy_get)]; + int err; + + err = nla_parse_nested(tb, ARRAY_SIZE(rtm_nh_res_bucket_policy_get) - 1, + res, rtm_nh_res_bucket_policy_get, extack); + if (err < 0) + return err; + + if (!tb[NHA_RES_BUCKET_INDEX]) { + NL_SET_ERR_MSG(extack, "Bucket index is missing"); + return -EINVAL; + } + + *bucket_index = nla_get_u16(tb[NHA_RES_BUCKET_INDEX]); + return 0; +} + +static int nh_valid_get_bucket_req(const struct nlmsghdr *nlh, + u32 *id, u16 *bucket_index, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_get_bucket)]; + int err; + + err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, + ARRAY_SIZE(rtm_nh_policy_get_bucket) - 1, + rtm_nh_policy_get_bucket, extack); + if (err < 0) + return err; + + err = __nh_valid_get_del_req(nlh, tb, id, extack); + if (err) + return err; + + if (!tb[NHA_RES_BUCKET]) { + NL_SET_ERR_MSG(extack, "Bucket information is missing"); + return -EINVAL; + } + + err = nh_valid_get_bucket_req_res_bucket(tb[NHA_RES_BUCKET], + bucket_index, extack); + if (err) + return err; + + return 0; +} + +/* rtnl */ +static int rtm_get_nexthop_bucket(struct sk_buff *in_skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(in_skb->sk); + struct nh_res_table *res_table; + struct sk_buff *skb = NULL; + struct nh_group *nhg; + struct nexthop *nh; + u16 bucket_index; + int err; + u32 id; + + err = nh_valid_get_bucket_req(nlh, &id, &bucket_index, extack); + if (err) + return err; + + nh = nexthop_find_group_resilient(net, id, extack); + if (IS_ERR(nh)) + return PTR_ERR(nh); + + nhg = rtnl_dereference(nh->nh_grp); + res_table = rtnl_dereference(nhg->res_table); + if (bucket_index >= res_table->num_nh_buckets) { + NL_SET_ERR_MSG(extack, "Bucket index out of bounds"); + return -ENOENT; + } + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + err = nh_fill_res_bucket(skb, nh, &res_table->nh_buckets[bucket_index], + bucket_index, RTM_NEWNEXTHOPBUCKET, + NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, + 0, extack); + if (err < 0) { + WARN_ON(err == -EMSGSIZE); + goto errout_free; + } + + return rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); + +errout_free: + kfree_skb(skb); + return err; +} + static void nexthop_sync_mtu(struct net_device *dev, u32 orig_mtu) { unsigned int hash = nh_dev_hashfn(dev->ifindex); @@ -2277,6 +3629,75 @@ out: } EXPORT_SYMBOL(nexthop_set_hw_flags); +void nexthop_bucket_set_hw_flags(struct net *net, u32 id, u16 bucket_index, + bool offload, bool trap) +{ + struct nh_res_table *res_table; + struct nh_res_bucket *bucket; + struct nexthop *nexthop; + struct nh_group *nhg; + + rcu_read_lock(); + + nexthop = nexthop_find_by_id(net, id); + if (!nexthop || !nexthop->is_group) + goto out; + + nhg = rcu_dereference(nexthop->nh_grp); + if (!nhg->resilient) + goto out; + + if (bucket_index >= nhg->res_table->num_nh_buckets) + goto out; + + res_table = rcu_dereference(nhg->res_table); + bucket = &res_table->nh_buckets[bucket_index]; + bucket->nh_flags &= ~(RTNH_F_OFFLOAD | RTNH_F_TRAP); + if (offload) + bucket->nh_flags |= RTNH_F_OFFLOAD; + if (trap) + bucket->nh_flags |= RTNH_F_TRAP; + +out: + rcu_read_unlock(); +} +EXPORT_SYMBOL(nexthop_bucket_set_hw_flags); + +void nexthop_res_grp_activity_update(struct net *net, u32 id, u16 num_buckets, + unsigned long *activity) +{ + struct nh_res_table *res_table; + struct nexthop *nexthop; + struct nh_group *nhg; + u16 i; + + rcu_read_lock(); + + nexthop = nexthop_find_by_id(net, id); + if (!nexthop || !nexthop->is_group) + goto out; + + nhg = rcu_dereference(nexthop->nh_grp); + if (!nhg->resilient) + goto out; + + /* Instead of silently ignoring some buckets, demand that the sizes + * be the same. + */ + res_table = rcu_dereference(nhg->res_table); + if (num_buckets != res_table->num_nh_buckets) + goto out; + + for (i = 0; i < num_buckets; i++) { + if (test_bit(i, activity)) + nh_res_bucket_set_busy(&res_table->nh_buckets[i]); + } + +out: + rcu_read_unlock(); +} +EXPORT_SYMBOL(nexthop_res_grp_activity_update); + static void __net_exit nexthop_net_exit(struct net *net) { rtnl_lock(); @@ -2320,6 +3741,9 @@ static int __init nexthop_init(void) rtnl_register(PF_INET6, RTM_NEWNEXTHOP, rtm_new_nexthop, NULL, 0); rtnl_register(PF_INET6, RTM_GETNEXTHOP, NULL, rtm_dump_nexthop, 0); + rtnl_register(PF_UNSPEC, RTM_GETNEXTHOPBUCKET, rtm_get_nexthop_bucket, + rtm_dump_nexthop_bucket, 0); + return 0; } subsys_initcall(nexthop_init); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index bba150fdd265..f6787c55f6ab 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -21,7 +21,7 @@ * Alan Cox : Added BSD route gw semantics * Alan Cox : Super /proc >4K * Alan Cox : MTU in route table - * Alan Cox : MSS actually. Also added the window + * Alan Cox : MSS actually. Also added the window * clamper. * Sam Lantinga : Fixed route matching in rt_del() * Alan Cox : Routing cache support. @@ -41,7 +41,7 @@ * Olaf Erb : irtt wasn't being copied right. * Bjorn Ekwall : Kerneld route support. * Alan Cox : Multicast fixed (I hope) - * Pavel Krauz : Limited broadcast fixed + * Pavel Krauz : Limited broadcast fixed * Mike McLagan : Routing by source * Alexey Kuznetsov : End of old history. Split to fib.c and * route.c and rewritten from scratch. @@ -54,8 +54,8 @@ * Robert Olsson : Added rt_cache statistics * Arnaldo C. Melo : Convert proc stuff to seq_file * Eric Dumazet : hashed spinlocks and rt_check_expire() fixes. - * Ilia Sotnikov : Ignore TOS on PMTUD and Redirect - * Ilia Sotnikov : Removed TOS from hash calculations + * Ilia Sotnikov : Ignore TOS on PMTUD and Redirect + * Ilia Sotnikov : Removed TOS from hash calculations */ #define pr_fmt(fmt) "IPv4: " fmt @@ -66,6 +66,7 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/memblock.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> @@ -234,19 +235,6 @@ static const struct seq_operations rt_cache_seq_ops = { .show = rt_cache_seq_show, }; -static int rt_cache_seq_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &rt_cache_seq_ops); -} - -static const struct proc_ops rt_cache_proc_ops = { - .proc_open = rt_cache_seq_open, - .proc_read = seq_read, - .proc_lseek = seq_lseek, - .proc_release = seq_release, -}; - - static void *rt_cpu_seq_start(struct seq_file *seq, loff_t *pos) { int cpu; @@ -324,19 +312,6 @@ static const struct seq_operations rt_cpu_seq_ops = { .show = rt_cpu_seq_show, }; - -static int rt_cpu_seq_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &rt_cpu_seq_ops); -} - -static const struct proc_ops rt_cpu_proc_ops = { - .proc_open = rt_cpu_seq_open, - .proc_read = seq_read, - .proc_lseek = seq_lseek, - .proc_release = seq_release, -}; - #ifdef CONFIG_IP_ROUTE_CLASSID static int rt_acct_proc_show(struct seq_file *m, void *v) { @@ -367,13 +342,13 @@ static int __net_init ip_rt_do_proc_init(struct net *net) { struct proc_dir_entry *pde; - pde = proc_create("rt_cache", 0444, net->proc_net, - &rt_cache_proc_ops); + pde = proc_create_seq("rt_cache", 0444, net->proc_net, + &rt_cache_seq_ops); if (!pde) goto err1; - pde = proc_create("rt_cache", 0444, - net->proc_net_stat, &rt_cpu_proc_ops); + pde = proc_create_seq("rt_cache", 0444, net->proc_net_stat, + &rt_cpu_seq_ops); if (!pde) goto err2; @@ -478,8 +453,10 @@ static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr) __ipv4_confirm_neigh(dev, *(__force u32 *)pkey); } -#define IP_IDENTS_SZ 2048u - +/* Hash tables of size 2048..262144 depending on RAM size. + * Each bucket uses 8 bytes. + */ +static u32 ip_idents_mask __read_mostly; static atomic_t *ip_idents __read_mostly; static u32 *ip_tstamps __read_mostly; @@ -489,12 +466,16 @@ static u32 *ip_tstamps __read_mostly; */ u32 ip_idents_reserve(u32 hash, int segs) { - u32 *p_tstamp = ip_tstamps + hash % IP_IDENTS_SZ; - atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ; - u32 old = READ_ONCE(*p_tstamp); - u32 now = (u32)jiffies; + u32 bucket, old, now = (u32)jiffies; + atomic_t *p_id; + u32 *p_tstamp; u32 delta = 0; + bucket = hash & ip_idents_mask; + p_tstamp = ip_tstamps + bucket; + p_id = ip_idents + bucket; + old = READ_ONCE(*p_tstamp); + if (old != now && cmpxchg(p_tstamp, old, now) == old) delta = prandom_u32_max(now - old); @@ -722,6 +703,7 @@ static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr, for_each_possible_cpu(i) { struct rtable __rcu **prt; + prt = per_cpu_ptr(nhc->nhc_pcpu_rth_output, i); rt = rcu_dereference(*prt); if (rt) @@ -1258,12 +1240,12 @@ static int ip_rt_bug(struct net *net, struct sock *sk, struct sk_buff *skb) } /* - We do not cache source address of outgoing interface, - because it is used only by IP RR, TS and SRR options, - so that it out of fast path. - - BTW remember: "addr" is allowed to be not aligned - in IP options! + * We do not cache source address of outgoing interface, + * because it is used only by IP RR, TS and SRR options, + * so that it out of fast path. + * + * BTW remember: "addr" is allowed to be not aligned + * in IP options! */ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt) @@ -2108,7 +2090,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, goto out; /* Check for the most weird martians, which can be not detected - by fib_lookup. + * by fib_lookup. */ tun_info = skb_tunnel_info(skb); @@ -2246,7 +2228,7 @@ local_input: if (res->type == RTN_UNREACHABLE) { rth->dst.input= ip_error; rth->dst.error= -err; - rth->rt_flags &= ~RTCF_LOCAL; + rth->rt_flags &= ~RTCF_LOCAL; } if (do_cache) { @@ -2317,15 +2299,15 @@ int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, struct fib_result *res) { /* Multicast recognition logic is moved from route cache to here. - The problem was that too many Ethernet cards have broken/missing - hardware multicast filters :-( As result the host on multicasting - network acquires a lot of useless route cache entries, sort of - SDR messages from all the world. Now we try to get rid of them. - Really, provided software IP multicast filter is organized - reasonably (at least, hashed), it does not result in a slowdown - comparing with route cache reject entries. - Note, that multicast routers are not affected, because - route cache entry is created eventually. + * The problem was that too many Ethernet cards have broken/missing + * hardware multicast filters :-( As result the host on multicasting + * network acquires a lot of useless route cache entries, sort of + * SDR messages from all the world. Now we try to get rid of them. + * Really, provided software IP multicast filter is organized + * reasonably (at least, hashed), it does not result in a slowdown + * comparing with route cache reject entries. + * Note, that multicast routers are not affected, because + * route cache entry is created eventually. */ if (ipv4_is_multicast(daddr)) { struct in_device *in_dev = __in_dev_get_rcu(dev); @@ -2537,11 +2519,11 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4, rth = ERR_PTR(-ENETUNREACH); /* I removed check for oif == dev_out->oif here. - It was wrong for two reasons: - 1. ip_dev_find(net, saddr) can return wrong iface, if saddr - is assigned to multiple interfaces. - 2. Moreover, we are allowed to send packets with saddr - of another iface. --ANK + * It was wrong for two reasons: + * 1. ip_dev_find(net, saddr) can return wrong iface, if saddr + * is assigned to multiple interfaces. + * 2. Moreover, we are allowed to send packets with saddr + * of another iface. --ANK */ if (fl4->flowi4_oif == 0 && @@ -2553,18 +2535,18 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4, goto out; /* Special hack: user can direct multicasts - and limited broadcast via necessary interface - without fiddling with IP_MULTICAST_IF or IP_PKTINFO. - This hack is not just for fun, it allows - vic,vat and friends to work. - They bind socket to loopback, set ttl to zero - and expect that it will work. - From the viewpoint of routing cache they are broken, - because we are not allowed to build multicast path - with loopback source addr (look, routing cache - cannot know, that ttl is zero, so that packet - will not leave this host and route is valid). - Luckily, this hack is good workaround. + * and limited broadcast via necessary interface + * without fiddling with IP_MULTICAST_IF or IP_PKTINFO. + * This hack is not just for fun, it allows + * vic,vat and friends to work. + * They bind socket to loopback, set ttl to zero + * and expect that it will work. + * From the viewpoint of routing cache they are broken, + * because we are not allowed to build multicast path + * with loopback source addr (look, routing cache + * cannot know, that ttl is zero, so that packet + * will not leave this host and route is valid). + * Luckily, this hack is good workaround. */ fl4->flowi4_oif = dev_out->ifindex; @@ -2627,21 +2609,21 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4, (ipv4_is_multicast(fl4->daddr) || !netif_index_is_l3_master(net, fl4->flowi4_oif))) { /* Apparently, routing tables are wrong. Assume, - that the destination is on link. - - WHY? DW. - Because we are allowed to send to iface - even if it has NO routes and NO assigned - addresses. When oif is specified, routing - tables are looked up with only one purpose: - to catch if destination is gatewayed, rather than - direct. Moreover, if MSG_DONTROUTE is set, - we send packet, ignoring both routing tables - and ifaddr state. --ANK - - - We could make it even if oif is unknown, - likely IPv6, but we do not. + * that the destination is on link. + * + * WHY? DW. + * Because we are allowed to send to iface + * even if it has NO routes and NO assigned + * addresses. When oif is specified, routing + * tables are looked up with only one purpose: + * to catch if destination is gatewayed, rather than + * direct. Moreover, if MSG_DONTROUTE is set, + * we send packet, ignoring both routing tables + * and ifaddr state. --ANK + * + * + * We could make it even if oif is unknown, + * likely IPv6, but we do not. */ if (fl4->saddr == 0) @@ -3553,18 +3535,25 @@ struct ip_rt_acct __percpu *ip_rt_acct __read_mostly; int __init ip_rt_init(void) { + void *idents_hash; int cpu; - ip_idents = kmalloc_array(IP_IDENTS_SZ, sizeof(*ip_idents), - GFP_KERNEL); - if (!ip_idents) - panic("IP: failed to allocate ip_idents\n"); + /* For modern hosts, this will use 2 MB of memory */ + idents_hash = alloc_large_system_hash("IP idents", + sizeof(*ip_idents) + sizeof(*ip_tstamps), + 0, + 16, /* one bucket per 64 KB */ + HASH_ZERO, + NULL, + &ip_idents_mask, + 2048, + 256*1024); + + ip_idents = idents_hash; - prandom_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents)); + prandom_bytes(ip_idents, (ip_idents_mask + 1) * sizeof(*ip_idents)); - ip_tstamps = kcalloc(IP_IDENTS_SZ, sizeof(*ip_tstamps), GFP_KERNEL); - if (!ip_tstamps) - panic("IP: failed to allocate ip_tstamps\n"); + ip_tstamps = idents_hash + (ip_idents_mask + 1) * sizeof(*ip_idents); for_each_possible_cpu(cpu) { struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index bc7d2a586e18..17c322b875fd 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -229,7 +229,7 @@ int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, } EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir); -#ifdef CONFIG_BPF_STREAM_PARSER +#ifdef CONFIG_BPF_SYSCALL static bool tcp_bpf_stream_read(const struct sock *sk) { struct sk_psock *psock; @@ -629,4 +629,4 @@ void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) if (prot == &tcp_bpf_prots[family][TCP_BPF_BASE]) newsk->sk_prot = sk->sk_prot_creator; } -#endif /* CONFIG_BPF_STREAM_PARSER */ +#endif /* CONFIG_BPF_SYSCALL */ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 69a545db80d2..4cf4dd532d1c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2914,7 +2914,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, /* D. Check state exit conditions. State can be terminated * when high_seq is ACKed. */ if (icsk->icsk_ca_state == TCP_CA_Open) { - WARN_ON(tp->retrans_out != 0); + WARN_ON(tp->retrans_out != 0 && !tp->syn_data); tp->retrans_stamp = 0; } else if (!before(tp->snd_una, tp->high_seq)) { switch (icsk->icsk_ca_state) { @@ -5994,11 +5994,9 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, tp->fastopen_client_fail = TFO_SYN_RETRANSMITTED; else tp->fastopen_client_fail = TFO_DATA_NOT_ACKED; - skb_rbtree_walk_from(data) { - if (__tcp_retransmit_skb(sk, data, 1)) - break; - } - tcp_rearm_rto(sk); + skb_rbtree_walk_from(data) + tcp_mark_skb_lost(sk, data); + tcp_xmit_retransmit_queue(sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVEFAIL); return true; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index fbf140a770d8..bde781f46b41 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2775,13 +2775,17 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) * a packet is still in a qdisc or driver queue. * In this case, there is very little point doing a retransmit ! */ -static bool skb_still_in_host_queue(const struct sock *sk, +static bool skb_still_in_host_queue(struct sock *sk, const struct sk_buff *skb) { if (unlikely(skb_fclone_busy(sk, skb))) { - NET_INC_STATS(sock_net(sk), - LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES); - return true; + set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); + smp_mb__after_atomic(); + if (skb_fclone_busy(sk, skb)) { + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES); + return true; + } } return false; } @@ -3147,14 +3151,6 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) if (icsk->icsk_mtup.probe_size) icsk->icsk_mtup.probe_size = 0; - /* Do not sent more than we queued. 1/4 is reserved for possible - * copying overhead: fragmentation, tunneling, mangling etc. - */ - if (refcount_read(&sk->sk_wmem_alloc) > - min_t(u32, sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), - sk->sk_sndbuf)) - return -EAGAIN; - if (skb_still_in_host_queue(sk, skb)) return -EBUSY; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 6126f8bf94b3..56e479d158b7 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -381,7 +381,7 @@ static int ipv6_srh_rcv(struct sk_buff *skb) looped_back: if (hdr->segments_left == 0) { - if (hdr->nexthdr == NEXTHDR_IPV6) { + if (hdr->nexthdr == NEXTHDR_IPV6 || hdr->nexthdr == NEXTHDR_IPV4) { int offset = (hdr->hdrlen + 1) << 3; skb_postpull_rcsum(skb, skb_network_header(skb), @@ -397,7 +397,8 @@ looped_back: skb_reset_network_header(skb); skb_reset_transport_header(skb); skb->encapsulation = 0; - + if (hdr->nexthdr == NEXTHDR_IPV4) + skb->protocol = htons(ETH_P_IP); __skb_tunnel_rx(skb, skb->dev, net); netif_rx(skb); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 1056b0229ffd..ebb7519bec2a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2360,7 +2360,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, memset(&hash_keys, 0, sizeof(hash_keys)); - if (!flkeys) { + if (!flkeys) { skb_flow_dissect_flow_keys(skb, &keys, flag); flkeys = &keys; } @@ -2500,20 +2500,20 @@ struct dst_entry *ip6_route_output_flags(struct net *net, struct flowi6 *fl6, int flags) { - struct dst_entry *dst; - struct rt6_info *rt6; + struct dst_entry *dst; + struct rt6_info *rt6; - rcu_read_lock(); - dst = ip6_route_output_flags_noref(net, sk, fl6, flags); - rt6 = (struct rt6_info *)dst; - /* For dst cached in uncached_list, refcnt is already taken. */ - if (list_empty(&rt6->rt6i_uncached) && !dst_hold_safe(dst)) { - dst = &net->ipv6.ip6_null_entry->dst; - dst_hold(dst); - } - rcu_read_unlock(); + rcu_read_lock(); + dst = ip6_route_output_flags_noref(net, sk, fl6, flags); + rt6 = (struct rt6_info *)dst; + /* For dst cached in uncached_list, refcnt is already taken. */ + if (list_empty(&rt6->rt6i_uncached) && !dst_hold_safe(dst)) { + dst = &net->ipv6.ip6_null_entry->dst; + dst_hold(dst); + } + rcu_read_unlock(); - return dst; + return dst; } EXPORT_SYMBOL_GPL(ip6_route_output_flags); diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index c2a0c78e84d4..8936f48570fc 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -119,12 +119,12 @@ static struct seg6_local_lwt *seg6_local_lwtunnel(struct lwtunnel_state *lwt) return (struct seg6_local_lwt *)lwt->data; } -static struct ipv6_sr_hdr *get_srh(struct sk_buff *skb) +static struct ipv6_sr_hdr *get_srh(struct sk_buff *skb, int flags) { struct ipv6_sr_hdr *srh; int len, srhoff = 0; - if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) + if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, &flags) < 0) return NULL; if (!pskb_may_pull(skb, srhoff + sizeof(*srh))) @@ -152,13 +152,10 @@ static struct ipv6_sr_hdr *get_and_validate_srh(struct sk_buff *skb) { struct ipv6_sr_hdr *srh; - srh = get_srh(skb); + srh = get_srh(skb, IP6_FH_F_SKIP_RH); if (!srh) return NULL; - if (srh->segments_left == 0) - return NULL; - #ifdef CONFIG_IPV6_SEG6_HMAC if (!seg6_hmac_validate_skb(skb)) return NULL; @@ -172,7 +169,7 @@ static bool decap_and_validate(struct sk_buff *skb, int proto) struct ipv6_sr_hdr *srh; unsigned int off = 0; - srh = get_srh(skb); + srh = get_srh(skb, 0); if (srh && srh->segments_left > 0) return false; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 203890e378cb..2ee20743cb41 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -802,7 +802,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) u16 version; int length; - /* UDP has verifed checksum */ + /* UDP has verified checksum */ /* UDP always verifies the packet length. */ __skb_pull(skb, sizeof(struct udphdr)); diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c index 0511bbe4af7b..1078e14f1acf 100644 --- a/net/lapb/lapb_iface.c +++ b/net/lapb/lapb_iface.c @@ -122,8 +122,8 @@ static struct lapb_cb *lapb_create_cb(void) timer_setup(&lapb->t1timer, NULL, 0); timer_setup(&lapb->t2timer, NULL, 0); - lapb->t1timer_stop = true; - lapb->t2timer_stop = true; + lapb->t1timer_running = false; + lapb->t2timer_running = false; lapb->t1 = LAPB_DEFAULT_T1; lapb->t2 = LAPB_DEFAULT_T2; diff --git a/net/lapb/lapb_timer.c b/net/lapb/lapb_timer.c index 0230b272b7d1..5be68869064d 100644 --- a/net/lapb/lapb_timer.c +++ b/net/lapb/lapb_timer.c @@ -40,7 +40,7 @@ void lapb_start_t1timer(struct lapb_cb *lapb) lapb->t1timer.function = lapb_t1timer_expiry; lapb->t1timer.expires = jiffies + lapb->t1; - lapb->t1timer_stop = false; + lapb->t1timer_running = true; add_timer(&lapb->t1timer); } @@ -51,25 +51,25 @@ void lapb_start_t2timer(struct lapb_cb *lapb) lapb->t2timer.function = lapb_t2timer_expiry; lapb->t2timer.expires = jiffies + lapb->t2; - lapb->t2timer_stop = false; + lapb->t2timer_running = true; add_timer(&lapb->t2timer); } void lapb_stop_t1timer(struct lapb_cb *lapb) { - lapb->t1timer_stop = true; + lapb->t1timer_running = false; del_timer(&lapb->t1timer); } void lapb_stop_t2timer(struct lapb_cb *lapb) { - lapb->t2timer_stop = true; + lapb->t2timer_running = false; del_timer(&lapb->t2timer); } int lapb_t1timer_running(struct lapb_cb *lapb) { - return timer_pending(&lapb->t1timer); + return lapb->t1timer_running; } static void lapb_t2timer_expiry(struct timer_list *t) @@ -79,13 +79,14 @@ static void lapb_t2timer_expiry(struct timer_list *t) spin_lock_bh(&lapb->lock); if (timer_pending(&lapb->t2timer)) /* A new timer has been set up */ goto out; - if (lapb->t2timer_stop) /* The timer has been stopped */ + if (!lapb->t2timer_running) /* The timer has been stopped */ goto out; if (lapb->condition & LAPB_ACK_PENDING_CONDITION) { lapb->condition &= ~LAPB_ACK_PENDING_CONDITION; lapb_timeout_response(lapb); } + lapb->t2timer_running = false; out: spin_unlock_bh(&lapb->lock); @@ -98,7 +99,7 @@ static void lapb_t1timer_expiry(struct timer_list *t) spin_lock_bh(&lapb->lock); if (timer_pending(&lapb->t1timer)) /* A new timer has been set up */ goto out; - if (lapb->t1timer_stop) /* The timer has been stopped */ + if (!lapb->t1timer_running) /* The timer has been stopped */ goto out; switch (lapb->state) { @@ -127,6 +128,7 @@ static void lapb_t1timer_expiry(struct timer_list *t) lapb->state = LAPB_STATE_0; lapb_disconnect_indication(lapb, LAPB_TIMEDOUT); lapb_dbg(0, "(%p) S1 -> S0\n", lapb->dev); + lapb->t1timer_running = false; goto out; } else { lapb->n2count++; @@ -151,6 +153,7 @@ static void lapb_t1timer_expiry(struct timer_list *t) lapb->state = LAPB_STATE_0; lapb_disconnect_confirmation(lapb, LAPB_TIMEDOUT); lapb_dbg(0, "(%p) S2 -> S0\n", lapb->dev); + lapb->t1timer_running = false; goto out; } else { lapb->n2count++; @@ -169,6 +172,7 @@ static void lapb_t1timer_expiry(struct timer_list *t) lapb_stop_t2timer(lapb); lapb_disconnect_indication(lapb, LAPB_TIMEDOUT); lapb_dbg(0, "(%p) S3 -> S0\n", lapb->dev); + lapb->t1timer_running = false; goto out; } else { lapb->n2count++; @@ -186,6 +190,7 @@ static void lapb_t1timer_expiry(struct timer_list *t) lapb->state = LAPB_STATE_0; lapb_disconnect_indication(lapb, LAPB_TIMEDOUT); lapb_dbg(0, "(%p) S4 -> S0\n", lapb->dev); + lapb->t1timer_running = false; goto out; } else { lapb->n2count++; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 89a4225ed321..2b7eec93c9f5 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -26,6 +26,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, int expected_opsize; u8 version; u8 flags; + u8 i; switch (subtype) { case MPTCPOPT_MP_CAPABLE: @@ -272,14 +273,17 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_RM_ADDR: - if (opsize != TCPOLEN_MPTCP_RM_ADDR_BASE) + if (opsize < TCPOLEN_MPTCP_RM_ADDR_BASE + 1 || + opsize > TCPOLEN_MPTCP_RM_ADDR_BASE + MPTCP_RM_IDS_MAX) break; ptr++; mp_opt->rm_addr = 1; - mp_opt->rm_id = *ptr++; - pr_debug("RM_ADDR: id=%d", mp_opt->rm_id); + mp_opt->rm_list.nr = opsize - TCPOLEN_MPTCP_RM_ADDR_BASE; + for (i = 0; i < mp_opt->rm_list.nr; i++) + mp_opt->rm_list.ids[i] = *ptr++; + pr_debug("RM_ADDR: rm_list_nr=%d", mp_opt->rm_list.nr); break; case MPTCPOPT_MP_PRIO: @@ -676,20 +680,25 @@ static bool mptcp_established_options_rm_addr(struct sock *sk, { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); - u8 rm_id; + struct mptcp_rm_list rm_list; + int i, len; if (!mptcp_pm_should_rm_signal(msk) || - !