diff options
Diffstat (limited to 'net')
473 files changed, 17943 insertions, 8389 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 4a72ee4e2ae9..8dfdd94e430f 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -138,7 +138,7 @@ int vlan_check_real_dev(struct net_device *real_dev, return 0; } -int register_vlan_dev(struct net_device *dev) +int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; @@ -174,7 +174,7 @@ int register_vlan_dev(struct net_device *dev) if (err < 0) goto out_uninit_mvrp; - err = netdev_upper_dev_link(real_dev, dev); + err = netdev_upper_dev_link(real_dev, dev, extack); if (err) goto out_unregister_netdev; @@ -270,7 +270,7 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id) vlan->flags = VLAN_FLAG_REORDER_HDR; new_dev->rtnl_link_ops = &vlan_link_ops; - err = register_vlan_dev(new_dev); + err = register_vlan_dev(new_dev, NULL); if (err < 0) goto out_free_newdev; @@ -328,6 +328,9 @@ static void vlan_transfer_features(struct net_device *dev, vlandev->fcoe_ddp_xid = dev->fcoe_ddp_xid; #endif + vlandev->priv_flags &= ~IFF_XMIT_DST_RELEASE; + vlandev->priv_flags |= (vlan->real_dev->priv_flags & IFF_XMIT_DST_RELEASE); + netdev_update_features(vlandev); } diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index 0e7afdf86127..a8ba51030b75 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -108,7 +108,7 @@ void vlan_dev_get_realdev_name(const struct net_device *dev, char *result); int vlan_check_real_dev(struct net_device *real_dev, __be16 protocol, u16 vlan_id); void vlan_setup(struct net_device *dev); -int register_vlan_dev(struct net_device *dev); +int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack); void unregister_vlan_dev(struct net_device *dev, struct list_head *head); bool vlan_dev_inherit_address(struct net_device *dev, struct net_device *real_dev); diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 5e831de3103e..6689c0b272a7 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -143,6 +143,7 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, vlan->vlan_proto = proto; vlan->vlan_id = nla_get_u16(data[IFLA_VLAN_ID]); vlan->real_dev = real_dev; + dev->priv_flags |= (real_dev->priv_flags & IFF_XMIT_DST_RELEASE); vlan->flags = VLAN_FLAG_REORDER_HDR; err = vlan_check_real_dev(real_dev, vlan->vlan_proto, vlan->vlan_id); @@ -160,7 +161,7 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, if (err < 0) return err; - return register_vlan_dev(dev); + return register_vlan_dev(dev, extack); } static inline size_t vlan_qos_map_size(unsigned int n) diff --git a/net/atm/clip.c b/net/atm/clip.c index 65f706e4344c..d4f6029d5109 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -153,7 +153,7 @@ static int neigh_check_cb(struct neighbour *n) return 1; } -static void idle_timer_check(unsigned long dummy) +static void idle_timer_check(struct timer_list *unused) { write_lock(&arp_tbl.lock); __neigh_for_each_release(&arp_tbl, neigh_check_cb); @@ -887,7 +887,7 @@ static int __init atm_clip_init(void) register_netdevice_notifier(&clip_dev_notifier); register_inetaddr_notifier(&clip_inet_notifier); - setup_timer(&idle_timer, idle_timer_check, 0); + timer_setup(&idle_timer, idle_timer_check, 0); #ifdef CONFIG_PROC_FS { diff --git a/net/atm/lec.c b/net/atm/lec.c index a3d93a1bb133..c976196da3ea 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -1232,7 +1232,7 @@ static void lane2_associate_ind(struct net_device *dev, const u8 *mac_addr, #define LEC_ARP_REFRESH_INTERVAL (3*HZ) static void lec_arp_check_expire(struct work_struct *work); -static void lec_arp_expire_arp(unsigned long data); +static void lec_arp_expire_arp(struct timer_list *t); /* * Arp table funcs @@ -1559,8 +1559,7 @@ static struct lec_arp_table *make_entry(struct lec_priv *priv, } ether_addr_copy(to_return->mac_addr, mac_addr); INIT_HLIST_NODE(&to_return->next); - setup_timer(&to_return->timer, lec_arp_expire_arp, - (unsigned long)to_return); + timer_setup(&to_return->timer, lec_arp_expire_arp, 0); to_return->last_used = jiffies; to_return->priv = priv; skb_queue_head_init(&to_return->tx_wait); @@ -1569,11 +1568,11 @@ static struct lec_arp_table *make_entry(struct lec_priv *priv, } /* Arp sent timer expired */ -static void lec_arp_expire_arp(unsigned long data) +static void lec_arp_expire_arp(struct timer_list *t) { struct lec_arp_table *entry; - entry = (struct lec_arp_table *)data; + entry = from_timer(entry, t, timer); pr_debug("\n"); if (entry->status == ESI_ARP_PENDING) { @@ -1591,10 +1590,10 @@ static void lec_arp_expire_arp(unsigned long data) } /* Unknown/unused vcc expire, remove associated entry */ -static void lec_arp_expire_vcc(unsigned long data) +static void lec_arp_expire_vcc(struct timer_list *t) { unsigned long flags; - struct lec_arp_table *to_remove = (struct lec_arp_table *)data; + struct lec_arp_table *to_remove = from_timer(to_remove, t, timer); struct lec_priv *priv = to_remove->priv; del_timer(&to_remove->timer); @@ -1799,7 +1798,7 @@ static struct atm_vcc *lec_arp_resolve(struct lec_priv *priv, else send_to_lecd(priv, l_arp_xmt, mac_to_find, NULL, NULL); entry->timer.expires = jiffies + (1 * HZ); - entry->timer.function = lec_arp_expire_arp; + entry->timer.function = (TIMER_FUNC_TYPE)lec_arp_expire_arp; add_timer(&entry->timer); found = priv->mcast_vcc; } @@ -1999,7 +1998,7 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data, entry->old_recv_push = old_push; entry->status = ESI_UNKNOWN; entry->timer.expires = jiffies + priv->vcc_timeout_period; - entry->timer.function = lec_arp_expire_vcc; + entry->timer.function = (TIMER_FUNC_TYPE)lec_arp_expire_vcc; hlist_add_head(&entry->next, &priv->lec_no_forward); add_timer(&entry->timer); dump_arp_table(priv); @@ -2083,7 +2082,7 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data, entry->status = ESI_UNKNOWN; hlist_add_head(&entry->next, &priv->lec_arp_empty_ones); entry->timer.expires = jiffies + priv->vcc_timeout_period; - entry->timer.function = lec_arp_expire_vcc; + entry->timer.function = (TIMER_FUNC_TYPE)lec_arp_expire_vcc; add_timer(&entry->timer); pr_debug("After vcc was added\n"); dump_arp_table(priv); diff --git a/net/atm/mpc.c b/net/atm/mpc.c index 5677147209e8..e882d8b5db05 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -95,7 +95,7 @@ static netdev_tx_t mpc_send_packet(struct sk_buff *skb, static int mpoa_event_listener(struct notifier_block *mpoa_notifier, unsigned long event, void *dev); static void mpc_timer_refresh(void); -static void mpc_cache_check(unsigned long checking_time); +static void mpc_cache_check(struct timer_list *unused); static struct llc_snap_hdr llc_snap_mpoa_ctrl = { 0xaa, 0xaa, 0x03, @@ -121,7 +121,7 @@ static struct notifier_block mpoa_notifier = { struct mpoa_client *mpcs = NULL; /* FIXME */ static struct atm_mpoa_qos *qos_head = NULL; -static DEFINE_TIMER(mpc_timer, NULL, 0, 0); +static DEFINE_TIMER(mpc_timer, NULL); static struct mpoa_client *find_mpc_by_itfnum(int itf) @@ -799,7 +799,6 @@ static int atm_mpoa_mpoad_attach(struct atm_vcc *vcc, int arg) int err; if (mpcs == NULL) { - init_timer(&mpc_timer); mpc_timer_refresh(); /* This lets us now how our LECs are doing */ @@ -1408,15 +1407,17 @@ static void clean_up(struct k_message *msg, struct mpoa_client *mpc, int action) msg_to_mpoad(msg, mpc); } +static unsigned long checking_time; + static void mpc_timer_refresh(void) { mpc_timer.expires = jiffies + (MPC_P2 * HZ); - mpc_timer.data = mpc_timer.expires; - mpc_timer.function = mpc_cache_check; + checking_time = mpc_timer.expires; + mpc_timer.function = (TIMER_FUNC_TYPE)mpc_cache_check; add_timer(&mpc_timer); } -static void mpc_cache_check(unsigned long checking_time) +static void mpc_cache_check(struct timer_list *unused) { struct mpoa_client *mpc = mpcs; static unsigned long previous_resolving_check_time; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index f3f9d18891de..06eac1f50c5e 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -268,9 +268,9 @@ void ax25_destroy_socket(ax25_cb *); /* * Handler for deferred kills. */ -static void ax25_destroy_timer(unsigned long data) +static void ax25_destroy_timer(struct timer_list *t) { - ax25_cb *ax25=(ax25_cb *)data; + ax25_cb *ax25 = from_timer(ax25, t, dtimer); struct sock *sk; sk=ax25->sk; @@ -326,8 +326,7 @@ void ax25_destroy_socket(ax25_cb *ax25) if (ax25->sk != NULL) { if (sk_has_allocations(ax25->sk)) { /* Defer: outstanding buffers */ - setup_timer(&ax25->dtimer, ax25_destroy_timer, - (unsigned long)ax25); + timer_setup(&ax25->dtimer, ax25_destroy_timer, 0); ax25->dtimer.expires = jiffies + 2 * HZ; add_timer(&ax25->dtimer); } else { diff --git a/net/ax25/ax25_ds_timer.c b/net/ax25/ax25_ds_timer.c index 5fb2104b7304..e9d11313d45b 100644 --- a/net/ax25/ax25_ds_timer.c +++ b/net/ax25/ax25_ds_timer.c @@ -29,7 +29,7 @@ #include <linux/mm.h> #include <linux/interrupt.h> -static void ax25_ds_timeout(unsigned long); +static void ax25_ds_timeout(struct timer_list *); /* * Add DAMA slave timeout timer to timer list. @@ -41,8 +41,7 @@ static void ax25_ds_timeout(unsigned long); void ax25_ds_setup_timer(ax25_dev *ax25_dev) { - setup_timer(&ax25_dev->dama.slave_timer, ax25_ds_timeout, - (unsigned long)ax25_dev); + timer_setup(&ax25_dev->dama.slave_timer, ax25_ds_timeout, 0); } void ax25_ds_del_timer(ax25_dev *ax25_dev) @@ -66,9 +65,9 @@ void ax25_ds_set_timer(ax25_dev *ax25_dev) * Silently discard all (slave) connections in case our master forgot us... */ -static void ax25_ds_timeout(unsigned long arg) +static void ax25_ds_timeout(struct timer_list *t) { - ax25_dev *ax25_dev = (struct ax25_dev *) arg; + ax25_dev *ax25_dev = from_timer(ax25_dev, t, dama.slave_timer); ax25_cb *ax25; if (ax25_dev == NULL || !ax25_dev->dama.slave) diff --git a/net/ax25/ax25_timer.c b/net/ax25/ax25_timer.c index 23a6f38a80bf..c47b7ee1e4da 100644 --- a/net/ax25/ax25_timer.c +++ b/net/ax25/ax25_timer.c @@ -33,20 +33,19 @@ #include <linux/mm.h> #include <linux/interrupt.h> -static void ax25_heartbeat_expiry(unsigned long); -static void ax25_t1timer_expiry(unsigned long); -static void ax25_t2timer_expiry(unsigned long); -static void ax25_t3timer_expiry(unsigned long); -static void ax25_idletimer_expiry(unsigned long); +static void ax25_heartbeat_expiry(struct timer_list *); +static void ax25_t1timer_expiry(struct timer_list *); +static void ax25_t2timer_expiry(struct timer_list *); +static void ax25_t3timer_expiry(struct timer_list *); +static void ax25_idletimer_expiry(struct timer_list *); void ax25_setup_timers(ax25_cb *ax25) { - setup_timer(&ax25->timer, ax25_heartbeat_expiry, (unsigned long)ax25); - setup_timer(&ax25->t1timer, ax25_t1timer_expiry, (unsigned long)ax25); - setup_timer(&ax25->t2timer, ax25_t2timer_expiry, (unsigned long)ax25); - setup_timer(&ax25->t3timer, ax25_t3timer_expiry, (unsigned long)ax25); - setup_timer(&ax25->idletimer, ax25_idletimer_expiry, - (unsigned long)ax25); + timer_setup(&ax25->timer, ax25_heartbeat_expiry, 0); + timer_setup(&ax25->t1timer, ax25_t1timer_expiry, 0); + timer_setup(&ax25->t2timer, ax25_t2timer_expiry, 0); + timer_setup(&ax25->t3timer, ax25_t3timer_expiry, 0); + timer_setup(&ax25->idletimer, ax25_idletimer_expiry, 0); } void ax25_start_heartbeat(ax25_cb *ax25) @@ -120,10 +119,10 @@ unsigned long ax25_display_timer(struct timer_list *timer) EXPORT_SYMBOL(ax25_display_timer); -static void ax25_heartbeat_expiry(unsigned long param) +static void ax25_heartbeat_expiry(struct timer_list *t) { int proto = AX25_PROTO_STD_SIMPLEX; - ax25_cb *ax25 = (ax25_cb *)param; + ax25_cb *ax25 = from_timer(ax25, t, timer); if (ax25->ax25_dev) proto = ax25->ax25_dev->values[AX25_VALUES_PROTOCOL]; @@ -145,9 +144,9 @@ static void ax25_heartbeat_expiry(unsigned long param) } } -static void ax25_t1timer_expiry(unsigned long param) +static void ax25_t1timer_expiry(struct timer_list *t) { - ax25_cb *ax25 = (ax25_cb *)param; + ax25_cb *ax25 = from_timer(ax25, t, t1timer); switch (ax25->ax25_dev->values[AX25_VALUES_PROTOCOL]) { case AX25_PROTO_STD_SIMPLEX: @@ -164,9 +163,9 @@ static void ax25_t1timer_expiry(unsigned long param) } } -static void ax25_t2timer_expiry(unsigned long param) +static void ax25_t2timer_expiry(struct timer_list *t) { - ax25_cb *ax25 = (ax25_cb *)param; + ax25_cb *ax25 = from_timer(ax25, t, t2timer); switch (ax25->ax25_dev->values[AX25_VALUES_PROTOCOL]) { case AX25_PROTO_STD_SIMPLEX: @@ -183,9 +182,9 @@ static void ax25_t2timer_expiry(unsigned long param) } } -static void ax25_t3timer_expiry(unsigned long param) +static void ax25_t3timer_expiry(struct timer_list *t) { - ax25_cb *ax25 = (ax25_cb *)param; + ax25_cb *ax25 = from_timer(ax25, t, t3timer); switch (ax25->ax25_dev->values[AX25_VALUES_PROTOCOL]) { case AX25_PROTO_STD_SIMPLEX: @@ -204,9 +203,9 @@ static void ax25_t3timer_expiry(unsigned long param) } } -static void ax25_idletimer_expiry(unsigned long param) +static void ax25_idletimer_expiry(struct timer_list *t) { - ax25_cb *ax25 = (ax25_cb *)param; + ax25_cb *ax25 = from_timer(ax25, t, idletimer); switch (ax25->ax25_dev->values[AX25_VALUES_PROTOCOL]) { case AX25_PROTO_STD_SIMPLEX: diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 83ba5483455a..1b659ab652fb 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -916,8 +916,8 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) u16 tvlv_len = 0; unsigned long send_time; - if ((hard_iface->if_status == BATADV_IF_NOT_IN_USE) || - (hard_iface->if_status == BATADV_IF_TO_BE_REMOVED)) + if (hard_iface->if_status == BATADV_IF_NOT_IN_USE || + hard_iface->if_status == BATADV_IF_TO_BE_REMOVED) return; /* the interface gets activated here to avoid race conditions between @@ -1264,7 +1264,7 @@ static bool batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, * drops as they can't send and receive at the same time. */ tq_iface_penalty = BATADV_TQ_MAX_VALUE; - if (if_outgoing && (if_incoming == if_outgoing) && + if (if_outgoing && if_incoming == if_outgoing && batadv_is_wifi_hardif(if_outgoing)) tq_iface_penalty = batadv_hop_penalty(BATADV_TQ_MAX_VALUE, bat_priv); @@ -1369,7 +1369,7 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, ret = BATADV_NEIGH_DUP; } else { set_mark = 0; - if (is_dup && (ret != BATADV_NEIGH_DUP)) + if (is_dup && ret != BATADV_NEIGH_DUP) ret = BATADV_ORIG_DUP; } @@ -1515,7 +1515,7 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset, /* drop packet if sender is not a direct neighbor and if we * don't route towards it */ - if (!is_single_hop_neigh && (!orig_neigh_router)) { + if (!is_single_hop_neigh && !orig_neigh_router) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Drop packet: OGM via unknown neighbor!\n"); goto out_neigh; @@ -1535,7 +1535,7 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset, sameseq = orig_ifinfo->last_real_seqno == ntohl(ogm_packet->seqno); similar_ttl = (orig_ifinfo->last_ttl - 3) <= ogm_packet->ttl; - if (is_bidirect && ((dup_status == BATADV_NO_DUP) || + if (is_bidirect && (dup_status == BATADV_NO_DUP || (sameseq && similar_ttl))) { batadv_iv_ogm_orig_update(bat_priv, orig_node, orig_ifinfo, ethhdr, @@ -1553,8 +1553,8 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset, /* OGMs from secondary interfaces should only scheduled once * per interface where it has been received, not multiple times */ - if ((ogm_packet->ttl <= 2) && - (if_incoming != if_outgoing)) { + if (ogm_packet->ttl <= 2 && + if_incoming != if_outgoing) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Drop packet: OGM from secondary interface and wrong outgoing interface\n"); goto out_neigh; @@ -1590,7 +1590,7 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset, if_incoming, if_outgoing); out_neigh: - if ((orig_neigh_node) && (!is_single_hop_neigh)) + if (orig_neigh_node && !is_single_hop_neigh) batadv_orig_node_put(orig_neigh_node); out: if (router_ifinfo) @@ -2523,9 +2523,9 @@ batadv_iv_gw_get_best_gw_node(struct batadv_priv *bat_priv) tmp_gw_factor *= 100 * 100; tmp_gw_factor >>= 18; - if ((tmp_gw_factor > max_gw_factor) || - ((tmp_gw_factor == max_gw_factor) && - (tq_avg > max_tq))) { + if (tmp_gw_factor > max_gw_factor || + (tmp_gw_factor == max_gw_factor && + tq_avg > max_tq)) { if (curr_gw) batadv_gw_node_put(curr_gw); curr_gw = gw_node; diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index 4e2724c5b33d..341ceab8338d 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -19,7 +19,6 @@ #include "main.h" #include <linux/atomic.h> -#include <linux/bug.h> #include <linux/cache.h> #include <linux/errno.h> #include <linux/if_ether.h> @@ -623,11 +622,11 @@ static int batadv_v_neigh_cmp(struct batadv_neigh_node *neigh1, int ret = 0; ifinfo1 = batadv_neigh_ifinfo_get(neigh1, if_outgoing1); - if (WARN_ON(!ifinfo1)) + if (!ifinfo1) goto err_ifinfo1; ifinfo2 = batadv_neigh_ifinfo_get(neigh2, if_outgoing2); - if (WARN_ON(!ifinfo2)) + if (!ifinfo2) goto err_ifinfo2; ret = ifinfo1->bat_v.throughput - ifinfo2->bat_v.throughput; @@ -649,11 +648,11 @@ static bool batadv_v_neigh_is_sob(struct batadv_neigh_node *neigh1, bool ret = false; ifinfo1 = batadv_neigh_ifinfo_get(neigh1, if_outgoing1); - if (WARN_ON(!ifinfo1)) + if (!ifinfo1) goto err_ifinfo1; ifinfo2 = batadv_neigh_ifinfo_get(neigh2, if_outgoing2); - if (WARN_ON(!ifinfo2)) + if (!ifinfo2) goto err_ifinfo2; threshold = ifinfo1->bat_v.throughput / 4; @@ -767,7 +766,7 @@ batadv_v_gw_get_best_gw_node(struct batadv_priv *bat_priv) if (batadv_v_gw_throughput_get(gw_node, &bw) < 0) goto next; - if (curr_gw && (bw <= max_bw)) + if (curr_gw && bw <= max_bw) goto next; if (curr_gw) diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index bd1064d98e16..1de992c58b35 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -134,7 +134,7 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) hard_iface->bat_v.flags &= ~BATADV_FULL_DUPLEX; throughput = link_settings.base.speed; - if (throughput && (throughput != SPEED_UNKNOWN)) + if (throughput && throughput != SPEED_UNKNOWN) return throughput * 10; } @@ -263,8 +263,8 @@ static void batadv_v_elp_periodic_work(struct work_struct *work) goto out; /* we are in the process of shutting this interface down */ - if ((hard_iface->if_status == BATADV_IF_NOT_IN_USE) || - (hard_iface->if_status == BATADV_IF_TO_BE_REMOVED)) + if (hard_iface->if_status == BATADV_IF_NOT_IN_USE || + hard_iface->if_status == BATADV_IF_TO_BE_REMOVED) goto out; /* the interface was enabled but may not be ready yet */ diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 8be61734fc43..c251445a42a0 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -304,8 +304,8 @@ static u32 batadv_v_forward_penalty(struct batadv_priv *bat_priv, * due to the store & forward characteristics of WIFI. * Very low throughput values are the exception. */ - if ((throughput > 10) && - (if_incoming == if_outgoing) && + if (throughput > 10 && + if_incoming == if_outgoing && !(if_incoming->bat_v.flags & BATADV_FULL_DUPLEX)) return throughput / 2; @@ -455,7 +455,7 @@ static int batadv_v_ogm_metric_update(struct batadv_priv *bat_priv, /* drop packets with old seqnos, however accept the first packet after * a host has been rebooted. */ - if ((seq_diff < 0) && !protection_started) + if (seq_diff < 0 && !protection_started) goto out; neigh_node->last_seen = jiffies; @@ -568,8 +568,8 @@ static bool batadv_v_ogm_route_update(struct batadv_priv *bat_priv, router_throughput = router_ifinfo->bat_v.throughput; neigh_throughput = neigh_ifinfo->bat_v.throughput; - if ((neigh_seq_diff < BATADV_OGM_MAX_ORIGDIFF) && - (router_throughput >= neigh_throughput)) + if (neigh_seq_diff < BATADV_OGM_MAX_ORIGDIFF && + router_throughput >= neigh_throughput) goto out; } @@ -621,7 +621,7 @@ batadv_v_ogm_process_per_outif(struct batadv_priv *bat_priv, return; /* only unknown & newer OGMs contain TVLVs we are interested in */ - if ((seqno_age > 0) && (if_outgoing == BATADV_IF_DEFAULT)) + if (seqno_age > 0 && if_outgoing == BATADV_IF_DEFAULT) batadv_tvlv_containers_process(bat_priv, true, orig_node, NULL, NULL, (unsigned char *)(ogm2 + 1), diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index b6cfa78e9381..760c0de72582 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -492,8 +492,8 @@ static bool batadv_is_orig_node_eligible(struct batadv_dat_candidate *res, /* this is an hash collision with the temporary selected node. Choose * the one with the lowest address */ - if ((tmp_max == max) && max_orig_node && - (batadv_compare_eth(candidate->orig, max_orig_node->orig) > 0)) + if (tmp_max == max && max_orig_node && + batadv_compare_eth(candidate->orig, max_orig_node->orig) > 0) goto out; ret = true; diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index de9955d5224d..10d521f0b17f 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -248,12 +248,12 @@ void batadv_gw_election(struct batadv_priv *bat_priv) } } - if ((curr_gw) && (!next_gw)) { + if (curr_gw && !next_gw) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Removing selected gateway - no gateway in range\n"); batadv_throw_uevent(bat_priv, BATADV_UEV_GW, BATADV_UEV_DEL, NULL); - } else if ((!curr_gw) && (next_gw)) { + } else if (!curr_gw && next_gw) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Adding route to gateway %pM (bandwidth: %u.%u/%u.%u MBit, tq: %i)\n", next_gw->orig_node->orig, @@ -411,8 +411,8 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv, goto out; } - if ((gw_node->bandwidth_down == ntohl(gateway->bandwidth_down)) && - (gw_node->bandwidth_up == ntohl(gateway->bandwidth_up))) + if (gw_node->bandwidth_down == ntohl(gateway->bandwidth_down) && + gw_node->bandwidth_up == ntohl(gateway->bandwidth_up)) goto out; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index 33940c5c74a8..2c26039c23fc 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -56,8 +56,8 @@ bool batadv_parse_throughput(struct net_device *net_dev, char *buff, if (strncasecmp(tmp_ptr, "mbit", 4) == 0) bw_unit_type = BATADV_BW_UNIT_MBIT; - if ((strncasecmp(tmp_ptr, "kbit", 4) == 0) || - (bw_unit_type == BATADV_BW_UNIT_MBIT)) + if (strncasecmp(tmp_ptr, "kbit", 4) == 0 || + bw_unit_type == BATADV_BW_UNIT_MBIT) *tmp_ptr = '\0'; } @@ -190,7 +190,7 @@ ssize_t batadv_gw_bandwidth_set(struct net_device *net_dev, char *buff, if (!up_new) up_new = 1; - if ((down_curr == down_new) && (up_curr == up_new)) + if (down_curr == down_new && up_curr == up_new) return count; batadv_gw_reselect(bat_priv); @@ -224,16 +224,16 @@ static void batadv_gw_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv, /* only fetch the tvlv value if the handler wasn't called via the * CIFNOTFND flag and if there is data to fetch */ - if ((flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND) || - (tvlv_value_len < sizeof(gateway))) { + if (flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND || + tvlv_value_len < sizeof(gateway)) { gateway.bandwidth_down = 0; gateway.bandwidth_up = 0; } else { gateway_ptr = tvlv_value; gateway.bandwidth_down = gateway_ptr->bandwidth_down; gateway.bandwidth_up = gateway_ptr->bandwidth_up; - if ((gateway.bandwidth_down == 0) || - (gateway.bandwidth_up == 0)) { + if (gateway.bandwidth_down == 0 || + gateway.bandwidth_up == 0) { gateway.bandwidth_down = 0; gateway.bandwidth_up = 0; } @@ -242,8 +242,8 @@ static void batadv_gw_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv, batadv_gw_node_update(bat_priv, orig, &gateway); /* restart gateway selection */ - if ((gateway.bandwidth_down != 0) && - (atomic_read(&bat_priv->gw.mode) == BATADV_GW_MODE_CLIENT)) + if (gateway.bandwidth_down != 0 && + atomic_read(&bat_priv->gw.mode) == BATADV_GW_MODE_CLIENT) batadv_gw_check_election(bat_priv, orig); } diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index e348f76ea8c1..4e3d5340ad96 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -504,8 +504,8 @@ static void batadv_check_known_mac_addr(const struct net_device *net_dev) rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { - if ((hard_iface->if_status != BATADV_IF_ACTIVE) && - (hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED)) + if (hard_iface->if_status != BATADV_IF_ACTIVE && + hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED) continue; if (hard_iface->net_dev == net_dev) @@ -568,8 +568,8 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface) rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { - if ((hard_iface->if_status != BATADV_IF_ACTIVE) && - (hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED)) + if (hard_iface->if_status != BATADV_IF_ACTIVE && + hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED) continue; if (hard_iface->soft_iface != soft_iface) @@ -654,8 +654,8 @@ out: static void batadv_hardif_deactivate_interface(struct batadv_hard_iface *hard_iface) { - if ((hard_iface->if_status != BATADV_IF_ACTIVE) && - (hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED)) + if (hard_iface->if_status != BATADV_IF_ACTIVE && + hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED) return; hard_iface->if_status = BATADV_IF_INACTIVE; @@ -738,7 +738,7 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, bat_priv = netdev_priv(hard_iface->soft_iface); ret = netdev_master_upper_dev_link(hard_iface->net_dev, - soft_iface, NULL, NULL); + soft_iface, NULL, NULL, NULL); if (ret) goto err_dev; diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index 8ead292886d1..bded31121d12 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -132,10 +132,10 @@ static ssize_t batadv_socket_read(struct file *file, char __user *buf, size_t packet_len; int error; - if ((file->f_flags & O_NONBLOCK) && (socket_client->queue_len == 0)) + if ((file->f_flags & O_NONBLOCK) && socket_client->queue_len == 0) return -EAGAIN; - if ((!buf) || (count < sizeof(struct batadv_icmp_packet))) + if (!buf || count < sizeof(struct batadv_icmp_packet)) return -EINVAL; if (!access_ok(VERIFY_WRITE, buf, count)) diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index fb381fb26a66..4daed7ad46f2 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -73,8 +73,8 @@ * list traversals just rcu-locked */ struct list_head batadv_hardif_list; -static int (*batadv_rx_handler[256])(struct sk_buff *, - struct batadv_hard_iface *); +static int (*batadv_rx_handler[256])(struct sk_buff *skb, + struct batadv_hard_iface *recv_if); unsigned char batadv_broadcast_addr[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; @@ -540,12 +540,12 @@ batadv_recv_handler_register(u8 packet_type, int (*recv_handler)(struct sk_buff *, struct batadv_hard_iface *)) { - int (*curr)(struct sk_buff *, - struct batadv_hard_iface *); + int (*curr)(struct sk_buff *skb, + struct batadv_hard_iface *recv_if); curr = batadv_rx_handler[packet_type]; - if ((curr != batadv_recv_unhandled_packet) && - (curr != batadv_recv_unhandled_unicast_packet)) + if (curr != batadv_recv_unhandled_packet && + curr != batadv_recv_unhandled_unicast_packet) return -EBUSY; batadv_rx_handler[packet_type] = recv_handler; diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 05cc7637c064..edb2f239d04d 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -24,7 +24,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2017.3" +#define BATADV_SOURCE_VERSION "2017.4" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index d327670641ac..e553a8770a89 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -1126,7 +1126,7 @@ static void batadv_mcast_tvlv_ogm_handler(struct batadv_priv *bat_priv, bool orig_initialized; if (orig_mcast_enabled && tvlv_value && - (tvlv_value_len >= sizeof(mcast_flags))) + tvlv_value_len >= sizeof(mcast_flags)) mcast_flags = *(u8 *)tvlv_value; spin_lock_bh(&orig->mcast_handler_lock); diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 8e2a4b205257..2967b86c13da 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1062,9 +1062,9 @@ batadv_purge_neigh_ifinfo(struct batadv_priv *bat_priv, continue; /* don't purge if the interface is not (going) down */ - if ((if_outgoing->if_status != BATADV_IF_INACTIVE) && - (if_outgoing->if_status != BATADV_IF_NOT_IN_USE) && - (if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED)) + if (if_outgoing->if_status != BATADV_IF_INACTIVE && + if_outgoing->if_status != BATADV_IF_NOT_IN_USE && + if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED) continue; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, @@ -1106,9 +1106,9 @@ batadv_purge_orig_ifinfo(struct batadv_priv *bat_priv, continue; /* don't purge if the interface is not (going) down */ - if ((if_outgoing->if_status != BATADV_IF_INACTIVE) && - (if_outgoing->if_status != BATADV_IF_NOT_IN_USE) && - (if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED)) + if (if_outgoing->if_status != BATADV_IF_INACTIVE && + if_outgoing->if_status != BATADV_IF_NOT_IN_USE && + if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED) continue; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, @@ -1155,13 +1155,13 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, last_seen = neigh_node->last_seen; if_incoming = neigh_node->if_incoming; - if ((batadv_has_timed_out(last_seen, BATADV_PURGE_TIMEOUT)) || - (if_incoming->if_status == BATADV_IF_INACTIVE) || - (if_incoming->if_status == BATADV_IF_NOT_IN_USE) || - (if_incoming->if_status == BATADV_IF_TO_BE_REMOVED)) { - if ((if_incoming->if_status == BATADV_IF_INACTIVE) || - (if_incoming->if_status == BATADV_IF_NOT_IN_USE) || - (if_incoming->if_status == BATADV_IF_TO_BE_REMOVED)) + if (batadv_has_timed_out(last_seen, BATADV_PURGE_TIMEOUT) || + if_incoming->if_status == BATADV_IF_INACTIVE || + if_incoming->if_status == BATADV_IF_NOT_IN_USE || + if_incoming->if_status == BATADV_IF_TO_BE_REMOVED) { + if (if_incoming->if_status == BATADV_IF_INACTIVE || + if_incoming->if_status == BATADV_IF_NOT_IN_USE || + if_incoming->if_status == BATADV_IF_TO_BE_REMOVED) batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "neighbor purge: originator %pM, neighbor: %pM, iface: %s\n", orig_node->orig, neigh_node->addr, diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index f10e3ff26f9d..40d9bf3e5bfe 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -93,14 +93,14 @@ static void _batadv_update_route(struct batadv_priv *bat_priv, batadv_orig_ifinfo_put(orig_ifinfo); /* route deleted */ - if ((curr_router) && (!neigh_node)) { + if (curr_router && !neigh_node) { batadv_dbg(BATADV_DBG_ROUTES, bat_priv, "Deleting route towards: %pM\n", orig_node->orig); batadv_tt_global_del_orig(bat_priv, orig_node, -1, "Deleted route towards originator"); /* route added */ - } else if ((!curr_router) && (neigh_node)) { + } else if (!curr_router && neigh_node) { batadv_dbg(BATADV_DBG_ROUTES, bat_priv, "Adding route towards: %pM (via %pM)\n", orig_node->orig, neigh_node->addr); @@ -381,7 +381,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb, /* add record route information if not full */ if ((icmph->msg_type == BATADV_ECHO_REPLY || icmph->msg_type == BATADV_ECHO_REQUEST) && - (skb->len >= sizeof(struct batadv_icmp_packet_rr))) { + skb->len >= sizeof(struct batadv_icmp_packet_rr)) { if (skb_linearize(skb) < 0) goto free_skb; diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 054a65e6eb68..7895323fd2a7 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -142,7 +142,7 @@ int batadv_send_unicast_skb(struct sk_buff *skb, #ifdef CONFIG_BATMAN_ADV_BATMAN_V hardif_neigh = batadv_hardif_neigh_get(neigh->if_incoming, neigh->addr); - if ((hardif_neigh) && (ret != NET_XMIT_DROP)) + if (hardif_neigh && ret != NET_XMIT_DROP) hardif_neigh->bat_v.last_unicast_tx = jiffies; if (hardif_neigh) @@ -615,8 +615,8 @@ batadv_forw_packet_list_steal(struct hlist_head *forw_list, * we delete only packets belonging to the given interface */ if (hard_iface && - (forw_packet->if_incoming != hard_iface) && - (forw_packet->if_outgoing != hard_iface)) + forw_packet->if_incoming != hard_iface && + forw_packet->if_outgoing != hard_iface) continue; hlist_del(&forw_packet->list); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 10f7edfb176e..9f673cdfecf8 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -69,8 +69,8 @@ int batadv_skb_head_push(struct sk_buff *skb, unsigned int len) int result; /* TODO: We must check if we can release all references to non-payload - * data using skb_header_release in our skbs to allow skb_cow_header to - * work optimally. This means that those skbs are not allowed to read + * data using __skb_header_release in our skbs to allow skb_cow_header + * to work optimally. This means that those skbs are not allowed to read * or write any data which is before the current position of skb->data * after that call and thus allow other skbs with the same data buffer * to write freely in that area. @@ -160,7 +160,7 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p) static int batadv_interface_change_mtu(struct net_device *dev, int new_mtu) { /* check ranges */ - if ((new_mtu < 68) || (new_mtu > batadv_hardif_min_mtu(dev))) + if (new_mtu < 68 || new_mtu > batadv_hardif_min_mtu(dev)) return -EINVAL; dev->mtu = new_mtu; @@ -863,11 +863,13 @@ free_bat_counters: * batadv_softif_slave_add - Add a slave interface to a batadv_soft_interface * @dev: batadv_soft_interface used as master interface * @slave_dev: net_device which should become the slave interface + * @extack: extended ACK report struct * * Return: 0 if successful or error otherwise. */ static int batadv_softif_slave_add(struct net_device *dev, - struct net_device *slave_dev) + struct net_device *slave_dev, + struct netlink_ext_ack *extack) { struct batadv_hard_iface *hard_iface; struct net *net = dev_net(dev); diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index 0ae8b30e4eaa..aa187fd42475 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -925,8 +925,8 @@ static int batadv_store_mesh_iface_finish(struct net_device *net_dev, if (hard_iface->if_status == status_tmp) goto out; - if ((hard_iface->soft_iface) && - (strncmp(hard_iface->soft_iface->name, ifname, IFNAMSIZ) == 0)) + if (hard_iface->soft_iface && + strncmp(hard_iface->soft_iface->name, ifname, IFNAMSIZ) == 0) goto out; if (status_tmp == BATADV_IF_NOT_IN_USE) { diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index bfe8effe9238..4b90033f35a8 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -1206,7 +1206,7 @@ static int batadv_tp_send_ack(struct batadv_priv *bat_priv, const u8 *dst, /* send the ack */ r = batadv_send_skb_to_orig(skb, orig_node, NULL); - if (unlikely(r < 0) || (r == NET_XMIT_DROP)) { + if (unlikely(r < 0) || r == NET_XMIT_DROP) { ret = BATADV_TP_REASON_DST_UNREACHABLE; goto out; } diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c index aad994edd3bb..51c2cf2d8923 100644 --- a/net/bluetooth/a2mp.c +++ b/net/bluetooth/a2mp.c @@ -573,7 +573,7 @@ static int a2mp_discphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, hcon = hci_conn_hash_lookup_ba(hdev, AMP_LINK, &mgr->l2cap_conn->hcon->dst); if (!hcon) { - BT_ERR("No phys link exist"); + bt_dev_err(hdev, "no phys link exist"); rsp.status = A2MP_STATUS_NO_PHYSICAL_LINK_EXISTS; goto clean; } diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c index ebcab5bbadd7..78bec8df8525 100644 --- a/net/bluetooth/amp.c +++ b/net/bluetooth/amp.c @@ -187,7 +187,7 @@ int phylink_gen_key(struct hci_conn *conn, u8 *data, u8 *len, u8 *type) /* Legacy key */ if (conn->key_type < 3) { - BT_ERR("Legacy key type %d", conn->key_type); + bt_dev_err(hdev, "legacy key type %d", conn->key_type); return -EACCES; } @@ -207,7 +207,7 @@ int phylink_gen_key(struct hci_conn *conn, u8 *data, u8 *len, u8 *type) /* Derive Generic AMP Link Key (gamp) */ err = hmac_sha256(keybuf, HCI_AMP_LINK_KEY_SIZE, "gamp", 4, gamp_key); if (err) { - BT_ERR("Could not derive Generic AMP Key: err %d", err); + bt_dev_err(hdev, "could not derive Generic AMP Key: err %d", err); return err; } diff --git a/net/bluetooth/ecdh_helper.c b/net/bluetooth/ecdh_helper.c index c7b1a9aee579..2155ce802877 100644 --- a/net/bluetooth/ecdh_helper.c +++ b/net/bluetooth/ecdh_helper.c @@ -23,7 +23,6 @@ #include "ecdh_helper.h" #include <linux/scatterlist.h> -#include <crypto/kpp.h> #include <crypto/ecdh.h> struct ecdh_completion { @@ -50,55 +49,35 @@ static inline void swap_digits(u64 *in, u64 *out, unsigned int ndigits) out[i] = __swab64(in[ndigits - 1 - i]); } -bool compute_ecdh_secret(const u8 public_key[64], const u8 private_key[32], - u8 secret[32]) +/* compute_ecdh_secret() - function assumes that the private key was + * already set. + * @tfm: KPP tfm handle allocated with crypto_alloc_kpp(). + * @public_key: pair's ecc public key. + * secret: memory where the ecdh computed shared secret will be saved. + * + * Return: zero on success; error code in case of error. + */ +int compute_ecdh_secret(struct crypto_kpp *tfm, const u8 public_key[64], + u8 secret[32]) { - struct crypto_kpp *tfm; struct kpp_request *req; - struct ecdh p; + u8 *tmp; struct ecdh_completion result; struct scatterlist src, dst; - u8 *tmp, *buf; - unsigned int buf_len; - int err = -ENOMEM; + int err; tmp = kmalloc(64, GFP_KERNEL); if (!tmp) - return false; + return -ENOMEM; - tfm = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0); - if (IS_ERR(tfm)) { - pr_err("alg: kpp: Failed to load tfm for kpp: %ld\n", - PTR_ERR(tfm)); + req = kpp_request_alloc(tfm, GFP_KERNEL); + if (!req) { + err = -ENOMEM; goto free_tmp; } - req = kpp_request_alloc(tfm, GFP_KERNEL); - if (!req) - goto free_kpp; - init_completion(&result.completion); - /* Security Manager Protocol holds digits in litte-endian order - * while ECC API expect big-endian data - */ - swap_digits((u64 *)private_key, (u64 *)tmp, 4); - p.key = (char *)tmp; - p.key_size = 32; - /* Set curve_id */ - p.curve_id = ECC_CURVE_NIST_P256; - buf_len = crypto_ecdh_key_len(&p); - buf = kmalloc(buf_len, GFP_KERNEL); - if (!buf) - goto free_req; - - crypto_ecdh_encode_key(buf, buf_len, &p); - - /* Set A private Key */ - err = crypto_kpp_set_secret(tfm, (void *)buf, buf_len); - if (err) - goto free_all; - swap_digits((u64 *)public_key, (u64 *)tmp, 4); /* x */ swap_digits((u64 *)&public_key[32], (u64 *)&tmp[32], 4); /* y */ @@ -123,104 +102,129 @@ bool compute_ecdh_secret(const u8 public_key[64], const u8 private_key[32], memcpy(secret, tmp, 32); free_all: - kzfree(buf); -free_req: kpp_request_free(req); -free_kpp: - crypto_free_kpp(tfm); free_tmp: - kfree(tmp); - return (err == 0); + kzfree(tmp); + return err; } -bool generate_ecdh_keys(u8 public_key[64], u8 private_key[32]) +/* set_ecdh_privkey() - set or generate ecc private key. + * + * Function generates an ecc private key in the crypto subsystem when receiving + * a NULL private key or sets the received key when not NULL. + * + * @tfm: KPP tfm handle allocated with crypto_alloc_kpp(). + * @private_key: user's ecc private key. When not NULL, the key is expected + * in little endian format. + * + * Return: zero on success; error code in case of error. + */ +int set_ecdh_privkey(struct crypto_kpp *tfm, const u8 private_key[32]) +{ + u8 *buf, *tmp = NULL; + unsigned int buf_len; + int err; + struct ecdh p = {0}; + + p.curve_id = ECC_CURVE_NIST_P256; + + if (private_key) { + tmp = kmalloc(32, GFP_KERNEL); + if (!tmp) + return -ENOMEM; + swap_digits((u64 *)private_key, (u64 *)tmp, 4); + p.key = tmp; + p.key_size = 32; + } + + buf_len = crypto_ecdh_key_len(&p); + buf = kmalloc(buf_len, GFP_KERNEL); + if (!buf) { + err = -ENOMEM; + goto free_tmp; + } + + err = crypto_ecdh_encode_key(buf, buf_len, &p); + if (err) + goto free_all; + + err = crypto_kpp_set_secret(tfm, buf, buf_len); + /* fall through */ +free_all: + kzfree(buf); +free_tmp: + kzfree(tmp); + return err; +} + +/* generate_ecdh_public_key() - function assumes that the private key was + * already set. + * + * @tfm: KPP tfm handle allocated with crypto_alloc_kpp(). + * @public_key: memory where the computed ecc public key will be saved. + * + * Return: zero on success; error code in case of error. + */ +int generate_ecdh_public_key(struct crypto_kpp *tfm, u8 public_key[64]) { - struct crypto_kpp *tfm; struct kpp_request *req; - struct ecdh p; + u8 *tmp; struct ecdh_completion result; struct scatterlist dst; - u8 *tmp, *buf; - unsigned int buf_len; - int err = -ENOMEM; - const unsigned short max_tries = 16; - unsigned short tries = 0; + int err; tmp = kmalloc(64, GFP_KERNEL); if (!tmp) - return false; + return -ENOMEM; - tfm = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0); - if (IS_ERR(tfm)) { - pr_err("alg: kpp: Failed to load tfm for kpp: %ld\n", - PTR_ERR(tfm)); + req = kpp_request_alloc(tfm, GFP_KERNEL); + if (!req) { + err = -ENOMEM; goto free_tmp; } - req = kpp_request_alloc(tfm, GFP_KERNEL); - if (!req) - goto free_kpp; - init_completion(&result.completion); + sg_init_one(&dst, tmp, 64); + kpp_request_set_input(req, NULL, 0); + kpp_request_set_output(req, &dst, 64); + kpp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, + ecdh_complete, &result); - /* Set curve_id */ - p.curve_id = ECC_CURVE_NIST_P256; - p.key_size = 32; - buf_len = crypto_ecdh_key_len(&p); - buf = kmalloc(buf_len, GFP_KERNEL); - if (!buf) - goto free_req; - - do { - if (tries++ >= max_tries) - goto free_all; - - /* Set private Key */ - p.key = (char *)private_key; - crypto_ecdh_encode_key(buf, buf_len, &p); - err = crypto_kpp_set_secret(tfm, buf, buf_len); - if (err) - goto free_all; - - sg_init_one(&dst, tmp, 64); - kpp_request_set_input(req, NULL, 0); - kpp_request_set_output(req, &dst, 64); - kpp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, - ecdh_complete, &result); - - err = crypto_kpp_generate_public_key(req); - - if (err == -EINPROGRESS) { - wait_for_completion(&result.completion); - err = result.err; - } - - /* Private key is not valid. Regenerate */ - if (err == -EINVAL) - continue; - - if (err < 0) - goto free_all; - else - break; - - } while (true); - - /* Keys are handed back in little endian as expected by Security - * Manager Protocol + err = crypto_kpp_generate_public_key(req); + if (err == -EINPROGRESS) { + wait_for_completion(&result.completion); + err = result.err; + } + if (err < 0) + goto free_all; + + /* The public key is handed back in little endian as expected by + * the Security Manager Protocol. */ swap_digits((u64 *)tmp, (u64 *)public_key, 4); /* x */ swap_digits((u64 *)&tmp[32], (u64 *)&public_key[32], 4); /* y */ - swap_digits((u64 *)private_key, (u64 *)tmp, 4); - memcpy(private_key, tmp, 32); free_all: - kzfree(buf); -free_req: kpp_request_free(req); -free_kpp: - crypto_free_kpp(tfm); free_tmp: kfree(tmp); - return (err == 0); + return err; +} + +/* generate_ecdh_keys() - generate ecc key pair. + * + * @tfm: KPP tfm handle allocated with crypto_alloc_kpp(). + * @public_key: memory where the computed ecc public key will be saved. + * + * Return: zero on success; error code in case of error. + */ +int generate_ecdh_keys(struct crypto_kpp *tfm, u8 public_key[64]) +{ + int err; + + err = set_ecdh_privkey(tfm, NULL); + if (err) + return err; + + return generate_ecdh_public_key(tfm, public_key); } diff --git a/net/bluetooth/ecdh_helper.h b/net/bluetooth/ecdh_helper.h index 7a423faf76e5..a6f8d03d4aaf 100644 --- a/net/bluetooth/ecdh_helper.h +++ b/net/bluetooth/ecdh_helper.h @@ -20,8 +20,11 @@ * COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS * SOFTWARE IS DISCLAIMED. */ +#include <crypto/kpp.h> #include <linux/types.h> -bool compute_ecdh_secret(const u8 pub_a[64], const u8 priv_b[32], - u8 secret[32]); -bool generate_ecdh_keys(u8 public_key[64], u8 private_key[32]); +int compute_ecdh_secret(struct crypto_kpp *tfm, const u8 pair_public_key[64], + u8 secret[32]); +int set_ecdh_privkey(struct crypto_kpp *tfm, const u8 *private_key); +int generate_ecdh_public_key(struct crypto_kpp *tfm, u8 public_key[64]); +int generate_ecdh_keys(struct crypto_kpp *tfm, u8 public_key[64]); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index dc59eae54717..a9682534c377 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -729,8 +729,8 @@ static void create_le_conn_complete(struct hci_dev *hdev, u8 status, u16 opcode) goto done; } - BT_ERR("HCI request failed to create LE connection: status 0x%2.2x", - status); + bt_dev_err(hdev, "request failed to create LE connection: " + "status 0x%2.2x", status); if (!conn) goto done; @@ -907,7 +907,7 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, */ if (hci_dev_test_flag(hdev, HCI_LE_SCAN) && hdev->le_scan_type == LE_SCAN_ACTIVE) { - skb_queue_purge(&req.cmd_q); + hci_req_purge(&req); hci_conn_del(conn); return ERR_PTR(-EBUSY); } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 6bc679cd3481..40d260f2bea5 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -267,7 +267,7 @@ static int hci_init1_req(struct hci_request *req, unsigned long opt) amp_init1(req); break; default: - BT_ERR("Unknown device type %d", hdev->dev_type); + bt_dev_err(hdev, "Unknown device type %d", hdev->dev_type); break; } @@ -2150,8 +2150,7 @@ static void hci_error_reset(struct work_struct *work) if (hdev->hw_error) hdev->hw_error(hdev, hdev->hw_error_code); else - BT_ERR("%s hardware error 0x%2.2x", hdev->name, - hdev->hw_error_code); + bt_dev_err(hdev, "hardware error 0x%2.2x", hdev->hw_error_code); if (hci_dev_do_close(hdev)) return; @@ -2524,9 +2523,9 @@ static void hci_cmd_timeout(struct work_struct *work) struct hci_command_hdr *sent = (void *) hdev->sent_cmd->data; u16 opcode = __le16_to_cpu(sent->opcode); - BT_ERR("%s command 0x%4.4x tx timeout", hdev->name, opcode); + bt_dev_err(hdev, "command 0x%4.4x tx timeout", opcode); } else { - BT_ERR("%s command tx timeout", hdev->name); + bt_dev_err(hdev, "command tx timeout"); } atomic_set(&hdev->cmd_cnt, 1); @@ -2858,7 +2857,7 @@ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, params = kzalloc(sizeof(*params), GFP_KERNEL); if (!params) { - BT_ERR("Out of memory"); + bt_dev_err(hdev, "out of memory"); return NULL; } @@ -3393,7 +3392,7 @@ static void hci_send_frame(struct hci_dev *hdev, struct sk_buff *skb) err = hdev->send(hdev, skb); if (err < 0) { - BT_ERR("%s sending frame failed (%d)", hdev->name, err); + bt_dev_err(hdev, "sending frame failed (%d)", err); kfree_skb(skb); } } @@ -3408,7 +3407,7 @@ int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, skb = hci_prepare_cmd(hdev, opcode, plen, param); if (!skb) { - BT_ERR("%s no memory for command", hdev->name); + bt_dev_err(hdev, "no memory for command"); return -ENOMEM; } @@ -3493,7 +3492,7 @@ static void hci_queue_acl(struct hci_chan *chan, struct sk_buff_head *queue, hci_add_acl_hdr(skb, chan->handle, flags); break; default: - BT_ERR("%s unknown dev_type %d", hdev->name, hdev->dev_type); + bt_dev_err(hdev, "unknown dev_type %d", hdev->dev_type); return; } @@ -3618,7 +3617,7 @@ static struct hci_conn *hci_low_sent(struct hci_dev *hdev, __u8 type, break; default: cnt = 0; - BT_ERR("Unknown link type"); + bt_dev_err(hdev, "unknown link type %d", conn->type); } q = cnt / num; @@ -3635,15 +3634,15 @@ static void hci_link_tx_to(struct hci_dev *hdev, __u8 type) struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; - BT_ERR("%s link tx timeout", hdev->name); + bt_dev_err(hdev, "link tx timeout"); rcu_read_lock(); /* Kill stalled connections */ list_for_each_entry_rcu(c, &h->list, list) { if (c->type == type && c->sent) { - BT_ERR("%s killing stalled connection %pMR", - hdev->name, &c->dst); + bt_dev_err(hdev, "killing stalled connection %pMR", + &c->dst); hci_disconnect(c, HCI_ERROR_REMOTE_USER_TERM); } } @@ -3724,7 +3723,7 @@ static struct hci_chan *hci_chan_sent(struct hci_dev *hdev, __u8 type, break; default: cnt = 0; - BT_ERR("Unknown link type"); + bt_dev_err(hdev, "unknown link type %d", chan->conn->type); } q = cnt / num; @@ -4066,8 +4065,8 @@ static void hci_acldata_packet(struct hci_dev *hdev, struct sk_buff *skb) l2cap_recv_acldata(conn, skb, flags); return; } else { - BT_ERR("%s ACL packet for unknown connection handle %d", - hdev->name, handle); + bt_dev_err(hdev, "ACL packet for unknown connection handle %d", + handle); } kfree_skb(skb); @@ -4097,8 +4096,8 @@ static void hci_scodata_packet(struct hci_dev *hdev, struct sk_buff *skb) sco_recv_scodata(conn, skb); return; } else { - BT_ERR("%s SCO packet for unknown connection handle %d", - hdev->name, handle); + bt_dev_err(hdev, "SCO packet for unknown connection handle %d", + handle); } kfree_skb(skb); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 0b4dba08a14e..cd3bbb766c24 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1188,7 +1188,8 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev, break; default: - BT_ERR("Used reserved LE_Scan_Enable param %d", cp->enable); + bt_dev_err(hdev, "use of reserved LE_Scan_Enable param %d", + cp->enable); break; } @@ -1485,7 +1486,7 @@ static void hci_cs_create_conn(struct hci_dev *hdev, __u8 status) conn = hci_conn_add(hdev, ACL_LINK, &cp->bdaddr, HCI_ROLE_MASTER); if (!conn) - BT_ERR("No memory for new connection"); + bt_dev_err(hdev, "no memory for new connection"); } } @@ -2269,7 +2270,7 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb) conn = hci_conn_add(hdev, ev->link_type, &ev->bdaddr, HCI_ROLE_SLAVE); if (!conn) { - BT_ERR("No memory for new connection"); + bt_dev_err(hdev, "no memory for new connection"); hci_dev_unlock(hdev); return; } @@ -2431,7 +2432,7 @@ static void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) if (!hci_conn_ssp_enabled(conn) && test_bit(HCI_CONN_REAUTH_PEND, &conn->flags)) { - BT_INFO("re-auth of legacy device is not possible."); + bt_dev_info(hdev, "re-auth of legacy device is not possible."); } else { set_bit(HCI_CONN_AUTH, &conn->flags); conn->sec_level = conn->pending_sec_level; @@ -2535,8 +2536,7 @@ static void read_enc_key_size_complete(struct hci_dev *hdev, u8 status, BT_DBG("%s status 0x%02x", hdev->name, status); if (!skb || skb->len < sizeof(*rp)) { - BT_ERR("%s invalid HCI Read Encryption Key Size response", - hdev->name); + bt_dev_err(hdev, "invalid read key size response"); return; } @@ -2554,8 +2554,8 @@ static void read_enc_key_size_complete(struct hci_dev *hdev, u8 status, * supported. */ if (rp->status) { - BT_ERR("%s failed to read key size for handle %u", hdev->name, - handle); + bt_dev_err(hdev, "failed to read key size for handle %u", + handle); conn->enc_key_size = HCI_LINK_KEY_SIZE; } else { conn->enc_key_size = rp->key_size; @@ -2664,7 +2664,7 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_req_add(&req, HCI_OP_READ_ENC_KEY_SIZE, sizeof(cp), &cp); if (hci_req_run_skb(&req, read_enc_key_size_complete)) { - BT_ERR("Sending HCI Read Encryption Key Size failed"); + bt_dev_err(hdev, "sending read key size failed"); conn->enc_key_size = HCI_LINK_KEY_SIZE; goto notify; } @@ -3197,7 +3197,7 @@ static void hci_num_comp_pkts_evt(struct hci_dev *hdev, struct sk_buff *skb) int i; if (hdev->flow_ctl_mode != HCI_FLOW_CTL_MODE_PACKET_BASED) { - BT_ERR("Wrong event for mode %d", hdev->flow_ctl_mode); + bt_dev_err(hdev, "wrong event for mode %d", hdev->flow_ctl_mode); return; } @@ -3249,7 +3249,8 @@ static void hci_num_comp_pkts_evt(struct hci_dev *hdev, struct sk_buff *skb) break; default: - BT_ERR("Unknown type %d conn %p", conn->type, conn); + bt_dev_err(hdev, "unknown type %d conn %p", + conn->type, conn); break; } } @@ -3271,7 +3272,7 @@ static struct hci_conn *__hci_conn_lookup_handle(struct hci_dev *hdev, return chan->conn; break; default: - BT_ERR("%s unknown dev_type %d", hdev->name, hdev->dev_type); + bt_dev_err(hdev, "unknown dev_type %d", hdev->dev_type); break; } @@ -3284,7 +3285,7 @@ static void hci_num_comp_blocks_evt(struct hci_dev *hdev, struct sk_buff *skb) int i; if (hdev->flow_ctl_mode != HCI_FLOW_CTL_MODE_BLOCK_BASED) { - BT_ERR("Wrong event for mode %d", hdev->flow_ctl_mode); + bt_dev_err(hdev, "wrong event for mode %d", hdev->flow_ctl_mode); return; } @@ -3320,7 +3321,8 @@ static void hci_num_comp_blocks_evt(struct hci_dev *hdev, struct sk_buff *skb) break; default: - BT_ERR("Unknown type %d conn %p", conn->type, conn); + bt_dev_err(hdev, "unknown type %d conn %p", + conn->type, conn); break; } } @@ -4479,7 +4481,7 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) if (!conn) { conn = hci_conn_add(hdev, LE_LINK, &ev->bdaddr, ev->role); if (!conn) { - BT_ERR("No memory for new connection"); + bt_dev_err(hdev, "no memory for new connection"); goto unlock; } @@ -4749,8 +4751,8 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, case LE_ADV_SCAN_RSP: break; default: - BT_ERR_RATELIMITED("Unknown advertising packet type: 0x%02x", - type); + bt_dev_err_ratelimited(hdev, "unknown advertising packet " + "type: 0x%02x", type); return; } @@ -4769,8 +4771,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, /* Adjust for actual length */ if (len != real_len) { - BT_ERR_RATELIMITED("%s advertising data length corrected", - hdev->name); + bt_dev_err_ratelimited(hdev, "advertising data len corrected"); len = real_len; } @@ -5192,7 +5193,7 @@ static bool hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode, return false; if (skb->len < sizeof(*hdr)) { - BT_ERR("Too short HCI event"); + bt_dev_err(hdev, "too short HCI event"); return false; } @@ -5206,12 +5207,13 @@ static bool hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode, } if (hdr->evt != HCI_EV_CMD_COMPLETE) { - BT_DBG("Last event is not cmd complete (0x%2.2x)", hdr->evt); + bt_dev_err(hdev, "last event is not cmd complete (0x%2.2x)", + hdr->evt); return false; } if (skb->len < sizeof(*ev)) { - BT_ERR("Too short cmd_complete event"); + bt_dev_err(hdev, "too short cmd_complete event"); return false; } diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index b73ac149de34..abc0f3224dd1 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -41,6 +41,11 @@ void hci_req_init(struct hci_request *req, struct hci_dev *hdev) req->err = 0; } +void hci_req_purge(struct hci_request *req) +{ + skb_queue_purge(&req->cmd_q); +} + static int req_run(struct hci_request *req, hci_req_complete_t complete, hci_req_complete_skb_t complete_skb) { @@ -331,8 +336,8 @@ void hci_req_add_ev(struct hci_request *req, u16 opcode, u32 plen, skb = hci_prepare_cmd(hdev, opcode, plen, param); if (!skb) { - BT_ERR("%s no memory for command (opcode 0x%4.4x)", - hdev->name, opcode); + bt_dev_err(hdev, "no memory for command (opcode 0x%4.4x)", + opcode); req->err = -ENOMEM; return; } @@ -1421,7 +1426,7 @@ int hci_update_random_address(struct hci_request *req, bool require_privacy, err = smp_generate_rpa(hdev, hdev->irk, &hdev->rpa); if (err < 0) { - BT_ERR("%s failed to generate new RPA", hdev->name); + bt_dev_err(hdev, "failed to generate new RPA"); return err; } @@ -1783,7 +1788,7 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason) err = hci_req_run(&req, abort_conn_complete); if (err && err != -ENODATA) { - BT_ERR("Failed to run HCI request: err %d", err); + bt_dev_err(conn->hdev, "failed to run HCI request: err %d", err); return err; } @@ -1867,7 +1872,8 @@ static void le_scan_disable_work(struct work_struct *work) hci_req_sync(hdev, le_scan_disable, 0, HCI_CMD_TIMEOUT, &status); if (status) { - BT_ERR("Failed to disable LE scan: status 0x%02x", status); + bt_dev_err(hdev, "failed to disable LE scan: status 0x%02x", + status); return; } @@ -1898,7 +1904,7 @@ static void le_scan_disable_work(struct work_struct *work) hci_req_sync(hdev, bredr_inquiry, DISCOV_INTERLEAVED_INQUIRY_LEN, HCI_CMD_TIMEOUT, &status); if (status) { - BT_ERR("Inquiry failed: status 0x%02x", status); + bt_dev_err(hdev, "inquiry failed: status 0x%02x", status); goto discov_stopped; } @@ -1940,7 +1946,8 @@ static void le_scan_restart_work(struct work_struct *work) hci_req_sync(hdev, le_scan_restart, 0, HCI_CMD_TIMEOUT, &status); if (status) { - BT_ERR("Failed to restart LE scan: status %d", status); + bt_dev_err(hdev, "failed to restart LE scan: status %d", + status); return; } diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h index dde77bd59f91..702beb140d9f 100644 --- a/net/bluetooth/hci_request.h +++ b/net/bluetooth/hci_request.h @@ -36,6 +36,7 @@ struct hci_request { }; void hci_req_init(struct hci_request *req, struct hci_dev *hdev); +void hci_req_purge(struct hci_request *req); int hci_req_run(struct hci_request *req, hci_req_complete_t complete); int hci_req_run_skb(struct hci_request *req, hci_req_complete_skb_t complete); void hci_req_add(struct hci_request *req, u16 opcode, u32 plen, diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 65d734c165bd..923e9a271872 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -251,15 +251,13 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb) } /* Send frame to sockets with specific channel */ -void hci_send_to_channel(unsigned short channel, struct sk_buff *skb, - int flag, struct sock *skip_sk) +static void __hci_send_to_channel(unsigned short channel, struct sk_buff *skb, + int flag, struct sock *skip_sk) { struct sock *sk; BT_DBG("channel %u len %d", channel, skb->len); - read_lock(&hci_sk_list.lock); - sk_for_each(sk, &hci_sk_list.head) { struct sk_buff *nskb; @@ -285,6 +283,13 @@ void hci_send_to_channel(unsigned short channel, struct sk_buff *skb, kfree_skb(nskb); } +} + +void hci_send_to_channel(unsigned short channel, struct sk_buff *skb, + int flag, struct sock *skip_sk) +{ + read_lock(&hci_sk_list.lock); + __hci_send_to_channel(channel, skb, flag, skip_sk); read_unlock(&hci_sk_list.lock); } @@ -388,8 +393,8 @@ void hci_send_monitor_ctrl_event(struct hci_dev *hdev, u16 event, hdr->index = index; hdr->len = cpu_to_le16(skb->len - HCI_MON_HDR_SIZE); - hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, - HCI_SOCK_TRUSTED, NULL); + __hci_send_to_channel(HCI_CHANNEL_MONITOR, skb, + HCI_SOCK_TRUSTED, NULL); kfree_skb(skb); } diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index d5c7c89ec4d6..9874844a95a9 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -51,7 +51,7 @@ void hci_conn_add_sysfs(struct hci_conn *conn) dev_set_name(&conn->dev, "%s:%d", hdev->name, conn->handle); if (device_add(&conn->dev) < 0) { - BT_ERR("Failed to register connection device"); + bt_dev_err(hdev, "failed to register connection device"); return; } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 1fba2a03f8ae..6e9fc86d8daf 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -2159,8 +2159,8 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, key_count = __le16_to_cpu(cp->key_count); if (key_count > max_key_count) { - BT_ERR("load_link_keys: too big key_count value %u", - key_count); + bt_dev_err(hdev, "load_link_keys: too big key_count value %u", + key_count); return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, MGMT_STATUS_INVALID_PARAMS); } @@ -2168,8 +2168,8 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, expected_len = sizeof(*cp) + key_count * sizeof(struct mgmt_link_key_info); if (expected_len != len) { - BT_ERR("load_link_keys: expected %u bytes, got %u bytes", - expected_len, len); + bt_dev_err(hdev, "load_link_keys: expected %u bytes, got %u bytes", + expected_len, len); return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, MGMT_STATUS_INVALID_PARAMS); } @@ -2561,7 +2561,7 @@ static int pin_code_reply(struct sock *sk, struct hci_dev *hdev, void *data, memcpy(&ncp.addr, &cp->addr, sizeof(ncp.addr)); - BT_ERR("PIN code is not 16 bytes long"); + bt_dev_err(hdev, "PIN code is not 16 bytes long"); err = send_pin_code_neg_reply(sk, hdev, &ncp); if (err >= 0) @@ -3391,7 +3391,8 @@ static int add_remote_oob_data(struct sock *sk, struct hci_dev *hdev, MGMT_OP_ADD_REMOTE_OOB_DATA, status, &cp->addr, sizeof(cp->addr)); } else { - BT_ERR("add_remote_oob_data: invalid length of %u bytes", len); + bt_dev_err(hdev, "add_remote_oob_data: invalid len of %u bytes", + len); err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_REMOTE_OOB_DATA, MGMT_STATUS_INVALID_PARAMS); } @@ -3604,8 +3605,8 @@ static int start_service_discovery(struct sock *sk, struct hci_dev *hdev, uuid_count = __le16_to_cpu(cp->uuid_count); if (uuid_count > max_uuid_count) { - BT_ERR("service_discovery: too big uuid_count value %u", - uuid_count); + bt_dev_err(hdev, "service_discovery: too big uuid_count value %u", + uuid_count); err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_START_SERVICE_DISCOVERY, MGMT_STATUS_INVALID_PARAMS, &cp->type, @@ -3615,8 +3616,8 @@ static int start_service_discovery(struct sock *sk, struct hci_dev *hdev, expected_len = sizeof(*cp) + uuid_count * 16; if (expected_len != len) { - BT_ERR("service_discovery: expected %u bytes, got %u bytes", - expected_len, len); + bt_dev_err(hdev, "service_discovery: expected %u bytes, got %u bytes", + expected_len, len); err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_START_SERVICE_DISCOVERY, MGMT_STATUS_INVALID_PARAMS, &cp->type, @@ -3943,7 +3944,7 @@ static void set_advertising_complete(struct hci_dev *hdev, u8 status, err = hci_req_run(&req, enable_advertising_instance); if (err) - BT_ERR("Failed to re-configure advertising"); + bt_dev_err(hdev, "failed to re-configure advertising"); unlock: hci_dev_unlock(hdev); @@ -4664,15 +4665,16 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, irk_count = __le16_to_cpu(cp->irk_count); if (irk_count > max_irk_count) { - BT_ERR("load_irks: too big irk_count value %u", irk_count); + bt_dev_err(hdev, "load_irks: too big irk_count value %u", + irk_count); return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_IRKS, MGMT_STATUS_INVALID_PARAMS); } expected_len = sizeof(*cp) + irk_count * sizeof(struct mgmt_irk_info); if (expected_len != len) { - BT_ERR("load_irks: expected %u bytes, got %u bytes", - expected_len, len); + bt_dev_err(hdev, "load_irks: expected %u bytes, got %u bytes", + expected_len, len); return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_IRKS, MGMT_STATUS_INVALID_PARAMS); } @@ -4745,7 +4747,8 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, key_count = __le16_to_cpu(cp->key_count); if (key_count > max_key_count) { - BT_ERR("load_ltks: too big key_count value %u", key_count); + bt_dev_err(hdev, "load_ltks: too big key_count value %u", + key_count); return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS, MGMT_STATUS_INVALID_PARAMS); } @@ -4753,8 +4756,8 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, expected_len = sizeof(*cp) + key_count * sizeof(struct mgmt_ltk_info); if (expected_len != len) { - BT_ERR("load_keys: expected %u bytes, got %u bytes", - expected_len, len); + bt_dev_err(hdev, "load_keys: expected %u bytes, got %u bytes", + expected_len, len); return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS, MGMT_STATUS_INVALID_PARAMS); } @@ -4873,14 +4876,15 @@ static void conn_info_refresh_complete(struct hci_dev *hdev, u8 hci_status, } if (!cp) { - BT_ERR("invalid sent_cmd in conn_info response"); + bt_dev_err(hdev, "invalid sent_cmd in conn_info response"); goto unlock; } handle = __le16_to_cpu(cp->handle); conn = hci_conn_hash_lookup_handle(hdev, handle); if (!conn) { - BT_ERR("unknown handle (%d) in conn_info response", handle); + bt_dev_err(hdev, "unknown handle (%d) in conn_info response", + handle); goto unlock; } @@ -5477,8 +5481,8 @@ static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data, param_count = __le16_to_cpu(cp->param_count); if (param_count > max_param_count) { - BT_ERR("load_conn_param: too big param_count value %u", - param_count); + bt_dev_err(hdev, "load_conn_param: too big param_count value %u", + param_count); return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_CONN_PARAM, MGMT_STATUS_INVALID_PARAMS); } @@ -5486,8 +5490,8 @@ static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data, expected_len = sizeof(*cp) + param_count * sizeof(struct mgmt_conn_param); if (expected_len != len) { - BT_ERR("load_conn_param: expected %u bytes, got %u bytes", - expected_len, len); + bt_dev_err(hdev, "load_conn_param: expected %u bytes, got %u bytes", + expected_len, len); return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_CONN_PARAM, MGMT_STATUS_INVALID_PARAMS); } @@ -5512,7 +5516,7 @@ static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data, } else if (param->addr.type == BDADDR_LE_RANDOM) { addr_type = ADDR_LE_DEV_RANDOM; } else { - BT_ERR("Ignoring invalid connection parameters"); + bt_dev_err(hdev, "ignoring invalid connection parameters"); continue; } @@ -5525,14 +5529,14 @@ static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data, min, max, latency, timeout); if (hci_check_conn_params(min, max, latency, timeout) < 0) { - BT_ERR("Ignoring invalid connection parameters"); + bt_dev_err(hdev, "ignoring invalid connection parameters"); continue; } hci_param = hci_conn_params_add(hdev, ¶m->addr.bdaddr, addr_type); if (!hci_param) { - BT_ERR("Failed to add connection parameters"); + bt_dev_err(hdev, "failed to add connection parameters"); continue; } @@ -6383,6 +6387,7 @@ static int remove_advertising(struct sock *sk, struct hci_dev *hdev, if (skb_queue_empty(&req.cmd_q) || !hdev_is_powered(hdev) || hci_dev_test_flag(hdev, HCI_ADVERTISING)) { + hci_req_purge(&req); rp.instance = cp->instance; err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_ADVERTISING, diff --git a/net/bluetooth/selftest.c b/net/bluetooth/selftest.c index 34a1227f4391..03e3c89c3046 100644 --- a/net/bluetooth/selftest.c +++ b/net/bluetooth/selftest.c @@ -138,12 +138,12 @@ static const u8 dhkey_3[32] __initconst = { 0x7c, 0x1c, 0xf9, 0x49, 0xe6, 0xd7, 0xaa, 0x70, }; -static int __init test_ecdh_sample(const u8 priv_a[32], const u8 priv_b[32], - const u8 pub_a[64], const u8 pub_b[64], - const u8 dhkey[32]) +static int __init test_ecdh_sample(struct crypto_kpp *tfm, const u8 priv_a[32], + const u8 priv_b[32], const u8 pub_a[64], + const u8 pub_b[64], const u8 dhkey[32]) { u8 *tmp, *dhkey_a, *dhkey_b; - int ret = 0; + int ret; tmp = kmalloc(64, GFP_KERNEL); if (!tmp) @@ -152,17 +152,30 @@ static int __init test_ecdh_sample(const u8 priv_a[32], const u8 priv_b[32], dhkey_a = &tmp[0]; dhkey_b = &tmp[32]; - compute_ecdh_secret(pub_b, priv_a, dhkey_a); - compute_ecdh_secret(pub_a, priv_b, dhkey_b); + ret = set_ecdh_privkey(tfm, priv_a); + if (ret) + goto out; + + ret = compute_ecdh_secret(tfm, pub_b, dhkey_a); + if (ret) + goto out; if (memcmp(dhkey_a, dhkey, 32)) { ret = -EINVAL; goto out; } + ret = set_ecdh_privkey(tfm, priv_b); + if (ret) + goto out; + + ret = compute_ecdh_secret(tfm, pub_a, dhkey_b); + if (ret) + goto out; + if (memcmp(dhkey_b, dhkey, 32)) ret = -EINVAL; - + /* fall through*/ out: kfree(tmp); return ret; @@ -185,30 +198,43 @@ static const struct file_operations test_ecdh_fops = { static int __init test_ecdh(void) { + struct crypto_kpp *tfm; ktime_t calltime, delta, rettime; - unsigned long long duration; + unsigned long long duration = 0; int err; calltime = ktime_get(); - err = test_ecdh_sample(priv_a_1, priv_b_1, pub_a_1, pub_b_1, dhkey_1); + tfm = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0); + if (IS_ERR(tfm)) { + BT_ERR("Unable to create ECDH crypto context"); + err = PTR_ERR(tfm); + goto done; + } + + err = test_ecdh_sample(tfm, priv_a_1, priv_b_1, pub_a_1, pub_b_1, + dhkey_1); if (err) { BT_ERR("ECDH sample 1 failed"); goto done; } - err = test_ecdh_sample(priv_a_2, priv_b_2, pub_a_2, pub_b_2, dhkey_2); + err = test_ecdh_sample(tfm, priv_a_2, priv_b_2, pub_a_2, pub_b_2, + dhkey_2); if (err) { BT_ERR("ECDH sample 2 failed"); goto done; } - err = test_ecdh_sample(priv_a_3, priv_a_3, pub_a_3, pub_a_3, dhkey_3); + err = test_ecdh_sample(tfm, priv_a_3, priv_a_3, pub_a_3, pub_a_3, + dhkey_3); if (err) { BT_ERR("ECDH sample 3 failed"); goto done; } + crypto_free_kpp(tfm); + rettime = ktime_get(); delta = ktime_sub(rettime, calltime); duration = (unsigned long long) ktime_to_ns(delta) >> 10; diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index a0ef89772c36..01117ae84f1d 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -26,6 +26,7 @@ #include <crypto/algapi.h> #include <crypto/b128ops.h> #include <crypto/hash.h> +#include <crypto/kpp.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> @@ -83,7 +84,6 @@ enum { struct smp_dev { /* Secure Connections OOB data */ u8 local_pk[64]; - u8 local_sk[32]; u8 local_rand[16]; bool debug_key; @@ -92,6 +92,7 @@ struct smp_dev { struct crypto_cipher *tfm_aes; struct crypto_shash *tfm_cmac; + struct crypto_kpp *tfm_ecdh; }; struct smp_chan { @@ -124,13 +125,13 @@ struct smp_chan { /* Secure Connections variables */ u8 local_pk[64]; - u8 local_sk[32]; u8 remote_pk[64]; u8 dhkey[32]; u8 mackey[16]; struct crypto_cipher *tfm_aes; struct crypto_shash *tfm_cmac; + struct crypto_kpp *tfm_ecdh; }; /* These debug key values are defined in the SMP section of the core @@ -565,22 +566,22 @@ int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16]) if (hci_dev_test_flag(hdev, HCI_USE_DEBUG_KEYS)) { BT_DBG("Using debug keys"); + err = set_ecdh_privkey(smp->tfm_ecdh, debug_sk); + if (err) + return err; memcpy(smp->local_pk, debug_pk, 64); - memcpy(smp->local_sk, debug_sk, 32); smp->debug_key = true; } else { while (true) { - /* Seed private key with random number */ - get_random_bytes(smp->local_sk, 32); - - /* Generate local key pair for Secure Connections */ - if (!generate_ecdh_keys(smp->local_pk, smp->local_sk)) - return -EIO; + /* Generate key pair for Secure Connections */ + err = generate_ecdh_keys(smp->tfm_ecdh, smp->local_pk); + if (err) + return err; /* This is unlikely, but we need to check that * we didn't accidentially generate a debug key. */ - if (crypto_memneq(smp->local_sk, debug_sk, 32)) + if (crypto_memneq(smp->local_pk, debug_pk, 64)) break; } smp->debug_key = false; @@ -588,7 +589,6 @@ int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16]) SMP_DBG("OOB Public Key X: %32phN", smp->local_pk); SMP_DBG("OOB Public Key Y: %32phN", smp->local_pk + 32); - SMP_DBG("OOB Private Key: %32phN", smp->local_sk); get_random_bytes(smp->local_rand, 16); @@ -771,6 +771,7 @@ static void smp_chan_destroy(struct l2cap_conn *conn) crypto_free_cipher(smp->tfm_aes); crypto_free_shash(smp->tfm_cmac); + crypto_free_kpp(smp->tfm_ecdh); /* Ensure that we don't leave any debug key around if debug key * support hasn't been explicitly enabled. @@ -995,7 +996,8 @@ static u8 smp_random(struct smp_chan *smp) return SMP_UNSPECIFIED; if (crypto_memneq(smp->pcnf, confirm, sizeof(smp->pcnf))) { - BT_ERR("Pairing failed (confirmation values mismatch)"); + bt_dev_err(hcon->hdev, "pairing failed " + "(confirmation values mismatch)"); return SMP_CONFIRM_FAILED; } @@ -1209,7 +1211,7 @@ static void sc_generate_ltk(struct smp_chan *smp) key = hci_find_link_key(hdev, &hcon->dst); if (!key) { - BT_ERR("%s No Link Key found to generate LTK", hdev->name); + bt_dev_err(hdev, "no Link Key found to generate LTK"); return; } @@ -1391,16 +1393,19 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn) smp->tfm_aes = crypto_alloc_cipher("aes", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(smp->tfm_aes)) { BT_ERR("Unable to create AES crypto context"); - kzfree(smp); - return NULL; + goto zfree_smp; } smp->tfm_cmac = crypto_alloc_shash("cmac(aes)", 0, 0); if (IS_ERR(smp->tfm_cmac)) { BT_ERR("Unable to create CMAC crypto context"); - crypto_free_cipher(smp->tfm_aes); - kzfree(smp); - return NULL; + goto free_cipher; + } + + smp->tfm_ecdh = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0); + if (IS_ERR(smp->tfm_ecdh)) { + BT_ERR("Unable to create ECDH crypto context"); + goto free_shash; } smp->conn = conn; @@ -1413,6 +1418,14 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn) hci_conn_hold(conn->hcon); return smp; + +free_shash: + crypto_free_shash(smp->tfm_cmac); +free_cipher: + crypto_free_cipher(smp->tfm_aes); +zfree_smp: + kzfree(smp); + return NULL; } static int sc_mackey_and_ltk(struct smp_chan *smp, u8 mackey[16], u8 ltk[16]) @@ -1883,7 +1896,6 @@ static u8 sc_send_public_key(struct smp_chan *smp) smp_dev = chan->data; memcpy(smp->local_pk, smp_dev->local_pk, 64); - memcpy(smp->local_sk, smp_dev->local_sk, 32); memcpy(smp->lr, smp_dev->local_rand, 16); if (smp_dev->debug_key) @@ -1894,22 +1906,20 @@ static u8 sc_send_public_key(struct smp_chan *smp) if (hci_dev_test_flag(hdev, HCI_USE_DEBUG_KEYS)) { BT_DBG("Using debug keys"); + if (set_ecdh_privkey(smp->tfm_ecdh, debug_sk)) + return SMP_UNSPECIFIED; memcpy(smp->local_pk, debug_pk, 64); - memcpy(smp->local_sk, debug_sk, 32); set_bit(SMP_FLAG_DEBUG_KEY, &smp->flags); } else { while (true) { - /* Seed private key with random number */ - get_random_bytes(smp->local_sk, 32); - - /* Generate local key pair for Secure Connections */ - if (!generate_ecdh_keys(smp->local_pk, smp->local_sk)) + /* Generate key pair for Secure Connections */ + if (generate_ecdh_keys(smp->tfm_ecdh, smp->local_pk)) return SMP_UNSPECIFIED; /* This is unlikely, but we need to check that * we didn't accidentially generate a debug key. */ - if (crypto_memneq(smp->local_sk, debug_sk, 32)) + if (crypto_memneq(smp->local_pk, debug_pk, 64)) break; } } @@ -1917,7 +1927,6 @@ static u8 sc_send_public_key(struct smp_chan *smp) done: SMP_DBG("Local Public Key X: %32phN", smp->local_pk); SMP_DBG("Local Public Key Y: %32phN", smp->local_pk + 32); - SMP_DBG("Local Private Key: %32phN", smp->local_sk); smp_send_cmd(smp->conn, SMP_CMD_PUBLIC_KEY, 64, smp->local_pk); @@ -2059,11 +2068,11 @@ static int fixup_sc_false_positive(struct smp_chan *smp) return SMP_UNSPECIFIED; if (hci_dev_test_flag(hdev, HCI_SC_ONLY)) { - BT_ERR("Refusing SMP SC -> legacy fallback in SC-only mode"); + bt_dev_err(hdev, "refusing legacy fallback in SC-only mode"); return SMP_UNSPECIFIED; } - BT_ERR("Trying to fall back to legacy SMP"); + bt_dev_err(hdev, "trying to fall back to legacy SMP"); req = (void *) &smp->preq[1]; rsp = (void *) &smp->prsp[1]; @@ -2074,7 +2083,7 @@ static int fixup_sc_false_positive(struct smp_chan *smp) auth = req->auth_req & AUTH_REQ_MASK(hdev); if (tk_request(conn, 0, auth, rsp->io_capability, req->io_capability)) { - BT_ERR("Failed to fall back to legacy SMP"); + bt_dev_err(hdev, "failed to fall back to legacy SMP"); return SMP_UNSPECIFIED; } @@ -2347,7 +2356,7 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) chan = conn->smp; if (!chan) { - BT_ERR("SMP security requested but not available"); + bt_dev_err(hcon->hdev, "security requested but not available"); return 1; } @@ -2540,7 +2549,7 @@ static int smp_cmd_ident_addr_info(struct l2cap_conn *conn, */ if (!bacmp(&info->bdaddr, BDADDR_ANY) || !hci_is_identity_address(&info->bdaddr, info->addr_type)) { - BT_ERR("Ignoring IRK with no identity address"); + bt_dev_err(hcon->hdev, "ignoring IRK with no identity address"); goto distribute; } @@ -2645,6 +2654,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) struct l2cap_chan *chan = conn->smp; struct smp_chan *smp = chan->data; struct hci_dev *hdev = hcon->hdev; + struct crypto_kpp *tfm_ecdh; struct smp_cmd_pairing_confirm cfm; int err; @@ -2677,7 +2687,18 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) SMP_DBG("Remote Public Key X: %32phN", smp->remote_pk); SMP_DBG("Remote Public Key Y: %32phN", smp->remote_pk + 32); - if (!compute_ecdh_secret(smp->remote_pk, smp->local_sk, smp->dhkey)) + /* Compute the shared secret on the same crypto tfm on which the private + * key was set/generated. + */ + if (test_bit(SMP_FLAG_LOCAL_OOB, &smp->flags)) { + struct smp_dev *smp_dev = chan->data; + + tfm_ecdh = smp_dev->tfm_ecdh; + } else { + tfm_ecdh = smp->tfm_ecdh; + } + + if (compute_ecdh_secret(tfm_ecdh, smp->remote_pk, smp->dhkey)) return SMP_UNSPECIFIED; SMP_DBG("DHKey %32phN", smp->dhkey); @@ -2933,8 +2954,8 @@ done: return err; drop: - BT_ERR("%s unexpected SMP command 0x%02x from %pMR", hcon->hdev->name, - code, &hcon->dst); + bt_dev_err(hcon->hdev, "unexpected SMP command 0x%02x from %pMR", + code, &hcon->dst); kfree_skb(skb); return 0; } @@ -3001,8 +3022,7 @@ static void bredr_pairing(struct l2cap_chan *chan) smp = smp_chan_create(conn); if (!smp) { - BT_ERR("%s unable to create SMP context for BR/EDR", - hdev->name); + bt_dev_err(hdev, "unable to create SMP context for BR/EDR"); return; } @@ -3169,6 +3189,7 @@ static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid) struct smp_dev *smp; struct crypto_cipher *tfm_aes; struct crypto_shash *tfm_cmac; + struct crypto_kpp *tfm_ecdh; if (cid == L2CAP_CID_SMP_BREDR) { smp = NULL; @@ -3194,8 +3215,18 @@ static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid) return ERR_CAST(tfm_cmac); } + tfm_ecdh = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0); + if (IS_ERR(tfm_ecdh)) { + BT_ERR("Unable to create ECDH crypto context"); + crypto_free_shash(tfm_cmac); + crypto_free_cipher(tfm_aes); + kzfree(smp); + return ERR_CAST(tfm_ecdh); + } + smp->tfm_aes = tfm_aes; smp->tfm_cmac = tfm_cmac; + smp->tfm_ecdh = tfm_ecdh; smp->min_key_size = SMP_MIN_ENC_KEY_SIZE; smp->max_key_size = SMP_MAX_ENC_KEY_SIZE; @@ -3205,6 +3236,7 @@ create_chan: if (smp) { crypto_free_cipher(smp->tfm_aes); crypto_free_shash(smp->tfm_cmac); + crypto_free_kpp(smp->tfm_ecdh); kzfree(smp); } return ERR_PTR(-ENOMEM); @@ -3252,6 +3284,7 @@ static void smp_del_chan(struct l2cap_chan *chan) chan->data = NULL; crypto_free_cipher(smp->tfm_aes); crypto_free_shash(smp->tfm_cmac); + crypto_free_kpp(smp->tfm_ecdh); kzfree(smp); } @@ -3490,25 +3523,18 @@ void smp_unregister(struct hci_dev *hdev) #if IS_ENABLED(CONFIG_BT_SELFTEST_SMP) -static inline void swap_digits(u64 *in, u64 *out, unsigned int ndigits) +static int __init test_debug_key(struct crypto_kpp *tfm_ecdh) { - int i; - - for (i = 0; i < ndigits; i++) - out[i] = __swab64(in[ndigits - 1 - i]); -} - -static int __init test_debug_key(void) -{ - u8 pk[64], sk[32]; - - swap_digits((u64 *)debug_sk, (u64 *)sk, 4); + u8 pk[64]; + int err; - if (!generate_ecdh_keys(pk, sk)) - return -EINVAL; + err = set_ecdh_privkey(tfm_ecdh, debug_sk); + if (err) + return err; - if (crypto_memneq(sk, debug_sk, 32)) - return -EINVAL; + err = generate_ecdh_public_key(tfm_ecdh, pk); + if (err) + return err; if (crypto_memneq(pk, debug_pk, 64)) return -EINVAL; @@ -3763,7 +3789,8 @@ static const struct file_operations test_smp_fops = { }; static int __init run_selftests(struct crypto_cipher *tfm_aes, - struct crypto_shash *tfm_cmac) + struct crypto_shash *tfm_cmac, + struct crypto_kpp *tfm_ecdh) { ktime_t calltime, delta, rettime; unsigned long long duration; @@ -3771,7 +3798,7 @@ static int __init run_selftests(struct crypto_cipher *tfm_aes, calltime = ktime_get(); - err = test_debug_key(); + err = test_debug_key(tfm_ecdh); if (err) { BT_ERR("debug_key test failed"); goto done; @@ -3848,6 +3875,7 @@ int __init bt_selftest_smp(void) { struct crypto_cipher *tfm_aes; struct crypto_shash *tfm_cmac; + struct crypto_kpp *tfm_ecdh; int err; tfm_aes = crypto_alloc_cipher("aes", 0, CRYPTO_ALG_ASYNC); @@ -3863,10 +3891,19 @@ int __init bt_selftest_smp(void) return PTR_ERR(tfm_cmac); } - err = run_selftests(tfm_aes, tfm_cmac); + tfm_ecdh = crypto_alloc_kpp("ecdh", CRYPTO_ALG_INTERNAL, 0); + if (IS_ERR(tfm_ecdh)) { + BT_ERR("Unable to create ECDH crypto context"); + crypto_free_shash(tfm_cmac); + crypto_free_cipher(tfm_aes); + return PTR_ERR(tfm_ecdh); + } + + err = run_selftests(tfm_aes, tfm_cmac, tfm_ecdh); crypto_free_shash(tfm_cmac); crypto_free_cipher(tfm_aes); + crypto_free_kpp(tfm_ecdh); return err; } diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 6be41a44d688..a86e6687026e 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -133,7 +133,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, if (is_l2) __skb_push(skb, ETH_HLEN); if (is_direct_pkt_access) - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); retval = bpf_test_run(prog, skb, repeat, &duration); if (!is_l2) __skb_push(skb, ETH_HLEN); @@ -162,6 +162,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, xdp.data_hard_start = data; xdp.data = data + XDP_PACKET_HEADROOM + NET_IP_ALIGN; + xdp.data_meta = xdp.data; xdp.data_end = xdp.data + size; retval = bpf_test_run(prog, &xdp, repeat, &duration); diff --git a/net/bridge/Makefile b/net/bridge/Makefile index f760e62a672a..ac9ef337f0fa 100644 --- a/net/bridge/Makefile +++ b/net/bridge/Makefile @@ -8,7 +8,7 @@ obj-$(CONFIG_BRIDGE) += bridge.o bridge-y := br.o br_device.o br_fdb.o br_forward.o br_if.o br_input.o \ br_ioctl.o br_stp.o br_stp_bpdu.o \ br_stp_if.o br_stp_timer.o br_netlink.o \ - br_netlink_tunnel.o + br_netlink_tunnel.o br_arp_nd_proxy.o bridge-$(CONFIG_SYSFS) += br_sysfs_if.o br_sysfs_br.o diff --git a/net/bridge/br.c b/net/bridge/br.c index 1407d1ba7577..6bf06e756df2 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -112,7 +112,7 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v /* Events that may cause spanning tree to refresh */ if (event == NETDEV_CHANGEADDR || event == NETDEV_UP || event == NETDEV_CHANGE || event == NETDEV_DOWN) - br_ifinfo_notify(RTM_NEWLINK, p); + br_ifinfo_notify(RTM_NEWLINK, NULL, p); return NOTIFY_DONE; } diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c new file mode 100644 index 000000000000..2cf7716254be --- /dev/null +++ b/net/bridge/br_arp_nd_proxy.c @@ -0,0 +1,469 @@ +/* + * Handle bridge arp/nd proxy/suppress + * + * Copyright (C) 2017 Cumulus Networks + * Copyright (c) 2017 Roopa Prabhu <roopa@cumulusnetworks.com> + * + * Authors: + * Roopa Prabhu <roopa@cumulusnetworks.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/neighbour.h> +#include <net/arp.h> +#include <linux/if_vlan.h> +#include <linux/inetdevice.h> +#include <net/addrconf.h> +#if IS_ENABLED(CONFIG_IPV6) +#include <net/ip6_checksum.h> +#endif + +#include "br_private.h" + +void br_recalculate_neigh_suppress_enabled(struct net_bridge *br) +{ + struct net_bridge_port *p; + bool neigh_suppress = false; + + list_for_each_entry(p, &br->port_list, list) { + if (p->flags & BR_NEIGH_SUPPRESS) { + neigh_suppress = true; + break; + } + } + + br->neigh_suppress_enabled = neigh_suppress; +} + +#if IS_ENABLED(CONFIG_INET) +static void br_arp_send(struct net_bridge *br, struct net_bridge_port *p, + struct net_device *dev, __be32 dest_ip, __be32 src_ip, + const unsigned char *dest_hw, + const unsigned char *src_hw, + const unsigned char *target_hw, + __be16 vlan_proto, u16 vlan_tci) +{ + struct net_bridge_vlan_group *vg; + struct sk_buff *skb; + u16 pvid; + + netdev_dbg(dev, "arp send dev %s dst %pI4 dst_hw %pM src %pI4 src_hw %pM\n", + dev->name, &dest_ip, dest_hw, &src_ip, src_hw); + + if (!vlan_tci) { + arp_send(ARPOP_REPLY, ETH_P_ARP, dest_ip, dev, src_ip, + dest_hw, src_hw, target_hw); + return; + } + + skb = arp_create(ARPOP_REPLY, ETH_P_ARP, dest_ip, dev, src_ip, + dest_hw, src_hw, target_hw); + if (!skb) + return; + + if (p) + vg = nbp_vlan_group_rcu(p); + else + vg = br_vlan_group_rcu(br); + pvid = br_get_pvid(vg); + if (pvid == (vlan_tci & VLAN_VID_MASK)) + vlan_tci = 0; + + if (vlan_tci) + __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci); + + if (p) { + arp_xmit(skb); + } else { + skb_reset_mac_header(skb); + __skb_pull(skb, skb_network_offset(skb)); + skb->ip_summed = CHECKSUM_UNNECESSARY; + skb->pkt_type = PACKET_HOST; + + netif_rx_ni(skb); + } +} + +static int br_chk_addr_ip(struct net_device *dev, void *data) +{ + __be32 ip = *(__be32 *)data; + struct in_device *in_dev; + __be32 addr = 0; + + in_dev = __in_dev_get_rcu(dev); + if (in_dev) + addr = inet_confirm_addr(dev_net(dev), in_dev, 0, ip, + RT_SCOPE_HOST); + + if (addr == ip) + return 1; + + return 0; +} + +static bool br_is_local_ip(struct net_device *dev, __be32 ip) +{ + if (br_chk_addr_ip(dev, &ip)) + return true; + + /* check if ip is configured on upper dev */ + if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip, &ip)) + return true; + + return false; +} + +void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br, + u16 vid, struct net_bridge_port *p) +{ + struct net_device *dev = br->dev; + struct net_device *vlandev = dev; + struct neighbour *n; + struct arphdr *parp; + u8 *arpptr, *sha; + __be32 sip, tip; + + BR_INPUT_SKB_CB(skb)->proxyarp_replied = false; + + if ((dev->flags & IFF_NOARP) || + !pskb_may_pull(skb, arp_hdr_len(dev))) + return; + + parp = arp_hdr(skb); + + if (parp->ar_pro != htons(ETH_P_IP) || + parp->ar_hln != dev->addr_len || + parp->ar_pln != 4) + return; + + arpptr = (u8 *)parp + sizeof(struct arphdr); + sha = arpptr; + arpptr += dev->addr_len; /* sha */ + memcpy(&sip, arpptr, sizeof(sip)); + arpptr += sizeof(sip); + arpptr += dev->addr_len; /* tha */ + memcpy(&tip, arpptr, sizeof(tip)); + + if (ipv4_is_loopback(tip) || + ipv4_is_multicast(tip)) + return; + + if (br->neigh_suppress_enabled) { + if (p && (p->flags & BR_NEIGH_SUPPRESS)) + return; + if (ipv4_is_zeronet(sip) || sip == tip) { + /* prevent flooding to neigh suppress ports */ + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + return; + } + } + + if (parp->ar_op != htons(ARPOP_REQUEST)) + return; + + if (vid != 0) { + vlandev = __vlan_find_dev_deep_rcu(br->dev, skb->vlan_proto, + vid); + if (!vlandev) + return; + } + + if (br->neigh_suppress_enabled && br_is_local_ip(vlandev, tip)) { + /* its our local ip, so don't proxy reply + * and don't forward to neigh suppress ports + */ + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + return; + } + + n = neigh_lookup(&arp_tbl, &tip, vlandev); + if (n) { + struct net_bridge_fdb_entry *f; + + if (!(n->nud_state & NUD_VALID)) { + neigh_release(n); + return; + } + + f = br_fdb_find_rcu(br, n->ha, vid); + if (f) { + bool replied = false; + + if ((p && (p->flags & BR_PROXYARP)) || + (f->dst && (f->dst->flags & (BR_PROXYARP_WIFI | + BR_NEIGH_SUPPRESS)))) { + if (!vid) + br_arp_send(br, p, skb->dev, sip, tip, + sha, n->ha, sha, 0, 0); + else + br_arp_send(br, p, skb->dev, sip, tip, + sha, n->ha, sha, + skb->vlan_proto, + skb_vlan_tag_get(skb)); + replied = true; + } + + /* If we have replied or as long as we know the + * mac, indicate to arp replied + */ + if (replied || br->neigh_suppress_enabled) + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + } + + neigh_release(n); + } +} +#endif + +#if IS_ENABLED(CONFIG_IPV6) +struct nd_msg *br_is_nd_neigh_msg(struct sk_buff *skb, struct nd_msg *msg) +{ + struct nd_msg *m; + + m = skb_header_pointer(skb, skb_network_offset(skb) + + sizeof(struct ipv6hdr), sizeof(*msg), msg); + if (!m) + return NULL; + + if (m->icmph.icmp6_code != 0 || + (m->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION && + m->icmph.icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT)) + return NULL; + + return m; +} + +static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p, + struct sk_buff *request, struct neighbour *n, + __be16 vlan_proto, u16 vlan_tci, struct nd_msg *ns) +{ + struct net_device *dev = request->dev; + struct net_bridge_vlan_group *vg; + struct sk_buff *reply; + struct nd_msg *na; + struct ipv6hdr *pip6; + int na_olen = 8; /* opt hdr + ETH_ALEN for target */ + int ns_olen; + int i, len; + u8 *daddr; + u16 pvid; + + if (!dev) + return; + + len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) + + sizeof(*na) + na_olen + dev->needed_tailroom; + + reply = alloc_skb(len, GFP_ATOMIC); + if (!reply) + return; + + reply->protocol = htons(ETH_P_IPV6); + reply->dev = dev; + skb_reserve(reply, LL_RESERVED_SPACE(dev)); + skb_push(reply, sizeof(struct ethhdr)); + skb_set_mac_header(reply, 0); + + daddr = eth_hdr(request)->h_source; + + /* Do we need option processing ? */ + ns_olen = request->len - (skb_network_offset(request) + + sizeof(struct ipv6hdr)) - sizeof(*ns); + for (i = 0; i < ns_olen - 1; i += (ns->opt[i + 1] << 3)) { + if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) { + daddr = ns->opt + i + sizeof(struct nd_opt_hdr); + break; + } + } + + /* Ethernet header */ + ether_addr_copy(eth_hdr(reply)->h_dest, daddr); + ether_addr_copy(eth_hdr(reply)->h_source, n->ha); + eth_hdr(reply)->h_proto = htons(ETH_P_IPV6); + reply->protocol = htons(ETH_P_IPV6); + + skb_pull(reply, sizeof(struct ethhdr)); + skb_set_network_header(reply, 0); + skb_put(reply, sizeof(struct ipv6hdr)); + + /* IPv6 header */ + pip6 = ipv6_hdr(reply); + memset(pip6, 0, sizeof(struct ipv6hdr)); + pip6->version = 6; + pip6->priority = ipv6_hdr(request)->priority; + pip6->nexthdr = IPPROTO_ICMPV6; + pip6->hop_limit = 255; + pip6->daddr = ipv6_hdr(request)->saddr; + pip6->saddr = *(struct in6_addr *)n->primary_key; + + skb_pull(reply, sizeof(struct ipv6hdr)); + skb_set_transport_header(reply, 0); + + na = (struct nd_msg *)skb_put(reply, sizeof(*na) + na_olen); + + /* Neighbor Advertisement */ + memset(na, 0, sizeof(*na) + na_olen); + na->icmph.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT; + na->icmph.icmp6_router = 0; /* XXX: should be 1 ? */ + na->icmph.icmp6_override = 1; + na->icmph.icmp6_solicited = 1; + na->target = ns->target; + ether_addr_copy(&na->opt[2], n->ha); + na->opt[0] = ND_OPT_TARGET_LL_ADDR; + na->opt[1] = na_olen >> 3; + + na->icmph.icmp6_cksum = csum_ipv6_magic(&pip6->saddr, + &pip6->daddr, + sizeof(*na) + na_olen, + IPPROTO_ICMPV6, + csum_partial(na, sizeof(*na) + na_olen, 0)); + + pip6->payload_len = htons(sizeof(*na) + na_olen); + + skb_push(reply, sizeof(struct ipv6hdr)); + skb_push(reply, sizeof(struct ethhdr)); + + reply->ip_summed = CHECKSUM_UNNECESSARY; + + if (p) + vg = nbp_vlan_group_rcu(p); + else + vg = br_vlan_group_rcu(br); + pvid = br_get_pvid(vg); + if (pvid == (vlan_tci & VLAN_VID_MASK)) + vlan_tci = 0; + + if (vlan_tci) + __vlan_hwaccel_put_tag(reply, vlan_proto, vlan_tci); + + netdev_dbg(dev, "nd send dev %s dst %pI6 dst_hw %pM src %pI6 src_hw %pM\n", + dev->name, &pip6->daddr, daddr, &pip6->saddr, n->ha); + + if (p) { + dev_queue_xmit(reply); + } else { + skb_reset_mac_header(reply); + __skb_pull(reply, skb_network_offset(reply)); + reply->ip_summed = CHECKSUM_UNNECESSARY; + reply->pkt_type = PACKET_HOST; + + netif_rx_ni(reply); + } +} + +static int br_chk_addr_ip6(struct net_device *dev, void *data) +{ + struct in6_addr *addr = (struct in6_addr *)data; + + if (ipv6_chk_addr(dev_net(dev), addr, dev, 0)) + return 1; + + return 0; +} + +static bool br_is_local_ip6(struct net_device *dev, struct in6_addr *addr) + +{ + if (br_chk_addr_ip6(dev, addr)) + return true; + + /* check if ip is configured on upper dev */ + if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip6, addr)) + return true; + + return false; +} + +void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br, + u16 vid, struct net_bridge_port *p, struct nd_msg *msg) +{ + struct net_device *dev = br->dev; + struct net_device *vlandev = NULL; + struct in6_addr *saddr, *daddr; + struct ipv6hdr *iphdr; + struct neighbour *n; + + BR_INPUT_SKB_CB(skb)->proxyarp_replied = false; + + if (p && (p->flags & BR_NEIGH_SUPPRESS)) + return; + + if (msg->icmph.icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT && + !msg->icmph.icmp6_solicited) { + /* prevent flooding to neigh suppress ports */ + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + return; + } + + if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION) + return; + + iphdr = ipv6_hdr(skb); + saddr = &iphdr->saddr; + daddr = &iphdr->daddr; + + if (ipv6_addr_any(saddr) || !ipv6_addr_cmp(saddr, daddr)) { + /* prevent flooding to neigh suppress ports */ + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + return; + } + + if (vid != 0) { + /* build neigh table lookup on the vlan device */ + vlandev = __vlan_find_dev_deep_rcu(br->dev, skb->vlan_proto, + vid); + if (!vlandev) + return; + } else { + vlandev = dev; + } + + if (br_is_local_ip6(vlandev, &msg->target)) { + /* its our own ip, so don't proxy reply + * and don't forward to arp suppress ports + */ + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + return; + } + + n = neigh_lookup(ipv6_stub->nd_tbl, &msg->target, vlandev); + if (n) { + struct net_bridge_fdb_entry *f; + + if (!(n->nud_state & NUD_VALID)) { + neigh_release(n); + return; + } + + f = br_fdb_find_rcu(br, n->ha, vid); + if (f) { + bool replied = false; + + if (f->dst && (f->dst->flags & BR_NEIGH_SUPPRESS)) { + if (vid != 0) + br_nd_send(br, p, skb, n, + skb->vlan_proto, + skb_vlan_tag_get(skb), msg); + else + br_nd_send(br, p, skb, n, 0, 0, msg); + replied = true; + } + + /* If we have replied or as long as we know the + * mac, indicate to NEIGH_SUPPRESS ports that we + * have replied + */ + if (replied || br->neigh_suppress_enabled) + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + } + neigh_release(n); + } +} +#endif diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index f6b6a92f1c48..af5b8c87f590 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -39,6 +39,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats); const struct nf_br_ops *nf_ops; const unsigned char *dest; + struct ethhdr *eth; u16 vid = 0; rcu_read_lock(); @@ -57,11 +58,30 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) BR_INPUT_SKB_CB(skb)->brdev = dev; skb_reset_mac_header(skb); + eth = eth_hdr(skb); skb_pull(skb, ETH_HLEN); if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid)) goto out; + if (IS_ENABLED(CONFIG_INET) && + (eth->h_proto == htons(ETH_P_ARP) || + eth->h_proto == htons(ETH_P_RARP)) && + br->neigh_suppress_enabled) { + br_do_proxy_suppress_arp(skb, br, vid, NULL); + } else if (IS_ENABLED(CONFIG_IPV6) && + skb->protocol == htons(ETH_P_IPV6) && + br->neigh_suppress_enabled && + pskb_may_pull(skb, sizeof(struct ipv6hdr) + + sizeof(struct nd_msg)) && + ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) { + struct nd_msg *msg, _msg; + + msg = br_is_nd_neigh_msg(skb, &_msg); + if (msg) + br_do_suppress_nd(skb, br, vid, NULL, msg); + } + dest = eth_hdr(skb)->h_dest; if (is_broadcast_ether_addr(dest)) { br_flood(br, skb, BR_PKT_BROADCAST, false, true); @@ -320,12 +340,13 @@ void br_netpoll_disable(struct net_bridge_port *p) #endif -static int br_add_slave(struct net_device *dev, struct net_device *slave_dev) +static int br_add_slave(struct net_device *dev, struct net_device *slave_dev, + struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(dev); - return br_add_if(br, slave_dev); + return br_add_if(br, slave_dev, extack); } static int br_del_slave(struct net_device *dev, struct net_device *slave_dev) @@ -400,7 +421,7 @@ void br_dev_setup(struct net_device *dev) br->bridge_id.prio[0] = 0x80; br->bridge_id.prio[1] = 0x00; - ether_addr_copy(br->group_addr, eth_reserved_addr_base); + ether_addr_copy(br->group_addr, eth_stp_addr); br->stp_enabled = BR_NO_STP; br->group_fwd_mask = BR_GROUPFWD_DEFAULT; diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 48fb17417fac..b4eed113d2ec 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -204,7 +204,7 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb, /* Do not flood to ports that enable proxy ARP */ if (p->flags & BR_PROXYARP) continue; - if ((p->flags & BR_PROXYARP_WIFI) && + if ((p->flags & (BR_PROXYARP_WIFI | BR_NEIGH_SUPPRESS)) && BR_INPUT_SKB_CB(skb)->proxyarp_replied) continue; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index f3aef22931ab..9ba4ed65c52b 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -271,7 +271,7 @@ static void del_nbp(struct net_bridge_port *p) br_stp_disable_port(p); spin_unlock_bh(&br->lock); - br_ifinfo_notify(RTM_DELLINK, p); + br_ifinfo_notify(RTM_DELLINK, NULL, p); list_del_rcu(&p->list); if (netdev_get_fwd_headroom(dev) == br->dev->needed_headroom) @@ -310,6 +310,8 @@ void br_dev_delete(struct net_device *dev, struct list_head *head) del_nbp(p); } + br_recalculate_neigh_suppress_enabled(br); + br_fdb_delete_by_port(br, NULL, 0, 1); cancel_delayed_work_sync(&br->gc_work); @@ -480,7 +482,8 @@ netdev_features_t br_features_recompute(struct net_bridge *br, } /* called with RTNL */ -int br_add_if(struct net_bridge *br, struct net_device *dev) +int br_add_if(struct net_bridge *br, struct net_device *dev, + struct netlink_ext_ack *extack) { struct net_bridge_port *p; int err = 0; @@ -500,16 +503,22 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) return -EINVAL; /* No bridging of bridges */ - if (dev->netdev_ops->ndo_start_xmit == br_dev_xmit) + if (dev->netdev_ops->ndo_start_xmit == br_dev_xmit) { + NL_SET_ERR_MSG(extack, + "Can not enslave a bridge to a bridge"); return -ELOOP; + } /* Device is already being bridged */ if (br_port_exists(dev)) return -EBUSY; /* No bridging devices that dislike that (e.g. wireless) */ - if (dev->priv_flags & IFF_DONT_BRIDGE) + if (dev->priv_flags & IFF_DONT_BRIDGE) { + NL_SET_ERR_MSG(extack, + "Device does not allow enslaving to a bridge"); return -EOPNOTSUPP; + } p = new_nbp(br, dev); if (IS_ERR(p)) @@ -540,7 +549,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) dev->priv_flags |= IFF_BRIDGE_PORT; - err = netdev_master_upper_dev_link(dev, br->dev, NULL, NULL); + err = netdev_master_upper_dev_link(dev, br->dev, NULL, NULL, extack); if (err) goto err5; @@ -580,7 +589,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) br_stp_enable_port(p); spin_unlock_bh(&br->lock); - br_ifinfo_notify(RTM_NEWLINK, p); + br_ifinfo_notify(RTM_NEWLINK, NULL, p); if (changed_addr) call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev); @@ -653,4 +662,7 @@ void br_port_flags_change(struct net_bridge_port *p, unsigned long mask) if (mask & BR_AUTO_MASK) nbp_update_port_count(br); + + if (mask & BR_NEIGH_SUPPRESS) + br_recalculate_neigh_suppress_enabled(br); } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 7637f58c1226..7f98a7d25866 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -71,62 +71,6 @@ static int br_pass_frame_up(struct sk_buff *skb) br_netif_receive_skb); } -static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br, - u16 vid, struct net_bridge_port *p) -{ - struct net_device *dev = br->dev; - struct neighbour *n; - struct arphdr *parp; - u8 *arpptr, *sha; - __be32 sip, tip; - - BR_INPUT_SKB_CB(skb)->proxyarp_replied = false; - - if ((dev->flags & IFF_NOARP) || - !pskb_may_pull(skb, arp_hdr_len(dev))) - return; - - parp = arp_hdr(skb); - - if (parp->ar_pro != htons(ETH_P_IP) || - parp->ar_op != htons(ARPOP_REQUEST) || - parp->ar_hln != dev->addr_len || - parp->ar_pln != 4) - return; - - arpptr = (u8 *)parp + sizeof(struct arphdr); - sha = arpptr; - arpptr += dev->addr_len; /* sha */ - memcpy(&sip, arpptr, sizeof(sip)); - arpptr += sizeof(sip); - arpptr += dev->addr_len; /* tha */ - memcpy(&tip, arpptr, sizeof(tip)); - - if (ipv4_is_loopback(tip) || - ipv4_is_multicast(tip)) - return; - - n = neigh_lookup(&arp_tbl, &tip, dev); - if (n) { - struct net_bridge_fdb_entry *f; - - if (!(n->nud_state & NUD_VALID)) { - neigh_release(n); - return; - } - - f = br_fdb_find_rcu(br, n->ha, vid); - if (f && ((p->flags & BR_PROXYARP) || - (f->dst && (f->dst->flags & BR_PROXYARP_WIFI)))) { - arp_send(ARPOP_REPLY, ETH_P_ARP, sip, skb->dev, tip, - sha, n->ha, sha); - BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; - } - - neigh_release(n); - } -} - /* note: already called with rcu_read_lock */ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { @@ -171,15 +115,29 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb BR_INPUT_SKB_CB(skb)->brdev = br->dev; - if (IS_ENABLED(CONFIG_INET) && skb->protocol == htons(ETH_P_ARP)) - br_do_proxy_arp(skb, br, vid, p); + if (IS_ENABLED(CONFIG_INET) && + (skb->protocol == htons(ETH_P_ARP) || + skb->protocol == htons(ETH_P_RARP))) { + br_do_proxy_suppress_arp(skb, br, vid, p); + } else if (IS_ENABLED(CONFIG_IPV6) && + skb->protocol == htons(ETH_P_IPV6) && + br->neigh_suppress_enabled && + pskb_may_pull(skb, sizeof(struct ipv6hdr) + + sizeof(struct nd_msg)) && + ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) { + struct nd_msg *msg, _msg; + + msg = br_is_nd_neigh_msg(skb, &_msg); + if (msg) + br_do_suppress_nd(skb, br, vid, p, msg); + } switch (pkt_type) { case BR_PKT_MULTICAST: mdst = br_mdb_get(br, skb, vid); if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) && br_multicast_querier_exists(br, eth_hdr(skb))) { - if ((mdst && mdst->mglist) || + if ((mdst && mdst->host_joined) || br_multicast_is_router(br)) { local_rcv = true; br->dev->stats.multicast++; @@ -289,6 +247,7 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb) * * Others reserved for future standardization */ + fwd_mask |= p->group_fwd_mask; switch (dest[5]) { case 0x00: /* Bridge Group Address */ /* If STP is turned off, diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c index 7970f8540cbb..73b957fd639d 100644 --- a/net/bridge/br_ioctl.c +++ b/net/bridge/br_ioctl.c @@ -98,7 +98,7 @@ static int add_del_if(struct net_bridge *br, int ifindex, int isadd) return -EINVAL; if (isadd) - ret = br_add_if(br, dev); + ret = br_add_if(br, dev, NULL); else ret = br_del_if(br, dev); @@ -293,7 +293,7 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) if (!ret) { if (p) - br_ifinfo_notify(RTM_NEWLINK, p); + br_ifinfo_notify(RTM_NEWLINK, NULL, p); else netdev_state_change(br->dev); } diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 31ddff22563e..b0f4c734900b 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -292,6 +292,46 @@ err: kfree(priv); } +static void br_mdb_switchdev_host_port(struct net_device *dev, + struct net_device *lower_dev, + struct br_mdb_entry *entry, int type) +{ + struct switchdev_obj_port_mdb mdb = { + .obj = { + .id = SWITCHDEV_OBJ_ID_HOST_MDB, + .flags = SWITCHDEV_F_DEFER, + }, + .vid = entry->vid, + }; + + if (entry->addr.proto == htons(ETH_P_IP)) + ip_eth_mc_map(entry->addr.u.ip4, mdb.addr); +#if IS_ENABLED(CONFIG_IPV6) + else + ipv6_eth_mc_map(&entry->addr.u.ip6, mdb.addr); +#endif + + mdb.obj.orig_dev = dev; + switch (type) { + case RTM_NEWMDB: + switchdev_port_obj_add(lower_dev, &mdb.obj); + break; + case RTM_DELMDB: + switchdev_port_obj_del(lower_dev, &mdb.obj); + break; + } +} + +static void br_mdb_switchdev_host(struct net_device *dev, + struct br_mdb_entry *entry, int type) +{ + struct net_device *lower_dev; + struct list_head *iter; + + netdev_for_each_lower_dev(dev, lower_dev, iter) + br_mdb_switchdev_host_port(dev, lower_dev, entry, type); +} + static void __br_mdb_notify(struct net_device *dev, struct net_bridge_port *p, struct br_mdb_entry *entry, int type) { @@ -317,7 +357,7 @@ static void __br_mdb_notify(struct net_device *dev, struct net_bridge_port *p, #endif mdb.obj.orig_dev = port_dev; - if (port_dev && type == RTM_NEWMDB) { + if (p && port_dev && type == RTM_NEWMDB) { complete_info = kmalloc(sizeof(*complete_info), GFP_ATOMIC); if (complete_info) { complete_info->port = p; @@ -327,10 +367,13 @@ static void __br_mdb_notify(struct net_device *dev, struct net_bridge_port *p, if (switchdev_port_obj_add(port_dev, &mdb.obj)) kfree(complete_info); } - } else if (port_dev && type == RTM_DELMDB) { + } else if (p && port_dev && type == RTM_DELMDB) { switchdev_port_obj_del(port_dev, &mdb.obj); } + if (!p) + br_mdb_switchdev_host(dev, entry, type); + skb = nlmsg_new(rtnl_mdb_nlmsg_size(), GFP_ATOMIC); if (!skb) goto errout; @@ -353,7 +396,10 @@ void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, struct br_mdb_entry entry; memset(&entry, 0, sizeof(entry)); - entry.ifindex = port->dev->ifindex; + if (port) + entry.ifindex = port->dev->ifindex; + else + entry.ifindex = dev->ifindex; entry.addr.proto = group->proto; entry.addr.u.ip4 = group->u.ip4; #if IS_ENABLED(CONFIG_IPV6) @@ -655,7 +701,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) call_rcu_bh(&p->rcu, br_multicast_free_pg); err = 0; - if (!mp->ports && !mp->mglist && + if (!mp->ports && !mp->host_joined && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); break; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 8dc5c8d69bcd..cb4729539b82 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -239,9 +239,9 @@ static void br_multicast_free_group(struct rcu_head *head) kfree(mp); } -static void br_multicast_group_expired(unsigned long data) +static void br_multicast_group_expired(struct timer_list *t) { - struct net_bridge_mdb_entry *mp = (void *)data; + struct net_bridge_mdb_entry *mp = from_timer(mp, t, timer); struct net_bridge *br = mp->br; struct net_bridge_mdb_htable *mdb; @@ -249,7 +249,8 @@ static void br_multicast_group_expired(unsigned long data) if (!netif_running(br->dev) || timer_pending(&mp->timer)) goto out; - mp->mglist = false; + mp->host_joined = false; + br_mdb_notify(br->dev, NULL, &mp->addr, RTM_DELMDB, 0); if (mp->ports) goto out; @@ -292,7 +293,7 @@ static void br_multicast_del_pg(struct net_bridge *br, p->flags); call_rcu_bh(&p->rcu, br_multicast_free_pg); - if (!mp->ports && !mp->mglist && + if (!mp->ports && !mp->host_joined && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); @@ -302,9 +303,9 @@ static void br_multicast_del_pg(struct net_bridge *br, WARN_ON(1); } -static void br_multicast_port_group_expired(unsigned long data) +static void br_multicast_port_group_expired(struct timer_list *t) { - struct net_bridge_port_group *pg = (void *)data; + struct net_bridge_port_group *pg = from_timer(pg, t, timer); struct net_bridge *br = pg->port->br; spin_lock(&br->multicast_lock); @@ -701,8 +702,7 @@ rehash: mp->br = br; mp->addr = *group; - setup_timer(&mp->timer, br_multicast_group_expired, - (unsigned long)mp); + timer_setup(&mp->timer, br_multicast_group_expired, 0); hlist_add_head_rcu(&mp->hlist[mdb->ver], &mdb->mhash[hash]); mdb->size++; @@ -729,8 +729,7 @@ struct net_bridge_port_group *br_multicast_new_port_group( p->flags = flags; rcu_assign_pointer(p->next, next); hlist_add_head(&p->mglist, &port->mglist); - setup_timer(&p->timer, br_multicast_port_group_expired, - (unsigned long)p); + timer_setup(&p->timer, br_multicast_port_group_expired, 0); if (src) memcpy(p->eth_addr, src, ETH_ALEN); @@ -775,7 +774,10 @@ static int br_multicast_add_group(struct net_bridge *br, goto err; if (!port) { - mp->mglist = true; + if (!mp->host_joined) { + mp->host_joined = true; + br_mdb_notify(br->dev, NULL, &mp->addr, RTM_NEWMDB, 0); + } mod_timer(&mp->timer, now + br->multicast_membership_interval); goto out; } @@ -843,9 +845,10 @@ static int br_ip6_multicast_add_group(struct net_bridge *br, } #endif -static void br_multicast_router_expired(unsigned long data) +static void br_multicast_router_expired(struct timer_list *t) { - struct net_bridge_port *port = (void *)data; + struct net_bridge_port *port = + from_timer(port, t, multicast_router_timer); struct net_bridge *br = port->br; spin_lock(&br->multicast_lock); @@ -859,8 +862,32 @@ out: spin_unlock(&br->multicast_lock); } -static void br_multicast_local_router_expired(unsigned long data) +static void br_mc_router_state_change(struct net_bridge *p, + bool is_mc_router) +{ + struct switchdev_attr attr = { + .orig_dev = p->dev, + .id = SWITCHDEV_ATTR_ID_BRIDGE_MROUTER, + .flags = SWITCHDEV_F_DEFER, + .u.mrouter = is_mc_router, + }; + + switchdev_port_attr_set(p->dev, &attr); +} + +static void br_multicast_local_router_expired(struct timer_list *t) { + struct net_bridge *br = from_timer(br, t, multicast_router_timer); + + spin_lock(&br->multicast_lock); + if (br->multicast_router == MDB_RTR_TYPE_DISABLED || + br->multicast_router == MDB_RTR_TYPE_PERM || + timer_pending(&br->multicast_router_timer)) + goto out; + + br_mc_router_state_change(br, false); +out: + spin_unlock(&br->multicast_lock); } static void br_multicast_querier_expired(struct net_bridge *br, @@ -876,17 +903,17 @@ out: spin_unlock(&br->multicast_lock); } -static void br_ip4_multicast_querier_expired(unsigned long data) +static void br_ip4_multicast_querier_expired(struct timer_list *t) { - struct net_bridge *br = (void *)data; + struct net_bridge *br = from_timer(br, t, ip4_other_query.timer); br_multicast_querier_expired(br, &br->ip4_own_query); } #if IS_ENABLED(CONFIG_IPV6) -static void br_ip6_multicast_querier_expired(unsigned long data) +static void br_ip6_multicast_querier_expired(struct timer_list *t) { - struct net_bridge *br = (void *)data; + struct net_bridge *br = from_timer(br, t, ip6_other_query.timer); br_multicast_querier_expired(br, &br->ip6_own_query); } @@ -987,17 +1014,17 @@ out: spin_unlock(&br->multicast_lock); } -static void br_ip4_multicast_port_query_expired(unsigned long data) +static void br_ip4_multicast_port_query_expired(struct timer_list *t) { - struct net_bridge_port *port = (void *)data; + struct net_bridge_port *port = from_timer(port, t, ip4_own_query.timer); br_multicast_port_query_expired(port, &port->ip4_own_query); } #if IS_ENABLED(CONFIG_IPV6) -static void br_ip6_multicast_port_query_expired(unsigned long data) +static void br_ip6_multicast_port_query_expired(struct timer_list *t) { - struct net_bridge_port *port = (void *)data; + struct net_bridge_port *port = from_timer(port, t, ip6_own_query.timer); br_multicast_port_query_expired(port, &port->ip6_own_query); } @@ -1019,13 +1046,13 @@ int br_multicast_add_port(struct net_bridge_port *port) { port->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; - setup_timer(&port->multicast_router_timer, br_multicast_router_expired, - (unsigned long)port); - setup_timer(&port->ip4_own_query.timer, - br_ip4_multicast_port_query_expired, (unsigned long)port); + timer_setup(&port->multicast_router_timer, + br_multicast_router_expired, 0); + timer_setup(&port->ip4_own_query.timer, + br_ip4_multicast_port_query_expired, 0); #if IS_ENABLED(CONFIG_IPV6) - setup_timer(&port->ip6_own_query.timer, - br_ip6_multicast_port_query_expired, (unsigned long)port); + timer_setup(&port->ip6_own_query.timer, + br_ip6_multicast_port_query_expired, 0); #endif br_mc_disabled_update(port->dev, port->br->multicast_disabled); @@ -1364,9 +1391,12 @@ static void br_multicast_mark_router(struct net_bridge *br, unsigned long now = jiffies; if (!port) { - if (br->multicast_router == MDB_RTR_TYPE_TEMP_QUERY) + if (br->multicast_router == MDB_RTR_TYPE_TEMP_QUERY) { + if (!timer_pending(&br->multicast_router_timer)) + br_mc_router_state_change(br, true); mod_timer(&br->multicast_router_timer, now + br->multicast_querier_interval); + } return; } @@ -1451,7 +1481,7 @@ static int br_ip4_multicast_query(struct net_bridge *br, max_delay *= br->multicast_last_member_count; - if (mp->mglist && + if (mp->host_joined && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, now + max_delay) : try_to_del_timer_sync(&mp->timer) >= 0)) @@ -1535,7 +1565,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, goto out; max_delay *= br->multicast_last_member_count; - if (mp->mglist && + if (mp->host_joined && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, now + max_delay) : try_to_del_timer_sync(&mp->timer) >= 0)) @@ -1596,7 +1626,7 @@ br_multicast_leave_group(struct net_bridge *br, br_mdb_notify(br->dev, port, group, RTM_DELMDB, p->flags); - if (!mp->ports && !mp->mglist && + if (!mp->ports && !mp->host_joined && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); } @@ -1636,7 +1666,7 @@ br_multicast_leave_group(struct net_bridge *br, br->multicast_last_member_interval; if (!port) { - if (mp->mglist && + if (mp->host_joined && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, time) : try_to_del_timer_sync(&mp->timer) >= 0)) { @@ -1906,17 +1936,17 @@ static void br_multicast_query_expired(struct net_bridge *br, spin_unlock(&br->multicast_lock); } -static void br_ip4_multicast_query_expired(unsigned long data) +static void br_ip4_multicast_query_expired(struct timer_list *t) { - struct net_bridge *br = (void *)data; + struct net_bridge *br = from_timer(br, t, ip4_own_query.timer); br_multicast_query_expired(br, &br->ip4_own_query, &br->ip4_querier); } #if IS_ENABLED(CONFIG_IPV6) -static void br_ip6_multicast_query_expired(unsigned long data) +static void br_ip6_multicast_query_expired(struct timer_list *t) { - struct net_bridge *br = (void *)data; + struct net_bridge *br = from_timer(br, t, ip6_own_query.timer); br_multicast_query_expired(br, &br->ip6_own_query, &br->ip6_querier); } @@ -1951,17 +1981,17 @@ void br_multicast_init(struct net_bridge *br) br->has_ipv6_addr = 1; spin_lock_init(&br->multicast_lock); - setup_timer(&br->multicast_router_timer, + timer_setup(&br->multicast_router_timer, br_multicast_local_router_expired, 0); - setup_timer(&br->ip4_other_query.timer, - br_ip4_multicast_querier_expired, (unsigned long)br); - setup_timer(&br->ip4_own_query.timer, br_ip4_multicast_query_expired, - (unsigned long)br); + timer_setup(&br->ip4_other_query.timer, + br_ip4_multicast_querier_expired, 0); + timer_setup(&br->ip4_own_query.timer, + br_ip4_multicast_query_expired, 0); #if IS_ENABLED(CONFIG_IPV6) - setup_timer(&br->ip6_other_query.timer, - br_ip6_multicast_querier_expired, (unsigned long)br); - setup_timer(&br->ip6_own_query.timer, br_ip6_multicast_query_expired, - (unsigned long)br); + timer_setup(&br->ip6_other_query.timer, + br_ip6_multicast_querier_expired, 0); + timer_setup(&br->ip6_own_query.timer, + br_ip6_multicast_query_expired, 0); #endif } @@ -2042,9 +2072,14 @@ int br_multicast_set_router(struct net_bridge *br, unsigned long val) switch (val) { case MDB_RTR_TYPE_DISABLED: case MDB_RTR_TYPE_PERM: + br_mc_router_state_change(br, val == MDB_RTR_TYPE_PERM); del_timer(&br->multicast_router_timer); - /* fall through */ + br->multicast_router = val; + err = 0; + break; case MDB_RTR_TYPE_TEMP_QUERY: + if (br->multicast_router != MDB_RTR_TYPE_TEMP_QUERY) + br_mc_router_state_change(br, false); br->multicast_router = val; err = 0; break; @@ -2184,6 +2219,18 @@ bool br_multicast_enabled(const struct net_device *dev) } EXPORT_SYMBOL_GPL(br_multicast_enabled); +bool br_multicast_router(const struct net_device *dev) +{ + struct net_bridge *br = netdev_priv(dev); + bool is_router; + + spin_lock_bh(&br->multicast_lock); + is_router = br_multicast_is_router(br); + spin_unlock_bh(&br->multicast_lock); + return is_router; +} +EXPORT_SYMBOL_GPL(br_multicast_router); + int br_multicast_set_querier(struct net_bridge *br, unsigned long val) { unsigned long max_delay; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index de2152730809..d0ef0a8e8831 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -138,6 +138,7 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_PROXYARP */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */ + nla_total_size(1) /* IFLA_BRPORT_VLAN_TUNNEL */ + + nla_total_size(1) /* IFLA_BRPORT_NEIGH_SUPPRESS */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */ @@ -152,6 +153,7 @@ static inline size_t br_port_info_size(void) #ifdef CONFIG_BRIDGE_IGMP_SNOOPING + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MULTICAST_ROUTER */ #endif + + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_GROUP_FWD_MASK */ + 0; } @@ -208,7 +210,10 @@ static int br_port_fill_attrs(struct sk_buff *skb, p->topology_change_ack) || nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, p->config_pending) || nla_put_u8(skb, IFLA_BRPORT_VLAN_TUNNEL, !!(p->flags & - BR_VLAN_TUNNEL))) + BR_VLAN_TUNNEL)) || + nla_put_u16(skb, IFLA_BRPORT_GROUP_FWD_MASK, p->group_fwd_mask) || + nla_put_u8(skb, IFLA_BRPORT_NEIGH_SUPPRESS, + !!(p->flags & BR_NEIGH_SUPPRESS))) return -EMSGSIZE; timerval = br_timer_value(&p->message_age_timer); @@ -356,14 +361,14 @@ nla_put_failure: * Contains port and master info as well as carrier and bridge state. */ static int br_fill_ifinfo(struct sk_buff *skb, - struct net_bridge_port *port, + const struct net_bridge_port *port, u32 pid, u32 seq, int event, unsigned int flags, u32 filter_mask, const struct net_device *dev) { + u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; struct net_bridge *br; struct ifinfomsg *hdr; struct nlmsghdr *nlh; - u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; if (port) br = port->br; @@ -449,28 +454,36 @@ nla_put_failure: return -EMSGSIZE; } -/* - * Notify listeners of a change in port information - */ -void br_ifinfo_notify(int event, struct net_bridge_port *port) +/* Notify listeners of a change in bridge or port information */ +void br_ifinfo_notify(int event, const struct net_bridge *br, + const struct net_bridge_port *port) { - struct net *net; + u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED; + struct net_device *dev; struct sk_buff *skb; int err = -ENOBUFS; - u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED; + struct net *net; + u16 port_no = 0; - if (!port) + if (WARN_ON(!port && !br)) return; - net = dev_net(port->dev); - br_debug(port->br, "port %u(%s) event %d\n", - (unsigned int)port->port_no, port->dev->name, event); + if (port) { + dev = port->dev; + br = port->br; + port_no = port->port_no; + } else { + dev = br->dev; + } + + net = dev_net(dev); + br_debug(br, "port %u(%s) event %d\n", port_no, dev->name, event); - skb = nlmsg_new(br_nlmsg_size(port->dev, filter), GFP_ATOMIC); + skb = nlmsg_new(br_nlmsg_size(dev, filter), GFP_ATOMIC); if (skb == NULL) goto errout; - err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, port->dev); + err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, dev); if (err < 0) { /* -EMSGSIZE implies BUG in br_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -483,7 +496,6 @@ errout: rtnl_set_sk_err(net, RTNLGRP_LINK, err); } - /* * Dump information about all ports, in response to GETLINK */ @@ -501,8 +513,9 @@ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, } static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p, - int cmd, struct bridge_vlan_info *vinfo) + int cmd, struct bridge_vlan_info *vinfo, bool *changed) { + bool curr_change; int err = 0; switch (cmd) { @@ -511,22 +524,27 @@ static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p, /* if the MASTER flag is set this will act on the global * per-VLAN entry as well */ - err = nbp_vlan_add(p, vinfo->vid, vinfo->flags); - if (err) - break; + err = nbp_vlan_add(p, vinfo->vid, vinfo->flags, + &curr_change); } else { vinfo->flags |= BRIDGE_VLAN_INFO_BRENTRY; - err = br_vlan_add(br, vinfo->vid, vinfo->flags); + err = br_vlan_add(br, vinfo->vid, vinfo->flags, + &curr_change); } + if (curr_change) + *changed = true; break; case RTM_DELLINK: if (p) { - nbp_vlan_delete(p, vinfo->vid); - if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER) - br_vlan_delete(p->br, vinfo->vid); - } else { - br_vlan_delete(br, vinfo->vid); + if (!nbp_vlan_delete(p, vinfo->vid)) + *changed = true; + + if ((vinfo->flags & BRIDGE_VLAN_INFO_MASTER) && + !br_vlan_delete(p->br, vinfo->vid)) + *changed = true; + } else if (!br_vlan_delete(br, vinfo->vid)) { + *changed = true; } break; } @@ -537,7 +555,8 @@ static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p, static int br_process_vlan_info(struct net_bridge *br, struct net_bridge_port *p, int cmd, struct bridge_vlan_info *vinfo_curr, - struct bridge_vlan_info **vinfo_last) + struct bridge_vlan_info **vinfo_last, + bool *changed) { if (!vinfo_curr->vid || vinfo_curr->vid >= VLAN_VID_MASK) return -EINVAL; @@ -567,7 +586,7 @@ static int br_process_vlan_info(struct net_bridge *br, sizeof(struct bridge_vlan_info)); for (v = (*vinfo_last)->vid; v <= vinfo_curr->vid; v++) { tmp_vinfo.vid = v; - err = br_vlan_info(br, p, cmd, &tmp_vinfo); + err = br_vlan_info(br, p, cmd, &tmp_vinfo, changed); if (err) break; } @@ -576,13 +595,13 @@ static int br_process_vlan_info(struct net_bridge *br, return err; } - return br_vlan_info(br, p, cmd, vinfo_curr); + return br_vlan_info(br, p, cmd, vinfo_curr, changed); } static int br_afspec(struct net_bridge *br, struct net_bridge_port *p, struct nlattr *af_spec, - int cmd) + int cmd, bool *changed) { struct bridge_vlan_info *vinfo_curr = NULL; struct bridge_vlan_info *vinfo_last = NULL; @@ -602,7 +621,8 @@ static int br_afspec(struct net_bridge *br, return err; err = br_process_vlan_tunnel_info(br, p, cmd, &tinfo_curr, - &tinfo_last); + &tinfo_last, + changed); if (err) return err; break; @@ -611,7 +631,7 @@ static int br_afspec(struct net_bridge *br, return -EINVAL; vinfo_curr = nla_data(attr); err = br_process_vlan_info(br, p, cmd, vinfo_curr, - &vinfo_last); + &vinfo_last, changed); if (err) return err; break; @@ -637,6 +657,9 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_MCAST_TO_UCAST] = { .type = NLA_U8 }, [IFLA_BRPORT_MCAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_BCAST_FLOOD] = { .type = NLA_U8 }, + [IFLA_BRPORT_VLAN_TUNNEL] = { .type = NLA_U8 }, + [IFLA_BRPORT_GROUP_FWD_MASK] = { .type = NLA_U16 }, + [IFLA_BRPORT_NEIGH_SUPPRESS] = { .type = NLA_U8 }, }; /* Change the state of the port and notify spanning tree */ @@ -773,6 +796,20 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) return err; } #endif + + if (tb[IFLA_BRPORT_GROUP_FWD_MASK]) { + u16 fwd_mask = nla_get_u16(tb[IFLA_BRPORT_GROUP_FWD_MASK]); + + if (fwd_mask & BR_GROUPFWD_MACPAUSE) + return -EINVAL; + p->group_fwd_mask = fwd_mask; + } + + err = br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_SUPPRESS, + BR_NEIGH_SUPPRESS); + if (err) + return err; + br_port_flags_change(p, old_flags ^ p->flags); return 0; } @@ -780,10 +817,12 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) /* Change state and parameters on port. */ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) { + struct net_bridge *br = (struct net_bridge *)netdev_priv(dev); + struct nlattr *tb[IFLA_BRPORT_MAX + 1]; + struct net_bridge_port *p; struct nlattr *protinfo; struct nlattr *afspec; - struct net_bridge_port *p; - struct nlattr *tb[IFLA_BRPORT_MAX + 1]; + bool changed = false; int err = 0; protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_PROTINFO); @@ -819,15 +858,14 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) } if (err) goto out; + changed = true; } - if (afspec) { - err = br_afspec((struct net_bridge *)netdev_priv(dev), p, - afspec, RTM_SETLINK); - } + if (afspec) + err = br_afspec(br, p, afspec, RTM_SETLINK, &changed); - if (err == 0) - br_ifinfo_notify(RTM_NEWLINK, p); + if (changed) + br_ifinfo_notify(RTM_NEWLINK, br, p); out: return err; } @@ -835,8 +873,10 @@ out: /* Delete port information */ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) { - struct nlattr *afspec; + struct net_bridge *br = (struct net_bridge *)netdev_priv(dev); struct net_bridge_port *p; + struct nlattr *afspec; + bool changed = false; int err = 0; afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); @@ -848,13 +888,12 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) if (!p && !(dev->priv_flags & IFF_EBRIDGE)) return -EINVAL; - err = br_afspec((struct net_bridge *)netdev_priv(dev), p, - afspec, RTM_DELLINK); - if (err == 0) + err = br_afspec(br, p, afspec, RTM_DELLINK, &changed); + if (changed) /* Send RTM_NEWLINK because userspace * expects RTM_NEWLINK for vlan dels */ - br_ifinfo_notify(RTM_NEWLINK, p); + br_ifinfo_notify(RTM_NEWLINK, br, p); return err; } diff --git a/net/bridge/br_netlink_tunnel.c b/net/bridge/br_netlink_tunnel.c index 3712c7f0e00c..da8cb99fd259 100644 --- a/net/bridge/br_netlink_tunnel.c +++ b/net/bridge/br_netlink_tunnel.c @@ -198,7 +198,7 @@ static const struct nla_policy vlan_tunnel_policy[IFLA_BRIDGE_VLAN_TUNNEL_MAX + }; static int br_vlan_tunnel_info(struct net_bridge_port *p, int cmd, - u16 vid, u32 tun_id) + u16 vid, u32 tun_id, bool *changed) { int err = 0; @@ -208,9 +208,12 @@ static int br_vlan_tunnel_info(struct net_bridge_port *p, int cmd, switch (cmd) { case RTM_SETLINK: err = nbp_vlan_tunnel_info_add(p, vid, tun_id); + if (!err) + *changed = true; break; case RTM_DELLINK: - nbp_vlan_tunnel_info_delete(p, vid); + if (!nbp_vlan_tunnel_info_delete(p, vid)) + *changed = true; break; } @@ -254,7 +257,8 @@ int br_parse_vlan_tunnel_info(struct nlattr *attr, int br_process_vlan_tunnel_info(struct net_bridge *br, struct net_bridge_port *p, int cmd, struct vtunnel_info *tinfo_curr, - struct vtunnel_info *tinfo_last) + struct vtunnel_info *tinfo_last, + bool *changed) { int err; @@ -272,7 +276,7 @@ int br_process_vlan_tunnel_info(struct net_bridge *br, return -EINVAL; t = tinfo_last->tunid; for (v = tinfo_last->vid; v <= tinfo_curr->vid; v++) { - err = br_vlan_tunnel_info(p, cmd, v, t); + err = br_vlan_tunnel_info(p, cmd, v, t, changed); if (err) return err; t++; @@ -283,7 +287,7 @@ int br_process_vlan_tunnel_info(struct net_bridge *br, if (tinfo_last->flags) return -EINVAL; err = br_vlan_tunnel_info(p, cmd, tinfo_curr->vid, - tinfo_curr->tunid); + tinfo_curr->tunid, changed); if (err) return err; memset(tinfo_last, 0, sizeof(struct vtunnel_info)); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index e870cfc85b14..1312b8d20ec3 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -36,7 +36,14 @@ /* Control of forwarding link local multicast */ #define BR_GROUPFWD_DEFAULT 0 /* Don't allow forwarding of control protocols like STP, MAC PAUSE and LACP */ -#define BR_GROUPFWD_RESTRICTED 0x0007u +enum { + BR_GROUPFWD_STP = BIT(0), + BR_GROUPFWD_MACPAUSE = BIT(1), + BR_GROUPFWD_LACP = BIT(2), +}; + +#define BR_GROUPFWD_RESTRICTED (BR_GROUPFWD_STP | BR_GROUPFWD_MACPAUSE | \ + BR_GROUPFWD_LACP) /* The Nearest Customer Bridge Group Address, 01-80-C2-00-00-[00,0B,0C,0D,0F] */ #define BR_GROUPFWD_8021AD 0xB801u @@ -202,7 +209,7 @@ struct net_bridge_mdb_entry struct rcu_head rcu; struct timer_list timer; struct br_ip addr; - bool mglist; + bool host_joined; }; struct net_bridge_mdb_htable @@ -268,6 +275,7 @@ struct net_bridge_port { #ifdef CONFIG_NET_SWITCHDEV int offload_fwd_mark; #endif + u16 group_fwd_mask; }; #define br_auto_port(p) ((p)->flags & BR_AUTO_MASK) @@ -396,6 +404,7 @@ struct net_bridge { #ifdef CONFIG_NET_SWITCHDEV int offload_fwd_mark; #endif + bool neigh_suppress_enabled; }; struct br_input_skb_cb { @@ -558,7 +567,8 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb, void br_port_carrier_check(struct net_bridge_port *p); int br_add_bridge(struct net *net, const char *name); int br_del_bridge(struct net *net, const char *name); -int br_add_if(struct net_bridge *br, struct net_device *dev); +int br_add_if(struct net_bridge *br, struct net_device *dev, + struct netlink_ext_ack *extack); int br_del_if(struct net_bridge *br, struct net_device *dev); int br_min_mtu(const struct net_bridge *br); netdev_features_t br_features_recompute(struct net_bridge *br, @@ -793,7 +803,8 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br, const struct net_bridge_port *port, struct net_bridge_vlan_group *vg, struct sk_buff *skb); -int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags); +int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags, + bool *changed); int br_vlan_delete(struct net_bridge *br, u16 vid); void br_vlan_flush(struct net_bridge *br); struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, u16 vid); @@ -806,7 +817,8 @@ int br_vlan_set_stats(struct net_bridge *br, unsigned long val); int br_vlan_init(struct net_bridge *br); int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val); int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid); -int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags); +int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags, + bool *changed); int nbp_vlan_delete(struct net_bridge_port *port, u16 vid); void nbp_vlan_flush(struct net_bridge_port *port); int nbp_vlan_init(struct net_bridge_port *port); @@ -893,8 +905,10 @@ static inline struct sk_buff *br_handle_vlan(struct net_bridge *br, return skb; } -static inline int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags) +static inline int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags, + bool *changed) { + *changed = false; return -EOPNOTSUPP; } @@ -916,8 +930,10 @@ static inline int br_vlan_init(struct net_bridge *br) return 0; } -static inline int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags) +static inline int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags, + bool *changed) { + *changed = false; return -EOPNOTSUPP; } @@ -1055,7 +1071,8 @@ extern int (*br_fdb_test_addr_hook)(struct net_device *dev, unsigned char *addr) extern struct rtnl_link_ops br_link_ops; int br_netlink_init(void); void br_netlink_fini(void); -void br_ifinfo_notify(int event, struct net_bridge_port *port); +void br_ifinfo_notify(int event, const struct net_bridge *br, + const struct net_bridge_port *port); int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags); int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags); int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, @@ -1130,4 +1147,11 @@ static inline void br_switchdev_frame_unmark(struct sk_buff *skb) } #endif /* CONFIG_NET_SWITCHDEV */ +/* br_arp_nd_proxy.c */ +void br_recalculate_neigh_suppress_enabled(struct net_bridge *br); +void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br, + u16 vid, struct net_bridge_port *p); +void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br, + u16 vid, struct net_bridge_port *p, struct nd_msg *msg); +struct nd_msg *br_is_nd_neigh_msg(struct sk_buff *skb, struct nd_msg *m); #endif diff --git a/net/bridge/br_private_tunnel.h b/net/bridge/br_private_tunnel.h index 4a447a378ab3..a259471bfd78 100644 --- a/net/bridge/br_private_tunnel.h +++ b/net/bridge/br_private_tunnel.h @@ -26,7 +26,8 @@ int br_process_vlan_tunnel_info(struct net_bridge *br, struct net_bridge_port *p, int cmd, struct vtunnel_info *tinfo_curr, - struct vtunnel_info *tinfo_last); + struct vtunnel_info *tinfo_last, + bool *changed); int br_get_vlan_tunnel_info_size(struct net_bridge_vlan_group *vg); int br_fill_vlan_tunnel_info(struct sk_buff *skb, struct net_bridge_vlan_group *vg); diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 8f56c2d1f1a7..b6941961a876 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -123,7 +123,7 @@ static void br_root_port_block(const struct net_bridge *br, (unsigned int) p->port_no, p->dev->name); br_set_state(p, BR_STATE_LISTENING); - br_ifinfo_notify(RTM_NEWLINK, p); + br_ifinfo_notify(RTM_NEWLINK, NULL, p); if (br->forward_delay > 0) mod_timer(&p->forward_delay_timer, jiffies + br->forward_delay); @@ -403,7 +403,7 @@ static void br_make_blocking(struct net_bridge_port *p) br_topology_change_detection(p->br); br_set_state(p, BR_STATE_BLOCKING); - br_ifinfo_notify(RTM_NEWLINK, p); + br_ifinfo_notify(RTM_NEWLINK, NULL, p); del_timer(&p->forward_delay_timer); } @@ -426,7 +426,7 @@ static void br_make_forwarding(struct net_bridge_port *p) else br_set_state(p, BR_STATE_LEARNING); - br_ifinfo_notify(RTM_NEWLINK, p); + br_ifinfo_notify(RTM_NEWLINK, NULL, p); if (br->forward_delay != 0) mod_timer(&p->forward_delay_timer, jiffies + br->forward_delay); diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 89110319ef0f..808e2b914015 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -96,7 +96,7 @@ void br_stp_enable_port(struct net_bridge_port *p) { br_init_port(p); br_port_state_selection(p->br); - br_ifinfo_notify(RTM_NEWLINK, p); + br_ifinfo_notify(RTM_NEWLINK, NULL, p); } /* called under bridge lock */ @@ -111,7 +111,7 @@ void br_stp_disable_port(struct net_bridge_port *p) p->topology_change_ack = 0; p->config_pending = 0; - br_ifinfo_notify(RTM_NEWLINK, p); + br_ifinfo_notify(RTM_NEWLINK, NULL, p); del_timer(&p->message_age_timer); del_timer(&p->forward_delay_timer); diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c index 60b6fe277a8b..e7739de5f0e1 100644 --- a/net/bridge/br_stp_timer.c +++ b/net/bridge/br_stp_timer.c @@ -31,9 +31,9 @@ static int br_is_designated_for_some_port(const struct net_bridge *br) return 0; } -static void br_hello_timer_expired(unsigned long arg) +static void br_hello_timer_expired(struct timer_list *t) { - struct net_bridge *br = (struct net_bridge *)arg; + struct net_bridge *br = from_timer(br, t, hello_timer); br_debug(br, "hello timer expired\n"); spin_lock(&br->lock); @@ -47,9 +47,9 @@ static void br_hello_timer_expired(unsigned long arg) spin_unlock(&br->lock); } -static void br_message_age_timer_expired(unsigned long arg) +static void br_message_age_timer_expired(struct timer_list *t) { - struct net_bridge_port *p = (struct net_bridge_port *) arg; + struct net_bridge_port *p = from_timer(p, t, message_age_timer); struct net_bridge *br = p->br; const bridge_id *id = &p->designated_bridge; int was_root; @@ -80,9 +80,9 @@ static void br_message_age_timer_expired(unsigned long arg) spin_unlock(&br->lock); } -static void br_forward_delay_timer_expired(unsigned long arg) +static void br_forward_delay_timer_expired(struct timer_list *t) { - struct net_bridge_port *p = (struct net_bridge_port *) arg; + struct net_bridge_port *p = from_timer(p, t, forward_delay_timer); struct net_bridge *br = p->br; br_debug(br, "port %u(%s) forward delay timer\n", @@ -99,14 +99,14 @@ static void br_forward_delay_timer_expired(unsigned long arg) netif_carrier_on(br->dev); } rcu_read_lock(); - br_ifinfo_notify(RTM_NEWLINK, p); + br_ifinfo_notify(RTM_NEWLINK, NULL, p); rcu_read_unlock(); spin_unlock(&br->lock); } -static void br_tcn_timer_expired(unsigned long arg) +static void br_tcn_timer_expired(struct timer_list *t) { - struct net_bridge *br = (struct net_bridge *) arg; + struct net_bridge *br = from_timer(br, t, tcn_timer); br_debug(br, "tcn timer expired\n"); spin_lock(&br->lock); @@ -118,9 +118,9 @@ static void br_tcn_timer_expired(unsigned long arg) spin_unlock(&br->lock); } -static void br_topology_change_timer_expired(unsigned long arg) +static void br_topology_change_timer_expired(struct timer_list *t) { - struct net_bridge *br = (struct net_bridge *) arg; + struct net_bridge *br = from_timer(br, t, topology_change_timer); br_debug(br, "topo change timer expired\n"); spin_lock(&br->lock); @@ -129,9 +129,9 @@ static void br_topology_change_timer_expired(unsigned long arg) spin_unlock(&br->lock); } -static void br_hold_timer_expired(unsigned long arg) +static void br_hold_timer_expired(struct timer_list *t) { - struct net_bridge_port *p = (struct net_bridge_port *) arg; + struct net_bridge_port *p = from_timer(p, t, hold_timer); br_debug(p->br, "port %u(%s) hold timer expired\n", (unsigned int) p->port_no, p->dev->name); @@ -144,27 +144,17 @@ static void br_hold_timer_expired(unsigned long arg) void br_stp_timer_init(struct net_bridge *br) { - setup_timer(&br->hello_timer, br_hello_timer_expired, - (unsigned long) br); - - setup_timer(&br->tcn_timer, br_tcn_timer_expired, - (unsigned long) br); - - setup_timer(&br->topology_change_timer, - br_topology_change_timer_expired, - (unsigned long) br); + timer_setup(&br->hello_timer, br_hello_timer_expired, 0); + timer_setup(&br->tcn_timer, br_tcn_timer_expired, 0); + timer_setup(&br->topology_change_timer, + br_topology_change_timer_expired, 0); } void br_stp_port_timer_init(struct net_bridge_port *p) { - setup_timer(&p->message_age_timer, br_message_age_timer_expired, - (unsigned long) p); - - setup_timer(&p->forward_delay_timer, br_forward_delay_timer_expired, - (unsigned long) p); - - setup_timer(&p->hold_timer, br_hold_timer_expired, - (unsigned long) p); + timer_setup(&p->message_age_timer, br_message_age_timer_expired, 0); + timer_setup(&p->forward_delay_timer, br_forward_delay_timer_expired, 0); + timer_setup(&p->hold_timer, br_hold_timer_expired, 0); } /* Report ticks left (in USER_HZ) used for API */ diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 5d5d413a6cf8..0254c35b2bf0 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -165,6 +165,23 @@ static int store_flush(struct net_bridge_port *p, unsigned long v) } static BRPORT_ATTR(flush, S_IWUSR, NULL, store_flush); +static ssize_t show_group_fwd_mask(struct net_bridge_port *p, char *buf) +{ + return sprintf(buf, "%#x\n", p->group_fwd_mask); +} + +static int store_group_fwd_mask(struct net_bridge_port *p, + unsigned long v) +{ + if (v & BR_GROUPFWD_MACPAUSE) + return -EINVAL; + p->group_fwd_mask = v; + + return 0; +} +static BRPORT_ATTR(group_fwd_mask, S_IRUGO | S_IWUSR, show_group_fwd_mask, + store_group_fwd_mask); + BRPORT_ATTR_FLAG(hairpin_mode, BR_HAIRPIN_MODE); BRPORT_ATTR_FLAG(bpdu_guard, BR_BPDU_GUARD); BRPORT_ATTR_FLAG(root_block, BR_ROOT_BLOCK); @@ -174,6 +191,7 @@ BRPORT_ATTR_FLAG(proxyarp, BR_PROXYARP); BRPORT_ATTR_FLAG(proxyarp_wifi, BR_PROXYARP_WIFI); BRPORT_ATTR_FLAG(multicast_flood, BR_MCAST_FLOOD); BRPORT_ATTR_FLAG(broadcast_flood, BR_BCAST_FLOOD); +BRPORT_ATTR_FLAG(neigh_suppress, BR_NEIGH_SUPPRESS); #ifdef CONFIG_BRIDGE_IGMP_SNOOPING static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf) @@ -223,6 +241,8 @@ static const struct brport_attribute *brport_attrs[] = { &brport_attr_proxyarp_wifi, &brport_attr_multicast_flood, &brport_attr_broadcast_flood, + &brport_attr_group_fwd_mask, + &brport_attr_neigh_suppress, NULL }; @@ -260,7 +280,7 @@ static ssize_t brport_store(struct kobject *kobj, ret = brport_attr->store(p, val); spin_unlock_bh(&p->br->lock); if (!ret) { - br_ifinfo_notify(RTM_NEWLINK, p); + br_ifinfo_notify(RTM_NEWLINK, NULL, p); ret = count; } } diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 233a30040c91..51935270c651 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -32,27 +32,34 @@ static struct net_bridge_vlan *br_vlan_lookup(struct rhashtable *tbl, u16 vid) return rhashtable_lookup_fast(tbl, &vid, br_vlan_rht_params); } -static void __vlan_add_pvid(struct net_bridge_vlan_group *vg, u16 vid) +static bool __vlan_add_pvid(struct net_bridge_vlan_group *vg, u16 vid) { if (vg->pvid == vid) - return; + return false; smp_wmb(); vg->pvid = vid; + + return true; } -static void __vlan_delete_pvid(struct net_bridge_vlan_group *vg, u16 vid) +static bool __vlan_delete_pvid(struct net_bridge_vlan_group *vg, u16 vid) { if (vg->pvid != vid) - return; + return false; smp_wmb(); vg->pvid = 0; + + return true; } -static void __vlan_add_flags(struct net_bridge_vlan *v, u16 flags) +/* return true if anything changed, false otherwise */ +static bool __vlan_add_flags(struct net_bridge_vlan *v, u16 flags) { struct net_bridge_vlan_group *vg; + u16 old_flags = v->flags; + bool ret; if (br_vlan_is_master(v)) vg = br_vlan_group(v->br); @@ -60,14 +67,16 @@ static void __vlan_add_flags(struct net_bridge_vlan *v, u16 flags) vg = nbp_vlan_group(v->port); if (flags & BRIDGE_VLAN_INFO_PVID) - __vlan_add_pvid(vg, v->vid); + ret = __vlan_add_pvid(vg, v->vid); else - __vlan_delete_pvid(vg, v->vid); + ret = __vlan_delete_pvid(vg, v->vid); if (flags & BRIDGE_VLAN_INFO_UNTAGGED) v->flags |= BRIDGE_VLAN_INFO_UNTAGGED; else v->flags &= ~BRIDGE_VLAN_INFO_UNTAGGED; + + return ret || !!(old_flags ^ v->flags); } static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, @@ -151,8 +160,10 @@ static struct net_bridge_vlan *br_vlan_get_master(struct net_bridge *br, u16 vid vg = br_vlan_group(br); masterv = br_vlan_find(vg, vid); if (!masterv) { + bool changed; + /* missing global ctx, create it now */ - if (br_vlan_add(br, vid, 0)) + if (br_vlan_add(br, vid, 0, &changed)) return NULL; masterv = br_vlan_find(vg, vid); if (WARN_ON(!masterv)) @@ -232,8 +243,11 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags) /* need to work on the master vlan too */ if (flags & BRIDGE_VLAN_INFO_MASTER) { - err = br_vlan_add(br, v->vid, flags | - BRIDGE_VLAN_INFO_BRENTRY); + bool changed; + + err = br_vlan_add(br, v->vid, + flags | BRIDGE_VLAN_INFO_BRENTRY, + &changed); if (err) goto out_filt; } @@ -550,8 +564,9 @@ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid) /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. + * changed must be true only if the vlan was created or updated */ -int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags) +int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags, bool *changed) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *vlan; @@ -559,6 +574,7 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags) ASSERT_RTNL(); + *changed = false; vg = br_vlan_group(br); vlan = br_vlan_find(vg, vid); if (vlan) { @@ -576,8 +592,11 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags) refcount_inc(&vlan->refcnt); vlan->flags |= BRIDGE_VLAN_INFO_BRENTRY; vg->num_vlans++; + *changed = true; } - __vlan_add_flags(vlan, flags); + if (__vlan_add_flags(vlan, flags)) + *changed = true; + return 0; } @@ -600,6 +619,8 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags) if (ret) { free_percpu(vlan->stats); kfree(vlan); + } else { + *changed = true; } return ret; @@ -824,9 +845,10 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) const struct net_bridge_vlan *pvent; struct net_bridge_vlan_group *vg; struct net_bridge_port *p; + unsigned long *changed; + bool vlchange; u16 old_pvid; int err = 0; - unsigned long *changed; if (!pvid) { br_vlan_disable_default_pvid(br); @@ -850,7 +872,8 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) err = br_vlan_add(br, pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | - BRIDGE_VLAN_INFO_BRENTRY); + BRIDGE_VLAN_INFO_BRENTRY, + &vlchange); if (err) goto out; br_vlan_delete(br, old_pvid); @@ -869,7 +892,8 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) err = nbp_vlan_add(p, pvid, BRIDGE_VLAN_INFO_PVID | - BRIDGE_VLAN_INFO_UNTAGGED); + BRIDGE_VLAN_INFO_UNTAGGED, + &vlchange); if (err) goto err_port; nbp_vlan_delete(p, old_pvid); @@ -890,7 +914,8 @@ err_port: if (old_pvid) nbp_vlan_add(p, old_pvid, BRIDGE_VLAN_INFO_PVID | - BRIDGE_VLAN_INFO_UNTAGGED); + BRIDGE_VLAN_INFO_UNTAGGED, + &vlchange); nbp_vlan_delete(p, pvid); } @@ -899,7 +924,8 @@ err_port: br_vlan_add(br, old_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | - BRIDGE_VLAN_INFO_BRENTRY); + BRIDGE_VLAN_INFO_BRENTRY, + &vlchange); br_vlan_delete(br, pvid); } goto out; @@ -931,6 +957,7 @@ int br_vlan_init(struct net_bridge *br) { struct net_bridge_vlan_group *vg; int ret = -ENOMEM; + bool changed; vg = kzalloc(sizeof(*vg), GFP_KERNEL); if (!vg) @@ -947,7 +974,7 @@ int br_vlan_init(struct net_bridge *br) rcu_assign_pointer(br->vlgrp, vg); ret = br_vlan_add(br, 1, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | - BRIDGE_VLAN_INFO_BRENTRY); + BRIDGE_VLAN_INFO_BRENTRY, &changed); if (ret) goto err_vlan_add; @@ -992,9 +1019,12 @@ int nbp_vlan_init(struct net_bridge_port *p) INIT_LIST_HEAD(&vg->vlan_list); rcu_assign_pointer(p->vlgrp, vg); if (p->br->default_pvid) { + bool changed; + ret = nbp_vlan_add(p, p->br->default_pvid, BRIDGE_VLAN_INFO_PVID | - BRIDGE_VLAN_INFO_UNTAGGED); + BRIDGE_VLAN_INFO_UNTAGGED, + &changed); if (ret) goto err_vlan_add; } @@ -1016,8 +1046,10 @@ err_vlan_enabled: /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. + * changed must be true only if the vlan was created or updated */ -int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags) +int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags, + bool *changed) { struct switchdev_obj_port_vlan v = { .obj.orig_dev = port->dev, @@ -1031,13 +1063,15 @@ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags) ASSERT_RTNL(); + *changed = false; vlan = br_vlan_find(nbp_vlan_group(port), vid); if (vlan) { /* Pass the flags to the hardware bridge */ ret = switchdev_port_obj_add(port->dev, &v.obj); if (ret && ret != -EOPNOTSUPP) return ret; - __vlan_add_flags(vlan, flags); + *changed = __vlan_add_flags(vlan, flags); + return 0; } @@ -1050,6 +1084,8 @@ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags) ret = __vlan_add(vlan, flags); if (ret) kfree(vlan); + else + *changed = true; return ret; } diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 3b3dcf719e07..37817d25b63d 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -2112,9 +2112,8 @@ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, for (i = 0, j = 1 ; j < 4 ; j++, i++) { struct compat_ebt_entry_mwt *match32; unsigned int size; - char *buf = buf_start; + char *buf = buf_start + offsets[i]; - buf = buf_start + offsets[i]; if (offsets[i] > offsets[j]) return -EINVAL; diff --git a/net/can/af_can.c b/net/can/af_can.c index ecd5c703d11e..003b2d6d655f 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -887,8 +887,8 @@ static int can_pernet_init(struct net *net) if (IS_ENABLED(CONFIG_PROC_FS)) { /* the statistics are updated every second (timer triggered) */ if (stats_timer) { - setup_timer(&net->can.can_stattimer, can_stat_update, - (unsigned long)net); + timer_setup(&net->can.can_stattimer, can_stat_update, + 0); mod_timer(&net->can.can_stattimer, round_jiffies(jiffies + HZ)); } diff --git a/net/can/af_can.h b/net/can/af_can.h index d0ef45bb2a72..eca6463c6213 100644 --- a/net/can/af_can.h +++ b/net/can/af_can.h @@ -113,6 +113,6 @@ struct s_pstats { /* function prototypes for the CAN networklayer procfs (proc.c) */ void can_init_proc(struct net *net); void can_remove_proc(struct net *net); -void can_stat_update(unsigned long data); +void can_stat_update(struct timer_list *t); #endif /* AF_CAN_H */ diff --git a/net/can/proc.c b/net/can/proc.c index 83045f00c63c..d979b3dc49a6 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -115,9 +115,9 @@ static unsigned long calc_rate(unsigned long oldjif, unsigned long newjif, return rate; } -void can_stat_update(unsigned long data) +void can_stat_update(struct timer_list *t) { - struct net *net = (struct net *)data; + struct net *net = from_timer(net, t, can.can_stattimer); struct s_stats *can_stats = net->can.can_stats; unsigned long j = jiffies; /* snapshot */ @@ -221,7 +221,7 @@ static int can_stats_proc_show(struct seq_file *m, void *v) seq_putc(m, '\n'); - if (net->can.can_stattimer.function == can_stat_update) { + if (net->can.can_stattimer.function == (TIMER_FUNC_TYPE)can_stat_update) { seq_printf(m, " %8ld %% total match ratio (RXMR)\n", can_stats->total_rx_match_ratio); @@ -291,7 +291,7 @@ static int can_reset_stats_proc_show(struct seq_file *m, void *v) user_reset = 1; - if (net->can.can_stattimer.function == can_stat_update) { + if (net->can.can_stattimer.function == (TIMER_FUNC_TYPE)can_stat_update) { seq_printf(m, "Scheduled statistic reset #%ld.\n", can_pstats->stats_reset + 1); } else { diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c index ee43bc13221c..a3d0adc828e6 100644 --- a/net/ceph/pagevec.c +++ b/net/ceph/pagevec.c @@ -25,9 +25,9 @@ struct page **ceph_get_direct_page_vector(const void __user *data, return ERR_PTR(-ENOMEM); while (got < num_pages) { - rc = get_user_pages_unlocked( + rc = get_user_pages_fast( (unsigned long)data + ((unsigned long)got * PAGE_SIZE), - num_pages - got, pages + got, write_page ? FOLL_WRITE : 0); + num_pages - got, write_page, pages + got); if (rc < 0) break; BUG_ON(rc == 0); diff --git a/net/core/datagram.c b/net/core/datagram.c index 3964c108b169..522873ed120b 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -189,7 +189,7 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, } if (!skb->len) { skb = skb_set_peeked(skb); - if (unlikely(IS_ERR(skb))) { + if (IS_ERR(skb)) { *err = PTR_ERR(skb); return NULL; } diff --git a/net/core/dev.c b/net/core/dev.c index 11596a302a26..8ee29f4f5fa9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -145,6 +145,7 @@ #include <linux/crash_dump.h> #include <linux/sctp.h> #include <net/udp_tunnel.h> +#include <linux/net_namespace.h> #include "net-sysfs.h" @@ -162,7 +163,6 @@ static struct list_head offload_base __read_mostly; static int netif_rx_internal(struct sk_buff *skb); static int call_netdevice_notifiers_info(unsigned long val, - struct net_device *dev, struct netdev_notifier_info *info); static struct napi_struct *napi_by_id(unsigned int napi_id); @@ -188,6 +188,8 @@ static struct napi_struct *napi_by_id(unsigned int napi_id); DEFINE_RWLOCK(dev_base_lock); EXPORT_SYMBOL(dev_base_lock); +static DEFINE_MUTEX(ifalias_mutex); + /* protects napi_hash addition/deletion and napi_gen_id */ static DEFINE_SPINLOCK(napi_hash_lock); @@ -1062,7 +1064,10 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) unsigned long *inuse; struct net_device *d; - p = strnchr(name, IFNAMSIZ-1, '%'); + if (!dev_valid_name(name)) + return -EINVAL; + + p = strchr(name, '%'); if (p) { /* * Verify the string as this thing may have come from @@ -1093,8 +1098,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) free_page((unsigned long) inuse); } - if (buf != name) - snprintf(buf, IFNAMSIZ, name, i); + snprintf(buf, IFNAMSIZ, name, i); if (!__dev_get_by_name(net, buf)) return i; @@ -1102,7 +1106,21 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) * when the name is long and there isn't enough space left * for the digits, or if all bits are used. */ - return -ENFILE; + return p ? -ENFILE : -EEXIST; +} + +static int dev_alloc_name_ns(struct net *net, + struct net_device *dev, + const char *name) +{ + char buf[IFNAMSIZ]; + int ret; + + BUG_ON(!net); + ret = __dev_alloc_name(net, name, buf); + if (ret >= 0) + strlcpy(dev->name, buf, IFNAMSIZ); + return ret; } /** @@ -1121,48 +1139,14 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) int dev_alloc_name(struct net_device *dev, const char *name) { - char buf[IFNAMSIZ]; - struct net *net; - int ret; - - BUG_ON(!dev_net(dev)); - net = dev_net(dev); - ret = __dev_alloc_name(net, name, buf); - if (ret >= 0) - strlcpy(dev->name, buf, IFNAMSIZ); - return ret; + return dev_alloc_name_ns(dev_net(dev), dev, name); } EXPORT_SYMBOL(dev_alloc_name); -static int dev_alloc_name_ns(struct net *net, - struct net_device *dev, - const char *name) -{ - char buf[IFNAMSIZ]; - int ret; - - ret = __dev_alloc_name(net, name, buf); - if (ret >= 0) - strlcpy(dev->name, buf, IFNAMSIZ); - return ret; -} - int dev_get_valid_name(struct net *net, struct net_device *dev, const char *name) { - BUG_ON(!net); - - if (!dev_valid_name(name)) - return -EINVAL; - - if (strchr(name, '%')) - return dev_alloc_name_ns(net, dev, name); - else if (__dev_get_by_name(net, name)) - return -EEXIST; - else if (dev->name != name) - strlcpy(dev->name, name, IFNAMSIZ); - - return 0; + return dev_alloc_name_ns(net, dev, name); } EXPORT_SYMBOL(dev_get_valid_name); @@ -1265,29 +1249,53 @@ rollback: */ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) { - char *new_ifalias; - - ASSERT_RTNL(); + struct dev_ifalias *new_alias = NULL; if (len >= IFALIASZ) return -EINVAL; - if (!len) { - kfree(dev->ifalias); - dev->ifalias = NULL; - return 0; + if (len) { + new_alias = kmalloc(sizeof(*new_alias) + len + 1, GFP_KERNEL); + if (!new_alias) + return -ENOMEM; + + memcpy(new_alias->ifalias, alias, len); + new_alias->ifalias[len] = 0; } - new_ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL); - if (!new_ifalias) - return -ENOMEM; - dev->ifalias = new_ifalias; - memcpy(dev->ifalias, alias, len); - dev->ifalias[len] = 0; + mutex_lock(&ifalias_mutex); + rcu_swap_protected(dev->ifalias, new_alias, + mutex_is_locked(&ifalias_mutex)); + mutex_unlock(&ifalias_mutex); + + if (new_alias) + kfree_rcu(new_alias, rcuhead); return len; } +/** + * dev_get_alias - get ifalias of a device + * @dev: device + * @name: buffer to store name of ifalias + * @len: size of buffer + * + * get ifalias for a device. Caller must make sure dev cannot go + * away, e.g. rcu read lock or own a reference count to device. + */ +int dev_get_alias(const struct net_device *dev, char *name, size_t len) +{ + const struct dev_ifalias *alias; + int ret = 0; + + rcu_read_lock(); + alias = rcu_dereference(dev->ifalias); + if (alias) + ret = snprintf(name, len, "%s", alias->ifalias); + rcu_read_unlock(); + + return ret; +} /** * netdev_features_change - device changes features @@ -1312,10 +1320,11 @@ EXPORT_SYMBOL(netdev_features_change); void netdev_state_change(struct net_device *dev) { if (dev->flags & IFF_UP) { - struct netdev_notifier_change_info change_info; + struct netdev_notifier_change_info change_info = { + .info.dev = dev, + }; - change_info.flags_changed = 0; - call_netdevice_notifiers_info(NETDEV_CHANGE, dev, + call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info); rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL); } @@ -1536,9 +1545,10 @@ EXPORT_SYMBOL(dev_disable_lro); static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val, struct net_device *dev) { - struct netdev_notifier_info info; + struct netdev_notifier_info info = { + .dev = dev, + }; - netdev_notifier_info_init(&info, dev); return nb->notifier_call(nb, val, &info); } @@ -1663,11 +1673,9 @@ EXPORT_SYMBOL(unregister_netdevice_notifier); */ static int call_netdevice_notifiers_info(unsigned long val, - struct net_device *dev, struct netdev_notifier_info *info) { ASSERT_RTNL(); - netdev_notifier_info_init(info, dev); return raw_notifier_call_chain(&netdev_chain, val, info); } @@ -1682,9 +1690,11 @@ static int call_netdevice_notifiers_info(unsigned long val, int call_netdevice_notifiers(unsigned long val, struct net_device *dev) { - struct netdev_notifier_info info; + struct netdev_notifier_info info = { + .dev = dev, + }; - return call_netdevice_notifiers_info(val, dev, &info); + return call_netdevice_notifiers_info(val, &info); } EXPORT_SYMBOL(call_netdevice_notifiers); @@ -2012,6 +2022,7 @@ int netdev_txq_to_tc(struct net_device *dev, unsigned int txq) return 0; } +EXPORT_SYMBOL(netdev_txq_to_tc); #ifdef CONFIG_XPS static DEFINE_MUTEX(xps_map_mutex); @@ -3245,22 +3256,22 @@ EXPORT_SYMBOL(dev_loopback_xmit); static struct sk_buff * sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) { - struct tcf_proto *cl = rcu_dereference_bh(dev->egress_cl_list); + struct mini_Qdisc *miniq = rcu_dereference_bh(dev->miniq_egress); struct tcf_result cl_res; - if (!cl) + if (!miniq) return skb; /* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */ - qdisc_bstats_cpu_update(cl->q, skb); + mini_qdisc_bstats_cpu_update(miniq, skb); - switch (tcf_classify(skb, cl, &cl_res, false)) { + switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) { case TC_ACT_OK: case TC_ACT_RECLASSIFY: skb->tc_index = TC_H_MIN(cl_res.classid); break; case TC_ACT_SHOT: - qdisc_qstats_cpu_drop(cl->q); + mini_qdisc_qstats_cpu_drop(miniq); *ret = NET_XMIT_DROP; kfree_skb(skb); return NULL; @@ -3725,7 +3736,7 @@ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, flow_table = rcu_dereference(rxqueue->rps_flow_table); if (flow_table && flow_id <= flow_table->mask) { rflow = &flow_table->flows[flow_id]; - cpu = ACCESS_ONCE(rflow->cpu); + cpu = READ_ONCE(rflow->cpu); if (rflow->filter == filter_id && cpu < nr_cpu_ids && ((int)(per_cpu(softnet_data, cpu).input_queue_head - rflow->last_qtail) < @@ -3864,8 +3875,8 @@ drop: static u32 netif_receive_generic_xdp(struct sk_buff *skb, struct bpf_prog *xdp_prog) { + u32 metalen, act = XDP_DROP; struct xdp_buff xdp; - u32 act = XDP_DROP; void *orig_data; int hlen, off; u32 mac_len; @@ -3876,8 +3887,25 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, if (skb_cloned(skb)) return XDP_PASS; - if (skb_linearize(skb)) - goto do_drop; + /* XDP packets must be linear and must have sufficient headroom + * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also + * native XDP provides, thus we need to do it here as well. + */ + if (skb_is_nonlinear(skb) || + skb_headroom(skb) < XDP_PACKET_HEADROOM) { + int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); + int troom = skb->tail + skb->data_len - skb->end; + + /* In case we have to go down the path and also linearize, + * then lets do the pskb_expand_head() work just once here. + */ + if (pskb_expand_head(skb, + hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0, + troom > 0 ? troom + 128 : 0, GFP_ATOMIC)) + goto do_drop; + if (troom > 0 && __skb_linearize(skb)) + goto do_drop; + } /* The XDP program wants to see the packet starting at the MAC * header. @@ -3885,6 +3913,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, mac_len = skb->data - skb_mac_header(skb); hlen = skb_headlen(skb) + mac_len; xdp.data = skb->data - mac_len; + xdp.data_meta = xdp.data; xdp.data_end = xdp.data + hlen; xdp.data_hard_start = skb->data - skb_headroom(skb); orig_data = xdp.data; @@ -3902,10 +3931,12 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, case XDP_REDIRECT: case XDP_TX: __skb_push(skb, mac_len); - /* fall through */ + break; case XDP_PASS: + metalen = xdp.data - xdp.data_meta; + if (metalen) + skb_metadata_set(skb, metalen); break; - default: bpf_warn_invalid_xdp_action(act); /* fall through */ @@ -4140,7 +4171,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev) { #ifdef CONFIG_NET_CLS_ACT - struct tcf_proto *cl = rcu_dereference_bh(skb->dev->ingress_cl_list); + struct mini_Qdisc *miniq = rcu_dereference_bh(skb->dev->miniq_ingress); struct tcf_result cl_res; /* If there's at least one ingress present somewhere (so @@ -4148,8 +4179,9 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, * that are not configured with an ingress qdisc will bail * out here. */ - if (!cl) + if (!miniq) return skb; + if (*pt_prev) { *ret = deliver_skb(skb, *pt_prev, orig_dev); *pt_prev = NULL; @@ -4157,15 +4189,15 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, qdisc_skb_cb(skb)->pkt_len = skb->len; skb->tc_at_ingress = 1; - qdisc_bstats_cpu_update(cl->q, skb); + mini_qdisc_bstats_cpu_update(miniq, skb); - switch (tcf_classify(skb, cl, &cl_res, false)) { + switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) { case TC_ACT_OK: case TC_ACT_RECLASSIFY: skb->tc_index = TC_H_MIN(cl_res.classid); break; case TC_ACT_SHOT: - qdisc_qstats_cpu_drop(cl->q); + mini_qdisc_qstats_cpu_drop(miniq); kfree_skb(skb); return NULL; case TC_ACT_STOLEN: @@ -4443,6 +4475,33 @@ out: return ret; } +/** + * netif_receive_skb_core - special purpose version of netif_receive_skb + * @skb: buffer to process + * + * More direct receive version of netif_receive_skb(). It should + * only be used by callers that have a need to skip RPS and Generic XDP. + * Caller must also take care of handling if (page_is_)pfmemalloc. + * + * This function may only be called from softirq context and interrupts + * should be enabled. + * + * Return values (usually ignored): + * NET_RX_SUCCESS: no congestion + * NET_RX_DROP: packet was dropped + */ +int netif_receive_skb_core(struct sk_buff *skb) +{ + int ret; + + rcu_read_lock(); + ret = __netif_receive_skb_core(skb, false); + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(netif_receive_skb_core); + static int __netif_receive_skb(struct sk_buff *skb) { int ret; @@ -4468,7 +4527,7 @@ static int __netif_receive_skb(struct sk_buff *skb) return ret; } -static int generic_xdp_install(struct net_device *dev, struct netdev_xdp *xdp) +static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) { struct bpf_prog *old = rtnl_dereference(dev->xdp_prog); struct bpf_prog *new = xdp->prog; @@ -4695,6 +4754,7 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; diffs |= p->vlan_tci ^ skb->vlan_tci; diffs |= skb_metadata_dst_cmp(p, skb); + diffs |= skb_metadata_differs(p, skb); if (maclen == ETH_HLEN) diffs |= compare_ether_header(skb_mac_header(p), skb_mac_header(skb)); @@ -6228,9 +6288,19 @@ static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, static int __netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, bool master, - void *upper_priv, void *upper_info) -{ - struct netdev_notifier_changeupper_info changeupper_info; + void *upper_priv, void *upper_info, + struct netlink_ext_ack *extack) +{ + struct netdev_notifier_changeupper_info changeupper_info = { + .info = { + .dev = dev, + .extack = extack, + }, + .upper_dev = upper_dev, + .master = master, + .linking = true, + .upper_info = upper_info, + }; int ret = 0; ASSERT_RTNL(); @@ -6248,12 +6318,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, if (master && netdev_master_upper_dev_get(dev)) return -EBUSY; - changeupper_info.upper_dev = upper_dev; - changeupper_info.master = master; - changeupper_info.linking = true; - changeupper_info.upper_info = upper_info; - - ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev, + ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, &changeupper_info.info); ret = notifier_to_errno(ret); if (ret) @@ -6264,7 +6329,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, if (ret) return ret; - ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev, + ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, &changeupper_info.info); ret = notifier_to_errno(ret); if (ret) @@ -6289,9 +6354,11 @@ rollback: * returns zero. */ int netdev_upper_dev_link(struct net_device *dev, - struct net_device *upper_dev) + struct net_device *upper_dev, + struct netlink_ext_ack *extack) { - return __netdev_upper_dev_link(dev, upper_dev, false, NULL, NULL); + return __netdev_upper_dev_link(dev, upper_dev, false, + NULL, NULL, extack); } EXPORT_SYMBOL(netdev_upper_dev_link); @@ -6310,10 +6377,11 @@ EXPORT_SYMBOL(netdev_upper_dev_link); */ int netdev_master_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, - void *upper_priv, void *upper_info) + void *upper_priv, void *upper_info, + struct netlink_ext_ack *extack) { return __netdev_upper_dev_link(dev, upper_dev, true, - upper_priv, upper_info); + upper_priv, upper_info, extack); } EXPORT_SYMBOL(netdev_master_upper_dev_link); @@ -6328,20 +6396,24 @@ EXPORT_SYMBOL(netdev_master_upper_dev_link); void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev) { - struct netdev_notifier_changeupper_info changeupper_info; + struct netdev_notifier_changeupper_info changeupper_info = { + .info = { + .dev = dev, + }, + .upper_dev = upper_dev, + .linking = false, + }; ASSERT_RTNL(); - changeupper_info.upper_dev = upper_dev; changeupper_info.master = netdev_master_upper_dev_get(dev) == upper_dev; - changeupper_info.linking = false; - call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev, + call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, &changeupper_info.info); __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); - call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev, + call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, &changeupper_info.info); } EXPORT_SYMBOL(netdev_upper_dev_unlink); @@ -6357,11 +6429,13 @@ EXPORT_SYMBOL(netdev_upper_dev_unlink); void netdev_bonding_info_change(struct net_device *dev, struct netdev_bonding_info *bonding_info) { - struct netdev_notifier_bonding_info info; + struct netdev_notifier_bonding_info info = { + .info.dev = dev, + }; memcpy(&info.bonding_info, bonding_info, sizeof(struct netdev_bonding_info)); - call_netdevice_notifiers_info(NETDEV_BONDING_INFO, dev, + call_netdevice_notifiers_info(NETDEV_BONDING_INFO, &info.info); } EXPORT_SYMBOL(netdev_bonding_info_change); @@ -6487,11 +6561,13 @@ EXPORT_SYMBOL(dev_get_nest_level); void netdev_lower_state_changed(struct net_device *lower_dev, void *lower_state_info) { - struct netdev_notifier_changelowerstate_info changelowerstate_info; + struct netdev_notifier_changelowerstate_info changelowerstate_info = { + .info.dev = lower_dev, + }; ASSERT_RTNL(); changelowerstate_info.lower_state_info = lower_state_info; - call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE, lower_dev, + call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE, &changelowerstate_info.info); } EXPORT_SYMBOL(netdev_lower_state_changed); @@ -6782,11 +6858,14 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags, if (dev->flags & IFF_UP && (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) { - struct netdev_notifier_change_info change_info; + struct netdev_notifier_change_info change_info = { + .info = { + .dev = dev, + }, + .flags_changed = changes, + }; - change_info.flags_changed = changes; - call_netdevice_notifiers_info(NETDEV_CHANGE, dev, - &change_info.info); + call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info); } } @@ -6993,26 +7072,26 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down) } EXPORT_SYMBOL(dev_change_proto_down); -u8 __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op, u32 *prog_id) +u8 __dev_xdp_attached(struct net_device *dev, bpf_op_t bpf_op, u32 *prog_id) { - struct netdev_xdp xdp; + struct netdev_bpf xdp; memset(&xdp, 0, sizeof(xdp)); xdp.command = XDP_QUERY_PROG; /* Query must always succeed. */ - WARN_ON(xdp_op(dev, &xdp) < 0); + WARN_ON(bpf_op(dev, &xdp) < 0); if (prog_id) *prog_id = xdp.prog_id; return xdp.prog_attached; } -static int dev_xdp_install(struct net_device *dev, xdp_op_t xdp_op, +static int dev_xdp_install(struct net_device *dev, bpf_op_t bpf_op, struct netlink_ext_ack *extack, u32 flags, struct bpf_prog *prog) { - struct netdev_xdp xdp; + struct netdev_bpf xdp; memset(&xdp, 0, sizeof(xdp)); if (flags & XDP_FLAGS_HW_MODE) @@ -7023,7 +7102,7 @@ static int dev_xdp_install(struct net_device *dev, xdp_op_t xdp_op, xdp.flags = flags; xdp.prog = prog; - return xdp_op(dev, &xdp); + return bpf_op(dev, &xdp); } /** @@ -7040,32 +7119,36 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, { const struct net_device_ops *ops = dev->netdev_ops; struct bpf_prog *prog = NULL; - xdp_op_t xdp_op, xdp_chk; + bpf_op_t bpf_op, bpf_chk; int err; ASSERT_RTNL(); - xdp_op = xdp_chk = ops->ndo_xdp; - if (!xdp_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE))) + bpf_op = bpf_chk = ops->ndo_bpf; + if (!bpf_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE))) return -EOPNOTSUPP; - if (!xdp_op || (flags & XDP_FLAGS_SKB_MODE)) - xdp_op = generic_xdp_install; - if (xdp_op == xdp_chk) - xdp_chk = generic_xdp_install; + if (!bpf_op || (flags & XDP_FLAGS_SKB_MODE)) + bpf_op = generic_xdp_install; + if (bpf_op == bpf_chk) + bpf_chk = generic_xdp_install; if (fd >= 0) { - if (xdp_chk && __dev_xdp_attached(dev, xdp_chk, NULL)) + if (bpf_chk && __dev_xdp_attached(dev, bpf_chk, NULL)) return -EEXIST; if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && - __dev_xdp_attached(dev, xdp_op, NULL)) + __dev_xdp_attached(dev, bpf_op, NULL)) return -EBUSY; - prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP); + if (bpf_op == ops->ndo_bpf) + prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP, + dev); + else + prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP); if (IS_ERR(prog)) return PTR_ERR(prog); } - err = dev_xdp_install(dev, xdp_op, extack, flags, prog); + err = dev_xdp_install(dev, bpf_op, extack, flags, prog); if (err < 0 && prog) bpf_prog_put(prog); @@ -7157,7 +7240,7 @@ static void rollback_registered_many(struct list_head *head) if (!dev->rtnl_link_ops || dev->rtnl_link_state == RTNL_LINK_INITIALIZED) skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, - GFP_KERNEL); + GFP_KERNEL, NULL); /* * Flush the unicast and multicast chains @@ -7994,7 +8077,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned int txqs, unsigned int rxqs) { struct net_device *dev; - size_t alloc_size; + unsigned int alloc_size; struct net_device *p; BUG_ON(strlen(name) >= sizeof(dev->name)); @@ -8244,7 +8327,7 @@ EXPORT_SYMBOL(unregister_netdev); int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat) { - int err; + int err, new_nsid; ASSERT_RTNL(); @@ -8300,7 +8383,11 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char call_netdevice_notifiers(NETDEV_UNREGISTER, dev); rcu_barrier(); call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); - rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL); + if (dev->rtnl_link_ops && dev->rtnl_link_ops->get_link_net) + new_nsid = peernet2id_alloc(dev_net(dev), net); + else + new_nsid = peernet2id(dev_net(dev), net); + rtmsg_ifinfo_newnet(RTM_DELLINK, dev, ~0U, GFP_KERNEL, &new_nsid); /* * Flush the unicast and multicast chains @@ -8562,6 +8649,8 @@ static void __net_exit netdev_exit(struct net *net) { kfree(net->dev_name_head); kfree(net->dev_index_head); + if (net != &init_net) + WARN_ON_ONCE(!list_empty(&net->dev_base_head)); } static struct pernet_operations __net_initdata netdev_net_ops = { diff --git a/net/core/dst.c b/net/core/dst.c index a6c47da7d0f8..662a2d4a3d19 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -322,3 +322,19 @@ metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags) return md_dst; } EXPORT_SYMBOL_GPL(metadata_dst_alloc_percpu); + +void metadata_dst_free_percpu(struct metadata_dst __percpu *md_dst) +{ +#ifdef CONFIG_DST_CACHE + int cpu; + + for_each_possible_cpu(cpu) { + struct metadata_dst *one_md_dst = per_cpu_ptr(md_dst, cpu); + + if (one_md_dst->type == METADATA_IP_TUNNEL) + dst_cache_destroy(&one_md_dst->u.tun_info.dst_cache); + } +#endif + free_percpu(md_dst); +} +EXPORT_SYMBOL_GPL(metadata_dst_free_percpu); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 9a9a3d77e327..f8fcf450a36e 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -403,6 +403,22 @@ static int __ethtool_set_flags(struct net_device *dev, u32 data) return 0; } +/* Given two link masks, AND them together and save the result in dst. */ +void ethtool_intersect_link_masks(struct ethtool_link_ksettings *dst, + struct ethtool_link_ksettings *src) +{ + unsigned int size = BITS_TO_LONGS(__ETHTOOL_LINK_MODE_MASK_NBITS); + unsigned int idx = 0; + + for (; idx < size; idx++) { + dst->link_modes.supported[idx] &= + src->link_modes.supported[idx]; + dst->link_modes.advertising[idx] &= + src->link_modes.advertising[idx]; + } +} +EXPORT_SYMBOL(ethtool_intersect_link_masks); + void ethtool_convert_legacy_u32_to_link_mode(unsigned long *dst, u32 legacy_u32) { diff --git a/net/core/fib_notifier.c b/net/core/fib_notifier.c index 4fc202dbdfb6..0c048bdeb016 100644 --- a/net/core/fib_notifier.c +++ b/net/core/fib_notifier.c @@ -34,12 +34,14 @@ static unsigned int fib_seq_sum(void) rtnl_lock(); for_each_net(net) { - list_for_each_entry(ops, &net->fib_notifier_ops, list) { + rcu_read_lock(); + list_for_each_entry_rcu(ops, &net->fib_notifier_ops, list) { if (!try_module_get(ops->owner)) continue; fib_seq += ops->fib_seq_read(net); module_put(ops->owner); } + rcu_read_unlock(); } rtnl_unlock(); @@ -161,8 +163,14 @@ static int __net_init fib_notifier_net_init(struct net *net) return 0; } +static void __net_exit fib_notifier_net_exit(struct net *net) +{ + WARN_ON_ONCE(!list_empty(&net->fib_notifier_ops)); +} + static struct pernet_operations fib_notifier_net_ops = { .init = fib_notifier_net_init, + .exit = fib_notifier_net_exit, }; static int __init fib_notifier_init(void) diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 9a6d97c1d810..98e1066c3d55 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -314,10 +314,12 @@ static int call_fib_rule_notifier(struct notifier_block *nb, struct net *net, static int call_fib_rule_notifiers(struct net *net, enum fib_event_type event_type, struct fib_rule *rule, - struct fib_rules_ops *ops) + struct fib_rules_ops *ops, + struct netlink_ext_ack *extack) { struct fib_rule_notifier_info info = { .info.family = ops->family, + .info.extack = extack, .rule = rule, }; @@ -609,7 +611,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, if (rule->tun_id) ip_tunnel_need_metadata(); - call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule, ops); + call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule, ops, extack); notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid); flush_route_cache(ops); rules_ops_put(ops); @@ -749,7 +751,8 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, } } - call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops); + call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops, + NULL); notify_rule_change(RTM_DELRULE, rule, ops, nlh, NETLINK_CB(skb).portid); fib_rule_put(rule); @@ -1019,8 +1022,14 @@ static int __net_init fib_rules_net_init(struct net *net) return 0; } +static void __net_exit fib_rules_net_exit(struct net *net) +{ + WARN_ON_ONCE(!list_empty(&net->rules_ops)); +} + static struct pernet_operations fib_rules_net_ops = { .init = fib_rules_net_init, + .exit = fib_rules_net_exit, }; static int __init fib_rules_init(void) diff --git a/net/core/filter.c b/net/core/filter.c index 6ae94f825f72..1afa17935954 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -43,6 +43,7 @@ #include <linux/timer.h> #include <linux/uaccess.h> #include <asm/unaligned.h> +#include <asm/cmpxchg.h> #include <linux/filter.h> #include <linux/ratelimit.h> #include <linux/seccomp.h> @@ -1406,7 +1407,7 @@ static inline int bpf_try_make_writable(struct sk_buff *skb, { int err = __bpf_try_make_writable(skb, write_len); - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); return err; } @@ -1968,7 +1969,7 @@ BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto, ret = skb_vlan_push(skb, vlan_proto, vlan_tci); bpf_pull_mac_rcsum(skb); - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); return ret; } @@ -1990,7 +1991,7 @@ BPF_CALL_1(bpf_skb_vlan_pop, struct sk_buff *, skb) ret = skb_vlan_pop(skb); bpf_pull_mac_rcsum(skb); - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); return ret; } @@ -2184,7 +2185,7 @@ BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto, * need to be verified first. */ ret = bpf_skb_proto_xlat(skb, proto); - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); return ret; } @@ -2309,7 +2310,7 @@ static int bpf_skb_adjust_net(struct sk_buff *skb, s32 len_diff) ret = shrink ? bpf_skb_net_shrink(skb, len_diff_abs) : bpf_skb_net_grow(skb, len_diff_abs); - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); return ret; } @@ -2400,7 +2401,7 @@ BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, skb_gso_reset(skb); } - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); return ret; } @@ -2440,7 +2441,7 @@ BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, skb_reset_mac_header(skb); } - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); return 0; } @@ -2453,14 +2454,26 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = { .arg3_type = ARG_ANYTHING, }; +static unsigned long xdp_get_metalen(const struct xdp_buff *xdp) +{ + return xdp_data_meta_unsupported(xdp) ? 0 : + xdp->data - xdp->data_meta; +} + BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset) { + unsigned long metalen = xdp_get_metalen(xdp); + void *data_start = xdp->data_hard_start + metalen; void *data = xdp->data + offset; - if (unlikely(data < xdp->data_hard_start || + if (unlikely(data < data_start || data > xdp->data_end - ETH_HLEN)) return -EINVAL; + if (metalen) + memmove(xdp->data_meta + offset, + xdp->data_meta, metalen); + xdp->data_meta += offset; xdp->data = data; return 0; @@ -2474,6 +2487,33 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = { .arg2_type = ARG_ANYTHING, }; +BPF_CALL_2(bpf_xdp_adjust_meta, struct xdp_buff *, xdp, int, offset) +{ + void *meta = xdp->data_meta + offset; + unsigned long metalen = xdp->data - meta; + + if (xdp_data_meta_unsupported(xdp)) + return -ENOTSUPP; + if (unlikely(meta < xdp->data_hard_start || + meta > xdp->data)) + return -EINVAL; + if (unlikely((metalen & (sizeof(__u32) - 1)) || + (metalen > 32))) + return -EACCES; + + xdp->data_meta = meta; + + return 0; +} + +static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = { + .func = bpf_xdp_adjust_meta, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + static int __bpf_tx_xdp(struct net_device *dev, struct bpf_map *map, struct xdp_buff *xdp, @@ -2488,10 +2528,36 @@ static int __bpf_tx_xdp(struct net_device *dev, err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp); if (err) return err; - if (map) + dev->netdev_ops->ndo_xdp_flush(dev); + return 0; +} + +static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd, + struct bpf_map *map, + struct xdp_buff *xdp, + u32 index) +{ + int err; + + if (map->map_type == BPF_MAP_TYPE_DEVMAP) { + struct net_device *dev = fwd; + + if (!dev->netdev_ops->ndo_xdp_xmit) + return -EOPNOTSUPP; + + err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp); + if (err) + return err; __dev_map_insert_ctx(map, index); - else - dev->netdev_ops->ndo_xdp_flush(dev); + + } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) { + struct bpf_cpu_map_entry *rcpu = fwd; + + err = cpu_map_enqueue(rcpu, xdp, dev_rx); + if (err) + return err; + __cpu_map_insert_ctx(map, index); + } return 0; } @@ -2501,11 +2567,33 @@ void xdp_do_flush_map(void) struct bpf_map *map = ri->map_to_flush; ri->map_to_flush = NULL; - if (map) - __dev_map_flush(map); + if (map) { + switch (map->map_type) { + case BPF_MAP_TYPE_DEVMAP: + __dev_map_flush(map); + break; + case BPF_MAP_TYPE_CPUMAP: + __cpu_map_flush(map); + break; + default: + break; + } + } } EXPORT_SYMBOL_GPL(xdp_do_flush_map); +static 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_CPUMAP: + return __cpu_map_lookup_elem(map, index); + default: + return NULL; + } +} + static inline bool xdp_map_invalid(const struct bpf_prog *xdp_prog, unsigned long aux) { @@ -2518,8 +2606,8 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp, struct redirect_info *ri = this_cpu_ptr(&redirect_info); unsigned long map_owner = ri->map_owner; struct bpf_map *map = ri->map; - struct net_device *fwd = NULL; u32 index = ri->ifindex; + void *fwd = NULL; int err; ri->ifindex = 0; @@ -2532,7 +2620,7 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp, goto err; } - fwd = __dev_map_lookup_elem(map, index); + fwd = __xdp_map_lookup_elem(map, index); if (!fwd) { err = -EINVAL; goto err; @@ -2540,7 +2628,7 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp, if (ri->map_to_flush && ri->map_to_flush != map) xdp_do_flush_map(); - err = __bpf_tx_xdp(fwd, map, xdp, index); + err = __bpf_tx_xdp_map(dev, fwd, map, xdp, index); if (unlikely(err)) goto err; @@ -2582,54 +2670,88 @@ err: } EXPORT_SYMBOL_GPL(xdp_do_redirect); -int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, - struct bpf_prog *xdp_prog) +static int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, struct net_device *fwd) +{ + unsigned int len; + + if (unlikely(!(fwd->flags & IFF_UP))) + return -ENETDOWN; + + len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN; + if (skb->len > len) + return -EMSGSIZE; + + return 0; +} + +int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb, + struct bpf_prog *xdp_prog) { struct redirect_info *ri = this_cpu_ptr(&redirect_info); unsigned long map_owner = ri->map_owner; struct bpf_map *map = ri->map; struct net_device *fwd = NULL; u32 index = ri->ifindex; - unsigned int len; int err = 0; ri->ifindex = 0; ri->map = NULL; ri->map_owner = 0; - if (map) { - if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) { - err = -EFAULT; - map = NULL; - goto err; - } - fwd = __dev_map_lookup_elem(map, index); - } else { - fwd = dev_get_by_index_rcu(dev_net(dev), index); + if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) { + err = -EFAULT; + map = NULL; + goto err; } + fwd = __xdp_map_lookup_elem(map, index); if (unlikely(!fwd)) { err = -EINVAL; goto err; } - if (unlikely(!(fwd->flags & IFF_UP))) { - err = -ENETDOWN; + if (map->map_type == BPF_MAP_TYPE_DEVMAP) { + if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd)))) + goto err; + skb->dev = fwd; + } else { + /* TODO: Handle BPF_MAP_TYPE_CPUMAP */ + err = -EBADRQC; goto err; } - len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN; - if (skb->len > len) { - err = -EMSGSIZE; + _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index); + return 0; +err: + _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err); + return err; +} + +int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, + struct bpf_prog *xdp_prog) +{ + struct redirect_info *ri = this_cpu_ptr(&redirect_info); + u32 index = ri->ifindex; + struct net_device *fwd; + int err = 0; + + if (ri->map) + return xdp_do_generic_redirect_map(dev, skb, xdp_prog); + + ri->ifindex = 0; + fwd = dev_get_by_index_rcu(dev_net(dev), index); + if (unlikely(!fwd)) { + err = -EINVAL; goto err; } + if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd)))) + goto err; + skb->dev = fwd; - map ? _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index) - : _trace_xdp_redirect(dev, xdp_prog, index); + _trace_xdp_redirect(dev, xdp_prog, index); return 0; err: - map ? _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err) - : _trace_xdp_redirect_err(dev, xdp_prog, index, err); + _trace_xdp_redirect_err(dev, xdp_prog, index, err); return err; } EXPORT_SYMBOL_GPL(xdp_do_generic_redirect); @@ -2698,7 +2820,8 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_clone_redirect || func == bpf_l3_csum_replace || func == bpf_l4_csum_replace || - func == bpf_xdp_adjust_head) + func == bpf_xdp_adjust_head || + func == bpf_xdp_adjust_meta) return true; return false; @@ -2949,14 +3072,15 @@ static const struct bpf_func_proto * bpf_get_skb_set_tunnel_proto(enum bpf_func_id which) { if (!md_dst) { - /* Race is not possible, since it's called from verifier - * that is holding verifier mutex. - */ - md_dst = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX, - METADATA_IP_TUNNEL, - GFP_KERNEL); - if (!md_dst) + struct metadata_dst __percpu *tmp; + + tmp = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX, + METADATA_IP_TUNNEL, + GFP_KERNEL); + if (!tmp) return NULL; + if (cmpxchg(&md_dst, NULL, tmp)) + metadata_dst_free_percpu(tmp); } switch (which) { @@ -3151,7 +3275,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, static const struct bpf_func_proto bpf_setsockopt_proto = { .func = bpf_setsockopt, - .gpl_only = true, + .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, @@ -3160,6 +3284,47 @@ static const struct bpf_func_proto bpf_setsockopt_proto = { .arg5_type = ARG_CONST_SIZE, }; +BPF_CALL_5(bpf_getsockopt, struct bpf_sock_ops_kern *, bpf_sock, + int, level, int, optname, char *, optval, int, optlen) +{ + struct sock *sk = bpf_sock->sk; + + if (!sk_fullsock(sk)) + goto err_clear; + +#ifdef CONFIG_INET + if (level == SOL_TCP && sk->sk_prot->getsockopt == tcp_getsockopt) { + if (optname == TCP_CONGESTION) { + struct inet_connection_sock *icsk = inet_csk(sk); + + if (!icsk->icsk_ca_ops || optlen <= 1) + goto err_clear; + strncpy(optval, icsk->icsk_ca_ops->name, optlen); + optval[optlen - 1] = 0; + } else { + goto err_clear; + } + } else { + goto err_clear; + } + return 0; +#endif +err_clear: + memset(optval, 0, optlen); + return -EINVAL; +} + +static const struct bpf_func_proto bpf_getsockopt_proto = { + .func = bpf_getsockopt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_UNINIT_MEM, + .arg5_type = ARG_CONST_SIZE, +}; + static const struct bpf_func_proto * bpf_base_func_proto(enum bpf_func_id func_id) { @@ -3294,6 +3459,8 @@ xdp_func_proto(enum bpf_func_id func_id) return &bpf_get_smp_processor_id_proto; case BPF_FUNC_xdp_adjust_head: return &bpf_xdp_adjust_head_proto; + case BPF_FUNC_xdp_adjust_meta: + return &bpf_xdp_adjust_meta_proto; case BPF_FUNC_redirect: return &bpf_xdp_redirect_proto; case BPF_FUNC_redirect_map: @@ -3336,6 +3503,8 @@ static const struct bpf_func_proto * switch (func_id) { case BPF_FUNC_setsockopt: return &bpf_setsockopt_proto; + case BPF_FUNC_getsockopt: + return &bpf_getsockopt_proto; case BPF_FUNC_sock_map_update: return &bpf_sock_map_update_proto; default: @@ -3424,6 +3593,7 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4): case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4): case bpf_ctx_range(struct __sk_buff, data): + case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): if (size != size_default) return false; @@ -3450,6 +3620,7 @@ static bool sk_filter_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data): + case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; @@ -3474,6 +3645,7 @@ static bool lwt_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range_till(struct __sk_buff, family, local_port): + case bpf_ctx_range(struct __sk_buff, data_meta): return false; } @@ -3592,6 +3764,9 @@ static bool tc_cls_act_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; + case bpf_ctx_range(struct __sk_buff, data_meta): + info->reg_type = PTR_TO_PACKET_META; + break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; @@ -3625,6 +3800,9 @@ static bool xdp_is_valid_access(int off, int size, case offsetof(struct xdp_md, data): info->reg_type = PTR_TO_PACKET; break; + case offsetof(struct xdp_md, data_meta): + info->reg_type = PTR_TO_PACKET_META; + break; case offsetof(struct xdp_md, data_end): info->reg_type = PTR_TO_PACKET_END; break; @@ -3683,6 +3861,12 @@ static bool sk_skb_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { + switch (off) { + case bpf_ctx_range(struct __sk_buff, tc_classid): + case bpf_ctx_range(struct __sk_buff, data_meta): + return false; + } + if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_index): @@ -3695,7 +3879,6 @@ static bool sk_skb_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, mark): - case bpf_ctx_range(struct __sk_buff, tc_classid): return false; case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; @@ -3853,6 +4036,15 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, offsetof(struct sk_buff, data)); break; + case offsetof(struct __sk_buff, data_meta): + off = si->off; + off -= offsetof(struct __sk_buff, data_meta); + off += offsetof(struct sk_buff, cb); + off += offsetof(struct bpf_skb_data_end, data_meta); + *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, + si->src_reg, off); + break; + case offsetof(struct __sk_buff, data_end): off = si->off; off -= offsetof(struct __sk_buff, data_end); @@ -4101,6 +4293,11 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type, si->dst_reg, si->src_reg, offsetof(struct xdp_buff, data)); break; + case offsetof(struct xdp_md, data_meta): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_meta), + si->dst_reg, si->src_reg, + offsetof(struct xdp_buff, data_meta)); + break; case offsetof(struct xdp_md, data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_end), si->dst_reg, si->src_reg, @@ -4269,68 +4466,95 @@ static u32 sk_skb_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; } -const struct bpf_verifier_ops sk_filter_prog_ops = { +const struct bpf_verifier_ops sk_filter_verifier_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; -const struct bpf_verifier_ops tc_cls_act_prog_ops = { +const struct bpf_prog_ops sk_filter_prog_ops = { +}; + +const struct bpf_verifier_ops tc_cls_act_verifier_ops = { .get_func_proto = tc_cls_act_func_proto, .is_valid_access = tc_cls_act_is_valid_access, .convert_ctx_access = tc_cls_act_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, +}; + +const struct bpf_prog_ops tc_cls_act_prog_ops = { .test_run = bpf_prog_test_run_skb, }; -const struct bpf_verifier_ops xdp_prog_ops = { +const struct bpf_verifier_ops xdp_verifier_ops = { .get_func_proto = xdp_func_proto, .is_valid_access = xdp_is_valid_access, .convert_ctx_access = xdp_convert_ctx_access, +}; + +const struct bpf_prog_ops xdp_prog_ops = { .test_run = bpf_prog_test_run_xdp, }; -const struct bpf_verifier_ops cg_skb_prog_ops = { +const struct bpf_verifier_ops cg_skb_verifier_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, +}; + +const struct bpf_prog_ops cg_skb_prog_ops = { .test_run = bpf_prog_test_run_skb, }; -const struct bpf_verifier_ops lwt_inout_prog_ops = { +const struct bpf_verifier_ops lwt_inout_verifier_ops = { .get_func_proto = lwt_inout_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, +}; + +const struct bpf_prog_ops lwt_inout_prog_ops = { .test_run = bpf_prog_test_run_skb, }; -const struct bpf_verifier_ops lwt_xmit_prog_ops = { +const struct bpf_verifier_ops lwt_xmit_verifier_ops = { .get_func_proto = lwt_xmit_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, +}; + +const struct bpf_prog_ops lwt_xmit_prog_ops = { .test_run = bpf_prog_test_run_skb, }; -const struct bpf_verifier_ops cg_sock_prog_ops = { +const struct bpf_verifier_ops cg_sock_verifier_ops = { .get_func_proto = sock_filter_func_proto, .is_valid_access = sock_filter_is_valid_access, .convert_ctx_access = sock_filter_convert_ctx_access, }; -const struct bpf_verifier_ops sock_ops_prog_ops = { +const struct bpf_prog_ops cg_sock_prog_ops = { +}; + +const struct bpf_verifier_ops sock_ops_verifier_ops = { .get_func_proto = sock_ops_func_proto, .is_valid_access = sock_ops_is_valid_access, .convert_ctx_access = sock_ops_convert_ctx_access, }; -const struct bpf_verifier_ops sk_skb_prog_ops = { +const struct bpf_prog_ops sock_ops_prog_ops = { +}; + +const struct bpf_verifier_ops sk_skb_verifier_ops = { .get_func_proto = sk_skb_func_proto, .is_valid_access = sk_skb_is_valid_access, .convert_ctx_access = sk_skb_convert_ctx_access, .gen_prologue = sk_skb_prologue, }; +const struct bpf_prog_ops sk_skb_prog_ops = { +}; + int sk_detach_filter(struct sock *sk) { int ret = -ENOENT; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 0a977373d003..15ce30063765 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -5,10 +5,12 @@ #include <linux/ipv6.h> #include <linux/if_vlan.h> #include <net/dsa.h> +#include <net/dst_metadata.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/gre.h> #include <net/pptp.h> +#include <net/tipc.h> #include <linux/igmp.h> #include <linux/icmp.h> #include <linux/sctp.h> @@ -115,6 +117,102 @@ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, } EXPORT_SYMBOL(__skb_flow_get_ports); +static void +skb_flow_dissect_set_enc_addr_type(enum flow_dissector_key_id type, + struct flow_dissector *flow_dissector, + void *target_container) +{ + struct flow_dissector_key_control *ctrl; + + if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL)) + return; + + ctrl = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_CONTROL, + target_container); + ctrl->addr_type = type; +} + +static void +__skb_flow_dissect_tunnel_info(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container) +{ + struct ip_tunnel_info *info; + struct ip_tunnel_key *key; + + /* A quick check to see if there might be something to do. */ + if (!dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_KEYID) && + !dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) && + !dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) && + !dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_CONTROL) && + !dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_PORTS)) + return; + + info = skb_tunnel_info(skb); + if (!info) + return; + + key = &info->key; + + switch (ip_tunnel_info_af(info)) { + case AF_INET: + skb_flow_dissect_set_enc_addr_type(FLOW_DISSECTOR_KEY_IPV4_ADDRS, + flow_dissector, + target_container); + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { + struct flow_dissector_key_ipv4_addrs *ipv4; + + ipv4 = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, + target_container); + ipv4->src = key->u.ipv4.src; + ipv4->dst = key->u.ipv4.dst; + } + break; + case AF_INET6: + skb_flow_dissect_set_enc_addr_type(FLOW_DISSECTOR_KEY_IPV6_ADDRS, + flow_dissector, + target_container); + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) { + struct flow_dissector_key_ipv6_addrs *ipv6; + + ipv6 = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, + target_container); + ipv6->src = key->u.ipv6.src; + ipv6->dst = key->u.ipv6.dst; + } + break; + } + + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_dissector_key_keyid *keyid; + + keyid = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_KEYID, + target_container); + keyid->keyid = tunnel_id_to_key32(key->tun_id); + } + + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) { + struct flow_dissector_key_ports *tp; + + tp = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_PORTS, + target_container); + tp->src = key->tp_src; + tp->dst = key->tp_dst; + } +} + static enum flow_dissect_ret __skb_flow_dissect_mpls(const struct sk_buff *skb, struct flow_dissector *flow_dissector, @@ -478,6 +576,9 @@ bool __skb_flow_dissect(const struct sk_buff *skb, FLOW_DISSECTOR_KEY_BASIC, target_container); + __skb_flow_dissect_tunnel_info(skb, flow_dissector, + target_container); + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct ethhdr *eth = eth_hdr(skb); @@ -672,23 +773,22 @@ proto_again: break; } case htons(ETH_P_TIPC): { - struct { - __be32 pre[3]; - __be32 srcnode; - } *hdr, _hdr; - hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); + struct tipc_basic_hdr *hdr, _hdr; + + hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), + data, hlen, &_hdr); if (!hdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_TIPC_ADDRS)) { + FLOW_DISSECTOR_KEY_TIPC)) { key_addrs = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_TIPC_ADDRS, + FLOW_DISSECTOR_KEY_TIPC, target_container); - key_addrs->tipcaddrs.srcnode = hdr->srcnode; - key_control->addr_type = FLOW_DISSECTOR_KEY_TIPC_ADDRS; + key_addrs->tipckey.key = tipc_hdr_rps_key(hdr); + key_control->addr_type = FLOW_DISSECTOR_KEY_TIPC; } fdret = FLOW_DISSECT_RET_OUT_GOOD; break; @@ -924,8 +1024,8 @@ static inline size_t flow_keys_hash_length(const struct flow_keys *flow) case FLOW_DISSECTOR_KEY_IPV6_ADDRS: diff -= sizeof(flow->addrs.v6addrs); break; - case FLOW_DISSECTOR_KEY_TIPC_ADDRS: - diff -= sizeof(flow->addrs.tipcaddrs); + case FLOW_DISSECTOR_KEY_TIPC: + diff -= sizeof(flow->addrs.tipckey); break; } return (sizeof(*flow) - diff) / sizeof(u32); @@ -939,8 +1039,8 @@ __be32 flow_get_u32_src(const struct flow_keys *flow) case FLOW_DISSECTOR_KEY_IPV6_ADDRS: return (__force __be32)ipv6_addr_hash( &flow->addrs.v6addrs.src); - case FLOW_DISSECTOR_KEY_TIPC_ADDRS: - return flow->addrs.tipcaddrs.srcnode; + case FLOW_DISSECTOR_KEY_TIPC: + return flow->addrs.tipckey.key; default: return 0; } @@ -1221,8 +1321,8 @@ static const struct flow_dissector_key flow_keys_dissector_keys[] = { .offset = offsetof(struct flow_keys, addrs.v6addrs), }, { - .key_id = FLOW_DISSECTOR_KEY_TIPC_ADDRS, - .offset = offsetof(struct flow_keys, addrs.tipcaddrs), + .key_id = FLOW_DISSECTOR_KEY_TIPC, + .offset = offsetof(struct flow_keys, addrs.tipckey), }, { .key_id = FLOW_DISSECTOR_KEY_PORTS, diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 1307731ddfe4..e7e626fb87bb 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -51,7 +51,7 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, */ preempt_disable(); rcu_read_lock(); - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); ret = bpf_prog_run_save_cb(lwt->prog, skb); rcu_read_unlock(); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 16a1a4c4eb57..6ea3a1a7f36a 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -457,7 +457,7 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net, const void *pkey) { struct neighbour *n; - int key_len = tbl->key_len; + unsigned int key_len = tbl->key_len; u32 hash_val; struct neigh_hash_table *nht; @@ -488,7 +488,7 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, struct net_device *dev, bool want_ref) { u32 hash_val; - int key_len = tbl->key_len; + unsigned int key_len = tbl->key_len; int error; struct neighbour *n1, *rc, *n = neigh_alloc(tbl, dev); struct neigh_hash_table *nht; @@ -572,7 +572,7 @@ out_neigh_release: } EXPORT_SYMBOL(__neigh_create); -static u32 pneigh_hash(const void *pkey, int key_len) +static u32 pneigh_hash(const void *pkey, unsigned int key_len) { u32 hash_val = *(u32 *)(pkey + key_len - 4); hash_val ^= (hash_val >> 16); @@ -585,7 +585,7 @@ static u32 pneigh_hash(const void *pkey, int key_len) static struct pneigh_entry *__pneigh_lookup_1(struct pneigh_entry *n, struct net *net, const void *pkey, - int key_len, + unsigned int key_len, struct net_device *dev) { while (n) { @@ -601,7 +601,7 @@ static struct pneigh_entry *__pneigh_lookup_1(struct pneigh_entry *n, struct pneigh_entry *__pneigh_lookup(struct neigh_table *tbl, struct net *net, const void *pkey, struct net_device *dev) { - int key_len = tbl->key_len; + unsigned int key_len = tbl->key_len; u32 hash_val = pneigh_hash(pkey, key_len); return __pneigh_lookup_1(tbl->phash_buckets[hash_val], @@ -614,7 +614,7 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, struct net_device *dev, int creat) { struct pneigh_entry *n; - int key_len = tbl->key_len; + unsigned int key_len = tbl->key_len; u32 hash_val = pneigh_hash(pkey, key_len); read_lock_bh(&tbl->lock); @@ -659,7 +659,7 @@ int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey, struct net_device *dev) { struct pneigh_entry *n, **np; - int key_len = tbl->key_len; + unsigned int key_len = tbl->key_len; u32 hash_val = pneigh_hash(pkey, key_len); write_lock_bh(&tbl->lock); @@ -1662,7 +1662,7 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, if (tbl == NULL) return -EAFNOSUPPORT; - if (nla_len(dst_attr) < tbl->key_len) + if (nla_len(dst_attr) < (int)tbl->key_len) goto out; if (ndm->ndm_flags & NTF_PROXY) { @@ -1730,7 +1730,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, if (tbl == NULL) return -EAFNOSUPPORT; - if (nla_len(tb[NDA_DST]) < tbl->key_len) + if (nla_len(tb[NDA_DST]) < (int)tbl->key_len) goto out; dst = nla_data(tb[NDA_DST]); lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 927a6dcbad96..799b75268291 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -382,7 +382,7 @@ static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr, struct net_device *netdev = to_net_dev(dev); struct net *net = dev_net(netdev); size_t count = len; - ssize_t ret; + ssize_t ret = 0; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; @@ -393,23 +393,30 @@ static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr, if (!rtnl_trylock()) return restart_syscall(); - ret = dev_set_alias(netdev, buf, count); + + if (dev_isalive(netdev)) { + ret = dev_set_alias(netdev, buf, count); + if (ret < 0) + goto err; + ret = len; + netdev_state_change(netdev); + } +err: rtnl_unlock(); - return ret < 0 ? ret : len; + return ret; } static ssize_t ifalias_show(struct device *dev, struct device_attribute *attr, char *buf) { const struct net_device *netdev = to_net_dev(dev); + char tmp[IFALIASZ]; ssize_t ret = 0; - if (!rtnl_trylock()) - return restart_syscall(); - if (netdev->ifalias) - ret = sprintf(buf, "%s\n", netdev->ifalias); - rtnl_unlock(); + ret = dev_get_alias(netdev, tmp, sizeof(tmp)); + if (ret > 0) + ret = sprintf(buf, "%s\n", tmp); return ret; } static DEVICE_ATTR_RW(ifalias); @@ -1488,7 +1495,10 @@ static void netdev_release(struct device *d) BUG_ON(dev->reg_state != NETREG_RELEASED); - kfree(dev->ifalias); + /* no need to wait for rcu grace period: + * device is dead and about to be freed. + */ + kfree(rcu_access_pointer(dev->ifalias)); netdev_freemem(dev); } diff --git a/net/core/net-traces.c b/net/core/net-traces.c index 71f209542364..380934580fa1 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -32,6 +32,7 @@ #include <trace/events/napi.h> #include <trace/events/sock.h> #include <trace/events/udp.h> +#include <trace/events/tcp.h> #include <trace/events/fib.h> #include <trace/events/qdisc.h> #if IS_ENABLED(CONFIG_IPV6) @@ -49,3 +50,5 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_update); EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb); EXPORT_TRACEPOINT_SYMBOL_GPL(napi_poll); + +EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_send_reset); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 6cfdc7c84c48..b797832565d3 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -234,6 +234,7 @@ int peernet2id_alloc(struct net *net, struct net *peer) rtnl_net_notifyid(net, RTM_NEWNSID, id); return id; } +EXPORT_SYMBOL_GPL(peernet2id_alloc); /* This function returns, if assigned, the id of a peer netns. */ int peernet2id(struct net *net, struct net *peer) diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 912731bed7b7..57557a6a950c 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -334,7 +334,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, /* It is up to the caller to keep npinfo alive. */ struct netpoll_info *npinfo; - WARN_ON_ONCE(!irqs_disabled()); + lockdep_assert_irqs_disabled(); npinfo = rcu_dereference_bh(np->dev->npinfo); if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) { diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 6e1e10ff433a..f95a15086225 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2165,7 +2165,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) + pkt_dev->pkt_overhead; } - for (i = 0; i < IN6_ADDR_HSIZE; i++) + for (i = 0; i < sizeof(struct in6_addr); i++) if (pkt_dev->cur_in6_saddr.s6_addr[i]) { set = 1; break; @@ -2711,7 +2711,7 @@ static inline __be16 build_tci(unsigned int id, unsigned int cfi, static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb, int datalen) { - struct timeval timestamp; + struct timespec64 timestamp; struct pktgen_hdr *pgh; pgh = skb_put(skb, sizeof(*pgh)); @@ -2773,9 +2773,17 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb, pgh->tv_sec = 0; pgh->tv_usec = 0; } else { - do_gettimeofday(×tamp); + /* + * pgh->tv_sec wraps in y2106 when interpreted as unsigned + * as done by wireshark, or y2038 when interpreted as signed. + * This is probably harmless, but if anyone wants to improve + * it, we could introduce a variant that puts 64-bit nanoseconds + * into the respective header bytes. + * This would also be slightly faster to read. + */ + ktime_get_real_ts64(×tamp); pgh->tv_sec = htonl(timestamp.tv_sec); - pgh->tv_usec = htonl(timestamp.tv_usec); + pgh->tv_usec = htonl(timestamp.tv_nsec / NSEC_PER_USEC); } } @@ -3377,7 +3385,7 @@ static void pktgen_wait_for_skb(struct pktgen_dev *pkt_dev) static void pktgen_xmit(struct pktgen_dev *pkt_dev) { - unsigned int burst = ACCESS_ONCE(pkt_dev->burst); + unsigned int burst = READ_ONCE(pkt_dev->burst); struct net_device *odev = pkt_dev->odev; struct netdev_queue *txq; struct sk_buff *skb; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5ace48926b19..dabba2a91fc8 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -453,7 +453,7 @@ static const struct rtnl_af_ops *rtnl_af_lookup(const int family) { const struct rtnl_af_ops *ops; - list_for_each_entry(ops, &rtnl_af_ops, list) { + list_for_each_entry_rcu(ops, &rtnl_af_ops, list) { if (ops->family == family) return ops; } @@ -470,32 +470,22 @@ static const struct rtnl_af_ops *rtnl_af_lookup(const int family) void rtnl_af_register(struct rtnl_af_ops *ops) { rtnl_lock(); - list_add_tail(&ops->list, &rtnl_af_ops); + list_add_tail_rcu(&ops->list, &rtnl_af_ops); rtnl_unlock(); } EXPORT_SYMBOL_GPL(rtnl_af_register); /** - * __rtnl_af_unregister - Unregister rtnl_af_ops from rtnetlink. - * @ops: struct rtnl_af_ops * to unregister - * - * The caller must hold the rtnl_mutex. - */ -void __rtnl_af_unregister(struct rtnl_af_ops *ops) -{ - list_del(&ops->list); -} -EXPORT_SYMBOL_GPL(__rtnl_af_unregister); - -/** * rtnl_af_unregister - Unregister rtnl_af_ops from rtnetlink. * @ops: struct rtnl_af_ops * to unregister */ void rtnl_af_unregister(struct rtnl_af_ops *ops) { rtnl_lock(); - __rtnl_af_unregister(ops); + list_del_rcu(&ops->list); rtnl_unlock(); + + synchronize_rcu(); } EXPORT_SYMBOL_GPL(rtnl_af_unregister); @@ -508,13 +498,15 @@ static size_t rtnl_link_get_af_size(const struct net_device *dev, /* IFLA_AF_SPEC */ size = nla_total_size(sizeof(struct nlattr)); - list_for_each_entry(af_ops, &rtnl_af_ops, list) { + rcu_read_lock(); + list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) { if (af_ops->get_link_af_size) { /* AF_* + nested data */ size += nla_total_size(sizeof(struct nlattr)) + af_ops->get_link_af_size(dev, ext_filter_mask); } } + rcu_read_unlock(); return size; } @@ -522,11 +514,15 @@ static size_t rtnl_link_get_af_size(const struct net_device *dev, static bool rtnl_have_link_slave_info(const struct net_device *dev) { struct net_device *master_dev; + bool ret = false; - master_dev = netdev_master_upper_dev_get((struct net_device *) dev); + rcu_read_lock(); + + master_dev = netdev_master_upper_dev_get_rcu((struct net_device *)dev); if (master_dev && master_dev->rtnl_link_ops) - return true; - return false; + ret = true; + rcu_read_unlock(); + return ret; } static int rtnl_link_slave_info_fill(struct sk_buff *skb, @@ -923,8 +919,10 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */ + rtnl_xdp_size() /* IFLA_XDP */ + nla_total_size(4) /* IFLA_EVENT */ - + nla_total_size(1); /* IFLA_PROTO_DOWN */ - + + nla_total_size(4) /* IFLA_NEW_NETNSID */ + + nla_total_size(1) /* IFLA_PROTO_DOWN */ + + nla_total_size(4) /* IFLA_IF_NETNSID */ + + 0; } static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev) @@ -1211,6 +1209,36 @@ nla_put_vfinfo_failure: return -EMSGSIZE; } +static noinline_for_stack int rtnl_fill_vf(struct sk_buff *skb, + struct net_device *dev, + u32 ext_filter_mask) +{ + struct nlattr *vfinfo; + int i, num_vfs; + + if (!dev->dev.parent || ((ext_filter_mask & RTEXT_FILTER_VF) == 0)) + return 0; + + num_vfs = dev_num_vf(dev->dev.parent); + if (nla_put_u32(skb, IFLA_NUM_VF, num_vfs)) + return -EMSGSIZE; + + if (!dev->netdev_ops->ndo_get_vf_config) + return 0; + + vfinfo = nla_nest_start(skb, IFLA_VFINFO_LIST); + if (!vfinfo) + return -EMSGSIZE; + + for (i = 0; i < num_vfs; i++) { + if (rtnl_fill_vfinfo(skb, dev, i, vfinfo)) + return -EMSGSIZE; + } + + nla_nest_end(skb, vfinfo); + return 0; +} + static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev) { struct rtnl_link_ifmap map; @@ -1242,10 +1270,10 @@ static u8 rtnl_xdp_attached_mode(struct net_device *dev, u32 *prog_id) *prog_id = generic_xdp_prog->aux->id; return XDP_ATTACHED_SKB; } - if (!ops->ndo_xdp) + if (!ops->ndo_bpf) return XDP_ATTACHED_NONE; - return __dev_xdp_attached(dev, ops->ndo_xdp, prog_id); + return __dev_xdp_attached(dev, ops->ndo_bpf, prog_id); } static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev) @@ -1307,16 +1335,108 @@ static u32 rtnl_get_event(unsigned long event) return rtnl_event_type; } -static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, +static int put_master_ifindex(struct sk_buff *skb, struct net_device *dev) +{ + const struct net_device *upper_dev; + int ret = 0; + + rcu_read_lock(); + + upper_dev = netdev_master_upper_dev_get_rcu(dev); + if (upper_dev) + ret = nla_put_u32(skb, IFLA_MASTER, upper_dev->ifindex); + + rcu_read_unlock(); + return ret; +} + +static int nla_put_iflink(struct sk_buff *skb, const struct net_device *dev) +{ + int ifindex = dev_get_iflink(dev); + + if (dev->ifindex == ifindex) + return 0; + + return nla_put_u32(skb, IFLA_LINK, ifindex); +} + +static noinline_for_stack int nla_put_ifalias(struct sk_buff *skb, + struct net_device *dev) +{ + char buf[IFALIASZ]; + int ret; + + ret = dev_get_alias(dev, buf, sizeof(buf)); + return ret > 0 ? nla_put_string(skb, IFLA_IFALIAS, buf) : 0; +} + +static int rtnl_fill_link_netnsid(struct sk_buff *skb, + const struct net_device *dev, + struct net *src_net) +{ + if (dev->rtnl_link_ops && dev->rtnl_link_ops->get_link_net) { + struct net *link_net = dev->rtnl_link_ops->get_link_net(dev); + + if (!net_eq(dev_net(dev), link_net)) { + int id = peernet2id_alloc(src_net, link_net); + + if (nla_put_s32(skb, IFLA_LINK_NETNSID, id)) + return -EMSGSIZE; + } + } + + return 0; +} + +static int rtnl_fill_link_af(struct sk_buff *skb, + const struct net_device *dev, + u32 ext_filter_mask) +{ + const struct rtnl_af_ops *af_ops; + struct nlattr *af_spec; + + af_spec = nla_nest_start(skb, IFLA_AF_SPEC); + if (!af_spec) + return -EMSGSIZE; + + list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) { + struct nlattr *af; + int err; + + if (!af_ops->fill_link_af) + continue; + + af = nla_nest_start(skb, af_ops->family); + if (!af) + return -EMSGSIZE; + + err = af_ops->fill_link_af(skb, dev, ext_filter_mask); + /* + * Caller may return ENODATA to indicate that there + * was no data to be dumped. This is not an error, it + * means we should trim the attribute header and + * continue. + */ + if (err == -ENODATA) + nla_nest_cancel(skb, af); + else if (err < 0) + return -EMSGSIZE; + + nla_nest_end(skb, af); + } + + nla_nest_end(skb, af_spec); + return 0; +} + +static int rtnl_fill_ifinfo(struct sk_buff *skb, + struct net_device *dev, struct net *src_net, int type, u32 pid, u32 seq, u32 change, unsigned int flags, u32 ext_filter_mask, - u32 event) + u32 event, int *new_nsid, int tgt_netnsid) { struct ifinfomsg *ifm; struct nlmsghdr *nlh; - struct nlattr *af_spec; - struct rtnl_af_ops *af_ops; - struct net_device *upper_dev = netdev_master_upper_dev_get(dev); ASSERT_RTNL(); nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags); @@ -1331,6 +1451,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, ifm->ifi_flags = dev_get_flags(dev); ifm->ifi_change = change; + if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_IF_NETNSID, tgt_netnsid)) + goto nla_put_failure; + if (nla_put_string(skb, IFLA_IFNAME, dev->name) || nla_put_u32(skb, IFLA_TXQLEN, dev->tx_queue_len) || nla_put_u8(skb, IFLA_OPERSTATE, @@ -1345,15 +1468,12 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, #ifdef CONFIG_RPS nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) || #endif - (dev->ifindex != dev_get_iflink(dev) && - nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))) || - (upper_dev && - nla_put_u32(skb, IFLA_MASTER, upper_dev->ifindex)) || + nla_put_iflink(skb, dev) || + put_master_ifindex(skb, dev) || nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) || (dev->qdisc && nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) || - (dev->ifalias && - nla_put_string(skb, IFLA_IFALIAS, dev->ifalias)) || + nla_put_ifalias(skb, dev) || nla_put_u32(skb, IFLA_CARRIER_CHANGES, atomic_read(&dev->carrier_changes)) || nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down)) @@ -1385,27 +1505,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, if (rtnl_fill_stats(skb, dev)) goto nla_put_failure; - if (dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF) && - nla_put_u32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent))) + if (rtnl_fill_vf(skb, dev, ext_filter_mask)) goto nla_put_failure; - if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent && - ext_filter_mask & RTEXT_FILTER_VF) { - int i; - struct nlattr *vfinfo; - int num_vfs = dev_num_vf(dev->dev.parent); - - vfinfo = nla_nest_start(skb, IFLA_VFINFO_LIST); - if (!vfinfo) - goto nla_put_failure; - for (i = 0; i < num_vfs; i++) { - if (rtnl_fill_vfinfo(skb, dev, i, vfinfo)) - goto nla_put_failure; - } - - nla_nest_end(skb, vfinfo); - } - if (rtnl_port_fill(skb, dev, ext_filter_mask)) goto nla_put_failure; @@ -1417,51 +1519,23 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, goto nla_put_failure; } - if (dev->rtnl_link_ops && - dev->rtnl_link_ops->get_link_net) { - struct net *link_net = dev->rtnl_link_ops->get_link_net(dev); - - if (!net_eq(dev_net(dev), link_net)) { - int id = peernet2id_alloc(dev_net(dev), link_net); - - if (nla_put_s32(skb, IFLA_LINK_NETNSID, id)) - goto nla_put_failure; - } - } - - if (!(af_spec = nla_nest_start(skb, IFLA_AF_SPEC))) + if (rtnl_fill_link_netnsid(skb, dev, src_net)) goto nla_put_failure; - list_for_each_entry(af_ops, &rtnl_af_ops, list) { - if (af_ops->fill_link_af) { - struct nlattr *af; - int err; - - if (!(af = nla_nest_start(skb, af_ops->family))) - goto nla_put_failure; - - err = af_ops->fill_link_af(skb, dev, ext_filter_mask); - - /* - * Caller may return ENODATA to indicate that there - * was no data to be dumped. This is not an error, it - * means we should trim the attribute header and - * continue. - */ - if (err == -ENODATA) - nla_nest_cancel(skb, af); - else if (err < 0) - goto nla_put_failure; - - nla_nest_end(skb, af); - } - } + if (new_nsid && + nla_put_s32(skb, IFLA_NEW_NETNSID, *new_nsid) < 0) + goto nla_put_failure; - nla_nest_end(skb, af_spec); + rcu_read_lock(); + if (rtnl_fill_link_af(skb, dev, ext_filter_mask)) + goto nla_put_failure_rcu; + rcu_read_unlock(); nlmsg_end(skb, nlh); return 0; +nla_put_failure_rcu: + rcu_read_unlock(); nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; @@ -1503,6 +1577,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_XDP] = { .type = NLA_NESTED }, [IFLA_EVENT] = { .type = NLA_U32 }, [IFLA_GROUP] = { .type = NLA_U32 }, + [IFLA_IF_NETNSID] = { .type = NLA_S32 }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { @@ -1606,9 +1681,28 @@ static bool link_dump_filtered(struct net_device *dev, return false; } +static struct net *get_target_net(struct sk_buff *skb, int netnsid) +{ + struct net *net; + + net = get_net_ns_by_id(sock_net(skb->sk), netnsid); + if (!net) + return ERR_PTR(-EINVAL); + + /* For now, the caller is required to have CAP_NET_ADMIN in + * the user namespace owning the target net ns. + */ + if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { + put_net(net); + return ERR_PTR(-EACCES); + } + return net; +} + static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); + struct net *tgt_net = net; int h, s_h; int idx = 0, s_idx; struct net_device *dev; @@ -1618,6 +1712,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) const struct rtnl_link_ops *kind_ops = NULL; unsigned int flags = NLM_F_MULTI; int master_idx = 0; + int netnsid = -1; int err; int hdrlen; @@ -1636,6 +1731,15 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX, ifla_policy, NULL) >= 0) { + if (tb[IFLA_IF_NETNSID]) { + netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]); + tgt_net = get_target_net(skb, netnsid); + if (IS_ERR(tgt_net)) { + tgt_net = net; + netnsid = -1; + } + } + if (tb[IFLA_EXT_MASK]) ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); @@ -1651,17 +1755,19 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; - head = &net->dev_index_head[h]; + head = &tgt_net->dev_index_head[h]; hlist_for_each_entry(dev, head, index_hlist) { if (link_dump_filtered(dev, master_idx, kind_ops)) goto cont; if (idx < s_idx) goto cont; - err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, + err = rtnl_fill_ifinfo(skb, dev, net, + RTM_NEWLINK, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, 0, flags, - ext_filter_mask, 0); + ext_filter_mask, 0, NULL, + netnsid); if (err < 0) { if (likely(skb->len)) @@ -1680,6 +1786,8 @@ out_err: cb->args[0] = h; cb->seq = net->dev_base_seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); + if (netnsid >= 0) + put_net(tgt_net); return err; } @@ -1726,17 +1834,27 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) { const struct rtnl_af_ops *af_ops; - if (!(af_ops = rtnl_af_lookup(nla_type(af)))) + rcu_read_lock(); + af_ops = rtnl_af_lookup(nla_type(af)); + if (!af_ops) { + rcu_read_unlock(); return -EAFNOSUPPORT; + } - if (!af_ops->set_link_af) + if (!af_ops->set_link_af) { + rcu_read_unlock(); return -EOPNOTSUPP; + } if (af_ops->validate_link_af) { err = af_ops->validate_link_af(dev, af); - if (err < 0) + if (err < 0) { + rcu_read_unlock(); return err; + } } + + rcu_read_unlock(); } } @@ -1912,7 +2030,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) return err; } -static int do_set_master(struct net_device *dev, int ifindex) +static int do_set_master(struct net_device *dev, int ifindex, + struct netlink_ext_ack *extack) { struct net_device *upper_dev = netdev_master_upper_dev_get(dev); const struct net_device_ops *ops; @@ -1937,7 +2056,7 @@ static int do_set_master(struct net_device *dev, int ifindex) return -EINVAL; ops = upper_dev->netdev_ops; if (ops->ndo_add_slave) { - err = ops->ndo_add_slave(upper_dev, dev); + err = ops->ndo_add_slave(upper_dev, dev, extack); if (err) return err; } else { @@ -2070,7 +2189,7 @@ static int do_setlink(const struct sk_buff *skb, } if (tb[IFLA_MASTER]) { - err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER])); + err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack); if (err) goto errout; status |= DO_SETLINK_MODIFIED; @@ -2193,13 +2312,17 @@ static int do_setlink(const struct sk_buff *skb, nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) { const struct rtnl_af_ops *af_ops; - if (!(af_ops = rtnl_af_lookup(nla_type(af)))) - BUG(); + rcu_read_lock(); + + BUG_ON(!(af_ops = rtnl_af_lookup(nla_type(af)))); err = af_ops->set_link_af(dev, af); - if (err < 0) + if (err < 0) { + rcu_read_unlock(); goto errout; + } + rcu_read_unlock(); status |= DO_SETLINK_NOTIFY; } } @@ -2277,6 +2400,9 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) goto errout; + if (tb[IFLA_IF_NETNSID]) + return -EOPNOTSUPP; + if (tb[IFLA_IFNAME]) nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); else @@ -2371,6 +2497,9 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) return err; + if (tb[IFLA_IF_NETNSID]) + return -EOPNOTSUPP; + if (tb[IFLA_IFNAME]) nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); @@ -2502,6 +2631,9 @@ replay: if (err < 0) return err; + if (tb[IFLA_IF_NETNSID]) + return -EOPNOTSUPP; + if (tb[IFLA_IFNAME]) nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); else @@ -2579,12 +2711,6 @@ replay: return err; slave_data = slave_attr; } - if (m_ops->slave_validate) { - err = m_ops->slave_validate(tb, slave_data, - extack); - if (err < 0) - return err; - } } if (dev) { @@ -2714,7 +2840,8 @@ replay: goto out_unregister; } if (tb[IFLA_MASTER]) { - err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER])); + err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), + extack); if (err) goto out_unregister; } @@ -2740,11 +2867,13 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); + struct net *tgt_net = net; struct ifinfomsg *ifm; char ifname[IFNAMSIZ]; struct nlattr *tb[IFLA_MAX+1]; struct net_device *dev = NULL; struct sk_buff *nskb; + int netnsid = -1; int err; u32 ext_filter_mask = 0; @@ -2752,35 +2881,50 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) return err; + if (tb[IFLA_IF_NETNSID]) { + netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]); + tgt_net = get_target_net(skb, netnsid); + if (IS_ERR(tgt_net)) + return PTR_ERR(tgt_net); + } + if (tb[IFLA_IFNAME]) nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); if (tb[IFLA_EXT_MASK]) ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + err = -EINVAL; ifm = nlmsg_data(nlh); if (ifm->ifi_index > 0) - dev = __dev_get_by_index(net, ifm->ifi_index); + dev = __dev_get_by_index(tgt_net, ifm->ifi_index); else if (tb[IFLA_IFNAME]) - dev = __dev_get_by_name(net, ifname); + dev = __dev_get_by_name(tgt_net, ifname); else - return -EINVAL; + goto out; + err = -ENODEV; if (dev == NULL) - return -ENODEV; + goto out; + err = -ENOBUFS; nskb = nlmsg_new(if_nlmsg_size(dev, ext_filter_mask), GFP_KERNEL); if (nskb == NULL) - return -ENOBUFS; + goto out; - err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, 0, 0, ext_filter_mask, 0); + err = rtnl_fill_ifinfo(nskb, dev, net, + RTM_NEWLINK, NETLINK_CB(skb).portid, + nlh->nlmsg_seq, 0, 0, ext_filter_mask, + 0, NULL, netnsid); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size */ WARN_ON(err == -EMSGSIZE); kfree_skb(nskb); } else err = rtnl_unicast(nskb, net, NETLINK_CB(skb).portid); +out: + if (netnsid >= 0) + put_net(tgt_net); return err; } @@ -2859,7 +3003,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned int change, - u32 event, gfp_t flags) + u32 event, gfp_t flags, int *new_nsid) { struct net *net = dev_net(dev); struct sk_buff *skb; @@ -2870,7 +3014,9 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, if (skb == NULL) goto errout; - err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0, event); + err = rtnl_fill_ifinfo(skb, dev, dev_net(dev), + type, 0, 0, change, 0, 0, event, + new_nsid, -1); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -2893,14 +3039,14 @@ void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags) static void rtmsg_ifinfo_event(int type, struct net_device *dev, unsigned int change, u32 event, - gfp_t flags) + gfp_t flags, int *new_nsid) { struct sk_buff *skb; if (dev->reg_state != NETREG_REGISTERED) return; - skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags); + skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags, new_nsid); if (skb) rtmsg_ifinfo_send(skb, dev, flags); } @@ -2908,9 +3054,15 @@ static void rtmsg_ifinfo_event(int type, struct net_device *dev, void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, gfp_t flags) { - rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags); + rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags, NULL); +} + +void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change, + gfp_t flags, int *new_nsid) +{ + rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags, + new_nsid); } -EXPORT_SYMBOL(rtmsg_ifinfo); static int nlmsg_populate_fdb_fill(struct sk_buff *skb, struct net_device *dev, @@ -3017,21 +3169,21 @@ int ndo_dflt_fdb_add(struct ndmsg *ndm, } EXPORT_SYMBOL(ndo_dflt_fdb_add); -static int fdb_vid_parse(struct nlattr *vlan_attr, u16 *p_vid) +static int fdb_vid_parse(struct nlattr *vlan_attr, u16 *p_vid, + struct netlink_ext_ack *extack) { u16 vid = 0; if (vlan_attr) { if (nla_len(vlan_attr) != sizeof(u16)) { - pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan\n"); + NL_SET_ERR_MSG(extack, "invalid vlan attribute size"); return -EINVAL; } vid = nla_get_u16(vlan_attr); if (!vid || vid >= VLAN_VID_MASK) { - pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan id %d\n", - vid); + NL_SET_ERR_MSG(extack, "invalid vlan id"); return -EINVAL; } } @@ -3056,24 +3208,24 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, ndm = nlmsg_data(nlh); if (ndm->ndm_ifindex == 0) { - pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid ifindex\n"); + NL_SET_ERR_MSG(extack, "invalid ifindex"); return -EINVAL; } dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (dev == NULL) { - pr_info("PF_BRIDGE: RTM_NEWNEIGH with unknown ifindex\n"); + NL_SET_ERR_MSG(extack, "unknown ifindex"); return -ENODEV; } if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) { - pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid address\n"); + NL_SET_ERR_MSG(extack, "invalid address"); return -EINVAL; } addr = nla_data(tb[NDA_LLADDR]); - err = fdb_vid_parse(tb[NDA_VLAN], &vid); + err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack); if (err) return err; @@ -3160,24 +3312,24 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, ndm = nlmsg_data(nlh); if (ndm->ndm_ifindex == 0) { - pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid ifindex\n"); + NL_SET_ERR_MSG(extack, "invalid ifindex"); return -EINVAL; } dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (dev == NULL) { - pr_info("PF_BRIDGE: RTM_DELNEIGH with unknown ifindex\n"); + NL_SET_ERR_MSG(extack, "unknown ifindex"); return -ENODEV; } if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) { - pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid address\n"); + NL_SET_ERR_MSG(extack, "invalid address"); return -EINVAL; } addr = nla_data(tb[NDA_LLADDR]); - err = fdb_vid_parse(tb[NDA_VLAN], &vid); + err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack); if (err) return err; @@ -3617,7 +3769,7 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, dev = __dev_get_by_index(net, ifm->ifi_index); if (!dev) { - pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n"); + NL_SET_ERR_MSG(extack, "unknown ifindex"); return -ENODEV; } @@ -3692,7 +3844,7 @@ static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, dev = __dev_get_by_index(net, ifm->ifi_index); if (!dev) { - pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n"); + NL_SET_ERR_MSG(extack, "unknown ifindex"); return -ENODEV; } @@ -3943,25 +4095,30 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, if (!attr) goto nla_put_failure; - list_for_each_entry(af_ops, &rtnl_af_ops, list) { + rcu_read_lock(); + list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) { if (af_ops->fill_stats_af) { struct nlattr *af; int err; af = nla_nest_start(skb, af_ops->family); - if (!af) + if (!af) { + rcu_read_unlock(); goto nla_put_failure; - + } err = af_ops->fill_stats_af(skb, dev); - if (err == -ENODATA) + if (err == -ENODATA) { nla_nest_cancel(skb, af); - else if (err < 0) + } else if (err < 0) { + rcu_read_unlock(); goto nla_put_failure; + } nla_nest_end(skb, af); } } + rcu_read_unlock(); nla_nest_end(skb, attr); @@ -4030,7 +4187,8 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev, /* for IFLA_STATS_AF_SPEC */ size += nla_total_size(0); - list_for_each_entry(af_ops, &rtnl_af_ops, list) { + rcu_read_lock(); + list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) { if (af_ops->get_stats_af_size) { size += nla_total_size( af_ops->get_stats_af_size(dev)); @@ -4039,6 +4197,7 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev, size += nla_total_size(0); } } + rcu_read_unlock(); } return size; @@ -4292,9 +4451,10 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi case NETDEV_CHANGEUPPER: case NETDEV_RESEND_IGMP: case NETDEV_CHANGEINFODATA: + case NETDEV_CHANGELOWERSTATE: case NETDEV_CHANGE_TX_QUEUE_LEN: rtmsg_ifinfo_event(RTM_NEWLINK, dev, 0, rtnl_get_event(event), - GFP_KERNEL); + GFP_KERNEL, NULL); break; default: break; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index e140ba49b30a..6b0ff396fa9d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -41,7 +41,6 @@ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> -#include <linux/kmemcheck.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/in.h> @@ -234,14 +233,12 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, shinfo = skb_shinfo(skb); memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); atomic_set(&shinfo->dataref, 1); - kmemcheck_annotate_variable(shinfo->destructor_arg); if (flags & SKB_ALLOC_FCLONE) { struct sk_buff_fclones *fclones; fclones = container_of(skb, struct sk_buff_fclones, skb1); - kmemcheck_annotate_bitfield(&fclones->skb2, flags1); skb->fclone = SKB_FCLONE_ORIG; refcount_set(&fclones->fclone_ref, 1); @@ -301,7 +298,6 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size) shinfo = skb_shinfo(skb); memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); atomic_set(&shinfo->dataref, 1); - kmemcheck_annotate_variable(shinfo->destructor_arg); return skb; } @@ -357,7 +353,7 @@ static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) */ void *netdev_alloc_frag(unsigned int fragsz) { - return __netdev_alloc_frag(fragsz, GFP_ATOMIC | __GFP_COLD); + return __netdev_alloc_frag(fragsz, GFP_ATOMIC); } EXPORT_SYMBOL(netdev_alloc_frag); @@ -370,7 +366,7 @@ static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) void *napi_alloc_frag(unsigned int fragsz) { - return __napi_alloc_frag(fragsz, GFP_ATOMIC | __GFP_COLD); + return __napi_alloc_frag(fragsz, GFP_ATOMIC); } EXPORT_SYMBOL(napi_alloc_frag); @@ -1283,7 +1279,6 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) if (!n) return NULL; - kmemcheck_annotate_bitfield(n, flags1); n->fclone = SKB_FCLONE_UNAVAILABLE; } @@ -1354,8 +1349,7 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) /* Set the tail pointer and length */ skb_put(n, skb->len); - if (skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len)) - BUG(); + BUG_ON(skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len)); copy_skb_header(n, skb); return n; @@ -1453,8 +1447,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, BUG_ON(nhead < 0); - if (skb_shared(skb)) - BUG(); + BUG_ON(skb_shared(skb)); size = SKB_DATA_ALIGN(size); @@ -1513,6 +1506,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, skb->nohdr = 0; atomic_set(&skb_shinfo(skb)->dataref, 1); + skb_metadata_clear(skb); + /* It is not generally safe to change skb->truesize. * For the moment, we really care of rx path, or * when skb is orphaned (not attached to a socket). @@ -1597,9 +1592,8 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, head_copy_off = newheadroom - head_copy_len; /* Copy the linear header and data. */ - if (skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off, - skb->len + head_copy_len)) - BUG(); + BUG_ON(skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off, + skb->len + head_copy_len)); copy_skb_header(n, skb); @@ -1880,8 +1874,8 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta) return NULL; } - if (skb_copy_bits(skb, skb_headlen(skb), skb_tail_pointer(skb), delta)) - BUG(); + BUG_ON(skb_copy_bits(skb, skb_headlen(skb), + skb_tail_pointer(skb), delta)); /* Optimization: no fragments, no reasons to preestimate * size of pulled pages. Superb. @@ -2852,12 +2846,15 @@ EXPORT_SYMBOL(skb_queue_purge); */ void skb_rbtree_purge(struct rb_root *root) { - struct sk_buff *skb, *next; + struct rb_node *p = rb_first(root); - rbtree_postorder_for_each_entry_safe(skb, next, root, rbnode) - kfree_skb(skb); + while (p) { + struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); - *root = RB_ROOT; + p = rb_next(p); + rb_erase(&skb->rbnode, root); + kfree_skb(skb); + } } /** @@ -4766,6 +4763,7 @@ EXPORT_SYMBOL(kfree_skb_partial); bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, bool *fragstolen, int *delta_truesize) { + struct skb_shared_info *to_shinfo, *from_shinfo; int i, delta, len = from->len; *fragstolen = false; @@ -4780,7 +4778,9 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, return true; } - if (skb_has_frag_list(to) || skb_has_frag_list(from)) + to_shinfo = skb_shinfo(to); + from_shinfo = skb_shinfo(from); + if (to_shinfo->frag_list || from_shinfo->frag_list) return false; if (skb_zcopy(to) || skb_zcopy(from)) return false; @@ -4789,8 +4789,8 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, struct page *page; unsigned int offset; - if (skb_shinfo(to)->nr_frags + - skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) + if (to_shinfo->nr_frags + + from_shinfo->nr_frags >= MAX_SKB_FRAGS) return false; if (skb_head_is_locked(from)) @@ -4801,12 +4801,12 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, page = virt_to_head_page(from->head); offset = from->data - (unsigned char *)page_address(page); - skb_fill_page_desc(to, skb_shinfo(to)->nr_frags, + skb_fill_page_desc(to, to_shinfo->nr_frags, page, offset, skb_headlen(from)); *fragstolen = true; } else { - if (skb_shinfo(to)->nr_frags + - skb_shinfo(from)->nr_frags > MAX_SKB_FRAGS) + if (to_shinfo->nr_frags + + from_shinfo->nr_frags > MAX_SKB_FRAGS) return false; delta = from->truesize - SKB_TRUESIZE(skb_end_offset(from)); @@ -4814,19 +4814,19 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, WARN_ON_ONCE(delta < len); - memcpy(skb_shinfo(to)->frags + skb_shinfo(to)->nr_frags, - skb_shinfo(from)->frags, - skb_shinfo(from)->nr_frags * sizeof(skb_frag_t)); - skb_shinfo(to)->nr_frags += skb_shinfo(from)->nr_frags; + memcpy(to_shinfo->frags + to_shinfo->nr_frags, + from_shinfo->frags, + from_shinfo->nr_frags * sizeof(skb_frag_t)); + to_shinfo->nr_frags += from_shinfo->nr_frags; if (!skb_cloned(from)) - skb_shinfo(from)->nr_frags = 0; + from_shinfo->nr_frags = 0; /* if the skb is not cloned this does nothing * since we set nr_frags to 0. */ - for (i = 0; i < skb_shinfo(from)->nr_frags; i++) - skb_frag_ref(from, i); + for (i = 0; i < from_shinfo->nr_frags; i++) + __skb_frag_ref(&from_shinfo->frags[i]); to->truesize += delta; to->len += len; diff --git a/net/core/sock.c b/net/core/sock.c index 415f441c63b9..c0b5b2f17412 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1469,8 +1469,6 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, sk = kmalloc(prot->obj_size, priority); if (sk != NULL) { - kmemcheck_annotate_bitfield(sk, flags); - if (security_sk_alloc(sk, family, priority)) goto out_free; @@ -2346,16 +2344,18 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) /* guarantee minimum buffer size under pressure */ if (kind == SK_MEM_RECV) { - if (atomic_read(&sk->sk_rmem_alloc) < prot->sysctl_rmem[0]) + if (atomic_read(&sk->sk_rmem_alloc) < sk_get_rmem0(sk, prot)) return 1; } else { /* SK_MEM_SEND */ + int wmem0 = sk_get_wmem0(sk, prot); + if (sk->sk_type == SOCK_STREAM) { - if (sk->sk_wmem_queued < prot->sysctl_wmem[0]) + if (sk->sk_wmem_queued < wmem0) return 1; - } else if (refcount_read(&sk->sk_wmem_alloc) < - prot->sysctl_wmem[0]) + } else if (refcount_read(&sk->sk_wmem_alloc) < wmem0) { return 1; + } } if (sk_has_memory_pressure(sk)) { @@ -2685,7 +2685,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk_init_common(sk); sk->sk_send_head = NULL; - init_timer(&sk->sk_timer); + timer_setup(&sk->sk_timer, NULL, 0); sk->sk_allocation = GFP_KERNEL; sk->sk_rcvbuf = sysctl_rmem_default; @@ -2744,6 +2744,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_max_pacing_rate = ~0U; sk->sk_pacing_rate = ~0U; + sk->sk_pacing_shift = 10; sk->sk_incoming_cpu = -1; /* * Before updating sk_refcnt, we must commit prior changes to memory @@ -3042,7 +3043,6 @@ struct prot_inuse { static DECLARE_BITMAP(proto_inuse_idx, PROTO_INUSE_NR); -#ifdef CONFIG_NET_NS void sock_prot_inuse_add(struct net *net, struct proto *prot, int val) { __this_cpu_add(net->core.inuse->val[prot->inuse_idx], val); @@ -3086,27 +3086,6 @@ static __init int net_inuse_init(void) } core_initcall(net_inuse_init); -#else -static DEFINE_PER_CPU(struct prot_inuse, prot_inuse); - -void sock_prot_inuse_add(struct net *net, struct proto *prot, int val) -{ - __this_cpu_add(prot_inuse.val[prot->inuse_idx], val); -} -EXPORT_SYMBOL_GPL(sock_prot_inuse_add); - -int sock_prot_inuse_get(struct net *net, struct proto *prot) -{ - int cpu, idx = prot->inuse_idx; - int res = 0; - - for_each_possible_cpu(cpu) - res += per_cpu(prot_inuse, cpu).val[idx]; - - return res >= 0 ? res : 0; -} -EXPORT_SYMBOL_GPL(sock_prot_inuse_get); -#endif static void assign_proto_idx(struct proto *prot) { diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index e1295d5f2c56..1c75cd1255f6 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -126,10 +126,10 @@ static void ccid2_change_l_seq_window(struct sock *sk, u64 val) DCCPF_SEQ_WMAX)); } -static void ccid2_hc_tx_rto_expire(unsigned long data) +static void ccid2_hc_tx_rto_expire(struct timer_list *t) { - struct sock *sk = (struct sock *)data; - struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + struct ccid2_hc_tx_sock *hc = from_timer(hc, t, tx_rtotimer); + struct sock *sk = hc->sk; const bool sender_was_blocked = ccid2_cwnd_network_limited(hc); bh_lock_sock(sk); @@ -733,8 +733,8 @@ static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk) hc->tx_rpdupack = -1; hc->tx_last_cong = hc->tx_lsndtime = hc->tx_cwnd_stamp = ccid2_jiffies32; hc->tx_cwnd_used = 0; - setup_timer(&hc->tx_rtotimer, ccid2_hc_tx_rto_expire, - (unsigned long)sk); + hc->sk = sk; + timer_setup(&hc->tx_rtotimer, ccid2_hc_tx_rto_expire, 0); INIT_LIST_HEAD(&hc->tx_av_chunks); return 0; } diff --git a/net/dccp/ccids/ccid2.h b/net/dccp/ccids/ccid2.h index 6e50ef2898fb..1af0116dc6ce 100644 --- a/net/dccp/ccids/ccid2.h +++ b/net/dccp/ccids/ccid2.h @@ -85,6 +85,7 @@ struct ccid2_hc_tx_sock { tx_rto; u64 tx_rtt_seq:48; struct timer_list tx_rtotimer; + struct sock *sk; /* Congestion Window validation (optional, RFC 2861) */ u32 tx_cwnd_used, diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index 119c04317d48..8b5ba6dffac7 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -195,10 +195,10 @@ static inline void ccid3_hc_tx_update_win_count(struct ccid3_hc_tx_sock *hc, } } -static void ccid3_hc_tx_no_feedback_timer(unsigned long data) +static void ccid3_hc_tx_no_feedback_timer(struct timer_list *t) { - struct sock *sk = (struct sock *)data; - struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); + struct ccid3_hc_tx_sock *hc = from_timer(hc, t, tx_no_feedback_timer); + struct sock *sk = hc->sk; unsigned long t_nfb = USEC_PER_SEC / 5; bh_lock_sock(sk); @@ -505,8 +505,9 @@ static int ccid3_hc_tx_init(struct ccid *ccid, struct sock *sk) hc->tx_state = TFRC_SSTATE_NO_SENT; hc->tx_hist = NULL; - setup_timer(&hc->tx_no_feedback_timer, - ccid3_hc_tx_no_feedback_timer, (unsigned long)sk); + hc->sk = sk; + timer_setup(&hc->tx_no_feedback_timer, + ccid3_hc_tx_no_feedback_timer, 0); return 0; } diff --git a/net/dccp/ccids/ccid3.h b/net/dccp/ccids/ccid3.h index 1a9933c29672..813d91c6e1e2 100644 --- a/net/dccp/ccids/ccid3.h +++ b/net/dccp/ccids/ccid3.h @@ -106,6 +106,7 @@ struct ccid3_hc_tx_sock { u8 tx_last_win_count; ktime_t tx_t_last_win_count; struct timer_list tx_no_feedback_timer; + struct sock *sk; ktime_t tx_t_ld; ktime_t tx_t_nom; struct tfrc_tx_hist_entry *tx_hist; diff --git a/net/dccp/ccids/lib/packet_history.c b/net/dccp/ccids/lib/packet_history.c index 08df7a3acb3d..876e18592d71 100644 --- a/net/dccp/ccids/lib/packet_history.c +++ b/net/dccp/ccids/lib/packet_history.c @@ -149,10 +149,8 @@ static void tfrc_rx_hist_swap(struct tfrc_rx_hist *h, const u8 a, const u8 b) { const u8 idx_a = tfrc_rx_hist_index(h, a), idx_b = tfrc_rx_hist_index(h, b); - struct tfrc_rx_hist_entry *tmp = h->ring[idx_a]; - h->ring[idx_a] = h->ring[idx_b]; - h->ring[idx_b] = tmp; + swap(h->ring[idx_a], h->ring[idx_b]); } /* diff --git a/net/dccp/input.c b/net/dccp/input.c index fa6be9750bb4..d28d46bff6ab 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -534,6 +534,7 @@ static int dccp_rcv_respond_partopen_state_process(struct sock *sk, case DCCP_PKT_DATA: if (sk->sk_state == DCCP_RESPOND) break; + /* fall through */ case DCCP_PKT_DATAACK: case DCCP_PKT_ACK: /* diff --git a/net/dccp/options.c b/net/dccp/options.c index 51cdfc3bd8ca..4e40db017e19 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -227,8 +227,8 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, * Ack vectors are processed by the TX CCID if it is * interested. The RX CCID need not parse Ack Vectors, * since it is only interested in clearing old state. - * Fall through. */ + /* fall through */ case DCCPO_MIN_TX_CCID_SPECIFIC ... DCCPO_MAX_TX_CCID_SPECIFIC: if (ccid_hc_tx_parse_options(dp->dccps_hc_tx_ccid, sk, pkt_type, opt, value, len)) diff --git a/net/dccp/timer.c b/net/dccp/timer.c index 3a2c34027758..b50a8732ff43 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -125,10 +125,11 @@ static void dccp_retransmit_timer(struct sock *sk) __sk_dst_reset(sk); } -static void dccp_write_timer(unsigned long data) +static void dccp_write_timer(struct timer_list *t) { - struct sock *sk = (struct sock *)data; - struct inet_connection_sock *icsk = inet_csk(sk); + struct inet_connection_sock *icsk = + from_timer(icsk, t, icsk_retransmit_timer); + struct sock *sk = &icsk->icsk_inet.sk; int event = 0; bh_lock_sock(sk); @@ -161,19 +162,20 @@ out: sock_put(sk); } -static void dccp_keepalive_timer(unsigned long data) +static void dccp_keepalive_timer(struct timer_list *t) { - struct sock *sk = (struct sock *)data; + struct sock *sk = from_timer(sk, t, sk_timer); pr_err("dccp should not use a keepalive timer !\n"); sock_put(sk); } /* This is the same as tcp_delack_timer, sans prequeue & mem_reclaim stuff */ -static void dccp_delack_timer(unsigned long data) +static void dccp_delack_timer(struct timer_list *t) { - struct sock *sk = (struct sock *)data; - struct inet_connection_sock *icsk = inet_csk(sk); + struct inet_connection_sock *icsk = + from_timer(icsk, t, icsk_delack_timer); + struct sock *sk = &icsk->icsk_inet.sk; bh_lock_sock(sk); if (sock_owned_by_user(sk)) { @@ -232,10 +234,13 @@ static void dccp_write_xmitlet(unsigned long data) bh_unlock_sock(sk); } -static void dccp_write_xmit_timer(unsigned long data) +static void dccp_write_xmit_timer(struct timer_list *t) { - dccp_write_xmitlet(data); - sock_put((struct sock *)data); + struct dccp_sock *dp = from_timer(dp, t, dccps_xmit_timer); + struct sock *sk = &dp->dccps_inet_connection.icsk_inet.sk; + + dccp_write_xmitlet((unsigned long)sk); + sock_put(sk); } void dccp_init_xmit_timers(struct sock *sk) @@ -243,8 +248,7 @@ void dccp_init_xmit_timers(struct sock *sk) struct dccp_sock *dp = dccp_sk(sk); tasklet_init(&dp->dccps_xmitlet, dccp_write_xmitlet, (unsigned long)sk); - setup_timer(&dp->dccps_xmit_timer, dccp_write_xmit_timer, - (unsigned long)sk); + timer_setup(&dp->dccps_xmit_timer, dccp_write_xmit_timer, 0); inet_csk_init_xmit_timers(sk, &dccp_write_timer, &dccp_delack_timer, &dccp_keepalive_timer); } diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 73a0399dc7a2..518cea17b811 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -533,10 +533,6 @@ static struct sock *dn_alloc_sock(struct net *net, struct socket *sock, gfp_t gf scp->keepalive = 10 * HZ; scp->keepalive_fxn = dn_keepalive; - init_timer(&scp->delack_timer); - scp->delack_pending = 0; - scp->delack_fxn = dn_nsp_delayed_ack; - dn_start_slow_timer(sk); out: return sk; @@ -634,10 +630,12 @@ static void dn_destroy_sock(struct sock *sk) goto disc_reject; case DN_RUN: scp->state = DN_DI; + /* fall through */ case DN_DI: case DN_DR: disc_reject: dn_nsp_send_disc(sk, NSP_DISCINIT, 0, sk->sk_allocation); + /* fall through */ case DN_NC: case DN_NR: case DN_RJ: @@ -651,6 +649,7 @@ disc_reject: break; default: printk(KERN_DEBUG "DECnet: dn_destroy_sock passed socket in invalid state\n"); + /* fall through */ case DN_O: dn_stop_slow_timer(sk); diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index df042b6d80b8..9153247dad28 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -1039,14 +1039,14 @@ static void dn_eth_down(struct net_device *dev) static void dn_dev_set_timer(struct net_device *dev); -static void dn_dev_timer_func(unsigned long arg) +static void dn_dev_timer_func(struct timer_list *t) { - struct net_device *dev = (struct net_device *)arg; - struct dn_dev *dn_db; + struct dn_dev *dn_db = from_timer(dn_db, t, timer); + struct net_device *dev; struct dn_ifaddr *ifa; rcu_read_lock(); - dn_db = rcu_dereference(dev->dn_ptr); + dev = dn_db->dev; if (dn_db->t3 <= dn_db->parms.t2) { if (dn_db->parms.timer3) { for (ifa = rcu_dereference(dn_db->ifa_list); @@ -1071,8 +1071,6 @@ static void dn_dev_set_timer(struct net_device *dev) if (dn_db->parms.t2 > dn_db->parms.t3) dn_db->parms.t2 = dn_db->parms.t3; - dn_db->timer.data = (unsigned long)dev; - dn_db->timer.function = dn_dev_timer_func; dn_db->timer.expires = jiffies + (dn_db->parms.t2 * HZ); add_timer(&dn_db->timer); @@ -1101,7 +1099,7 @@ static struct dn_dev *dn_dev_create(struct net_device *dev, int *err) rcu_assign_pointer(dev->dn_ptr, dn_db); dn_db->dev = dev; - init_timer(&dn_db->timer); + timer_setup(&dn_db->timer, dn_dev_timer_func, 0); dn_db->uptime = jiffies; diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c index 7ac086d5c0c0..1b2120645730 100644 --- a/net/decnet/dn_nsp_in.c +++ b/net/decnet/dn_nsp_in.c @@ -776,12 +776,8 @@ static int dn_nsp_rx_packet(struct net *net, struct sock *sk2, * Swap src & dst and look up in the normal way. */ if (unlikely(cb->rt_flags & DN_RT_F_RTS)) { - __le16 tmp = cb->dst_port; - cb->dst_port = cb->src_port; - cb->src_port = tmp; - tmp = cb->dst; - cb->dst = cb->src; - cb->src = tmp; + swap(cb->dst_port, cb->src_port); + swap(cb->dst, cb->src); } /* diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c index 66f035e476ea..56a52a004c56 100644 --- a/net/decnet/dn_nsp_out.c +++ b/net/decnet/dn_nsp_out.c @@ -313,11 +313,8 @@ static __le16 *dn_mk_ack_header(struct sock *sk, struct sk_buff *skb, unsigned c ackcrs |= 0x8000; /* If this is an "other data/ack" message, swap acknum and ackcrs */ - if (other) { - unsigned short tmp = acknum; - acknum = ackcrs; - ackcrs = tmp; - } + if (other) + swap(acknum, ackcrs); /* Set "cross subchannel" bit in ackcrs */ ackcrs |= 0x2000; @@ -491,17 +488,6 @@ void dn_send_conn_ack (struct sock *sk) dn_nsp_send(skb); } -void dn_nsp_delayed_ack(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - - if (scp->ackxmt_oth != scp->numoth_rcv) - dn_nsp_send_oth_ack(sk); - - if (scp->ackxmt_dat != scp->numdat_rcv) - dn_nsp_send_data_ack(sk); -} - static int dn_nsp_retrans_conn_conf(struct sock *sk) { struct dn_scp *scp = DN_SK(sk); diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 0bd3afd01dd2..b36dceab0dc1 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -131,7 +131,7 @@ static struct dn_rt_hash_bucket *dn_rt_hash_table; static unsigned int dn_rt_hash_mask; static struct timer_list dn_route_timer; -static DEFINE_TIMER(dn_rt_flush_timer, dn_run_flush, 0, 0); +static DEFINE_TIMER(dn_rt_flush_timer, dn_run_flush); int decnet_dst_gc_interval = 2; static struct dst_ops dn_dst_ops = { @@ -338,7 +338,7 @@ static int dn_insert_route(struct dn_route *rt, unsigned int hash, struct dn_rou dn_rt_hash_table[hash].chain); rcu_assign_pointer(dn_rt_hash_table[hash].chain, rth); - dst_use(&rth->dst, now); + dst_hold_and_use(&rth->dst, now); spin_unlock_bh(&dn_rt_hash_table[hash].lock); dst_release_immediate(&rt->dst); @@ -351,7 +351,7 @@ static int dn_insert_route(struct dn_route *rt, unsigned int hash, struct dn_rou rcu_assign_pointer(rt->dst.dn_next, dn_rt_hash_table[hash].chain); rcu_assign_pointer(dn_rt_hash_table[hash].chain, rt); - dst_use(&rt->dst, now); + dst_hold_and_use(&rt->dst, now); spin_unlock_bh(&dn_rt_hash_table[hash].lock); *rp = rt; return 0; @@ -1258,7 +1258,7 @@ static int __dn_route_output_key(struct dst_entry **pprt, const struct flowidn * (flp->flowidn_mark == rt->fld.flowidn_mark) && dn_is_output_route(rt) && (rt->fld.flowidn_oif == flp->flowidn_oif)) { - dst_use(&rt->dst, jiffies); + dst_hold_and_use(&rt->dst, jiffies); rcu_read_unlock_bh(); *pprt = &rt->dst; return 0; @@ -1535,7 +1535,7 @@ static int dn_route_input(struct sk_buff *skb) (rt->fld.flowidn_oif == 0) && (rt->fld.flowidn_mark == skb->mark) && (rt->fld.flowidn_iif == cb->iif)) { - dst_use(&rt->dst, jiffies); + dst_hold_and_use(&rt->dst, jiffies); rcu_read_unlock(); skb_dst_set(skb, (struct dst_entry *)rt); return 0; diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index 08667f68e601..f0710b5d037d 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -156,6 +156,7 @@ static void dn_rehash_zone(struct dn_zone *dz) default: printk(KERN_DEBUG "DECnet: dn_rehash_zone: BUG! %d\n", old_divisor); + /* fall through */ case 256: new_divisor = 1024; new_hashmask = 0x3FF; diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index cc5f8f971689..03c3bdf25468 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -7,6 +7,7 @@ config HAVE_NET_DSA config NET_DSA tristate "Distributed Switch Architecture" depends on HAVE_NET_DSA && MAY_USE_DEVLINK + depends on BRIDGE || BRIDGE=n select NET_SWITCHDEV select PHYLIB ---help--- @@ -19,6 +20,9 @@ if NET_DSA config NET_DSA_TAG_BRCM bool +config NET_DSA_TAG_BRCM_PREPEND + bool + config NET_DSA_TAG_DSA bool diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 3d3c74193d06..0e13c1f95d13 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -1,10 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 # the core obj-$(CONFIG_NET_DSA) += dsa_core.o -dsa_core-y += dsa.o dsa2.o legacy.o port.o slave.o switch.o +dsa_core-y += dsa.o dsa2.o legacy.o master.o port.o slave.o switch.o # tagging formats dsa_core-$(CONFIG_NET_DSA_TAG_BRCM) += tag_brcm.o +dsa_core-$(CONFIG_NET_DSA_TAG_BRCM_PREPEND) += tag_brcm.o dsa_core-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o dsa_core-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o dsa_core-$(CONFIG_NET_DSA_TAG_KSZ) += tag_ksz.o diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 03c58b0eb082..6a9d0f50fbee 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -14,6 +14,7 @@ #include <linux/platform_device.h> #include <linux/slab.h> #include <linux/module.h> +#include <linux/notifier.h> #include <linux/of.h> #include <linux/of_mdio.h> #include <linux/of_platform.h> @@ -43,6 +44,9 @@ const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = { #ifdef CONFIG_NET_DSA_TAG_BRCM [DSA_TAG_PROTO_BRCM] = &brcm_netdev_ops, #endif +#ifdef CONFIG_NET_DSA_TAG_BRCM_PREPEND + [DSA_TAG_PROTO_BRCM_PREPEND] = &brcm_prepend_netdev_ops, +#endif #ifdef CONFIG_NET_DSA_TAG_DSA [DSA_TAG_PROTO_DSA] = &dsa_netdev_ops, #endif @@ -67,37 +71,6 @@ const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = { [DSA_TAG_PROTO_NONE] = &none_ops, }; -int dsa_cpu_dsa_setup(struct dsa_port *port) -{ - struct device_node *port_dn = port->dn; - struct dsa_switch *ds = port->ds; - struct phy_device *phydev; - int ret, mode; - - if (of_phy_is_fixed_link(port_dn)) { - ret = of_phy_register_fixed_link(port_dn); - if (ret) { - dev_err(ds->dev, "failed to register fixed PHY\n"); - return ret; - } - phydev = of_phy_find_device(port_dn); - - mode = of_get_phy_mode(port_dn); - if (mode < 0) - mode = PHY_INTERFACE_MODE_NA; - phydev->interface = mode; - - genphy_config_init(phydev); - genphy_read_status(phydev); - if (ds->ops->adjust_link) - ds->ops->adjust_link(ds, port->index, phydev); - - put_device(&phydev->mdio.dev); - } - - return 0; -} - const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol) { const struct dsa_device_ops *ops; @@ -112,42 +85,6 @@ const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol) return ops; } -int dsa_cpu_port_ethtool_setup(struct dsa_port *cpu_dp) -{ - struct dsa_switch *ds = cpu_dp->ds; - struct net_device *master; - struct ethtool_ops *cpu_ops; - - master = cpu_dp->netdev; - - cpu_ops = devm_kzalloc(ds->dev, sizeof(*cpu_ops), GFP_KERNEL); - if (!cpu_ops) - return -ENOMEM; - - memcpy(&cpu_dp->ethtool_ops, master->ethtool_ops, - sizeof(struct ethtool_ops)); - cpu_dp->orig_ethtool_ops = master->ethtool_ops; - memcpy(cpu_ops, &cpu_dp->ethtool_ops, - sizeof(struct ethtool_ops)); - dsa_cpu_port_ethtool_init(cpu_ops); - master->ethtool_ops = cpu_ops; - - return 0; -} - -void dsa_cpu_port_ethtool_restore(struct dsa_port *cpu_dp) -{ - cpu_dp->netdev->ethtool_ops = cpu_dp->orig_ethtool_ops; -} - -void dsa_cpu_dsa_destroy(struct dsa_port *port) -{ - struct device_node *port_dn = port->dn; - - if (of_phy_is_fixed_link(port_dn)) - of_phy_deregister_fixed_link(port_dn); -} - static int dev_is_class(struct device *dev, void *class) { if (dev->class != NULL && !strcmp(dev->class->name, class)) @@ -188,12 +125,12 @@ EXPORT_SYMBOL_GPL(dsa_dev_to_net_device); static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *unused) { - struct dsa_switch_tree *dst = dev->dsa_ptr; + struct dsa_port *cpu_dp = dev->dsa_ptr; struct sk_buff *nskb = NULL; struct pcpu_sw_netstats *s; struct dsa_slave_priv *p; - if (unlikely(dst == NULL)) { + if (unlikely(!cpu_dp)) { kfree_skb(skb); return 0; } @@ -202,7 +139,7 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, if (!skb) return 0; - nskb = dst->rcv(skb, dev, pt); + nskb = cpu_dp->rcv(skb, dev, pt); if (!nskb) { kfree_skb(skb); return 0; @@ -228,7 +165,7 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, #ifdef CONFIG_PM_SLEEP static bool dsa_is_port_initialized(struct dsa_switch *ds, int p) { - return ds->enabled_port_mask & (1 << p) && ds->ports[p].netdev; + return dsa_is_user_port(ds, p) && ds->ports[p].slave; } int dsa_switch_suspend(struct dsa_switch *ds) @@ -240,7 +177,7 @@ int dsa_switch_suspend(struct dsa_switch *ds) if (!dsa_is_port_initialized(ds, i)) continue; - ret = dsa_slave_suspend(ds->ports[i].netdev); + ret = dsa_slave_suspend(ds->ports[i].slave); if (ret) return ret; } @@ -267,7 +204,7 @@ int dsa_switch_resume(struct dsa_switch *ds) if (!dsa_is_port_initialized(ds, i)) continue; - ret = dsa_slave_resume(ds->ports[i].netdev); + ret = dsa_slave_resume(ds->ports[i].slave); if (ret) return ret; } @@ -289,6 +226,28 @@ bool dsa_schedule_work(struct work_struct *work) return queue_work(dsa_owq, work); } +static ATOMIC_NOTIFIER_HEAD(dsa_notif_chain); + +int register_dsa_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_register(&dsa_notif_chain, nb); +} +EXPORT_SYMBOL_GPL(register_dsa_notifier); + +int unregister_dsa_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&dsa_notif_chain, nb); +} +EXPORT_SYMBOL_GPL(unregister_dsa_notifier); + +int call_dsa_notifiers(unsigned long val, struct net_device *dev, + struct dsa_notifier_info *info) +{ + info->dev = dev; + return atomic_notifier_call_chain(&dsa_notif_chain, val, info); +} +EXPORT_SYMBOL_GPL(call_dsa_notifiers); + static int __init dsa_init_module(void) { int rc; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 045d8a176279..44e3fb7dec8c 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -21,293 +21,297 @@ #include "dsa_priv.h" -static LIST_HEAD(dsa_switch_trees); +static LIST_HEAD(dsa_tree_list); static DEFINE_MUTEX(dsa2_mutex); static const struct devlink_ops dsa_devlink_ops = { }; -static struct dsa_switch_tree *dsa_get_dst(u32 tree) +static struct dsa_switch_tree *dsa_tree_find(int index) { struct dsa_switch_tree *dst; - list_for_each_entry(dst, &dsa_switch_trees, list) - if (dst->tree == tree) { - kref_get(&dst->refcount); + list_for_each_entry(dst, &dsa_tree_list, list) + if (dst->index == index) return dst; - } + return NULL; } -static void dsa_free_dst(struct kref *ref) +static struct dsa_switch_tree *dsa_tree_alloc(int index) { - struct dsa_switch_tree *dst = container_of(ref, struct dsa_switch_tree, - refcount); + struct dsa_switch_tree *dst; - list_del(&dst->list); - kfree(dst); + dst = kzalloc(sizeof(*dst), GFP_KERNEL); + if (!dst) + return NULL; + + dst->index = index; + + INIT_LIST_HEAD(&dst->list); + list_add_tail(&dsa_tree_list, &dst->list); + + /* Initialize the reference counter to the number of switches, not 1 */ + kref_init(&dst->refcount); + refcount_set(&dst->refcount.refcount, 0); + + return dst; } -static void dsa_put_dst(struct dsa_switch_tree *dst) +static void dsa_tree_free(struct dsa_switch_tree *dst) { - kref_put(&dst->refcount, dsa_free_dst); + list_del(&dst->list); + kfree(dst); } -static struct dsa_switch_tree *dsa_add_dst(u32 tree) +static struct dsa_switch_tree *dsa_tree_touch(int index) { struct dsa_switch_tree *dst; - dst = kzalloc(sizeof(*dst), GFP_KERNEL); + dst = dsa_tree_find(index); if (!dst) - return NULL; - dst->tree = tree; - INIT_LIST_HEAD(&dst->list); - list_add_tail(&dsa_switch_trees, &dst->list); - kref_init(&dst->refcount); + dst = dsa_tree_alloc(index); return dst; } -static void dsa_dst_add_ds(struct dsa_switch_tree *dst, - struct dsa_switch *ds, u32 index) +static void dsa_tree_get(struct dsa_switch_tree *dst) { kref_get(&dst->refcount); - dst->ds[index] = ds; } -static void dsa_dst_del_ds(struct dsa_switch_tree *dst, - struct dsa_switch *ds, u32 index) +static void dsa_tree_release(struct kref *ref) { - dst->ds[index] = NULL; - kref_put(&dst->refcount, dsa_free_dst); + struct dsa_switch_tree *dst; + + dst = container_of(ref, struct dsa_switch_tree, refcount); + + dsa_tree_free(dst); } -/* For platform data configurations, we need to have a valid name argument to - * differentiate a disabled port from an enabled one - */ -static bool dsa_port_is_valid(struct dsa_port *port) +static void dsa_tree_put(struct dsa_switch_tree *dst) { - return !!(port->dn || port->name); + kref_put(&dst->refcount, dsa_tree_release); } static bool dsa_port_is_dsa(struct dsa_port *port) { - if (port->name && !strcmp(port->name, "dsa")) - return true; - else - return !!of_parse_phandle(port->dn, "link", 0); + return port->type == DSA_PORT_TYPE_DSA; } static bool dsa_port_is_cpu(struct dsa_port *port) { - if (port->name && !strcmp(port->name, "cpu")) - return true; - else - return !!of_parse_phandle(port->dn, "ethernet", 0); + return port->type == DSA_PORT_TYPE_CPU; } -static bool dsa_ds_find_port_dn(struct dsa_switch *ds, - struct device_node *port) +static bool dsa_port_is_user(struct dsa_port *dp) { - u32 index; - - for (index = 0; index < ds->num_ports; index++) - if (ds->ports[index].dn == port) - return true; - return false; + return dp->type == DSA_PORT_TYPE_USER; } -static struct dsa_switch *dsa_dst_find_port_dn(struct dsa_switch_tree *dst, - struct device_node *port) +static struct dsa_port *dsa_tree_find_port_by_node(struct dsa_switch_tree *dst, + struct device_node *dn) { struct dsa_switch *ds; - u32 index; + struct dsa_port *dp; + int device, port; - for (index = 0; index < DSA_MAX_SWITCHES; index++) { - ds = dst->ds[index]; + for (device = 0; device < DSA_MAX_SWITCHES; device++) { + ds = dst->ds[device]; if (!ds) continue; - if (dsa_ds_find_port_dn(ds, port)) - return ds; + for (port = 0; port < ds->num_ports; port++) { + dp = &ds->ports[port]; + + if (dp->dn == dn) + return dp; + } } return NULL; } -static int dsa_port_complete(struct dsa_switch_tree *dst, - struct dsa_switch *src_ds, - struct dsa_port *port, - u32 src_port) +static bool dsa_port_setup_routing_table(struct dsa_port *dp) { - struct device_node *link; - int index; - struct dsa_switch *dst_ds; - - for (index = 0;; index++) { - link = of_parse_phandle(port->dn, "link", index); - if (!link) - break; - - dst_ds = dsa_dst_find_port_dn(dst, link); - of_node_put(link); + struct dsa_switch *ds = dp->ds; + struct dsa_switch_tree *dst = ds->dst; + struct device_node *dn = dp->dn; + struct of_phandle_iterator it; + struct dsa_port *link_dp; + int err; - if (!dst_ds) - return 1; + of_for_each_phandle(&it, err, dn, "link", NULL, 0) { + link_dp = dsa_tree_find_port_by_node(dst, it.node); + if (!link_dp) { + of_node_put(it.node); + return false; + } - src_ds->rtable[dst_ds->index] = src_port; + ds->rtable[link_dp->ds->index] = dp->index; } - return 0; + return true; } -/* A switch is complete if all the DSA ports phandles point to ports - * known in the tree. A return value of 1 means the tree is not - * complete. This is not an error condition. A value of 0 is - * success. - */ -static int dsa_ds_complete(struct dsa_switch_tree *dst, struct dsa_switch *ds) +static bool dsa_switch_setup_routing_table(struct dsa_switch *ds) { - struct dsa_port *port; - u32 index; - int err; - - for (index = 0; index < ds->num_ports; index++) { - port = &ds->ports[index]; - if (!dsa_port_is_valid(port)) - continue; + bool complete = true; + struct dsa_port *dp; + int i; - if (!dsa_port_is_dsa(port)) - continue; + for (i = 0; i < DSA_MAX_SWITCHES; i++) + ds->rtable[i] = DSA_RTABLE_NONE; - err = dsa_port_complete(dst, ds, port, index); - if (err != 0) - return err; + for (i = 0; i < ds->num_ports; i++) { + dp = &ds->ports[i]; - ds->dsa_port_mask |= BIT(index); + if (dsa_port_is_dsa(dp)) { + complete = dsa_port_setup_routing_table(dp); + if (!complete) + break; + } } - return 0; + return complete; } -/* A tree is complete if all the DSA ports phandles point to ports - * known in the tree. A return value of 1 means the tree is not - * complete. This is not an error condition. A value of 0 is - * success. - */ -static int dsa_dst_complete(struct dsa_switch_tree *dst) +static bool dsa_tree_setup_routing_table(struct dsa_switch_tree *dst) { struct dsa_switch *ds; - u32 index; - int err; + bool complete = true; + int device; - for (index = 0; index < DSA_MAX_SWITCHES; index++) { - ds = dst->ds[index]; + for (device = 0; device < DSA_MAX_SWITCHES; device++) { + ds = dst->ds[device]; if (!ds) continue; - err = dsa_ds_complete(dst, ds); - if (err != 0) - return err; + complete = dsa_switch_setup_routing_table(ds); + if (!complete) + break; } - return 0; + return complete; } -static int dsa_dsa_port_apply(struct dsa_port *port) +static struct dsa_port *dsa_tree_find_first_cpu(struct dsa_switch_tree *dst) { - struct dsa_switch *ds = port->ds; - int err; + struct dsa_switch *ds; + struct dsa_port *dp; + int device, port; - err = dsa_cpu_dsa_setup(port); - if (err) { - dev_warn(ds->dev, "Failed to setup dsa port %d: %d\n", - port->index, err); - return err; - } + for (device = 0; device < DSA_MAX_SWITCHES; device++) { + ds = dst->ds[device]; + if (!ds) + continue; - memset(&port->devlink_port, 0, sizeof(port->devlink_port)); + for (port = 0; port < ds->num_ports; port++) { + dp = &ds->ports[port]; - return devlink_port_register(ds->devlink, &port->devlink_port, - port->index); -} + if (dsa_port_is_cpu(dp)) + return dp; + } + } -static void dsa_dsa_port_unapply(struct dsa_port *port) -{ - devlink_port_unregister(&port->devlink_port); - dsa_cpu_dsa_destroy(port); + return NULL; } -static int dsa_cpu_port_apply(struct dsa_port *port) +static int dsa_tree_setup_default_cpu(struct dsa_switch_tree *dst) { - struct dsa_switch *ds = port->ds; - int err; + struct dsa_switch *ds; + struct dsa_port *dp; + int device, port; - err = dsa_cpu_dsa_setup(port); - if (err) { - dev_warn(ds->dev, "Failed to setup cpu port %d: %d\n", - port->index, err); - return err; + /* DSA currently only supports a single CPU port */ + dst->cpu_dp = dsa_tree_find_first_cpu(dst); + if (!dst->cpu_dp) { + pr_warn("Tree has no master device\n"); + return -EINVAL; } - memset(&port->devlink_port, 0, sizeof(port->devlink_port)); - err = devlink_port_register(ds->devlink, &port->devlink_port, - port->index); - return err; + /* Assign the default CPU port to all ports of the fabric */ + for (device = 0; device < DSA_MAX_SWITCHES; device++) { + ds = dst->ds[device]; + if (!ds) + continue; + + for (port = 0; port < ds->num_ports; port++) { + dp = &ds->ports[port]; + + if (dsa_port_is_user(dp)) + dp->cpu_dp = dst->cpu_dp; + } + } + + return 0; } -static void dsa_cpu_port_unapply(struct dsa_port *port) +static void dsa_tree_teardown_default_cpu(struct dsa_switch_tree *dst) { - devlink_port_unregister(&port->devlink_port); - dsa_cpu_dsa_destroy(port); - port->ds->cpu_port_mask &= ~BIT(port->index); - + /* DSA currently only supports a single CPU port */ + dst->cpu_dp = NULL; } -static int dsa_user_port_apply(struct dsa_port *port) +static int dsa_port_setup(struct dsa_port *dp) { - struct dsa_switch *ds = port->ds; - const char *name = port->name; + struct dsa_switch *ds = dp->ds; int err; - if (port->dn) - name = of_get_property(port->dn, "label", NULL); - if (!name) - name = "eth%d"; + memset(&dp->devlink_port, 0, sizeof(dp->devlink_port)); - err = dsa_slave_create(port, name); - if (err) { - dev_warn(ds->dev, "Failed to create slave %d: %d\n", - port->index, err); - port->netdev = NULL; - return err; - } - - memset(&port->devlink_port, 0, sizeof(port->devlink_port)); - err = devlink_port_register(ds->devlink, &port->devlink_port, - port->index); + err = devlink_port_register(ds->devlink, &dp->devlink_port, dp->index); if (err) return err; - devlink_port_type_eth_set(&port->devlink_port, port->netdev); + switch (dp->type) { + case DSA_PORT_TYPE_UNUSED: + break; + case DSA_PORT_TYPE_CPU: + case DSA_PORT_TYPE_DSA: + err = dsa_port_fixed_link_register_of(dp); + if (err) { + dev_err(ds->dev, "failed to register fixed link for port %d.%d\n", + ds->index, dp->index); + return err; + } + + break; + case DSA_PORT_TYPE_USER: + err = dsa_slave_create(dp); + if (err) + dev_err(ds->dev, "failed to create slave for port %d.%d\n", + ds->index, dp->index); + else + devlink_port_type_eth_set(&dp->devlink_port, dp->slave); + break; + } return 0; } -static void dsa_user_port_unapply(struct dsa_port *port) +static void dsa_port_teardown(struct dsa_port *dp) { - devlink_port_unregister(&port->devlink_port); - if (port->netdev) { - dsa_slave_destroy(port->netdev); - port->netdev = NULL; - port->ds->enabled_port_mask &= ~(1 << port->index); + devlink_port_unregister(&dp->devlink_port); + + switch (dp->type) { + case DSA_PORT_TYPE_UNUSED: + break; + case DSA_PORT_TYPE_CPU: + case DSA_PORT_TYPE_DSA: + dsa_port_fixed_link_unregister_of(dp); + break; + case DSA_PORT_TYPE_USER: + if (dp->slave) { + dsa_slave_destroy(dp->slave); + dp->slave = NULL; + } + break; } } -static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds) +static int dsa_switch_setup(struct dsa_switch *ds) { - struct dsa_port *port; - u32 index; int err; /* Initialize ds->phys_mii_mask before registering the slave MDIO bus @@ -315,7 +319,7 @@ static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds) * the slave MDIO bus driver rely on these values for probing PHY * devices or not */ - ds->phys_mii_mask = ds->enabled_port_mask; + ds->phys_mii_mask |= dsa_user_ports(ds); /* Add the switch to devlink before calling setup, so that setup can * add dpipe tables @@ -336,12 +340,6 @@ static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds) if (err) return err; - if (ds->ops->set_addr) { - err = ds->ops->set_addr(ds, dst->cpu_dp->netdev->dev_addr); - if (err < 0) - return err; - } - if (!ds->slave_mii_bus && ds->ops->phy_read) { ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev); if (!ds->slave_mii_bus) @@ -354,56 +352,11 @@ static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds) return err; } - for (index = 0; index < ds->num_ports; index++) { - port = &ds->ports[index]; - if (!dsa_port_is_valid(port)) - continue; - - if (dsa_port_is_dsa(port)) { - err = dsa_dsa_port_apply(port); - if (err) - return err; - continue; - } - - if (dsa_port_is_cpu(port)) { - err = dsa_cpu_port_apply(port); - if (err) - return err; - continue; - } - - err = dsa_user_port_apply(port); - if (err) - continue; - } - return 0; } -static void dsa_ds_unapply(struct dsa_switch_tree *dst, struct dsa_switch *ds) +static void dsa_switch_teardown(struct dsa_switch *ds) { - struct dsa_port *port; - u32 index; - - for (index = 0; index < ds->num_ports; index++) { - port = &ds->ports[index]; - if (!dsa_port_is_valid(port)) - continue; - - if (dsa_port_is_dsa(port)) { - dsa_dsa_port_unapply(port); - continue; - } - - if (dsa_port_is_cpu(port)) { - dsa_cpu_port_unapply(port); - continue; - } - - dsa_user_port_unapply(port); - } - if (ds->slave_mii_bus && ds->ops->phy_read) mdiobus_unregister(ds->slave_mii_bus); @@ -417,199 +370,228 @@ static void dsa_ds_unapply(struct dsa_switch_tree *dst, struct dsa_switch *ds) } -static int dsa_dst_apply(struct dsa_switch_tree *dst) +static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) { struct dsa_switch *ds; - u32 index; + struct dsa_port *dp; + int device, port; int err; - for (index = 0; index < DSA_MAX_SWITCHES; index++) { - ds = dst->ds[index]; + for (device = 0; device < DSA_MAX_SWITCHES; device++) { + ds = dst->ds[device]; if (!ds) continue; - err = dsa_ds_apply(dst, ds); + err = dsa_switch_setup(ds); if (err) return err; - } - if (dst->cpu_dp) { - err = dsa_cpu_port_ethtool_setup(dst->cpu_dp); - if (err) - return err; - } + for (port = 0; port < ds->num_ports; port++) { + dp = &ds->ports[port]; - /* If we use a tagging format that doesn't have an ethertype - * field, make sure that all packets from this point on get - * sent to the tag format's receive function. - */ - wmb(); - dst->cpu_dp->netdev->dsa_ptr = dst; - dst->applied = true; + err = dsa_port_setup(dp); + if (err) + return err; + } + } return 0; } -static void dsa_dst_unapply(struct dsa_switch_tree *dst) +static void dsa_tree_teardown_switches(struct dsa_switch_tree *dst) { struct dsa_switch *ds; - u32 index; - - if (!dst->applied) - return; - - dst->cpu_dp->netdev->dsa_ptr = NULL; - - /* If we used a tagging format that doesn't have an ethertype - * field, make sure that all packets from this point get sent - * without the tag and go through the regular receive path. - */ - wmb(); + struct dsa_port *dp; + int device, port; - for (index = 0; index < DSA_MAX_SWITCHES; index++) { - ds = dst->ds[index]; + for (device = 0; device < DSA_MAX_SWITCHES; device++) { + ds = dst->ds[device]; if (!ds) continue; - dsa_ds_unapply(dst, ds); - } + for (port = 0; port < ds->num_ports; port++) { + dp = &ds->ports[port]; - if (dst->cpu_dp) { - dsa_cpu_port_ethtool_restore(dst->cpu_dp); - dst->cpu_dp = NULL; + dsa_port_teardown(dp); + } + + dsa_switch_teardown(ds); } +} + +static int dsa_tree_setup_master(struct dsa_switch_tree *dst) +{ + struct dsa_port *cpu_dp = dst->cpu_dp; + struct net_device *master = cpu_dp->master; - pr_info("DSA: tree %d unapplied\n", dst->tree); - dst->applied = false; + /* DSA currently supports a single pair of CPU port and master device */ + return dsa_master_setup(master, cpu_dp); } -static int dsa_cpu_parse(struct dsa_port *port, u32 index, - struct dsa_switch_tree *dst, - struct dsa_switch *ds) +static void dsa_tree_teardown_master(struct dsa_switch_tree *dst) { - enum dsa_tag_protocol tag_protocol; - struct net_device *ethernet_dev; - struct device_node *ethernet; + struct dsa_port *cpu_dp = dst->cpu_dp; + struct net_device *master = cpu_dp->master; - if (port->dn) { - ethernet = of_parse_phandle(port->dn, "ethernet", 0); - if (!ethernet) - return -EINVAL; - ethernet_dev = of_find_net_device_by_node(ethernet); - if (!ethernet_dev) - return -EPROBE_DEFER; - } else { - ethernet_dev = dsa_dev_to_net_device(ds->cd->netdev[index]); - if (!ethernet_dev) - return -EPROBE_DEFER; - dev_put(ethernet_dev); - } + return dsa_master_teardown(master); +} - if (!dst->cpu_dp) { - dst->cpu_dp = port; - dst->cpu_dp->netdev = ethernet_dev; +static int dsa_tree_setup(struct dsa_switch_tree *dst) +{ + bool complete; + int err; + + if (dst->setup) { + pr_err("DSA: tree %d already setup! Disjoint trees?\n", + dst->index); + return -EEXIST; } - /* Initialize cpu_port_mask now for drv->setup() - * to have access to a correct value, just like what - * net/dsa/dsa.c::dsa_switch_setup_one does. - */ - ds->cpu_port_mask |= BIT(index); + complete = dsa_tree_setup_routing_table(dst); + if (!complete) + return 0; - tag_protocol = ds->ops->get_tag_protocol(ds); - dst->tag_ops = dsa_resolve_tag_protocol(tag_protocol); - if (IS_ERR(dst->tag_ops)) { - dev_warn(ds->dev, "No tagger for this switch\n"); - ds->cpu_port_mask &= ~BIT(index); - return PTR_ERR(dst->tag_ops); - } + err = dsa_tree_setup_default_cpu(dst); + if (err) + return err; - dst->rcv = dst->tag_ops->rcv; + err = dsa_tree_setup_switches(dst); + if (err) + return err; + + err = dsa_tree_setup_master(dst); + if (err) + return err; + + dst->setup = true; + + pr_info("DSA: tree %d setup\n", dst->index); return 0; } -static int dsa_ds_parse(struct dsa_switch_tree *dst, struct dsa_switch *ds) +static void dsa_tree_teardown(struct dsa_switch_tree *dst) +{ + if (!dst->setup) + return; + + dsa_tree_teardown_master(dst); + + dsa_tree_teardown_switches(dst); + + dsa_tree_teardown_default_cpu(dst); + + pr_info("DSA: tree %d torn down\n", dst->index); + + dst->setup = false; +} + +static void dsa_tree_remove_switch(struct dsa_switch_tree *dst, + unsigned int index) { - struct dsa_port *port; - u32 index; + dsa_tree_teardown(dst); + + dst->ds[index] = NULL; + dsa_tree_put(dst); +} + +static int dsa_tree_add_switch(struct dsa_switch_tree *dst, + struct dsa_switch *ds) +{ + unsigned int index = ds->index; int err; - for (index = 0; index < ds->num_ports; index++) { - port = &ds->ports[index]; - if (!dsa_port_is_valid(port) || - dsa_port_is_dsa(port)) - continue; + if (dst->ds[index]) + return -EBUSY; - if (dsa_port_is_cpu(port)) { - err = dsa_cpu_parse(port, index, dst, ds); - if (err) - return err; - } else { - /* Initialize enabled_port_mask now for drv->setup() - * to have access to a correct value, just like what - * net/dsa/dsa.c::dsa_switch_setup_one does. - */ - ds->enabled_port_mask |= BIT(index); - } + dsa_tree_get(dst); + dst->ds[index] = ds; - } + err = dsa_tree_setup(dst); + if (err) + dsa_tree_remove_switch(dst, index); - pr_info("DSA: switch %d %d parsed\n", dst->tree, ds->index); + return err; +} + +static int dsa_port_parse_user(struct dsa_port *dp, const char *name) +{ + if (!name) + name = "eth%d"; + + dp->type = DSA_PORT_TYPE_USER; + dp->name = name; return 0; } -static int dsa_dst_parse(struct dsa_switch_tree *dst) +static int dsa_port_parse_dsa(struct dsa_port *dp) { - struct dsa_switch *ds; - struct dsa_port *dp; - u32 index; - int port; - int err; + dp->type = DSA_PORT_TYPE_DSA; - for (index = 0; index < DSA_MAX_SWITCHES; index++) { - ds = dst->ds[index]; - if (!ds) - continue; + return 0; +} - err = dsa_ds_parse(dst, ds); - if (err) - return err; - } +static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master) +{ + struct dsa_switch *ds = dp->ds; + struct dsa_switch_tree *dst = ds->dst; + const struct dsa_device_ops *tag_ops; + enum dsa_tag_protocol tag_protocol; - if (!dst->cpu_dp) { - pr_warn("Tree has no master device\n"); - return -EINVAL; + tag_protocol = ds->ops->get_tag_protocol(ds, dp->index); + tag_ops = dsa_resolve_tag_protocol(tag_protocol); + if (IS_ERR(tag_ops)) { + dev_warn(ds->dev, "No tagger for this switch\n"); + return PTR_ERR(tag_ops); } - /* Assign the default CPU port to all ports of the fabric */ - for (index = 0; index < DSA_MAX_SWITCHES; index++) { - ds = dst->ds[index]; - if (!ds) - continue; + dp->type = DSA_PORT_TYPE_CPU; + dp->rcv = tag_ops->rcv; + dp->tag_ops = tag_ops; + dp->master = master; + dp->dst = dst; - for (port = 0; port < ds->num_ports; port++) { - dp = &ds->ports[port]; - if (!dsa_port_is_valid(dp) || - dsa_port_is_dsa(dp) || - dsa_port_is_cpu(dp)) - continue; + return 0; +} - dp->cpu_dp = dst->cpu_dp; - } +static int dsa_port_parse_of(struct dsa_port *dp, struct device_node *dn) +{ + struct device_node *ethernet = of_parse_phandle(dn, "ethernet", 0); + const char *name = of_get_property(dn, "label", NULL); + bool link = of_property_read_bool(dn, "link"); + + dp->dn = dn; + + if (ethernet) { + struct net_device *master; + + master = of_find_net_device_by_node(ethernet); + if (!master) + return -EPROBE_DEFER; + + return dsa_port_parse_cpu(dp, master); } - pr_info("DSA: tree %d parsed\n", dst->tree); + if (link) + return dsa_port_parse_dsa(dp); - return 0; + return dsa_port_parse_user(dp, name); } -static int dsa_parse_ports_dn(struct device_node *ports, struct dsa_switch *ds) +static int dsa_switch_parse_ports_of(struct dsa_switch *ds, + struct device_node *dn) { - struct device_node *port; - int err; + struct device_node *ports, *port; + struct dsa_port *dp; u32 reg; + int err; + + ports = of_get_child_by_name(dn, "ports"); + if (!ports) { + dev_err(ds->dev, "no ports child node found\n"); + return -EINVAL; + } for_each_available_child_of_node(ports, port) { err = of_property_read_u32(port, "reg", ®); @@ -619,174 +601,140 @@ static int dsa_parse_ports_dn(struct device_node *ports, struct dsa_switch *ds) if (reg >= ds->num_ports) return -EINVAL; - ds->ports[reg].dn = port; + dp = &ds->ports[reg]; + + err = dsa_port_parse_of(dp, port); + if (err) + return err; } return 0; } -static int dsa_parse_ports(struct dsa_chip_data *cd, struct dsa_switch *ds) +static int dsa_switch_parse_member_of(struct dsa_switch *ds, + struct device_node *dn) { - bool valid_name_found = false; - unsigned int i; + u32 m[2] = { 0, 0 }; + int sz; - for (i = 0; i < DSA_MAX_PORTS; i++) { - if (!cd->port_names[i]) - continue; + /* Don't error out if this optional property isn't found */ + sz = of_property_read_variable_u32_array(dn, "dsa,member", m, 2, 2); + if (sz < 0 && sz != -EINVAL) + return sz; - ds->ports[i].name = cd->port_names[i]; - valid_name_found = true; - } - - if (!valid_name_found && i == DSA_MAX_PORTS) + ds->index = m[1]; + if (ds->index >= DSA_MAX_SWITCHES) return -EINVAL; + ds->dst = dsa_tree_touch(m[0]); + if (!ds->dst) + return -ENOMEM; + return 0; } -static int dsa_parse_member_dn(struct device_node *np, u32 *tree, u32 *index) +static int dsa_switch_parse_of(struct dsa_switch *ds, struct device_node *dn) { int err; - *tree = *index = 0; - - err = of_property_read_u32_index(np, "dsa,member", 0, tree); - if (err) { - /* Does not exist, but it is optional */ - if (err == -EINVAL) - return 0; - return err; - } - - err = of_property_read_u32_index(np, "dsa,member", 1, index); + err = dsa_switch_parse_member_of(ds, dn); if (err) return err; - if (*index >= DSA_MAX_SWITCHES) - return -EINVAL; - - return 0; + return dsa_switch_parse_ports_of(ds, dn); } -static int dsa_parse_member(struct dsa_chip_data *pd, u32 *tree, u32 *index) +static int dsa_port_parse(struct dsa_port *dp, const char *name, + struct device *dev) { - if (!pd) - return -ENODEV; - - /* We do not support complex trees with dsa_chip_data */ - *tree = 0; - *index = 0; + if (!strcmp(name, "cpu")) { + struct net_device *master; - return 0; -} + master = dsa_dev_to_net_device(dev); + if (!master) + return -EPROBE_DEFER; -static struct device_node *dsa_get_ports(struct dsa_switch *ds, - struct device_node *np) -{ - struct device_node *ports; + dev_put(master); - ports = of_get_child_by_name(np, "ports"); - if (!ports) { - dev_err(ds->dev, "no ports child node found\n"); - return ERR_PTR(-EINVAL); + return dsa_port_parse_cpu(dp, master); } - return ports; + if (!strcmp(name, "dsa")) + return dsa_port_parse_dsa(dp); + + return dsa_port_parse_user(dp, name); } -static int _dsa_register_switch(struct dsa_switch *ds) +static int dsa_switch_parse_ports(struct dsa_switch *ds, + struct dsa_chip_data *cd) { - struct dsa_chip_data *pdata = ds->dev->platform_data; - struct device_node *np = ds->dev->of_node; - struct dsa_switch_tree *dst; - struct device_node *ports; - u32 tree, index; - int i, err; - - if (np) { - err = dsa_parse_member_dn(np, &tree, &index); - if (err) - return err; + bool valid_name_found = false; + struct dsa_port *dp; + struct device *dev; + const char *name; + unsigned int i; + int err; - ports = dsa_get_ports(ds, np); - if (IS_ERR(ports)) - return PTR_ERR(ports); + for (i = 0; i < DSA_MAX_PORTS; i++) { + name = cd->port_names[i]; + dev = cd->netdev[i]; + dp = &ds->ports[i]; - err = dsa_parse_ports_dn(ports, ds); - if (err) - return err; - } else { - err = dsa_parse_member(pdata, &tree, &index); - if (err) - return err; + if (!name) + continue; - err = dsa_parse_ports(pdata, ds); + err = dsa_port_parse(dp, name, dev); if (err) return err; - } - dst = dsa_get_dst(tree); - if (!dst) { - dst = dsa_add_dst(tree); - if (!dst) - return -ENOMEM; - } - - if (dst->ds[index]) { - err = -EBUSY; - goto out; + valid_name_found = true; } - ds->dst = dst; - ds->index = index; - ds->cd = pdata; - - /* Initialize the routing table */ - for (i = 0; i < DSA_MAX_SWITCHES; ++i) - ds->rtable[i] = DSA_RTABLE_NONE; + if (!valid_name_found && i == DSA_MAX_PORTS) + return -EINVAL; - dsa_dst_add_ds(dst, ds, index); + return 0; +} - err = dsa_dst_complete(dst); - if (err < 0) - goto out_del_dst; +static int dsa_switch_parse(struct dsa_switch *ds, struct dsa_chip_data *cd) +{ + ds->cd = cd; - if (err == 1) { - /* Not all switches registered yet */ - err = 0; - goto out; - } + /* We don't support interconnected switches nor multiple trees via + * platform data, so this is the unique switch of the tree. + */ + ds->index = 0; + ds->dst = dsa_tree_touch(0); + if (!ds->dst) + return -ENOMEM; - if (dst->applied) { - pr_info("DSA: Disjoint trees?