(mptcp_pm_rm_addr_signal(msk, remaining, &rm_id))) + !(mptcp_pm_rm_addr_signal(msk, remaining, &rm_list))) return false; - if (remaining < TCPOLEN_MPTCP_RM_ADDR_BASE) + len = mptcp_rm_addr_len(&rm_list); + if (len < 0) + return false; + if (remaining < len) return false; - *size = TCPOLEN_MPTCP_RM_ADDR_BASE; + *size = len; opts->suboptions |= OPTION_MPTCP_RM_ADDR; - opts->rm_id = rm_id; + opts->rm_list = rm_list; - pr_debug("rm_id=%d", opts->rm_id); + for (i = 0; i < opts->rm_list.nr; i++) + pr_debug("rm_list_ids[%d]=%d", i, opts->rm_list.ids[i]); return true; } @@ -1042,7 +1051,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) } if (mp_opt.rm_addr) { - mptcp_pm_rm_addr_received(msk, mp_opt.rm_id); + mptcp_pm_rm_addr_received(msk, &mp_opt.rm_list); mp_opt.rm_addr = 0; } @@ -1221,9 +1230,23 @@ mp_capable_done: } if (OPTION_MPTCP_RM_ADDR & opts->suboptions) { + u8 i = 1; + *ptr++ = mptcp_option(MPTCPOPT_RM_ADDR, - TCPOLEN_MPTCP_RM_ADDR_BASE, - 0, opts->rm_id); + TCPOLEN_MPTCP_RM_ADDR_BASE + opts->rm_list.nr, + 0, opts->rm_list.ids[0]); + + while (i < opts->rm_list.nr) { + u8 id1, id2, id3, id4; + + id1 = opts->rm_list.ids[i]; + id2 = i + 1 < opts->rm_list.nr ? opts->rm_list.ids[i + 1] : TCPOPT_NOP; + id3 = i + 2 < opts->rm_list.nr ? opts->rm_list.ids[i + 2] : TCPOPT_NOP; + id4 = i + 3 < opts->rm_list.nr ? opts->rm_list.ids[i + 3] : TCPOPT_NOP; + put_unaligned_be32(id1 << 24 | id2 << 16 | id3 << 8 | id4, ptr); + ptr += 1; + i += 4; + } } if (OPTION_MPTCP_PRIO & opts->suboptions) { diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 6fd4b2c1b076..4cfd80f90003 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -39,29 +39,29 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk, return 0; } -int mptcp_pm_remove_addr(struct mptcp_sock *msk, u8 local_id) +int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list) { u8 rm_addr = READ_ONCE(msk->pm.addr_signal); - pr_debug("msk=%p, local_id=%d", msk, local_id); + pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr); if (rm_addr) { pr_warn("addr_signal error, rm_addr=%d", rm_addr); return -EINVAL; } - msk->pm.rm_id = local_id; + msk->pm.rm_list_tx = *rm_list; rm_addr |= BIT(MPTCP_RM_ADDR_SIGNAL); WRITE_ONCE(msk->pm.addr_signal, rm_addr); return 0; } -int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 local_id) +int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list) { - pr_debug("msk=%p, local_id=%d", msk, local_id); + pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr); spin_lock_bh(&msk->pm.lock); - mptcp_pm_nl_rm_subflow_received(msk, local_id); + mptcp_pm_nl_rm_subflow_received(msk, rm_list); spin_unlock_bh(&msk->pm.lock); return 0; } @@ -205,17 +205,20 @@ void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk) mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_SEND_ACK); } -void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, u8 rm_id) +void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, + const struct mptcp_rm_list *rm_list) { struct mptcp_pm_data *pm = &msk->pm; + u8 i; - pr_debug("msk=%p remote_id=%d", msk, rm_id); + pr_debug("msk=%p remote_ids_nr=%d", msk, rm_list->nr); - mptcp_event_addr_removed(msk, rm_id); + for (i = 0; i < rm_list->nr; i++) + mptcp_event_addr_removed(msk, rm_list->ids[i]); spin_lock_bh(&pm->lock); mptcp_pm_schedule_work(msk, MPTCP_PM_RM_ADDR_RECEIVED); - pm->rm_id = rm_id; + pm->rm_list_rx = *rm_list; spin_unlock_bh(&pm->lock); } @@ -258,9 +261,9 @@ out_unlock: } bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, - u8 *rm_id) + struct mptcp_rm_list *rm_list) { - int ret = false; + int ret = false, len; spin_lock_bh(&msk->pm.lock); @@ -268,10 +271,15 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, if (!mptcp_pm_should_rm_signal(msk)) goto out_unlock; - if (remaining < TCPOLEN_MPTCP_RM_ADDR_BASE) + len = mptcp_rm_addr_len(&msk->pm.rm_list_tx); + if (len < 0) { + WRITE_ONCE(msk->pm.addr_signal, 0); + goto out_unlock; + } + if (remaining < len) goto out_unlock; - *rm_id = msk->pm.rm_id; + *rm_list = msk->pm.rm_list_tx; WRITE_ONCE(msk->pm.addr_signal, 0); ret = true; @@ -291,7 +299,8 @@ void mptcp_pm_data_init(struct mptcp_sock *msk) msk->pm.add_addr_accepted = 0; msk->pm.local_addr_used = 0; msk->pm.subflows = 0; - msk->pm.rm_id = 0; + msk->pm.rm_list_tx.nr = 0; + msk->pm.rm_list_rx.nr = 0; WRITE_ONCE(msk->pm.work_pending, false); WRITE_ONCE(msk->pm.addr_signal, 0); WRITE_ONCE(msk->pm.accept_addr, false); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 8e8e35fa4002..5857b82c88bf 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -575,36 +575,40 @@ static void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow, *tmp; struct sock *sk = (struct sock *)msk; + u8 i; - pr_debug("address rm_id %d", msk->pm.rm_id); + pr_debug("address rm_list_nr %d", msk->pm.rm_list_rx.nr); msk_owned_by_me(msk); - if (!msk->pm.rm_id) + if (!msk->pm.rm_list_rx.nr) return; if (list_empty(&msk->conn_list)) return; - list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) { - struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - int how = RCV_SHUTDOWN | SEND_SHUTDOWN; + for (i = 0; i < msk->pm.rm_list_rx.nr; i++) { + list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + int how = RCV_SHUTDOWN | SEND_SHUTDOWN; - if (msk->pm.rm_id != subflow->remote_id) - continue; + if (msk->pm.rm_list_rx.ids[i] != subflow->remote_id) + continue; - spin_unlock_bh(&msk->pm.lock); - mptcp_subflow_shutdown(sk, ssk, how); - mptcp_close_ssk(sk, ssk, subflow); - spin_lock_bh(&msk->pm.lock); + pr_debug(" -> address rm_list_ids[%d]=%u", i, msk->pm.rm_list_rx.ids[i]); + spin_unlock_bh(&msk->pm.lock); + mptcp_subflow_shutdown(sk, ssk, how); + mptcp_close_ssk(sk, ssk, subflow); + spin_lock_bh(&msk->pm.lock); - msk->pm.add_addr_accepted--; - msk->pm.subflows--; - WRITE_ONCE(msk->pm.accept_addr, true); + msk->pm.add_addr_accepted--; + msk->pm.subflows--; + WRITE_ONCE(msk->pm.accept_addr, true); - __MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMADDR); + __MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMADDR); - break; + break; + } } } @@ -641,39 +645,44 @@ void mptcp_pm_nl_work(struct mptcp_sock *msk) spin_unlock_bh(&msk->pm.lock); } -void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id) +void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, + const struct mptcp_rm_list *rm_list) { struct mptcp_subflow_context *subflow, *tmp; struct sock *sk = (struct sock *)msk; + u8 i; - pr_debug("subflow rm_id %d", rm_id); + pr_debug("subflow rm_list_nr %d", rm_list->nr); msk_owned_by_me(msk); - if (!rm_id) + if (!rm_list->nr) return; if (list_empty(&msk->conn_list)) return; - list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) { - struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - int how = RCV_SHUTDOWN | SEND_SHUTDOWN; + for (i = 0; i < rm_list->nr; i++) { + list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + int how = RCV_SHUTDOWN | SEND_SHUTDOWN; - if (rm_id != subflow->local_id) - continue; + if (rm_list->ids[i] != subflow->local_id) + continue; - spin_unlock_bh(&msk->pm.lock); - mptcp_subflow_shutdown(sk, ssk, how); - mptcp_close_ssk(sk, ssk, subflow); - spin_lock_bh(&msk->pm.lock); + pr_debug(" -> subflow rm_list_ids[%d]=%u", i, rm_list->ids[i]); + spin_unlock_bh(&msk->pm.lock); + mptcp_subflow_shutdown(sk, ssk, how); + mptcp_close_ssk(sk, ssk, subflow); + spin_lock_bh(&msk->pm.lock); - msk->pm.local_addr_used--; - msk->pm.subflows--; + msk->pm.local_addr_used--; + msk->pm.subflows--; - __MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMSUBFLOW); + __MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMSUBFLOW); - break; + break; + } } } @@ -1071,12 +1080,15 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, struct mptcp_addr_info *addr, bool force) { + struct mptcp_rm_list list = { .nr = 0 }; bool ret; + list.ids[list.nr++] = addr->id; + ret = remove_anno_list_by_saddr(msk, addr); if (ret || force) { spin_lock_bh(&msk->pm.lock); - mptcp_pm_remove_addr(msk, addr->id); + mptcp_pm_remove_addr(msk, &list); spin_unlock_bh(&msk->pm.lock); } return ret; @@ -1087,9 +1099,12 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, { struct mptcp_sock *msk; long s_slot = 0, s_num = 0; + struct mptcp_rm_list list = { .nr = 0 }; pr_debug("remove_id=%d", addr->id); + list.ids[list.nr++] = addr->id; + while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { struct sock *sk = (struct sock *)msk; bool remove_subflow; @@ -1103,7 +1118,7 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr); mptcp_pm_remove_anno_addr(msk, addr, remove_subflow); if (remove_subflow) - mptcp_pm_remove_subflow(msk, addr->id); + mptcp_pm_remove_subflow(msk, &list); release_sock(sk); next: @@ -1185,14 +1200,61 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info) return ret; } -static void __flush_addrs(struct net *net, struct list_head *list) +static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, + struct list_head *rm_list) +{ + struct mptcp_rm_list alist = { .nr = 0 }, slist = { .nr = 0 }; + struct mptcp_pm_addr_entry *entry; + + list_for_each_entry(entry, rm_list, list) { + if (lookup_subflow_by_saddr(&msk->conn_list, &entry->addr) && + alist.nr < MPTCP_RM_IDS_MAX && + slist.nr < MPTCP_RM_IDS_MAX) { + alist.ids[alist.nr++] = entry->addr.id; + slist.ids[slist.nr++] = entry->addr.id; + } else if (remove_anno_list_by_saddr(msk, &entry->addr) && + alist.nr < MPTCP_RM_IDS_MAX) { + alist.ids[alist.nr++] = entry->addr.id; + } + } + + if (alist.nr) { + spin_lock_bh(&msk->pm.lock); + mptcp_pm_remove_addr(msk, &alist); + spin_unlock_bh(&msk->pm.lock); + } + if (slist.nr) + mptcp_pm_remove_subflow(msk, &slist); +} + +static void mptcp_nl_remove_addrs_list(struct net *net, + struct list_head *rm_list) +{ + long s_slot = 0, s_num = 0; + struct mptcp_sock *msk; + + if (list_empty(rm_list)) + return; + + while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { + struct sock *sk = (struct sock *)msk; + + lock_sock(sk); + mptcp_pm_remove_addrs_and_subflows(msk, rm_list); + release_sock(sk); + + sock_put(sk); + cond_resched(); + } +} + +static void __flush_addrs(struct list_head *list) { while (!list_empty(list)) { struct mptcp_pm_addr_entry *cur; cur = list_entry(list->next, struct mptcp_pm_addr_entry, list); - mptcp_nl_remove_subflow_and_signal_addr(net, &cur->addr); list_del_rcu(&cur->list); mptcp_pm_free_addr_entry(cur); } @@ -1217,7 +1279,8 @@ static int mptcp_nl_cmd_flush_addrs(struct sk_buff *skb, struct genl_info *info) pernet->next_id = 1; bitmap_zero(pernet->id_bitmap, MAX_ADDR_ID + 1); spin_unlock_bh(&pernet->lock); - __flush_addrs(sock_net(skb->sk), &free_list); + mptcp_nl_remove_addrs_list(sock_net(skb->sk), &free_list); + __flush_addrs(&free_list); return 0; } @@ -1814,7 +1877,7 @@ static void __net_exit pm_nl_exit_net(struct list_head *net_list) /* net is removed from namespace list, can't race with * other modifiers */ - __flush_addrs(net, &pernet->local_addr_list); + __flush_addrs(&pernet->local_addr_list); } } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index e21a5bc36cf0..1111a99b024f 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -61,7 +61,7 @@ #define TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT 22 #define TCPOLEN_MPTCP_PORT_LEN 2 #define TCPOLEN_MPTCP_PORT_ALIGN 2 -#define TCPOLEN_MPTCP_RM_ADDR_BASE 4 +#define TCPOLEN_MPTCP_RM_ADDR_BASE 3 #define TCPOLEN_MPTCP_PRIO 3 #define TCPOLEN_MPTCP_PRIO_ALIGN 4 #define TCPOLEN_MPTCP_FASTCLOSE 12 @@ -142,7 +142,7 @@ struct mptcp_options_received { mpc_map:1, __unused:2; u8 addr_id; - u8 rm_id; + struct mptcp_rm_list rm_list; union { struct in_addr addr; #if IS_ENABLED(CONFIG_MPTCP_IPV6) @@ -207,7 +207,8 @@ struct mptcp_pm_data { u8 local_addr_used; u8 subflows; u8 status; - u8 rm_id; + struct mptcp_rm_list rm_list_tx; + struct mptcp_rm_list rm_list_rx; }; struct mptcp_data_frag { @@ -647,7 +648,8 @@ void mptcp_pm_subflow_closed(struct mptcp_sock *msk, u8 id); void mptcp_pm_add_addr_received(struct mptcp_sock *msk, const struct mptcp_addr_info *addr); void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk); -void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, u8 rm_id); +void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, + const struct mptcp_rm_list *rm_list); void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup); int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, struct mptcp_addr_info *addr, @@ -661,8 +663,8 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk, int mptcp_pm_announce_addr(struct mptcp_sock *msk, const struct mptcp_addr_info *addr, bool echo, bool port); -int mptcp_pm_remove_addr(struct mptcp_sock *msk, u8 local_id); -int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 local_id); +int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); +int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp); @@ -709,16 +711,25 @@ static inline unsigned int mptcp_add_addr_len(int family, bool echo, bool port) return len; } +static inline int mptcp_rm_addr_len(const struct mptcp_rm_list *rm_list) +{ + if (rm_list->nr == 0 || rm_list->nr > MPTCP_RM_IDS_MAX) + return -EINVAL; + + return TCPOLEN_MPTCP_RM_ADDR_BASE + roundup(rm_list->nr - 1, 4) + 1; +} + bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int remaining, struct mptcp_addr_info *saddr, bool *echo, bool *port); bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, - u8 *rm_id); + struct mptcp_rm_list *rm_list); int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); void __init mptcp_pm_nl_init(void); void mptcp_pm_nl_data_init(struct mptcp_sock *msk); void mptcp_pm_nl_work(struct mptcp_sock *msk); -void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id); +void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, + const struct mptcp_rm_list *rm_list); int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); unsigned int mptcp_pm_get_add_addr_signal_max(struct mptcp_sock *msk); unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk); diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index db7479db8512..4f33307fa3cf 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -397,6 +397,7 @@ dccp_new(struct nf_conn *ct, const struct sk_buff *skb, msg = "not picking up existing connection "; goto out_invalid; } + break; case CT_DCCP_REQUEST: break; case CT_DCCP_INVALID: diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index c77ba8690ed8..1bce1d2805c4 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -79,11 +79,8 @@ static int flow_offload_fill_route(struct flow_offload *flow, enum flow_offload_tuple_dir dir) { struct flow_offload_tuple *flow_tuple = &flow->tuplehash[dir].tuple; - struct dst_entry *other_dst = route->tuple[!dir].dst; struct dst_entry *dst = route->tuple[dir].dst; - - if (!dst_hold_safe(route->tuple[dir].dst)) - return -1; + int i, j = 0; switch (flow_tuple->l3proto) { case NFPROTO_IPV4: @@ -94,12 +91,46 @@ static int flow_offload_fill_route(struct flow_offload *flow, break; } - flow_tuple->iifidx = other_dst->dev->ifindex; - flow_tuple->dst_cache = dst; + flow_tuple->iifidx = route->tuple[dir].in.ifindex; + for (i = route->tuple[dir].in.num_encaps - 1; i >= 0; i--) { + flow_tuple->encap[j].id = route->tuple[dir].in.encap[i].id; + flow_tuple->encap[j].proto = route->tuple[dir].in.encap[i].proto; + if (route->tuple[dir].in.ingress_vlans & BIT(i)) + flow_tuple->in_vlan_ingress |= BIT(j); + j++; + } + flow_tuple->encap_num = route->tuple[dir].in.num_encaps; + + switch (route->tuple[dir].xmit_type) { + case FLOW_OFFLOAD_XMIT_DIRECT: + memcpy(flow_tuple->out.h_dest, route->tuple[dir].out.h_dest, + ETH_ALEN); + memcpy(flow_tuple->out.h_source, route->tuple[dir].out.h_source, + ETH_ALEN); + flow_tuple->out.ifidx = route->tuple[dir].out.ifindex; + flow_tuple->out.hw_ifidx = route->tuple[dir].out.hw_ifindex; + break; + case FLOW_OFFLOAD_XMIT_XFRM: + case FLOW_OFFLOAD_XMIT_NEIGH: + if (!dst_hold_safe(route->tuple[dir].dst)) + return -1; + + flow_tuple->dst_cache = dst; + break; + } + flow_tuple->xmit_type = route->tuple[dir].xmit_type; return 0; } +static void nft_flow_dst_release(struct flow_offload *flow, + enum flow_offload_tuple_dir dir) +{ + if (flow->tuplehash[dir].tuple.xmit_type == FLOW_OFFLOAD_XMIT_NEIGH || + flow->tuplehash[dir].tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM) + dst_release(flow->tuplehash[dir].tuple.dst_cache); +} + int flow_offload_route_init(struct flow_offload *flow, const struct nf_flow_route *route) { @@ -118,7 +149,7 @@ int flow_offload_route_init(struct flow_offload *flow, return 0; err_route_reply: - dst_release(route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].dst); + nft_flow_dst_release(flow, FLOW_OFFLOAD_DIR_ORIGINAL); return err; } @@ -169,8 +200,8 @@ static void flow_offload_fixup_ct(struct nf_conn *ct) static void flow_offload_route_release(struct flow_offload *flow) { - dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache); - dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache); + nft_flow_dst_release(flow, FLOW_OFFLOAD_DIR_ORIGINAL); + nft_flow_dst_release(flow, FLOW_OFFLOAD_DIR_REPLY); } void flow_offload_free(struct flow_offload *flow) @@ -389,29 +420,20 @@ static void nf_flow_offload_work_gc(struct work_struct *work) queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ); } - -static int nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff, - __be16 port, __be16 new_port) +static void nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff, + __be16 port, __be16 new_port) { struct tcphdr *tcph; - if (skb_try_make_writable(skb, thoff + sizeof(*tcph))) - return -1; - tcph = (void *)(skb_network_header(skb) + thoff); inet_proto_csum_replace2(&tcph->check, skb, port, new_port, false); - - return 0; } -static int nf_flow_nat_port_udp(struct sk_buff *skb, unsigned int thoff, - __be16 port, __be16 new_port) +static void nf_flow_nat_port_udp(struct sk_buff *skb, unsigned int thoff, + __be16 port, __be16 new_port) { struct udphdr *udph; - if (skb_try_make_writable(skb, thoff + sizeof(*udph))) - return -1; - udph = (void *)(skb_network_header(skb) + thoff); if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) { inet_proto_csum_replace2(&udph->check, skb, port, @@ -419,37 +441,28 @@ static int nf_flow_nat_port_udp(struct sk_buff *skb, unsigned int thoff, if (!udph->check) udph->check = CSUM_MANGLED_0; } - - return 0; } -static int nf_flow_nat_port(struct sk_buff *skb, unsigned int thoff, - u8 protocol, __be16 port, __be16 new_port) +static void nf_flow_nat_port(struct sk_buff *skb, unsigned int thoff, + u8 protocol, __be16 port, __be16 new_port) { switch (protocol) { case IPPROTO_TCP: - if (nf_flow_nat_port_tcp(skb, thoff, port, new_port) < 0) - return NF_DROP; + nf_flow_nat_port_tcp(skb, thoff, port, new_port); break; case IPPROTO_UDP: - if (nf_flow_nat_port_udp(skb, thoff, port, new_port) < 0) - return NF_DROP; + nf_flow_nat_port_udp(skb, thoff, port, new_port); break; } - - return 0; } -int nf_flow_snat_port(const struct flow_offload *flow, - struct sk_buff *skb, unsigned int thoff, - u8 protocol, enum flow_offload_tuple_dir dir) +void nf_flow_snat_port(const struct flow_offload *flow, + struct sk_buff *skb, unsigned int thoff, + u8 protocol, enum flow_offload_tuple_dir dir) { struct flow_ports *hdr; __be16 port, new_port; - if (skb_try_make_writable(skb, thoff + sizeof(*hdr))) - return -1; - hdr = (void *)(skb_network_header(skb) + thoff); switch (dir) { @@ -463,24 +476,19 @@ int nf_flow_snat_port(const struct flow_offload *flow, new_port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port; hdr->dest = new_port; break; - default: - return -1; } - return nf_flow_nat_port(skb, thoff, protocol, port, new_port); + nf_flow_nat_port(skb, thoff, protocol, port, new_port); } EXPORT_SYMBOL_GPL(nf_flow_snat_port); -int nf_flow_dnat_port(const struct flow_offload *flow, - struct sk_buff *skb, unsigned int thoff, - u8 protocol, enum flow_offload_tuple_dir dir) +void nf_flow_dnat_port(const struct flow_offload *flow, struct sk_buff *skb, + unsigned int thoff, u8 protocol, + enum flow_offload_tuple_dir dir) { struct flow_ports *hdr; __be16 port, new_port; - if (skb_try_make_writable(skb, thoff + sizeof(*hdr))) - return -1; - hdr = (void *)(skb_network_header(skb) + thoff); switch (dir) { @@ -494,11 +502,9 @@ int nf_flow_dnat_port(const struct flow_offload *flow, new_port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_port; hdr->source = new_port; break; - default: - return -1; } - return nf_flow_nat_port(skb, thoff, protocol, port, new_port); + nf_flow_nat_port(skb, thoff, protocol, port, new_port); } EXPORT_SYMBOL_GPL(nf_flow_dnat_port); diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index a698dbe28ef5..12cb0cc6958c 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -7,6 +7,9 @@ #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/netdevice.h> +#include <linux/if_ether.h> +#include <linux/if_pppox.h> +#include <linux/ppp_defs.