\n"); - return -EINVAL; - } + return dsa_switch_parse_ports(ds, cd); +} - err = dsa_dst_parse(dst); - if (err) { - if (err == -EPROBE_DEFER) { - dsa_dst_del_ds(dst, ds, ds->index); - return err; - } +static int dsa_switch_add(struct dsa_switch *ds) +{ + struct dsa_switch_tree *dst = ds->dst; - goto out_del_dst; - } + return dsa_tree_add_switch(dst, ds); +} - err = dsa_dst_apply(dst); - if (err) { - dsa_dst_unapply(dst); - goto out_del_dst; - } +static int dsa_switch_probe(struct dsa_switch *ds) +{ + struct dsa_chip_data *pdata = ds->dev->platform_data; + struct device_node *np = ds->dev->of_node; + int err; - dsa_put_dst(dst); - return 0; + if (np) + err = dsa_switch_parse_of(ds, np); + else if (pdata) + err = dsa_switch_parse(ds, pdata); + else + err = -ENODEV; -out_del_dst: - dsa_dst_del_ds(dst, ds, ds->index); -out: - dsa_put_dst(dst); + if (err) + return err; - return err; + return dsa_switch_add(ds); } struct dsa_switch *dsa_switch_alloc(struct device *dev, size_t n) @@ -816,26 +764,25 @@ int dsa_register_switch(struct dsa_switch *ds) int err; mutex_lock(&dsa2_mutex); - err = _dsa_register_switch(ds); + err = dsa_switch_probe(ds); mutex_unlock(&dsa2_mutex); return err; } EXPORT_SYMBOL_GPL(dsa_register_switch); -static void _dsa_unregister_switch(struct dsa_switch *ds) +static void dsa_switch_remove(struct dsa_switch *ds) { struct dsa_switch_tree *dst = ds->dst; + unsigned int index = ds->index; - dsa_dst_unapply(dst); - - dsa_dst_del_ds(dst, ds, ds->index); + dsa_tree_remove_switch(dst, index); } void dsa_unregister_switch(struct dsa_switch *ds) { mutex_lock(&dsa2_mutex); - _dsa_unregister_switch(ds); + dsa_switch_remove(ds); mutex_unlock(&dsa2_mutex); } EXPORT_SYMBOL_GPL(dsa_unregister_switch); diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 9c3eeb72462d..7d036696e8c4 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -66,7 +66,7 @@ struct dsa_notifier_vlan_info { }; struct dsa_slave_priv { - /* Copy of dp->ds->dst->tag_ops->xmit for faster access in hot path */ + /* Copy of CPU port xmit for faster access in slave transmit hot path */ struct sk_buff * (*xmit)(struct sk_buff *skb, struct net_device *dev); @@ -79,7 +79,6 @@ struct dsa_slave_priv { * The phylib phy_device pointer for the PHY connected * to this port. */ - struct phy_device *phy; phy_interface_t phy_interface; int old_link; int old_pause; @@ -94,11 +93,7 @@ struct dsa_slave_priv { }; /* dsa.c */ -int dsa_cpu_dsa_setup(struct dsa_port *port); -void dsa_cpu_dsa_destroy(struct dsa_port *dport); const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol); -int dsa_cpu_port_ethtool_setup(struct dsa_port *cpu_dp); -void dsa_cpu_port_ethtool_restore(struct dsa_port *cpu_dp); bool dsa_schedule_work(struct work_struct *work); /* legacy.c */ @@ -112,10 +107,35 @@ int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid); +/* master.c */ +int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp); +void dsa_master_teardown(struct net_device *dev); + +static inline struct net_device *dsa_master_find_slave(struct net_device *dev, + int device, int port) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + struct dsa_switch_tree *dst = cpu_dp->dst; + struct dsa_switch *ds; + + if (device < 0 || device >= DSA_MAX_SWITCHES) + return NULL; + + ds = dst->ds[device]; + if (!ds) + return NULL; + + if (port < 0 || port >= ds->num_ports) + return NULL; + + return ds->ports[port].slave; +} + /* port.c */ int dsa_port_set_state(struct dsa_port *dp, u8 state, struct switchdev_trans *trans); -void dsa_port_set_state_now(struct dsa_port *dp, u8 state); +int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy); +void dsa_port_disable(struct dsa_port *dp, struct phy_device *phy); int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br); void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br); int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, @@ -126,33 +146,52 @@ int dsa_port_fdb_add(struct dsa_port *dp, const unsigned char *addr, u16 vid); int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr, u16 vid); -int dsa_port_mdb_add(struct dsa_port *dp, +int dsa_port_fdb_dump(struct dsa_port *dp, dsa_fdb_dump_cb_t *cb, void *data); +int dsa_port_mdb_add(const struct dsa_port *dp, const struct switchdev_obj_port_mdb *mdb, struct switchdev_trans *trans); -int dsa_port_mdb_del(struct dsa_port *dp, +int dsa_port_mdb_del(const struct dsa_port *dp, const struct switchdev_obj_port_mdb *mdb); int dsa_port_vlan_add(struct dsa_port *dp, const struct switchdev_obj_port_vlan *vlan, struct switchdev_trans *trans); int dsa_port_vlan_del(struct dsa_port *dp, const struct switchdev_obj_port_vlan *vlan); +int dsa_port_fixed_link_register_of(struct dsa_port *dp); +void dsa_port_fixed_link_unregister_of(struct dsa_port *dp); + /* slave.c */ extern const struct dsa_device_ops notag_netdev_ops; void dsa_slave_mii_bus_init(struct dsa_switch *ds); -void dsa_cpu_port_ethtool_init(struct ethtool_ops *ops); -int dsa_slave_create(struct dsa_port *port, const char *name); +int dsa_slave_create(struct dsa_port *dp); void dsa_slave_destroy(struct net_device *slave_dev); int dsa_slave_suspend(struct net_device *slave_dev); int dsa_slave_resume(struct net_device *slave_dev); int dsa_slave_register_notifier(void); void dsa_slave_unregister_notifier(void); +static inline struct dsa_port *dsa_slave_to_port(const struct net_device *dev) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + + return p->dp; +} + +static inline struct net_device * +dsa_slave_to_master(const struct net_device *dev) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + + return dp->cpu_dp->master; +} + /* switch.c */ int dsa_switch_register_notifier(struct dsa_switch *ds); void dsa_switch_unregister_notifier(struct dsa_switch *ds); /* tag_brcm.c */ extern const struct dsa_device_ops brcm_netdev_ops; +extern const struct dsa_device_ops brcm_prepend_netdev_ops; /* tag_dsa.c */ extern const struct dsa_device_ops dsa_netdev_ops; @@ -175,14 +214,4 @@ extern const struct dsa_device_ops qca_netdev_ops; /* tag_trailer.c */ extern const struct dsa_device_ops trailer_netdev_ops; -static inline struct net_device *dsa_master_netdev(struct dsa_slave_priv *p) -{ - return p->dp->cpu_dp->netdev; -} - -static inline struct dsa_port *dsa_get_cpu_port(struct dsa_switch_tree *dst) -{ - return dst->cpu_dp; -} - #endif diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index 91e6f7981d39..84611d7fcfa2 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -86,7 +86,7 @@ static int dsa_cpu_dsa_setups(struct dsa_switch *ds) if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port))) continue; - ret = dsa_cpu_dsa_setup(&ds->ports[port]); + ret = dsa_port_fixed_link_register_of(&ds->ports[port]); if (ret) return ret; } @@ -101,6 +101,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct dsa_chip_data *cd = ds->cd; bool valid_name_found = false; int index = ds->index; + struct dsa_port *dp; int i, ret; /* @@ -109,9 +110,12 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, for (i = 0; i < ds->num_ports; i++) { char *name; + dp = &ds->ports[i]; + name = cd->port_names[i]; if (name == NULL) continue; + dp->name = name; if (!strcmp(name, "cpu")) { if (dst->cpu_dp) { @@ -120,12 +124,12 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, return -EINVAL; } dst->cpu_dp = &ds->ports[i]; - dst->cpu_dp->netdev = master; - ds->cpu_port_mask |= 1 << i; + dst->cpu_dp->master = master; + dp->type = DSA_PORT_TYPE_CPU; } else if (!strcmp(name, "dsa")) { - ds->dsa_port_mask |= 1 << i; + dp->type = DSA_PORT_TYPE_DSA; } else { - ds->enabled_port_mask |= 1 << i; + dp->type = DSA_PORT_TYPE_USER; } valid_name_found = true; } @@ -136,7 +140,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, /* Make the built-in MII bus mask match the number of ports, * switch drivers can override this later */ - ds->phys_mii_mask = ds->enabled_port_mask; + ds->phys_mii_mask |= dsa_user_ports(ds); /* * If the CPU connects to this switch, set the switch tree @@ -144,14 +148,19 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, * switch. */ if (dst->cpu_dp->ds == ds) { + const struct dsa_device_ops *tag_ops; enum dsa_tag_protocol tag_protocol; - tag_protocol = ops->get_tag_protocol(ds); - dst->tag_ops = dsa_resolve_tag_protocol(tag_protocol); - if (IS_ERR(dst->tag_ops)) - return PTR_ERR(dst->tag_ops); + tag_protocol = ops->get_tag_protocol(ds, dst->cpu_dp->index); + tag_ops = dsa_resolve_tag_protocol(tag_protocol); + if (IS_ERR(tag_ops)) + return PTR_ERR(tag_ops); + + dst->cpu_dp->tag_ops = tag_ops; - dst->rcv = dst->tag_ops->rcv; + /* Few copies for faster access in master receive hot path */ + dst->cpu_dp->rcv = dst->cpu_dp->tag_ops->rcv; + dst->cpu_dp->dst = dst; } memcpy(ds->rtable, cd->rtable, sizeof(ds->rtable)); @@ -167,12 +176,6 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, if (ret) return ret; - if (ops->set_addr) { - ret = ops->set_addr(ds, master->dev_addr); - if (ret < 0) - return ret; - } - if (!ds->slave_mii_bus && ops->phy_read) { ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev); if (!ds->slave_mii_bus) @@ -191,10 +194,10 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, ds->ports[i].dn = cd->port_dn[i]; ds->ports[i].cpu_dp = dst->cpu_dp; - if (!(ds->enabled_port_mask & (1 << i))) + if (dsa_is_user_port(ds, i)) continue; - ret = dsa_slave_create(&ds->ports[i], cd->port_names[i]); + ret = dsa_slave_create(&ds->ports[i]); if (ret < 0) netdev_err(master, "[%d]: can't create dsa slave device for port %d(%s): %d\n", index, i, cd->port_names[i], ret); @@ -206,10 +209,6 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, netdev_err(master, "[%d] : can't configure CPU and DSA ports\n", index); - ret = dsa_cpu_port_ethtool_setup(ds->dst->cpu_dp); - if (ret) - return ret; - return 0; } @@ -263,24 +262,20 @@ static void dsa_switch_destroy(struct dsa_switch *ds) /* Destroy network devices for physical switch ports. */ for (port = 0; port < ds->num_ports; port++) { - if (!(ds->enabled_port_mask & (1 << port))) + if (!dsa_is_user_port(ds, port)) continue; - if (!ds->ports[port].netdev) + if (!ds->ports[port].slave) continue; - dsa_slave_destroy(ds->ports[port].netdev); + dsa_slave_destroy(ds->ports[port].slave); } /* Disable configuration of the CPU and DSA ports */ for (port = 0; port < ds->num_ports; port++) { if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port))) continue; - dsa_cpu_dsa_destroy(&ds->ports[port]); - - /* Clearing a bit which is not set does no harm */ - ds->cpu_port_mask |= ~(1 << port); - ds->dsa_port_mask |= ~(1 << port); + dsa_port_fixed_link_unregister_of(&ds->ports[port]); } if (ds->slave_mii_bus && ds->ops->phy_read) @@ -598,15 +593,7 @@ static int dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, if (!configured) return -EPROBE_DEFER; - /* - * If we use a tagging format that doesn't have an ethertype - * field, make sure that all packets from this point on get - * sent to the tag format's receive function. - */ - wmb(); - dev->dsa_ptr = dst; - - return 0; + return dsa_master_setup(dst->cpu_dp->master, dst->cpu_dp); } static int dsa_probe(struct platform_device *pdev) @@ -671,13 +658,7 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst) { int i; - dst->cpu_dp->netdev->dsa_ptr = NULL; - - /* If we used a tagging format that doesn't have an ethertype - * field, make sure that all packets from this point get sent - * without the tag and go through the regular receive path. - */ - wmb(); + dsa_master_teardown(dst->cpu_dp->master); for (i = 0; i < dst->pd->nr_chips; i++) { struct dsa_switch *ds = dst->ds[i]; @@ -686,9 +667,7 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst) dsa_switch_destroy(ds); } - dsa_cpu_port_ethtool_restore(dst->cpu_dp); - - dev_put(dst->cpu_dp->netdev); + dev_put(dst->cpu_dp->master); } static int dsa_remove(struct platform_device *pdev) @@ -745,8 +724,7 @@ int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], const unsigned char *addr, u16 vid, u16 flags) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; + struct dsa_port *dp = dsa_slave_to_port(dev); return dsa_port_fdb_add(dp, addr, vid); } @@ -755,8 +733,7 @@ int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; + struct dsa_port *dp = dsa_slave_to_port(dev); return dsa_port_fdb_del(dp, addr, vid); } diff --git a/net/dsa/master.c b/net/dsa/master.c new file mode 100644 index 000000000000..00589147f042 --- /dev/null +++ b/net/dsa/master.c @@ -0,0 +1,143 @@ +/* + * Handling of a master device, switching frames via its switch fabric CPU port + * + * Copyright (c) 2017 Savoir-faire Linux Inc. + * Vivien Didelot <vivien.didelot@savoirfairelinux.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include "dsa_priv.h" + +static void dsa_master_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, + uint64_t *data) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch *ds = cpu_dp->ds; + int port = cpu_dp->index; + int count = 0; + + if (ops && ops->get_sset_count && ops->get_ethtool_stats) { + count = ops->get_sset_count(dev, ETH_SS_STATS); + ops->get_ethtool_stats(dev, stats, data); + } + + if (ds->ops->get_ethtool_stats) + ds->ops->get_ethtool_stats(ds, port, data + count); +} + +static int dsa_master_get_sset_count(struct net_device *dev, int sset) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch *ds = cpu_dp->ds; + int count = 0; + + if (ops && ops->get_sset_count) + count += ops->get_sset_count(dev, sset); + + if (sset == ETH_SS_STATS && ds->ops->get_sset_count) + count += ds->ops->get_sset_count(ds); + + return count; +} + +static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, + uint8_t *data) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch *ds = cpu_dp->ds; + int port = cpu_dp->index; + int len = ETH_GSTRING_LEN; + int mcount = 0, count; + unsigned int i; + uint8_t pfx[4]; + uint8_t *ndata; + + snprintf(pfx, sizeof(pfx), "p%.2d", port); + /* We do not want to be NULL-terminated, since this is a prefix */ + pfx[sizeof(pfx) - 1] = '_'; + + if (ops && ops->get_sset_count && ops->get_strings) { + mcount = ops->get_sset_count(dev, ETH_SS_STATS); + ops->get_strings(dev, stringset, data); + } + + if (stringset == ETH_SS_STATS && ds->ops->get_strings) { + ndata = data + mcount * len; + /* This function copies ETH_GSTRINGS_LEN bytes, we will mangle + * the output after to prepend our CPU port prefix we + * constructed earlier + */ + ds->ops->get_strings(ds, port, ndata); + count = ds->ops->get_sset_count(ds); + for (i = 0; i < count; i++) { + memmove(ndata + (i * len + sizeof(pfx)), + ndata + i * len, len - sizeof(pfx)); + memcpy(ndata + i * len, pfx, sizeof(pfx)); + } + } +} + +static int dsa_master_ethtool_setup(struct net_device *dev) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + struct dsa_switch *ds = cpu_dp->ds; + struct ethtool_ops *ops; + + ops = devm_kzalloc(ds->dev, sizeof(*ops), GFP_KERNEL); + if (!ops) + return -ENOMEM; + + cpu_dp->orig_ethtool_ops = dev->ethtool_ops; + if (cpu_dp->orig_ethtool_ops) + memcpy(ops, cpu_dp->orig_ethtool_ops, sizeof(*ops)); + + ops->get_sset_count = dsa_master_get_sset_count; + ops->get_ethtool_stats = dsa_master_get_ethtool_stats; + ops->get_strings = dsa_master_get_strings; + + dev->ethtool_ops = ops; + + return 0; +} + +static void dsa_master_ethtool_teardown(struct net_device *dev) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + + dev->ethtool_ops = cpu_dp->orig_ethtool_ops; + cpu_dp->orig_ethtool_ops = NULL; +} + +int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) +{ + /* If we use a tagging format that doesn't have an ethertype + * field, make sure that all packets from this point on get + * sent to the tag format's receive function. + */ + wmb(); + + dev->dsa_ptr = cpu_dp; + + return dsa_master_ethtool_setup(dev); +} + +void dsa_master_teardown(struct net_device *dev) +{ + dsa_master_ethtool_teardown(dev); + + dev->dsa_ptr = NULL; + + /* If we used a tagging format that doesn't have an ethertype + * field, make sure that all packets from this point get sent + * without the tag and go through the regular receive path. + */ + wmb(); +} diff --git a/net/dsa/port.c b/net/dsa/port.c index 659676ba3f8b..bb4be2679904 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -12,10 +12,12 @@ #include <linux/if_bridge.h> #include <linux/notifier.h> +#include <linux/of_mdio.h> +#include <linux/of_net.h> #include "dsa_priv.h" -static int dsa_port_notify(struct dsa_port *dp, unsigned long e, void *v) +static int dsa_port_notify(const struct dsa_port *dp, unsigned long e, void *v) { struct raw_notifier_head *nh = &dp->ds->dst->nh; int err; @@ -56,7 +58,7 @@ int dsa_port_set_state(struct dsa_port *dp, u8 state, return 0; } -void dsa_port_set_state_now(struct dsa_port *dp, u8 state) +static void dsa_port_set_state_now(struct dsa_port *dp, u8 state) { int err; @@ -65,6 +67,35 @@ void dsa_port_set_state_now(struct dsa_port *dp, u8 state) pr_err("DSA: failed to set STP state %u (%d)\n", state, err); } +int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy) +{ + u8 stp_state = dp->bridge_dev ? BR_STATE_BLOCKING : BR_STATE_FORWARDING; + struct dsa_switch *ds = dp->ds; + int port = dp->index; + int err; + + if (ds->ops->port_enable) { + err = ds->ops->port_enable(ds, port, phy); + if (err) + return err; + } + + dsa_port_set_state_now(dp, stp_state); + + return 0; +} + +void dsa_port_disable(struct dsa_port *dp, struct phy_device *phy) +{ + struct dsa_switch *ds = dp->ds; + int port = dp->index; + + dsa_port_set_state_now(dp, BR_STATE_DISABLED); + + if (ds->ops->port_disable) + ds->ops->port_disable(ds, port, phy); +} + int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br) { struct dsa_notifier_bridge_info info = { @@ -173,7 +204,18 @@ int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr, return dsa_port_notify(dp, DSA_NOTIFIER_FDB_DEL, &info); } -int dsa_port_mdb_add(struct dsa_port *dp, +int dsa_port_fdb_dump(struct dsa_port *dp, dsa_fdb_dump_cb_t *cb, void *data) +{ + struct dsa_switch *ds = dp->ds; + int port = dp->index; + + if (!ds->ops->port_fdb_dump) + return -EOPNOTSUPP; + + return ds->ops->port_fdb_dump(ds, port, cb, data); +} + +int dsa_port_mdb_add(const struct dsa_port *dp, const struct switchdev_obj_port_mdb *mdb, struct switchdev_trans *trans) { @@ -187,7 +229,7 @@ int dsa_port_mdb_add(struct dsa_port *dp, return dsa_port_notify(dp, DSA_NOTIFIER_MDB_ADD, &info); } -int dsa_port_mdb_del(struct dsa_port *dp, +int dsa_port_mdb_del(const struct dsa_port *dp, const struct switchdev_obj_port_mdb *mdb) { struct dsa_notifier_mdb_info info = { @@ -210,7 +252,10 @@ int dsa_port_vlan_add(struct dsa_port *dp, .vlan = vlan, }; - return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_ADD, &info); + if (br_vlan_enabled(dp->bridge_dev)) + return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_ADD, &info); + + return 0; } int dsa_port_vlan_del(struct dsa_port *dp, @@ -222,5 +267,53 @@ int dsa_port_vlan_del(struct dsa_port *dp, .vlan = vlan, }; - return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_DEL, &info); + if (br_vlan_enabled(dp->bridge_dev)) + return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_DEL, &info); + + return 0; +} + +int dsa_port_fixed_link_register_of(struct dsa_port *dp) +{ + struct device_node *dn = dp->dn; + struct dsa_switch *ds = dp->ds; + struct phy_device *phydev; + int port = dp->index; + int mode; + int err; + + if (of_phy_is_fixed_link(dn)) { + err = of_phy_register_fixed_link(dn); + if (err) { + dev_err(ds->dev, + "failed to register the fixed PHY of port %d\n", + port); + return err; + } + + phydev = of_phy_find_device(dn); + + mode = of_get_phy_mode(dn); + if (mode < 0) + mode = PHY_INTERFACE_MODE_NA; + phydev->interface = mode; + + genphy_config_init(phydev); + genphy_read_status(phydev); + + if (ds->ops->adjust_link) + ds->ops->adjust_link(ds, port, phydev); + + put_device(&phydev->mdio.dev); + } + + return 0; +} + +void dsa_port_fixed_link_unregister_of(struct dsa_port *dp) +{ + struct device_node *dn = dp->dn; + + if (of_phy_is_fixed_link(dn)) + of_phy_deregister_fixed_link(dn); } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 865e29e62bad..d6e7a642493b 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -55,7 +55,7 @@ void dsa_slave_mii_bus_init(struct dsa_switch *ds) ds->slave_mii_bus->read = dsa_slave_phy_read; ds->slave_mii_bus->write = dsa_slave_phy_write; snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d.%d", - ds->dst->tree, ds->index); + ds->dst->index, ds->index); ds->slave_mii_bus->parent = ds->dev; ds->slave_mii_bus->phy_mask = ~ds->phys_mii_mask; } @@ -64,18 +64,13 @@ void dsa_slave_mii_bus_init(struct dsa_switch *ds) /* slave device handling ****************************************************/ static int dsa_slave_get_iflink(const struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); - - return dsa_master_netdev(p)->ifindex; + return dsa_slave_to_master(dev)->ifindex; } static int dsa_slave_open(struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; - struct dsa_switch *ds = dp->ds; - struct net_device *master = dsa_master_netdev(p); - u8 stp_state = dp->bridge_dev ? BR_STATE_BLOCKING : BR_STATE_FORWARDING; + struct net_device *master = dsa_slave_to_master(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); int err; if (!(master->flags & IFF_UP)) @@ -98,16 +93,12 @@ static int dsa_slave_open(struct net_device *dev) goto clear_allmulti; } - if (ds->ops->port_enable) { - err = ds->ops->port_enable(ds, p->dp->index, p->phy); - if (err) - goto clear_promisc; - } - - dsa_port_set_state_now(p->dp, stp_state); + err = dsa_port_enable(dp, dev->phydev); + if (err) + goto clear_promisc; - if (p->phy) - phy_start(p->phy); + if (dev->phydev) + phy_start(dev->phydev); return 0; @@ -126,12 +117,13 @@ out: static int dsa_slave_close(struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = dsa_master_netdev(p); - struct dsa_switch *ds = p->dp->ds; + struct net_device *master = dsa_slave_to_master(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); + + if (dev->phydev) + phy_stop(dev->phydev); - if (p->phy) - phy_stop(p->phy); + dsa_port_disable(dp, dev->phydev); dev_mc_unsync(master, dev); dev_uc_unsync(master, dev); @@ -143,18 +135,12 @@ static int dsa_slave_close(struct net_device *dev) if (!ether_addr_equal(dev->dev_addr, master->dev_addr)) dev_uc_del(master, dev->dev_addr); - if (ds->ops->port_disable) - ds->ops->port_disable(ds, p->dp->index, p->phy); - - dsa_port_set_state_now(p->dp, BR_STATE_DISABLED); - return 0; } static void dsa_slave_change_rx_flags(struct net_device *dev, int change) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = dsa_master_netdev(p); + struct net_device *master = dsa_slave_to_master(dev); if (change & IFF_ALLMULTI) dev_set_allmulti(master, dev->flags & IFF_ALLMULTI ? 1 : -1); @@ -164,8 +150,7 @@ static void dsa_slave_change_rx_flags(struct net_device *dev, int change) static void dsa_slave_set_rx_mode(struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = dsa_master_netdev(p); + struct net_device *master = dsa_slave_to_master(dev); dev_mc_sync(master, dev); dev_uc_sync(master, dev); @@ -173,8 +158,7 @@ static void dsa_slave_set_rx_mode(struct net_device *dev) static int dsa_slave_set_mac_address(struct net_device *dev, void *a) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = dsa_master_netdev(p); + struct net_device *master = dsa_slave_to_master(dev); struct sockaddr *addr = a; int err; @@ -255,43 +239,34 @@ dsa_slave_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, int *idx) { + struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_slave_dump_ctx dump = { .dev = dev, .skb = skb, .cb = cb, .idx = *idx, }; - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; - struct dsa_switch *ds = dp->ds; int err; - if (!ds->ops->port_fdb_dump) - return -EOPNOTSUPP; - - err = ds->ops->port_fdb_dump(ds, dp->index, - dsa_slave_port_fdb_do_dump, - &dump); + err = dsa_port_fdb_dump(dp, dsa_slave_port_fdb_do_dump, &dump); *idx = dump.idx; + return err; } static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { - struct dsa_slave_priv *p = netdev_priv(dev); - - if (p->phy != NULL) - return phy_mii_ioctl(p->phy, ifr, cmd); + if (!dev->phydev) + return -ENODEV; - return -EOPNOTSUPP; + return phy_mii_ioctl(dev->phydev, ifr, cmd); } static int dsa_slave_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, struct switchdev_trans *trans) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; + struct dsa_port *dp = dsa_slave_to_port(dev); int ret; switch (attr->id) { @@ -317,8 +292,7 @@ static int dsa_slave_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj, struct switchdev_trans *trans) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; + struct dsa_port *dp = dsa_slave_to_port(dev); int err; /* For the prepare phase, ensure the full set of changes is feasable in @@ -330,6 +304,13 @@ static int dsa_slave_port_obj_add(struct net_device *dev, case SWITCHDEV_OBJ_ID_PORT_MDB: err = dsa_port_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj), trans); break; + case SWITCHDEV_OBJ_ID_HOST_MDB: + /* DSA can directly translate this to a normal MDB add, + * but on the CPU port. + */ + err = dsa_port_mdb_add(dp->cpu_dp, SWITCHDEV_OBJ_PORT_MDB(obj), + trans); + break; case SWITCHDEV_OBJ_ID_PORT_VLAN: err = dsa_port_vlan_add(dp, SWITCHDEV_OBJ_PORT_VLAN(obj), trans); @@ -345,14 +326,19 @@ static int dsa_slave_port_obj_add(struct net_device *dev, static int dsa_slave_port_obj_del(struct net_device *dev, const struct switchdev_obj *obj) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; + struct dsa_port *dp = dsa_slave_to_port(dev); int err; switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: err = dsa_port_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; + case SWITCHDEV_OBJ_ID_HOST_MDB: + /* DSA can directly translate this to a normal MDB add, + * but on the CPU port. + */ + err = dsa_port_mdb_del(dp->cpu_dp, SWITCHDEV_OBJ_PORT_MDB(obj)); + break; case SWITCHDEV_OBJ_ID_PORT_VLAN: err = dsa_port_vlan_del(dp, SWITCHDEV_OBJ_PORT_VLAN(obj)); break; @@ -367,13 +353,14 @@ static int dsa_slave_port_obj_del(struct net_device *dev, static int dsa_slave_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; + struct dsa_switch_tree *dst = ds->dst; switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: - attr->u.ppid.id_len = sizeof(ds->index); - memcpy(&attr->u.ppid.id, &ds->index, attr->u.ppid.id_len); + attr->u.ppid.id_len = sizeof(dst->index); + memcpy(&attr->u.ppid.id, &dst->index, attr->u.ppid.id_len); break; case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT: attr->u.brport_flags_support = 0; @@ -385,10 +372,12 @@ static int dsa_slave_port_attr_get(struct net_device *dev, return 0; } -static inline netdev_tx_t dsa_netpoll_send_skb(struct dsa_slave_priv *p, - struct sk_buff *skb) +static inline netdev_tx_t dsa_slave_netpoll_send_skb(struct net_device *dev, + struct sk_buff *skb) { #ifdef CONFIG_NET_POLL_CONTROLLER + struct dsa_slave_priv *p = netdev_priv(dev); + if (p->netpoll) netpoll_send_skb(p->netpoll, skb); #else @@ -422,43 +411,18 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) * tag to be successfully transmitted */ if (unlikely(netpoll_tx_running(dev))) - return dsa_netpoll_send_skb(p, nskb); + return dsa_slave_netpoll_send_skb(dev, nskb); /* Queue the SKB for transmission on the parent interface, but * do not modify its EtherType */ - nskb->dev = dsa_master_netdev(p); + nskb->dev = dsa_slave_to_master(dev); dev_queue_xmit(nskb); return NETDEV_TX_OK; } /* ethtool operations *******************************************************/ -static int -dsa_slave_get_link_ksettings(struct net_device *dev, - struct ethtool_link_ksettings *cmd) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - - if (!p->phy) - return -EOPNOTSUPP; - - phy_ethtool_ksettings_get(p->phy, cmd); - - return 0; -} - -static int -dsa_slave_set_link_ksettings(struct net_device *dev, - const struct ethtool_link_ksettings *cmd) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - - if (p->phy != NULL) - return phy_ethtool_ksettings_set(p->phy, cmd); - - return -EOPNOTSUPP; -} static void dsa_slave_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) @@ -470,11 +434,11 @@ static void dsa_slave_get_drvinfo(struct net_device *dev, static int dsa_slave_get_regs_len(struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (ds->ops->get_regs_len) - return ds->ops->get_regs_len(ds, p->dp->index); + return ds->ops->get_regs_len(ds, dp->index); return -EOPNOTSUPP; } @@ -482,39 +446,27 @@ static int dsa_slave_get_regs_len(struct net_device *dev) static void dsa_slave_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (ds->ops->get_regs) - ds->ops->get_regs(ds, p->dp->index, regs, _p); -} - -static int dsa_slave_nway_reset(struct net_device *dev) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - - if (p->phy != NULL) - return genphy_restart_aneg(p->phy); - - return -EOPNOTSUPP; + ds->ops->get_regs(ds, dp->index, regs, _p); } static u32 dsa_slave_get_link(struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + if (!dev->phydev) + return -ENODEV; - if (p->phy != NULL) { - genphy_update_link(p->phy); - return p->phy->link; - } + genphy_update_link(dev->phydev); - return -EOPNOTSUPP; + return dev->phydev->link; } static int dsa_slave_get_eeprom_len(struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (ds->cd && ds->cd->eeprom_len) return ds->cd->eeprom_len; @@ -528,8 +480,8 @@ static int dsa_slave_get_eeprom_len(struct net_device *dev) static int dsa_slave_get_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, u8 *data) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (ds->ops->get_eeprom) return ds->ops->get_eeprom(ds, eeprom, data); @@ -540,8 +492,8 @@ static int dsa_slave_get_eeprom(struct net_device *dev, static int dsa_slave_set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, u8 *data) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (ds->ops->set_eeprom) return ds->ops->set_eeprom(ds, eeprom, data); @@ -552,8 +504,8 @@ static int dsa_slave_set_eeprom(struct net_device *dev, static void dsa_slave_get_strings(struct net_device *dev, uint32_t stringset, uint8_t *data) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (stringset == ETH_SS_STATS) { int len = ETH_GSTRING_LEN; @@ -563,80 +515,7 @@ static void dsa_slave_get_strings(struct net_device *dev, strncpy(data + 2 * len, "rx_packets", len); strncpy(data + 3 * len, "rx_bytes", len); if (ds->ops->get_strings) - ds->ops->get_strings(ds, p->dp->index, data + 4 * len); - } -} - -static void dsa_cpu_port_get_ethtool_stats(struct net_device *dev, - struct ethtool_stats *stats, - uint64_t *data) -{ - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *cpu_dp = dsa_get_cpu_port(dst); - struct dsa_switch *ds = cpu_dp->ds; - s8 cpu_port = cpu_dp->index; - int count = 0; - - if (cpu_dp->ethtool_ops.get_sset_count) { - count = cpu_dp->ethtool_ops.get_sset_count(dev, ETH_SS_STATS); - cpu_dp->ethtool_ops.get_ethtool_stats(dev, stats, data); - } - - if (ds->ops->get_ethtool_stats) - ds->ops->get_ethtool_stats(ds, cpu_port, data + count); -} - -static int dsa_cpu_port_get_sset_count(struct net_device *dev, int sset) -{ - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *cpu_dp = dsa_get_cpu_port(dst); - struct dsa_switch *ds = cpu_dp->ds; - int count = 0; - - if (cpu_dp->ethtool_ops.get_sset_count) - count += cpu_dp->ethtool_ops.get_sset_count(dev, sset); - - if (sset == ETH_SS_STATS && ds->ops->get_sset_count) - count += ds->ops->get_sset_count(ds); - - return count; -} - -static void dsa_cpu_port_get_strings(struct net_device *dev, - uint32_t stringset, uint8_t *data) -{ - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *cpu_dp = dsa_get_cpu_port(dst); - struct dsa_switch *ds = cpu_dp->ds; - s8 cpu_port = cpu_dp->index; - int len = ETH_GSTRING_LEN; - int mcount = 0, count; - unsigned int i; - uint8_t pfx[4]; - uint8_t *ndata; - - snprintf(pfx, sizeof(pfx), "p%.2d", cpu_port); - /* We do not want to be NULL-terminated, since this is a prefix */ - pfx[sizeof(pfx) - 1] = '_'; - - if (cpu_dp->ethtool_ops.get_sset_count) { - mcount = cpu_dp->ethtool_ops.get_sset_count(dev, ETH_SS_STATS); - cpu_dp->ethtool_ops.get_strings(dev, stringset, data); - } - - if (stringset == ETH_SS_STATS && ds->ops->get_strings) { - ndata = data + mcount * len; - /* This function copies ETH_GSTRINGS_LEN bytes, we will mangle - * the output after to prepend our CPU port prefix we - * constructed earlier - */ - ds->ops->get_strings(ds, cpu_port, ndata); - count = ds->ops->get_sset_count(ds); - for (i = 0; i < count; i++) { - memmove(ndata + (i * len + sizeof(pfx)), - ndata + i * len, len - sizeof(pfx)); - memcpy(ndata + i * len, pfx, sizeof(pfx)); - } + ds->ops->get_strings(ds, dp->index, data + 4 * len); } } @@ -644,8 +523,9 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, uint64_t *data) { + struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_switch *ds = dp->ds; struct pcpu_sw_netstats *s; unsigned int start; int i; @@ -667,13 +547,13 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev, data[3] += rx_bytes; } if (ds->ops->get_ethtool_stats) - ds->ops->get_ethtool_stats(ds, p->dp->index, data + 4); + ds->ops->get_ethtool_stats(ds, dp->index, data + 4); } static int dsa_slave_get_sset_count(struct net_device *dev, int sset) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (sset == ETH_SS_STATS) { int count; @@ -690,77 +570,77 @@ static int dsa_slave_get_sset_count(struct net_device *dev, int sset) static void dsa_slave_get_wol(struct net_device *dev, struct ethtool_wolinfo *w) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (ds->ops->get_wol) - ds->ops->get_wol(ds, p->dp->index, w); + ds->ops->get_wol(ds, dp->index, w); } static int dsa_slave_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; int ret = -EOPNOTSUPP; if (ds->ops->set_wol) - ret = ds->ops->set_wol(ds, p->dp->index, w); + ret = ds->ops->set_wol(ds, dp->index, w); return ret; } static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; int ret; /* Port's PHY and MAC both need to be EEE capable */ - if (!p->phy) + if (!dev->phydev) return -ENODEV; if (!ds->ops->set_mac_eee) return -EOPNOTSUPP; - ret = ds->ops->set_mac_eee(ds, p->dp->index, e); + ret = ds->ops->set_mac_eee(ds, dp->index, e); if (ret) return ret; if (e->eee_enabled) { - ret = phy_init_eee(p->phy, 0); + ret = phy_init_eee(dev->phydev, 0); if (ret) return ret; } - return phy_ethtool_set_eee(p->phy, e); + return phy_ethtool_set_eee(dev->phydev, e); } static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; int ret; /* Port's PHY and MAC both need to be EEE capable */ - if (!p->phy) + if (!dev->phydev) return -ENODEV; if (!ds->ops->get_mac_eee) return -EOPNOTSUPP; - ret = ds->ops->get_mac_eee(ds, p->dp->index, e); + ret = ds->ops->get_mac_eee(ds, dp->index, e); if (ret) return ret; - return phy_ethtool_get_eee(p->phy, e); + return phy_ethtool_get_eee(dev->phydev, e); } #ifdef CONFIG_NET_POLL_CONTROLLER static int dsa_slave_netpoll_setup(struct net_device *dev, struct netpoll_info *ni) { + struct net_device *master = dsa_slave_to_master(dev); struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = dsa_master_netdev(p); struct netpoll *netpoll; int err = 0; @@ -800,18 +680,18 @@ static void dsa_slave_poll_controller(struct net_device *dev) static int dsa_slave_get_phys_port_name(struct net_device *dev, char *name, size_t len) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); - if (snprintf(name, len, "p%d", p->dp->index) >= len) + if (snprintf(name, len, "p%d", dp->index) >= len) return -EINVAL; return 0; } static struct dsa_mall_tc_entry * -dsa_slave_mall_tc_entry_find(struct dsa_slave_priv *p, - unsigned long cookie) +dsa_slave_mall_tc_entry_find(struct net_device *dev, unsigned long cookie) { + struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_mall_tc_entry *mall_tc_entry; list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list) @@ -825,14 +705,15 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress) { + struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_mall_tc_entry *mall_tc_entry; __be16 protocol = cls->common.protocol; - struct dsa_switch *ds = p->dp->ds; struct net *net = dev_net(dev); - struct dsa_slave_priv *to_p; + struct dsa_switch *ds = dp->ds; struct net_device *to_dev; const struct tc_action *a; + struct dsa_port *to_dp; int err = -EOPNOTSUPP; LIST_HEAD(actions); int ifindex; @@ -865,13 +746,12 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev, mall_tc_entry->type = DSA_PORT_MALL_MIRROR; mirror = &mall_tc_entry->mirror; - to_p = netdev_priv(to_dev); + to_dp = dsa_slave_to_port(to_dev); - mirror->to_local_port = to_p->dp->index; + mirror->to_local_port = to_dp->index; mirror->ingress = ingress; - err = ds->ops->port_mirror_add(ds, p->dp->index, mirror, - ingress); + err = ds->ops->port_mirror_add(ds, dp->index, mirror, ingress); if (err) { kfree(mall_tc_entry); return err; @@ -886,14 +766,14 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev, static void dsa_slave_del_cls_matchall(struct net_device *dev, struct tc_cls_matchall_offload *cls) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_mall_tc_entry *mall_tc_entry; - struct dsa_switch *ds = p->dp->ds; + struct dsa_switch *ds = dp->ds; if (!ds->ops->port_mirror_del) return; - mall_tc_entry = dsa_slave_mall_tc_entry_find(p, cls->cookie); + mall_tc_entry = dsa_slave_mall_tc_entry_find(dev, cls->cookie); if (!mall_tc_entry) return; @@ -901,8 +781,7 @@ static void dsa_slave_del_cls_matchall(struct net_device *dev, switch (mall_tc_entry->type) { case DSA_PORT_MALL_MIRROR: - ds->ops->port_mirror_del(ds, p->dp->index, - &mall_tc_entry->mirror); + ds->ops->port_mirror_del(ds, dp->index, &mall_tc_entry->mirror); break; default: WARN_ON(1); @@ -912,17 +791,9 @@ static void dsa_slave_del_cls_matchall(struct net_device *dev, } static int dsa_slave_setup_tc_cls_matchall(struct net_device *dev, - struct tc_cls_matchall_offload *cls) + struct tc_cls_matchall_offload *cls, + bool ingress) { - bool ingress; - - if (is_classid_clsact_ingress(cls->common.classid)) - ingress = true; - else if (is_classid_clsact_egress(cls->common.classid)) - ingress = false; - else - return -EOPNOTSUPP; - if (cls->common.chain_index) return -EOPNOTSUPP; @@ -937,12 +808,63 @@ static int dsa_slave_setup_tc_cls_matchall(struct net_device *dev, } } +static int dsa_slave_setup_tc_block_cb(enum tc_setup_type type, void *type_data, + void *cb_priv, bool ingress) +{ + struct net_device *dev = cb_priv; + + if (!tc_can_offload(dev)) + return -EOPNOTSUPP; + + switch (type) { + case TC_SETUP_CLSMATCHALL: + return dsa_slave_setup_tc_cls_matchall(dev, type_data, ingress); + default: + return -EOPNOTSUPP; + } +} + +static int dsa_slave_setup_tc_block_cb_ig(enum tc_setup_type type, + void *type_data, void *cb_priv) +{ + return dsa_slave_setup_tc_block_cb(type, type_data, cb_priv, true); +} + +static int dsa_slave_setup_tc_block_cb_eg(enum tc_setup_type type, + void *type_data, void *cb_priv) +{ + return dsa_slave_setup_tc_block_cb(type, type_data, cb_priv, false); +} + +static int dsa_slave_setup_tc_block(struct net_device *dev, + struct tc_block_offload *f) +{ + tc_setup_cb_t *cb; + + if (f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) + cb = dsa_slave_setup_tc_block_cb_ig; + else if (f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS) + cb = dsa_slave_setup_tc_block_cb_eg; + else + return -EOPNOTSUPP; + + switch (f->command) { + case TC_BLOCK_BIND: + return tcf_block_cb_register(f->block, cb, dev, dev); + case TC_BLOCK_UNBIND: + tcf_block_cb_unregister(f->block, cb, dev); + return 0; + default: + return -EOPNOTSUPP; + } +} + static int dsa_slave_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { switch (type) { - case TC_SETUP_CLSMATCHALL: - return dsa_slave_setup_tc_cls_matchall(dev, type_data); + case TC_SETUP_BLOCK: + return dsa_slave_setup_tc_block(dev, type_data); default: return -EOPNOTSUPP; } @@ -976,42 +898,35 @@ static void dsa_slave_get_stats64(struct net_device *dev, } } -void dsa_cpu_port_ethtool_init(struct ethtool_ops *ops) -{ - ops->get_sset_count = dsa_cpu_port_get_sset_count; - ops->get_ethtool_stats = dsa_cpu_port_get_ethtool_stats; - ops->get_strings = dsa_cpu_port_get_strings; -} - static int dsa_slave_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc, u32 *rule_locs) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (!ds->ops->get_rxnfc) return -EOPNOTSUPP; - return ds->ops->get_rxnfc(ds, p->dp->index, nfc, rule_locs); + return ds->ops->get_rxnfc(ds, dp->index, nfc, rule_locs); } static int dsa_slave_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (!ds->ops->set_rxnfc) return -EOPNOTSUPP; - return ds->ops->set_rxnfc(ds, p->dp->index, nfc); + return ds->ops->set_rxnfc(ds, dp->index, nfc); } static const struct ethtool_ops dsa_slave_ethtool_ops = { .get_drvinfo = dsa_slave_get_drvinfo, .get_regs_len = dsa_slave_get_regs_len, .get_regs = dsa_slave_get_regs, - .nway_reset = dsa_slave_nway_reset, + .nway_reset = phy_ethtool_nway_reset, .get_link = dsa_slave_get_link, .get_eeprom_len = dsa_slave_get_eeprom_len, .get_eeprom = dsa_slave_get_eeprom, @@ -1023,8 +938,8 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = { .get_wol = dsa_slave_get_wol, .set_eee = dsa_slave_set_eee, .get_eee = dsa_slave_get_eee, - .get_link_ksettings = dsa_slave_get_link_ksettings, - .set_link_ksettings = dsa_slave_set_link_ksettings, + .get_link_ksettings = phy_ethtool_get_link_ksettings, + .set_link_ksettings = phy_ethtool_set_link_ksettings, .get_rxnfc = dsa_slave_get_rxnfc, .set_rxnfc = dsa_slave_set_rxnfc, }; @@ -1064,78 +979,81 @@ static struct device_type dsa_type = { static void dsa_slave_adjust_link(struct net_device *dev) { + struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_switch *ds = dp->ds; unsigned int status_changed = 0; - if (p->old_link != p->phy->link) { + if (p->old_link != dev->phydev->link) { status_changed = 1; - p->old_link = p->phy->link; + p->old_link = dev->phydev->link; } - if (p->old_duplex != p->phy->duplex) { + if (p->old_duplex != dev->phydev->duplex) { status_changed = 1; - p->old_duplex = p->phy->duplex; + p->old_duplex = dev->phydev->duplex; } - if (p->old_pause != p->phy->pause) { + if (p->old_pause != dev->phydev->pause) { status_changed = 1; - p->old_pause = p->phy->pause; + p->old_pause = dev->phydev->pause; } if (ds->ops->adjust_link && status_changed) - ds->ops->adjust_link(ds, p->dp->index, p->phy); + ds->ops->adjust_link(ds, dp->index, dev->phydev); if (status_changed) - phy_print_status(p->phy); + phy_print_status(dev->phydev); } static int dsa_slave_fixed_link_update(struct net_device *dev, struct fixed_phy_status *status) { - struct dsa_slave_priv *p; struct dsa_switch *ds; + struct dsa_port *dp; if (dev) { - p = netdev_priv(dev); - ds = p->dp->ds; + dp = dsa_slave_to_port(dev); + ds = dp->ds; if (ds->ops->fixed_link_update) - ds->ops->fixed_link_update(ds, p->dp->index, status); + ds->ops->fixed_link_update(ds, dp->index, status); } return 0; } /* slave device setup *******************************************************/ -static int dsa_slave_phy_connect(struct dsa_slave_priv *p, - struct net_device *slave_dev, - int addr) +static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr) { - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(slave_dev); + struct dsa_slave_priv *p = netdev_priv(slave_dev); + struct dsa_switch *ds = dp->ds; - p->phy = mdiobus_get_phy(ds->slave_mii_bus, addr); - if (!p->phy) { + slave_dev->phydev = mdiobus_get_phy(ds->slave_mii_bus, addr); + if (!slave_dev->phydev) { netdev_err(slave_dev, "no phy at %d\n", addr); return -ENODEV; } /* Use already configured phy mode */ if (p->phy_interface == PHY_INTERFACE_MODE_NA) - p->phy_interface = p->phy->interface; - return phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link, - p->phy_interface); + p->phy_interface = slave_dev->phydev->interface; + + return phy_connect_direct(slave_dev, slave_dev->phydev, + dsa_slave_adjust_link, p->phy_interface); } -static int dsa_slave_phy_setup(struct dsa_slave_priv *p, - struct net_device *slave_dev) +static int dsa_slave_phy_setup(struct net_device *slave_dev) { - struct dsa_switch *ds = p->dp->ds; - struct device_node *phy_dn, *port_dn; + struct dsa_port *dp = dsa_slave_to_port(slave_dev); + struct dsa_slave_priv *p = netdev_priv(slave_dev); + struct device_node *port_dn = dp->dn; + struct dsa_switch *ds = dp->ds; + struct device_node *phy_dn; bool phy_is_fixed = false; u32 phy_flags = 0; int mode, ret; - port_dn = p->dp->dn; mode = of_get_phy_mode(port_dn); if (mode < 0) mode = PHY_INTERFACE_MODE_NA; @@ -1156,52 +1074,35 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, } if (ds->ops->get_phy_flags) - phy_flags = ds->ops->get_phy_flags(ds, p->dp->index); + phy_flags = ds->ops->get_phy_flags(ds, dp->index); if (phy_dn) { - int phy_id = of_mdio_parse_addr(&slave_dev->dev, phy_dn); - - /* If this PHY address is part of phys_mii_mask, which means - * that we need to divert reads and writes to/from it, then we - * want to bind this device using the slave MII bus created by - * DSA to make that happen. - */ - if (!phy_is_fixed && phy_id >= 0 && - (ds->phys_mii_mask & (1 << phy_id))) { - ret = dsa_slave_phy_connect(p, slave_dev, phy_id); - if (ret) { - netdev_err(slave_dev, "failed to connect to phy%d: %d\n", phy_id, ret); - of_node_put(phy_dn); - return ret; - } - } else { - p->phy = of_phy_connect(slave_dev, phy_dn, - dsa_slave_adjust_link, - phy_flags, - p->phy_interface); - } - + slave_dev->phydev = of_phy_connect(slave_dev, phy_dn, + dsa_slave_adjust_link, + phy_flags, + p->phy_interface); of_node_put(phy_dn); } - if (p->phy && phy_is_fixed) - fixed_phy_set_link_update(p->phy, dsa_slave_fixed_link_update); + if (slave_dev->phydev && phy_is_fixed) + fixed_phy_set_link_update(slave_dev->phydev, + dsa_slave_fixed_link_update); /* We could not connect to a designated PHY, so use the switch internal * MDIO bus instead */ - if (!p->phy) { - ret = dsa_slave_phy_connect(p, slave_dev, p->dp->index); + if (!slave_dev->phydev) { + ret = dsa_slave_phy_connect(slave_dev, dp->index); if (ret) { netdev_err(slave_dev, "failed to connect to port %d: %d\n", - p->dp->index, ret); + dp->index, ret); if (phy_is_fixed) of_phy_deregister_fixed_link(port_dn); return ret; } } - phy_attached_info(p->phy); + phy_attached_info(slave_dev->phydev); return 0; } @@ -1221,12 +1122,12 @@ int dsa_slave_suspend(struct net_device *slave_dev) netif_device_detach(slave_dev); - if (p->phy) { - phy_stop(p->phy); + if (slave_dev->phydev) { + phy_stop(slave_dev->phydev); p->old_pause = -1; p->old_link = -1; p->old_duplex = -1; - phy_suspend(p->phy); + phy_suspend(slave_dev->phydev); } return 0; @@ -1234,31 +1135,40 @@ int dsa_slave_suspend(struct net_device *slave_dev) int dsa_slave_resume(struct net_device *slave_dev) { - struct dsa_slave_priv *p = netdev_priv(slave_dev); - netif_device_attach(slave_dev); - if (p->phy) { - phy_resume(p->phy); - phy_start(p->phy); + if (slave_dev->phydev) { + phy_resume(slave_dev->phydev); + phy_start(slave_dev->phydev); } return 0; } -int dsa_slave_create(struct dsa_port *port, const char *name) +static void dsa_slave_notify(struct net_device *dev, unsigned long val) +{ + struct net_device *master = dsa_slave_to_master(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_notifier_register_info rinfo = { + .switch_number = dp->ds->index, + .port_number = dp->index, + .master = master, + .info.dev = dev, + }; + + call_dsa_notifiers(val, dev, &rinfo.info); +} + +int dsa_slave_create(struct dsa_port *port) { + const struct dsa_port *cpu_dp = port->cpu_dp; + struct net_device *master = cpu_dp->master; struct dsa_switch *ds = port->ds; - struct dsa_switch_tree *dst = ds->dst; - struct net_device *master; + const char *name = port->name; struct net_device *slave_dev; struct dsa_slave_priv *p; - struct dsa_port *cpu_dp; int ret; - cpu_dp = ds->dst->cpu_dp; - master = cpu_dp->netdev; - if (!ds->num_tx_queues) ds->num_tx_queues = 1; @@ -1294,22 +1204,24 @@ int dsa_slave_create(struct dsa_port *port, const char *name) } p->dp = port; INIT_LIST_HEAD(&p->mall_tc_list); - p->xmit = dst->tag_ops->xmit; + p->xmit = cpu_dp->tag_ops->xmit; p->old_pause = -1; p->old_link = -1; p->old_duplex = -1; - port->netdev = slave_dev; + port->slave = slave_dev; netif_carrier_off(slave_dev); - ret = dsa_slave_phy_setup(p, slave_dev); + ret = dsa_slave_phy_setup(slave_dev); if (ret) { netdev_err(master, "error %d setting up slave phy\n", ret); goto out_free; } + dsa_slave_notify(slave_dev, DSA_PORT_REGISTER); + ret = register_netdev(slave_dev); if (ret) { netdev_err(master, "error %d registering interface %s\n", @@ -1320,30 +1232,30 @@ int dsa_slave_create(struct dsa_port *port, const char *name) return 0; out_phy: - phy_disconnect(p->phy); - if (of_phy_is_fixed_link(p->dp->dn)) - of_phy_deregister_fixed_link(p->dp->dn); + phy_disconnect(slave_dev->phydev); + if (of_phy_is_fixed_link(port->dn)) + of_phy_deregister_fixed_link(port->dn); out_free: free_percpu(p->stats64); free_netdev(slave_dev); - port->netdev = NULL; + port->slave = NULL; return ret; } void dsa_slave_destroy(struct net_device *slave_dev) { + struct dsa_port *dp = dsa_slave_to_port(slave_dev); struct dsa_slave_priv *p = netdev_priv(slave_dev); - struct device_node *port_dn; - - port_dn = p->dp->dn; + struct device_node *port_dn = dp->dn; netif_carrier_off(slave_dev); - if (p->phy) { - phy_disconnect(p->phy); + if (slave_dev->phydev) { + phy_disconnect(slave_dev->phydev); if (of_phy_is_fixed_link(port_dn)) of_phy_deregister_fixed_link(port_dn); } + dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER); unregister_netdev(slave_dev); free_percpu(p->stats64); free_netdev(slave_dev); @@ -1357,8 +1269,7 @@ static bool dsa_slave_dev_check(struct net_device *dev) static int dsa_slave_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; + struct dsa_port *dp = dsa_slave_to_port(dev); int err = NOTIFY_DONE; if (netif_is_bridge_master(info->upper_dev)) { @@ -1379,7 +1290,7 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, { struct net_device *dev = netdev_notifier_info_to_dev(ptr); - if (dev->netdev_ops != &dsa_slave_netdev_ops) + if (!dsa_slave_dev_check(dev)) return NOTIFY_DONE; if (event == NETDEV_CHANGEUPPER) @@ -1401,14 +1312,14 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) container_of(work, struct dsa_switchdev_event_work, work); struct net_device *dev = switchdev_work->dev; struct switchdev_notifier_fdb_info *fdb_info; - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); int err; rtnl_lock(); switch (switchdev_work->event) { case SWITCHDEV_FDB_ADD_TO_DEVICE: fdb_info = &switchdev_work->fdb_info; - err = dsa_port_fdb_add(p->dp, fdb_info->addr, fdb_info->vid); + err = dsa_port_fdb_add(dp, fdb_info->addr, fdb_info->vid); if (err) { netdev_dbg(dev, "fdb add failed err=%d\n", err); break; @@ -1419,7 +1330,7 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) case SWITCHDEV_FDB_DEL_TO_DEVICE: fdb_info = &switchdev_work->fdb_info; - err = dsa_port_fdb_del(p->dp, fdb_info->addr, fdb_info->vid); + err = dsa_port_fdb_del(dp, fdb_info->addr, fdb_info->vid); if (err) { netdev_dbg(dev, "fdb del failed err=%d\n", err); dev_close(dev); diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 1e2929f4290a..29608d087a7c 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -121,7 +121,7 @@ static int dsa_switch_mdb_add(struct dsa_switch *ds, if (ds->index == info->sw_index) set_bit(info->port, group); for (port = 0; port < ds->num_ports; port++) - if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)) + if (dsa_is_dsa_port(ds, port)) set_bit(port, group); if (switchdev_trans_ph_prepare(trans)) { diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index dbb016434ace..e6e0b7b6025c 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -59,9 +59,11 @@ #define BRCM_EG_TC_MASK 0x7 #define BRCM_EG_PID_MASK 0x1f -static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev) +static struct sk_buff *brcm_tag_xmit_ll(struct sk_buff *skb, + struct net_device *dev, + unsigned int offset) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); u16 queue = skb_get_queue_mapping(skb); u8 *brcm_tag; @@ -70,10 +72,10 @@ static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev skb_push(skb, BRCM_TAG_LEN); - memmove(skb->data, skb->data + BRCM_TAG_LEN, 2 * ETH_ALEN); + if (offset) + memmove(skb->data, skb->data + BRCM_TAG_LEN, offset); - /* Build the tag after the MAC Source Address */ - brcm_tag = skb->data + 2 * ETH_ALEN; + brcm_tag = skb->data + offset; /* Set the ingress opcode, traffic class, tag enforcment is * deprecated @@ -82,27 +84,30 @@ static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev ((queue & BRCM_IG_TC_MASK) << BRCM_IG_TC_SHIFT); brcm_tag[1] = 0; brcm_tag[2] = 0; - if (p->dp->index == 8) + if (dp->index == 8) brcm_tag[2] = BRCM_IG_DSTMAP2_MASK; - brcm_tag[3] = (1 << p->dp->index) & BRCM_IG_DSTMAP1_MASK; + brcm_tag[3] = (1 << dp->index) & BRCM_IG_DSTMAP1_MASK; + + /* Now tell the master network device about the desired output queue + * as well + */ + skb_set_queue_mapping(skb, BRCM_TAG_SET_PORT_QUEUE(dp->index, queue)); return skb; } -static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt) +static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb, + struct net_device *dev, + struct packet_type *pt, + unsigned int offset) { - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *cpu_dp = dsa_get_cpu_port(dst); - struct dsa_switch *ds = cpu_dp->ds; int source_port; u8 *brcm_tag; if (unlikely(!pskb_may_pull(skb, BRCM_TAG_LEN))) return NULL; - /* skb->data points to the EtherType, the tag is right before it */ - brcm_tag = skb->data - 2; + brcm_tag = skb->data - offset; /* The opcode should never be different than 0b000 */ if (unlikely((brcm_tag[0] >> BRCM_OPCODE_SHIFT) & BRCM_OPCODE_MASK)) @@ -117,24 +122,67 @@ static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev, /* Locate which port this is coming from */ source_port = brcm_tag[3] & BRCM_EG_PID_MASK; - /* Validate port against switch setup, either the port is totally */ - if (source_port >= ds->num_ports || !ds->ports[source_port].netdev) + 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_TAG_LEN); + return skb; +} + +#ifdef CONFIG_NET_DSA_TAG_BRCM +static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + /* Build the tag after the MAC Source Address */ + return brcm_tag_xmit_ll(skb, dev, 2 * ETH_ALEN); +} + + +static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt) +{ + struct sk_buff *nskb; + + /* skb->data points to the EtherType, the tag is right before it */ + nskb = brcm_tag_rcv_ll(skb, dev, pt, 2); + if (!nskb) + return nskb; + /* Move the Ethernet DA and SA */ - memmove(skb->data - ETH_HLEN, - skb->data - ETH_HLEN - BRCM_TAG_LEN, + memmove(nskb->data - ETH_HLEN, + nskb->data - ETH_HLEN - BRCM_TAG_LEN, 2 * ETH_ALEN); - skb->dev = ds->ports[source_port].netdev; - - return skb; + return nskb; } const struct dsa_device_ops brcm_netdev_ops = { .xmit = brcm_tag_xmit, .rcv = brcm_tag_rcv, }; +#endif + +#ifdef CONFIG_NET_DSA_TAG_BRCM_PREPEND +static struct sk_buff *brcm_tag_xmit_prepend(struct sk_buff *skb, + struct net_device *dev) +{ + /* tag is prepended to the packet */ + return brcm_tag_xmit_ll(skb, dev, 0); +} + +static struct sk_buff *brcm_tag_rcv_prepend(struct sk_buff *skb, + struct net_device *dev, + struct packet_type *pt) +{ + /* tag is prepended to the packet */ + return brcm_tag_rcv_ll(skb, dev, pt, ETH_HLEN); +} + +const struct dsa_device_ops brcm_prepend_netdev_ops = { + .xmit = brcm_tag_xmit_prepend, + .rcv = brcm_tag_rcv_prepend, +}; +#endif diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index fbf9ca954773..cd13cfc542ce 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -18,7 +18,7 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); u8 *dsa_header; /* @@ -34,8 +34,8 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev) * Construct tagged FROM_CPU DSA tag from 802.1q tag. */ dsa_header = skb->data + 2 * ETH_ALEN; - dsa_header[0] = 0x60 | p->dp->ds->index; - dsa_header[1] = p->dp->index << 3; + dsa_header[0] = 0x60 | dp->ds->index; + dsa_header[1] = dp->index << 3; /* * Move CFI field from byte 2 to byte 1. @@ -55,8 +55,8 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev) * Construct untagged FROM_CPU DSA tag. */ dsa_header = skb->data + 2 * ETH_ALEN; - dsa_header[0] = 0x40 | p->dp->ds->index; - dsa_header[1] = p->dp->index << 3; + dsa_header[0] = 0x40 | dp->ds->index; + dsa_header[1] = dp->index << 3; dsa_header[2] = 0x00; dsa_header[3] = 0x00; } @@ -67,8 +67,6 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev) static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt) { - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_switch *ds; u8 *dsa_header; int source_device; int source_port; @@ -93,18 +91,8 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev, source_device = dsa_header[0] & 0x1f; source_port = (dsa_header[1] >> 3) & 0x1f; - /* - * Check that the source device exists and that the source - * port is a registered DSA port. - */ - if (source_device >= DSA_MAX_SWITCHES) - return NULL; - - ds = dst->ds[source_device]; - if (!ds) - return NULL; - - if (source_port >= ds->num_ports || !ds->ports[source_port].netdev) + skb->dev = dsa_master_find_slave(dev, source_device, source_port); + if (!skb->dev) return NULL; /* @@ -153,7 +141,7 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev, 2 * ETH_ALEN); } - skb->dev = ds->ports[source_port].netdev; + skb->offload_fwd_mark = 1; return skb; } diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c index 76367ba1b2e2..4083326b806e 100644 --- a/net/dsa/tag_edsa.c +++ b/net/dsa/tag_edsa.c @@ -19,7 +19,7 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); u8 *edsa_header; /* @@ -43,8 +43,8 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) edsa_header[1] = ETH_P_EDSA & 0xff; edsa_header[2] = 0x00; edsa_header[3] = 0x00; - edsa_header[4] = 0x60 | p->dp->ds->index; - edsa_header[5] = p->dp->index << 3; + edsa_header[4] = 0x60 | dp->ds->index; + edsa_header[5] = dp->index << 3; /* * Move CFI field from byte 6 to byte 5. @@ -68,8 +68,8 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) edsa_header[1] = ETH_P_EDSA & 0xff; edsa_header[2] = 0x00; edsa_header[3] = 0x00; - edsa_header[4] = 0x40 | p->dp->ds->index; - edsa_header[5] = p->dp->index << 3; + edsa_header[4] = 0x40 | dp->ds->index; + edsa_header[5] = dp->index << 3; edsa_header[6] = 0x00; edsa_header[7] = 0x00; } @@ -80,8 +80,6 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt) { - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_switch *ds; u8 *edsa_header; int source_device; int source_port; @@ -106,18 +104,8 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, source_device = edsa_header[0] & 0x1f; source_port = (edsa_header[1] >> 3) & 0x1f; - /* - * Check that the source device exists and that the source - * port is a registered DSA port. - */ - if (source_device >= DSA_MAX_SWITCHES) - return NULL; - - ds = dst->ds[source_device]; - if (!ds) - return NULL; - - if (source_port >= ds->num_ports || !ds->ports[source_port].netdev) + skb->dev = dsa_master_find_slave(dev, source_device, source_port); + if (!skb->dev) return NULL; /* @@ -172,7 +160,7 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, 2 * ETH_ALEN); } - skb->dev = ds->ports[source_port].netdev; + skb->offload_fwd_mark = 1; return skb; } diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 010ca0a336c4..0f62effad88f 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -34,7 +34,7 @@ static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); struct sk_buff *nskb; int padlen; u8 *tag; @@ -72,7 +72,7 @@ static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev) tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN); tag[0] = 0; - tag[1] = 1 << p->dp->index; /* destination port */ + tag[1] = 1 << dp->index; /* destination port */ return nskb; } @@ -80,22 +80,19 @@ static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev) static struct sk_buff *ksz_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt) { - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *cpu_dp = dsa_get_cpu_port(dst); - struct dsa_switch *ds = cpu_dp->ds; u8 *tag; int source_port; tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; source_port = tag[0] & 7; - if (source_port >= ds->num_ports || !ds->ports[source_port].netdev) + + skb->dev = dsa_master_find_slave(dev, 0, source_port); + if (!skb->dev) return NULL; pskb_trim_rcsum(skb, skb->len - KSZ_EGRESS_TAG_LEN); - skb->dev = ds->ports[source_port].netdev; - return skb; } diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c index 0b9826105e42..548c00254c07 100644 --- a/net/dsa/tag_lan9303.c +++ b/net/dsa/tag_lan9303.c @@ -11,6 +11,7 @@ * GNU General Public License for more details. * */ +#include <linux/dsa/lan9303.h> #include <linux/etherdevice.h> #include <linux/list.h> #include <linux/slab.h> @@ -39,10 +40,30 @@ */ #define LAN9303_TAG_LEN 4 +# define LAN9303_TAG_TX_USE_ALR BIT(3) +# define LAN9303_TAG_TX_STP_OVERRIDE BIT(4) +# define LAN9303_TAG_RX_IGMP BIT(3) +# define LAN9303_TAG_RX_STP BIT(4) +# define LAN9303_TAG_RX_TRAPPED_TO_CPU (LAN9303_TAG_RX_IGMP | \ + LAN9303_TAG_RX_STP) + +/* Decide whether to transmit using ALR lookup, or transmit directly to + * port using tag. ALR learning is performed only when using ALR lookup. + * If the two external ports are bridged and the frame is unicast, + * then use ALR lookup to allow ALR learning on CPU port. + * Otherwise transmit directly to port with STP state override. + * See also: lan9303_separate_ports() and lan9303.pdf 6.4.10.1 + */ +static int lan9303_xmit_use_arl(struct dsa_port *dp, u8 *dest_addr) +{ + struct lan9303 *chip = dp->ds->priv; + + return chip->is_bridged && !is_multicast_ether_addr(dest_addr); +} static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); u16 *lan9303_tag; /* insert a special VLAN tag between the MAC addresses @@ -62,26 +83,21 @@ static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev) lan9303_tag = (u16 *)(skb->data + 2 * ETH_ALEN); lan9303_tag[0] = htons(ETH_P_8021Q); - lan9303_tag[1] = htons(p->dp->index | BIT(4)); + lan9303_tag[1] = lan9303_xmit_use_arl(dp, skb->data) ? + LAN9303_TAG_TX_USE_ALR : + dp->index | LAN9303_TAG_TX_STP_OVERRIDE; + lan9303_tag[1] = htons(lan9303_tag[1]); return skb; } static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt) + struct packet_type *pt) { u16 *lan9303_tag; - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_switch *ds; + u16 lan9303_tag1; unsigned int source_port; - ds = dst->ds[0]; - - if (unlikely(!ds)) { - dev_warn_ratelimited(&dev->dev, "Dropping packet, due to missing DSA switch device\n"); - return NULL; - } - if (unlikely(!pskb_may_pull(skb, LAN9303_TAG_LEN))) { dev_warn_ratelimited(&dev->dev, "Dropping packet, cannot pull\n"); @@ -101,27 +117,22 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev, return NULL; } - source_port = ntohs(lan9303_tag[1]) & 0x3; + lan9303_tag1 = ntohs(lan9303_tag[1]); + source_port = lan9303_tag1 & 0x3; - if (source_port >= ds->num_ports) { + skb->dev = dsa_master_find_slave(dev, 0, source_port); + if (!skb->dev) { dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid source port\n"); return NULL; } - if (!ds->ports[source_port].netdev) { - dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid netdev or device\n"); - return NULL; - } - /* remove the special VLAN tag between the MAC addresses * and the current ethertype field. */ skb_pull_rcsum(skb, 2 + 2); memmove(skb->data - ETH_HLEN, skb->data - (ETH_HLEN + LAN9303_TAG_LEN), 2 * ETH_ALEN); - - /* forward the packet to the dedicated interface */ - skb->dev = ds->ports[source_port].netdev; + skb->offload_fwd_mark = !(lan9303_tag1 & LAN9303_TAG_RX_TRAPPED_TO_CPU); return skb; } diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index ec8ee5f43255..8475434af7d5 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -23,7 +23,7 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); u8 *mtk_tag; if (skb_cow_head(skb, MTK_HDR_LEN) < 0) @@ -36,7 +36,7 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, /* Build the tag after the MAC Source Address */ mtk_tag = skb->data + 2 * ETH_ALEN; mtk_tag[0] = 0; - mtk_tag[1] = (1 << p->dp->index) & MTK_HDR_XMIT_DP_BIT_MASK; + mtk_tag[1] = (1 << dp->index) & MTK_HDR_XMIT_DP_BIT_MASK; mtk_tag[2] = 0; mtk_tag[3] = 0; @@ -46,8 +46,6 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt) { - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_switch *ds; int port; __be16 *phdr, hdr; @@ -68,20 +66,12 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, skb->data - ETH_HLEN - MTK_HDR_LEN, 2 * ETH_ALEN); - /* This protocol doesn't support cascading multiple - * switches so it's safe to assume the switch is first - * in the tree. - */ - ds = dst->ds[0]; - if (!ds) - return NULL; - /* Get source port information */ port = (hdr & MTK_HDR_RECV_SOURCE_PORT_MASK); - if (!ds->ports[port].netdev) - return NULL; - skb->dev = ds->ports[port].netdev; + skb->dev = dsa_master_find_slave(dev, 0, port); + if (!skb->dev) + return NULL; return skb; } diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index 1d4c70711c0f..613f4ee97771 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -38,7 +38,7 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); u16 *phdr, hdr; dev->stats.tx_packets++; @@ -54,8 +54,7 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) /* Set the version field, and set destination port information */ hdr = QCA_HDR_VERSION << QCA_HDR_XMIT_VERSION_S | - QCA_HDR_XMIT_FROM_CPU | - BIT(p->dp->index); + QCA_HDR_XMIT_FROM_CPU | BIT(dp->index); *phdr = htons(hdr); @@ -65,9 +64,6 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt) { - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *cpu_dp = dsa_get_cpu_port(dst); - struct dsa_switch *ds; u8 ver; int port; __be16 *phdr, hdr; @@ -92,20 +88,12 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - QCA_HDR_LEN, ETH_HLEN - QCA_HDR_LEN); - /* This protocol doesn't support cascading multiple switches so it's - * safe to assume the switch is first in the tree - */ - ds = cpu_dp->ds; - if (!ds) - return NULL; - /* Get source port information */ port = (hdr & QCA_HDR_RECV_SOURCE_PORT_MASK); - if (!ds->ports[port].netdev) - return NULL; - /* Update skb & forward the frame accordingly */ - skb->dev = ds->ports[port].netdev; + skb->dev = dsa_master_find_slave(dev, 0, port); + if (!skb->dev) + return NULL; return skb; } diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index d2fd4923aa3e..7d20e1f3de28 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -16,7 +16,7 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); struct sk_buff *nskb; int padlen; u8 *trailer; @@ -48,7 +48,7 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) trailer = skb_put(nskb, 4); trailer[0] = 0x80; - trailer[1] = 1 << p->dp->index; + trailer[1] = 1 << dp->index; trailer[2] = 0x10; trailer[3] = 0x00; @@ -58,9 +58,6 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt) { - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *cpu_dp = dsa_get_cpu_port(dst); - struct dsa_switch *ds = cpu_dp->ds; u8 *trailer; int source_port; @@ -73,13 +70,13 @@ static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev, return NULL; source_port = trailer[1] & 7; - if (source_port >= ds->num_ports || !ds->ports[source_port].netdev) + + skb->dev = dsa_master_find_slave(dev, 0, source_port); + if (!skb->dev) return NULL; pskb_trim_rcsum(skb, skb->len - 4); - skb->dev = ds->ports[source_port].netdev; - return skb; } diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 172d8309f89e..b8cd43c9ed5b 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -328,12 +328,12 @@ out: /* Announce (supervision frame) timer function */ -static void hsr_announce(unsigned long data) +static void hsr_announce(struct timer_list *t) { struct hsr_priv *hsr; struct hsr_port *master; - hsr = (struct hsr_priv *) data; + hsr = from_timer(hsr, t, announce_timer); rcu_read_lock(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); @@ -463,9 +463,8 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], hsr->sequence_nr = HSR_SEQNR_START; hsr->sup_sequence_nr = HSR_SUP_SEQNR_START; - setup_timer(&hsr->announce_timer, hsr_announce, (unsigned long)hsr); - - setup_timer(&hsr->prune_timer, hsr_prune_nodes, (unsigned long)hsr); + timer_setup(&hsr->announce_timer, hsr_announce, 0); + timer_setup(&hsr->prune_timer, hsr_prune_nodes, 0); ether_addr_copy(hsr->sup_multicast_addr, def_multicast_addr); hsr->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec; diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 284a9b820df8..286ceb41ac0c 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -365,16 +365,14 @@ static struct hsr_port *get_late_port(struct hsr_priv *hsr, /* Remove stale sequence_nr records. Called by timer every * HSR_LIFE_CHECK_INTERVAL (two seconds or so). */ -void hsr_prune_nodes(unsigned long data) +void hsr_prune_nodes(struct timer_list *t) { - struct hsr_priv *hsr; + struct hsr_priv *hsr = from_timer(hsr, t, prune_timer); struct hsr_node *node; struct hsr_port *port; unsigned long timestamp; unsigned long time_a, time_b; - hsr = (struct hsr_priv *) data; - rcu_read_lock(); list_for_each_entry_rcu(node, &hsr->node_db, mac_list) { /* Shorthand */ diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h index 4e04f0e868e9..370b45998121 100644 --- a/net/hsr/hsr_framereg.h +++ b/net/hsr/hsr_framereg.h @@ -33,7 +33,7 @@ void hsr_register_frame_in(struct hsr_node *node, struct hsr_port *port, int hsr_register_frame_out(struct hsr_port *port, struct hsr_node *node, u16 sequence_nr); -void hsr_prune_nodes(unsigned long data); +void hsr_prune_nodes(struct timer_list *t); int hsr_create_self_node(struct list_head *self_node_db, unsigned char addr_a[ETH_ALEN], diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index f85b08baff16..85bf86ad6b18 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -80,12 +80,13 @@ static void lowpan_frag_init(struct inet_frag_queue *q, const void *a) fq->daddr = *arg->dst; } -static void lowpan_frag_expire(unsigned long data) +static void lowpan_frag_expire(struct timer_list *t) { + struct inet_frag_queue *frag = from_timer(frag, t, timer); struct frag_queue *fq; struct net *net; - fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q); + fq = container_of(frag, struct frag_queue, q); net = container_of(fq->q.net, struct net, ieee802154_lowpan.frags); spin_lock(&fq->q.lock); diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c index 6bde9e5a5503..96636e3b7aa9 100644 --- a/net/ieee802154/netlink.c +++ b/net/ieee802154/netlink.c @@ -89,7 +89,7 @@ int ieee802154_nl_reply(struct sk_buff *msg, struct genl_info *info) return genlmsg_reply(msg, info); } -static const struct genl_ops ieee8021154_ops[] = { +static const struct genl_ops ieee802154_ops[] = { /* see nl-phy.c */ IEEE802154_DUMP(IEEE802154_LIST_PHY, ieee802154_list_phy, ieee802154_dump_phy), @@ -137,8 +137,8 @@ struct genl_family nl802154_family __ro_after_init = { .version = 1, .maxattr = IEEE802154_ATTR_MAX, .module = THIS_MODULE, - .ops = ieee8021154_ops, - .n_ops = ARRAY_SIZE(ieee8021154_ops), + .ops = ieee802154_ops, + .n_ops = ARRAY_SIZE(ieee802154_ops), .mcgrps = ieee802154_mcgrps, .n_mcgrps = ARRAY_SIZE(ieee802154_mcgrps), }; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index e31108e5ef79..ce4aa827be05 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -195,7 +195,7 @@ int inet_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; unsigned char old_state; - int err; + int err, tcp_fastopen; lock_sock(sk); @@ -217,11 +217,12 @@ int inet_listen(struct socket *sock, int backlog) * because the socket was in TCP_LISTEN state previously but * was shutdown() rather than close(). */ - if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) && - (sysctl_tcp_fastopen & TFO_SERVER_ENABLE) && + tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen; + if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) && + (tcp_fastopen & TFO_SERVER_ENABLE) && !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) { fastopen_queue_tune(sk, backlog); - tcp_fastopen_init_key_once(true); + tcp_fastopen_init_key_once(sock_net(sk)); } err = inet_csk_listen_start(sk, backlog); @@ -826,6 +827,7 @@ int inet_shutdown(struct socket *sock, int how) err = -ENOTCONN; /* Hack to wake up other listeners, who can poll for POLLHUP, even on eg. unconnected UDP sockets -- RR */ + /* fall through */ default: sk->sk_shutdown |= how; if (sk->sk_prot->shutdown) @@ -839,7 +841,7 @@ int inet_shutdown(struct socket *sock, int how) case TCP_LISTEN: if (!(how & RCV_SHUTDOWN)) break; - /* Fall through */ + /* fall through */ case TCP_SYN_SENT: err = sk->sk_prot->disconnect(sk, O_NONBLOCK); sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 37db44f60718..4dd95cdd8070 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -240,7 +240,7 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) if (err == -EINPROGRESS) goto out; - if (err == -EBUSY) + if (err == -ENOSPC) err = NET_XMIT_DROP; goto out_free; } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 7c45b8896709..a8d7c5a9fb05 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1180,6 +1180,7 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) case SIOCSARP: if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; + /* fall through */ case SIOCGARP: err = copy_from_user(&r, arg, sizeof(struct arpreq)); if (err) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index d7adc0616599..a4573bccd6da 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -137,22 +137,12 @@ static void inet_hash_remove(struct in_ifaddr *ifa) */ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) { - u32 hash = inet_addr_hash(net, addr); struct net_device *result = NULL; struct in_ifaddr *ifa; rcu_read_lock(); - hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash) { - if (ifa->ifa_local == addr) { - struct net_device *dev = ifa->ifa_dev->dev; - - if (!net_eq(dev_net(dev), net)) - continue; - result = dev; - break; - } - } - if (!result) { + ifa = inet_lookup_ifaddr_rcu(net, addr); + if (!ifa) { struct flowi4 fl4 = { .daddr = addr }; struct fib_result res = { 0 }; struct fib_table *local; @@ -165,6 +155,8 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) !fib_table_lookup(local, &fl4, &res, FIB_LOOKUP_NOREF) && res.type == RTN_LOCAL) result = FIB_RES_DEV(res); + } else { + result = ifa->ifa_dev->dev; } if (result && devref) dev_hold(result); @@ -173,6 +165,20 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) } EXPORT_SYMBOL(__ip_dev_find); +/* called under RCU lock */ +struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr) +{ + u32 hash = inet_addr_hash(net, addr); + struct in_ifaddr *ifa; + + hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash) + if (ifa->ifa_local == addr && + net_eq(dev_net(ifa->ifa_dev->dev), net)) + return ifa; + + return NULL; +} + static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32); static BLOCKING_NOTIFIER_HEAD(inetaddr_chain); @@ -438,7 +444,7 @@ static void check_lifetime(struct work_struct *work); static DECLARE_DELAYED_WORK(check_lifetime_work, check_lifetime); static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, - u32 portid) + u32 portid, struct netlink_ext_ack *extack) { struct in_device *in_dev = ifa->ifa_dev; struct in_ifaddr *ifa1, **ifap, **last_primary; @@ -483,6 +489,7 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, */ ivi.ivi_addr = ifa->ifa_address; ivi.ivi_dev = ifa->ifa_dev; + ivi.extack = extack; ret = blocking_notifier_call_chain(&inetaddr_validator_chain, NETDEV_UP, &ivi); ret = notifier_to_errno(ret); @@ -515,7 +522,7 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, static int inet_insert_ifa(struct in_ifaddr *ifa) { - return __inet_insert_ifa(ifa, NULL, 0); + return __inet_insert_ifa(ifa, NULL, 0, NULL); } static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa) @@ -896,7 +903,8 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, return ret; } } - return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid); + return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid, + extack); } else { inet_free_ifa(ifa); @@ -1516,6 +1524,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, if (inetdev_valid_mtu(dev->mtu)) break; /* disable IP when MTU is not enough */ + /* fall through */ case NETDEV_UNREGISTER: inetdev_destroy(in_dev); break; @@ -1751,7 +1760,7 @@ static int inet_validate_link_af(const struct net_device *dev, struct nlattr *a, *tb[IFLA_INET_MAX+1]; int err, rem; - if (dev && !__in_dev_get_rtnl(dev)) + if (dev && !__in_dev_get_rcu(dev)) return -EAFNOSUPPORT; err = nla_parse_nested(tb, IFLA_INET_MAX, nla, inet_af_policy, NULL); @@ -1775,7 +1784,7 @@ static int inet_validate_link_af(const struct net_device *dev, static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla) { - struct in_device *in_dev = __in_dev_get_rtnl(dev); + struct in_device *in_dev = __in_dev_get_rcu(dev); struct nlattr *a, *tb[IFLA_INET_MAX+1]; int rem; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index b00e4a43b4dc..d57aa64fa7c7 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -432,7 +432,7 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * case -EINPROGRESS: goto error; - case -EBUSY: + case -ENOSPC: err = NET_XMIT_DROP; break; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 37819ab4cc74..f52d27a422c3 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -73,6 +73,11 @@ fail: fib_free_table(main_table); return -ENOMEM; } + +static bool fib4_has_custom_rules(struct net *net) +{ + return false; +} #else struct fib_table *fib_new_table(struct net *net, u32 id) @@ -128,6 +133,11 @@ struct fib_table *fib_get_table(struct net *net, u32 id) } return NULL; } + +static bool fib4_has_custom_rules(struct net *net) +{ + return net->ipv4.fib_has_custom_rules; +} #endif /* CONFIG_IP_MULTIPLE_TABLES */ static void fib_replace_table(struct net *net, struct fib_table *old, @@ -345,9 +355,6 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, if (res.type != RTN_UNICAST && (res.type != RTN_LOCAL || !IN_DEV_ACCEPT_LOCAL(idev))) goto e_inval; - if (!rpf && !fib_num_tclassid_users(net) && - (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) - goto last_resort; fib_combine_itag(itag, &res); dev_match = false; @@ -402,13 +409,28 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, struct in_device *idev, u32 *itag) { int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev); + struct net *net = dev_net(dev); - if (!r && !fib_num_tclassid_users(dev_net(dev)) && - IN_DEV_ACCEPT_LOCAL(idev) && + if (!r && !fib_num_tclassid_users(net) && (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) { + if (IN_DEV_ACCEPT_LOCAL(idev)) + goto ok; + /* with custom local routes in place, checking local addresses + * only will be too optimistic, with custom rules, checking + * local addresses only can be too strict, e.g. due to vrf + */ + if (net->ipv4.fib_has_custom_local_routes || + fib4_has_custom_rules(net)) + goto full_check; + if (inet_lookup_ifaddr_rcu(net, src)) + return -EINVAL; + +ok: *itag = 0; return 0; } + +full_check: return __fib_validate_source(skb, src, dst, tos, oif, dev, r, idev, itag); } @@ -759,6 +781,8 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, } err = fib_table_insert(net, tb, &cfg, extack); + if (!err && cfg.fc_type == RTN_LOCAL) + net->ipv4.fib_has_custom_local_routes = true; errout: return err; } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 01ed22139ac2..f04d944f8abe 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -601,17 +601,9 @@ static void fib_rebalance(struct fib_info *fi) atomic_set(&nexthop_nh->nh_upper_bound, upper_bound); } endfor_nexthops(fi); } - -static inline void fib_add_weight(struct fib_info *fi, - const struct fib_nh *nh) -{ - fi->fib_weight += nh->nh_weight; -} - #else /* CONFIG_IP_ROUTE_MULTIPATH */ #define fib_rebalance(fi) do { } while (0) -#define fib_add_weight(fi, nh) do { } while (0) #endif /* CONFIG_IP_ROUTE_MULTIPATH */ @@ -718,7 +710,7 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi) bool ecn_ca = false; nla_strlcpy(tmp, nla, sizeof(tmp)); - val = tcp_ca_get_key_by_name(tmp, &ecn_ca); + val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca); } else { val = nla_get_u32(nla); } @@ -774,8 +766,8 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi) * | * |-> {local prefix} (terminal node) */ -static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, - struct fib_nh *nh, struct netlink_ext_ack *extack) +static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh, + struct netlink_ext_ack *extack) { int err = 0; struct net *net; @@ -1038,7 +1030,7 @@ fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg) char tmp[TCP_CA_NAME_MAX]; nla_strlcpy(tmp, nla, sizeof(tmp)); - val = tcp_ca_get_key_by_name(tmp, &ecn_ca); + val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca); if (val == TCP_CA_UNSPEC) return -EINVAL; } else { @@ -1258,7 +1250,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg, int linkdown = 0; change_nexthops(fi) { - err = fib_check_nh(cfg, fi, nexthop_nh, extack); + err = fib_check_nh(cfg, nexthop_nh, extack); if (err != 0) goto failure; if (nexthop_nh->nh_flags & RTNH_F_LINKDOWN) @@ -1275,7 +1267,6 @@ struct fib_info *fib_create_info(struct fib_config *cfg, change_nexthops(fi) { fib_info_update_nh_saddr(net, nexthop_nh); - fib_add_weight(fi, nexthop_nh); } endfor_nexthops(fi) fib_rebalance(fi); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index c636650a6a70..5ddc4aefff12 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -87,32 +87,32 @@ static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net, enum fib_event_type event_type, u32 dst, - int dst_len, struct fib_info *fi, - u8 tos, u8 type, u32 tb_id) + int dst_len, struct fib_alias *fa) { struct fib_entry_notifier_info info = { .dst = dst, .dst_len = dst_len, - .fi = fi, - .tos = tos, - .type = type, - .tb_id = tb_id, + .fi = fa->fa_info, + .tos = fa->fa_tos, + .type = fa->fa_type, + .tb_id = fa->tb_id, }; return call_fib4_notifier(nb, net, event_type, &info.info); } static int call_fib_entry_notifiers(struct net *net, enum fib_event_type event_type, u32 dst, - int dst_len, struct fib_info *fi, - u8 tos, u8 type, u32 tb_id) + int dst_len, struct fib_alias *fa, + struct netlink_ext_ack *extack) { struct fib_entry_notifier_info info = { + .info.extack = extack, .dst = dst, .dst_len = dst_len, - .fi = fi, - .tos = tos, - .type = type, - .tb_id = tb_id, + .fi = fa->fa_info, + .tos = fa->fa_tos, + .type = fa->fa_type, + .tb_id = fa->tb_id, }; return call_fib4_notifiers(net, event_type, &info.info); } @@ -1216,9 +1216,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, new_fa->fa_default = -1; call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, - key, plen, fi, - new_fa->fa_tos, cfg->fc_type, - tb->tb_id); + key, plen, new_fa, extack); rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, nlflags); @@ -1273,8 +1271,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, tb->tb_num_default++; rt_cache_flush(cfg->fc_nlinfo.nl_net); - call_fib_entry_notifiers(net, event, key, plen, fi, tos, cfg->fc_type, - tb->tb_id); + call_fib_entry_notifiers(net, event, key, plen, new_fa, extack); rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, new_fa->tb_id, &cfg->fc_nlinfo, nlflags); succeeded: @@ -1574,8 +1571,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb, return -ESRCH; call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, key, plen, - fa_to_delete->fa_info, tos, - fa_to_delete->fa_type, tb->tb_id); + fa_to_delete, extack); rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id, &cfg->fc_nlinfo, 0); @@ -1892,9 +1888,8 @@ int fib_table_flush(struct net *net, struct fib_table *tb) call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, n->key, - KEYLENGTH - fa->fa_slen, - fi, fa->fa_tos, fa->fa_type, - tb->tb_id); + KEYLENGTH - fa->fa_slen, fa, + NULL); hlist_del_rcu(&fa->fa_list); fib_release_info(fa->fa_info); alias_free_mem_rcu(fa); @@ -1932,8 +1927,7 @@ static void fib_leaf_notify(struct net *net, struct key_vector *l, continue; call_fib_entry_notifier(nb, net, FIB_EVENT_ENTRY_ADD, l->key, - KEYLENGTH - fa->fa_slen, fi, fa->fa_tos, - fa->fa_type, fa->tb_id); + KEYLENGTH - fa->fa_slen, fa); } } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 681e33998e03..1617604c9284 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -782,7 +782,7 @@ static bool icmp_tag_validation(int proto) } /* - * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, ICMP_QUENCH, and + * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEEDED, ICMP_QUENCH, and * ICMP_PARAMETERPROB. */ @@ -810,7 +810,8 @@ static bool icmp_unreach(struct sk_buff *skb) if (iph->ihl < 5) /* Mangled header, drop. */ goto out_err; - if (icmph->type == ICMP_DEST_UNREACH) { + switch (icmph->type) { + case ICMP_DEST_UNREACH: switch (icmph->code & 15) { case ICMP_NET_UNREACH: case ICMP_HOST_UNREACH: @@ -846,8 +847,16 @@ static bool icmp_unreach(struct sk_buff *skb) } if (icmph->code > NR_ICMP_UNREACH) goto out; - } else if (icmph->type == ICMP_PARAMETERPROB) + break; + case ICMP_PARAMETERPROB: info = ntohl(icmph->un.gateway) >> 24; + break; + case ICMP_TIME_EXCEEDED: + __ICMP_INC_STATS(net, ICMP_MIB_INTIMEEXCDS); + if (icmph->code == ICMP_EXC_FRAGTIME) + goto out; + break; + } /* * Throw it at our lower layers @@ -959,8 +968,9 @@ static bool icmp_timestamp(struct sk_buff *skb) */ icmp_param.data.times[1] = inet_current_timestamp(); icmp_param.data.times[2] = icmp_param.data.times[1]; - if (skb_copy_bits(skb, 0, &icmp_param.data.times[0], 4)) - BUG(); + + BUG_ON(skb_copy_bits(skb, 0, &icmp_param.data.times[0], 4)); + icmp_param.data.icmph = *icmp_hdr(skb); icmp_param.data.icmph.type = ICMP_TIMESTAMPREPLY; icmp_param.data.icmph.code = 0; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index b47a59cb3573..4ca46dc08e63 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -39,11 +39,11 @@ EXPORT_SYMBOL(inet_csk_timer_bug_msg); * IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY, * and 0.0.0.0 equals to 0.0.0.0 only */ -static int ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6, - const struct in6_addr *sk2_rcv_saddr6, - __be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr, - bool sk1_ipv6only, bool sk2_ipv6only, - bool match_wildcard) +static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6, + const struct in6_addr *sk2_rcv_saddr6, + __be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr, + bool sk1_ipv6only, bool sk2_ipv6only, + bool match_wildcard) { int addr_type = ipv6_addr_type(sk1_rcv_saddr6); int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED; @@ -52,29 +52,29 @@ static int ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6, if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) { if (!sk2_ipv6only) { if (sk1_rcv_saddr == sk2_rcv_saddr) - return 1; + return true; if (!sk1_rcv_saddr || !sk2_rcv_saddr) return match_wildcard; } - return 0; + return false; } if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY) - return 1; + return true; if (addr_type2 == IPV6_ADDR_ANY && match_wildcard && !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED)) - return 1; + return true; if (addr_type == IPV6_ADDR_ANY && match_wildcard && !(sk1_ipv6only && addr_type2 == IPV6_ADDR_MAPPED)) - return 1; + return true; if (sk2_rcv_saddr6 && ipv6_addr_equal(sk1_rcv_saddr6, sk2_rcv_saddr6)) - return 1; + return true; - return 0; + return false; } #endif @@ -82,20 +82,20 @@ static int ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6, * match_wildcard == false: addresses must be exactly the same, i.e. * 0.0.0.0 only equals to 0.0.0.0 */ -static int ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr, - bool sk2_ipv6only, bool match_wildcard) +static bool ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr, + bool sk2_ipv6only, bool match_wildcard) { if (!sk2_ipv6only) { if (sk1_rcv_saddr == sk2_rcv_saddr) - return 1; + return true; if (!sk1_rcv_saddr || !sk2_rcv_saddr) return match_wildcard; } - return 0; + return false; } -int inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, - bool match_wildcard) +bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, + bool match_wildcard) { #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) @@ -495,17 +495,15 @@ EXPORT_SYMBOL(inet_csk_accept); * to optimize. */ void inet_csk_init_xmit_timers(struct sock *sk, - void (*retransmit_handler)(unsigned long), - void (*delack_handler)(unsigned long), - void (*keepalive_handler)(unsigned long)) + void (*retransmit_handler)(struct timer_list *t), + void (*delack_handler)(struct timer_list *t), + void (*keepalive_handler)(struct timer_list *t)) { struct inet_connection_sock *icsk = inet_csk(sk); - setup_timer(&icsk->icsk_retransmit_timer, retransmit_handler, - (unsigned long)sk); - setup_timer(&icsk->icsk_delack_timer, delack_handler, - (unsigned long)sk); - setup_timer(&sk->sk_timer, keepalive_handler, (unsigned long)sk); + timer_setup(&icsk->icsk_retransmit_timer, retransmit_handler, 0); + timer_setup(&icsk->icsk_delack_timer, delack_handler, 0); + timer_setup(&sk->sk_timer, keepalive_handler, 0); icsk->icsk_pending = icsk->icsk_ack.pending = 0; } EXPORT_SYMBOL(inet_csk_init_xmit_timers); @@ -676,9 +674,9 @@ void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req } EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put); -static void reqsk_timer_handler(unsigned long data) +static void reqsk_timer_handler(struct timer_list *t) { - struct request_sock *req = (struct request_sock *)data; + struct request_sock *req = from_timer(req, t, rsk_timer); struct sock *sk_listener = req->rsk_listener; struct net *net = sock_net(sk_listener); struct inet_connection_sock *icsk = inet_csk(sk_listener); @@ -749,8 +747,7 @@ static void reqsk_queue_hash_req(struct request_sock *req, req->num_timeout = 0; req->sk = NULL; - setup_pinned_timer(&req->rsk_timer, reqsk_timer_handler, - (unsigned long)req); + timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED); mod_timer(&req->rsk_timer, jiffies + timeout); inet_ehash_insert(req_to_sk(req), NULL); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index af74d0433453..26a3d0315728 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -147,7 +147,7 @@ inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb) spin_unlock(&hb->chain_lock); hlist_for_each_entry_safe(fq, n, &expired, list_evictor) - f->frag_expire((unsigned long) fq); + f->frag_expire(&fq->timer); return evicted; } @@ -164,7 +164,7 @@ static void inet_frag_worker(struct work_struct *work) local_bh_disable(); - for (i = ACCESS_ONCE(f->next_bucket); budget; --budget) { + for (i = READ_ONCE(f->next_bucket); budget; --budget) { evicted += inet_evict_bucket(f, &f->hash[i]); i = (i + 1) & (INETFRAGS_HASHSZ - 1); if (evicted > INETFRAGS_EVICT_MAX) @@ -366,7 +366,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, f->constructor(q, arg); add_frag_mem_limit(nf, f->qsize); - setup_timer(&q->timer, f->frag_expire, (unsigned long)q); + timer_setup(&q->timer, f->frag_expire, 0); spin_lock_init(&q->lock); refcount_set(&q->refcnt, 1); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 5b039159e67a..c690cd0d9b3f 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -9,7 +9,6 @@ */ #include <linux/kernel.h> -#include <linux/kmemcheck.h> #include <linux/slab.h> #include <linux/module.h> #include <net/inet_hashtables.h> @@ -142,9 +141,9 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, } EXPORT_SYMBOL_GPL(__inet_twsk_hashdance); -static void tw_timer_handler(unsigned long data) +static void tw_timer_handler(struct timer_list *t) { - struct inet_timewait_sock *tw = (struct inet_timewait_sock *)data; + struct inet_timewait_sock *tw = from_timer(tw, t, tw_timer); if (tw->tw_kill) __NET_INC_STATS(twsk_net(tw), LINUX_MIB_TIMEWAITKILLED); @@ -167,8 +166,6 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, if (tw) { const struct inet_sock *inet = inet_sk(sk); - kmemcheck_annotate_bitfield(tw, flags); - tw->tw_dr = dr; /* Give us an identity. */ tw->tw_daddr = inet->inet_daddr; @@ -188,8 +185,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, tw->tw_prot = sk->sk_prot_creator; atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie)); twsk_net_set(tw, sock_net(sk)); - setup_pinned_timer(&tw->tw_timer, tw_timer_handler, - (unsigned long)tw); + timer_setup(&tw->tw_timer, tw_timer_handler, TIMER_PINNED); /* * Because we use RCU lookups, we should not set tw_refcnt * to a non null value before everything is setup for this diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index b20c8ac64081..914d56928578 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -284,14 +284,17 @@ EXPORT_SYMBOL(inet_peer_xrlim_allow); void inetpeer_invalidate_tree(struct inet_peer_base *base) { - struct inet_peer *p, *n; + struct rb_node *p = rb_first(&base->rb_root); - rbtree_postorder_for_each_entry_safe(p, n, &base->rb_root, rb_node) { - inet_putpeer(p); + while (p) { + struct inet_peer *peer = rb_entry(p, struct inet_peer, rb_node); + + p = rb_next(p); + rb_erase(&peer->rb_node, &base->rb_root); + inet_putpeer(peer); cond_resched(); } - base->rb_root = RB_ROOT; base->total = 0; } EXPORT_SYMBOL(inetpeer_invalidate_tree); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index df8fe0503de0..bbf1b94942c0 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -191,12 +191,13 @@ static bool frag_expire_skip_icmp(u32 user) /* * Oops, a fragment queue timed out. Kill it and send an ICMP reply. */ -static void ip_expire(unsigned long arg) +static void ip_expire(struct timer_list *t) { + struct inet_frag_queue *frag = from_timer(frag, t, timer); struct ipq *qp; struct net *net; - qp = container_of((struct inet_frag_queue *) arg, struct ipq, q); + qp = container_of(frag, struct ipq, q); net = container_of(qp->q.net, struct net, ipv4.frags); rcu_read_lock(); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 467e44d7587d..bb6239169b1a 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -579,8 +579,8 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev, if (gre_handle_offloads(skb, false)) goto err_free_rt; - if (skb->len > dev->mtu) { - pskb_trim(skb, dev->mtu); + if (skb->len > dev->mtu + dev->hard_header_len) { + pskb_trim(skb, dev->mtu + dev->hard_header_len); truncate = true; } @@ -731,8 +731,8 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; - if (skb->len - dev->hard_header_len > dev->mtu) { - pskb_trim(skb, dev->mtu); + if (skb->len > dev->mtu + dev->hard_header_len) { + pskb_trim(skb, dev->mtu + dev->hard_header_len); truncate = true; } @@ -773,20 +773,46 @@ free_skb: return NETDEV_TX_OK; } +static void ipgre_link_update(struct net_device *dev, bool set_mtu) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + int len; + + len = tunnel->tun_hlen; + tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); + len = tunnel->tun_hlen - len; + tunnel->hlen = tunnel->hlen + len; + + dev->needed_headroom = dev->needed_headroom + len; + if (set_mtu) + dev->mtu = max_t(int, dev->mtu - len, 68); + + if (!(tunnel->parms.o_flags & TUNNEL_SEQ)) { + if (!(tunnel->parms.o_flags & TUNNEL_CSUM) || + tunnel->encap.type == TUNNEL_ENCAP_NONE) { + dev->features |= NETIF_F_GSO_SOFTWARE; + dev->hw_features |= NETIF_F_GSO_SOFTWARE; + } + dev->features |= NETIF_F_LLTX; + } +} + static int ipgre_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { - int err; struct ip_tunnel_parm p; + int err; if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) return -EFAULT; + if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { if (p.iph.version != 4 || p.iph.protocol != IPPROTO_GRE || - p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)) || - ((p.i_flags|p.o_flags)&(GRE_VERSION|GRE_ROUTING))) + p.iph.ihl != 5 || (p.iph.frag_off & htons(~IP_DF)) || + ((p.i_flags | p.o_flags) & (GRE_VERSION | GRE_ROUTING))) return -EINVAL; } + p.i_flags = gre_flags_to_tnl_flags(p.i_flags); p.o_flags = gre_flags_to_tnl_flags(p.o_flags); @@ -794,11 +820,22 @@ static int ipgre_tunnel_ioctl(struct net_device *dev, if (err) return err; + if (cmd == SIOCCHGTUNNEL) { + struct ip_tunnel *t = netdev_priv(dev); + + t->parms.i_flags = p.i_flags; + t->parms.o_flags = p.o_flags; + + if (strcmp(dev->rtnl_link_ops->kind, "erspan")) + ipgre_link_update(dev, true); + } + p.i_flags = gre_tnl_flags_to_gre_flags(p.i_flags); p.o_flags = gre_tnl_flags_to_gre_flags(p.o_flags); if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) return -EFAULT; + return 0; } @@ -1011,15 +1048,14 @@ static int __net_init ipgre_init_net(struct net *net) return ip_tunnel_init_net(net, ipgre_net_id, &ipgre_link_ops, NULL); } -static void __net_exit ipgre_exit_net(struct net *net) +static void __net_exit ipgre_exit_batch_net(struct list_head *list_net) { - struct ip_tunnel_net *itn = net_generic(net, ipgre_net_id); - ip_tunnel_delete_net(itn, &ipgre_link_ops); + ip_tunnel_delete_nets(list_net, ipgre_net_id, &ipgre_link_ops); } static struct pernet_operations ipgre_net_ops = { .init = ipgre_init_net, - .exit = ipgre_exit_net, + .exit_batch = ipgre_exit_batch_net, .id = &ipgre_net_id, .size = sizeof(struct ip_tunnel_net), }; @@ -1308,9 +1344,9 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); - struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; __u32 fwmark = t->fwmark; + struct ip_tunnel_parm p; int err; if (ipgre_netlink_encap_parms(data, &ipencap)) { @@ -1323,7 +1359,18 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; - return ip_tunnel_changelink(dev, tb, &p, fwmark); + + err = ip_tunnel_changelink(dev, tb, &p, fwmark); + if (err < 0) + return err; + + t->parms.i_flags = p.i_flags; + t->parms.o_flags = p.o_flags; + + if (strcmp(dev->rtnl_link_ops->kind, "erspan")) + ipgre_link_update(dev, !tb[IFLA_MTU]); + + return 0; } static size_t ipgre_get_size(const struct net_device *dev) @@ -1542,15 +1589,14 @@ static int __net_init ipgre_tap_init_net(struct net *net) return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, "gretap0"); } -static void __net_exit ipgre_tap_exit_net(struct net *net) +static void __net_exit ipgre_tap_exit_batch_net(struct list_head *list_net) { - struct ip_tunnel_net *itn = net_generic(net, gre_tap_net_id); - ip_tunnel_delete_net(itn, &ipgre_tap_ops); + ip_tunnel_delete_nets(list_net, gre_tap_net_id, &ipgre_tap_ops); } static struct pernet_operations ipgre_tap_net_ops = { .init = ipgre_tap_init_net, - .exit = ipgre_tap_exit_net, + .exit_batch = ipgre_tap_exit_batch_net, .id = &gre_tap_net_id, .size = sizeof(struct ip_tunnel_net), }; @@ -1561,16 +1607,14 @@ static int __net_init erspan_init_net(struct net *net) &erspan_link_ops, "erspan0"); } -static void __net_exit erspan_exit_net(struct net *net) +static void __net_exit erspan_exit_batch_net(struct list_head *net_list) { - struct ip_tunnel_net *itn = net_generic(net, erspan_net_id); - - ip_tunnel_delete_net(itn, &erspan_link_ops); + ip_tunnel_delete_nets(net_list, erspan_net_id, &erspan_link_ops); } static struct pernet_operations erspan_net_ops = { .init = erspan_init_net, - .exit = erspan_exit_net, + .exit_batch = erspan_exit_batch_net, .id = &erspan_net_id, .size = sizeof(struct ip_tunnel_net), }; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index e9805ad664ac..fe6fee728ce4 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -1061,16 +1061,22 @@ static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head, } } -void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops) +void ip_tunnel_delete_nets(struct list_head *net_list, unsigned int id, + struct rtnl_link_ops *ops) { + struct ip_tunnel_net *itn; + struct net *net; LIST_HEAD(list); rtnl_lock(); - ip_tunnel_destroy(itn, &list, ops); + list_for_each_entry(net, net_list, exit_list) { + itn = net_generic(net, id); + ip_tunnel_destroy(itn, &list, ops); + } unregister_netdevice_many(&list); rtnl_unlock(); } -EXPORT_SYMBOL_GPL(ip_tunnel_delete_net); +EXPORT_SYMBOL_GPL(ip_tunnel_delete_nets); int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm *p, __u32 fwmark) diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 89453cf62158..949f432a5f04 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -198,15 +198,6 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, goto tx_error; } - if (tunnel->err_count > 0) { - if (time_before(jiffies, - tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { - tunnel->err_count--; - dst_link_failure(skb); - } else - tunnel->err_count = 0; - } - mtu = dst_mtu(dst); if (skb->len > mtu) { skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); @@ -453,15 +444,14 @@ static int __net_init vti_init_net(struct net *net) return 0; } -static void __net_exit vti_exit_net(struct net *net) +static void __net_exit vti_exit_batch_net(struct list_head *list_net) { - struct ip_tunnel_net *itn = net_generic(net, vti_net_id); - ip_tunnel_delete_net(itn, &vti_link_ops); + ip_tunnel_delete_nets(list_net, vti_net_id, &vti_link_ops); } static struct pernet_operations vti_net_ops = { .init = vti_init_net, - .exit = vti_exit_net, + .exit_batch = vti_exit_batch_net, .id = &vti_net_id, .size = sizeof(struct ip_tunnel_net), }; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index cdd627355ed1..c891235b4966 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -659,15 +659,14 @@ static int __net_init ipip_init_net(struct net *net) return ip_tunnel_init_net(net, ipip_net_id, &ipip_link_ops, "tunl0"); } -static void __net_exit ipip_exit_net(struct net *net) +static void __net_exit ipip_exit_batch_net(struct list_head *list_net) { - struct ip_tunnel_net *itn = net_generic(net, ipip_net_id); - ip_tunnel_delete_net(itn, &ipip_link_ops); + ip_tunnel_delete_nets(list_net, ipip_net_id, &ipip_link_ops); } static struct pernet_operations ipip_net_ops = { .init = ipip_init_net, - .exit = ipip_exit_net, + .exit_batch = ipip_exit_batch_net, .id = &ipip_net_id, .size = sizeof(struct ip_tunnel_net), }; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index c9b3e6e069ae..40a43ad294cb 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -67,6 +67,7 @@ #include <net/fib_rules.h> #include <linux/netconf.h> #include <net/nexthop.h> +#include <net/switchdev.h> struct ipmr_rule { struct fib_rule common; @@ -264,6 +265,22 @@ static void __net_exit ipmr_rules_exit(struct net *net) fib_rules_unregister(net->ipv4.mr_rules_ops); rtnl_unlock(); } + +static int ipmr_rules_dump(struct net *net, struct notifier_block *nb) +{ + return fib_rules_dump(net, nb, RTNL_FAMILY_IPMR); +} + +static unsigned int ipmr_rules_seq_read(struct net *net) +{ + return fib_rules_seq_read(net, RTNL_FAMILY_IPMR); +} + +bool ipmr_rule_default(const struct fib_rule *rule) +{ + return fib_rule_matchall(rule) && rule->table == RT_TABLE_DEFAULT; +} +EXPORT_SYMBOL(ipmr_rule_default); #else #define ipmr_for_each_table(mrt, net) \ for (mrt = net->ipv4.mrt; mrt; mrt = NULL) @@ -298,6 +315,22 @@ static void __net_exit ipmr_rules_exit(struct net *net) net->ipv4.mrt = NULL; rtnl_unlock(); } + +static int ipmr_rules_dump(struct net *net, struct notifier_block *nb) +{ + return 0; +} + +static unsigned int ipmr_rules_seq_read(struct net *net) +{ + return 0; +} + +bool ipmr_rule_default(const struct fib_rule *rule) +{ + return true; +} +EXPORT_SYMBOL(ipmr_rule_default); #endif static inline int ipmr_hash_cmp(struct rhashtable_compare_arg *arg, @@ -587,6 +620,82 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) } #endif +static int call_ipmr_vif_entry_notifier(struct notifier_block *nb, + struct net *net, + enum fib_event_type event_type, + struct vif_device *vif, + vifi_t vif_index, u32 tb_id) +{ + struct vif_entry_notifier_info info = { + .info = { + .family = RTNL_FAMILY_IPMR, + .net = net, + }, + .dev = vif->dev, + .vif_index = vif_index, + .vif_flags = vif->flags, + .tb_id = tb_id, + }; + + return call_fib_notifier(nb, net, event_type, &info.info); +} + +static int call_ipmr_vif_entry_notifiers(struct net *net, + enum fib_event_type event_type, + struct vif_device *vif, + vifi_t vif_index, u32 tb_id) +{ + struct vif_entry_notifier_info info = { + .info = { + .family = RTNL_FAMILY_IPMR, + .net = net, + }, + .dev = vif->dev, + .vif_index = vif_index, + .vif_flags = vif->flags, + .tb_id = tb_id, + }; + + ASSERT_RTNL(); + net->ipv4.ipmr_seq++; + return call_fib_notifiers(net, event_type, &info.info); +} + +static int call_ipmr_mfc_entry_notifier(struct notifier_block *nb, + struct net *net, + enum fib_event_type event_type, + struct mfc_cache *mfc, u32 tb_id) +{ + struct mfc_entry_notifier_info info = { + .info = { + .family = RTNL_FAMILY_IPMR, + .net = net, + }, + .mfc = mfc, + .tb_id = tb_id + }; + + return call_fib_notifier(nb, net, event_type, &info.info); +} + +static int call_ipmr_mfc_entry_notifiers(struct net *net, + enum fib_event_type event_type, + struct mfc_cache *mfc, u32 tb_id) +{ + struct mfc_entry_notifier_info info = { + .info = { + .family = RTNL_FAMILY_IPMR, + .net = net, + }, + .mfc = mfc, + .tb_id = tb_id + }; + + ASSERT_RTNL(); + net->ipv4.ipmr_seq++; + return call_fib_notifiers(net, event_type, &info.info); +} + /** * vif_delete - Delete a VIF entry * @notify: Set to 1, if the caller is a notifier_call @@ -594,6 +703,7 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) static int vif_delete(struct mr_table *mrt, int vifi, int notify, struct list_head *head) { + struct net *net = read_pnet(&mrt->net); struct vif_device *v; struct net_device *dev; struct in_device *in_dev; @@ -603,6 +713,10 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify, v = &mrt->vif_table[vifi]; + if (VIF_EXISTS(mrt, vifi)) + call_ipmr_vif_entry_notifiers(net, FIB_EVENT_VIF_DEL, v, vifi, + mrt->id); + write_lock_bh(&mrt_lock); dev = v->dev; v->dev = NULL; @@ -652,10 +766,11 @@ static void ipmr_cache_free_rcu(struct rcu_head *head) kmem_cache_free(mrt_cachep, c); } -static inline void ipmr_cache_free(struct mfc_cache *c) +void ipmr_cache_free(struct mfc_cache *c) { call_rcu(&c->rcu, ipmr_cache_free_rcu); } +EXPORT_SYMBOL(ipmr_cache_free); /* Destroy an unresolved cache entry, killing queued skbs * and reporting error to netlink readers. @@ -754,6 +869,9 @@ static int vif_add(struct net *net, struct mr_table *mrt, struct vifctl *vifc, int mrtsock) { int vifi = vifc->vifc_vifi; + struct switchdev_attr attr = { + .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, + }; struct vif_device *v = &mrt->vif_table[vifi]; struct net_device *dev; struct in_device *in_dev; @@ -828,6 +946,13 @@ static int vif_add(struct net *net, struct mr_table *mrt, /* Fill in the VIF structures */ + attr.orig_dev = dev; + if (!switchdev_port_attr_get(dev, &attr)) { + memcpy(v->dev_parent_id.id, attr.u.ppid.id, attr.u.ppid.id_len); + v->dev_parent_id.id_len = attr.u.ppid.id_len; + } else { + v->dev_parent_id.id_len = 0; + } v->rate_limit = vifc->vifc_rate_limit; v->local = vifc->vifc_lcl_addr.s_addr; v->remote = vifc->vifc_rmt_addr.s_addr; @@ -851,6 +976,7 @@ static int vif_add(struct net *net, struct mr_table *mrt, if (vifi+1 > mrt->maxvif) mrt->maxvif = vifi+1; write_unlock_bh(&mrt_lock); + call_ipmr_vif_entry_notifiers(net, FIB_EVENT_VIF_ADD, v, vifi, mrt->id); return 0; } @@ -949,6 +1075,7 @@ static struct mfc_cache *ipmr_cache_alloc(void) if (c) { c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1; c->mfc_un.res.minvif = MAXVIFS; + refcount_set(&c->mfc_un.res.refcount, 1); } return c; } @@ -1150,6 +1277,7 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent) { + struct net *net = read_pnet(&mrt->net); struct mfc_cache *c; /* The entries are added/deleted only under RTNL */ @@ -1161,8 +1289,9 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent) return -ENOENT; rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params); list_del_rcu(&c->list); + call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c, mrt->id); mroute_netlink_event(mrt, c, RTM_DELROUTE); - ipmr_cache_free(c); + ipmr_cache_put(c); return 0; } @@ -1189,6 +1318,8 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, if (!mrtsock) c->mfc_flags |= MFC_STATIC; write_unlock_bh(&mrt_lock); + call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, c, + mrt->id); mroute_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } @@ -1238,6 +1369,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, ipmr_cache_resolve(net, mrt, uc, c); ipmr_cache_free(uc); } + call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_ADD, c, mrt->id); mroute_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } @@ -1245,6 +1377,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, /* Close the multicast socket, and clear the vif tables etc */ static void mroute_clean_tables(struct mr_table *mrt, bool all) { + struct net *net = read_pnet(&mrt->net); struct mfc_cache *c, *tmp; LIST_HEAD(list); int i; @@ -1263,8 +1396,10 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all) continue; rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params); list_del_rcu(&c->list); + call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c, + mrt->id); mroute_netlink_event(mrt, c, RTM_DELROUTE); - ipmr_cache_free(c); + ipmr_cache_put(c); } if (atomic_read(&mrt->cache_resolve_queue_len) != 0) { @@ -1393,6 +1528,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, case MRT_ADD_MFC: case MRT_DEL_MFC: parent = -1; + /* fall through */ case MRT_ADD_MFC_PROXY: case MRT_DEL_MFC_PROXY: if (optlen != sizeof(mfc)) { @@ -1724,10 +1860,33 @@ static inline int ipmr_forward_finish(struct net *net, struct sock *sk, return dst_output(net, sk, skb); } +#ifdef CONFIG_NET_SWITCHDEV +static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt, + int in_vifi, int out_vifi) +{ + struct vif_device *out_vif = &mrt->vif_table[out_vifi]; + struct vif_device *in_vif = &mrt->vif_table[in_vifi]; + + if (!skb->offload_mr_fwd_mark) + return false; + if (!out_vif->dev_parent_id.id_len || !in_vif->dev_parent_id.id_len) + return false; + return netdev_phys_item_id_same(&out_vif->dev_parent_id, + &in_vif->dev_parent_id); +} +#else +static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt, + int in_vifi, int out_vifi) +{ + return false; +} +#endif + /* Processing handlers for ipmr_forward */ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, - struct sk_buff *skb, struct mfc_cache *c, int vifi) + int in_vifi, struct sk_buff *skb, + struct mfc_cache *c, int vifi) { const struct iphdr *iph = ip_hdr(skb); struct vif_device *vif = &mrt->vif_table[vifi]; @@ -1748,6 +1907,9 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, goto out_free; } + if (ipmr_forward_offloaded(skb, mrt, in_vifi, vifi)) + goto out_free; + if (vif->flags & VIFF_TUNNEL) { rt = ip_route_output_ports(net, &fl4, NULL, vif->remote, vif->local, @@ -1925,8 +2087,8 @@ forward: struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) - ipmr_queue_xmit(net, mrt, skb2, cache, - psend); + ipmr_queue_xmit(net, mrt, true_vifi, + skb2, cache, psend); } psend = ct; } @@ -1937,9 +2099,10 @@ last_forward: struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) - ipmr_queue_xmit(net, mrt, skb2, cache, psend); + ipmr_queue_xmit(net, mrt, true_vifi, skb2, + cache, psend); } else { - ipmr_queue_xmit(net, mrt, skb, cache, psend); + ipmr_queue_xmit(net, mrt, true_vifi, skb, cache, psend); return; } } @@ -2156,6 +2319,9 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, nla_put_u32(skb, RTA_IIF, mrt->vif_table[c->mfc_parent].dev->ifindex) < 0) return -EMSGSIZE; + if (c->mfc_flags & MFC_OFFLOAD) + rtm->rtm_flags |= RTNH_F_OFFLOAD; + if (!(mp_attr = nla_nest_start(skb, RTA_MULTIPATH))) return -EMSGSIZE; @@ -3048,14 +3214,87 @@ static const struct net_protocol pim_protocol = { }; #endif +static unsigned int ipmr_seq_read(struct net *net) +{ + ASSERT_RTNL(); + + return net->ipv4.ipmr_seq + ipmr_rules_seq_read(net); +} + +static int ipmr_dump(struct net *net, struct notifier_block *nb) +{ + struct mr_table *mrt; + int err; + + err = ipmr_rules_dump(net, nb); + if (err) + return err; + + ipmr_for_each_table(mrt, net) { + struct vif_device *v = &mrt->vif_table[0]; + struct mfc_cache *mfc; + int vifi; + + /* Notifiy on table VIF entries */ + read_lock(&mrt_lock); + for (vifi = 0; vifi < mrt->maxvif; vifi++, v++) { + if (!v->dev) + continue; + + call_ipmr_vif_entry_notifier(nb, net, FIB_EVENT_VIF_ADD, + v, vifi, mrt->id); + } + read_unlock(&mrt_lock); + + /* Notify on table MFC entries */ + list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) + call_ipmr_mfc_entry_notifier(nb, net, + FIB_EVENT_ENTRY_ADD, mfc, + mrt->id); + } + + return 0; +} + +static const struct fib_notifier_ops ipmr_notifier_ops_template = { + .family = RTNL_FAMILY_IPMR, + .fib_seq_read = ipmr_seq_read, + .fib_dump = ipmr_dump, + .owner = THIS_MODULE, +}; + +static int __net_init ipmr_notifier_init(struct net *net) +{ + struct fib_notifier_ops *ops; + + net->ipv4.ipmr_seq = 0; + + ops = fib_notifier_ops_register(&ipmr_notifier_ops_template, net); + if (IS_ERR(ops)) + return PTR_ERR(ops); + net->ipv4.ipmr_notifier_ops = ops; + + return 0; +} + +static void __net_exit ipmr_notifier_exit(struct net *net) +{ + fib_notifier_ops_unregister(net->ipv4.ipmr_notifier_ops); + net->ipv4.ipmr_notifier_ops = NULL; +} + /* Setup for IP multicast routing */ static int __net_init ipmr_net_init(struct net *net) { int err; + err = ipmr_notifier_init(net); + if (err) + goto ipmr_notifier_fail; + err = ipmr_rules_init(net); if (err < 0) - goto fail; + goto ipmr_rules_fail; #ifdef CONFIG_PROC_FS err = -ENOMEM; @@ -3072,7 +3311,9 @@ proc_cache_fail: proc_vif_fail: ipmr_rules_exit(net); #endif -fail: +ipmr_rules_fail: + ipmr_notifier_exit(net); +ipmr_notifier_fail: return err; } @@ -3082,6 +3323,7 @@ static void __net_exit ipmr_net_exit(struct net *net) remove_proc_entry("ip_mr_cache", net->proc_net); remove_proc_entry("ip_mr_vif", net->proc_net); #endif + ipmr_notifier_exit(net); ipmr_rules_exit(net); } diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 9e2770fd00be..f88221aebc9d 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -634,6 +634,25 @@ static void get_counters(const struct xt_table_info *t, } } +static void get_old_counters(const struct xt_table_info *t, + struct xt_counters counters[]) +{ + struct arpt_entry *iter; + unsigned int cpu, i; + + for_each_possible_cpu(cpu) { + i = 0; + xt_entry_foreach(iter, t->entries, t->size) { + struct xt_counters *tmp; + + tmp = xt_get_per_cpu_counter(&iter->counters, cpu); + ADD_COUNTER(counters[i], tmp->bcnt, tmp->pcnt); + ++i; + } + cond_resched(); + } +} + static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; @@ -910,8 +929,7 @@ static int __do_replace(struct net *net, const char *name, (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); - /* Get the old counters, and synchronize with replace */ - get_counters(oldinfo, counters); + get_old_counters(oldinfo, counters); /* Decrease module usage counts and free resource */ loc_cpu_old_entry = oldinfo->entries; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 39286e543ee6..4cbe5e80f3bf 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -781,6 +781,26 @@ get_counters(const struct xt_table_info *t, } } +static void get_old_counters(const struct xt_table_info *t, + struct xt_counters counters[]) +{ + struct ipt_entry *iter; + unsigned int cpu, i; + + for_each_possible_cpu(cpu) { + i = 0; + xt_entry_foreach(iter, t->entries, t->size) { + const struct xt_counters *tmp; + + tmp = xt_get_per_cpu_counter(&iter->counters, cpu); + ADD_COUNTER(counters[i], tmp->bcnt, tmp->pcnt); + ++i; /* macro does multi eval of i */ + } + + cond_resched(); + } +} + static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; @@ -1070,8 +1090,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); - /* Get the old counters, and synchronize with replace */ - get_counters(oldinfo, counters); + get_old_counters(oldinfo, counters); /* Decrease module usage counts and free resource */ xt_entry_foreach(iter, oldinfo->entries, oldinfo->size) diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index fe374da4bc13..89af9d88ca21 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -344,7 +344,7 @@ static void ipv4_hooks_unregister(struct net *net) mutex_unlock(®ister_ipv4_hooks); } -struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 __read_mostly = { +const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 = { .l3proto = PF_INET, .pkt_to_tuple = ipv4_pkt_to_tuple, .invert_tuple = ipv4_invert_tuple, diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index a046c298413a..1849fedd9b81 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -81,7 +81,6 @@ static int icmp_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, - u_int8_t pf, unsigned int *timeout) { /* Do not immediately delete the connection after the first @@ -165,6 +164,12 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, return NF_ACCEPT; } +static void icmp_error_log(const struct sk_buff *skb, struct net *net, + u8 pf, const char *msg) +{ + nf_l4proto_log_invalid(skb, net, pf, IPPROTO_ICMP, "%s", msg); +} + /* Small and modified version of icmp_rcv */ static int icmp_error(struct net *net, struct nf_conn *tmpl, @@ -177,18 +182,14 @@ icmp_error(struct net *net, struct nf_conn *tmpl, /* Not enough header? */ icmph = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_ih), &_ih); if (icmph == NULL) { - if (LOG_INVALID(net, IPPROTO_ICMP)) - nf_log_packet(net, PF_INET, 0, skb, NULL, NULL, - NULL, "nf_ct_icmp: short packet "); + icmp_error_log(skb, net, pf, "short packet"); return -NF_ACCEPT; } /* See ip_conntrack_proto_tcp.c */ if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING && nf_ip_checksum(skb, hooknum, dataoff, 0)) { - if (LOG_INVALID(net, IPPROTO_ICMP)) - nf_log_packet(net, PF_INET, 0, skb, NULL, NULL, NULL, - "nf_ct_icmp: bad HW ICMP checksum "); + icmp_error_log(skb, net, pf, "bad hw icmp checksum"); return -NF_ACCEPT; } @@ -199,9 +200,7 @@ icmp_error(struct net *net, struct nf_conn *tmpl, * discarded. */ if (icmph->type > NR_ICMP_TYPES) { - if (LOG_INVALID(net, IPPROTO_ICMP)) - nf_log_packet(net, PF_INET, 0, skb, NULL, NULL, NULL, - "nf_ct_icmp: invalid ICMP type "); + icmp_error_log(skb, net, pf, "invalid icmp type"); return -NF_ACCEPT; } @@ -259,9 +258,14 @@ static int icmp_nlattr_to_tuple(struct nlattr *tb[], return 0; } -static int icmp_nlattr_tuple_size(void) +static unsigned int icmp_nlattr_tuple_size(void) { - return nla_policy_len(icmp_nla_policy, CTA_PROTO_MAX + 1); + static unsigned int size __read_mostly; + + if (!size) + size = nla_policy_len(icmp_nla_policy, CTA_PROTO_MAX + 1); + + return size; } #endif diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index a0f37b208268..0443ca4120b0 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -276,7 +276,8 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, else return NF_ACCEPT; } - /* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */ + /* Only ICMPs can be IP_CT_IS_REPLY: */ + /* fall through */ case IP_CT_NEW: /* Seen it before? This can happen for loopback, retrans, * or local packets. diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 127153f1ed8a..9f37c4727861 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -212,7 +212,6 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPRenoRecovery", LINUX_MIB_TCPRENORECOVERY), SNMP_MIB_ITEM("TCPSackRecovery", LINUX_MIB_TCPSACKRECOVERY), SNMP_MIB_ITEM("TCPSACKReneging", LINUX_MIB_TCPSACKRENEGING), - SNMP_MIB_ITEM("TCPFACKReorder", LINUX_MIB_TCPFACKREORDER), SNMP_MIB_ITEM("TCPSACKReorder", LINUX_MIB_TCPSACKREORDER), SNMP_MIB_ITEM("TCPRenoReorder", LINUX_MIB_TCPRENOREORDER), SNMP_MIB_ITEM("TCPTSReorder", LINUX_MIB_TCPTSREORDER), diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 3d9f1c2f81c5..43b69af242e1 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -495,7 +495,7 @@ 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 = ACCESS_ONCE(*p_tstamp); + u32 old = READ_ONCE(*p_tstamp); u32 now = (u32)jiffies; u32 new, delta = 0; @@ -651,9 +651,12 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, struct fnhe_hash_bucket *hash; struct fib_nh_exception *fnhe; struct rtable *rt; + u32 genid, hval; unsigned int i; int depth; - u32 hval = fnhe_hashfun(daddr); + + genid = fnhe_genid(dev_net(nh->nh_dev)); + hval = fnhe_hashfun(daddr); spin_lock_bh(&fnhe_lock); @@ -676,12 +679,13 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, } if (fnhe) { + if (fnhe->fnhe_genid != genid) + fnhe->fnhe_genid = genid; if (gw) fnhe->fnhe_gw = gw; - if (pmtu) { + if (pmtu) fnhe->fnhe_pmtu = pmtu; - fnhe->fnhe_expires = max(1UL, expires); - } + fnhe->fnhe_expires = max(1UL, expires); /* Update all cached dsts too */ rt = rcu_dereference(fnhe->fnhe_rth_input); if (rt) @@ -700,7 +704,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_next = hash->chain; rcu_assign_pointer(hash->chain, fnhe); } - fnhe->fnhe_genid = fnhe_genid(dev_net(nh->nh_dev)); + fnhe->fnhe_genid = genid; fnhe->fnhe_daddr = daddr; fnhe->fnhe_gw = gw; fnhe->fnhe_pmtu = pmtu; @@ -1250,7 +1254,7 @@ static void set_class_tag(struct rtable *rt, u32 tag) static unsigned int ipv4_default_advmss(const struct dst_entry *dst) { unsigned int header_size = sizeof(struct tcphdr) + sizeof(struct iphdr); - unsigned int advmss = max_t(unsigned int, dst->dev->mtu - header_size, + unsigned int advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size, ip_rt_min_advmss); return min(advmss, IPV4_MAX_PMTU - header_size); @@ -3038,7 +3042,6 @@ struct ip_rt_acct __percpu *ip_rt_acct __read_mostly; int __init ip_rt_init(void) { - int rc = 0; int cpu; ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL); @@ -3095,7 +3098,7 @@ int __init ip_rt_init(void) #endif register_pernet_subsys(&rt_genid_ops); register_pernet_subsys(&ipv4_inetpeer_ops); - return rc; + return 0; } #ifdef CONFIG_SYSCTL diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 77cf32a80952..fda37f2862c9 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -385,7 +385,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) /* Try to redo what tcp_v4_send_synack did. */ req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW); - tcp_select_initial_window(tcp_full_space(sk), req->mss, + tcp_select_initial_window(sk, tcp_full_space(sk), req->mss, &req->rsk_rcv_wnd, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, dst_metric(&rt->dst, RTAX_INITRWND)); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 0989e739d098..93e172118a94 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -26,6 +26,7 @@ #include <net/inet_frag.h> #include <net/ping.h> #include <net/protocol.h> +#include <net/netevent.h> static int zero; static int one = 1; @@ -200,6 +201,8 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write, static int proc_tcp_congestion_control(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + struct net *net = container_of(ctl->data, struct net, + ipv4.tcp_congestion_control); char val[TCP_CA_NAME_MAX]; struct ctl_table tbl = { .data = val, @@ -207,11 +210,11 @@ static int proc_tcp_congestion_control(struct ctl_table *ctl, int write, }; int ret; - tcp_get_default_congestion_control(val); + tcp_get_default_congestion_control(net, val); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) - ret = tcp_set_default_congestion_control(val); + ret = tcp_set_default_congestion_control(net, val); return ret; } @@ -252,10 +255,12 @@ static int proc_allowed_congestion_control(struct ctl_table *ctl, return ret; } -static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write, +static int proc_tcp_fastopen_key(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + struct net *net = container_of(table->data, struct net, + ipv4.sysctl_tcp_fastopen); struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) }; struct tcp_fastopen_context *ctxt; int ret; @@ -266,7 +271,7 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write, return -ENOMEM; rcu_read_lock(); - ctxt = rcu_dereference(tcp_fastopen_ctx); + ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx); if (ctxt) memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH); else @@ -283,12 +288,8 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write, ret = -EINVAL; goto bad_key; } - /* Generate a dummy secret but don't publish it. This - * is needed so we don't regenerate a new key on the - * first invocation of tcp_fastopen_cookie_gen - */ - tcp_fastopen_init_key_once(false); - tcp_fastopen_reset_cipher(user_key, TCP_FASTOPEN_KEY_LENGTH); + tcp_fastopen_reset_cipher(net, NULL, user_key, + TCP_FASTOPEN_KEY_LENGTH); } bad_key: @@ -359,11 +360,13 @@ static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table, void __user *buffer, size_t *lenp, loff_t *ppos) { + struct net *net = container_of(table->data, struct net, + ipv4.sysctl_tcp_fastopen_blackhole_timeout); int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) - tcp_fastopen_active_timeout_reset(); + atomic_set(&net->ipv4.tfo_active_disable_times, 0); return ret; } @@ -386,15 +389,25 @@ static int proc_tcp_available_ulp(struct ctl_table *ctl, return ret; } +#ifdef CONFIG_IP_ROUTE_MULTIPATH +static int proc_fib_multipath_hash_policy(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + struct net *net = container_of(table->data, struct net, + ipv4.sysctl_fib_multipath_hash_policy); + int ret; + + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (write && ret == 0) + call_netevent_notifiers(NETEVENT_MULTIPATH_HASH_UPDATE, net); + + return ret; +} +#endif + static struct ctl_table ipv4_table[] = { { - .procname = "tcp_retrans_collapse", - .data = &sysctl_tcp_retrans_collapse, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .procname = "tcp_max_orphans", .data = &sysctl_tcp_max_orphans, .maxlen = sizeof(int), @@ -402,48 +415,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .procname = "tcp_fastopen", - .data = &sysctl_tcp_fastopen, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "tcp_fastopen_key", - .mode = 0600, - .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10), - .proc_handler = proc_tcp_fastopen_key, - }, - { - .procname = "tcp_fastopen_blackhole_timeout_sec", - .data = &sysctl_tcp_fastopen_blackhole_timeout, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_tfo_blackhole_detect_timeout, - .extra1 = &zero, - }, - { - .procname = "tcp_abort_on_overflow", - .data = &sysctl_tcp_abort_on_overflow, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { - .procname = "tcp_stdurg", - .data = &sysctl_tcp_stdurg, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { - .procname = "tcp_rfc1337", - .data = &sysctl_tcp_rfc1337, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .procname = "inet_peer_threshold", .data = &inet_peer_threshold, .maxlen = sizeof(int), @@ -465,34 +436,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec_jiffies, }, { - .procname = "tcp_fack", - .data = &sysctl_tcp_fack, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { - .procname = "tcp_recovery", - .data = &sysctl_tcp_recovery, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "tcp_max_reordering", - .data = &sysctl_tcp_max_reordering, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { - .procname = "tcp_dsack", - .data = &sysctl_tcp_dsack, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .procname = "tcp_mem", .maxlen = sizeof(sysctl_tcp_mem), .data = &sysctl_tcp_mem, @@ -500,113 +443,12 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_doulongvec_minmax, }, { - .procname = "tcp_wmem", - .data = &sysctl_tcp_wmem, - .maxlen = sizeof(sysctl_tcp_wmem), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &one, - }, - { - .procname = "tcp_rmem", - .data = &sysctl_tcp_rmem, - .maxlen = sizeof(sysctl_tcp_rmem), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &one, - }, - { - .procname = "tcp_app_win", - .data = &sysctl_tcp_app_win, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { - .procname = "tcp_adv_win_scale", - .data = &sysctl_tcp_adv_win_scale, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &tcp_adv_win_scale_min, - .extra2 = &tcp_adv_win_scale_max, - }, - { - .procname = "tcp_frto", - .data = &sysctl_tcp_frto, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { - .procname = "tcp_min_rtt_wlen", - .data = &sysctl_tcp_min_rtt_wlen, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .procname = "tcp_low_latency", .data = &sysctl_tcp_low_latency, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "tcp_no_metrics_save", - .data = &sysctl_tcp_nometrics_save, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "tcp_moderate_rcvbuf", - .data = &sysctl_tcp_moderate_rcvbuf, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "tcp_tso_win_divisor", - .data = &sysctl_tcp_tso_win_divisor, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "tcp_congestion_control", - .mode = 0644, - .maxlen = TCP_CA_NAME_MAX, - .proc_handler = proc_tcp_congestion_control, - }, - { - .procname = "tcp_workaround_signed_windows", - .data = &sysctl_tcp_workaround_signed_windows, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { - .procname = "tcp_limit_output_bytes", - .data = &sysctl_tcp_limit_output_bytes, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { - .procname = "tcp_challenge_ack_limit", - .data = &sysctl_tcp_challenge_ack_limit, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { - .procname = "tcp_slow_start_after_idle", - .data = &sysctl_tcp_slow_start_after_idle, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, #ifdef CONFIG_NETLABEL { .procname = "cipso_cache_enable", @@ -650,65 +492,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_allowed_congestion_control, }, { - .procname = "tcp_thin_linear_timeouts", - .data = &sysctl_tcp_thin_linear_timeouts, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { - .procname = "tcp_early_retrans", - .data = &sysctl_tcp_early_retrans, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &four, - }, - { - .procname = "tcp_min_tso_segs", - .data = &sysctl_tcp_min_tso_segs, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &one, - .extra2 = &gso_max_segs, - }, - { - .procname = "tcp_pacing_ss_ratio", - .data = &sysctl_tcp_pacing_ss_ratio, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &thousand, - }, - { - .procname = "tcp_pacing_ca_ratio", - .data = &sysctl_tcp_pacing_ca_ratio, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &thousand, - }, - { - .procname = "tcp_autocorking", - .data = &sysctl_tcp_autocorking, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, - }, - { - .procname = "tcp_invalid_ratelimit", - .data = &sysctl_tcp_invalid_ratelimit, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_ms_jiffies, - }, - { .procname = "tcp_available_ulp", .maxlen = TCP_ULP_BUF_MAX, .mode = 0444, @@ -977,6 +760,13 @@ static struct ctl_table ipv4_net_table[] = { }, #endif { + .procname = "tcp_congestion_control", + .data = &init_net.ipv4.tcp_congestion_control, + .mode = 0644, + .maxlen = TCP_CA_NAME_MAX, + .proc_handler = proc_tcp_congestion_control, + }, + { .procname = "tcp_keepalive_time", .data = &init_net.ipv4.sysctl_tcp_keepalive_time, .maxlen = sizeof(int), @@ -1086,6 +876,28 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "tcp_fastopen", + .data = &init_net.ipv4.sysctl_tcp_fastopen, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "tcp_fastopen_key", + .mode = 0600, + .data = &init_net.ipv4.sysctl_tcp_fastopen, + .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10), + .proc_handler = proc_tcp_fastopen_key, + }, + { + .procname = "tcp_fastopen_blackhole_timeout_sec", + .data = &init_net.ipv4.sysctl_tcp_fastopen_blackhole_timeout, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_tfo_blackhole_detect_timeout, + .extra1 = &zero, + }, #ifdef CONFIG_IP_ROUTE_MULTIPATH { .procname = "fib_multipath_use_neigh", @@ -1101,7 +913,7 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_fib_multipath_hash_policy, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_fib_multipath_hash_policy, .extra1 = &zero, .extra2 = &one, }, @@ -1145,6 +957,216 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "tcp_early_retrans", + .data = &init_net.ipv4.sysctl_tcp_early_retrans, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &four, + }, + { + .procname = "tcp_recovery", + .data = &init_net.ipv4.sysctl_tcp_recovery, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "tcp_thin_linear_timeouts", + .data = &init_net.ipv4.sysctl_tcp_thin_linear_timeouts, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "tcp_slow_start_after_idle", + .data = &init_net.ipv4.sysctl_tcp_slow_start_after_idle, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "tcp_retrans_collapse", + .data = &init_net.ipv4.sysctl_tcp_retrans_collapse, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "tcp_stdurg", + .data = &init_net.ipv4.sysctl_tcp_stdurg, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "tcp_rfc1337", + .data = &init_net.ipv4.sysctl_tcp_rfc1337, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "tcp_abort_on_overflow", + .data = &init_net.ipv4.sysctl_tcp_abort_on_overflow, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "tcp_fack", + .data = &init_net.ipv4.sysctl_tcp_fack, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "tcp_max_reordering", + .data = &init_net.ipv4.sysctl_tcp_max_reordering, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "tcp_dsack", + .data = &init_net.ipv4.sysctl_tcp_dsack, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "tcp_app_win", + .data = &init_net.ipv4.sysctl_tcp_app_win, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "tcp_adv_win_scale", + .data = &init_net.ipv4.sysctl_tcp_adv_win_scale, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &tcp_adv_win_scale_min, + .extra2 = &tcp_adv_win_scale_max, + }, + { + .procname = "tcp_frto", + .data = &init_net.ipv4.sysctl_tcp_frto, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "tcp_no_metrics_save", + .data = &init_net.ipv4.sysctl_tcp_nometrics_save, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "tcp_moderate_rcvbuf", + .data = &init_net.ipv4.sysctl_tcp_moderate_rcvbuf, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "tcp_tso_win_divisor", + .data = &init_net.ipv4.sysctl_tcp_tso_win_divisor, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "tcp_workaround_signed_windows", + .data = &init_net.ipv4.sysctl_tcp_workaround_signed_windows, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "tcp_limit_output_bytes", + .data = &init_net.ipv4.sysctl_tcp_limit_output_bytes, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "tcp_challenge_ack_limit", + .data = &init_net.ipv4.sysctl_tcp_challenge_ack_limit, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "tcp_min_tso_segs", + .data = &init_net.ipv4.sysctl_tcp_min_tso_segs, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + .extra2 = &gso_max_segs, + }, + { + .procname = "tcp_min_rtt_wlen", + .data = &init_net.ipv4.sysctl_tcp_min_rtt_wlen, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "tcp_autocorking", + .data = &init_net.ipv4.sysctl_tcp_autocorking, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, + { + .procname = "tcp_invalid_ratelimit", + .data = &init_net.ipv4.sysctl_tcp_invalid_ratelimit, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_ms_jiffies, + }, + { + .procname = "tcp_pacing_ss_ratio", + .data = &init_net.ipv4.sysctl_tcp_pacing_ss_ratio, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &thousand, + }, + { + .procname = "tcp_pacing_ca_ratio", + .data = &init_net.ipv4.sysctl_tcp_pacing_ca_ratio, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &thousand, + }, + { + .procname = "tcp_wmem", + .data = &init_net.ipv4.sysctl_tcp_wmem, + .maxlen = sizeof(init_net.ipv4.sysctl_tcp_wmem), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + }, + { + .procname = "tcp_rmem", + .data = &init_net.ipv4.sysctl_tcp_rmem, + .maxlen = sizeof(init_net.ipv4.sysctl_tcp_rmem), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + }, { } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5091402720ab..bf97317e6c97 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -270,6 +270,7 @@ #include <linux/time.h> #include <linux/slab.h> #include <linux/errqueue.h> +#include <linux/static_key.h> #include <net/icmp.h> #include <net/inet_common.h> @@ -282,24 +283,22 @@ #include <asm/ioctls.h> #include <net/busy_poll.h> -int sysctl_tcp_min_tso_segs __read_mostly = 2; - -int sysctl_tcp_autocorking __read_mostly = 1; +#include <trace/events/tcp.h> struct percpu_counter tcp_orphan_count; EXPORT_SYMBOL_GPL(tcp_orphan_count); long sysctl_tcp_mem[3] __read_mostly; -int sysctl_tcp_wmem[3] __read_mostly; -int sysctl_tcp_rmem[3] __read_mostly; - EXPORT_SYMBOL(sysctl_tcp_mem); -EXPORT_SYMBOL(sysctl_tcp_rmem); -EXPORT_SYMBOL(sysctl_tcp_wmem); atomic_long_t tcp_memory_allocated; /* Current allocated memory. */ EXPORT_SYMBOL(tcp_memory_allocated); +#if IS_ENABLED(CONFIG_SMC) +DEFINE_STATIC_KEY_FALSE(tcp_have_smc); +EXPORT_SYMBOL(tcp_have_smc); +#endif + /* * Current number of TCP sockets. */ @@ -413,8 +412,10 @@ void tcp_init_sock(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); tp->out_of_order_queue = RB_ROOT; + sk->tcp_rtx_queue = RB_ROOT; tcp_init_xmit_timers(sk); INIT_LIST_HEAD(&tp->tsq_node); + INIT_LIST_HEAD(&tp->tsorted_sent_queue); icsk->icsk_rto = TCP_TIMEOUT_INIT; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); @@ -441,6 +442,7 @@ void tcp_init_sock(struct sock *sk) tcp_assign_congestion_control(sk); tp->tsoffset = 0; + tp->rack.reo_wnd_steps = 1; sk->sk_state = TCP_CLOSE; @@ -449,15 +451,29 @@ void tcp_init_sock(struct sock *sk) icsk->icsk_sync_mss = tcp_sync_mss; - sk->sk_sndbuf = sysctl_tcp_wmem[1]; - sk->sk_rcvbuf = sysctl_tcp_rmem[1]; + sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1]; + sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1]; sk_sockets_allocated_inc(sk); } EXPORT_SYMBOL(tcp_init_sock); -static void tcp_tx_timestamp(struct sock *sk, u16 tsflags, struct sk_buff *skb) +void tcp_init_transfer(struct sock *sk, int bpf_op) { + struct inet_connection_sock *icsk = inet_csk(sk); + + tcp_mtup_init(sk); + icsk->icsk_af_ops->rebuild_header(sk); + tcp_init_metrics(sk); + tcp_call_bpf(sk, bpf_op); + tcp_init_congestion_control(sk); + tcp_init_buffer_space(sk); +} + +static void tcp_tx_timestamp(struct sock *sk, u16 tsflags) +{ + struct sk_buff *skb = tcp_write_queue_tail(sk); + if (tsflags && skb) { struct skb_shared_info *shinfo = skb_shinfo(skb); struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); @@ -675,7 +691,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb, int size_goal) { return skb->len < size_goal && - sysctl_tcp_autocorking && + sock_net(sk)->ipv4.sysctl_tcp_autocorking && skb != tcp_write_queue_head(sk) && refcount_read(&sk->sk_wmem_alloc) > skb->truesize; } @@ -686,10 +702,9 @@ static void tcp_push(struct sock *sk, int flags, int mss_now, struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; - if (!tcp_send_head(sk)) - return; - skb = tcp_write_queue_tail(sk); + if (!skb) + return; if (!(flags & MSG_MORE) || forced_push(tp)) tcp_mark_push(tp, skb); @@ -869,6 +884,7 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, * available to the caller, no more, no less. */ skb->reserved_tailroom = skb->end - skb->tail - size; + INIT_LIST_HEAD(&skb->tcp_tsorted_anchor); return skb; } __kfree_skb(skb); @@ -948,14 +964,14 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, int copy, i; bool can_coalesce; - if (!tcp_send_head(sk) || (copy = size_goal - skb->len) <= 0 || + if (!skb || (copy = size_goal - skb->len) <= 0 || !tcp_skb_can_collapse_to(skb)) { new_segment: if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation, - skb_queue_empty(&sk->sk_write_queue)); + tcp_rtx_and_write_queues_empty(sk)); if (!skb) goto wait_for_memory; @@ -1027,7 +1043,7 @@ wait_for_memory: out: if (copied) { - tcp_tx_timestamp(sk, sk->sk_tsflags, tcp_write_queue_tail(sk)); + tcp_tx_timestamp(sk, sk->sk_tsflags); if (!(flags & MSG_SENDPAGE_NOTLAST)) tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); } @@ -1126,7 +1142,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, struct sockaddr *uaddr = msg->msg_name; int err, flags; - if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) || + if (!(sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) || (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) && uaddr->sa_family == AF_UNSPEC)) return -EOPNOTSUPP; @@ -1183,7 +1199,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) goto out_err; } - skb = tcp_send_head(sk) ? tcp_write_queue_tail(sk) : NULL; + skb = tcp_write_queue_tail(sk); uarg = sock_zerocopy_realloc(sk, size, skb_zcopy(skb)); if (!uarg) { err = -ENOBUFS; @@ -1259,7 +1275,7 @@ restart: int max = size_goal; skb = tcp_write_queue_tail(sk); - if (tcp_send_head(sk)) { + if (skb) { if (skb->ip_summed == CHECKSUM_NONE) max = mss_now; copy = max - skb->len; @@ -1279,7 +1295,7 @@ new_segment: process_backlog = false; goto restart; } - first_skb = skb_queue_empty(&sk->sk_write_queue); + first_skb = tcp_rtx_and_write_queues_empty(sk); skb = sk_stream_alloc_skb(sk, select_size(sk, sg, first_skb), sk->sk_allocation, @@ -1404,7 +1420,7 @@ wait_for_memory: out: if (copied) { - tcp_tx_timestamp(sk, sockc.tsflags, tcp_write_queue_tail(sk)); + tcp_tx_timestamp(sk, sockc.tsflags); tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); } out_nopush: @@ -1505,6 +1521,13 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len) /* XXX -- need to support SO_PEEK_OFF */ + skb_rbtree_walk(skb, &sk->tcp_rtx_queue) { + err = skb_copy_datagram_msg(skb, 0, msg, skb->len); + if (err) + return err; + copied += skb->len; + } + skb_queue_walk(&sk->sk_write_queue, skb) { err = skb_copy_datagram_msg(skb, 0, msg, skb->len); if (err) @@ -2017,6 +2040,8 @@ void tcp_set_state(struct sock *sk, int state) { int oldstate = sk->sk_state; + trace_tcp_set_state(sk, oldstate, state); + switch (state) { case TCP_ESTABLISHED: if (oldstate != TCP_ESTABLISHED) @@ -2304,6 +2329,37 @@ static inline bool tcp_need_reset(int state) TCPF_FIN_WAIT2 | TCPF_SYN_RECV); } +static void tcp_rtx_queue_purge(struct sock *sk) +{ + struct rb_node *p = rb_first(&sk->tcp_rtx_queue); + + while (p) { + struct sk_buff *skb = rb_to_skb(p); + + p = rb_next(p); + /* Since we are deleting whole queue, no need to + * list_del(&skb->tcp_tsorted_anchor) + */ + tcp_rtx_queue_unlink(skb, sk); + sk_wmem_free_skb(sk, skb); + } +} + +void tcp_write_queue_purge(struct sock *sk) +{ + struct sk_buff *skb; + + tcp_chrono_stop(sk, TCP_CHRONO_BUSY); + while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) { + tcp_skb_tsorted_anchor_cleanup(skb); + sk_wmem_free_skb(sk, skb); + } + tcp_rtx_queue_purge(sk); + INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue); + sk_mem_reclaim(sk); + tcp_clear_all_retrans_hints(tcp_sk(sk)); +} + int tcp_disconnect(struct sock *sk, int flags) { struct inet_sock *inet = inet_sk(sk); @@ -2362,7 +2418,6 @@ int tcp_disconnect(struct sock *sk, int flags) * issue in __tcp_select_window() */ icsk->icsk_ack.rcv_mss = TCP_MIN_MSS; - tcp_init_send_head(sk); memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); dst_release(sk->sk_rx_dst); @@ -2454,8 +2509,6 @@ static int tcp_repair_options_est(struct sock *sk, return -EINVAL; tp->rx_opt.sack_ok |= TCP_SACK_SEEN; - if (sysctl_tcp_fack) - tcp_enable_fack(tp); break; case TCPOPT_TIMESTAMP: if (opt.opt_val != 0) @@ -2518,6 +2571,17 @@ static int do_tcp_setsockopt(struct sock *sk, int level, release_sock(sk); return err; } + case TCP_FASTOPEN_KEY: { + __u8 key[TCP_FASTOPEN_KEY_LENGTH]; + + if (optlen != sizeof(key)) + return -EINVAL; + + if (copy_from_user(key, optval, optlen)) + return -EFAULT; + + return tcp_fastopen_reset_cipher(net, sk, key, sizeof(key)); + } default: /* fallthru */ break; @@ -2749,7 +2813,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_FASTOPEN: if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { - tcp_fastopen_init_key_once(true); + tcp_fastopen_init_key_once(net); fastopen_queue_tune(sk, val); } else { @@ -2759,7 +2823,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_FASTOPEN_CONNECT: if (val > 1 || val < 0) { err = -EINVAL; - } else if (sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) { + } else if (net->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) { if (sk->sk_state == TCP_CLOSE) tp->fastopen_connect = val; else @@ -2768,6 +2832,14 @@ static int do_tcp_setsockopt(struct sock *sk, int level, err = -EOPNOTSUPP; } break; + case TCP_FASTOPEN_NO_COOKIE: + if (val > 1 || val < 0) + err = -EINVAL; + else if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) + err = -EINVAL; + else + tp->fastopen_no_cookie = val; + break; case TCP_TIMESTAMP: if (!tp->repair) err = -EPERM; @@ -2905,7 +2977,6 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_lost = tp->lost_out; info->tcpi_retrans = tp->retrans_out; - info->tcpi_fackets = tp->fackets_out; now = tcp_jiffies32; info->tcpi_last_data_sent = jiffies_to_msecs(now - tp->lsndtime); @@ -3104,6 +3175,28 @@ static int do_tcp_getsockopt(struct sock *sk, int level, return -EFAULT; return 0; + case TCP_FASTOPEN_KEY: { + __u8 key[TCP_FASTOPEN_KEY_LENGTH]; + struct tcp_fastopen_context *ctx; + + if (get_user(len, optlen)) + return -EFAULT; + + rcu_read_lock(); + ctx = rcu_dereference(icsk->icsk_accept_queue.fastopenq.ctx); + if (ctx) + memcpy(key, ctx->key, sizeof(key)); + else + len = 0; + rcu_read_unlock(); + + len = min_t(unsigned int, len, sizeof(key)); + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, key, len)) + return -EFAULT; + return 0; + } case TCP_THIN_LINEAR_TIMEOUTS: val = tp->thin_lto; break; @@ -3166,6 +3259,10 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = tp->fastopen_connect; break; + case TCP_FASTOPEN_NO_COOKIE: + val = tp->fastopen_no_cookie; + break; + case TCP_TIMESTAMP: val = tcp_time_stamp_raw() + tp->tsoffset; break; @@ -3531,13 +3628,13 @@ void __init tcp_init(void) max_wshare = min(4UL*1024*1024, limit); max_rshare = min(6UL*1024*1024, limit); - sysctl_tcp_wmem[0] = SK_MEM_QUANTUM; - sysctl_tcp_wmem[1] = 16*1024; - sysctl_tcp_wmem[2] = max(64*1024, max_wshare); + init_net.ipv4.sysctl_tcp_wmem[0] = SK_MEM_QUANTUM; + init_net.ipv4.sysctl_tcp_wmem[1] = 16*1024; + init_net.ipv4.sysctl_tcp_wmem[2] = max(64*1024, max_wshare); - sysctl_tcp_rmem[0] = SK_MEM_QUANTUM; - sysctl_tcp_rmem[1] = 87380; - sysctl_tcp_rmem[2] = max(87380, max_rshare); + init_net.ipv4.sysctl_tcp_rmem[0] = SK_MEM_QUANTUM; + init_net.ipv4.sysctl_tcp_rmem[1] = 87380; + init_net.ipv4.sysctl_tcp_rmem[2] = max(87380, max_rshare); pr_info("Hash tables configured (established %u bind %u)\n", tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size); diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c index 66ac69f7bd19..06fbe102a425 100644 --- a/net/ipv4/tcp_cdg.c +++ b/net/ipv4/tcp_cdg.c @@ -389,7 +389,7 @@ static void tcp_cdg_release(struct sock *sk) kfree(ca->gradients); } -struct tcp_congestion_ops tcp_cdg __read_mostly = { +static struct tcp_congestion_ops tcp_cdg __read_mostly = { .cong_avoid = tcp_cdg_cong_avoid, .cwnd_event = tcp_cdg_cwnd_event, .pkts_acked = tcp_cdg_acked, diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 2f26124fd160..bc6c02f16243 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -33,9 +33,11 @@ static struct tcp_congestion_ops *tcp_ca_find(const char *name) } /* Must be called with rcu lock held */ -static const struct tcp_congestion_ops *__tcp_ca_find_autoload(const char *name) +static struct tcp_congestion_ops *tcp_ca_find_autoload(struct net *net, + const char *name) { - const struct tcp_congestion_ops *ca = tcp_ca_find(name); + struct tcp_congestion_ops *ca = tcp_ca_find(name); + #ifdef CONFIG_MODULES if (!ca && capable(CAP_NET_ADMIN)) { rcu_read_unlock(); @@ -115,7 +117,7 @@ void tcp_unregister_congestion_control(struct tcp_congestion_ops *ca) } EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control); -u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca) +u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca) { const struct tcp_congestion_ops *ca; u32 key = TCP_CA_UNSPEC; @@ -123,7 +125,7 @@ u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca) might_sleep(); rcu_read_lock(); - ca = __tcp_ca_find_autoload(name); + ca = tcp_ca_find_autoload(net, name); if (ca) { key = ca->key; *ecn_ca = ca->flags & TCP_CONG_NEEDS_ECN; @@ -153,23 +155,18 @@ EXPORT_SYMBOL_GPL(tcp_ca_get_name_by_key); /* Assign choice of congestion control. */ void tcp_assign_congestion_control(struct sock *sk) { + struct net *net = sock_net(sk); struct inet_connection_sock *icsk = inet_csk(sk); - struct tcp_congestion_ops *ca; + const struct tcp_congestion_ops *ca; rcu_read_lock(); - list_for_each_entry_rcu(ca, &tcp_cong_list, list) { - if (likely(try_module_get(ca->owner))) { - icsk->icsk_ca_ops = ca; - goto out; - } - /* Fallback to next available. The last really - * guaranteed fallback is Reno from this list. - */ - } -out: + ca = rcu_dereference(net->ipv4.tcp_congestion_control); + if (unlikely(!try_module_get(ca->owner))) + ca = &tcp_reno; + icsk->icsk_ca_ops = ca; rcu_read_unlock(); - memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); + memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); if (ca->flags & TCP_CONG_NEEDS_ECN) INET_ECN_xmit(sk); else @@ -214,29 +211,27 @@ void tcp_cleanup_congestion_control(struct sock *sk) } /* Used by sysctl to change default congestion control */ -int tcp_set_default_congestion_control(const char *name) +int tcp_set_default_congestion_control(struct net *net, const char *name) { struct tcp_congestion_ops *ca; - int ret = -ENOENT; - - spin_lock(&tcp_cong_list_lock); - ca = tcp_ca_find(name); -#ifdef CONFIG_MODULES - if (!ca && capable(CAP_NET_ADMIN)) { - spin_unlock(&tcp_cong_list_lock); + const struct tcp_congestion_ops *prev; + int ret; - request_module("tcp_%s", name); - spin_lock(&tcp_cong_list_lock); - ca = tcp_ca_find(name); - } -#endif + rcu_read_lock(); + ca = tcp_ca_find_autoload(net, name); + if (!ca) { + ret = -ENOENT; + } else if (!try_module_get(ca->owner)) { + ret = -EBUSY; + } else { + prev = xchg(&net->ipv4.tcp_congestion_control, ca); + if (prev) + module_put(prev->owner); - if (ca) { - ca->flags |= TCP_CONG_NON_RESTRICTED; /* default is always allowed */ - list_move(&ca->list, &tcp_cong_list); + ca->flags |= TCP_CONG_NON_RESTRICTED; ret = 0; } - spin_unlock(&tcp_cong_list_lock); + rcu_read_unlock(); return ret; } @@ -244,7 +239,8 @@ int tcp_set_default_congestion_control(const char *name) /* Set default value from kernel configuration at bootup */ static int __init tcp_congestion_default(void) { - return tcp_set_default_congestion_control(CONFIG_DEFAULT_TCP_CONG); + return tcp_set_default_congestion_control(&init_net, + CONFIG_DEFAULT_TCP_CONG); } late_initcall(tcp_congestion_default); @@ -264,14 +260,12 @@ void tcp_get_available_congestion_control(char *buf, size_t maxlen) } /* Get current default congestion control */ -void tcp_get_default_congestion_control(char *name) +void tcp_get_default_congestion_control(struct net *net, char *name) { - struct tcp_congestion_ops *ca; - /* We will always have reno... */ - BUG_ON(list_empty(&tcp_cong_list)); + const struct tcp_congestion_ops *ca; rcu_read_lock(); - ca = list_entry(tcp_cong_list.next, struct tcp_congestion_ops, list); + ca = rcu_dereference(net->ipv4.tcp_congestion_control); strncpy(name, ca->name, TCP_CA_NAME_MAX); rcu_read_unlock(); } @@ -351,12 +345,14 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, boo if (!load) ca = tcp_ca_find(name); else - ca = __tcp_ca_find_autoload(name); + ca = tcp_ca_find_autoload(sock_net(sk), name); + /* No change asking for existing value */ if (ca == icsk->icsk_ca_ops) { icsk->icsk_ca_setsockopt = 1; goto out; } + if (!ca) { err = -ENOENT; } else if (!load) { diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index fbbeda647774..78c192ee03a4 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -10,15 +10,18 @@ #include <net/inetpeer.h> #include <net/tcp.h> -int sysctl_tcp_fastopen __read_mostly = TFO_CLIENT_ENABLE; - -struct tcp_fastopen_context __rcu *tcp_fastopen_ctx; - -static DEFINE_SPINLOCK(tcp_fastopen_ctx_lock); - -void tcp_fastopen_init_key_once(bool publish) +void tcp_fastopen_init_key_once(struct net *net) { - static u8 key[TCP_FASTOPEN_KEY_LENGTH]; + u8 key[TCP_FASTOPEN_KEY_LENGTH]; + struct tcp_fastopen_context *ctxt; + + rcu_read_lock(); + ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx); + if (ctxt) { + rcu_read_unlock(); + return; + } + rcu_read_unlock(); /* tcp_fastopen_reset_cipher publishes the new context * atomically, so we allow this race happening here. @@ -26,8 +29,8 @@ void tcp_fastopen_init_key_once(bool publish) * All call sites of tcp_fastopen_cookie_gen also check * for a valid cookie, so this is an acceptable risk. */ - if (net_get_random_once(key, sizeof(key)) && publish) - tcp_fastopen_reset_cipher(key, sizeof(key)); + get_random_bytes(key, sizeof(key)); + tcp_fastopen_reset_cipher(net, NULL, key, sizeof(key)); } static void tcp_fastopen_ctx_free(struct rcu_head *head) @@ -38,10 +41,37 @@ static void tcp_fastopen_ctx_free(struct rcu_head *head) kfree(ctx); } -int tcp_fastopen_reset_cipher(void *key, unsigned int len) +void tcp_fastopen_destroy_cipher(struct sock *sk) +{ + struct tcp_fastopen_context *ctx; + + ctx = rcu_dereference_protected( + inet_csk(sk)->icsk_accept_queue.fastopenq.ctx, 1); + if (ctx) + call_rcu(&ctx->rcu, tcp_fastopen_ctx_free); +} + +void tcp_fastopen_ctx_destroy(struct net *net) +{ + struct tcp_fastopen_context *ctxt; + + spin_lock(&net->ipv4.tcp_fastopen_ctx_lock); + + ctxt = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx, + lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock)); + rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, NULL); + spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock); + + if (ctxt) + call_rcu(&ctxt->rcu, tcp_fastopen_ctx_free); +} + +int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk, + void *key, unsigned int len) { - int err; struct tcp_fastopen_context *ctx, *octx; + struct fastopen_queue *q; + int err; ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) @@ -62,26 +92,37 @@ error: kfree(ctx); } memcpy(ctx->key, key, len); - spin_lock(&tcp_fastopen_ctx_lock); - octx = rcu_dereference_protected(tcp_fastopen_ctx, - lockdep_is_held(&tcp_fastopen_ctx_lock)); - rcu_assign_pointer(tcp_fastopen_ctx, ctx); - spin_unlock(&tcp_fastopen_ctx_lock); + spin_lock(&net->ipv4.tcp_fastopen_ctx_lock); + if (sk) { + q = &inet_csk(sk)->icsk_accept_queue.fastopenq; + octx = rcu_dereference_protected(q->ctx, + lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock)); + rcu_assign_pointer(q->ctx, ctx); + } else { + octx = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx, + lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock)); + rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, ctx); + } + spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock); if (octx) call_rcu(&octx->rcu, tcp_fastopen_ctx_free); return err; } -static bool __tcp_fastopen_cookie_gen(const void *path, +static bool __tcp_fastopen_cookie_gen(struct sock *sk, const void *path, struct tcp_fastopen_cookie *foc) { struct tcp_fastopen_context *ctx; bool ok = false; rcu_read_lock(); - ctx = rcu_dereference(tcp_fastopen_ctx); + + ctx = rcu_dereference(inet_csk(sk)->icsk_accept_queue.fastopenq.ctx); + if (!ctx) + ctx = rcu_dereference(sock_net(sk)->ipv4.tcp_fastopen_ctx); + if (ctx) { crypto_cipher_encrypt_one(ctx->tfm, foc->val, path); foc->len = TCP_FASTOPEN_COOKIE_SIZE; @@ -97,7 +138,8 @@ static bool __tcp_fastopen_cookie_gen(const void *path, * * XXX (TFO) - refactor when TCP_FASTOPEN_COOKIE_SIZE != AES_BLOCK_SIZE. */ -static bool tcp_fastopen_cookie_gen(struct request_sock *req, +static bool tcp_fastopen_cookie_gen(struct sock *sk, + struct request_sock *req, struct sk_buff *syn, struct tcp_fastopen_cookie *foc) { @@ -105,7 +147,7 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req, const struct iphdr *iph = ip_hdr(syn); __be32 path[4] = { iph->saddr, iph->daddr, 0, 0 }; - return __tcp_fastopen_cookie_gen(path, foc); + return __tcp_fastopen_cookie_gen(sk, path, foc); } #if IS_ENABLED(CONFIG_IPV6) @@ -113,13 +155,13 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req, const struct ipv6hdr *ip6h = ipv6_hdr(syn); struct tcp_fastopen_cookie tmp; - if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) { + if (__tcp_fastopen_cookie_gen(sk, &ip6h->saddr, &tmp)) { struct in6_addr *buf = &tmp.addr; int i; for (i = 0; i < 4; i++) buf->s6_addr32[i] ^= ip6h->daddr.s6_addr32[i]; - return __tcp_fastopen_cookie_gen(buf, foc); + return __tcp_fastopen_cookie_gen(sk, buf, foc); } } #endif @@ -217,12 +259,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, refcount_set(&req->rsk_refcnt, 2); /* Now finish processing the fastopen child socket. */ - inet_csk(child)->icsk_af_ops->rebuild_header(child); - tcp_init_congestion_control(child); - tcp_mtup_init(child); - tcp_init_metrics(child); - tcp_call_bpf(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); - tcp_init_buffer_space(child); + tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; @@ -272,33 +309,45 @@ static bool tcp_fastopen_queue_check(struct sock *sk) return true; } +static bool tcp_fastopen_no_cookie(const struct sock *sk, + const struct dst_entry *dst, + int flag) +{ + return (sock_net(sk)->ipv4.sysctl_tcp_fastopen & flag) || + tcp_sk(sk)->fastopen_no_cookie || + (dst && dst_metric(dst, RTAX_FASTOPEN_NO_COOKIE)); +} + /* Returns true if we should perform Fast Open on the SYN. The cookie (foc) * may be updated and return the client in the SYN-ACK later. E.g., Fast Open * cookie request (foc->len == 0). */ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, - struct tcp_fastopen_cookie *foc) + struct tcp_fastopen_cookie *foc, + const struct dst_entry *dst) { - struct tcp_fastopen_cookie valid_foc = { .len = -1 }; bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1; + int tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen; + struct tcp_fastopen_cookie valid_foc = { .len = -1 }; struct sock *child; if (foc->len == 0) /* Client requests a cookie */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENCOOKIEREQD); - if (!((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) && + if (!((tcp_fastopen & TFO_SERVER_ENABLE) && (syn_data || foc->len >= 0) && tcp_fastopen_queue_check(sk))) { foc->len = -1; return NULL; } - if (syn_data && (sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD)) + if (syn_data && + tcp_fastopen_no_cookie(sk, dst, TFO_SERVER_COOKIE_NOT_REQD)) goto fastopen; if (foc->len >= 0 && /* Client presents or requests a cookie */ - tcp_fastopen_cookie_gen(req, skb, &valid_foc) && + tcp_fastopen_cookie_gen(sk, req, skb, &valid_foc) && foc->len == TCP_FASTOPEN_COOKIE_SIZE && foc->len == valid_foc.len && !memcmp(foc->val, valid_foc.val, foc->len)) { @@ -331,6 +380,7 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie) { unsigned long last_syn_loss = 0; + const struct dst_entry *dst; int syn_loss = 0; tcp_fastopen_cache_get(sk, mss, cookie, &syn_loss, &last_syn_loss); @@ -348,7 +398,9 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, return false; } - if (sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) { + dst = __sk_dst_get(sk); + + if (tcp_fastopen_no_cookie(sk, dst, TFO_CLIENT_NO_COOKIE)) { cookie->len = -1; return true; } @@ -402,25 +454,16 @@ EXPORT_SYMBOL(tcp_fastopen_defer_connect); * TFO connection with data exchanges. */ -/* Default to 1hr */ -unsigned int sysctl_tcp_fastopen_blackhole_timeout __read_mostly = 60 * 60; -static atomic_t tfo_active_disable_times __read_mostly = ATOMIC_INIT(0); -static unsigned long tfo_active_disable_stamp __read_mostly; - /* Disable active TFO and record current jiffies and * tfo_active_disable_times */ void tcp_fastopen_active_disable(struct sock *sk) { - atomic_inc(&tfo_active_disable_times); - tfo_active_disable_stamp = jiffies; - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENBLACKHOLE); -} + struct net *net = sock_net(sk); -/* Reset tfo_active_disable_times to 0 */ -void tcp_fastopen_active_timeout_reset(void) -{ - atomic_set(&tfo_active_disable_times, 0); + atomic_inc(&net->ipv4.tfo_active_disable_times); + net->ipv4.tfo_active_disable_stamp = jiffies; + NET_INC_STATS(net, LINUX_MIB_TCPFASTOPENBLACKHOLE); } /* Calculate timeout for tfo active disable @@ -429,17 +472,18 @@ void tcp_fastopen_active_timeout_reset(void) */ bool tcp_fastopen_active_should_disable(struct sock *sk) { - int tfo_da_times = atomic_read(&tfo_active_disable_times); - int multiplier; + unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout; + int tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times); unsigned long timeout; + int multiplier; if (!tfo_da_times) return false; /* Limit timout to max: 2^6 * initial timeout */ multiplier = 1 << min(tfo_da_times - 1, 6); - timeout = multiplier * sysctl_tcp_fastopen_blackhole_timeout * HZ; - if (time_before(jiffies, tfo_active_disable_stamp + timeout)) + timeout = multiplier * tfo_bh_timeout * HZ; + if (time_before(jiffies, sock_net(sk)->ipv4.tfo_active_disable_stamp + timeout)) return true; /* Mark check bit so we can check for successful active TFO @@ -458,27 +502,25 @@ bool tcp_fastopen_active_should_disable(struct sock *sk) void tcp_fastopen_active_disable_ofo_check(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - struct rb_node *p; - struct sk_buff *skb; struct dst_entry *dst; + struct sk_buff *skb; if (!tp->syn_fastopen) return; if (!tp->data_segs_in) { - p = rb_first(&tp->out_of_order_queue); - if (p && !rb_next(p)) { - skb = rb_entry(p, struct sk_buff, rbnode); + skb = skb_rb_first(&tp->out_of_order_queue); + if (skb && !skb_rb_next(skb)) { if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) { tcp_fastopen_active_disable(sk); return; } } } else if (tp->syn_fastopen_ch && - atomic_read(&tfo_active_disable_times)) { + atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times)) { dst = sk_dst_get(sk); if (!(dst && dst->dev && (dst->dev->flags & IFF_LOOPBACK))) - tcp_fastopen_active_timeout_reset(); + atomic_set(&sock_net(sk)->ipv4.tfo_active_disable_times, 0); dst_release(dst); } } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b6bb3cdfad09..f844c06c0676 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -76,25 +76,10 @@ #include <linux/ipsec.h> #include <asm/unaligned.h> #include <linux/errqueue.h> +#include <trace/events/tcp.h> +#include <linux/static_key.h> -int sysctl_tcp_fack __read_mostly; -int sysctl_tcp_max_reordering __read_mostly = 300; -int sysctl_tcp_dsack __read_mostly = 1; -int sysctl_tcp_app_win __read_mostly = 31; -int sysctl_tcp_adv_win_scale __read_mostly = 1; -EXPORT_SYMBOL(sysctl_tcp_adv_win_scale); - -/* rfc5961 challenge ack rate limiting */ -int sysctl_tcp_challenge_ack_limit = 1000; - -int sysctl_tcp_stdurg __read_mostly; -int sysctl_tcp_rfc1337 __read_mostly; int sysctl_tcp_max_orphans __read_mostly = NR_FILE; -int sysctl_tcp_frto __read_mostly = 2; -int sysctl_tcp_min_rtt_wlen __read_mostly = 300; -int sysctl_tcp_moderate_rcvbuf __read_mostly = 1; -int sysctl_tcp_early_retrans __read_mostly = 3; -int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2; #define FLAG_DATA 0x01 /* Incoming frame contained data. */ #define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */ @@ -335,7 +320,7 @@ static void tcp_sndbuf_expand(struct sock *sk) sndmem *= nr_segs * per_mss; if (sk->sk_sndbuf < sndmem) - sk->sk_sndbuf = min(sndmem, sysctl_tcp_wmem[2]); + sk->sk_sndbuf = min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]); } /* 2. Tuning advertised window (window_clamp, rcv_ssthresh) @@ -368,8 +353,8 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); /* Optimize this! */ - int truesize = tcp_win_from_space(skb->truesize) >> 1; - int window = tcp_win_from_space(sysctl_tcp_rmem[2]) >> 1; + int truesize = tcp_win_from_space(sk, skb->truesize) >> 1; + int window = tcp_win_from_space(sk, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1; while (tp->rcv_ssthresh <= window) { if (truesize <= skb->len) @@ -394,7 +379,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) /* Check #2. Increase window, if skb with such overhead * will fit to rcvbuf in future. */ - if (tcp_win_from_space(skb->truesize) <= skb->len) + if (tcp_win_from_space(sk, skb->truesize) <= skb->len) incr = 2 * tp->advmss; else incr = __tcp_grow_window(sk, skb); @@ -420,11 +405,11 @@ static void tcp_fixup_rcvbuf(struct sock *sk) /* Dynamic Right Sizing (DRS) has 2 to 3 RTT latency * Allow enough cushion so that sender is not limited by our window */ - if (sysctl_tcp_moderate_rcvbuf) + if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) rcvmem <<= 2; if (sk->sk_rcvbuf < rcvmem) - sk->sk_rcvbuf = min(rcvmem, sysctl_tcp_rmem[2]); + sk->sk_rcvbuf = min(rcvmem, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]); } /* 4. Try to fixup all. It is made immediately after connection enters @@ -432,6 +417,7 @@ static void tcp_fixup_rcvbuf(struct sock *sk) */ void tcp_init_buffer_space(struct sock *sk) { + int tcp_app_win = sock_net(sk)->ipv4.sysctl_tcp_app_win; struct tcp_sock *tp = tcp_sk(sk); int maxwin; @@ -450,14 +436,14 @@ void tcp_init_buffer_space(struct sock *sk) if (tp->window_clamp >= maxwin) { tp->window_clamp = maxwin; - if (sysctl_tcp_app_win && maxwin > 4 * tp->advmss) + if (tcp_app_win && maxwin > 4 * tp->advmss) tp->window_clamp = max(maxwin - - (maxwin >> sysctl_tcp_app_win), + (maxwin >> tcp_app_win), 4 * tp->advmss); } /* Force reservation of one segment. */ - if (sysctl_tcp_app_win && + if (tcp_app_win && tp->window_clamp > 2 * tp->advmss && tp->window_clamp + tp->advmss > maxwin) tp->window_clamp = max(2 * tp->advmss, maxwin - tp->advmss); @@ -471,15 +457,16 @@ static void tcp_clamp_window(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); + struct net *net = sock_net(sk); icsk->icsk_ack.quick = 0; - if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] && + if (sk->sk_rcvbuf < net->ipv4.sysctl_tcp_rmem[2] && !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) && !tcp_under_memory_pressure(sk) && sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) { sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc), - sysctl_tcp_rmem[2]); + net->ipv4.sysctl_tcp_rmem[2]); } if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss); @@ -610,7 +597,7 @@ void tcp_rcv_space_adjust(struct sock *sk) * <prev RTT . ><current RTT .. ><next RTT .... > */ - if (sysctl_tcp_moderate_rcvbuf && + if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf && !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { int rcvwin, rcvmem, rcvbuf; @@ -634,10 +621,11 @@ void tcp_rcv_space_adjust(struct sock *sk) } rcvmem = SKB_TRUESIZE(tp->advmss + MAX_TCP_HEADER); - while (tcp_win_from_space(rcvmem) < tp->advmss) + while (tcp_win_from_space(sk, rcvmem) < tp->advmss) rcvmem += 128; - rcvbuf = min(rcvwin / tp->advmss * rcvmem, sysctl_tcp_rmem[2]); + rcvbuf = min(rcvwin / tp->advmss * rcvmem, + sock_net(sk)->ipv4.sysctl_tcp_rmem[2]); if (rcvbuf > sk->sk_rcvbuf) { sk->sk_rcvbuf = rcvbuf; @@ -781,15 +769,6 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us) tp->srtt_us = max(1U, srtt); } -/* Set the sk_pacing_rate to allow proper sizing of TSO packets. - * Note: TCP stack does not yet implement pacing. - * FQ packet scheduler can be used to implement cheap but effective - * TCP pacing, to smooth the burst on large writes when packets - * in flight is significantly lower than cwnd (or rwin) - */ -int sysctl_tcp_pacing_ss_ratio __read_mostly = 200; -int sysctl_tcp_pacing_ca_ratio __read_mostly = 120; - static void tcp_update_pacing_rate(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); @@ -807,21 +786,21 @@ static void tcp_update_pacing_rate(struct sock *sk) * end of slow start and should slow down. */ if (tp->snd_cwnd < tp->snd_ssthresh / 2) - rate *= sysctl_tcp_pacing_ss_ratio; + rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio; else - rate *= sysctl_tcp_pacing_ca_ratio; + rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ca_ratio; rate *= max(tp->snd_cwnd, tp->packets_out); if (likely(tp->srtt_us)) do_div(rate, tp->srtt_us); - /* ACCESS_ONCE() is needed because sch_fq fetches sk_pacing_rate + /* WRITE_ONCE() is needed because sch_fq fetches sk_pacing_rate * without any lock. We want to make sure compiler wont store * intermediate values in this location. */ - ACCESS_ONCE(sk->sk_pacing_rate) = min_t(u64, rate, - sk->sk_max_pacing_rate); + WRITE_ONCE(sk->sk_pacing_rate, min_t(u64, rate, + sk->sk_max_pacing_rate)); } /* Calculate rto without backoff. This is the second half of Van Jacobson's @@ -863,60 +842,46 @@ __u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst) return min_t(__u32, cwnd, tp->snd_cwnd_clamp); } -/* - * Packet counting of FACK is based on in-order assumptions, therefore TCP - * disables it when reordering is detected - */ -void tcp_disable_fack(struct tcp_sock *tp) -{ - /* RFC3517 uses different metric in lost marker => reset on change */ - if (tcp_is_fack(tp)) - tp->lost_skb_hint = NULL; - tp->rx_opt.sack_ok &= ~TCP_FACK_ENABLED; -} - /* Take a notice that peer is sending D-SACKs */ static void tcp_dsack_seen(struct tcp_sock *tp) { tp->rx_opt.sack_ok |= TCP_DSACK_SEEN; + tp->rack.dsack_seen = 1; } -static void tcp_update_reordering(struct sock *sk, const int metric, - const int ts) +/* It's reordering when higher sequence was delivered (i.e. sacked) before + * some lower never-retransmitted sequence ("low_seq"). The maximum reordering + * distance is approximated in full-mss packet distance ("reordering"). + */ +static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq, + const int ts) { struct tcp_sock *tp = tcp_sk(sk); - int mib_idx; + const u32 mss = tp->mss_cache; + u32 fack, metric; - if (WARN_ON_ONCE(metric < 0)) + fack = tcp_highest_sack_seq(tp); + if (!before(low_seq, fack)) return; - if (metric > tp->reordering) { - tp->reordering = min(sysctl_tcp_max_reordering, metric); - + metric = fack - low_seq; + if ((metric > tp->reordering * mss) && mss) { #if FASTRETRANS_DEBUG > 1 pr_debug("Disorder%d %d %u f%u s%u rr%d\n", tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state, tp->reordering, - tp->fackets_out, + 0, tp->sacked_out, tp->undo_marker ? tp->undo_retrans : 0); #endif - tcp_disable_fack(tp); + tp->reordering = min_t(u32, (metric + mss - 1) / mss, + sock_net(sk)->ipv4.sysctl_tcp_max_reordering); } tp->rack.reord = 1; - /* This exciting event is worth to be remembered. 8) */ - if (ts) - mib_idx = LINUX_MIB_TCPTSREORDER; - else if (tcp_is_reno(tp)) - mib_idx = LINUX_MIB_TCPRENOREORDER; - else if (tcp_is_fack(tp)) - mib_idx = LINUX_MIB_TCPFACKREORDER; - else - mib_idx = LINUX_MIB_TCPSACKREORDER; - - NET_INC_STATS(sock_net(sk), mib_idx); + NET_INC_STATS(sock_net(sk), + ts ? LINUX_MIB_TCPTSREORDER : LINUX_MIB_TCPSACKREORDER); } /* This must be called before lost_out is incremented */ @@ -990,7 +955,6 @@ void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb) * 3. Loss detection event of two flavors: * A. Scoreboard estimator decided the packet is lost. * A'. Reno "three dupacks" marks head of queue lost. - * A''. Its FACK modification, head until snd.fack is lost. * B. SACK arrives sacking SND.NXT at the moment, when the * segment was retransmitted. * 4. D-SACK added new rule: D-SACK changes any tag to S. @@ -1133,8 +1097,7 @@ static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb, } struct tcp_sacktag_state { - int reord; - int fack_count; + u32 reord; /* Timestamps for earliest and latest never-retransmitted segment * that was SACKed. RTO needs the earliest RTT to stay conservative, * but congestion control should still get an accurate delay signal. @@ -1143,6 +1106,7 @@ struct tcp_sacktag_state { u64 last_sackt; struct rate_sample *rate; int flag; + unsigned int mss_now; }; /* Check if skb is fully within the SACK block. In presence of GSO skbs, @@ -1192,7 +1156,8 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, if (pkt_len >= skb->len && !in_sack) return 0; - err = tcp_fragment(sk, skb, pkt_len, mss, GFP_ATOMIC); + err = tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, + pkt_len, mss, GFP_ATOMIC); if (err < 0) return err; } @@ -1208,15 +1173,15 @@ static u8 tcp_sacktag_one(struct sock *sk, u64 xmit_time) { struct tcp_sock *tp = tcp_sk(sk); - int fack_count = state->fack_count; /* Account D-SACK for retransmitted packet. */ if (dup_sack && (sacked & TCPCB_RETRANS)) { if (tp->undo_marker && tp->undo_retrans > 0 && after(end_seq, tp->undo_marker)) tp->undo_retrans--; - if (sacked & TCPCB_SACKED_ACKED) - state->reord = min(fack_count, state->reord); + if ((sacked & TCPCB_SACKED_ACKED) && + before(start_seq, state->reord)) + state->reord = start_seq; } /* Nothing to do; acked frame is about to be dropped (was ACKed). */ @@ -1242,9 +1207,10 @@ static u8 tcp_sacktag_one(struct sock *sk, * which was in hole. It is reordering. */ if (before(start_seq, - tcp_highest_sack_seq(tp))) - state->reord = min(fack_count, - state->reord); + tcp_highest_sack_seq(tp)) && + before(start_seq, state->reord)) + state->reord = start_seq; + if (!after(end_seq, tp->high_seq)) state->flag |= FLAG_ORIG_SACK_ACKED; if (state->first_sackt == 0) @@ -1263,15 +1229,10 @@ static u8 tcp_sacktag_one(struct sock *sk, tp->sacked_out += pcount; tp->delivered += pcount; /* Out-of-order packets delivered */ - fack_count += pcount; - /* Lost marker hint past SACKed? Tweak RFC3517 cnt */ - if (!tcp_is_fack(tp) && tp->lost_skb_hint && + if (tp->lost_skb_hint && before(start_seq, TCP_SKB_CB(tp->lost_skb_hint)->seq)) tp->lost_cnt_hint += pcount; - - if (fack_count > tp->fackets_out) - tp->fackets_out = fack_count; } /* D-SACK. We can detect redundant retransmission in S|R and plain R @@ -1289,13 +1250,13 @@ static u8 tcp_sacktag_one(struct sock *sk, /* Shift newly-SACKed bytes from this skb to the immediately previous * already-SACKed sk_buff. Mark the newly-SACKed bytes as such. */ -static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, +static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev, + struct sk_buff *skb, struct tcp_sacktag_state *state, unsigned int pcount, int shifted, int mss, bool dup_sack) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *prev = tcp_write_queue_prev(sk, skb); u32 start_seq = TCP_SKB_CB(skb)->seq; /* start of newly-SACKed */ u32 end_seq = start_seq + shifted; /* end of newly-SACKed */ @@ -1364,8 +1325,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, if (unlikely(TCP_SKB_CB(prev)->tx.delivered_mstamp)) TCP_SKB_CB(prev)->tx.delivered_mstamp = 0; - tcp_unlink_write_queue(skb, sk); - sk_wmem_free_skb(sk, skb); + tcp_rtx_queue_unlink_and_free(skb, sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_SACKMERGED); @@ -1415,9 +1375,9 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, goto fallback; /* Can only happen with delayed DSACK + discard craziness */ - if (unlikely(skb == tcp_write_queue_head(sk))) + prev = skb_rb_prev(skb); + if (!prev) goto fallback; - prev = tcp_write_queue_prev(sk, skb); if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) goto fallback; @@ -1496,18 +1456,17 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, if (!skb_shift(prev, skb, len)) goto fallback; - if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss, dup_sack)) + if (!tcp_shifted_skb(sk, prev, skb, state, pcount, len, mss, dup_sack)) goto out; /* Hole filled allows collapsing with the next as well, this is very * useful when hole on every nth skb pattern happens */ - if (prev == tcp_write_queue_tail(sk)) + skb = skb_rb_next(prev); + if (!skb) goto out; - skb = tcp_write_queue_next(sk, prev); if (!skb_can_shift(skb) || - (skb == tcp_send_head(sk)) || ((TCP_SKB_CB(skb)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) || (mss != tcp_skb_seglen(skb))) goto out; @@ -1515,11 +1474,11 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, len = skb->len; if (skb_shift(prev, skb, len)) { pcount += tcp_skb_pcount(skb); - tcp_shifted_skb(sk, skb, state, tcp_skb_pcount(skb), len, mss, 0); + tcp_shifted_skb(sk, prev, skb, state, tcp_skb_pcount(skb), + len, mss, 0); } out: - state->fack_count += pcount; return prev; noop: @@ -1539,13 +1498,10 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *tmp; - tcp_for_write_queue_from(skb, sk) { + skb_rbtree_walk_from(skb) { int in_sack = 0; bool dup_sack = dup_sack_in; - if (skb == tcp_send_head(sk)) - break; - /* queue is in-order => we can short-circuit the walk early */ if (!before(TCP_SKB_CB(skb)->seq, end_seq)) break; @@ -1594,34 +1550,48 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, tcp_skb_pcount(skb), skb->skb_mstamp); tcp_rate_skb_delivered(sk, skb, state->rate); + if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) + list_del_init(&skb->tcp_tsorted_anchor); if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) tcp_advance_highest_sack(sk, skb); } - - state->fack_count += tcp_skb_pcount(skb); } return skb; } -/* Avoid all extra work that is being done by sacktag while walking in - * a normal way - */ +static struct sk_buff *tcp_sacktag_bsearch(struct sock *sk, + struct tcp_sacktag_state *state, + u32 seq) +{ + struct rb_node *parent, **p = &sk->tcp_rtx_queue.rb_node; + struct sk_buff *skb; + + while (*p) { + parent = *p; + skb = rb_to_skb(parent); + if (before(seq, TCP_SKB_CB(skb)->seq)) { + p = &parent->rb_left; + continue; + } + if (!before(seq, TCP_SKB_CB(skb)->end_seq)) { + p = &parent->rb_right; + continue; + } + return skb; + } + return NULL; +} + static struct sk_buff *tcp_sacktag_skip(struct sk_buff *skb, struct sock *sk, struct tcp_sacktag_state *state, u32 skip_to_seq) { - tcp_for_write_queue_from(skb, sk) { - if (skb == tcp_send_head(sk)) - break; - - if (after(TCP_SKB_CB(skb)->end_seq, skip_to_seq)) - break; + if (skb && after(TCP_SKB_CB(skb)->seq, skip_to_seq)) + return skb; - state->fack_count += tcp_skb_pcount(skb); - } - return skb; + return tcp_sacktag_bsearch(sk, state, skip_to_seq); } static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb, @@ -1666,13 +1636,10 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, int first_sack_index; state->flag = 0; - state->reord = tp->packets_out; + state->reord = tp->snd_nxt; - if (!tp->sacked_out) { - if (WARN_ON(tp->fackets_out)) - tp->fackets_out = 0; + if (!tp->sacked_out) tcp_highest_sack_reset(sk); - } found_dup_sack = tcp_check_dsack(sk, ack_skb, sp_wire, num_sacks, prior_snd_una); @@ -1743,8 +1710,8 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, } } - skb = tcp_write_queue_head(sk); - state->fack_count = 0; + state->mss_now = tcp_current_mss(sk); + skb = NULL; i = 0; if (!tp->sacked_out) { @@ -1801,7 +1768,6 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, skb = tcp_highest_sack(sk); if (!skb) break; - state->fack_count = tp->fackets_out; cache++; goto walk; } @@ -1816,7 +1782,6 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, skb = tcp_highest_sack(sk); if (!skb) break; - state->fack_count = tp->fackets_out; } skb = tcp_sacktag_skip(skb, sk, state, start_seq); @@ -1836,9 +1801,8 @@ advance_sp: for (j = 0; j < used_sacks; j++) tp->recv_sack_cache[i++] = sp[j]; - if ((state->reord < tp->fackets_out) && - ((inet_csk(sk)->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker)) - tcp_update_reordering(sk, tp->fackets_out - state->reord, 0); + if (inet_csk(sk)->icsk_ca_state != TCP_CA_Loss || tp->undo_marker) + tcp_check_sack_reordering(sk, state->reord, 0); tcp_verify_left_out(tp); out: @@ -1876,8 +1840,13 @@ static bool tcp_limit_reno_sacked(struct tcp_sock *tp) static void tcp_check_reno_reordering(struct sock *sk, const int addend) { struct tcp_sock *tp = tcp_sk(sk); - if (tcp_limit_reno_sacked(tp)) - tcp_update_reordering(sk, tp->packets_out + addend, 0); + + if (!tcp_limit_reno_sacked(tp)) + return; + + tp->reordering = min_t(u32, tp->packets_out + addend, + sock_net(sk)->ipv4.sysctl_tcp_max_reordering); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRENOREORDER); } /* Emulate SACKs for SACKless connection: account for a new dupack. */ @@ -1923,7 +1892,6 @@ void tcp_clear_retrans(struct tcp_sock *tp) tp->lost_out = 0; tp->undo_marker = 0; tp->undo_retrans = -1; - tp->fackets_out = 0; tp->sacked_out = 0; } @@ -1968,19 +1936,15 @@ void tcp_enter_loss(struct sock *sk) if (tcp_is_reno(tp)) tcp_reset_reno_sack(tp); - skb = tcp_write_queue_head(sk); + skb = tcp_rtx_queue_head(sk); is_reneg = skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED); if (is_reneg) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING); tp->sacked_out = 0; - tp->fackets_out = 0; } tcp_clear_all_retrans_hints(tp); - tcp_for_write_queue(skb, sk) { - if (skb == tcp_send_head(sk)) - break; - + skb_rbtree_walk_from(skb) { mark_lost = (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) || is_reneg); if (mark_lost) @@ -2014,7 +1978,7 @@ void tcp_enter_loss(struct sock *sk) * falsely raise the receive window, which results in repeated * timeouts and stop-and-go behavior. */ - tp->frto = sysctl_tcp_frto && + tp->frto = net->ipv4.sysctl_tcp_frto && (new_recovery || icsk->icsk_retransmits) && !inet_csk(sk)->icsk_mtup.probe_size; } @@ -2043,19 +2007,10 @@ static bool tcp_check_sack_reneging(struct sock *sk, int flag) return false; } -static inline int tcp_fackets_out(const struct tcp_sock *tp) -{ - return tcp_is_reno(tp) ? tp->sacked_out + 1 : tp->fackets_out; -} - /* Heurestics to calculate number of duplicate ACKs. There's no dupACKs * counter when SACK is enabled (without SACK, sacked_out is used for * that purpose). * - * Instead, with FACK TCP uses fackets_out that includes both SACKed - * segments up to the highest received SACK block so far and holes in - * between them. - * * With reordering, holes may still be in flight, so RFC3517 recovery * uses pure sacked_out (total number of SACKed segments) even though * it violates the RFC that uses duplicate ACKs, often these are equal @@ -2065,10 +2020,10 @@ static inline int tcp_fackets_out(const struct tcp_sock *tp) */ static inline int tcp_dupack_heuristics(const struct tcp_sock *tp) { - return tcp_is_fack(tp) ? tp->fackets_out : tp->sacked_out + 1; + return tp->sacked_out + 1; } -/* Linux NewReno/SACK/FACK/ECN state machine. +/* Linux NewReno/SACK/ECN state machine. * -------------------------------------- * * "Open" Normal state, no dubious events, fast path. @@ -2133,16 +2088,6 @@ static inline int tcp_dupack_heuristics(const struct tcp_sock *tp) * dynamically measured and adjusted. This is implemented in * tcp_rack_mark_lost. * - * FACK (Disabled by default. Subsumbed by RACK): - * It is the simplest heuristics. As soon as we decided - * that something is lost, we decide that _all_ not SACKed - * packets until the most forward SACK are lost. I.e. - * lost_out = fackets_out - sacked_out and left_out = fackets_out. - * It is absolutely correct estimate, if network does not reorder - * packets. And it loses any connection to reality when reordering - * takes place. We use FACK by default until reordering - * is suspected on the path to this destination. - * * If the receiver does not support SACK: * * NewReno (RFC6582): in Recovery we assume that one segment @@ -2191,7 +2136,7 @@ static bool tcp_time_to_recover(struct sock *sk, int flag) } /* Detect loss in event "A" above by marking head of queue up as lost. - * For FACK or non-SACK(Reno) senders, the first "packets" number of segments + * For non-SACK(Reno) senders, the first "packets" number of segments * are considered lost. For RFC3517 SACK, a segment is considered lost if it * has at least tp->reordering SACKed seqments above it; "packets" refers to * the maximum SACKed segments to pass before reaching this limit. @@ -2206,20 +2151,18 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) const u32 loss_high = tcp_is_sack(tp) ? tp->snd_nxt : tp->high_seq; WARN_ON(packets > tp->packets_out); - if (tp->lost_skb_hint) { - skb = tp->lost_skb_hint; - cnt = tp->lost_cnt_hint; + skb = tp->lost_skb_hint; + if (skb) { /* Head already handled? */ - if (mark_head && skb != tcp_write_queue_head(sk)) + if (mark_head && after(TCP_SKB_CB(skb)->seq, tp->snd_una)) return; + cnt = tp->lost_cnt_hint; } else { - skb = tcp_write_queue_head(sk); + skb = tcp_rtx_queue_head(sk); cnt = 0; } - tcp_for_write_queue_from(skb, sk) { - if (skb == tcp_send_head(sk)) - break; + skb_rbtree_walk_from(skb) { /* TODO: do this better */ /* this is not the most efficient way to do this... */ tp->lost_skb_hint = skb; @@ -2229,12 +2172,12 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) break; oldcnt = cnt; - if (tcp_is_fack(tp) || tcp_is_reno(tp) || + if (tcp_is_reno(tp) || (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) cnt += tcp_skb_pcount(skb); if (cnt > packets) { - if ((tcp_is_sack(tp) && !tcp_is_fack(tp)) || + if (tcp_is_sack(tp) || (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) || (oldcnt >= packets)) break; @@ -2243,7 +2186,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) /* If needed, chop off the prefix to mark as lost. */ lost = (packets - oldcnt) * mss; if (lost < skb->len && - tcp_fragment(sk, skb, lost, mss, GFP_ATOMIC) < 0) + tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, + lost, mss, GFP_ATOMIC) < 0) break; cnt = packets; } @@ -2264,11 +2208,6 @@ static void tcp_update_scoreboard(struct sock *sk, int fast_rexmit) if (tcp_is_reno(tp)) { tcp_mark_head_lost(sk, 1, 1); - } else if (tcp_is_fack(tp)) { - int lost = tp->fackets_out - tp->reordering; - if (lost <= 0) - lost = 1; - tcp_mark_head_lost(sk, lost, 0); } else { int sacked_upto = tp->sacked_out - tp->reordering; if (sacked_upto >= 0) @@ -2327,16 +2266,16 @@ static bool tcp_any_retrans_done(const struct sock *sk) if (tp->retrans_out) return true; - skb = tcp_write_queue_head(sk); + skb = tcp_rtx_queue_head(sk); if (unlikely(skb && TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS)) return true; return false; } -#if FASTRETRANS_DEBUG > 1 static void DBGUNDO(struct sock *sk, const char *msg) { +#if FASTRETRANS_DEBUG > 1 struct tcp_sock *tp = tcp_sk(sk); struct inet_sock *inet = inet_sk(sk); @@ -2358,10 +2297,8 @@ static void DBGUNDO(struct sock *sk, const char *msg) tp->packets_out); } #endif -} -#else -#define DBGUNDO(x...) do { } while (0) #endif +} static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss) { @@ -2370,9 +2307,7 @@ static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss) if (unmark_loss) { struct sk_buff *skb; - tcp_for_write_queue(skb, sk) { - if (skb == tcp_send_head(sk)) - break; + skb_rbtree_walk(skb, &sk->tcp_rtx_queue) { TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST; } tp->lost_out = 0; @@ -2417,6 +2352,8 @@ static bool tcp_try_undo_recovery(struct sock *sk) mib_idx = LINUX_MIB_TCPFULLUNDO; NET_INC_STATS(sock_net(sk), mib_idx); + } else if (tp->rack.reo_wnd_persist) { + tp->rack.reo_wnd_persist--; } if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) { /* Hold old state until something *above* high_seq @@ -2436,6 +2373,8 @@ static bool tcp_try_undo_dsack(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); if (tp->undo_marker && !tp->undo_retrans) { + tp->rack.reo_wnd_persist = min(TCP_RACK_RECOVERY_THRESH, + tp->rack.reo_wnd_persist + 1); DBGUNDO(sk, "D-SACK"); tcp_undo_cwnd_reduction(sk, false); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDSACKUNDO); @@ -2616,9 +2555,7 @@ void tcp_simple_retransmit(struct sock *sk) struct sk_buff *skb; unsigned int mss = tcp_current_mss(sk); - tcp_for_write_queue(skb, sk) { - if (skb == tcp_send_head(sk)) - break; + skb_rbtree_walk(skb, &sk->tcp_rtx_queue) { if (tcp_skb_seglen(skb) > mss && !(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) { if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { @@ -2712,7 +2649,7 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack, * is updated in tcp_ack()). Otherwise fall back to * the conventional recovery. */ - if (tcp_send_head(sk) && + if (!tcp_write_queue_empty(sk) && after(tcp_wnd_end(tp), tp->snd_nxt)) { *rexmit = REXMIT_NEW; return; @@ -2739,15 +2676,15 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack, } /* Undo during fast recovery after partial ACK. */ -static bool tcp_try_undo_partial(struct sock *sk, const int acked) +static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una) { struct tcp_sock *tp = tcp_sk(sk); if (tp->undo_marker && tcp_packet_delayed(tp)) { /* Plain luck! Hole if filled with delayed - * packet, rather than with a retransmit. + * packet, rather than with a retransmit. Check reordering. */ - tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1); + tcp_check_sack_reordering(sk, prior_snd_una, 1); /* We are getting evidence that the reordering degree is higher * than we realized. If there are no retransmits out then we @@ -2774,7 +2711,7 @@ static void tcp_rack_identify_loss(struct sock *sk, int *ack_flag) struct tcp_sock *tp = tcp_sk(sk); /* Use RACK to detect loss */ - if (sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION) { + if (sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION) { u32 prior_retrans = tp->retrans_out; tcp_rack_mark_lost(sk); @@ -2783,6 +2720,14 @@ static void tcp_rack_identify_loss(struct sock *sk, int *ack_flag) } } +static bool tcp_force_fast_retransmit(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + return after(tcp_highest_sack_seq(tp), + tp->snd_una + tp->reordering * tp->mss_cache); +} + /* Process an event, which can update packets-in-flight not trivially. * Main goal of this function is to calculate new estimate for left_out, * taking into account both packets sitting in receiver's buffer and @@ -2795,19 +2740,17 @@ static void tcp_rack_identify_loss(struct sock *sk, int *ack_flag) * It does _not_ decide what to send, it is made in function * tcp_xmit_retransmit_queue(). */ -static void tcp_fastretrans_alert(struct sock *sk, const int acked, +static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, bool is_dupack, int *ack_flag, int *rexmit) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int fast_rexmit = 0, flag = *ack_flag; bool do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) && - (tcp_fackets_out(tp) > tp->reordering)); + tcp_force_fast_retransmit(sk)); - if (WARN_ON(!tp->packets_out && tp->sacked_out)) + if (!tp->packets_out && tp->sacked_out) tp->sacked_out = 0; - if (WARN_ON(!tp->sacked_out && tp->fackets_out)) - tp->fackets_out = 0; /* Now state machine starts. * A. ECE, hence prohibit cwnd undoing, the reduction is required. */ @@ -2854,11 +2797,11 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, if (tcp_is_reno(tp) && is_dupack) tcp_add_reno_sack(sk); } else { - if (tcp_try_undo_partial(sk, acked)) + if (tcp_try_undo_partial(sk, prior_snd_una)) return; /* Partial ACK arrived. Force fast retransmit. */ do_lost = tcp_is_reno(tp) || - tcp_fackets_out(tp) > tp->reordering; + tcp_force_fast_retransmit(sk); } if (tcp_try_undo_dsack(sk)) { tcp_try_keep_open(sk); @@ -2873,6 +2816,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, (*ack_flag & FLAG_LOST_RETRANS))) return; /* Change state if cwnd is undone or retransmits are lost */ + /* fall through */ default: if (tcp_is_reno(tp)) { if (flag & FLAG_SND_UNA_ADVANCED) @@ -2913,8 +2857,8 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us) { + u32 wlen = sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen * HZ; struct tcp_sock *tp = tcp_sk(sk); - u32 wlen = sysctl_tcp_min_rtt_wlen * HZ; minmax_running_min(&tp->rtt_min, wlen, tcp_jiffies32, rtt_us ? : jiffies_to_usecs(1)); @@ -3056,28 +3000,31 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb, shinfo = skb_shinfo(skb); if (!before(shinfo->tskey, prior_snd_una) && - before(shinfo->tskey, tcp_sk(sk)->snd_una)) - __skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK); + before(shinfo->tskey, tcp_sk(sk)->snd_una)) { + tcp_skb_tsorted_save(skb) { + __skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK); + } tcp_skb_tsorted_restore(skb); + } } /* Remove acknowledged frames from the retransmission queue. If our packet * is before the ack sequence we can discard it as it's confirmed to have * arrived at the other end. */ -static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, - u32 prior_snd_una, int *acked, +static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack, + u32 prior_snd_una, struct tcp_sacktag_state *sack) { const struct inet_connection_sock *icsk = inet_csk(sk); u64 first_ackt, last_ackt; struct tcp_sock *tp = tcp_sk(sk); u32 prior_sacked = tp->sacked_out; - u32 reord = tp->packets_out; + u32 reord = tp->snd_nxt; /* lowest acked un-retx un-sacked seq */ + struct sk_buff *skb, *next; bool fully_acked = true; long sack_rtt_us = -1L; long seq_rtt_us = -1L; long ca_rtt_us = -1L; - struct sk_buff *skb; u32 pkts_acked = 0; u32 last_in_flight = 0; bool rtt_update; @@ -3085,8 +3032,9 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, first_ackt = 0; - while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) { + for (skb = skb_rb_first(&sk->tcp_rtx_queue); skb; skb = next) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb); + const u32 start_seq = scb->seq; u8 sacked = scb->sacked; u32 acked_pcount; @@ -3103,8 +3051,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, break; fully_acked = false; } else { - /* Speedup tcp_unlink_write_queue() and next loop */ - prefetchw(skb->next); acked_pcount = tcp_skb_pcount(skb); } @@ -3119,7 +3065,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, first_ackt = last_ackt; last_in_flight = TCP_SKB_CB(skb)->tx.in_flight; - reord = min(pkts_acked, reord); + if (before(start_seq, reord)) + reord = start_seq; if (!after(scb->end_seq, tp->high_seq)) flag |= FLAG_ORIG_SACK_ACKED; } @@ -3156,12 +3103,12 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (!fully_acked) break; - tcp_unlink_write_queue(skb, sk); - sk_wmem_free_skb(sk, skb); + next = skb_rb_next(skb); if (unlikely(skb == tp->retransmit_skb_hint)) tp->retransmit_skb_hint = NULL; if (unlikely(skb == tp->lost_skb_hint)) tp->lost_skb_hint = NULL; + tcp_rtx_queue_unlink_and_free(skb, sk); } if (!skb) @@ -3197,16 +3144,12 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, int delta; /* Non-retransmitted hole got filled? That's reordering */ - if (reord < prior_fackets && reord <= tp->fackets_out) - tcp_update_reordering(sk, tp->fackets_out - reord, 0); + if (before(reord, prior_fack)) + tcp_check_sack_reordering(sk, reord, 0); - delta = tcp_is_fack(tp) ? pkts_acked : - prior_sacked - tp->sacked_out; + delta = prior_sacked - tp->sacked_out; tp->lost_cnt_hint -= min(tp->lost_cnt_hint, delta); } - - tp->fackets_out -= min(pkts_acked, tp->fackets_out); - } else if (skb && rtt_update && sack_rtt_us >= 0 && sack_rtt_us > tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp)) { /* Do not re-arm RTO if the sack RTT is measured from data sent @@ -3247,18 +3190,19 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, } } #endif - *acked = pkts_acked; return flag; } static void tcp_ack_probe(struct sock *sk) { - const struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); + struct sk_buff *head = tcp_send_head(sk); + const struct tcp_sock *tp = tcp_sk(sk); /* Was it a usable window open? */ - - if (!after(TCP_SKB_CB(tcp_send_head(sk))->end_seq, tcp_wnd_end(tp))) { + if (!head) + return; + if (!after(TCP_SKB_CB(head)->end_seq, tcp_wnd_end(tp))) { icsk->icsk_backoff = 0; inet_csk_clear_xmit_timer(sk, ICSK_TIME_PROBE0); /* Socket must be waked up by subsequent tcp_data_snd_check(). @@ -3378,7 +3322,7 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 tp->pred_flags = 0; tcp_fast_path_check(sk); - if (tcp_send_head(sk)) + if (!tcp_write_queue_empty(sk)) tcp_slow_start_after_idle_check(sk); if (nwin > tp->max_window) { @@ -3399,7 +3343,7 @@ static bool __tcp_oow_rate_limited(struct net *net, int mib_idx, if (*last_oow_ack_time) { s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time); - if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { + if (0 <= elapsed && elapsed < net->ipv4.sysctl_tcp_invalid_ratelimit) { NET_INC_STATS(net, mib_idx); return true; /* rate-limited: don't send yet! */ } @@ -3435,10 +3379,11 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb) static u32 challenge_timestamp; static unsigned int challenge_count; struct tcp_sock *tp = tcp_sk(sk); + struct net *net = sock_net(sk); u32 count, now; /* First check our per-socket dupack rate limit. */ - if (__tcp_oow_rate_limited(sock_net(sk), + if (__tcp_oow_rate_limited(net, LINUX_MIB_TCPACKSKIPPEDCHALLENGE, &tp->last_oow_ack_time)) return; @@ -3446,16 +3391,16 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb) /* Then check host-wide RFC 5961 rate limit. */ now = jiffies / HZ; if (now != challenge_timestamp) { - u32 half = (sysctl_tcp_challenge_ack_limit + 1) >> 1; + u32 ack_limit = net->ipv4.sysctl_tcp_challenge_ack_limit; + u32 half = (ack_limit + 1) >> 1; challenge_timestamp = now; - WRITE_ONCE(challenge_count, half + - prandom_u32_max(sysctl_tcp_challenge_ack_limit)); + WRITE_ONCE(challenge_count, half + prandom_u32_max(ack_limit)); } count = READ_ONCE(challenge_count); if (count > 0) { WRITE_ONCE(challenge_count, count - 1); - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK); + NET_INC_STATS(net, LINUX_MIB_TCPCHALLENGEACK); tcp_send_ack(sk); } } @@ -3553,18 +3498,17 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) u32 ack_seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; bool is_dupack = false; - u32 prior_fackets; int prior_packets = tp->packets_out; u32 delivered = tp->delivered; u32 lost = tp->lost; - int acked = 0; /* Number of packets newly acked */ int rexmit = REXMIT_NONE; /* Flag to (re)transmit to recover losses */ + u32 prior_fack; sack_state.first_sackt = 0; sack_state.rate = &rs; - /* We very likely will need to access write queue head. */ - prefetchw(sk->sk_write_queue.next); + /* We very likely will need to access rtx queue. */ + prefetch(sk->tcp_rtx_queue.rb_node); /* If the ack is older than previous acks * then we can probably ignore it. @@ -3590,7 +3534,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) icsk->icsk_retransmits = 0; } - prior_fackets = tp->fackets_out; + prior_fack = tcp_is_sack(tp) ? tcp_highest_sack_seq(tp) : tp->snd_una; rs.prior_in_flight = tcp_packets_in_flight(tp); /* ts_recent update must be made after we are sure that the packet @@ -3646,8 +3590,9 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) goto no_queue; /* See if we can take anything off of the retransmit queue. */ - flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, &acked, - &sack_state); + flag |= tcp_clean_rtx_queue(sk, prior_fack, prior_snd_una, &sack_state); + + tcp_rack_update_reo_wnd(sk, &rs); if (tp->tlp_high_seq) tcp_process_tlp_ack(sk, ack, flag); @@ -3657,7 +3602,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (tcp_ack_is_dubious(sk, flag)) { is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); - tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit); + tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag, + &rexmit); } if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) @@ -3673,13 +3619,13 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) no_queue: /* If data was DSACKed, see if we can undo a cwnd reduction. */ if (flag & FLAG_DSACKING_ACK) - tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit); + tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag, + &rexmit); /* If this ack opens up a zero window, clear backoff. It was * being used to time the probes, and is probably far higher than * it needs to be for normal retransmission. */ - if (tcp_send_head(sk)) - tcp_ack_probe(sk); + tcp_ack_probe(sk); if (tp->tlp_high_seq) tcp_process_tlp_ack(sk, ack, flag); @@ -3696,7 +3642,8 @@ old_ack: if (TCP_SKB_CB(skb)->sacked) { flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una, &sack_state); - tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit); + tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag, + &rexmit); tcp_xmit_recovery(sk, rexmit); } @@ -3721,6 +3668,21 @@ static void tcp_parse_fastopen_option(int len, const unsigned char *cookie, foc->exp = exp_opt; } +static void smc_parse_options(const struct tcphdr *th, + struct tcp_options_received *opt_rx, + const unsigned char *ptr, + int opsize) +{ +#if IS_ENABLED(CONFIG_SMC) + if (static_branch_unlikely(&tcp_have_smc)) { + if (th->syn && !(opsize & 1) && + opsize >= TCPOLEN_EXP_SMC_BASE && + get_unaligned_be32(ptr) == TCPOPT_SMC_MAGIC) + opt_rx->smc_ok = 1; + } +#endif +} + /* Look for tcp options. Normally only called on SYN and SYNACK packets. * But, this can also be called on packets in the established flow when * the fast version below fails. @@ -3828,6 +3790,9 @@ void tcp_parse_options(const struct net *net, tcp_parse_fastopen_option(opsize - TCPOLEN_EXP_FASTOPEN_BASE, ptr + 2, th->syn, foc, true); + else + smc_parse_options(th, opt_rx, ptr, + opsize); break; } @@ -3995,6 +3960,8 @@ static inline bool tcp_sequence(const struct tcp_sock *tp, u32 seq, u32 end_seq) /* When we get a reset we do this. */ void tcp_reset(struct sock *sk) { + trace_tcp_receive_reset(sk); + /* We want the right error as BSD sees it (and indeed as we do). */ switch (sk->sk_state) { case TCP_SYN_SENT: @@ -4117,7 +4084,7 @@ static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq) { struct tcp_sock *tp = tcp_sk(sk); - if (tcp_is_sack(tp) && sysctl_tcp_dsack) { + if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) { int mib_idx; if (before(seq, tp->rcv_nxt)) @@ -4152,7 +4119,7 @@ static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb) NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST); tcp_enter_quickack_mode(sk); - if (tcp_is_sack(tp) && sysctl_tcp_dsack) { + if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) { u32 end_seq = TCP_SKB_CB(skb)->end_seq; if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) @@ -4268,11 +4235,6 @@ static void tcp_sack_remove(struct tcp_sock *tp) tp->rx_opt.num_sacks = num_sacks; } -enum tcp_queue { - OOO_QUEUE, - RCV_QUEUE, -}; - /** * tcp_try_coalesce - try to merge skb to prior one * @sk: socket @@ -4288,7 +4250,6 @@ enum tcp_queue { * Returns true if caller should free @from instead of queueing it */ static bool tcp_try_coalesce(struct sock *sk, - enum tcp_queue dest, struct sk_buff *to, struct sk_buff *from, bool *fragstolen) @@ -4313,10 +4274,7 @@ static bool tcp_try_coalesce(struct sock *sk, if (TCP_SKB_CB(from)->has_rxtstamp) { TCP_SKB_CB(to)->has_rxtstamp = true; - if (dest == OOO_QUEUE) - TCP_SKB_CB(to)->swtstamp = TCP_SKB_CB(from)->swtstamp; - else - to->tstamp = from->tstamp; + to->tstamp = from->tstamp; } return true; @@ -4341,7 +4299,7 @@ static void tcp_ofo_queue(struct sock *sk) p = rb_first(&tp->out_of_order_queue); while (p) { - skb = rb_entry(p, struct sk_buff, rbnode); + skb = rb_to_skb(p); if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) break; @@ -4353,9 +4311,6 @@ static void tcp_ofo_queue(struct sock *sk) } p = rb_next(p); rb_erase(&skb->rbnode, &tp->out_of_order_queue); - /* Replace tstamp which was stomped by rbnode */ - if (TCP_SKB_CB(skb)->has_rxtstamp) - skb->tstamp = TCP_SKB_CB(skb)->swtstamp; if (unlikely(!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))) { SOCK_DEBUG(sk, "ofo packet was already received\n"); @@ -4367,8 +4322,7 @@ static void tcp_ofo_queue(struct sock *sk) TCP_SKB_CB(skb)->end_seq); tail = skb_peek_tail(&sk->sk_receive_queue); - eaten = tail && tcp_try_coalesce(sk, RCV_QUEUE, - tail, skb, &fragstolen); + eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen); tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; if (!eaten) @@ -4409,7 +4363,7 @@ static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb, static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); - struct rb_node **p, *q, *parent; + struct rb_node **p, *parent; struct sk_buff *skb1; u32 seq, end_seq; bool fragstolen; @@ -4422,10 +4376,6 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) return; } - /* Stash tstamp to avoid being stomped on by rbnode */ - if (TCP_SKB_CB(skb)->has_rxtstamp) - TCP_SKB_CB(skb)->swtstamp = skb->tstamp; - /* Disable header prediction. */ tp->pred_flags = 0; inet_csk_schedule_ack(sk); @@ -4453,7 +4403,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) /* In the typical case, we are adding an skb to the end of the list. * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup. */ - if (tcp_try_coalesce(sk, OOO_QUEUE, tp->ooo_last_skb, + if (tcp_try_coalesce(sk, tp->ooo_last_skb, skb, &fragstolen)) { coalesce_done: tcp_grow_window(sk, skb); @@ -4472,7 +4422,7 @@ coalesce_done: parent = NULL; while (*p) { parent = *p; - skb1 = rb_entry(parent, struct sk_buff, rbnode); + skb1 = rb_to_skb(parent); if (before(seq, TCP_SKB_CB(skb1)->seq)) { p = &parent->rb_left; continue; @@ -4504,7 +4454,7 @@ coalesce_done: __kfree_skb(skb1); goto merge_right; } - } else if (tcp_try_coalesce(sk, OOO_QUEUE, skb1, + } else if (tcp_try_coalesce(sk, skb1, skb, &fragstolen)) { goto coalesce_done; } @@ -4517,9 +4467,7 @@ insert: merge_right: /* Remove other segments covered by skb. */ - while ((q = rb_next(&skb->rbnode)) != NULL) { - skb1 = rb_entry(q, struct sk_buff, rbnode); - + while ((skb1 = skb_rb_next(skb)) != NULL) { if (!after(end_seq, TCP_SKB_CB(skb1)->seq)) break; if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) { @@ -4534,7 +4482,7 @@ merge_right: tcp_drop(sk, skb1); } /* If there is no skb after us, we are the last_skb ! */ - if (!q) + if (!skb1) tp->ooo_last_skb = skb; add_sack: @@ -4556,7 +4504,7 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int __skb_pull(skb, hdrlen); eaten = (tail && - tcp_try_coalesce(sk, RCV_QUEUE, tail, + tcp_try_coalesce(sk, tail, skb, fragstolen)) ? 1 : 0; tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq); if (!eaten) { @@ -4720,7 +4668,7 @@ static struct sk_buff *tcp_skb_next(struct sk_buff *skb, struct sk_buff_head *li if (list) return !skb_queue_is_last(list, skb) ? skb->next : NULL; - return rb_entry_safe(rb_next(&skb->rbnode), struct sk_buff, rbnode); + return skb_rb_next(skb); } static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb, @@ -4741,7 +4689,7 @@ static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb, } /* Insert skb into rb tree, ordered by TCP_SKB_CB(skb)->seq */ -static void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb) +void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; @@ -4749,7 +4697,7 @@ static void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb) while (*p) { parent = *p; - skb1 = rb_entry(parent, struct sk_buff, rbnode); + skb1 = rb_to_skb(parent); if (before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb1)->seq)) p = &parent->rb_left; else @@ -4796,7 +4744,7 @@ restart: * overlaps to the next one. */ if (!(TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) && - (tcp_win_from_space(skb->truesize) > skb->len || + (tcp_win_from_space(sk, skb->truesize) > skb->len || before(TCP_SKB_CB(skb)->seq, start))) { end_of_skbs = false; break; @@ -4868,26 +4816,19 @@ static void tcp_collapse_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb, *head; - struct rb_node *p; u32 start, end; - p = rb_first(&tp->out_of_order_queue); - skb = rb_entry_safe(p, struct sk_buff, rbnode); + skb = skb_rb_first(&tp->out_of_order_queue); new_range: if (!skb) { - p = rb_last(&tp->out_of_order_queue); - /* Note: This is possible p is NULL here. We do not - * use rb_entry_safe(), as ooo_last_skb is valid only - * if rbtree is not empty. - */ - tp->ooo_last_skb = rb_entry(p, struct sk_buff, rbnode); + tp->ooo_last_skb = skb_rb_last(&tp->out_of_order_queue); return; } start = TCP_SKB_CB(skb)->seq; end = TCP_SKB_CB(skb)->end_seq; for (head = skb;;) { - skb = tcp_skb_next(skb, NULL); + skb = skb_rb_next(skb); /* Range is terminated when we see a gap or when * we are at the queue end. @@ -4930,14 +4871,14 @@ static bool tcp_prune_ofo_queue(struct sock *sk) do { prev = rb_prev(node); rb_erase(node, &tp->out_of_order_queue); - tcp_drop(sk, rb_entry(node, struct sk_buff, rbnode)); + tcp_drop(sk, rb_to_skb(node)); sk_mem_reclaim(sk); if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && !tcp_under_memory_pressure(sk)) break; node = prev; } while (node); - tp->ooo_last_skb = rb_entry(prev, struct sk_buff, rbnode); + tp->ooo_last_skb = rb_to_skb(prev); /* Reset SACK state. A conforming SACK implementation will * do the same at a timeout based retransmit. When a connection @@ -5112,7 +5053,7 @@ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th) struct tcp_sock *tp = tcp_sk(sk); u32 ptr = ntohs(th->urg_ptr); - if (ptr && !sysctl_tcp_stdurg) + if (ptr && !sock_net(sk)->ipv4.sysctl_tcp_stdurg) ptr--; ptr += ntohl(th->seq); @@ -5532,20 +5473,13 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) security_inet_conn_established(sk, skb); } - /* Make sure socket is routed, for correct metrics. */ - icsk->icsk_af_ops->rebuild_header(sk); - - tcp_init_metrics(sk); - tcp_call_bpf(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB); - tcp_init_congestion_control(sk); + tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB); /* Prevent spurious tcp_cwnd_restart() on first data * packet. */ tp->lsndtime = tcp_jiffies32; - tcp_init_buffer_space(sk); - if (sock_flag(sk, SOCK_KEEPOPEN)) inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tp)); @@ -5559,7 +5493,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, struct tcp_fastopen_cookie *cookie) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *data = tp->syn_data ? tcp_write_queue_head(sk) : NULL; + struct sk_buff *data = tp->syn_data ? tcp_rtx_queue_head(sk) : NULL; u16 mss = tp->rx_opt.mss_clamp, try_exp = 0; bool syn_drop = false; @@ -5594,9 +5528,8 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, tcp_fastopen_cache_set(sk, mss, cookie, syn_drop, try_exp); if (data) { /* Retransmit unacked data in SYN */ - tcp_for_write_queue_from(data, sk) { - if (data == tcp_send_head(sk) || - __tcp_retransmit_skb(sk, data, 1)) + skb_rbtree_walk_from(data) { + if (__tcp_retransmit_skb(sk, data, 1)) break; } tcp_rearm_rto(sk); @@ -5614,6 +5547,16 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, return false; } +static void smc_check_reset_syn(struct tcp_sock *tp) +{ +#if IS_ENABLED(CONFIG_SMC) + if (static_branch_unlikely(&tcp_have_smc)) { + if (tp->syn_smc && !tp->rx_opt.smc_ok) + tp->syn_smc = 0; + } +#endif +} + static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th) { @@ -5709,10 +5652,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, tp->tcp_header_len = sizeof(struct tcphdr); } - if (tcp_is_sack(tp) && sysctl_tcp_fack) - tcp_enable_fack(tp); - - tcp_mtup_init(sk); tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); tcp_initialize_rcv_mss(sk); @@ -5721,6 +5660,8 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, * is initialized. */ tp->copied_seq = tp->rcv_nxt; + smc_check_reset_syn(tp); + smp_mb(); tcp_finish_connect(sk, skb); @@ -5938,15 +5879,18 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) if (req) { inet_csk(sk)->icsk_retransmits = 0; reqsk_fastopen_remove(sk, req, false); + /* Re-arm the timer because data may have been sent out. + * This is similar to the regular data transmission case + * when new data has just been ack'ed. + * + * (TFO) - we could try to be more aggressive and + * retransmitting any data sooner based on when they + * are sent out. + */ + tcp_rearm_rto(sk); } else { - /* Make sure socket is routed, for correct metrics. */ - icsk->icsk_af_ops->rebuild_header(sk); - tcp_call_bpf(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); - tcp_init_congestion_control(sk); - - tcp_mtup_init(sk); + tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); tp->copied_seq = tp->rcv_nxt; - tcp_init_buffer_space(sk); } smp_mb(); tcp_set_state(sk, TCP_ESTABLISHED); @@ -5966,19 +5910,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) if (tp->rx_opt.tstamp_ok) tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; - if (req) { - /* Re-arm the timer because data may have been sent out. - * This is similar to the regular data transmission case - * when new data has just been ack'ed. - * - * (TFO) - we could try to be more aggressive and - * retransmitting any data sooner based on when they - * are sent out. - */ - tcp_rearm_rto(sk); - } else - tcp_init_metrics(sk); - if (!inet_csk(sk)->icsk_ca_ops->cong_control) tcp_update_pacing_rate(sk); @@ -6075,6 +6006,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) case TCP_LAST_ACK: if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) break; + /* fall through */ case TCP_FIN_WAIT1: case TCP_FIN_WAIT2: /* RFC 793 says to queue data in these states, @@ -6183,6 +6115,9 @@ static void tcp_openreq_init(struct request_sock *req, ireq->ir_rmt_port = tcp_hdr(skb)->source; ireq->ir_num = ntohs(tcp_hdr(skb)->dest); ireq->ir_mark = inet_request_mark(sk, skb); +#if IS_ENABLED(CONFIG_SMC) + ireq->smc_ok = rx_opt->smc_ok; +#endif } struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, @@ -6195,7 +6130,6 @@ struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, if (req) { struct inet_request_sock *ireq = inet_rsk(req); - kmemcheck_annotate_bitfield(ireq, flags); ireq->ireq_opt = NULL; #if IS_ENABLED(CONFIG_IPV6) ireq->pktopts = NULL; @@ -6358,7 +6292,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_openreq_init_rwin(req, sk, dst); if (!want_cookie) { tcp_reqsk_record_syn(sk, req, skb); - fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc); + fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc, dst); } if (fastopen_sk) { af_ops->send_synack(fastopen_sk, dst, &fl, req, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5b027c69cbc5..c6bc0c4d19c6 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -85,6 +85,8 @@ #include <crypto/hash.h> #include <linux/scatterlist.h> +#include <trace/events/tcp.h> + #ifdef CONFIG_TCP_MD5SIG static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, __be32 daddr, __be32 saddr, const struct tcphdr *th); @@ -480,7 +482,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) TCP_TIMEOUT_INIT; icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX); - skb = tcp_write_queue_head(sk); + skb = tcp_rtx_queue_head(sk); BUG_ON(!skb); tcp_mstamp_refresh(tp); @@ -701,8 +703,10 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) * routing might fail in this case. No choice here, if we choose to force * input interface, we will misroute in case of asymmetric route. */ - if (sk) + if (sk) { arg.bound_dev_if = sk->sk_bound_dev_if; + trace_tcp_send_reset(sk, skb); + } BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) != offsetof(struct inet_timewait_sock, tw_bound_dev_if)); @@ -1783,8 +1787,9 @@ do_time_wait: refcounted = false; goto process; } - /* Fall through to ACK */ } + /* to ACK */ + /* fall through */ case TCP_TW_ACK: tcp_v4_timewait_ack(sk, skb); break; @@ -1864,6 +1869,8 @@ void tcp_v4_destroy_sock(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + trace_tcp_destroy_sock(sk); + tcp_clear_xmit_timers(sk); tcp_cleanup_congestion_control(sk); @@ -1896,6 +1903,7 @@ void tcp_v4_destroy_sock(struct sock *sk) /* If socket is aborted during connect operation */ tcp_free_fastopen_req(tp); + tcp_fastopen_destroy_cipher(sk); tcp_saved_syn_free(tp); sk_sockets_allocated_dec(sk); @@ -2401,8 +2409,8 @@ struct proto tcp_prot = { .memory_allocated = &tcp_memory_allocated, .memory_pressure = &tcp_memory_pressure, .sysctl_mem = sysctl_tcp_mem, - .sysctl_wmem = sysctl_tcp_wmem, - .sysctl_rmem = sysctl_tcp_rmem, + .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem), + .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem), .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp_sock), .slab_flags = SLAB_TYPESAFE_BY_RCU, @@ -2422,6 +2430,8 @@ static void __net_exit tcp_sk_exit(struct net *net) { int cpu; + module_put(net->ipv4.tcp_congestion_control->owner); + for_each_possible_cpu(cpu) inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu)); free_percpu(net->ipv4.tcp_sk); @@ -2476,6 +2486,50 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_sack = 1; net->ipv4.sysctl_tcp_window_scaling = 1; net->ipv4.sysctl_tcp_timestamps = 1; + net->ipv4.sysctl_tcp_early_retrans = 3; + net->ipv4.sysctl_tcp_recovery = TCP_RACK_LOSS_DETECTION; + net->ipv4.sysctl_tcp_slow_start_after_idle = 1; /* By default, RFC2861 behavior. */ + net->ipv4.sysctl_tcp_retrans_collapse = 1; + net->ipv4.sysctl_tcp_max_reordering = 300; + net->ipv4.sysctl_tcp_dsack = 1; + net->ipv4.sysctl_tcp_app_win = 31; + net->ipv4.sysctl_tcp_adv_win_scale = 1; + net->ipv4.sysctl_tcp_frto = 2; + net->ipv4.sysctl_tcp_moderate_rcvbuf = 1; + /* This limits the percentage of the congestion window which we + * will allow a single TSO frame to consume. Building TSO frames + * which are too large can cause TCP streams to be bursty. + */ + net->ipv4.sysctl_tcp_tso_win_divisor = 3; + /* Default TSQ limit of four TSO segments */ + net->ipv4.sysctl_tcp_limit_output_bytes = 262144; + /* rfc5961 challenge ack rate limiting */ + net->ipv4.sysctl_tcp_challenge_ack_limit = 1000; + net->ipv4.sysctl_tcp_min_tso_segs = 2; + net->ipv4.sysctl_tcp_min_rtt_wlen = 300; + net->ipv4.sysctl_tcp_autocorking = 1; + net->ipv4.sysctl_tcp_invalid_ratelimit = HZ/2; + net->ipv4.sysctl_tcp_pacing_ss_ratio = 200; + net->ipv4.sysctl_tcp_pacing_ca_ratio = 120; + if (net != &init_net) { + memcpy(net->ipv4.sysctl_tcp_rmem, + init_net.ipv4.sysctl_tcp_rmem, + sizeof(init_net.ipv4.sysctl_tcp_rmem)); + memcpy(net->ipv4.sysctl_tcp_wmem, + init_net.ipv4.sysctl_tcp_wmem, + sizeof(init_net.ipv4.sysctl_tcp_wmem)); + } + net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE; + spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock); + net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 60 * 60; + atomic_set(&net->ipv4.tfo_active_disable_times, 0); + + /* Reno is always built in */ + if (!net_eq(net, &init_net) && + try_module_get(init_net.ipv4.tcp_congestion_control->owner)) + net->ipv4.tcp_congestion_control = init_net.ipv4.tcp_congestion_control; + else + net->ipv4.tcp_congestion_control = &tcp_reno; return 0; fail: @@ -2486,7 +2540,12 @@ fail: static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) { + struct net *net; + inet_twsk_purge(&tcp_hashinfo, AF_INET); + + list_for_each_entry(net, net_exit_list, exit_list) + tcp_fastopen_ctx_destroy(net); } static struct pernet_operations __net_initdata tcp_sk_ops = { diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 0f0d740f6c8b..7097f92d16e5 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -21,8 +21,6 @@ #include <net/tcp.h> #include <net/genetlink.h> -int sysctl_tcp_nometrics_save __read_mostly; - static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *saddr, const struct inetpeer_addr *daddr, struct net *net, unsigned int hash); @@ -331,7 +329,7 @@ void tcp_update_metrics(struct sock *sk) int m; sk_dst_confirm(sk); - if (sysctl_tcp_nometrics_save || !dst) + if (net->ipv4.sysctl_tcp_nometrics_save || !dst) return; rcu_read_lock(); @@ -472,10 +470,8 @@ void tcp_init_metrics(struct sock *sk) tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; } val = tcp_metric_get(tm, TCP_METRIC_REORDERING); - if (val && tp->reordering != val) { - tcp_disable_fack(tp); + if (val && tp->reordering != val) tp->reordering = val; - } crtt = tcp_metric_get(tm, TCP_METRIC_RTT); rcu_read_unlock(); @@ -893,10 +889,14 @@ static void tcp_metrics_flush_all(struct net *net) for (row = 0; row < max_rows; row++, hb++) { struct tcp_metrics_block __rcu **pp; + bool match; + spin_lock_bh(&tcp_metrics_lock); pp = &hb->chain; for (tm = deref_locked(*pp); tm; tm = deref_locked(*pp)) { - if (net_eq(tm_net(tm), net)) { + match = net ? net_eq(tm_net(tm), net) : + !atomic_read(&tm_net(tm)->count); + if (match) { *pp = tm->tcpm_next; kfree_rcu(tm, rcu_head); } else { @@ -1019,14 +1019,14 @@ static int __net_init tcp_net_metrics_init(struct net *net) return 0; } -static void __net_exit tcp_net_metrics_exit(struct net *net) +static void __net_exit tcp_net_metrics_exit_batch(struct list_head *net_exit_list) { - tcp_metrics_flush_all(net); + tcp_metrics_flush_all(NULL); } static __net_initdata struct pernet_operations tcp_net_metrics_ops = { - .init = tcp_net_metrics_init, - .exit = tcp_net_metrics_exit, + .init = tcp_net_metrics_init, + .exit_batch = tcp_net_metrics_exit_batch, }; void __init tcp_metrics_init(void) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 188a6f31356d..e36eff0403f4 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -23,13 +23,12 @@ #include <linux/slab.h> #include <linux/sysctl.h> #include <linux/workqueue.h> +#include <linux/static_key.h> #include <net/tcp.h> #include <net/inet_common.h> #include <net/xfrm.h> #include <net/busy_poll.h> -int sysctl_tcp_abort_on_overflow __read_mostly; - static bool tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win) { if (seq == s_win) @@ -180,7 +179,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, * Oh well... nobody has a sufficient solution to this * protocol bug yet. */ - if (sysctl_tcp_rfc1337 == 0) { + if (twsk_net(tw)->ipv4.sysctl_tcp_rfc1337 == 0) { kill: inet_twsk_deschedule_put(tw); return TCP_TW_SUCCESS; @@ -298,8 +297,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) key = tp->af_specific->md5_lookup(sk, sk); if (key) { tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC); - if (tcptw->tw_md5_key && !tcp_alloc_md5sig_pool()) - BUG(); + BUG_ON(tcptw->tw_md5_key && !tcp_alloc_md5sig_pool()); } } while (0); #endif @@ -371,7 +369,7 @@ void tcp_openreq_init_rwin(struct request_sock *req, full_space = rcv_wnd * mss; /* tcp_full_space because it is guaranteed to be the first packet */ - tcp_select_initial_window(full_space, + tcp_select_initial_window(sk_listener, full_space, mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0), &req->rsk_rcv_wnd, &req->rsk_window_clamp, @@ -417,6 +415,21 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst) } EXPORT_SYMBOL_GPL(tcp_ca_openreq_child); +static void smc_check_reset_syn_req(struct tcp_sock *oldtp, + struct request_sock *req, + struct tcp_sock *newtp) +{ +#if IS_ENABLED(CONFIG_SMC) + struct inet_request_sock *ireq; + + if (static_branch_unlikely(&tcp_have_smc)) { + ireq = inet_rsk(req); + if (oldtp->syn_smc && !ireq->smc_ok) + newtp->syn_smc = 0; + } +#endif +} + /* This is not only more efficient than what we used to do, it eliminates * a lot of code duplication between IPv4/IPv6 SYN recv processing. -DaveM * @@ -434,6 +447,9 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, struct tcp_request_sock *treq = tcp_rsk(req); struct inet_connection_sock *newicsk = inet_csk(newsk); struct tcp_sock *newtp = tcp_sk(newsk); + struct tcp_sock *oldtp = tcp_sk(sk); + + smc_check_reset_syn_req(oldtp, req, newtp); /* Now setup tcp_sock */ newtp->pred_flags = 0; @@ -446,6 +462,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1; INIT_LIST_HEAD(&newtp->tsq_node); + INIT_LIST_HEAD(&newtp->tsorted_sent_queue); tcp_init_wl(newtp, treq->rcv_isn); @@ -458,7 +475,6 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->packets_out = 0; newtp->retrans_out = 0; newtp->sacked_out = 0; - newtp->fackets_out = 0; newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH; newtp->tlp_high_seq = 0; newtp->lsndtime = tcp_jiffies32; @@ -492,10 +508,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, keepalive_time_when(newtp)); newtp->rx_opt.tstamp_ok = ireq->tstamp_ok; - if ((newtp->rx_opt.sack_ok = ireq->sack_ok) != 0) { - if (sysctl_tcp_fack) - tcp_enable_fack(newtp); - } + newtp->rx_opt.sack_ok = ireq->sack_ok; newtp->window_clamp = req->rsk_window_clamp; newtp->rcv_ssthresh = req->rsk_rcv_wnd; newtp->rcv_wnd = req->rsk_rcv_wnd; @@ -534,6 +547,10 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->syn_data_acked = 0; newtp->rack.mstamp = 0; newtp->rack.advanced = 0; + newtp->rack.reo_wnd_steps = 1; + newtp->rack.last_delivered = 0; + newtp->rack.reo_wnd_persist = 0; + newtp->rack.dsack_seen = 0; __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); } @@ -764,7 +781,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, return inet_csk_complete_hashdance(sk, child, req, own_req); listen_overflow: - if (!sysctl_tcp_abort_on_overflow) { + if (!sock_net(sk)->ipv4.sysctl_tcp_abort_on_overflow) { inet_rsk(req)->acked = 1; return NULL; } diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c index 125fc1450b01..0b5a05bd82e3 100644 --- a/net/ipv4/tcp_nv.c +++ b/net/ipv4/tcp_nv.c @@ -39,7 +39,7 @@ * nv_cong_dec_mult Decrease cwnd by X% (30%) of congestion when detected * nv_ssthresh_factor On congestion set ssthresh to this * <desired cwnd> / 8 * nv_rtt_factor RTT averaging factor - * nv_loss_dec_factor Decrease cwnd by this (50%) when losses occur + * nv_loss_dec_factor Decrease cwnd to this (80%) when losses occur * nv_dec_eval_min_calls Wait this many RTT measurements before dec cwnd * nv_inc_eval_min_calls Wait this many RTT measurements before inc cwnd * nv_ssthresh_eval_min_calls Wait this many RTT measurements before stopping @@ -61,7 +61,7 @@ static int nv_min_cwnd __read_mostly = 2; static int nv_cong_dec_mult __read_mostly = 30 * 128 / 100; /* = 30% */ static int nv_ssthresh_factor __read_mostly = 8; /* = 1 */ static int nv_rtt_factor __read_mostly = 128; /* = 1/2*old + 1/2*new */ -static int nv_loss_dec_factor __read_mostly = 512; /* => 50% */ +static int nv_loss_dec_factor __read_mostly = 819; /* => 80% */ static int nv_cwnd_growth_rate_neg __read_mostly = 8; static int nv_cwnd_growth_rate_pos __read_mostly; /* 0 => fixed like Reno */ static int nv_dec_eval_min_calls __read_mostly = 60; @@ -101,6 +101,11 @@ struct tcpnv { u32 nv_last_rtt; /* last rtt */ u32 nv_min_rtt; /* active min rtt. Used to determine slope */ u32 nv_min_rtt_new; /* min rtt for future use */ + u32 nv_base_rtt; /* If non-zero it represents the threshold for + * congestion */ + u32 nv_lower_bound_rtt; /* Used in conjunction with nv_base_rtt. It is + * set to 80% of nv_base_rtt. It helps reduce + * unfairness between flows */ u32 nv_rtt_max_rate; /* max rate seen during current RTT */ u32 nv_rtt_start_seq; /* current RTT ends when packet arrives * acking beyond nv_rtt_start_seq */ @@ -132,9 +137,24 @@ static inline void tcpnv_reset(struct tcpnv *ca, struct sock *sk) static void tcpnv_init(struct sock *sk) { struct tcpnv *ca = inet_csk_ca(sk); + int base_rtt; tcpnv_reset(ca, sk); + /* See if base_rtt is available from socket_ops bpf program. + * It is meant to be used in environments, such as communication + * within a datacenter, where we have reasonable estimates of + * RTTs + */ + base_rtt = tcp_call_bpf(sk, BPF_SOCK_OPS_BASE_RTT); + if (base_rtt > 0) { + ca->nv_base_rtt = base_rtt; + ca->nv_lower_bound_rtt = (base_rtt * 205) >> 8; /* 80% */ + } else { + ca->nv_base_rtt = 0; + ca->nv_lower_bound_rtt = 0; + } + ca->nv_allow_cwnd_growth = 1; ca->nv_min_rtt_reset_jiffies = jiffies + 2 * HZ; ca->nv_min_rtt = NV_INIT_RTT; @@ -144,6 +164,19 @@ static void tcpnv_init(struct sock *sk) ca->cwnd_growth_factor = 0; } +/* If provided, apply upper (base_rtt) and lower (lower_bound_rtt) + * bounds to RTT. + */ +inline u32 nv_get_bounded_rtt(struct tcpnv *ca, u32 val) +{ + if (ca->nv_lower_bound_rtt > 0 && val < ca->nv_lower_bound_rtt) + return ca->nv_lower_bound_rtt; + else if (ca->nv_base_rtt > 0 && val > ca->nv_base_rtt) + return ca->nv_base_rtt; + else + return val; +} + static void tcpnv_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); @@ -209,7 +242,7 @@ static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample) struct tcp_sock *tp = tcp_sk(sk); struct tcpnv *ca = inet_csk_ca(sk); unsigned long now = jiffies; - s64 rate64 = 0; + u64 rate64; u32 rate, max_win, cwnd_by_slope; u32 avg_rtt; u32 bytes_acked = 0; @@ -251,8 +284,9 @@ static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample) } /* rate in 100's bits per second */ - rate64 = ((u64)sample->in_flight) * 8000000; - rate = (u32)div64_u64(rate64, (u64)(avg_rtt ?: 1) * 100); + rate64 = ((u64)sample->in_flight) * 80000; + do_div(rate64, avg_rtt ?: 1); + rate = (u32)rate64; /* Remember the maximum rate seen during this RTT * Note: It may be more than one RTT. This function should be @@ -265,6 +299,9 @@ static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample) if (ca->nv_eval_call_cnt < 255) ca->nv_eval_call_cnt++; + /* Apply bounds to rtt. Only used to update min_rtt */ + avg_rtt = nv_get_bounded_rtt(ca, avg_rtt); + /* update min rtt if necessary */ if (avg_rtt < ca->nv_min_rtt) ca->nv_min_rtt = avg_rtt; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 478909f4694d..540b7d92cc70 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -41,40 +41,25 @@ #include <linux/compiler.h> #include <linux/gfp.h> #include <linux/module.h> +#include <linux/static_key.h> -/* People can turn this off for buggy TCP's found in printers etc. */ -int sysctl_tcp_retrans_collapse __read_mostly = 1; - -/* People can turn this on to work with those rare, broken TCPs that - * interpret the window field as a signed quantity. - */ -int sysctl_tcp_workaround_signed_windows __read_mostly = 0; - -/* Default TSQ limit of four TSO segments */ -int sysctl_tcp_limit_output_bytes __read_mostly = 262144; - -/* This limits the percentage of the congestion window which we - * will allow a single TSO frame to consume. Building TSO frames - * which are too large can cause TCP streams to be bursty. - */ -int sysctl_tcp_tso_win_divisor __read_mostly = 3; - -/* By default, RFC2861 behavior. */ -int sysctl_tcp_slow_start_after_idle __read_mostly = 1; +#include <trace/events/tcp.h> static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, int push_one, gfp_t gfp); /* Account for new data that has been sent to the network. */ -static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb) +static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); unsigned int prior_packets = tp->packets_out; - tcp_advance_send_head(sk, skb); tp->snd_nxt = TCP_SKB_CB(skb)->end_seq; + __skb_unlink(skb, &sk->sk_write_queue); + tcp_rbtree_insert(&sk->tcp_rtx_queue, skb); + tp->packets_out += tcp_skb_pcount(skb); if (!prior_packets || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk); @@ -203,7 +188,7 @@ u32 tcp_default_init_rwnd(u32 mss) * be a multiple of mss if possible. We assume here that mss >= 1. * This MUST be enforced by all callers. */ -void tcp_select_initial_window(int __space, __u32 mss, +void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, __u32 *rcv_wnd, __u32 *window_clamp, int wscale_ok, __u8 *rcv_wscale, __u32 init_rcv_wnd) @@ -227,7 +212,7 @@ void tcp_select_initial_window(int __space, __u32 mss, * which we interpret as a sign the remote TCP is not * misinterpreting the window field as a signed quantity. */ - if (sysctl_tcp_workaround_signed_windows) + if (sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows) (*rcv_wnd) = min(space, MAX_TCP_WINDOW); else (*rcv_wnd) = space; @@ -235,7 +220,7 @@ void tcp_select_initial_window(int __space, __u32 mss, (*rcv_wscale) = 0; if (wscale_ok) { /* Set window scaling on max possible window */ - space = max_t(u32, space, sysctl_tcp_rmem[2]); + space = max_t(u32, space, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]); space = max_t(u32, space, sysctl_rmem_max); space = min_t(u32, space, *window_clamp); while (space > U16_MAX && (*rcv_wscale) < TCP_MAX_WSCALE) { @@ -287,7 +272,8 @@ static u16 tcp_select_window(struct sock *sk) /* Make sure we do not exceed the maximum possible * scaled window. */ - if (!tp->rx_opt.rcv_wscale && sysctl_tcp_workaround_signed_windows) + if (!tp->rx_opt.rcv_wscale && + sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows) new_win = min(new_win, MAX_TCP_WINDOW); else new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale)); @@ -395,7 +381,6 @@ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb, static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags) { skb->ip_summed = CHECKSUM_PARTIAL; - skb->csum = 0; TCP_SKB_CB(skb)->tcp_flags = flags; TCP_SKB_CB(skb)->sacked = 0; @@ -418,6 +403,22 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp) #define OPTION_MD5 (1 << 2) #define OPTION_WSCALE (1 << 3) #define OPTION_FAST_OPEN_COOKIE (1 << 8) +#define OPTION_SMC (1 << 9) + +static void smc_options_write(__be32 *ptr, u16 *options) +{ +#if IS_ENABLED(CONFIG_SMC) + if (static_branch_unlikely(&tcp_have_smc)) { + if (unlikely(OPTION_SMC & *options)) { + *ptr++ = htonl((TCPOPT_NOP << 24) | + (TCPOPT_NOP << 16) | + (TCPOPT_EXP << 8) | + (TCPOLEN_EXP_SMC_BASE)); + *ptr++ = htonl(TCPOPT_SMC_MAGIC); + } + } +#endif +} struct tcp_out_options { u16 options; /* bit field of OPTION_* */ @@ -536,6 +537,41 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, } ptr += (len + 3) >> 2; } + + smc_options_write(ptr, &options); +} + +static void smc_set_option(const struct tcp_sock *tp, + struct tcp_out_options *opts, + unsigned int *remaining) +{ +#if IS_ENABLED(CONFIG_SMC) + if (static_branch_unlikely(&tcp_have_smc)) { + if (tp->syn_smc) { + if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) { + opts->options |= OPTION_SMC; + *remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED; + } + } + } +#endif +} + +static void smc_set_option_cond(const struct tcp_sock *tp, + const struct inet_request_sock *ireq, + struct tcp_out_options *opts, + unsigned int *remaining) +{ +#if IS_ENABLED(CONFIG_SMC) + if (static_branch_unlikely(&tcp_have_smc)) { + if (tp->syn_smc && ireq->smc_ok) { + if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) { + opts->options |= OPTION_SMC; + *remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED; + } + } + } +#endif } /* Compute TCP options for SYN packets. This is not the final @@ -603,11 +639,14 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, } } + smc_set_option(tp, opts, &remaining); + return MAX_TCP_OPTION_SPACE - remaining; } /* Set up TCP options for SYN-ACKs. */ -static unsigned int tcp_synack_options(struct request_sock *req, +static unsigned int tcp_synack_options(const struct sock *sk, + struct request_sock *req, unsigned int mss, struct sk_buff *skb, struct tcp_out_options *opts, const struct tcp_md5sig_key *md5, @@ -663,6 +702,8 @@ static unsigned int tcp_synack_options(struct request_sock *req, } } + smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining); + return MAX_TCP_OPTION_SPACE - remaining; } @@ -973,6 +1014,12 @@ static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb) HRTIMER_MODE_ABS_PINNED); } +static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb) +{ + skb->skb_mstamp = tp->tcp_mstamp; + list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue); +} + /* This routine actually transmits TCP packets queued in by * tcp_do_sendmsg(). This is used by both the initial * transmission and possible later retransmissions. @@ -1005,10 +1052,14 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq - tp->snd_una; oskb = skb; - if (unlikely(skb_cloned(skb))) - skb = pskb_copy(skb, gfp_mask); - else - skb = skb_clone(skb, gfp_mask); + + tcp_skb_tsorted_save(oskb) { + if (unlikely(skb_cloned(oskb))) + skb = pskb_copy(oskb, gfp_mask); + else + skb = skb_clone(oskb, gfp_mask); + } tcp_skb_tsorted_restore(oskb); + if (unlikely(!skb)) return -ENOBUFS; } @@ -1129,7 +1180,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, err = net_xmit_eval(err); } if (!err && oskb) { - oskb->skb_mstamp = tp->tcp_mstamp; + tcp_update_skb_after_send(tp, oskb); tcp_rate_skb_sent(sk, oskb); } return err; @@ -1167,21 +1218,6 @@ static void tcp_set_skb_tso_segs(struct sk_buff *skb, unsigned int mss_now) } } -/* When a modification to fackets out becomes necessary, we need to check - * skb is counted to fackets_out or not. - */ -static void tcp_adjust_fackets_out(struct sock *sk, const struct sk_buff *skb, - int decr) -{ - struct tcp_sock *tp = tcp_sk(sk); - - if (!tp->sacked_out || tcp_is_reno(tp)) - return; - - if (after(tcp_highest_sack_seq(tp), TCP_SKB_CB(skb)->seq)) - tp->fackets_out -= decr; -} - /* Pcount in the middle of the write queue got changed, we need to do various * tweaks to fix counters */ @@ -1202,11 +1238,9 @@ static void tcp_adjust_pcount(struct sock *sk, const struct sk_buff *skb, int de if (tcp_is_reno(tp) && decr > 0) tp->sacked_out -= min_t(u32, tp->sacked_out, decr); - tcp_adjust_fackets_out(sk, skb, decr); - if (tp->lost_skb_hint && before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->lost_skb_hint)->seq) && - (tcp_is_fack(tp) || (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))) + (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) tp->lost_cnt_hint -= decr; tcp_verify_left_out(tp); @@ -1241,12 +1275,25 @@ static void tcp_skb_fragment_eor(struct sk_buff *skb, struct sk_buff *skb2) TCP_SKB_CB(skb)->eor = 0; } +/* Insert buff after skb on the write or rtx queue of sk. */ +static void tcp_insert_write_queue_after(struct sk_buff *skb, + struct sk_buff *buff, + struct sock *sk, + enum tcp_queue tcp_queue) +{ + if (tcp_queue == TCP_FRAG_IN_WRITE_QUEUE) + __skb_queue_after(&sk->sk_write_queue, skb, buff); + else + tcp_rbtree_insert(&sk->tcp_rtx_queue, buff); +} + /* Function to create two new TCP segments. Shrinks the given segment * to the specified size and appends a new segment with the rest of the * packet to the list. This won't be called frequently, I hope. * Remember, these are still headerless SKBs at this point. */ -int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, +int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, + struct sk_buff *skb, u32 len, unsigned int mss_now, gfp_t gfp) { struct tcp_sock *tp = tcp_sk(sk); @@ -1329,7 +1376,9 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, /* Link BUFF into the send queue. */ __skb_header_release(buff); - tcp_insert_write_queue_after(skb, buff, sk); + tcp_insert_write_queue_after(skb, buff, sk, tcp_queue); + if (tcp_queue == TCP_FRAG_IN_RTX_QUEUE) + list_add(&buff->tcp_tsorted_anchor, &skb->tcp_tsorted_anchor); return 0; } @@ -1607,7 +1656,7 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) if (tp->packets_out > tp->snd_cwnd_used) tp->snd_cwnd_used = tp->packets_out; - if (sysctl_tcp_slow_start_after_idle && + if (sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle && (s32)(tcp_jiffies32 - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto && !ca_ops->cong_control) tcp_cwnd_application_limited(sk); @@ -1616,10 +1665,10 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) * is caused by insufficient sender buffer: * 1) just sent some data (see tcp_write_xmit) * 2) not cwnd limited (this else condition) - * 3) no more data to send (null tcp_send_head ) + * 3) no more data to send (tcp_write_queue_empty()) * 4) application is hitting buffer limit (SOCK_NOSPACE) */ - if (!tcp_send_head(sk) && sk->sk_socket && + if (tcp_write_queue_empty(sk) && sk->sk_socket && test_bit(SOCK_NOSPACE, &sk->sk_socket->flags) && (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) tcp_chrono_start(sk, TCP_CHRONO_SNDBUF_LIMITED); @@ -1671,7 +1720,7 @@ u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, { u32 bytes, segs; - bytes = min(sk->sk_pacing_rate >> 10, + bytes = min(sk->sk_pacing_rate >> sk->sk_pacing_shift, sk->sk_gso_max_size - 1 - MAX_TCP_HEADER); /* Goal is to send at least one packet per ms, @@ -1694,7 +1743,8 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now) u32 tso_segs = ca_ops->tso_segs_goal ? ca_ops->tso_segs_goal(sk) : 0; return tso_segs ? : - tcp_tso_autosize(sk, mss_now, sysctl_tcp_min_tso_segs); + tcp_tso_autosize(sk, mss_now, + sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs); } /* Returns the portion of skb which can be sent right away */ @@ -1815,7 +1865,8 @@ static bool tcp_snd_wnd_test(const struct tcp_sock *tp, * know that all the data is in scatter-gather pages, and that the * packet has never been sent out before (and thus is not cloned). */ -static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, +static int tso_fragment(struct sock *sk, enum tcp_queue tcp_queue, + struct sk_buff *skb, unsigned int len, unsigned int mss_now, gfp_t gfp) { struct sk_buff *buff; @@ -1824,7 +1875,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, /* All of a TSO frame must be composed of paged data. */ if (skb->len != skb->data_len) - return tcp_fragment(sk, skb, len, mss_now, gfp); + return tcp_fragment(sk, tcp_queue, skb, len, mss_now, gfp); buff = sk_stream_alloc_skb(sk, 0, gfp, true); if (unlikely(!buff)) @@ -1860,7 +1911,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, /* Link BUFF into the send queue. */ __skb_header_release(buff); - tcp_insert_write_queue_after(skb, buff, sk); + tcp_insert_write_queue_after(skb, buff, sk, tcp_queue); return 0; } @@ -1910,7 +1961,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len)) goto send_now; - win_divisor = ACCESS_ONCE(sysctl_tcp_tso_win_divisor); + win_divisor = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_win_divisor); if (win_divisor) { u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache); @@ -1930,8 +1981,10 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, goto send_now; } - head = tcp_write_queue_head(sk); - + /* TODO : use tsorted_sent_queue ? */ + head = tcp_rtx_queue_head(sk); + if (!head) + goto send_now; age = tcp_stamp_us_delta(tp->tcp_mstamp, head->skb_mstamp); /* If next ACK is likely to come too late (half srtt), do not defer */ if (age < (tp->srtt_us >> 4)) @@ -2145,18 +2198,18 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, { unsigned int limit; - limit = max(2 * skb->truesize, sk->sk_pacing_rate >> 10); - limit = min_t(u32, limit, sysctl_tcp_limit_output_bytes); + limit = max(2 * skb->truesize, sk->sk_pacing_rate >> sk->sk_pacing_shift); + limit = min_t(u32, limit, + sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes); limit <<= factor; if (refcount_read(&sk->sk_wmem_alloc) > limit) { - /* Always send the 1st or 2nd skb in write queue. + /* Always send skb if rtx queue is empty. * No need to wait for TX completion to call us back, * after softirq/tasklet schedule. * This helps when TX completions are delayed too much. */ - if (skb == sk->sk_write_queue.next || - skb->prev == sk->sk_write_queue.next) + if (tcp_rtx_queue_empty(sk)) return false; set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); @@ -2207,7 +2260,7 @@ void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type) * it's the "most interesting" or current chrono we are * tracking and starts busy chrono if we have pending data. */ - if (tcp_write_queue_empty(sk)) + if (tcp_rtx_and_write_queues_empty(sk)) tcp_chrono_set(tp, TCP_CHRONO_UNSPEC); else if (type == tp->chrono_type) tcp_chrono_set(tp, TCP_CHRONO_BUSY); @@ -2263,7 +2316,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) { /* "skb_mstamp" is used as a start point for the retransmit timer */ - skb->skb_mstamp = tp->tcp_mstamp; + tcp_update_skb_after_send(tp, skb); goto repair; /* Skip network transmission */ } @@ -2302,7 +2355,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, nonagle); if (skb->len > limit && - unlikely(tso_fragment(sk, skb, limit, mss_now, gfp))) + unlikely(tso_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE, + skb, limit, mss_now, gfp))) break; if (test_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags)) @@ -2342,7 +2396,7 @@ repair: tcp_cwnd_validate(sk, is_cwnd_limited); return false; } - return !tp->packets_out && tcp_send_head(sk); + return !tp->packets_out && !tcp_write_queue_empty(sk); } bool tcp_schedule_loss_probe(struct sock *sk) @@ -2350,6 +2404,7 @@ bool tcp_schedule_loss_probe(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); u32 timeout, rto_delta_us; + int early_retrans; /* Don't do any loss probe on a Fast Open connection before 3WHS * finishes. @@ -2357,16 +2412,17 @@ bool tcp_schedule_loss_probe(struct sock *sk) if (tp->fastopen_rsk) return false; + early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans; /* Schedule a loss probe in 2*RTT for SACK capable connections * in Open state, that are either limited by cwnd or application. */ - if ((sysctl_tcp_early_retrans != 3 && sysctl_tcp_early_retrans != 4) || + if ((early_retrans != 3 && early_retrans != 4) || !tp->packets_out || !tcp_is_sack(tp) || icsk->icsk_ca_state != TCP_CA_Open) return false; if ((tp->snd_cwnd > tcp_packets_in_flight(tp)) && - tcp_send_head(sk)) + !tcp_write_queue_empty(sk)) return false; /* Probe timeout is 2*rtt. Add minimum RTO to account @@ -2419,18 +2475,14 @@ void tcp_send_loss_probe(struct sock *sk) int mss = tcp_current_mss(sk); skb = tcp_send_head(sk); - if (skb) { - if (tcp_snd_wnd_test(tp, skb, mss)) { - pcount = tp->packets_out; - tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC); - if (tp->packets_out > pcount) - goto probe_sent; - goto rearm_timer; - } - skb = tcp_write_queue_prev(sk, skb); - } else { - skb = tcp_write_queue_tail(sk); + if (skb && tcp_snd_wnd_test(tp, skb, mss)) { + pcount = tp->packets_out; + tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC); + if (tp->packets_out > pcount) + goto probe_sent; + goto rearm_timer; } + skb = skb_rb_last(&sk->tcp_rtx_queue); /* At most one outstanding TLP retransmission. */ if (tp->tlp_high_seq) @@ -2448,10 +2500,11 @@ void tcp_send_loss_probe(struct sock *sk) goto rearm_timer; if ((pcount > 1) && (skb->len > (pcount - 1) * mss)) { - if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss, + if (unlikely(tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, + (pcount - 1) * mss, mss, GFP_ATOMIC))) goto rearm_timer; - skb = tcp_write_queue_next(sk, skb); + skb = skb_rb_next(skb); } if (WARN_ON(!skb || !tcp_skb_pcount(skb))) @@ -2651,7 +2704,7 @@ void tcp_skb_collapse_tstamp(struct sk_buff *skb, static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *next_skb = tcp_write_queue_next(sk, skb); + struct sk_buff *next_skb = skb_rb_next(skb); int skb_size, next_skb_size; skb_size = skb->len; @@ -2668,8 +2721,6 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) } tcp_highest_sack_replace(sk, next_skb, skb); - tcp_unlink_write_queue(next_skb, sk); - if (next_skb->ip_summed == CHECKSUM_PARTIAL) skb->ip_summed = CHECKSUM_PARTIAL; @@ -2697,7 +2748,7 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) tcp_skb_collapse_tstamp(skb, next_skb); - sk_wmem_free_skb(sk, next_skb); + tcp_rtx_queue_unlink_and_free(next_skb, sk); return true; } @@ -2708,8 +2759,6 @@ static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb) return false; if (skb_cloned(skb)) return false; - if (skb == tcp_send_head(sk)) - return false; /* Some heuristics for collapsing over SACK'd could be invented */ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) return false; @@ -2727,12 +2776,12 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, struct sk_buff *skb = to, *tmp; bool first = true; - if (!sysctl_tcp_retrans_collapse) + if (!sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse) return; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) return; - tcp_for_write_queue_from_safe(skb, tmp, sk) { + skb_rbtree_walk_from_safe(skb, tmp) { if (!tcp_can_collapse(sk, skb)) break; @@ -2807,7 +2856,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) len = cur_mss * segs; if (skb->len > len) { - if (tcp_fragment(sk, skb, len, cur_mss, GFP_ATOMIC)) + if (tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, len, + cur_mss, GFP_ATOMIC)) return -ENOMEM; /* We'll try again later. */ } else { if (skb_unclone(skb, GFP_ATOMIC)) @@ -2841,11 +2891,14 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) skb_headroom(skb) >= 0xFFFF)) { struct sk_buff *nskb; - nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); - err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : - -ENOBUFS; + tcp_skb_tsorted_save(skb) { + nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); + err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : + -ENOBUFS; + } tcp_skb_tsorted_restore(skb); + if (!err) { - skb->skb_mstamp = tp->tcp_mstamp; + tcp_update_skb_after_send(tp, skb); tcp_rate_skb_sent(sk, skb); } } else { @@ -2854,6 +2907,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) if (likely(!err)) { TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; + trace_tcp_retransmit_skb(sk, skb); } else if (err != -EBUSY) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL); } @@ -2890,36 +2944,25 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) * retransmitted data is acknowledged. It tries to continue * resending the rest of the retransmit queue, until either * we've sent it all or the congestion window limit is reached. - * If doing SACK, the first ACK which comes back for a timeout - * based retransmit packet might feed us FACK information again. - * If so, we use it to avoid unnecessarily retransmissions. */ void tcp_xmit_retransmit_queue(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); + struct sk_buff *skb, *rtx_head, *hole = NULL; struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; - struct sk_buff *hole = NULL; u32 max_segs; int mib_idx; if (!tp->packets_out) return; - if (tp->retransmit_skb_hint) { - skb = tp->retransmit_skb_hint; - } else { - skb = tcp_write_queue_head(sk); - } - + rtx_head = tcp_rtx_queue_head(sk); + skb = tp->retransmit_skb_hint ?: rtx_head; max_segs = tcp_tso_segs(sk, tcp_current_mss(sk)); - tcp_for_write_queue_from(skb, sk) { + skb_rbtree_walk_from(skb) { __u8 sacked; int segs; - if (skb == tcp_send_head(sk)) - break; - if (tcp_pacing_check(sk)) break; @@ -2964,7 +3007,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk) if (tcp_in_cwnd_reduction(sk)) tp->prr_out += tcp_skb_pcount(skb); - if (skb == tcp_write_queue_head(sk) && + if (skb == rtx_head && icsk->icsk_pending != ICSK_TIME_REO_TIMEOUT) inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, inet_csk(sk)->icsk_rto, @@ -3006,12 +3049,15 @@ void tcp_send_fin(struct sock *sk) * Note: in the latter case, FIN packet will be sent after a timeout, * as TCP stack thinks it has already been transmitted. */ - if (tskb && (tcp_send_head(sk) || tcp_under_memory_pressure(sk))) { + if (!tskb && tcp_under_memory_pressure(sk)) + tskb = skb_rb_last(&sk->tcp_rtx_queue); + + if (tskb) { coalesce: TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; TCP_SKB_CB(tskb)->end_seq++; tp->write_seq++; - if (!tcp_send_head(sk)) { + if (tcp_write_queue_empty(sk)) { /* This means tskb was already sent. * Pretend we included the FIN on previous transmit. * We need to set tp->snd_nxt to the value it would have @@ -3028,6 +3074,7 @@ coalesce: goto coalesce; return; } + INIT_LIST_HEAD(&skb->tcp_tsorted_anchor); skb_reserve(skb, MAX_TCP_HEADER); sk_forced_mem_schedule(sk, skb->truesize); /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ @@ -3064,6 +3111,11 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority) /* Send it off. */ if (tcp_transmit_skb(sk, skb, 0, priority)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); + + /* skb of trace_tcp_send_reset() keeps the skb that caused RST, + * skb here is different to the troublesome skb, so use NULL + */ + trace_tcp_send_reset(sk, NULL); } /* Send a crossed SYN-ACK during socket establishment. @@ -3076,20 +3128,24 @@ int tcp_send_synack(struct sock *sk) { struct sk_buff *skb; - skb = tcp_write_queue_head(sk); + skb = tcp_rtx_queue_head(sk); if (!skb || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { - pr_debug("%s: wrong queue state\n", __func__); + pr_err("%s: wrong queue state\n", __func__); return -EFAULT; } if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)) { if (skb_cloned(skb)) { - struct sk_buff *nskb = skb_copy(skb, GFP_ATOMIC); + struct sk_buff *nskb; + + tcp_skb_tsorted_save(skb) { + nskb = skb_copy(skb, GFP_ATOMIC); + } tcp_skb_tsorted_restore(skb); if (!nskb) return -ENOMEM; - tcp_unlink_write_queue(skb, sk); + INIT_LIST_HEAD(&nskb->tcp_tsorted_anchor); + tcp_rtx_queue_unlink_and_free(skb, sk); __skb_header_release(nskb); - __tcp_add_write_queue_head(sk, nskb); - sk_wmem_free_skb(sk, skb); + tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb); sk->sk_wmem_queued += nskb->truesize; sk_mem_charge(sk, nskb->truesize); skb = nskb; @@ -3166,8 +3222,8 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req)); #endif skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4); - tcp_header_size = tcp_synack_options(req, mss, skb, &opts, md5, foc) + - sizeof(*th); + tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, + foc) + sizeof(*th); skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); @@ -3268,7 +3324,7 @@ static void tcp_connect_init(struct sock *sk) if (rcv_wnd == 0) rcv_wnd = dst_metric(dst, RTAX_INITRWND); - tcp_select_initial_window(tcp_full_space(sk), + tcp_select_initial_window(sk, tcp_full_space(sk), tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0), &tp->rcv_wnd, &tp->window_clamp, @@ -3307,7 +3363,6 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb) tcb->end_seq += skb->len; __skb_header_release(skb); - __tcp_add_write_queue_tail(sk, skb); sk->sk_wmem_queued += skb->truesize; sk_mem_charge(sk, skb->truesize); tp->write_seq = tcb->end_seq; @@ -3355,6 +3410,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) int copied = copy_from_iter(skb_put(syn_data, space), space, &fo->data->msg_iter); if (unlikely(!copied)) { + tcp_skb_tsorted_anchor_cleanup(syn_data); kfree_skb(syn_data); goto fallback; } @@ -3385,12 +3441,13 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) TCP_SKB_CB(syn_data)->tcp_flags = TCPHDR_ACK | TCPHDR_PSH; if (!err) { tp->syn_data = (fo->copied > 0); + tcp_rbtree_insert(&sk->tcp_rtx_queue, syn_data); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT); goto done; } - /* data was not sent, this is our new send_head */ - sk->sk_send_head = syn_data; + /* data was not sent, put it in write_queue */ + __skb_queue_tail(&sk->sk_write_queue, syn_data); tp->packets_out -= tcp_skb_pcount(syn_data); fallback: @@ -3433,6 +3490,7 @@ int tcp_connect(struct sock *sk) tp->retrans_stamp = tcp_time_stamp(tp); tcp_connect_queue_skb(sk, buff); tcp_ecn_send_syn(sk, buff); + tcp_rbtree_insert(&sk->tcp_rtx_queue, buff); /* Send off SYN; include data in Fast Open. */ err = tp->fastopen_req ? tcp_send_syn_data(sk, buff) : @@ -3627,7 +3685,8 @@ int tcp_write_wakeup(struct sock *sk, int mib) skb->len > mss) { seg_size = min(seg_size, mss); TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; - if (tcp_fragment(sk, skb, seg_size, mss, GFP_ATOMIC)) + if (tcp_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE, + skb, seg_size, mss, GFP_ATOMIC)) return -1; } else if (!tcp_skb_pcount(skb)) tcp_set_skb_tso_segs(skb, mss); @@ -3657,7 +3716,7 @@ void tcp_send_probe0(struct sock *sk) err = tcp_write_wakeup(sk, LINUX_MIB_TCPWINPROBE); - if (tp->packets_out || !tcp_send_head(sk)) { + if (tp->packets_out || tcp_write_queue_empty(sk)) { /* Cancel probe timer, if it is not required. */ icsk->icsk_probes_out = 0; icsk->icsk_backoff = 0; @@ -3698,6 +3757,7 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); if (unlikely(tcp_passive_fastopen(sk))) tcp_sk(sk)->total_retrans++; + trace_tcp_retransmit_synack(sk, req); } return res; } diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index be8ef1e5dfef..d3ea89020c69 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -2,8 +2,6 @@ #include <linux/tcp.h> #include <net/tcp.h> -int sysctl_tcp_recovery __read_mostly = TCP_RACK_LOSS_DETECTION; - static void tcp_rack_mark_skb_lost(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); @@ -46,7 +44,8 @@ static bool tcp_rack_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; + u32 min_rtt = tcp_min_rtt(tp); + struct sk_buff *skb, *n; u32 reo_wnd; *reo_timeout = 0; @@ -56,48 +55,36 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout) * to queuing or delayed ACKs. */ reo_wnd = 1000; - if ((tp->rack.reord || !tp->lost_out) && tcp_min_rtt(tp) != ~0U) - reo_wnd = max(tcp_min_rtt(tp) >> 2, reo_wnd); + if ((tp->rack.reord || !tp->lost_out) && min_rtt != ~0U) { + reo_wnd = max((min_rtt >> 2) * tp->rack.reo_wnd_steps, reo_wnd); + reo_wnd = min(reo_wnd, tp->srtt_us >> 3); + } - tcp_for_write_queue(skb, sk) { + list_for_each_entry_safe(skb, n, &tp->tsorted_sent_queue, + tcp_tsorted_anchor) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb); + s32 remaining; - if (skb == tcp_send_head(sk)) - break; - - /* Skip ones already (s)acked */ - if (!after(scb->end_seq, tp->snd_una) || - scb->sacked & TCPCB_SACKED_ACKED) + /* Skip ones marked lost but not yet retransmitted */ + if ((scb->sacked & TCPCB_LOST) && + !(scb->sacked & TCPCB_SACKED_RETRANS)) continue; - if (tcp_rack_sent_after(tp->rack.mstamp, skb->skb_mstamp, - tp->rack.end_seq, scb->end_seq)) { - /* Step 3 in draft-cheng-tcpm-rack-00.txt: - * A packet is lost if its elapsed time is beyond - * the recent RTT plus the reordering window. - */ - u32 elapsed = tcp_stamp_us_delta(tp->tcp_mstamp, - skb->skb_mstamp); - s32 remaining = tp->rack.rtt_us + reo_wnd - elapsed; - - if (remaining < 0) { - tcp_rack_mark_skb_lost(sk, skb); - continue; - } - - /* Skip ones marked lost but not yet retransmitted */ - if ((scb->sacked & TCPCB_LOST) && - !(scb->sacked & TCPCB_SACKED_RETRANS)) - continue; + if (!tcp_rack_sent_after(tp->rack.mstamp, skb->skb_mstamp, + tp->rack.end_seq, scb->end_seq)) + break; + /* A packet is lost if it has not been s/acked beyond + * the recent RTT plus the reordering window. + */ + remaining = tp->rack.rtt_us + reo_wnd - + tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp); + if (remaining < 0) { + tcp_rack_mark_skb_lost(sk, skb); + list_del_init(&skb->tcp_tsorted_anchor); + } else { /* Record maximum wait time (+1 to avoid 0) */ *reo_timeout = max_t(u32, *reo_timeout, 1 + remaining); - - } else if (!(scb->sacked & TCPCB_RETRANS)) { - /* Original data are sent sequentially so stop early - * b/c the rest are all sent after rack_sent - */ - break; } } } @@ -176,3 +163,44 @@ void tcp_rack_reo_timeout(struct sock *sk) if (inet_csk(sk)->icsk_pending != ICSK_TIME_RETRANS) tcp_rearm_rto(sk); } + +/* Updates the RACK's reo_wnd based on DSACK and no. of recoveries. + * + * If DSACK is received, increment reo_wnd by min_rtt/4 (upper bounded + * by srtt), since there is possibility that spurious retransmission was + * due to reordering delay longer than reo_wnd. + * + * Persist the current reo_wnd value for TCP_RACK_RECOVERY_THRESH (16) + * no. of successful recoveries (accounts for full DSACK-based loss + * recovery undo). After that, reset it to default (min_rtt/4). + * + * At max, reo_wnd is incremented only once per rtt. So that the new + * DSACK on which we are reacting, is due to the spurious retx (approx) + * after the reo_wnd has been updated last time. + * + * reo_wnd is tracked in terms of steps (of min_rtt/4), rather than + * absolute value to account for change in rtt. + */ +void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_STATIC_REO_WND || + !rs->prior_delivered) + return; + + /* Disregard DSACK if a rtt has not passed since we adjusted reo_wnd */ + if (before(rs->prior_delivered, tp->rack.last_delivered)) + tp->rack.dsack_seen = 0; + + /* Adjust the reo_wnd if update is pending */ + if (tp->rack.dsack_seen) { + tp->rack.reo_wnd_steps = min_t(u32, 0xFF, + tp->rack.reo_wnd_steps + 1); + tp->rack.dsack_seen = 0; + tp->rack.last_delivered = tp->delivered; + tp->rack.reo_wnd_persist = TCP_RACK_RECOVERY_THRESH; + } else if (!tp->rack.reo_wnd_persist) { + tp->rack.reo_wnd_steps = 1; + } +} diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 655dd8d7f064..16df6dd44b98 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -22,8 +22,6 @@ #include <linux/gfp.h> #include <net/tcp.h> -int sysctl_tcp_thin_linear_timeouts __read_mostly; - /** * tcp_write_err() - close socket and save error info * @sk: The socket the error has appeared on. @@ -109,26 +107,23 @@ static int tcp_orphan_retries(struct sock *sk, bool alive) static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) { - struct net *net = sock_net(sk); + const struct net *net = sock_net(sk); + int mss; /* Black hole detection */ - if (net->ipv4.sysctl_tcp_mtu_probing) { - if (!icsk->icsk_mtup.enabled) { - icsk->icsk_mtup.enabled = 1; - icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; - tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); - } else { - struct net *net = sock_net(sk); - struct tcp_sock *tp = tcp_sk(sk); - int mss; - - mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1; - mss = min(net->ipv4.sysctl_tcp_base_mss, mss); - mss = max(mss, 68 - tp->tcp_header_len); - icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); - tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); - } + if (!net->ipv4.sysctl_tcp_mtu_probing) + return; + + if (!icsk->icsk_mtup.enabled) { + icsk->icsk_mtup.enabled = 1; + icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; + } else { + mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1; + mss = min(net->ipv4.sysctl_tcp_base_mss, mss); + mss = max(mss, 68 - tcp_sk(sk)->tcp_header_len); + icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); } + tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); } @@ -156,8 +151,13 @@ static bool retransmits_timed_out(struct sock *sk, return false; start_ts = tcp_sk(sk)->retrans_stamp; - if (unlikely(!start_ts)) - start_ts = tcp_skb_timestamp(tcp_write_queue_head(sk)); + if (unlikely(!start_ts)) { + struct sk_buff *head = tcp_rtx_queue_head(sk); + + if (!head) + return false; + start_ts = tcp_skb_timestamp(head); + } if (likely(timeout == 0)) { linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base); @@ -283,15 +283,17 @@ out: * * Returns: Nothing (void) */ -static void tcp_delack_timer(unsigned long data) +static void tcp_delack_timer(struct timer_list *t) { - struct sock *sk = (struct sock *)data; + struct inet_connection_sock *icsk = + from_timer(icsk, t, icsk_delack_timer); + struct sock *sk = &icsk->icsk_inet.sk; bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { tcp_delack_timer_handler(sk); } else { - inet_csk(sk)->icsk_ack.blocked = 1; + icsk->icsk_ack.blocked = 1; __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED); /* deleguate our work to tcp_release_cb() */ if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &sk->sk_tsq_flags)) @@ -304,11 +306,12 @@ static void tcp_delack_timer(unsigned long data) static void tcp_probe_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); + struct sk_buff *skb = tcp_send_head(sk); struct tcp_sock *tp = tcp_sk(sk); int max_probes; u32 start_ts; - if (tp->packets_out || !tcp_send_head(sk)) { + if (tp->packets_out || !skb) { icsk->icsk_probes_out = 0; return; } @@ -321,9 +324,9 @@ static void tcp_probe_timer(struct sock *sk) * corresponding system limit. We also implement similar policy when * we use RTO to probe window in tcp_retransmit_timer(). */ - start_ts = tcp_skb_timestamp(tcp_send_head(sk)); + start_ts = tcp_skb_timestamp(skb); if (!start_ts) - tcp_send_head(sk)->skb_mstamp = tp->tcp_mstamp; + skb->skb_mstamp = tp->tcp_mstamp; else if (icsk->icsk_user_timeout && (s32)(tcp_time_stamp(tp) - start_ts) > jiffies_to_msecs(icsk->icsk_user_timeout)) @@ -408,7 +411,7 @@ void tcp_retransmit_timer(struct sock *sk) if (!tp->packets_out) goto out; - WARN_ON(tcp_write_queue_empty(sk)); + WARN_ON(tcp_rtx_queue_empty(sk)); tp->tlp_high_seq = 0; @@ -441,7 +444,7 @@ void tcp_retransmit_timer(struct sock *sk) goto out; } tcp_enter_loss(sk); - tcp_retransmit_skb(sk, tcp_write_queue_head(sk), 1); + tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1); __sk_dst_reset(sk); goto out_reset_timer; } @@ -473,7 +476,7 @@ void tcp_retransmit_timer(struct sock *sk) tcp_enter_loss(sk); - if (tcp_retransmit_skb(sk, tcp_write_queue_head(sk), 1) > 0) { + if (tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1) > 0) { /* Retransmission failed because of local congestion, * do not backoff. */ @@ -514,7 +517,7 @@ out_reset_timer: * linear-timeout retransmissions into a black hole */ if (sk->sk_state == TCP_ESTABLISHED && - (tp->thin_lto || sysctl_tcp_thin_linear_timeouts) && + (tp->thin_lto || net->ipv4.sysctl_tcp_thin_linear_timeouts) && tcp_stream_is_thin(tp) && icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) { icsk->icsk_backoff = 0; @@ -570,9 +573,11 @@ out: sk_mem_reclaim(sk); } -static void tcp_write_timer(unsigned long data) +static void tcp_write_timer(struct timer_list *t) { - struct sock *sk = (struct sock *)data; + struct inet_connection_sock *icsk = + from_timer(icsk, t, icsk_retransmit_timer); + struct sock *sk = &icsk->icsk_inet.sk; bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { @@ -607,9 +612,9 @@ void tcp_set_keepalive(struct sock *sk, int val) EXPORT_SYMBOL_GPL(tcp_set_keepalive); -static void tcp_keepalive_timer (unsigned long data) +static void tcp_keepalive_timer (struct timer_list *t) { - struct sock *sk = (struct sock *) data; + struct sock *sk = from_timer(sk, t, sk_timer); struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); u32 elapsed; @@ -647,7 +652,7 @@ static void tcp_keepalive_timer (unsigned long data) elapsed = keepalive_time_when(tp); /* It is alive without keepalive 8) */ - if (tp->packets_out || tcp_send_head(sk)) + if (tp->packets_out || !tcp_write_queue_empty(sk)) goto resched; elapsed = keepalive_time_elapsed(tp); diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index 218cfcc77650..ee113ff15fd0 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -158,7 +158,7 @@ EXPORT_SYMBOL_GPL(tcp_vegas_cwnd_event); static inline u32 tcp_vegas_ssthresh(struct tcp_sock *tp) { - return min(tp->snd_ssthresh, tp->snd_cwnd-1); + return min(tp->snd_ssthresh, tp->snd_cwnd); } static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ebfbccae62fd..e4ff25c947c5 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1209,8 +1209,7 @@ static void udp_rmem_release(struct sock *sk, int size, int partial, if (likely(partial)) { up->forward_deficit += size; size = up->forward_deficit; - if (size < (sk->sk_rcvbuf >> 2) && - !skb_queue_empty(&up->reader_queue)) + if (size < (sk->sk_rcvbuf >> 2)) return; } else { size += up->forward_deficit; @@ -1853,7 +1852,7 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) */ /* if we're overly short, let UDP handle it */ - encap_rcv = ACCESS_ONCE(up->encap_rcv); + encap_rcv = READ_ONCE(up->encap_rcv); if (encap_rcv) { int ret; @@ -2298,7 +2297,7 @@ void udp_destroy_sock(struct sock *sk) unlock_sock_fast(sk, slow); if (static_key_false(&udp_encap_needed) && up->encap_type) { void (*encap_destroy)(struct sock *sk); - encap_destroy = ACCESS_ONCE(up->encap_destroy); + encap_destroy = READ_ONCE(up->encap_destroy); if (encap_destroy) encap_destroy(sk); } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 8a1c846d3df9..a0ae1c9d37df 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -152,11 +152,13 @@ static void ipv6_regen_rndid(struct inet6_dev *idev); static void ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr); static int ipv6_generate_eui64(u8 *eui, struct net_device *dev); -static int ipv6_count_addresses(struct inet6_dev *idev); +static int ipv6_count_addresses(const struct inet6_dev *idev); static int ipv6_generate_stable_address(struct in6_addr *addr, u8 dad_count, const struct inet6_dev *idev); +#define IN6_ADDR_HSIZE_SHIFT 8 +#define IN6_ADDR_HSIZE (1 << IN6_ADDR_HSIZE_SHIFT) /* * Configured unicast address hash table */ @@ -192,8 +194,6 @@ static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa); static void inet6_prefix_notify(int event, struct inet6_dev *idev, struct prefix_info *pinfo); -static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, - struct net_device *dev); static struct ipv6_devconf ipv6_devconf __read_mostly = { .forwarding = 0, @@ -231,7 +231,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .proxy_ndp = 0, .accept_source_route = 0, /* we do not accept RH0 by default. */ .disable_ipv6 = 0, - .accept_dad = 1, + .accept_dad = 0, .suppress_frag_ndisc = 1, .accept_ra_mtu = 1, .stable_secret = { @@ -303,10 +303,10 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .disable_policy = 0, }; -/* Check if a valid qdisc is available */ -static inline bool addrconf_qdisc_ok(const struct net_device *dev) +/* Check if link is ready: is it up and is a valid qdisc available */ +static inline bool addrconf_link_ready(const struct net_device *dev) { - return !qdisc_tx_is_noop(dev); + return netif_oper_up(dev) && !qdisc_tx_is_noop(dev); } static void addrconf_del_rs_timer(struct inet6_dev *idev) @@ -451,7 +451,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) ndev->token = in6addr_any; - if (netif_running(dev) && addrconf_qdisc_ok(dev)) + if (netif_running(dev) && addrconf_link_ready(dev)) ndev->if_flags |= IF_READY; ipv6_mc_init_dev(ndev); @@ -616,23 +616,23 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[NETCONFA_MAX+1]; + struct inet6_dev *in6_dev = NULL; + struct net_device *dev = NULL; struct netconfmsg *ncm; struct sk_buff *skb; struct ipv6_devconf *devconf; - struct inet6_dev *in6_dev; - struct net_device *dev; int ifindex; int err; err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX, devconf_ipv6_policy, extack); if (err < 0) - goto errout; + return err; - err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) - goto errout; + return -EINVAL; + err = -EINVAL; ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); switch (ifindex) { case NETCONFA_IFINDEX_ALL: @@ -642,10 +642,10 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, devconf = net->ipv6.devconf_dflt; break; default: - dev = __dev_get_by_index(net, ifindex); + dev = dev_get_by_index(net, ifindex); if (!dev) - goto errout; - in6_dev = __in6_dev_get(dev); + return -EINVAL; + in6_dev = in6_dev_get(dev); if (!in6_dev) goto errout; devconf = &in6_dev->cnf; @@ -653,7 +653,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, } err = -ENOBUFS; - skb = nlmsg_new(inet6_netconf_msgsize_devconf(NETCONFA_ALL), GFP_ATOMIC); + skb = nlmsg_new(inet6_netconf_msgsize_devconf(NETCONFA_ALL), GFP_KERNEL); if (!skb) goto errout; @@ -669,6 +669,10 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: + if (in6_dev) + in6_dev_put(in6_dev); + if (dev) + dev_put(dev); return err; } @@ -945,12 +949,50 @@ ipv6_link_dev_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp) break; } - list_add_tail(&ifp->if_list, p); + list_add_tail_rcu(&ifp->if_list, p); } -static u32 inet6_addr_hash(const struct in6_addr *addr) +static u32 inet6_addr_hash(const struct net *net, const struct in6_addr *addr) { - return hash_32(ipv6_addr_hash(addr), IN6_ADDR_HSIZE_SHIFT); + u32 val = ipv6_addr_hash(addr) ^ net_hash_mix(net); + + return hash_32(val, IN6_ADDR_HSIZE_SHIFT); +} + +static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, + struct net_device *dev, unsigned int hash) +{ + struct inet6_ifaddr *ifp; + + hlist_for_each_entry(ifp, &inet6_addr_lst[hash], addr_lst) { + if (!net_eq(dev_net(ifp->idev->dev), net)) + continue; + if (ipv6_addr_equal(&ifp->addr, addr)) { + if (!dev || ifp->idev->dev == dev) + return true; + } + } + return false; +} + +static int ipv6_add_addr_hash(struct net_device *dev, struct inet6_ifaddr *ifa) +{ + unsigned int hash = inet6_addr_hash(dev_net(dev), &ifa->addr); + int err = 0; + + spin_lock(&addrconf_hash_lock); + + /* Ignore adding duplicate addresses on an interface */ + if (ipv6_chk_same_addr(dev_net(dev), &ifa->addr, dev, hash)) { + ADBG("ipv6_add_addr: already assigned\n"); + err = -EEXIST; + } else { + hlist_add_head_rcu(&ifa->addr_lst, &inet6_addr_lst[hash]); + } + + spin_unlock(&addrconf_hash_lock); + + return err; } /* On success it returns ifp with increased reference count */ @@ -958,13 +1000,13 @@ static u32 inet6_addr_hash(const struct in6_addr *addr) static struct inet6_ifaddr * ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, const struct in6_addr *peer_addr, int pfxlen, - int scope, u32 flags, u32 valid_lft, u32 prefered_lft) + int scope, u32 flags, u32 valid_lft, u32 prefered_lft, + bool can_block, struct netlink_ext_ack *extack) { + gfp_t gfp_flags = can_block ? GFP_KERNEL : GFP_ATOMIC; struct net *net = dev_net(idev->dev); struct inet6_ifaddr *ifa = NULL; - struct rt6_info *rt; - struct in6_validator_info i6vi; - unsigned int hash; + struct rt6_info *rt = NULL; int err = 0; int addr_type = ipv6_addr_type(addr); @@ -974,42 +1016,33 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, addr_type & IPV6_ADDR_LOOPBACK)) return ERR_PTR(-EADDRNOTAVAIL); - rcu_read_lock_bh(); - - in6_dev_hold(idev); - if (idev->dead) { err = -ENODEV; /*XXX*/ - goto out2; + goto out; } if (idev->cnf.disable_ipv6) { err = -EACCES; - goto out2; - } - - i6vi.i6vi_addr = *addr; - i6vi.i6vi_dev = idev; - rcu_read_unlock_bh(); - - err = inet6addr_validator_notifier_call_chain(NETDEV_UP, &i6vi); - - rcu_read_lock_bh(); - err = notifier_to_errno(err); - if (err) - goto out2; - - spin_lock(&addrconf_hash_lock); - - /* Ignore adding duplicate addresses on an interface */ - if (ipv6_chk_same_addr(dev_net(idev->dev), addr, idev->dev)) { - ADBG("ipv6_add_addr: already assigned\n"); - err = -EEXIST; goto out; } - ifa = kzalloc(sizeof(struct inet6_ifaddr), GFP_ATOMIC); + /* validator notifier needs to be blocking; + * do not call in atomic context + */ + if (can_block) { + struct in6_validator_info i6vi = { + .i6vi_addr = *addr, + .i6vi_dev = idev, + .extack = extack, + }; + + err = inet6addr_validator_notifier_call_chain(NETDEV_UP, &i6vi); + err = notifier_to_errno(err); + if (err < 0) + goto out; + } + ifa = kzalloc(sizeof(*ifa), gfp_flags); if (!ifa) { ADBG("ipv6_add_addr: malloc failed\n"); err = -ENOBUFS; @@ -1019,6 +1052,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, rt = addrconf_dst_alloc(idev, addr, false); if (IS_ERR(rt)) { err = PTR_ERR(rt); + rt = NULL; goto out; } @@ -1049,16 +1083,21 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, ifa->rt = rt; ifa->idev = idev; + in6_dev_hold(idev); + /* For caller */ refcount_set(&ifa->refcnt, 1); - /* Add to big hash table */ - hash = inet6_addr_hash(addr); + rcu_read_lock_bh(); - hlist_add_head_rcu(&ifa->addr_lst, &inet6_addr_lst[hash]); - spin_unlock(&addrconf_hash_lock); + err = ipv6_add_addr_hash(idev->dev, ifa); + if (err < 0) { + rcu_read_unlock_bh(); + goto out; + } write_lock(&idev->lock); + /* Add to inet6_dev unicast addr list. */ ipv6_link_dev_addr(idev, ifa); @@ -1069,21 +1108,23 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, in6_ifa_hold(ifa); write_unlock(&idev->lock); -out2: + rcu_read_unlock_bh(); - if (likely(err == 0)) - inet6addr_notifier_call_chain(NETDEV_UP, ifa); - else { - kfree(ifa); - in6_dev_put(idev); + inet6addr_notifier_call_chain(NETDEV_UP, ifa); +out: + if (unlikely(err < 0)) { + if (rt) + ip6_rt_put(rt); + if (ifa) { + if (ifa->idev) + in6_dev_put(ifa->idev); + kfree(ifa); + } ifa = ERR_PTR(err); } return ifa; -out: - spin_unlock(&addrconf_hash_lock); - goto out2; } enum cleanup_prefix_rt_t { @@ -1204,7 +1245,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) if (ifp->flags & IFA_F_PERMANENT && !