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/ip6_route.h> @@ -34,28 +37,20 @@ static int nf_flow_state_check(struct flow_offload *flow, int proto, return 0; } -static int nf_flow_nat_ip_tcp(struct sk_buff *skb, unsigned int thoff, - __be32 addr, __be32 new_addr) +static void nf_flow_nat_ip_tcp(struct sk_buff *skb, unsigned int thoff, + __be32 addr, __be32 new_addr) { struct tcphdr *tcph; - if (skb_try_make_writable(skb, thoff + sizeof(*tcph))) - return -1; - tcph = (void *)(skb_network_header(skb) + thoff); inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr, true); - - return 0; } -static int nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff, - __be32 addr, __be32 new_addr) +static void nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff, + __be32 addr, __be32 new_addr) { struct udphdr *udph; - if (skb_try_make_writable(skb, thoff + sizeof(*udph))) - return -1; - udph = (void *)(skb_network_header(skb) + thoff); if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) { inet_proto_csum_replace4(&udph->check, skb, addr, @@ -63,31 +58,25 @@ static int nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff, if (!udph->check) udph->check = CSUM_MANGLED_0; } - - return 0; } -static int nf_flow_nat_ip_l4proto(struct sk_buff *skb, struct iphdr *iph, - unsigned int thoff, __be32 addr, - __be32 new_addr) +static void nf_flow_nat_ip_l4proto(struct sk_buff *skb, struct iphdr *iph, + unsigned int thoff, __be32 addr, + __be32 new_addr) { switch (iph->protocol) { case IPPROTO_TCP: - if (nf_flow_nat_ip_tcp(skb, thoff, addr, new_addr) < 0) - return NF_DROP; + nf_flow_nat_ip_tcp(skb, thoff, addr, new_addr); break; case IPPROTO_UDP: - if (nf_flow_nat_ip_udp(skb, thoff, addr, new_addr) < 0) - return NF_DROP; + nf_flow_nat_ip_udp(skb, thoff, addr, new_addr); break; } - - return 0; } -static int nf_flow_snat_ip(const struct flow_offload *flow, struct sk_buff *skb, - struct iphdr *iph, unsigned int thoff, - enum flow_offload_tuple_dir dir) +static void nf_flow_snat_ip(const struct flow_offload *flow, + struct sk_buff *skb, struct iphdr *iph, + unsigned int thoff, enum flow_offload_tuple_dir dir) { __be32 addr, new_addr; @@ -102,17 +91,15 @@ static int nf_flow_snat_ip(const struct flow_offload *flow, struct sk_buff *skb, new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4.s_addr; iph->daddr = new_addr; break; - default: - return -1; } csum_replace4(&iph->check, addr, new_addr); - return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr); + nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr); } -static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb, - struct iphdr *iph, unsigned int thoff, - enum flow_offload_tuple_dir dir) +static void nf_flow_dnat_ip(const struct flow_offload *flow, + struct sk_buff *skb, struct iphdr *iph, + unsigned int thoff, enum flow_offload_tuple_dir dir) { __be32 addr, new_addr; @@ -127,31 +114,24 @@ static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb, new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4.s_addr; iph->saddr = new_addr; break; - default: - return -1; } csum_replace4(&iph->check, addr, new_addr); - return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr); + nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr); } -static int nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb, - unsigned int thoff, enum flow_offload_tuple_dir dir) +static void nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb, + unsigned int thoff, enum flow_offload_tuple_dir dir, + struct iphdr *iph) { - struct iphdr *iph = ip_hdr(skb); - - if (test_bit(NF_FLOW_SNAT, &flow->flags) && - (nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir) < 0 || - nf_flow_snat_ip(flow, skb, ip_hdr(skb), thoff, dir) < 0)) - return -1; - - iph = ip_hdr(skb); - if (test_bit(NF_FLOW_DNAT, &flow->flags) && - (nf_flow_dnat_port(flow, skb, thoff, iph->protocol, dir) < 0 || - nf_flow_dnat_ip(flow, skb, ip_hdr(skb), thoff, dir) < 0)) - return -1; - - return 0; + if (test_bit(NF_FLOW_SNAT, &flow->flags)) { + nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir); + nf_flow_snat_ip(flow, skb, iph, thoff, dir); + } + if (test_bit(NF_FLOW_DNAT, &flow->flags)) { + nf_flow_dnat_port(flow, skb, thoff, iph->protocol, dir); + nf_flow_dnat_ip(flow, skb, iph, thoff, dir); + } } static bool ip_has_options(unsigned int thoff) @@ -159,29 +139,58 @@ static bool ip_has_options(unsigned int thoff) return thoff != sizeof(struct iphdr); } +static void nf_flow_tuple_encap(struct sk_buff *skb, + struct flow_offload_tuple *tuple) +{ + struct vlan_ethhdr *veth; + struct pppoe_hdr *phdr; + int i = 0; + + if (skb_vlan_tag_present(skb)) { + tuple->encap[i].id = skb_vlan_tag_get(skb); + tuple->encap[i].proto = skb->vlan_proto; + i++; + } + switch (skb->protocol) { + case htons(ETH_P_8021Q): + veth = (struct vlan_ethhdr *)skb_mac_header(skb); + tuple->encap[i].id = ntohs(veth->h_vlan_TCI); + tuple->encap[i].proto = skb->protocol; + break; + case htons(ETH_P_PPP_SES): + phdr = (struct pppoe_hdr *)skb_mac_header(skb); + tuple->encap[i].id = ntohs(phdr->sid); + tuple->encap[i].proto = skb->protocol; + break; + } +} + static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev, - struct flow_offload_tuple *tuple) + struct flow_offload_tuple *tuple, u32 *hdrsize, + u32 offset) { - unsigned int thoff, hdrsize; struct flow_ports *ports; + unsigned int thoff; struct iphdr *iph; - if (!pskb_may_pull(skb, sizeof(*iph))) + if (!pskb_may_pull(skb, sizeof(*iph) + offset)) return -1; - iph = ip_hdr(skb); - thoff = iph->ihl * 4; + iph = (struct iphdr *)(skb_network_header(skb) + offset); + thoff = (iph->ihl * 4); if (ip_is_fragment(iph) || unlikely(ip_has_options(thoff))) return -1; + thoff += offset; + switch (iph->protocol) { case IPPROTO_TCP: - hdrsize = sizeof(struct tcphdr); + *hdrsize = sizeof(struct tcphdr); break; case IPPROTO_UDP: - hdrsize = sizeof(struct udphdr); + *hdrsize = sizeof(struct udphdr); break; default: return -1; @@ -190,11 +199,10 @@ static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev, if (iph->ttl <= 1) return -1; - thoff = iph->ihl * 4; - if (!pskb_may_pull(skb, thoff + hdrsize)) + if (!pskb_may_pull(skb, thoff + *hdrsize)) return -1; - iph = ip_hdr(skb); + iph = (struct iphdr *)(skb_network_header(skb) + offset); ports = (struct flow_ports *)(skb_network_header(skb) + thoff); tuple->src_v4.s_addr = iph->saddr; @@ -204,6 +212,7 @@ static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev, tuple->l3proto = AF_INET; tuple->l4proto = iph->protocol; tuple->iifidx = dev->ifindex; + nf_flow_tuple_encap(skb, tuple); return 0; } @@ -220,14 +229,6 @@ static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) return true; } -static int nf_flow_offload_dst_check(struct dst_entry *dst) -{ - if (unlikely(dst_xfrm(dst))) - return dst_check(dst, 0) ? 0 : -1; - - return 0; -} - static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, const struct nf_hook_state *state, struct dst_entry *dst) @@ -238,6 +239,91 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, return NF_STOLEN; } +static inline __be16 nf_flow_pppoe_proto(const struct sk_buff *skb) +{ + __be16 proto; + + proto = *((__be16 *)(skb_mac_header(skb) + ETH_HLEN + + sizeof(struct pppoe_hdr))); + switch (proto) { + case htons(PPP_IP): + return htons(ETH_P_IP); + case htons(PPP_IPV6): + return htons(ETH_P_IPV6); + } + + return 0; +} + +static bool nf_flow_skb_encap_protocol(const struct sk_buff *skb, __be16 proto, + u32 *offset) +{ + struct vlan_ethhdr *veth; + + switch (skb->protocol) { + case htons(ETH_P_8021Q): + veth = (struct vlan_ethhdr *)skb_mac_header(skb); + if (veth->h_vlan_encapsulated_proto == proto) { + *offset += VLAN_HLEN; + return true; + } + break; + case htons(ETH_P_PPP_SES): + if (nf_flow_pppoe_proto(skb) == proto) { + *offset += PPPOE_SES_HLEN; + return true; + } + break; + } + + return false; +} + +static void nf_flow_encap_pop(struct sk_buff *skb, + struct flow_offload_tuple_rhash *tuplehash) +{ + struct vlan_hdr *vlan_hdr; + int i; + + for (i = 0; i < tuplehash->tuple.encap_num; i++) { + if (skb_vlan_tag_present(skb)) { + __vlan_hwaccel_clear_tag(skb); + continue; + } + switch (skb->protocol) { + case htons(ETH_P_8021Q): + vlan_hdr = (struct vlan_hdr *)skb->data; + __skb_pull(skb, VLAN_HLEN); + vlan_set_encap_proto(skb, vlan_hdr); + skb_reset_network_header(skb); + break; + case htons(ETH_P_PPP_SES): + skb->protocol = nf_flow_pppoe_proto(skb); + skb_pull(skb, PPPOE_SES_HLEN); + skb_reset_network_header(skb); + break; + } + } +} + +static unsigned int nf_flow_queue_xmit(struct net *net, struct sk_buff *skb, + const struct flow_offload_tuple_rhash *tuplehash, + unsigned short type) +{ + struct net_device *outdev; + + outdev = dev_get_by_index_rcu(net, tuplehash->tuple.out.ifidx); + if (!outdev) + return NF_DROP; + + skb->dev = outdev; + dev_hard_header(skb, skb->dev, type, tuplehash->tuple.out.h_dest, + tuplehash->tuple.out.h_source, skb->len); + dev_queue_xmit(skb); + + return NF_STOLEN; +} + unsigned int nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) @@ -248,15 +334,18 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, enum flow_offload_tuple_dir dir; struct flow_offload *flow; struct net_device *outdev; + u32 hdrsize, offset = 0; + unsigned int thoff, mtu; struct rtable *rt; - unsigned int thoff; struct iphdr *iph; __be32 nexthop; + int ret; - if (skb->protocol != htons(ETH_P_IP)) + if (skb->protocol != htons(ETH_P_IP) && + !nf_flow_skb_encap_protocol(skb, htons(ETH_P_IP), &offset)) return NF_ACCEPT; - if (nf_flow_tuple_ip(skb, state->in, &tuple) < 0) + if (nf_flow_tuple_ip(skb, state->in, &tuple, &hdrsize, offset) < 0) return NF_ACCEPT; tuplehash = flow_offload_lookup(flow_table, &tuple); @@ -265,77 +354,87 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, dir = tuplehash->tuple.dir; flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); - rt = (struct rtable *)flow->tuplehash[dir].tuple.dst_cache; - outdev = rt->dst.dev; - if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu))) + mtu = flow->tuplehash[dir].tuple.mtu + offset; + if (unlikely(nf_flow_exceeds_mtu(skb, mtu))) return NF_ACCEPT; - if (skb_try_make_writable(skb, sizeof(*iph))) - return NF_DROP; - - thoff = ip_hdr(skb)->ihl * 4; - if (nf_flow_state_check(flow, ip_hdr(skb)->protocol, skb, thoff)) + iph = (struct iphdr *)(skb_network_header(skb) + offset); + thoff = (iph->ihl * 4) + offset; + if (nf_flow_state_check(flow, iph->protocol, skb, thoff)) return NF_ACCEPT; - flow_offload_refresh(flow_table, flow); - - if (nf_flow_offload_dst_check(&rt->dst)) { - flow_offload_teardown(flow); - return NF_ACCEPT; + if (tuplehash->tuple.xmit_type == FLOW_OFFLOAD_XMIT_NEIGH || + tuplehash->tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM) { + rt = (struct rtable *)tuplehash->tuple.dst_cache; + if (!dst_check(&rt->dst, 0)) { + flow_offload_teardown(flow); + return NF_ACCEPT; + } } - if (nf_flow_nat_ip(flow, skb, thoff, dir) < 0) + if (skb_try_make_writable(skb, thoff + hdrsize)) return NF_DROP; + flow_offload_refresh(flow_table, flow); + + nf_flow_encap_pop(skb, tuplehash); + thoff -= offset; + iph = ip_hdr(skb); + nf_flow_nat_ip(flow, skb, thoff, dir, iph); + ip_decrease_ttl(iph); skb->tstamp = 0; if (flow_table->flags & NF_FLOWTABLE_COUNTER) nf_ct_acct_update(flow->ct, tuplehash->tuple.dir, skb->len); - if (unlikely(dst_xfrm(&rt->dst))) { + if (unlikely(tuplehash->tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM)) { memset(skb->cb, 0, sizeof(struct inet_skb_parm)); IPCB(skb)->iif = skb->dev->ifindex; IPCB(skb)->flags = IPSKB_FORWARDED; return nf_flow_xmit_xfrm(skb, state, &rt->dst); } - skb->dev = outdev; - nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr); - skb_dst_set_noref(skb, &rt->dst); - neigh_xmit(NEIGH_ARP_TABLE, outdev, &nexthop, skb); + switch (tuplehash->tuple.xmit_type) { + case FLOW_OFFLOAD_XMIT_NEIGH: + outdev = rt->dst.dev; + skb->dev = outdev; + nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr); + skb_dst_set_noref(skb, &rt->dst); + neigh_xmit(NEIGH_ARP_TABLE, outdev, &nexthop, skb); + ret = NF_STOLEN; + break; + case FLOW_OFFLOAD_XMIT_DIRECT: + ret = nf_flow_queue_xmit(state->net, skb, tuplehash, ETH_P_IP); + if (ret == NF_DROP) + flow_offload_teardown(flow); + break; + } - return NF_STOLEN; + return ret; } EXPORT_SYMBOL_GPL(nf_flow_offload_ip_hook); -static int nf_flow_nat_ipv6_tcp(struct sk_buff *skb, unsigned int thoff, - struct in6_addr *addr, - struct in6_addr *new_addr) +static void nf_flow_nat_ipv6_tcp(struct sk_buff *skb, unsigned int thoff, + struct in6_addr *addr, + struct in6_addr *new_addr, + struct ipv6hdr *ip6h) { struct tcphdr *tcph; - if (skb_try_make_writable(skb, thoff + sizeof(*tcph))) - return -1; - tcph = (void *)(skb_network_header(skb) + thoff); inet_proto_csum_replace16(&tcph->check, skb, addr->s6_addr32, new_addr->s6_addr32, true); - - return 0; } -static int nf_flow_nat_ipv6_udp(struct sk_buff *skb, unsigned int thoff, - struct in6_addr *addr, - struct in6_addr *new_addr) +static void nf_flow_nat_ipv6_udp(struct sk_buff *skb, unsigned int thoff, + struct in6_addr *addr, + struct in6_addr *new_addr) { struct udphdr *udph; - if (skb_try_make_writable(skb, thoff + sizeof(*udph))) - return -1; - udph = (void *)(skb_network_header(skb) + thoff); if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) { inet_proto_csum_replace16(&udph->check, skb, addr->s6_addr32, @@ -343,32 +442,26 @@ static int nf_flow_nat_ipv6_udp(struct sk_buff *skb, unsigned int thoff, if (!udph->check) udph->check = CSUM_MANGLED_0; } - - return 0; } -static int nf_flow_nat_ipv6_l4proto(struct sk_buff *skb, struct ipv6hdr *ip6h, - unsigned int thoff, struct in6_addr *addr, - struct in6_addr *new_addr) +static void nf_flow_nat_ipv6_l4proto(struct sk_buff *skb, struct ipv6hdr *ip6h, + unsigned int thoff, struct in6_addr *addr, + struct in6_addr *new_addr) { switch (ip6h->nexthdr) { case IPPROTO_TCP: - if (nf_flow_nat_ipv6_tcp(skb, thoff, addr, new_addr) < 0) - return NF_DROP; + nf_flow_nat_ipv6_tcp(skb, thoff, addr, new_addr, ip6h); break; case IPPROTO_UDP: - if (nf_flow_nat_ipv6_udp(skb, thoff, addr, new_addr) < 0) - return NF_DROP; + nf_flow_nat_ipv6_udp(skb, thoff, addr, new_addr); break; } - - return 0; } -static int nf_flow_snat_ipv6(const struct flow_offload *flow, - struct sk_buff *skb, struct ipv6hdr *ip6h, - unsigned int thoff, - enum flow_offload_tuple_dir dir) +static void nf_flow_snat_ipv6(const struct flow_offload *flow, + struct sk_buff *skb, struct ipv6hdr *ip6h, + unsigned int thoff, + enum flow_offload_tuple_dir dir) { struct in6_addr addr, new_addr; @@ -383,17 +476,15 @@ static int nf_flow_snat_ipv6(const struct flow_offload *flow, new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6; ip6h->daddr = new_addr; break; - default: - return -1; } - return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr); + nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr); } -static int nf_flow_dnat_ipv6(const struct flow_offload *flow, - struct sk_buff *skb, struct ipv6hdr *ip6h, - unsigned int thoff, - enum flow_offload_tuple_dir dir) +static void nf_flow_dnat_ipv6(const struct flow_offload *flow, + struct sk_buff *skb, struct ipv6hdr *ip6h, + unsigned int thoff, + enum flow_offload_tuple_dir dir) { struct in6_addr addr, new_addr; @@ -408,52 +499,48 @@ static int nf_flow_dnat_ipv6(const struct flow_offload *flow, new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6; ip6h->saddr = new_addr; break; - default: - return -1; } - return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr); + nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr); } -static int nf_flow_nat_ipv6(const struct flow_offload *flow, - struct sk_buff *skb, - enum flow_offload_tuple_dir dir) +static void nf_flow_nat_ipv6(const struct flow_offload *flow, + struct sk_buff *skb, + enum flow_offload_tuple_dir dir, + struct ipv6hdr *ip6h) { - struct ipv6hdr *ip6h = ipv6_hdr(skb); unsigned int thoff = sizeof(*ip6h); - if (test_bit(NF_FLOW_SNAT, &flow->flags) && - (nf_flow_snat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 || - nf_flow_snat_ipv6(flow, skb, ipv6_hdr(skb), thoff, dir) < 0)) - return -1; - - ip6h = ipv6_hdr(skb); - if (test_bit(NF_FLOW_DNAT, &flow->flags) && - (nf_flow_dnat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 || - nf_flow_dnat_ipv6(flow, skb, ipv6_hdr(skb), thoff, dir) < 0)) - return -1; - - return 0; + if (test_bit(NF_FLOW_SNAT, &flow->flags)) { + nf_flow_snat_port(flow, skb, thoff, ip6h->nexthdr, dir); + nf_flow_snat_ipv6(flow, skb, ip6h, thoff, dir); + } + if (test_bit(NF_FLOW_DNAT, &flow->flags)) { + nf_flow_dnat_port(flow, skb, thoff, ip6h->nexthdr, dir); + nf_flow_dnat_ipv6(flow, skb, ip6h, thoff, dir); + } } static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev, - struct flow_offload_tuple *tuple) + struct flow_offload_tuple *tuple, u32 *hdrsize, + u32 offset) { - unsigned int thoff, hdrsize; struct flow_ports *ports; struct ipv6hdr *ip6h; + unsigned int thoff; - if (!pskb_may_pull(skb, sizeof(*ip6h))) + thoff = sizeof(*ip6h) + offset; + if (!pskb_may_pull(skb, thoff)) return -1; - ip6h = ipv6_hdr(skb); + ip6h = (struct ipv6hdr *)(skb_network_header(skb) + offset); switch (ip6h->nexthdr) { case IPPROTO_TCP: - hdrsize = sizeof(struct tcphdr); + *hdrsize = sizeof(struct tcphdr); break; case IPPROTO_UDP: - hdrsize = sizeof(struct udphdr); + *hdrsize = sizeof(struct udphdr); break; default: return -1; @@ -462,11 +549,10 @@ static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev, if (ip6h->hop_limit <= 1) return -1; - thoff = sizeof(*ip6h); - if (!pskb_may_pull(skb, thoff + hdrsize)) + if (!pskb_may_pull(skb, thoff + *hdrsize)) return -1; - ip6h = ipv6_hdr(skb); + ip6h = (struct ipv6hdr *)(skb_network_header(skb) + offset); ports = (struct flow_ports *)(skb_network_header(skb) + thoff); tuple->src_v6 = ip6h->saddr; @@ -476,6 +562,7 @@ static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev, tuple->l3proto = AF_INET6; tuple->l4proto = ip6h->nexthdr; tuple->iifidx = dev->ifindex; + nf_flow_tuple_encap(skb, tuple); return 0; } @@ -491,13 +578,17 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, const struct in6_addr *nexthop; struct flow_offload *flow; struct net_device *outdev; + unsigned int thoff, mtu; + u32 hdrsize, offset = 0; struct ipv6hdr *ip6h; struct rt6_info *rt; + int ret; - if (skb->protocol != htons(ETH_P_IPV6)) + if (skb->protocol != htons(ETH_P_IPV6) && + !nf_flow_skb_encap_protocol(skb, htons(ETH_P_IPV6), &offset)) return NF_ACCEPT; - if (nf_flow_tuple_ipv6(skb, state->in, &tuple) < 0) + if (nf_flow_tuple_ipv6(skb, state->in, &tuple, &hdrsize, offset) < 0) return NF_ACCEPT; tuplehash = flow_offload_lookup(flow_table, &tuple); @@ -506,48 +597,64 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, dir = tuplehash->tuple.dir; flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); - rt = (struct rt6_info *)flow->tuplehash[dir].tuple.dst_cache; - outdev = rt->dst.dev; - if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu))) + mtu = flow->tuplehash[dir].tuple.mtu + offset; + if (unlikely(nf_flow_exceeds_mtu(skb, mtu))) return NF_ACCEPT; - if (nf_flow_state_check(flow, ipv6_hdr(skb)->nexthdr, skb, - sizeof(*ip6h))) + ip6h = (struct ipv6hdr *)(skb_network_header(skb) + offset); + thoff = sizeof(*ip6h) + offset; + if (nf_flow_state_check(flow, ip6h->nexthdr, skb, thoff)) return NF_ACCEPT; - flow_offload_refresh(flow_table, flow); - - if (nf_flow_offload_dst_check(&rt->dst)) { - flow_offload_teardown(flow); - return NF_ACCEPT; + if (tuplehash->tuple.xmit_type == FLOW_OFFLOAD_XMIT_NEIGH || + tuplehash->tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM) { + rt = (struct rt6_info *)tuplehash->tuple.dst_cache; + if (!dst_check(&rt->dst, 0)) { + flow_offload_teardown(flow); + return NF_ACCEPT; + } } - if (skb_try_make_writable(skb, sizeof(*ip6h))) + if (skb_try_make_writable(skb, thoff + hdrsize)) return NF_DROP; - if (nf_flow_nat_ipv6(flow, skb, dir) < 0) - return NF_DROP; + flow_offload_refresh(flow_table, flow); + + nf_flow_encap_pop(skb, tuplehash); ip6h = ipv6_hdr(skb); + nf_flow_nat_ipv6(flow, skb, dir, ip6h); + ip6h->hop_limit--; skb->tstamp = 0; if (flow_table->flags & NF_FLOWTABLE_COUNTER) nf_ct_acct_update(flow->ct, tuplehash->tuple.dir, skb->len); - if (unlikely(dst_xfrm(&rt->dst))) { + if (unlikely(tuplehash->tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM)) { memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); IP6CB(skb)->iif = skb->dev->ifindex; IP6CB(skb)->flags = IP6SKB_FORWARDED; return nf_flow_xmit_xfrm(skb, state, &rt->dst); } - skb->dev = outdev; - nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6); - skb_dst_set_noref(skb, &rt->dst); - neigh_xmit(NEIGH_ND_TABLE, outdev, nexthop, skb); + switch (tuplehash->tuple.xmit_type) { + case FLOW_OFFLOAD_XMIT_NEIGH: + outdev = rt->dst.dev; + skb->dev = outdev; + nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6); + skb_dst_set_noref(skb, &rt->dst); + neigh_xmit(NEIGH_ND_TABLE, outdev, nexthop, skb); + ret = NF_STOLEN; + break; + case FLOW_OFFLOAD_XMIT_DIRECT: + ret = nf_flow_queue_xmit(state->net, skb, tuplehash, ETH_P_IPV6); + if (ret == NF_DROP) + flow_offload_teardown(flow); + break; + } - return NF_STOLEN; + return ret; } EXPORT_SYMBOL_GPL(nf_flow_offload_ipv6_hook); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 2a6993fa40d7..7d0d128407be 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -13,7 +13,9 @@ #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_tuple.h> -static struct workqueue_struct *nf_flow_offload_wq; +static struct workqueue_struct *nf_flow_offload_add_wq; +static struct workqueue_struct *nf_flow_offload_del_wq; +static struct workqueue_struct *nf_flow_offload_stats_wq; struct flow_offload_work { struct list_head list; @@ -175,28 +177,45 @@ static int flow_offload_eth_src(struct net *net, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule) { - const struct flow_offload_tuple *tuple = &flow->tuplehash[!dir].tuple; struct flow_action_entry *entry0 = flow_action_entry_next(flow_rule); struct flow_action_entry *entry1 = flow_action_entry_next(flow_rule); - struct net_device *dev; + const struct flow_offload_tuple *other_tuple, *this_tuple; + struct net_device *dev = NULL; + const unsigned char *addr; u32 mask, val; u16 val16; - dev = dev_get_by_index(net, tuple->iifidx); - if (!dev) - return -ENOENT; + this_tuple = &flow->tuplehash[dir].tuple; + + switch (this_tuple->xmit_type) { + case FLOW_OFFLOAD_XMIT_DIRECT: + addr = this_tuple->out.h_source; + break; + case FLOW_OFFLOAD_XMIT_NEIGH: + other_tuple = &flow->tuplehash[!dir].tuple; + dev = dev_get_by_index(net, other_tuple->iifidx); + if (!dev) + return -ENOENT; + + addr = dev->dev_addr; + break; + default: + return -EOPNOTSUPP; + } mask = ~0xffff0000; - memcpy(&val16, dev->dev_addr, 2); + memcpy(&val16, addr, 2); val = val16 << 16; flow_offload_mangle(entry0, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 4, &val, &mask); mask = ~0xffffffff; - memcpy(&val, dev->dev_addr + 2, 4); + memcpy(&val, addr + 2, 4); flow_offload_mangle(entry1, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 8, &val, &mask); - dev_put(dev); + + if (dev) + dev_put(dev); return 0; } @@ -208,27 +227,40 @@ static int flow_offload_eth_dst(struct net *net, { struct flow_action_entry *entry0 = flow_action_entry_next(flow_rule); struct flow_action_entry *entry1 = flow_action_entry_next(flow_rule); - const void *daddr = &flow->tuplehash[!dir].tuple.src_v4; + const struct flow_offload_tuple *other_tuple, *this_tuple; const struct dst_entry *dst_cache; unsigned char ha[ETH_ALEN]; struct neighbour *n; + const void *daddr; u32 mask, val; u8 nud_state; u16 val16; - dst_cache = flow->tuplehash[dir].tuple.dst_cache; - n = dst_neigh_lookup(dst_cache, daddr); - if (!n) - return -ENOENT; + this_tuple = &flow->tuplehash[dir].tuple; - read_lock_bh(&n->lock); - nud_state = n->nud_state; - ether_addr_copy(ha, n->ha); - read_unlock_bh(&n->lock); - - if (!(nud_state & NUD_VALID)) { + switch (this_tuple->xmit_type) { + case FLOW_OFFLOAD_XMIT_DIRECT: + ether_addr_copy(ha, this_tuple->out.h_dest); + break; + case FLOW_OFFLOAD_XMIT_NEIGH: + other_tuple = &flow->tuplehash[!dir].tuple; + daddr = &other_tuple->src_v4; + dst_cache = this_tuple->dst_cache; + n = dst_neigh_lookup(dst_cache, daddr); + if (!n) + return -ENOENT; + + read_lock_bh(&n->lock); + nud_state = n->nud_state; + ether_addr_copy(ha, n->ha); + read_unlock_bh(&n->lock); neigh_release(n); - return -ENOENT; + + if (!(nud_state & NUD_VALID)) + return -ENOENT; + break; + default: + return -EOPNOTSUPP; } mask = ~0xffffffff; @@ -241,7 +273,6 @@ static int flow_offload_eth_dst(struct net *net, val = val16; flow_offload_mangle(entry1, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 4, &val, &mask); - neigh_release(n); return 0; } @@ -463,27 +494,52 @@ static void flow_offload_ipv4_checksum(struct net *net, } } -static void flow_offload_redirect(const struct flow_offload *flow, +static void flow_offload_redirect(struct net *net, + const struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule) { - struct flow_action_entry *entry = flow_action_entry_next(flow_rule); - struct rtable *rt; + const struct flow_offload_tuple *this_tuple, *other_tuple; + struct flow_action_entry *entry; + struct net_device *dev; + int ifindex; + + this_tuple = &flow->tuplehash[dir].tuple; + switch (this_tuple->xmit_type) { + case FLOW_OFFLOAD_XMIT_DIRECT: + this_tuple = &flow->tuplehash[dir].tuple; + ifindex = this_tuple->out.hw_ifidx; + break; + case FLOW_OFFLOAD_XMIT_NEIGH: + other_tuple = &flow->tuplehash[!dir].tuple; + ifindex = other_tuple->iifidx; + break; + default: + return; + } - rt = (struct rtable *)flow->tuplehash[dir].tuple.dst_cache; + dev = dev_get_by_index(net, ifindex); + if (!dev) + return; + + entry = flow_action_entry_next(flow_rule); entry->id = FLOW_ACTION_REDIRECT; - entry->dev = rt->dst.dev; - dev_hold(rt->dst.dev); + entry->dev = dev; } static void flow_offload_encap_tunnel(const struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule) { + const struct flow_offload_tuple *this_tuple; struct flow_action_entry *entry; struct dst_entry *dst; - dst = flow->tuplehash[dir].tuple.dst_cache; + this_tuple = &flow->tuplehash[dir].tuple; + if (this_tuple->xmit_type == FLOW_OFFLOAD_XMIT_DIRECT) + return; + + dst = this_tuple->dst_cache; if (dst && dst->lwtstate) { struct ip_tunnel_info *tun_info; @@ -500,10 +556,15 @@ static void flow_offload_decap_tunnel(const struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule) { + const struct flow_offload_tuple *other_tuple; struct flow_action_entry *entry; struct dst_entry *dst; - dst = flow->tuplehash[!dir].tuple.dst_cache; + other_tuple = &flow->tuplehash[!dir].tuple; + if (other_tuple->xmit_type == FLOW_OFFLOAD_XMIT_DIRECT) + return; + + dst = other_tuple->dst_cache; if (dst && dst->lwtstate) { struct ip_tunnel_info *tun_info; @@ -515,10 +576,14 @@ static void flow_offload_decap_tunnel(const struct flow_offload *flow, } } -int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow, - enum flow_offload_tuple_dir dir, - struct nf_flow_rule *flow_rule) +static int +nf_flow_rule_route_common(struct net *net, const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct nf_flow_rule *flow_rule) { + const struct flow_offload_tuple *other_tuple; + int i; + flow_offload_decap_tunnel(flow, dir, flow_rule); flow_offload_encap_tunnel(flow, dir, flow_rule); @@ -526,6 +591,39 @@ int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow, flow_offload_eth_dst(net, flow, dir, flow_rule) < 0) return -1; + other_tuple = &flow->tuplehash[!dir].tuple; + + for (i = 0; i < other_tuple->encap_num; i++) { + struct flow_action_entry *entry; + + if (other_tuple->in_vlan_ingress & BIT(i)) + continue; + + entry = flow_action_entry_next(flow_rule); + + switch (other_tuple->encap[i].proto) { + case htons(ETH_P_PPP_SES): + entry->id = FLOW_ACTION_PPPOE_PUSH; + entry->pppoe.sid = other_tuple->encap[i].id; + break; + case htons(ETH_P_8021Q): + entry->id = FLOW_ACTION_VLAN_PUSH; + entry->vlan.vid = other_tuple->encap[i].id; + entry->vlan.proto = other_tuple->encap[i].proto; + break; + } + } + + return 0; +} + +int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct nf_flow_rule *flow_rule) +{ + if (nf_flow_rule_route_common(net, flow, dir, flow_rule) < 0) + return -1; + if (test_bit(NF_FLOW_SNAT, &flow->flags)) { flow_offload_ipv4_snat(net, flow, dir, flow_rule); flow_offload_port_snat(net, flow, dir, flow_rule); @@ -538,7 +636,7 @@ int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow, test_bit(NF_FLOW_DNAT, &flow->flags)) flow_offload_ipv4_checksum(net, flow, flow_rule); - flow_offload_redirect(flow, dir, flow_rule); + flow_offload_redirect(net, flow, dir, flow_rule); return 0; } @@ -548,11 +646,7 @@ int nf_flow_rule_route_ipv6(struct net *net, const struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule) { - flow_offload_decap_tunnel(flow, dir, flow_rule); - flow_offload_encap_tunnel(flow, dir, flow_rule); - - if (flow_offload_eth_src(net, flow, dir, flow_rule) < 0 || - flow_offload_eth_dst(net, flow, dir, flow_rule) < 0) + if (nf_flow_rule_route_common(net, flow, dir, flow_rule) < 0) return -1; if (test_bit(NF_FLOW_SNAT, &flow->flags)) { @@ -564,7 +658,7 @@ int nf_flow_rule_route_ipv6(struct net *net, const struct flow_offload *flow, flow_offload_port_dnat(net, flow, dir, flow_rule); } - flow_offload_redirect(flow, dir, flow_rule); + flow_offload_redirect(net, flow, dir, flow_rule); return 0; } @@ -578,10 +672,10 @@ nf_flow_offload_rule_alloc(struct net *net, enum flow_offload_tuple_dir dir) { const struct nf_flowtable *flowtable = offload->flowtable; + const struct flow_offload_tuple *tuple, *other_tuple; const struct flow_offload *flow = offload->flow; - const struct flow_offload_tuple *tuple; + struct dst_entry *other_dst = NULL; struct nf_flow_rule *flow_rule; - struct dst_entry *other_dst; int err = -ENOMEM; flow_rule = kzalloc(sizeof(*flow_rule), GFP_KERNEL); @@ -597,7 +691,10 @@ nf_flow_offload_rule_alloc(struct net *net, flow_rule->rule->match.key = &flow_rule->match.key; tuple = &flow->tuplehash[dir].tuple; - other_dst = flow->tuplehash[!dir].tuple.dst_cache; + other_tuple = &flow->tuplehash[!dir].tuple; + if (other_tuple->xmit_type == FLOW_OFFLOAD_XMIT_NEIGH) + other_dst = other_tuple->dst_cache; + err = nf_flow_rule_match(&flow_rule->match, tuple, other_dst); if (err < 0) goto err_flow_match; @@ -826,7 +923,12 @@ static void flow_offload_work_handler(struct work_struct *work) static void flow_offload_queue_work(struct flow_offload_work *offload) { - queue_work(nf_flow_offload_wq, &offload->work); + if (offload->cmd == FLOW_CLS_REPLACE) + queue_work(nf_flow_offload_add_wq, &offload->work); + else if (offload->cmd == FLOW_CLS_DESTROY) + queue_work(nf_flow_offload_del_wq, &offload->work); + else + queue_work(nf_flow_offload_stats_wq, &offload->work); } static struct flow_offload_work * @@ -898,8 +1000,11 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable, void nf_flow_table_offload_flush(struct nf_flowtable *flowtable) { - if (nf_flowtable_hw_offload(flowtable)) - flush_workqueue(nf_flow_offload_wq); + if (nf_flowtable_hw_offload(flowtable)) { + flush_workqueue(nf_flow_offload_add_wq); + flush_workqueue(nf_flow_offload_del_wq); + flush_workqueue(nf_flow_offload_stats_wq); + } } static int nf_flow_table_block_setup(struct nf_flowtable *flowtable, @@ -1011,15 +1116,33 @@ EXPORT_SYMBOL_GPL(nf_flow_table_offload_setup); int nf_flow_table_offload_init(void) { - nf_flow_offload_wq = alloc_workqueue("nf_flow_table_offload", - WQ_UNBOUND, 0); - if (!nf_flow_offload_wq) + nf_flow_offload_add_wq = alloc_workqueue("nf_ft_offload_add", + WQ_UNBOUND | WQ_SYSFS, 0); + if (!nf_flow_offload_add_wq) return -ENOMEM; + nf_flow_offload_del_wq = alloc_workqueue("nf_ft_offload_del", + WQ_UNBOUND | WQ_SYSFS, 0); + if (!nf_flow_offload_del_wq) + goto err_del_wq; + + nf_flow_offload_stats_wq = alloc_workqueue("nf_ft_offload_stats", + WQ_UNBOUND | WQ_SYSFS, 0); + if (!nf_flow_offload_stats_wq) + goto err_stats_wq; + return 0; + +err_stats_wq: + destroy_workqueue(nf_flow_offload_del_wq); +err_del_wq: + destroy_workqueue(nf_flow_offload_add_wq); + return -ENOMEM; } void nf_flow_table_offload_exit(void) { - destroy_workqueue(nf_flow_offload_wq); + destroy_workqueue(nf_flow_offload_add_wq); + destroy_workqueue(nf_flow_offload_del_wq); + destroy_workqueue(nf_flow_offload_stats_wq); } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index f57f1a6ba96f..fc2526b8bd55 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -900,6 +900,12 @@ static void nf_tables_table_disable(struct net *net, struct nft_table *table) nft_table_disable(net, table, 0); } +enum { + NFT_TABLE_STATE_UNCHANGED = 0, + NFT_TABLE_STATE_DORMANT, + NFT_TABLE_STATE_WAKEUP +}; + static int nf_tables_updtable(struct nft_ctx *ctx) { struct nft_trans *trans; @@ -929,19 +935,17 @@ static int nf_tables_updtable(struct nft_ctx *ctx) if ((flags & NFT_TABLE_F_DORMANT) && !(ctx->table->flags & NFT_TABLE_F_DORMANT)) { - nft_trans_table_enable(trans) = false; + nft_trans_table_state(trans) = NFT_TABLE_STATE_DORMANT; } else if (!(flags & NFT_TABLE_F_DORMANT) && ctx->table->flags & NFT_TABLE_F_DORMANT) { - ctx->table->flags &= ~NFT_TABLE_F_DORMANT; ret = nf_tables_table_enable(ctx->net, ctx->table); if (ret >= 0) - nft_trans_table_enable(trans) = true; - else - ctx->table->flags |= NFT_TABLE_F_DORMANT; + nft_trans_table_state(trans) = NFT_TABLE_STATE_WAKEUP; } if (ret < 0) goto err; + nft_trans_table_flags(trans) = flags; nft_trans_table_update(trans) = true; list_add_tail(&trans->list, &ctx->net->nft.commit_list); return 0; @@ -8086,11 +8090,10 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) switch (trans->msg_type) { case NFT_MSG_NEWTABLE: if (nft_trans_table_update(trans)) { - if (!nft_trans_table_enable(trans)) { - nf_tables_table_disable(net, - trans->ctx.table); - trans->ctx.table->flags |= NFT_TABLE_F_DORMANT; - } + if (nft_trans_table_state(trans) == NFT_TABLE_STATE_DORMANT) + nf_tables_table_disable(net, trans->ctx.table); + + trans->ctx.table->flags = nft_trans_table_flags(trans); } else { nft_clear(net, trans->ctx.table); } @@ -8303,11 +8306,9 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) switch (trans->msg_type) { case NFT_MSG_NEWTABLE: if (nft_trans_table_update(trans)) { - if (nft_trans_table_enable(trans)) { - nf_tables_table_disable(net, - trans->ctx.table); - trans->ctx.table->flags |= NFT_TABLE_F_DORMANT; - } + if (nft_trans_table_state(trans) == NFT_TABLE_STATE_WAKEUP) + nf_tables_table_disable(net, trans->ctx.table); + nft_trans_destroy(trans); } else { list_del_rcu(&trans->ctx.table->list); @@ -8577,6 +8578,7 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, data->verdict.chain); if (err < 0) return err; + break; default: break; } diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 882fe8648653..0592a9456084 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -527,6 +527,7 @@ static void __nft_ct_set_destroy(const struct nft_ctx *ctx, struct nft_ct *priv) case NFT_CT_ZONE: if (--nft_ct_pcpu_template_refcnt == 0) nft_ct_tmpl_put_pcpu(); + break; #endif default: break; diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 3a6c84fb2c90..4843dd2b410c 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -19,10 +19,205 @@ struct nft_flow_offload { struct nft_flowtable *flowtable; }; +static enum flow_offload_xmit_type nft_xmit_type(struct dst_entry *dst) +{ + if (dst_xfrm(dst)) + return FLOW_OFFLOAD_XMIT_XFRM; + + return FLOW_OFFLOAD_XMIT_NEIGH; +} + +static void nft_default_forward_path(struct nf_flow_route *route, + struct dst_entry *dst_cache, + enum ip_conntrack_dir dir) +{ + route->tuple[!dir].in.ifindex = dst_cache->dev->ifindex; + route->tuple[dir].dst = dst_cache; + route->tuple[dir].xmit_type = nft_xmit_type(dst_cache); +} + +static int nft_dev_fill_forward_path(const struct nf_flow_route *route, + const struct dst_entry *dst_cache, + const struct nf_conn *ct, + enum ip_conntrack_dir dir, u8 *ha, + struct net_device_path_stack *stack) +{ + const void *daddr = &ct->tuplehash[!dir].tuple.src.u3; + struct net_device *dev = dst_cache->dev; + struct neighbour *n; + u8 nud_state; + + n = dst_neigh_lookup(dst_cache, daddr); + if (!n) + return -1; + + read_lock_bh(&n->lock); + nud_state = n->nud_state; + ether_addr_copy(ha, n->ha); + read_unlock_bh(&n->lock); + neigh_release(n); + + if (!(nud_state & NUD_VALID)) + return -1; + + return dev_fill_forward_path(dev, ha, stack); +} + +struct nft_forward_info { + const struct net_device *indev; + const struct net_device *outdev; + const struct net_device *hw_outdev; + struct id { + __u16 id; + __be16 proto; + } encap[NF_FLOW_TABLE_ENCAP_MAX]; + u8 num_encaps; + u8 ingress_vlans; + u8 h_source[ETH_ALEN]; + u8 h_dest[ETH_ALEN]; + enum flow_offload_xmit_type xmit_type; +}; + +static bool nft_is_valid_ether_device(const struct net_device *dev) +{ + if (!dev || (dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || + dev->addr_len != ETH_ALEN || !is_valid_ether_addr(dev->dev_addr)) + return false; + + return true; +} + +static void nft_dev_path_info(const struct net_device_path_stack *stack, + struct nft_forward_info *info, + unsigned char *ha, struct nf_flowtable *flowtable) +{ + const struct net_device_path *path; + int i; + + memcpy(info->h_dest, ha, ETH_ALEN); + + for (i = 0; i < stack->num_paths; i++) { + path = &stack->path[i]; + switch (path->type) { + case DEV_PATH_ETHERNET: + case DEV_PATH_DSA: + case DEV_PATH_VLAN: + case DEV_PATH_PPPOE: + info->indev = path->dev; + if (is_zero_ether_addr(info->h_source)) + memcpy(info->h_source, path->dev->dev_addr, ETH_ALEN); + + if (path->type == DEV_PATH_ETHERNET) + break; + if (path->type == DEV_PATH_DSA) { + i = stack->num_paths; + break; + } + + /* DEV_PATH_VLAN and DEV_PATH_PPPOE */ + if (info->num_encaps >= NF_FLOW_TABLE_ENCAP_MAX) { + info->indev = NULL; + break; + } + info->outdev = path->dev; + info->encap[info->num_encaps].id = path->encap.id; + info->encap[info->num_encaps].proto = path->encap.proto; + info->num_encaps++; + if (path->type == DEV_PATH_PPPOE) + memcpy(info->h_dest, path->encap.h_dest, ETH_ALEN); + break; + case DEV_PATH_BRIDGE: + if (is_zero_ether_addr(info->h_source)) + memcpy(info->h_source, path->dev->dev_addr, ETH_ALEN); + + switch (path->bridge.vlan_mode) { + case DEV_PATH_BR_VLAN_UNTAG_HW: + info->ingress_vlans |= BIT(info->num_encaps - 1); + break; + case DEV_PATH_BR_VLAN_TAG: + info->encap[info->num_encaps].id = path->bridge.vlan_id; + info->encap[info->num_encaps].proto = path->bridge.vlan_proto; + info->num_encaps++; + break; + case DEV_PATH_BR_VLAN_UNTAG: + info->num_encaps--; + break; + case DEV_PATH_BR_VLAN_KEEP: + break; + } + info->xmit_type = FLOW_OFFLOAD_XMIT_DIRECT; + break; + default: + info->indev = NULL; + break; + } + } + if (!info->outdev) + info->outdev = info->indev; + + info->hw_outdev = info->indev; + + if (nf_flowtable_hw_offload(flowtable) && + nft_is_valid_ether_device(info->indev)) + info->xmit_type = FLOW_OFFLOAD_XMIT_DIRECT; +} + +static bool nft_flowtable_find_dev(const struct net_device *dev, + struct nft_flowtable *ft) +{ + struct nft_hook *hook; + bool found = false; + + list_for_each_entry_rcu(hook, &ft->hook_list, list) { + if (hook->ops.dev != dev) + continue; + + found = true; + break; + } + + return found; +} + +static void nft_dev_forward_path(struct nf_flow_route *route, + const struct nf_conn *ct, + enum ip_conntrack_dir dir, + struct nft_flowtable *ft) +{ + const struct dst_entry *dst = route->tuple[dir].dst; + struct net_device_path_stack stack; + struct nft_forward_info info = {}; + unsigned char ha[ETH_ALEN]; + int i; + + if (nft_dev_fill_forward_path(route, dst, ct, dir, ha, &stack) >= 0) + nft_dev_path_info(&stack, &info, ha, &ft->data); + + if (!info.indev || !nft_flowtable_find_dev(info.indev, ft)) + return; + + route->tuple[!dir].in.ifindex = info.indev->ifindex; + for (i = 0; i < info.num_encaps; i++) { + route->tuple[!dir].in.encap[i].id = info.encap[i].id; + route->tuple[!dir].in.encap[i].proto = info.encap[i].proto; + } + route->tuple[!dir].in.num_encaps = info.num_encaps; + route->tuple[!dir].in.ingress_vlans = info.ingress_vlans; + + if (info.xmit_type == FLOW_OFFLOAD_XMIT_DIRECT) { + memcpy(route->tuple[dir].out.h_source, info.h_source, ETH_ALEN); + memcpy(route->tuple[dir].out.h_dest, info.h_dest, ETH_ALEN); + route->tuple[dir].out.ifindex = info.outdev->ifindex; + route->tuple[dir].out.hw_ifindex = info.hw_outdev->ifindex; + route->tuple[dir].xmit_type = info.xmit_type; + } +} + static int nft_flow_route(const struct nft_pktinfo *pkt, const struct nf_conn *ct, struct nf_flow_route *route, - enum ip_conntrack_dir dir) + enum ip_conntrack_dir dir, + struct nft_flowtable *ft) { struct dst_entry *this_dst = skb_dst(pkt->skb); struct dst_entry *other_dst = NULL; @@ -44,8 +239,14 @@ static int nft_flow_route(const struct nft_pktinfo *pkt, if (!other_dst) return -ENOENT; - route->tuple[dir].dst = this_dst; - route->tuple[!dir].dst = other_dst; + nft_default_forward_path(route, this_dst, dir); + nft_default_forward_path(route, other_dst, !dir); + + if (route->tuple[dir].xmit_type == FLOW_OFFLOAD_XMIT_NEIGH && + route->tuple[!dir].xmit_type == FLOW_OFFLOAD_XMIT_NEIGH) { + nft_dev_forward_path(route, ct, dir, ft); + nft_dev_forward_path(route, ct, !dir, ft); + } return 0; } @@ -74,8 +275,8 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, struct nft_flow_offload *priv = nft_expr_priv(expr); struct nf_flowtable *flowtable = &priv->flowtable->data; struct tcphdr _tcph, *tcph = NULL; + struct nf_flow_route route = {}; enum ip_conntrack_info ctinfo; - struct nf_flow_route route; struct flow_offload *flow; enum ip_conntrack_dir dir; struct nf_conn *ct; @@ -112,7 +313,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, goto out; dir = CTINFO2DIR(ctinfo); - if (nft_flow_route(pkt, ct, &route, dir) < 0) + if (nft_flow_route(pkt, ct, &route, dir, priv->flowtable) < 0) goto err_flow_route; flow = flow_offload_alloc(ct); diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 4ed7e52c7012..88deb5b41429 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -497,10 +497,12 @@ void ovs_vport_send(struct vport *vport, struct sk_buff *skb, u8 mac_proto) if (unlikely(packet_length(skb, vport->dev) > mtu && !skb_is_gso(skb))) { - net_warn_ratelimited("%s: dropped over-mtu packet: %d > %d\n", - vport->dev->name, - packet_length(skb, vport->dev), mtu); vport->dev->stats.tx_errors++; + if (vport->dev->flags & IFF_UP) + net_warn_ratelimited("%s: dropped over-mtu packet: " + "%d > %d\n", vport->dev->name, + packet_length(skb, vport->dev), + mtu); goto drop; } diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h index 1eb7495ac5b4..8a930ca6d6b1 100644 --- a/net/openvswitch/vport.h +++ b/net/openvswitch/vport.h @@ -20,7 +20,7 @@ struct vport; struct vport_parms; -/* The following definitions are for users of the vport subsytem: */ +/* The following definitions are for users of the vport subsystem: */ int ovs_vport_init(void); void ovs_vport_exit(void); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index e24b2841c643..118d585337d7 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2057,7 +2057,7 @@ static int packet_rcv_vnet(struct msghdr *msg, const struct sk_buff *skb, * and skb->cb are mangled. It works because (and until) packets * falling here are owned by current CPU. Output packets are cloned * by dev_queue_xmit_nit(), input packets are processed by net_bh - * sequencially, so that if we return skb to original state on exit, + * sequentially, so that if we return skb to original state on exit, * we will not harm anyone. */ diff --git a/net/psample/psample.c b/net/psample/psample.c index 482c07f2766b..118d5d2a81a0 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -8,6 +8,7 @@ #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/module.h> +#include <linux/timekeeping.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/netlink.h> @@ -356,9 +357,12 @@ static int psample_tunnel_meta_len(struct ip_tunnel_info *tun_info) #endif void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, - u32 trunc_size, int in_ifindex, int out_ifindex, - u32 sample_rate) + u32 sample_rate, const struct psample_metadata *md) { + ktime_t tstamp = ktime_get_real(); + int out_ifindex = md->out_ifindex; + int in_ifindex = md->in_ifindex; + u32 trunc_size = md->trunc_size; #ifdef CONFIG_INET struct ip_tunnel_info *tun_info; #endif @@ -370,10 +374,15 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, meta_len = (in_ifindex ? nla_total_size(sizeof(u16)) : 0) + (out_ifindex ? nla_total_size(sizeof(u16)) : 0) + + (md->out_tc_valid ? nla_total_size(sizeof(u16)) : 0) + + (md->out_tc_occ_valid ? nla_total_size_64bit(sizeof(u64)) : 0) + + (md->latency_valid ? nla_total_size_64bit(sizeof(u64)) : 0) + nla_total_size(sizeof(u32)) + /* sample_rate */ nla_total_size(sizeof(u32)) + /* orig_size */ nla_total_size(sizeof(u32)) + /* group_num */ - nla_total_size(sizeof(u32)); /* seq */ + nla_total_size(sizeof(u32)) + /* seq */ + nla_total_size_64bit(sizeof(u64)) + /* timestamp */ + nla_total_size(sizeof(u16)); /* protocol */ #ifdef CONFIG_INET tun_info = skb_tunnel_info(skb); @@ -423,6 +432,36 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, if (unlikely(ret < 0)) goto error; + if (md->out_tc_valid) { + ret = nla_put_u16(nl_skb, PSAMPLE_ATTR_OUT_TC, md->out_tc); + if (unlikely(ret < 0)) + goto error; + } + + if (md->out_tc_occ_valid) { + ret = nla_put_u64_64bit(nl_skb, PSAMPLE_ATTR_OUT_TC_OCC, + md->out_tc_occ, PSAMPLE_ATTR_PAD); + if (unlikely(ret < 0)) + goto error; + } + + if (md->latency_valid) { + ret = nla_put_u64_64bit(nl_skb, PSAMPLE_ATTR_LATENCY, + md->latency, PSAMPLE_ATTR_PAD); + if (unlikely(ret < 0)) + goto error; + } + + ret = nla_put_u64_64bit(nl_skb, PSAMPLE_ATTR_TIMESTAMP, + ktime_to_ns(tstamp), PSAMPLE_ATTR_PAD); + if (unlikely(ret < 0)) + goto error; + + ret = nla_put_u16(nl_skb, PSAMPLE_ATTR_PROTO, + be16_to_cpu(skb->protocol)); + if (unlikely(ret < 0)) + goto error; + if (data_len) { int nla_len = nla_total_size(data_len); struct nlattr *nla; diff --git a/net/rds/recv.c b/net/rds/recv.c index aba4afe4dfed..4db109fb6ec2 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -722,8 +722,6 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, if (msg->msg_name) { if (ipv6_addr_v4mapped(&inc->i_saddr)) { - sin = (struct sockaddr_in *)msg->msg_name; - sin->sin_family = AF_INET; sin->sin_port = inc->i_hdr.h_sport; sin->sin_addr.s_addr = @@ -731,8 +729,6 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); msg->msg_namelen = sizeof(*sin); } else { - sin6 = (struct sockaddr_in6 *)msg->msg_name; - sin6->sin6_family = AF_INET6; sin6->sin6_port = inc->i_hdr.h_sport; sin6->sin6_addr = inc->i_saddr; diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index 6e35703ff353..c0e04c261a15 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -347,6 +347,7 @@ static int rose_del_node(struct rose_route_struct *rose_route, case 1: rose_node->neighbour[1] = rose_node->neighbour[2]; + break; case 2: break; } @@ -508,6 +509,7 @@ void rose_rt_device_down(struct net_device *dev) fallthrough; case 1: t->neighbour[1] = t->neighbour[2]; + break; case 2: break; } diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 8d8452b1cdd4..0fab8de176d2 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -42,6 +42,8 @@ static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { [TCA_POLICE_RESULT] = { .type = NLA_U32 }, [TCA_POLICE_RATE64] = { .type = NLA_U64 }, [TCA_POLICE_PEAKRATE64] = { .type = NLA_U64 }, + [TCA_POLICE_PKTRATE64] = { .type = NLA_U64, .min = 1 }, + [TCA_POLICE_PKTBURST64] = { .type = NLA_U64, .min = 1 }, }; static int tcf_police_init(struct net *net, struct nlattr *nla, @@ -61,6 +63,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, bool exists = false; u32 index; u64 rate64, prate64; + u64 pps, ppsburst; if (nla == NULL) return -EINVAL; @@ -142,6 +145,21 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, } } + if ((tb[TCA_POLICE_PKTRATE64] && !tb[TCA_POLICE_PKTBURST64]) || + (!tb[TCA_POLICE_PKTRATE64] && tb[TCA_POLICE_PKTBURST64])) { + NL_SET_ERR_MSG(extack, + "Both or neither packet-per-second burst and rate must be provided"); + err = -EINVAL; + goto failure; + } + + if (tb[TCA_POLICE_PKTRATE64] && R_tab) { + NL_SET_ERR_MSG(extack, + "packet-per-second and byte-per-second rate limits not allowed in same action"); + err = -EINVAL; + goto failure; + } + new = kzalloc(sizeof(*new), GFP_KERNEL); if (unlikely(!new)) { err = -ENOMEM; @@ -183,6 +201,14 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, if (tb[TCA_POLICE_AVRATE]) new->tcfp_ewma_rate = nla_get_u32(tb[TCA_POLICE_AVRATE]); + if (tb[TCA_POLICE_PKTRATE64]) { + pps = nla_get_u64(tb[TCA_POLICE_PKTRATE64]); + ppsburst = nla_get_u64(tb[TCA_POLICE_PKTBURST64]); + new->pps_present = true; + new->tcfp_pkt_burst = PSCHED_TICKS2NS(ppsburst); + psched_ppscfg_precompute(&new->ppsrate, pps); + } + spin_lock_bh(&police->tcf_lock); spin_lock_bh(&police->tcfp_lock); police->tcfp_t_c = ktime_get_ns(); @@ -217,8 +243,8 @@ static int tcf_police_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_police *police = to_police(a); + s64 now, toks, ppstoks = 0, ptoks = 0; struct tcf_police_params *p; - s64 now, toks, ptoks = 0; int ret; tcf_lastuse_update(&police->tcf_tm); @@ -236,7 +262,7 @@ static int tcf_police_act(struct sk_buff *skb, const struct tc_action *a, } if (qdisc_pkt_len(skb) <= p->tcfp_mtu) { - if (!p->rate_present) { + if (!p->rate_present && !p->pps_present) { ret = p->tcfp_result; goto end; } @@ -251,14 +277,23 @@ static int tcf_police_act(struct sk_buff *skb, const struct tc_action *a, ptoks -= (s64)psched_l2t_ns(&p->peak, qdisc_pkt_len(skb)); } - toks += police->tcfp_toks; - if (toks > p->tcfp_burst) - toks = p->tcfp_burst; - toks -= (s64)psched_l2t_ns(&p->rate, qdisc_pkt_len(skb)); - if ((toks|ptoks) >= 0) { + if (p->rate_present) { + toks += police->tcfp_toks; + if (toks > p->tcfp_burst) + toks = p->tcfp_burst; + toks -= (s64)psched_l2t_ns(&p->rate, qdisc_pkt_len(skb)); + } else if (p->pps_present) { + ppstoks = min_t(s64, now - police->tcfp_t_c, p->tcfp_pkt_burst); + ppstoks += police->tcfp_pkttoks; + if (ppstoks > p->tcfp_pkt_burst) + ppstoks = p->tcfp_pkt_burst; + ppstoks -= (s64)psched_pkt2t_ns(&p->ppsrate, 1); + } + if ((toks | ptoks | ppstoks) >= 0) { police->tcfp_t_c = now; police->tcfp_toks = toks; police->tcfp_ptoks = ptoks; + police->tcfp_pkttoks = ppstoks; spin_unlock_bh(&police->tcfp_lock); ret = p->tcfp_result; goto inc_drops; @@ -331,6 +366,16 @@ static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a, TCA_POLICE_PAD)) goto nla_put_failure; } + if (p->pps_present) { + if (nla_put_u64_64bit(skb, TCA_POLICE_PKTRATE64, + police->params->ppsrate.rate_pkts_ps, + TCA_POLICE_PAD)) + goto nla_put_failure; + if (nla_put_u64_64bit(skb, TCA_POLICE_PKTBURST64, + PSCHED_NS2TICKS(p->tcfp_pkt_burst), + TCA_POLICE_PAD)) + goto nla_put_failure; + } if (nla_put(skb, TCA_POLICE_TBF, sizeof(opt), &opt)) goto nla_put_failure; if (p->tcfp_result && diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 3ebf9ede3cf1..6a0c16e4351d 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -158,10 +158,8 @@ static int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a, { struct tcf_sample *s = to_sample(a); struct psample_group *psample_group; + struct psample_metadata md = {}; int retval; - int size; - int iif; - int oif; tcf_lastuse_update(&s->tcf_tm); bstats_cpu_update(this_cpu_ptr(s->common.cpu_bstats), skb); @@ -172,20 +170,18 @@ static int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a, /* randomly sample packets according to rate */ if (psample_group && (prandom_u32() % s->rate == 0)) { if (!skb_at_tc_ingress(skb)) { - iif = skb->skb_iif; - oif = skb->dev->ifindex; + md.in_ifindex = skb->skb_iif; + md.out_ifindex = skb->dev->ifindex; } else { - iif = skb->dev->ifindex; - oif = 0; + md.in_ifindex = skb->dev->ifindex; } /* on ingress, the mac header gets popped, so push it back */ if (skb_at_tc_ingress(skb) && tcf_sample_dev_ok_push(skb->dev)) skb_push(skb, skb->mac_len); - size = s->truncate ? s->trunc_size : skb->len; - psample_sample_packet(psample_group, skb, size, iif, oif, - s->rate); + md.trunc_size = s->truncate ? s->trunc_size : skb->len; + psample_sample_packet(psample_group, skb, s->rate, &md); if (skb_at_tc_ingress(skb) && tcf_sample_dev_ok_push(skb->dev)) skb_pull(skb, skb->mac_len); @@ -194,6 +190,16 @@ static int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a, return retval; } +static void tcf_sample_stats_update(struct tc_action *a, u64 bytes, u64 packets, + u64 drops, u64 lastuse, bool hw) +{ + struct tcf_sample *s = to_sample(a); + struct tcf_t *tm = &s->tcf_tm; + + tcf_action_update_stats(a, bytes, packets, drops, hw); + tm->lastuse = max_t(u64, tm->lastuse, lastuse); +} + static int tcf_sample_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { @@ -280,6 +286,7 @@ static struct tc_action_ops act_sample_ops = { .id = TCA_ID_SAMPLE, .owner = THIS_MODULE, .act = tcf_sample_act, + .stats_update = tcf_sample_stats_update, .dump = tcf_sample_dump, .init = tcf_sample_init, .cleanup = tcf_sample_cleanup, diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 13341e7fb077..d3db70865d66 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -3662,6 +3662,9 @@ int tc_setup_flow_action(struct flow_action *flow_action, entry->police.burst = tcf_police_burst(act); entry->police.rate_bytes_ps = tcf_police_rate_bytes_ps(act); + entry->police.burst_pkt = tcf_police_burst_pkt(act); + entry->police.rate_pkt_ps = + tcf_police_rate_pkt_ps(act); entry->police.mtu = tcf_police_tcfp_mtu(act); entry->police.index = act->tcfa_index; } else if (is_tcf_ct(act)) { diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index c69a4ba9c33f..d7869a984881 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -209,16 +209,16 @@ static bool fl_range_port_dst_cmp(struct cls_fl_filter *filter, struct fl_flow_key *key, struct fl_flow_key *mkey) { - __be16 min_mask, max_mask, min_val, max_val; + u16 min_mask, max_mask, min_val, max_val; - min_mask = htons(filter->mask->key.tp_range.tp_min.dst); - max_mask = htons(filter->mask->key.tp_range.tp_max.dst); - min_val = htons(filter->key.tp_range.tp_min.dst); - max_val = htons(filter->key.tp_range.tp_max.dst); + min_mask = ntohs(filter->mask->key.tp_range.tp_min.dst); + max_mask = ntohs(filter->mask->key.tp_range.tp_max.dst); + min_val = ntohs(filter->key.tp_range.tp_min.dst); + max_val = ntohs(filter->key.tp_range.tp_max.dst); if (min_mask && max_mask) { - if (htons(key->tp_range.tp.dst) < min_val || - htons(key->tp_range.tp.dst) > max_val) + if (ntohs(key->tp_range.tp.dst) < min_val || + ntohs(key->tp_range.tp.dst) > max_val) return false; /* skb does not have min and max values */ @@ -232,16 +232,16 @@ static bool fl_range_port_src_cmp(struct cls_fl_filter *filter, struct fl_flow_key *key, struct fl_flow_key *mkey) { - __be16 min_mask, max_mask, min_val, max_val; + u16 min_mask, max_mask, min_val, max_val; - min_mask = htons(filter->mask->key.tp_range.tp_min.src); - max_mask = htons(filter->mask->key.tp_range.tp_max.src); - min_val = htons(filter->key.tp_range.tp_min.src); - max_val = htons(filter->key.tp_range.tp_max.src); + min_mask = ntohs(filter->mask->key.tp_range.tp_min.src); + max_mask = ntohs(filter->mask->key.tp_range.tp_max.src); + min_val = ntohs(filter->key.tp_range.tp_min.src); + max_val = ntohs(filter->key.tp_range.tp_max.src); if (min_mask && max_mask) { - if (htons(key->tp_range.tp.src) < min_val || - htons(key->tp_range.tp.src) > max_val) + if (ntohs(key->tp_range.tp.src) < min_val || + ntohs(key->tp_range.tp.src) > max_val) return false; /* skb does not have min and max values */ @@ -783,16 +783,16 @@ static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key, TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_max.src)); if (mask->tp_range.tp_min.dst && mask->tp_range.tp_max.dst && - htons(key->tp_range.tp_max.dst) <= - htons(key->tp_range.tp_min.dst)) { + ntohs(key->tp_range.tp_max.dst) <= + ntohs(key->tp_range.tp_min.dst)) { NL_SET_ERR_MSG_ATTR(extack, tb[TCA_FLOWER_KEY_PORT_DST_MIN], "Invalid destination port range (min must be strictly smaller than max)"); return -EINVAL; } if (mask->tp_range.tp_min.src && mask->tp_range.tp_max.src && - htons(key->tp_range.tp_max.src) <= - htons(key->tp_range.tp_min.src)) { + ntohs(key->tp_range.tp_max.src) <= + ntohs(key->tp_range.tp_min.src)) { NL_SET_ERR_MSG_ATTR(extack, tb[TCA_FLOWER_KEY_PORT_SRC_MIN], "Invalid source port range (min must be strictly smaller than max)"); @@ -1044,8 +1044,8 @@ static int fl_set_key_flags(struct nlattr **tb, u32 *flags_key, return -EINVAL; } - key = be32_to_cpu(nla_get_u32(tb[TCA_FLOWER_KEY_FLAGS])); - mask = be32_to_cpu(nla_get_u32(tb[TCA_FLOWER_KEY_FLAGS_MASK])); + key = be32_to_cpu(nla_get_be32(tb[TCA_FLOWER_KEY_FLAGS])); + mask = be32_to_cpu(nla_get_be32(tb[TCA_FLOWER_KEY_FLAGS_MASK])); *flags_key = 0; *flags_mask = 0; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 320b3d31fa97..b79a7e27bb31 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -263,7 +263,7 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) /* * Step 3+n. If classifier selected a link sharing class, * apply agency specific classifier. - * Repeat this procdure until we hit a leaf node. + * Repeat this procedure until we hit a leaf node. */ head = cl; } @@ -859,7 +859,7 @@ cbq_dequeue(struct Qdisc *sch) return NULL; } -/* CBQ class maintanance routines */ +/* CBQ class maintenance routines */ static void cbq_adjust_levels(struct cbq_class *this) { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 49eae93d1489..44991ea726fc 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -1325,6 +1325,48 @@ void dev_shutdown(struct net_device *dev) WARN_ON(timer_pending(&dev->watchdog_timer)); } +/** + * psched_ratecfg_precompute__() - Pre-compute values for reciprocal division + * @rate: Rate to compute reciprocal division values of + * @mult: Multiplier for reciprocal division + * @shift: Shift for reciprocal division + * + * The multiplier and shift for reciprocal division by rate are stored + * in mult and shift. + * + * The deal here is to replace a divide by a reciprocal one + * in fast path (a reciprocal divide is a multiply and a shift) + * + * Normal formula would be : + * time_in_ns = (NSEC_PER_SEC * len) / rate_bps + * + * We compute mult/shift to use instead : + * time_in_ns = (len * mult) >> shift; + * + * We try to get the highest possible mult value for accuracy, + * but have to make sure no overflows will ever happen. + * + * reciprocal_value() is not used here it doesn't handle 64-bit values. + */ +static void psched_ratecfg_precompute__(u64 rate, u32 *mult, u8 *shift) +{ + u64 factor = NSEC_PER_SEC; + + *mult = 1; + *shift = 0; + + if (rate <= 0) + return; + + for (;;) { + *mult = div64_u64(factor, rate); + if (*mult & (1U << 31) || factor & (1ULL << 63)) + break; + factor <<= 1; + (*shift)++; + } +} + void psched_ratecfg_precompute(struct psched_ratecfg *r, const struct tc_ratespec *conf, u64 rate64) @@ -1333,34 +1375,17 @@ void psched_ratecfg_precompute(struct psched_ratecfg *r, r->overhead = conf->overhead; r->rate_bytes_ps = max_t(u64, conf->rate, rate64); r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK); - r->mult = 1; - /* - * The deal here is to replace a divide by a reciprocal one - * in fast path (a reciprocal divide is a multiply and a shift) - * - * Normal formula would be : - * time_in_ns = (NSEC_PER_SEC * len) / rate_bps - * - * We compute mult/shift to use instead : - * time_in_ns = (len * mult) >> shift; - * - * We try to get the highest possible mult value for accuracy, - * but have to make sure no overflows will ever happen. - */ - if (r->rate_bytes_ps > 0) { - u64 factor = NSEC_PER_SEC; - - for (;;) { - r->mult = div64_u64(factor, r->rate_bytes_ps); - if (r->mult & (1U << 31) || factor & (1ULL << 63)) - break; - factor <<= 1; - r->shift++; - } - } + psched_ratecfg_precompute__(r->rate_bytes_ps, &r->mult, &r->shift); } EXPORT_SYMBOL(psched_ratecfg_precompute); +void psched_ppscfg_precompute(struct psched_pktrate *r, u64 pktrate64) +{ + r->rate_pkts_ps = pktrate64; + psched_ratecfg_precompute__(r->rate_pkts_ps, &r->mult, &r->shift); +} +EXPORT_SYMBOL(psched_ppscfg_precompute); + static void mini_qdisc_rcu_func(struct rcu_head *head) { } diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 8287894541e3..922ed6b91abb 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -411,18 +411,10 @@ done: return txtime; } -static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, - struct sk_buff **to_free) +static int taprio_enqueue_one(struct sk_buff *skb, struct Qdisc *sch, + struct Qdisc *child, struct sk_buff **to_free) { struct taprio_sched *q = qdisc_priv(sch); - struct Qdisc *child; - int queue; - - queue = skb_get_queue_mapping(skb); - - child = q->qdiscs[queue]; - if (unlikely(!child)) - return qdisc_drop(skb, sch, to_free); if (skb->sk && sock_flag(skb->sk, SOCK_TXTIME)) { if (!is_valid_interval(skb, sch)) @@ -439,6 +431,58 @@ static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, return qdisc_enqueue(skb, child, to_free); } +static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct Qdisc *child; + int queue; + + queue = skb_get_queue_mapping(skb); + + child = q->qdiscs[queue]; + if (unlikely(!child)) + return qdisc_drop(skb, sch, to_free); + + /* Large packets might not be transmitted when the transmission duration + * exceeds any configured interval. Therefore, segment the skb into + * smaller chunks. Skip it for the full offload case, as the driver + * and/or the hardware is expected to handle this. + */ + if (skb_is_gso(skb) && !FULL_OFFLOAD_IS_ENABLED(q->flags)) { + unsigned int slen = 0, numsegs = 0, len = qdisc_pkt_len(skb); + netdev_features_t features = netif_skb_features(skb); + struct sk_buff *segs, *nskb; + int ret; + + segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + if (IS_ERR_OR_NULL(segs)) + return qdisc_drop(skb, sch, to_free); + + skb_list_walk_safe(segs, segs, nskb) { + skb_mark_not_on_list(segs); + qdisc_skb_cb(segs)->pkt_len = segs->len; + slen += segs->len; + + ret = taprio_enqueue_one(segs, sch, child, to_free); + if (ret != NET_XMIT_SUCCESS) { + if (net_xmit_drop_count(ret)) + qdisc_qstats_drop(sch); + } else { + numsegs++; + } + } + + if (numsegs > 1) + qdisc_tree_reduce_backlog(sch, 1 - numsegs, len - slen); + consume_skb(skb); + + return numsegs > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; + } + + return taprio_enqueue_one(skb, sch, child, to_free); +} + static struct sk_buff *taprio_peek_soft(struct Qdisc *sch) { struct taprio_sched *q = qdisc_priv(sch); diff --git a/net/tipc/addr.c b/net/tipc/addr.c index abe29d1aa23a..fd0796269eed 100644 --- a/net/tipc/addr.c +++ b/net/tipc/addr.c @@ -3,6 +3,7 @@ * * Copyright (c) 2000-2006, 2018, Ericsson AB * Copyright (c) 2004-2005, 2010-2011, Wind River Systems + * Copyright (c) 2020-2021, Red Hat Inc * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/net/tipc/addr.h b/net/tipc/addr.h index 1a11831bef62..0772cfadaa0d 100644 --- a/net/tipc/addr.h +++ b/net/tipc/addr.h @@ -3,7 +3,7 @@ * * Copyright (c) 2000-2006, 2018, Ericsson AB * Copyright (c) 2004-2005, Wind River Systems - * Copyright (c) 2020, Red Hat Inc + * Copyright (c) 2020-2021, Red Hat Inc * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -44,6 +44,50 @@ #include <net/netns/generic.h> #include "core.h" +/* Struct tipc_uaddr: internal version of struct sockaddr_tipc. + * Must be kept aligned both regarding field positions and size. + */ +struct tipc_uaddr { + unsigned short family; + unsigned char addrtype; + signed char scope; + union { + struct { + struct tipc_service_addr sa; + u32 lookup_node; + }; + struct tipc_service_range sr; + struct tipc_socket_addr sk; + }; +}; + +static inline void tipc_uaddr(struct tipc_uaddr *ua, u32 atype, u32 scope, + u32 type, u32 lower, u32 upper) +{ + ua->family = AF_TIPC; + ua->addrtype = atype; + ua->scope = scope; + ua->sr.type = type; + ua->sr.lower = lower; + ua->sr.upper = upper; +} + +static inline bool tipc_uaddr_valid(struct tipc_uaddr *ua, int len) +{ + u32 atype; + + if (len < sizeof(struct sockaddr_tipc)) + return false; + atype = ua->addrtype; + if (ua->family != AF_TIPC) + return false; + if (atype == TIPC_SERVICE_ADDR || atype == TIPC_SOCKET_ADDR) + return true; + if (atype == TIPC_SERVICE_RANGE) + return ua->sr.upper >= ua->sr.lower; + return false; +} + static inline u32 tipc_own_addr(struct net *net) { return tipc_net(net)->node_addr; diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index f4fca8f7f63f..6f64acef73dc 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -317,7 +317,7 @@ static int tipc_aead_key_generate(struct tipc_aead_key *skey); #define tipc_aead_rcu_replace(rcu_ptr, ptr, lock) \ do { \ - typeof(rcu_ptr) __tmp = rcu_dereference_protected((rcu_ptr), \ + struct tipc_aead *__tmp = rcu_dereference_protected((rcu_ptr), \ lockdep_is_held(lock)); \ rcu_assign_pointer((rcu_ptr), (ptr)); \ tipc_aead_put(__tmp); \ @@ -798,7 +798,7 @@ static int tipc_aead_encrypt(struct tipc_aead *aead, struct sk_buff *skb, ehdr = (struct tipc_ehdr *)skb->data; salt = aead->salt; if (aead->mode == CLUSTER_KEY) - salt ^= ehdr->addr; /* __be32 */ + salt ^= __be32_to_cpu(ehdr->addr); else if (__dnode) salt ^= tipc_node_get_addr(__dnode); memcpy(iv, &salt, 4); @@ -929,7 +929,7 @@ static int tipc_aead_decrypt(struct net *net, struct tipc_aead *aead, ehdr = (struct tipc_ehdr *)skb->data; salt = aead->salt; if (aead->mode == CLUSTER_KEY) - salt ^= ehdr->addr; /* __be32 */ + salt ^= __be32_to_cpu(ehdr->addr); else if (ehdr->destined) salt ^= tipc_own_addr(net); memcpy(iv, &salt, 4); @@ -1946,16 +1946,16 @@ static void tipc_crypto_rcv_complete(struct net *net, struct tipc_aead *aead, goto rcv; } tipc_aead_put(aead); - aead = tipc_aead_get(tmp); + aead = tipc_aead_get((struct tipc_aead __force __rcu *)tmp); } if (unlikely(err)) { - tipc_aead_users_dec(aead, INT_MIN); + tipc_aead_users_dec((struct tipc_aead __force __rcu *)aead, INT_MIN); goto free_skb; } /* Set the RX key's user */ - tipc_aead_users_set(aead, 1); + tipc_aead_users_set((struct tipc_aead __force __rcu *)aead, 1); /* Mark this point, RX works */ rx->timer1 = jiffies; diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index 48fac3b17e40..407619697292 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -104,6 +104,36 @@ static struct tipc_monitor *tipc_monitor(struct net *net, int bearer_id) const int tipc_max_domain_size = sizeof(struct tipc_mon_domain); +static inline u16 mon_cpu_to_le16(u16 val) +{ + return (__force __u16)htons(val); +} + +static inline u32 mon_cpu_to_le32(u32 val) +{ + return (__force __u32)htonl(val); +} + +static inline u64 mon_cpu_to_le64(u64 val) +{ + return (__force __u64)cpu_to_be64(val); +} + +static inline u16 mon_le16_to_cpu(u16 val) +{ + return ntohs((__force __be16)val); +} + +static inline u32 mon_le32_to_cpu(u32 val) +{ + return ntohl((__force __be32)val); +} + +static inline u64 mon_le64_to_cpu(u64 val) +{ + return be64_to_cpu((__force __be64)val); +} + /* dom_rec_len(): actual length of domain record for transport */ static int dom_rec_len(struct tipc_mon_domain *dom, u16 mcnt) @@ -260,16 +290,16 @@ static void mon_update_local_domain(struct tipc_monitor *mon) diff |= dom->members[i] != peer->addr; dom->members[i] = peer->addr; map_set(&dom->up_map, i, peer->is_up); - cache->members[i] = htonl(peer->addr); + cache->members[i] = mon_cpu_to_le32(peer->addr); } diff |= dom->up_map != prev_up_map; if (!diff) return; dom->gen = ++mon->dom_gen; - cache->len = htons(dom->len); - cache->gen = htons(dom->gen); - cache->member_cnt = htons(member_cnt); - cache->up_map = cpu_to_be64(dom->up_map); + cache->len = mon_cpu_to_le16(dom->len); + cache->gen = mon_cpu_to_le16(dom->gen); + cache->member_cnt = mon_cpu_to_le16(member_cnt); + cache->up_map = mon_cpu_to_le64(dom->up_map); mon_apply_domain(mon, self); } @@ -455,10 +485,11 @@ void tipc_mon_rcv(struct net *net, void *data, u16 dlen, u32 addr, struct tipc_mon_domain dom_bef; struct tipc_mon_domain *dom; struct tipc_peer *peer; - u16 new_member_cnt = ntohs(arrv_dom->member_cnt); + u16 new_member_cnt = mon_le16_to_cpu(arrv_dom->member_cnt); int new_dlen = dom_rec_len(arrv_dom, new_member_cnt); - u16 new_gen = ntohs(arrv_dom->gen); - u16 acked_gen = ntohs(arrv_dom->ack_gen); + u16 new_gen = mon_le16_to_cpu(arrv_dom->gen); + u16 acked_gen = mon_le16_to_cpu(arrv_dom->ack_gen); + u16 arrv_dlen = mon_le16_to_cpu(arrv_dom->len); bool probing = state->probing; int i, applied_bef; @@ -469,7 +500,7 @@ void tipc_mon_rcv(struct net *net, void *data, u16 dlen, u32 addr, return; if (dlen != dom_rec_len(arrv_dom, new_member_cnt)) return; - if ((dlen < new_dlen) || ntohs(arrv_dom->len) != new_dlen) + if (dlen < new_dlen || arrv_dlen != new_dlen) return; /* Synch generation numbers with peer if link just came up */ @@ -517,9 +548,9 @@ void tipc_mon_rcv(struct net *net, void *data, u16 dlen, u32 addr, dom->len = new_dlen; dom->gen = new_gen; dom->member_cnt = new_member_cnt; - dom->up_map = be64_to_cpu(arrv_dom->up_map); + dom->up_map = mon_le64_to_cpu(arrv_dom->up_map); for (i = 0; i < new_member_cnt; i++) - dom->members[i] = ntohl(arrv_dom->members[i]); + dom->members[i] = mon_le32_to_cpu(arrv_dom->members[i]); /* Update peers affected by this domain record */ applied_bef = peer->applied; @@ -548,19 +579,19 @@ void tipc_mon_prep(struct net *net, void *data, int *dlen, if (likely(state->acked_gen == gen)) { len = dom_rec_len(dom, 0); *dlen = len; - dom->len = htons(len); - dom->gen = htons(gen); - dom->ack_gen = htons(state->peer_gen); + dom->len = mon_cpu_to_le16(len); + dom->gen = mon_cpu_to_le16(gen); + dom->ack_gen = mon_cpu_to_le16(state->peer_gen); dom->member_cnt = 0; return; } /* Send the full record */ read_lock_bh(&mon->lock); - len = ntohs(mon->cache.len); + len = mon_le16_to_cpu(mon->cache.len); *dlen = len; memcpy(data, &mon->cache, len); read_unlock_bh(&mon->lock); - dom->ack_gen = htons(state->peer_gen); + dom->ack_gen = mon_cpu_to_le16(state->peer_gen); } void tipc_mon_get_state(struct net *net, u32 addr, diff --git a/net/tipc/msg.c b/net/tipc/msg.c index e9263280a2d4..3f0a25345a7c 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -707,8 +707,11 @@ bool tipc_msg_skb_clone(struct sk_buff_head *msg, struct sk_buff_head *cpy) bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err) { struct tipc_msg *msg = buf_msg(skb); - u32 dport, dnode; - u32 onode = tipc_own_addr(net); + u32 scope = msg_lookup_scope(msg); + u32 self = tipc_own_addr(net); + u32 inst = msg_nameinst(msg); + struct tipc_socket_addr sk; + struct tipc_uaddr ua; if (!msg_isdata(msg)) return false; @@ -722,16 +725,16 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err) msg = buf_msg(skb); if (msg_reroute_cnt(msg)) return false; - dnode = tipc_scope2node(net, msg_lookup_scope(msg)); - dport = tipc_nametbl_translate(net, msg_nametype(msg), - msg_nameinst(msg), &dnode); - if (!dport) + tipc_uaddr(&ua, TIPC_SERVICE_RANGE, scope, + msg_nametype(msg), inst, inst); + sk.node = tipc_scope2node(net, scope); + if (!tipc_nametbl_lookup_anycast(net, &ua, &sk)) return false; msg_incr_reroute_cnt(msg); - if (dnode != onode) - msg_set_prevnode(msg, onode); - msg_set_destnode(msg, dnode); - msg_set_destport(msg, dport); + if (sk.node != self) + msg_set_prevnode(msg, self); + msg_set_destnode(msg, sk.node); + msg_set_destport(msg, sk.ref); *err = TIPC_OK; return true; diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index 6cf57c3bfa27..bda902caa814 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -1,8 +1,9 @@ /* * net/tipc/name_distr.c: TIPC name distribution code * - * Copyright (c) 2000-2006, 2014, Ericsson AB + * Copyright (c) 2000-2006, 2014-2019, Ericsson AB * Copyright (c) 2005, 2010-2011, Wind River Systems + * Copyright (c) 2020-2021, Red Hat Inc * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -55,10 +56,10 @@ struct distr_queue_item { */ static void publ_to_item(struct distr_item *i, struct publication *p) { - i->type = htonl(p->type); - i->lower = htonl(p->lower); - i->upper = htonl(p->upper); - i->port = htonl(p->port); + i->type = htonl(p->sr.type); + i->lower = htonl(p->sr.lower); + i->upper = htonl(p->sr.upper); + i->port = htonl(p->sk.ref); i->key = htonl(p->key); } @@ -90,20 +91,20 @@ static struct sk_buff *named_prepare_buf(struct net *net, u32 type, u32 size, /** * tipc_named_publish - tell other nodes about a new publication by this node * @net: the associated network namespace - * @publ: the new publication + * @p: the new publication */ -struct sk_buff *tipc_named_publish(struct net *net, struct publication *publ) +struct sk_buff *tipc_named_publish(struct net *net, struct publication *p) { struct name_table *nt = tipc_name_table(net); struct distr_item *item; struct sk_buff *skb; - if (publ->scope == TIPC_NODE_SCOPE) { - list_add_tail_rcu(&publ->binding_node, &nt->node_scope); + if (p->scope == TIPC_NODE_SCOPE) { + list_add_tail_rcu(&p->binding_node, &nt->node_scope); return NULL; } write_lock_bh(&nt->cluster_scope_lock); - list_add_tail(&publ->binding_node, &nt->cluster_scope); + list_add_tail(&p->binding_node, &nt->cluster_scope); write_unlock_bh(&nt->cluster_scope_lock); skb = named_prepare_buf(net, PUBLICATION, ITEM_SIZE, 0); if (!skb) { @@ -113,25 +114,25 @@ struct sk_buff *tipc_named_publish(struct net *net, struct publication *publ) msg_set_named_seqno(buf_msg(skb), nt->snd_nxt++); msg_set_non_legacy(buf_msg(skb)); item = (struct distr_item *)msg_data(buf_msg(skb)); - publ_to_item(item, publ); + publ_to_item(item, p); return skb; } /** * tipc_named_withdraw - tell other nodes about a withdrawn publication by this node * @net: the associated network namespace - * @publ: the withdrawn publication + * @p: the withdrawn publication */ -struct sk_buff *tipc_named_withdraw(struct net *net, struct publication *publ) +struct sk_buff *tipc_named_withdraw(struct net *net, struct publication *p) { struct name_table *nt = tipc_name_table(net); struct distr_item *item; struct sk_buff *skb; write_lock_bh(&nt->cluster_scope_lock); - list_del(&publ->binding_node); + list_del(&p->binding_node); write_unlock_bh(&nt->cluster_scope_lock); - if (publ->scope == TIPC_NODE_SCOPE) + if (p->scope == TIPC_NODE_SCOPE) return NULL; skb = named_prepare_buf(net, WITHDRAWAL, ITEM_SIZE, 0); @@ -142,7 +143,7 @@ struct sk_buff *tipc_named_withdraw(struct net *net, struct publication *publ) msg_set_named_seqno(buf_msg(skb), nt->snd_nxt++); msg_set_non_legacy(buf_msg(skb)); item = (struct distr_item *)msg_data(buf_msg(skb)); - publ_to_item(item, publ); + publ_to_item(item, p); return skb; } @@ -233,33 +234,27 @@ void tipc_named_node_up(struct net *net, u32 dnode, u16 capabilities) /** * tipc_publ_purge - remove publication associated with a failed node * @net: the associated network namespace - * @publ: the publication to remove + * @p: the publication to remove * @addr: failed node's address * * Invoked for each publication issued by a newly failed node. * Removes publication structure from name table & deletes it. */ -static void tipc_publ_purge(struct net *net, struct publication *publ, u32 addr) +static void tipc_publ_purge(struct net *net, struct publication *p, u32 addr) { struct tipc_net *tn = tipc_net(net); - struct publication *p; + struct publication *_p; + struct tipc_uaddr ua; + tipc_uaddr(&ua, TIPC_SERVICE_RANGE, p->scope, p->sr.type, + p->sr.lower, p->sr.upper); spin_lock_bh(&tn->nametbl_lock); - p = tipc_nametbl_remove_publ(net, publ->type, publ->lower, publ->upper, - publ->node, publ->key); - if (p) - tipc_node_unsubscribe(net, &p->binding_node, addr); + _p = tipc_nametbl_remove_publ(net, &ua, &p->sk, p->key); + if (_p) + tipc_node_unsubscribe(net, &_p->binding_node, addr); spin_unlock_bh(&tn->nametbl_lock); - - if (p != publ) { - pr_err("Unable to remove publication from failed node\n" - " (type=%u, lower=%u, node=0x%x, port=%u, key=%u)\n", - publ->type, publ->lower, publ->node, publ->port, - publ->key); - } - - if (p) - kfree_rcu(p, rcu); + if (_p) + kfree_rcu(_p, rcu); } void tipc_publ_notify(struct net *net, struct list_head *nsub_list, @@ -293,30 +288,30 @@ static bool tipc_update_nametbl(struct net *net, struct distr_item *i, u32 node, u32 dtype) { struct publication *p = NULL; - u32 lower = ntohl(i->lower); - u32 upper = ntohl(i->upper); - u32 type = ntohl(i->type); - u32 port = ntohl(i->port); + struct tipc_socket_addr sk; + struct tipc_uaddr ua; u32 key = ntohl(i->key); + tipc_uaddr(&ua, TIPC_SERVICE_RANGE, TIPC_CLUSTER_SCOPE, + ntohl(i->type), ntohl(i->lower), ntohl(i->upper)); + sk.ref = ntohl(i->port); + sk.node = node; + if (dtype == PUBLICATION) { - p = tipc_nametbl_insert_publ(net, type, lower, upper, - TIPC_CLUSTER_SCOPE, node, - port, key); + p = tipc_nametbl_insert_publ(net, &ua, &sk, key); if (p) { tipc_node_subscribe(net, &p->binding_node, node); return true; } } else if (dtype == WITHDRAWAL) { - p = tipc_nametbl_remove_publ(net, type, lower, - upper, node, key); + p = tipc_nametbl_remove_publ(net, &ua, &sk, key); if (p) { tipc_node_unsubscribe(net, &p->binding_node, node); kfree_rcu(p, rcu); return true; } - pr_warn_ratelimited("Failed to remove binding %u,%u from %x\n", - type, lower, node); + pr_warn_ratelimited("Failed to remove binding %u,%u from %u\n", + ua.sr.type, ua.sr.lower, node); } else { pr_warn("Unrecognized name table message received\n"); } @@ -410,15 +405,15 @@ void tipc_named_reinit(struct net *net) { struct name_table *nt = tipc_name_table(net); struct tipc_net *tn = tipc_net(net); - struct publication *publ; + struct publication *p; u32 self = tipc_own_addr(net); spin_lock_bh(&tn->nametbl_lock); - list_for_each_entry_rcu(publ, &nt->node_scope, binding_node) - publ->node = self; - list_for_each_entry_rcu(publ, &nt->cluster_scope, binding_node) - publ->node = self; + list_for_each_entry_rcu(p, &nt->node_scope, binding_node) + p->sk.node = self; + list_for_each_entry_rcu(p, &nt->cluster_scope, binding_node) + p->sk.node = self; nt->rc_dests = 0; spin_unlock_bh(&tn->nametbl_lock); } diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index ee5ac40ea2b6..6db9f9e7c0ac 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -3,7 +3,7 @@ * * Copyright (c) 2000-2006, 2014-2018, Ericsson AB * Copyright (c) 2004-2008, 2010-2014, Wind River Systems - * Copyright (c) 2020, Red Hat Inc + * Copyright (c) 2020-2021, Red Hat Inc * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -222,59 +222,57 @@ static int hash(int x) /** * tipc_publ_create - create a publication structure - * @type: name sequence type - * @lower: name sequence lower bound - * @upper: name sequence upper bound - * @scope: publication scope - * @node: network address of publishing socket - * @port: publishing port + * @ua: the service range the user is binding to + * @sk: the address of the socket that is bound * @key: publication key */ -static struct publication *tipc_publ_create(u32 type, u32 lower, u32 upper, - u32 scope, u32 node, u32 port, +static struct publication *tipc_publ_create(struct tipc_uaddr *ua, + struct tipc_socket_addr *sk, u32 key) { - struct publication *publ = kzalloc(sizeof(*publ), GFP_ATOMIC); + struct publication *p = kzalloc(sizeof(*p), GFP_ATOMIC); - if (!publ) + if (!p) return NULL; - publ->type = type; - publ->lower = lower; - publ->upper = upper; - publ->scope = scope; - publ->node = node; - publ->port = port; - publ->key = key; - INIT_LIST_HEAD(&publ->binding_sock); - INIT_LIST_HEAD(&publ->binding_node); - INIT_LIST_HEAD(&publ->local_publ); - INIT_LIST_HEAD(&publ->all_publ); - INIT_LIST_HEAD(&publ->list); - return publ; + p->sr = ua->sr; + p->sk = *sk; + p->scope = ua->scope; + p->key = key; + INIT_LIST_HEAD(&p->binding_sock); + INIT_LIST_HEAD(&p->binding_node); + INIT_LIST_HEAD(&p->local_publ); + INIT_LIST_HEAD(&p->all_publ); + INIT_LIST_HEAD(&p->list); + return p; } /** * tipc_service_create - create a service structure for the specified 'type' - * @type: service type - * @hd: name_table services list + * @net: network namespace + * @ua: address representing the service to be bound * * Allocates a single range structure and sets it to all 0's. */ -static struct tipc_service *tipc_service_create(u32 type, struct hlist_head *hd) +static struct tipc_service *tipc_service_create(struct net *net, + struct tipc_uaddr *ua) { - struct tipc_service *service = kzalloc(sizeof(*service), GFP_ATOMIC); + struct name_table *nt = tipc_name_table(net); + struct tipc_service *service; + struct hlist_head *hd; + service = kzalloc(sizeof(*service), GFP_ATOMIC); if (!service) { pr_warn("Service creation failed, no memory\n"); return NULL; } spin_lock_init(&service->lock); - service->type = type; + service->type = ua->sr.type; service->ranges = RB_ROOT; INIT_HLIST_NODE(&service->service_list); INIT_LIST_HEAD(&service->subscriptions); + hd = &nt->services[hash(ua->sr.type)]; hlist_add_head_rcu(&service->service_list, hd); return service; } @@ -282,13 +280,13 @@ static struct tipc_service *tipc_service_create(u32 type, struct hlist_head *hd) /* 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 tipc_uaddr *ua) { struct service_range *sr; - service_range_foreach_match(sr, sc, lower, upper) { + service_range_foreach_match(sr, sc, ua->sr.lower, ua->sr.upper) { /* Look for exact match */ - if (sr->lower == lower && sr->upper == upper) + if (sr->lower == ua->sr.lower && sr->upper == ua->sr.upper) return sr; } @@ -296,10 +294,12 @@ static struct service_range *tipc_service_find_range(struct tipc_service *sc, } static struct service_range *tipc_service_create_range(struct tipc_service *sc, - u32 lower, u32 upper) + struct publication *p) { struct rb_node **n, *parent = NULL; struct service_range *sr; + u32 lower = p->sr.lower; + u32 upper = p->sr.upper; n = &sc->ranges.rb_node; while (*n) { @@ -327,64 +327,68 @@ static struct service_range *tipc_service_create_range(struct tipc_service *sc, return sr; } -static struct publication *tipc_service_insert_publ(struct net *net, - struct tipc_service *sc, - u32 type, u32 lower, - u32 upper, u32 scope, - u32 node, u32 port, - u32 key) +static bool tipc_service_insert_publ(struct net *net, + struct tipc_service *sc, + struct publication *p) { struct tipc_subscription *sub, *tmp; struct service_range *sr; - struct publication *p; + struct publication *_p; + u32 node = p->sk.node; bool first = false; + bool res = false; + u32 key = p->key; - sr = tipc_service_create_range(sc, lower, upper); + spin_lock_bh(&sc->lock); + sr = tipc_service_create_range(sc, p); if (!sr) - goto err; + goto exit; first = list_empty(&sr->all_publ); /* Return if the publication already exists */ - list_for_each_entry(p, &sr->all_publ, all_publ) { - if (p->key == key && (!p->node || p->node == node)) - return NULL; + list_for_each_entry(_p, &sr->all_publ, all_publ) { + if (_p->key == key && (!_p->sk.node || _p->sk.node == node)) { + pr_debug("Failed to bind duplicate %u,%u,%u/%u:%u/%u\n", + p->sr.type, p->sr.lower, p->sr.upper, + node, p->sk.ref, key); + goto exit; + } } - /* Create and insert publication */ - p = tipc_publ_create(type, lower, upper, scope, node, port, key); - if (!p) - goto err; - /* Suppose there shouldn't be a huge gap btw publs i.e. >INT_MAX */ - p->id = sc->publ_cnt++; - if (in_own_node(net, node)) + if (in_own_node(net, p->sk.node)) list_add(&p->local_publ, &sr->local_publ); list_add(&p->all_publ, &sr->all_publ); + p->id = sc->publ_cnt++; /* Any subscriptions waiting for notification? */ list_for_each_entry_safe(sub, tmp, &sc->subscriptions, service_list) { - tipc_sub_report_overlap(sub, p->lower, p->upper, TIPC_PUBLISHED, - p->port, p->node, p->scope, first); + tipc_sub_report_overlap(sub, p, TIPC_PUBLISHED, first); } - return p; -err: - pr_warn("Failed to bind to %u,%u,%u, no memory\n", type, lower, upper); - return NULL; + res = true; +exit: + if (!res) + pr_warn("Failed to bind to %u,%u,%u\n", + p->sr.type, p->sr.lower, p->sr.upper); + spin_unlock_bh(&sc->lock); + return res; } /** * tipc_service_remove_publ - remove a publication from a service - * @sr: service_range to remove publication from - * @node: target node + * @r: service_range to remove publication from + * @sk: address publishing socket * @key: target publication key */ -static struct publication *tipc_service_remove_publ(struct service_range *sr, - u32 node, u32 key) +static struct publication *tipc_service_remove_publ(struct service_range *r, + struct tipc_socket_addr *sk, + u32 key) { struct publication *p; + u32 node = sk->node; - list_for_each_entry(p, &sr->all_publ, all_publ) { - if (p->key != key || (node && node != p->node)) + list_for_each_entry(p, &r->all_publ, all_publ) { + if (p->key != key || (node && node != p->sk.node)) continue; list_del(&p->all_publ); list_del(&p->local_publ); @@ -417,17 +421,14 @@ static int tipc_publ_sort(void *priv, struct list_head *a, static void tipc_service_subscribe(struct tipc_service *service, struct tipc_subscription *sub) { - struct tipc_subscr *sb = &sub->evt.s; struct publication *p, *first, *tmp; struct list_head publ_list; struct service_range *sr; - struct tipc_service_range r; - u32 filter; + u32 filter, lower, upper; - r.type = tipc_sub_read(sb, seq.type); - r.lower = tipc_sub_read(sb, seq.lower); - r.upper = tipc_sub_read(sb, seq.upper); - filter = tipc_sub_read(sb, filter); + filter = sub->s.filter; + lower = sub->s.seq.lower; + upper = sub->s.seq.upper; tipc_sub_get(sub); list_add(&sub->service_list, &service->subscriptions); @@ -436,7 +437,7 @@ static void tipc_service_subscribe(struct tipc_service *service, return; INIT_LIST_HEAD(&publ_list); - service_range_foreach_match(sr, service, r.lower, r.upper) { + service_range_foreach_match(sr, service, lower, upper) { first = NULL; list_for_each_entry(p, &sr->all_publ, all_publ) { if (filter & TIPC_SUB_PORTS) @@ -452,80 +453,74 @@ static void tipc_service_subscribe(struct tipc_service *service, /* Sort the publications before reporting */ list_sort(NULL, &publ_list, tipc_publ_sort); list_for_each_entry_safe(p, tmp, &publ_list, list) { - tipc_sub_report_overlap(sub, p->lower, p->upper, - TIPC_PUBLISHED, p->port, p->node, - p->scope, true); + tipc_sub_report_overlap(sub, p, TIPC_PUBLISHED, true); list_del_init(&p->list); } } -static struct tipc_service *tipc_service_find(struct net *net, u32 type) +static struct tipc_service *tipc_service_find(struct net *net, + struct tipc_uaddr *ua) { struct name_table *nt = tipc_name_table(net); struct hlist_head *service_head; struct tipc_service *service; - service_head = &nt->services[hash(type)]; + service_head = &nt->services[hash(ua->sr.type)]; hlist_for_each_entry_rcu(service, service_head, service_list) { - if (service->type == type) + if (service->type == ua->sr.type) return service; } return NULL; }; -struct publication *tipc_nametbl_insert_publ(struct net *net, u32 type, - u32 lower, u32 upper, - u32 scope, u32 node, - u32 port, u32 key) +struct publication *tipc_nametbl_insert_publ(struct net *net, + struct tipc_uaddr *ua, + struct tipc_socket_addr *sk, + u32 key) { - struct name_table *nt = tipc_name_table(net); struct tipc_service *sc; struct publication *p; - if (scope > TIPC_NODE_SCOPE || lower > upper) { - pr_debug("Failed to bind illegal {%u,%u,%u} with scope %u\n", - type, lower, upper, scope); - return NULL; - } - sc = tipc_service_find(net, type); - if (!sc) - sc = tipc_service_create(type, &nt->services[hash(type)]); - if (!sc) + p = tipc_publ_create(ua, sk, key); + if (!p) return NULL; - spin_lock_bh(&sc->lock); - p = tipc_service_insert_publ(net, sc, type, lower, upper, - scope, node, port, key); - spin_unlock_bh(&sc->lock); - return p; + sc = tipc_service_find(net, ua); + if (!sc) + sc = tipc_service_create(net, ua); + if (sc && tipc_service_insert_publ(net, sc, p)) + return p; + kfree(p); + return NULL; } -struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type, - u32 lower, u32 upper, - u32 node, u32 key) +struct publication *tipc_nametbl_remove_publ(struct net *net, + struct tipc_uaddr *ua, + struct tipc_socket_addr *sk, + u32 key) { - struct tipc_service *sc = tipc_service_find(net, type); struct tipc_subscription *sub, *tmp; - struct service_range *sr = NULL; struct publication *p = NULL; + struct service_range *sr; + struct tipc_service *sc; bool last; + sc = tipc_service_find(net, ua); if (!sc) - return NULL; + goto exit; spin_lock_bh(&sc->lock); - sr = tipc_service_find_range(sc, lower, upper); + sr = tipc_service_find_range(sc, ua); if (!sr) - goto exit; - p = tipc_service_remove_publ(sr, node, key); + goto unlock; + p = tipc_service_remove_publ(sr, sk, key); if (!p) - goto exit; + goto unlock; /* Notify any waiting subscriptions */ last = list_empty(&sr->all_publ); list_for_each_entry_safe(sub, tmp, &sc->subscriptions, service_list) { - tipc_sub_report_overlap(sub, lower, upper, TIPC_WITHDRAWN, - p->port, node, p->scope, last); + tipc_sub_report_overlap(sub, p, TIPC_WITHDRAWN, last); } /* Remove service range item if this was its last publication */ @@ -534,77 +529,83 @@ struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type, kfree(sr); } - /* Delete service item if this no more publications and subscriptions */ + /* Delete service item if no more publications and subscriptions */ if (RB_EMPTY_ROOT(&sc->ranges) && list_empty(&sc->subscriptions)) { hlist_del_init_rcu(&sc->service_list); kfree_rcu(sc, rcu); } -exit: +unlock: spin_unlock_bh(&sc->lock); +exit: + if (!p) { + pr_err("Failed to remove unknown binding: %u,%u,%u/%u:%u/%u\n", + ua->sr.type, ua->sr.lower, ua->sr.upper, + sk->node, sk->ref, key); + } return p; } /** - * tipc_nametbl_translate - perform service instance to socket translation + * tipc_nametbl_lookup_anycast - perform service instance to socket translation * @net: network namespace - * @type: message type - * @instance: message instance - * @dnode: the search domain used during translation + * @ua: service address to look up + * @sk: address to socket we want to find * + * On entry, a non-zero 'sk->node' indicates the node where we want lookup to be + * performed, which may not be this one. * On exit: - * - if translation is deferred to another node, leave 'dnode' unchanged and - * return 0 - * - if translation is attempted and succeeds, set 'dnode' to the publishing - * node and return the published (non-zero) port number - * - if translation is attempted and fails, set 'dnode' to 0 and return 0 + * - If lookup is deferred to another node, leave 'sk->node' unchanged and + * return 'true'. + * - If lookup is successful, set the 'sk->node' and 'sk->ref' (== portid) which + * represent the bound socket and return 'true'. + * - If lookup fails, return 'false' * * Note that for legacy users (node configured with Z.C.N address format) the - * 'closest-first' lookup algorithm must be maintained, i.e., if dnode is 0 + * 'closest-first' lookup algorithm must be maintained, i.e., if sk.node is 0 * we must look in the local binding list first */ -u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, u32 *dnode) +bool tipc_nametbl_lookup_anycast(struct net *net, + struct tipc_uaddr *ua, + struct tipc_socket_addr *sk) { struct tipc_net *tn = tipc_net(net); bool legacy = tn->legacy_addr_format; u32 self = tipc_own_addr(net); - struct service_range *sr; + u32 inst = ua->sa.instance; + struct service_range *r; struct tipc_service *sc; - struct list_head *list; struct publication *p; - u32 port = 0; - u32 node = 0; + struct list_head *l; + bool res = false; - if (!tipc_in_scope(legacy, *dnode, self)) - return 0; + if (!tipc_in_scope(legacy, sk->node, self)) + return true; rcu_read_lock(); - sc = tipc_service_find(net, type); + sc = tipc_service_find(net, ua); if (unlikely(!sc)) goto exit; spin_lock_bh(&sc->lock); - service_range_foreach_match(sr, sc, instance, instance) { + service_range_foreach_match(r, sc, inst, inst) { /* Select lookup algo: local, closest-first or round-robin */ - if (*dnode == self) { - list = &sr->local_publ; - if (list_empty(list)) + if (sk->node == self) { + l = &r->local_publ; + if (list_empty(l)) 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); + p = list_first_entry(l, struct publication, local_publ); + list_move_tail(&p->local_publ, &r->local_publ); + } else if (legacy && !sk->node && !list_empty(&r->local_publ)) { + l = &r->local_publ; + p = list_first_entry(l, struct publication, local_publ); + list_move_tail(&p->local_publ, &r->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); + l = &r->all_publ; + p = list_first_entry(l, struct publication, all_publ); + list_move_tail(&p->all_publ, &r->all_publ); } - port = p->port; - node = p->node; + *sk = p->sk; + res = true; /* Todo: as for legacy, pick the first matching range only, a * "true" round-robin will be performed as needed. */ @@ -614,40 +615,45 @@ u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, u32 *dnode) exit: rcu_read_unlock(); - *dnode = node; - return port; + return res; } -bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 scope, - struct list_head *dsts, int *dstcnt, u32 exclude, - bool all) +/* tipc_nametbl_lookup_group(): lookup destinaton(s) in a communication group + * Returns a list of one (== group anycast) or more (== group multicast) + * destination socket/node pairs matching the given address. + * The requester may or may not want to exclude himself from the list. + */ +bool tipc_nametbl_lookup_group(struct net *net, struct tipc_uaddr *ua, + struct list_head *dsts, int *dstcnt, + u32 exclude, bool mcast) { u32 self = tipc_own_addr(net); + u32 inst = ua->sa.instance; struct service_range *sr; struct tipc_service *sc; struct publication *p; *dstcnt = 0; rcu_read_lock(); - sc = tipc_service_find(net, type); + sc = tipc_service_find(net, ua); if (unlikely(!sc)) goto exit; spin_lock_bh(&sc->lock); /* Todo: a full search i.e. service_range_foreach_match() instead? */ - sr = service_range_match_first(sc->ranges.rb_node, instance, instance); + sr = service_range_match_first(sc->ranges.rb_node, inst, inst); if (!sr) goto no_match; list_for_each_entry(p, &sr->all_publ, all_publ) { - if (p->scope != scope) + if (p->scope != ua->scope) continue; - if (p->port == exclude && p->node == self) + if (p->sk.ref == exclude && p->sk.node == self) continue; - tipc_dest_push(dsts, p->node, p->port); + tipc_dest_push(dsts, p->sk.node, p->sk.ref); (*dstcnt)++; - if (all) + if (mcast) continue; list_move_tail(&p->all_publ, &sr->all_publ); break; @@ -659,23 +665,29 @@ exit: return !list_empty(dsts); } -void tipc_nametbl_mc_lookup(struct net *net, u32 type, u32 lower, u32 upper, - u32 scope, bool exact, struct list_head *dports) +/* tipc_nametbl_lookup_mcast_sockets(): look up node local destinaton sockets + * matching the given address + * Used on nodes which have received a multicast/broadcast message + * Returns a list of local sockets + */ +void tipc_nametbl_lookup_mcast_sockets(struct net *net, struct tipc_uaddr *ua, + bool exact, struct list_head *dports) { struct service_range *sr; struct tipc_service *sc; struct publication *p; + u32 scope = ua->scope; rcu_read_lock(); - sc = tipc_service_find(net, type); + sc = tipc_service_find(net, ua); if (!sc) goto exit; spin_lock_bh(&sc->lock); - service_range_foreach_match(sr, sc, lower, upper) { + service_range_foreach_match(sr, sc, ua->sr.lower, ua->sr.