(ifp->flags & IFA_F_NOPREFIXROUTE)) action = check_cleanup_prefix_route(ifp, &expires); - list_del_init(&ifp->if_list); + list_del_rcu(&ifp->if_list); __in6_ifa_put(ifp); write_unlock_bh(&ifp->idev->lock); @@ -1226,7 +1267,9 @@ out: in6_ifa_put(ifp); } -static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, struct inet6_ifaddr *ift) +static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, + struct inet6_ifaddr *ift, + bool block) { struct inet6_dev *idev = ifp->idev; struct in6_addr addr, *tmpaddr; @@ -1330,7 +1373,7 @@ retry: ift = ipv6_add_addr(idev, &addr, NULL, tmp_plen, ipv6_addr_scope(&addr), addr_flags, - tmp_valid_lft, tmp_prefered_lft); + tmp_valid_lft, tmp_prefered_lft, block, NULL); if (IS_ERR(ift)) { in6_ifa_put(ifp); in6_dev_put(idev); @@ -1558,8 +1601,7 @@ static int __ipv6_dev_get_saddr(struct net *net, { struct ipv6_saddr_score *score = &scores[1 - hiscore_idx], *hiscore = &scores[hiscore_idx]; - read_lock_bh(&idev->lock); - list_for_each_entry(score->ifa, &idev->addr_list, if_list) { + list_for_each_entry_rcu(score->ifa, &idev->addr_list, if_list) { int i; /* @@ -1609,11 +1651,6 @@ static int __ipv6_dev_get_saddr(struct net *net, } break; } else if (minihiscore < miniscore) { - if (hiscore->ifa) - in6_ifa_put(hiscore->ifa); - - in6_ifa_hold(score->ifa); - swap(hiscore, score); hiscore_idx = 1 - hiscore_idx; @@ -1625,7 +1662,6 @@ static int __ipv6_dev_get_saddr(struct net *net, } } out: - read_unlock_bh(&idev->lock); return hiscore_idx; } @@ -1662,6 +1698,7 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, int dst_type; bool use_oif_addr = false; int hiscore_idx = 0; + int ret = 0; dst_type = __ipv6_addr_type(daddr); dst.addr = daddr; @@ -1737,15 +1774,14 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, } out: - rcu_read_unlock(); - hiscore = &scores[hiscore_idx]; if (!hiscore->ifa) - return -EADDRNOTAVAIL; + ret = -EADDRNOTAVAIL; + else + *saddr = hiscore->ifa->addr; - *saddr = hiscore->ifa->addr; - in6_ifa_put(hiscore->ifa); - return 0; + rcu_read_unlock(); + return ret; } EXPORT_SYMBOL(ipv6_dev_get_saddr); @@ -1785,15 +1821,15 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, return err; } -static int ipv6_count_addresses(struct inet6_dev *idev) +static int ipv6_count_addresses(const struct inet6_dev *idev) { + const struct inet6_ifaddr *ifp; int cnt = 0; - struct inet6_ifaddr *ifp; - read_lock_bh(&idev->lock); - list_for_each_entry(ifp, &idev->addr_list, if_list) + rcu_read_lock(); + list_for_each_entry_rcu(ifp, &idev->addr_list, if_list) cnt++; - read_unlock_bh(&idev->lock); + rcu_read_unlock(); return cnt; } @@ -1808,11 +1844,11 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, const struct net_device *dev, int strict, u32 banned_flags) { + unsigned int hash = inet6_addr_hash(net, addr); struct inet6_ifaddr *ifp; - unsigned int hash = inet6_addr_hash(addr); u32 ifp_flags; - rcu_read_lock_bh(); + rcu_read_lock(); hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; @@ -1826,32 +1862,16 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, !(ifp_flags&banned_flags) && (!dev || ifp->idev->dev == dev || !(ifp->scope&(IFA_LINK|IFA_HOST) || strict))) { - rcu_read_unlock_bh(); + rcu_read_unlock(); return 1; } } - rcu_read_unlock_bh(); + rcu_read_unlock(); return 0; } EXPORT_SYMBOL(ipv6_chk_addr_and_flags); -static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, - struct net_device *dev) -{ - unsigned int hash = inet6_addr_hash(addr); - struct inet6_ifaddr *ifp; - - hlist_for_each_entry(ifp, &inet6_addr_lst[hash], addr_lst) { - if (!net_eq(dev_net(ifp->idev->dev), net)) - continue; - if (ipv6_addr_equal(&ifp->addr, addr)) { - if (!dev || ifp->idev->dev == dev) - return true; - } - } - return false; -} /* Compares an address/prefix_len with addresses on device @dev. * If one is found it returns true. @@ -1859,20 +1879,18 @@ static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, bool ipv6_chk_custom_prefix(const struct in6_addr *addr, const unsigned int prefix_len, struct net_device *dev) { - struct inet6_dev *idev; - struct inet6_ifaddr *ifa; + const struct inet6_ifaddr *ifa; + const struct inet6_dev *idev; bool ret = false; rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { - read_lock_bh(&idev->lock); - list_for_each_entry(ifa, &idev->addr_list, if_list) { + list_for_each_entry_rcu(ifa, &idev->addr_list, if_list) { ret = ipv6_prefix_equal(addr, &ifa->addr, prefix_len); if (ret) break; } - read_unlock_bh(&idev->lock); } rcu_read_unlock(); @@ -1882,22 +1900,20 @@ EXPORT_SYMBOL(ipv6_chk_custom_prefix); int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev) { - struct inet6_dev *idev; - struct inet6_ifaddr *ifa; + const struct inet6_ifaddr *ifa; + const struct inet6_dev *idev; int onlink; onlink = 0; rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { - read_lock_bh(&idev->lock); - list_for_each_entry(ifa, &idev->addr_list, if_list) { + list_for_each_entry_rcu(ifa, &idev->addr_list, if_list) { onlink = ipv6_prefix_equal(addr, &ifa->addr, ifa->prefix_len); if (onlink) break; } - read_unlock_bh(&idev->lock); } rcu_read_unlock(); return onlink; @@ -1907,11 +1923,11 @@ EXPORT_SYMBOL(ipv6_chk_prefix); struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *addr, struct net_device *dev, int strict) { + unsigned int hash = inet6_addr_hash(net, addr); struct inet6_ifaddr *ifp, *result = NULL; - unsigned int hash = inet6_addr_hash(addr); - rcu_read_lock_bh(); - hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[hash], addr_lst) { + rcu_read_lock(); + hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr)) { @@ -1923,7 +1939,7 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add } } } - rcu_read_unlock_bh(); + rcu_read_unlock(); return result; } @@ -1942,7 +1958,7 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) if (ifpub) { in6_ifa_hold(ifpub); spin_unlock_bh(&ifp->lock); - ipv6_create_tempaddr(ifpub, ifp); + ipv6_create_tempaddr(ifpub, ifp, true); in6_ifa_put(ifpub); } else { spin_unlock_bh(&ifp->lock); @@ -1975,7 +1991,7 @@ static int addrconf_dad_end(struct inet6_ifaddr *ifp) return err; } -void addrconf_dad_failure(struct inet6_ifaddr *ifp) +void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; struct net *net = dev_net(ifp->idev->dev); @@ -1985,8 +2001,8 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) return; } - net_info_ratelimited("%s: IPv6 duplicate address %pI6c detected!\n", - ifp->idev->dev->name, &ifp->addr); + net_info_ratelimited("%s: IPv6 duplicate address %pI6c used by %pM detected!\n", + ifp->idev->dev->name, &ifp->addr, eth_hdr(skb)->h_source); spin_lock_bh(&ifp->lock); @@ -2025,7 +2041,7 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) ifp2 = ipv6_add_addr(idev, &new_addr, NULL, pfxlen, scope, flags, valid_lft, - preferred_lft); + preferred_lft, false, NULL); if (IS_ERR(ifp2)) goto lock_errdad; @@ -2321,24 +2337,24 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, if (!table) return NULL; - read_lock_bh(&table->tb6_lock); - fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0); + rcu_read_lock(); + fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0, true); if (!fn) goto out; - noflags |= RTF_CACHE; - for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { + for_each_fib6_node_rt_rcu(fn) { if (rt->dst.dev->ifindex != dev->ifindex) continue; if ((rt->rt6i_flags & flags) != flags) continue; if ((rt->rt6i_flags & noflags) != 0) continue; - dst_hold(&rt->dst); + if (!dst_hold_safe(&rt->dst)) + rt = NULL; break; } out: - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); return rt; } @@ -2442,7 +2458,7 @@ static void manage_tempaddrs(struct inet6_dev *idev, * no temporary address currently exists. */ read_unlock_bh(&idev->lock); - ipv6_create_tempaddr(ifp, NULL); + ipv6_create_tempaddr(ifp, NULL, false); } else { read_unlock_bh(&idev->lock); } @@ -2483,7 +2499,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, pinfo->prefix_len, addr_type&IPV6_ADDR_SCOPE_MASK, addr_flags, valid_lft, - prefered_lft); + prefered_lft, false, NULL); if (IS_ERR_OR_NULL(ifp)) return -1; @@ -2793,7 +2809,8 @@ static int inet6_addr_add(struct net *net, int ifindex, const struct in6_addr *pfx, const struct in6_addr *peer_pfx, unsigned int plen, __u32 ifa_flags, - __u32 prefered_lft, __u32 valid_lft) + __u32 prefered_lft, __u32 valid_lft, + struct netlink_ext_ack *extack) { struct inet6_ifaddr *ifp; struct inet6_dev *idev; @@ -2852,7 +2869,7 @@ static int inet6_addr_add(struct net *net, int ifindex, } ifp = ipv6_add_addr(idev, pfx, peer_pfx, plen, scope, ifa_flags, - valid_lft, prefered_lft); + valid_lft, prefered_lft, true, extack); if (!IS_ERR(ifp)) { if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) { @@ -2937,7 +2954,7 @@ int addrconf_add_ifaddr(struct net *net, void __user *arg) rtnl_lock(); err = inet6_addr_add(net, ireq.ifr6_ifindex, &ireq.ifr6_addr, NULL, ireq.ifr6_prefixlen, IFA_F_PERMANENT, - INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); + INFINITY_LIFE_TIME, INFINITY_LIFE_TIME, NULL); rtnl_unlock(); return err; } @@ -2967,7 +2984,8 @@ static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr, ifp = ipv6_add_addr(idev, addr, NULL, plen, scope, IFA_F_PERMANENT, - INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); + INFINITY_LIFE_TIME, INFINITY_LIFE_TIME, + true, NULL); if (!IS_ERR(ifp)) { spin_lock_bh(&ifp->lock); ifp->flags &= ~IFA_F_TENTATIVE; @@ -3067,7 +3085,7 @@ void addrconf_add_linklocal(struct inet6_dev *idev, #endif ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags, - INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); + INFINITY_LIFE_TIME, INFINITY_LIFE_TIME, true, NULL); if (!IS_ERR(ifp)) { addrconf_prefix_route(&ifp->addr, ifp->prefix_len, idev->dev, 0, 0); addrconf_dad_start(ifp); @@ -3297,7 +3315,7 @@ static int fixup_permanent_addr(struct inet6_dev *idev, struct rt6_info *rt, *prev; rt = addrconf_dst_alloc(idev, &ifp->addr, false); - if (unlikely(IS_ERR(rt))) + if (IS_ERR(rt)) return PTR_ERR(rt); /* ifp->rt can be accessed outside of rtnl */ @@ -3404,7 +3422,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, /* restore routes for permanent addresses */ addrconf_permanent_addr(dev); - if (!addrconf_qdisc_ok(dev)) { + if (!addrconf_link_ready(dev)) { /* device is not ready yet. */ pr_info("ADDRCONF(NETDEV_UP): %s: link is not ready\n", dev->name); @@ -3419,7 +3437,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, run_pending = 1; } } else if (event == NETDEV_CHANGE) { - if (!addrconf_qdisc_ok(dev)) { + if (!addrconf_link_ready(dev)) { /* device is still not ready. */ break; } @@ -3563,7 +3581,6 @@ static int addrconf_ifdown(struct net_device *dev, int how) struct net *net = dev_net(dev); struct inet6_dev *idev; struct inet6_ifaddr *ifa, *tmp; - struct list_head del_list; int _keep_addr; bool keep_addr; int state, i; @@ -3655,7 +3672,6 @@ restart: */ keep_addr = (!how && _keep_addr > 0 && !idev->cnf.disable_ipv6); - INIT_LIST_HEAD(&del_list); list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { struct rt6_info *rt = NULL; bool keep; @@ -3664,8 +3680,6 @@ restart: keep = keep_addr && (ifa->flags & IFA_F_PERMANENT) && !addr_is_local(&ifa->addr); - if (!keep) - list_move(&ifa->if_list, &del_list); write_unlock_bh(&idev->lock); spin_lock_bh(&ifa->lock); @@ -3699,19 +3713,14 @@ restart: } write_lock_bh(&idev->lock); + if (!keep) { + list_del_rcu(&ifa->if_list); + in6_ifa_put(ifa); + } } write_unlock_bh(&idev->lock); - /* now clean up addresses to be removed */ - while (!list_empty(&del_list)) { - ifa = list_first_entry(&del_list, - struct inet6_ifaddr, if_list); - list_del(&ifa->if_list); - - in6_ifa_put(ifa); - } - /* Step 5: Discard anycast and multicast list */ if (how) { ipv6_ac_destroy_dev(idev); @@ -4093,9 +4102,9 @@ struct if6_iter_state { static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos) { - struct inet6_ifaddr *ifa = NULL; struct if6_iter_state *state = seq->private; struct net *net = seq_file_net(seq); + struct inet6_ifaddr *ifa = NULL; int p = 0; /* initial bucket if pos is 0 */ @@ -4105,7 +4114,7 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos) } for (; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) { - hlist_for_each_entry_rcu_bh(ifa, &inet6_addr_lst[state->bucket], + hlist_for_each_entry_rcu(ifa, &inet6_addr_lst[state->bucket], addr_lst) { if (!net_eq(dev_net(ifa->idev->dev), net)) continue; @@ -4131,7 +4140,7 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, struct if6_iter_state *state = seq->private; struct net *net = seq_file_net(seq); - hlist_for_each_entry_continue_rcu_bh(ifa, addr_lst) { + hlist_for_each_entry_continue_rcu(ifa, addr_lst) { if (!net_eq(dev_net(ifa->idev->dev), net)) continue; state->offset++; @@ -4140,7 +4149,7 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, while (++state->bucket < IN6_ADDR_HSIZE) { state->offset = 0; - hlist_for_each_entry_rcu_bh(ifa, + hlist_for_each_entry_rcu(ifa, &inet6_addr_lst[state->bucket], addr_lst) { if (!net_eq(dev_net(ifa->idev->dev), net)) continue; @@ -4153,9 +4162,9 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, } static void *if6_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(rcu_bh) + __acquires(rcu) { - rcu_read_lock_bh(); + rcu_read_lock(); return if6_get_first(seq, *pos); } @@ -4169,9 +4178,9 @@ static void *if6_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void if6_seq_stop(struct seq_file *seq, void *v) - __releases(rcu_bh) + __releases(rcu) { - rcu_read_unlock_bh(); + rcu_read_unlock(); } static int if6_seq_show(struct seq_file *seq, void *v) @@ -4240,12 +4249,12 @@ void if6_proc_exit(void) /* Check if address is a home address configured on any interface. */ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr) { - int ret = 0; + unsigned int hash = inet6_addr_hash(net, addr); struct inet6_ifaddr *ifp = NULL; - unsigned int hash = inet6_addr_hash(addr); + int ret = 0; - rcu_read_lock_bh(); - hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[hash], addr_lst) { + rcu_read_lock(); + hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr) && @@ -4254,7 +4263,7 @@ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr) break; } } - rcu_read_unlock_bh(); + rcu_read_unlock(); return ret; } #endif @@ -4344,7 +4353,7 @@ restart: spin_lock(&ifpub->lock); ifpub->regen_count = 0; spin_unlock(&ifpub->lock); - ipv6_create_tempaddr(ifpub, ifp); + ipv6_create_tempaddr(ifpub, ifp, true); in6_ifa_put(ifpub); in6_ifa_put(ifp); goto restart; @@ -4580,7 +4589,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, */ return inet6_addr_add(net, ifm->ifa_index, pfx, peer_pfx, ifm->ifa_prefixlen, ifa_flags, - preferred_lft, valid_lft); + preferred_lft, valid_lft, extack); } if (nlh->nlmsg_flags & NLM_F_EXCL || @@ -4907,17 +4916,15 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, extack); if (err < 0) - goto errout; + return err; addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer); - if (!addr) { - err = -EINVAL; - goto errout; - } + if (!addr) + return -EINVAL; ifm = nlmsg_data(nlh); if (ifm->ifa_index) - dev = __dev_get_by_index(net, ifm->ifa_index); + dev = dev_get_by_index(net, ifm->ifa_index); ifa = ipv6_get_ifaddr(net, addr, dev, 1); if (!ifa) { @@ -4943,6 +4950,8 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, errout_ifa: in6_ifa_put(ifa); errout: + if (dev) + dev_put(dev); return err; } @@ -5050,6 +5059,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_ENHANCED_DAD] = cnf->enhanced_dad; array[DEVCONF_ADDR_GEN_MODE] = cnf->addr_gen_mode; array[DEVCONF_DISABLE_POLICY] = cnf->disable_policy; + array[DEVCONF_NDISC_TCLASS] = cnf->ndisc_tclass; } static inline size_t inet6_ifla6_size(void) @@ -5899,10 +5909,9 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val) spin_lock(&ifa->lock); if (ifa->rt) { struct rt6_info *rt = ifa->rt; - struct fib6_table *table = rt->rt6i_table; int cpu; - read_lock(&table->tb6_lock); + rcu_read_lock(); addrconf_set_nopolicy(ifa->rt, val); if (rt->rt6i_pcpu) { for_each_possible_cpu(cpu) { @@ -5912,7 +5921,7 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val) addrconf_set_nopolicy(*rtp, val); } } - read_unlock(&table->tb6_lock); + rcu_read_unlock(); } spin_unlock(&ifa->lock); } @@ -5978,6 +5987,7 @@ int addrconf_sysctl_disable_policy(struct ctl_table *ctl, int write, } static int minus_one = -1; +static const int zero = 0; static const int one = 1; static const int two_five_five = 255; @@ -6349,6 +6359,15 @@ static const struct ctl_table addrconf_sysctl[] = { .proc_handler = addrconf_sysctl_disable_policy, }, { + .procname = "ndisc_tclass", + .data = &ipv6_devconf.ndisc_tclass, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&zero, + .extra2 = (void *)&two_five_five, + }, + { /* sentinel */ } }; @@ -6586,13 +6605,13 @@ int __init addrconf_init(void) __rtnl_register(PF_INET6, RTM_NEWADDR, inet6_rtm_newaddr, NULL, 0); __rtnl_register(PF_INET6, RTM_DELADDR, inet6_rtm_deladdr, NULL, 0); __rtnl_register(PF_INET6, RTM_GETADDR, inet6_rtm_getaddr, - inet6_dump_ifaddr, 0); + inet6_dump_ifaddr, RTNL_FLAG_DOIT_UNLOCKED); __rtnl_register(PF_INET6, RTM_GETMULTICAST, NULL, inet6_dump_ifmcaddr, 0); __rtnl_register(PF_INET6, RTM_GETANYCAST, NULL, inet6_dump_ifacaddr, 0); __rtnl_register(PF_INET6, RTM_GETNETCONF, inet6_netconf_get_devconf, - inet6_netconf_dump_devconf, 0); + inet6_netconf_dump_devconf, RTNL_FLAG_DOIT_UNLOCKED); ipv6_addr_label_rtnl_register(); @@ -6619,9 +6638,9 @@ void addrconf_cleanup(void) unregister_pernet_subsys(&addrconf_ops); ipv6_addr_label_cleanup(); - rtnl_lock(); + rtnl_af_unregister(&inet6_ops); - __rtnl_af_unregister(&inet6_ops); + rtnl_lock(); /* clean dev list */ for_each_netdev(&init_net, dev) { diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 9e3488d50b15..32b564dfd02a 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -88,7 +88,7 @@ int __ipv6_addr_type(const struct in6_addr *addr) EXPORT_SYMBOL(__ipv6_addr_type); static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); -static ATOMIC_NOTIFIER_HEAD(inet6addr_validator_chain); +static BLOCKING_NOTIFIER_HEAD(inet6addr_validator_chain); int register_inet6addr_notifier(struct notifier_block *nb) { @@ -110,19 +110,20 @@ EXPORT_SYMBOL(inet6addr_notifier_call_chain); int register_inet6addr_validator_notifier(struct notifier_block *nb) { - return atomic_notifier_chain_register(&inet6addr_validator_chain, nb); + return blocking_notifier_chain_register(&inet6addr_validator_chain, nb); } EXPORT_SYMBOL(register_inet6addr_validator_notifier); int unregister_inet6addr_validator_notifier(struct notifier_block *nb) { - return atomic_notifier_chain_unregister(&inet6addr_validator_chain, nb); + return blocking_notifier_chain_unregister(&inet6addr_validator_chain, + nb); } EXPORT_SYMBOL(unregister_inet6addr_validator_notifier); int inet6addr_validator_notifier_call_chain(unsigned long val, void *v) { - return atomic_notifier_call_chain(&inet6addr_validator_chain, val, v); + return blocking_notifier_call_chain(&inet6addr_validator_chain, val, v); } EXPORT_SYMBOL(inet6addr_validator_notifier_call_chain); diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index f664871feca6..00e1f8ee08f8 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -19,7 +19,6 @@ #include <linux/if_addrlabel.h> #include <linux/netlink.h> #include <linux/rtnetlink.h> -#include <linux/refcount.h> #if 0 #define ADDRLABEL(x...) printk(x) @@ -31,30 +30,15 @@ * Policy Table */ struct ip6addrlbl_entry { - possible_net_t lbl_net; struct in6_addr prefix; int prefixlen; int ifindex; int addrtype; u32 label; struct hlist_node list; - refcount_t refcnt; struct rcu_head rcu; }; -static struct ip6addrlbl_table -{ - struct hlist_head head; - spinlock_t lock; - u32 seq; -} ip6addrlbl_table; - -static inline -struct net *ip6addrlbl_net(const struct ip6addrlbl_entry *lbl) -{ - return read_pnet(&lbl->lbl_net); -} - /* * Default policy table (RFC6724 + extensions) * @@ -126,36 +110,11 @@ static const __net_initconst struct ip6addrlbl_init_table } }; -/* Object management */ -static inline void ip6addrlbl_free(struct ip6addrlbl_entry *p) -{ - kfree(p); -} - -static void ip6addrlbl_free_rcu(struct rcu_head *h) -{ - ip6addrlbl_free(container_of(h, struct ip6addrlbl_entry, rcu)); -} - -static bool ip6addrlbl_hold(struct ip6addrlbl_entry *p) -{ - return refcount_inc_not_zero(&p->refcnt); -} - -static inline void ip6addrlbl_put(struct ip6addrlbl_entry *p) -{ - if (refcount_dec_and_test(&p->refcnt)) - call_rcu(&p->rcu, ip6addrlbl_free_rcu); -} - /* Find label */ -static bool __ip6addrlbl_match(struct net *net, - const struct ip6addrlbl_entry *p, +static bool __ip6addrlbl_match(const struct ip6addrlbl_entry *p, const struct in6_addr *addr, int addrtype, int ifindex) { - if (!net_eq(ip6addrlbl_net(p), net)) - return false; if (p->ifindex && p->ifindex != ifindex) return false; if (p->addrtype && p->addrtype != addrtype) @@ -170,8 +129,9 @@ static struct ip6addrlbl_entry *__ipv6_addr_label(struct net *net, int type, int ifindex) { struct ip6addrlbl_entry *p; - hlist_for_each_entry_rcu(p, &ip6addrlbl_table.head, list) { - if (__ip6addrlbl_match(net, p, addr, type, ifindex)) + + hlist_for_each_entry_rcu(p, &net->ipv6.ip6addrlbl_table.head, list) { + if (__ip6addrlbl_match(p, addr, type, ifindex)) return p; } return NULL; @@ -197,8 +157,7 @@ u32 ipv6_addr_label(struct net *net, } /* allocate one entry */ -static struct ip6addrlbl_entry *ip6addrlbl_alloc(struct net *net, - const struct in6_addr *prefix, +static struct ip6addrlbl_entry *ip6addrlbl_alloc(const struct in6_addr *prefix, int prefixlen, int ifindex, u32 label) { @@ -237,24 +196,22 @@ static struct ip6addrlbl_entry *ip6addrlbl_alloc(struct net *net, newp->addrtype = addrtype; newp->label = label; INIT_HLIST_NODE(&newp->list); - write_pnet(&newp->lbl_net, net); - refcount_set(&newp->refcnt, 1); return newp; } /* add a label */ -static int __ip6addrlbl_add(struct ip6addrlbl_entry *newp, int replace) +static int __ip6addrlbl_add(struct net *net, struct ip6addrlbl_entry *newp, + int replace) { - struct hlist_node *n; struct ip6addrlbl_entry *last = NULL, *p = NULL; + struct hlist_node *n; int ret = 0; ADDRLABEL(KERN_DEBUG "%s(newp=%p, replace=%d)\n", __func__, newp, replace); - hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) { + hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { if (p->prefixlen == newp->prefixlen && - net_eq(ip6addrlbl_net(p), ip6addrlbl_net(newp)) && p->ifindex == newp->ifindex && ipv6_addr_equal(&p->prefix, &newp->prefix)) { if (!replace) { @@ -262,7 +219,7 @@ static int __ip6addrlbl_add(struct ip6addrlbl_entry *newp, int replace) goto out; } hlist_replace_rcu(&p->list, &newp->list); - ip6addrlbl_put(p); + kfree_rcu(p, rcu); goto out; } else if ((p->prefixlen == newp->prefixlen && !p->ifindex) || (p->prefixlen < newp->prefixlen)) { @@ -274,10 +231,10 @@ static int __ip6addrlbl_add(struct ip6addrlbl_entry *newp, int replace) if (last) hlist_add_behind_rcu(&newp->list, &last->list); else - hlist_add_head_rcu(&newp->list, &ip6addrlbl_table.head); + hlist_add_head_rcu(&newp->list, &net->ipv6.ip6addrlbl_table.head); out: if (!ret) - ip6addrlbl_table.seq++; + net->ipv6.ip6addrlbl_table.seq++; return ret; } @@ -293,14 +250,14 @@ static int ip6addrlbl_add(struct net *net, __func__, prefix, prefixlen, ifindex, (unsigned int)label, replace); - newp = ip6addrlbl_alloc(net, prefix, prefixlen, ifindex, label); + newp = ip6addrlbl_alloc(prefix, prefixlen, ifindex, label); if (IS_ERR(newp)) return PTR_ERR(newp); - spin_lock(&ip6addrlbl_table.lock); - ret = __ip6addrlbl_add(newp, replace); - spin_unlock(&ip6addrlbl_table.lock); + spin_lock(&net->ipv6.ip6addrlbl_table.lock); + ret = __ip6addrlbl_add(net, newp, replace); + spin_unlock(&net->ipv6.ip6addrlbl_table.lock); if (ret) - ip6addrlbl_free(newp); + kfree(newp); return ret; } @@ -316,13 +273,12 @@ static int __ip6addrlbl_del(struct net *net, ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d)\n", __func__, prefix, prefixlen, ifindex); - hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) { + hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { if (p->prefixlen == prefixlen && - net_eq(ip6addrlbl_net(p), net) && p->ifindex == ifindex && ipv6_addr_equal(&p->prefix, prefix)) { hlist_del_rcu(&p->list); - ip6addrlbl_put(p); + kfree_rcu(p, rcu); ret = 0; break; } @@ -341,9 +297,9 @@ static int ip6addrlbl_del(struct net *net, __func__, prefix, prefixlen, ifindex); ipv6_addr_prefix(&prefix_buf, prefix, prefixlen); - spin_lock(&ip6addrlbl_table.lock); + spin_lock(&net->ipv6.ip6addrlbl_table.lock); ret = __ip6addrlbl_del(net, &prefix_buf, prefixlen, ifindex); - spin_unlock(&ip6addrlbl_table.lock); + spin_unlock(&net->ipv6.ip6addrlbl_table.lock); return ret; } @@ -355,6 +311,9 @@ static int __net_init ip6addrlbl_net_init(struct net *net) ADDRLABEL(KERN_DEBUG "%s\n", __func__); + spin_lock_init(&net->ipv6.ip6addrlbl_table.lock); + INIT_HLIST_HEAD(&net->ipv6.ip6addrlbl_table.head); + for (i = 0; i < ARRAY_SIZE(ip6addrlbl_init_table); i++) { int ret = ip6addrlbl_add(net, ip6addrlbl_init_table[i].prefix, @@ -374,14 +333,12 @@ static void __net_exit ip6addrlbl_net_exit(struct net *net) struct hlist_node *n; /* Remove all labels belonging to the exiting net */ - spin_lock(&ip6addrlbl_table.lock); - hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) { - if (net_eq(ip6addrlbl_net(p), net)) { - hlist_del_rcu(&p->list); - ip6addrlbl_put(p); - } + spin_lock(&net->ipv6.ip6addrlbl_table.lock); + hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { + hlist_del_rcu(&p->list); + kfree_rcu(p, rcu); } - spin_unlock(&ip6addrlbl_table.lock); + spin_unlock(&net->ipv6.ip6addrlbl_table.lock); } static struct pernet_operations ipv6_addr_label_ops = { @@ -391,8 +348,6 @@ static struct pernet_operations ipv6_addr_label_ops = { int __init ipv6_addr_label_init(void) { - spin_lock_init(&ip6addrlbl_table.lock); - return register_pernet_subsys(&ipv6_addr_label_ops); } @@ -511,11 +466,10 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) int err; rcu_read_lock(); - hlist_for_each_entry_rcu(p, &ip6addrlbl_table.head, list) { - if (idx >= s_idx && - net_eq(ip6addrlbl_net(p), net)) { + hlist_for_each_entry_rcu(p, &net->ipv6.ip6addrlbl_table.head, list) { + if (idx >= s_idx) { err = ip6addrlbl_fill(skb, p, - ip6addrlbl_table.seq, + net->ipv6.ip6addrlbl_table.seq, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWADDRLABEL, @@ -568,38 +522,28 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh, return -EINVAL; addr = nla_data(tb[IFAL_ADDRESS]); - rcu_read_lock(); - p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index); - if (p && !ip6addrlbl_hold(p)) - p = NULL; - lseq = ip6addrlbl_table.seq; - rcu_read_unlock(); - - if (!p) { - err = -ESRCH; - goto out; - } - skb = nlmsg_new(ip6addrlbl_msgsize(), GFP_KERNEL); - if (!skb) { - ip6addrlbl_put(p); + if (!skb) return -ENOBUFS; - } - err = ip6addrlbl_fill(skb, p, lseq, - NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, - RTM_NEWADDRLABEL, 0); + err = -ESRCH; - ip6addrlbl_put(p); + rcu_read_lock(); + p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index); + lseq = net->ipv6.ip6addrlbl_table.seq; + if (p) + err = ip6addrlbl_fill(skb, p, lseq, + NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, + RTM_NEWADDRLABEL, 0); + rcu_read_unlock(); if (err < 0) { WARN_ON(err == -EMSGSIZE); kfree_skb(skb); - goto out; + } else { + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); } - - err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); -out: return err; } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index fe5262fd6aa5..c26f71234b9c 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -810,6 +810,10 @@ static int __net_init inet6_net_init(struct net *net) net->ipv6.sysctl.idgen_retries = 3; net->ipv6.sysctl.idgen_delay = 1 * HZ; net->ipv6.sysctl.flowlabel_state_ranges = 0; + net->ipv6.sysctl.max_dst_opts_cnt = IP6_DEFAULT_MAX_DST_OPTS_CNT; + net->ipv6.sysctl.max_hbh_opts_cnt = IP6_DEFAULT_MAX_HBH_OPTS_CNT; + net->ipv6.sysctl.max_dst_opts_len = IP6_DEFAULT_MAX_DST_OPTS_LEN; + net->ipv6.sysctl.max_hbh_opts_len = IP6_DEFAULT_MAX_HBH_OPTS_LEN; atomic_set(&net->ipv6.fib6_sernum, 1); err = ipv6_init_mibs(net); diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 7802b72196f3..78c974391567 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -271,6 +271,7 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir) case NEXTHDR_DEST: if (dir == XFRM_POLICY_OUT) ipv6_rearrange_destopt(iph, exthdr.opth); + /* fall through */ case NEXTHDR_HOP: if (!zero_out_mutable_opts(exthdr.opth)) { net_dbg_ratelimited("overrun %sopts\n", @@ -443,7 +444,7 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) if (err == -EINPROGRESS) goto out; - if (err == -EBUSY) + if (err == -ENOSPC) err = NET_XMIT_DROP; goto out_free; } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 89910e2c10f4..a902ff8f59be 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -396,7 +396,7 @@ int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info case -EINPROGRESS: goto error; - case -EBUSY: + case -ENOSPC: err = NET_XMIT_DROP; break; @@ -483,8 +483,8 @@ static inline int esp_remove_trailer(struct sk_buff *skb) goto out; } - if (skb_copy_bits(skb, skb->len - alen - 2, nexthdr, 2)) - BUG(); + ret = skb_copy_bits(skb, skb->len - alen - 2, nexthdr, 2); + BUG_ON(ret); ret = -EINVAL; padlen = nexthdr[0]; @@ -559,14 +559,14 @@ static void esp_input_restore_header(struct sk_buff *skb) static void esp_input_set_header(struct sk_buff *skb, __be32 *seqhi) { struct xfrm_state *x = xfrm_input_state(skb); - struct ip_esp_hdr *esph = (struct ip_esp_hdr *)skb->data; /* For ESN we move the header forward by 4 bytes to * accomodate the high bits. We will move it back after * decryption. */ if ((x->props.flags & XFRM_STATE_ESN)) { - esph = skb_push(skb, 4); + struct ip_esp_hdr *esph = skb_push(skb, 4); + *seqhi = esph->spi; esph->spi = esph->seq_no; esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 95516138e861..83bd75713535 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -74,8 +74,20 @@ struct tlvtype_proc { /* An unknown option is detected, decide what to do */ -static bool ip6_tlvopt_unknown(struct sk_buff *skb, int optoff) +static bool ip6_tlvopt_unknown(struct sk_buff *skb, int optoff, + bool disallow_unknowns) { + if (disallow_unknowns) { + /* If unknown TLVs are disallowed by configuration + * then always silently drop packet. Note this also + * means no ICMP parameter problem is sent which + * could be a good property to mitigate a reflection DOS + * attack. + */ + + goto drop; + } + switch ((skb_network_header(skb)[optoff] & 0xC0) >> 6) { case 0: /* ignore */ return true; @@ -89,25 +101,36 @@ static bool ip6_tlvopt_unknown(struct sk_buff *skb, int optoff) */ if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) break; + /* fall through */ case 2: /* send ICMP PARM PROB regardless and drop packet */ icmpv6_param_prob(skb, ICMPV6_UNK_OPTION, optoff); return false; } +drop: kfree_skb(skb); return false; } /* Parse tlv encoded option header (hop-by-hop or destination) */ -static bool ip6_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb) +static bool ip6_parse_tlv(const struct tlvtype_proc *procs, + struct sk_buff *skb, + int max_count) { - const struct tlvtype_proc *curr; + int len = (skb_transport_header(skb)[1] + 1) << 3; const unsigned char *nh = skb_network_header(skb); int off = skb_network_header_len(skb); - int len = (skb_transport_header(skb)[1] + 1) << 3; + const struct tlvtype_proc *curr; + bool disallow_unknowns = false; + int tlv_count = 0; int padlen = 0; + if (unlikely(max_count < 0)) { + disallow_unknowns = true; + max_count = -max_count; + } + if (skb_transport_offset(skb) + len > skb_headlen(skb)) goto bad; @@ -148,6 +171,11 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb) default: /* Other TLV code so scan list */ if (optlen > len) goto bad; + + tlv_count++; + if (tlv_count > max_count) + goto bad; + for (curr = procs; curr->type >= 0; curr++) { if (curr->type == nh[off]) { /* type specific length/alignment @@ -158,10 +186,10 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, struct sk_buff *skb) break; } } - if (curr->type < 0) { - if (ip6_tlvopt_unknown(skb, off) == 0) - return false; - } + if (curr->type < 0 && + !ip6_tlvopt_unknown(skb, off, disallow_unknowns)) + return false; + padlen = 0; break; } @@ -186,7 +214,6 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff) struct ipv6_destopt_hao *hao; struct inet6_skb_parm *opt = IP6CB(skb); struct ipv6hdr *ipv6h = ipv6_hdr(skb); - struct in6_addr tmp_addr; int ret; if (opt->dsthao) { @@ -228,9 +255,7 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff) if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; - tmp_addr = ipv6h->saddr; - ipv6h->saddr = hao->addr; - hao->addr = tmp_addr; + swap(ipv6h->saddr, hao->addr); if (skb->tstamp == 0) __net_timestamp(skb); @@ -260,23 +285,31 @@ static int ipv6_destopt_rcv(struct sk_buff *skb) __u16 dstbuf; #endif struct dst_entry *dst = skb_dst(skb); + struct net *net = dev_net(skb->dev); + int extlen; if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) || !pskb_may_pull(skb, (skb_transport_offset(skb) + ((skb_transport_header(skb)[1] + 1) << 3)))) { __IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS); +fail_and_free: kfree_skb(skb); return -1; } + extlen = (skb_transport_header(skb)[1] + 1) << 3; + if (extlen > net->ipv6.sysctl.max_dst_opts_len) + goto fail_and_free; + opt->lastopt = opt->dst1 = skb_network_header_len(skb); #if IS_ENABLED(CONFIG_IPV6_MIP6) dstbuf = opt->dst1; #endif - if (ip6_parse_tlv(tlvprocdestopt_lst, skb)) { - skb->transport_header += (skb_transport_header(skb)[1] + 1) << 3; + if (ip6_parse_tlv(tlvprocdestopt_lst, skb, + init_net.ipv6.sysctl.max_dst_opts_cnt)) { + skb->transport_header += extlen; opt = IP6CB(skb); #if IS_ENABLED(CONFIG_IPV6_MIP6) opt->nhoff = dstbuf; @@ -805,6 +838,8 @@ static const struct tlvtype_proc tlvprochopopt_lst[] = { int ipv6_parse_hopopts(struct sk_buff *skb) { struct inet6_skb_parm *opt = IP6CB(skb); + struct net *net = dev_net(skb->dev); + int extlen; /* * skb_network_header(skb) is equal to skb->data, and @@ -815,13 +850,19 @@ int ipv6_parse_hopopts(struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + 8) || !pskb_may_pull(skb, (sizeof(struct ipv6hdr) + ((skb_transport_header(skb)[1] + 1) << 3)))) { +fail_and_free: kfree_skb(skb); return -1; } + extlen = (skb_transport_header(skb)[1] + 1) << 3; + if (extlen > net->ipv6.sysctl.max_hbh_opts_len) + goto fail_and_free; + opt->flags |= IP6SKB_HOPBYHOP; - if (ip6_parse_tlv(tlvprochopopt_lst, skb)) { - skb->transport_header += (skb_transport_header(skb)[1] + 1) << 3; + if (ip6_parse_tlv(tlvprochopopt_lst, skb, + init_net.ipv6.sysctl.max_hbh_opts_cnt)) { + skb->transport_header += extlen; opt = IP6CB(skb); opt->nhoff = sizeof(struct ipv6hdr); return 1; diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 305e2ed730bf..11025f8d124b 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -99,7 +99,7 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp, break; hdrlen = 8; } else if (nexthdr == NEXTHDR_AUTH) - hdrlen = (hp->hdrlen+2)<<2; + hdrlen = ipv6_authlen(hp); else hdrlen = ipv6_optlen(hp); @@ -187,7 +187,6 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, { unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr); u8 nexthdr = ipv6_hdr(skb)->nexthdr; - unsigned int len; bool found; if (fragoff) @@ -204,7 +203,6 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, start = *offset + sizeof(struct ipv6hdr); nexthdr = ip6->nexthdr; } - len = skb->len - start; do { struct ipv6_opt_hdr _hdr, *hp; @@ -273,7 +271,6 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, if (!found) { nexthdr = hp->nexthdr; - len -= hdrlen; start += hdrlen; } } while (!found); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 5acb54405b10..6ae5dd3f4d0d 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -250,16 +250,15 @@ static bool opt_unrec(struct sk_buff *skb, __u32 offset) return (*op & 0xC0) == 0x80; } -int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, - struct icmp6hdr *thdr, int len) +void icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, + struct icmp6hdr *thdr, int len) { struct sk_buff *skb; struct icmp6hdr *icmp6h; - int err = 0; skb = skb_peek(&sk->sk_write_queue); if (!skb) - goto out; + return; icmp6h = icmp6_hdr(skb); memcpy(icmp6h, thdr, sizeof(struct icmp6hdr)); @@ -287,8 +286,6 @@ int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, tmp_csum); } ip6_push_pending_frames(sk); -out: - return err; } struct icmpv6_msg { @@ -438,7 +435,6 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, int iif = 0; int addr_type = 0; int len; - int err = 0; u32 mark = IP6_REPLY_MARK(net, skb->mark); if ((u8 *)hdr < skb->head || @@ -575,17 +571,16 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, rcu_read_lock(); idev = __in6_dev_get(skb->dev); - err = ip6_append_data(sk, icmpv6_getfrag, &msg, - len + sizeof(struct icmp6hdr), - sizeof(struct icmp6hdr), - &ipc6, &fl6, (struct rt6_info *)dst, - MSG_DONTWAIT, &sockc_unused); - if (err) { + if (ip6_append_data(sk, icmpv6_getfrag, &msg, + len + sizeof(struct icmp6hdr), + sizeof(struct icmp6hdr), + &ipc6, &fl6, (struct rt6_info *)dst, + MSG_DONTWAIT, &sockc_unused)) { ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { - err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, - len + sizeof(struct icmp6hdr)); + icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, + len + sizeof(struct icmp6hdr)); } rcu_read_unlock(); out_dst_release: @@ -682,7 +677,6 @@ static void icmpv6_echo_reply(struct sk_buff *skb) struct icmpv6_msg msg; struct dst_entry *dst; struct ipcm6_cookie ipc6; - int err = 0; u32 mark = IP6_REPLY_MARK(net, skb->mark); struct sockcm_cookie sockc_unused = {0}; @@ -719,8 +713,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) else if (!fl6.flowi6_oif) fl6.flowi6_oif = np->ucast_oif; - err = ip6_dst_lookup(net, sk, &dst, &fl6); - if (err) + if (ip6_dst_lookup(net, sk, &dst, &fl6)) goto out; dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0); if (IS_ERR(dst)) @@ -737,17 +730,16 @@ static void icmpv6_echo_reply(struct sk_buff *skb) ipc6.dontfrag = np->dontfrag; ipc6.opt = NULL; - err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), - sizeof(struct icmp6hdr), &ipc6, &fl6, - (struct rt6_info *)dst, MSG_DONTWAIT, - &sockc_unused); - - if (err) { + if (ip6_append_data(sk, icmpv6_getfrag, &msg, + skb->len + sizeof(struct icmp6hdr), + sizeof(struct icmp6hdr), &ipc6, &fl6, + (struct rt6_info *)dst, MSG_DONTWAIT, + &sockc_unused)) { __ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { - err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, - skb->len + sizeof(struct icmp6hdr)); + icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, + skb->len + sizeof(struct icmp6hdr)); } dst_release(dst); out: @@ -872,10 +864,8 @@ static int icmpv6_rcv(struct sk_buff *skb) goto discard_it; hdr = icmp6_hdr(skb); - /* - * Drop through to notify - */ - + /* to notify */ + /* fall through */ case ICMPV6_DEST_UNREACH: case ICMPV6_TIME_EXCEED: case ICMPV6_PARAMPROB: diff --git a/net/ipv6/ila/ila.h b/net/ipv6/ila/ila.h index e0170f62bc39..3c7a11b62334 100644 --- a/net/ipv6/ila/ila.h +++ b/net/ipv6/ila/ila.h @@ -55,17 +55,6 @@ struct ila_identifier { }; }; -enum { - ILA_ATYPE_IID = 0, - ILA_ATYPE_LUID, - ILA_ATYPE_VIRT_V4, - ILA_ATYPE_VIRT_UNI_V6, - ILA_ATYPE_VIRT_MULTI_V6, - ILA_ATYPE_RSVD_1, - ILA_ATYPE_RSVD_2, - ILA_ATYPE_RSVD_3, -}; - #define CSUM_NEUTRAL_FLAG htonl(0x10000000) struct ila_addr { @@ -93,6 +82,7 @@ struct ila_params { struct ila_locator locator_match; __wsum csum_diff; u8 csum_mode; + u8 ident_type; }; static inline __wsum compute_csum_diff8(const __be32 *from, const __be32 *to) diff --git a/net/ipv6/ila/ila_common.c b/net/ipv6/ila/ila_common.c index aba0998ddbfb..8c88ecf29b93 100644 --- a/net/ipv6/ila/ila_common.c +++ b/net/ipv6/ila/ila_common.c @@ -13,30 +13,37 @@ #include <uapi/linux/ila.h> #include "ila.h" -static __wsum get_csum_diff(struct ipv6hdr *ip6h, struct ila_params *p) +void ila_init_saved_csum(struct ila_params *p) { - struct ila_addr *iaddr = ila_a2i(&ip6h->daddr); + if (!p->locator_match.v64) + return; + p->csum_diff = compute_csum_diff8( + (__be32 *)&p->locator, + (__be32 *)&p->locator_match); +} + +static __wsum get_csum_diff_iaddr(struct ila_addr *iaddr, struct ila_params *p) +{ if (p->locator_match.v64) return p->csum_diff; else - return compute_csum_diff8((__be32 *)&iaddr->loc, - (__be32 *)&p->locator); + return compute_csum_diff8((__be32 *)&p->locator, + (__be32 *)&iaddr->loc); } -static void ila_csum_do_neutral(struct ila_addr *iaddr, - struct ila_params *p) +static __wsum get_csum_diff(struct ipv6hdr *ip6h, struct ila_params *p) +{ + return get_csum_diff_iaddr(ila_a2i(&ip6h->daddr), p); +} + +static void ila_csum_do_neutral_fmt(struct ila_addr *iaddr, + struct ila_params *p) { __sum16 *adjust = (__force __sum16 *)&iaddr->ident.v16[3]; __wsum diff, fval; - /* Check if checksum adjust value has been cached */ - if (p->locator_match.v64) { - diff = p->csum_diff; - } else { - diff = compute_csum_diff8((__be32 *)&p->locator, - (__be32 *)iaddr); - } + diff = get_csum_diff_iaddr(iaddr, p); fval = (__force __wsum)(ila_csum_neutral_set(iaddr->ident) ? CSUM_NEUTRAL_FLAG : ~CSUM_NEUTRAL_FLAG); @@ -53,13 +60,23 @@ static void ila_csum_do_neutral(struct ila_addr *iaddr, iaddr->ident.csum_neutral ^= 1; } -static void ila_csum_adjust_transport(struct sk_buff *skb, +static void ila_csum_do_neutral_nofmt(struct ila_addr *iaddr, struct ila_params *p) { + __sum16 *adjust = (__force __sum16 *)&iaddr->ident.v16[3]; __wsum diff; - struct ipv6hdr *ip6h = ipv6_hdr(skb); - struct ila_addr *iaddr = ila_a2i(&ip6h->daddr); + + diff = get_csum_diff_iaddr(iaddr, p); + + *adjust = ~csum_fold(csum_add(diff, csum_unfold(*adjust))); +} + +static void ila_csum_adjust_transport(struct sk_buff *skb, + struct ila_params *p) +{ size_t nhoff = sizeof(struct ipv6hdr); + struct ipv6hdr *ip6h = ipv6_hdr(skb); + __wsum diff; switch (ip6h->nexthdr) { case NEXTHDR_TCP: @@ -98,52 +115,45 @@ static void ila_csum_adjust_transport(struct sk_buff *skb, } break; } - - /* Now change destination address */ - iaddr->loc = p->locator; } void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p, - bool set_csum_neutral) + bool sir2ila) { struct ipv6hdr *ip6h = ipv6_hdr(skb); struct ila_addr *iaddr = ila_a2i(&ip6h->daddr); - /* First deal with the transport checksum */ - if (ila_csum_neutral_set(iaddr->ident)) { - /* C-bit is set in the locator indicating that this - * is a locator being translated to a SIR address. - * Perform (receiver) checksum-neutral translation. - */ - if (!set_csum_neutral) - ila_csum_do_neutral(iaddr, p); - } else { - switch (p->csum_mode) { - case ILA_CSUM_ADJUST_TRANSPORT: - ila_csum_adjust_transport(skb, p); - break; - case ILA_CSUM_NEUTRAL_MAP: - ila_csum_do_neutral(iaddr, p); - break; - case ILA_CSUM_NO_ACTION: + switch (p->csum_mode) { + case ILA_CSUM_ADJUST_TRANSPORT: + ila_csum_adjust_transport(skb, p); + break; + case ILA_CSUM_NEUTRAL_MAP: + if (sir2ila) { + if (WARN_ON(ila_csum_neutral_set(iaddr->ident))) { + /* Checksum flag should never be + * set in a formatted SIR address. + */ + break; + } + } else if (!ila_csum_neutral_set(iaddr->ident)) { + /* ILA to SIR translation and C-bit isn't + * set so we're good. + */ break; } + ila_csum_do_neutral_fmt(iaddr, p); + break; + case ILA_CSUM_NEUTRAL_MAP_AUTO: + ila_csum_do_neutral_nofmt(iaddr, p); + break; + case ILA_CSUM_NO_ACTION: + break; } /* Now change destination address */ iaddr->loc = p->locator; } -void ila_init_saved_csum(struct ila_params *p) -{ - if (!p->locator_match.v64) - return; - - p->csum_diff = compute_csum_diff8( - (__be32 *)&p->locator, - (__be32 *)&p->locator_match); -} - static int __init ila_init(void) { int ret; diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c index 696281b4bca2..3d56a2fb6f86 100644 --- a/net/ipv6/ila/ila_lwt.c +++ b/net/ipv6/ila/ila_lwt.c @@ -20,6 +20,7 @@ struct ila_lwt { struct ila_params p; struct dst_cache dst_cache; u32 connected : 1; + u32 lwt_output : 1; }; static inline struct ila_lwt *ila_lwt_lwtunnel( @@ -45,8 +46,10 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb) if (skb->protocol != htons(ETH_P_IPV6)) goto drop; - ila_update_ipv6_locator(skb, ila_params_lwtunnel(orig_dst->lwtstate), - true); + if (ilwt->lwt_output) + ila_update_ipv6_locator(skb, + ila_params_lwtunnel(orig_dst->lwtstate), + true); if (rt->rt6i_flags & (RTF_GATEWAY | RTF_CACHE)) { /* Already have a next hop address in route, no need for @@ -98,11 +101,15 @@ drop: static int ila_input(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); + struct ila_lwt *ilwt = ila_lwt_lwtunnel(dst->lwtstate); if (skb->protocol != htons(ETH_P_IPV6)) goto drop; - ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate), false); + if (!ilwt->lwt_output) + ila_update_ipv6_locator(skb, + ila_params_lwtunnel(dst->lwtstate), + false); return dst->lwtstate->orig_input(skb); @@ -114,6 +121,8 @@ drop: static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = { [ILA_ATTR_LOCATOR] = { .type = NLA_U64, }, [ILA_ATTR_CSUM_MODE] = { .type = NLA_U8, }, + [ILA_ATTR_IDENT_TYPE] = { .type = NLA_U8, }, + [ILA_ATTR_HOOK_TYPE] = { .type = NLA_U8, }, }; static int ila_build_state(struct nlattr *nla, @@ -127,33 +136,84 @@ static int ila_build_state(struct nlattr *nla, struct lwtunnel_state *newts; const struct fib6_config *cfg6 = cfg; struct ila_addr *iaddr; + u8 ident_type = ILA_ATYPE_USE_FORMAT; + u8 hook_type = ILA_HOOK_ROUTE_OUTPUT; + u8 csum_mode = ILA_CSUM_NO_ACTION; + bool lwt_output = true; + u8 eff_ident_type; int ret; if (family != AF_INET6) return -EINVAL; - if (cfg6->fc_dst_len < 8 * sizeof(struct ila_locator) + 3) { - /* Need to have full locator and at least type field - * included in destination - */ + ret = nla_parse_nested(tb, ILA_ATTR_MAX, nla, ila_nl_policy, extack); + if (ret < 0) + return ret; + + if (!tb[ILA_ATTR_LOCATOR]) return -EINVAL; - } iaddr = (struct ila_addr *)&cfg6->fc_dst; - if (!ila_addr_is_ila(iaddr) || ila_csum_neutral_set(iaddr->ident)) { - /* Don't allow translation for a non-ILA address or checksum - * neutral flag to be set. + if (tb[ILA_ATTR_IDENT_TYPE]) + ident_type = nla_get_u8(tb[ILA_ATTR_IDENT_TYPE]); + + if (ident_type == ILA_ATYPE_USE_FORMAT) { + /* Infer identifier type from type field in formatted + * identifier. */ + + if (cfg6->fc_dst_len < 8 * sizeof(struct ila_locator) + 3) { + /* Need to have full locator and at least type field + * included in destination + */ + return -EINVAL; + } + + eff_ident_type = iaddr->ident.type; + } else { + eff_ident_type = ident_type; + } + + switch (eff_ident_type) { + case ILA_ATYPE_IID: + /* Don't allow ILA for IID type */ + return -EINVAL; + case ILA_ATYPE_LUID: + break; + case ILA_ATYPE_VIRT_V4: + case ILA_ATYPE_VIRT_UNI_V6: + case ILA_ATYPE_VIRT_MULTI_V6: + case ILA_ATYPE_NONLOCAL_ADDR: + /* These ILA formats are not supported yet. */ + default: return -EINVAL; } - ret = nla_parse_nested(tb, ILA_ATTR_MAX, nla, ila_nl_policy, extack); - if (ret < 0) - return ret; + if (tb[ILA_ATTR_HOOK_TYPE]) + hook_type = nla_get_u8(tb[ILA_ATTR_HOOK_TYPE]); + + switch (hook_type) { + case ILA_HOOK_ROUTE_OUTPUT: + lwt_output = true; + break; + case ILA_HOOK_ROUTE_INPUT: + lwt_output = false; + break; + default: + return -EINVAL; + } - if (!tb[ILA_ATTR_LOCATOR]) + if (tb[ILA_ATTR_CSUM_MODE]) + csum_mode = nla_get_u8(tb[ILA_ATTR_CSUM_MODE]); + + if (csum_mode == ILA_CSUM_NEUTRAL_MAP && + ila_csum_neutral_set(iaddr->ident)) { + /* Don't allow translation if checksum neutral bit is + * configured and it's set in the SIR address. + */ return -EINVAL; + } newts = lwtunnel_state_alloc(sizeof(*ilwt)); if (!newts) @@ -166,19 +226,18 @@ static int ila_build_state(struct nlattr *nla, return ret; } + ilwt->lwt_output = !!lwt_output; + p = ila_params_lwtunnel(newts); + p->csum_mode = csum_mode; + p->ident_type = ident_type; p->locator.v64 = (__force __be64)nla_get_u64(tb[ILA_ATTR_LOCATOR]); /* Precompute checksum difference for translation since we * know both the old locator and the new one. */ p->locator_match = iaddr->loc; - p->csum_diff = compute_csum_diff8( - (__be32 *)&p->locator_match, (__be32 *)&p->locator); - - if (tb[ILA_ATTR_CSUM_MODE]) - p->csum_mode = nla_get_u8(tb[ILA_ATTR_CSUM_MODE]); ila_init_saved_csum(p); @@ -203,13 +262,23 @@ static int ila_fill_encap_info(struct sk_buff *skb, struct lwtunnel_state *lwtstate) { struct ila_params *p = ila_params_lwtunnel(lwtstate); + struct ila_lwt *ilwt = ila_lwt_lwtunnel(lwtstate); if (nla_put_u64_64bit(skb, ILA_ATTR_LOCATOR, (__force u64)p->locator.v64, ILA_ATTR_PAD)) goto nla_put_failure; + if (nla_put_u8(skb, ILA_ATTR_CSUM_MODE, (__force u8)p->csum_mode)) goto nla_put_failure; + if (nla_put_u8(skb, ILA_ATTR_IDENT_TYPE, (__force u8)p->ident_type)) + goto nla_put_failure; + + if (nla_put_u8(skb, ILA_ATTR_HOOK_TYPE, + ilwt->lwt_output ? ILA_HOOK_ROUTE_OUTPUT : + ILA_HOOK_ROUTE_INPUT)) + goto nla_put_failure; + return 0; nla_put_failure: @@ -220,6 +289,8 @@ static int ila_encap_nlsize(struct lwtunnel_state *lwtstate) { return nla_total_size_64bit(sizeof(u64)) + /* ILA_ATTR_LOCATOR */ nla_total_size(sizeof(u8)) + /* ILA_ATTR_CSUM_MODE */ + nla_total_size(sizeof(u8)) + /* ILA_ATTR_IDENT_TYPE */ + nla_total_size(sizeof(u8)) + /* ILA_ATTR_HOOK_TYPE */ 0; } diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index 3123b9de91b5..6eb5e68f112a 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -121,6 +121,7 @@ static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = { [ILA_ATTR_LOCATOR_MATCH] = { .type = NLA_U64, }, [ILA_ATTR_IFINDEX] = { .type = NLA_U32, }, [ILA_ATTR_CSUM_MODE] = { .type = NLA_U8, }, + [ILA_ATTR_IDENT_TYPE] = { .type = NLA_U8, }, }; static int parse_nl_config(struct genl_info *info, @@ -138,6 +139,14 @@ static int parse_nl_config(struct genl_info *info, if (info->attrs[ILA_ATTR_CSUM_MODE]) xp->ip.csum_mode = nla_get_u8(info->attrs[ILA_ATTR_CSUM_MODE]); + else + xp->ip.csum_mode = ILA_CSUM_NO_ACTION; + + if (info->attrs[ILA_ATTR_IDENT_TYPE]) + xp->ip.ident_type = nla_get_u8( + info->attrs[ILA_ATTR_IDENT_TYPE]); + else + xp->ip.ident_type = ILA_ATYPE_USE_FORMAT; if (info->attrs[ILA_ATTR_IFINDEX]) xp->ifindex = nla_get_s32(info->attrs[ILA_ATTR_IFINDEX]); @@ -198,7 +207,7 @@ static void ila_free_cb(void *ptr, void *arg) } } -static int ila_xlat_addr(struct sk_buff *skb, bool set_csum_neutral); +static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila); static unsigned int ila_nf_input(void *priv, @@ -396,7 +405,8 @@ static int ila_fill_info(struct ila_map *ila, struct sk_buff *msg) (__force u64)ila->xp.ip.locator_match.v64, ILA_ATTR_PAD) || nla_put_s32(msg, ILA_ATTR_IFINDEX, ila->xp.ifindex) || - nla_put_u32(msg, ILA_ATTR_CSUM_MODE, ila->xp.ip.csum_mode)) + nla_put_u8(msg, ILA_ATTR_CSUM_MODE, ila->xp.ip.csum_mode) || + nla_put_u8(msg, ILA_ATTR_IDENT_TYPE, ila->xp.ip.ident_type)) return -1; return 0; @@ -607,7 +617,7 @@ static struct pernet_operations ila_net_ops = { .size = sizeof(struct ila_net), }; -static int ila_xlat_addr(struct sk_buff *skb, bool set_csum_neutral) +static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila) { struct ila_map *ila; struct ipv6hdr *ip6h = ipv6_hdr(skb); @@ -617,16 +627,16 @@ static int ila_xlat_addr(struct sk_buff *skb, bool set_csum_neutral) /* Assumes skb contains a valid IPv6 header that is pulled */ - if (!ila_addr_is_ila(iaddr)) { - /* Type indicates this is not an ILA address */ - return 0; - } + /* No check here that ILA type in the mapping matches what is in the + * address. We assume that whatever sender gaves us can be translated. + * The checksum mode however is relevant. + */ rcu_read_lock(); ila = ila_lookup_wildcards(iaddr, skb->dev->ifindex, ilan); if (ila) - ila_update_ipv6_locator(skb, &ila->xp.ip, set_csum_neutral); + ila_update_ipv6_locator(skb, &ila->xp.ip, sir2ila); rcu_read_unlock(); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index e5308d7cbd75..2e2804f5823e 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -38,14 +38,6 @@ #include <net/ip6_fib.h> #include <net/ip6_route.h> -#define RT6_DEBUG 2 - -#if RT6_DEBUG >= 3 -#define RT6_TRACE(x...) pr_debug(x) -#else -#define RT6_TRACE(x...) do { ; } while (0) -#endif - static struct kmem_cache *fib6_node_kmem __read_mostly; struct fib6_cleaner { @@ -62,9 +54,12 @@ struct fib6_cleaner { #define FWS_INIT FWS_L #endif -static void fib6_prune_clones(struct net *net, struct fib6_node *fn); -static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn); -static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_node *fn); +static struct rt6_info *fib6_find_prefix(struct net *net, + struct fib6_table *table, + struct fib6_node *fn); +static struct fib6_node *fib6_repair_tree(struct net *net, + struct fib6_table *table, + struct fib6_node *fn); static int fib6_walk(struct net *net, struct fib6_walker *w); static int fib6_walk_continue(struct fib6_walker *w); @@ -110,6 +105,20 @@ enum { FIB6_NO_SERNUM_CHANGE = 0, }; +void fib6_update_sernum(struct rt6_info *rt) +{ + struct fib6_table *table = rt->rt6i_table; + struct net *net = dev_net(rt->dst.dev); + struct fib6_node *fn; + + spin_lock_bh(&table->tb6_lock); + fn = rcu_dereference_protected(rt->rt6i_node, + lockdep_is_held(&table->tb6_lock)); + if (fn) + fn->fn_sernum = fib6_new_sernum(net); + spin_unlock_bh(&table->tb6_lock); +} + /* * Auxiliary address test functions for the radix tree. * @@ -140,18 +149,21 @@ static __be32 addr_bit_set(const void *token, int fn_bit) addr[fn_bit >> 5]; } -static struct fib6_node *node_alloc(void) +static struct fib6_node *node_alloc(struct net *net) { struct fib6_node *fn; fn = kmem_cache_zalloc(fib6_node_kmem, GFP_ATOMIC); + if (fn) + net->ipv6.rt6_stats->fib_nodes++; return fn; } -static void node_free_immediate(struct fib6_node *fn) +static void node_free_immediate(struct net *net, struct fib6_node *fn) { kmem_cache_free(fib6_node_kmem, fn); + net->ipv6.rt6_stats->fib_nodes--; } static void node_free_rcu(struct rcu_head *head) @@ -161,9 +173,10 @@ static void node_free_rcu(struct rcu_head *head) kmem_cache_free(fib6_node_kmem, fn); } -static void node_free(struct fib6_node *fn) +static void node_free(struct net *net, struct fib6_node *fn) { call_rcu(&fn->rcu, node_free_rcu); + net->ipv6.rt6_stats->fib_nodes--; } void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) @@ -185,9 +198,6 @@ void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) *ppcpu_rt = NULL; } } - - free_percpu(non_pcpu_rt->rt6i_pcpu); - non_pcpu_rt->rt6i_pcpu = NULL; } EXPORT_SYMBOL_GPL(rt6_free_pcpu); @@ -205,8 +215,7 @@ static void fib6_link_table(struct net *net, struct fib6_table *tb) * Initialize table lock at a single place to give lockdep a key, * tables aren't visible prior to being linked to the list. */ - rwlock_init(&tb->tb6_lock); - + spin_lock_init(&tb->tb6_lock); h = tb->tb6_id & (FIB6_TABLE_HASHSZ - 1); /* @@ -225,7 +234,8 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) table = kzalloc(sizeof(*table), GFP_ATOMIC); if (table) { table->tb6_id = id; - table->tb6_root.leaf = net->ipv6.ip6_null_entry; + rcu_assign_pointer(table->tb6_root.leaf, + net->ipv6.ip6_null_entry); table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&table->tb6_peers); } @@ -322,11 +332,8 @@ unsigned int fib6_tables_seq_read(struct net *net) struct hlist_head *head = &net->ipv6.fib_table_hash[h]; struct fib6_table *tb; - hlist_for_each_entry_rcu(tb, head, tb6_hlist) { - read_lock_bh(&tb->tb6_lock); + hlist_for_each_entry_rcu(tb, head, tb6_hlist) fib_seq += tb->fib_seq; - read_unlock_bh(&tb->tb6_lock); - } } rcu_read_unlock(); @@ -346,9 +353,11 @@ static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net, static int call_fib6_entry_notifiers(struct net *net, enum fib_event_type event_type, - struct rt6_info *rt) + struct rt6_info *rt, + struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { + .info.extack = extack, .rt = rt, }; @@ -372,7 +381,7 @@ static int fib6_node_dump(struct fib6_walker *w) { struct rt6_info *rt; - for (rt = w->leaf; rt; rt = rt->dst.rt6_next) + for_each_fib6_walker_rt(w) fib6_rt_dump(rt, w->args); w->leaf = NULL; return 0; @@ -382,9 +391,9 @@ static void fib6_table_dump(struct net *net, struct fib6_table *tb, struct fib6_walker *w) { w->root = &tb->tb6_root; - read_lock_bh(&tb->tb6_lock); + spin_lock_bh(&tb->tb6_lock); fib6_walk(net, w); - read_unlock_bh(&tb->tb6_lock); + spin_unlock_bh(&tb->tb6_lock); } /* Called with rcu_read_lock() */ @@ -421,7 +430,7 @@ static int fib6_dump_node(struct fib6_walker *w) int res; struct rt6_info *rt; - for (rt = w->leaf; rt; rt = rt->dst.rt6_next) { + for_each_fib6_walker_rt(w) { res = rt6_dump_route(rt, w->args); if (res < 0) { /* Frame is full, suspend walking */ @@ -480,9 +489,9 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, w->count = 0; w->skip = 0; - read_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); res = fib6_walk(net, w); - read_unlock_bh(&table->tb6_lock); + spin_unlock_bh(&table->tb6_lock); if (res > 0) { cb->args[4] = 1; cb->args[5] = w->root->fn_sernum; @@ -497,9 +506,9 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, } else w->skip = 0; - read_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); res = fib6_walk_continue(w); - read_unlock_bh(&table->tb6_lock); + spin_unlock_bh(&table->tb6_lock); if (res <= 0) { fib6_walker_unlink(net, w); cb->args[4] = 0; @@ -580,11 +589,13 @@ out: * node. */ -static struct fib6_node *fib6_add_1(struct fib6_node *root, - struct in6_addr *addr, int plen, - int offset, int allow_create, - int replace_required, int sernum, - struct netlink_ext_ack *extack) +static struct fib6_node *fib6_add_1(struct net *net, + struct fib6_table *table, + struct fib6_node *root, + struct in6_addr *addr, int plen, + int offset, int allow_create, + int replace_required, + struct netlink_ext_ack *extack) { struct fib6_node *fn, *in, *ln; struct fib6_node *pn = NULL; @@ -599,7 +610,9 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, fn = root; do { - key = (struct rt6key *)((u8 *)fn->leaf + offset); + struct rt6_info *leaf = rcu_dereference_protected(fn->leaf, + lockdep_is_held(&table->tb6_lock)); + key = (struct rt6key *)((u8 *)leaf + offset); /* * Prefix match @@ -625,12 +638,10 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, if (plen == fn->fn_bit) { /* clean up an intermediate node */ if (!(fn->fn_flags & RTN_RTINFO)) { - rt6_release(fn->leaf); - fn->leaf = NULL; + RCU_INIT_POINTER(fn->leaf, NULL); + rt6_release(leaf); } - fn->fn_sernum = sernum; - return fn; } @@ -639,10 +650,13 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, */ /* Try to walk down on tree. */ - fn->fn_sernum = sernum; dir = addr_bit_set(addr, fn->fn_bit); pn = fn; - fn = dir ? fn->right : fn->left; + fn = dir ? + rcu_dereference_protected(fn->right, + lockdep_is_held(&table->tb6_lock)) : + rcu_dereference_protected(fn->left, + lockdep_is_held(&table->tb6_lock)); } while (fn); if (!allow_create) { @@ -668,19 +682,17 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, * Create new leaf node without children. */ - ln = node_alloc(); + ln = node_alloc(net); if (!ln) return ERR_PTR(-ENOMEM); ln->fn_bit = plen; - - ln->parent = pn; - ln->fn_sernum = sernum; + RCU_INIT_POINTER(ln->parent, pn); if (dir) - pn->right = ln; + rcu_assign_pointer(pn->right, ln); else - pn->left = ln; + rcu_assign_pointer(pn->left, ln); return ln; @@ -694,7 +706,8 @@ insert_above: * and the current */ - pn = fn->parent; + pn = rcu_dereference_protected(fn->parent, + lockdep_is_held(&table->tb6_lock)); /* find 1st bit in difference between the 2 addrs. @@ -710,14 +723,14 @@ insert_above: * (new leaf node)[ln] (old node)[fn] */ if (plen > bit) { - in = node_alloc(); - ln = node_alloc(); + in = node_alloc(net); + ln = node_alloc(net); if (!in || !ln) { if (in) - node_free_immediate(in); + node_free_immediate(net, in); if (ln) - node_free_immediate(ln); + node_free_immediate(net, ln); return ERR_PTR(-ENOMEM); } @@ -731,31 +744,28 @@ insert_above: in->fn_bit = bit; - in->parent = pn; + RCU_INIT_POINTER(in->parent, pn); in->leaf = fn->leaf; - atomic_inc(&in->leaf->rt6i_ref); - - in->fn_sernum = sernum; + atomic_inc(&rcu_dereference_protected(in->leaf, + lockdep_is_held(&table->tb6_lock))->rt6i_ref); /* update parent pointer */ if (dir) - pn->right = in; + rcu_assign_pointer(pn->right, in); else - pn->left = in; + rcu_assign_pointer(pn->left, in); ln->fn_bit = plen; - ln->parent = in; - fn->parent = in; - - ln->fn_sernum = sernum; + RCU_INIT_POINTER(ln->parent, in); + rcu_assign_pointer(fn->parent, in); if (addr_bit_set(addr, bit)) { - in->right = ln; - in->left = fn; + rcu_assign_pointer(in->right, ln); + rcu_assign_pointer(in->left, fn); } else { - in->left = ln; - in->right = fn; + rcu_assign_pointer(in->left, ln); + rcu_assign_pointer(in->right, fn); } } else { /* plen <= bit */ @@ -765,28 +775,26 @@ insert_above: * (old node)[fn] NULL */ - ln = node_alloc(); + ln = node_alloc(net); if (!ln) return ERR_PTR(-ENOMEM); ln->fn_bit = plen; - ln->parent = pn; - - ln->fn_sernum = sernum; - - if (dir) - pn->right = ln; - else - pn->left = ln; + RCU_INIT_POINTER(ln->parent, pn); if (addr_bit_set(&key->addr, plen)) - ln->right = fn; + RCU_INIT_POINTER(ln->right, fn); else - ln->left = fn; + RCU_INIT_POINTER(ln->left, fn); + + rcu_assign_pointer(fn->parent, ln); - fn->parent = ln; + if (dir) + rcu_assign_pointer(pn->right, ln); + else + rcu_assign_pointer(pn->left, ln); } return ln; } @@ -832,6 +840,8 @@ static int fib6_commit_metrics(struct dst_entry *dst, struct mx6_config *mxc) static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, struct net *net) { + struct fib6_table *table = rt->rt6i_table; + if (atomic_read(&rt->rt6i_ref) != 1) { /* This route is used as dummy address holder in some split * nodes. It is not leaked, but it still holds other resources, @@ -840,12 +850,17 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, * to still alive ones. */ while (fn) { - if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) { - fn->leaf = fib6_find_prefix(net, fn); - atomic_inc(&fn->leaf->rt6i_ref); + struct rt6_info *leaf = rcu_dereference_protected(fn->leaf, + lockdep_is_held(&table->tb6_lock)); + struct rt6_info *new_leaf; + if (!(fn->fn_flags & RTN_RTINFO) && leaf == rt) { + new_leaf = fib6_find_prefix(net, table, fn); + atomic_inc(&new_leaf->rt6i_ref); + rcu_assign_pointer(fn->leaf, new_leaf); rt6_release(rt); } - fn = fn->parent; + fn = rcu_dereference_protected(fn->parent, + lockdep_is_held(&table->tb6_lock)); } } } @@ -855,11 +870,14 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, */ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, - struct nl_info *info, struct mx6_config *mxc) + struct nl_info *info, struct mx6_config *mxc, + struct netlink_ext_ack *extack) { + struct rt6_info *leaf = rcu_dereference_protected(fn->leaf, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); struct rt6_info *iter = NULL; - struct rt6_info **ins; - struct rt6_info **fallback_ins = NULL; + struct rt6_info __rcu **ins; + struct rt6_info __rcu **fallback_ins = NULL; int replace = (info->nlh && (info->nlh->nlmsg_flags & NLM_F_REPLACE)); int add = (!info->nlh || @@ -874,7 +892,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, ins = &fn->leaf; - for (iter = fn->leaf; iter; iter = iter->dst.rt6_next) { + for (iter = leaf; iter; + iter = rcu_dereference_protected(iter->dst.rt6_next, + lockdep_is_held(&rt->rt6i_table->tb6_lock))) { /* * Search for duplicates */ @@ -936,7 +956,8 @@ next_iter: if (fallback_ins && !found) { /* No ECMP-able route found, replace first non-ECMP one */ ins = fallback_ins; - iter = *ins; + iter = rcu_dereference_protected(*ins, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); found++; } @@ -950,7 +971,7 @@ next_iter: struct rt6_info *sibling, *temp_sibling; /* Find the first route that have the same metric */ - sibling = fn->leaf; + sibling = leaf; while (sibling) { if (sibling->rt6i_metric == rt->rt6i_metric && rt6_qualify_for_ecmp(sibling)) { @@ -958,7 +979,8 @@ next_iter: &sibling->rt6i_siblings); break; } - sibling = sibling->dst.rt6_next; + sibling = rcu_dereference_protected(sibling->dst.rt6_next, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); } /* For each sibling in the list, increment the counter of * siblings. BUG() if counters does not match, list of siblings @@ -987,12 +1009,12 @@ add: if (err) return err; - rt->dst.rt6_next = iter; - *ins = rt; - rcu_assign_pointer(rt->rt6i_node, fn); + rcu_assign_pointer(rt->dst.rt6_next, iter); atomic_inc(&rt->rt6i_ref); + rcu_assign_pointer(rt->rt6i_node, fn); + rcu_assign_pointer(*ins, rt); call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_ADD, - rt); + rt, extack); if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); info->nl_net->ipv6.rt6_stats->fib_rt_entries++; @@ -1016,12 +1038,12 @@ add: if (err) return err; - *ins = rt; + atomic_inc(&rt->rt6i_ref); rcu_assign_pointer(rt->rt6i_node, fn); rt->dst.rt6_next = iter->dst.rt6_next; - atomic_inc(&rt->rt6i_ref); + rcu_assign_pointer(*ins, rt); call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_REPLACE, - rt); + rt, extack); if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE); if (!(fn->fn_flags & RTN_RTINFO)) { @@ -1031,14 +1053,15 @@ add: nsiblings = iter->rt6i_nsiblings; iter->rt6i_node = NULL; fib6_purge_rt(iter, fn, info->nl_net); - if (fn->rr_ptr == iter) + if (rcu_access_pointer(fn->rr_ptr) == iter) fn->rr_ptr = NULL; rt6_release(iter); if (nsiblings) { /* Replacing an ECMP route, remove all siblings */ ins = &rt->dst.rt6_next; - iter = *ins; + iter = rcu_dereference_protected(*ins, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); while (iter) { if (iter->rt6i_metric > rt->rt6i_metric) break; @@ -1046,14 +1069,16 @@ add: *ins = iter->dst.rt6_next; iter->rt6i_node = NULL; fib6_purge_rt(iter, fn, info->nl_net); - if (fn->rr_ptr == iter) + if (rcu_access_pointer(fn->rr_ptr) == iter) fn->rr_ptr = NULL; rt6_release(iter); nsiblings--; + info->nl_net->ipv6.rt6_stats->fib_rt_entries--; } else { ins = &iter->dst.rt6_next; } - iter = *ins; + iter = rcu_dereference_protected(*ins, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); } WARN_ON(nsiblings != 0); } @@ -1077,16 +1102,33 @@ void fib6_force_start_gc(struct net *net) jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } +static void fib6_update_sernum_upto_root(struct rt6_info *rt, + int sernum) +{ + struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); + + /* paired with smp_rmb() in rt6_get_cookie_safe() */ + smp_wmb(); + while (fn) { + fn->fn_sernum = sernum; + fn = rcu_dereference_protected(fn->parent, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); + } +} + /* * Add routing information to the routing tree. * <destination addr>/<source addr> * with source addr info in sub-trees + * Need to own table->tb6_lock */ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info, struct mx6_config *mxc, struct netlink_ext_ack *extack) { + struct fib6_table *table = rt->rt6i_table; struct fib6_node *fn, *pn = NULL; int err = -ENOMEM; int allow_create = 1; @@ -1095,6 +1137,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, if (WARN_ON_ONCE(!atomic_read(&rt->dst.__refcnt))) return -EINVAL; + if (WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE)) + return -EINVAL; if (info->nlh) { if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) @@ -1105,9 +1149,10 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, if (!allow_create && !replace_required) pr_warn("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n"); - fn = fib6_add_1(root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen, + fn = fib6_add_1(info->nl_net, table, root, + &rt->rt6i_dst.addr, rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst), allow_create, - replace_required, sernum, extack); + replace_required, extack); if (IS_ERR(fn)) { err = PTR_ERR(fn); fn = NULL; @@ -1120,7 +1165,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, if (rt->rt6i_src.plen) { struct fib6_node *sn; - if (!fn->subtree) { + if (!rcu_access_pointer(fn->subtree)) { struct fib6_node *sfn; /* @@ -1134,42 +1179,40 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, */ /* Create subtree root node */ - sfn = node_alloc(); + sfn = node_alloc(info->nl_net); if (!sfn) goto failure; - sfn->leaf = info->nl_net->ipv6.ip6_null_entry; atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref); + rcu_assign_pointer(sfn->leaf, + info->nl_net->ipv6.ip6_null_entry); sfn->fn_flags = RTN_ROOT; - sfn->fn_sernum = sernum; /* Now add the first leaf node to new subtree */ - sn = fib6_add_1(sfn, &rt->rt6i_src.addr, - rt->rt6i_src.plen, + sn = fib6_add_1(info->nl_net, table, sfn, + &rt->rt6i_src.addr, rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), - allow_create, replace_required, sernum, - extack); + allow_create, replace_required, extack); if (IS_ERR(sn)) { /* If it is failed, discard just allocated root, and then (in failure) stale node in main tree. */ - node_free_immediate(sfn); + node_free_immediate(info->nl_net, sfn); err = PTR_ERR(sn); goto failure; } /* Now link new subtree to main tree */ - sfn->parent = fn; - fn->subtree = sfn; + rcu_assign_pointer(sfn->parent, fn); + rcu_assign_pointer(fn->subtree, sfn); } else { - sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr, - rt->rt6i_src.plen, + sn = fib6_add_1(info->nl_net, table, FIB6_SUBTREE(fn), + &rt->rt6i_src.addr, rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), - allow_create, replace_required, sernum, - extack); + allow_create, replace_required, extack); if (IS_ERR(sn)) { err = PTR_ERR(sn); @@ -1177,19 +1220,18 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, } } - if (!fn->leaf) { - fn->leaf = rt; + if (!rcu_access_pointer(fn->leaf)) { atomic_inc(&rt->rt6i_ref); + rcu_assign_pointer(fn->leaf, rt); } fn = sn; } #endif - err = fib6_add_rt2node(fn, rt, info, mxc); + err = fib6_add_rt2node(fn, rt, info, mxc, extack); if (!err) { + fib6_update_sernum_upto_root(rt, sernum); fib6_start_gc(info->nl_net, rt); - if (!(rt->rt6i_flags & RTF_CACHE)) - fib6_prune_clones(info->nl_net, pn); } out: @@ -1199,19 +1241,23 @@ out: * If fib6_add_1 has cleared the old leaf pointer in the * super-tree leaf node we have to find a new one for it. */ - if (pn != fn && pn->leaf == rt) { - pn->leaf = NULL; + struct rt6_info *pn_leaf = rcu_dereference_protected(pn->leaf, + lockdep_is_held(&table->tb6_lock)); + if (pn != fn && pn_leaf == rt) { + pn_leaf = NULL; + RCU_INIT_POINTER(pn->leaf, NULL); atomic_dec(&rt->rt6i_ref); } - if (pn != fn && !pn->leaf && !(pn->fn_flags & RTN_RTINFO)) { - pn->leaf = fib6_find_prefix(info->nl_net, pn); + if (pn != fn && !pn_leaf && !(pn->fn_flags & RTN_RTINFO)) { + pn_leaf = fib6_find_prefix(info->nl_net, table, pn); #if RT6_DEBUG >= 2 - if (!pn->leaf) { - WARN_ON(pn->leaf == NULL); - pn->leaf = info->nl_net->ipv6.ip6_null_entry; + if (!pn_leaf) { + WARN_ON(!pn_leaf); + pn_leaf = info->nl_net->ipv6.ip6_null_entry; } #endif - atomic_inc(&pn->leaf->rt6i_ref); + atomic_inc(&pn_leaf->rt6i_ref); + rcu_assign_pointer(pn->leaf, pn_leaf); } #endif goto failure; @@ -1226,7 +1272,7 @@ failure: * fn->leaf. */ if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT))) - fib6_repair_tree(info->nl_net, fn); + fib6_repair_tree(info->nl_net, table, fn); /* Always release dst as dst->__refcnt is guaranteed * to be taken before entering this function */ @@ -1264,7 +1310,8 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root, dir = addr_bit_set(args->addr, fn->fn_bit); - next = dir ? fn->right : fn->left; + next = dir ? rcu_dereference(fn->right) : + rcu_dereference(fn->left); if (next) { fn = next; @@ -1274,18 +1321,22 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root, } while (fn) { - if (FIB6_SUBTREE(fn) || fn->fn_flags & RTN_RTINFO) { + struct fib6_node *subtree = FIB6_SUBTREE(fn); + + if (subtree || fn->fn_flags & RTN_RTINFO) { + struct rt6_info *leaf = rcu_dereference(fn->leaf); struct rt6key *key; - key = (struct rt6key *) ((u8 *) fn->leaf + - args->offset); + if (!leaf) + goto backtrack; + + key = (struct rt6key *) ((u8 *)leaf + args->offset); if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) { #ifdef CONFIG_IPV6_SUBTREES - if (fn->subtree) { + if (subtree) { struct fib6_node *sfn; - sfn = fib6_lookup_1(fn->subtree, - args + 1); + sfn = fib6_lookup_1(subtree, args + 1); if (!sfn) goto backtrack; fn = sfn; @@ -1295,18 +1346,18 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root, return fn; } } -#ifdef CONFIG_IPV6_SUBTREES backtrack: -#endif if (fn->fn_flags & RTN_ROOT) break; - fn = fn->parent; + fn = rcu_dereference(fn->parent); } return NULL; } +/* called with rcu_read_lock() held + */ struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr, const struct in6_addr *saddr) { @@ -1337,54 +1388,87 @@ struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *dad /* * Get node with specified destination prefix (and source prefix, * if subtrees are used) + * exact_match == true means we try to find fn with exact match of + * the passed in prefix addr + * exact_match == false means we try to find fn with longest prefix + * match of the passed in prefix addr. This is useful for finding fn + * for cached route as it will be stored in the exception table under + * the node with longest prefix length. */ static struct fib6_node *fib6_locate_1(struct fib6_node *root, const struct in6_addr *addr, - int plen, int offset) + int plen, int offset, + bool exact_match) { - struct fib6_node *fn; + struct fib6_node *fn, *prev = NULL; for (fn = root; fn ; ) { - struct rt6key *key = (struct rt6key *)((u8 *)fn->leaf + offset); + struct rt6_info *leaf = rcu_dereference(fn->leaf); + struct rt6key *key; + + /* This node is being deleted */ + if (!leaf) { + if (plen <= fn->fn_bit) + goto out; + else + goto next; + } + + key = (struct rt6key *)((u8 *)leaf + offset); /* * Prefix match */ if (plen < fn->fn_bit || !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) - return NULL; + goto out; if (plen == fn->fn_bit) return fn; + prev = fn; + +next: /* * We have more bits to go */ if (addr_bit_set(addr, fn->fn_bit)) - fn = fn->right; + fn = rcu_dereference(fn->right); else - fn = fn->left; + fn = rcu_dereference(fn->left); } - return NULL; +out: + if (exact_match) + return NULL; + else + return prev; } struct fib6_node *fib6_locate(struct fib6_node *root, const struct in6_addr *daddr, int dst_len, - const struct in6_addr *saddr, int src_len) + const struct in6_addr *saddr, int src_len, + bool exact_match) { struct fib6_node *fn; fn = fib6_locate_1(root, daddr, dst_len, - offsetof(struct rt6_info, rt6i_dst)); + offsetof(struct rt6_info, rt6i_dst), + exact_match); #ifdef CONFIG_IPV6_SUBTREES if (src_len) { WARN_ON(saddr == NULL); - if (fn && fn->subtree) - fn = fib6_locate_1(fn->subtree, saddr, src_len, - offsetof(struct rt6_info, rt6i_src)); + if (fn) { + struct fib6_node *subtree = FIB6_SUBTREE(fn); + + if (subtree) { + fn = fib6_locate_1(subtree, saddr, src_len, + offsetof(struct rt6_info, rt6i_src), + exact_match); + } + } } #endif @@ -1400,16 +1484,26 @@ struct fib6_node *fib6_locate(struct fib6_node *root, * */ -static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn) +static struct rt6_info *fib6_find_prefix(struct net *net, + struct fib6_table *table, + struct fib6_node *fn) { + struct fib6_node *child_left, *child_right; + if (fn->fn_flags & RTN_ROOT) return net->ipv6.ip6_null_entry; while (fn) { - if (fn->left) - return fn->left->leaf; - if (fn->right) - return fn->right->leaf; + child_left = rcu_dereference_protected(fn->left, + lockdep_is_held(&table->tb6_lock)); + child_right = rcu_dereference_protected(fn->right, + lockdep_is_held(&table->tb6_lock)); + if (child_left) + return rcu_dereference_protected(child_left->leaf, + lockdep_is_held(&table->tb6_lock)); + if (child_right) + return rcu_dereference_protected(child_right->leaf, + lockdep_is_held(&table->tb6_lock)); fn = FIB6_SUBTREE(fn); } @@ -1419,31 +1513,49 @@ static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn) /* * Called to trim the tree of intermediate nodes when possible. "fn" * is the node we want to try and remove. + * Need to own table->tb6_lock */ static struct fib6_node *fib6_repair_tree(struct net *net, - struct fib6_node *fn) + struct fib6_table *table, + struct fib6_node *fn) { int children; int nstate; - struct fib6_node *child, *pn; + struct fib6_node *child; struct fib6_walker *w; int iter = 0; for (;;) { + struct fib6_node *fn_r = rcu_dereference_protected(fn->right, + lockdep_is_held(&table->tb6_lock)); + struct fib6_node *fn_l = rcu_dereference_protected(fn->left, + lockdep_is_held(&table->tb6_lock)); + struct fib6_node *pn = rcu_dereference_protected(fn->parent, + lockdep_is_held(&table->tb6_lock)); + struct fib6_node *pn_r = rcu_dereference_protected(pn->right, + lockdep_is_held(&table->tb6_lock)); + struct fib6_node *pn_l = rcu_dereference_protected(pn->left, + lockdep_is_held(&table->tb6_lock)); + struct rt6_info *fn_leaf = rcu_dereference_protected(fn->leaf, + lockdep_is_held(&table->tb6_lock)); + struct rt6_info *pn_leaf = rcu_dereference_protected(pn->leaf, + lockdep_is_held(&table->tb6_lock)); + struct rt6_info *new_fn_leaf; + RT6_TRACE("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter); iter++; WARN_ON(fn->fn_flags & RTN_RTINFO); WARN_ON(fn->fn_flags & RTN_TL_ROOT); - WARN_ON(fn->leaf); + WARN_ON(fn_leaf); children = 0; child = NULL; - if (fn->right) - child = fn->right, children |= 1; - if (fn->left) - child = fn->left, children |= 2; + if (fn_r) + child = fn_r, children |= 1; + if (fn_l) + child = fn_l, children |= 2; if (children == 3 || FIB6_SUBTREE(fn) #ifdef CONFIG_IPV6_SUBTREES @@ -1451,36 +1563,36 @@ static struct fib6_node *fib6_repair_tree(struct net *net, || (children && fn->fn_flags & RTN_ROOT) #endif ) { - fn->leaf = fib6_find_prefix(net, fn); + new_fn_leaf = fib6_find_prefix(net, table, fn); #if RT6_DEBUG >= 2 - if (!fn->leaf) { - WARN_ON(!fn->leaf); - fn->leaf = net->ipv6.ip6_null_entry; + if (!new_fn_leaf) { + WARN_ON(!new_fn_leaf); + new_fn_leaf = net->ipv6.ip6_null_entry; } #endif - atomic_inc(&fn->leaf->rt6i_ref); - return fn->parent; + atomic_inc(&new_fn_leaf->rt6i_ref); + rcu_assign_pointer(fn->leaf, new_fn_leaf); + return pn; } - pn = fn->parent; #ifdef CONFIG_IPV6_SUBTREES if (FIB6_SUBTREE(pn) == fn) { WARN_ON(!(fn->fn_flags & RTN_ROOT)); - FIB6_SUBTREE(pn) = NULL; + RCU_INIT_POINTER(pn->subtree, NULL); nstate = FWS_L; } else { WARN_ON(fn->fn_flags & RTN_ROOT); #endif - if (pn->right == fn) - pn->right = child; - else if (pn->left == fn) - pn->left = child; + if (pn_r == fn) + rcu_assign_pointer(pn->right, child); + else if (pn_l == fn) + rcu_assign_pointer(pn->left, child); #if RT6_DEBUG >= 2 else WARN_ON(1); #endif if (child) - child->parent = pn; + rcu_assign_pointer(child->parent, pn); nstate = FWS_R; #ifdef CONFIG_IPV6_SUBTREES } @@ -1489,19 +1601,12 @@ static struct fib6_node *fib6_repair_tree(struct net *net, read_lock(&net->ipv6.fib6_walker_lock); FOR_WALKERS(net, w) { if (!child) { - if (w->root == fn) { - w->root = w->node = NULL; - RT6_TRACE("W %p adjusted by delroot 1\n", w); - } else if (w->node == fn) { + if (w->node == fn) { RT6_TRACE("W %p adjusted by delnode 1, s=%d/%d\n", w, w->state, nstate); w->node = pn; w->state = nstate; } } else { - if (w->root == fn) { - w->root = child; - RT6_TRACE("W %p adjusted by delroot 2\n", w); - } if (w->node == fn) { w->node = child; if (children&2) { @@ -1516,33 +1621,39 @@ static struct fib6_node *fib6_repair_tree(struct net *net, } read_unlock(&net->ipv6.fib6_walker_lock); - node_free(fn); + node_free(net, fn); if (pn->fn_flags & RTN_RTINFO || FIB6_SUBTREE(pn)) return pn; - rt6_release(pn->leaf); - pn->leaf = NULL; + RCU_INIT_POINTER(pn->leaf, NULL); + rt6_release(pn_leaf); fn = pn; } } -static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, - struct nl_info *info) +static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, + struct rt6_info __rcu **rtp, struct nl_info *info) { struct fib6_walker *w; - struct rt6_info *rt = *rtp; + struct rt6_info *rt = rcu_dereference_protected(*rtp, + lockdep_is_held(&table->tb6_lock)); struct net *net = info->nl_net; RT6_TRACE("fib6_del_route\n"); + WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE); + /* Unlink it */ *rtp = rt->dst.rt6_next; rt->rt6i_node = NULL; net->ipv6.rt6_stats->fib_rt_entries--; net->ipv6.rt6_stats->fib_discarded_routes++; + /* Flush all cached dst in exception table */ + rt6_flush_exceptions(rt); + /* Reset round-robin state, if necessary */ - if (fn->rr_ptr == rt) + if (rcu_access_pointer(fn->rr_ptr) == rt) fn->rr_ptr = NULL; /* Remove this entry from other siblings */ @@ -1561,36 +1672,38 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, FOR_WALKERS(net, w) { if (w->state == FWS_C && w->leaf == rt) { RT6_TRACE("walker %p adjusted by delroute\n", w); - w->leaf = rt->dst.rt6_next; + w->leaf = rcu_dereference_protected(rt->dst.rt6_next, + lockdep_is_held(&table->tb6_lock)); if (!w->leaf) w->state = FWS_U; } } read_unlock(&net->ipv6.fib6_walker_lock); - rt->dst.rt6_next = NULL; - /* If it was last route, expunge its radix tree node */ - if (!fn->leaf) { + if (!rcu_access_pointer(fn->leaf)) { fn->fn_flags &= ~RTN_RTINFO; net->ipv6.rt6_stats->fib_route_nodes--; - fn = fib6_repair_tree(net, fn); + fn = fib6_repair_tree(net, table, fn); } fib6_purge_rt(rt, fn, net); - call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt); + call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, NULL); if (!info->skip_notify) inet6_rt_notify(RTM_DELROUTE, rt, info, 0); rt6_release(rt); } +/* Need to own table->tb6_lock */ int fib6_del(struct rt6_info *rt, struct nl_info *info) { struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node, lockdep_is_held(&rt->rt6i_table->tb6_lock)); + struct fib6_table *table = rt->rt6i_table; struct net *net = info->nl_net; - struct rt6_info **rtp; + struct rt6_info __rcu **rtp; + struct rt6_info __rcu **rtp_next; #if RT6_DEBUG >= 2 if (rt->dst.obsolete > 0) { @@ -1603,28 +1716,22 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info) WARN_ON(!(fn->fn_flags & RTN_RTINFO)); - if (!(rt->rt6i_flags & RTF_CACHE)) { - struct fib6_node *pn = fn; -#ifdef CONFIG_IPV6_SUBTREES - /* clones of this route might be in another subtree */ - if (rt->rt6i_src.plen) { - while (!(pn->fn_flags & RTN_ROOT)) - pn = pn->parent; - pn = pn->parent; - } -#endif - fib6_prune_clones(info->nl_net, pn); - } + /* remove cached dst from exception table */ + if (rt->rt6i_flags & RTF_CACHE) + return rt6_remove_exception_rt(rt); /* * Walk the leaf entries looking for ourself */ - for (rtp = &fn->leaf; *rtp; rtp = &(*rtp)->dst.rt6_next) { - if (*rtp == rt) { - fib6_del_route(fn, rtp, info); + for (rtp = &fn->leaf; *rtp; rtp = rtp_next) { + struct rt6_info *cur = rcu_dereference_protected(*rtp, + lockdep_is_held(&table->tb6_lock)); + if (rt == cur) { + fib6_del_route(table, fn, rtp, info); return 0; } + rtp_next = &cur->dst.rt6_next; } return -ENOENT; } @@ -1651,22 +1758,22 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info) * 0 -> walk is complete. * >0 -> walk is incomplete (i.e. suspended) * <0 -> walk is terminated by an error. + * + * This function is called with tb6_lock held. */ static int fib6_walk_continue(struct fib6_walker *w) { - struct fib6_node *fn, *pn; + struct fib6_node *fn, *pn, *left, *right; + + /* w->root should always be table->tb6_root */ + WARN_ON_ONCE(!(w->root->fn_flags & RTN_TL_ROOT)); for (;;) { fn = w->node; if (!fn) return 0; - if (w->prune && fn != w->root && - fn->fn_flags & RTN_RTINFO && w->state < FWS_C) { - w->state = FWS_C; - w->leaf = fn->leaf; - } switch (w->state) { #ifdef CONFIG_IPV6_SUBTREES case FWS_S: @@ -1676,21 +1783,26 @@ static int fib6_walk_continue(struct fib6_walker *w) } w->state = FWS_L; #endif + /* fall through */ case FWS_L: - if (fn->left) { - w->node = fn->left; + left = rcu_dereference_protected(fn->left, 1); + if (left) { + w->node = left; w->state = FWS_INIT; continue; } w->state = FWS_R; + /* fall through */ case FWS_R: - if (fn->right) { - w->node = fn->right; + right = rcu_dereference_protected(fn->right, 1); + if (right) { + w->node = right; w->state = FWS_INIT; continue; } w->state = FWS_C; - w->leaf = fn->leaf; + w->leaf = rcu_dereference_protected(fn->leaf, 1); + /* fall through */ case FWS_C: if (w->leaf && fn->fn_flags & RTN_RTINFO) { int err; @@ -1709,10 +1821,13 @@ static int fib6_walk_continue(struct fib6_walker *w) } skip: w->state = FWS_U; + /* fall through */ case FWS_U: if (fn == w->root) return 0; - pn = fn->parent; + pn = rcu_dereference_protected(fn->parent, 1); + left = rcu_dereference_protected(pn->left, 1); + right = rcu_dereference_protected(pn->right, 1); w->node = pn; #ifdef CONFIG_IPV6_SUBTREES if (FIB6_SUBTREE(pn) == fn) { @@ -1721,13 +1836,13 @@ skip: continue; } #endif - if (pn->left == fn) { + if (left == fn) { w->state = FWS_R; continue; } - if (pn->right == fn) { + if (right == fn) { w->state = FWS_C; - w->leaf = w->node->leaf; + w->leaf = rcu_dereference_protected(w->node->leaf, 1); continue; } #if RT6_DEBUG >= 2 @@ -1770,7 +1885,7 @@ static int fib6_clean_node(struct fib6_walker *w) return 0; } - for (rt = w->leaf; rt; rt = rt->dst.rt6_next) { + for_each_fib6_walker_rt(w) { res = c->func(rt, c->arg); if (res < 0) { w->leaf = rt; @@ -1798,20 +1913,16 @@ static int fib6_clean_node(struct fib6_walker *w) * func is called on each route. * It may return -1 -> delete this route. * 0 -> continue walking - * - * prune==1 -> only immediate children of node (certainly, - * ignoring pure split nodes) will be scanned. */ static void fib6_clean_tree(struct net *net, struct fib6_node *root, int (*func)(struct rt6_info *, void *arg), - bool prune, int sernum, void *arg) + int sernum, void *arg) { struct fib6_cleaner c; c.w.root = root; c.w.func = fib6_clean_node; - c.w.prune = prune; c.w.count = 0; c.w.skip = 0; c.func = func; @@ -1834,10 +1945,10 @@ static void __fib6_clean_all(struct net *net, for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, head, tb6_hlist) { - write_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); fib6_clean_tree(net, &table->tb6_root, - func, false, sernum, arg); - write_unlock_bh(&table->tb6_lock); + func, sernum, arg); + spin_unlock_bh(&table->tb6_lock); } } rcu_read_unlock(); @@ -1849,22 +1960,6 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *), __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg); } -static int fib6_prune_clone(struct rt6_info *rt, void *arg) -{ - if (rt->rt6i_flags & RTF_CACHE) { - RT6_TRACE("pruning clone %p\n", rt); - return -1; - } - - return 0; -} - -static void fib6_prune_clones(struct net *net, struct fib6_node *fn) -{ - fib6_clean_tree(net, fn, fib6_prune_clone, true, - FIB6_NO_SERNUM_CHANGE, NULL); -} - static void fib6_flush_trees(struct net *net) { int new_sernum = fib6_new_sernum(net); @@ -1876,12 +1971,6 @@ static void fib6_flush_trees(struct net *net) * Garbage collection */ -struct fib6_gc_args -{ - int timeout; - int more; -}; - static int fib6_age(struct rt6_info *rt, void *arg) { struct fib6_gc_args *gc_args = arg; @@ -1890,9 +1979,6 @@ static int fib6_age(struct rt6_info *rt, void *arg) /* * check addrconf expiration here. * Routes are expired even if they are in use. - * - * Also age clones. Note, that clones are aged out - * only if they are not in use now. */ if (rt->rt6i_flags & RTF_EXPIRES && rt->dst.expires) { @@ -1901,31 +1987,14 @@ static int fib6_age(struct rt6_info *rt, void *arg) return -1; } gc_args->more++; - } else if (rt->rt6i_flags & RTF_CACHE) { - if (time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) - rt->dst.obsolete = DST_OBSOLETE_KILL; - if (atomic_read(&rt->dst.__refcnt) == 1 && - rt->dst.obsolete == DST_OBSOLETE_KILL) { - RT6_TRACE("aging clone %p\n", rt); - return -1; - } else if (rt->rt6i_flags & RTF_GATEWAY) { - struct neighbour *neigh; - __u8 neigh_flags = 0; - - neigh = dst_neigh_lookup(&rt->dst, &rt->rt6i_gateway); - if (neigh) { - neigh_flags = neigh->flags; - neigh_release(neigh); - } - if (!(neigh_flags & NTF_ROUTER)) { - RT6_TRACE("purging route %p via non-router but gateway\n", - rt); - return -1; - } - } - gc_args->more++; } + /* Also age clones in the exception table. + * Note, that clones are aged out + * only if they are not in use now. + */ + rt6_age_exceptions(rt, gc_args, now); + return 0; } @@ -1993,7 +2062,8 @@ static int __net_init fib6_net_init(struct net *net) goto out_fib_table_hash; net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN; - net->ipv6.fib6_main_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry; + rcu_assign_pointer(net->ipv6.fib6_main_tbl->tb6_root.leaf, + net->ipv6.ip6_null_entry); net->ipv6.fib6_main_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers); @@ -2004,7 +2074,8 @@ static int __net_init fib6_net_init(struct net *net) if (!net->ipv6.fib6_local_tbl) goto out_fib6_main_tbl; net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL; - net->ipv6.fib6_local_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry; + rcu_assign_pointer(net->ipv6.fib6_local_tbl->tb6_root.leaf, + net->ipv6.ip6_null_entry); net->ipv6.fib6_local_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers); @@ -2134,7 +2205,9 @@ static int ipv6_route_yield(struct fib6_walker *w) return 1; do { - iter->w.leaf = iter->w.leaf->dst.rt6_next; + iter->w.leaf = rcu_dereference_protected( + iter->w.leaf->dst.rt6_next, + lockdep_is_held(&iter->tbl->tb6_lock)); iter->skip--; if (!iter->skip && iter->w.leaf) return 1; @@ -2199,7 +2272,7 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (!v) goto iter_table; - n = ((struct rt6_info *)v)->dst.rt6_next; + n = rcu_dereference_bh(((struct rt6_info *)v)->dst.rt6_next); if (n) { ++*pos; return n; @@ -2207,9 +2280,9 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) iter_table: ipv6_route_check_sernum(iter); - read_lock(&iter->tbl->tb6_lock); + spin_lock_bh(&iter->tbl->tb6_lock); r = fib6_walk_continue(&iter->w); - read_unlock(&iter->tbl->tb6_lock); + spin_unlock_bh(&iter->tbl->tb6_lock); if (r > 0) { if (v) ++*pos; diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 15535ee327c5..9f2e73c71768 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -47,7 +47,7 @@ static atomic_t fl_size = ATOMIC_INIT(0); static struct ip6_flowlabel __rcu *fl_ht[FL_HASH_MASK+1]; static void ip6_fl_gc(unsigned long dummy); -static DEFINE_TIMER(ip6_fl_gc_timer, ip6_fl_gc, 0, 0); +static DEFINE_TIMER(ip6_fl_gc_timer, ip6_fl_gc); /* FL hash table lock: it protects only of GC */ diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 59c121b932ac..b90bad7a4e56 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -369,6 +369,7 @@ static void ip6gre_tunnel_uninit(struct net_device *dev) static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { + struct net *net = dev_net(skb->dev); const struct gre_base_hdr *greh; const struct ipv6hdr *ipv6h; int grehlen = sizeof(*greh); @@ -402,9 +403,8 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return; switch (type) { - __u32 teli; struct ipv6_tlv_tnl_enc_lim *tel; - __u32 mtu; + __u32 teli; case ICMPV6_DEST_UNREACH: net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n", t->parms.name); @@ -435,12 +435,11 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } return; case ICMPV6_PKT_TOOBIG: - mtu = be32_to_cpu(info) - offset - t->tun_hlen; - if (t->dev->type == ARPHRD_ETHER) - mtu -= ETH_HLEN; - if (mtu < IPV6_MIN_MTU) - mtu = IPV6_MIN_MTU; - t->dev->mtu = mtu; + ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL)); + return; + case NDISC_REDIRECT: + ip6_redirect(skb, net, skb->dev->ifindex, 0, + sock_net_uid(net, NULL)); return; } @@ -503,7 +502,6 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, __u32 *pmtu, __be16 proto) { struct ip6_tnl *tunnel = netdev_priv(dev); - struct dst_entry *dst = skb_dst(skb); __be16 protocol; if (dev->type == ARPHRD_ETHER) @@ -522,10 +520,6 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags, protocol, tunnel->parms.o_key, htonl(tunnel->o_seqno)); - /* TooBig packet may have updated dst->dev's mtu */ - if (dst && dst_mtu(dst) > dst->dev->mtu) - dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu); - return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu, NEXTHDR_GRE); } @@ -1164,19 +1158,21 @@ err_alloc_dev: return err; } -static void __net_exit ip6gre_exit_net(struct net *net) +static void __net_exit ip6gre_exit_batch_net(struct list_head *net_list) { + struct net *net; LIST_HEAD(list); rtnl_lock(); - ip6gre_destroy_tunnels(net, &list); + list_for_each_entry(net, net_list, exit_list) + ip6gre_destroy_tunnels(net, &list); unregister_netdevice_many(&list); rtnl_unlock(); } static struct pernet_operations ip6gre_net_ops = { .init = ip6gre_init_net, - .exit = ip6gre_exit_net, + .exit_batch = ip6gre_exit_batch_net, .id = &ip6gre_net_id, .size = sizeof(struct ip6gre_net), }; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index a1c24443cd9e..3d3092adf1d2 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -471,15 +471,16 @@ static int ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, u8 *type, u8 *code, int *msg, __u32 *info, int offset) { - const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) skb->data; - struct ip6_tnl *t; - int rel_msg = 0; + const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)skb->data; + struct net *net = dev_net(skb->dev); u8 rel_type = ICMPV6_DEST_UNREACH; u8 rel_code = ICMPV6_ADDR_UNREACH; - u8 tproto; __u32 rel_info = 0; - __u16 len; + struct ip6_tnl *t; int err = -ENOENT; + int rel_msg = 0; + u8 tproto; + __u16 len; /* If the packet doesn't contain the original IPv6 header we are in trouble since we might need the source address for further @@ -490,16 +491,15 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, if (!t) goto out; - tproto = ACCESS_ONCE(t->parms.proto); + tproto = READ_ONCE(t->parms.proto); if (tproto != ipproto && tproto != 0) goto out; err = 0; switch (*type) { - __u32 teli; struct ipv6_tlv_tnl_enc_lim *tel; - __u32 mtu; + __u32 mtu, teli; case ICMPV6_DEST_UNREACH: net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n", t->parms.name); @@ -530,11 +530,11 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, } break; case ICMPV6_PKT_TOOBIG: + ip6_update_pmtu(skb, net, htonl(*info), 0, 0, + sock_net_uid(net, NULL)); mtu = *info - offset; if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - t->dev->mtu = mtu; - len = sizeof(*ipv6h) + ntohs(ipv6h->payload_len); if (len > mtu) { rel_type = ICMPV6_PKT_TOOBIG; @@ -543,6 +543,10 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, rel_msg = 1; } break; + case NDISC_REDIRECT: + ip6_redirect(skb, net, skb->dev->ifindex, 0, + sock_net_uid(net, NULL)); + break; } *type = rel_type; @@ -559,13 +563,12 @@ static int ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { - int rel_msg = 0; - u8 rel_type = type; - u8 rel_code = code; __u32 rel_info = ntohl(info); - int err; - struct sk_buff *skb2; const struct iphdr *eiph; + struct sk_buff *skb2; + int err, rel_msg = 0; + u8 rel_type = type; + u8 rel_code = code; struct rtable *rt; struct flowi4 fl4; @@ -590,9 +593,6 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, rel_type = ICMP_DEST_UNREACH; rel_code = ICMP_FRAG_NEEDED; break; - case NDISC_REDIRECT: - rel_type = ICMP_REDIRECT; - rel_code = ICMP_REDIR_HOST; default: return 0; } @@ -611,33 +611,26 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, eiph = ip_hdr(skb2); /* Try to guess incoming interface */ - rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, - eiph->saddr, 0, - 0, 0, - IPPROTO_IPIP, RT_TOS(eiph->tos), 0); + rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->saddr, + 0, 0, 0, IPPROTO_IPIP, RT_TOS(eiph->tos), 0); if (IS_ERR(rt)) goto out; skb2->dev = rt->dst.dev; + ip_rt_put(rt); /* route "incoming" packet */ if (rt->rt_flags & RTCF_LOCAL) { - ip_rt_put(rt); - rt = NULL; rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, - eiph->daddr, eiph->saddr, - 0, 0, - IPPROTO_IPIP, - RT_TOS(eiph->tos), 0); - if (IS_ERR(rt) || - rt->dst.dev->type != ARPHRD_TUNNEL) { + eiph->daddr, eiph->saddr, 0, 0, + IPPROTO_IPIP, RT_TOS(eiph->tos), 0); + if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL) { if (!IS_ERR(rt)) ip_rt_put(rt); goto out; } skb_dst_set(skb2, &rt->dst); } else { - ip_rt_put(rt); if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, skb2->dev) || skb_dst(skb2)->dev->type != ARPHRD_TUNNEL) @@ -649,10 +642,9 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (rel_info > dst_mtu(skb_dst(skb2))) goto out; - skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), NULL, skb2, rel_info); + skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), NULL, skb2, + rel_info); } - if (rel_type == ICMP_REDIRECT) - skb_dst(skb2)->ops->redirect(skb_dst(skb2), NULL, skb2); icmp_send(skb2, rel_type, rel_code, htonl(rel_info)); @@ -665,11 +657,10 @@ static int ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { - int rel_msg = 0; + __u32 rel_info = ntohl(info); + int err, rel_msg = 0; u8 rel_type = type; u8 rel_code = code; - __u32 rel_info = ntohl(info); - int err; err = ip6_tnl_err(skb, IPPROTO_IPV6, opt, &rel_type, &rel_code, &rel_msg, &rel_info, offset); @@ -769,7 +760,8 @@ int ip6_tnl_rcv_ctl(struct ip6_tnl *t, if ((ipv6_addr_is_multicast(laddr) || likely(ipv6_chk_addr(net, laddr, ldev, 0))) && - likely(!ipv6_chk_addr(net, raddr, NULL, 0))) + ((p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) || + likely(!ipv6_chk_addr(net, raddr, NULL, 0)))) ret = 1; } return ret; @@ -899,7 +891,7 @@ static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto, t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr); if (t) { - u8 tproto = ACCESS_ONCE(t->parms.proto); + u8 tproto = READ_ONCE(t->parms.proto); if (tproto != ipproto && tproto != 0) goto drop; @@ -999,7 +991,8 @@ int ip6_tnl_xmit_ctl(struct ip6_tnl *t, if (unlikely(!ipv6_chk_addr(net, laddr, ldev, 0))) pr_warn("%s xmit: Local address not yet configured!\n", p->name); - else if (!ipv6_addr_is_multicast(raddr) && + else if (!(p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) && + !ipv6_addr_is_multicast(raddr) && unlikely(ipv6_chk_addr(net, raddr, NULL, 0))) pr_warn("%s xmit: Routing loop! Remote address found on this node!\n", p->name); @@ -1233,7 +1226,7 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - tproto = ACCESS_ONCE(t->parms.proto); + tproto = READ_ONCE(t->parms.proto); if (tproto != IPPROTO_IPIP && tproto != 0) return -1; @@ -1303,7 +1296,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) u8 tproto; int err; - tproto = ACCESS_ONCE(t->parms.proto); + tproto = READ_ONCE(t->parms.proto); if ((tproto != IPPROTO_IPV6 && tproto != 0) || ip6_tnl_addr_conflict(t, ipv6h)) return -1; @@ -2168,17 +2161,16 @@ static struct xfrm6_tunnel ip6ip6_handler __read_mostly = { .priority = 1, }; -static void __net_exit ip6_tnl_destroy_tunnels(struct net *net) +static void __net_exit ip6_tnl_destroy_tunnels(struct net *net, struct list_head *list) { struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct net_device *dev, *aux; int h; struct ip6_tnl *t; - LIST_HEAD(list); for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == &ip6_link_ops) - unregister_netdevice_queue(dev, &list); + unregister_netdevice_queue(dev, list); for (h = 0; h < IP6_TUNNEL_HASH_SIZE; h++) { t = rtnl_dereference(ip6n->tnls_r_l[h]); @@ -2187,12 +2179,10 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct net *net) * been added to the list by the previous loop. */ if (!net_eq(dev_net(t->dev), net)) - unregister_netdevice_queue(t->dev, &list); + unregister_netdevice_queue(t->dev, list); t = rtnl_dereference(t->next); } } - - unregister_netdevice_many(&list); } static int __net_init ip6_tnl_init_net(struct net *net) @@ -2236,16 +2226,21 @@ err_alloc_dev: return err; } -static void __net_exit ip6_tnl_exit_net(struct net *net) +static void __net_exit ip6_tnl_exit_batch_net(struct list_head *net_list) { + struct net *net; + LIST_HEAD(list); + rtnl_lock(); - ip6_tnl_destroy_tunnels(net); + list_for_each_entry(net, net_list, exit_list) + ip6_tnl_destroy_tunnels(net, &list); + unregister_netdevice_many(&list); rtnl_unlock(); } static struct pernet_operations ip6_tnl_net_ops = { .init = ip6_tnl_init_net, - .exit = ip6_tnl_exit_net, + .exit_batch = ip6_tnl_exit_batch_net, .id = &ip6_tnl_net_id, .size = sizeof(struct ip6_tnl_net), }; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index bcdc2d557de1..dbb74f3c57a7 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -1053,23 +1053,22 @@ static struct rtnl_link_ops vti6_link_ops __read_mostly = { .get_link_net = ip6_tnl_get_link_net, }; -static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n) +static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n, + struct list_head *list) { int h; struct ip6_tnl *t; - LIST_HEAD(list); for (h = 0; h < IP6_VTI_HASH_SIZE; h++) { t = rtnl_dereference(ip6n->tnls_r_l[h]); while (t) { - unregister_netdevice_queue(t->dev, &list); + unregister_netdevice_queue(t->dev, list); t = rtnl_dereference(t->next); } } t = rtnl_dereference(ip6n->tnls_wc[0]); - unregister_netdevice_queue(t->dev, &list); - unregister_netdevice_many(&list); + unregister_netdevice_queue(t->dev, list); } static int __net_init vti6_init_net(struct net *net) @@ -1109,18 +1108,24 @@ err_alloc_dev: return err; } -static void __net_exit vti6_exit_net(struct net *net) +static void __net_exit vti6_exit_batch_net(struct list_head *net_list) { - struct vti6_net *ip6n = net_generic(net, vti6_net_id); + struct vti6_net *ip6n; + struct net *net; + LIST_HEAD(list); rtnl_lock(); - vti6_destroy_tunnels(ip6n); + list_for_each_entry(net, net_list, exit_list) { + ip6n = net_generic(net, vti6_net_id); + vti6_destroy_tunnels(ip6n, &list); + } + unregister_netdevice_many(&list); rtnl_unlock(); } static struct pernet_operations vti6_net_ops = { .init = vti6_init_net, - .exit = vti6_exit_net, + .exit_batch = vti6_exit_batch_net, .id = &vti6_net_id, .size = sizeof(struct vti6_net), }; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index f5500f5444e9..9c24b85949c1 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1617,6 +1617,10 @@ int ip6mr_sk_done(struct sock *sk) struct net *net = sock_net(sk); struct mr6_table *mrt; + if (sk->sk_type != SOCK_RAW || + inet_sk(sk)->inet_num != IPPROTO_ICMPV6) + return err; + rtnl_lock(); ip6mr_for_each_table(mrt, net) { if (sk == mrt->mroute6_sk) { @@ -1722,6 +1726,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns case MRT6_ADD_MFC: case MRT6_DEL_MFC: parent = -1; + /* fall through */ case MRT6_ADD_MFC_PROXY: case MRT6_DEL_MFC_PROXY: if (optlen < sizeof(mfc)) diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index a5e466d4e093..b9404feabd78 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -377,6 +377,14 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, retv = 0; break; + case IPV6_FREEBIND: + if (optlen < sizeof(int)) + goto e_inval; + /* we also don't have a separate freebind bit for IPV6 */ + inet_sk(sk)->freebind = valbool; + retv = 0; + break; + case IPV6_RECVORIGDSTADDR: if (optlen < sizeof(int)) goto e_inval; @@ -1214,6 +1222,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, val = inet_sk(sk)->transparent; break; + case IPV6_FREEBIND: + val = inet_sk(sk)->freebind; + break; + case IPV6_RECVORIGDSTADDR: val = np->rxopt.bits.rxorigdstaddr; break; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 266a530414d7..b3cea200c85e 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -46,6 +46,7 @@ #endif #include <linux/if_addr.h> +#include <linux/if_ether.h> #include <linux/if_arp.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> @@ -426,12 +427,19 @@ static void ip6_nd_hdr(struct sk_buff *skb, int hop_limit, int len) { struct ipv6hdr *hdr; + struct inet6_dev *idev; + unsigned tclass; + + rcu_read_lock(); + idev = __in6_dev_get(skb->dev); + tclass = idev ? idev->cnf.ndisc_tclass : 0; + rcu_read_unlock(); skb_push(skb, sizeof(*hdr)); skb_reset_network_header(skb); hdr = ipv6_hdr(skb); - ip6_flow_hdr(hdr, 0, 0); + ip6_flow_hdr(hdr, tclass, 0); hdr->payload_len = htons(len); hdr->nexthdr = IPPROTO_ICMPV6; @@ -822,7 +830,7 @@ have_ifp: * who is doing DAD * so fail our DAD process */ - addrconf_dad_failure(ifp); + addrconf_dad_failure(skb, ifp); return; } else { /* @@ -975,7 +983,7 @@ static void ndisc_recv_na(struct sk_buff *skb) if (ifp) { if (skb->pkt_type != PACKET_LOOPBACK && (ifp->flags & IFA_F_TENTATIVE)) { - addrconf_dad_failure(ifp); + addrconf_dad_failure(skb, ifp); return; } /* What should we make now? The advertisement @@ -989,8 +997,8 @@ static void ndisc_recv_na(struct sk_buff *skb) */ if (skb->pkt_type != PACKET_LOOPBACK) ND_PRINTK(1, warn, - "NA: someone advertises our address %pI6 on %s!\n", - &ifp->addr, ifp->idev->dev->name); + "NA: %pM advertised our address %pI6c on %s!\n", + eth_hdr(skb)->h_source, &ifp->addr, ifp->idev->dev->name); in6_ifa_put(ifp); return; } diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 01bd3ee5ebc6..f06e25065a34 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -800,6 +800,25 @@ get_counters(const struct xt_table_info *t, } } +static void get_old_counters(const struct xt_table_info *t, + struct xt_counters counters[]) +{ + struct ip6t_entry *iter; + unsigned int cpu, i; + + for_each_possible_cpu(cpu) { + i = 0; + xt_entry_foreach(iter, t->entries, t->size) { + const struct xt_counters *tmp; + + tmp = xt_get_per_cpu_counter(&iter->counters, cpu); + ADD_COUNTER(counters[i], tmp->bcnt, tmp->pcnt); + ++i; + } + cond_resched(); + } +} + static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; @@ -1090,8 +1109,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); - /* Get the old counters, and synchronize with replace */ - get_counters(oldinfo, counters); + get_old_counters(oldinfo, counters); /* Decrease module usage counts and free resource */ xt_entry_foreach(iter, oldinfo->entries, oldinfo->size) diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index fe01dc953c56..3b80a38f62b8 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -339,7 +339,7 @@ static void ipv6_hooks_unregister(struct net *net) mutex_unlock(®ister_ipv6_hooks); } -struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 __read_mostly = { +const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 = { .l3proto = PF_INET6, .pkt_to_tuple = ipv6_pkt_to_tuple, .invert_tuple = ipv6_invert_tuple, diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index a9e1fd1a8536..3ac0d826afc4 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -94,7 +94,6 @@ static int icmpv6_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, - u_int8_t pf, unsigned int *timeout) { /* Do not immediately delete the connection after the first @@ -176,6 +175,12 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl, return NF_ACCEPT; } +static void icmpv6_error_log(const struct sk_buff *skb, struct net *net, + u8 pf, const char *msg) +{ + nf_l4proto_log_invalid(skb, net, pf, IPPROTO_ICMPV6, "%s", msg); +} + static int icmpv6_error(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, @@ -187,17 +192,13 @@ icmpv6_error(struct net *net, struct nf_conn *tmpl, icmp6h = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih); if (icmp6h == NULL) { - if (LOG_INVALID(net, IPPROTO_ICMPV6)) - nf_log_packet(net, PF_INET6, 0, skb, NULL, NULL, NULL, - "nf_ct_icmpv6: short packet "); + icmpv6_error_log(skb, net, pf, "short packet"); return -NF_ACCEPT; } if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING && nf_ip6_checksum(skb, hooknum, dataoff, IPPROTO_ICMPV6)) { - if (LOG_INVALID(net, IPPROTO_ICMPV6)) - nf_log_packet(net, PF_INET6, 0, skb, NULL, NULL, NULL, - "nf_ct_icmpv6: ICMPv6 checksum failed "); + icmpv6_error_log(skb, net, pf, "ICMPv6 checksum failed"); return -NF_ACCEPT; } @@ -258,9 +259,14 @@ static int icmpv6_nlattr_to_tuple(struct nlattr *tb[], return 0; } -static int icmpv6_nlattr_tuple_size(void) +static unsigned int icmpv6_nlattr_tuple_size(void) { - return nla_policy_len(icmpv6_nla_policy, CTA_PROTO_MAX + 1); + static unsigned int size __read_mostly; + + if (!size) + size = nla_policy_len(icmpv6_nla_policy, CTA_PROTO_MAX + 1); + + return size; } #endif diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index b263bf3a19f7..977d8900cfd1 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -169,12 +169,13 @@ static unsigned int nf_hashfn(const struct inet_frag_queue *q) return nf_hash_frag(nq->id, &nq->saddr, &nq->daddr); } -static void nf_ct_frag6_expire(unsigned long data) +static void nf_ct_frag6_expire(struct timer_list *t) { + struct inet_frag_queue *frag = from_timer(frag, t, timer); struct frag_queue *fq; struct net *net; - fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q); + fq = container_of(frag, struct frag_queue, q); net = container_of(fq->q.net, struct net, nf_frag.frags); ip6_expire_frag_queue(net, fq, &nf_frags); diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index 46d6dba50698..1d2fb9267d6f 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -290,7 +290,8 @@ nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, else return NF_ACCEPT; } - /* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */ + /* Only ICMPs can be IP_CT_IS_REPLY: */ + /* fall through */ case IP_CT_NEW: /* Seen it before? This can happen for loopback, retrans, * or local packets. diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index a338bbc33cf3..4a7e5ffa5108 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -31,37 +31,6 @@ static u32 __ipv6_select_ident(struct net *net, u32 hashrnd, return id; } -/* This function exists only for tap drivers that must support broken - * clients requesting UFO without specifying an IPv6 fragment ID. - * - * This is similar to ipv6_select_ident() but we use an independent hash - * seed to limit information leakage. - * - * The network header must be set before calling this. - */ -void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb) -{ - static u32 ip6_proxy_idents_hashrnd __read_mostly; - struct in6_addr buf[2]; - struct in6_addr *addrs; - u32 id; - - addrs = skb_header_pointer(skb, - skb_network_offset(skb) + - offsetof(struct ipv6hdr, saddr), - sizeof(buf), buf); - if (!addrs) - return; - - net_get_random_once(&ip6_proxy_idents_hashrnd, - sizeof(ip6_proxy_idents_hashrnd)); - - id = __ipv6_select_ident(net, ip6_proxy_idents_hashrnd, - &addrs[1], &addrs[0]); - skb_shinfo(skb)->ip6_frag_id = htonl(id); -} -EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident); - __be32 ipv6_select_ident(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr) diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index ac826dd338ff..d12c55dad7d1 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -154,9 +154,8 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { - err = icmpv6_push_pending_frames(sk, &fl6, - (struct icmp6hdr *) &pfh.icmph, - len); + icmpv6_push_pending_frames(sk, &fl6, + (struct icmp6hdr *)&pfh.icmph, len); } release_sock(sk); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index e4462b0ff801..761a473a07c5 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1055,6 +1055,7 @@ static int rawv6_setsockopt(struct sock *sk, int level, int optname, if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; + /* fall through */ default: return ipv6_setsockopt(sk, level, optname, optval, optlen); } @@ -1077,6 +1078,7 @@ static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname, if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; + /* fall through */ default: return compat_ipv6_setsockopt(sk, level, optname, optval, optlen); @@ -1138,6 +1140,7 @@ static int rawv6_getsockopt(struct sock *sk, int level, int optname, if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; + /* fall through */ default: return ipv6_getsockopt(sk, level, optname, optval, optlen); } @@ -1160,6 +1163,7 @@ static int compat_rawv6_getsockopt(struct sock *sk, int level, int optname, if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; + /* fall through */ default: return compat_ipv6_getsockopt(sk, level, optname, optval, optlen); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 846012eae526..afbc000ad4f2 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -170,12 +170,13 @@ out: } EXPORT_SYMBOL(ip6_expire_frag_queue); -static void ip6_frag_expire(unsigned long data) +static void ip6_frag_expire(struct timer_list *t) { + struct inet_frag_queue *frag = from_timer(frag, t, timer); struct frag_queue *fq; struct net *net; - fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q); + fq = container_of(frag, struct frag_queue, q); net = container_of(fq->q.net, struct net, ipv6.frags); ip6_expire_frag_queue(net, fq, &ip6_frags); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index a96d5b385d8f..05eb7bc36156 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -44,6 +44,7 @@ #include <linux/seq_file.h> #include <linux/nsproxy.h> #include <linux/slab.h> +#include <linux/jhash.h> #include <net/net_namespace.h> #include <net/snmp.h> #include <net/ipv6.h> @@ -104,6 +105,9 @@ static int rt6_fill_node(struct net *net, struct in6_addr *dst, struct in6_addr *src, int iif, int type, u32 portid, u32 seq, unsigned int flags); +static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt, + struct in6_addr *daddr, + struct in6_addr *saddr); #ifdef CONFIG_IPV6_ROUTE_INFO static struct rt6_info *rt6_add_route_info(struct net *net, @@ -139,9 +143,11 @@ static void rt6_uncached_list_del(struct rt6_info *rt) { if (!list_empty(&rt->rt6i_uncached)) { struct uncached_list *ul = rt->rt6i_uncached_list; + struct net *net = dev_net(rt->dst.dev); spin_lock_bh(&ul->lock); list_del(&rt->rt6i_uncached); + atomic_dec(&net->ipv6.rt6_stats->fib_rt_uncache); spin_unlock_bh(&ul->lock); } } @@ -355,8 +361,10 @@ static struct rt6_info *__ip6_dst_alloc(struct net *net, struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, flags); - if (rt) + if (rt) { rt6_info_init(rt); + atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc); + } return rt; } @@ -369,17 +377,7 @@ struct rt6_info *ip6_dst_alloc(struct net *net, if (rt) { rt->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, GFP_ATOMIC); - if (rt->rt6i_pcpu) { - int cpu; - - for_each_possible_cpu(cpu) { - struct rt6_info **p; - - p = per_cpu_ptr(rt->rt6i_pcpu, cpu); - /* no one shares rt */ - *p = NULL; - } - } else { + if (!rt->rt6i_pcpu) { dst_release_immediate(&rt->dst); return NULL; } @@ -392,6 +390,7 @@ EXPORT_SYMBOL(ip6_dst_alloc); static void ip6_dst_destroy(struct dst_entry *dst) { struct rt6_info *rt = (struct rt6_info *)dst; + struct rt6_exception_bucket *bucket; struct dst_entry *from = dst->from; struct inet6_dev *idev; @@ -404,6 +403,11 @@ static void ip6_dst_destroy(struct dst_entry *dst) rt->rt6i_idev = NULL; in6_dev_put(idev); } + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, 1); + if (bucket) { + rt->rt6i_exception_bucket = NULL; + kfree(bucket); + } dst->from = NULL; dst_release(from); @@ -478,7 +482,7 @@ static struct rt6_info *rt6_multipath_select(struct rt6_info *match, } /* - * Route lookup. Any table->tb6_lock is implied. + * Route lookup. rcu_read_lock() should be held. */ static inline struct rt6_info *rt6_device_match(struct net *net, @@ -493,7 +497,7 @@ static inline struct rt6_info *rt6_device_match(struct net *net, if (!oif && ipv6_addr_any(saddr)) goto out; - for (sprt = rt; sprt; sprt = sprt->dst.rt6_next) { + for (sprt = rt; sprt; sprt = rcu_dereference(sprt->dst.rt6_next)) { struct net_device *dev = sprt->dst.dev; if (oif) { @@ -702,6 +706,7 @@ out: } static struct rt6_info *find_rr_leaf(struct fib6_node *fn, + struct rt6_info *leaf, struct rt6_info *rr_head, u32 metric, int oif, int strict, bool *do_rr) @@ -711,7 +716,7 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, match = NULL; cont = NULL; - for (rt = rr_head; rt; rt = rt->dst.rt6_next) { + for (rt = rr_head; rt; rt = rcu_dereference(rt->dst.rt6_next)) { if (rt->rt6i_metric != metric) { cont = rt; break; @@ -720,7 +725,8 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, match = find_match(rt, oif, strict, &mpri, match, do_rr); } - for (rt = fn->leaf; rt && rt != rr_head; rt = rt->dst.rt6_next) { + for (rt = leaf; rt && rt != rr_head; + rt = rcu_dereference(rt->dst.rt6_next)) { if (rt->rt6i_metric != metric) { cont = rt; break; @@ -732,37 +738,59 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, if (match || !cont) return match; - for (rt = cont; rt; rt = rt->dst.rt6_next) + for (rt = cont; rt; rt = rcu_dereference(rt->dst.rt6_next)) match = find_match(rt, oif, strict, &mpri, match, do_rr); return match; } -static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict) +static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn, + int oif, int strict) { + struct rt6_info *leaf = rcu_dereference(fn->leaf); struct rt6_info *match, *rt0; - struct net *net; bool do_rr = false; + int key_plen; - rt0 = fn->rr_ptr; + if (!leaf || leaf == net->ipv6.ip6_null_entry) + return net->ipv6.ip6_null_entry; + + rt0 = rcu_dereference(fn->rr_ptr); if (!rt0) - fn->rr_ptr = rt0 = fn->leaf; + rt0 = leaf; - match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict, + /* Double check to make sure fn is not an intermediate node + * and fn->leaf does not points to its child's leaf + * (This might happen if all routes under fn are deleted from + * the tree and fib6_repair_tree() is called on the node.) + */ + key_plen = rt0->rt6i_dst.plen; +#ifdef CONFIG_IPV6_SUBTREES + if (rt0->rt6i_src.plen) + key_plen = rt0->rt6i_src.plen; +#endif + if (fn->fn_bit != key_plen) + return net->ipv6.ip6_null_entry; + + match = find_rr_leaf(fn, leaf, rt0, rt0->rt6i_metric, oif, strict, &do_rr); if (do_rr) { - struct rt6_info *next = rt0->dst.rt6_next; + struct rt6_info *next = rcu_dereference(rt0->dst.rt6_next); /* no entries matched; do round-robin */ if (!next || next->rt6i_metric != rt0->rt6i_metric) - next = fn->leaf; - - if (next != rt0) - fn->rr_ptr = next; + next = leaf; + + if (next != rt0) { + spin_lock_bh(&leaf->rt6i_table->tb6_lock); + /* make sure next is not being deleted from the tree */ + if (next->rt6i_node) + rcu_assign_pointer(fn->rr_ptr, next); + spin_unlock_bh(&leaf->rt6i_table->tb6_lock); + } } - net = dev_net(rt0->dst.dev); return match ? match : net->ipv6.ip6_null_entry; } @@ -850,13 +878,14 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, static struct fib6_node* fib6_backtrack(struct fib6_node *fn, struct in6_addr *saddr) { - struct fib6_node *pn; + struct fib6_node *pn, *sn; while (1) { if (fn->fn_flags & RTN_TL_ROOT) return NULL; - pn = fn->parent; - if (FIB6_SUBTREE(pn) && FIB6_SUBTREE(pn) != fn) - fn = fib6_lookup(FIB6_SUBTREE(pn), NULL, saddr); + pn = rcu_dereference(fn->parent); + sn = FIB6_SUBTREE(pn); + if (sn && sn != fn) + fn = fib6_lookup(sn, NULL, saddr); else fn = pn; if (fn->fn_flags & RTN_RTINFO) @@ -864,29 +893,59 @@ static struct fib6_node* fib6_backtrack(struct fib6_node *fn, } } +static bool ip6_hold_safe(struct net *net, struct rt6_info **prt, + bool null_fallback) +{ + struct rt6_info *rt = *prt; + + if (dst_hold_safe(&rt->dst)) + return true; + if (null_fallback) { + rt = net->ipv6.ip6_null_entry; + dst_hold(&rt->dst); + } else { + rt = NULL; + } + *prt = rt; + return false; +} + static struct rt6_info *ip6_pol_route_lookup(struct net *net, struct fib6_table *table, struct flowi6 *fl6, int flags) { + struct rt6_info *rt, *rt_cache; struct fib6_node *fn; - struct rt6_info *rt; - read_lock_bh(&table->tb6_lock); + rcu_read_lock(); fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: - rt = fn->leaf; - rt = rt6_device_match(net, rt, &fl6->saddr, fl6->flowi6_oif, flags); - if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0) - rt = rt6_multipath_select(rt, fl6, fl6->flowi6_oif, flags); + rt = rcu_dereference(fn->leaf); + if (!rt) { + rt = net->ipv6.ip6_null_entry; + } else { + rt = rt6_device_match(net, rt, &fl6->saddr, + fl6->flowi6_oif, flags); + if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0) + rt = rt6_multipath_select(rt, fl6, + fl6->flowi6_oif, flags); + } if (rt == net->ipv6.ip6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto restart; } - dst_use(&rt->dst, jiffies); - read_unlock_bh(&table->tb6_lock); + /* Search through exception table */ + rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr); + if (rt_cache) + rt = rt_cache; + + if (ip6_hold_safe(net, &rt, true)) + dst_use_noref(&rt->dst, jiffies); + + rcu_read_unlock(); - trace_fib6_table_lookup(net, rt, table->tb6_id, fl6); + trace_fib6_table_lookup(net, rt, table, fl6); return rt; @@ -938,9 +997,9 @@ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info, struct fib6_table *table; table = rt->rt6i_table; - write_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); err = fib6_add(&table->tb6_root, rt, info, mxc, extack); - write_unlock_bh(&table->tb6_lock); + spin_unlock_bh(&table->tb6_lock); return err; } @@ -1038,7 +1097,7 @@ static struct rt6_info *ip6_rt_pcpu_alloc(struct rt6_info *rt) return pcpu_rt; } -/* It should be called with read_lock_bh(&tb6_lock) acquired */ +/* It should be called with rcu_read_lock() acquired */ static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt) { struct rt6_info *pcpu_rt, **p; @@ -1046,16 +1105,14 @@ static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt) p = this_cpu_ptr(rt->rt6i_pcpu); pcpu_rt = *p; - if (pcpu_rt) { - dst_hold(&pcpu_rt->dst); + if (pcpu_rt && ip6_hold_safe(NULL, &pcpu_rt, false)) rt6_dst_from_metrics_check(pcpu_rt); - } + return pcpu_rt; } static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt) { - struct fib6_table *table = rt->rt6i_table; struct rt6_info *pcpu_rt, *prev, **p; pcpu_rt = ip6_rt_pcpu_alloc(rt); @@ -1066,36 +1123,526 @@ static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt) return net->ipv6.ip6_null_entry; } - read_lock_bh(&table->tb6_lock); - if (rt->rt6i_pcpu) { - p = this_cpu_ptr(rt->rt6i_pcpu); - prev = cmpxchg(p, NULL, pcpu_rt); - if (prev) { - /* If someone did it before us, return prev instead */ - dst_release_immediate(&pcpu_rt->dst); - pcpu_rt = prev; - } - } else { - /* rt has been removed from the fib6 tree - * before we have a chance to acquire the read_lock. - * In this case, don't brother to create a pcpu rt - * since rt is going away anyway. The next - * dst_check() will trigger a re-lookup. - */ - dst_release_immediate(&pcpu_rt->dst); - pcpu_rt = rt; - } dst_hold(&pcpu_rt->dst); + p = this_cpu_ptr(rt->rt6i_pcpu); + prev = cmpxchg(p, NULL, pcpu_rt); + BUG_ON(prev); + rt6_dst_from_metrics_check(pcpu_rt); - read_unlock_bh(&table->tb6_lock); return pcpu_rt; } +/* exception hash table implementation + */ +static DEFINE_SPINLOCK(rt6_exception_lock); + +/* Remove rt6_ex from hash table and free the memory + * Caller must hold rt6_exception_lock + */ +static void rt6_remove_exception(struct rt6_exception_bucket *bucket, + struct rt6_exception *rt6_ex) +{ + struct net *net; + + if (!bucket || !rt6_ex) + return; + + net = dev_net(rt6_ex->rt6i->dst.dev); + rt6_ex->rt6i->rt6i_node = NULL; + hlist_del_rcu(&rt6_ex->hlist); + rt6_release(rt6_ex->rt6i); + kfree_rcu(rt6_ex, rcu); + WARN_ON_ONCE(!bucket->depth); + bucket->depth--; + net->ipv6.rt6_stats->fib_rt_cache--; +} + +/* Remove oldest rt6_ex in bucket and free the memory + * Caller must hold rt6_exception_lock + */ +static void rt6_exception_remove_oldest(struct rt6_exception_bucket *bucket) +{ + struct rt6_exception *rt6_ex, *oldest = NULL; + + if (!bucket) + return; + + hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { + if (!oldest || time_before(rt6_ex->stamp, oldest->stamp)) + oldest = rt6_ex; + } + rt6_remove_exception(bucket, oldest); +} + +static u32 rt6_exception_hash(const struct in6_addr *dst, + const struct in6_addr *src) +{ + static u32 seed __read_mostly; + u32 val; + + net_get_random_once(&seed, sizeof(seed)); + val = jhash(dst, sizeof(*dst), seed); + +#ifdef CONFIG_IPV6_SUBTREES + if (src) + val = jhash(src, sizeof(*src), val); +#endif + return hash_32(val, FIB6_EXCEPTION_BUCKET_SIZE_SHIFT); +} + +/* Helper function to find the cached rt in the hash table + * and update bucket pointer to point to the bucket for this + * (daddr, saddr) pair + * Caller must hold rt6_exception_lock + */ +static struct rt6_exception * +__rt6_find_exception_spinlock(struct rt6_exception_bucket **bucket, + const struct in6_addr *daddr, + const struct in6_addr *saddr) +{ + struct rt6_exception *rt6_ex; + u32 hval; + + if (!(*bucket) || !daddr) + return NULL; + + hval = rt6_exception_hash(daddr, saddr); + *bucket += hval; + + hlist_for_each_entry(rt6_ex, &(*bucket)->chain, hlist) { + struct rt6_info *rt6 = rt6_ex->rt6i; + bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr); + +#ifdef CONFIG_IPV6_SUBTREES + if (matched && saddr) + matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr); +#endif + if (matched) + return rt6_ex; + } + return NULL; +} + +/* Helper function to find the cached rt in the hash table + * and update bucket pointer to point to the bucket for this + * (daddr, saddr) pair + * Caller must hold rcu_read_lock() + */ +static struct rt6_exception * +__rt6_find_exception_rcu(struct rt6_exception_bucket **bucket, + const struct in6_addr *daddr, + const struct in6_addr *saddr) +{ + struct rt6_exception *rt6_ex; + u32 hval; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + if (!(*bucket) || !daddr) + return NULL; + + hval = rt6_exception_hash(daddr, saddr); + *bucket += hval; + + hlist_for_each_entry_rcu(rt6_ex, &(*bucket)->chain, hlist) { + struct rt6_info *rt6 = rt6_ex->rt6i; + bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr); + +#ifdef CONFIG_IPV6_SUBTREES + if (matched && saddr) + matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr); +#endif + if (matched) + return rt6_ex; + } + return NULL; +} + +static int rt6_insert_exception(struct rt6_info *nrt, + struct rt6_info *ort) +{ + struct net *net = dev_net(ort->dst.dev); + struct rt6_exception_bucket *bucket; + struct in6_addr *src_key = NULL; + struct rt6_exception *rt6_ex; + int err = 0; + + /* ort can't be a cache or pcpu route */ + if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU)) + ort = (struct rt6_info *)ort->dst.from; + WARN_ON_ONCE(ort->rt6i_flags & (RTF_CACHE | RTF_PCPU)); + + spin_lock_bh(&rt6_exception_lock); + + if (ort->exception_bucket_flushed) { + err = -EINVAL; + goto out; + } + + bucket = rcu_dereference_protected(ort->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + if (!bucket) { + bucket = kcalloc(FIB6_EXCEPTION_BUCKET_SIZE, sizeof(*bucket), + GFP_ATOMIC); + if (!bucket) { + err = -ENOMEM; + goto out; + } + rcu_assign_pointer(ort->rt6i_exception_bucket, bucket); + } + +#ifdef CONFIG_IPV6_SUBTREES + /* rt6i_src.plen != 0 indicates ort is in subtree + * and exception table is indexed by a hash of + * both rt6i_dst and rt6i_src. + * Otherwise, the exception table is indexed by + * a hash of only rt6i_dst. + */ + if (ort->rt6i_src.plen) + src_key = &nrt->rt6i_src.addr; +#endif + + /* Update rt6i_prefsrc as it could be changed + * in rt6_remove_prefsrc() + */ + nrt->rt6i_prefsrc = ort->rt6i_prefsrc; + /* rt6_mtu_change() might lower mtu on ort. + * Only insert this exception route if its mtu + * is less than ort's mtu value. + */ + if (nrt->rt6i_pmtu >= dst_mtu(&ort->dst)) { + err = -EINVAL; + goto out; + } + + rt6_ex = __rt6_find_exception_spinlock(&bucket, &nrt->rt6i_dst.addr, + src_key); + if (rt6_ex) + rt6_remove_exception(bucket, rt6_ex); + + rt6_ex = kzalloc(sizeof(*rt6_ex), GFP_ATOMIC); + if (!rt6_ex) { + err = -ENOMEM; + goto out; + } + rt6_ex->rt6i = nrt; + rt6_ex->stamp = jiffies; + atomic_inc(&nrt->rt6i_ref); + nrt->rt6i_node = ort->rt6i_node; + hlist_add_head_rcu(&rt6_ex->hlist, &bucket->chain); + bucket->depth++; + net->ipv6.rt6_stats->fib_rt_cache++; + + if (bucket->depth > FIB6_MAX_DEPTH) + rt6_exception_remove_oldest(bucket); + +out: + spin_unlock_bh(&rt6_exception_lock); + + /* Update fn->fn_sernum to invalidate all cached dst */ + if (!err) { + fib6_update_sernum(ort); + fib6_force_start_gc(net); + } + + return err; +} + +void rt6_flush_exceptions(struct rt6_info *rt) +{ + struct rt6_exception_bucket *bucket; + struct rt6_exception *rt6_ex; + struct hlist_node *tmp; + int i; + + spin_lock_bh(&rt6_exception_lock); + /* Prevent rt6_insert_exception() to recreate the bucket list */ + rt->exception_bucket_flushed = 1; + + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + if (!bucket) + goto out; + + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) + rt6_remove_exception(bucket, rt6_ex); + WARN_ON_ONCE(bucket->depth); + bucket++; + } + +out: + spin_unlock_bh(&rt6_exception_lock); +} + +/* Find cached rt in the hash table inside passed in rt + * Caller has to hold rcu_read_lock() + */ +static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt, + struct in6_addr *daddr, + struct in6_addr *saddr) +{ + struct rt6_exception_bucket *bucket; + struct in6_addr *src_key = NULL; + struct rt6_exception *rt6_ex; + struct rt6_info *res = NULL; + + bucket = rcu_dereference(rt->rt6i_exception_bucket); + +#ifdef CONFIG_IPV6_SUBTREES + /* rt6i_src.plen != 0 indicates rt is in subtree + * and exception table is indexed by a hash of + * both rt6i_dst and rt6i_src. + * Otherwise, the exception table is indexed by + * a hash of only rt6i_dst. + */ + if (rt->rt6i_src.plen) + src_key = saddr; +#endif + rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key); + + if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i)) + res = rt6_ex->rt6i; + + return res; +} + +/* Remove the passed in cached rt from the hash table that contains it */ +int rt6_remove_exception_rt(struct rt6_info *rt) +{ + struct rt6_info *from = (struct rt6_info *)rt->dst.from; + struct rt6_exception_bucket *bucket; + struct in6_addr *src_key = NULL; + struct rt6_exception *rt6_ex; + int err; + + if (!from || + !(rt->rt6i_flags & RTF_CACHE)) + return -EINVAL; + + if (!rcu_access_pointer(from->rt6i_exception_bucket)) + return -ENOENT; + + spin_lock_bh(&rt6_exception_lock); + bucket = rcu_dereference_protected(from->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); +#ifdef CONFIG_IPV6_SUBTREES + /* rt6i_src.plen != 0 indicates 'from' is in subtree + * and exception table is indexed by a hash of + * both rt6i_dst and rt6i_src. + * Otherwise, the exception table is indexed by + * a hash of only rt6i_dst. + */ + if (from->rt6i_src.plen) + src_key = &rt->rt6i_src.addr; +#endif + rt6_ex = __rt6_find_exception_spinlock(&bucket, + &rt->rt6i_dst.addr, + src_key); + if (rt6_ex) { + rt6_remove_exception(bucket, rt6_ex); + err = 0; + } else { + err = -ENOENT; + } + + spin_unlock_bh(&rt6_exception_lock); + return err; +} + +/* Find rt6_ex which contains the passed in rt cache and + * refresh its stamp + */ +static void rt6_update_exception_stamp_rt(struct rt6_info *rt) +{ + struct rt6_info *from = (struct rt6_info *)rt->dst.from; + struct rt6_exception_bucket *bucket; + struct in6_addr *src_key = NULL; + struct rt6_exception *rt6_ex; + + if (!from || + !(rt->rt6i_flags & RTF_CACHE)) + return; + + rcu_read_lock(); + bucket = rcu_dereference(from->rt6i_exception_bucket); + +#ifdef CONFIG_IPV6_SUBTREES + /* rt6i_src.plen != 0 indicates 'from' is in subtree + * and exception table is indexed by a hash of + * both rt6i_dst and rt6i_src. + * Otherwise, the exception table is indexed by + * a hash of only rt6i_dst. + */ + if (from->rt6i_src.plen) + src_key = &rt->rt6i_src.addr; +#endif + rt6_ex = __rt6_find_exception_rcu(&bucket, + &rt->rt6i_dst.addr, + src_key); + if (rt6_ex) + rt6_ex->stamp = jiffies; + + rcu_read_unlock(); +} + +static void rt6_exceptions_remove_prefsrc(struct rt6_info *rt) +{ + struct rt6_exception_bucket *bucket; + struct rt6_exception *rt6_ex; + int i; + + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + + if (bucket) { + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { + rt6_ex->rt6i->rt6i_prefsrc.plen = 0; + } + bucket++; + } + } +} + +static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu) +{ + struct rt6_exception_bucket *bucket; + struct rt6_exception *rt6_ex; + int i; + + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + + if (bucket) { + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { + struct rt6_info *entry = rt6_ex->rt6i; + /* For RTF_CACHE with rt6i_pmtu == 0 + * (i.e. a redirected route), + * the metrics of its rt->dst.from has already + * been updated. + */ + if (entry->rt6i_pmtu && entry->rt6i_pmtu > mtu) + entry->rt6i_pmtu = mtu; + } + bucket++; + } + } +} + +#define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE) + +static void rt6_exceptions_clean_tohost(struct rt6_info *rt, + struct in6_addr *gateway) +{ + struct rt6_exception_bucket *bucket; + struct rt6_exception *rt6_ex; + struct hlist_node *tmp; + int i; + + if (!rcu_access_pointer(rt->rt6i_exception_bucket)) + return; + + spin_lock_bh(&rt6_exception_lock); + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + + if (bucket) { + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry_safe(rt6_ex, tmp, + &bucket->chain, hlist) { + struct rt6_info *entry = rt6_ex->rt6i; + + if ((entry->rt6i_flags & RTF_CACHE_GATEWAY) == + RTF_CACHE_GATEWAY && + ipv6_addr_equal(gateway, + &entry->rt6i_gateway)) { + rt6_remove_exception(bucket, rt6_ex); + } + } + bucket++; + } + } + + spin_unlock_bh(&rt6_exception_lock); +} + +static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket, + struct rt6_exception *rt6_ex, + struct fib6_gc_args *gc_args, + unsigned long now) +{ + struct rt6_info *rt = rt6_ex->rt6i; + + /* we are pruning and obsoleting aged-out and non gateway exceptions + * even if others have still references to them, so that on next + * dst_check() such references can be dropped. + * EXPIRES exceptions - e.g. pmtu-generated ones are pruned when + * expired, independently from their aging, as per RFC 8201 section 4 + */ + if (!(rt->rt6i_flags & RTF_EXPIRES) && + time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) { + RT6_TRACE("aging clone %p\n", rt); + rt6_remove_exception(bucket, rt6_ex); + return; + } else if (rt->rt6i_flags & RTF_GATEWAY) { + struct neighbour *neigh; + __u8 neigh_flags = 0; + + neigh = dst_neigh_lookup(&rt->dst, &rt->rt6i_gateway); + if (neigh) { + neigh_flags = neigh->flags; + neigh_release(neigh); + } + if (!(neigh_flags & NTF_ROUTER)) { + RT6_TRACE("purging route %p via non-router but gateway\n", + rt); + rt6_remove_exception(bucket, rt6_ex); + return; + } + } else if (__rt6_check_expired(rt)) { + RT6_TRACE("purging expired route %p\n", rt); + rt6_remove_exception(bucket, rt6_ex); + return; + } + gc_args->more++; +} + +void rt6_age_exceptions(struct rt6_info *rt, + struct fib6_gc_args *gc_args, + unsigned long now) +{ + struct rt6_exception_bucket *bucket; + struct rt6_exception *rt6_ex; + struct hlist_node *tmp; + int i; + + if (!rcu_access_pointer(rt->rt6i_exception_bucket)) + return; + + spin_lock_bh(&rt6_exception_lock); + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + + if (bucket) { + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry_safe(rt6_ex, tmp, + &bucket->chain, hlist) { + rt6_age_examine_exception(bucket, rt6_ex, + gc_args, now); + } + bucket++; + } + } + spin_unlock_bh(&rt6_exception_lock); +} + struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, int flags) { struct fib6_node *fn, *saved_fn; - struct rt6_info *rt; + struct rt6_info *rt, *rt_cache; int strict = 0; strict |= flags & RT6_LOOKUP_F_IFACE; @@ -1103,7 +1650,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, if (net->ipv6.devconf_all->forwarding == 0) strict |= RT6_LOOKUP_F_REACHABLE; - read_lock_bh(&table->tb6_lock); + rcu_read_lock(); fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); saved_fn = fn; @@ -1112,7 +1659,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, oif = 0; redo_rt6_select: - rt = rt6_select(fn, oif, strict); + rt = rt6_select(net, fn, oif, strict); if (rt->rt6i_nsiblings) rt = rt6_multipath_select(rt, fl6, oif, strict); if (rt == net->ipv6.ip6_null_entry) { @@ -1127,14 +1674,23 @@ redo_rt6_select: } } + /*Search through exception table */ + rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr); + if (rt_cache) + rt = rt_cache; - if (rt == net->ipv6.ip6_null_entry || (rt->rt6i_flags & RTF_CACHE)) { - dst_use(&rt->dst, jiffies); - read_unlock_bh(&table->tb6_lock); - - rt6_dst_from_metrics_check(rt); - - trace_fib6_table_lookup(net, rt, table->tb6_id, fl6); + if (rt == net->ipv6.ip6_null_entry) { + rcu_read_unlock(); + dst_hold(&rt->dst); + trace_fib6_table_lookup(net, rt, table, fl6); + return rt; + } else if (rt->rt6i_flags & RTF_CACHE) { + if (ip6_hold_safe(net, &rt, true)) { + dst_use_noref(&rt->dst, jiffies); + rt6_dst_from_metrics_check(rt); + } + rcu_read_unlock(); + trace_fib6_table_lookup(net, rt, table, fl6); return rt; } else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) && !(rt->rt6i_flags & RTF_GATEWAY))) { @@ -1146,8 +1702,14 @@ redo_rt6_select: struct rt6_info *uncached_rt; - dst_use(&rt->dst, jiffies); - read_unlock_bh(&table->tb6_lock); + if (ip6_hold_safe(net, &rt, true)) { + dst_use_noref(&rt->dst, jiffies); + } else { + rcu_read_unlock(); + uncached_rt = rt; + goto uncached_rt_out; + } + rcu_read_unlock(); uncached_rt = ip6_rt_cache_alloc(rt, &fl6->daddr, NULL); dst_release(&rt->dst); @@ -1157,12 +1719,14 @@ redo_rt6_select: * No need for another dst_hold() */ rt6_uncached_list_add(uncached_rt); + atomic_inc(&net->ipv6.rt6_stats->fib_rt_uncache); } else { uncached_rt = net->ipv6.ip6_null_entry; dst_hold(&uncached_rt->dst); } - trace_fib6_table_lookup(net, uncached_rt, table->tb6_id, fl6); +uncached_rt_out: + trace_fib6_table_lookup(net, uncached_rt, table, fl6); return uncached_rt; } else { @@ -1170,26 +1734,28 @@ redo_rt6_select: struct rt6_info *pcpu_rt; - rt->dst.lastuse = jiffies; - rt->dst.__use++; + dst_use_noref(&rt->dst, jiffies); + local_bh_disable(); pcpu_rt = rt6_get_pcpu_route(rt); - if (pcpu_rt) { - read_unlock_bh(&table->tb6_lock); - } else { - /* We have to do the read_unlock first - * because rt6_make_pcpu_route() may trigger - * ip6_dst_gc() which will take the write_lock. - */ - dst_hold(&rt->dst); - read_unlock_bh(&table->tb6_lock); - pcpu_rt = rt6_make_pcpu_route(rt); - dst_release(&rt->dst); + if (!pcpu_rt) { + /* atomic_inc_not_zero() is needed when using rcu */ + if (atomic_inc_not_zero(&rt->rt6i_ref)) { + /* No dst_hold() on rt is needed because grabbing + * rt->rt6i_ref makes sure rt can't be released. + */ + pcpu_rt = rt6_make_pcpu_route(rt); + rt6_release(rt); + } else { + /* rt is already removed from tree */ + pcpu_rt = net->ipv6.ip6_null_entry; + dst_hold(&pcpu_rt->dst); + } } - - trace_fib6_table_lookup(net, pcpu_rt, table->tb6_id, fl6); + local_bh_enable(); + rcu_read_unlock(); + trace_fib6_table_lookup(net, pcpu_rt, table, fl6); return pcpu_rt; - } } EXPORT_SYMBOL_GPL(ip6_pol_route); @@ -1328,6 +1894,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori DST_OBSOLETE_DEAD, 0); if (rt) { rt6_info_init(rt); + atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc); new = &rt->dst; new->__use = 1; @@ -1491,23 +2058,17 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, if (!rt6_cache_allowed_for_pmtu(rt6)) { rt6_do_update_pmtu(rt6, mtu); + /* update rt6_ex->stamp for cache */ + if (rt6->rt6i_flags & RTF_CACHE) + rt6_update_exception_stamp_rt(rt6); } else if (daddr) { struct rt6_info *nrt6; nrt6 = ip6_rt_cache_alloc(rt6, daddr, saddr); if (nrt6) { rt6_do_update_pmtu(nrt6, mtu); - - /* ip6_ins_rt(nrt6) will bump the - * rt6->rt6i_node->fn_sernum - * which will fail the next rt6_check() and - * invalidate the sk->sk_dst_cache. - */ - ip6_ins_rt(nrt6); - /* Release the reference taken in - * ip6_rt_cache_alloc() - */ - dst_release(&nrt6->dst); + if (rt6_insert_exception(nrt6, rt6)) + dst_release_immediate(&nrt6->dst); } } } @@ -1571,7 +2132,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net, int flags) { struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6; - struct rt6_info *rt; + struct rt6_info *rt, *rt_cache; struct fib6_node *fn; /* Get the "current" route for this destination and @@ -1584,10 +2145,10 @@ static struct rt6_info *__ip6_route_redirect(struct net *net, * routes. */ - read_lock_bh(&table->tb6_lock); + rcu_read_lock(); fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: - for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { + for_each_fib6_node_rt_rcu(fn) { if (rt6_check_expired(rt)) continue; if (rt->dst.error) @@ -1596,8 +2157,23 @@ restart: continue; if (fl6->flowi6_oif != rt->dst.dev->ifindex) continue; - if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) + /* rt_cache's gateway might be different from its 'parent' + * in the case of an ip redirect. + * So we keep searching in the exception table if the gateway + * is different. + */ + if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) { + rt_cache = rt6_find_cached_rt(rt, + &fl6->daddr, + &fl6->saddr); + if (rt_cache && + ipv6_addr_equal(&rdfl->gateway, + &rt_cache->rt6i_gateway)) { + rt = rt_cache; + break; + } continue; + } break; } @@ -1615,11 +2191,11 @@ restart: } out: - dst_hold(&rt->dst); + ip6_hold_safe(net, &rt, true); - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); - trace_fib6_table_lookup(net, rt, table->tb6_id, fl6); + trace_fib6_table_lookup(net, rt, table, fl6); return rt; }; @@ -1766,6 +2342,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, * do proper release of the net_device */ rt6_uncached_list_add(rt); + atomic_inc(&net->ipv6.rt6_stats->fib_rt_uncache); dst = xfrm_lookup(net, &rt->dst, flowi6_to_flowi(fl6), NULL, 0); @@ -1801,6 +2378,7 @@ out: static int ip6_convert_metrics(struct mx6_config *mxc, const struct fib6_config *cfg) { + struct net *net = cfg->fc_nlinfo.nl_net; bool ecn_ca = false; struct nlattr *nla; int remaining; @@ -1826,7 +2404,7 @@ static int ip6_convert_metrics(struct mx6_config *mxc, char tmp[TCP_CA_NAME_MAX]; nla_strlcpy(tmp, nla, sizeof(tmp)); - val = tcp_ca_get_key_by_name(tmp, &ecn_ca); + val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca); if (val == TCP_CA_UNSPEC) goto err; } else { @@ -1901,6 +2479,12 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, goto out; } + /* RTF_CACHE is an internal flag; can not be set by userspace */ + if (cfg->fc_flags & RTF_CACHE) { + NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE"); + goto out; + } + if (cfg->fc_dst_len > 128) { NL_SET_ERR_MSG(extack, "Invalid prefix length"); goto out; @@ -2216,9 +2800,9 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) } table = rt->rt6i_table; - write_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); err = fib6_del(rt, info); - write_unlock_bh(&table->tb6_lock); + spin_unlock_bh(&table->tb6_lock); out: ip6_rt_put(rt); @@ -2244,7 +2828,7 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg) if (rt == net->ipv6.ip6_null_entry) goto out_put; table = rt->rt6i_table; - write_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); if (rt->rt6i_nsiblings && cfg->fc_delete_all_nh) { struct rt6_info *sibling, *next_sibling; @@ -2274,7 +2858,7 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg) err = fib6_del(rt, info); out_unlock: - write_unlock_bh(&table->tb6_lock); + spin_unlock_bh(&table->tb6_lock); out_put: ip6_rt_put(rt); @@ -2288,9 +2872,9 @@ out_put: static int ip6_route_del(struct fib6_config *cfg, struct netlink_ext_ack *extack) { + struct rt6_info *rt, *rt_cache; struct fib6_table *table; struct fib6_node *fn; - struct rt6_info *rt; int err = -ESRCH; table = fib6_get_table(cfg->fc_nlinfo.nl_net, cfg->fc_table); @@ -2299,17 +2883,22 @@ static int ip6_route_del(struct fib6_config *cfg, return err; } - read_lock_bh(&table->tb6_lock); + rcu_read_lock(); fn = fib6_locate(&table->tb6_root, &cfg->fc_dst, cfg->fc_dst_len, - &cfg->fc_src, cfg->fc_src_len); + &cfg->fc_src, cfg->fc_src_len, + !(cfg->fc_flags & RTF_CACHE)); if (fn) { - for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { - if ((rt->rt6i_flags & RTF_CACHE) && - !(cfg->fc_flags & RTF_CACHE)) - continue; + for_each_fib6_node_rt_rcu(fn) { + if (cfg->fc_flags & RTF_CACHE) { + rt_cache = rt6_find_cached_rt(rt, &cfg->fc_dst, + &cfg->fc_src); + if (!rt_cache) + continue; + rt = rt_cache; + } if (cfg->fc_ifindex && (!rt->dst.dev || rt->dst.dev->ifindex != cfg->fc_ifindex)) @@ -2321,8 +2910,9 @@ static int ip6_route_del(struct fib6_config *cfg, continue; if (cfg->fc_protocol && cfg->fc_protocol != rt->rt6i_protocol) continue; - dst_hold(&rt->dst); - read_unlock_bh(&table->tb6_lock); + if (!dst_hold_safe(&rt->dst)) + break; + rcu_read_unlock(); /* if gateway was specified only delete the one hop */ if (cfg->fc_flags & RTF_GATEWAY) @@ -2331,7 +2921,7 @@ static int ip6_route_del(struct fib6_config *cfg, return __ip6_del_rt_siblings(rt, cfg); } } - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); return err; } @@ -2435,8 +3025,14 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu nrt->rt6i_protocol = RTPROT_REDIRECT; nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; - if (ip6_ins_rt(nrt)) - goto out_release; + /* No need to remove rt from the exception table if rt is + * a cached route because rt6_insert_exception() will + * takes care of it + */ + if (rt6_insert_exception(nrt, rt)) { + dst_release_immediate(&nrt->dst); + goto out; + } netevent.old = &rt->dst; netevent.new = &nrt->dst; @@ -2444,17 +3040,6 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu netevent.neigh = neigh; call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); - if (rt->rt6i_flags & RTF_CACHE) { - rt = (struct rt6_info *) dst_clone(&rt->dst); - ip6_del_rt(rt); - } - -out_release: - /* Release the reference taken in - * ip6_rt_cache_alloc() - */ - dst_release(&nrt->dst); - out: neigh_release(neigh); } @@ -2511,23 +3096,23 @@ static struct rt6_info *rt6_get_route_info(struct net *net, if (!table) return NULL; - read_lock_bh(&table->tb6_lock); - fn = fib6_locate(&table->tb6_root, prefix, prefixlen, NULL, 0); + rcu_read_lock(); + fn = fib6_locate(&table->tb6_root, prefix, prefixlen, NULL, 0, true); if (!fn) goto out; - for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { + for_each_fib6_node_rt_rcu(fn) { if (rt->dst.dev->ifindex != ifindex) continue; if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY)) continue; if (!ipv6_addr_equal(&rt->rt6i_gateway, gwaddr)) continue; - dst_hold(&rt->dst); + ip6_hold_safe(NULL, &rt, false); break; } out: - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); return rt; } @@ -2573,16 +3158,16 @@ struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_dev if (!table) return NULL; - read_lock_bh(&table->tb6_lock); - for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) { + rcu_read_lock(); + for_each_fib6_node_rt_rcu(&table->tb6_root) { if (dev == rt->dst.dev && ((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) && ipv6_addr_equal(&rt->rt6i_gateway, addr)) break; } if (rt) - dst_hold(&rt->dst); - read_unlock_bh(&table->tb6_lock); + ip6_hold_safe(NULL, &rt, false); + rcu_read_unlock(); return rt; } @@ -2620,17 +3205,20 @@ static void __rt6_purge_dflt_routers(struct fib6_table *table) struct rt6_info *rt; restart: - read_lock_bh(&table->tb6_lock); - for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) { + rcu_read_lock(); + for_each_fib6_node_rt_rcu(&table->tb6_root) { if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) && (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) { - dst_hold(&rt->dst); - read_unlock_bh(&table->tb6_lock); - ip6_del_rt(rt); + if (dst_hold_safe(&rt->dst)) { + rcu_read_unlock(); + ip6_del_rt(rt); + } else { + rcu_read_unlock(); + } goto restart; } } - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); table->flags &= ~RT6_TABLE_HAS_DFLT_ROUTER; } @@ -2818,8 +3406,12 @@ static int fib6_remove_prefsrc(struct rt6_info *rt, void *arg) if (((void *)rt->dst.dev == dev || !dev) && rt != net->ipv6.ip6_null_entry && ipv6_addr_equal(addr, &rt->rt6i_prefsrc.addr)) { + spin_lock_bh(&rt6_exception_lock); /* remove prefsrc entry */ rt->rt6i_prefsrc.plen = 0; + /* need to update cache as well */ + rt6_exceptions_remove_prefsrc(rt); + spin_unlock_bh(&rt6_exception_lock); } return 0; } @@ -2836,18 +3428,23 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp) } #define RTF_RA_ROUTER (RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY) -#define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE) /* Remove routers and update dst entries when gateway turn into host. */ static int fib6_clean_tohost(struct rt6_info *rt, void *arg) { struct in6_addr *gateway = (struct in6_addr *)arg; - if ((((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) || - ((rt->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY)) && - ipv6_addr_equal(gateway, &rt->rt6i_gateway)) { + if (((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) && + ipv6_addr_equal(gateway, &rt->rt6i_gateway)) { return -1; } + + /* Further clean up cached routes in exception table. + * This is needed because cached route may have a different + * gateway than its 'parent' in the case of an ip redirect. + */ + rt6_exceptions_clean_tohost(rt, gateway); + return 0; } @@ -2926,19 +3523,14 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) if (rt->dst.dev == arg->dev && dst_metric_raw(&rt->dst, RTAX_MTU) && !dst_metric_locked(&rt->dst, RTAX_MTU)) { - if (rt->rt6i_flags & RTF_CACHE) { - /* For RTF_CACHE with rt6i_pmtu == 0 - * (i.e. a redirected route), - * the metrics of its rt->dst.from has already - * been updated. - */ - if (rt->rt6i_pmtu && rt->rt6i_pmtu > arg->mtu) - rt->rt6i_pmtu = arg->mtu; - } else if (dst_mtu(&rt->dst) >= arg->mtu || - (dst_mtu(&rt->dst) < arg->mtu && - dst_mtu(&rt->dst) == idev->cnf.mtu6)) { + spin_lock_bh(&rt6_exception_lock); + if (dst_mtu(&rt->dst) >= arg->mtu || + (dst_mtu(&rt->dst) < arg->mtu && + dst_mtu(&rt->dst) == idev->cnf.mtu6)) { dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu); } + rt6_exceptions_update_pmtu(rt, arg->mtu); + spin_unlock_bh(&rt6_exception_lock); } return 0; } @@ -3839,7 +4431,7 @@ static int rt6_stats_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%04x %04x %04x %04x %04x %04x %04x\n", net->ipv6.rt6_stats->fib_nodes, net->ipv6.rt6_stats->fib_route_nodes, - net->ipv6.rt6_stats->fib_rt_alloc, + atomic_read(&net->ipv6.rt6_stats->fib_rt_alloc), net->ipv6.rt6_stats->fib_rt_entries, net->ipv6.rt6_stats->fib_rt_cache, dst_entries_get_slow(&net->ipv6.ip6_dst_ops), diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index ac912bb21747..d60ddcb0bfe2 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -91,29 +91,35 @@ struct sit_net { * Must be invoked with rcu_read_lock */ static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net, - struct net_device *dev, __be32 remote, __be32 local) + struct net_device *dev, + __be32 remote, __be32 local, + int sifindex) { unsigned int h0 = HASH(remote); unsigned int h1 = HASH(local); struct ip_tunnel *t; struct sit_net *sitn = net_generic(net, sit_net_id); + int ifindex = dev ? dev->ifindex : 0; for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && - (!dev || !t->parms.link || dev->ifindex == t->parms.link) && + (!dev || !t->parms.link || ifindex == t->parms.link || + sifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) { if (remote == t->parms.iph.daddr && - (!dev || !t->parms.link || dev->ifindex == t->parms.link) && + (!dev || !t->parms.link || ifindex == t->parms.link || + sifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) { if (local == t->parms.iph.saddr && - (!dev || !t->parms.link || dev->ifindex == t->parms.link) && + (!dev || !t->parms.link || ifindex == t->parms.link || + sifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } @@ -486,6 +492,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info) const int code = icmp_hdr(skb)->code; unsigned int data_len = 0; struct ip_tunnel *t; + int sifindex; int err; switch (type) { @@ -517,10 +524,9 @@ static int ipip6_err(struct sk_buff *skb, u32 info) err = -ENOENT; - t = ipip6_tunnel_lookup(dev_net(skb->dev), - skb->dev, - iph->daddr, - iph->saddr); + sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0; + t = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, + iph->daddr, iph->saddr, sifindex); if (!t) goto out; @@ -633,10 +639,12 @@ static int ipip6_rcv(struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); struct ip_tunnel *tunnel; + int sifindex; int err; + sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0; tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, - iph->saddr, iph->daddr); + iph->saddr, iph->daddr, sifindex); if (tunnel) { struct pcpu_sw_netstats *tstats; @@ -704,10 +712,13 @@ static int sit_tunnel_rcv(struct sk_buff *skb, u8 ipproto) { const struct iphdr *iph; struct ip_tunnel *tunnel; + int sifindex; + + sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0; iph = ip_hdr(skb); tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, - iph->saddr, iph->daddr); + iph->saddr, iph->daddr, sifindex); if (tunnel) { const struct tnl_ptk_info *tpi; @@ -1848,19 +1859,22 @@ err_alloc_dev: return err; } -static void __net_exit sit_exit_net(struct net *net) +static void __net_exit sit_exit_batch_net(struct list_head *net_list) { LIST_HEAD(list); + struct net *net; rtnl_lock(); - sit_destroy_tunnels(net, &list); + list_for_each_entry(net, net_list, exit_list) + sit_destroy_tunnels(net, &list); + unregister_netdevice_many(&list); rtnl_unlock(); } static struct pernet_operations sit_net_ops = { .init = sit_init_net, - .exit = sit_exit_net, + .exit_batch = sit_exit_batch_net, .id = &sit_net_id, .size = sizeof(struct sit_net), }; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 4e7817abc0b9..e7a3a6b6cf56 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -244,7 +244,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) } req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW); - tcp_select_initial_window(tcp_full_space(sk), req->mss, + tcp_select_initial_window(sk, tcp_full_space(sk), req->mss, &req->rsk_rcv_wnd, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, dst_metric(dst, RTAX_INITRWND)); diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index f7051ba5b8af..a789a8ac6a64 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -98,6 +98,34 @@ static struct ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "max_dst_opts_number", + .data = &init_net.ipv6.sysctl.max_dst_opts_cnt, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "max_hbh_opts_number", + .data = &init_net.ipv6.sysctl.max_hbh_opts_cnt, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "max_dst_opts_length", + .data = &init_net.ipv6.sysctl.max_dst_opts_len, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "max_hbh_length", + .data = &init_net.ipv6.sysctl.max_hbh_opts_len, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; @@ -158,6 +186,10 @@ static int __net_init ipv6_sysctl_net_init(struct net *net) ipv6_table[7].data = &net->ipv6.sysctl.flowlabel_state_ranges; ipv6_table[8].data = &net->ipv6.sysctl.ip_nonlocal_bind; ipv6_table[9].data = &net->ipv6.sysctl.flowlabel_reflect; + ipv6_table[10].data = &net->ipv6.sysctl.max_dst_opts_cnt; + ipv6_table[11].data = &net->ipv6.sysctl.max_hbh_opts_cnt; + ipv6_table[12].data = &net->ipv6.sysctl.max_dst_opts_len; + ipv6_table[13].data = &net->ipv6.sysctl.max_hbh_opts_len; ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 64d94afa427f..6bb98c93edfe 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -69,6 +69,8 @@ #include <crypto/hash.h> #include <linux/scatterlist.h> +#include <trace/events/tcp.h> + static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb); static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req); @@ -890,7 +892,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) int genhash; struct sock *sk1 = NULL; #endif - int oif; + int oif = 0; if (th->rst) return; @@ -939,7 +941,11 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) ack_seq = ntohl(th->seq) + th->syn + th->fin + skb->len - (th->doff << 2); - oif = sk ? sk->sk_bound_dev_if : 0; + if (sk) { + oif = sk->sk_bound_dev_if; + trace_tcp_send_reset(sk, skb); + } + tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0); #ifdef CONFIG_TCP_MD5SIG @@ -1577,8 +1583,9 @@ do_time_wait: refcounted = false; goto process; } - /* Fall through to ACK */ } + /* to ACK */ + /* fall through */ case TCP_TW_ACK: tcp_v6_timewait_ack(sk, skb); break; @@ -1933,8 +1940,8 @@ struct proto tcpv6_prot = { .memory_pressure = &tcp_memory_pressure, .orphan_count = &tcp_orphan_count, .sysctl_mem = sysctl_tcp_mem, - .sysctl_wmem = sysctl_tcp_wmem, - .sysctl_rmem = sysctl_tcp_rmem, + .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem), + .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem), .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp6_sock), .slab_flags = SLAB_TYPESAFE_BY_RCU, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 40d7234c27b9..3f30fa313bf2 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -606,7 +606,7 @@ static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) */ /* if we're overly short, let UDP handle it */ - encap_rcv = ACCESS_ONCE(up->encap_rcv); + encap_rcv = READ_ONCE(up->encap_rcv); if (encap_rcv) { int ret; @@ -1432,7 +1432,7 @@ void udpv6_destroy_sock(struct sock *sk) if (static_key_false(&udpv6_encap_needed) && up->encap_type) { void (*encap_destroy)(struct sock *sk); - encap_destroy = ACCESS_ONCE(up->encap_destroy); + encap_destroy = READ_ONCE(up->encap_destroy); if (encap_destroy) encap_destroy(sk); } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 17e95a0386b3..885ade234a49 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -153,6 +153,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) switch (nexthdr) { case NEXTHDR_FRAGMENT: onlyproto = 1; + /* fall through */ case NEXTHDR_ROUTING: case NEXTHDR_HOP: case NEXTHDR_DEST: diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 4e438bc7ee87..f85f0d7480ac 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -338,6 +338,14 @@ static int __net_init xfrm6_tunnel_net_init(struct net *net) static void __net_exit xfrm6_tunnel_net_exit(struct net *net) { + struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); + unsigned int i; + + for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) + WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i])); + + for (i = 0; i < XFRM6_TUNNEL_SPI_BYSPI_HSIZE; i++) + WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byspi[i])); } static struct pernet_operations xfrm6_tunnel_net_ops = { diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index ac598ec90589..d21a9d128d3e 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -1867,6 +1867,7 @@ static int ipx_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) rc = -EPERM; if (!capable(CAP_NET_ADMIN)) break; + /* fall through */ case SIOCGIFADDR: rc = ipxitf_ioctl(cmd, argp); break; diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index af4e76ac88ff..0b750a22c4b9 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1650,7 +1650,7 @@ static int kcm_clone(struct socket *osock, struct kcm_clone *info, } newfile = sock_alloc_file(newsock, 0, osock->sk->sk_prot_creator->name); - if (unlikely(IS_ERR(newfile))) { + if (IS_ERR(newfile)) { err = PTR_ERR(newfile); goto out_sock_alloc_fail; } diff --git a/net/key/af_key.c b/net/key/af_key.c index a00d607e7224..3dffb892d52c 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3845,7 +3845,7 @@ static void __net_exit pfkey_net_exit(struct net *net) struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); pfkey_exit_proc(net); - BUG_ON(!hlist_empty(&net_pfkey->table)); + WARN_ON(!hlist_empty(&net_pfkey->table)); } static struct pernet_operations pfkey_net_ops = { diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 02d61101b108..115918ad8eca 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -100,8 +100,6 @@ struct l2tp_skb_cb { #define L2TP_SKB_CB(skb) ((struct l2tp_skb_cb *) &skb->cb[sizeof(struct inet_skb_parm)]) -static atomic_t l2tp_tunnel_count; -static atomic_t l2tp_session_count; static struct workqueue_struct *l2tp_wq; /* per-net private data for this module */ @@ -216,12 +214,10 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) } EXPORT_SYMBOL_GPL(l2tp_tunnel_get); -/* Lookup a session. A new reference is held on the returned session. - * Optionally calls session->ref() too if do_ref is true. - */ +/* Lookup a session. A new reference is held on the returned session. */ struct l2tp_session *l2tp_session_get(const struct net *net, struct l2tp_tunnel *tunnel, - u32 session_id, bool do_ref) + u32 session_id) { struct hlist_head *session_list; struct l2tp_session *session; @@ -235,8 +231,6 @@ struct l2tp_session *l2tp_session_get(const struct net *net, hlist_for_each_entry_rcu(session, session_list, global_hlist) { if (session->session_id == session_id) { l2tp_session_inc_refcount(session); - if (do_ref && session->ref) - session->ref(session); rcu_read_unlock_bh(); return session; @@ -252,8 +246,6 @@ struct l2tp_session *l2tp_session_get(const struct net *net, hlist_for_each_entry(session, session_list, hlist) { if (session->session_id == session_id) { l2tp_session_inc_refcount(session); - if (do_ref && session->ref) - session->ref(session); read_unlock_bh(&tunnel->hlist_lock); return session; @@ -265,8 +257,7 @@ struct l2tp_session *l2tp_session_get(const struct net *net, } EXPORT_SYMBOL_GPL(l2tp_session_get); -struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth, - bool do_ref) +struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth) { int hash; struct l2tp_session *session; @@ -277,8 +268,6 @@ struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth, hlist_for_each_entry(session, &tunnel->session_hlist[hash], hlist) { if (++count > nth) { l2tp_session_inc_refcount(session); - if (do_ref && session->ref) - session->ref(session); read_unlock_bh(&tunnel->hlist_lock); return session; } @@ -295,8 +284,7 @@ EXPORT_SYMBOL_GPL(l2tp_session_get_nth); * This is very inefficient but is only used by management interfaces. */ struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, - const char *ifname, - bool do_ref) + const char *ifname) { struct l2tp_net *pn = l2tp_pernet(net); int hash; @@ -307,8 +295,6 @@ struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, hlist_for_each_entry_rcu(session, &pn->l2tp_session_hlist[hash], global_hlist) { if (!strcmp(session->ifname, ifname)) { l2tp_session_inc_refcount(session); - if (do_ref && session->ref) - session->ref(session); rcu_read_unlock_bh(); return session; @@ -322,8 +308,8 @@ struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, } EXPORT_SYMBOL_GPL(l2tp_session_get_by_ifname); -static int l2tp_session_add_to_tunnel(struct l2tp_tunnel *tunnel, - struct l2tp_session *session) +int l2tp_session_register(struct l2tp_session *session, + struct l2tp_tunnel *tunnel) { struct l2tp_session *session_walk; struct hlist_head *g_head; @@ -380,6 +366,7 @@ err_tlock: return err; } +EXPORT_SYMBOL_GPL(l2tp_session_register); /* Lookup a tunnel by id */ @@ -484,9 +471,6 @@ static void l2tp_recv_dequeue_skb(struct l2tp_session *session, struct sk_buff * (*session->recv_skb)(session, skb, L2TP_SKB_CB(skb)->length); else kfree_skb(skb); - - if (session->deref) - (*session->deref)(session); } /* Dequeue skbs from the session's reorder_q, subject to packet order. @@ -515,8 +499,6 @@ start: session->reorder_skip = 1; __skb_unlink(skb, &session->reorder_q); kfree_skb(skb); - if (session->deref) - (*session->deref)(session); continue; } @@ -689,9 +671,6 @@ discard: * a data (not control) frame before coming here. Fields up to the * session-id have already been parsed and ptr points to the data * after the session-id. - * - * session->ref() must have been called prior to l2tp_recv_common(). - * session->deref() will be called automatically after skb is processed. */ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, unsigned char *ptr, unsigned char *optr, u16 hdrflags, @@ -858,9 +837,6 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, discard: atomic_long_inc(&session->stats.rx_errors); kfree_skb(skb); - - if (session->deref) - (*session->deref)(session); } EXPORT_SYMBOL(l2tp_recv_common); @@ -874,8 +850,6 @@ int l2tp_session_queue_purge(struct l2tp_session *session) while ((skb = skb_dequeue(&session->reorder_q))) { atomic_long_inc(&session->stats.rx_errors); kfree_skb(skb); - if (session->deref) - (*session->deref)(session); } return 0; } @@ -967,13 +941,10 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, } /* Find the session context */ - session = l2tp_session_get(tunnel->l2tp_net, tunnel, session_id, true); + session = l2tp_session_get(tunnel->l2tp_net, tunnel, session_id); if (!session || !session->recv_skb) { - if (session) { - if (session->deref) - session->deref(session); + if (session) l2tp_session_dec_refcount(session); - } /* Not found? Pass to userspace to deal with */ l2tp_info(tunnel, L2TP_MSG_DATA, @@ -1274,9 +1245,6 @@ static void l2tp_tunnel_destruct(struct sock *sk) spin_lock_bh(&pn->l2tp_tunnel_list_lock); list_del_rcu(&tunnel->list); spin_unlock_bh(&pn->l2tp_tunnel_list_lock); - atomic_dec(&l2tp_tunnel_count); - - l2tp_tunnel_closeall(tunnel); tunnel->sock = NULL; l2tp_tunnel_dec_refcount(tunnel); @@ -1317,9 +1285,6 @@ again: if (test_and_set_bit(0, &session->dead)) goto again; - if (session->ref != NULL) - (*session->ref)(session); - write_unlock_bh(&tunnel->hlist_lock); __l2tp_session_unhash(session); @@ -1328,9 +1293,6 @@ again: if (session->session_close != NULL) (*session->session_close)(session); - if (session->deref != NULL) - (*session->deref)(session); - l2tp_session_dec_refcount(session); write_lock_bh(&tunnel->hlist_lock); @@ -1661,7 +1623,6 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 /* Add tunnel to our list */ INIT_LIST_HEAD(&tunnel->list); - atomic_inc(&l2tp_tunnel_count); /* Bump the reference count. The tunnel context is deleted * only when this drops to zero. Must be done before list insertion @@ -1707,8 +1668,6 @@ void l2tp_session_free(struct l2tp_session *session) if (tunnel) { BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC); - if (session->session_id != 0) - atomic_dec(&l2tp_session_count); sock_put(tunnel->sock); session->tunnel = NULL; l2tp_tunnel_dec_refcount(tunnel); @@ -1754,15 +1713,13 @@ int l2tp_session_delete(struct l2tp_session *session) if (test_and_set_bit(0, &session->dead)) return 0; - if (session->ref) - (*session->ref)(session); __l2tp_session_unhash(session); l2tp_session_queue_purge(session); if (session->session_close != NULL) (*session->session_close)(session); - if (session->deref) - (*session->deref)(session); + l2tp_session_dec_refcount(session); + return 0; } EXPORT_SYMBOL_GPL(l2tp_session_delete); @@ -1788,7 +1745,6 @@ EXPORT_SYMBOL_GPL(l2tp_session_set_header_len); struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg) { struct l2tp_session *session; - int err; session = kzalloc(sizeof(struct l2tp_session) + priv_size, GFP_KERNEL); if (session != NULL) { @@ -1846,17 +1802,6 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn refcount_set(&session->ref_count, 1); - err = l2tp_session_add_to_tunnel(tunnel, session); - if (err) { - kfree(session); - - return ERR_PTR(err); - } - - /* Ignore management session in session count value */ - if (session->session_id != 0) - atomic_inc(&l2tp_session_count); - return session; } @@ -1888,15 +1833,19 @@ static __net_exit void l2tp_exit_net(struct net *net) { struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_tunnel *tunnel = NULL; + int hash; rcu_read_lock_bh(); list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) { - (void)l2tp_tunnel_delete(tunnel); + l2tp_tunnel_delete(tunnel); } rcu_read_unlock_bh(); flush_workqueue(l2tp_wq); rcu_barrier(); + + for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) + WARN_ON_ONCE(!hlist_empty(&pn->l2tp_session_hlist[hash])); } static struct pernet_operations l2tp_net_ops = { diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 67c79d9b5c6c..9534e16965cc 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -129,8 +129,6 @@ struct l2tp_session { int (*build_header)(struct l2tp_session *session, void *buf); void (*recv_skb)(struct l2tp_session *session, struct sk_buff *skb, int data_len); void (*session_close)(struct l2tp_session *session); - void (*ref)(struct l2tp_session *session); - void (*deref)(struct l2tp_session *session); #if IS_ENABLED(CONFIG_L2TP_DEBUGFS) void (*show)(struct seq_file *m, void *priv); #endif @@ -245,12 +243,10 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id); struct l2tp_session *l2tp_session_get(const struct net *net, struct l2tp_tunnel *tunnel, - u32 session_id, bool do_ref); -struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth, - bool do_ref); + u32 session_id); +struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth); struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, - const char *ifname, - bool do_ref); + const char *ifname); struct l2tp_tunnel *l2tp_tunnel_find(const struct net *net, u32 tunnel_id); struct l2tp_tunnel *l2tp_tunnel_find_nth(const struct net *net, int nth); @@ -263,6 +259,9 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg); +int l2tp_session_register(struct l2tp_session *session, + struct l2tp_tunnel *tunnel); + void __l2tp_session_unhash(struct l2tp_session *session); int l2tp_session_delete(struct l2tp_session *session); void l2tp_session_free(struct l2tp_session *session); @@ -295,37 +294,17 @@ static inline void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel) /* Session reference counts. Incremented when code obtains a reference * to a session. */ -static inline void l2tp_session_inc_refcount_1(struct l2tp_session *session) +static inline void l2tp_session_inc_refcount(struct l2tp_session *session) { refcount_inc(&session->ref_count); } -static inline void l2tp_session_dec_refcount_1(struct l2tp_session *session) +static inline void l2tp_session_dec_refcount(struct l2tp_session *session) { if (refcount_dec_and_test(&session->ref_count)) l2tp_session_free(session); } -#ifdef L2TP_REFCNT_DEBUG -#define l2tp_session_inc_refcount(_s) \ -do { \ - pr_debug("l2tp_session_inc_refcount: %s:%d %s: cnt=%d\n", \ - __func__, __LINE__, (_s)->name, \ - refcount_read(&_s->ref_count)); \ - l2tp_session_inc_refcount_1(_s); \ -} while (0) -#define l2tp_session_dec_refcount(_s) \ -do { \ - pr_debug("l2tp_session_dec_refcount: %s:%d %s: cnt=%d\n", \ - __func__, __LINE__, (_s)->name, \ - refcount_read(&_s->ref_count)); \ - l2tp_session_dec_refcount_1(_s); \ -} while (0) -#else -#define l2tp_session_inc_refcount(s) l2tp_session_inc_refcount_1(s) -#define l2tp_session_dec_refcount(s) l2tp_session_dec_refcount_1(s) -#endif - #define l2tp_printk(ptr, type, func, fmt, ...) \ do { \ if (((ptr)->debug) & (type)) \ diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index 53bae54c4d6e..eb69411bcb47 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -53,7 +53,7 @@ static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd) static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd) { - pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true); + pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx); pd->session_idx++; if (pd->session == NULL) { @@ -241,8 +241,6 @@ static int l2tp_dfs_seq_show(struct seq_file *m, void *v) l2tp_dfs_seq_tunnel_show(m, pd->tunnel); } else { l2tp_dfs_seq_session_show(m, pd->session); - if (pd->session->deref) - pd->session->deref(pd->session); l2tp_session_dec_refcount(pd->session); } diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 014a7bc2a872..5c366ecfa1cb 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -41,8 +41,6 @@ /* via netdev_priv() */ struct l2tp_eth { - struct net_device *dev; - struct sock *tunnel_sock; struct l2tp_session *session; atomic_long_t tx_bytes; atomic_long_t tx_packets; @@ -54,15 +52,12 @@ struct l2tp_eth { /* via l2tp_session_priv() */ struct l2tp_eth_sess { - struct net_device *dev; + struct net_device __rcu *dev; }; static int l2tp_eth_dev_init(struct net_device *dev) { - struct l2tp_eth *priv = netdev_priv(dev); - - priv->dev = dev; eth_hw_addr_random(dev); eth_broadcast_addr(dev->broadcast); netdev_lockdep_set_classes(dev); @@ -72,7 +67,14 @@ static int l2tp_eth_dev_init(struct net_device *dev) static void l2tp_eth_dev_uninit(struct net_device *dev) { - dev_put(dev); + struct l2tp_eth *priv = netdev_priv(dev); + struct l2tp_eth_sess *spriv; + + spriv = l2tp_session_priv(priv->session); + RCU_INIT_POINTER(spriv->dev, NULL); + /* No need for synchronize_net() here. We're called by + * unregister_netdev*(), which does the synchronisation for us. + */ } static int l2tp_eth_dev_xmit(struct sk_buff *skb, struct net_device *dev) @@ -130,8 +132,8 @@ static void l2tp_eth_dev_setup(struct net_device *dev) static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, int data_len) { struct l2tp_eth_sess *spriv = l2tp_session_priv(session); - struct net_device *dev = spriv->dev; - struct l2tp_eth *priv = netdev_priv(dev); + struct net_device *dev; + struct l2tp_eth *priv; if (session->debug & L2TP_MSG_DATA) { unsigned int length; @@ -155,16 +157,25 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, skb_dst_drop(skb); nf_reset(skb); + rcu_read_lock(); + dev = rcu_dereference(spriv->dev); + if (!dev) + goto error_rcu; + + priv = netdev_priv(dev); if (dev_forward_skb(dev, skb) == NET_RX_SUCCESS) { atomic_long_inc(&priv->rx_packets); atomic_long_add(data_len, &priv->rx_bytes); } else { atomic_long_inc(&priv->rx_errors); } + rcu_read_unlock(); + return; +error_rcu: + rcu_read_unlock(); error: - atomic_long_inc(&priv->rx_errors); kfree_skb(skb); } @@ -175,11 +186,15 @@ static void l2tp_eth_delete(struct l2tp_session *session) if (session) { spriv = l2tp_session_priv(session); - dev = spriv->dev; + + rtnl_lock(); + dev = rtnl_dereference(spriv->dev); if (dev) { - unregister_netdev(dev); - spriv->dev = NULL; + unregister_netdevice(dev); + rtnl_unlock(); module_put(THIS_MODULE); + } else { + rtnl_unlock(); } } } @@ -189,9 +204,20 @@ static void l2tp_eth_show(struct seq_file *m, void *arg) { struct l2tp_session *session = arg; struct l2tp_eth_sess *spriv = l2tp_session_priv(session); - struct net_device *dev = spriv->dev; + struct net_device *dev; + + rcu_read_lock(); + dev = rcu_dereference(spriv->dev); + if (!dev) { + rcu_read_unlock(); + return; + } + dev_hold(dev); + rcu_read_unlock(); seq_printf(m, " interface %s\n", dev->name); + + dev_put(dev); } #endif @@ -268,14 +294,14 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel, peer_session_id, cfg); if (IS_ERR(session)) { rc = PTR_ERR(session); - goto out; + goto err; } dev = alloc_netdev(sizeof(*priv), name, name_assign_type, l2tp_eth_dev_setup); if (!dev) { rc = -ENOMEM; - goto out_del_session; + goto err_sess; } dev_net_set(dev, net); @@ -284,10 +310,8 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel, l2tp_eth_adjust_mtu(tunnel, session, dev); priv = netdev_priv(dev); - priv->dev = dev; priv->session = session; - priv->tunnel_sock = tunnel->sock; session->recv_skb = l2tp_eth_dev_recv; session->session_close = l2tp_eth_delete; #if IS_ENABLED(CONFIG_L2TP_DEBUGFS) @@ -295,26 +319,48 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel, #endif spriv = l2tp_session_priv(session); - spriv->dev = dev; - rc = register_netdev(dev); - if (rc < 0) - goto out_del_dev; + l2tp_session_inc_refcount(session); + + rtnl_lock(); + + /* Register both device and session while holding the rtnl lock. This + * ensures that l2tp_eth_delete() will see that there's a device to + * unregister, even if it happened to run before we assign spriv->dev. + */ + rc = l2tp_session_register(session, tunnel); + if (rc < 0) { + rtnl_unlock(); + goto err_sess_dev; + } + + rc = register_netdevice(dev); + if (rc < 0) { + rtnl_unlock(); + l2tp_session_delete(session); + l2tp_session_dec_refcount(session); + free_netdev(dev); + + return rc; + } - __module_get(THIS_MODULE); - /* Must be done after register_netdev() */ strlcpy(session->ifname, dev->name, IFNAMSIZ); + rcu_assign_pointer(spriv->dev, dev); - dev_hold(dev); + rtnl_unlock(); + + l2tp_session_dec_refcount(session); + + __module_get(THIS_MODULE); return 0; -out_del_dev: +err_sess_dev: + l2tp_session_dec_refcount(session); free_netdev(dev); - spriv->dev = NULL; -out_del_session: - l2tp_session_delete(session); -out: +err_sess: + kfree(session); +err: return rc; } diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index e4280b6568b4..ff61124fdf59 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -144,7 +144,7 @@ static int l2tp_ip_recv(struct sk_buff *skb) } /* Ok, this is a data packet. Lookup the session. */ - session = l2tp_session_get(net, NULL, session_id, true); + session = l2tp_session_get(net, NULL, session_id); if (!session) goto discard; @@ -199,8 +199,6 @@ pass_up: return sk_receive_skb(sk, skb, 1); discard_sess: - if (session->deref) - session->deref(session); l2tp_session_dec_refcount(session); goto discard; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 8bcaa975b432..192344688c06 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -157,7 +157,7 @@ static int l2tp_ip6_recv(struct sk_buff *skb) } /* Ok, this is a data packet. Lookup the session. */ - session = l2tp_session_get(net, NULL, session_id, true); + session = l2tp_session_get(net, NULL, session_id); if (!session) goto discard; @@ -213,8 +213,6 @@ pass_up: return sk_receive_skb(sk, skb, 1); discard_sess: - if (session->deref) - session->deref(session); l2tp_session_dec_refcount(session); goto discard; diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 7135f4645d3a..a1f24fb2be98 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -48,8 +48,7 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, /* Accessed under genl lock */ static const struct l2tp_nl_cmd_ops *l2tp_nl_cmd_ops[__L2TP_PWTYPE_MAX]; -static struct l2tp_session *l2tp_nl_session_get(struct genl_info *info, - bool do_ref) +static struct l2tp_session *l2tp_nl_session_get(struct genl_info *info) { u32 tunnel_id; u32 session_id; @@ -60,15 +59,14 @@ static struct l2tp_session *l2tp_nl_session_get(struct genl_info *info, if (info->attrs[L2TP_ATTR_IFNAME]) { ifname = nla_data(info->attrs[L2TP_ATTR_IFNAME]); - session = l2tp_session_get_by_ifname(net, ifname, do_ref); + session = l2tp_session_get_by_ifname(net, ifname); } else if ((info->attrs[L2TP_ATTR_SESSION_ID]) && (info->attrs[L2TP_ATTR_CONN_ID])) { tunnel_id = nla_get_u32(info->attrs[L2TP_ATTR_CONN_ID]); session_id = nla_get_u32(info->attrs[L2TP_ATTR_SESSION_ID]); tunnel = l2tp_tunnel_get(net, tunnel_id); if (tunnel) { - session = l2tp_session_get(net, tunnel, session_id, - do_ref); + session = l2tp_session_get(net, tunnel, session_id); l2tp_tunnel_dec_refcount(tunnel); } } @@ -282,7 +280,7 @@ static int l2tp_nl_cmd_tunnel_delete(struct sk_buff *skb, struct genl_info *info l2tp_tunnel_notify(&l2tp_nl_family, info, tunnel, L2TP_CMD_TUNNEL_DELETE); - (void) l2tp_tunnel_delete(tunnel); + l2tp_tunnel_delete(tunnel); l2tp_tunnel_dec_refcount(tunnel); @@ -406,7 +404,7 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla if (nla_put_u16(skb, L2TP_ATTR_UDP_SPORT, ntohs(inet->inet_sport)) || nla_put_u16(skb, L2TP_ATTR_UDP_DPORT, ntohs(inet->inet_dport))) goto nla_put_failure; - /* NOBREAK */ + /* fall through */ case L2TP_ENCAPTYPE_IP: #if IS_ENABLED(CONFIG_IPV6) if (np) { @@ -649,7 +647,7 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf &cfg); if (ret >= 0) { - session = l2tp_session_get(net, tunnel, session_id, false); + session = l2tp_session_get(net, tunnel, session_id); if (session) { ret = l2tp_session_notify(&l2tp_nl_family, info, session, L2TP_CMD_SESSION_CREATE); @@ -669,7 +667,7 @@ static int l2tp_nl_cmd_session_delete(struct sk_buff *skb, struct genl_info *inf struct l2tp_session *session; u16 pw_type; - session = l2tp_nl_session_get(info, true); + session = l2tp_nl_session_get(info); if (session == NULL) { ret = -ENODEV; goto out; @@ -683,8 +681,6 @@ static int l2tp_nl_cmd_session_delete(struct sk_buff *skb, struct genl_info *inf if (l2tp_nl_cmd_ops[pw_type] && l2tp_nl_cmd_ops[pw_type]->session_delete) ret = (*l2tp_nl_cmd_ops[pw_type]->session_delete)(session); - if (session->deref) - session->deref(session); l2tp_session_dec_refcount(session); out: @@ -696,7 +692,7 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf int ret = 0; struct l2tp_session *session; - session = l2tp_nl_session_get(info, false); + session = l2tp_nl_session_get(info); if (session == NULL) { ret = -ENODEV; goto out; @@ -828,7 +824,7 @@ static int l2tp_nl_cmd_session_get(struct sk_buff *skb, struct genl_info *info) struct sk_buff *msg; int ret; - session = l2tp_nl_session_get(info, false); + session = l2tp_nl_session_get(info); if (session == NULL) { ret = -ENODEV; goto err; @@ -874,7 +870,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback goto out; } - session = l2tp_session_get_nth(tunnel, si, false); + session = l2tp_session_get_nth(tunnel, si); if (session == NULL) { ti++; tunnel = NULL; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 0c2738349442..b412fc3351dc 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -122,10 +122,11 @@ struct pppol2tp_session { int owner; /* pid that opened the socket */ - struct sock *sock; /* Pointer to the session + struct mutex sk_lock; /* Protects .sk */ + struct sock __rcu *sk; /* Pointer to the session * PPPoX socket */ - struct sock *tunnel_sock; /* Pointer to the tunnel UDP - * socket */ + struct sock *__sk; /* Copy of .sk, for cleanup */ + struct rcu_head rcu; /* For asynchronous release */ int flags; /* accessed by PPPIOCGFLAGS. * Unused. */ }; @@ -138,6 +139,24 @@ static const struct ppp_channel_ops pppol2tp_chan_ops = { static const struct proto_ops pppol2tp_ops; +/* Retrieves the pppol2tp socket associated to a session. + * A reference is held on the returned socket, so this function must be paired + * with sock_put(). + */ +static struct sock *pppol2tp_session_get_sock(struct l2tp_session *session) +{ + struct pppol2tp_session *ps = l2tp_session_priv(session); + struct sock *sk; + + rcu_read_lock(); + sk = rcu_dereference(ps->sk); + if (sk) + sock_hold(sk); + rcu_read_unlock(); + + return sk; +} + /* Helpers to obtain tunnel/session contexts from sockets. */ static inline struct l2tp_session *pppol2tp_sock_to_session(struct sock *sk) @@ -224,7 +243,8 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int /* If the socket is bound, send it in to PPP's input queue. Otherwise * queue it on the session socket. */ - sk = ps->sock; + rcu_read_lock(); + sk = rcu_dereference(ps->sk); if (sk == NULL) goto no_sock; @@ -247,30 +267,16 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int kfree_skb(skb); } } + rcu_read_unlock(); return; no_sock: + rcu_read_unlock(); l2tp_info(session, L2TP_MSG_DATA, "%s: no socket\n", session->name); kfree_skb(skb); } -static void pppol2tp_session_sock_hold(struct l2tp_session *session) -{ - struct pppol2tp_session *ps = l2tp_session_priv(session); - - if (ps->sock) - sock_hold(ps->sock); -} - -static void pppol2tp_session_sock_put(struct l2tp_session *session) -{ - struct pppol2tp_session *ps = l2tp_session_priv(session); - - if (ps->sock) - sock_put(ps->sock); -} - /************************************************************************ * Transmit handling ***********************************************************************/ @@ -287,7 +293,6 @@ static int pppol2tp_sendmsg(struct socket *sock, struct msghdr *m, int error; struct l2tp_session *session; struct l2tp_tunnel *tunnel; - struct pppol2tp_session *ps; int uhlen; error = -ENOTCONN; @@ -300,10 +305,7 @@ static int pppol2tp_sendmsg(struct socket *sock, struct msghdr *m, if (session == NULL) goto error; - ps = l2tp_session_priv(session); - tunnel = l2tp_sock_to_tunnel(ps->tunnel_sock); - if (tunnel == NULL) - goto error_put_sess; + tunnel = session->tunnel; uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0; @@ -314,7 +316,7 @@ static int pppol2tp_sendmsg(struct socket *sock, struct msghdr *m, 2 + total_len, /* 2 bytes for PPP_ALLSTATIONS & PPP_UI */ 0, GFP_KERNEL); if (!skb) - goto error_put_sess_tun; + goto error_put_sess; /* Reserve space for headers. */ skb_reserve(skb, NET_SKB_PAD); @@ -332,20 +334,17 @@ static int pppol2tp_sendmsg(struct socket *sock, struct msghdr *m, error = memcpy_from_msg(skb_put(skb, total_len), m, total_len); if (error < 0) { kfree_skb(skb); - goto error_put_sess_tun; + goto error_put_sess; } local_bh_disable(); l2tp_xmit_skb(session, skb, session->hdr_len); local_bh_enable(); - sock_put(ps->tunnel_sock); sock_put(sk); return total_len; -error_put_sess_tun: - sock_put(ps->tunnel_sock); error_put_sess: sock_put(sk); error: @@ -369,10 +368,8 @@ error: static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) { struct sock *sk = (struct sock *) chan->private; - struct sock *sk_tun; struct l2tp_session *session; struct l2tp_tunnel *tunnel; - struct pppol2tp_session *ps; int uhlen, headroom; if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED)) @@ -383,13 +380,7 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) if (session == NULL) goto abort; - ps = l2tp_session_priv(session); - sk_tun = ps->tunnel_sock; - if (sk_tun == NULL) - goto abort_put_sess; - tunnel = l2tp_sock_to_tunnel(sk_tun); - if (tunnel == NULL) - goto abort_put_sess; + tunnel = session->tunnel; uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0; headroom = NET_SKB_PAD + @@ -398,7 +389,7 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) session->hdr_len + /* L2TP header */ 2; /* 2 bytes for PPP_ALLSTATIONS & PPP_UI */ if (skb_cow_head(skb, headroom)) - goto abort_put_sess_tun; + goto abort_put_sess; /* Setup PPP header */ __skb_push(skb, 2); @@ -409,12 +400,10 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) l2tp_xmit_skb(session, skb, session->hdr_len); local_bh_enable(); - sock_put(sk_tun); sock_put(sk); + return 1; -abort_put_sess_tun: - sock_put(sk_tun); abort_put_sess: sock_put(sk); abort: @@ -431,17 +420,16 @@ abort: */ static void pppol2tp_session_close(struct l2tp_session *session) { - struct pppol2tp_session *ps = l2tp_session_priv(session); - struct sock *sk = ps->sock; - struct socket *sock = sk->sk_socket; + struct sock *sk; BUG_ON(session->magic != L2TP_SESSION_MAGIC); - if (sock) - inet_shutdown(sock, SEND_SHUTDOWN); - - /* Don't let the session go away before our socket does */ - l2tp_session_inc_refcount(session); + sk = pppol2tp_session_get_sock(session); + if (sk) { + if (sk->sk_socket) + inet_shutdown(sk->sk_socket, SEND_SHUTDOWN); + sock_put(sk); + } } /* Really kill the session socket. (Called from sock_put() if @@ -461,6 +449,14 @@ static void pppol2tp_session_destruct(struct sock *sk) } } +static void pppol2tp_put_sk(struct rcu_head *head) +{ + struct pppol2tp_session *ps; + + ps = container_of(head, typeof(*ps), rcu); + sock_put(ps->__sk); +} + /* Called when the PPPoX socket (session) is closed. */ static int pppol2tp_release(struct socket *sock) @@ -486,11 +482,23 @@ static int pppol2tp_release(struct socket *sock) session = pppol2tp_sock_to_session(sk); - /* Purge any queued data */ if (session != NULL) { - __l2tp_session_unhash(session); - l2tp_session_queue_purge(session); - sock_put(sk); + struct pppol2tp_session *ps; + + l2tp_session_delete(session); + + ps = l2tp_session_priv(session); + mutex_lock(&ps->sk_lock); + ps->__sk = rcu_dereference_protected(ps->sk, + lockdep_is_held(&ps->sk_lock)); + RCU_INIT_POINTER(ps->sk, NULL); + mutex_unlock(&ps->sk_lock); + call_rcu(&ps->rcu, pppol2tp_put_sk); + + /* Rely on the sock_put() call at the end of the function for + * dropping the reference held by pppol2tp_sock_to_session(). + * The last reference will be dropped by pppol2tp_put_sk(). + */ } release_sock(sk); @@ -557,16 +565,46 @@ out: static void pppol2tp_show(struct seq_file *m, void *arg) { struct l2tp_session *session = arg; - struct pppol2tp_session *ps = l2tp_session_priv(session); + struct sock *sk; - if (ps) { - struct pppox_sock *po = pppox_sk(ps->sock); - if (po) - seq_printf(m, " interface %s\n", ppp_dev_name(&po->chan)); + sk = pppol2tp_session_get_sock(session); + if (sk) { + struct pppox_sock *po = pppox_sk(sk); + + seq_printf(m, " interface %s\n", ppp_dev_name(&po->chan)); + sock_put(sk); } } #endif +static void pppol2tp_session_init(struct l2tp_session *session) +{ + struct pppol2tp_session *ps; + struct dst_entry *dst; + + session->recv_skb = pppol2tp_recv; + session->session_close = pppol2tp_session_close; +#if IS_ENABLED(CONFIG_L2TP_DEBUGFS) + session->show = pppol2tp_show; +#endif + + ps = l2tp_session_priv(session); + mutex_init(&ps->sk_lock); + ps->owner = current->pid; + + /* If PMTU discovery was enabled, use the MTU that was discovered */ + dst = sk_dst_get(session->tunnel->sock); + if (dst) { + u32 pmtu = dst_mtu(dst); + + if (pmtu) { + session->mtu = pmtu - PPPOL2TP_HEADER_OVERHEAD; + session->mru = pmtu - PPPOL2TP_HEADER_OVERHEAD; + } + dst_release(dst); + } +} + /* connect() handler. Attach a PPPoX socket to a tunnel UDP socket */ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, @@ -578,7 +616,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, struct l2tp_session *session = NULL; struct l2tp_tunnel *tunnel; struct pppol2tp_session *ps; - struct dst_entry *dst; struct l2tp_session_cfg cfg = { 0, }; int error = 0; u32 tunnel_id, peer_tunnel_id; @@ -688,7 +725,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, if (tunnel->peer_tunnel_id == 0) tunnel->peer_tunnel_id = peer_tunnel_id; - session = l2tp_session_get(sock_net(sk), tunnel, session_id, false); + session = l2tp_session_get(sock_net(sk), tunnel, session_id); if (session) { drop_refcnt = true; ps = l2tp_session_priv(session); @@ -696,13 +733,10 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, /* Using a pre-existing session is fine as long as it hasn't * been connected yet. */ - if (ps->sock) { - error = -EEXIST; - goto end; - } - - /* consistency checks */ - if (ps->tunnel_sock != tunnel->sock) { + mutex_lock(&ps->sk_lock); + if (rcu_dereference_protected(ps->sk, + lockdep_is_held(&ps->sk_lock))) { + mutex_unlock(&ps->sk_lock); error = -EEXIST; goto end; } @@ -718,35 +752,19 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, error = PTR_ERR(session); goto end; } - } - - /* Associate session with its PPPoL2TP socket */ - ps = l2tp_session_priv(session); - ps->owner = current->pid; - ps->sock = sk; - ps->tunnel_sock = tunnel->sock; - session->recv_skb = pppol2tp_recv; - session->session_close = pppol2tp_session_close; -#if IS_ENABLED(CONFIG_L2TP_DEBUGFS) - session->show = pppol2tp_show; -#endif - - /* We need to know each time a skb is dropped from the reorder - * queue. - */ - session->ref = pppol2tp_session_sock_hold; - session->deref = pppol2tp_session_sock_put; - - /* If PMTU discovery was enabled, use the MTU that was discovered */ - dst = sk_dst_get(tunnel->sock); - if (dst != NULL) { - u32 pmtu = dst_mtu(dst); + pppol2tp_session_init(session); + ps = l2tp_session_priv(session); + l2tp_session_inc_refcount(session); - if (pmtu != 0) - session->mtu = session->mru = pmtu - - PPPOL2TP_HEADER_OVERHEAD; - dst_release(dst); + mutex_lock(&ps->sk_lock); + error = l2tp_session_register(session, tunnel); + if (error < 0) { + mutex_unlock(&ps->sk_lock); + kfree(session); + goto end; + } + drop_refcnt = true; } /* Special case: if source & dest session_id == 0x0000, this @@ -771,12 +789,23 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, po->chan.mtu = session->mtu; error = ppp_register_net_channel(sock_net(sk), &po->chan); - if (error) + if (error) { + mutex_unlock(&ps->sk_lock); goto end; + } out_no_ppp: /* This is how we get the session context from the socket. */ sk->sk_user_data = session; + rcu_assign_pointer(ps->sk, sk); + mutex_unlock(&ps->sk_lock); + + /* Keep the reference we've grabbed on the session: sk doesn't expect + * the session to disappear. pppol2tp_session_destruct() is responsible + * for dropping it. + */ + drop_refcnt = false; + sk->sk_state = PPPOX_CONNECTED; l2tp_info(session, L2TP_MSG_CONTROL, "%s: created\n", session->name); @@ -800,12 +829,11 @@ static int pppol2tp_session_create(struct net *net, struct l2tp_tunnel *tunnel, { int error; struct l2tp_session *session; - struct pppol2tp_session *ps; /* Error if tunnel socket is not prepped */ if (!tunnel->sock) { error = -ENOENT; - goto out; + goto err; } /* Default MTU values. */ @@ -820,18 +848,20 @@ static int pppol2tp_session_create(struct net *net, struct l2tp_tunnel *tunnel, peer_session_id, cfg); if (IS_ERR(session)) { error = PTR_ERR(session); - goto out; + goto err; } - ps = l2tp_session_priv(session); - ps->tunnel_sock = tunnel->sock; + pppol2tp_session_init(session); - l2tp_info(session, L2TP_MSG_CONTROL, "%s: created\n", - session->name); + error = l2tp_session_register(session, tunnel); + if (error < 0) + goto err_sess; - error = 0; + return 0; -out: +err_sess: + kfree(session); +err: return error; } @@ -862,9 +892,7 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr, goto end; pls = l2tp_session_priv(session); - tunnel = l2tp_sock_to_tunnel(pls->tunnel_sock); - if (tunnel == NULL) - goto end_put_sess; + tunnel = session->tunnel; inet = inet_sk(tunnel->sock); if ((tunnel->version == 2) && (tunnel->sock->sk_family == AF_INET)) { @@ -944,8 +972,6 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr, *usockaddr_len = len; error = 0; - sock_put(pls->tunnel_sock); -end_put_sess: sock_put(sk); end: return error; @@ -992,12 +1018,10 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session, "%s: pppol2tp_session_ioctl(cmd=%#x, arg=%#lx)\n", session->name, cmd, arg); - sk = ps->sock; + sk = pppol2tp_session_get_sock(session); if (!sk) return -EBADR; - sock_hold(sk); - switch (cmd) { case SIOCGIFMTU: err = -ENXIO; @@ -1143,13 +1167,11 @@ static int pppol2tp_tunnel_ioctl(struct l2tp_tunnel *tunnel, /* resend to session ioctl handler */ struct l2tp_session *session = l2tp_session_get(sock_net(sk), tunnel, - stats.session_id, true); + stats.session_id); if (session) { err = pppol2tp_session_ioctl(session, cmd, arg); - if (session->deref) - session->deref(session); l2tp_session_dec_refcount(session); } else { err = -EBADR; @@ -1188,7 +1210,6 @@ static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd, struct sock *sk = sock->sk; struct l2tp_session *session; struct l2tp_tunnel *tunnel; - struct pppol2tp_session *ps; int err; if (!sk) @@ -1212,16 +1233,10 @@ static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd, /* Special case: if session's session_id is zero, treat ioctl as a * tunnel ioctl */ - ps = l2tp_session_priv(session); if ((session->session_id == 0) && (session->peer_session_id == 0)) { - err = -EBADF; - tunnel = l2tp_sock_to_tunnel(ps->tunnel_sock); - if (tunnel == NULL) - goto end_put_sess; - + tunnel = session->tunnel; err = pppol2tp_tunnel_ioctl(tunnel, cmd, arg); - sock_put(ps->tunnel_sock); goto end_put_sess; } @@ -1273,7 +1288,6 @@ static int pppol2tp_session_setsockopt(struct sock *sk, int optname, int val) { int err = 0; - struct pppol2tp_session *ps = l2tp_session_priv(session); switch (optname) { case PPPOL2TP_SO_RECVSEQ: @@ -1294,8 +1308,8 @@ static int pppol2tp_session_setsockopt(struct sock *sk, } session->send_seq = !!val; { - struct sock *ssk = ps->sock; - struct pppox_sock *po = pppox_sk(ssk); + struct pppox_sock *po = pppox_sk(sk); + po->chan.hdrlen = val ? PPPOL2TP_L2TP_HDR_SIZE_SEQ : PPPOL2TP_L2TP_HDR_SIZE_NOSEQ; } @@ -1348,7 +1362,6 @@ static int pppol2tp_setsockopt(struct socket *sock, int level, int optname, struct sock *sk = sock->sk; struct l2tp_session *session; struct l2tp_tunnel *tunnel; - struct pppol2tp_session *ps; int val; int err; @@ -1373,20 +1386,14 @@ static int pppol2tp_setsockopt(struct socket *sock, int level, int optname, /* Special case: if session_id == 0x0000, treat as operation on tunnel */ - ps = l2tp_session_priv(session); if ((session->session_id == 0) && (session->peer_session_id == 0)) { - err = -EBADF; - tunnel = l2tp_sock_to_tunnel(ps->tunnel_sock); - if (tunnel == NULL) - goto end_put_sess; - + tunnel = session->tunnel; err = pppol2tp_tunnel_setsockopt(sk, tunnel, optname, val); - sock_put(ps->tunnel_sock); - } else + } else { err = pppol2tp_session_setsockopt(sk, session, optname, val); + } -end_put_sess: sock_put(sk); end: return err; @@ -1474,7 +1481,6 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname, struct l2tp_tunnel *tunnel; int val, len; int err; - struct pppol2tp_session *ps; if (level != SOL_PPPOL2TP) return -EINVAL; @@ -1498,16 +1504,10 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname, goto end; /* Special case: if session_id == 0x0000, treat as operation on tunnel */ - ps = l2tp_session_priv(session); if ((session->session_id == 0) && (session->peer_session_id == 0)) { - err = -EBADF; - tunnel = l2tp_sock_to_tunnel(ps->tunnel_sock); - if (tunnel == NULL) - goto end_put_sess; - + tunnel = session->tunnel; err = pppol2tp_tunnel_getsockopt(sk, tunnel, optname, &val); - sock_put(ps->tunnel_sock); if (err) goto end_put_sess; } else { @@ -1566,7 +1566,7 @@ static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd) static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd) { - pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true); + pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx); pd->session_idx++; if (pd->session == NULL) { @@ -1634,8 +1634,9 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v) { struct l2tp_session *session = v; struct l2tp_tunnel *tunnel = session->tunnel; - struct pppol2tp_session *ps = l2tp_session_priv(session); - struct pppox_sock *po = pppox_sk(ps->sock); + unsigned char state; + char user_data_ok; + struct sock *sk; u32 ip = 0; u16 port = 0; @@ -1645,6 +1646,15 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v) port = ntohs(inet->inet_sport); } + sk = pppol2tp_session_get_sock(session); + if (sk) { + state = sk->sk_state; + user_data_ok = (session == sk->sk_user_data) ? 'Y' : 'N'; + } else { + state = 0; + user_data_ok = 'N'; + } + seq_printf(m, " SESSION '%s' %08X/%d %04X/%04X -> " "%04X/%04X %d %c\n", session->name, ip, port, @@ -1652,9 +1662,7 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v) session->session_id, tunnel->peer_tunnel_id, session->peer_session_id, - ps->sock->sk_state, - (session == ps->sock->sk_user_data) ? - 'Y' : 'N'); + state, user_data_ok); seq_printf(m, " %d/%d/%c/%c/%s %08x %u\n", session->mtu, session->mru, session->recv_seq ? 'R' : '-', @@ -1671,8 +1679,12 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v) atomic_long_read(&session->stats.rx_bytes), atomic_long_read(&session->stats.rx_errors)); - if (po) + if (sk) { + struct pppox_sock *po = pppox_sk(sk); + seq_printf(m, " interface %s\n", ppp_dev_name(&po->chan)); + sock_put(sk); + } } static int pppol2tp_seq_show(struct seq_file *m, void *v) @@ -1697,8 +1709,6 @@ static int pppol2tp_seq_show(struct seq_file *m, void *v) pppol2tp_seq_tunnel_show(m, pd->tunnel); } else { pppol2tp_seq_session_show(m, pd->session); - if (pd->session->deref) - pd->session->deref(pd->session); l2tp_session_dec_refcount(pd->session); } diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c index e15314e3b464..db6e0afe3a20 100644 --- a/net/lapb/lapb_iface.c +++ b/net/lapb/lapb_iface.c @@ -127,8 +127,8 @@ static struct lapb_cb *lapb_create_cb(void) skb_queue_head_init(&lapb->write_queue); skb_queue_head_init(&lapb->ack_queue); - init_timer(&lapb->t1timer); - init_timer(&lapb->t2timer); + timer_setup(&lapb->t1timer, NULL, 0); + timer_setup(&lapb->t2timer, NULL, 0); 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 1a5535bc3b8d..8bb469cb3abe 100644 --- a/net/lapb/lapb_timer.c +++ b/net/lapb/lapb_timer.c @@ -35,15 +35,14 @@ #include <linux/interrupt.h> #include <net/lapb.h> -static void lapb_t1timer_expiry(unsigned long); -static void lapb_t2timer_expiry(unsigned long); +static void lapb_t1timer_expiry(struct timer_list *); +static void lapb_t2timer_expiry(struct timer_list *); void lapb_start_t1timer(struct lapb_cb *lapb) { del_timer(&lapb->t1timer); - lapb->t1timer.data = (unsigned long)lapb; - lapb->t1timer.function = &lapb_t1timer_expiry; + lapb->t1timer.function = (TIMER_FUNC_TYPE)lapb_t1timer_expiry; lapb->t1timer.expires = jiffies + lapb->t1; add_timer(&lapb->t1timer); @@ -53,8 +52,7 @@ void lapb_start_t2timer(struct lapb_cb *lapb) { del_timer(&lapb->t2timer); - lapb->t2timer.data = (unsigned long)lapb; - lapb->t2timer.function = &lapb_t2timer_expiry; + lapb->t2timer.function = (TIMER_FUNC_TYPE)lapb_t2timer_expiry; lapb->t2timer.expires = jiffies + lapb->t2; add_timer(&lapb->t2timer); @@ -75,9 +73,9 @@ int lapb_t1timer_running(struct lapb_cb *lapb) return timer_pending(&lapb->t1timer); } -static void lapb_t2timer_expiry(unsigned long param) +static void lapb_t2timer_expiry(struct timer_list *t) { - struct lapb_cb *lapb = (struct lapb_cb *)param; + struct lapb_cb *lapb = from_timer(lapb, t, t2timer); if (lapb->condition & LAPB_ACK_PENDING_CONDITION) { lapb->condition &= ~LAPB_ACK_PENDING_CONDITION; @@ -85,9 +83,9 @@ static void lapb_t2timer_expiry(unsigned long param) } } -static void lapb_t1timer_expiry(unsigned long param) +static void lapb_t1timer_expiry(struct timer_list *t) { - struct lapb_cb *lapb = (struct lapb_cb *)param; + struct lapb_cb *lapb = from_timer(lapb, t, t1timer); switch (lapb->state) { diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c index ea225bd2672c..f59648018060 100644 --- a/net/llc/llc_c_ac.c +++ b/net/llc/llc_c_ac.c @@ -1318,9 +1318,8 @@ static int llc_conn_ac_inc_vs_by_1(struct sock *sk, struct sk_buff *skb) return 0; } -static void llc_conn_tmr_common_cb(unsigned long timeout_data, u8 type) +static void llc_conn_tmr_common_cb(struct sock *sk, u8 type) { - struct sock *sk = (struct sock *)timeout_data; struct sk_buff *skb = alloc_skb(0, GFP_ATOMIC); bh_lock_sock(sk); @@ -1334,24 +1333,32 @@ static void llc_conn_tmr_common_cb(unsigned long timeout_data, u8 type) bh_unlock_sock(sk); } -void llc_conn_pf_cycle_tmr_cb(unsigned long timeout_data) +void llc_conn_pf_cycle_tmr_cb(struct timer_list *t) { - llc_conn_tmr_common_cb(timeout_data, LLC_CONN_EV_TYPE_P_TMR); + struct llc_sock *llc = from_timer(llc, t, pf_cycle_timer.timer); + + llc_conn_tmr_common_cb(&llc->sk, LLC_CONN_EV_TYPE_P_TMR); } -void llc_conn_busy_tmr_cb(unsigned long timeout_data) +void llc_conn_busy_tmr_cb(struct timer_list *t) { - llc_conn_tmr_common_cb(timeout_data, LLC_CONN_EV_TYPE_BUSY_TMR); + struct llc_sock *llc = from_timer(llc, t, busy_state_timer.timer); + + llc_conn_tmr_common_cb(&llc->sk, LLC_CONN_EV_TYPE_BUSY_TMR); } -void llc_conn_ack_tmr_cb(unsigned long timeout_data) +void llc_conn_ack_tmr_cb(struct timer_list *t) { - llc_conn_tmr_common_cb(timeout_data, LLC_CONN_EV_TYPE_ACK_TMR); + struct llc_sock *llc = from_timer(llc, t, ack_timer.timer); + + llc_conn_tmr_common_cb(&llc->sk, LLC_CONN_EV_TYPE_ACK_TMR); } -void llc_conn_rej_tmr_cb(unsigned long timeout_data) +void llc_conn_rej_tmr_cb(struct timer_list *t) { - llc_conn_tmr_common_cb(timeout_data, LLC_CONN_EV_TYPE_REJ_TMR); + struct llc_sock *llc = from_timer(llc, t, rej_sent_timer.timer); + + llc_conn_tmr_common_cb(&llc->sk, LLC_CONN_EV_TYPE_REJ_TMR); } int llc_conn_ac_rst_vs(struct sock *sk, struct sk_buff *skb) diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 5e91b47f0d2a..9177dbb16dce 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -902,20 +902,16 @@ static void llc_sk_init(struct sock *sk) llc->inc_cntr = llc->dec_cntr = 2; llc->dec_step = llc->connect_step = 1; - setup_timer(&llc->ack_timer.timer, llc_conn_ack_tmr_cb, - (unsigned long)sk); + timer_setup(&llc->ack_timer.timer, llc_conn_ack_tmr_cb, 0); llc->ack_timer.expire = sysctl_llc2_ack_timeout; - setup_timer(&llc->pf_cycle_timer.timer, llc_conn_pf_cycle_tmr_cb, - (unsigned long)sk); + timer_setup(&llc->pf_cycle_timer.timer, llc_conn_pf_cycle_tmr_cb, 0); llc->pf_cycle_timer.expire = sysctl_llc2_p_timeout; - setup_timer(&llc->rej_sent_timer.timer, llc_conn_rej_tmr_cb, - (unsigned long)sk); + timer_setup(&llc->rej_sent_timer.timer, llc_conn_rej_tmr_cb, 0); llc->rej_sent_timer.expire = sysctl_llc2_rej_timeout; - setup_timer(&llc->busy_state_timer.timer, llc_conn_busy_tmr_cb, - (unsigned long)sk); + timer_setup(&llc->busy_state_timer.timer, llc_conn_busy_tmr_cb, 0); llc->busy_state_timer.expire = sysctl_llc2_busy_timeout; llc->n2 = 2; /* max retransmit */ diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c index dd3e83328ad5..82cb93f66b9b 100644 --- a/net/llc/llc_input.c +++ b/net/llc/llc_input.c @@ -193,7 +193,7 @@ int llc_rcv(struct sk_buff *skb, struct net_device *dev, */ rcv = rcu_dereference(sap->rcv_func); dest = llc_pdu_type(skb); - sap_handler = dest ? ACCESS_ONCE(llc_type_handlers[dest - 1]) : NULL; + sap_handler = dest ? READ_ONCE(llc_type_handlers[dest - 1]) : NULL; if (unlikely(!sap_handler)) { if (rcv) rcv(skb, dev, pt, orig_dev); @@ -214,7 +214,7 @@ drop: kfree_skb(skb); goto out; handle_station: - sta_handler = ACCESS_ONCE(llc_station_handler); + sta_handler = READ_ONCE(llc_station_handler); if (!sta_handler) goto drop; sta_handler(skb); diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile index 80bfe29099f6..e3589ade62e0 100644 --- a/net/mac80211/Makefile +++ b/net/mac80211/Makefile @@ -7,6 +7,7 @@ mac80211-y := \ driver-ops.o \ sta_info.o \ wep.o \ + aead_api.o \ wpa.o \ scan.o offchannel.o \ ht.o agg-tx.o agg-rx.o \ @@ -16,8 +17,6 @@ mac80211-y := \ rate.o \ michael.o \ tkip.o \ - aes_ccm.o \ - aes_gcm.o \ aes_cmac.o \ aes_gmac.o \ fils_aead.o \ diff --git a/net/mac80211/aes_ccm.c b/net/mac80211/aead_api.c index a4e0d59a40dd..160f9df30402 100644 --- a/net/mac80211/aes_ccm.c +++ b/net/mac80211/aead_api.c @@ -1,6 +1,7 @@ /* * Copyright 2003-2004, Instant802 Networks, Inc. * Copyright 2005-2006, Devicescape Software, Inc. + * Copyright 2014-2015, Qualcomm Atheros, Inc. * * Rewrite: Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org> * @@ -12,30 +13,29 @@ #include <linux/kernel.h> #include <linux/types.h> #include <linux/err.h> +#include <linux/scatterlist.h> #include <crypto/aead.h> -#include <net/mac80211.h> -#include "key.h" -#include "aes_ccm.h" +#include "aead_api.h" -int ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic, - size_t mic_len) +int aead_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, size_t aad_len, + u8 *data, size_t data_len, u8 *mic) { + size_t mic_len = crypto_aead_authsize(tfm); struct scatterlist sg[3]; struct aead_request *aead_req; int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm); u8 *__aad; - aead_req = kzalloc(reqsize + CCM_AAD_LEN, GFP_ATOMIC); + aead_req = kzalloc(reqsize + aad_len, GFP_ATOMIC); if (!aead_req) return -ENOMEM; __aad = (u8 *)aead_req + reqsize; - memcpy(__aad, aad, CCM_AAD_LEN); + memcpy(__aad, aad, aad_len); sg_init_table(sg, 3); - sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad)); + sg_set_buf(&sg[0], __aad, aad_len); sg_set_buf(&sg[1], data, data_len); sg_set_buf(&sg[2], mic, mic_len); @@ -49,10 +49,10 @@ int ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, return 0; } -int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic, - size_t mic_len) +int aead_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, size_t aad_len, + u8 *data, size_t data_len, u8 *mic) { + size_t mic_len = crypto_aead_authsize(tfm); struct scatterlist sg[3]; struct aead_request *aead_req; int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm); @@ -62,15 +62,15 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, if (data_len == 0) return -EINVAL; - aead_req = kzalloc(reqsize + CCM_AAD_LEN, GFP_ATOMIC); + aead_req = kzalloc(reqsize + aad_len, GFP_ATOMIC); if (!aead_req) return -ENOMEM; __aad = (u8 *)aead_req + reqsize; - memcpy(__aad, aad, CCM_AAD_LEN); + memcpy(__aad, aad, aad_len); sg_init_table(sg, 3); - sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad)); + sg_set_buf(&sg[0], __aad, aad_len); sg_set_buf(&sg[1], data, data_len); sg_set_buf(&sg[2], mic, mic_len); @@ -84,14 +84,14 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, return err; } -struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[], - size_t key_len, - size_t mic_len) +struct crypto_aead * +aead_key_setup_encrypt(const char *alg, const u8 key[], + size_t key_len, size_t mic_len) { struct crypto_aead *tfm; int err; - tfm = crypto_alloc_aead("ccm(aes)", 0, CRYPTO_ALG_ASYNC); + tfm = crypto_alloc_aead(alg, 0, CRYPTO_ALG_ASYNC); if (IS_ERR(tfm)) return tfm; @@ -109,7 +109,7 @@ free_aead: return ERR_PTR(err); } -void ieee80211_aes_key_free(struct crypto_aead *tfm) +void aead_key_free(struct crypto_aead *tfm) { crypto_free_aead(tfm); } diff --git a/net/mac80211/aead_api.h b/net/mac80211/aead_api.h new file mode 100644 index 000000000000..5e39ea843bbf --- /dev/null +++ b/net/mac80211/aead_api.h @@ -0,0 +1,27 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _AEAD_API_H +#define _AEAD_API_H + +#include <crypto/aead.h> +#include <linux/crypto.h> + +struct crypto_aead * +aead_key_setup_encrypt(const char *alg, const u8 key[], + size_t key_len, size_t mic_len); + +int aead_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, + size_t aad_len, u8 *data, + size_t data_len, u8 *mic); + +int aead_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, + size_t aad_len, u8 *data, + size_t data_len, u8 *mic); + +void aead_key_free(struct crypto_aead *tfm); + +#endif /* _AEAD_API_H */ diff --git a/net/mac80211/aes_ccm.h b/net/mac80211/aes_ccm.h index fcd3254c5cf0..e9b7ca0bde5b 100644 --- a/net/mac80211/aes_ccm.h +++ b/net/mac80211/aes_ccm.h @@ -10,19 +10,39 @@ #ifndef AES_CCM_H #define AES_CCM_H -#include <linux/crypto.h> +#include "aead_api.h" #define CCM_AAD_LEN 32 -struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[], - size_t key_len, - size_t mic_len); -int ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic, - size_t mic_len); -int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic, - size_t mic_len); -void ieee80211_aes_key_free(struct crypto_aead *tfm); +static inline struct crypto_aead * +ieee80211_aes_key_setup_encrypt(const u8 key[], size_t key_len, size_t mic_len) +{ + return aead_key_setup_encrypt("ccm(aes)", key, key_len, mic_len); +} + +static inline int +ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, + u8 *b_0, u8 *aad, u8 *data, + size_t data_len, u8 *mic) +{ + return aead_encrypt(tfm, b_0, aad + 2, + be16_to_cpup((__be16 *)aad), + data, data_len, mic); +} + +static inline int +ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, + u8 *b_0, u8 *aad, u8 *data, + size_t data_len, u8 *mic) +{ + return aead_decrypt(tfm, b_0, aad + 2, + be16_to_cpup((__be16 *)aad), + data, data_len, mic); +} + +static inline void ieee80211_aes_key_free(struct crypto_aead *tfm) +{ + return aead_key_free(tfm); +} #endif /* AES_CCM_H */ diff --git a/net/mac80211/aes_gcm.c b/net/mac80211/aes_gcm.c deleted file mode 100644 index 8a4397cc1b08..000000000000 --- a/net/mac80211/aes_gcm.c +++ /dev/null @@ -1,109 +0,0 @@ -/* - * Copyright 2014-2015, Qualcomm Atheros, Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/err.h> -#include <crypto/aead.h> - -#include <net/mac80211.h> -#include "key.h" -#include "aes_gcm.h" - -int ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic) -{ - struct scatterlist sg[3]; - struct aead_request *aead_req; - int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm); - u8 *__aad; - - aead_req = kzalloc(reqsize + GCM_AAD_LEN, GFP_ATOMIC); - if (!aead_req) - return -ENOMEM; - - __aad = (u8 *)aead_req + reqsize; - memcpy(__aad, aad, GCM_AAD_LEN); - - sg_init_table(sg, 3); - sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad)); - sg_set_buf(&sg[1], data, data_len); - sg_set_buf(&sg[2], mic, IEEE80211_GCMP_MIC_LEN); - - aead_request_set_tfm(aead_req, tfm); - aead_request_set_crypt(aead_req, sg, sg, data_len, j_0); - aead_request_set_ad(aead_req, sg[0].length); - - crypto_aead_encrypt(aead_req); - kzfree(aead_req); - return 0; -} - -int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic) -{ - struct scatterlist sg[3]; - struct aead_request *aead_req; - int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm); - u8 *__aad; - int err; - - if (data_len == 0) - return -EINVAL; - - aead_req = kzalloc(reqsize + GCM_AAD_LEN, GFP_ATOMIC); - if (!aead_req) - return -ENOMEM; - - __aad = (u8 *)aead_req + reqsize; - memcpy(__aad, aad, GCM_AAD_LEN); - - sg_init_table(sg, 3); - sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad)); - sg_set_buf(&sg[1], data, data_len); - sg_set_buf(&sg[2], mic, IEEE80211_GCMP_MIC_LEN); - - aead_request_set_tfm(aead_req, tfm); - aead_request_set_crypt(aead_req, sg, sg, - data_len + IEEE80211_GCMP_MIC_LEN, j_0); - aead_request_set_ad(aead_req, sg[0].length); - - err = crypto_aead_decrypt(aead_req); - kzfree(aead_req); - - return err; -} - -struct crypto_aead *ieee80211_aes_gcm_key_setup_encrypt(const u8 key[], - size_t key_len) -{ - struct crypto_aead *tfm; - int err; - - tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(tfm)) - return tfm; - - err = crypto_aead_setkey(tfm, key, key_len); - if (err) - goto free_aead; - err = crypto_aead_setauthsize(tfm, IEEE80211_GCMP_MIC_LEN); - if (err) - goto free_aead; - - return tfm; - -free_aead: - crypto_free_aead(tfm); - return ERR_PTR(err); -} - -void ieee80211_aes_gcm_key_free(struct crypto_aead *tfm) -{ - crypto_free_aead(tfm); -} diff --git a/net/mac80211/aes_gcm.h b/net/mac80211/aes_gcm.h index 55aed5352494..d2b096033009 100644 --- a/net/mac80211/aes_gcm.h +++ b/net/mac80211/aes_gcm.h @@ -9,16 +9,38 @@ #ifndef AES_GCM_H #define AES_GCM_H -#include <linux/crypto.h> +#include "aead_api.h" #define GCM_AAD_LEN 32 -int ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic); -int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic); -struct crypto_aead *ieee80211_aes_gcm_key_setup_encrypt(const u8 key[], - size_t key_len); -void ieee80211_aes_gcm_key_free(struct crypto_aead *tfm); +static inline int ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, + u8 *j_0, u8 *aad, u8 *data, + size_t data_len, u8 *mic) +{ + return aead_encrypt(tfm, j_0, aad + 2, + be16_to_cpup((__be16 *)aad), + data, data_len, mic); +} + +static inline int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, + u8 *j_0, u8 *aad, u8 *data, + size_t data_len, u8 *mic) +{ + return aead_decrypt(tfm, j_0, aad + 2, + be16_to_cpup((__be16 *)aad), + data, data_len, mic); +} + +static inline struct crypto_aead * +ieee80211_aes_gcm_key_setup_encrypt(const u8 key[], size_t key_len) +{ + return aead_key_setup_encrypt("gcm(aes)", key, + key_len, IEEE80211_GCMP_MIC_LEN); +} + +static inline void ieee80211_aes_gcm_key_free(struct crypto_aead *tfm) +{ + return aead_key_free(tfm); +} #endif /* AES_GCM_H */ diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 2849a1fc41c5..88cc1ae935ea 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -459,7 +459,7 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, } void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif, - const u8 *addr, unsigned int bit) + const u8 *addr, unsigned int tid) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; @@ -470,7 +470,7 @@ void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif, if (!sta) goto unlock; - set_bit(bit, sta->ampdu_mlme.tid_rx_manage_offl); + set_bit(tid, sta->ampdu_mlme.tid_rx_manage_offl); ieee80211_queue_work(&local->hw, &sta->ampdu_mlme.work); unlock: rcu_read_unlock(); diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index d6d0b4201e40..41f5e48f8021 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -290,13 +290,15 @@ void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta, { int i; + mutex_lock(&sta->ampdu_mlme.mtx); for (i = 0; i < IEEE80211_NUM_TIDS; i++) { - __ieee80211_stop_tx_ba_session(sta, i, reason); - __ieee80211_stop_rx_ba_session(sta, i, WLAN_BACK_RECIPIENT, - WLAN_REASON_QSTA_LEAVE_QBSS, - reason != AGG_STOP_DESTROY_STA && - reason != AGG_STOP_PEER_REQUEST); + ___ieee80211_stop_tx_ba_session(sta, i, reason); + ___ieee80211_stop_rx_ba_session(sta, i, WLAN_BACK_RECIPIENT, + WLAN_REASON_QSTA_LEAVE_QBSS, + reason != AGG_STOP_DESTROY_STA && + reason != AGG_STOP_PEER_REQUEST); } + mutex_unlock(&sta->ampdu_mlme.mtx); /* stopping might queue the work again - so cancel only afterwards */ cancel_work_sync(&sta->ampdu_mlme.work); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 9675814f64db..68f874e73561 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -2009,6 +2009,8 @@ void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata, struct txq_info *txq, int tid); void ieee80211_txq_purge(struct ieee80211_local *local, struct txq_info *txqi); +void ieee80211_txq_remove_vlan(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata); void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, u16 transaction, u16 auth_alg, u16 status, const u8 *extra, size_t extra_len, const u8 *bssid, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index f75029abf728..13b16f90e1cf 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -793,9 +793,7 @@ static int ieee80211_open(struct net_device *dev) static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_down) { - struct ieee80211_sub_if_data *txq_sdata = sdata; struct ieee80211_local *local = sdata->local; - struct fq *fq = &local->fq; unsigned long flags; struct sk_buff *skb, *tmp; u32 hw_reconf_flags = 0; @@ -939,9 +937,6 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, switch (sdata->vif.type) { case NL80211_IFTYPE_AP_VLAN: - txq_sdata = container_of(sdata->bss, - struct ieee80211_sub_if_data, u.ap); - mutex_lock(&local->mtx); list_del(&sdata->u.vlan.list); mutex_unlock(&local->mtx); @@ -998,8 +993,6 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, skb_queue_purge(&sdata->skb_queue); } - sdata->bss = NULL; - spin_lock_irqsave(&local->queue_stop_reason_lock, flags); for (i = 0; i < IEEE80211_MAX_QUEUES; i++) { skb_queue_walk_safe(&local->pending[i], skb, tmp) { @@ -1012,22 +1005,10 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, } spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); - if (txq_sdata->vif.txq) { - struct txq_info *txqi = to_txq_info(txq_sdata->vif.txq); - - /* - * FIXME FIXME - * - * We really shouldn't purge the *entire* txqi since that - * contains frames for the other AP_VLANs (and possibly - * the AP itself) as well, but there's no API in FQ now - * to be able to filter. - */ + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + ieee80211_txq_remove_vlan(local, sdata); - spin_lock_bh(&fq->lock); - ieee80211_txq_purge(local, txqi); - spin_unlock_bh(&fq->lock); - } + sdata->bss = NULL; if (local->open_count == 0) ieee80211_clear_tx_pending(local); @@ -1772,7 +1753,9 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, sizeof(void *)); int txq_size = 0; - if (local->ops->wake_tx_queue) + if (local->ops->wake_tx_queue && + type != NL80211_IFTYPE_AP_VLAN && + type != NL80211_IFTYPE_MONITOR) txq_size += sizeof(struct txq_info) + local->hw.txq_data_size; diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index a550c707cd8a..7a76c4a6df30 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -675,8 +675,7 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) enum nl80211_band band; u8 *pos; struct ieee80211_sub_if_data *sdata; - int hdr_len = offsetof(struct ieee80211_mgmt, u.beacon) + - sizeof(mgmt->u.beacon); + int hdr_len = offsetofend(struct ieee80211_mgmt, u.beacon); sdata = container_of(ifmsh, struct ieee80211_sub_if_data, u.mesh); rcu_read_lock(); diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 7e5f271e3c30..465b7853edc0 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -275,6 +275,7 @@ void mesh_neighbour_update(struct ieee80211_sub_if_data *sdata, u8 *hw_addr, struct ieee802_11_elems *ie); bool mesh_peer_accepts_plinks(struct ieee802_11_elems *ie); u32 mesh_accept_plinks_update(struct ieee80211_sub_if_data *sdata); +void mesh_plink_timer(struct timer_list *t); void mesh_plink_broken(struct sta_info *sta); u32 mesh_plink_deactivate(struct sta_info *sta); u32 mesh_plink_open(struct sta_info *sta); diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index d8bbd0d2225a..146ec6c0f12f 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -111,8 +111,8 @@ static int mesh_path_sel_frame_tx(enum mpath_frame_type action, u8 flags, struct sk_buff *skb; struct ieee80211_mgmt *mgmt; u8 *pos, ie_len; - int hdr_len = offsetof(struct ieee80211_mgmt, u.action.u.mesh_action) + - sizeof(mgmt->u.action.u.mesh_action); + int hdr_len = offsetofend(struct ieee80211_mgmt, + u.action.u.mesh_action); skb = dev_alloc_skb(local->tx_headroom + hdr_len + @@ -242,8 +242,8 @@ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; struct ieee80211_mgmt *mgmt; u8 *pos, ie_len; - int hdr_len = offsetof(struct ieee80211_mgmt, u.action.u.mesh_action) + - sizeof(mgmt->u.action.u.mesh_action); + int hdr_len = offsetofend(struct ieee80211_mgmt, + u.action.u.mesh_action); if (time_before(jiffies, ifmsh->next_perr)) return -EAGAIN; diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index f69c6c38ca43..e2d00cce3c17 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -220,8 +220,7 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, bool include_plid = false; u16 peering_proto = 0; u8 *pos, ie_len = 4; - int hdr_len = offsetof(struct ieee80211_mgmt, u.action.u.self_prot) + - sizeof(mgmt->u.action.u.self_prot); + int hdr_len = offsetofend(struct ieee80211_mgmt, u.action.u.self_prot); int err = -ENOMEM; skb = dev_alloc_skb(local->tx_headroom + @@ -604,8 +603,9 @@ out: ieee80211_mbss_info_change_notify(sdata, changed); } -static void mesh_plink_timer(unsigned long data) +void mesh_plink_timer(struct timer_list *t) { + struct mesh_sta *mesh = from_timer(mesh, t, plink_timer); struct sta_info *sta; u16 reason = 0; struct ieee80211_sub_if_data *sdata; @@ -617,7 +617,7 @@ static void mesh_plink_timer(unsigned long data) * del_timer_sync() this timer after having made sure * it cannot be readded (by deleting the plink.) */ - sta = (struct sta_info *) data; + sta = mesh->plink_sta; if (sta->sdata->local->quiescing) return; @@ -697,11 +697,8 @@ static void mesh_plink_timer(unsigned long data) static inline void mesh_plink_timer_set(struct sta_info *sta, u32 timeout) { - sta->mesh->plink_timer.expires = jiffies + msecs_to_jiffies(timeout); - sta->mesh->plink_timer.data = (unsigned long) sta; - sta->mesh->plink_timer.function = mesh_plink_timer; sta->mesh->plink_timeout = timeout; - add_timer(&sta->mesh->plink_timer); + mod_timer(&sta->mesh->plink_timer, jiffies + msecs_to_jiffies(timeout)); } static bool llid_in_use(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 3b8e2709d8de..e4ededa1909d 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -145,7 +145,6 @@ static u32 ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband, struct ieee80211_channel *channel, - const struct ieee80211_ht_cap *ht_cap, const struct ieee80211_ht_operation *ht_oper, const struct ieee80211_vht_operation *vht_oper, struct cfg80211_chan_def *chandef, bool tracking) @@ -163,20 +162,13 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, chandef->center_freq1 = channel->center_freq; chandef->center_freq2 = 0; - if (!ht_cap || !ht_oper || !sta_ht_cap.ht_supported) { + if (!ht_oper || !sta_ht_cap.ht_supported) { ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT; goto out; } chandef->width = NL80211_CHAN_WIDTH_20; - if (!(ht_cap->cap_info & - cpu_to_le16(IEEE80211_HT_CAP_SUP_WIDTH_20_40))) { - ret = IEEE80211_STA_DISABLE_40MHZ; - vht_chandef = *chandef; - goto out; - } - ht_cfreq = ieee80211_channel_to_frequency(ht_oper->primary_chan, channel->band); /* check that channel matches the right operating channel */ @@ -344,7 +336,7 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, /* calculate new channel (type) based on HT/VHT operation IEs */ flags = ieee80211_determine_chantype(sdata, sband, chan, - ht_cap, ht_oper, vht_oper, + ht_oper, vht_oper, &chandef, true); /* @@ -780,11 +772,12 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) WLAN_EID_SUPPORTED_REGULATORY_CLASSES, WLAN_EID_HT_CAPABILITY, WLAN_EID_BSS_COEX_2040, + /* luckily this is almost always there */ WLAN_EID_EXT_CAPABILITY, WLAN_EID_QOS_TRAFFIC_CAPA, WLAN_EID_TIM_BCAST_REQ, WLAN_EID_INTERWORKING, - /* 60GHz doesn't happen right now */ + /* 60 GHz (Multi-band, DMG, MMS) can't happen */ WLAN_EID_VHT_CAPABILITY, WLAN_EID_OPMODE_NOTIF, }; @@ -811,22 +804,16 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) /* if present, add any custom IEs that go before VHT */ if (assoc_data->ie_len) { static const u8 before_vht[] = { - WLAN_EID_SSID, - WLAN_EID_SUPP_RATES, - WLAN_EID_EXT_SUPP_RATES, - WLAN_EID_PWR_CAPABILITY, - WLAN_EID_SUPPORTED_CHANNELS, - WLAN_EID_RSN, - WLAN_EID_QOS_CAPA, - WLAN_EID_RRM_ENABLED_CAPABILITIES, - WLAN_EID_MOBILITY_DOMAIN, - WLAN_EID_SUPPORTED_REGULATORY_CLASSES, - WLAN_EID_HT_CAPABILITY, + /* + * no need to list the ones split off before HT + * or generated here + */ WLAN_EID_BSS_COEX_2040, WLAN_EID_EXT_CAPABILITY, WLAN_EID_QOS_TRAFFIC_CAPA, WLAN_EID_TIM_BCAST_REQ, WLAN_EID_INTERWORKING, + /* 60 GHz (Multi-band, DMG, MMS) can't happen */ }; /* RIC already taken above, so no need to handle here anymore */ @@ -4317,7 +4304,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, ifmgd->flags |= ieee80211_determine_chantype(sdata, sband, cbss->channel, - ht_cap, ht_oper, vht_oper, + ht_oper, vht_oper, &chandef, false); sdata->needed_rx_chains = min(ieee80211_ht_vht_rx_chains(sdata, cbss), diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 47d2ed570470..ef2becaade50 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -7,7 +7,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2013-2015 Intel Mobile Communications GmbH - * Copyright 2016 Intel Deutschland GmbH + * Copyright 2016-2017 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -183,6 +183,20 @@ ieee80211_bss_info_update(struct ieee80211_local *local, return bss; } +static bool ieee80211_scan_accept_presp(struct ieee80211_sub_if_data *sdata, + u32 scan_flags, const u8 *da) +{ + if (!sdata) + return false; + /* accept broadcast for OCE */ + if (scan_flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP && + is_broadcast_ether_addr(da)) + return true; + if (scan_flags & NL80211_SCAN_FLAG_RANDOM_ADDR) + return true; + return ether_addr_equal(da, sdata->vif.addr); +} + void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) { struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb); @@ -208,19 +222,24 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) if (ieee80211_is_probe_resp(mgmt->frame_control)) { struct cfg80211_scan_request *scan_req; struct cfg80211_sched_scan_request *sched_scan_req; + u32 scan_req_flags = 0, sched_scan_req_flags = 0; scan_req = rcu_dereference(local->scan_req); sched_scan_req = rcu_dereference(local->sched_scan_req); - /* ignore ProbeResp to foreign address unless scanning - * with randomised address + if (scan_req) + scan_req_flags = scan_req->flags; + + if (sched_scan_req) + sched_scan_req_flags = sched_scan_req->flags; + + /* ignore ProbeResp to foreign address or non-bcast (OCE) + * unless scanning with randomised address */ - if (!(sdata1 && - (ether_addr_equal(mgmt->da, sdata1->vif.addr) || - scan_req->flags & NL80211_SCAN_FLAG_RANDOM_ADDR)) && - !(sdata2 && - (ether_addr_equal(mgmt->da, sdata2->vif.addr) || - sched_scan_req->flags & NL80211_SCAN_FLAG_RANDOM_ADDR))) + if (!ieee80211_scan_accept_presp(sdata1, scan_req_flags, + mgmt->da) && + !ieee80211_scan_accept_presp(sdata2, sched_scan_req_flags, + mgmt->da)) return; elements = mgmt->u.probe_resp.variable; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 69615016d5bf..a3060e55122c 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -329,10 +329,12 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, sta->mesh = kzalloc(sizeof(*sta->mesh), gfp); if (!sta->mesh) goto free; + sta->mesh->plink_sta = sta; spin_lock_init(&sta->mesh->plink_lock); if (ieee80211_vif_is_mesh(&sdata->vif) && !sdata->u.mesh.user_mpm) - init_timer(&sta->mesh->plink_timer); + timer_setup(&sta->mesh->plink_timer, mesh_plink_timer, + 0); sta->mesh->nonpeer_pm = NL80211_MESH_POWER_ACTIVE; } #endif @@ -515,6 +517,31 @@ static int sta_info_insert_drv_state(struct ieee80211_local *local, return err; } +static void +ieee80211_recalc_p2p_go_ps_allowed(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + bool allow_p2p_go_ps = sdata->vif.p2p; + struct sta_info *sta; + + rcu_read_lock(); + list_for_each_entry_rcu(sta, &local->sta_list, list) { + if (sdata != sta->sdata || + !test_sta_flag(sta, WLAN_STA_ASSOC)) + continue; + if (!sta->sta.support_p2p_ps) { + allow_p2p_go_ps = false; + break; + } + } + rcu_read_unlock(); + + if (allow_p2p_go_ps != sdata->vif.bss_conf.allow_p2p_go_ps) { + sdata->vif.bss_conf.allow_p2p_go_ps = allow_p2p_go_ps; + ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_P2P_PS); + } +} + /* * should be called with sta_mtx locked * this function replaces the mutex lock @@ -561,6 +588,13 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) goto out_remove; set_sta_flag(sta, WLAN_STA_INSERTED); + + if (sta->sta_state >= IEEE80211_STA_ASSOC) { + ieee80211_recalc_min_chandef(sta->sdata); + if (!sta->sta.support_p2p_ps) + ieee80211_recalc_p2p_go_ps_allowed(sta->sdata); + } + /* accept BA sessions now */ clear_sta_flag(sta, WLAN_STA_BLOCK_BA); @@ -1788,31 +1822,6 @@ void ieee80211_sta_set_buffered(struct ieee80211_sta *pubsta, } EXPORT_SYMBOL(ieee80211_sta_set_buffered); -static void -ieee80211_recalc_p2p_go_ps_allowed(struct ieee80211_sub_if_data *sdata) -{ - struct ieee80211_local *local = sdata->local; - bool allow_p2p_go_ps = sdata->vif.p2p; - struct sta_info *sta; - - rcu_read_lock(); - list_for_each_entry_rcu(sta, &local->sta_list, list) { - if (sdata != sta->sdata || - !test_sta_flag(sta, WLAN_STA_ASSOC)) - continue; - if (!sta->sta.support_p2p_ps) { - allow_p2p_go_ps = false; - break; - } - } - rcu_read_unlock(); - - if (allow_p2p_go_ps != sdata->vif.bss_conf.allow_p2p_go_ps) { - sdata->vif.bss_conf.allow_p2p_go_ps = allow_p2p_go_ps; - ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_P2P_PS); - } -} - int sta_info_move_state(struct sta_info *sta, enum ieee80211_sta_state new_state) { @@ -2008,7 +2017,7 @@ static void sta_stats_decode_rate(struct ieee80211_local *local, u16 rate, static int sta_set_rate_info_rx(struct sta_info *sta, struct rate_info *rinfo) { - u16 rate = ACCESS_ONCE(sta_get_last_rx_stats(sta)->last_rate); + u16 rate = READ_ONCE(sta_get_last_rx_stats(sta)->last_rate); if (rate == STA_STATS_RATE_INVALID) return -EINVAL; diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 3acbdfa9f649..5c54acd10562 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -344,6 +344,7 @@ DECLARE_EWMA(mesh_fail_avg, 20, 8) * @plink_state: peer link state * @plink_timeout: timeout of peer link * @plink_timer: peer link watch timer + * @plink_sta: peer link watch timer's sta_info * @t_offset: timing offset relative to this host * @t_offset_setpoint: reference timing offset of this sta to be used when * calculating clockdrift @@ -356,6 +357,7 @@ DECLARE_EWMA(mesh_fail_avg, 20, 8) */ struct mesh_sta { struct timer_list plink_timer; + struct sta_info *plink_sta; s64 t_offset; s64 t_offset_setpoint; @@ -398,7 +400,7 @@ struct ieee80211_sta_rx_stats { u64 msdu[IEEE80211_NUM_TIDS + 1]; }; -/** +/* * The bandwidth threshold below which the per-station CoDel parameters will be * scaled to be more lenient (to prevent starvation of slow stations). This * value will be scaled by the number of active stations when it is being diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 94826680cf2b..7b8154474b9e 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1396,6 +1396,40 @@ static void ieee80211_txq_enqueue(struct ieee80211_local *local, fq_flow_get_default_func); } +static bool fq_vlan_filter_func(struct fq *fq, struct fq_tin *tin, + struct fq_flow *flow, struct sk_buff *skb, + void *data) +{ + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + + return info->control.vif == data; +} + +void ieee80211_txq_remove_vlan(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) +{ + struct fq *fq = &local->fq; + struct txq_info *txqi; + struct fq_tin *tin; + struct ieee80211_sub_if_data *ap; + + if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_AP_VLAN)) + return; + + ap = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap); + + if (!ap->vif.txq) + return; + + txqi = to_txq_info(ap->vif.txq); + tin = &txqi->tin; + + spin_lock_bh(&fq->lock); + fq_tin_filter(fq, tin, fq_vlan_filter_func, &sdata->vif, + fq_skb_free_func); + spin_unlock_bh(&fq->lock); +} + void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, struct txq_info *txqi, int tid) diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 6aef6793d052..d57e5f6bd8b6 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1392,10 +1392,10 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local, /* insert custom IEs that go before HT */ if (ie && ie_len) { static const u8 before_ht[] = { - WLAN_EID_SSID, - WLAN_EID_SUPP_RATES, - WLAN_EID_REQUEST, - WLAN_EID_EXT_SUPP_RATES, + /* + * no need to list the ones split off already + * (or generated here) + */ WLAN_EID_DS_PARAMS, WLAN_EID_SUPPORTED_REGULATORY_CLASSES, }; @@ -1424,20 +1424,17 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local, /* insert custom IEs that go before VHT */ if (ie && ie_len) { static const u8 before_vht[] = { - WLAN_EID_SSID, - WLAN_EID_SUPP_RATES, - WLAN_EID_REQUEST, - WLAN_EID_EXT_SUPP_RATES, - WLAN_EID_DS_PARAMS, - WLAN_EID_SUPPORTED_REGULATORY_CLASSES, - WLAN_EID_HT_CAPABILITY, + /* + * no need to list the ones split off already + * (or generated here) + */ WLAN_EID_BSS_COEX_2040, WLAN_EID_EXT_CAPABILITY, WLAN_EID_SSID_LIST, WLAN_EID_CHANNEL_USAGE, WLAN_EID_INTERWORKING, WLAN_EID_MESH_ID, - /* 60 GHz can't happen here right now */ + /* 60 GHz (Multi-band, DMG, MMS) can't happen */ }; noffset = ieee80211_ie_split(ie, ie_len, before_vht, ARRAY_SIZE(before_vht), @@ -2980,8 +2977,8 @@ int ieee80211_send_action_csa(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt; struct ieee80211_local *local = sdata->local; int freq; - int hdr_len = offsetof(struct ieee80211_mgmt, u.action.u.chan_switch) + - sizeof(mgmt->u.action.u.chan_switch); + int hdr_len = offsetofend(struct ieee80211_mgmt, + u.action.u.chan_switch); u8 *pos; if (sdata->vif.type != NL80211_IFTYPE_ADHOC && diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index 19ec2189d3ac..b9276ac849fa 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -386,6 +386,16 @@ enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta) bw = ieee80211_sta_cap_rx_bw(sta); bw = min(bw, sta->cur_max_bandwidth); + + /* Don't consider AP's bandwidth for TDLS peers, section 11.23.1 of + * IEEE80211-2016 specification makes higher bandwidth operation + * possible on the TDLS link if the peers have wider bandwidth + * capability. + */ + if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) && + test_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW)) + return bw; + bw = min(bw, ieee80211_chan_width_to_rx_bw(bss_width)); return bw; diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 0d722ea98a1b..b58722d9de37 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -464,7 +464,7 @@ static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb, pos += IEEE80211_CCMP_HDR_LEN; ccmp_special_blocks(skb, pn, b_0, aad); return ieee80211_aes_ccm_encrypt(key->u.ccmp.tfm, b_0, aad, pos, len, - skb_put(skb, mic_len), mic_len); + skb_put(skb, mic_len)); } @@ -543,7 +543,7 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx, key->u.ccmp.tfm, b_0, aad, skb->data + hdrlen + IEEE80211_CCMP_HDR_LEN, data_len, - skb->data + skb->len - mic_len, mic_len)) + skb->data + skb->len - mic_len)) return RX_DROP_UNUSABLE; } diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c index 1e1c9b20bab7..2fb703d70803 100644 --- a/net/mac802154/llsec.c +++ b/net/mac802154/llsec.c @@ -623,13 +623,18 @@ llsec_do_encrypt_unauth(struct sk_buff *skb, const struct mac802154_llsec *sec, u8 iv[16]; struct scatterlist src; SKCIPHER_REQUEST_ON_STACK(req, key->tfm0); - int err; + int err, datalen; + unsigned char *data; llsec_geniv(iv, sec->params.hwaddr, &hdr->sec); - sg_init_one(&src, skb->data, skb->len); + /* Compute data payload offset and data length */ + data = skb_mac_header(skb) + skb->mac_len; + datalen = skb_tail_pointer(skb) - data; + sg_init_one(&src, data, datalen); + skcipher_request_set_tfm(req, key->tfm0); skcipher_request_set_callback(req, 0, NULL, NULL); - skcipher_request_set_crypt(req, &src, &src, skb->len, iv); + skcipher_request_set_crypt(req, &src, &src, datalen, iv); err = crypto_skcipher_encrypt(req); skcipher_request_zero(req); return err; @@ -713,7 +718,8 @@ int mac802154_llsec_encrypt(struct mac802154_llsec *sec, struct sk_buff *skb) if (hlen < 0 || hdr.fc.type != IEEE802154_FC_TYPE_DATA) return -EINVAL; - if (!hdr.fc.security_enabled || hdr.sec.level == 0) { + if (!hdr.fc.security_enabled || + (hdr.sec.level == IEEE802154_SCF_SECLEVEL_NONE)) { skb_push(skb, hlen); return 0; } diff --git a/net/mpls/Kconfig b/net/mpls/Kconfig index 5c467ef97311..801ea9098387 100644 --- a/net/mpls/Kconfig +++ b/net/mpls/Kconfig @@ -24,6 +24,7 @@ config NET_MPLS_GSO config MPLS_ROUTING tristate "MPLS: routing support" + depends on NET_IP_TUNNEL || NET_IP_TUNNEL=n ---help--- Add support for forwarding of mpls packets. diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index c5b9ce41d66f..8ca9915befc8 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -16,6 +16,7 @@ #include <net/arp.h> #include <net/ip_fib.h> #include <net/netevent.h> +#include <net/ip_tunnels.h> #include <net/netns/generic.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> @@ -39,6 +40,36 @@ static int one = 1; static int label_limit = (1 << 20) - 1; static int ttl_max = 255; +#if IS_ENABLED(CONFIG_NET_IP_TUNNEL) +static size_t ipgre_mpls_encap_hlen(struct ip_tunnel_encap *e) +{ + return sizeof(struct mpls_shim_hdr); +} + +static const struct ip_tunnel_encap_ops mpls_iptun_ops = { + .encap_hlen = ipgre_mpls_encap_hlen, +}; + +static int ipgre_tunnel_encap_add_mpls_ops(void) +{ + return ip_tunnel_encap_add_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS); +} + +static void ipgre_tunnel_encap_del_mpls_ops(void) +{ + ip_tunnel_encap_del_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS); +} +#else +static int ipgre_tunnel_encap_add_mpls_ops(void) +{ + return 0; +} + +static void ipgre_tunnel_encap_del_mpls_ops(void) +{ +} +#endif + static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt, struct nlmsghdr *nlh, struct net *net, u32 portid, unsigned int nlm_flags); @@ -2485,6 +2516,10 @@ static int __init mpls_init(void) 0); rtnl_register(PF_MPLS, RTM_GETNETCONF, mpls_netconf_get_devconf, mpls_netconf_dump_devconf, 0); + err = ipgre_tunnel_encap_add_mpls_ops(); + if (err) + pr_err("Can't add mpls over gre tunnel ops\n"); + err = 0; out: return err; @@ -2502,6 +2537,7 @@ static void __exit mpls_exit(void) dev_remove_pack(&mpls_packet_type); unregister_netdevice_notifier(&mpls_dev_notifier); unregister_pernet_subsys(&mpls_net_ops); + ipgre_tunnel_encap_del_mpls_ops(); } module_exit(mpls_exit); diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c index f135938bf781..67e708e98ccf 100644 --- a/net/ncsi/ncsi-aen.c +++ b/net/ncsi/ncsi-aen.c @@ -73,6 +73,9 @@ static int ncsi_aen_handler_lsc(struct ncsi_dev_priv *ndp, ncm->data[2] = data; ncm->data[4] = ntohl(lsc->oem_status); + netdev_info(ndp->ndev.dev, "NCSI: LSC AEN - channel %u state %s\n", + nc->id, data & 0x1 ? "up" : "down"); + chained = !list_empty(&nc->link); state = nc->state; spin_unlock_irqrestore(&nc->lock, flags); @@ -145,6 +148,8 @@ static int ncsi_aen_handler_hncdsc(struct ncsi_dev_priv *ndp, ncm = &nc->modes[NCSI_MODE_LINK]; hncdsc = (struct ncsi_aen_hncdsc_pkt *)h; ncm->data[3] = ntohl(hncdsc->status); + netdev_info(ndp->ndev.dev, "NCSI: HNCDSC AEN - channel %u state %s\n", + nc->id, ncm->data[3] & 0x3 ? "up" : "down"); if (!list_empty(&nc->link) || nc->state != NCSI_CHANNEL_ACTIVE) { spin_unlock_irqrestore(&nc->lock, flags); @@ -212,10 +217,18 @@ int ncsi_aen_handler(struct ncsi_dev_priv *ndp, struct sk_buff *skb) } ret = ncsi_validate_aen_pkt(h, nah->payload); - if (ret) + if (ret) { + netdev_warn(ndp->ndev.dev, + "NCSI: 'bad' packet ignored for AEN type 0x%x\n", + h->type); goto out; + } ret = nah->handler(ndp, h); + if (ret) + netdev_err(ndp->ndev.dev, + "NCSI: Handler for AEN type 0x%x returned %d\n", + h->type, ret); out: consume_skb(skb); return ret; diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index 28c42b22b748..a2b904a718c6 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -38,7 +38,7 @@ static inline int ncsi_filter_size(int table) return sizes[table]; } -u32 *ncsi_get_filter(struct ncsi_channel *nc, int table, int index) +static u32 *ncsi_get_filter(struct ncsi_channel *nc, int table, int index) { struct ncsi_channel_filter *ncf; int size; @@ -229,6 +229,8 @@ static void ncsi_channel_monitor(unsigned long data) case NCSI_CHANNEL_MONITOR_WAIT ... NCSI_CHANNEL_MONITOR_WAIT_MAX: break; default: + netdev_err(ndp->ndev.dev, "NCSI Channel %d timed out!\n", + nc->id); if (!(ndp->flags & NCSI_DEV_HWA)) { ncsi_report_link(ndp, true); ndp->flags |= NCSI_DEV_RESHUFFLE; @@ -682,7 +684,7 @@ static int clear_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc, data = ncsi_get_filter(nc, NCSI_FILTER_VLAN, index); if (!data) { netdev_err(ndp->ndev.dev, - "ncsi: failed to retrieve filter %d\n", index); + "NCSI: failed to retrieve filter %d\n", index); /* Set the VLAN id to 0 - this will still disable the entry in * the filter table, but we won't know what it was. */ @@ -692,7 +694,7 @@ static int clear_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc, } netdev_printk(KERN_DEBUG, ndp->ndev.dev, - "ncsi: removed vlan tag %u at index %d\n", + "NCSI: removed vlan tag %u at index %d\n", vid, index + 1); ncsi_remove_filter(nc, NCSI_FILTER_VLAN, index); @@ -718,7 +720,7 @@ static int set_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc, if (index < 0) { /* New tag to add */ netdev_printk(KERN_DEBUG, ndp->ndev.dev, - "ncsi: new vlan id to set: %u\n", + "NCSI: new vlan id to set: %u\n", vlan->vid); break; } @@ -745,7 +747,7 @@ static int set_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc, } netdev_printk(KERN_DEBUG, ndp->ndev.dev, - "ncsi: set vid %u in packet, index %u\n", + "NCSI: set vid %u in packet, index %u\n", vlan->vid, index + 1); nca->type = NCSI_PKT_CMD_SVF; nca->words[1] = vlan->vid; @@ -784,8 +786,11 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) nca.package = np->id; nca.channel = NCSI_RESERVED_CHANNEL; ret = ncsi_xmit_cmd(&nca); - if (ret) + if (ret) { + netdev_err(ndp->ndev.dev, + "NCSI: Failed to transmit CMD_SP\n"); goto error; + } nd->state = ncsi_dev_state_config_cis; break; @@ -797,8 +802,11 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) nca.package = np->id; nca.channel = nc->id; ret = ncsi_xmit_cmd(&nca); - if (ret) + if (ret) { + netdev_err(ndp->ndev.dev, + "NCSI: Failed to transmit CMD_CIS\n"); goto error; + } nd->state = ncsi_dev_state_config_clear_vids; break; @@ -895,10 +903,16 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) } ret = ncsi_xmit_cmd(&nca); - if (ret) + if (ret) { + netdev_err(ndp->ndev.dev, + "NCSI: Failed to transmit CMD %x\n", + nca.type); goto error; + } break; case ncsi_dev_state_config_done: + netdev_printk(KERN_DEBUG, ndp->ndev.dev, + "NCSI: channel %u config done\n", nc->id); spin_lock_irqsave(&nc->lock, flags); if (nc->reconfigure_needed) { /* This channel's configuration has been updated @@ -925,6 +939,9 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) } else { hot_nc = NULL; nc->state = NCSI_CHANNEL_INACTIVE; + netdev_warn(ndp->ndev.dev, + "NCSI: channel %u link down after config\n", + nc->id); } spin_unlock_irqrestore(&nc->lock, flags); @@ -937,8 +954,8 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) ncsi_process_next_channel(ndp); break; default: - netdev_warn(dev, "Wrong NCSI state 0x%x in config\n", - nd->state); + netdev_alert(dev, "Wrong NCSI state 0x%x in config\n", + nd->state); } return; @@ -990,10 +1007,17 @@ static int ncsi_choose_active_channel(struct ncsi_dev_priv *ndp) } if (!found) { + netdev_warn(ndp->ndev.dev, + "NCSI: No channel found with link\n"); ncsi_report_link(ndp, true); return -ENODEV; } + ncm = &found->modes[NCSI_MODE_LINK]; + netdev_printk(KERN_DEBUG, ndp->ndev.dev, + "NCSI: Channel %u added to queue (link %s)\n", + found->id, ncm->data[2] & 0x1 ? "up" : "down"); + out: spin_lock_irqsave(&ndp->lock, flags); list_add_tail_rcu(&found->link, &ndp->channel_queue); @@ -1055,6 +1079,8 @@ static int ncsi_enable_hwa(struct ncsi_dev_priv *ndp) /* We can have no channels in extremely case */ if (list_empty(&ndp->channel_queue)) { + netdev_err(ndp->ndev.dev, + "NCSI: No available channels for HWA\n"); ncsi_report_link(ndp, false); return -ENOENT; } @@ -1223,6 +1249,9 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) return; error: + netdev_err(ndp->ndev.dev, + "NCSI: Failed to transmit cmd 0x%x during probe\n", + nca.type); ncsi_report_link(ndp, true); } @@ -1276,10 +1305,14 @@ int ncsi_process_next_channel(struct ncsi_dev_priv *ndp) switch (old_state) { case NCSI_CHANNEL_INACTIVE: ndp->ndev.state = ncsi_dev_state_config; + netdev_info(ndp->ndev.dev, "NCSI: configuring channel %u\n", + nc->id); ncsi_configure_channel(ndp); break; case NCSI_CHANNEL_ACTIVE: ndp->ndev.state = ncsi_dev_state_suspend; + netdev_info(ndp->ndev.dev, "NCSI: suspending channel %u\n", + nc->id); ncsi_suspend_channel(ndp); break; default: @@ -1299,6 +1332,8 @@ out: return ncsi_choose_active_channel(ndp); } + netdev_printk(KERN_DEBUG, ndp->ndev.dev, + "NCSI: No more channels to process\n"); ncsi_report_link(ndp, false); return -ENODEV; } @@ -1390,7 +1425,7 @@ static int ncsi_kick_channels(struct ncsi_dev_priv *ndp) ncsi_dev_state_config || !list_empty(&nc->link)) { netdev_printk(KERN_DEBUG, nd->dev, - "ncsi: channel %p marked dirty\n", + "NCSI: channel %p marked dirty\n", nc); nc->reconfigure_needed = true; } @@ -1410,7 +1445,7 @@ static int ncsi_kick_channels(struct ncsi_dev_priv *ndp) spin_unlock_irqrestore(&ndp->lock, flags); netdev_printk(KERN_DEBUG, nd->dev, - "ncsi: kicked channel %p\n", nc); + "NCSI: kicked channel %p\n", nc); n++; } } @@ -1431,7 +1466,7 @@ int ncsi_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) nd = ncsi_find_dev(dev); if (!nd) { - netdev_warn(dev, "ncsi: No net_device?\n"); + netdev_warn(dev, "NCSI: No net_device?\n"); return 0; } @@ -1442,7 +1477,7 @@ int ncsi_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) n_vids++; if (vlan->vid == vid) { netdev_printk(KERN_DEBUG, dev, - "vid %u already registered\n", vid); + "NCSI: vid %u already registered\n", vid); return 0; } } @@ -1461,7 +1496,7 @@ int ncsi_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) vlan->vid = vid; list_add_rcu(&vlan->list, &ndp->vlan_vids); - netdev_printk(KERN_DEBUG, dev, "Added new vid %u\n", vid); + netdev_printk(KERN_DEBUG, dev, "NCSI: Added new vid %u\n", vid); found = ncsi_kick_channels(ndp) != 0; @@ -1481,7 +1516,7 @@ int ncsi_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) nd = ncsi_find_dev(dev); if (!nd) { - netdev_warn(dev, "ncsi: no net_device?\n"); + netdev_warn(dev, "NCSI: no net_device?\n"); return 0; } @@ -1491,14 +1526,14 @@ int ncsi_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) list_for_each_entry_safe(vlan, tmp, &ndp->vlan_vids, list) if (vlan->vid == vid) { netdev_printk(KERN_DEBUG, dev, - "vid %u found, removing\n", vid); + "NCSI: vid %u found, removing\n", vid); list_del_rcu(&vlan->list); found = true; kfree(vlan); } if (!found) { - netdev_err(dev, "ncsi: vid %u wasn't registered!\n", vid); + netdev_err(dev, "NCSI: vid %u wasn't registered!\n", vid); return -EINVAL; } @@ -1581,10 +1616,12 @@ int ncsi_start_dev(struct ncsi_dev *nd) return 0; } - if (ndp->flags & NCSI_DEV_HWA) + if (ndp->flags & NCSI_DEV_HWA) { + netdev_info(ndp->ndev.dev, "NCSI: Enabling HWA mode\n"); ret = ncsi_enable_hwa(ndp); - else + } else { ret = ncsi_choose_active_channel(ndp); + } return ret; } @@ -1615,6 +1652,7 @@ void ncsi_stop_dev(struct ncsi_dev *nd) } } + netdev_printk(KERN_DEBUG, ndp->ndev.dev, "NCSI: Stopping device\n"); ncsi_report_link(ndp, true); } EXPORT_SYMBOL_GPL(ncsi_stop_dev); diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index 927dad4759d1..efd933ff5570 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -146,7 +146,7 @@ static int ncsi_rsp_handler_ec(struct ncsi_request *nr) ncm = &nc->modes[NCSI_MODE_ENABLE]; if (ncm->enable) - return -EBUSY; + return 0; ncm->enable = 1; return 0; @@ -173,7 +173,7 @@ static int ncsi_rsp_handler_dc(struct ncsi_request *nr) ncm = &nc->modes[NCSI_MODE_ENABLE]; if (!ncm->enable) - return -EBUSY; + return 0; ncm->enable = 0; return 0; @@ -217,7 +217,7 @@ static int ncsi_rsp_handler_ecnt(struct ncsi_request *nr) ncm = &nc->modes[NCSI_MODE_TX_ENABLE]; if (ncm->enable) - return -EBUSY; + return 0; ncm->enable = 1; return 0; @@ -239,7 +239,7 @@ static int ncsi_rsp_handler_dcnt(struct ncsi_request *nr) ncm = &nc->modes[NCSI_MODE_TX_ENABLE]; if (!ncm->enable) - return -EBUSY; + return 0; ncm->enable = 1; return 0; @@ -263,7 +263,7 @@ static int ncsi_rsp_handler_ae(struct ncsi_request *nr) /* Check if the AEN has been enabled */ ncm = &nc->modes[NCSI_MODE_AEN]; if (ncm->enable) - return -EBUSY; + return 0; /* Update to AEN configuration */ cmd = (struct ncsi_cmd_ae_pkt *)skb_network_header(nr->cmd); @@ -382,7 +382,7 @@ static int ncsi_rsp_handler_ev(struct ncsi_request *nr) /* Check if VLAN mode has been enabled */ ncm = &nc->modes[NCSI_MODE_VLAN]; if (ncm->enable) - return -EBUSY; + return 0; /* Update to VLAN mode */ cmd = (struct ncsi_cmd_ev_pkt *)skb_network_header(nr->cmd); @@ -409,7 +409,7 @@ static int ncsi_rsp_handler_dv(struct ncsi_request *nr) /* Check if VLAN mode has been enabled */ ncm = &nc->modes[NCSI_MODE_VLAN]; if (!ncm->enable) - return -EBUSY; + return 0; /* Update to VLAN mode */ ncm->enable = 0; @@ -455,13 +455,10 @@ static int ncsi_rsp_handler_sma(struct ncsi_request *nr) bitmap = &ncf->bitmap; if (cmd->at_e & 0x1) { - if (test_and_set_bit(cmd->index, bitmap)) - return -EBUSY; + set_bit(cmd->index, bitmap); memcpy(ncf->data + 6 * cmd->index, cmd->mac, 6); } else { - if (!test_and_clear_bit(cmd->index, bitmap)) - return -EBUSY; - + clear_bit(cmd->index, bitmap); memset(ncf->data + 6 * cmd->index, 0, 6); } @@ -485,7 +482,7 @@ static int ncsi_rsp_handler_ebf(struct ncsi_request *nr) /* Check if broadcast filter has been enabled */ ncm = &nc->modes[NCSI_MODE_BC]; if (ncm->enable) - return -EBUSY; + return 0; /* Update to broadcast filter mode */ cmd = (struct ncsi_cmd_ebf_pkt *)skb_network_header(nr->cmd); @@ -511,7 +508,7 @@ static int ncsi_rsp_handler_dbf(struct ncsi_request *nr) /* Check if broadcast filter isn't enabled */ ncm = &nc->modes[NCSI_MODE_BC]; if (!ncm->enable) - return -EBUSY; + return 0; /* Update to broadcast filter mode */ ncm->enable = 0; @@ -538,7 +535,7 @@ static int ncsi_rsp_handler_egmf(struct ncsi_request *nr) /* Check if multicast filter has been enabled */ ncm = &nc->modes[NCSI_MODE_MC]; if (ncm->enable) - return -EBUSY; + return 0; /* Update to multicast filter mode */ cmd = (struct ncsi_cmd_egmf_pkt *)skb_network_header(nr->cmd); @@ -564,7 +561,7 @@ static int ncsi_rsp_handler_dgmf(struct ncsi_request *nr) /* Check if multicast filter has been enabled */ ncm = &nc->modes[NCSI_MODE_MC]; if (!ncm->enable) - return -EBUSY; + return 0; /* Update to multicast filter mode */ ncm->enable = 0; @@ -591,7 +588,7 @@ static int ncsi_rsp_handler_snfc(struct ncsi_request *nr) /* Check if flow control has been enabled */ ncm = &nc->modes[NCSI_MODE_FC]; if (ncm->enable) - return -EBUSY; + return 0; /* Update to flow control mode */ cmd = (struct ncsi_cmd_snfc_pkt *)skb_network_header(nr->cmd); @@ -1032,11 +1029,19 @@ int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev, if (payload < 0) payload = ntohs(hdr->length); ret = ncsi_validate_rsp_pkt(nr, payload); - if (ret) + if (ret) { + netdev_warn(ndp->ndev.dev, + "NCSI: 'bad' packet ignored for type 0x%x\n", + hdr->type); goto out; + } /* Process the packet */ ret = nrh->handler(nr); + if (ret) + netdev_err(ndp->ndev.dev, + "NCSI: Handler for packet type 0x%x returned %d\n", + hdr->type, ret); out: ncsi_free_request(nr); return ret; diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index 8ad2b52a0b32..5ca18f07683b 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -37,11 +37,11 @@ #define get_ext(set, map, id) ((map)->extensions + ((set)->dsize * (id))) static void -mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set)) +mtype_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t)) { struct mtype *map = set->data; - setup_timer(&map->gc, gc, (unsigned long)set); + timer_setup(&map->gc, gc, 0); mod_timer(&map->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ); } @@ -272,10 +272,10 @@ out: } static void -mtype_gc(unsigned long ul_set) +mtype_gc(struct timer_list *t) { - struct ip_set *set = (struct ip_set *)ul_set; - struct mtype *map = set->data; + struct mtype *map = from_timer(map, t, gc); + struct ip_set *set = map->set; void *x; u32 id; diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index 4783efff0bde..d8975a0b4282 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -48,6 +48,7 @@ struct bitmap_ip { size_t memsize; /* members size */ u8 netmask; /* subnet netmask */ struct timer_list gc; /* garbage collection */ + struct ip_set *set; /* attached to this ip_set */ unsigned char extensions[0] /* data extensions */ __aligned(__alignof__(u64)); }; @@ -232,6 +233,7 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map, map->netmask = netmask; set->timeout = IPSET_NO_TIMEOUT; + map->set = set; set->data = map; set->family = NFPROTO_IPV4; diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index 9a065f672d3a..4c279fbd2d5d 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -52,6 +52,7 @@ struct bitmap_ipmac { u32 elements; /* number of max elements in the set */ size_t memsize; /* members size */ struct timer_list gc; /* garbage collector */ + struct ip_set *set; /* attached to this ip_set */ unsigned char extensions[0] /* MAC + data extensions */ __aligned(__alignof__(u64)); }; @@ -307,6 +308,7 @@ init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map, map->elements = elements; set->timeout = IPSET_NO_TIMEOUT; + map->set = set; set->data = map; set->family = NFPROTO_IPV4; diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c index 7f0c733358a4..7f9bbd7c98b5 100644 --- a/net/netfilter/ipset/ip_set_bitmap_port.c +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -40,6 +40,7 @@ struct bitmap_port { u32 elements; /* number of max elements in the set */ size_t memsize; /* members size */ struct timer_list gc; /* garbage collection */ + struct ip_set *set; /* attached to this ip_set */ unsigned char extensions[0] /* data extensions */ __aligned(__alignof__(u64)); }; @@ -214,6 +215,7 @@ init_map_port(struct ip_set *set, struct bitmap_port *map, map->last_port = last_port; set->timeout = IPSET_NO_TIMEOUT; + map->set = set; set->data = map; set->family = NFPROTO_UNSPEC; diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 51063d9ed0f7..efffc8eabafe 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -280,6 +280,7 @@ htable_bits(u32 hashsize) struct htype { struct htable __rcu *table; /* the hash table */ struct timer_list gc; /* garbage collection when timeout enabled */ + struct ip_set *set; /* attached to this ip_set */ u32 maxelem; /* max elements in the hash */ u32 initval; /* random jhash init value */ #ifdef IP_SET_HASH_WITH_MARKMASK @@ -429,11 +430,11 @@ mtype_destroy(struct ip_set *set) } static void -mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set)) +mtype_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t)) { struct htype *h = set->data; - setup_timer(&h->gc, gc, (unsigned long)set); + timer_setup(&h->gc, gc, 0); mod_timer(&h->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ); pr_debug("gc initialized, run in every %u\n", IPSET_GC_PERIOD(set->timeout)); @@ -526,10 +527,10 @@ mtype_expire(struct ip_set *set, struct htype *h) } static void -mtype_gc(unsigned long ul_set) +mtype_gc(struct timer_list *t) { - struct ip_set *set = (struct ip_set *)ul_set; - struct htype *h = set->data; + struct htype *h = from_timer(h, t, gc); + struct ip_set *set = h->set; pr_debug("called\n"); spin_lock_bh(&set->lock); @@ -1314,6 +1315,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, t->htable_bits = hbits; RCU_INIT_POINTER(h->table, t); + h->set = set; set->data = h; #ifndef IP_SET_PROTO_UNDEF if (set->family == NFPROTO_IPV4) { diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index a2f19b9906e9..0f164e986bf1 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -434,7 +434,7 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (unlikely(tb[IPSET_ATTR_IP_TO])) return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; if (unlikely(tb[IPSET_ATTR_CIDR])) { - u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); + cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); if (cidr != HOST_MASK) return -IPSET_ERR_INVALID_CIDR; diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 178d4eba013b..e864681b8dc5 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -44,6 +44,7 @@ struct set_adt_elem { struct list_set { u32 size; /* size of set list array */ struct timer_list gc; /* garbage collection */ + struct ip_set *set; /* attached to this ip_set */ struct net *net; /* namespace */ struct list_head members; /* the set members */ }; @@ -453,7 +454,6 @@ static size_t list_set_memsize(const struct list_set *map, size_t dsize) { struct set_elem *e; - size_t memsize; u32 n = 0; rcu_read_lock(); @@ -461,9 +461,7 @@ list_set_memsize(const struct list_set *map, size_t dsize) n++; rcu_read_unlock(); - memsize = sizeof(*map) + n * dsize; - - return memsize; + return (sizeof(*map) + n * dsize); } static int @@ -571,10 +569,10 @@ static const struct ip_set_type_variant set_variant = { }; static void -list_set_gc(unsigned long ul_set) +list_set_gc(struct timer_list *t) { - struct ip_set *set = (struct ip_set *)ul_set; - struct list_set *map = set->data; + struct list_set *map = from_timer(map, t, gc); + struct ip_set *set = map->set; spin_lock_bh(&set->lock); set_cleanup_entries(set); @@ -585,11 +583,11 @@ list_set_gc(unsigned long ul_set) } static void -list_set_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set)) +list_set_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t)) { struct list_set *map = set->data; - setup_timer(&map->gc, gc, (unsigned long)set); + timer_setup(&map->gc, gc, 0); mod_timer(&map->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ); } @@ -606,6 +604,7 @@ init_list_set(struct net *net, struct ip_set *set, u32 size) map->size = size; map->net = net; + map->set = set; INIT_LIST_HEAD(&map->members); set->data = map; diff --git a/net/netfilter/ipset/pfxlen.c b/net/netfilter/ipset/pfxlen.c index 1c8a42c1056c..d5be9c25fad6 100644 --- a/net/netfilter/ipset/pfxlen.c +++ b/net/netfilter/ipset/pfxlen.c @@ -3,6 +3,141 @@ /* Prefixlen maps for fast conversions, by Jan Engelhardt. */ +#ifdef E +#undef E +#endif + +#define PREFIXES_MAP \ + E(0x00000000, 0x00000000, 0x00000000, 0x00000000), \ + E(0x80000000, 0x00000000, 0x00000000, 0x00000000), \ + E(0xC0000000, 0x00000000, 0x00000000, 0x00000000), \ + E(0xE0000000, 0x00000000, 0x00000000, 0x00000000), \ + E(0xF0000000, 0x00000000, 0x00000000, 0x00000000), \ + E(0xF8000000, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFC000000, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFE000000, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFF000000, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFF800000, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFC00000, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFE00000, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFF00000, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFF80000, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFFC0000, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFFE0000, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFFF0000, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFFF8000, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFFFC000, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFFFE000, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFFFF000, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFFFF800, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFFFFC00, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFFFFE00, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFFFFF00, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFFFFF80, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFFFFFC0, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFFFFFE0, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFFFFFF0, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFFFFFF8, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFC, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFE, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0x00000000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0x80000000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xC0000000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xE0000000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xF0000000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xF8000000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFC000000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFE000000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFF000000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFF800000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFC00000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFE00000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFF00000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFF80000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFC0000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFE0000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFF0000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFF8000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFC000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFE000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFF000, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFF800, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFC00, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFE00, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFF00, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFF80, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFC0, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFE0, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFF0, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFF8, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFC, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFE, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0x00000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0x80000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xC0000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xE0000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xF0000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xF8000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFC000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFE000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFF000000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFF800000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFC00000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFE00000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFF00000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFF80000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFC0000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFE0000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF0000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF8000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFC000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFE000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF000, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF800, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFC00, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFE00, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF00, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF80, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFC0, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFE0, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF0, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF8, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFC, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFE, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x00000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x80000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xC0000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xE0000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xF0000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xF8000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFC000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFE000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFF000000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFF800000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFC00000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFE00000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFF00000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFF80000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFC0000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFE0000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF0000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF8000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFC000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFE000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF000), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF800), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFC00), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFE00), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF00), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF80), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFC0), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFE0), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF0), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF8), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFC), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFE), \ + E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF), + #define E(a, b, c, d) \ {.ip6 = { \ htonl(a), htonl(b), \ @@ -13,135 +148,7 @@ * just use prefixlen_netmask_map[prefixlength].ip. */ const union nf_inet_addr ip_set_netmask_map[] = { - E(0x00000000, 0x00000000, 0x00000000, 0x00000000), - E(0x80000000, 0x00000000, 0x00000000, 0x00000000), - E(0xC0000000, 0x00000000, 0x00000000, 0x00000000), - E(0xE0000000, 0x00000000, 0x00000000, 0x00000000), - E(0xF0000000, 0x00000000, 0x00000000, 0x00000000), - E(0xF8000000, 0x00000000, 0x00000000, 0x00000000), - E(0xFC000000, 0x00000000, 0x00000000, 0x00000000), - E(0xFE000000, 0x00000000, 0x00000000, 0x00000000), - E(0xFF000000, 0x00000000, 0x00000000, 0x00000000), - E(0xFF800000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFC00000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFE00000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFF00000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFF80000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFC0000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFE0000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFF0000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFF8000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFC000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFE000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFF000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFF800, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFC00, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFE00, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFF00, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFF80, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFFC0, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFFE0, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFFF0, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFFF8, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFFFC, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFFFE, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0x80000000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xC0000000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xE0000000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xF0000000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xF8000000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFC000000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFE000000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFF000000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFF800000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFC00000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFE00000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFF00000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFF80000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFC0000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFE0000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFF0000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFF8000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFC000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFE000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFF000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFF800, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFC00, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFE00, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFF00, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFF80, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFC0, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFE0, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFF0, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFF8, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFC, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFE, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0x80000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xC0000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xE0000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xF0000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xF8000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFC000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFE000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFF000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFF800000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFC00000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFE00000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFF00000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFF80000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFC0000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFE0000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF0000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF8000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFC000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFE000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF800, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFC00, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFE00, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF00, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF80, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFC0, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFE0, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF0, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF8, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFC, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFE, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x80000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xC0000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xE0000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xF0000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xF8000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFC000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFE000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFF000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFF800000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFC00000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFE00000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFF00000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFF80000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFC0000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFE0000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF0000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF8000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFC000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFE000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF800), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFC00), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFE00), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF00), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF80), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFC0), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFE0), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF0), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF8), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFC), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFE), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF), + PREFIXES_MAP }; EXPORT_SYMBOL_GPL(ip_set_netmask_map); @@ -155,135 +162,7 @@ EXPORT_SYMBOL_GPL(ip_set_netmask_map); * just use prefixlen_hostmask_map[prefixlength].ip. */ const union nf_inet_addr ip_set_hostmask_map[] = { - E(0x00000000, 0x00000000, 0x00000000, 0x00000000), - E(0x80000000, 0x00000000, 0x00000000, 0x00000000), - E(0xC0000000, 0x00000000, 0x00000000, 0x00000000), - E(0xE0000000, 0x00000000, 0x00000000, 0x00000000), - E(0xF0000000, 0x00000000, 0x00000000, 0x00000000), - E(0xF8000000, 0x00000000, 0x00000000, 0x00000000), - E(0xFC000000, 0x00000000, 0x00000000, 0x00000000), - E(0xFE000000, 0x00000000, 0x00000000, 0x00000000), - E(0xFF000000, 0x00000000, 0x00000000, 0x00000000), - E(0xFF800000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFC00000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFE00000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFF00000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFF80000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFC0000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFE0000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFF0000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFF8000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFC000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFE000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFF000, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFF800, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFC00, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFE00, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFF00, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFF80, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFFC0, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFFE0, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFFF0, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFFF8, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFFFC, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFFFE, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0x00000000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0x80000000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xC0000000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xE0000000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xF0000000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xF8000000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFC000000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFE000000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFF000000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFF800000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFC00000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFE00000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFF00000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFF80000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFC0000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFE0000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFF0000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFF8000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFC000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFE000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFF000, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFF800, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFC00, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFE00, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFF00, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFF80, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFC0, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFE0, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFF0, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFF8, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFC, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFE, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0x00000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0x80000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xC0000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xE0000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xF0000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xF8000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFC000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFE000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFF000000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFF800000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFC00000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFE00000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFF00000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFF80000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFC0000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFE0000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF0000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF8000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFC000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFE000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF000, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF800, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFC00, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFE00, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF00, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF80, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFC0, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFE0, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF0, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF8, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFC, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFE, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x00000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x80000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xC0000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xE0000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xF0000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xF8000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFC000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFE000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFF000000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFF800000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFC00000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFE00000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFF00000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFF80000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFC0000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFE0000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF0000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFF8000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFC000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFE000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF000), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFF800), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFC00), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFE00), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF00), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFF80), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFC0), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFE0), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF0), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFF8), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFC), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFE), - E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF), + PREFIXES_MAP }; EXPORT_SYMBOL_GPL(ip_set_hostmask_map); diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 3d2ac71a83ec..3e053cb30070 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -104,7 +104,7 @@ static inline void ct_write_unlock_bh(unsigned int key) spin_unlock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l); } -static void ip_vs_conn_expire(unsigned long data); +static void ip_vs_conn_expire(struct timer_list *t); /* * Returns hash value for IPVS connection entry @@ -185,7 +185,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) hlist_add_head_rcu(&cp->c_list, &ip_vs_conn_tab[hash]); ret = 1; } else { - pr_err("%s(): request for already hashed, called from %pF\n", + pr_err("%s(): request for already hashed, called from %pS\n", __func__, __builtin_return_address(0)); ret = 0; } @@ -457,7 +457,7 @@ EXPORT_SYMBOL_GPL(ip_vs_conn_out_get_proto); static void __ip_vs_conn_put_notimer(struct ip_vs_conn *cp) { __ip_vs_conn_put(cp); - ip_vs_conn_expire((unsigned long)cp); + ip_vs_conn_expire(&cp->timer); } /* @@ -817,9 +817,9 @@ static void ip_vs_conn_rcu_free(struct rcu_head *head) kmem_cache_free(ip_vs_conn_cachep, cp); } -static void ip_vs_conn_expire(unsigned long data) +static void ip_vs_conn_expire(struct timer_list *t) { - struct ip_vs_conn *cp = (struct ip_vs_conn *)data; + struct ip_vs_conn *cp = from_timer(cp, t, timer); struct netns_ipvs *ipvs = cp->ipvs; /* @@ -909,7 +909,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af, } INIT_HLIST_NODE(&cp->c_list); - setup_timer(&cp->timer, ip_vs_conn_expire, (unsigned long)cp); + timer_setup(&cp->timer, ip_vs_conn_expire, 0); cp->ipvs = ipvs; cp->af = p->af; cp->daf = dest_af; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 4f940d7eb2f7..fff213eacf2a 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -300,7 +300,7 @@ static int ip_vs_svc_hash(struct ip_vs_service *svc) unsigned int hash; if (svc->flags & IP_VS_SVC_F_HASHED) { - pr_err("%s(): request for already hashed, called from %pF\n", + pr_err("%s(): request for already hashed, called from %pS\n", __func__, __builtin_return_address(0)); return 0; } @@ -334,7 +334,7 @@ static int ip_vs_svc_hash(struct ip_vs_service *svc) static int ip_vs_svc_unhash(struct ip_vs_service *svc) { if (!