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); + tipc_dest_push(dports, 0, p->sk.ref); } } spin_unlock_bh(&sc->lock); @@ -683,26 +695,27 @@ exit: rcu_read_unlock(); } -/* tipc_nametbl_lookup_dst_nodes - find broadcast destination nodes - * - Creates list of nodes that overlap the given multicast address - * - Determines if any node local destinations overlap +/* tipc_nametbl_lookup_mcast_nodes(): look up all destination nodes matching + * the given address. Used in sending node. + * Used on nodes which are sending out a multicast/broadcast message + * Returns a list of nodes, including own node if applicable */ -void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower, - u32 upper, struct tipc_nlist *nodes) +void tipc_nametbl_lookup_mcast_nodes(struct net *net, struct tipc_uaddr *ua, + struct tipc_nlist *nodes) { struct service_range *sr; struct tipc_service *sc; struct publication *p; rcu_read_lock(); - sc = tipc_service_find(net, type); + sc = tipc_service_find(net, ua); if (!sc) goto exit; spin_lock_bh(&sc->lock); - service_range_foreach_match(sr, sc, lower, upper) { + service_range_foreach_match(sr, sc, ua->sr.lower, ua->sr.upper) { list_for_each_entry(p, &sr->all_publ, all_publ) { - tipc_nlist_add(nodes, p->node); + tipc_nlist_add(nodes, p->sk.node); } } spin_unlock_bh(&sc->lock); @@ -713,7 +726,7 @@ exit: /* tipc_nametbl_build_group - build list of communication group members */ void tipc_nametbl_build_group(struct net *net, struct tipc_group *grp, - u32 type, u32 scope) + struct tipc_uaddr *ua) { struct service_range *sr; struct tipc_service *sc; @@ -721,7 +734,7 @@ void tipc_nametbl_build_group(struct net *net, struct tipc_group *grp, struct rb_node *n; rcu_read_lock(); - sc = tipc_service_find(net, type); + sc = tipc_service_find(net, ua); if (!sc) goto exit; @@ -729,9 +742,10 @@ void tipc_nametbl_build_group(struct net *net, struct tipc_group *grp, for (n = rb_first(&sc->ranges); n; n = rb_next(n)) { sr = container_of(n, struct service_range, tree_node); list_for_each_entry(p, &sr->all_publ, all_publ) { - if (p->scope != scope) + if (p->scope != ua->scope) continue; - tipc_group_add_member(grp, p->node, p->port, p->lower); + tipc_group_add_member(grp, p->sk.node, p->sk.ref, + p->sr.lower); } } spin_unlock_bh(&sc->lock); @@ -741,9 +755,8 @@ exit: /* tipc_nametbl_publish - add service binding to name table */ -struct publication *tipc_nametbl_publish(struct net *net, u32 type, u32 lower, - u32 upper, u32 scope, u32 port, - u32 key) +struct publication *tipc_nametbl_publish(struct net *net, struct tipc_uaddr *ua, + struct tipc_socket_addr *sk, u32 key) { struct name_table *nt = tipc_name_table(net); struct tipc_net *tn = tipc_net(net); @@ -758,8 +771,7 @@ struct publication *tipc_nametbl_publish(struct net *net, u32 type, u32 lower, goto exit; } - p = tipc_nametbl_insert_publ(net, type, lower, upper, scope, - tipc_own_addr(net), port, key); + p = tipc_nametbl_insert_publ(net, ua, sk, key); if (p) { nt->local_publ_count++; skb = tipc_named_publish(net, p); @@ -777,41 +789,33 @@ exit: /** * tipc_nametbl_withdraw - withdraw a service binding * @net: network namespace - * @type: service type - * @lower: service range lower bound - * @upper: service range upper bound + * @ua: service address/range being unbound + * @sk: address of the socket being unbound from * @key: target publication key */ -int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower, - u32 upper, u32 key) +void tipc_nametbl_withdraw(struct net *net, struct tipc_uaddr *ua, + struct tipc_socket_addr *sk, u32 key) { struct name_table *nt = tipc_name_table(net); struct tipc_net *tn = tipc_net(net); - u32 self = tipc_own_addr(net); struct sk_buff *skb = NULL; struct publication *p; u32 rc_dests; spin_lock_bh(&tn->nametbl_lock); - p = tipc_nametbl_remove_publ(net, type, lower, upper, self, key); + p = tipc_nametbl_remove_publ(net, ua, sk, key); if (p) { nt->local_publ_count--; skb = tipc_named_withdraw(net, p); list_del_init(&p->binding_sock); kfree_rcu(p, rcu); - } else { - pr_err("Failed to remove local publication {%u,%u,%u}/%u\n", - type, lower, upper, key); } rc_dests = nt->rc_dests; spin_unlock_bh(&tn->nametbl_lock); - if (skb) { + if (skb) tipc_node_broadcast(net, skb, rc_dests); - return 1; - } - return 0; } /** @@ -820,25 +824,25 @@ int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower, */ bool tipc_nametbl_subscribe(struct tipc_subscription *sub) { - struct name_table *nt = tipc_name_table(sub->net); struct tipc_net *tn = tipc_net(sub->net); - struct tipc_subscr *s = &sub->evt.s; - u32 type = tipc_sub_read(s, seq.type); + u32 type = sub->s.seq.type; struct tipc_service *sc; + struct tipc_uaddr ua; bool res = true; + tipc_uaddr(&ua, TIPC_SERVICE_RANGE, TIPC_NODE_SCOPE, type, + sub->s.seq.lower, sub->s.seq.upper); spin_lock_bh(&tn->nametbl_lock); - sc = tipc_service_find(sub->net, type); + sc = tipc_service_find(sub->net, &ua); if (!sc) - sc = tipc_service_create(type, &nt->services[hash(type)]); + sc = tipc_service_create(sub->net, &ua); if (sc) { spin_lock_bh(&sc->lock); tipc_service_subscribe(sc, sub); spin_unlock_bh(&sc->lock); } else { - pr_warn("Failed to subscribe for {%u,%u,%u}\n", type, - tipc_sub_read(s, seq.lower), - tipc_sub_read(s, seq.upper)); + pr_warn("Failed to subscribe for {%u,%u,%u}\n", + type, sub->s.seq.lower, sub->s.seq.upper); res = false; } spin_unlock_bh(&tn->nametbl_lock); @@ -852,12 +856,13 @@ bool tipc_nametbl_subscribe(struct tipc_subscription *sub) void tipc_nametbl_unsubscribe(struct tipc_subscription *sub) { struct tipc_net *tn = tipc_net(sub->net); - struct tipc_subscr *s = &sub->evt.s; - u32 type = tipc_sub_read(s, seq.type); struct tipc_service *sc; + struct tipc_uaddr ua; + tipc_uaddr(&ua, TIPC_SERVICE_RANGE, TIPC_NODE_SCOPE, + sub->s.seq.type, sub->s.seq.lower, sub->s.seq.upper); spin_lock_bh(&tn->nametbl_lock); - sc = tipc_service_find(sub->net, type); + sc = tipc_service_find(sub->net, &ua); if (!sc) goto exit; @@ -909,7 +914,7 @@ static void tipc_service_delete(struct net *net, struct tipc_service *sc) spin_lock_bh(&sc->lock); rbtree_postorder_for_each_entry_safe(sr, tmpr, &sc->ranges, tree_node) { list_for_each_entry_safe(p, tmp, &sr->all_publ, all_publ) { - tipc_service_remove_publ(sr, p->node, p->key); + tipc_service_remove_publ(sr, &p->sk, p->key); kfree_rcu(p, rcu); } rb_erase_augmented(&sr->tree_node, &sc->ranges, &sr_callbacks); @@ -993,9 +998,9 @@ static int __tipc_nl_add_nametable_publ(struct tipc_nl_msg *msg, goto publ_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_SCOPE, p->scope)) goto publ_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_NODE, p->node)) + if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_NODE, p->sk.node)) goto publ_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_REF, p->port)) + if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_REF, p->sk.ref)) goto publ_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PUBL_KEY, p->key)) goto publ_msg_full; @@ -1046,6 +1051,7 @@ static int tipc_nl_service_list(struct net *net, struct tipc_nl_msg *msg, struct tipc_net *tn = tipc_net(net); struct tipc_service *service = NULL; struct hlist_head *head; + struct tipc_uaddr ua; int err; int i; @@ -1059,7 +1065,9 @@ static int tipc_nl_service_list(struct net *net, struct tipc_nl_msg *msg, if (*last_type || (!i && *last_key && (*last_lower == *last_key))) { - service = tipc_service_find(net, *last_type); + tipc_uaddr(&ua, TIPC_SERVICE_RANGE, TIPC_NODE_SCOPE, + *last_type, *last_lower, *last_lower); + service = tipc_service_find(net, &ua); if (!service) return -EPIPE; } else { diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index 5a82a01369d6..c7c9a3ddd420 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -3,6 +3,7 @@ * * Copyright (c) 2000-2006, 2014-2018, Ericsson AB * Copyright (c) 2004-2005, 2010-2011, Wind River Systems + * Copyright (c) 2020-2021, Red Hat Inc * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -41,6 +42,7 @@ struct tipc_subscription; struct tipc_plist; struct tipc_nlist; struct tipc_group; +struct tipc_uaddr; /* * TIPC name types reserved for internal TIPC use (both current and planned) @@ -50,13 +52,10 @@ struct tipc_group; #define TIPC_NAMETBL_SIZE 1024 /* must be a power of 2 */ /** - * struct publication - info about a published (name or) name sequence - * @type: name sequence type - * @lower: name sequence lower bound - * @upper: name sequence upper bound + * struct publication - info about a published service address or range + * @sr: service range represented by this publication + * @sk: address of socket bound to this publication * @scope: scope of publication, TIPC_NODE_SCOPE or TIPC_CLUSTER_SCOPE - * @node: network address of publishing socket's node - * @port: publishing port * @key: publication key, unique across the cluster * @id: publication id * @binding_node: all publications from the same node which bound this one @@ -74,12 +73,9 @@ struct tipc_group; * @rcu: RCU callback head used for deferred freeing */ struct publication { - u32 type; - u32 lower; - u32 upper; - u32 scope; - u32 node; - u32 port; + struct tipc_service_range sr; + struct tipc_socket_addr sk; + u16 scope; u32 key; u32 id; struct list_head binding_node; @@ -114,28 +110,29 @@ struct name_table { }; int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb); - -u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, u32 *node); -void tipc_nametbl_mc_lookup(struct net *net, u32 type, u32 lower, u32 upper, - u32 scope, bool exact, struct list_head *dports); +bool tipc_nametbl_lookup_anycast(struct net *net, struct tipc_uaddr *ua, + struct tipc_socket_addr *sk); +void tipc_nametbl_lookup_mcast_sockets(struct net *net, struct tipc_uaddr *ua, + bool exact, struct list_head *dports); +void tipc_nametbl_lookup_mcast_nodes(struct net *net, struct tipc_uaddr *ua, + struct tipc_nlist *nodes); +bool tipc_nametbl_lookup_group(struct net *net, struct tipc_uaddr *ua, + struct list_head *dsts, int *dstcnt, + u32 exclude, bool mcast); void tipc_nametbl_build_group(struct net *net, struct tipc_group *grp, - u32 type, u32 domain); -void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower, - u32 upper, struct tipc_nlist *nodes); -bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 domain, - struct list_head *dsts, int *dstcnt, u32 exclude, - bool all); -struct publication *tipc_nametbl_publish(struct net *net, u32 type, u32 lower, - u32 upper, u32 scope, u32 port, - u32 key); -int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower, u32 upper, - u32 key); -struct publication *tipc_nametbl_insert_publ(struct net *net, u32 type, - u32 lower, u32 upper, u32 scope, - u32 node, u32 ref, u32 key); -struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type, - u32 lower, u32 upper, - u32 node, u32 key); + struct tipc_uaddr *ua); +struct publication *tipc_nametbl_publish(struct net *net, struct tipc_uaddr *ua, + struct tipc_socket_addr *sk, u32 key); +void tipc_nametbl_withdraw(struct net *net, struct tipc_uaddr *ua, + struct tipc_socket_addr *sk, u32 key); +struct publication *tipc_nametbl_insert_publ(struct net *net, + struct tipc_uaddr *ua, + struct tipc_socket_addr *sk, + u32 key); +struct publication *tipc_nametbl_remove_publ(struct net *net, + struct tipc_uaddr *ua, + struct tipc_socket_addr *sk, + u32 key); bool tipc_nametbl_subscribe(struct tipc_subscription *s); void tipc_nametbl_unsubscribe(struct tipc_subscription *s); int tipc_nametbl_init(struct net *net); diff --git a/net/tipc/net.c b/net/tipc/net.c index a129f661bee3..3f927949bb23 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -125,6 +125,11 @@ int tipc_net_init(struct net *net, u8 *node_id, u32 addr) static void tipc_net_finalize(struct net *net, u32 addr) { struct tipc_net *tn = tipc_net(net); + struct tipc_socket_addr sk = {0, addr}; + struct tipc_uaddr ua; + + tipc_uaddr(&ua, TIPC_SERVICE_RANGE, TIPC_CLUSTER_SCOPE, + TIPC_NODE_STATE, addr, addr); if (cmpxchg(&tn->node_addr, 0, addr)) return; @@ -132,8 +137,7 @@ static void tipc_net_finalize(struct net *net, u32 addr) tipc_named_reinit(net); tipc_sk_reinit(net); tipc_mon_reinit_self(net); - tipc_nametbl_publish(net, TIPC_NODE_STATE, addr, addr, - TIPC_CLUSTER_SCOPE, 0, addr); + tipc_nametbl_publish(net, &ua, &sk, addr); } void tipc_net_finalize_work(struct work_struct *work) diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 5a1ce64039f7..0749df80454d 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -696,7 +696,7 @@ static int tipc_nl_compat_link_dump(struct tipc_nl_compat_msg *msg, if (err) return err; - link_info.dest = nla_get_flag(link[TIPC_NLA_LINK_DEST]); + link_info.dest = htonl(nla_get_flag(link[TIPC_NLA_LINK_DEST])); link_info.up = htonl(nla_get_flag(link[TIPC_NLA_LINK_UP])); nla_strscpy(link_info.str, link[TIPC_NLA_LINK_NAME], TIPC_MAX_LINK_NAME); diff --git a/net/tipc/node.c b/net/tipc/node.c index 136338b85504..61c38eaaa298 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -372,42 +372,49 @@ static struct tipc_node *tipc_node_find_by_id(struct net *net, u8 *id) } static void tipc_node_read_lock(struct tipc_node *n) + __acquires(n->lock) { read_lock_bh(&n->lock); } static void tipc_node_read_unlock(struct tipc_node *n) + __releases(n->lock) { read_unlock_bh(&n->lock); } static void tipc_node_write_lock(struct tipc_node *n) + __acquires(n->lock) { write_lock_bh(&n->lock); } static void tipc_node_write_unlock_fast(struct tipc_node *n) + __releases(n->lock) { write_unlock_bh(&n->lock); } static void tipc_node_write_unlock(struct tipc_node *n) + __releases(n->lock) { + struct tipc_socket_addr sk; struct net *net = n->net; - u32 addr = 0; u32 flags = n->action_flags; - u32 link_id = 0; - u32 bearer_id; struct list_head *publ_list; + struct tipc_uaddr ua; + u32 bearer_id; if (likely(!flags)) { write_unlock_bh(&n->lock); return; } - addr = n->addr; - link_id = n->link_id; - bearer_id = link_id & 0xffff; + tipc_uaddr(&ua, TIPC_SERVICE_RANGE, TIPC_NODE_SCOPE, + TIPC_LINK_STATE, n->addr, n->addr); + sk.ref = n->link_id; + sk.node = n->addr; + bearer_id = n->link_id & 0xffff; publ_list = &n->publ_list; n->action_flags &= ~(TIPC_NOTIFY_NODE_DOWN | TIPC_NOTIFY_NODE_UP | @@ -416,20 +423,18 @@ static void tipc_node_write_unlock(struct tipc_node *n) write_unlock_bh(&n->lock); if (flags & TIPC_NOTIFY_NODE_DOWN) - tipc_publ_notify(net, publ_list, addr, n->capabilities); + tipc_publ_notify(net, publ_list, n->addr, n->capabilities); if (flags & TIPC_NOTIFY_NODE_UP) - tipc_named_node_up(net, addr, n->capabilities); + tipc_named_node_up(net, n->addr, n->capabilities); if (flags & TIPC_NOTIFY_LINK_UP) { - tipc_mon_peer_up(net, addr, bearer_id); - tipc_nametbl_publish(net, TIPC_LINK_STATE, addr, addr, - TIPC_NODE_SCOPE, link_id, link_id); + tipc_mon_peer_up(net, n->addr, bearer_id); + tipc_nametbl_publish(net, &ua, &sk, n->link_id); } if (flags & TIPC_NOTIFY_LINK_DOWN) { - tipc_mon_peer_down(net, addr, bearer_id); - tipc_nametbl_withdraw(net, TIPC_LINK_STATE, addr, - addr, link_id); + tipc_mon_peer_down(net, n->addr, bearer_id); + tipc_nametbl_withdraw(net, &ua, &sk, n->link_id); } } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index cebcc104dc70..117a472a8e61 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -3,7 +3,7 @@ * * Copyright (c) 2001-2007, 2012-2019, Ericsson AB * Copyright (c) 2004-2008, 2010-2013, Wind River Systems - * Copyright (c) 2020, Red Hat Inc + * Copyright (c) 2020-2021, Red Hat Inc * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -111,7 +111,6 @@ struct tipc_sock { struct sock sk; u32 conn_type; u32 conn_instance; - int published; u32 max_pkt; u32 maxnagle; u32 portid; @@ -141,6 +140,7 @@ struct tipc_sock { bool expect_ack; bool nodelay; bool group_is_open; + bool published; }; static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb); @@ -151,10 +151,8 @@ static int tipc_release(struct socket *sock); static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, bool kern); static void tipc_sk_timeout(struct timer_list *t); -static int tipc_sk_publish(struct tipc_sock *tsk, uint scope, - struct tipc_service_range const *seq); -static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope, - struct tipc_service_range const *seq); +static int tipc_sk_publish(struct tipc_sock *tsk, struct tipc_uaddr *ua); +static int tipc_sk_withdraw(struct tipc_sock *tsk, struct tipc_uaddr *ua); static int tipc_sk_leave(struct tipc_sock *tsk); static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid); static int tipc_sk_insert(struct tipc_sock *tsk); @@ -644,7 +642,7 @@ static int tipc_release(struct socket *sock) __tipc_shutdown(sock, TIPC_ERR_NO_PORT); sk->sk_shutdown = SHUTDOWN_MASK; tipc_sk_leave(tsk); - tipc_sk_withdraw(tsk, 0, NULL); + tipc_sk_withdraw(tsk, NULL); __skb_queue_purge(&tsk->mc_method.deferredq); sk_stop_timer(sk, &sk->sk_timer); tipc_sk_remove(tsk); @@ -677,22 +675,31 @@ static int tipc_release(struct socket *sock) */ static int __tipc_bind(struct socket *sock, struct sockaddr *skaddr, int alen) { - struct sockaddr_tipc *addr = (struct sockaddr_tipc *)skaddr; + struct tipc_uaddr *ua = (struct tipc_uaddr *)skaddr; struct tipc_sock *tsk = tipc_sk(sock->sk); + bool unbind = false; if (unlikely(!alen)) - return tipc_sk_withdraw(tsk, 0, NULL); + return tipc_sk_withdraw(tsk, NULL); - if (addr->addrtype == TIPC_SERVICE_ADDR) - addr->addr.nameseq.upper = addr->addr.nameseq.lower; + if (ua->addrtype == TIPC_SERVICE_ADDR) { + ua->addrtype = TIPC_SERVICE_RANGE; + ua->sr.upper = ua->sr.lower; + } + if (ua->scope < 0) { + unbind = true; + ua->scope = -ua->scope; + } + /* Users may still use deprecated TIPC_ZONE_SCOPE */ + if (ua->scope != TIPC_NODE_SCOPE) + ua->scope = TIPC_CLUSTER_SCOPE; if (tsk->group) return -EACCES; - if (addr->scope >= 0) - return tipc_sk_publish(tsk, addr->scope, &addr->addr.nameseq); - else - return tipc_sk_withdraw(tsk, -addr->scope, &addr->addr.nameseq); + if (unbind) + return tipc_sk_withdraw(tsk, ua); + return tipc_sk_publish(tsk, ua); } int tipc_sk_bind(struct socket *sock, struct sockaddr *skaddr, int alen) @@ -707,18 +714,17 @@ int tipc_sk_bind(struct socket *sock, struct sockaddr *skaddr, int alen) static int tipc_bind(struct socket *sock, struct sockaddr *skaddr, int alen) { - struct sockaddr_tipc *addr = (struct sockaddr_tipc *)skaddr; + struct tipc_uaddr *ua = (struct tipc_uaddr *)skaddr; + u32 atype = ua->addrtype; if (alen) { - if (alen < sizeof(struct sockaddr_tipc)) + if (!tipc_uaddr_valid(ua, alen)) return -EINVAL; - if (addr->family != AF_TIPC) + if (atype == TIPC_SOCKET_ADDR) return -EAFNOSUPPORT; - if (addr->addrtype > TIPC_SERVICE_ADDR) - return -EAFNOSUPPORT; - if (addr->addr.nameseq.type < TIPC_RESERVED_TYPES) { + if (ua->sr.type < TIPC_RESERVED_TYPES) { pr_warn_once("Can't bind to reserved service type %u\n", - addr->addr.nameseq.type); + ua->sr.type); return -EACCES; } } @@ -826,7 +832,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock, /** * tipc_sendmcast - send multicast message * @sock: socket structure - * @seq: destination address + * @ua: destination address struct * @msg: message to send * @dlen: length of data to send * @timeout: timeout to wait for wakeup @@ -834,7 +840,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock, * Called from function tipc_sendmsg(), which has done all sanity checks * Return: the number of bytes sent on success, or errno */ -static int tipc_sendmcast(struct socket *sock, struct tipc_service_range *seq, +static int tipc_sendmcast(struct socket *sock, struct tipc_uaddr *ua, struct msghdr *msg, size_t dlen, long timeout) { struct sock *sk = sock->sk; @@ -842,7 +848,6 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_service_range *seq, struct tipc_msg *hdr = &tsk->phdr; struct net *net = sock_net(sk); int mtu = tipc_bcast_get_mtu(net); - struct tipc_mc_method *method = &tsk->mc_method; struct sk_buff_head pkts; struct tipc_nlist dsts; int rc; @@ -857,8 +862,7 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_service_range *seq, /* Lookup destination nodes */ tipc_nlist_init(&dsts, tipc_own_addr(net)); - tipc_nametbl_lookup_dst_nodes(net, seq->type, seq->lower, - seq->upper, &dsts); + tipc_nametbl_lookup_mcast_nodes(net, ua, &dsts); if (!dsts.local && !dsts.remote) return -EHOSTUNREACH; @@ -868,9 +872,9 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_service_range *seq, msg_set_lookup_scope(hdr, TIPC_CLUSTER_SCOPE); msg_set_destport(hdr, 0); msg_set_destnode(hdr, 0); - msg_set_nametype(hdr, seq->type); - msg_set_namelower(hdr, seq->lower); - msg_set_nameupper(hdr, seq->upper); + msg_set_nametype(hdr, ua->sr.type); + msg_set_namelower(hdr, ua->sr.lower); + msg_set_nameupper(hdr, ua->sr.upper); /* Build message as chain of buffers */ __skb_queue_head_init(&pkts); @@ -880,7 +884,7 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_service_range *seq, if (unlikely(rc == dlen)) { trace_tipc_sk_sendmcast(sk, skb_peek(&pkts), TIPC_DUMP_SK_SNDQ, " "); - rc = tipc_mcast_xmit(net, &pkts, method, &dsts, + rc = tipc_mcast_xmit(net, &pkts, &tsk->mc_method, &dsts, &tsk->cong_link_cnt); } @@ -954,7 +958,7 @@ static int tipc_send_group_unicast(struct socket *sock, struct msghdr *m, int dlen, long timeout) { struct sock *sk = sock->sk; - DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); + struct tipc_uaddr *ua = (struct tipc_uaddr *)m->msg_name; int blks = tsk_blocks(GROUP_H_SIZE + dlen); struct tipc_sock *tsk = tipc_sk(sk); struct net *net = sock_net(sk); @@ -962,8 +966,8 @@ static int tipc_send_group_unicast(struct socket *sock, struct msghdr *m, u32 node, port; int rc; - node = dest->addr.id.node; - port = dest->addr.id.ref; + node = ua->sk.node; + port = ua->sk.ref; if (!port && !node) return -EHOSTUNREACH; @@ -997,7 +1001,7 @@ static int tipc_send_group_unicast(struct socket *sock, struct msghdr *m, static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m, int dlen, long timeout) { - DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); + struct tipc_uaddr *ua = (struct tipc_uaddr *)m->msg_name; struct sock *sk = sock->sk; struct tipc_sock *tsk = tipc_sk(sk); struct list_head *cong_links = &tsk->cong_links; @@ -1008,16 +1012,13 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m, struct net *net = sock_net(sk); u32 node, port, exclude; struct list_head dsts; - u32 type, inst, scope; int lookups = 0; int dstcnt, rc; bool cong; INIT_LIST_HEAD(&dsts); - - type = msg_nametype(hdr); - inst = dest->addr.name.name.instance; - scope = msg_lookup_scope(hdr); + ua->sa.type = msg_nametype(hdr); + ua->scope = msg_lookup_scope(hdr); while (++lookups < 4) { exclude = tipc_group_exclude(tsk->group); @@ -1026,8 +1027,8 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m, /* Look for a non-congested destination member, if any */ while (1) { - if (!tipc_nametbl_lookup(net, type, inst, scope, &dsts, - &dstcnt, exclude, false)) + if (!tipc_nametbl_lookup_group(net, ua, &dsts, &dstcnt, + exclude, false)) return -EHOSTUNREACH; tipc_dest_pop(&dsts, &node, &port); cong = tipc_group_cong(tsk->group, node, port, blks, @@ -1082,7 +1083,7 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m, static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, int dlen, long timeout) { - DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); + struct tipc_uaddr *ua = (struct tipc_uaddr *)m->msg_name; struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct tipc_sock *tsk = tipc_sk(sk); @@ -1107,9 +1108,9 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, return -EHOSTUNREACH; /* Complete message header */ - if (dest) { + if (ua) { msg_set_type(hdr, TIPC_GRP_MCAST_MSG); - msg_set_nameinst(hdr, dest->addr.name.name.instance); + msg_set_nameinst(hdr, ua->sa.instance); } else { msg_set_type(hdr, TIPC_GRP_BCAST_MSG); msg_set_nameinst(hdr, 0); @@ -1156,29 +1157,25 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, static int tipc_send_group_mcast(struct socket *sock, struct msghdr *m, int dlen, long timeout) { + struct tipc_uaddr *ua = (struct tipc_uaddr *)m->msg_name; struct sock *sk = sock->sk; - DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); struct tipc_sock *tsk = tipc_sk(sk); struct tipc_group *grp = tsk->group; struct tipc_msg *hdr = &tsk->phdr; struct net *net = sock_net(sk); - u32 type, inst, scope, exclude; struct list_head dsts; - u32 dstcnt; + u32 dstcnt, exclude; INIT_LIST_HEAD(&dsts); - - type = msg_nametype(hdr); - inst = dest->addr.name.name.instance; - scope = msg_lookup_scope(hdr); + ua->sa.type = msg_nametype(hdr); + ua->scope = msg_lookup_scope(hdr); exclude = tipc_group_exclude(grp); - if (!tipc_nametbl_lookup(net, type, inst, scope, &dsts, - &dstcnt, exclude, true)) + if (!tipc_nametbl_lookup_group(net, ua, &dsts, &dstcnt, exclude, true)) return -EHOSTUNREACH; if (dstcnt == 1) { - tipc_dest_pop(&dsts, &dest->addr.id.node, &dest->addr.id.ref); + tipc_dest_pop(&dsts, &ua->sk.node, &ua->sk.ref); return tipc_send_group_unicast(sock, m, dlen, timeout); } @@ -1198,17 +1195,18 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, struct sk_buff_head *inputq) { u32 self = tipc_own_addr(net); - u32 type, lower, upper, scope; struct sk_buff *skb, *_skb; u32 portid, onode; struct sk_buff_head tmpq; struct list_head dports; struct tipc_msg *hdr; + struct tipc_uaddr ua; int user, mtyp, hlen; bool exact; __skb_queue_head_init(&tmpq); INIT_LIST_HEAD(&dports); + ua.addrtype = TIPC_SERVICE_RANGE; skb = tipc_skb_peek(arrvq, &inputq->lock); for (; skb; skb = tipc_skb_peek(arrvq, &inputq->lock)) { @@ -1217,7 +1215,7 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, mtyp = msg_type(hdr); hlen = skb_headroom(skb) + msg_hdr_sz(hdr); onode = msg_orignode(hdr); - type = msg_nametype(hdr); + ua.sr.type = msg_nametype(hdr); if (mtyp == TIPC_GRP_UCAST_MSG || user == GROUP_PROTOCOL) { spin_lock_bh(&inputq->lock); @@ -1232,24 +1230,23 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, /* Group messages require exact scope match */ if (msg_in_group(hdr)) { - lower = 0; - upper = ~0; - scope = msg_lookup_scope(hdr); + ua.sr.lower = 0; + ua.sr.upper = ~0; + ua.scope = msg_lookup_scope(hdr); exact = true; } else { /* TIPC_NODE_SCOPE means "any scope" in this context */ if (onode == self) - scope = TIPC_NODE_SCOPE; + ua.scope = TIPC_NODE_SCOPE; else - scope = TIPC_CLUSTER_SCOPE; + ua.scope = TIPC_CLUSTER_SCOPE; exact = false; - lower = msg_namelower(hdr); - upper = msg_nameupper(hdr); + ua.sr.lower = msg_namelower(hdr); + ua.sr.upper = msg_nameupper(hdr); } /* Create destination port list: */ - tipc_nametbl_mc_lookup(net, type, lower, upper, - scope, exact, &dports); + tipc_nametbl_lookup_mcast_sockets(net, &ua, exact, &dports); /* Clone message per destination */ while (tipc_dest_pop(&dports, NULL, &portid)) { @@ -1417,44 +1414,43 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct tipc_sock *tsk = tipc_sk(sk); - DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); + struct tipc_uaddr *ua = (struct tipc_uaddr *)m->msg_name; long timeout = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); struct list_head *clinks = &tsk->cong_links; bool syn = !tipc_sk_type_connectionless(sk); struct tipc_group *grp = tsk->group; struct tipc_msg *hdr = &tsk->phdr; - struct tipc_service_range *seq; + struct tipc_socket_addr skaddr; struct