(svc->flags & IP_VS_SVC_F_HASHED)) { - pr_err("%s(): request for unhash flagged, called from %pF\n", + pr_err("%s(): request for unhash flagged, called from %pS\n", __func__, __builtin_return_address(0)); return 0; } @@ -1146,9 +1146,9 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) return 0; } -static void ip_vs_dest_trash_expire(unsigned long data) +static void ip_vs_dest_trash_expire(struct timer_list *t) { - struct netns_ipvs *ipvs = (struct netns_ipvs *)data; + struct netns_ipvs *ipvs = from_timer(ipvs, t, dest_trash_timer); struct ip_vs_dest *dest, *next; unsigned long now = jiffies; @@ -2034,12 +2034,16 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v) seq_puts(seq, " -> RemoteAddress:Port Forward Weight ActiveConn InActConn\n"); } else { + struct net *net = seq_file_net(seq); + struct netns_ipvs *ipvs = net_ipvs(net); const struct ip_vs_service *svc = v; const struct ip_vs_iter *iter = seq->private; const struct ip_vs_dest *dest; struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler); char *sched_name = sched ? sched->name : "none"; + if (svc->ipvs != ipvs) + return 0; if (iter->table == ip_vs_svc_table) { #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) @@ -4019,8 +4023,7 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) INIT_LIST_HEAD(&ipvs->dest_trash); spin_lock_init(&ipvs->dest_trash_lock); - setup_timer(&ipvs->dest_trash_timer, ip_vs_dest_trash_expire, - (unsigned long) ipvs); + timer_setup(&ipvs->dest_trash_timer, ip_vs_dest_trash_expire, 0); atomic_set(&ipvs->ftpsvc_counter, 0); atomic_set(&ipvs->nullsvc_counter, 0); atomic_set(&ipvs->conn_out_counter, 0); diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index 457c6c193e13..489055091a9b 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -97,12 +97,12 @@ static void ip_vs_read_cpu_stats(struct ip_vs_kstats *sum, } -static void estimation_timer(unsigned long arg) +static void estimation_timer(struct timer_list *t) { struct ip_vs_estimator *e; struct ip_vs_stats *s; u64 rate; - struct netns_ipvs *ipvs = (struct netns_ipvs *)arg; + struct netns_ipvs *ipvs = from_timer(ipvs, t, est_timer); spin_lock(&ipvs->est_lock); list_for_each_entry(e, &ipvs->est_list, list) { @@ -192,7 +192,7 @@ int __net_init ip_vs_estimator_net_init(struct netns_ipvs *ipvs) { INIT_LIST_HEAD(&ipvs->est_list); spin_lock_init(&ipvs->est_lock); - setup_timer(&ipvs->est_timer, estimation_timer, (unsigned long)ipvs); + timer_setup(&ipvs->est_timer, estimation_timer, 0); mod_timer(&ipvs->est_timer, jiffies + 2 * HZ); return 0; } diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index b6aa4a970c6e..d625179de485 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -106,6 +106,7 @@ struct ip_vs_lblc_table { struct rcu_head rcu_head; struct hlist_head bucket[IP_VS_LBLC_TAB_SIZE]; /* hash bucket */ struct timer_list periodic_timer; /* collect stale entries */ + struct ip_vs_service *svc; /* pointer back to service */ atomic_t entries; /* number of entries */ int max_size; /* maximum size of entries */ int rover; /* rover for expire check */ @@ -294,10 +295,10 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc) * of the table. * The full expiration check is for this purpose now. */ -static void ip_vs_lblc_check_expire(unsigned long data) +static void ip_vs_lblc_check_expire(struct timer_list *t) { - struct ip_vs_service *svc = (struct ip_vs_service *) data; - struct ip_vs_lblc_table *tbl = svc->sched_data; + struct ip_vs_lblc_table *tbl = from_timer(tbl, t, periodic_timer); + struct ip_vs_service *svc = tbl->svc; unsigned long now = jiffies; int goal; int i, j; @@ -369,12 +370,12 @@ static int ip_vs_lblc_init_svc(struct ip_vs_service *svc) tbl->rover = 0; tbl->counter = 1; tbl->dead = 0; + tbl->svc = svc; /* * Hook periodic timer for garbage collection */ - setup_timer(&tbl->periodic_timer, ip_vs_lblc_check_expire, - (unsigned long)svc); + timer_setup(&tbl->periodic_timer, ip_vs_lblc_check_expire, 0); mod_timer(&tbl->periodic_timer, jiffies + CHECK_EXPIRE_INTERVAL); return 0; diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index c13ff575f9f7..84c57b62a588 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -278,6 +278,7 @@ struct ip_vs_lblcr_table { atomic_t entries; /* number of entries */ int max_size; /* maximum size of entries */ struct timer_list periodic_timer; /* collect stale entries */ + struct ip_vs_service *svc; /* pointer back to service */ int rover; /* rover for expire check */ int counter; /* counter for no expire */ bool dead; @@ -458,10 +459,10 @@ static inline void ip_vs_lblcr_full_check(struct ip_vs_service *svc) * of the table. * The full expiration check is for this purpose now. */ -static void ip_vs_lblcr_check_expire(unsigned long data) +static void ip_vs_lblcr_check_expire(struct timer_list *t) { - struct ip_vs_service *svc = (struct ip_vs_service *) data; - struct ip_vs_lblcr_table *tbl = svc->sched_data; + struct ip_vs_lblcr_table *tbl = from_timer(tbl, t, periodic_timer); + struct ip_vs_service *svc = tbl->svc; unsigned long now = jiffies; int goal; int i, j; @@ -532,12 +533,12 @@ static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc) tbl->rover = 0; tbl->counter = 1; tbl->dead = 0; + tbl->svc = svc; /* * Hook periodic timer for garbage collection */ - setup_timer(&tbl->periodic_timer, ip_vs_lblcr_check_expire, - (unsigned long)svc); + timer_setup(&tbl->periodic_timer, ip_vs_lblcr_check_expire, 0); mod_timer(&tbl->periodic_timer, jiffies + CHECK_EXPIRE_INTERVAL); return 0; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 13f740875507..9ee71cb276d7 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -458,7 +458,7 @@ static inline bool in_persistence(struct ip_vs_conn *cp) static int ip_vs_sync_conn_needed(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts) { - unsigned long orig = ACCESS_ONCE(cp->sync_endtime); + unsigned long orig = READ_ONCE(cp->sync_endtime); unsigned long now = jiffies; unsigned long n = (now + cp->timeout) & ~3UL; unsigned int sync_refresh_period; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 01130392b7c0..85f643c1e227 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1083,7 +1083,7 @@ static void gc_worker(struct work_struct *work) next_run = gc_work->next_gc_run; gc_work->last_bucket = i; gc_work->early_drop = false; - queue_delayed_work(system_long_wq, &gc_work->dwork, next_run); + queue_delayed_work(system_power_efficient_wq, &gc_work->dwork, next_run); } static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work) @@ -1419,7 +1419,7 @@ repeat: /* Decide what timeout policy we want to apply to this flow. */ timeouts = nf_ct_timeout_lookup(net, ct, l4proto); - ret = l4proto->packet(ct, skb, dataoff, ctinfo, pf, timeouts); + ret = l4proto->packet(ct, skb, dataoff, ctinfo, timeouts); if (ret <= 0) { /* Invalid: inverse of the return code tells * the netfilter core what to do */ @@ -1563,9 +1563,14 @@ int nf_ct_port_nlattr_to_tuple(struct nlattr *tb[], } EXPORT_SYMBOL_GPL(nf_ct_port_nlattr_to_tuple); -int nf_ct_port_nlattr_tuple_size(void) +unsigned int nf_ct_port_nlattr_tuple_size(void) { - return nla_policy_len(nf_ct_port_nla_policy, CTA_PROTO_MAX + 1); + static unsigned int size __read_mostly; + + if (!size) + size = nla_policy_len(nf_ct_port_nla_policy, CTA_PROTO_MAX + 1); + + return size; } EXPORT_SYMBOL_GPL(nf_ct_port_nlattr_tuple_size); #endif @@ -1940,7 +1945,7 @@ int nf_conntrack_hash_resize(unsigned int hashsize) return 0; } -int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) +int nf_conntrack_set_hashsize(const char *val, const struct kernel_param *kp) { unsigned int hashsize; int rc; @@ -2084,7 +2089,7 @@ int nf_conntrack_init_start(void) goto err_proto; conntrack_gc_work_init(&conntrack_gc_work); - queue_delayed_work(system_long_wq, &conntrack_gc_work.dwork, HZ); + queue_delayed_work(system_power_efficient_wq, &conntrack_gc_work.dwork, HZ); return 0; diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c index 89b2e46925c4..cf1bf2605c10 100644 --- a/net/netfilter/nf_conntrack_h323_asn1.c +++ b/net/netfilter/nf_conntrack_h323_asn1.c @@ -91,41 +91,41 @@ typedef struct field_t { } field_t; /* Bit Stream */ -typedef struct { +struct bitstr { unsigned char *buf; unsigned char *beg; unsigned char *end; unsigned char *cur; unsigned int bit; -} bitstr_t; +}; /* Tool Functions */ #define INC_BIT(bs) if((++(bs)->bit)>7){(bs)->cur++;(bs)->bit=0;} #define INC_BITS(bs,b) if(((bs)->bit+=(b))>7){(bs)->cur+=(bs)->bit>>3;(bs)->bit&=7;} #define BYTE_ALIGN(bs) if((bs)->bit){(bs)->cur++;(bs)->bit=0;} #define CHECK_BOUND(bs,n) if((bs)->cur+(n)>(bs)->end)return(H323_ERROR_BOUND) -static unsigned int get_len(bitstr_t *bs); -static unsigned int get_bit(bitstr_t *bs); -static unsigned int get_bits(bitstr_t *bs, unsigned int b); -static unsigned int get_bitmap(bitstr_t *bs, unsigned int b); -static unsigned int get_uint(bitstr_t *bs, int b); +static unsigned int get_len(struct bitstr *bs); +static unsigned int get_bit(struct bitstr *bs); +static unsigned int get_bits(struct bitstr *bs, unsigned int b); +static unsigned int get_bitmap(struct bitstr *bs, unsigned int b); +static unsigned int get_uint(struct bitstr *bs, int b); /* Decoder Functions */ -static int decode_nul(bitstr_t *bs, const struct field_t *f, char *base, int level); -static int decode_bool(bitstr_t *bs, const struct field_t *f, char *base, int level); -static int decode_oid(bitstr_t *bs, const struct field_t *f, char *base, int level); -static int decode_int(bitstr_t *bs, const struct field_t *f, char *base, int level); -static int decode_enum(bitstr_t *bs, const struct field_t *f, char *base, int level); -static int decode_bitstr(bitstr_t *bs, const struct field_t *f, char *base, int level); -static int decode_numstr(bitstr_t *bs, const struct field_t *f, char *base, int level); -static int decode_octstr(bitstr_t *bs, const struct field_t *f, char *base, int level); -static int decode_bmpstr(bitstr_t *bs, const struct field_t *f, char *base, int level); -static int decode_seq(bitstr_t *bs, const struct field_t *f, char *base, int level); -static int decode_seqof(bitstr_t *bs, const struct field_t *f, char *base, int level); -static int decode_choice(bitstr_t *bs, const struct field_t *f, char *base, int level); +static int decode_nul(struct bitstr *bs, const struct field_t *f, char *base, int level); +static int decode_bool(struct bitstr *bs, const struct field_t *f, char *base, int level); +static int decode_oid(struct bitstr *bs, const struct field_t *f, char *base, int level); +static int decode_int(struct bitstr *bs, const struct field_t *f, char *base, int level); +static int decode_enum(struct bitstr *bs, const struct field_t *f, char *base, int level); +static int decode_bitstr(struct bitstr *bs, const struct field_t *f, char *base, int level); +static int decode_numstr(struct bitstr *bs, const struct field_t *f, char *base, int level); +static int decode_octstr(struct bitstr *bs, const struct field_t *f, char *base, int level); +static int decode_bmpstr(struct bitstr *bs, const struct field_t *f, char *base, int level); +static int decode_seq(struct bitstr *bs, const struct field_t *f, char *base, int level); +static int decode_seqof(struct bitstr *bs, const struct field_t *f, char *base, int level); +static int decode_choice(struct bitstr *bs, const struct field_t *f, char *base, int level); /* Decoder Functions Vector */ -typedef int (*decoder_t)(bitstr_t *, const struct field_t *, char *, int); +typedef int (*decoder_t)(struct bitstr *, const struct field_t *, char *, int); static const decoder_t Decoders[] = { decode_nul, decode_bool, @@ -150,7 +150,7 @@ static const decoder_t Decoders[] = { * Functions ****************************************************************************/ /* Assume bs is aligned && v < 16384 */ -static unsigned int get_len(bitstr_t *bs) +static unsigned int get_len(struct bitstr *bs) { unsigned int v; @@ -166,7 +166,7 @@ static unsigned int get_len(bitstr_t *bs) } /****************************************************************************/ -static unsigned int get_bit(bitstr_t *bs) +static unsigned int get_bit(struct bitstr *bs) { unsigned int b = (*bs->cur) & (0x80 >> bs->bit); @@ -177,7 +177,7 @@ static unsigned int get_bit(bitstr_t *bs) /****************************************************************************/ /* Assume b <= 8 */ -static unsigned int get_bits(bitstr_t *bs, unsigned int b) +static unsigned int get_bits(struct bitstr *bs, unsigned int b) { unsigned int v, l; @@ -203,7 +203,7 @@ static unsigned int get_bits(bitstr_t *bs, unsigned int b) /****************************************************************************/ /* Assume b <= 32 */ -static unsigned int get_bitmap(bitstr_t *bs, unsigned int b) +static unsigned int get_bitmap(struct bitstr *bs, unsigned int b) { unsigned int v, l, shift, bytes; @@ -242,7 +242,7 @@ static unsigned int get_bitmap(bitstr_t *bs, unsigned int b) /**************************************************************************** * Assume bs is aligned and sizeof(unsigned int) == 4 ****************************************************************************/ -static unsigned int get_uint(bitstr_t *bs, int b) +static unsigned int get_uint(struct bitstr *bs, int b) { unsigned int v = 0; @@ -264,7 +264,7 @@ static unsigned int get_uint(bitstr_t *bs, int b) } /****************************************************************************/ -static int decode_nul(bitstr_t *bs, const struct field_t *f, +static int decode_nul(struct bitstr *bs, const struct field_t *f, char *base, int level) { PRINT("%*.s%s\n", level * TAB_SIZE, " ", f->name); @@ -273,7 +273,7 @@ static int decode_nul(bitstr_t *bs, const struct field_t *f, } /****************************************************************************/ -static int decode_bool(bitstr_t *bs, const struct field_t *f, +static int decode_bool(struct bitstr *bs, const struct field_t *f, char *base, int level) { PRINT("%*.s%s\n", level * TAB_SIZE, " ", f->name); @@ -285,7 +285,7 @@ static int decode_bool(bitstr_t *bs, const struct field_t *f, } /****************************************************************************/ -static int decode_oid(bitstr_t *bs, const struct field_t *f, +static int decode_oid(struct bitstr *bs, const struct field_t *f, char *base, int level) { int len; @@ -302,7 +302,7 @@ static int decode_oid(bitstr_t *bs, const struct field_t *f, } /****************************************************************************/ -static int decode_int(bitstr_t *bs, const struct field_t *f, +static int decode_int(struct bitstr *bs, const struct field_t *f, char *base, int level) { unsigned int len; @@ -346,7 +346,7 @@ static int decode_int(bitstr_t *bs, const struct field_t *f, } /****************************************************************************/ -static int decode_enum(bitstr_t *bs, const struct field_t *f, +static int decode_enum(struct bitstr *bs, const struct field_t *f, char *base, int level) { PRINT("%*.s%s\n", level * TAB_SIZE, " ", f->name); @@ -362,7 +362,7 @@ static int decode_enum(bitstr_t *bs, const struct field_t *f, } /****************************************************************************/ -static int decode_bitstr(bitstr_t *bs, const struct field_t *f, +static int decode_bitstr(struct bitstr *bs, const struct field_t *f, char *base, int level) { unsigned int len; @@ -396,7 +396,7 @@ static int decode_bitstr(bitstr_t *bs, const struct field_t *f, } /****************************************************************************/ -static int decode_numstr(bitstr_t *bs, const struct field_t *f, +static int decode_numstr(struct bitstr *bs, const struct field_t *f, char *base, int level) { unsigned int len; @@ -414,7 +414,7 @@ static int decode_numstr(bitstr_t *bs, const struct field_t *f, } /****************************************************************************/ -static int decode_octstr(bitstr_t *bs, const struct field_t *f, +static int decode_octstr(struct bitstr *bs, const struct field_t *f, char *base, int level) { unsigned int len; @@ -463,7 +463,7 @@ static int decode_octstr(bitstr_t *bs, const struct field_t *f, } /****************************************************************************/ -static int decode_bmpstr(bitstr_t *bs, const struct field_t *f, +static int decode_bmpstr(struct bitstr *bs, const struct field_t *f, char *base, int level) { unsigned int len; @@ -489,7 +489,7 @@ static int decode_bmpstr(bitstr_t *bs, const struct field_t *f, } /****************************************************************************/ -static int decode_seq(bitstr_t *bs, const struct field_t *f, +static int decode_seq(struct bitstr *bs, const struct field_t *f, char *base, int level) { unsigned int ext, bmp, i, opt, len = 0, bmp2, bmp2_len; @@ -606,7 +606,7 @@ static int decode_seq(bitstr_t *bs, const struct field_t *f, } /****************************************************************************/ -static int decode_seqof(bitstr_t *bs, const struct field_t *f, +static int decode_seqof(struct bitstr *bs, const struct field_t *f, char *base, int level) { unsigned int count, effective_count = 0, i, len = 0; @@ -696,7 +696,7 @@ static int decode_seqof(bitstr_t *bs, const struct field_t *f, /****************************************************************************/ -static int decode_choice(bitstr_t *bs, const struct field_t *f, +static int decode_choice(struct bitstr *bs, const struct field_t *f, char *base, int level) { unsigned int type, ext, len = 0; @@ -772,7 +772,7 @@ int DecodeRasMessage(unsigned char *buf, size_t sz, RasMessage *ras) FNAME("RasMessage") CHOICE, 5, 24, 32, DECODE | EXT, 0, _RasMessage }; - bitstr_t bs; + struct bitstr bs; bs.buf = bs.beg = bs.cur = buf; bs.end = buf + sz; @@ -789,7 +789,7 @@ static int DecodeH323_UserInformation(unsigned char *buf, unsigned char *beg, FNAME("H323-UserInformation") SEQ, 1, 2, 2, DECODE | EXT, 0, _H323_UserInformation }; - bitstr_t bs; + struct bitstr bs; bs.buf = buf; bs.beg = bs.cur = beg; @@ -808,7 +808,7 @@ int DecodeMultimediaSystemControlMessage(unsigned char *buf, size_t sz, FNAME("MultimediaSystemControlMessage") CHOICE, 2, 4, 4, DECODE | EXT, 0, _MultimediaSystemControlMessage }; - bitstr_t bs; + struct bitstr bs; bs.buf = bs.beg = bs.cur = buf; bs.end = buf + sz; @@ -877,6 +877,7 @@ int DecodeQ931(unsigned char *buf, size_t sz, Q931 *q931) if (sz < 1) break; len = *p++; + sz--; if (sz < len) break; p += len; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index de4053d84364..59c08997bfdf 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -533,11 +533,12 @@ nla_put_failure: return -1; } -static inline size_t ctnetlink_proto_size(const struct nf_conn *ct) +#if defined(CONFIG_NETFILTER_NETLINK_GLUE_CT) || defined(CONFIG_NF_CONNTRACK_EVENTS) +static size_t ctnetlink_proto_size(const struct nf_conn *ct) { const struct nf_conntrack_l3proto *l3proto; const struct nf_conntrack_l4proto *l4proto; - size_t len; + size_t len, len4 = 0; l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct)); len = l3proto->nla_size; @@ -545,9 +546,14 @@ static inline size_t ctnetlink_proto_size(const struct nf_conn *ct) l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); len += l4proto->nla_size; + if (l4proto->nlattr_tuple_size) { + len4 = l4proto->nlattr_tuple_size(); + len4 *= 3u; /* ORIG, REPLY, MASTER */ + } - return len; + return len + len4; } +#endif static inline size_t ctnetlink_acct_size(const struct nf_conn *ct) { diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index b3e489c859ec..c8e9c9503a08 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -27,6 +27,7 @@ #include <net/netfilter/nf_conntrack_l3proto.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_log.h> static struct nf_conntrack_l4proto __rcu **nf_ct_protos[NFPROTO_NUMPROTO] __read_mostly; struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[NFPROTO_NUMPROTO] __read_mostly; @@ -63,6 +64,52 @@ nf_ct_unregister_sysctl(struct ctl_table_header **header, *header = NULL; *table = NULL; } + +__printf(5, 6) +void nf_l4proto_log_invalid(const struct sk_buff *skb, + struct net *net, + u16 pf, u8 protonum, + const char *fmt, ...) +{ + struct va_format vaf; + va_list args; + + if (net->ct.sysctl_log_invalid != protonum || + net->ct.sysctl_log_invalid != IPPROTO_RAW) + return; + + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + + nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, + "nf_ct_proto_%d: %pV ", protonum, &vaf); + va_end(args); +} +EXPORT_SYMBOL_GPL(nf_l4proto_log_invalid); + +__printf(3, 4) +void nf_ct_l4proto_log_invalid(const struct sk_buff *skb, + const struct nf_conn *ct, + const char *fmt, ...) +{ + struct va_format vaf; + struct net *net; + va_list args; + + net = nf_ct_net(ct); + if (likely(net->ct.sysctl_log_invalid == 0)) + return; + + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + + nf_l4proto_log_invalid(skb, net, nf_ct_l3num(ct), + nf_ct_protonum(ct), "%pV", &vaf); + va_end(args); +} +EXPORT_SYMBOL_GPL(nf_ct_l4proto_log_invalid); #endif const struct nf_conntrack_l4proto * @@ -125,7 +172,7 @@ void nf_ct_l3proto_module_put(unsigned short l3proto) } EXPORT_SYMBOL_GPL(nf_ct_l3proto_module_put); -int nf_ct_netns_get(struct net *net, u8 nfproto) +static int nf_ct_netns_do_get(struct net *net, u8 nfproto) { const struct nf_conntrack_l3proto *l3proto; int ret; @@ -150,9 +197,33 @@ int nf_ct_netns_get(struct net *net, u8 nfproto) return ret; } + +int nf_ct_netns_get(struct net *net, u8 nfproto) +{ + int err; + + if (nfproto == NFPROTO_INET) { + err = nf_ct_netns_do_get(net, NFPROTO_IPV4); + if (err < 0) + goto err1; + err = nf_ct_netns_do_get(net, NFPROTO_IPV6); + if (err < 0) + goto err2; + } else { + err = nf_ct_netns_do_get(net, nfproto); + if (err < 0) + goto err1; + } + return 0; + +err2: + nf_ct_netns_put(net, NFPROTO_IPV4); +err1: + return err; +} EXPORT_SYMBOL_GPL(nf_ct_netns_get); -void nf_ct_netns_put(struct net *net, u8 nfproto) +static void nf_ct_netns_do_put(struct net *net, u8 nfproto) { const struct nf_conntrack_l3proto *l3proto; @@ -171,6 +242,15 @@ void nf_ct_netns_put(struct net *net, u8 nfproto) nf_ct_l3proto_module_put(nfproto); } + +void nf_ct_netns_put(struct net *net, uint8_t nfproto) +{ + if (nfproto == NFPROTO_INET) { + nf_ct_netns_do_put(net, NFPROTO_IPV4); + nf_ct_netns_do_put(net, NFPROTO_IPV6); + } else + nf_ct_netns_do_put(net, nfproto); +} EXPORT_SYMBOL_GPL(nf_ct_netns_put); const struct nf_conntrack_l4proto * @@ -351,8 +431,6 @@ int nf_ct_l4proto_register_one(struct nf_conntrack_l4proto *l4proto) l4proto->nla_size = 0; if (l4proto->nlattr_size) l4proto->nla_size += l4proto->nlattr_size(); - if (l4proto->nlattr_tuple_size) - l4proto->nla_size += 3 * l4proto->nlattr_tuple_size(); rcu_assign_pointer(nf_ct_protos[l4proto->l3proto][l4proto->l4proto], l4proto); diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 0f5a4d79f6b8..2a446f4a554c 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -428,13 +428,13 @@ static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb, default: dn = dccp_pernet(net); if (dn->dccp_loose == 0) { - msg = "nf_ct_dccp: not picking up existing connection "; + msg = "not picking up existing connection "; goto out_invalid; } case CT_DCCP_REQUEST: break; case CT_DCCP_INVALID: - msg = "nf_ct_dccp: invalid state transition "; + msg = "invalid state transition "; goto out_invalid; } @@ -447,9 +447,7 @@ static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb, return true; out_invalid: - if (LOG_INVALID(net, IPPROTO_DCCP)) - nf_log_packet(net, nf_ct_l3num(ct), 0, skb, NULL, NULL, - NULL, "%s", msg); + nf_ct_l4proto_log_invalid(skb, ct, "%s", msg); return false; } @@ -469,10 +467,8 @@ static unsigned int *dccp_get_timeouts(struct net *net) static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, - u_int8_t pf, unsigned int *timeouts) { - struct net *net = nf_ct_net(ct); enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); struct dccp_hdr _dh, *dh; u_int8_t type, old_state, new_state; @@ -534,15 +530,11 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb, ct->proto.dccp.last_pkt = type; spin_unlock_bh(&ct->lock); - if (LOG_INVALID(net, IPPROTO_DCCP)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_dccp: invalid packet ignored "); + nf_ct_l4proto_log_invalid(skb, ct, "%s", "invalid packet"); return NF_ACCEPT; case CT_DCCP_INVALID: spin_unlock_bh(&ct->lock); - if (LOG_INVALID(net, IPPROTO_DCCP)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_dccp: invalid state transition "); + nf_ct_l4proto_log_invalid(skb, ct, "%s", "invalid state transition"); return -NF_ACCEPT; } @@ -604,8 +596,7 @@ static int dccp_error(struct net *net, struct nf_conn *tmpl, return NF_ACCEPT; out_invalid: - if (LOG_INVALID(net, IPPROTO_DCCP)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, "%s", msg); + nf_l4proto_log_invalid(skb, net, pf, IPPROTO_DCCP, "%s", msg); return -NF_ACCEPT; } diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index 9cd40700842e..1f86ddf6649a 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -60,7 +60,6 @@ static int generic_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, - u_int8_t pf, unsigned int *timeout) { nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 09a90484c27d..a2503005d80b 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -244,7 +244,6 @@ static int gre_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, - u_int8_t pf, unsigned int *timeouts) { /* If we've seen traffic both ways, this is a GRE connection. diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 6303a88af12b..80faf04ddf15 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -306,7 +306,6 @@ static int sctp_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, - u_int8_t pf, unsigned int *timeouts) { enum sctp_conntrack new_state, old_state; @@ -522,8 +521,7 @@ static int sctp_error(struct net *net, struct nf_conn *tpl, struct sk_buff *skb, } return NF_ACCEPT; out_invalid: - if (LOG_INVALID(net, IPPROTO_SCTP)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, "%s", logmsg); + nf_l4proto_log_invalid(skb, net, pf, IPPROTO_SCTP, "%s", logmsg); return -NF_ACCEPT; } diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index cba1c6ffe51a..b12fc07111d0 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -493,8 +493,7 @@ static bool tcp_in_window(const struct nf_conn *ct, unsigned int index, const struct sk_buff *skb, unsigned int dataoff, - const struct tcphdr *tcph, - u_int8_t pf) + const struct tcphdr *tcph) { struct net *net = nf_ct_net(ct); struct nf_tcp_net *tn = tcp_pernet(net); @@ -702,9 +701,9 @@ static bool tcp_in_window(const struct nf_conn *ct, if (sender->flags & IP_CT_TCP_FLAG_BE_LIBERAL || tn->tcp_be_liberal) res = true; - if (!res && LOG_INVALID(net, IPPROTO_TCP)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_tcp: %s ", + if (!res) { + nf_ct_l4proto_log_invalid(skb, ct, + "%s", before(seq, sender->td_maxend + 1) ? in_recv_win ? before(sack, receiver->td_end + 1) ? @@ -713,6 +712,7 @@ static bool tcp_in_window(const struct nf_conn *ct, : "ACK is over the upper bound (ACKed data not seen yet)" : "SEQ is under the lower bound (already ACKed data retransmitted)" : "SEQ is over the upper bound (over the window of the receiver)"); + } } pr_debug("tcp_in_window: res=%u sender end=%u maxend=%u maxwin=%u " @@ -738,6 +738,12 @@ static const u8 tcp_valid_flags[(TCPHDR_FIN|TCPHDR_SYN|TCPHDR_RST|TCPHDR_ACK| [TCPHDR_ACK|TCPHDR_URG] = 1, }; +static void tcp_error_log(const struct sk_buff *skb, struct net *net, + u8 pf, const char *msg) +{ + nf_l4proto_log_invalid(skb, net, pf, IPPROTO_TCP, "%s", msg); +} + /* Protect conntrack agaist broken packets. Code taken from ipt_unclean.c. */ static int tcp_error(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, @@ -753,17 +759,13 @@ static int tcp_error(struct net *net, struct nf_conn *tmpl, /* Smaller that minimal TCP header? */ th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph); if (th == NULL) { - if (LOG_INVALID(net, IPPROTO_TCP)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_tcp: short packet "); + tcp_error_log(skb, net, pf, "short packet"); return -NF_ACCEPT; } /* Not whole TCP header or malformed packet */ if (th->doff*4 < sizeof(struct tcphdr) || tcplen < th->doff*4) { - if (LOG_INVALID(net, IPPROTO_TCP)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_tcp: truncated/malformed packet "); + tcp_error_log(skb, net, pf, "truncated packet"); return -NF_ACCEPT; } @@ -774,18 +776,14 @@ static int tcp_error(struct net *net, struct nf_conn *tmpl, /* FIXME: Source route IP option packets --RR */ if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING && nf_checksum(skb, hooknum, dataoff, IPPROTO_TCP, pf)) { - if (LOG_INVALID(net, IPPROTO_TCP)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_tcp: bad TCP checksum "); + tcp_error_log(skb, net, pf, "bad checksum"); return -NF_ACCEPT; } /* Check TCP flags. */ tcpflags = (tcp_flag_byte(th) & ~(TCPHDR_ECE|TCPHDR_CWR|TCPHDR_PSH)); if (!tcp_valid_flags[tcpflags]) { - if (LOG_INVALID(net, IPPROTO_TCP)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_tcp: invalid TCP flag combination "); + tcp_error_log(skb, net, pf, "invalid tcp flag combination"); return -NF_ACCEPT; } @@ -802,7 +800,6 @@ static int tcp_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, - u_int8_t pf, unsigned int *timeouts) { struct net *net = nf_ct_net(ct); @@ -939,10 +936,8 @@ static int tcp_packet(struct nf_conn *ct, IP_CT_EXP_CHALLENGE_ACK; } spin_unlock_bh(&ct->lock); - if (LOG_INVALID(net, IPPROTO_TCP)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_tcp: invalid packet ignored in " - "state %s ", tcp_conntrack_names[old_state]); + nf_ct_l4proto_log_invalid(skb, ct, "invalid packet ignored in " + "state %s ", tcp_conntrack_names[old_state]); return NF_ACCEPT; case TCP_CONNTRACK_MAX: /* Special case for SYN proxy: when the SYN to the server or @@ -964,9 +959,7 @@ static int tcp_packet(struct nf_conn *ct, pr_debug("nf_ct_tcp: Invalid dir=%i index=%u ostate=%u\n", dir, get_conntrack_index(th), old_state); spin_unlock_bh(&ct->lock); - if (LOG_INVALID(net, IPPROTO_TCP)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_tcp: invalid state "); + nf_ct_l4proto_log_invalid(skb, ct, "invalid state"); return -NF_ACCEPT; case TCP_CONNTRACK_TIME_WAIT: /* RFC5961 compliance cause stack to send "challenge-ACK" @@ -981,9 +974,7 @@ static int tcp_packet(struct nf_conn *ct, /* Detected RFC5961 challenge ACK */ ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK; spin_unlock_bh(&ct->lock); - if (LOG_INVALID(net, IPPROTO_TCP)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_tcp: challenge-ACK ignored "); + nf_ct_l4proto_log_invalid(skb, ct, "challenge-ack ignored"); return NF_ACCEPT; /* Don't change state */ } break; @@ -993,9 +984,7 @@ static int tcp_packet(struct nf_conn *ct, && before(ntohl(th->seq), ct->proto.tcp.seen[!dir].td_maxack)) { /* Invalid RST */ spin_unlock_bh(&ct->lock); - if (LOG_INVALID(net, IPPROTO_TCP)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, - NULL, "nf_ct_tcp: invalid RST "); + nf_ct_l4proto_log_invalid(skb, ct, "invalid rst"); return -NF_ACCEPT; } if (index == TCP_RST_SET @@ -1022,7 +1011,7 @@ static int tcp_packet(struct nf_conn *ct, } if (!tcp_in_window(ct, &ct->proto.tcp, dir, index, - skb, dataoff, th, pf)) { + skb, dataoff, th)) { spin_unlock_bh(&ct->lock); return -NF_ACCEPT; } @@ -1288,9 +1277,14 @@ static int tcp_nlattr_size(void) + nla_policy_len(tcp_nla_policy, CTA_PROTOINFO_TCP_MAX + 1); } -static int tcp_nlattr_tuple_size(void) +static unsigned int tcp_nlattr_tuple_size(void) { - return nla_policy_len(nf_ct_port_nla_policy, CTA_PROTO_MAX + 1); + static unsigned int size __read_mostly; + + if (!size) + size = nla_policy_len(nf_ct_port_nla_policy, CTA_PROTO_MAX + 1); + + return size; } #endif diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 8af734cd1a94..3a5f727103af 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -73,7 +73,6 @@ static int udp_packet(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, - u_int8_t pf, unsigned int *timeouts) { /* If we've seen traffic both ways, this is some kind of UDP @@ -99,6 +98,12 @@ static bool udp_new(struct nf_conn *ct, const struct sk_buff *skb, } #ifdef CONFIG_NF_CT_PROTO_UDPLITE +static void udplite_error_log(const struct sk_buff *skb, struct net *net, + u8 pf, const char *msg) +{ + nf_l4proto_log_invalid(skb, net, pf, IPPROTO_UDPLITE, "%s", msg); +} + static int udplite_error(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, @@ -112,9 +117,7 @@ static int udplite_error(struct net *net, struct nf_conn *tmpl, /* Header is too small? */ hdr = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); if (!hdr) { - if (LOG_INVALID(net, IPPROTO_UDPLITE)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_udplite: short packet "); + udplite_error_log(skb, net, pf, "short packet"); return -NF_ACCEPT; } @@ -122,17 +125,13 @@ static int udplite_error(struct net *net, struct nf_conn *tmpl, if (cscov == 0) { cscov = udplen; } else if (cscov < sizeof(*hdr) || cscov > udplen) { - if (LOG_INVALID(net, IPPROTO_UDPLITE)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_udplite: invalid checksum coverage "); + udplite_error_log(skb, net, pf, "invalid checksum coverage"); return -NF_ACCEPT; } /* UDPLITE mandates checksums */ if (!hdr->check) { - if (LOG_INVALID(net, IPPROTO_UDPLITE)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_udplite: checksum missing "); + udplite_error_log(skb, net, pf, "checksum missing"); return -NF_ACCEPT; } @@ -140,9 +139,7 @@ static int udplite_error(struct net *net, struct nf_conn *tmpl, if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING && nf_checksum_partial(skb, hooknum, dataoff, cscov, IPPROTO_UDP, pf)) { - if (LOG_INVALID(net, IPPROTO_UDPLITE)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_udplite: bad UDPLite checksum "); + udplite_error_log(skb, net, pf, "bad checksum"); return -NF_ACCEPT; } @@ -150,6 +147,12 @@ static int udplite_error(struct net *net, struct nf_conn *tmpl, } #endif +static void udp_error_log(const struct sk_buff *skb, struct net *net, + u8 pf, const char *msg) +{ + nf_l4proto_log_invalid(skb, net, pf, IPPROTO_UDP, "%s", msg); +} + static int udp_error(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, u_int8_t pf, @@ -162,17 +165,13 @@ static int udp_error(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, /* Header is too small? */ hdr = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); if (hdr == NULL) { - if (LOG_INVALID(net, IPPROTO_UDP)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_udp: short packet "); + udp_error_log(skb, net, pf, "short packet"); return -NF_ACCEPT; } /* Truncated/malformed packets */ if (ntohs(hdr->len) > udplen || ntohs(hdr->len) < sizeof(*hdr)) { - if (LOG_INVALID(net, IPPROTO_UDP)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_udp: truncated/malformed packet "); + udp_error_log(skb, net, pf, "truncated/malformed packet"); return -NF_ACCEPT; } @@ -186,9 +185,7 @@ static int udp_error(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, * FIXME: Source route IP option packets --RR */ if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING && nf_checksum(skb, hooknum, dataoff, IPPROTO_UDP, pf)) { - if (LOG_INVALID(net, IPPROTO_UDP)) - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_udp: bad UDP checksum "); + udp_error_log(skb, net, pf, "bad checksum"); return -NF_ACCEPT; } diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index af8345fc4fbd..6c38421e31f9 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -542,17 +542,14 @@ static int nf_nat_proto_clean(struct nf_conn *ct, void *data) if (nf_nat_proto_remove(ct, data)) return 1; - if ((ct->status & IPS_SRC_NAT_DONE) == 0) - return 0; - - /* This netns is being destroyed, and conntrack has nat null binding. + /* This module is being removed and conntrack has nat null binding. * Remove it from bysource hash, as the table will be freed soon. * * Else, when the conntrack is destoyed, nf_nat_cleanup_conntrack() * will delete entry from already-freed table. */ - clear_bit(IPS_SRC_NAT_DONE_BIT, &ct->status); - __nf_nat_cleanup_conntrack(ct); + if (test_and_clear_bit(IPS_SRC_NAT_DONE_BIT, &ct->status)) + __nf_nat_cleanup_conntrack(ct); /* don't delete conntrack. Although that would make things a lot * simpler, we'd end up flushing all conntracks on nat rmmod. diff --git a/net/netfilter/nf_nat_ftp.c b/net/netfilter/nf_nat_ftp.c index e84a578dbe35..d76afafdc699 100644 --- a/net/netfilter/nf_nat_ftp.c +++ b/net/netfilter/nf_nat_ftp.c @@ -134,7 +134,7 @@ static int __init nf_nat_ftp_init(void) } /* Prior to 2.6.11, we had a ports param. No longer, but don't break users. */ -static int warn_set(const char *val, struct kernel_param *kp) +static int warn_set(const char *val, const struct kernel_param *kp) { printk(KERN_INFO KBUILD_MODNAME ": kernel >= 2.6.10 only uses 'ports' for conntrack modules\n"); diff --git a/net/netfilter/nf_nat_irc.c b/net/netfilter/nf_nat_irc.c index 0648cb096bd8..dcb5f6375d9d 100644 --- a/net/netfilter/nf_nat_irc.c +++ b/net/netfilter/nf_nat_irc.c @@ -106,7 +106,7 @@ static int __init nf_nat_irc_init(void) } /* Prior to 2.6.11, we had a ports param. No longer, but don't break users. */ -static int warn_set(const char *val, struct kernel_param *kp) +static int warn_set(const char *val, const struct kernel_param *kp) { printk(KERN_INFO KBUILD_MODNAME ": kernel >= 2.6.10 only uses 'ports' for conntrack modules\n"); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 64e1ee091225..d8327b43e4dc 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2549,14 +2549,9 @@ nft_select_set_ops(const struct nft_ctx *ctx, case NFT_SET_POL_PERFORMANCE: if (est.lookup < best.lookup) break; - if (est.lookup == best.lookup) { - if (!desc->size) { - if (est.space < best.space) - break; - } else if (est.size < best.size) { - break; - } - } + if (est.lookup == best.lookup && + est.space < best.space) + break; continue; case NFT_SET_POL_MEMORY: if (!desc->size) { @@ -3593,45 +3588,6 @@ static int nf_tables_dump_set_done(struct netlink_callback *cb) return 0; } -static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack) -{ - u8 genmask = nft_genmask_cur(net); - const struct nft_set *set; - struct nft_ctx ctx; - int err; - - err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, genmask); - if (err < 0) - return err; - - set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], - genmask); - if (IS_ERR(set)) - return PTR_ERR(set); - - if (nlh->nlmsg_flags & NLM_F_DUMP) { - struct netlink_dump_control c = { - .dump = nf_tables_dump_set, - .done = nf_tables_dump_set_done, - }; - struct nft_set_dump_ctx *dump_ctx; - - dump_ctx = kmalloc(sizeof(*dump_ctx), GFP_KERNEL); - if (!dump_ctx) - return -ENOMEM; - - dump_ctx->set = set; - dump_ctx->ctx = ctx; - - c.data = dump_ctx; - return netlink_dump_start(nlsk, skb, nlh, &c); - } - return -EOPNOTSUPP; -} - static int nf_tables_fill_setelem_info(struct sk_buff *skb, const struct nft_ctx *ctx, u32 seq, u32 portid, int event, u16 flags, @@ -3677,6 +3633,135 @@ nla_put_failure: return -1; } +static int nft_setelem_parse_flags(const struct nft_set *set, + const struct nlattr *attr, u32 *flags) +{ + if (attr == NULL) + return 0; + + *flags = ntohl(nla_get_be32(attr)); + if (*flags & ~NFT_SET_ELEM_INTERVAL_END) + return -EINVAL; + if (!(set->flags & NFT_SET_INTERVAL) && + *flags & NFT_SET_ELEM_INTERVAL_END) + return -EINVAL; + + return 0; +} + +static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, + const struct nlattr *attr) +{ + struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; + const struct nft_set_ext *ext; + struct nft_data_desc desc; + struct nft_set_elem elem; + struct sk_buff *skb; + uint32_t flags = 0; + void *priv; + int err; + + err = nla_parse_nested(nla, NFTA_SET_ELEM_MAX, attr, + nft_set_elem_policy, NULL); + if (err < 0) + return err; + + if (!nla[NFTA_SET_ELEM_KEY]) + return -EINVAL; + + err = nft_setelem_parse_flags(set, nla[NFTA_SET_ELEM_FLAGS], &flags); + if (err < 0) + return err; + + err = nft_data_init(ctx, &elem.key.val, sizeof(elem.key), &desc, + nla[NFTA_SET_ELEM_KEY]); + if (err < 0) + return err; + + err = -EINVAL; + if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) + return err; + + priv = set->ops->get(ctx->net, set, &elem, flags); + if (IS_ERR(priv)) + return PTR_ERR(priv); + + elem.priv = priv; + ext = nft_set_elem_ext(set, &elem); + + err = -ENOMEM; + skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (skb == NULL) + goto err1; + + err = nf_tables_fill_setelem_info(skb, ctx, ctx->seq, ctx->portid, + NFT_MSG_NEWSETELEM, 0, set, &elem); + if (err < 0) + goto err2; + + err = nfnetlink_unicast(skb, ctx->net, ctx->portid, MSG_DONTWAIT); + /* This avoids a loop in nfnetlink. */ + if (err < 0) + goto err1; + + return 0; +err2: + kfree_skb(skb); +err1: + /* this avoids a loop in nfnetlink. */ + return err == -EAGAIN ? -ENOBUFS : err; +} + +static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, + struct sk_buff *skb, const struct nlmsghdr *nlh, + const struct nlattr * const nla[], + struct netlink_ext_ack *extack) +{ + u8 genmask = nft_genmask_cur(net); + struct nft_set *set; + struct nlattr *attr; + struct nft_ctx ctx; + int rem, err = 0; + + err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, genmask); + if (err < 0) + return err; + + set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], + genmask); + if (IS_ERR(set)) + return PTR_ERR(set); + + if (nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .dump = nf_tables_dump_set, + .done = nf_tables_dump_set_done, + }; + struct nft_set_dump_ctx *dump_ctx; + + dump_ctx = kmalloc(sizeof(*dump_ctx), GFP_KERNEL); + if (!dump_ctx) + return -ENOMEM; + + dump_ctx->set = set; + dump_ctx->ctx = ctx; + + c.data = dump_ctx; + return netlink_dump_start(nlsk, skb, nlh, &c); + } + + if (!nla[NFTA_SET_ELEM_LIST_ELEMENTS]) + return -EINVAL; + + nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { + err = nft_get_set_elem(&ctx, set, attr); + if (err < 0) + break; + } + + return err; +} + static void nf_tables_setelem_notify(const struct nft_ctx *ctx, const struct nft_set *set, const struct nft_set_elem *elem, @@ -3777,22 +3862,6 @@ static void nf_tables_set_elem_destroy(const struct nft_set *set, void *elem) kfree(elem); } -static int nft_setelem_parse_flags(const struct nft_set *set, - const struct nlattr *attr, u32 *flags) -{ - if (attr == NULL) - return 0; - - *flags = ntohl(nla_get_be32(attr)); - if (*flags & ~NFT_SET_ELEM_INTERVAL_END) - return -EINVAL; - if (!(set->flags & NFT_SET_INTERVAL) && - *flags & NFT_SET_ELEM_INTERVAL_END) - return -EINVAL; - - return 0; -} - static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr, u32 nlmsg_flags) { diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index c9796629858f..a16356cacec3 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -401,7 +401,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, outdev = entry->state.out; - switch ((enum nfqnl_config_mode)ACCESS_ONCE(queue->copy_mode)) { + switch ((enum nfqnl_config_mode)READ_ONCE(queue->copy_mode)) { case NFQNL_COPY_META: case NFQNL_COPY_NONE: break; @@ -412,7 +412,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, skb_checksum_help(entskb)) return NULL; - data_len = ACCESS_ONCE(queue->copy_range); + data_len = READ_ONCE(queue->copy_range); if (data_len > entskb->len) data_len = entskb->len; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index bd0975d7dd6f..2647b895f4b0 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -312,39 +312,6 @@ static const struct nla_policy nft_ct_policy[NFTA_CT_MAX + 1] = { [NFTA_CT_SREG] = { .type = NLA_U32 }, }; -static int nft_ct_netns_get(struct net *net, uint8_t family) -{ - int err; - - if (family == NFPROTO_INET) { - err = nf_ct_netns_get(net, NFPROTO_IPV4); - if (err < 0) - goto err1; - err = nf_ct_netns_get(net, NFPROTO_IPV6); - if (err < 0) - goto err2; - } else { - err = nf_ct_netns_get(net, family); - if (err < 0) - goto err1; - } - return 0; - -err2: - nf_ct_netns_put(net, NFPROTO_IPV4); -err1: - return err; -} - -static void nft_ct_netns_put(struct net *net, uint8_t family) -{ - if (family == NFPROTO_INET) { - nf_ct_netns_put(net, NFPROTO_IPV4); - nf_ct_netns_put(net, NFPROTO_IPV6); - } else - nf_ct_netns_put(net, family); -} - #ifdef CONFIG_NF_CONNTRACK_ZONES static void nft_ct_tmpl_put_pcpu(void) { @@ -489,7 +456,7 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, if (err < 0) return err; - err = nft_ct_netns_get(ctx->net, ctx->afi->family); + err = nf_ct_netns_get(ctx->net, ctx->afi->family); if (err < 0) return err; @@ -583,7 +550,7 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, if (err < 0) goto err1; - err = nft_ct_netns_get(ctx->net, ctx->afi->family); + err = nf_ct_netns_get(ctx->net, ctx->afi->family); if (err < 0) goto err1; @@ -606,7 +573,7 @@ static void nft_ct_set_destroy(const struct nft_ctx *ctx, struct nft_ct *priv = nft_expr_priv(expr); __nft_ct_set_destroy(ctx, priv); - nft_ct_netns_put(ctx->net, ctx->afi->family); + nf_ct_netns_put(ctx->net, ctx->afi->family); } static int nft_ct_get_dump(struct sk_buff *skb, const struct nft_expr *expr) diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 734989c40579..45fb2752fb63 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -106,6 +106,23 @@ nft_bitmap_elem_find(const struct nft_set *set, struct nft_bitmap_elem *this, return NULL; } +static void *nft_bitmap_get(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem, unsigned int flags) +{ + const struct nft_bitmap *priv = nft_set_priv(set); + u8 genmask = nft_genmask_cur(net); + struct nft_bitmap_elem *be; + + list_for_each_entry_rcu(be, &priv->list, head) { + if (memcmp(nft_set_ext_key(&be->ext), elem->key.val.data, set->klen) || + !nft_set_elem_active(&be->ext, genmask)) + continue; + + return be; + } + return ERR_PTR(-ENOENT); +} + static int nft_bitmap_insert(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, struct nft_set_ext **ext) @@ -294,6 +311,7 @@ static struct nft_set_ops nft_bitmap_ops __read_mostly = { .activate = nft_bitmap_activate, .lookup = nft_bitmap_lookup, .walk = nft_bitmap_walk, + .get = nft_bitmap_get, }; static struct nft_set_type nft_bitmap_type __read_mostly = { diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 9c0d5a7ce5f9..f8166c1d5430 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -95,6 +95,24 @@ static bool nft_rhash_lookup(const struct net *net, const struct nft_set *set, return !!he; } +static void *nft_rhash_get(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem, unsigned int flags) +{ + struct nft_rhash *priv = nft_set_priv(set); + struct nft_rhash_elem *he; + struct nft_rhash_cmp_arg arg = { + .genmask = nft_genmask_cur(net), + .set = set, + .key = elem->key.val.data, + }; + + he = rhashtable_lookup_fast(&priv->ht, &arg, nft_rhash_params); + if (he != NULL) + return he; + + return ERR_PTR(-ENOENT); +} + static bool nft_rhash_update(struct nft_set *set, const u32 *key, void *(*new)(struct nft_set *, const struct nft_expr *, @@ -409,6 +427,24 @@ static bool nft_hash_lookup(const struct net *net, const struct nft_set *set, return false; } +static void *nft_hash_get(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem, unsigned int flags) +{ + struct nft_hash *priv = nft_set_priv(set); + u8 genmask = nft_genmask_cur(net); + struct nft_hash_elem *he; + u32 hash; + + hash = jhash(elem->key.val.data, set->klen, priv->seed); + hash = reciprocal_scale(hash, priv->buckets); + hlist_for_each_entry_rcu(he, &priv->table[hash], node) { + if (!memcmp(nft_set_ext_key(&he->ext), elem->key.val.data, set->klen) && + nft_set_elem_active(&he->ext, genmask)) + return he; + } + return ERR_PTR(-ENOENT); +} + /* nft_hash_select_ops() makes sure key size can be either 2 or 4 bytes . */ static inline u32 nft_hash_key(const u32 *key, u32 klen) { @@ -494,7 +530,7 @@ static void *nft_hash_deactivate(const struct net *net, hash = reciprocal_scale(hash, priv->buckets); hlist_for_each_entry(he, &priv->table[hash], node) { if (!memcmp(nft_set_ext_key(&this->ext), &elem->key.val, - set->klen) || + set->klen) && nft_set_elem_active(&he->ext, genmask)) { nft_set_elem_change_active(net, set, &he->ext); return he; @@ -600,6 +636,7 @@ static struct nft_set_ops nft_rhash_ops __read_mostly = { .lookup = nft_rhash_lookup, .update = nft_rhash_update, .walk = nft_rhash_walk, + .get = nft_rhash_get, .features = NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, }; @@ -617,6 +654,7 @@ static struct nft_set_ops nft_hash_ops __read_mostly = { .remove = nft_hash_remove, .lookup = nft_hash_lookup, .walk = nft_hash_walk, + .get = nft_hash_get, .features = NFT_SET_MAP | NFT_SET_OBJECT, }; @@ -634,6 +672,7 @@ static struct nft_set_ops nft_hash_fast_ops __read_mostly = { .remove = nft_hash_remove, .lookup = nft_hash_lookup_fast, .walk = nft_hash_walk, + .get = nft_hash_get, .features = NFT_SET_MAP | NFT_SET_OBJECT, }; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index d83a4ec5900d..e6f08bc5f359 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -113,6 +113,78 @@ static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, return ret; } +static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, + const u32 *key, struct nft_rbtree_elem **elem, + unsigned int seq, unsigned int flags, u8 genmask) +{ + struct nft_rbtree_elem *rbe, *interval = NULL; + struct nft_rbtree *priv = nft_set_priv(set); + const struct rb_node *parent; + const void *this; + int d; + + parent = rcu_dereference_raw(priv->root.rb_node); + while (parent != NULL) { + if (read_seqcount_retry(&priv->count, seq)) + return false; + + rbe = rb_entry(parent, struct nft_rbtree_elem, node); + + this = nft_set_ext_key(&rbe->ext); + d = memcmp(this, key, set->klen); + if (d < 0) { + parent = rcu_dereference_raw(parent->rb_left); + interval = rbe; + } else if (d > 0) { + parent = rcu_dereference_raw(parent->rb_right); + } else { + if (!nft_set_elem_active(&rbe->ext, genmask)) + parent = rcu_dereference_raw(parent->rb_left); + + if (!nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) || + (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END) == + (flags & NFT_SET_ELEM_INTERVAL_END)) { + *elem = rbe; + return true; + } + return false; + } + } + + if (set->flags & NFT_SET_INTERVAL && interval != NULL && + nft_set_elem_active(&interval->ext, genmask) && + !nft_rbtree_interval_end(interval)) { + *elem = interval; + return true; + } + + return false; +} + +static void *nft_rbtree_get(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem, unsigned int flags) +{ + struct nft_rbtree *priv = nft_set_priv(set); + unsigned int seq = read_seqcount_begin(&priv->count); + struct nft_rbtree_elem *rbe = ERR_PTR(-ENOENT); + const u32 *key = (const u32 *)&elem->key.val; + u8 genmask = nft_genmask_cur(net); + bool ret; + + ret = __nft_rbtree_get(net, set, key, &rbe, seq, flags, genmask); + if (ret || !read_seqcount_retry(&priv->count, seq)) + return rbe; + + read_lock_bh(&priv->lock); + seq = read_seqcount_begin(&priv->count); + ret = __nft_rbtree_get(net, set, key, &rbe, seq, flags, genmask); + if (!ret) + rbe = ERR_PTR(-ENOENT); + read_unlock_bh(&priv->lock); + + return rbe; +} + static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree_elem *new, struct nft_set_ext **ext) @@ -336,6 +408,7 @@ static struct nft_set_ops nft_rbtree_ops __read_mostly = { .activate = nft_rbtree_activate, .lookup = nft_rbtree_lookup, .walk = nft_rbtree_walk, + .get = nft_rbtree_get, .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT, }; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index d8571f414208..a77dd514297c 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1153,6 +1153,7 @@ xt_replace_table(struct xt_table *table, int *error) { struct xt_table_info *private; + unsigned int cpu; int ret; ret = xt_jumpstack_alloc(newinfo); @@ -1182,14 +1183,28 @@ xt_replace_table(struct xt_table *table, smp_wmb(); table->private = newinfo; + /* make sure all cpus see new ->private value */ + smp_wmb(); + /* * Even though table entries have now been swapped, other CPU's - * may still be using the old entries. This is okay, because - * resynchronization happens because of the locking done - * during the get_counters() routine. + * may still be using the old entries... */ local_bh_enable(); + /* ... so wait for even xt_recseq on all cpus */ + for_each_possible_cpu(cpu) { + seqcount_t *s = &per_cpu(xt_recseq, cpu); + u32 seq = raw_read_seqcount(s); + + if (seq & 1) { + do { + cond_resched(); + cpu_relax(); + } while (seq == raw_read_seqcount(s)); + } + } + #ifdef CONFIG_AUDIT if (audit_enabled) { audit_log(current->audit_context, GFP_KERNEL, diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c index 29123934887b..041da0d9c06f 100644 --- a/net/netfilter/xt_bpf.c +++ b/net/netfilter/xt_bpf.c @@ -56,7 +56,7 @@ static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret) int retval, fd; set_fs(KERNEL_DS); - fd = bpf_obj_get_user(path); + fd = bpf_obj_get_user(path, 0); set_fs(oldfs); if (fd < 0) return fd; diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index ffa8eec980e9..a6214f235333 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -46,7 +46,6 @@ struct xt_connlimit_conn { struct hlist_node node; struct nf_conntrack_tuple tuple; - union nf_inet_addr addr; }; struct xt_connlimit_rb { @@ -72,16 +71,9 @@ static inline unsigned int connlimit_iphash(__be32 addr) } static inline unsigned int -connlimit_iphash6(const union nf_inet_addr *addr, - const union nf_inet_addr *mask) +connlimit_iphash6(const union nf_inet_addr *addr) { - union nf_inet_addr res; - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(addr->ip6); ++i) - res.ip6[i] = addr->ip6[i] & mask->ip6[i]; - - return jhash2((u32 *)res.ip6, ARRAY_SIZE(res.ip6), + return jhash2((u32 *)addr->ip6, ARRAY_SIZE(addr->ip6), connlimit_rnd) % CONNLIMIT_SLOTS; } @@ -95,24 +87,13 @@ static inline bool already_closed(const struct nf_conn *conn) } static int -same_source_net(const union nf_inet_addr *addr, - const union nf_inet_addr *mask, - const union nf_inet_addr *u3, u_int8_t family) +same_source(const union nf_inet_addr *addr, + const union nf_inet_addr *u3, u_int8_t family) { - if (family == NFPROTO_IPV4) { - return ntohl(addr->ip & mask->ip) - - ntohl(u3->ip & mask->ip); - } else { - union nf_inet_addr lh, rh; - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(addr->ip6); ++i) { - lh.ip6[i] = addr->ip6[i] & mask->ip6[i]; - rh.ip6[i] = u3->ip6[i] & mask->ip6[i]; - } + if (family == NFPROTO_IPV4) + return ntohl(addr->ip) - ntohl(u3->ip); - return memcmp(&lh.ip6, &rh.ip6, sizeof(lh.ip6)); - } + return memcmp(addr->ip6, u3->ip6, sizeof(addr->ip6)); } static bool add_hlist(struct hlist_head *head, @@ -125,7 +106,6 @@ static bool add_hlist(struct hlist_head *head, if (conn == NULL) return false; conn->tuple = *tuple; - conn->addr = *addr; hlist_add_head(&conn->node, head); return true; } @@ -196,7 +176,7 @@ static void tree_nodes_free(struct rb_root *root, static unsigned int count_tree(struct net *net, struct rb_root *root, const struct nf_conntrack_tuple *tuple, - const union nf_inet_addr *addr, const union nf_inet_addr *mask, + const union nf_inet_addr *addr, u8 family, const struct nf_conntrack_zone *zone) { struct xt_connlimit_rb *gc_nodes[CONNLIMIT_GC_MAX_NODES]; @@ -217,7 +197,7 @@ count_tree(struct net *net, struct rb_root *root, rbconn = rb_entry(*rbnode, struct xt_connlimit_rb, node); parent = *rbnode; - diff = same_source_net(addr, mask, &rbconn->addr, family); + diff = same_source(addr, &rbconn->addr, family); if (diff < 0) { rbnode = &((*rbnode)->rb_left); } else if (diff > 0) { @@ -270,7 +250,6 @@ count_tree(struct net *net, struct rb_root *root, } conn->tuple = *tuple; - conn->addr = *addr; rbconn->addr = *addr; INIT_HLIST_HEAD(&rbconn->hhead); @@ -285,7 +264,6 @@ static int count_them(struct net *net, struct xt_connlimit_data *data, const struct nf_conntrack_tuple *tuple, const union nf_inet_addr *addr, - const union nf_inet_addr *mask, u_int8_t family, const struct nf_conntrack_zone *zone) { @@ -294,14 +272,14 @@ static int count_them(struct net *net, u32 hash; if (family == NFPROTO_IPV6) - hash = connlimit_iphash6(addr, mask); + hash = connlimit_iphash6(addr); else - hash = connlimit_iphash(addr->ip & mask->ip); + hash = connlimit_iphash(addr->ip); root = &data->climit_root[hash]; spin_lock_bh(&xt_connlimit_locks[hash % CONNLIMIT_LOCK_SLOTS]); - count = count_tree(net, root, tuple, addr, mask, family, zone); + count = count_tree(net, root, tuple, addr, family, zone); spin_unlock_bh(&xt_connlimit_locks[hash % CONNLIMIT_LOCK_SLOTS]); @@ -332,16 +310,23 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) if (xt_family(par) == NFPROTO_IPV6) { const struct ipv6hdr *iph = ipv6_hdr(skb); + unsigned int i; + memcpy(&addr.ip6, (info->flags & XT_CONNLIMIT_DADDR) ? &iph->daddr : &iph->saddr, sizeof(addr.ip6)); + + for (i = 0; i < ARRAY_SIZE(addr.ip6); ++i) + addr.ip6[i] &= info->mask.ip6[i]; } else { const struct iphdr *iph = ip_hdr(skb); addr.ip = (info->flags & XT_CONNLIMIT_DADDR) ? iph->daddr : iph->saddr; + + addr.ip &= info->mask.ip; } connections = count_them(net, info->data, tuple_ptr, &addr, - &info->mask, xt_family(par), zone); + xt_family(par), zone); if (connections == 0) /* kmalloc failed, drop it entirely */ goto hotdrop; diff --git a/net/netlabel/netlabel_addrlist.h b/net/netlabel/netlabel_addrlist.h index d0f38bc9af6d..ac709f0f197b 100644 --- a/net/netlabel/netlabel_addrlist.h +++ b/net/netlabel/netlabel_addrlist.h @@ -87,7 +87,7 @@ static inline struct netlbl_af4list *__af4list_valid_rcu(struct list_head *s, struct list_head *i = s; struct netlbl_af4list *n = __af4list_entry(s); while (i != h && !n->valid) { - i = rcu_dereference(i->next); + i = rcu_dereference(list_next_rcu(i)); n = __af4list_entry(i); } return n; @@ -154,7 +154,7 @@ static inline struct netlbl_af6list *__af6list_valid_rcu(struct list_head *s, struct list_head *i = s; struct netlbl_af6list *n = __af6list_entry(s); while (i != h && !n->valid) { - i = rcu_dereference(i->next); + i = rcu_dereference(list_next_rcu(i)); n = __af6list_entry(i); } return n; diff --git a/net/netlabel/netlabel_calipso.c b/net/netlabel/netlabel_calipso.c index d177dd066504..4d748975117d 100644 --- a/net/netlabel/netlabel_calipso.c +++ b/net/netlabel/netlabel_calipso.c @@ -393,7 +393,7 @@ EXPORT_SYMBOL(netlbl_calipso_ops_register); static const struct netlbl_calipso_ops *netlbl_calipso_ops_get(void) { - return ACCESS_ONCE(calipso_ops); + return READ_ONCE(calipso_ops); } /** diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index b93148e8e9fb..b9e0ee4e22f5 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -128,7 +128,6 @@ static const char *const nlk_cb_mutex_key_strings[MAX_LINKS + 1] = { }; static int netlink_dump(struct sock *sk); -static void netlink_skb_destructor(struct sk_buff *skb); /* nl_table locking explained: * Lookup and traversal are protected with an RCU read-side lock. Insertion @@ -2136,7 +2135,7 @@ static int netlink_dump(struct sock *sk) struct sk_buff *skb = NULL; struct nlmsghdr *nlh; struct module *module; - int len, err = -ENOBUFS; + int err = -ENOBUFS; int alloc_min_size; int alloc_size; @@ -2183,9 +2182,11 @@ static int netlink_dump(struct sock *sk) skb_reserve(skb, skb_tailroom(skb) - alloc_size); netlink_skb_set_owner_r(skb, sk); - len = cb->dump(skb, cb); + if (nlk->dump_done_errno > 0) + nlk->dump_done_errno = cb->dump(skb, cb); - if (len > 0) { + if (nlk->dump_done_errno > 0 || + skb_tailroom(skb) < nlmsg_total_size(sizeof(nlk->dump_done_errno))) { mutex_unlock(nlk->cb_mutex); if (sk_filter(sk, skb)) @@ -2195,13 +2196,15 @@ static int netlink_dump(struct sock *sk) return 0; } - nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(len), NLM_F_MULTI); - if (!nlh) + nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, + sizeof(nlk->dump_done_errno), NLM_F_MULTI); + if (WARN_ON(!nlh)) goto errout_skb; nl_dump_check_consistent(cb, nlh); - memcpy(nlmsg_data(nlh), &len, sizeof(len)); + memcpy(nlmsg_data(nlh), &nlk->dump_done_errno, + sizeof(nlk->dump_done_errno)); if (sk_filter(sk, skb)) kfree_skb(skb); @@ -2273,6 +2276,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, } nlk->cb_running = true; + nlk->dump_done_errno = INT_MAX; mutex_unlock(nlk->cb_mutex); @@ -2313,17 +2317,16 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, * requests to cap the error message, and get extra error data if * requested. */ + if (nlk_has_extack && extack && extack->_msg) + tlvlen += nla_total_size(strlen(extack->_msg) + 1); + if (err) { if (!(nlk->flags & NETLINK_F_CAP_ACK)) payload += nlmsg_len(nlh); else flags |= NLM_F_CAPPED; - if (nlk_has_extack && extack) { - if (extack->_msg) - tlvlen += nla_total_size(strlen(extack->_msg) + 1); - if (extack->bad_attr) - tlvlen += nla_total_size(sizeof(u32)); - } + if (nlk_has_extack && extack && extack->bad_attr) + tlvlen += nla_total_size(sizeof(u32)); } else { flags |= NLM_F_CAPPED; @@ -2336,16 +2339,8 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, skb = nlmsg_new(payload + tlvlen, GFP_KERNEL); if (!skb) { - struct sock *sk; - - sk = netlink_lookup(sock_net(in_skb->sk), - in_skb->sk->sk_protocol, - NETLINK_CB(in_skb).portid); - if (sk) { - sk->sk_err = ENOBUFS; - sk->sk_error_report(sk); - sock_put(sk); - } + NETLINK_CB(in_skb).sk->sk_err = ENOBUFS; + NETLINK_CB(in_skb).sk->sk_error_report(NETLINK_CB(in_skb).sk); return; } @@ -2356,10 +2351,11 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, memcpy(&errmsg->msg, nlh, payload > sizeof(*errmsg) ? nlh->nlmsg_len : sizeof(*nlh)); if (nlk_has_extack && extack) { + if (extack->_msg) { + WARN_ON(nla_put_string(skb, NLMSGERR_ATTR_MSG, + extack->_msg)); + } if (err) { - if (extack->_msg) - WARN_ON(nla_put_string(skb, NLMSGERR_ATTR_MSG, - extack->_msg)); if (extack->bad_attr && !WARN_ON((u8 *)extack->bad_attr < in_skb->data || (u8 *)extack->bad_attr >= in_skb->data + diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index 028188597eaa..962de7b3c023 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -34,6 +34,7 @@ struct netlink_sock { wait_queue_head_t wait; bool bound; bool cb_running; + int dump_done_errno; struct netlink_callback cb; struct mutex *cb_mutex; struct mutex cb_def_mutex; diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index ebf16f7f9089..2dec3583c97d 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -241,9 +241,9 @@ void nr_destroy_socket(struct sock *); /* * Handler for deferred kills. */ -static void nr_destroy_timer(unsigned long data) +static void nr_destroy_timer(struct timer_list *t) { - struct sock *sk=(struct sock *)data; + struct sock *sk = from_timer(sk, t, sk_timer); bh_lock_sock(sk); sock_hold(sk); nr_destroy_socket(sk); @@ -284,7 +284,7 @@ void nr_destroy_socket(struct sock *sk) if (sk_has_allocations(sk)) { /* Defer: outstanding buffers */ - sk->sk_timer.function = nr_destroy_timer; + sk->sk_timer.function = (TIMER_FUNC_TYPE)nr_destroy_timer; sk->sk_timer.expires = jiffies + 2 * HZ; add_timer(&sk->sk_timer); } else diff --git a/net/netrom/nr_in.c b/net/netrom/nr_in.c index 80dbd0beb516..fbfdae452ff9 100644 --- a/net/netrom/nr_in.c +++ b/net/netrom/nr_in.c @@ -125,7 +125,7 @@ static int nr_state2_machine(struct sock *sk, struct sk_buff *skb, case NR_DISCREQ: nr_write_internal(sk, NR_DISCACK); - + /* fall through */ case NR_DISCACK: nr_disconnect(sk, 0); break; diff --git a/net/netrom/nr_loopback.c b/net/netrom/nr_loopback.c index 94d4e922af53..989ae647825e 100644 --- a/net/netrom/nr_loopback.c +++ b/net/netrom/nr_loopback.c @@ -18,7 +18,7 @@ static void nr_loopback_timer(unsigned long); static struct sk_buff_head loopback_queue; -static DEFINE_TIMER(loopback_timer, nr_loopback_timer, 0, 0); +static DEFINE_TIMER(loopback_timer, nr_loopback_timer); void __init nr_loopback_init(void) { diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index 0c59354e280e..75e6ba970fde 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -80,6 +80,19 @@ static struct nr_neigh *nr_neigh_get_dev(ax25_address *callsign, static void nr_remove_neigh(struct nr_neigh *); +/* re-sort the routes in quality order. */ +static void re_sort_routes(struct nr_node *nr_node, int x, int y) +{ + if (nr_node->routes[y].quality > nr_node->routes[x].quality) { + if (nr_node->which == x) + nr_node->which = y; + else if (nr_node->which == y) + nr_node->which = x; + + swap(nr_node->routes[x], nr_node->routes[y]); + } +} + /* * Add a new route to a node, and in the process add the node and the * neighbour if it is new. @@ -90,7 +103,6 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic, { struct nr_node *nr_node; struct nr_neigh *nr_neigh; - struct nr_route nr_route; int i, found; struct net_device *odev; @@ -251,49 +263,11 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic, /* Now re-sort the routes in quality order */ switch (nr_node->count) { case 3: - if (nr_node->routes[1].quality > nr_node->routes[0].quality) { - switch (nr_node->which) { - case 0: - nr_node->which = 1; - break; - case 1: - nr_node->which = 0; - break; - } - nr_route = nr_node->routes[0]; - nr_node->routes[0] = nr_node->routes[1]; - nr_node->routes[1] = nr_route; - } - if (nr_node->routes[2].quality > nr_node->routes[1].quality) { - switch (nr_node->which) { - case 1: nr_node->which = 2; - break; - - case 2: nr_node->which = 1; - break; - - default: - break; - } - nr_route = nr_node->routes[1]; - nr_node->routes[1] = nr_node->routes[2]; - nr_node->routes[2] = nr_route; - } + re_sort_routes(nr_node, 0, 1); + re_sort_routes(nr_node, 1, 2); + /* fall through */ case 2: - if (nr_node->routes[1].quality > nr_node->routes[0].quality) { - switch (nr_node->which) { - case 0: nr_node->which = 1; - break; - - case 1: nr_node->which = 0; - break; - - default: break; - } - nr_route = nr_node->routes[0]; - nr_node->routes[0] = nr_node->routes[1]; - nr_node->routes[1] = nr_route; - } + re_sort_routes(nr_node, 0, 1); case 1: break; } @@ -384,6 +358,7 @@ static int nr_del_node(ax25_address *callsign, ax25_address *neighbour, struct n switch (i) { case 0: nr_node->routes[0] = nr_node->routes[1]; + /* fall through */ case 1: nr_node->routes[1] = nr_node->routes[2]; case 2: @@ -553,6 +528,7 @@ void nr_rt_device_down(struct net_device *dev) switch (i) { case 0: t->routes[0] = t->routes[1]; + /* fall through */ case 1: t->routes[1] = t->routes[2]; case 2: diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c index 94d05806a9a2..43569aea0f5e 100644 --- a/net/netrom/nr_timer.c +++ b/net/netrom/nr_timer.c @@ -29,24 +29,23 @@ #include <linux/interrupt.h> #include <net/netrom.h> -static void nr_heartbeat_expiry(unsigned long); -static void nr_t1timer_expiry(unsigned long); -static void nr_t2timer_expiry(unsigned long); -static void nr_t4timer_expiry(unsigned long); -static void nr_idletimer_expiry(unsigned long); +static void nr_heartbeat_expiry(struct timer_list *); +static void nr_t1timer_expiry(struct timer_list *); +static void nr_t2timer_expiry(struct timer_list *); +static void nr_t4timer_expiry(struct timer_list *); +static void nr_idletimer_expiry(struct timer_list *); void nr_init_timers(struct sock *sk) { struct nr_sock *nr = nr_sk(sk); - setup_timer(&nr->t1timer, nr_t1timer_expiry, (unsigned long)sk); - setup_timer(&nr->t2timer, nr_t2timer_expiry, (unsigned long)sk); - setup_timer(&nr->t4timer, nr_t4timer_expiry, (unsigned long)sk); - setup_timer(&nr->idletimer, nr_idletimer_expiry, (unsigned long)sk); + timer_setup(&nr->t1timer, nr_t1timer_expiry, 0); + timer_setup(&nr->t2timer, nr_t2timer_expiry, 0); + timer_setup(&nr->t4timer, nr_t4timer_expiry, 0); + timer_setup(&nr->idletimer, nr_idletimer_expiry, 0); /* initialized by sock_init_data */ - sk->sk_timer.data = (unsigned long)sk; - sk->sk_timer.function = &nr_heartbeat_expiry; + sk->sk_timer.function = (TIMER_FUNC_TYPE)nr_heartbeat_expiry; } void nr_start_t1timer(struct sock *sk) @@ -113,9 +112,9 @@ int nr_t1timer_running(struct sock *sk) return timer_pending(&nr_sk(sk)->t1timer); } -static void nr_heartbeat_expiry(unsigned long param) +static void nr_heartbeat_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; + struct sock *sk = from_timer(sk, t, sk_timer); struct nr_sock *nr = nr_sk(sk); bh_lock_sock(sk); @@ -152,10 +151,10 @@ static void nr_heartbeat_expiry(unsigned long param) bh_unlock_sock(sk); } -static void nr_t2timer_expiry(unsigned long param) +static void nr_t2timer_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; - struct nr_sock *nr = nr_sk(sk); + struct nr_sock *nr = from_timer(nr, t, t2timer); + struct sock *sk = &nr->sock; bh_lock_sock(sk); if (nr->condition & NR_COND_ACK_PENDING) { @@ -165,19 +164,20 @@ static void nr_t2timer_expiry(unsigned long param) bh_unlock_sock(sk); } -static void nr_t4timer_expiry(unsigned long param) +static void nr_t4timer_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; + struct nr_sock *nr = from_timer(nr, t, t4timer); + struct sock *sk = &nr->sock; bh_lock_sock(sk); nr_sk(sk)->condition &= ~NR_COND_PEER_RX_BUSY; bh_unlock_sock(sk); } -static void nr_idletimer_expiry(unsigned long param) +static void nr_idletimer_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; - struct nr_sock *nr = nr_sk(sk); + struct nr_sock *nr = from_timer(nr, t, idletimer); + struct sock *sk = &nr->sock; bh_lock_sock(sk); @@ -202,10 +202,10 @@ static void nr_idletimer_expiry(unsigned long param) bh_unlock_sock(sk); } -static void nr_t1timer_expiry(unsigned long param) +static void nr_t1timer_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; - struct nr_sock *nr = nr_sk(sk); + struct nr_sock *nr = from_timer(nr, t, t1timer); + struct sock *sk = &nr->sock; bh_lock_sock(sk); switch (nr->state) { diff --git a/net/nfc/core.c b/net/nfc/core.c index 5cf33df888c3..947a470f929d 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -1015,9 +1015,9 @@ exit: device_unlock(&dev->dev); } -static void nfc_check_pres_timeout(unsigned long data) +static void nfc_check_pres_timeout(struct timer_list *t) { - struct nfc_dev *dev = (struct nfc_dev *)data; + struct nfc_dev *dev = from_timer(dev, t, check_pres_timer); schedule_work(&dev->check_pres_work); } @@ -1094,10 +1094,7 @@ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, dev->targets_generation = 1; if (ops->check_presence) { - init_timer(&dev->check_pres_timer); - dev->check_pres_timer.data = (unsigned long)dev; - dev->check_pres_timer.function = nfc_check_pres_timeout; - + timer_setup(&dev->check_pres_timer, nfc_check_pres_timeout, 0); INIT_WORK(&dev->check_pres_work, nfc_check_pres_work); } @@ -1106,7 +1103,7 @@ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, err_free_dev: kfree(dev); - return ERR_PTR(rc); + return NULL; } EXPORT_SYMBOL(nfc_allocate_device); diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c index de6dd37d04c7..ec0a8998e52d 100644 --- a/net/nfc/digital_core.c +++ b/net/nfc/digital_core.c @@ -650,6 +650,7 @@ static void digital_deactivate_target(struct nfc_dev *nfc_dev, return; } + digital_abort_cmd(ddev); ddev->curr_protocol = 0; } diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c index b740fef0acc5..ac8030c4bcf8 100644 --- a/net/nfc/hci/core.c +++ b/net/nfc/hci/core.c @@ -428,9 +428,9 @@ exit_noskb: nfc_hci_driver_failure(hdev, r); } -static void nfc_hci_cmd_timeout(unsigned long data) +static void nfc_hci_cmd_timeout(struct timer_list *t) { - struct nfc_hci_dev *hdev = (struct nfc_hci_dev *)data; + struct nfc_hci_dev *hdev = from_timer(hdev, t, cmd_timer); schedule_work(&hdev->msg_tx_work); } @@ -1004,9 +1004,7 @@ int nfc_hci_register_device(struct nfc_hci_dev *hdev) INIT_WORK(&hdev->msg_tx_work, nfc_hci_msg_tx_work); - init_timer(&hdev->cmd_timer); - hdev->cmd_timer.data = (unsigned long)hdev; - hdev->cmd_timer.function = nfc_hci_cmd_timeout; + timer_setup(&hdev->cmd_timer, nfc_hci_cmd_timeout, 0); skb_queue_head_init(&hdev->rx_hcp_frags); diff --git a/net/nfc/hci/llc_shdlc.c b/net/nfc/hci/llc_shdlc.c index 17e59a009ce6..fe988936ad92 100644 --- a/net/nfc/hci/llc_shdlc.c +++ b/net/nfc/hci/llc_shdlc.c @@ -580,27 +580,27 @@ static void llc_shdlc_handle_send_queue(struct llc_shdlc *shdlc) } } -static void llc_shdlc_connect_timeout(unsigned long data) +static void llc_shdlc_connect_timeout(struct timer_list *t) { - struct llc_shdlc *shdlc = (struct llc_shdlc *)data; + struct llc_shdlc *shdlc = from_timer(shdlc, t, connect_timer); pr_debug("\n"); schedule_work(&shdlc->sm_work); } -static void llc_shdlc_t1_timeout(unsigned long data) +static void llc_shdlc_t1_timeout(struct timer_list *t) { - struct llc_shdlc *shdlc = (struct llc_shdlc *)data; + struct llc_shdlc *shdlc = from_timer(shdlc, t, t1_timer); pr_debug("SoftIRQ: need to send ack\n"); schedule_work(&shdlc->sm_work); } -static void llc_shdlc_t2_timeout(unsigned long data) +static void llc_shdlc_t2_timeout(struct timer_list *t) { - struct llc_shdlc *shdlc = (struct llc_shdlc *)data; + struct llc_shdlc *shdlc = from_timer(shdlc, t, t2_timer); pr_debug("SoftIRQ: need to retransmit\n"); @@ -763,17 +763,9 @@ static void *llc_shdlc_init(struct nfc_hci_dev *hdev, xmit_to_drv_t xmit_to_drv, mutex_init(&shdlc->state_mutex); shdlc->state = SHDLC_DISCONNECTED; - init_timer(&shdlc->connect_timer); - shdlc->connect_timer.data = (unsigned long)shdlc; - shdlc->connect_timer.function = llc_shdlc_connect_timeout; - - init_timer(&shdlc->t1_timer); - shdlc->t1_timer.data = (unsigned long)shdlc; - shdlc->t1_timer.function = llc_shdlc_t1_timeout; - - init_timer(&shdlc->t2_timer); - shdlc->t2_timer.data = (unsigned long)shdlc; - shdlc->t2_timer.function = llc_shdlc_t2_timeout; + timer_setup(&shdlc->connect_timer, llc_shdlc_connect_timeout, 0); + timer_setup(&shdlc->t1_timer, llc_shdlc_t1_timeout, 0); + timer_setup(&shdlc->t2_timer, llc_shdlc_t2_timeout, 0); shdlc->w = SHDLC_MAX_WINDOW; shdlc->srej_support = SHDLC_SREJ_SUPPORT; diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index 02eef5cf3cce..ef4026a23e80 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -242,9 +242,9 @@ static void nfc_llcp_timeout_work(struct work_struct *work) nfc_dep_link_down(local->dev); } -static void nfc_llcp_symm_timer(unsigned long data) +static void nfc_llcp_symm_timer(struct timer_list *t) { - struct nfc_llcp_local *local = (struct nfc_llcp_local *) data; + struct nfc_llcp_local *local = from_timer(local, t, link_timer); pr_err("SYMM timeout\n"); @@ -285,9 +285,9 @@ static void nfc_llcp_sdreq_timeout_work(struct work_struct *work) nfc_genl_llc_send_sdres(local->dev, &nl_sdres_list); } -static void nfc_llcp_sdreq_timer(unsigned long data) +static void nfc_llcp_sdreq_timer(struct timer_list *t) { - struct nfc_llcp_local *local = (struct nfc_llcp_local *) data; + struct nfc_llcp_local *local = from_timer(local, t, sdreq_timer); schedule_work(&local->sdreq_timeout_work); } @@ -1573,9 +1573,7 @@ int nfc_llcp_register_device(struct nfc_dev *ndev) INIT_LIST_HEAD(&local->list); kref_init(&local->ref); mutex_init(&local->sdp_lock); - init_timer(&local->link_timer); - local->link_timer.data = (unsigned long) local; - local->link_timer.function = nfc_llcp_symm_timer; + timer_setup(&local->link_timer, nfc_llcp_symm_timer, 0); skb_queue_head_init(&local->tx_queue); INIT_WORK(&local->tx_work, nfc_llcp_tx_work); @@ -1601,9 +1599,7 @@ int nfc_llcp_register_device(struct nfc_dev *ndev) mutex_init(&local->sdreq_lock); INIT_HLIST_HEAD(&local->pending_sdreqs); - init_timer(&local->sdreq_timer); - local->sdreq_timer.data = (unsigned long) local; - local->sdreq_timer.function = nfc_llcp_sdreq_timer; + timer_setup(&local->sdreq_timer, nfc_llcp_sdreq_timer, 0); INIT_WORK(&local->sdreq_timeout_work, nfc_llcp_sdreq_timeout_work); list_add(&local->list, &llcp_devices); diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index b251fb936a27..c0b83dc9d993 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -75,7 +75,7 @@ static int nfc_genl_send_target(struct sk_buff *msg, struct nfc_target *target, if (!hdr) return -EMSGSIZE; - genl_dump_check_consistent(cb, hdr, &nfc_genl_family); + genl_dump_check_consistent(cb, hdr); if (nla_put_u32(msg, NFC_ATTR_TARGET_INDEX, target->idx) || nla_put_u32(msg, NFC_ATTR_PROTOCOLS, target->supported_protocols) || @@ -603,7 +603,7 @@ static int nfc_genl_send_device(struct sk_buff *msg, struct nfc_dev *dev, return -EMSGSIZE; if (cb) - genl_dump_check_consistent(cb, hdr, &nfc_genl_family); + genl_dump_check_consistent(cb, hdr); if (nfc_genl_setup_device_added(dev, msg)) goto nla_put_failure; @@ -928,6 +928,30 @@ static int nfc_genl_activate_target(struct sk_buff *skb, struct genl_info *info) return rc; } +static int nfc_genl_deactivate_target(struct sk_buff *skb, + struct genl_info *info) +{ + struct nfc_dev *dev; + u32 device_idx, target_idx; + int rc; + + if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) + return -EINVAL; + + device_idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); + + dev = nfc_get_device(device_idx); + if (!dev) + return -ENODEV; + + target_idx = nla_get_u32(info->attrs[NFC_ATTR_TARGET_INDEX]); + + rc = nfc_deactivate_target(dev, target_idx, NFC_TARGET_MODE_SLEEP); + + nfc_put_device(dev); + return rc; +} + static int nfc_genl_dep_link_up(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; @@ -1332,7 +1356,7 @@ static int nfc_genl_send_se(struct sk_buff *msg, struct nfc_dev *dev, goto nla_put_failure; if (cb) - genl_dump_check_consistent(cb, hdr, &nfc_genl_family); + genl_dump_check_consistent(cb, hdr); if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) || nla_put_u32(msg, NFC_ATTR_SE_INDEX, se->idx) || @@ -1751,6 +1775,11 @@ static const struct genl_ops nfc_genl_ops[] = { .doit = nfc_genl_vendor_cmd, .policy = nfc_genl_policy, }, + { + .cmd = NFC_CMD_DEACTIVATE_TARGET, + .doit = nfc_genl_deactivate_target, + .policy = nfc_genl_policy, + }, }; static struct genl_family nfc_genl_family __ro_after_init = { diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c index 58fb827439a8..d7da99a0b0b8 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -14,6 +14,66 @@ #include <net/nsh.h> #include <net/tun_proto.h> +int nsh_push(struct sk_buff *skb, const struct nshhdr *pushed_nh) +{ + struct nshhdr *nh; + size_t length = nsh_hdr_len(pushed_nh); + u8 next_proto; + + if (skb->mac_len) { + next_proto = TUN_P_ETHERNET; + } else { + next_proto = tun_p_from_eth_p(skb->protocol); + if (!next_proto) + return -EAFNOSUPPORT; + } + + /* Add the NSH header */ + if (skb_cow_head(skb, length) < 0) + return -ENOMEM; + + skb_push(skb, length); + nh = (struct nshhdr *)(skb->data); + memcpy(nh, pushed_nh, length); + nh->np = next_proto; + skb_postpush_rcsum(skb, nh, length); + + skb->protocol = htons(ETH_P_NSH); + skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb_reset_mac_len(skb); + + return 0; +} +EXPORT_SYMBOL_GPL(nsh_push); + +int nsh_pop(struct sk_buff *skb) +{ + struct nshhdr *nh; + size_t length; + __be16 inner_proto; + + if (!pskb_may_pull(skb, NSH_BASE_HDR_LEN)) + return -ENOMEM; + nh = (struct nshhdr *)(skb->data); + length = nsh_hdr_len(nh); + inner_proto = tun_p_to_eth_p(nh->np); + if (!pskb_may_pull(skb, length)) + return -ENOMEM; + + if (!inner_proto) + return -EAFNOSUPPORT; + + skb_pull_rcsum(skb, length); + skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb_reset_mac_len(skb); + skb->protocol = inner_proto; + + return 0; +} +EXPORT_SYMBOL_GPL(nsh_pop); + static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, netdev_features_t features) { diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index ce947292ae77..2650205cdaf9 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -14,6 +14,7 @@ config OPENVSWITCH select MPLS select NET_MPLS_GSO select DST_CACHE + select NET_NSH ---help--- Open vSwitch is a multilayer Ethernet switch targeted at virtualized environments. In addition to supporting a variety of features diff --git a/net/openvswitch/Makefile b/net/openvswitch/Makefile index 299f4476cf44..41109c326f3a 100644 --- a/net/openvswitch/Makefile +++ b/net/openvswitch/Makefile @@ -12,6 +12,7 @@ openvswitch-y := \ flow.o \ flow_netlink.o \ flow_table.o \ + meter.o \ vport.o \ vport-internal_dev.o \ vport-netdev.o diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index a54a556fcdb5..30a5df27116e 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -43,6 +43,7 @@ #include "flow.h" #include "conntrack.h" #include "vport.h" +#include "flow_netlink.h" struct deferred_action { struct sk_buff *skb; @@ -380,6 +381,38 @@ static int push_eth(struct sk_buff *skb, struct sw_flow_key *key, return 0; } +static int push_nsh(struct sk_buff *skb, struct sw_flow_key *key, + const struct nshhdr *nh) +{ + int err; + + err = nsh_push(skb, nh); + if (err) + return err; + + /* safe right before invalidate_flow_key */ + key->mac_proto = MAC_PROTO_NONE; + invalidate_flow_key(key); + return 0; +} + +static int pop_nsh(struct sk_buff *skb, struct sw_flow_key *key) +{ + int err; + + err = nsh_pop(skb); + if (err) + return err; + + /* safe right before invalidate_flow_key */ + if (skb->protocol == htons(ETH_P_TEB)) + key->mac_proto = MAC_PROTO_ETHERNET; + else + key->mac_proto = MAC_PROTO_NONE; + invalidate_flow_key(key); + return 0; +} + static void update_ip_l4_checksum(struct sk_buff *skb, struct iphdr *nh, __be32 addr, __be32 new_addr) { @@ -602,6 +635,69 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key, return 0; } +static int set_nsh(struct sk_buff *skb, struct sw_flow_key *flow_key, + const struct nlattr *a) +{ + struct nshhdr *nh; + size_t length; + int err; + u8 flags; + u8 ttl; + int i; + + struct ovs_key_nsh key; + struct ovs_key_nsh mask; + + err = nsh_key_from_nlattr(a, &key, &mask); + if (err) + return err; + + /* Make sure the NSH base header is there */ + if (!pskb_may_pull(skb, skb_network_offset(skb) + NSH_BASE_HDR_LEN)) + return -ENOMEM; + + nh = nsh_hdr(skb); + length = nsh_hdr_len(nh); + + /* Make sure the whole NSH header is there */ + err = skb_ensure_writable(skb, skb_network_offset(skb) + + length); + if (unlikely(err)) + return err; + + nh = nsh_hdr(skb); + skb_postpull_rcsum(skb, nh, length); + flags = nsh_get_flags(nh); + flags = OVS_MASKED(flags, key.base.flags, mask.base.flags); + flow_key->nsh.base.flags = flags; + ttl = nsh_get_ttl(nh); + ttl = OVS_MASKED(ttl, key.base.ttl, mask.base.ttl); + flow_key->nsh.base.ttl = ttl; + nsh_set_flags_and_ttl(nh, flags, ttl); + nh->path_hdr = OVS_MASKED(nh->path_hdr, key.base.path_hdr, + mask.base.path_hdr); + flow_key->nsh.base.path_hdr = nh->path_hdr; + switch (nh->mdtype) { + case NSH_M_TYPE1: + for (i = 0; i < NSH_MD1_CONTEXT_SIZE; i++) { + nh->md1.context[i] = + OVS_MASKED(nh->md1.context[i], key.context[i], + mask.context[i]); + } + memcpy(flow_key->nsh.context, nh->md1.context, + sizeof(nh->md1.context)); + break; + case NSH_M_TYPE2: + memset(flow_key->nsh.context, 0, + sizeof(flow_key->nsh.context)); + break; + default: + return -EINVAL; + } + skb_postpush_rcsum(skb, nh, length); + return 0; +} + /* Must follow skb_ensure_writable() since that can move the skb data. */ static void set_tp_port(struct sk_buff *skb, __be16 *port, __be16 new_port, __sum16 *check) @@ -1024,6 +1120,10 @@ static int execute_masked_set_action(struct sk_buff *skb, get_mask(a, struct ovs_key_ethernet *)); break; + case OVS_KEY_ATTR_NSH: + err = set_nsh(skb, flow_key, a); + break; + case OVS_KEY_ATTR_IPV4: err = set_ipv4(skb, flow_key, nla_data(a), get_mask(a, struct ovs_key_ipv4 *)); @@ -1203,6 +1303,10 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, return err == -EINPROGRESS ? 0 : err; break; + case OVS_ACTION_ATTR_CT_CLEAR: + err = ovs_ct_clear(skb, key); + break; + case OVS_ACTION_ATTR_PUSH_ETH: err = push_eth(skb, key, nla_data(a)); break; @@ -1210,6 +1314,28 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, case OVS_ACTION_ATTR_POP_ETH: err = pop_eth(skb, key); break; + + case OVS_ACTION_ATTR_PUSH_NSH: { + u8 buffer[NSH_HDR_MAX_LEN]; + struct nshhdr *nh = (struct nshhdr *)buffer; + + err = nsh_hdr_from_nlattr(nla_data(a), nh, + NSH_HDR_MAX_LEN); + if (unlikely(err)) + break; + err = push_nsh(skb, key, nh); + break; + } + + case OVS_ACTION_ATTR_POP_NSH: + err = pop_nsh(skb, key); + break; + + case OVS_ACTION_ATTR_METER: + if (ovs_meter_execute(dp, skb, key, nla_get_u32(a))) { + consume_skb(skb); + return 0; + } } if (unlikely(err)) { diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index d558e882ca0c..b27c5c6d9cab 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -752,6 +752,7 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, } } /* Non-ICMP, fall thru to initialize if needed. */ + /* fall through */ case IP_CT_NEW: /* Seen it before? This can happen for loopback, retrans, * or local packets. @@ -1129,6 +1130,17 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, return err; } +int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key) +{ + if (skb_nfct(skb)) { + nf_conntrack_put(skb_nfct(skb)); + nf_ct_set(skb, NULL, IP_CT_UNTRACKED); + ovs_ct_fill_key(skb, key); + } + + return 0; +} + static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name, const struct sw_flow_key *key, bool log) { diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h index bc7efd1867ab..399dfdd2c4f9 100644 --- a/net/openvswitch/conntrack.h +++ b/net/openvswitch/conntrack.h @@ -30,6 +30,7 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *, struct sk_buff *); int ovs_ct_execute(struct net *, struct sk_buff *, struct sw_flow_key *, const struct ovs_conntrack_info *); +int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key); void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key); int ovs_ct_put_key(const struct sw_flow_key *swkey, @@ -73,6 +74,12 @@ static inline int ovs_ct_execute(struct net *net, struct sk_buff *skb, return -ENOTSUPP; } +static inline int ovs_ct_clear(struct sk_buff *skb, + struct sw_flow_key *key) +{ + return -ENOTSUPP; +} + static inline void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key) { diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index c3aec6227c91..0dab33fb9844 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -55,6 +55,7 @@ #include "flow.h" #include "flow_table.h" #include "flow_netlink.h" +#include "meter.h" #include "vport-internal_dev.h" #include "vport-netdev.h" @@ -142,35 +143,6 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *, const struct dp_upcall_info *, uint32_t cutlen); -/* Must be called with rcu_read_lock. */ -static struct datapath *get_dp_rcu(struct net *net, int dp_ifindex) -{ - struct net_device *dev = dev_get_by_index_rcu(net, dp_ifindex); - - if (dev) { - struct vport *vport = ovs_internal_dev_get_vport(dev); - if (vport) - return vport->dp; - } - - return NULL; -} - -/* The caller must hold either ovs_mutex or rcu_read_lock to keep the - * returned dp pointer valid. - */ -static inline struct datapath *get_dp(struct net *net, int dp_ifindex) -{ - struct datapath *dp; - - WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_ovsl_is_held()); - rcu_read_lock(); - dp = get_dp_rcu(net, dp_ifindex); - rcu_read_unlock(); - - return dp; -} - /* Must be called with rcu_read_lock or ovs_mutex. */ const char *ovs_dp_name(const struct datapath *dp) { @@ -203,6 +175,7 @@ static void destroy_dp_rcu(struct rcu_head *rcu) ovs_flow_tbl_destroy(&dp->table); free_percpu(dp->stats_percpu); kfree(dp->ports); + ovs_meters_exit(dp); kfree(dp); } @@ -1601,6 +1574,10 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) INIT_HLIST_HEAD(&dp->ports[i]); + err = ovs_meters_init(dp); + if (err) + goto err_destroy_ports_array; + /* Set up our datapath device. */ parms.name = nla_data(a[OVS_DP_ATTR_NAME]); parms.type = OVS_VPORT_TYPE_INTERNAL; @@ -1629,7 +1606,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) ovs_dp_reset_user_features(skb, info); } - goto err_destroy_ports_array; + goto err_destroy_meters; } err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid, @@ -1644,8 +1621,10 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) ovs_notify(&dp_datapath_genl_family, reply, info); return 0; -err_destroy_ports_array: +err_destroy_meters: ovs_unlock(); + ovs_meters_exit(dp); +err_destroy_ports_array: kfree(dp->ports); err_destroy_percpu: free_percpu(dp->stats_percpu); @@ -1848,7 +1827,8 @@ static struct genl_family dp_datapath_genl_family __ro_after_init = { /* Called with ovs_mutex or RCU read lock. */ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, - u32 portid, u32 seq, u32 flags, u8 cmd) + struct net *net, u32 portid, u32 seq, + u32 flags, u8 cmd) { struct ovs_header *ovs_header; struct ovs_vport_stats vport_stats; @@ -1864,9 +1844,17 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, if (nla_put_u32(skb, OVS_VPORT_ATTR_PORT_NO, vport->port_no) || nla_put_u32(skb, OVS_VPORT_ATTR_TYPE, vport->ops->type) || nla_put_string(skb, OVS_VPORT_ATTR_NAME, - ovs_vport_name(vport))) + ovs_vport_name(vport)) || + nla_put_u32(skb, OVS_VPORT_ATTR_IFINDEX, vport->dev->ifindex)) goto nla_put_failure; + if (!net_eq(net, dev_net(vport->dev))) { + int id = peernet2id_alloc(net, dev_net(vport->dev)); + + if (nla_put_s32(skb, OVS_VPORT_ATTR_NETNSID, id)) + goto nla_put_failure; + } + ovs_vport_get_stats(vport, &vport_stats); if (nla_put_64bit(skb, OVS_VPORT_ATTR_STATS, sizeof(struct ovs_vport_stats), &vport_stats, @@ -1896,8 +1884,8 @@ static struct sk_buff *ovs_vport_cmd_alloc_info(void) } /* Called with ovs_mutex, only via ovs_dp_notify_wq(). */ -struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid, - u32 seq, u8 cmd) +struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, struct net *net, + u32 portid, u32 seq, u8 cmd) { struct sk_buff *skb; int retval; @@ -1906,7 +1894,7 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid, if (!skb) return ERR_PTR(-ENOMEM); - retval = ovs_vport_cmd_fill_info(vport, skb, portid, seq, 0, cmd); + retval = ovs_vport_cmd_fill_info(vport, skb, net, portid, seq, 0, cmd); BUG_ON(retval < 0); return skb; @@ -1920,6 +1908,8 @@ static struct vport *lookup_vport(struct net *net, struct datapath *dp; struct vport *vport; + if (a[OVS_VPORT_ATTR_IFINDEX]) + return ERR_PTR(-EOPNOTSUPP); if (a[OVS_VPORT_ATTR_NAME]) { vport = ovs_vport_locate(net, nla_data(a[OVS_VPORT_ATTR_NAME])); if (!vport) @@ -1944,6 +1934,7 @@ static struct vport *lookup_vport(struct net *net, return vport; } else return ERR_PTR(-EINVAL); + } /* Called with ovs_mutex */ @@ -1983,6 +1974,8 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) if (!a[OVS_VPORT_ATTR_NAME] || !a[OVS_VPORT_ATTR_TYPE] || !a[OVS_VPORT_ATTR_UPCALL_PID]) return -EINVAL; + if (a[OVS_VPORT_ATTR_IFINDEX]) + return -EOPNOTSUPP; port_no = a[OVS_VPORT_ATTR_PORT_NO] ? nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]) : 0; @@ -2032,8 +2025,9 @@ restart: goto exit_unlock_free; } - err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, - info->snd_seq, 0, OVS_VPORT_CMD_NEW); + err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), + info->snd_portid, info->snd_seq, 0, + OVS_VPORT_CMD_NEW); if (netdev_get_fwd_headroom(vport->dev) > dp->max_headroom) update_headroom(dp); @@ -2090,8 +2084,9 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) goto exit_unlock_free; } - err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, - info->snd_seq, 0, OVS_VPORT_CMD_NEW); + err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), + info->snd_portid, info->snd_seq, 0, + OVS_VPORT_CMD_NEW); BUG_ON(err < 0); ovs_unlock(); @@ -2128,8 +2123,9 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info) goto exit_unlock_free; } - err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, - info->snd_seq, 0, OVS_VPORT_CMD_DEL); + err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), + info->snd_portid, info->snd_seq, 0, + OVS_VPORT_CMD_DEL); BUG_ON(err < 0); /* the vport deletion may trigger dp headroom update */ @@ -2169,8 +2165,9 @@ static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info) err = PTR_ERR(vport); if (IS_ERR(vport)) goto exit_unlock_free; - err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, - info->snd_seq, 0, OVS_VPORT_CMD_NEW); + err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), + info->snd_portid, info->snd_seq, 0, + OVS_VPORT_CMD_NEW); BUG_ON(err < 0); rcu_read_unlock(); @@ -2202,6 +2199,7 @@ static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) { if (j >= skip && ovs_vport_cmd_fill_info(vport, skb, + sock_net(skb->sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, @@ -2228,6 +2226,8 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = { [OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 }, [OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 }, [OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED }, + [OVS_VPORT_ATTR_IFINDEX] = { .type = NLA_U32 }, + [OVS_VPORT_ATTR_NETNSID] = { .type = NLA_S32 }, }; static const struct genl_ops dp_vport_genl_ops[] = { @@ -2273,6 +2273,7 @@ static struct genl_family * const dp_genl_families[] = { &dp_vport_genl_family, &dp_flow_genl_family, &dp_packet_genl_family, + &dp_meter_genl_family, }; static void dp_unregister_genl(int n_families) @@ -2453,3 +2454,4 @@ MODULE_ALIAS_GENL_FAMILY(OVS_DATAPATH_FAMILY); MODULE_ALIAS_GENL_FAMILY(OVS_VPORT_FAMILY); MODULE_ALIAS_GENL_FAMILY(OVS_FLOW_FAMILY); MODULE_ALIAS_GENL_FAMILY(OVS_PACKET_FAMILY); +MODULE_ALIAS_GENL_FAMILY(OVS_METER_FAMILY); diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 480600649d0b..523d65526766 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -30,6 +30,8 @@ #include "conntrack.h" #include "flow.h" #include "flow_table.h" +#include "meter.h" +#include "vport-internal_dev.h" #define DP_MAX_PORTS USHRT_MAX #define DP_VPORT_HASH_BUCKETS 1024 @@ -91,6 +93,9 @@ struct datapath { u32 user_features; u32 max_headroom; + + /* Switch meters. */ + struct hlist_head *meters; }; /** @@ -190,6 +195,36 @@ static inline struct vport *ovs_vport_ovsl(const struct datapath *dp, int port_n return ovs_lookup_vport(dp, port_no); } +/* Must be called with rcu_read_lock. */ +static inline struct datapath *get_dp_rcu(struct net *net, int dp_ifindex) +{ + struct net_device *dev = dev_get_by_index_rcu(net, dp_ifindex); + + if (dev) { + struct vport *vport = ovs_internal_dev_get_vport(dev); + + if (vport) + return vport->dp; + } + + return NULL; +} + +/* The caller must hold either ovs_mutex or rcu_read_lock to keep the + * returned dp pointer valid. + */ +static inline struct datapath *get_dp(struct net *net, int dp_ifindex) +{ + struct datapath *dp; + + WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_ovsl_is_held()); + rcu_read_lock(); + dp = get_dp_rcu(net, dp_ifindex); + rcu_read_unlock(); + + return dp; +} + extern struct notifier_block ovs_dp_device_notifier; extern struct genl_family dp_vport_genl_family; @@ -200,8 +235,8 @@ int ovs_dp_upcall(struct datapath *, struct sk_buff *, uint32_t cutlen); const char *ovs_dp_name(const struct datapath *dp); -struct sk_buff *ovs_vport_cmd_build_info(struct vport *, u32 pid, u32 seq, - u8 cmd); +struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, struct net *net, + u32 portid, u32 seq, u8 cmd); int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb, const struct sw_flow_actions *, struct sw_flow_key *); diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c index 653d073bae45..f3ee2f2825c0 100644 --- a/net/openvswitch/dp_notify.c +++ b/net/openvswitch/dp_notify.c @@ -30,8 +30,8 @@ static void dp_detach_port_notify(struct vport *vport) struct datapath *dp; dp = vport->dp; - notify = ovs_vport_cmd_build_info(vport, 0, 0, - OVS_VPORT_CMD_DEL); + notify = ovs_vport_cmd_build_info(vport, ovs_dp_get_net(dp), + 0, 0, OVS_VPORT_CMD_DEL); ovs_dp_detach_port(vport); if (IS_ERR(notify)) { genl_set_err(&dp_vport_genl_family, ovs_dp_get_net(dp), 0, diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 8c94cef25a72..864ddb1e3642 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -46,6 +46,7 @@ #include <net/ipv6.h> #include <net/mpls.h> #include <net/ndisc.h> +#include <net/nsh.h> #include "conntrack.h" #include "datapath.h" @@ -490,6 +491,52 @@ invalid: return 0; } +static int parse_nsh(struct sk_buff *skb, struct sw_flow_key *key) +{ + struct nshhdr *nh; + unsigned int nh_ofs = skb_network_offset(skb); + u8 version, length; + int err; + + err = check_header(skb, nh_ofs + NSH_BASE_HDR_LEN); + if (unlikely(err)) + return err; + + nh = nsh_hdr(skb); + version = nsh_get_ver(nh); + length = nsh_hdr_len(nh); + + if (version != 0) + return -EINVAL; + + err = check_header(skb, nh_ofs + length); + if (unlikely(err)) + return err; + + nh = nsh_hdr(skb); + key->nsh.base.flags = nsh_get_flags(nh); + key->nsh.base.ttl = nsh_get_ttl(nh); + key->nsh.base.mdtype = nh->mdtype; + key->nsh.base.np = nh->np; + key->nsh.base.path_hdr = nh->path_hdr; + switch (key->nsh.base.mdtype) { + case NSH_M_TYPE1: + if (length != NSH_M_TYPE1_LEN) + return -EINVAL; + memcpy(key->nsh.context, nh->md1.context, + sizeof(nh->md1)); + break; + case NSH_M_TYPE2: + memset(key->nsh.context, 0, + sizeof(nh->md1)); + break; + default: + return -EINVAL; + } + + return 0; +} + /** * key_extract - extracts a flow key from an Ethernet frame. * @skb: sk_buff that contains the frame, with skb->data pointing to the @@ -735,6 +782,10 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) memset(&key->tp, 0, sizeof(key->tp)); } } + } else if (key->eth.type == htons(ETH_P_NSH)) { + error = parse_nsh(skb, key); + if (error) + return error; } return 0; } diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index 1875bba4f865..c670dd24b8b7 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -35,6 +35,7 @@ #include <net/inet_ecn.h> #include <net/ip_tunnels.h> #include <net/dst_metadata.h> +#include <net/nsh.h> struct sk_buff; @@ -66,6 +67,11 @@ struct vlan_head { (offsetof(struct sw_flow_key, recirc_id) + \ FIELD_SIZEOF(struct sw_flow_key, recirc_id)) +struct ovs_key_nsh { + struct ovs_nsh_key_base base; + __be32 context[NSH_MD1_CONTEXT_SIZE]; +}; + struct sw_flow_key { u8 tun_opts[IP_TUNNEL_OPTS_MAX]; u8 tun_opts_len; @@ -143,6 +149,7 @@ struct sw_flow_key { } nd; }; } ipv6; + struct ovs_key_nsh nsh; /* network service header */ }; struct { /* Connection tracking fields not packed above. */ diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index e8eb427ce6d1..dc424798ba6f 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -48,6 +48,8 @@ #include <net/ndisc.h> #include <net/mpls.h> #include <net/vxlan.h> +#include <net/tun_proto.h> +#include <net/erspan.h> #include "flow_netlink.h" @@ -75,16 +77,20 @@ static bool actions_may_change_flow(const struct nlattr *actions) break; case OVS_ACTION_ATTR_CT: + case OVS_ACTION_ATTR_CT_CLEAR: case OVS_ACTION_ATTR_HASH: case OVS_ACTION_ATTR_POP_ETH: case OVS_ACTION_ATTR_POP_MPLS: + case OVS_ACTION_ATTR_POP_NSH: case OVS_ACTION_ATTR_POP_VLAN: case OVS_ACTION_ATTR_PUSH_ETH: case OVS_ACTION_ATTR_PUSH_MPLS: + case OVS_ACTION_ATTR_PUSH_NSH: case OVS_ACTION_ATTR_PUSH_VLAN: case OVS_ACTION_ATTR_SAMPLE: case OVS_ACTION_ATTR_SET: case OVS_ACTION_ATTR_SET_MASKED: + case OVS_ACTION_ATTR_METER: default: return true; } @@ -173,7 +179,8 @@ static bool match_validate(const struct sw_flow_match *match, | (1 << OVS_KEY_ATTR_ICMPV6) | (1 << OVS_KEY_ATTR_ARP) | (1 << OVS_KEY_ATTR_ND) - | (1 << OVS_KEY_ATTR_MPLS)); + | (1 << OVS_KEY_ATTR_MPLS) + | (1 << OVS_KEY_ATTR_NSH)); /* Always allowed mask fields. */ mask_allowed |= ((1 << OVS_KEY_ATTR_TUNNEL) @@ -282,6 +289,14 @@ static bool match_validate(const struct sw_flow_match *match, } } + if (match->key->eth.type == htons(ETH_P_NSH)) { + key_expected |= 1 << OVS_KEY_ATTR_NSH; + if (match->mask && + match->mask->key.eth.type == htons(0xffff)) { + mask_allowed |= 1 << OVS_KEY_ATTR_NSH; + } + } + if ((key_attrs & key_expected) != key_expected) { /* Key attributes check failed. */ OVS_NLERR(log, "Missing key (keys=%llx, expected=%llx)", @@ -319,7 +334,21 @@ size_t ovs_tun_key_attr_size(void) * OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS and covered by it. */ + nla_total_size(2) /* OVS_TUNNEL_KEY_ATTR_TP_SRC */ - + nla_total_size(2); /* OVS_TUNNEL_KEY_ATTR_TP_DST */ + + nla_total_size(2) /* OVS_TUNNEL_KEY_ATTR_TP_DST */ + + nla_total_size(4); /* OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS */ +} + +static size_t ovs_nsh_key_attr_size(void) +{ + /* Whenever adding new OVS_NSH_KEY_ FIELDS, we should consider + * updating this function. + */ + return nla_total_size(NSH_BASE_HDR_LEN) /* OVS_NSH_KEY_ATTR_BASE */ + /* OVS_NSH_KEY_ATTR_MD1 and OVS_NSH_KEY_ATTR_MD2 are + * mutually exclusive, so the bigger one can cover + * the small one. + */ + + nla_total_size(NSH_CTX_HDRS_MAX_LEN); } size_t ovs_key_attr_size(void) @@ -327,7 +356,7 @@ size_t ovs_key_attr_size(void) /* Whenever adding new OVS_KEY_ FIELDS, we should consider * updating this function. */ - BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 28); + BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 29); return nla_total_size(4) /* OVS_KEY_ATTR_PRIORITY */ + nla_total_size(0) /* OVS_KEY_ATTR_TUNNEL */ @@ -341,6 +370,8 @@ size_t ovs_key_attr_size(void) + nla_total_size(4) /* OVS_KEY_ATTR_CT_MARK */ + nla_total_size(16) /* OVS_KEY_ATTR_CT_LABELS */ + nla_total_size(40) /* OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6 */ + + nla_total_size(0) /* OVS_KEY_ATTR_NSH */ + + ovs_nsh_key_attr_size() + nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */ + nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */ + nla_total_size(4) /* OVS_KEY_ATTR_VLAN */ @@ -371,6 +402,14 @@ static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] .next = ovs_vxlan_ext_key_lens }, [OVS_TUNNEL_KEY_ATTR_IPV6_SRC] = { .len = sizeof(struct in6_addr) }, [OVS_TUNNEL_KEY_ATTR_IPV6_DST] = { .len = sizeof(struct in6_addr) }, + [OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS] = { .len = sizeof(u32) }, +}; + +static const struct ovs_len_tbl +ovs_nsh_key_attr_lens[OVS_NSH_KEY_ATTR_MAX + 1] = { + [OVS_NSH_KEY_ATTR_BASE] = { .len = sizeof(struct ovs_nsh_key_base) }, + [OVS_NSH_KEY_ATTR_MD1] = { .len = sizeof(struct ovs_nsh_key_md1) }, + [OVS_NSH_KEY_ATTR_MD2] = { .len = OVS_ATTR_VARIABLE }, }; /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */ @@ -405,6 +444,8 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { .len = sizeof(struct ovs_key_ct_tuple_ipv4) }, [OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6] = { .len = sizeof(struct ovs_key_ct_tuple_ipv6) }, + [OVS_KEY_ATTR_NSH] = { .len = OVS_ATTR_NESTED, + .next = ovs_nsh_key_attr_lens, }, }; static bool check_attr_len(unsigned int attr_len, unsigned int expected_len) @@ -593,6 +634,33 @@ static int vxlan_tun_opt_from_nlattr(const struct nlattr *attr, return 0; } +static int erspan_tun_opt_from_nlattr(const struct nlattr *attr, + struct sw_flow_match *match, bool is_mask, + bool log) +{ + unsigned long opt_key_offset; + struct erspan_metadata opts; + + BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts)); + + memset(&opts, 0, sizeof(opts)); + opts.index = nla_get_be32(attr); + + /* Index has only 20-bit */ + if (ntohl(opts.index) & ~INDEX_MASK) { + OVS_NLERR(log, "ERSPAN index number %x too large.", + ntohl(opts.index)); + return -EINVAL; + } + + SW_FLOW_KEY_PUT(match, tun_opts_len, sizeof(opts), is_mask); + opt_key_offset = TUN_METADATA_OFFSET(sizeof(opts)); + SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, &opts, sizeof(opts), + is_mask); + + return 0; +} + static int ip_tun_from_nlattr(const struct nlattr *attr, struct sw_flow_match *match, bool is_mask, bool log) @@ -700,6 +768,19 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, break; case OVS_TUNNEL_KEY_ATTR_PAD: break; + case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS: + if (opts_type) { + OVS_NLERR(log, "Multiple metadata blocks provided"); + return -EINVAL; + } + + err = erspan_tun_opt_from_nlattr(a, match, is_mask, log); + if (err) + return err; + + tun_flags |= TUNNEL_ERSPAN_OPT; + opts_type = type; + break; default: OVS_NLERR(log, "Unknown IP tunnel attribute %d", type); @@ -824,6 +905,10 @@ static int __ip_tun_to_nlattr(struct sk_buff *skb, else if (output->tun_flags & TUNNEL_VXLAN_OPT && vxlan_opt_to_nlattr(skb, tun_opts, swkey_tun_opts_len)) return -EMSGSIZE; + else if (output->tun_flags & TUNNEL_ERSPAN_OPT && + nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS, + ((struct erspan_metadata *)tun_opts)->index)) + return -EMSGSIZE; } return 0; @@ -1179,6 +1264,221 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, return 0; } +int nsh_hdr_from_nlattr(const struct nlattr *attr, + struct nshhdr *nh, size_t size) +{ + struct nlattr *a; + int rem; + u8 flags = 0; + u8 ttl = 0; + int mdlen = 0; + + /* validate_nsh has check this, so we needn't do duplicate check here + */ + if (size < NSH_BASE_HDR_LEN) + return -ENOBUFS; + + nla_for_each_nested(a, attr, rem) { + int type = nla_type(a); + + switch (type) { + case OVS_NSH_KEY_ATTR_BASE: { + const struct ovs_nsh_key_base *base = nla_data(a); + + flags = base->flags; + ttl = base->ttl; + nh->np = base->np; + nh->mdtype = base->mdtype; + nh->path_hdr = base->path_hdr; + break; + } + case OVS_NSH_KEY_ATTR_MD1: + mdlen = nla_len(a); + if (mdlen > size - NSH_BASE_HDR_LEN) + return -ENOBUFS; + memcpy(&nh->md1, nla_data(a), mdlen); + break; + + case OVS_NSH_KEY_ATTR_MD2: + mdlen = nla_len(a); + if (mdlen > size - NSH_BASE_HDR_LEN) + return -ENOBUFS; + memcpy(&nh->md2, nla_data(a), mdlen); + break; + + default: + return -EINVAL; + } + } + + /* nsh header length = NSH_BASE_HDR_LEN + mdlen */ + nh->ver_flags_ttl_len = 0; + nsh_set_flags_ttl_len(nh, flags, ttl, NSH_BASE_HDR_LEN + mdlen); + + return 0; +} + +int nsh_key_from_nlattr(const struct nlattr *attr, + struct ovs_key_nsh *nsh, struct ovs_key_nsh *nsh_mask) +{ + struct nlattr *a; + int rem; + + /* validate_nsh has check this, so we needn't do duplicate check here + */ + nla_for_each_nested(a, attr, rem) { + int type = nla_type(a); + + switch (type) { + case OVS_NSH_KEY_ATTR_BASE: { + const struct ovs_nsh_key_base *base = nla_data(a); + const struct ovs_nsh_key_base *base_mask = base + 1; + + nsh->base = *base; + nsh_mask->base = *base_mask; + break; + } + case OVS_NSH_KEY_ATTR_MD1: { + const struct ovs_nsh_key_md1 *md1 = nla_data(a); + const struct ovs_nsh_key_md1 *md1_mask = md1 + 1; + + memcpy(nsh->context, md1->context, sizeof(*md1)); + memcpy(nsh_mask->context, md1_mask->context, + sizeof(*md1_mask)); + break; + } + case OVS_NSH_KEY_ATTR_MD2: + /* Not supported yet */ + return -ENOTSUPP; + default: + return -EINVAL; + } + } + + return 0; +} + +static int nsh_key_put_from_nlattr(const struct nlattr *attr, + struct sw_flow_match *match, bool is_mask, + bool is_push_nsh, bool log) +{ + struct nlattr *a; + int rem; + bool has_base = false; + bool has_md1 = false; + bool has_md2 = false; + u8 mdtype = 0; + int mdlen = 0; + + if (WARN_ON(is_push_nsh && is_mask)) + return -EINVAL; + + nla_for_each_nested(a, attr, rem) { + int type = nla_type(a); + int i; + + if (type > OVS_NSH_KEY_ATTR_MAX) { + OVS_NLERR(log, "nsh attr %d is out of range max %d", + type, OVS_NSH_KEY_ATTR_MAX); + return -EINVAL; + } + + if (!check_attr_len(nla_len(a), + ovs_nsh_key_attr_lens[type].len)) { + OVS_NLERR( + log, + "nsh attr %d has unexpected len %d expected %d", + type, + nla_len(a), + ovs_nsh_key_attr_lens[type].len + ); + return -EINVAL; + } + + switch (type) { + case OVS_NSH_KEY_ATTR_BASE: { + const struct ovs_nsh_key_base *base = nla_data(a); + + has_base = true; + mdtype = base->mdtype; + SW_FLOW_KEY_PUT(match, nsh.base.flags, + base->flags, is_mask); + SW_FLOW_KEY_PUT(match, nsh.base.ttl, + base->ttl, is_mask); + SW_FLOW_KEY_PUT(match, nsh.base.mdtype, + base->mdtype, is_mask); + SW_FLOW_KEY_PUT(match, nsh.base.np, + base->np, is_mask); + SW_FLOW_KEY_PUT(match, nsh.base.path_hdr, + base->path_hdr, is_mask); + break; + } + case OVS_NSH_KEY_ATTR_MD1: { + const struct ovs_nsh_key_md1 *md1 = nla_data(a); + + has_md1 = true; + for (i = 0; i < NSH_MD1_CONTEXT_SIZE; i++) + SW_FLOW_KEY_PUT(match, nsh.context[i], + md1->context[i], is_mask); + break; + } + case OVS_NSH_KEY_ATTR_MD2: + if (!is_push_nsh) /* Not supported MD type 2 yet */ + return -ENOTSUPP; + + has_md2 = true; + mdlen = nla_len(a); + if (mdlen > NSH_CTX_HDRS_MAX_LEN || mdlen <= 0) { + OVS_NLERR( + log, + "Invalid MD length %d for MD type %d", + mdlen, + mdtype + ); + return -EINVAL; + } + break; + default: + OVS_NLERR(log, "Unknown nsh attribute %d", + type); + return -EINVAL; + } + } + + if (rem > 0) { + OVS_NLERR(log, "nsh attribute has %d unknown bytes.", rem); + return -EINVAL; + } + + if (has_md1 && has_md2) { + OVS_NLERR( + 1, + "invalid nsh attribute: md1 and md2 are exclusive." + ); + return -EINVAL; + } + + if (!is_mask) { + if ((has_md1 && mdtype != NSH_M_TYPE1) || + (has_md2 && mdtype != NSH_M_TYPE2)) { + OVS_NLERR(1, "nsh attribute has unmatched MD type %d.", + mdtype); + return -EINVAL; + } + + if (is_push_nsh && + (!has_base || (!has_md1 && !has_md2))) { + OVS_NLERR( + 1, + "push_nsh: missing base or metadata attributes" + ); + return -EINVAL; + } + } + + return 0; +} + static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match, u64 attrs, const struct nlattr **a, bool is_mask, bool log) @@ -1306,6 +1606,13 @@ static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match, attrs &= ~(1 << OVS_KEY_ATTR_ARP); } + if (attrs & (1 << OVS_KEY_ATTR_NSH)) { + if (nsh_key_put_from_nlattr(a[OVS_KEY_ATTR_NSH], match, + is_mask, false, log) < 0) + return -EINVAL; + attrs &= ~(1 << OVS_KEY_ATTR_NSH); + } + if (attrs & (1 << OVS_KEY_ATTR_MPLS)) { const struct ovs_key_mpls *mpls_key; @@ -1622,6 +1929,34 @@ static int ovs_nla_put_vlan(struct sk_buff *skb, const struct vlan_head *vh, return 0; } +static int nsh_key_to_nlattr(const struct ovs_key_nsh *nsh, bool is_mask, + struct sk_buff *skb) +{ + struct nlattr *start; + + start = nla_nest_start(skb, OVS_KEY_ATTR_NSH); + if (!start) + return -EMSGSIZE; + + if (nla_put(skb, OVS_NSH_KEY_ATTR_BASE, sizeof(nsh->base), &nsh->base)) + goto nla_put_failure; + + if (is_mask || nsh->base.mdtype == NSH_M_TYPE1) { + if (nla_put(skb, OVS_NSH_KEY_ATTR_MD1, + sizeof(nsh->context), nsh->context)) + goto nla_put_failure; + } + + /* Don't support MD type 2 yet */ + + nla_nest_end(skb, start); + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + static int __ovs_nla_put_key(const struct sw_flow_key *swkey, const struct sw_flow_key *output, bool is_mask, struct sk_buff *skb) @@ -1750,6 +2085,9 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, ipv6_key->ipv6_tclass = output->ip.tos; ipv6_key->ipv6_hlimit = output->ip.ttl; ipv6_key->ipv6_frag = output->ip.frag; + } else if (swkey->eth.type == htons(ETH_P_NSH)) { + if (nsh_key_to_nlattr(&output->nsh, is_mask, skb)) + goto nla_put_failure; } else if (swkey->eth.type == htons(ETH_P_ARP) || swkey->eth.type == htons(ETH_P_RARP)) { struct ovs_key_arp *arp_key; @@ -2195,6 +2533,8 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, break; case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS: break; + case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS: + break; } }; @@ -2242,6 +2582,19 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, return err; } +static bool validate_nsh(const struct nlattr *attr, bool is_mask, + bool is_push_nsh, bool log) +{ + struct sw_flow_match match; + struct sw_flow_key key; + int ret = 0; + + ovs_match_init(&match, &key, true, NULL); + ret = nsh_key_put_from_nlattr(attr, &match, is_mask, + is_push_nsh, log); + return !ret; +} + /* Return false if there are any non-masked bits set. * Mask follows data immediately, before any netlink padding. */ @@ -2384,6 +2737,13 @@ static int validate_set(const struct nlattr *a, break; + case OVS_KEY_ATTR_NSH: + if (eth_type != htons(ETH_P_NSH)) + return -EINVAL; + if (!validate_nsh(nla_data(a), masked, false, log)) + return -EINVAL; + break; + default: return -EINVAL; } @@ -2479,9 +2839,13 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, [OVS_ACTION_ATTR_SAMPLE] = (u32)-1, [OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash), [OVS_ACTION_ATTR_CT] = (u32)-1, + [OVS_ACTION_ATTR_CT_CLEAR] = 0, [OVS_ACTION_ATTR_TRUNC] = sizeof(struct ovs_action_trunc), [OVS_ACTION_ATTR_PUSH_ETH] = sizeof(struct ovs_action_push_eth), [OVS_ACTION_ATTR_POP_ETH] = 0, + [OVS_ACTION_ATTR_PUSH_NSH] = (u32)-1, + [OVS_ACTION_ATTR_POP_NSH] = 0, + [OVS_ACTION_ATTR_METER] = sizeof(u32), }; const struct ovs_action_push_vlan *vlan; int type = nla_type(a); @@ -2620,6 +2984,9 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, skip_copy = true; break; + case OVS_ACTION_ATTR_CT_CLEAR: + break; + case OVS_ACTION_ATTR_PUSH_ETH: /* Disallow pushing an Ethernet header if one * is already present */ @@ -2636,6 +3003,38 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, mac_proto = MAC_PROTO_ETHERNET; break; + case OVS_ACTION_ATTR_PUSH_NSH: + if (mac_proto != MAC_PROTO_ETHERNET) { + u8 next_proto; + + next_proto = tun_p_from_eth_p(eth_type); + if (!next_proto) + return -EINVAL; + } + mac_proto = MAC_PROTO_NONE; + if (!validate_nsh(nla_data(a), false, true, true)) + return -EINVAL; + break; + + case OVS_ACTION_ATTR_POP_NSH: { + __be16 inner_proto; + + if (eth_type != htons(ETH_P_NSH)) + return -EINVAL; + inner_proto = tun_p_to_eth_p(key->nsh.base.np); + if (!inner_proto) + return -EINVAL; + if (key->nsh.base.np == TUN_P_ETHERNET) + mac_proto = MAC_PROTO_ETHERNET; + else + mac_proto = MAC_PROTO_NONE; + break; + } + + case OVS_ACTION_ATTR_METER: + /* Non-existent meters are simply ignored. */ + break; + default: OVS_NLERR(log, "Unknown Action type %d", type); return -EINVAL; diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h index 929c665ac3aa..6657606b2b47 100644 --- a/net/openvswitch/flow_netlink.h +++ b/net/openvswitch/flow_netlink.h @@ -79,4 +79,9 @@ int ovs_nla_put_actions(const struct nlattr *attr, void ovs_nla_free_flow_actions(struct sw_flow_actions *); void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *); +int nsh_key_from_nlattr(const struct nlattr *attr, struct ovs_key_nsh *nsh, + struct ovs_key_nsh *nsh_mask); +int nsh_hdr_from_nlattr(const struct nlattr *attr, struct nshhdr *nh, + size_t size); + #endif /* flow_netlink.h */ diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c new file mode 100644 index 000000000000..3fbfc78991ac --- /dev/null +++ b/net/openvswitch/meter.c @@ -0,0 +1,597 @@ +/* + * Copyright (c) 2017 Nicira, Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/if.h> +#include <linux/skbuff.h> +#include <linux/ip.h> +#include <linux/kernel.h> +#include <linux/openvswitch.h> +#include <linux/netlink.h> +#include <linux/rculist.h> + +#include <net/netlink.h> +#include <net/genetlink.h> + +#include "datapath.h" +#include "meter.h" + +#define METER_HASH_BUCKETS 1024 + +static const struct nla_policy meter_policy[OVS_METER_ATTR_MAX + 1] = { + [OVS_METER_ATTR_ID] = { .type = NLA_U32, }, + [OVS_METER_ATTR_KBPS] = { .type = NLA_FLAG }, + [OVS_METER_ATTR_STATS] = { .len = sizeof(struct ovs_flow_stats) }, + [OVS_METER_ATTR_BANDS] = { .type = NLA_NESTED }, + [OVS_METER_ATTR_USED] = { .type = NLA_U64 }, + [OVS_METER_ATTR_CLEAR] = { .type = NLA_FLAG }, + [OVS_METER_ATTR_MAX_METERS] = { .type = NLA_U32 }, + [OVS_METER_ATTR_MAX_BANDS] = { .type = NLA_U32 }, +}; + +static const struct nla_policy band_policy[OVS_BAND_ATTR_MAX + 1] = { + [OVS_BAND_ATTR_TYPE] = { .type = NLA_U32, }, + [OVS_BAND_ATTR_RATE] = { .type = NLA_U32, }, + [OVS_BAND_ATTR_BURST] = { .type = NLA_U32, }, + [OVS_BAND_ATTR_STATS] = { .len = sizeof(struct ovs_flow_stats) }, +}; + +static void ovs_meter_free(struct dp_meter *meter) +{ + if (!meter) + return; + + kfree_rcu(meter, rcu); +} + +static struct hlist_head *meter_hash_bucket(const struct datapath *dp, + u32 meter_id) +{ + return &dp->meters[meter_id & (METER_HASH_BUCKETS - 1)]; +} + +/* Call with ovs_mutex or RCU read lock. */ +static struct dp_meter *lookup_meter(const struct datapath *dp, + u32 meter_id) +{ + struct dp_meter *meter; + struct hlist_head *head; + + head = meter_hash_bucket(dp, meter_id); + hlist_for_each_entry_rcu(meter, head, dp_hash_node) { + if (meter->id == meter_id) + return meter; + } + return NULL; +} + +static void attach_meter(struct datapath *dp, struct dp_meter *meter) +{ + struct hlist_head *head = meter_hash_bucket(dp, meter->id); + + hlist_add_head_rcu(&meter->dp_hash_node, head); +} + +static void detach_meter(struct dp_meter *meter) +{ + ASSERT_OVSL(); + if (meter) + hlist_del_rcu(&meter->dp_hash_node); +} + +static struct sk_buff * +ovs_meter_cmd_reply_start(struct genl_info *info, u8 cmd, + struct ovs_header **ovs_reply_header) +{ + struct sk_buff *skb; + struct ovs_header *ovs_header = info->userhdr; + + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + if (!skb) + return ERR_PTR(-ENOMEM); + + *ovs_reply_header = genlmsg_put(skb, info->snd_portid, + info->snd_seq, + &dp_meter_genl_family, 0, cmd); + if (!*ovs_reply_header) { + nlmsg_free(skb); + return ERR_PTR(-EMSGSIZE); + } + (*ovs_reply_header)->dp_ifindex = ovs_header->dp_ifindex; + + return skb; +} + +static int ovs_meter_cmd_reply_stats(struct sk_buff *reply, u32 meter_id, + struct dp_meter *meter) +{ + struct nlattr *nla; + struct dp_meter_band *band; + u16 i; + + if (nla_put_u32(reply, OVS_METER_ATTR_ID, meter_id)) + goto error; + + if (!meter) + return 0; + + if (nla_put(reply, OVS_METER_ATTR_STATS, + sizeof(struct ovs_flow_stats), &meter->stats) || + nla_put_u64_64bit(reply, OVS_METER_ATTR_USED, meter->used, + OVS_METER_ATTR_PAD)) + goto error; + + nla = nla_nest_start(reply, OVS_METER_ATTR_BANDS); + if (!nla) + goto error; + + band = meter->bands; + + for (i = 0; i < meter->n_bands; ++i, ++band) { + struct nlattr *band_nla; + + band_nla = nla_nest_start(reply, OVS_BAND_ATTR_UNSPEC); + if (!band_nla || nla_put(reply, OVS_BAND_ATTR_STATS, + sizeof(struct ovs_flow_stats), + &band->stats)) + goto error; + nla_nest_end(reply, band_nla); + } + nla_nest_end(reply, nla); + + return 0; +error: + return -EMSGSIZE; +} + +static int ovs_meter_cmd_features(struct sk_buff *skb, struct genl_info *info) +{ + struct sk_buff *reply; + struct ovs_header *ovs_reply_header; + struct nlattr *nla, *band_nla; + int err; + + reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_FEATURES, + &ovs_reply_header); + if (IS_ERR(reply)) + return PTR_ERR(reply); + + if (nla_put_u32(reply, OVS_METER_ATTR_MAX_METERS, U32_MAX) || + nla_put_u32(reply, OVS_METER_ATTR_MAX_BANDS, DP_MAX_BANDS)) + goto nla_put_failure; + + nla = nla_nest_start(reply, OVS_METER_ATTR_BANDS); + if (!nla) + goto nla_put_failure; + + band_nla = nla_nest_start(reply, OVS_BAND_ATTR_UNSPEC); + if (!band_nla) + goto nla_put_failure; + /* Currently only DROP band type is supported. */ + if (nla_put_u32(reply, OVS_BAND_ATTR_TYPE, OVS_METER_BAND_TYPE_DROP)) + goto nla_put_failure; + nla_nest_end(reply, band_nla); + nla_nest_end(reply, nla); + + genlmsg_end(reply, ovs_reply_header); + return genlmsg_reply(reply, info); + +nla_put_failure: + nlmsg_free(reply); + err = -EMSGSIZE; + return err; +} + +static struct dp_meter *dp_meter_create(struct nlattr **a) +{ + struct nlattr *nla; + int rem; + u16 n_bands = 0; + struct dp_meter *meter; + struct dp_meter_band *band; + int err; + + /* Validate attributes, count the bands. */ + if (!a[OVS_METER_ATTR_BANDS]) + return ERR_PTR(-EINVAL); + + nla_for_each_nested(nla, a[OVS_METER_ATTR_BANDS], rem) + if (++n_bands > DP_MAX_BANDS) + return ERR_PTR(-EINVAL); + + /* Allocate and set up the meter before locking anything. */ + meter = kzalloc(n_bands * sizeof(struct dp_meter_band) + + sizeof(*meter), GFP_KERNEL); + if (!meter) + return ERR_PTR(-ENOMEM); + + meter->used = div_u64(ktime_get_ns(), 1000 * 1000); + meter->kbps = a[OVS_METER_ATTR_KBPS] ? 1 : 0; + meter->keep_stats = !a[OVS_METER_ATTR_CLEAR]; + spin_lock_init(&meter->lock); + if (meter->keep_stats && a[OVS_METER_ATTR_STATS]) { + meter->stats = *(struct ovs_flow_stats *) + nla_data(a[OVS_METER_ATTR_STATS]); + } + meter->n_bands = n_bands; + + /* Set up meter bands. */ + band = meter->bands; + nla_for_each_nested(nla, a[OVS_METER_ATTR_BANDS], rem) { + struct nlattr *attr[OVS_BAND_ATTR_MAX + 1]; + u32 band_max_delta_t; + + err = nla_parse((struct nlattr **)&attr, OVS_BAND_ATTR_MAX, + nla_data(nla), nla_len(nla), band_policy, + NULL); + if (err) + goto exit_free_meter; + + if (!attr[OVS_BAND_ATTR_TYPE] || + !attr[OVS_BAND_ATTR_RATE] || + !attr[OVS_BAND_ATTR_BURST]) { + err = -EINVAL; + goto exit_free_meter; + } + + band->type = nla_get_u32(attr[OVS_BAND_ATTR_TYPE]); + band->rate = nla_get_u32(attr[OVS_BAND_ATTR_RATE]); + band->burst_size = nla_get_u32(attr[OVS_BAND_ATTR_BURST]); + /* Figure out max delta_t that is enough to fill any bucket. + * Keep max_delta_t size to the bucket units: + * pkts => 1/1000 packets, kilobits => bits. + */ + band_max_delta_t = (band->burst_size + band->rate) * 1000; + /* Start with a full bucket. */ + band->bucket = band_max_delta_t; + if (band_max_delta_t > meter->max_delta_t) + meter->max_delta_t = band_max_delta_t; + band++; + } + + return meter; + +exit_free_meter: + kfree(meter); + return ERR_PTR(err); +} + +static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr **a = info->attrs; + struct dp_meter *meter, *old_meter; + struct sk_buff *reply; + struct ovs_header *ovs_reply_header; + struct ovs_header *ovs_header = info->userhdr; + struct datapath *dp; + int err; + u32 meter_id; + bool failed; + + meter = dp_meter_create(a); + if (IS_ERR_OR_NULL(meter)) + return PTR_ERR(meter); + + reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_SET, + &ovs_reply_header); + if (IS_ERR(reply)) { + err = PTR_ERR(reply); + goto exit_free_meter; + } + + ovs_lock(); + dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); + if (!dp) { + err = -ENODEV; + goto exit_unlock; + } + + if (!a[OVS_METER_ATTR_ID]) { + err = -ENODEV; + goto exit_unlock; + } + + meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]); + + /* Cannot fail after this. */ + old_meter = lookup_meter(dp, meter_id); + detach_meter(old_meter); + attach_meter(dp, meter); + ovs_unlock(); + + /* Build response with the meter_id and stats from + * the old meter, if any. + */ + failed = nla_put_u32(reply, OVS_METER_ATTR_ID, meter_id); + WARN_ON(failed); + if (old_meter) { + spin_lock_bh(&old_meter->lock); + if (old_meter->keep_stats) { + err = ovs_meter_cmd_reply_stats(reply, meter_id, + old_meter); + WARN_ON(err); + } + spin_unlock_bh(&old_meter->lock); + ovs_meter_free(old_meter); + } + + genlmsg_end(reply, ovs_reply_header); + return genlmsg_reply(reply, info); + +exit_unlock: + ovs_unlock(); + nlmsg_free(reply); +exit_free_meter: + kfree(meter); + return err; +} + +static int ovs_meter_cmd_get(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr **a = info->attrs; + u32 meter_id; + struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_reply_header; + struct datapath *dp; + int err; + struct sk_buff *reply; + struct dp_meter *meter; + + if (!a[OVS_METER_ATTR_ID]) + return -EINVAL; + + meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]); + + reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_GET, + &ovs_reply_header); + if (IS_ERR(reply)) + return PTR_ERR(reply); + + ovs_lock(); + + dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); + if (!dp) { + err = -ENODEV; + goto exit_unlock; + } + + /* Locate meter, copy stats. */ + meter = lookup_meter(dp, meter_id); + if (!meter) { + err = -ENOENT; + goto exit_unlock; + } + + spin_lock_bh(&meter->lock); + err = ovs_meter_cmd_reply_stats(reply, meter_id, meter); + spin_unlock_bh(&meter->lock); + if (err) + goto exit_unlock; + + ovs_unlock(); + + genlmsg_end(reply, ovs_reply_header); + return genlmsg_reply(reply, info); + +exit_unlock: + ovs_unlock(); + nlmsg_free(reply); + return err; +} + +static int ovs_meter_cmd_del(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr **a = info->attrs; + u32 meter_id; + struct ovs_header *ovs_header = info->userhdr; + struct ovs_header *ovs_reply_header; + struct datapath *dp; + int err; + struct sk_buff *reply; + struct dp_meter *old_meter; + + if (!a[OVS_METER_ATTR_ID]) + return -EINVAL; + meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]); + + reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_DEL, + &ovs_reply_header); + if (IS_ERR(reply)) + return PTR_ERR(reply); + + ovs_lock(); + + dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); + if (!dp) { + err = -ENODEV; + goto exit_unlock; + } + + old_meter = lookup_meter(dp, meter_id); + if (old_meter) { + spin_lock_bh(&old_meter->lock); + err = ovs_meter_cmd_reply_stats(reply, meter_id, old_meter); + WARN_ON(err); + spin_unlock_bh(&old_meter->lock); + detach_meter(old_meter); + } + ovs_unlock(); + ovs_meter_free(old_meter); + genlmsg_end(reply, ovs_reply_header); + return genlmsg_reply(reply, info); + +exit_unlock: + ovs_unlock(); + nlmsg_free(reply); + return err; +} + +/* Meter action execution. + * + * Return true 'meter_id' drop band is triggered. The 'skb' should be + * dropped by the caller'. + */ +bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb, + struct sw_flow_key *key, u32 meter_id) +{ + struct dp_meter *meter; + struct dp_meter_band *band; + long long int now_ms = div_u64(ktime_get_ns(), 1000 * 1000); + long long int long_delta_ms; + u32 delta_ms; + u32 cost; + int i, band_exceeded_max = -1; + u32 band_exceeded_rate = 0; + + meter = lookup_meter(dp, meter_id); + /* Do not drop the packet when there is no meter. */ + if (!meter) + return false; + + /* Lock the meter while using it. */ + spin_lock(&meter->lock); + + long_delta_ms = (now_ms - meter->used); /* ms */ + + /* Make sure delta_ms will not be too large, so that bucket will not + * wrap around below. + */ + delta_ms = (long_delta_ms > (long long int)meter->max_delta_t) + ? meter->max_delta_t : (u32)long_delta_ms; + + /* Update meter statistics. + */ + meter->used = now_ms; + meter->stats.n_packets += 1; + meter->stats.n_bytes += skb->len; + + /* Bucket rate is either in kilobits per second, or in packets per + * second. We maintain the bucket in the units of either bits or + * 1/1000th of a packet, correspondingly. + * Then, when rate is multiplied with milliseconds, we get the + * bucket units: + * msec * kbps = bits, and + * msec * packets/sec = 1/1000 packets. + * + * 'cost' is the number of bucket units in this packet. + */ + cost = (meter->kbps) ? skb->len * 8 : 1000; + + /* Update all bands and find the one hit with the highest rate. */ + for (i = 0; i < meter->n_bands; ++i) { + long long int max_bucket_size; + + band = &meter->bands[i]; + max_bucket_size = (band->burst_size + band->rate) * 1000; + + band->bucket += delta_ms * band->rate; + if (band->bucket > max_bucket_size) + band->bucket = max_bucket_size; + + if (band->bucket >= cost) { + band->bucket -= cost; + } else if (band->rate > band_exceeded_rate) { + band_exceeded_rate = band->rate; + band_exceeded_max = i; + } + } + + if (band_exceeded_max >= 0) { + /* Update band statistics. */ + band = &meter->bands[band_exceeded_max]; + band->stats.n_packets += 1; + band->stats.n_bytes += skb->len; + + /* Drop band triggered, let the caller drop the 'skb'. */ + if (band->type == OVS_METER_BAND_TYPE_DROP) { + spin_unlock(&meter->lock); + return true; + } + } + + spin_unlock(&meter->lock); + return false; +} + +static struct genl_ops dp_meter_genl_ops[] = { + { .cmd = OVS_METER_CMD_FEATURES, + .flags = 0, /* OK for unprivileged users. */ + .policy = meter_policy, + .doit = ovs_meter_cmd_features + }, + { .cmd = OVS_METER_CMD_SET, + .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN + * privilege. + */ + .policy = meter_policy, + .doit = ovs_meter_cmd_set, + }, + { .cmd = OVS_METER_CMD_GET, + .flags = 0, /* OK for unprivileged users. */ + .policy = meter_policy, + .doit = ovs_meter_cmd_get, + }, + { .cmd = OVS_METER_CMD_DEL, + .