sk_buff_head pkts; - u32 dport = 0, dnode = 0; - u32 type = 0, inst = 0; - int mtu, rc; + int atype, mtu, rc; if (unlikely(dlen > TIPC_MAX_USER_MSG_SIZE)) return -EMSGSIZE; - if (likely(dest)) { - if (unlikely(m->msg_namelen < sizeof(*dest))) - return -EINVAL; - if (unlikely(dest->family != AF_TIPC)) + if (ua) { + if (!tipc_uaddr_valid(ua, m->msg_namelen)) return -EINVAL; + atype = ua->addrtype; } + /* If socket belongs to a communication group follow other paths */ if (grp) { - if (!dest) + if (!ua) return tipc_send_group_bcast(sock, m, dlen, timeout); - if (dest->addrtype == TIPC_SERVICE_ADDR) + if (atype == TIPC_SERVICE_ADDR) return tipc_send_group_anycast(sock, m, dlen, timeout); - if (dest->addrtype == TIPC_SOCKET_ADDR) + if (atype == TIPC_SOCKET_ADDR) return tipc_send_group_unicast(sock, m, dlen, timeout); - if (dest->addrtype == TIPC_ADDR_MCAST) + if (atype == TIPC_SERVICE_RANGE) return tipc_send_group_mcast(sock, m, dlen, timeout); return -EINVAL; } - if (unlikely(!dest)) { - dest = &tsk->peer; - if (!syn && dest->family != AF_TIPC) + if (!ua) { + ua = (struct tipc_uaddr *)&tsk->peer; + if (!syn && ua->family != AF_TIPC) return -EDESTADDRREQ; + atype = ua->addrtype; } if (unlikely(syn)) { @@ -1464,54 +1460,51 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) return -EISCONN; if (tsk->published) return -EOPNOTSUPP; - if (dest->addrtype == TIPC_SERVICE_ADDR) { - tsk->conn_type = dest->addr.name.name.type; - tsk->conn_instance = dest->addr.name.name.instance; + if (atype == TIPC_SERVICE_ADDR) { + tsk->conn_type = ua->sa.type; + tsk->conn_instance = ua->sa.instance; } msg_set_syn(hdr, 1); } - seq = &dest->addr.nameseq; - if (dest->addrtype == TIPC_ADDR_MCAST) - return tipc_sendmcast(sock, seq, m, dlen, timeout); - - if (dest->addrtype == TIPC_SERVICE_ADDR) { - type = dest->addr.name.name.type; - inst = dest->addr.name.name.instance; - dnode = dest->addr.name.domain; - dport = tipc_nametbl_translate(net, type, inst, &dnode); - if (unlikely(!dport && !dnode)) + /* Determine destination */ + if (atype == TIPC_SERVICE_RANGE) { + return tipc_sendmcast(sock, ua, m, dlen, timeout); + } else if (atype == TIPC_SERVICE_ADDR) { + skaddr.node = ua->lookup_node; + ua->scope = tipc_node2scope(skaddr.node); + if (!tipc_nametbl_lookup_anycast(net, ua, &skaddr)) return -EHOSTUNREACH; - } else if (dest->addrtype == TIPC_SOCKET_ADDR) { - dnode = dest->addr.id.node; + } else if (atype == TIPC_SOCKET_ADDR) { + skaddr = ua->sk; } else { return -EINVAL; } /* Block or return if destination link is congested */ rc = tipc_wait_for_cond(sock, &timeout, - !tipc_dest_find(clinks, dnode, 0)); + !tipc_dest_find(clinks, skaddr.node, 0)); if (unlikely(rc)) return rc; - if (dest->addrtype == TIPC_SERVICE_ADDR) { + /* Finally build message header */ + msg_set_destnode(hdr, skaddr.node); + msg_set_destport(hdr, skaddr.ref); + if (atype == TIPC_SERVICE_ADDR) { 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); + msg_set_nametype(hdr, ua->sa.type); + msg_set_nameinst(hdr, ua->sa.instance); + msg_set_lookup_scope(hdr, ua->scope); } else { /* TIPC_SOCKET_ADDR */ 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); } + /* Add message body */ __skb_queue_head_init(&pkts); - mtu = tipc_node_get_mtu(net, dnode, tsk->portid, true); + mtu = tipc_node_get_mtu(net, skaddr.node, tsk->portid, true); rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts); if (unlikely(rc != dlen)) return rc; @@ -1520,10 +1513,11 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) return -ENOMEM; } + /* Send message */ trace_tipc_sk_sendmsg(sk, skb_peek(&pkts), TIPC_DUMP_SK_SNDQ, " "); - rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid); + rc = tipc_node_xmit(net, &pkts, skaddr.node, tsk->portid); if (unlikely(rc == -ELINKCONG)) { - tipc_dest_push(clinks, dnode, 0); + tipc_dest_push(clinks, skaddr.node, 0); tsk->cong_link_cnt++; rc = 0; } @@ -2891,66 +2885,62 @@ static void tipc_sk_timeout(struct timer_list *t) sock_put(sk); } -static int tipc_sk_publish(struct tipc_sock *tsk, uint scope, - struct tipc_service_range const *seq) +static int tipc_sk_publish(struct tipc_sock *tsk, struct tipc_uaddr *ua) { struct sock *sk = &tsk->sk; struct net *net = sock_net(sk); - struct publication *publ; + struct tipc_socket_addr skaddr; + struct publication *p; u32 key; - if (scope != TIPC_NODE_SCOPE) - scope = TIPC_CLUSTER_SCOPE; - if (tipc_sk_connected(sk)) return -EINVAL; key = tsk->portid + tsk->pub_count + 1; if (key == tsk->portid) return -EADDRINUSE; - - publ = tipc_nametbl_publish(net, seq->type, seq->lower, seq->upper, - scope, tsk->portid, key); - if (unlikely(!publ)) + skaddr.ref = tsk->portid; + skaddr.node = tipc_own_addr(net); + p = tipc_nametbl_publish(net, ua, &skaddr, key); + if (unlikely(!p)) return -EINVAL; - list_add(&publ->binding_sock, &tsk->publications); + list_add(&p->binding_sock, &tsk->publications); tsk->pub_count++; - tsk->published = 1; + tsk->published = true; return 0; } -static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope, - struct tipc_service_range const *seq) +static int tipc_sk_withdraw(struct tipc_sock *tsk, struct tipc_uaddr *ua) { struct net *net = sock_net(&tsk->sk); - struct publication *publ; - struct publication *safe; + struct publication *safe, *p; + struct tipc_uaddr _ua; int rc = -EINVAL; - if (scope != TIPC_NODE_SCOPE) - scope = TIPC_CLUSTER_SCOPE; - - list_for_each_entry_safe(publ, safe, &tsk->publications, binding_sock) { - if (seq) { - if (publ->scope != scope) - continue; - if (publ->type != seq->type) - continue; - if (publ->lower != seq->lower) - continue; - if (publ->upper != seq->upper) - break; - tipc_nametbl_withdraw(net, publ->type, publ->lower, - publ->upper, publ->key); - rc = 0; - break; + list_for_each_entry_safe(p, safe, &tsk->publications, binding_sock) { + if (!ua) { + tipc_uaddr(&_ua, TIPC_SERVICE_RANGE, p->scope, + p->sr.type, p->sr.lower, p->sr.upper); + tipc_nametbl_withdraw(net, &_ua, &p->sk, p->key); + continue; } - tipc_nametbl_withdraw(net, publ->type, publ->lower, - publ->upper, publ->key); + /* Unbind specific publication */ + if (p->scope != ua->scope) + continue; + if (p->sr.type != ua->sr.type) + continue; + if (p->sr.lower != ua->sr.lower) + continue; + if (p->sr.upper != ua->sr.upper) + break; + tipc_nametbl_withdraw(net, ua, &p->sk, p->key); rc = 0; + break; } - if (list_empty(&tsk->publications)) + if (list_empty(&tsk->publications)) { tsk->published = 0; + rc = 0; + } return rc; } @@ -3067,13 +3057,15 @@ static int tipc_sk_join(struct tipc_sock *tsk, struct tipc_group_req *mreq) struct net *net = sock_net(&tsk->sk); struct tipc_group *grp = tsk->group; struct tipc_msg *hdr = &tsk->phdr; - struct tipc_service_range seq; + struct tipc_uaddr ua; int rc; if (mreq->type < TIPC_RESERVED_TYPES) return -EACCES; if (mreq->scope > TIPC_NODE_SCOPE) return -EINVAL; + if (mreq->scope != TIPC_NODE_SCOPE) + mreq->scope = TIPC_CLUSTER_SCOPE; if (grp) return -EACCES; grp = tipc_group_create(net, tsk->portid, mreq, &tsk->group_is_open); @@ -3083,11 +3075,10 @@ static int tipc_sk_join(struct tipc_sock *tsk, struct tipc_group_req *mreq) msg_set_lookup_scope(hdr, mreq->scope); msg_set_nametype(hdr, mreq->type); msg_set_dest_droppable(hdr, true); - seq.type = mreq->type; - seq.lower = mreq->instance; - seq.upper = seq.lower; - tipc_nametbl_build_group(net, grp, mreq->type, mreq->scope); - rc = tipc_sk_publish(tsk, mreq->scope, &seq); + tipc_uaddr(&ua, TIPC_SERVICE_RANGE, mreq->scope, + mreq->type, mreq->instance, mreq->instance); + tipc_nametbl_build_group(net, grp, &ua); + rc = tipc_sk_publish(tsk, &ua); if (rc) { tipc_group_delete(net, grp); tsk->group = NULL; @@ -3104,15 +3095,17 @@ static int tipc_sk_leave(struct tipc_sock *tsk) { struct net *net = sock_net(&tsk->sk); struct tipc_group *grp = tsk->group; - struct tipc_service_range seq; + struct tipc_uaddr ua; int scope; if (!grp) return -EINVAL; - tipc_group_self(grp, &seq, &scope); + ua.addrtype = TIPC_SERVICE_RANGE; + tipc_group_self(grp, &ua.sr, &scope); + ua.scope = scope; tipc_group_delete(net, grp); tsk->group = NULL; - tipc_sk_withdraw(tsk, scope, &seq); + tipc_sk_withdraw(tsk, &ua); return 0; } @@ -3711,11 +3704,11 @@ static int __tipc_nl_add_sk_publ(struct sk_buff *skb, if (nla_put_u32(skb, TIPC_NLA_PUBL_KEY, publ->key)) goto attr_msg_cancel; - if (nla_put_u32(skb, TIPC_NLA_PUBL_TYPE, publ->type)) + if (nla_put_u32(skb, TIPC_NLA_PUBL_TYPE, publ->sr.type)) goto attr_msg_cancel; - if (nla_put_u32(skb, TIPC_NLA_PUBL_LOWER, publ->lower)) + if (nla_put_u32(skb, TIPC_NLA_PUBL_LOWER, publ->sr.lower)) goto attr_msg_cancel; - if (nla_put_u32(skb, TIPC_NLA_PUBL_UPPER, publ->upper)) + if (nla_put_u32(skb, TIPC_NLA_PUBL_UPPER, publ->sr.upper)) goto attr_msg_cancel; nla_nest_end(skb, attrs); @@ -3863,9 +3856,9 @@ bool tipc_sk_filtering(struct sock *sk) p = list_first_entry_or_null(&tsk->publications, struct publication, binding_sock); if (p) { - type = p->type; - lower = p->lower; - upper = p->upper; + type = p->sr.type; + lower = p->sr.lower; + upper = p->sr.upper; } } @@ -3964,9 +3957,9 @@ int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf) if (tsk->published) { p = list_first_entry_or_null(&tsk->publications, struct publication, binding_sock); - i += scnprintf(buf + i, sz - i, " %u", (p) ? p->type : 0); - i += scnprintf(buf + i, sz - i, " %u", (p) ? p->lower : 0); - i += scnprintf(buf + i, sz - i, " %u", (p) ? p->upper : 0); + i += scnprintf(buf + i, sz - i, " %u", (p) ? p->sr.type : 0); + i += scnprintf(buf + i, sz - i, " %u", (p) ? p->sr.lower : 0); + i += scnprintf(buf + i, sz - i, " %u", (p) ? p->sr.upper : 0); } i += scnprintf(buf + i, sz - i, " | %u", tsk->snd_win); i += scnprintf(buf + i, sz - i, " %u", tsk->rcv_win); diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index f6ad0005218c..8e00d739f03a 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -3,7 +3,7 @@ * * Copyright (c) 2000-2017, Ericsson AB * Copyright (c) 2005-2007, 2010-2013, Wind River Systems - * Copyright (c) 2020, Red Hat Inc + * Copyright (c) 2020-2021, Red Hat Inc * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -40,77 +40,75 @@ #include "subscr.h" static void tipc_sub_send_event(struct tipc_subscription *sub, - u32 found_lower, u32 found_upper, - u32 event, u32 port, u32 node) + struct publication *p, + u32 event) { + struct tipc_subscr *s = &sub->evt.s; struct tipc_event *evt = &sub->evt; if (sub->inactive) return; tipc_evt_write(evt, event, event); - tipc_evt_write(evt, found_lower, found_lower); - tipc_evt_write(evt, found_upper, found_upper); - tipc_evt_write(evt, port.ref, port); - tipc_evt_write(evt, port.node, node); + if (p) { + tipc_evt_write(evt, found_lower, p->sr.lower); + tipc_evt_write(evt, found_upper, p->sr.upper); + tipc_evt_write(evt, port.ref, p->sk.ref); + tipc_evt_write(evt, port.node, p->sk.node); + } else { + tipc_evt_write(evt, found_lower, s->seq.lower); + tipc_evt_write(evt, found_upper, s->seq.upper); + tipc_evt_write(evt, port.ref, 0); + tipc_evt_write(evt, port.node, 0); + } tipc_topsrv_queue_evt(sub->net, sub->conid, event, evt); } /** * tipc_sub_check_overlap - test for subscription overlap with the given values - * @seq: tipc_name_seq to check - * @found_lower: lower value to test - * @found_upper: upper value to test + * @subscribed: the service range subscribed for + * @found: the service range we are checning for match * - * Return: 1 if there is overlap, otherwise 0. + * Returns true if there is overlap, otherwise false. */ -int tipc_sub_check_overlap(struct tipc_service_range *seq, u32 found_lower, - u32 found_upper) +static bool tipc_sub_check_overlap(struct tipc_service_range *subscribed, + struct tipc_service_range *found) { - if (found_lower < seq->lower) - found_lower = seq->lower; - if (found_upper > seq->upper) - found_upper = seq->upper; - if (found_lower > found_upper) - return 0; - return 1; + u32 found_lower = found->lower; + u32 found_upper = found->upper; + + if (found_lower < subscribed->lower) + found_lower = subscribed->lower; + if (found_upper > subscribed->upper) + found_upper = subscribed->upper; + return found_lower <= found_upper; } void tipc_sub_report_overlap(struct tipc_subscription *sub, - u32 found_lower, u32 found_upper, - u32 event, u32 port, u32 node, - u32 scope, int must) + struct publication *p, + u32 event, bool must) { - struct tipc_subscr *s = &sub->evt.s; - u32 filter = tipc_sub_read(s, filter); - struct tipc_service_range seq; + struct tipc_service_range *sr = &sub->s.seq; + u32 filter = sub->s.filter; - seq.type = tipc_sub_read(s, seq.type); - seq.lower = tipc_sub_read(s, seq.lower); - seq.upper = tipc_sub_read(s, seq.upper); - - if (!tipc_sub_check_overlap(&seq, found_lower, found_upper)) + if (!tipc_sub_check_overlap(sr, &p->sr)) return; - if (!must && !(filter & TIPC_SUB_PORTS)) return; - if (filter & TIPC_SUB_CLUSTER_SCOPE && scope == TIPC_NODE_SCOPE) + if (filter & TIPC_SUB_CLUSTER_SCOPE && p->scope == TIPC_NODE_SCOPE) return; - if (filter & TIPC_SUB_NODE_SCOPE && scope != TIPC_NODE_SCOPE) + if (filter & TIPC_SUB_NODE_SCOPE && p->scope != TIPC_NODE_SCOPE) return; spin_lock(&sub->lock); - tipc_sub_send_event(sub, found_lower, found_upper, - event, port, node); + tipc_sub_send_event(sub, p, event); spin_unlock(&sub->lock); } static void tipc_sub_timeout(struct timer_list *t) { struct tipc_subscription *sub = from_timer(sub, t, timer); - struct tipc_subscr *s = &sub->evt.s; spin_lock(&sub->lock); - tipc_sub_send_event(sub, s->seq.lower, s->seq.upper, - TIPC_SUBSCR_TIMEOUT, 0, 0); + tipc_sub_send_event(sub, NULL, TIPC_SUBSCR_TIMEOUT); sub->inactive = true; spin_unlock(&sub->lock); } @@ -134,12 +132,14 @@ struct tipc_subscription *tipc_sub_subscribe(struct net *net, struct tipc_subscr *s, int conid) { + u32 lower = tipc_sub_read(s, seq.lower); + u32 upper = tipc_sub_read(s, seq.upper); u32 filter = tipc_sub_read(s, filter); struct tipc_subscription *sub; u32 timeout; if ((filter & TIPC_SUB_PORTS && filter & TIPC_SUB_SERVICE) || - (tipc_sub_read(s, seq.lower) > tipc_sub_read(s, seq.upper))) { + lower > upper) { pr_warn("Subscription rejected, illegal request\n"); return NULL; } @@ -154,6 +154,12 @@ struct tipc_subscription *tipc_sub_subscribe(struct net *net, sub->conid = conid; sub->inactive = false; memcpy(&sub->evt.s, s, sizeof(*s)); + sub->s.seq.type = tipc_sub_read(s, seq.type); + sub->s.seq.lower = lower; + sub->s.seq.upper = upper; + sub->s.filter = filter; + sub->s.timeout = tipc_sub_read(s, timeout); + memcpy(sub->s.usr_handle, s->usr_handle, 8); spin_lock_init(&sub->lock); kref_init(&sub->kref); if (!tipc_nametbl_subscribe(sub)) { diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h index 3ded27391d54..ddea6554ec46 100644 --- a/net/tipc/subscr.h +++ b/net/tipc/subscr.h @@ -3,7 +3,7 @@ * * Copyright (c) 2003-2017, Ericsson AB * Copyright (c) 2005-2007, 2012-2013, Wind River Systems - * Copyright (c) 2020, Red Hat Inc + * Copyright (c) 2020-2021, Red Hat Inc * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -43,6 +43,7 @@ #define TIPC_MAX_SUBSCR 65535 #define TIPC_MAX_PUBL 65535 +struct publication; struct tipc_subscription; struct tipc_conn; @@ -59,12 +60,13 @@ struct tipc_conn; * @lock: serialize up/down and timer events */ struct tipc_subscription { + struct tipc_subscr s; + struct tipc_event evt; struct kref kref; struct net *net; struct timer_list timer; struct list_head service_list; struct list_head sub_list; - struct tipc_event evt; int conid; bool inactive; spinlock_t lock; @@ -74,13 +76,9 @@ struct tipc_subscription *tipc_sub_subscribe(struct net *net, struct tipc_subscr *s, int conid); void tipc_sub_unsubscribe(struct tipc_subscription *sub); - -int tipc_sub_check_overlap(struct tipc_service_range *seq, - u32 found_lower, u32 found_upper); void tipc_sub_report_overlap(struct tipc_subscription *sub, - u32 found_lower, u32 found_upper, - u32 event, u32 port, u32 node, - u32 scope, int must); + struct publication *p, + u32 event, bool must); int __net_init tipc_topsrv_init_net(struct net *net); void __net_exit tipc_topsrv_exit_net(struct net *net); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index d9cd229aa111..790c6b7ecb26 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -601,7 +601,7 @@ struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, if (!info || before(seq, info->end_seq - info->len)) { /* if retransmit_hint is irrelevant start - * from the beggining of the list + * from the beginning of the list */ info = list_first_entry_or_null(&context->records_list, struct tls_record_info, list); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 4faabd1ecfd1..a71ed664da0a 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -445,6 +445,97 @@ static void xsk_destruct_skb(struct sk_buff *skb) sock_wfree(skb); } +static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs, + struct xdp_desc *desc) +{ + struct xsk_buff_pool *pool = xs->pool; + u32 hr, len, ts, offset, copy, copied; + struct sk_buff *skb; + struct page *page; + void *buffer; + int err, i; + u64 addr; + + hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(xs->dev->needed_headroom)); + + skb = sock_alloc_send_skb(&xs->sk, hr, 1, &err); + if (unlikely(!skb)) + return ERR_PTR(err); + + skb_reserve(skb, hr); + + addr = desc->addr; + len = desc->len; + ts = pool->unaligned ? len : pool->chunk_size; + + buffer = xsk_buff_raw_get_data(pool, addr); + offset = offset_in_page(buffer); + addr = buffer - pool->addrs; + + for (copied = 0, i = 0; copied < len; i++) { + page = pool->umem->pgs[addr >> PAGE_SHIFT]; + get_page(page); + + copy = min_t(u32, PAGE_SIZE - offset, len - copied); + skb_fill_page_desc(skb, i, page, offset, copy); + + copied += copy; + addr += copy; + offset = 0; + } + + skb->len += len; + skb->data_len += len; + skb->truesize += ts; + + refcount_add(ts, &xs->sk.sk_wmem_alloc); + + return skb; +} + +static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, + struct xdp_desc *desc) +{ + struct net_device *dev = xs->dev; + struct sk_buff *skb; + + if (dev->priv_flags & IFF_TX_SKB_NO_LINEAR) { + skb = xsk_build_skb_zerocopy(xs, desc); + if (IS_ERR(skb)) + return skb; + } else { + u32 hr, tr, len; + void *buffer; + int err; + + hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(dev->needed_headroom)); + tr = dev->needed_tailroom; + len = desc->len; + + skb = sock_alloc_send_skb(&xs->sk, hr + len + tr, 1, &err); + if (unlikely(!skb)) + return ERR_PTR(err); + + skb_reserve(skb, hr); + skb_put(skb, len); + + buffer = xsk_buff_raw_get_data(xs->pool, desc->addr); + err = skb_store_bits(skb, 0, buffer, len); + if (unlikely(err)) { + kfree_skb(skb); + return ERR_PTR(err); + } + } + + skb->dev = dev; + skb->priority = xs->sk.sk_priority; + skb->mark = xs->sk.sk_mark; + skb_shinfo(skb)->destructor_arg = (void *)(long)desc->addr; + skb->destructor = xsk_destruct_skb; + + return skb; +} + static int xsk_generic_xmit(struct sock *sk) { struct xdp_sock *xs = xdp_sk(sk); @@ -461,43 +552,30 @@ static int xsk_generic_xmit(struct sock *sk) goto out; while (xskq_cons_peek_desc(xs->tx, &desc, xs->pool)) { - char *buffer; - u64 addr; - u32 len; - if (max_batch-- == 0) { err = -EAGAIN; goto out; } - len = desc.len; - skb = sock_alloc_send_skb(sk, len, 1, &err); - if (unlikely(!skb)) + skb = xsk_build_skb(xs, &desc); + if (IS_ERR(skb)) { + err = PTR_ERR(skb); goto out; + } - skb_put(skb, len); - addr = desc.addr; - buffer = xsk_buff_raw_get_data(xs->pool, addr); - err = skb_store_bits(skb, 0, buffer, len); /* This is the backpressure mechanism for the Tx path. * Reserve space in the completion queue and only proceed * if there is space in it. This avoids having to implement * any buffering in the Tx path. */ spin_lock_irqsave(&xs->pool->cq_lock, flags); - if (unlikely(err) || xskq_prod_reserve(xs->pool->cq)) { + if (xskq_prod_reserve(xs->pool->cq)) { spin_unlock_irqrestore(&xs->pool->cq_lock, flags); kfree_skb(skb); goto out; } spin_unlock_irqrestore(&xs->pool->cq_lock, flags); - skb->dev = xs->dev; - skb->priority = sk->sk_priority; - skb->mark = sk->sk_mark; - skb_shinfo(skb)->destructor_arg = (void *)(long)desc.addr; - skb->destructor = xsk_destruct_skb; - err = __dev_direct_xmit(skb, xs->queue_id); if (err == NETDEV_TX_BUSY) { /* Tell user-space to retry the send */ diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 2823b7c3302d..2ac3802c2cd7 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -47,19 +47,18 @@ struct xsk_queue { u64 queue_empty_descs; }; -/* The structure of the shared state of the rings are the same as the - * ring buffer in kernel/events/ring_buffer.c. For the Rx and completion - * ring, the kernel is the producer and user space is the consumer. For - * the Tx and fill rings, the kernel is the consumer and user space is - * the producer. +/* The structure of the shared state of the rings are a simple + * circular buffer, as outlined in + * Documentation/core-api/circular-buffers.rst. For the Rx and + * completion ring, the kernel is the producer and user space is the + * consumer. For the Tx and fill rings, the kernel is the consumer and + * user space is the producer. * * producer consumer * - * if (LOAD ->consumer) { LOAD ->producer - * (A) smp_rmb() (C) + * if (LOAD ->consumer) { (A) LOAD.acq ->producer (C) * STORE $data LOAD $data - * smp_wmb() (B) smp_mb() (D) - * STORE ->producer STORE ->consumer + * STORE.rel ->producer (B) STORE.rel ->consumer (D) * } * * (A) pairs with (D), and (B) pairs with (C). @@ -78,7 +77,8 @@ struct xsk_queue { * * (A) is a control dependency that separates the load of ->consumer * from the stores of $data. In case ->consumer indicates there is no - * room in the buffer to store $data we do not. So no barrier is needed. + * room in the buffer to store $data we do not. The dependency will + * order both of the stores after the loads. So no barrier is needed. * * (D) protects the load of the data to be observed to happen after the * store of the consumer pointer. If we did not have this memory @@ -227,15 +227,13 @@ static inline u32 xskq_cons_read_desc_batch(struct xsk_queue *q, static inline void __xskq_cons_release(struct xsk_queue *q) { - smp_mb(); /* D, matches A */ - WRITE_ONCE(q->ring->consumer, q->cached_cons); + smp_store_release(&q->ring->consumer, q->cached_cons); /* D, matchees A */ } static inline void __xskq_cons_peek(struct xsk_queue *q) { /* Refresh the local pointer */ - q->cached_prod = READ_ONCE(q->ring->producer); - smp_rmb(); /* C, matches B */ + q->cached_prod = smp_load_acquire(&q->ring->producer); /* C, matches B */ } static inline void xskq_cons_get_entries(struct xsk_queue *q) @@ -397,9 +395,7 @@ static inline int xskq_prod_reserve_desc(struct xsk_queue *q, static inline void __xskq_prod_submit(struct xsk_queue *q, u32 idx) { - smp_wmb(); /* B, matches C */ - - WRITE_ONCE(q->ring->producer, idx); + smp_store_release(&q->ring->producer, idx); /* B, matches C */ } static inline void xskq_prod_submit(struct xsk_queue *q) diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c index 113fd9017203..67b4ce504852 100644 --- a/net/xdp/xskmap.c +++ b/net/xdp/xskmap.c @@ -87,7 +87,6 @@ static void xsk_map_free(struct bpf_map *map) { struct xsk_map *m = container_of(map, struct xsk_map, map); - bpf_clear_redirect_map(map); synchronize_net(); bpf_map_area_free(m); } @@ -125,6 +124,16 @@ static int xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) return insn - insn_buf; } +static void *__xsk_map_lookup_elem(struct bpf_map *map, u32 key) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + + if (key >= map->max_entries) + return NULL; + + return READ_ONCE(m->xsk_map[key]); +} + static void *xsk_map_lookup_elem(struct bpf_map *map, void *key) { WARN_ON_ONCE(!rcu_read_lock_held()); @@ -215,6 +224,11 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key) return 0; } +static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) +{ + return __bpf_xdp_redirect_map(map, ifindex, flags, __xsk_map_lookup_elem); +} + void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, struct xdp_sock **map_entry) { @@ -247,4 +261,5 @@ const struct bpf_map_ops xsk_map_ops = { .map_check_btf = map_check_no_btf, .map_btf_name = "xsk_map", .map_btf_id = &xsk_map_btf_id, + .map_redirect = xsk_map_redirect, }; |