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN + * privilege. + */ + .policy = meter_policy, + .doit = ovs_meter_cmd_del + }, +}; + +static const struct genl_multicast_group ovs_meter_multicast_group = { + .name = OVS_METER_MCGROUP, +}; + +struct genl_family dp_meter_genl_family __ro_after_init = { + .hdrsize = sizeof(struct ovs_header), + .name = OVS_METER_FAMILY, + .version = OVS_METER_VERSION, + .maxattr = OVS_METER_ATTR_MAX, + .netnsok = true, + .parallel_ops = true, + .ops = dp_meter_genl_ops, + .n_ops = ARRAY_SIZE(dp_meter_genl_ops), + .mcgrps = &ovs_meter_multicast_group, + .n_mcgrps = 1, + .module = THIS_MODULE, +}; + +int ovs_meters_init(struct datapath *dp) +{ + int i; + + dp->meters = kmalloc_array(METER_HASH_BUCKETS, + sizeof(struct hlist_head), GFP_KERNEL); + + if (!dp->meters) + return -ENOMEM; + + for (i = 0; i < METER_HASH_BUCKETS; i++) + INIT_HLIST_HEAD(&dp->meters[i]); + + return 0; +} + +void ovs_meters_exit(struct datapath *dp) +{ + int i; + + for (i = 0; i < METER_HASH_BUCKETS; i++) { + struct hlist_head *head = &dp->meters[i]; + struct dp_meter *meter; + struct hlist_node *n; + + hlist_for_each_entry_safe(meter, n, head, dp_hash_node) + kfree(meter); + } + + kfree(dp->meters); +} diff --git a/net/openvswitch/meter.h b/net/openvswitch/meter.h new file mode 100644 index 000000000000..964ace2650f8 --- /dev/null +++ b/net/openvswitch/meter.h @@ -0,0 +1,54 @@ +/* + * Copyright (c) 2017 Nicira, Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ + +#ifndef METER_H +#define METER_H 1 + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/netlink.h> +#include <linux/openvswitch.h> +#include <linux/genetlink.h> +#include <linux/skbuff.h> + +#include "flow.h" +struct datapath; + +#define DP_MAX_BANDS 1 + +struct dp_meter_band { + u32 type; + u32 rate; + u32 burst_size; + u32 bucket; /* 1/1000 packets, or in bits */ + struct ovs_flow_stats stats; +}; + +struct dp_meter { + spinlock_t lock; /* Per meter lock */ + struct rcu_head rcu; + struct hlist_node dp_hash_node; /*Element in datapath->meters + * hash table. + */ + u32 id; + u16 kbps:1, keep_stats:1; + u16 n_bands; + u32 max_delta_t; + u64 used; + struct ovs_flow_stats stats; + struct dp_meter_band bands[]; +}; + +extern struct genl_family dp_meter_genl_family; +int ovs_meters_init(struct datapath *dp); +void ovs_meters_exit(struct datapath *dp); +bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb, + struct sw_flow_key *key, u32 meter_id); + +#endif /* meter.h */ diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index 0389398fa4ab..2e5e7a41d8ef 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -108,7 +108,8 @@ struct vport *ovs_netdev_link(struct vport *vport, const char *name) rtnl_lock(); err = netdev_master_upper_dev_link(vport->dev, - get_dpdev(vport->dp), NULL, NULL); + get_dpdev(vport->dp), + NULL, NULL, NULL); if (err) goto error_unlock; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 2986941164b1..737092ca9b4e 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -201,11 +201,8 @@ static void prb_retire_current_block(struct tpacket_kbdq_core *, static int prb_queue_frozen(struct tpacket_kbdq_core *); static void prb_open_block(struct tpacket_kbdq_core *, struct tpacket_block_desc *); -static void prb_retire_rx_blk_timer_expired(unsigned long); +static void prb_retire_rx_blk_timer_expired(struct timer_list *); static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *); -static void prb_init_blk_timer(struct packet_sock *, - struct tpacket_kbdq_core *, - void (*func) (unsigned long)); static void prb_fill_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void prb_clear_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *); @@ -540,22 +537,14 @@ static void prb_shutdown_retire_blk_timer(struct packet_sock *po, prb_del_retire_blk_timer(pkc); } -static void prb_init_blk_timer(struct packet_sock *po, - struct tpacket_kbdq_core *pkc, - void (*func) (unsigned long)) -{ - init_timer(&pkc->retire_blk_timer); - pkc->retire_blk_timer.data = (long)po; - pkc->retire_blk_timer.function = func; - pkc->retire_blk_timer.expires = jiffies; -} - static void prb_setup_retire_blk_timer(struct packet_sock *po) { struct tpacket_kbdq_core *pkc; pkc = GET_PBDQC_FROM_RB(&po->rx_ring); - prb_init_blk_timer(po, pkc, prb_retire_rx_blk_timer_expired); + timer_setup(&pkc->retire_blk_timer, prb_retire_rx_blk_timer_expired, + 0); + pkc->retire_blk_timer.expires = jiffies; } static int prb_calc_retire_blk_tmo(struct packet_sock *po, @@ -673,9 +662,10 @@ static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *pkc) * prb_calc_retire_blk_tmo() calculates the tmo. * */ -static void prb_retire_rx_blk_timer_expired(unsigned long data) +static void prb_retire_rx_blk_timer_expired(struct timer_list *t) { - struct packet_sock *po = (struct packet_sock *)data; + struct packet_sock *po = + from_timer(po, t, rx_ring.prb_bdqc.retire_blk_timer); struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(&po->rx_ring); unsigned int frozen; struct tpacket_block_desc *pbd; @@ -4570,6 +4560,7 @@ static int __net_init packet_net_init(struct net *net) static void __net_exit packet_net_exit(struct net *net) { remove_proc_entry("packet", net->proc_net); + WARN_ON_ONCE(!hlist_empty(&net->packet.sklist)); } static struct pernet_operations packet_net_ops = { diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index f925753668a7..3b0ef691f5b1 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -35,11 +35,11 @@ #include <net/phonet/pn_dev.h> /* Transport protocol registration */ -static struct phonet_protocol *proto_tab[PHONET_NPROTO] __read_mostly; +static const struct phonet_protocol *proto_tab[PHONET_NPROTO] __read_mostly; -static struct phonet_protocol *phonet_proto_get(unsigned int protocol) +static const struct phonet_protocol *phonet_proto_get(unsigned int protocol) { - struct phonet_protocol *pp; + const struct phonet_protocol *pp; if (protocol >= PHONET_NPROTO) return NULL; @@ -53,7 +53,7 @@ static struct phonet_protocol *phonet_proto_get(unsigned int protocol) return pp; } -static inline void phonet_proto_put(struct phonet_protocol *pp) +static inline void phonet_proto_put(const struct phonet_protocol *pp) { module_put(pp->prot->owner); } @@ -65,7 +65,7 @@ static int pn_socket_create(struct net *net, struct socket *sock, int protocol, { struct sock *sk; struct pn_sock *pn; - struct phonet_protocol *pnp; + const struct phonet_protocol *pnp; int err; if (!capable(CAP_SYS_ADMIN)) @@ -149,7 +149,7 @@ static int pn_header_parse(const struct sk_buff *skb, unsigned char *haddr) return 1; } -struct header_ops phonet_header_ops = { +const struct header_ops phonet_header_ops = { .create = pn_header_create, .parse = pn_header_parse, }; @@ -470,7 +470,7 @@ static struct packet_type phonet_packet_type __read_mostly = { static DEFINE_MUTEX(proto_tab_lock); int __init_or_module phonet_proto_register(unsigned int protocol, - struct phonet_protocol *pp) + const struct phonet_protocol *pp) { int err = 0; @@ -492,7 +492,8 @@ int __init_or_module phonet_proto_register(unsigned int protocol, } EXPORT_SYMBOL(phonet_proto_register); -void phonet_proto_unregister(unsigned int protocol, struct phonet_protocol *pp) +void phonet_proto_unregister(unsigned int protocol, + const struct phonet_protocol *pp) { mutex_lock(&proto_tab_lock); BUG_ON(proto_tab[protocol] != pp); diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c index 5e710435ffa9..b44fb9018fb8 100644 --- a/net/phonet/datagram.c +++ b/net/phonet/datagram.c @@ -195,7 +195,7 @@ static struct proto pn_proto = { .name = "PHONET", }; -static struct phonet_protocol pn_dgram_proto = { +static const struct phonet_protocol pn_dgram_proto = { .ops = &phonet_dgram_ops, .prot = &pn_proto, .sock_type = SOCK_DGRAM, diff --git a/net/phonet/pep.c b/net/phonet/pep.c index e81537991ddf..9fc76b19cd3c 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -1351,7 +1351,7 @@ static struct proto pep_proto = { .name = "PNPIPE", }; -static struct phonet_protocol pep_pn_proto = { +static const struct phonet_protocol pep_pn_proto = { .ops = &phonet_stream_ops, .prot = &pep_proto, .sock_type = SOCK_SEQPACKET, diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index 2cb4c5dfad6f..77787512fc32 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -331,7 +331,10 @@ static int __net_init phonet_init_net(struct net *net) static void __net_exit phonet_exit_net(struct net *net) { + struct phonet_net *pnn = phonet_pernet(net); + remove_proc_entry("phonet", net->proc_net); + WARN_ON_ONCE(!list_empty(&pnn->pndevs.list)); } static struct pernet_operations phonet_net_ops = { diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 78418f38464a..77ab05e23001 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -20,26 +20,15 @@ #include "qrtr.h" -#define QRTR_PROTO_VER 1 +#define QRTR_PROTO_VER_1 1 +#define QRTR_PROTO_VER_2 3 /* auto-bind range */ #define QRTR_MIN_EPH_SOCKET 0x4000 #define QRTR_MAX_EPH_SOCKET 0x7fff -enum qrtr_pkt_type { - QRTR_TYPE_DATA = 1, - QRTR_TYPE_HELLO = 2, - QRTR_TYPE_BYE = 3, - QRTR_TYPE_NEW_SERVER = 4, - QRTR_TYPE_DEL_SERVER = 5, - QRTR_TYPE_DEL_CLIENT = 6, - QRTR_TYPE_RESUME_TX = 7, - QRTR_TYPE_EXIT = 8, - QRTR_TYPE_PING = 9, -}; - /** - * struct qrtr_hdr - (I|R)PCrouter packet header + * struct qrtr_hdr_v1 - (I|R)PCrouter packet header version 1 * @version: protocol version * @type: packet type; one of QRTR_TYPE_* * @src_node_id: source node @@ -49,7 +38,7 @@ enum qrtr_pkt_type { * @dst_node_id: destination node * @dst_port_id: destination port */ -struct qrtr_hdr { +struct qrtr_hdr_v1 { __le32 version; __le32 type; __le32 src_node_id; @@ -60,9 +49,44 @@ struct qrtr_hdr { __le32 dst_port_id; } __packed; -#define QRTR_HDR_SIZE sizeof(struct qrtr_hdr) -#define QRTR_NODE_BCAST ((unsigned int)-1) -#define QRTR_PORT_CTRL ((unsigned int)-2) +/** + * struct qrtr_hdr_v2 - (I|R)PCrouter packet header later versions + * @version: protocol version + * @type: packet type; one of QRTR_TYPE_* + * @flags: bitmask of QRTR_FLAGS_* + * @optlen: length of optional header data + * @size: length of packet, excluding this header and optlen + * @src_node_id: source node + * @src_port_id: source port + * @dst_node_id: destination node + * @dst_port_id: destination port + */ +struct qrtr_hdr_v2 { + u8 version; + u8 type; + u8 flags; + u8 optlen; + __le32 size; + __le16 src_node_id; + __le16 src_port_id; + __le16 dst_node_id; + __le16 dst_port_id; +}; + +#define QRTR_FLAGS_CONFIRM_RX BIT(0) + +struct qrtr_cb { + u32 src_node; + u32 src_port; + u32 dst_node; + u32 dst_port; + + u8 type; + u8 confirm_rx; +}; + +#define QRTR_HDR_MAX_SIZE max_t(size_t, sizeof(struct qrtr_hdr_v1), \ + sizeof(struct qrtr_hdr_v2)) struct qrtr_sock { /* WARNING: sk must be the first member */ @@ -111,8 +135,12 @@ struct qrtr_node { struct list_head item; }; -static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb); -static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb); +static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb, + int type, struct sockaddr_qrtr *from, + struct sockaddr_qrtr *to); +static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb, + int type, struct sockaddr_qrtr *from, + struct sockaddr_qrtr *to); /* Release node resources and free the node. * @@ -150,10 +178,27 @@ static void qrtr_node_release(struct qrtr_node *node) } /* Pass an outgoing packet socket buffer to the endpoint driver. */ -static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb) +static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, + int type, struct sockaddr_qrtr *from, + struct sockaddr_qrtr *to) { + struct qrtr_hdr_v1 *hdr; + size_t len = skb->len; int rc = -ENODEV; + hdr = skb_push(skb, sizeof(*hdr)); + hdr->version = cpu_to_le32(QRTR_PROTO_VER_1); + hdr->type = cpu_to_le32(type); + hdr->src_node_id = cpu_to_le32(from->sq_node); + hdr->src_port_id = cpu_to_le32(from->sq_port); + hdr->dst_node_id = cpu_to_le32(to->sq_node); + hdr->dst_port_id = cpu_to_le32(to->sq_port); + + hdr->size = cpu_to_le32(len); + hdr->confirm_rx = 0; + + skb_put_padto(skb, ALIGN(len, 4)); + mutex_lock(&node->ep_lock); if (node->ep) rc = node->ep->xmit(node->ep, skb); @@ -207,125 +252,103 @@ static void qrtr_node_assign(struct qrtr_node *node, unsigned int nid) int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) { struct qrtr_node *node = ep->node; - const struct qrtr_hdr *phdr = data; + const struct qrtr_hdr_v1 *v1; + const struct qrtr_hdr_v2 *v2; struct sk_buff *skb; - unsigned int psize; + struct qrtr_cb *cb; unsigned int size; - unsigned int type; unsigned int ver; - unsigned int dst; - - if (len < QRTR_HDR_SIZE || len & 3) - return -EINVAL; - - ver = le32_to_cpu(phdr->version); - size = le32_to_cpu(phdr->size); - type = le32_to_cpu(phdr->type); - dst = le32_to_cpu(phdr->dst_port_id); - - psize = (size + 3) & ~3; + size_t hdrlen; - if (ver != QRTR_PROTO_VER) - return -EINVAL; - - if (len != psize + QRTR_HDR_SIZE) - return -EINVAL; - - if (dst != QRTR_PORT_CTRL && type != QRTR_TYPE_DATA) + if (len & 3) return -EINVAL; skb = netdev_alloc_skb(NULL, len); if (!skb) return -ENOMEM; - skb_reset_transport_header(skb); - skb_put_data(skb, data, len); - - skb_queue_tail(&node->rx_queue, skb); - schedule_work(&node->work); - - return 0; -} -EXPORT_SYMBOL_GPL(qrtr_endpoint_post); + cb = (struct qrtr_cb *)skb->cb; -static struct sk_buff *qrtr_alloc_ctrl_packet(u32 type, size_t pkt_len, - u32 src_node, u32 dst_node) -{ - struct qrtr_hdr *hdr; - struct sk_buff *skb; - - skb = alloc_skb(QRTR_HDR_SIZE + pkt_len, GFP_KERNEL); - if (!skb) - return NULL; - skb_reset_transport_header(skb); + /* Version field in v1 is little endian, so this works for both cases */ + ver = *(u8*)data; - hdr = skb_put(skb, QRTR_HDR_SIZE); - hdr->version = cpu_to_le32(QRTR_PROTO_VER); - hdr->type = cpu_to_le32(type); - hdr->src_node_id = cpu_to_le32(src_node); - hdr->src_port_id = cpu_to_le32(QRTR_PORT_CTRL); - hdr->confirm_rx = cpu_to_le32(0); - hdr->size = cpu_to_le32(pkt_len); - hdr->dst_node_id = cpu_to_le32(dst_node); - hdr->dst_port_id = cpu_to_le32(QRTR_PORT_CTRL); + switch (ver) { + case QRTR_PROTO_VER_1: + v1 = data; + hdrlen = sizeof(*v1); - return skb; -} + cb->type = le32_to_cpu(v1->type); + cb->src_node = le32_to_cpu(v1->src_node_id); + cb->src_port = le32_to_cpu(v1->src_port_id); + cb->confirm_rx = !!v1->confirm_rx; + cb->dst_node = le32_to_cpu(v1->dst_node_id); + cb->dst_port = le32_to_cpu(v1->dst_port_id); -/* Allocate and construct a resume-tx packet. */ -static struct sk_buff *qrtr_alloc_resume_tx(u32 src_node, - u32 dst_node, u32 port) -{ - const int pkt_len = 20; - struct sk_buff *skb; - __le32 *buf; + size = le32_to_cpu(v1->size); + break; + case QRTR_PROTO_VER_2: + v2 = data; + hdrlen = sizeof(*v2) + v2->optlen; + + cb->type = v2->type; + cb->confirm_rx = !!(v2->flags & QRTR_FLAGS_CONFIRM_RX); + cb->src_node = le16_to_cpu(v2->src_node_id); + cb->src_port = le16_to_cpu(v2->src_port_id); + cb->dst_node = le16_to_cpu(v2->dst_node_id); + cb->dst_port = le16_to_cpu(v2->dst_port_id); + + if (cb->src_port == (u16)QRTR_PORT_CTRL) + cb->src_port = QRTR_PORT_CTRL; + if (cb->dst_port == (u16)QRTR_PORT_CTRL) + cb->dst_port = QRTR_PORT_CTRL; + + size = le32_to_cpu(v2->size); + break; + default: + pr_err("qrtr: Invalid version %d\n", ver); + goto err; + } - skb = qrtr_alloc_ctrl_packet(QRTR_TYPE_RESUME_TX, pkt_len, - src_node, dst_node); - if (!skb) - return NULL; + if (len != ALIGN(size, 4) + hdrlen) + goto err; - buf = skb_put_zero(skb, pkt_len); - buf[0] = cpu_to_le32(QRTR_TYPE_RESUME_TX); - buf[1] = cpu_to_le32(src_node); - buf[2] = cpu_to_le32(port); + if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA) + goto err; - return skb; -} + skb_put_data(skb, data + hdrlen, size); -/* Allocate and construct a BYE message to signal remote termination */ -static struct sk_buff *qrtr_alloc_local_bye(u32 src_node) -{ - const int pkt_len = 20; - struct sk_buff *skb; - __le32 *buf; + skb_queue_tail(&node->rx_queue, skb); + schedule_work(&node->work); - skb = qrtr_alloc_ctrl_packet(QRTR_TYPE_BYE, pkt_len, - src_node, qrtr_local_nid); - if (!skb) - return NULL; + return 0; - buf = skb_put_zero(skb, pkt_len); - buf[0] = cpu_to_le32(QRTR_TYPE_BYE); +err: + kfree_skb(skb); + return -EINVAL; - return skb; } +EXPORT_SYMBOL_GPL(qrtr_endpoint_post); -static struct sk_buff *qrtr_alloc_del_client(struct sockaddr_qrtr *sq) +/** + * qrtr_alloc_ctrl_packet() - allocate control packet skb + * @pkt: reference to qrtr_ctrl_pkt pointer + * + * Returns newly allocated sk_buff, or NULL on failure + * + * This function allocates a sk_buff large enough to carry a qrtr_ctrl_pkt and + * on success returns a reference to the control packet in @pkt. + */ +static struct sk_buff *qrtr_alloc_ctrl_packet(struct qrtr_ctrl_pkt **pkt) { - const int pkt_len = 20; + const int pkt_len = sizeof(struct qrtr_ctrl_pkt); struct sk_buff *skb; - __le32 *buf; - skb = qrtr_alloc_ctrl_packet(QRTR_TYPE_DEL_CLIENT, pkt_len, - sq->sq_node, QRTR_NODE_BCAST); + skb = alloc_skb(QRTR_HDR_MAX_SIZE + pkt_len, GFP_KERNEL); if (!skb) return NULL; - buf = skb_put_zero(skb, pkt_len); - buf[0] = cpu_to_le32(QRTR_TYPE_DEL_CLIENT); - buf[1] = cpu_to_le32(sq->sq_node); - buf[2] = cpu_to_le32(sq->sq_port); + skb_reserve(skb, QRTR_HDR_MAX_SIZE); + *pkt = skb_put_zero(skb, pkt_len); return skb; } @@ -340,24 +363,26 @@ static void qrtr_port_put(struct qrtr_sock *ipc); static void qrtr_node_rx_work(struct work_struct *work) { struct qrtr_node *node = container_of(work, struct qrtr_node, work); + struct qrtr_ctrl_pkt *pkt; + struct sockaddr_qrtr dst; + struct sockaddr_qrtr src; struct sk_buff *skb; while ((skb = skb_dequeue(&node->rx_queue)) != NULL) { - const struct qrtr_hdr *phdr; - u32 dst_node, dst_port; struct qrtr_sock *ipc; - u32 src_node; + struct qrtr_cb *cb; int confirm; - phdr = (const struct qrtr_hdr *)skb_transport_header(skb); - src_node = le32_to_cpu(phdr->src_node_id); - dst_node = le32_to_cpu(phdr->dst_node_id); - dst_port = le32_to_cpu(phdr->dst_port_id); - confirm = !!phdr->confirm_rx; + cb = (struct qrtr_cb *)skb->cb; + src.sq_node = cb->src_node; + src.sq_port = cb->src_port; + dst.sq_node = cb->dst_node; + dst.sq_port = cb->dst_port; + confirm = !!cb->confirm_rx; - qrtr_node_assign(node, src_node); + qrtr_node_assign(node, cb->src_node); - ipc = qrtr_port_lookup(dst_port); + ipc = qrtr_port_lookup(cb->dst_port); if (!ipc) { kfree_skb(skb); } else { @@ -368,10 +393,16 @@ static void qrtr_node_rx_work(struct work_struct *work) } if (confirm) { - skb = qrtr_alloc_resume_tx(dst_node, node->nid, dst_port); + skb = qrtr_alloc_ctrl_packet(&pkt); if (!skb) break; - if (qrtr_node_enqueue(node, skb)) + + pkt->cmd = cpu_to_le32(QRTR_TYPE_RESUME_TX); + pkt->client.node = cpu_to_le32(dst.sq_node); + pkt->client.port = cpu_to_le32(dst.sq_port); + + if (qrtr_node_enqueue(node, skb, QRTR_TYPE_RESUME_TX, + &dst, &src)) break; } } @@ -421,6 +452,9 @@ EXPORT_SYMBOL_GPL(qrtr_endpoint_register); void qrtr_endpoint_unregister(struct qrtr_endpoint *ep) { struct qrtr_node *node = ep->node; + struct sockaddr_qrtr src = {AF_QIPCRTR, node->nid, QRTR_PORT_CTRL}; + struct sockaddr_qrtr dst = {AF_QIPCRTR, qrtr_local_nid, QRTR_PORT_CTRL}; + struct qrtr_ctrl_pkt *pkt; struct sk_buff *skb; mutex_lock(&node->ep_lock); @@ -428,9 +462,11 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep) mutex_unlock(&node->ep_lock); /* Notify the local controller about the event */ - skb = qrtr_alloc_local_bye(node->nid); - if (skb) - qrtr_local_enqueue(NULL, skb); + skb = qrtr_alloc_ctrl_packet(&pkt); + if (skb) { + pkt->cmd = cpu_to_le32(QRTR_TYPE_BYE); + qrtr_local_enqueue(NULL, skb, QRTR_TYPE_BYE, &src, &dst); + } qrtr_node_release(node); ep->node = NULL; @@ -466,13 +502,24 @@ static void qrtr_port_put(struct qrtr_sock *ipc) /* Remove port assignment. */ static void qrtr_port_remove(struct qrtr_sock *ipc) { + struct qrtr_ctrl_pkt *pkt; struct sk_buff *skb; int port = ipc->us.sq_port; + struct sockaddr_qrtr to; - skb = qrtr_alloc_del_client(&ipc->us); + to.sq_family = AF_QIPCRTR; + to.sq_node = QRTR_NODE_BCAST; + to.sq_port = QRTR_PORT_CTRL; + + skb = qrtr_alloc_ctrl_packet(&pkt); if (skb) { + pkt->cmd = cpu_to_le32(QRTR_TYPE_DEL_CLIENT); + pkt->client.node = cpu_to_le32(ipc->us.sq_node); + pkt->client.port = cpu_to_le32(ipc->us.sq_port); + skb_set_owner_w(skb, &ipc->sk); - qrtr_bcast_enqueue(NULL, skb); + qrtr_bcast_enqueue(NULL, skb, QRTR_TYPE_DEL_CLIENT, &ipc->us, + &to); } if (port == QRTR_PORT_CTRL) @@ -541,7 +588,7 @@ static void qrtr_reset_ports(void) sock_hold(&ipc->sk); ipc->sk.sk_err = ENETRESET; - wake_up_interruptible(sk_sleep(&ipc->sk)); + ipc->sk.sk_error_report(&ipc->sk); sock_put(&ipc->sk); } mutex_unlock(&qrtr_port_lock); @@ -620,19 +667,23 @@ static int qrtr_bind(struct socket *sock, struct sockaddr *saddr, int len) } /* Queue packet to local peer socket. */ -static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb) +static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb, + int type, struct sockaddr_qrtr *from, + struct sockaddr_qrtr *to) { - const struct qrtr_hdr *phdr; struct qrtr_sock *ipc; + struct qrtr_cb *cb; - phdr = (const struct qrtr_hdr *)skb_transport_header(skb); - - ipc = qrtr_port_lookup(le32_to_cpu(phdr->dst_port_id)); + ipc = qrtr_port_lookup(to->sq_port); if (!ipc || &ipc->sk == skb->sk) { /* do not send to self */ kfree_skb(skb); return -ENODEV; } + cb = (struct qrtr_cb *)skb->cb; + cb->src_node = from->sq_node; + cb->src_port = from->sq_port; + if (sock_queue_rcv_skb(&ipc->sk, skb)) { qrtr_port_put(ipc); kfree_skb(skb); @@ -645,7 +696,9 @@ static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb) } /* Queue packet for broadcast. */ -static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb) +static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb, + int type, struct sockaddr_qrtr *from, + struct sockaddr_qrtr *to) { struct sk_buff *skbn; @@ -655,11 +708,11 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb) if (!skbn) break; skb_set_owner_w(skbn, skb->sk); - qrtr_node_enqueue(node, skbn); + qrtr_node_enqueue(node, skbn, type, from, to); } mutex_unlock(&qrtr_node_lock); - qrtr_local_enqueue(node, skb); + qrtr_local_enqueue(node, skb, type, from, to); return 0; } @@ -667,13 +720,14 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb) static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { DECLARE_SOCKADDR(struct sockaddr_qrtr *, addr, msg->msg_name); - int (*enqueue_fn)(struct qrtr_node *, struct sk_buff *); + int (*enqueue_fn)(struct qrtr_node *, struct sk_buff *, int, + struct sockaddr_qrtr *, struct sockaddr_qrtr *); struct qrtr_sock *ipc = qrtr_sk(sock->sk); struct sock *sk = sock->sk; struct qrtr_node *node; - struct qrtr_hdr *hdr; struct sk_buff *skb; size_t plen; + u32 type = QRTR_TYPE_DATA; int rc; if (msg->msg_flags & ~(MSG_DONTWAIT)) @@ -722,37 +776,19 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) } plen = (len + 3) & ~3; - skb = sock_alloc_send_skb(sk, plen + QRTR_HDR_SIZE, + skb = sock_alloc_send_skb(sk, plen + QRTR_HDR_MAX_SIZE, msg->msg_flags & MSG_DONTWAIT, &rc); if (!skb) goto out_node; - skb_reset_transport_header(skb); - skb_put(skb, len + QRTR_HDR_SIZE); - - hdr = (struct qrtr_hdr *)skb_transport_header(skb); - hdr->version = cpu_to_le32(QRTR_PROTO_VER); - hdr->src_node_id = cpu_to_le32(ipc->us.sq_node); - hdr->src_port_id = cpu_to_le32(ipc->us.sq_port); - hdr->confirm_rx = cpu_to_le32(0); - hdr->size = cpu_to_le32(len); - hdr->dst_node_id = cpu_to_le32(addr->sq_node); - hdr->dst_port_id = cpu_to_le32(addr->sq_port); + skb_reserve(skb, QRTR_HDR_MAX_SIZE); - rc = skb_copy_datagram_from_iter(skb, QRTR_HDR_SIZE, - &msg->msg_iter, len); + rc = memcpy_from_msg(skb_put(skb, len), msg, len); if (rc) { kfree_skb(skb); goto out_node; } - if (plen != len) { - rc = skb_pad(skb, plen - len); - if (rc) - goto out_node; - skb_put(skb, plen - len); - } - if (ipc->us.sq_port == QRTR_PORT_CTRL) { if (len < 4) { rc = -EINVAL; @@ -761,12 +797,11 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) } /* control messages already require the type as 'command' */ - skb_copy_bits(skb, QRTR_HDR_SIZE, &hdr->type, 4); - } else { - hdr->type = cpu_to_le32(QRTR_TYPE_DATA); + skb_copy_bits(skb, 0, &type, 4); + type = le32_to_cpu(type); } - rc = enqueue_fn(node, skb); + rc = enqueue_fn(node, skb, type, &ipc->us, addr); if (rc >= 0) rc = len; @@ -781,9 +816,9 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { DECLARE_SOCKADDR(struct sockaddr_qrtr *, addr, msg->msg_name); - const struct qrtr_hdr *phdr; struct sock *sk = sock->sk; struct sk_buff *skb; + struct qrtr_cb *cb; int copied, rc; lock_sock(sk); @@ -800,22 +835,22 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg, return rc; } - phdr = (const struct qrtr_hdr *)skb_transport_header(skb); - copied = le32_to_cpu(phdr->size); + copied = skb->len; if (copied > size) { copied = size; msg->msg_flags |= MSG_TRUNC; } - rc = skb_copy_datagram_msg(skb, QRTR_HDR_SIZE, msg, copied); + rc = skb_copy_datagram_msg(skb, 0, msg, copied); if (rc < 0) goto out; rc = copied; if (addr) { + cb = (struct qrtr_cb *)skb->cb; addr->sq_family = AF_QIPCRTR; - addr->sq_node = le32_to_cpu(phdr->src_node_id); - addr->sq_port = le32_to_cpu(phdr->src_port_id); + addr->sq_node = cb->src_node; + addr->sq_port = cb->src_port; msg->msg_namelen = sizeof(*addr); } @@ -908,7 +943,7 @@ static int qrtr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) case TIOCINQ: skb = skb_peek(&sk->sk_receive_queue); if (skb) - len = skb->len - QRTR_HDR_SIZE; + len = skb->len; rc = put_user(len, (int __user *)argp); break; case SIOCGIFADDR: diff --git a/net/rds/ib.c b/net/rds/ib.c index a0954ace3774..36dd2099048a 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -126,6 +126,7 @@ void rds_ib_dev_put(struct rds_ib_device *rds_ibdev) static void rds_ib_add_one(struct ib_device *device) { struct rds_ib_device *rds_ibdev; + bool has_fr, has_fmr; /* Only handle IB (no iWARP) devices */ if (device->node_type != RDMA_NODE_IB_CA) @@ -143,11 +144,11 @@ static void rds_ib_add_one(struct ib_device *device) rds_ibdev->max_wrs = device->attrs.max_qp_wr; rds_ibdev->max_sge = min(device->attrs.max_sge, RDS_IB_MAX_SGE); - rds_ibdev->has_fr = (device->attrs.device_cap_flags & - IB_DEVICE_MEM_MGT_EXTENSIONS); - rds_ibdev->has_fmr = (device->alloc_fmr && device->dealloc_fmr && - device->map_phys_fmr && device->unmap_fmr); - rds_ibdev->use_fastreg = (rds_ibdev->has_fr && !rds_ibdev->has_fmr); + has_fr = (device->attrs.device_cap_flags & + IB_DEVICE_MEM_MGT_EXTENSIONS); + has_fmr = (device->alloc_fmr && device->dealloc_fmr && + device->map_phys_fmr && device->unmap_fmr); + rds_ibdev->use_fastreg = (has_fr && !has_fmr); rds_ibdev->fmr_max_remaps = device->attrs.max_map_per_fmr?: 32; rds_ibdev->max_1m_mrs = device->attrs.max_mr ? diff --git a/net/rds/ib.h b/net/rds/ib.h index 86a8578d95b8..a6f4d7d68e95 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -216,8 +216,6 @@ struct rds_ib_device { struct list_head conn_list; struct ib_device *dev; struct ib_pd *pd; - bool has_fmr; - bool has_fr; bool use_fastreg; unsigned int max_mrs; diff --git a/net/rds/ib_fmr.c b/net/rds/ib_fmr.c index 86ef907067bb..e0f70c4051b6 100644 --- a/net/rds/ib_fmr.c +++ b/net/rds/ib_fmr.c @@ -139,8 +139,8 @@ static int rds_ib_map_fmr(struct rds_ib_device *rds_ibdev, return -EINVAL; } - dma_pages = kmalloc_node(sizeof(u64) * page_cnt, GFP_ATOMIC, - rdsibdev_to_node(rds_ibdev)); + dma_pages = kmalloc_array_node(sizeof(u64), page_cnt, GFP_ATOMIC, + rdsibdev_to_node(rds_ibdev)); if (!dma_pages) { ib_dma_unmap_sg(dev, sg, nents, DMA_BIDIRECTIONAL); return -ENOMEM; diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index 9a3c54e659e9..e678699268a2 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -601,11 +601,11 @@ struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *rds_ibdev, if (pool_type == RDS_IB_MR_1M_POOL) { /* +1 allows for unaligned MRs */ pool->fmr_attr.max_pages = RDS_MR_1M_MSG_SIZE + 1; - pool->max_items = RDS_MR_1M_POOL_SIZE; + pool->max_items = rds_ibdev->max_1m_mrs; } else { /* pool_type == RDS_IB_MR_8K_POOL */ pool->fmr_attr.max_pages = RDS_MR_8K_MSG_SIZE + 1; - pool->max_items = RDS_MR_8K_POOL_SIZE; + pool->max_items = rds_ibdev->max_8k_mrs; } pool->max_free_pinned = pool->max_items * pool->fmr_attr.max_pages / 4; diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 4a9729257023..6a5c4992cf61 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -318,9 +318,11 @@ void rose_destroy_socket(struct sock *); /* * Handler for deferred kills. */ -static void rose_destroy_timer(unsigned long data) +static void rose_destroy_timer(struct timer_list *t) { - rose_destroy_socket((struct sock *)data); + struct sock *sk = from_timer(sk, t, sk_timer); + + rose_destroy_socket(sk); } /* @@ -353,8 +355,7 @@ void rose_destroy_socket(struct sock *sk) if (sk_has_allocations(sk)) { /* Defer: outstanding buffers */ - setup_timer(&sk->sk_timer, rose_destroy_timer, - (unsigned long)sk); + timer_setup(&sk->sk_timer, rose_destroy_timer, 0); sk->sk_timer.expires = jiffies + 10 * HZ; add_timer(&sk->sk_timer); } else @@ -538,8 +539,8 @@ static int rose_create(struct net *net, struct socket *sock, int protocol, sock->ops = &rose_proto_ops; sk->sk_protocol = protocol; - init_timer(&rose->timer); - init_timer(&rose->idletimer); + timer_setup(&rose->timer, NULL, 0); + timer_setup(&rose->idletimer, NULL, 0); rose->t1 = msecs_to_jiffies(sysctl_rose_call_request_timeout); rose->t2 = msecs_to_jiffies(sysctl_rose_reset_request_timeout); @@ -582,8 +583,8 @@ static struct sock *rose_make_new(struct sock *osk) sk->sk_state = TCP_ESTABLISHED; sock_copy_flags(sk, osk); - init_timer(&rose->timer); - init_timer(&rose->idletimer); + timer_setup(&rose->timer, NULL, 0); + timer_setup(&rose->idletimer, NULL, 0); orose = rose_sk(osk); rose->t1 = orose->t1; diff --git a/net/rose/rose_in.c b/net/rose/rose_in.c index 0a6394754e81..9bbbfe325c5a 100644 --- a/net/rose/rose_in.c +++ b/net/rose/rose_in.c @@ -219,6 +219,7 @@ static int rose_state4_machine(struct sock *sk, struct sk_buff *skb, int framety switch (frametype) { case ROSE_RESET_REQUEST: rose_write_internal(sk, ROSE_RESET_CONFIRMATION); + /* fall through */ case ROSE_RESET_CONFIRMATION: rose_stop_timer(sk); rose_start_idletimer(sk); diff --git a/net/rose/rose_link.c b/net/rose/rose_link.c index c76638cc2cd5..cda4c6678ef1 100644 --- a/net/rose/rose_link.c +++ b/net/rose/rose_link.c @@ -27,8 +27,8 @@ #include <linux/interrupt.h> #include <net/rose.h> -static void rose_ftimer_expiry(unsigned long); -static void rose_t0timer_expiry(unsigned long); +static void rose_ftimer_expiry(struct timer_list *); +static void rose_t0timer_expiry(struct timer_list *); static void rose_transmit_restart_confirmation(struct rose_neigh *neigh); static void rose_transmit_restart_request(struct rose_neigh *neigh); @@ -37,8 +37,7 @@ void rose_start_ftimer(struct rose_neigh *neigh) { del_timer(&neigh->ftimer); - neigh->ftimer.data = (unsigned long)neigh; - neigh->ftimer.function = &rose_ftimer_expiry; + neigh->ftimer.function = (TIMER_FUNC_TYPE)rose_ftimer_expiry; neigh->ftimer.expires = jiffies + msecs_to_jiffies(sysctl_rose_link_fail_timeout); @@ -49,8 +48,7 @@ static void rose_start_t0timer(struct rose_neigh *neigh) { del_timer(&neigh->t0timer); - neigh->t0timer.data = (unsigned long)neigh; - neigh->t0timer.function = &rose_t0timer_expiry; + neigh->t0timer.function = (TIMER_FUNC_TYPE)rose_t0timer_expiry; neigh->t0timer.expires = jiffies + msecs_to_jiffies(sysctl_rose_restart_request_timeout); @@ -77,13 +75,13 @@ static int rose_t0timer_running(struct rose_neigh *neigh) return timer_pending(&neigh->t0timer); } -static void rose_ftimer_expiry(unsigned long param) +static void rose_ftimer_expiry(struct timer_list *t) { } -static void rose_t0timer_expiry(unsigned long param) +static void rose_t0timer_expiry(struct timer_list *t) { - struct rose_neigh *neigh = (struct rose_neigh *)param; + struct rose_neigh *neigh = from_timer(neigh, t, t0timer); rose_transmit_restart_request(neigh); diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c index 344456206b70..7af4f99c4a93 100644 --- a/net/rose/rose_loopback.c +++ b/net/rose/rose_loopback.c @@ -19,12 +19,13 @@ static struct sk_buff_head loopback_queue; static struct timer_list loopback_timer; static void rose_set_loopback_timer(void); +static void rose_loopback_timer(struct timer_list *unused); void rose_loopback_init(void) { skb_queue_head_init(&loopback_queue); - init_timer(&loopback_timer); + timer_setup(&loopback_timer, rose_loopback_timer, 0); } static int rose_loopback_running(void) @@ -50,20 +51,16 @@ int rose_loopback_queue(struct sk_buff *skb, struct rose_neigh *neigh) return 1; } -static void rose_loopback_timer(unsigned long); static void rose_set_loopback_timer(void) { del_timer(&loopback_timer); - loopback_timer.data = 0; - loopback_timer.function = &rose_loopback_timer; loopback_timer.expires = jiffies + 10; - add_timer(&loopback_timer); } -static void rose_loopback_timer(unsigned long param) +static void rose_loopback_timer(struct timer_list *unused) { struct sk_buff *skb; struct net_device *dev; diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index 452bbb38d943..8ca3124df83f 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -104,8 +104,8 @@ static int __must_check rose_add_node(struct rose_route_struct *rose_route, skb_queue_head_init(&rose_neigh->queue); - init_timer(&rose_neigh->ftimer); - init_timer(&rose_neigh->t0timer); + timer_setup(&rose_neigh->ftimer, NULL, 0); + timer_setup(&rose_neigh->t0timer, NULL, 0); if (rose_route->ndigis != 0) { rose_neigh->digipeat = @@ -346,6 +346,7 @@ static int rose_del_node(struct rose_route_struct *rose_route, case 0: rose_node->neighbour[0] = rose_node->neighbour[1]; + /* fall through */ case 1: rose_node->neighbour[1] = rose_node->neighbour[2]; @@ -390,8 +391,8 @@ void rose_add_loopback_neigh(void) skb_queue_head_init(&sn->queue); - init_timer(&sn->ftimer); - init_timer(&sn->t0timer); + timer_setup(&sn->ftimer, NULL, 0); + timer_setup(&sn->t0timer, NULL, 0); spin_lock_bh(&rose_neigh_list_lock); sn->next = rose_neigh_list; @@ -507,6 +508,7 @@ void rose_rt_device_down(struct net_device *dev) switch (i) { case 0: t->neighbour[0] = t->neighbour[1]; + /* fall through */ case 1: t->neighbour[1] = t->neighbour[2]; case 2: diff --git a/net/rose/rose_timer.c b/net/rose/rose_timer.c index bc5469d6d9cb..ea613b2a9735 100644 --- a/net/rose/rose_timer.c +++ b/net/rose/rose_timer.c @@ -28,16 +28,15 @@ #include <linux/interrupt.h> #include <net/rose.h> -static void rose_heartbeat_expiry(unsigned long); -static void rose_timer_expiry(unsigned long); -static void rose_idletimer_expiry(unsigned long); +static void rose_heartbeat_expiry(struct timer_list *t); +static void rose_timer_expiry(struct timer_list *); +static void rose_idletimer_expiry(struct timer_list *); void rose_start_heartbeat(struct sock *sk) { del_timer(&sk->sk_timer); - sk->sk_timer.data = (unsigned long)sk; - sk->sk_timer.function = &rose_heartbeat_expiry; + sk->sk_timer.function = (TIMER_FUNC_TYPE)rose_heartbeat_expiry; sk->sk_timer.expires = jiffies + 5 * HZ; add_timer(&sk->sk_timer); @@ -49,8 +48,7 @@ void rose_start_t1timer(struct sock *sk) del_timer(&rose->timer); - rose->timer.data = (unsigned long)sk; - rose->timer.function = &rose_timer_expiry; + rose->timer.function = (TIMER_FUNC_TYPE)rose_timer_expiry; rose->timer.expires = jiffies + rose->t1; add_timer(&rose->timer); @@ -62,8 +60,7 @@ void rose_start_t2timer(struct sock *sk) del_timer(&rose->timer); - rose->timer.data = (unsigned long)sk; - rose->timer.function = &rose_timer_expiry; + rose->timer.function = (TIMER_FUNC_TYPE)rose_timer_expiry; rose->timer.expires = jiffies + rose->t2; add_timer(&rose->timer); @@ -75,8 +72,7 @@ void rose_start_t3timer(struct sock *sk) del_timer(&rose->timer); - rose->timer.data = (unsigned long)sk; - rose->timer.function = &rose_timer_expiry; + rose->timer.function = (TIMER_FUNC_TYPE)rose_timer_expiry; rose->timer.expires = jiffies + rose->t3; add_timer(&rose->timer); @@ -88,8 +84,7 @@ void rose_start_hbtimer(struct sock *sk) del_timer(&rose->timer); - rose->timer.data = (unsigned long)sk; - rose->timer.function = &rose_timer_expiry; + rose->timer.function = (TIMER_FUNC_TYPE)rose_timer_expiry; rose->timer.expires = jiffies + rose->hb; add_timer(&rose->timer); @@ -102,8 +97,7 @@ void rose_start_idletimer(struct sock *sk) del_timer(&rose->idletimer); if (rose->idle > 0) { - rose->idletimer.data = (unsigned long)sk; - rose->idletimer.function = &rose_idletimer_expiry; + rose->idletimer.function = (TIMER_FUNC_TYPE)rose_idletimer_expiry; rose->idletimer.expires = jiffies + rose->idle; add_timer(&rose->idletimer); @@ -125,9 +119,9 @@ void rose_stop_idletimer(struct sock *sk) del_timer(&rose_sk(sk)->idletimer); } -static void rose_heartbeat_expiry(unsigned long param) +static void rose_heartbeat_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; + struct sock *sk = from_timer(sk, t, sk_timer); struct rose_sock *rose = rose_sk(sk); bh_lock_sock(sk); @@ -163,10 +157,10 @@ static void rose_heartbeat_expiry(unsigned long param) bh_unlock_sock(sk); } -static void rose_timer_expiry(unsigned long param) +static void rose_timer_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; - struct rose_sock *rose = rose_sk(sk); + struct rose_sock *rose = from_timer(rose, t, timer); + struct sock *sk = &rose->sock; bh_lock_sock(sk); switch (rose->state) { @@ -192,9 +186,10 @@ static void rose_timer_expiry(unsigned long param) bh_unlock_sock(sk); } -static void rose_idletimer_expiry(unsigned long param) +static void rose_idletimer_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; + struct rose_sock *rose = from_timer(rose, t, idletimer); + struct sock *sk = &rose->sock; bh_lock_sock(sk); rose_clear_queues(sk); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 4b0a8288c98a..9b5c46b052fd 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -246,6 +246,7 @@ static int rxrpc_listen(struct socket *sock, int backlog) ret = 0; break; } + /* Fall through */ default: ret = -EBUSY; break; @@ -265,6 +266,7 @@ static int rxrpc_listen(struct socket *sock, int backlog) * @tx_total_len: Total length of data to transmit during the call (or -1) * @gfp: The allocation constraints * @notify_rx: Where to send notifications instead of socket queue + * @upgrade: Request service upgrade for call * * Allow a kernel service to begin a call on the nominated socket. This just * sets up all the internal tracking structures and allocates connection and @@ -279,7 +281,8 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, unsigned long user_call_ID, s64 tx_total_len, gfp_t gfp, - rxrpc_notify_rx_t notify_rx) + rxrpc_notify_rx_t notify_rx, + bool upgrade) { struct rxrpc_conn_parameters cp; struct rxrpc_call *call; @@ -304,6 +307,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, cp.key = key; cp.security_level = 0; cp.exclusive = false; + cp.upgrade = upgrade; cp.service_id = srx->srx_service; call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, tx_total_len, gfp); @@ -318,6 +322,14 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, } EXPORT_SYMBOL(rxrpc_kernel_begin_call); +/* + * Dummy function used to stop the notifier talking to recvmsg(). + */ +static void rxrpc_dummy_notify_rx(struct sock *sk, struct rxrpc_call *rxcall, + unsigned long call_user_ID) +{ +} + /** * rxrpc_kernel_end_call - Allow a kernel service to end a call it was using * @sock: The socket the call is on @@ -332,12 +344,39 @@ void rxrpc_kernel_end_call(struct socket *sock, struct rxrpc_call *call) mutex_lock(&call->user_mutex); rxrpc_release_call(rxrpc_sk(sock->sk), call); + + /* Make sure we're not going to call back into a kernel service */ + if (call->notify_rx) { + spin_lock_bh(&call->notify_lock); + call->notify_rx = rxrpc_dummy_notify_rx; + spin_unlock_bh(&call->notify_lock); + } + mutex_unlock(&call->user_mutex); rxrpc_put_call(call, rxrpc_call_put_kernel); } EXPORT_SYMBOL(rxrpc_kernel_end_call); /** + * rxrpc_kernel_check_life - Check to see whether a call is still alive + * @sock: The socket the call is on + * @call: The call to check + * + * Allow a kernel service to find out whether a call is still alive - ie. we're + * getting ACKs from the server. Returns a number representing the life state + * which can be compared to that returned by a previous call. + * + * If this is a client call, ping ACKs will be sent to the server to find out + * whether it's still responsive and whether the call is still alive on the + * server. + */ +u32 rxrpc_kernel_check_life(struct socket *sock, struct rxrpc_call *call) +{ + return call->acks_latest; +} +EXPORT_SYMBOL(rxrpc_kernel_check_life); + +/** * rxrpc_kernel_check_call - Check a call's state * @sock: The socket the call is on * @call: The call to check @@ -538,6 +577,7 @@ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len) m->msg_name = &rx->connect_srx; m->msg_namelen = sizeof(rx->connect_srx); } + /* Fall through */ case RXRPC_SERVER_BOUND: case RXRPC_SERVER_LISTENING: ret = rxrpc_do_sendmsg(rx, m, len); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index ea5600b747cc..b2151993d384 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -525,6 +525,7 @@ struct rxrpc_call { unsigned long flags; unsigned long events; spinlock_t lock; + spinlock_t notify_lock; /* Kernel notification lock */ rwlock_t state_lock; /* lock for state transition */ u32 abort_code; /* Local/remote abort code */ int error; /* Local error incurred */ diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 7a77844aab16..3574508baf9a 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -386,7 +386,7 @@ recheck_state: now = ktime_get_real(); if (ktime_before(call->expire_at, now)) { - rxrpc_abort_call("EXP", call, 0, RX_CALL_TIMEOUT, -ETIME); + rxrpc_abort_call("EXP", call, 0, RX_USER_ABORT, -ETIME); set_bit(RXRPC_CALL_EV_ABORT, &call->events); goto recheck_state; } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index fcdd6555a820..4c7fbc6dcce7 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -124,6 +124,7 @@ struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp) INIT_LIST_HEAD(&call->sock_link); init_waitqueue_head(&call->waitq); spin_lock_init(&call->lock); + spin_lock_init(&call->notify_lock); rwlock_init(&call->state_lock); atomic_set(&call->usage, 1); call->debug_id = atomic_inc_return(&rxrpc_debug_id); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index e56e23ed2229..1b592073ec96 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -298,8 +298,6 @@ static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, write_unlock(&call->state_lock); if (call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY) { - rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, 0, 0, false, true, - rxrpc_propose_ack_client_tx_end); trace_rxrpc_transmit(call, rxrpc_transmit_await_reply); } else { trace_rxrpc_transmit(call, rxrpc_transmit_end); @@ -1125,6 +1123,7 @@ void rxrpc_data_ready(struct sock *udp_sk) case RXRPC_PACKET_TYPE_BUSY: if (sp->hdr.flags & RXRPC_CLIENT_INITIATED) goto discard; + /* Fall through */ case RXRPC_PACKET_TYPE_DATA: if (sp->hdr.callNumber == 0) diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 71e6f713fbe7..f47659c7b224 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -35,7 +35,8 @@ struct rxrpc_abort_buffer { /* * Fill out an ACK packet. */ -static size_t rxrpc_fill_out_ack(struct rxrpc_call *call, +static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, + struct rxrpc_call *call, struct rxrpc_ack_buffer *pkt, rxrpc_seq_t *_hard_ack, rxrpc_seq_t *_top, @@ -77,8 +78,8 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_call *call, } while (before_eq(seq, top)); } - mtu = call->conn->params.peer->if_mtu; - mtu -= call->conn->params.peer->hdrsize; + mtu = conn->params.peer->if_mtu; + mtu -= conn->params.peer->hdrsize; jmax = (call->nr_jumbo_bad > 3) ? 1 : rxrpc_rx_jumbo_max; pkt->ackinfo.rxMTU = htonl(rxrpc_rx_mtu); pkt->ackinfo.maxMTU = htonl(mtu); @@ -148,7 +149,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping) } call->ackr_reason = 0; } - n = rxrpc_fill_out_ack(call, pkt, &hard_ack, &top, reason); + n = rxrpc_fill_out_ack(conn, call, pkt, &hard_ack, &top, reason); spin_unlock_bh(&call->lock); @@ -221,6 +222,16 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) rxrpc_serial_t serial; int ret; + /* Don't bother sending aborts for a client call once the server has + * hard-ACK'd all of its request data. After that point, we're not + * going to stop the operation proceeding, and whilst we might limit + * the reply, it's not worth it if we can send a new call on the same + * channel instead, thereby closing off this call. + */ + if (rxrpc_is_client_call(call) && + test_bit(RXRPC_CALL_TX_LAST, &call->flags)) + return 0; + spin_lock_bh(&call->lock); if (call->conn) conn = rxrpc_get_connection_maybe(call->conn); diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 5787f97f5330..d02a99f37f5f 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -411,3 +411,16 @@ void rxrpc_kernel_get_peer(struct socket *sock, struct rxrpc_call *call, *_srx = call->peer->srx; } EXPORT_SYMBOL(rxrpc_kernel_get_peer); + +/** + * rxrpc_kernel_get_rtt - Get a call's peer RTT + * @sock: The socket on which the call is in progress. + * @call: The call to query + * + * Get the call's peer RTT. + */ +u64 rxrpc_kernel_get_rtt(struct socket *sock, struct rxrpc_call *call) +{ + return call->peer->rtt; +} +EXPORT_SYMBOL(rxrpc_kernel_get_rtt); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index bdece21f313d..8510a98b87e1 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -40,7 +40,9 @@ void rxrpc_notify_socket(struct rxrpc_call *call) sk = &rx->sk; if (rx && sk->sk_state < RXRPC_CLOSE) { if (call->notify_rx) { + spin_lock_bh(&call->notify_lock); call->notify_rx(sk, call, call->user_call_ID); + spin_unlock_bh(&call->notify_lock); } else { write_lock_bh(&rx->recvmsg_lock); if (list_empty(&call->recvmsg_link)) { @@ -607,6 +609,7 @@ wait_error: * @_offset: The running offset into the buffer. * @want_more: True if more data is expected to be read * @_abort: Where the abort code is stored if -ECONNABORTED is returned + * @_service: Where to store the actual service ID (may be upgraded) * * Allow a kernel service to receive data and pick up information about the * state of a call. Returns 0 if got what was asked for and there's more @@ -624,7 +627,7 @@ wait_error: */ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, void *buf, size_t size, size_t *_offset, - bool want_more, u32 *_abort) + bool want_more, u32 *_abort, u16 *_service) { struct iov_iter iter; struct kvec iov; @@ -680,6 +683,8 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, read_phase_complete: ret = 1; out: + if (_service) + *_service = call->service_id; mutex_unlock(&call->user_mutex); _leave(" = %d [%zu,%d]", ret, *_offset, *_abort); return ret; diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 9ea6f972767e..7d2595582c09 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -38,12 +38,86 @@ struct rxrpc_send_params { }; /* + * Wait for space to appear in the Tx queue or a signal to occur. + */ +static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx, + struct rxrpc_call *call, + long *timeo) +{ + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); + if (call->tx_top - call->tx_hard_ack < + min_t(unsigned int, call->tx_winsize, + call->cong_cwnd + call->cong_extra)) + return 0; + + if (call->state >= RXRPC_CALL_COMPLETE) + return call->error; + + if (signal_pending(current)) + return sock_intr_errno(*timeo); + + trace_rxrpc_transmit(call, rxrpc_transmit_wait); + mutex_unlock(&call->user_mutex); + *timeo = schedule_timeout(*timeo); + if (mutex_lock_interruptible(&call->user_mutex) < 0) + return sock_intr_errno(*timeo); + } +} + +/* + * Wait for space to appear in the Tx queue uninterruptibly, but with + * a timeout of 2*RTT if no progress was made and a signal occurred. + */ +static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx, + struct rxrpc_call *call) +{ + rxrpc_seq_t tx_start, tx_win; + signed long rtt2, timeout; + u64 rtt; + + rtt = READ_ONCE(call->peer->rtt); + rtt2 = nsecs_to_jiffies64(rtt) * 2; + if (rtt2 < 1) + rtt2 = 1; + + timeout = rtt2; + tx_start = READ_ONCE(call->tx_hard_ack); + + for (;;) { + set_current_state(TASK_UNINTERRUPTIBLE); + + tx_win = READ_ONCE(call->tx_hard_ack); + if (call->tx_top - tx_win < + min_t(unsigned int, call->tx_winsize, + call->cong_cwnd + call->cong_extra)) + return 0; + + if (call->state >= RXRPC_CALL_COMPLETE) + return call->error; + + if (timeout == 0 && + tx_win == tx_start && signal_pending(current)) + return -EINTR; + + if (tx_win != tx_start) { + timeout = rtt2; + tx_start = tx_win; + } + + trace_rxrpc_transmit(call, rxrpc_transmit_wait); + timeout = schedule_timeout(timeout); + } +} + +/* * wait for space to appear in the transmit/ACK window * - caller holds the socket locked */ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx, struct rxrpc_call *call, - long *timeo) + long *timeo, + bool waitall) { DECLARE_WAITQUEUE(myself, current); int ret; @@ -53,30 +127,10 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx, add_wait_queue(&call->waitq, &myself); - for (;;) { - set_current_state(TASK_INTERRUPTIBLE); - ret = 0; - if (call->tx_top - call->tx_hard_ack < - min_t(unsigned int, call->tx_winsize, - call->cong_cwnd + call->cong_extra)) - break; - if (call->state >= RXRPC_CALL_COMPLETE) { - ret = call->error; - break; - } - if (signal_pending(current)) { - ret = sock_intr_errno(*timeo); - break; - } - - trace_rxrpc_transmit(call, rxrpc_transmit_wait); - mutex_unlock(&call->user_mutex); - *timeo = schedule_timeout(*timeo); - if (mutex_lock_interruptible(&call->user_mutex) < 0) { - ret = sock_intr_errno(*timeo); - break; - } - } + if (waitall) + ret = rxrpc_wait_for_tx_window_nonintr(rx, call); + else + ret = rxrpc_wait_for_tx_window_intr(rx, call, timeo); remove_wait_queue(&call->waitq, &myself); set_current_state(TASK_RUNNING); @@ -166,6 +220,7 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, ktime_get_real()); if (!last) break; + /* Fall through */ case RXRPC_CALL_SERVER_SEND_REPLY: call->state = RXRPC_CALL_SERVER_AWAIT_ACK; rxrpc_notify_end_tx(rx, call, notify_end_tx); @@ -254,7 +309,8 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, if (msg->msg_flags & MSG_DONTWAIT) goto maybe_error; ret = rxrpc_wait_for_tx_window(rx, call, - &timeo); + &timeo, + msg->msg_flags & MSG_WAITALL); if (ret < 0) goto maybe_error; } diff --git a/net/sched/Kconfig b/net/sched/Kconfig index e70ed26485a2..c03d86a7775e 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -172,6 +172,17 @@ config NET_SCH_TBF To compile this code as a module, choose M here: the module will be called sch_tbf. +config NET_SCH_CBS + tristate "Credit Based Shaper (CBS)" + ---help--- + Say Y here if you want to use the Credit Based Shaper (CBS) packet + scheduling algorithm. + + See the top of <file:net/sched/sch_cbs.c> for more details. + + To compile this code as a module, choose M here: the + module will be called sch_cbs. + config NET_SCH_GRED tristate "Generic Random Early Detection (GRED)" ---help--- diff --git a/net/sched/Makefile b/net/sched/Makefile index 9e43a4721ef8..5b635447e3f8 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -53,6 +53,7 @@ obj-$(CONFIG_NET_SCH_FQ_CODEL) += sch_fq_codel.o obj-$(CONFIG_NET_SCH_FQ) += sch_fq.o obj-$(CONFIG_NET_SCH_HHF) += sch_hhf.o obj-$(CONFIG_NET_SCH_PIE) += sch_pie.o +obj-$(CONFIG_NET_SCH_CBS) += sch_cbs.o obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 8f2c63514956..4d33a50a8a6d 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -21,6 +21,8 @@ #include <linux/kmod.h> #include <linux/err.h> #include <linux/module.h> +#include <linux/rhashtable.h> +#include <linux/list.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/sch_generic.h> @@ -1251,8 +1253,227 @@ out_module_put: return skb->len; } +struct tcf_action_net { + struct rhashtable egdev_ht; +}; + +static unsigned int tcf_action_net_id; + +struct tcf_action_egdev_cb { + struct list_head list; + tc_setup_cb_t *cb; + void *cb_priv; +}; + +struct tcf_action_egdev { + struct rhash_head ht_node; + const struct net_device *dev; + unsigned int refcnt; + struct list_head cb_list; +}; + +static const struct rhashtable_params tcf_action_egdev_ht_params = { + .key_offset = offsetof(struct tcf_action_egdev, dev), + .head_offset = offsetof(struct tcf_action_egdev, ht_node), + .key_len = sizeof(const struct net_device *), +}; + +static struct tcf_action_egdev * +tcf_action_egdev_lookup(const struct net_device *dev) +{ + struct net *net = dev_net(dev); + struct tcf_action_net *tan = net_generic(net, tcf_action_net_id); + + return rhashtable_lookup_fast(&tan->egdev_ht, &dev, + tcf_action_egdev_ht_params); +} + +static struct tcf_action_egdev * +tcf_action_egdev_get(const struct net_device *dev) +{ + struct tcf_action_egdev *egdev; + struct tcf_action_net *tan; + + egdev = tcf_action_egdev_lookup(dev); + if (egdev) + goto inc_ref; + + egdev = kzalloc(sizeof(*egdev), GFP_KERNEL); + if (!egdev) + return NULL; + INIT_LIST_HEAD(&egdev->cb_list); + egdev->dev = dev; + tan = net_generic(dev_net(dev), tcf_action_net_id); + rhashtable_insert_fast(&tan->egdev_ht, &egdev->ht_node, + tcf_action_egdev_ht_params); + +inc_ref: + egdev->refcnt++; + return egdev; +} + +static void tcf_action_egdev_put(struct tcf_action_egdev *egdev) +{ + struct tcf_action_net *tan; + + if (--egdev->refcnt) + return; + tan = net_generic(dev_net(egdev->dev), tcf_action_net_id); + rhashtable_remove_fast(&tan->egdev_ht, &egdev->ht_node, + tcf_action_egdev_ht_params); + kfree(egdev); +} + +static struct tcf_action_egdev_cb * +tcf_action_egdev_cb_lookup(struct tcf_action_egdev *egdev, + tc_setup_cb_t *cb, void *cb_priv) +{ + struct tcf_action_egdev_cb *egdev_cb; + + list_for_each_entry(egdev_cb, &egdev->cb_list, list) + if (egdev_cb->cb == cb && egdev_cb->cb_priv == cb_priv) + return egdev_cb; + return NULL; +} + +static int tcf_action_egdev_cb_call(struct tcf_action_egdev *egdev, + enum tc_setup_type type, + void *type_data, bool err_stop) +{ + struct tcf_action_egdev_cb *egdev_cb; + int ok_count = 0; + int err; + + list_for_each_entry(egdev_cb, &egdev->cb_list, list) { + err = egdev_cb->cb(type, type_data, egdev_cb->cb_priv); + if (err) { + if (err_stop) + return err; + } else { + ok_count++; + } + } + return ok_count; +} + +static int tcf_action_egdev_cb_add(struct tcf_action_egdev *egdev, + tc_setup_cb_t *cb, void *cb_priv) +{ + struct tcf_action_egdev_cb *egdev_cb; + + egdev_cb = tcf_action_egdev_cb_lookup(egdev, cb, cb_priv); + if (WARN_ON(egdev_cb)) + return -EEXIST; + egdev_cb = kzalloc(sizeof(*egdev_cb), GFP_KERNEL); + if (!egdev_cb) + return -ENOMEM; + egdev_cb->cb = cb; + egdev_cb->cb_priv = cb_priv; + list_add(&egdev_cb->list, &egdev->cb_list); + return 0; +} + +static void tcf_action_egdev_cb_del(struct tcf_action_egdev *egdev, + tc_setup_cb_t *cb, void *cb_priv) +{ + struct tcf_action_egdev_cb *egdev_cb; + + egdev_cb = tcf_action_egdev_cb_lookup(egdev, cb, cb_priv); + if (WARN_ON(!egdev_cb)) + return; + list_del(&egdev_cb->list); + kfree(egdev_cb); +} + +static int __tc_setup_cb_egdev_register(const struct net_device *dev, + tc_setup_cb_t *cb, void *cb_priv) +{ + struct tcf_action_egdev *egdev = tcf_action_egdev_get(dev); + int err; + + if (!egdev) + return -ENOMEM; + err = tcf_action_egdev_cb_add(egdev, cb, cb_priv); + if (err) + goto err_cb_add; + return 0; + +err_cb_add: + tcf_action_egdev_put(egdev); + return err; +} +int tc_setup_cb_egdev_register(const struct net_device *dev, + tc_setup_cb_t *cb, void *cb_priv) +{ + int err; + + rtnl_lock(); + err = __tc_setup_cb_egdev_register(dev, cb, cb_priv); + rtnl_unlock(); + return err; +} +EXPORT_SYMBOL_GPL(tc_setup_cb_egdev_register); + +static void __tc_setup_cb_egdev_unregister(const struct net_device *dev, + tc_setup_cb_t *cb, void *cb_priv) +{ + struct tcf_action_egdev *egdev = tcf_action_egdev_lookup(dev); + + if (WARN_ON(!egdev)) + return; + tcf_action_egdev_cb_del(egdev, cb, cb_priv); + tcf_action_egdev_put(egdev); +} +void tc_setup_cb_egdev_unregister(const struct net_device *dev, + tc_setup_cb_t *cb, void *cb_priv) +{ + rtnl_lock(); + __tc_setup_cb_egdev_unregister(dev, cb, cb_priv); + rtnl_unlock(); +} +EXPORT_SYMBOL_GPL(tc_setup_cb_egdev_unregister); + +int tc_setup_cb_egdev_call(const struct net_device *dev, + enum tc_setup_type type, void *type_data, + bool err_stop) +{ + struct tcf_action_egdev *egdev = tcf_action_egdev_lookup(dev); + + if (!egdev) + return 0; + return tcf_action_egdev_cb_call(egdev, type, type_data, err_stop); +} +EXPORT_SYMBOL_GPL(tc_setup_cb_egdev_call); + +static __net_init int tcf_action_net_init(struct net *net) +{ + struct tcf_action_net *tan = net_generic(net, tcf_action_net_id); + + return rhashtable_init(&tan->egdev_ht, &tcf_action_egdev_ht_params); +} + +static void __net_exit tcf_action_net_exit(struct net *net) +{ + struct tcf_action_net *tan = net_generic(net, tcf_action_net_id); + + rhashtable_destroy(&tan->egdev_ht); +} + +static struct pernet_operations tcf_action_net_ops = { + .init = tcf_action_net_init, + .exit = tcf_action_net_exit, + .id = &tcf_action_net_id, + .size = sizeof(struct tcf_action_net), +}; + static int __init tc_action_init(void) { + int err; + + err = register_pernet_subsys(&tcf_action_net_ops); + if (err) + return err; + rtnl_register(PF_UNSPEC, RTM_NEWACTION, tc_ctl_action, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELACTION, tc_ctl_action, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETACTION, tc_ctl_action, tc_dump_action, diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index c0c707eb2c96..5ef8ce8c83d4 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -49,11 +49,11 @@ static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act, filter = rcu_dereference(prog->filter); if (at_ingress) { __skb_push(skb, skb->mac_len); - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); filter_res = BPF_PROG_RUN(filter, skb); __skb_pull(skb, skb->mac_len); } else { - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); filter_res = BPF_PROG_RUN(filter, skb); } rcu_read_unlock(); diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 8ccd35825b6b..3007cb1310ea 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -248,6 +248,22 @@ static int ife_validate_metatype(struct tcf_meta_ops *ops, void *val, int len) return ret; } +#ifdef CONFIG_MODULES +static const char *ife_meta_id2name(u32 metaid) +{ + switch (metaid) { + case IFE_META_SKBMARK: + return "skbmark"; + case IFE_META_PRIO: + return "skbprio"; + case IFE_META_TCINDEX: + return "tcindex"; + default: + return "unknown"; + } +} +#endif + /* called when adding new meta information * under ife->tcf_lock for existing action */ @@ -263,7 +279,7 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid, if (exists) spin_unlock_bh(&ife->tcf_lock); rtnl_unlock(); - request_module("ifemeta%u", metaid); + request_module("ife-meta-%s", ife_meta_id2name(metaid)); rtnl_lock(); if (exists) spin_lock_bh(&ife->tcf_lock); @@ -392,10 +408,14 @@ static void _tcf_ife_cleanup(struct tc_action *a, int bind) static void tcf_ife_cleanup(struct tc_action *a, int bind) { struct tcf_ife_info *ife = to_ife(a); + struct tcf_ife_params *p; spin_lock_bh(&ife->tcf_lock); _tcf_ife_cleanup(a, bind); spin_unlock_bh(&ife->tcf_lock); + + p = rcu_dereference_protected(ife->params, 1); + kfree_rcu(p, rcu); } /* under ife->tcf_lock for existing action */ @@ -432,6 +452,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, struct tc_action_net *tn = net_generic(net, ife_net_id); struct nlattr *tb[TCA_IFE_MAX + 1]; struct nlattr *tb2[IFE_META_MAX + 1]; + struct tcf_ife_params *p, *p_old; struct tcf_ife_info *ife; u16 ife_type = ETH_P_IFE; struct tc_ife *parm; @@ -450,24 +471,41 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_IFE_PARMS]); + /* IFE_DECODE is 0 and indicates the opposite of IFE_ENCODE because + * they cannot run as the same time. Check on all other values which + * are not supported right now. + */ + if (parm->flags & ~IFE_ENCODE) + return -EINVAL; + + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return -ENOMEM; + exists = tcf_idr_check(tn, parm->index, a, bind); - if (exists && bind) + if (exists && bind) { + kfree(p); return 0; + } if (!exists) { ret = tcf_idr_create(tn, parm->index, est, a, &act_ife_ops, - bind, false); - if (ret) + bind, true); + if (ret) { + kfree(p); return ret; + } ret = ACT_P_CREATED; } else { tcf_idr_release(*a, bind); - if (!ovr) + if (!ovr) { + kfree(p); return -EEXIST; + } } ife = to_ife(*a); - ife->flags = parm->flags; + p->flags = parm->flags; if (parm->flags & IFE_ENCODE) { if (tb[TCA_IFE_TYPE]) @@ -478,24 +516,25 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, saddr = nla_data(tb[TCA_IFE_SMAC]); } - if (exists) - spin_lock_bh(&ife->tcf_lock); ife->tcf_action = parm->action; if (parm->flags & IFE_ENCODE) { if (daddr) - ether_addr_copy(ife->eth_dst, daddr); + ether_addr_copy(p->eth_dst, daddr); else - eth_zero_addr(ife->eth_dst); + eth_zero_addr(p->eth_dst); if (saddr) - ether_addr_copy(ife->eth_src, saddr); + ether_addr_copy(p->eth_src, saddr); else - eth_zero_addr(ife->eth_src); + eth_zero_addr(p->eth_src); - ife->eth_type = ife_type; + p->eth_type = ife_type; } + if (exists) + spin_lock_bh(&ife->tcf_lock); + if (ret == ACT_P_CREATED) INIT_LIST_HEAD(&ife->metalist); @@ -511,6 +550,7 @@ metadata_parse_err: if (exists) spin_unlock_bh(&ife->tcf_lock); + kfree(p); return err; } @@ -531,6 +571,7 @@ metadata_parse_err: if (exists) spin_unlock_bh(&ife->tcf_lock); + kfree(p); return err; } } @@ -538,6 +579,11 @@ metadata_parse_err: if (exists) spin_unlock_bh(&ife->tcf_lock); + p_old = rtnl_dereference(ife->params); + rcu_assign_pointer(ife->params, p); + if (p_old) + kfree_rcu(p_old, rcu); + if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); @@ -549,12 +595,13 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, { unsigned char *b = skb_tail_pointer(skb); struct tcf_ife_info *ife = to_ife(a); + struct tcf_ife_params *p = rtnl_dereference(ife->params); struct tc_ife opt = { .index = ife->tcf_index, .refcnt = ife->tcf_refcnt - ref, .bindcnt = ife->tcf_bindcnt - bind, .action = ife->tcf_action, - .flags = ife->flags, + .flags = p->flags, }; struct tcf_t t; @@ -565,17 +612,17 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, if (nla_put_64bit(skb, TCA_IFE_TM, sizeof(t), &t, TCA_IFE_PAD)) goto nla_put_failure; - if (!is_zero_ether_addr(ife->eth_dst)) { - if (nla_put(skb, TCA_IFE_DMAC, ETH_ALEN, ife->eth_dst)) + if (!is_zero_ether_addr(p->eth_dst)) { + if (nla_put(skb, TCA_IFE_DMAC, ETH_ALEN, p->eth_dst)) goto nla_put_failure; } - if (!is_zero_ether_addr(ife->eth_src)) { - if (nla_put(skb, TCA_IFE_SMAC, ETH_ALEN, ife->eth_src)) + if (!is_zero_ether_addr(p->eth_src)) { + if (nla_put(skb, TCA_IFE_SMAC, ETH_ALEN, p->eth_src)) goto nla_put_failure; } - if (nla_put(skb, TCA_IFE_TYPE, 2, &ife->eth_type)) + if (nla_put(skb, TCA_IFE_TYPE, 2, &p->eth_type)) goto nla_put_failure; if (dump_metalist(skb, ife)) { @@ -617,19 +664,15 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, u8 *tlv_data; u16 metalen; - spin_lock(&ife->tcf_lock); - bstats_update(&ife->tcf_bstats, skb); + bstats_cpu_update(this_cpu_ptr(ife->common.cpu_bstats), skb); tcf_lastuse_update(&ife->tcf_tm); - spin_unlock(&ife->tcf_lock); if (skb_at_tc_ingress(skb)) skb_push(skb, skb->dev->hard_header_len); tlv_data = ife_decode(skb, &metalen); if (unlikely(!tlv_data)) { - spin_lock(&ife->tcf_lock); - ife->tcf_qstats.drops++; - spin_unlock(&ife->tcf_lock); + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } @@ -647,14 +690,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, */ pr_info_ratelimited("Unknown metaid %d dlen %d\n", mtype, dlen); - ife->tcf_qstats.overlimits++; + qstats_overlimit_inc(this_cpu_ptr(ife->common.cpu_qstats)); } } if (WARN_ON(tlv_data != ifehdr_end)) { - spin_lock(&ife->tcf_lock); - ife->tcf_qstats.drops++; - spin_unlock(&ife->tcf_lock); + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } @@ -683,7 +724,7 @@ static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_info *ife) } static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, - struct tcf_result *res) + struct tcf_result *res, struct tcf_ife_params *p) { struct tcf_ife_info *ife = to_ife(a); int action = ife->tcf_action; @@ -706,23 +747,20 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, exceed_mtu = true; } - spin_lock(&ife->tcf_lock); - bstats_update(&ife->tcf_bstats, skb); + bstats_cpu_update(this_cpu_ptr(ife->common.cpu_bstats), skb); tcf_lastuse_update(&ife->tcf_tm); if (!metalen) { /* no metadata to send */ /* abuse overlimits to count when we allow packet * with no metadata */ - ife->tcf_qstats.overlimits++; - spin_unlock(&ife->tcf_lock); + qstats_overlimit_inc(this_cpu_ptr(ife->common.cpu_qstats)); return action; } /* could be stupid policy setup or mtu config * so lets be conservative.. */ if ((action == TC_ACT_SHOT) || exceed_mtu) { - ife->tcf_qstats.drops++; - spin_unlock(&ife->tcf_lock); + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } @@ -731,6 +769,8 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, ife_meta = ife_encode(skb, metalen); + spin_lock(&ife->tcf_lock); + /* XXX: we dont have a clever way of telling encode to * not repeat some of the computations that are done by * ops->presence_check... @@ -742,25 +782,24 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, } if (err < 0) { /* too corrupt to keep around if overwritten */ - ife->tcf_qstats.drops++; spin_unlock(&ife->tcf_lock); + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } skboff += err; } + spin_unlock(&ife->tcf_lock); oethh = (struct ethhdr *)skb->data; - if (!is_zero_ether_addr(ife->eth_src)) - ether_addr_copy(oethh->h_source, ife->eth_src); - if (!is_zero_ether_addr(ife->eth_dst)) - ether_addr_copy(oethh->h_dest, ife->eth_dst); - oethh->h_proto = htons(ife->eth_type); + if (!is_zero_ether_addr(p->eth_src)) + ether_addr_copy(oethh->h_source, p->eth_src); + if (!is_zero_ether_addr(p->eth_dst)) + ether_addr_copy(oethh->h_dest, p->eth_dst); + oethh->h_proto = htons(p->eth_type); if (skb_at_tc_ingress(skb)) skb_pull(skb, skb->dev->hard_header_len); - spin_unlock(&ife->tcf_lock); - return action; } @@ -768,21 +807,19 @@ static int tcf_ife_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_ife_info *ife = to_ife(a); + struct tcf_ife_params *p; + int ret; + + rcu_read_lock(); + p = rcu_dereference(ife->params); + if (p->flags & IFE_ENCODE) { + ret = tcf_ife_encode(skb, a, res, p); + rcu_read_unlock(); + return ret; + } + rcu_read_unlock(); - if (ife->flags & IFE_ENCODE) - return tcf_ife_encode(skb, a, res); - - if (!(ife->flags & IFE_ENCODE)) - return tcf_ife_decode(skb, a, res); - - pr_info_ratelimited("unknown failure(policy neither de/encode\n"); - spin_lock(&ife->tcf_lock); - bstats_update(&ife->tcf_bstats, skb); - tcf_lastuse_update(&ife->tcf_tm); - ife->tcf_qstats.drops++; - spin_unlock(&ife->tcf_lock); - - return TC_ACT_SHOT; + return tcf_ife_decode(skb, a, res); } static int tcf_ife_walker(struct net *net, struct sk_buff *skb, diff --git a/net/sched/act_meta_mark.c b/net/sched/act_meta_mark.c index 82892170ce4f..1e3f10e5da99 100644 --- a/net/sched/act_meta_mark.c +++ b/net/sched/act_meta_mark.c @@ -76,4 +76,4 @@ module_exit(ifemark_cleanup_module); MODULE_AUTHOR("Jamal Hadi Salim(2015)"); MODULE_DESCRIPTION("Inter-FE skb mark metadata module"); MODULE_LICENSE("GPL"); -MODULE_ALIAS_IFE_META(IFE_META_SKBMARK); +MODULE_ALIAS_IFE_META("skbmark"); diff --git a/net/sched/act_meta_skbprio.c b/net/sched/act_meta_skbprio.c index 26bf4d86030b..4033f9fc4d4a 100644 --- a/net/sched/act_meta_skbprio.c +++ b/net/sched/act_meta_skbprio.c @@ -73,4 +73,4 @@ module_exit(ifeprio_cleanup_module); MODULE_AUTHOR("Jamal Hadi Salim(2015)"); MODULE_DESCRIPTION("Inter-FE skb prio metadata action"); MODULE_LICENSE("GPL"); -MODULE_ALIAS_IFE_META(IFE_META_PRIO); +MODULE_ALIAS_IFE_META("skbprio"); diff --git a/net/sched/act_meta_skbtcindex.c b/net/sched/act_meta_skbtcindex.c index 3b35774ce890..2ea1f26c9e96 100644 --- a/net/sched/act_meta_skbtcindex.c +++ b/net/sched/act_meta_skbtcindex.c @@ -76,4 +76,4 @@ module_exit(ifetc_index_cleanup_module); MODULE_AUTHOR("Jamal Hadi Salim(2016)"); MODULE_DESCRIPTION("Inter-FE skb tc_index metadata module"); MODULE_LICENSE("GPL"); -MODULE_ALIAS_IFE_META(IFE_META_SKBTCINDEX); +MODULE_ALIAS_IFE_META("tcindex"); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 416627c66f08..8b3e59388480 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -140,6 +140,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, m->tcfm_eaction = parm->eaction; if (dev != NULL) { m->tcfm_ifindex = parm->ifindex; + m->net = net; if (ret != ACT_P_CREATED) dev_put(rcu_dereference_protected(m->tcfm_dev, 1)); dev_hold(dev); @@ -313,15 +314,11 @@ static struct notifier_block mirred_device_notifier = { .notifier_call = mirred_device_event, }; -static int tcf_mirred_device(const struct tc_action *a, struct net *net, - struct net_device **mirred_dev) +static struct net_device *tcf_mirred_get_dev(const struct tc_action *a) { - int ifindex = tcf_mirred_ifindex(a); + struct tcf_mirred *m = to_mirred(a); - *mirred_dev = __dev_get_by_index(net, ifindex); - if (!*mirred_dev) - return -EINVAL; - return 0; + return __dev_get_by_index(m->net, m->tcfm_ifindex); } static struct tc_action_ops act_mirred_ops = { @@ -336,7 +333,7 @@ static struct tc_action_ops act_mirred_ops = { .walk = tcf_mirred_walker, .lookup = tcf_mirred_search, .size = sizeof(struct tcf_mirred), - .get_dev = tcf_mirred_device, + .get_dev = tcf_mirred_get_dev, }; static __net_init int mirred_init_net(struct net *net) diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 16eb067a8d8f..97f717a13ad5 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -26,14 +26,13 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_vlan *v = to_vlan(a); + struct tcf_vlan_params *p; int action; int err; u16 tci; - spin_lock(&v->tcf_lock); tcf_lastuse_update(&v->tcf_tm); - bstats_update(&v->tcf_bstats, skb); - action = v->tcf_action; + bstats_cpu_update(this_cpu_ptr(v->common.cpu_bstats), skb); /* Ensure 'data' points at mac_header prior calling vlan manipulating * functions. @@ -41,15 +40,21 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, if (skb_at_tc_ingress(skb)) skb_push_rcsum(skb, skb->mac_len); - switch (v->tcfv_action) { + rcu_read_lock(); + + action = READ_ONCE(v->tcf_action); + + p = rcu_dereference(v->vlan_p); + + switch (p->tcfv_action) { case TCA_VLAN_ACT_POP: err = skb_vlan_pop(skb); if (err) goto drop; break; case TCA_VLAN_ACT_PUSH: - err = skb_vlan_push(skb, v->tcfv_push_proto, v->tcfv_push_vid | - (v->tcfv_push_prio << VLAN_PRIO_SHIFT)); + err = skb_vlan_push(skb, p->tcfv_push_proto, p->tcfv_push_vid | + (p->tcfv_push_prio << VLAN_PRIO_SHIFT)); if (err) goto drop; break; @@ -68,14 +73,14 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, goto drop; } /* replace the vid */ - tci = (tci & ~VLAN_VID_MASK) | v->tcfv_push_vid; + tci = (tci & ~VLAN_VID_MASK) | p->tcfv_push_vid; /* replace prio bits, if tcfv_push_prio specified */ - if (v->tcfv_push_prio) { + if (p->tcfv_push_prio) { tci &= ~VLAN_PRIO_MASK; - tci |= v->tcfv_push_prio << VLAN_PRIO_SHIFT; + tci |= p->tcfv_push_prio << VLAN_PRIO_SHIFT; } /* put updated tci as hwaccel tag */ - __vlan_hwaccel_put_tag(skb, v->tcfv_push_proto, tci); + __vlan_hwaccel_put_tag(skb, p->tcfv_push_proto, tci); break; default: BUG(); @@ -85,12 +90,13 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, drop: action = TC_ACT_SHOT; - v->tcf_qstats.drops++; + qstats_drop_inc(this_cpu_ptr(v->common.cpu_qstats)); + unlock: + rcu_read_unlock(); if (skb_at_tc_ingress(skb)) skb_pull_rcsum(skb, skb->mac_len); - spin_unlock(&v->tcf_lock); return action; } @@ -107,6 +113,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, { struct tc_action_net *tn = net_generic(net, vlan_net_id); struct nlattr *tb[TCA_VLAN_MAX + 1]; + struct tcf_vlan_params *p, *p_old; struct tc_vlan *parm; struct tcf_vlan *v; int action; @@ -172,7 +179,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, parm->index, est, a, - &act_vlan_ops, bind, false); + &act_vlan_ops, bind, true); if (ret) return ret; @@ -185,46 +192,67 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, v = to_vlan(*a); - spin_lock_bh(&v->tcf_lock); - - v->tcfv_action = action; - v->tcfv_push_vid = push_vid; - v->tcfv_push_prio = push_prio; - v->tcfv_push_proto = push_proto; + ASSERT_RTNL(); + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) { + if (ovr) + tcf_idr_release(*a, bind); + return -ENOMEM; + } v->tcf_action = parm->action; - spin_unlock_bh(&v->tcf_lock); + p_old = rtnl_dereference(v->vlan_p); + + p->tcfv_action = action; + p->tcfv_push_vid = push_vid; + p->tcfv_push_prio = push_prio; + p->tcfv_push_proto = push_proto; + + rcu_assign_pointer(v->vlan_p, p); + + if (p_old) + kfree_rcu(p_old, rcu); if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); return ret; } +static void tcf_vlan_cleanup(struct tc_action *a, int bind) +{ + struct tcf_vlan *v = to_vlan(a); + struct tcf_vlan_params *p; + + p = rcu_dereference_protected(v->vlan_p, 1); + kfree_rcu(p, rcu); +} + static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_vlan *v = to_vlan(a); + struct tcf_vlan_params *p = rtnl_dereference(v->vlan_p); struct tc_vlan opt = { .index = v->tcf_index, .refcnt = v->tcf_refcnt - ref, .bindcnt = v->tcf_bindcnt - bind, .action = v->tcf_action, - .v_action = v->tcfv_action, + .v_action = p->tcfv_action, }; struct tcf_t t; if (nla_put(skb, TCA_VLAN_PARMS, sizeof(opt), &opt)) goto nla_put_failure; - if ((v->tcfv_action == TCA_VLAN_ACT_PUSH || - v->tcfv_action == TCA_VLAN_ACT_MODIFY) && - (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, v->tcfv_push_vid) || + if ((p->tcfv_action == TCA_VLAN_ACT_PUSH || + p->tcfv_action == TCA_VLAN_ACT_MODIFY) && + (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, p->tcfv_push_vid) || nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL, - v->tcfv_push_proto) || + p->tcfv_push_proto) || (nla_put_u8(skb, TCA_VLAN_PUSH_VLAN_PRIORITY, - v->tcfv_push_prio)))) + p->tcfv_push_prio)))) goto nla_put_failure; tcf_tm_dump(&t, &v->tcf_tm); @@ -260,6 +288,7 @@ static struct tc_action_ops act_vlan_ops = { .act = tcf_vlan, .dump = tcf_vlan_dump, .init = tcf_vlan_init, + .cleanup = tcf_vlan_cleanup, .walk = tcf_vlan_walker, .lookup = tcf_vlan_search, .size = sizeof(struct tcf_vlan), diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index ecbb019efcbd..ab255b421781 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -195,12 +195,19 @@ static struct tcf_chain *tcf_chain_create(struct tcf_block *block, return chain; } +static void tcf_chain_head_change(struct tcf_chain *chain, + struct tcf_proto *tp_head) +{ + if (chain->chain_head_change) + chain->chain_head_change(tp_head, + chain->chain_head_change_priv); +} + static void tcf_chain_flush(struct tcf_chain *chain) { struct tcf_proto *tp; - if (chain->p_filter_chain) - RCU_INIT_POINTER(*chain->p_filter_chain, NULL); + tcf_chain_head_change(chain, NULL); while ((tp = rtnl_dereference(chain->filter_chain)) != NULL) { RCU_INIT_POINTER(chain->filter_chain, tp->next); tcf_chain_put(chain); @@ -242,15 +249,35 @@ void tcf_chain_put(struct tcf_chain *chain) } EXPORT_SYMBOL(tcf_chain_put); -static void -tcf_chain_filter_chain_ptr_set(struct tcf_chain *chain, - struct tcf_proto __rcu **p_filter_chain) +static void tcf_block_offload_cmd(struct tcf_block *block, struct Qdisc *q, + struct tcf_block_ext_info *ei, + enum tc_block_command command) { - chain->p_filter_chain = p_filter_chain; + struct net_device *dev = q->dev_queue->dev; + struct tc_block_offload bo = {}; + + if (!dev->netdev_ops->ndo_setup_tc) + return; + bo.command = command; + bo.binder_type = ei->binder_type; + bo.block = block; + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); } -int tcf_block_get(struct tcf_block **p_block, - struct tcf_proto __rcu **p_filter_chain) +static void tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q, + struct tcf_block_ext_info *ei) +{ + tcf_block_offload_cmd(block, q, ei, TC_BLOCK_BIND); +} + +static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q, + struct tcf_block_ext_info *ei) +{ + tcf_block_offload_cmd(block, q, ei, TC_BLOCK_UNBIND); +} + +int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, + struct tcf_block_ext_info *ei) { struct tcf_block *block = kzalloc(sizeof(*block), GFP_KERNEL); struct tcf_chain *chain; @@ -259,13 +286,20 @@ int tcf_block_get(struct tcf_block **p_block, if (!block) return -ENOMEM; INIT_LIST_HEAD(&block->chain_list); + INIT_LIST_HEAD(&block->cb_list); + /* Create chain 0 by default, it has to be always present. */ chain = tcf_chain_create(block, 0); if (!chain) { err = -ENOMEM; goto err_chain_create; } - tcf_chain_filter_chain_ptr_set(chain, p_filter_chain); + WARN_ON(!ei->chain_head_change); + chain->chain_head_change = ei->chain_head_change; + chain->chain_head_change_priv = ei->chain_head_change_priv; + block->net = qdisc_net(q); + block->q = q; + tcf_block_offload_bind(block, q, ei); *p_block = block; return 0; @@ -273,6 +307,26 @@ err_chain_create: kfree(block); return err; } +EXPORT_SYMBOL(tcf_block_get_ext); + +static void tcf_chain_head_change_dflt(struct tcf_proto *tp_head, void *priv) +{ + struct tcf_proto __rcu **p_filter_chain = priv; + + rcu_assign_pointer(*p_filter_chain, tp_head); +} + +int tcf_block_get(struct tcf_block **p_block, + struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q) +{ + struct tcf_block_ext_info ei = { + .chain_head_change = tcf_chain_head_change_dflt, + .chain_head_change_priv = p_filter_chain, + }; + + WARN_ON(!p_filter_chain); + return tcf_block_get_ext(p_block, q, &ei); +} EXPORT_SYMBOL(tcf_block_get); static void tcf_block_put_final(struct work_struct *work) @@ -292,25 +346,140 @@ static void tcf_block_put_final(struct work_struct *work) * actions should be all removed after flushing. However, filters are now * destroyed in tc filter workqueue with RTNL lock, they can not race here. */ -void tcf_block_put(struct tcf_block *block) +void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, + struct tcf_block_ext_info *ei) { struct tcf_chain *chain, *tmp; - if (!block) - return; - list_for_each_entry_safe(chain, tmp, &block->chain_list, list) tcf_chain_flush(chain); + tcf_block_offload_unbind(block, q, ei); + INIT_WORK(&block->work, tcf_block_put_final); - /* Wait for RCU callbacks to release the reference count and make - * sure their works have been queued before this. + /* Wait for existing RCU callbacks to cool down, make sure their works + * have been queued before this. We can not flush pending works here + * because we are holding the RTNL lock. */ rcu_barrier(); tcf_queue_work(&block->work); } +EXPORT_SYMBOL(tcf_block_put_ext); + +void tcf_block_put(struct tcf_block *block) +{ + struct tcf_block_ext_info ei = {0, }; + + if (!block) + return; + tcf_block_put_ext(block, block->q, &ei); +} + EXPORT_SYMBOL(tcf_block_put); +struct tcf_block_cb { + struct list_head list; + tc_setup_cb_t *cb; + void *cb_ident; + void *cb_priv; + unsigned int refcnt; +}; + +void *tcf_block_cb_priv(struct tcf_block_cb *block_cb) +{ + return block_cb->cb_priv; +} +EXPORT_SYMBOL(tcf_block_cb_priv); + +struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block, + tc_setup_cb_t *cb, void *cb_ident) +{ struct tcf_block_cb *block_cb; + + list_for_each_entry(block_cb, &block->cb_list, list) + if (block_cb->cb == cb && block_cb->cb_ident == cb_ident) + return block_cb; + return NULL; +} +EXPORT_SYMBOL(tcf_block_cb_lookup); + +void tcf_block_cb_incref(struct tcf_block_cb *block_cb) +{ + block_cb->refcnt++; +} +EXPORT_SYMBOL(tcf_block_cb_incref); + +unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb) +{ + return --block_cb->refcnt; +} +EXPORT_SYMBOL(tcf_block_cb_decref); + +struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block, + tc_setup_cb_t *cb, void *cb_ident, + void *cb_priv) +{ + struct tcf_block_cb *block_cb; + + block_cb = kzalloc(sizeof(*block_cb), GFP_KERNEL); + if (!block_cb) + return NULL; + block_cb->cb = cb; + block_cb->cb_ident = cb_ident; + block_cb->cb_priv = cb_priv; + list_add(&block_cb->list, &block->cb_list); + return block_cb; +} +EXPORT_SYMBOL(__tcf_block_cb_register); + +int tcf_block_cb_register(struct tcf_block *block, + tc_setup_cb_t *cb, void *cb_ident, + void *cb_priv) +{ + struct tcf_block_cb *block_cb; + + block_cb = __tcf_block_cb_register(block, cb, cb_ident, cb_priv); + return block_cb ? 0 : -ENOMEM; +} +EXPORT_SYMBOL(tcf_block_cb_register); + +void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb) +{ + list_del(&block_cb->list); + kfree(block_cb); +} +EXPORT_SYMBOL(__tcf_block_cb_unregister); + +void tcf_block_cb_unregister(struct tcf_block *block, + tc_setup_cb_t *cb, void *cb_ident) +{ + struct tcf_block_cb *block_cb; + + block_cb = tcf_block_cb_lookup(block, cb, cb_ident); + if (!block_cb) + return; + __tcf_block_cb_unregister(block_cb); +} +EXPORT_SYMBOL(tcf_block_cb_unregister); + +static int tcf_block_cb_call(struct tcf_block *block, enum tc_setup_type type, + void *type_data, bool err_stop) +{ + struct tcf_block_cb *block_cb; + int ok_count = 0; + int err; + + list_for_each_entry(block_cb, &block->cb_list, list) { + err = block_cb->cb(type, type_data, block_cb->cb_priv); + if (err) { + if (err_stop) + return err; + } else { + ok_count++; + } + } + return ok_count; +} + /* Main classifier routine: scans classifier chain attached * to this qdisc, (optionally) tests for protocol and asks * specific classifiers. @@ -379,9 +548,8 @@ static void tcf_chain_tp_insert(struct tcf_chain *chain, struct tcf_chain_info *chain_info, struct tcf_proto *tp) { - if (chain->p_filter_chain && - *chain_info->pprev == chain->filter_chain) - rcu_assign_pointer(*chain->p_filter_chain, tp); + if (*chain_info->pprev == chain->filter_chain) + tcf_chain_head_change(chain, tp); RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain_info)); rcu_assign_pointer(*chain_info->pprev, tp); tcf_chain_hold(chain); @@ -393,8 +561,8 @@ static void tcf_chain_tp_remove(struct tcf_chain *chain, { struct tcf_proto *next = rtnl_dereference(chain_info->next); - if (chain->p_filter_chain && tp == chain->filter_chain) - RCU_INIT_POINTER(*chain->p_filter_chain, next); + if (tp == chain->filter_chain) + tcf_chain_head_change(chain, next); RCU_INIT_POINTER(*chain_info->pprev, next); tcf_chain_put(chain); } @@ -427,8 +595,8 @@ static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, } static int tcf_fill_node(struct net *net, struct sk_buff *skb, - struct tcf_proto *tp, void *fh, u32 portid, - u32 seq, u16 flags, int event) + struct tcf_proto *tp, struct Qdisc *q, u32 parent, + void *fh, u32 portid, u32 seq, u16 flags, int event) { struct tcmsg *tcm; struct nlmsghdr *nlh; @@ -441,8 +609,8 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb, tcm->tcm_family = AF_UNSPEC; tcm->tcm__pad1 = 0; tcm->tcm__pad2 = 0; - tcm->tcm_ifindex = qdisc_dev(tp->q)->ifindex; - tcm->tcm_parent = tp->classid; + tcm->tcm_ifindex = qdisc_dev(q)->ifindex; + tcm->tcm_parent = parent; tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol); if (nla_put_string(skb, TCA_KIND, tp->ops->kind)) goto nla_put_failure; @@ -465,6 +633,7 @@ nla_put_failure: static int tfilter_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct tcf_proto *tp, + struct Qdisc *q, u32 parent, void *fh, int event, bool unicast) { struct sk_buff *skb; @@ -474,7 +643,7 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, + if (tcf_fill_node(net, skb, tp, q, parent, fh, portid, n->nlmsg_seq, n->nlmsg_flags, event) <= 0) { kfree_skb(skb); return -EINVAL; @@ -489,6 +658,7 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct tcf_proto *tp, + struct Qdisc *q, u32 parent, void *fh, bool unicast, bool *last) { struct sk_buff *skb; @@ -499,7 +669,7 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, + if (tcf_fill_node(net, skb, tp, q, parent, fh, portid, n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER) <= 0) { kfree_skb(skb); return -EINVAL; @@ -519,6 +689,7 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, } static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, + struct Qdisc *q, u32 parent, struct nlmsghdr *n, struct tcf_chain *chain, int event) { @@ -526,7 +697,7 @@ static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, for (tp = rtnl_dereference(chain->filter_chain); tp; tp = rtnl_dereference(tp->next)) - tfilter_notify(net, oskb, n, tp, 0, event, false); + tfilter_notify(net, oskb, n, tp, q, parent, 0, event, false); } /* Add/change/delete/get a filter node */ @@ -645,7 +816,8 @@ replay: } if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) { - tfilter_notify_chain(net, skb, n, chain, RTM_DELTFILTER); + tfilter_notify_chain(net, skb, q, parent, n, + chain, RTM_DELTFILTER); tcf_chain_flush(chain); err = 0; goto errout; @@ -692,7 +864,7 @@ replay: if (!fh) { if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) { tcf_chain_tp_remove(chain, &chain_info, tp); - tfilter_notify(net, skb, n, tp, fh, + tfilter_notify(net, skb, n, tp, q, parent, fh, RTM_DELTFILTER, false); tcf_proto_destroy(tp); err = 0; @@ -717,8 +889,8 @@ replay: } break; case RTM_DELTFILTER: - err = tfilter_del_notify(net, skb, n, tp, fh, false, - &last); + err = tfilter_del_notify(net, skb, n, tp, q, parent, + fh, false, &last); if (err) goto errout; if (last) { @@ -727,7 +899,7 @@ replay: } goto errout; case RTM_GETTFILTER: - err = tfilter_notify(net, skb, n, tp, fh, + err = tfilter_notify(net, skb, n, tp, q, parent, fh, RTM_NEWTFILTER, true); goto errout; default: @@ -741,7 +913,8 @@ replay: if (err == 0) { if (tp_created) tcf_chain_tp_insert(chain, &chain_info, tp); - tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER, false); + tfilter_notify(net, skb, n, tp, q, parent, fh, + RTM_NEWTFILTER, false); } else { if (tp_created) tcf_proto_destroy(tp); @@ -760,6 +933,8 @@ struct tcf_dump_args { struct tcf_walker w; struct sk_buff *skb; struct netlink_callback *cb; + struct Qdisc *q; + u32 parent; }; static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg) @@ -767,13 +942,14 @@ static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg) struct tcf_dump_args *a = (void *)arg; struct net *net = sock_net(a->skb->sk); - return tcf_fill_node(net, a->skb, tp, n, NETLINK_CB(a->cb->skb).portid, + return tcf_fill_node(net, a->skb, tp, a->q, a->parent, + n, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER); } -static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, - struct netlink_callback *cb, +static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, + struct sk_buff *skb, struct netlink_callback *cb, long index_start, long *p_index) { struct net *net = sock_net(skb->sk); @@ -795,7 +971,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); if (cb->args[1] == 0) { - if (tcf_fill_node(net, skb, tp, 0, + if (tcf_fill_node(net, skb, tp, q, parent, 0, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER) <= 0) @@ -808,6 +984,8 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, arg.w.fn = tcf_node_dump; arg.skb = skb; arg.cb = cb; + arg.q = q; + arg.parent = parent; arg.w.stop = 0; arg.w.skip = cb->args[1] - 1; arg.w.count = 0; @@ -833,6 +1011,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) const struct Qdisc_class_ops *cops; long index_start; long index; + u32 parent; int err; if (nlmsg_len(cb->nlh) < sizeof(*tcm)) @@ -846,10 +1025,13 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) if (!dev) return skb->len; - if (!tcm->tcm_parent) + parent = tcm->tcm_parent; + if (!parent) { q = dev->qdisc; - else + parent = q->handle; + } else { q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); + } if (!q) goto out; cops = q->ops->cl_ops; @@ -873,7 +1055,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) if (tca[TCA_CHAIN] && nla_get_u32(tca[TCA_CHAIN]) != chain->index) continue; - if (!tcf_chain_dump(chain, skb, cb, index_start, &index)) + if (!tcf_chain_dump(chain, q, parent, skb, cb, + index_start, &index)) break; } @@ -1015,29 +1198,56 @@ int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts) } EXPORT_SYMBOL(tcf_exts_dump_stats); -int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts, - struct net_device **hw_dev) +static int tc_exts_setup_cb_egdev_call(struct tcf_exts *exts, + enum tc_setup_type type, + void *type_data, bool err_stop) { + int ok_count = 0; #ifdef CONFIG_NET_CLS_ACT const struct tc_action *a; - LIST_HEAD(actions); + struct net_device *dev; + int i, ret; if (!tcf_exts_has_actions(exts)) - return -EINVAL; + return 0; - tcf_exts_to_list(exts, &actions); - list_for_each_entry(a, &actions, list) { - if (a->ops->get_dev) { - a->ops->get_dev(a, dev_net(dev), hw_dev); - break; - } + for (i = 0; i < exts->nr_actions; i++) { + a = exts->actions[i]; + if (!a->ops->get_dev) + continue; + dev = a->ops->get_dev(a); + if (!dev) + continue; + ret = tc_setup_cb_egdev_call(dev, type, type_data, err_stop); + if (ret < 0) + return ret; + ok_count += ret; } - if (*hw_dev) - return 0; #endif - return -EOPNOTSUPP; + return ok_count; +} + +int tc_setup_cb_call(struct tcf_block *block, struct tcf_exts *exts, + enum tc_setup_type type, void *type_data, bool err_stop) +{ + int ok_count; + int ret; + + ret = tcf_block_cb_call(block, type, type_data, err_stop); + if (ret < 0) + return ret; + ok_count = ret; + + if (!exts) + return ok_count; + ret = tc_exts_setup_cb_egdev_call(exts, type, type_data, err_stop); + if (ret < 0) + return ret; + ok_count += ret; + + return ok_count; } -EXPORT_SYMBOL(tcf_exts_get_dev); +EXPORT_SYMBOL(tc_setup_cb_call); static int __init tc_filter_init(void) { diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index e43c56d5b96a..5f169ded347e 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -17,13 +17,14 @@ #include <linux/errno.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> +#include <linux/idr.h> #include <net/netlink.h> #include <net/act_api.h> #include <net/pkt_cls.h> struct basic_head { - u32 hgenerator; struct list_head flist; + struct idr handle_idr; struct rcu_head rcu; }; @@ -81,6 +82,7 @@ static int basic_init(struct tcf_proto *tp) if (head == NULL) return -ENOBUFS; INIT_LIST_HEAD(&head->flist); + idr_init(&head->handle_idr); rcu_assign_pointer(tp->root, head); return 0; } @@ -118,11 +120,13 @@ static void basic_destroy(struct tcf_proto *tp) list_for_each_entry_safe(f, n, &head->flist, link) { list_del_rcu(&f->link); tcf_unbind_filter(tp, &f->res); + idr_remove_ext(&head->handle_idr, f->handle); if (tcf_exts_get_net(&f->exts)) call_rcu(&f->rcu, basic_delete_filter); else __basic_delete_filter(f); } + idr_destroy(&head->handle_idr); kfree_rcu(head, rcu); } @@ -133,6 +137,7 @@ static int basic_delete(struct tcf_proto *tp, void *arg, bool *last) list_del_rcu(&f->link); tcf_unbind_filter(tp, &f->res); + idr_remove_ext(&head->handle_idr, f->handle); tcf_exts_get_net(&f->exts); call_rcu(&f->rcu, basic_delete_filter); *last = list_empty(&head->flist); @@ -177,6 +182,7 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, struct nlattr *tb[TCA_BASIC_MAX + 1]; struct basic_filter *fold = (struct basic_filter *) *arg; struct basic_filter *fnew; + unsigned long idr_index; if (tca[TCA_OPTIONS] == NULL) return -EINVAL; @@ -199,33 +205,33 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, if (err < 0) goto errout; - err = -EINVAL; if (handle) { fnew->handle = handle; - } else if (fold) { - fnew->handle = fold->handle; + if (!fold) { + err = idr_alloc_ext(&head->handle_idr, fnew, &idr_index, + handle, handle + 1, GFP_KERNEL); + if (err) + goto errout; + } } else { - unsigned int i = 0x80000000; - do { - if (++head->hgenerator == 0x7FFFFFFF) - head->hgenerator = 1; - } while (--i > 0 && basic_get(tp, head->hgenerator)); - - if (i <= 0) { - pr_err("Insufficient number of handles\n"); + err = idr_alloc_ext(&head->handle_idr, fnew, &idr_index, + 1, 0x7FFFFFFF, GFP_KERNEL); + if (err) goto errout; - } - - fnew->handle = head->hgenerator; + fnew->handle = idr_index; } err = basic_set_parms(net, tp, fnew, base, tb, tca[TCA_RATE], ovr); - if (err < 0) + if (err < 0) { + if (!fold) + idr_remove_ext(&head->handle_idr, fnew->handle); goto errout; + } *arg = fnew; if (fold) { + idr_replace_ext(&head->handle_idr, fnew, fnew->handle); list_replace_rcu(&fold->link, &fnew->link); tcf_unbind_filter(tp, &fold->res); tcf_exts_get_net(&fold->exts); diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 990eb4d91d54..fb680dafac5a 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -17,6 +17,7 @@ #include <linux/skbuff.h> #include <linux/filter.h> #include <linux/bpf.h> +#include <linux/idr.h> #include <net/rtnetlink.h> #include <net/pkt_cls.h> @@ -32,7 +33,7 @@ MODULE_DESCRIPTION("TC BPF based classifier"); struct cls_bpf_head { struct list_head plist; - u32 hgen; + struct idr handle_idr; struct rcu_head rcu; }; @@ -102,11 +103,11 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, } else if (at_ingress) { /* It is safe to push/pull even if skb_shared() */ __skb_push(skb, skb->mac_len); - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); filter_res = BPF_PROG_RUN(prog->filter, skb); __skb_pull(skb, skb->mac_len); } else { - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); filter_res = BPF_PROG_RUN(prog->filter, skb); } @@ -149,7 +150,9 @@ static bool cls_bpf_is_ebpf(const struct cls_bpf_prog *prog) static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, enum tc_clsbpf_command cmd) { - struct net_device *dev = tp->q->dev_queue->dev; + bool addorrep = cmd == TC_CLSBPF_ADD || cmd == TC_CLSBPF_REPLACE; + struct tcf_block *block = tp->chain->block; + bool skip_sw = tc_skip_sw(prog->gen_flags); struct tc_cls_bpf_offload cls_bpf = {}; int err; @@ -161,17 +164,25 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, cls_bpf.exts_integrated = prog->exts_integrated; cls_bpf.gen_flags = prog->gen_flags; - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSBPF, &cls_bpf); - if (!err && (cmd == TC_CLSBPF_ADD || cmd == TC_CLSBPF_REPLACE)) - prog->gen_flags |= TCA_CLS_FLAGS_IN_HW; + err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSBPF, &cls_bpf, skip_sw); + if (addorrep) { + if (err < 0) { + cls_bpf_offload_cmd(tp, prog, TC_CLSBPF_DESTROY); + return err; + } else if (err > 0) { + prog->gen_flags |= TCA_CLS_FLAGS_IN_HW; + } + } + + if (addorrep && skip_sw && !(prog->gen_flags & TCA_CLS_FLAGS_IN_HW)) + return -EINVAL; - return err; + return 0; } static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog, struct cls_bpf_prog *oldprog) { - struct net_device *dev = tp->q->dev_queue->dev; struct cls_bpf_prog *obj = prog; enum tc_clsbpf_command cmd; bool skip_sw; @@ -181,7 +192,7 @@ static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog, (oldprog && tc_skip_sw(oldprog->gen_flags)); if (oldprog && oldprog->offloaded) { - if (tc_should_offload(dev, prog->gen_flags)) { + if (!tc_skip_hw(prog->gen_flags)) { cmd = TC_CLSBPF_REPLACE; } else if (!tc_skip_sw(prog->gen_flags)) { obj = oldprog; @@ -190,14 +201,14 @@ static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog, return -EINVAL; } } else { - if (!tc_should_offload(dev, prog->gen_flags)) + if (tc_skip_hw(prog->gen_flags)) return skip_sw ? -EINVAL : 0; cmd = TC_CLSBPF_ADD; } ret = cls_bpf_offload_cmd(tp, obj, cmd); if (ret) - return skip_sw ? ret : 0; + return ret; obj->offloaded = true; if (oldprog) @@ -241,6 +252,7 @@ static int cls_bpf_init(struct tcf_proto *tp) return -ENOBUFS; INIT_LIST_HEAD_RCU(&head->plist); + idr_init(&head->handle_idr); rcu_assign_pointer(tp->root, head); return 0; @@ -280,6 +292,9 @@ static void cls_bpf_delete_prog_rcu(struct rcu_head *rcu) static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog) { + struct cls_bpf_head *head = rtnl_dereference(tp->root); + + idr_remove_ext(&head->handle_idr, prog->handle); cls_bpf_stop_offload(tp, prog); list_del_rcu(&prog->link); tcf_unbind_filter(tp, &prog->res); @@ -306,6 +321,7 @@ static void cls_bpf_destroy(struct tcf_proto *tp) list_for_each_entry_safe(prog, tmp, &head->plist, link) __cls_bpf_delete(tp, prog); + idr_destroy(&head->handle_idr); kfree_rcu(head, rcu); } @@ -362,7 +378,7 @@ static int cls_bpf_prog_from_ops(struct nlattr **tb, struct cls_bpf_prog *prog) } static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog, - const struct tcf_proto *tp) + u32 gen_flags, const struct tcf_proto *tp) { struct bpf_prog *fp; char *name = NULL; @@ -370,7 +386,11 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog, bpf_fd = nla_get_u32(tb[TCA_BPF_FD]); - fp = bpf_prog_get_type(bpf_fd, BPF_PROG_TYPE_SCHED_CLS); + if (gen_flags & TCA_CLS_FLAGS_SKIP_SW) + fp = bpf_prog_get_type_dev(bpf_fd, BPF_PROG_TYPE_SCHED_CLS, + qdisc_dev(tp->q)); + else + fp = bpf_prog_get_type(bpf_fd, BPF_PROG_TYPE_SCHED_CLS); if (IS_ERR(fp)) return PTR_ERR(fp); @@ -428,7 +448,7 @@ static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp, prog->gen_flags = gen_flags; ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) : - cls_bpf_prog_from_efd(tb, prog, tp); + cls_bpf_prog_from_efd(tb, prog, gen_flags, tp); if (ret < 0) return ret; @@ -440,27 +460,6 @@ static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp, return 0; } -static u32 cls_bpf_grab_new_handle(struct tcf_proto *tp, - struct cls_bpf_head *head) -{ - unsigned int i = 0x80000000; - u32 handle; - - do { - if (++head->hgen == 0x7FFFFFFF) - head->hgen = 1; - } while (--i > 0 && cls_bpf_get(tp, head->hgen)); - - if (unlikely(i == 0)) { - pr_err("Insufficient number of handles\n"); - handle = 0; - } else { - handle = head->hgen; - } - - return handle; -} - static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, @@ -470,6 +469,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, struct cls_bpf_prog *oldprog = *arg; struct nlattr *tb[TCA_BPF_MAX + 1]; struct cls_bpf_prog *prog; + unsigned long idr_index; int ret; if (tca[TCA_OPTIONS] == NULL) @@ -495,21 +495,30 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, } } - if (handle == 0) - prog->handle = cls_bpf_grab_new_handle(tp, head); - else + if (handle == 0) { + ret = idr_alloc_ext(&head->handle_idr, prog, &idr_index, + 1, 0x7FFFFFFF, GFP_KERNEL); + if (ret) + goto errout; + prog->handle = idr_index; + } else { + if (!oldprog) { + ret = idr_alloc_ext(&head->handle_idr, prog, &idr_index, + handle, handle + 1, GFP_KERNEL); + if (ret) + goto errout; + } prog->handle = handle; - if (prog->handle == 0) { - ret = -EINVAL; - goto errout; } ret = cls_bpf_set_parms(net, tp, prog, base, tb, tca[TCA_RATE], ovr); if (ret < 0) - goto errout; + goto errout_idr; ret = cls_bpf_offload(tp, prog, oldprog); if (ret) { + if (!oldprog) + idr_remove_ext(&head->handle_idr, prog->handle); __cls_bpf_delete_prog(prog); return ret; } @@ -518,6 +527,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, prog->gen_flags |= TCA_CLS_FLAGS_NOT_IN_HW; if (oldprog) { + idr_replace_ext(&head->handle_idr, prog, handle); list_replace_rcu(&oldprog->link, &prog->link); tcf_unbind_filter(tp, &oldprog->res); tcf_exts_get_net(&oldprog->exts); @@ -529,6 +539,9 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, *arg = prog; return 0; +errout_idr: + if (!oldprog) + idr_remove_ext(&head->handle_idr, prog->handle); errout: tcf_exts_destroy(&prog->exts); kfree(prog); diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 85f765cff697..25c2a888e1f0 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -348,9 +348,9 @@ static int flow_classify(struct sk_buff *skb, const struct tcf_proto *tp, return -1; } -static void flow_perturbation(unsigned long arg) +static void flow_perturbation(struct timer_list *t) { - struct flow_filter *f = (struct flow_filter *)arg; + struct flow_filter *f = from_timer(f, t, perturb_timer); get_random_bytes(&f->hashrnd, 4); if (f->perturb_period) @@ -510,8 +510,11 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, perturb_period = nla_get_u32(tb[TCA_FLOW_PERTURB]) * HZ; } - if (TC_H_MAJ(baseclass) == 0) - baseclass = TC_H_MAKE(tp->q->handle, baseclass); + if (TC_H_MAJ(baseclass) == 0) { + struct Qdisc *q = tcf_block_q(tp->chain->block); + + baseclass = TC_H_MAKE(q->handle, baseclass); + } if (TC_H_MIN(baseclass) == 0) baseclass = TC_H_MAKE(baseclass, 1); @@ -521,8 +524,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, get_random_bytes(&fnew->hashrnd, 4); } - setup_deferrable_timer(&fnew->perturb_timer, flow_perturbation, - (unsigned long)fnew); + timer_setup(&fnew->perturb_timer, flow_perturbation, TIMER_DEFERRABLE); netif_keep_dst(qdisc_dev(tp->q)); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 7a838d1c1c00..543a3e875d05 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -155,37 +155,12 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct cls_fl_filter *f; struct fl_flow_key skb_key; struct fl_flow_key skb_mkey; - struct ip_tunnel_info *info; if (!atomic_read(&head->ht.nelems)) return -1; fl_clear_masked_range(&skb_key, &head->mask); - info = skb_tunnel_info(skb); - if (info) { - struct ip_tunnel_key *key = &info->key; - - switch (ip_tunnel_info_af(info)) { - case AF_INET: - skb_key.enc_control.addr_type = - FLOW_DISSECTOR_KEY_IPV4_ADDRS; - skb_key.enc_ipv4.src = key->u.ipv4.src; - skb_key.enc_ipv4.dst = key->u.ipv4.dst; - break; - case AF_INET6: - skb_key.enc_control.addr_type = - FLOW_DISSECTOR_KEY_IPV6_ADDRS; - skb_key.enc_ipv6.src = key->u.ipv6.src; - skb_key.enc_ipv6.dst = key->u.ipv6.dst; - break; - } - - skb_key.enc_key_id.keyid = tunnel_id_to_key32(key->tun_id); - skb_key.enc_tp.src = key->tp_src; - skb_key.enc_tp.dst = key->tp_dst; - } - skb_key.indev_ifindex = skb->skb_iif; /* skb_flow_dissect() does not set n_proto in case an unknown protocol, * so do it rather here. @@ -245,17 +220,14 @@ static void fl_destroy_filter(struct rcu_head *head) static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f) { struct tc_cls_flower_offload cls_flower = {}; - struct net_device *dev = f->hw_dev; - - if (!tc_can_offload(dev)) - return; + struct tcf_block *block = tp->chain->block; tc_cls_common_offload_init(&cls_flower.common, tp); cls_flower.command = TC_CLSFLOWER_DESTROY; cls_flower.cookie = (unsigned long) f; - cls_flower.egress_dev = f->hw_dev != tp->q->dev_queue->dev; - dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, &cls_flower); + tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER, + &cls_flower, false); } static int fl_hw_replace_filter(struct tcf_proto *tp, @@ -263,22 +235,11 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, struct fl_flow_key *mask, struct cls_fl_filter *f) { - struct net_device *dev = tp->q->dev_queue->dev; struct tc_cls_flower_offload cls_flower = {}; + struct tcf_block *block = tp->chain->block; + bool skip_sw = tc_skip_sw(f->flags); int err; - if (!tc_can_offload(dev)) { - if (tcf_exts_get_dev(dev, &f->exts, &f->hw_dev) || - (f->hw_dev && !tc_can_offload(f->hw_dev))) { - f->hw_dev = dev; - return tc_skip_sw(f->flags) ? -EINVAL : 0; - } - dev = f->hw_dev; - cls_flower.egress_dev = true; - } else { - f->hw_dev = dev; - } - tc_cls_common_offload_init(&cls_flower.common, tp); cls_flower.command = TC_CLSFLOWER_REPLACE; cls_flower.cookie = (unsigned long) f; @@ -286,33 +247,36 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, cls_flower.mask = mask; cls_flower.key = &f->mkey; cls_flower.exts = &f->exts; + cls_flower.classid = f->res.classid; - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, - &cls_flower); - if (!err) + err = tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER, + &cls_flower, skip_sw); + if (err < 0) { + fl_hw_destroy_filter(tp, f); + return err; + } else if (err > 0) { f->flags |= TCA_CLS_FLAGS_IN_HW; + } + + if (skip_sw && !(f->flags & TCA_CLS_FLAGS_IN_HW)) + return -EINVAL; - if (tc_skip_sw(f->flags)) - return err; return 0; } static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f) { struct tc_cls_flower_offload cls_flower = {}; - struct net_device *dev = f->hw_dev; - - if (!tc_can_offload(dev)) - return; + struct tcf_block *block = tp->chain->block; tc_cls_common_offload_init(&cls_flower.common, tp); cls_flower.command = TC_CLSFLOWER_STATS; cls_flower.cookie = (unsigned long) f; cls_flower.exts = &f->exts; - cls_flower.egress_dev = f->hw_dev != tp->q->dev_queue->dev; + cls_flower.classid = f->res.classid; - dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, - &cls_flower); + tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER, + &cls_flower, false); } static void __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f) diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 7f45e5ab8afc..20f0de1a960a 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -28,6 +28,7 @@ #include <net/netlink.h> #include <net/act_api.h> #include <net/pkt_cls.h> +#include <net/sch_generic.h> #define HTSIZE 256 @@ -86,9 +87,11 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, } } } else { + struct Qdisc *q = tcf_block_q(tp->chain->block); + /* Old method: classify the packet using its skb mark. */ if (id && (TC_H_MAJ(id) == 0 || - !(TC_H_MAJ(id ^ tp->q->handle)))) { + !(TC_H_MAJ(id ^ q->handle)))) { res->classid = id; res->class = 0; return 0; diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 3684153cd8a9..66d4e0099158 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -69,12 +69,27 @@ static void mall_destroy_rcu(struct rcu_head *rcu) tcf_queue_work(&head->work); } +static void mall_destroy_hw_filter(struct tcf_proto *tp, + struct cls_mall_head *head, + unsigned long cookie) +{ + struct tc_cls_matchall_offload cls_mall = {}; + struct tcf_block *block = tp->chain->block; + + tc_cls_common_offload_init(&cls_mall.common, tp); + cls_mall.command = TC_CLSMATCHALL_DESTROY; + cls_mall.cookie = cookie; + + tc_setup_cb_call(block, NULL, TC_SETUP_CLSMATCHALL, &cls_mall, false); +} + static int mall_replace_hw_filter(struct tcf_proto *tp, struct cls_mall_head *head, unsigned long cookie) { - struct net_device *dev = tp->q->dev_queue->dev; struct tc_cls_matchall_offload cls_mall = {}; + struct tcf_block *block = tp->chain->block; + bool skip_sw = tc_skip_sw(head->flags); int err; tc_cls_common_offload_init(&cls_mall.common, tp); @@ -82,37 +97,29 @@ static int mall_replace_hw_filter(struct tcf_proto *tp, cls_mall.exts = &head->exts; cls_mall.cookie = cookie; - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSMATCHALL, - &cls_mall); - if (!err) + err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSMATCHALL, + &cls_mall, skip_sw); + if (err < 0) { + mall_destroy_hw_filter(tp, head, cookie); + return err; + } else if (err > 0) { head->flags |= TCA_CLS_FLAGS_IN_HW; + } - return err; -} - -static void mall_destroy_hw_filter(struct tcf_proto *tp, - struct cls_mall_head *head, - unsigned long cookie) -{ - struct net_device *dev = tp->q->dev_queue->dev; - struct tc_cls_matchall_offload cls_mall = {}; - - tc_cls_common_offload_init(&cls_mall.common, tp); - cls_mall.command = TC_CLSMATCHALL_DESTROY; - cls_mall.cookie = cookie; + if (skip_sw && !(head->flags & TCA_CLS_FLAGS_IN_HW)) + return -EINVAL; - dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSMATCHALL, &cls_mall); + return 0; } static void mall_destroy(struct tcf_proto *tp) { struct cls_mall_head *head = rtnl_dereference(tp->root); - struct net_device *dev = tp->q->dev_queue->dev; if (!head) return; - if (tc_should_offload(dev, head->flags)) + if (!tc_skip_hw(head->flags)) mall_destroy_hw_filter(tp, head, (unsigned long) head); if (tcf_exts_get_net(&head->exts)) @@ -155,7 +162,6 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, void **arg, bool ovr) { struct cls_mall_head *head = rtnl_dereference(tp->root); - struct net_device *dev = tp->q->dev_queue->dev; struct nlattr *tb[TCA_MATCHALL_MAX + 1]; struct cls_mall_head *new; u32 flags = 0; @@ -195,14 +201,10 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, if (err) goto err_set_parms; - if (tc_should_offload(dev, flags)) { + if (!tc_skip_hw(new->flags)) { err = mall_replace_hw_filter(tp, new, (unsigned long) new); - if (err) { - if (tc_skip_sw(flags)) - goto err_replace_hw_filter; - else - err = 0; - } + if (err) + goto err_replace_hw_filter; } if (!tc_in_hw(new->flags)) diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index a76937ee0b2d..67467ae24c97 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -13,6 +13,7 @@ #include <net/act_api.h> #include <net/netlink.h> #include <net/pkt_cls.h> +#include <net/sch_generic.h> /* * Passing parameters to the root seems to be done more awkwardly than really @@ -96,9 +97,11 @@ static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp, f = tcindex_lookup(p, key); if (!f) { + struct Qdisc *q = tcf_block_q(tp->chain->block); + if (!p->fall_through) return -1; - res->classid = TC_H_MAKE(TC_H_MAJ(tp->q->handle), key); + res->classid = TC_H_MAKE(TC_H_MAJ(q->handle), key); res->class = 0; pr_debug("alg 0x%x\n", res->classid); return 0; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index b58eccb21f03..ac152b4f4247 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -46,6 +46,7 @@ #include <net/act_api.h> #include <net/pkt_cls.h> #include <linux/netdevice.h> +#include <linux/idr.h> struct tc_u_knode { struct tc_u_knode __rcu *next; @@ -85,6 +86,7 @@ struct tc_u_hnode { struct tc_u_common *tp_c; int refcnt; unsigned int divisor; + struct idr handle_idr; struct rcu_head rcu; /* The 'ht' field MUST be the last field in structure to allow for * more entries allocated at end of structure. @@ -94,9 +96,9 @@ struct tc_u_hnode { struct tc_u_common { struct tc_u_hnode __rcu *hlist; - struct Qdisc *q; + struct tcf_block *block; int refcnt; - u32 hgenerator; + struct idr handle_idr; struct hlist_node hnode; struct rcu_head rcu; }; @@ -314,19 +316,19 @@ static void *u32_get(struct tcf_proto *tp, u32 handle) return u32_lookup_key(ht, handle); } -static u32 gen_new_htid(struct tc_u_common *tp_c) +static u32 gen_new_htid(struct tc_u_common *tp_c, struct tc_u_hnode *ptr) { - int i = 0x800; + unsigned long idr_index; + int err; - /* hgenerator only used inside rtnl lock it is safe to increment + /* This is only used inside rtnl lock it is safe to increment * without read _copy_ update semantics */ - do { - if (++tp_c->hgenerator == 0x7FF) - tp_c->hgenerator = 1; - } while (--i > 0 && u32_lookup_ht(tp_c, (tp_c->hgenerator|0x800)<<20)); - - return i > 0 ? (tp_c->hgenerator|0x800)<<20 : 0; + err = idr_alloc_ext(&tp_c->handle_idr, ptr, &idr_index, + 1, 0x7FF, GFP_KERNEL); + if (err) + return 0; + return (u32)(idr_index | 0x800) << 20; } static struct hlist_head *tc_u_common_hash; @@ -336,11 +338,7 @@ static struct hlist_head *tc_u_common_hash; static unsigned int tc_u_hash(const struct tcf_proto *tp) { - struct net_device *dev = tp->q->dev_queue->dev; - u32 qhandle = tp->q->handle; - int ifindex = dev->ifindex; - - return hash_64((u64)ifindex << 32 | qhandle, U32_HASH_SHIFT); + return hash_ptr(tp->chain->block, U32_HASH_SHIFT); } static struct tc_u_common *tc_u_common_find(const struct tcf_proto *tp) @@ -350,7 +348,7 @@ static struct tc_u_common *tc_u_common_find(const struct tcf_proto *tp) h = tc_u_hash(tp); hlist_for_each_entry(tc, &tc_u_common_hash[h], hnode) { - if (tc->q == tp->q) + if (tc->block == tp->chain->block) return tc; } return NULL; @@ -369,8 +367,9 @@ static int u32_init(struct tcf_proto *tp) return -ENOBUFS; root_ht->refcnt++; - root_ht->handle = tp_c ? gen_new_htid(tp_c) : 0x80000000; + root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : 0x80000000; root_ht->prio = tp->prio; + idr_init(&root_ht->handle_idr); if (tp_c == NULL) { tp_c = kzalloc(sizeof(*tp_c), GFP_KERNEL); @@ -378,8 +377,9 @@ static int u32_init(struct tcf_proto *tp) kfree(root_ht); return -ENOBUFS; } - tp_c->q = tp->q; + tp_c->block = tp->chain->block; INIT_HLIST_NODE(&tp_c->hnode); + idr_init(&tp_c->handle_idr); h = tc_u_hash(tp); hlist_add_head(&tp_c->hnode, &tc_u_common_hash[h]); @@ -487,71 +487,69 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key) return 0; } -static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle) +static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) { - struct net_device *dev = tp->q->dev_queue->dev; + struct tcf_block *block = tp->chain->block; struct tc_cls_u32_offload cls_u32 = {}; - if (!tc_should_offload(dev, 0)) - return; - tc_cls_common_offload_init(&cls_u32.common, tp); - cls_u32.command = TC_CLSU32_DELETE_KNODE; - cls_u32.knode.handle = handle; + cls_u32.command = TC_CLSU32_DELETE_HNODE; + cls_u32.hnode.divisor = h->divisor; + cls_u32.hnode.handle = h->handle; + cls_u32.hnode.prio = h->prio; - dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32); + tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, false); } static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h, u32 flags) { - struct net_device *dev = tp->q->dev_queue->dev; + struct tcf_block *block = tp->chain->block; struct tc_cls_u32_offload cls_u32 = {}; + bool skip_sw = tc_skip_sw(flags); + bool offloaded = false; int err; - if (!tc_should_offload(dev, flags)) - return tc_skip_sw(flags) ? -EINVAL : 0; - tc_cls_common_offload_init(&cls_u32.common, tp); cls_u32.command = TC_CLSU32_NEW_HNODE; cls_u32.hnode.divisor = h->divisor; cls_u32.hnode.handle = h->handle; cls_u32.hnode.prio = h->prio; - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32); - if (tc_skip_sw(flags)) + err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, skip_sw); + if (err < 0) { + u32_clear_hw_hnode(tp, h); return err; + } else if (err > 0) { + offloaded = true; + } + + if (skip_sw && !offloaded) + return -EINVAL; return 0; } -static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h) +static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle) { - struct net_device *dev = tp->q->dev_queue->dev; + struct tcf_block *block = tp->chain->block; struct tc_cls_u32_offload cls_u32 = {}; - if (!tc_should_offload(dev, 0)) - return; - tc_cls_common_offload_init(&cls_u32.common, tp); - cls_u32.command = TC_CLSU32_DELETE_HNODE; - cls_u32.hnode.divisor = h->divisor; - cls_u32.hnode.handle = h->handle; - cls_u32.hnode.prio = h->prio; + cls_u32.command = TC_CLSU32_DELETE_KNODE; + cls_u32.knode.handle = handle; - dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32); + tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, false); } static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, u32 flags) { - struct net_device *dev = tp->q->dev_queue->dev; + struct tcf_block *block = tp->chain->block; struct tc_cls_u32_offload cls_u32 = {}; + bool skip_sw = tc_skip_sw(flags); int err; - if (!tc_should_offload(dev, flags)) - return tc_skip_sw(flags) ? -EINVAL : 0; - tc_cls_common_offload_init(&cls_u32.common, tp); cls_u32.command = TC_CLSU32_REPLACE_KNODE; cls_u32.knode.handle = n->handle; @@ -568,13 +566,16 @@ static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n, if (n->ht_down) cls_u32.knode.link_handle = n->ht_down->handle; - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32); - - if (!err) + err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, skip_sw); + if (err < 0) { + u32_remove_hw_knode(tp, n->handle); + return err; + } else if (err > 0) { n->flags |= TCA_CLS_FLAGS_IN_HW; + } - if (tc_skip_sw(flags)) - return err; + if (skip_sw && !(n->flags & TCA_CLS_FLAGS_IN_HW)) + return -EINVAL; return 0; } @@ -590,6 +591,7 @@ static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) rtnl_dereference(n->next)); tcf_unbind_filter(tp, &n->res); u32_remove_hw_knode(tp, n->handle); + idr_remove_ext(&ht->handle_idr, n->handle); if (tcf_exts_get_net(&n->exts)) call_rcu(&n->rcu, u32_delete_key_freepf_rcu); else @@ -614,6 +616,8 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) hn = &phn->next, phn = rtnl_dereference(*hn)) { if (phn == ht) { u32_clear_hw_hnode(tp, ht); + idr_destroy(&ht->handle_idr); + idr_remove_ext(&tp_c->handle_idr, ht->handle); RCU_INIT_POINTER(*hn, ht->next); kfree_rcu(ht, rcu); return 0; @@ -661,6 +665,7 @@ static void u32_destroy(struct tcf_proto *tp) kfree_rcu(ht, rcu); } + idr_destroy(&tp_c->handle_idr); kfree(tp_c); } @@ -729,27 +734,21 @@ ret: return ret; } -#define NR_U32_NODE (1<<12) -static u32 gen_new_kid(struct tc_u_hnode *ht, u32 handle) +static u32 gen_new_kid(struct tc_u_hnode *ht, u32 htid) { - struct tc_u_knode *n; - unsigned long i; - unsigned long *bitmap = kzalloc(BITS_TO_LONGS(NR_U32_NODE) * sizeof(unsigned long), - GFP_KERNEL); - if (!bitmap) - return handle | 0xFFF; - - for (n = rtnl_dereference(ht->ht[TC_U32_HASH(handle)]); - n; - n = rtnl_dereference(n->next)) - set_bit(TC_U32_NODE(n->handle), bitmap); - - i = find_next_zero_bit(bitmap, NR_U32_NODE, 0x800); - if (i >= NR_U32_NODE) - i = find_next_zero_bit(bitmap, NR_U32_NODE, 1); + unsigned long idr_index; + u32 start = htid | 0x800; + u32 max = htid | 0xFFF; + u32 min = htid; + + if (idr_alloc_ext(&ht->handle_idr, NULL, &idr_index, + start, max + 1, GFP_KERNEL)) { + if (idr_alloc_ext(&ht->handle_idr, NULL, &idr_index, + min + 1, max + 1, GFP_KERNEL)) + return max; + } - kfree(bitmap); - return handle | (i >= NR_U32_NODE ? 0xFFF : i); + return (u32)idr_index; } static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { @@ -834,6 +833,7 @@ static void u32_replace_knode(struct tcf_proto *tp, struct tc_u_common *tp_c, if (pins->handle == n->handle) break; + idr_replace_ext(&ht->handle_idr, n, n->handle); RCU_INIT_POINTER(n->next, pins->next); rcu_assign_pointer(*ins, n); } @@ -966,22 +966,33 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return -EINVAL; if (TC_U32_KEY(handle)) return -EINVAL; - if (handle == 0) { - handle = gen_new_htid(tp->data); - if (handle == 0) - return -ENOMEM; - } ht = kzalloc(sizeof(*ht) + divisor*sizeof(void *), GFP_KERNEL); if (ht == NULL) return -ENOBUFS; + if (handle == 0) { + handle = gen_new_htid(tp->data, ht); + if (handle == 0) { + kfree(ht); + return -ENOMEM; + } + } else { + err = idr_alloc_ext(&tp_c->handle_idr, ht, NULL, + handle, handle + 1, GFP_KERNEL); + if (err) { + kfree(ht); + return err; + } + } ht->tp_c = tp_c; ht->refcnt = 1; ht->divisor = divisor; ht->handle = handle; ht->prio = tp->prio; + idr_init(&ht->handle_idr); err = u32_replace_hw_hnode(tp, ht, flags); if (err) { + idr_remove_ext(&tp_c->handle_idr, handle); kfree(ht); return err; } @@ -1015,24 +1026,33 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, if (TC_U32_HTID(handle) && TC_U32_HTID(handle^htid)) return -EINVAL; handle = htid | TC_U32_NODE(handle); + err = idr_alloc_ext(&ht->handle_idr, NULL, NULL, + handle, handle + 1, + GFP_KERNEL); + if (err) + return err; } else handle = gen_new_kid(ht, htid); - if (tb[TCA_U32_SEL] == NULL) - return -EINVAL; + if (tb[TCA_U32_SEL] == NULL) { + err = -EINVAL; + goto erridr; + } s = nla_data(tb[TCA_U32_SEL]); n = kzalloc(sizeof(*n) + s->nkeys*sizeof(struct tc_u32_key), GFP_KERNEL); - if (n == NULL) - return -ENOBUFS; + if (n == NULL) { + err = -ENOBUFS; + goto erridr; + } #ifdef CONFIG_CLS_U32_PERF size = sizeof(struct tc_u32_pcnt) + s->nkeys * sizeof(u64); n->pf = __alloc_percpu(size, __alignof__(struct tc_u32_pcnt)); if (!n->pf) { - kfree(n); - return -ENOBUFS; + err = -ENOBUFS; + goto errfree; } #endif @@ -1095,9 +1115,12 @@ errhw: errout: tcf_exts_destroy(&n->exts); #ifdef CONFIG_CLS_U32_PERF +errfree: free_percpu(n->pf); #endif kfree(n); +erridr: + idr_remove_ext(&ht->handle_idr, handle); return err; } diff --git a/net/sched/ematch.c b/net/sched/ematch.c index 03b677bc0700..1331a4c2d8ff 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -178,7 +178,7 @@ static int tcf_em_validate(struct tcf_proto *tp, struct tcf_ematch_hdr *em_hdr = nla_data(nla); int data_len = nla_len(nla) - sizeof(*em_hdr); void *data = (void *) em_hdr + sizeof(*em_hdr); - struct net *net = dev_net(qdisc_dev(tp->q)); + struct net *net = tp->chain->block->net; if (!TCF_EM_REL_VALID(em_hdr->flags)) goto errout; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 22bc6fc48311..b6c4f536876b 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1502,7 +1502,6 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) int s_idx, s_q_idx; struct net_device *dev; const struct nlmsghdr *nlh = cb->nlh; - struct tcmsg *tcm = nlmsg_data(nlh); struct nlattr *tca[TCA_MAX + 1]; int err; @@ -1512,7 +1511,7 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) idx = 0; ASSERT_RTNL(); - err = nlmsg_parse(nlh, sizeof(*tcm), tca, TCA_MAX, NULL, NULL); + err = nlmsg_parse(nlh, sizeof(struct tcmsg), tca, TCA_MAX, NULL, NULL); if (err < 0) return err; @@ -1664,9 +1663,11 @@ static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg) struct tcf_bind_args *a = (void *)arg; if (tp->ops->bind_class) { - tcf_tree_lock(tp); + struct Qdisc *q = tcf_block_q(tp->chain->block); + + sch_tree_lock(q); tp->ops->bind_class(n, a->classid, a->cl); - tcf_tree_unlock(tp); + sch_tree_unlock(q); } return 0; } diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index c5fcdf1a58a0..2dbd249c0b2f 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -281,7 +281,7 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, goto err_out; } - error = tcf_block_get(&flow->block, &flow->filter_list); + error = tcf_block_get(&flow->block, &flow->filter_list, sch); if (error) { kfree(flow); goto err_out; @@ -546,7 +546,7 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt) p->link.q = &noop_qdisc; pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q); - err = tcf_block_get(&p->link.block, &p->link.filter_list); + err = tcf_block_get(&p->link.block, &p->link.filter_list, sch); if (err) return err; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index dcef97fa8047..6361be7881f1 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -255,6 +255,7 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) case TC_ACT_STOLEN: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ case TC_ACT_SHOT: return NULL; case TC_ACT_RECLASSIFY: @@ -1566,7 +1567,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t if (cl == NULL) goto failure; - err = tcf_block_get(&cl->block, &cl->filter_list); + err = tcf_block_get(&cl->block, &cl->filter_list, sch); if (err) { kfree(cl); return err; diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c new file mode 100644 index 000000000000..7a72980c1509 --- /dev/null +++ b/net/sched/sch_cbs.c @@ -0,0 +1,373 @@ +/* + * net/sched/sch_cbs.c Credit Based Shaper + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Authors: Vinicius Costa Gomes <vinicius.gomes@intel.com> + * + */ + +/* Credit Based Shaper (CBS) + * ========================= + * + * This is a simple rate-limiting shaper aimed at TSN applications on + * systems with known traffic workloads. + * + * Its algorithm is defined by the IEEE 802.1Q-2014 Specification, + * Section 8.6.8.2, and explained in more detail in the Annex L of the + * same specification. + * + * There are four tunables to be considered: + * + * 'idleslope': Idleslope is the rate of credits that is + * accumulated (in kilobits per second) when there is at least + * one packet waiting for transmission. Packets are transmitted + * when the current value of credits is equal or greater than + * zero. When there is no packet to be transmitted the amount of + * credits is set to zero. This is the main tunable of the CBS + * algorithm. + * + * 'sendslope': + * Sendslope is the rate of credits that is depleted (it should be a + * negative number of kilobits per second) when a transmission is + * ocurring. It can be calculated as follows, (IEEE 802.1Q-2014 Section + * 8.6.8.2 item g): + * + * sendslope = idleslope - port_transmit_rate + * + * 'hicredit': Hicredit defines the maximum amount of credits (in + * bytes) that can be accumulated. Hicredit depends on the + * characteristics of interfering traffic, + * 'max_interference_size' is the maximum size of any burst of + * traffic that can delay the transmission of a frame that is + * available for transmission for this traffic class, (IEEE + * 802.1Q-2014 Annex L, Equation L-3): + * + * hicredit = max_interference_size * (idleslope / port_transmit_rate) + * + * 'locredit': Locredit is the minimum amount of credits that can + * be reached. It is a function of the traffic flowing through + * this qdisc (IEEE 802.1Q-2014 Annex L, Equation L-2): + * + * locredit = max_frame_size * (sendslope / port_transmit_rate) + */ + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <net/netlink.h> +#include <net/sch_generic.h> +#include <net/pkt_sched.h> + +#define BYTES_PER_KBIT (1000LL / 8) + +struct cbs_sched_data { + bool offload; + int queue; + s64 port_rate; /* in bytes/s */ + s64 last; /* timestamp in ns */ + s64 credits; /* in bytes */ + s32 locredit; /* in bytes */ + s32 hicredit; /* in bytes */ + s64 sendslope; /* in bytes/s */ + s64 idleslope; /* in bytes/s */ + struct qdisc_watchdog watchdog; + int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch); + struct sk_buff *(*dequeue)(struct Qdisc *sch); +}; + +static int cbs_enqueue_offload(struct sk_buff *skb, struct Qdisc *sch) +{ + return qdisc_enqueue_tail(skb, sch); +} + +static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + + if (sch->q.qlen == 0 && q->credits > 0) { + /* We need to stop accumulating credits when there's + * no enqueued packets and q->credits is positive. + */ + q->credits = 0; + q->last = ktime_get_ns(); + } + + return qdisc_enqueue_tail(skb, sch); +} + +static int cbs_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + + return q->enqueue(skb, sch); +} + +/* timediff is in ns, slope is in bytes/s */ +static s64 timediff_to_credits(s64 timediff, s64 slope) +{ + return div64_s64(timediff * slope, NSEC_PER_SEC); +} + +static s64 delay_from_credits(s64 credits, s64 slope) +{ + if (unlikely(slope == 0)) + return S64_MAX; + + return div64_s64(-credits * NSEC_PER_SEC, slope); +} + +static s64 credits_from_len(unsigned int len, s64 slope, s64 port_rate) +{ + if (unlikely(port_rate == 0)) + return S64_MAX; + + return div64_s64(len * slope, port_rate); +} + +static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + s64 now = ktime_get_ns(); + struct sk_buff *skb; + s64 credits; + int len; + + if (q->credits < 0) { + credits = timediff_to_credits(now - q->last, q->idleslope); + + credits = q->credits + credits; + q->credits = min_t(s64, credits, q->hicredit); + + if (q->credits < 0) { + s64 delay; + + delay = delay_from_credits(q->credits, q->idleslope); + qdisc_watchdog_schedule_ns(&q->watchdog, now + delay); + + q->last = now; + + return NULL; + } + } + + skb = qdisc_dequeue_head(sch); + if (!skb) + return NULL; + + len = qdisc_pkt_len(skb); + + /* As sendslope is a negative number, this will decrease the + * amount of q->credits. + */ + credits = credits_from_len(len, q->sendslope, q->port_rate); + credits += q->credits; + + q->credits = max_t(s64, credits, q->locredit); + q->last = now; + + return skb; +} + +static struct sk_buff *cbs_dequeue_offload(struct Qdisc *sch) +{ + return qdisc_dequeue_head(sch); +} + +static struct sk_buff *cbs_dequeue(struct Qdisc *sch) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + + return q->dequeue(sch); +} + +static const struct nla_policy cbs_policy[TCA_CBS_MAX + 1] = { + [TCA_CBS_PARMS] = { .len = sizeof(struct tc_cbs_qopt) }, +}; + +static void cbs_disable_offload(struct net_device *dev, + struct cbs_sched_data *q) +{ + struct tc_cbs_qopt_offload cbs = { }; + const struct net_device_ops *ops; + int err; + + if (!q->offload) + return; + + q->enqueue = cbs_enqueue_soft; + q->dequeue = cbs_dequeue_soft; + + ops = dev->netdev_ops; + if (!ops->ndo_setup_tc) + return; + + cbs.queue = q->queue; + cbs.enable = 0; + + err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_CBS, &cbs); + if (err < 0) + pr_warn("Couldn't disable CBS offload for queue %d\n", + cbs.queue); +} + +static int cbs_enable_offload(struct net_device *dev, struct cbs_sched_data *q, + const struct tc_cbs_qopt *opt) +{ + const struct net_device_ops *ops = dev->netdev_ops; + struct tc_cbs_qopt_offload cbs = { }; + int err; + + if (!ops->ndo_setup_tc) + return -EOPNOTSUPP; + + cbs.queue = q->queue; + + cbs.enable = 1; + cbs.hicredit = opt->hicredit; + cbs.locredit = opt->locredit; + cbs.idleslope = opt->idleslope; + cbs.sendslope = opt->sendslope; + + err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_CBS, &cbs); + if (err < 0) + return err; + + q->enqueue = cbs_enqueue_offload; + q->dequeue = cbs_dequeue_offload; + + return 0; +} + +static int cbs_change(struct Qdisc *sch, struct nlattr *opt) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct nlattr *tb[TCA_CBS_MAX + 1]; + struct tc_cbs_qopt *qopt; + int err; + + err = nla_parse_nested(tb, TCA_CBS_MAX, opt, cbs_policy, NULL); + if (err < 0) + return err; + + if (!tb[TCA_CBS_PARMS]) + return -EINVAL; + + qopt = nla_data(tb[TCA_CBS_PARMS]); + + if (!qopt->offload) { + struct ethtool_link_ksettings ecmd; + s64 link_speed; + + if (!__ethtool_get_link_ksettings(dev, &ecmd)) + link_speed = ecmd.base.speed; + else + link_speed = SPEED_1000; + + q->port_rate = link_speed * 1000 * BYTES_PER_KBIT; + + cbs_disable_offload(dev, q); + } else { + err = cbs_enable_offload(dev, q, qopt); + if (err < 0) + return err; + } + + /* Everything went OK, save the parameters used. */ + q->hicredit = qopt->hicredit; + q->locredit = qopt->locredit; + q->idleslope = qopt->idleslope * BYTES_PER_KBIT; + q->sendslope = qopt->sendslope * BYTES_PER_KBIT; + q->offload = qopt->offload; + + return 0; +} + +static int cbs_init(struct Qdisc *sch, struct nlattr *opt) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + + if (!opt) + return -EINVAL; + + q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0); + + q->enqueue = cbs_enqueue_soft; + q->dequeue = cbs_dequeue_soft; + + qdisc_watchdog_init(&q->watchdog, sch); + + return cbs_change(sch, opt); +} + +static void cbs_destroy(struct Qdisc *sch) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + + qdisc_watchdog_cancel(&q->watchdog); + + cbs_disable_offload(dev, q); +} + +static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + struct tc_cbs_qopt opt = { }; + struct nlattr *nest; + + nest = nla_nest_start(skb, TCA_OPTIONS); + if (!nest) + goto nla_put_failure; + + opt.hicredit = q->hicredit; + opt.locredit = q->locredit; + opt.sendslope = div64_s64(q->sendslope, BYTES_PER_KBIT); + opt.idleslope = div64_s64(q->idleslope, BYTES_PER_KBIT); + opt.offload = q->offload; + + if (nla_put(skb, TCA_CBS_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; + + return nla_nest_end(skb, nest); + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -1; +} + +static struct Qdisc_ops cbs_qdisc_ops __read_mostly = { + .id = "cbs", + .priv_size = sizeof(struct cbs_sched_data), + .enqueue = cbs_enqueue, + .dequeue = cbs_dequeue, + .peek = qdisc_peek_dequeued, + .init = cbs_init, + .reset = qdisc_reset_queue, + .destroy = cbs_destroy, + .change = cbs_change, + .dump = cbs_dump, + .owner = THIS_MODULE, +}; + +static int __init cbs_module_init(void) +{ + return register_qdisc(&cbs_qdisc_ops); +} + +static void __exit cbs_module_exit(void) +{ + unregister_qdisc(&cbs_qdisc_ops); +} +module_init(cbs_module_init) +module_exit(cbs_module_exit) +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 2d0e8d4bdc29..5bbcef3dcd8c 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -321,6 +321,7 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_STOLEN: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ case TC_ACT_SHOT: return NULL; } @@ -412,7 +413,7 @@ static int drr_init_qdisc(struct Qdisc *sch, struct nlattr *opt) struct drr_sched *q = qdisc_priv(sch); int err; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; err = qdisc_class_hash_init(&q->clhash); diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 2836c80c7aa5..fb4fb71c68cf 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -344,7 +344,7 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) if (!opt) goto errout; - err = tcf_block_get(&p->block, &p->filter_list); + err = tcf_block_get(&p->block, &p->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index de3b57ceca7b..0305d791ea94 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -105,6 +105,7 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ case TC_ACT_SHOT: return 0; } @@ -481,7 +482,7 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) return err; } - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index bf8c81e07c70..3839cbbdc32b 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -288,9 +288,9 @@ unsigned long dev_trans_start(struct net_device *dev) } EXPORT_SYMBOL(dev_trans_start); -static void dev_watchdog(unsigned long arg) +static void dev_watchdog(struct timer_list *t) { - struct net_device *dev = (struct net_device *)arg; + struct net_device *dev = from_timer(dev, t, watchdog_timer); netif_tx_lock(dev); if (!qdisc_tx_is_noop(dev)) { @@ -603,8 +603,14 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, struct Qdisc *sch; unsigned int size = QDISC_ALIGN(sizeof(*sch)) + ops->priv_size; int err = -ENOBUFS; - struct net_device *dev = dev_queue->dev; + struct net_device *dev; + + if (!dev_queue) { + err = -EINVAL; + goto errout; + } + dev = dev_queue->dev; p = kzalloc_node(size, GFP_KERNEL, netdev_queue_numa_node_read(dev_queue)); @@ -689,10 +695,8 @@ void qdisc_reset(struct Qdisc *qdisc) } EXPORT_SYMBOL(qdisc_reset); -static void qdisc_rcu_free(struct rcu_head *head) +static void qdisc_free(struct Qdisc *qdisc) { - struct Qdisc *qdisc = container_of(head, struct Qdisc, rcu_head); - if (qdisc_is_percpu_stats(qdisc)) { free_percpu(qdisc->cpu_bstats); free_percpu(qdisc->cpu_qstats); @@ -725,11 +729,7 @@ void qdisc_destroy(struct Qdisc *qdisc) kfree_skb_list(qdisc->gso_skb); kfree_skb(qdisc->skb_bad_txq); - /* - * gen_estimator est_timer() might access qdisc->q.lock, - * wait a RCU grace period before freeing qdisc. - */ - call_rcu(&qdisc->rcu_head, qdisc_rcu_free); + qdisc_free(qdisc); } EXPORT_SYMBOL(qdisc_destroy); @@ -960,7 +960,7 @@ void dev_init_scheduler(struct net_device *dev) if (dev_ingress_queue(dev)) dev_init_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); - setup_timer(&dev->watchdog_timer, dev_watchdog, (unsigned long)dev); + timer_setup(&dev->watchdog_timer, dev_watchdog, 0); } static void shutdown_scheduler_queue(struct net_device *dev, @@ -1024,3 +1024,49 @@ void psched_ratecfg_precompute(struct psched_ratecfg *r, } } EXPORT_SYMBOL(psched_ratecfg_precompute); + +static void mini_qdisc_rcu_func(struct rcu_head *head) +{ +} + +void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp, + struct tcf_proto *tp_head) +{ + struct mini_Qdisc *miniq_old = rtnl_dereference(*miniqp->p_miniq); + struct mini_Qdisc *miniq; + + if (!tp_head) { + RCU_INIT_POINTER(*miniqp->p_miniq, NULL); + return; + } + + miniq = !miniq_old || miniq_old == &miniqp->miniq2 ? + &miniqp->miniq1 : &miniqp->miniq2; + + /* We need to make sure that readers won't see the miniq + * we are about to modify. So wait until previous call_rcu_bh callback + * is done. + */ + rcu_barrier_bh(); + miniq->filter_list = tp_head; + rcu_assign_pointer(*miniqp->p_miniq, miniq); + + if (miniq_old) + /* This is counterpart of the rcu barrier above. We need to + * block potential new user of miniq_old until all readers + * are not seeing it. + */ + call_rcu_bh(&miniq_old->rcu, mini_qdisc_rcu_func); +} +EXPORT_SYMBOL(mini_qdisc_pair_swap); + +void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc, + struct mini_Qdisc __rcu **p_miniq) +{ + miniqp->miniq1.cpu_bstats = qdisc->cpu_bstats; + miniqp->miniq1.cpu_qstats = qdisc->cpu_qstats; + miniqp->miniq2.cpu_bstats = qdisc->cpu_bstats; + miniqp->miniq2.cpu_qstats = qdisc->cpu_qstats; + miniqp->p_miniq = p_miniq; +} +EXPORT_SYMBOL(mini_qdisc_pair_init); diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 3f88b75488b0..d04068a97d81 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1033,7 +1033,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl == NULL) return -ENOBUFS; - err = tcf_block_get(&cl->block, &cl->filter_list); + err = tcf_block_get(&cl->block, &cl->filter_list, sch); if (err) { kfree(cl); return err; @@ -1144,6 +1144,7 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) case TC_ACT_STOLEN: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ case TC_ACT_SHOT: return NULL; } @@ -1405,7 +1406,7 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt) return err; q->eligible = RB_ROOT; - err = tcf_block_get(&q->root.block, &q->root.filter_list); + err = tcf_block_get(&q->root.block, &q->root.filter_list, sch); if (err) return err; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 7e148376ba52..fa0380730ff0 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -142,6 +142,7 @@ struct htb_class { struct rb_node node[TC_HTB_NUMPRIO]; /* node for self or feed tree */ unsigned int drops ____cacheline_aligned_in_smp; + unsigned int overlimits; }; struct htb_level { @@ -243,6 +244,7 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_STOLEN: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ case TC_ACT_SHOT: return NULL; } @@ -533,6 +535,9 @@ htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff) if (new_mode == cl->cmode) return; + if (new_mode == HTB_CANT_SEND) + cl->overlimits++; + if (cl->prio_activity) { /* not necessary: speed optimization */ if (cl->cmode != HTB_CANT_SEND) htb_deactivate_prios(q, cl); @@ -1026,7 +1031,7 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt) if (!opt) return -EINVAL; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; @@ -1143,6 +1148,7 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) struct htb_class *cl = (struct htb_class *)arg; struct gnet_stats_queue qs = { .drops = cl->drops, + .overlimits = cl->overlimits, }; __u32 qlen = 0; @@ -1388,7 +1394,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (!cl) goto failure; - err = tcf_block_get(&cl->block, &cl->filter_list); + err = tcf_block_get(&cl->block, &cl->filter_list, sch); if (err) { kfree(cl); goto failure; diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 44de4ee51ce9..5ecc38f35d47 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -20,6 +20,8 @@ struct ingress_sched_data { struct tcf_block *block; + struct tcf_block_ext_info block_info; + struct mini_Qdisc_pair miniqp; }; static struct Qdisc *ingress_leaf(struct Qdisc *sch, unsigned long arg) @@ -53,13 +55,26 @@ static struct tcf_block *ingress_tcf_block(struct Qdisc *sch, unsigned long cl) return q->block; } +static void clsact_chain_head_change(struct tcf_proto *tp_head, void *priv) +{ + struct mini_Qdisc_pair *miniqp = priv; + + mini_qdisc_pair_swap(miniqp, tp_head); +} + static int ingress_init(struct Qdisc *sch, struct nlattr *opt) { struct ingress_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); int err; - err = tcf_block_get(&q->block, &dev->ingress_cl_list); + mini_qdisc_pair_init(&q->miniqp, sch, &dev->miniq_ingress); + + q->block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS; + q->block_info.chain_head_change = clsact_chain_head_change; + q->block_info.chain_head_change_priv = &q->miniqp; + + err = tcf_block_get_ext(&q->block, sch, &q->block_info); if (err) return err; @@ -73,7 +88,7 @@ static void ingress_destroy(struct Qdisc *sch) { struct ingress_sched_data *q = qdisc_priv(sch); - tcf_block_put(q->block); + tcf_block_put_ext(q->block, sch, &q->block_info); net_dec_ingress_queue(); } @@ -114,6 +129,10 @@ static struct Qdisc_ops ingress_qdisc_ops __read_mostly = { struct clsact_sched_data { struct tcf_block *ingress_block; struct tcf_block *egress_block; + struct tcf_block_ext_info ingress_block_info; + struct tcf_block_ext_info egress_block_info; + struct mini_Qdisc_pair miniqp_ingress; + struct mini_Qdisc_pair miniqp_egress; }; static unsigned long clsact_find(struct Qdisc *sch, u32 classid) @@ -153,13 +172,25 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt) struct net_device *dev = qdisc_dev(sch); int err; - err = tcf_block_get(&q->ingress_block, &dev->ingress_cl_list); + mini_qdisc_pair_init(&q->miniqp_ingress, sch, &dev->miniq_ingress); + + q->ingress_block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS; + q->ingress_block_info.chain_head_change = clsact_chain_head_change; + q->ingress_block_info.chain_head_change_priv = &q->miniqp_ingress; + + err = tcf_block_get_ext(&q->ingress_block, sch, &q->ingress_block_info); if (err) return err; - err = tcf_block_get(&q->egress_block, &dev->egress_cl_list); + mini_qdisc_pair_init(&q->miniqp_egress, sch, &dev->miniq_egress); + + q->egress_block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS; + q->egress_block_info.chain_head_change = clsact_chain_head_change; + q->egress_block_info.chain_head_change_priv = &q->miniqp_egress; + + err = tcf_block_get_ext(&q->egress_block, sch, &q->egress_block_info); if (err) - return err; + goto err_egress_block_get; net_inc_ingress_queue(); net_inc_egress_queue(); @@ -167,14 +198,18 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt) sch->flags |= TCQ_F_CPUSTATS; return 0; + +err_egress_block_get: + tcf_block_put_ext(q->ingress_block, sch, &q->ingress_block_info); + return err; } static void clsact_destroy(struct Qdisc *sch) { struct clsact_sched_data *q = qdisc_priv(sch); - tcf_block_put(q->egress_block); - tcf_block_put(q->ingress_block); + tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info); + tcf_block_put_ext(q->ingress_block, sch, &q->ingress_block_info); net_dec_ingress_queue(); net_dec_egress_queue(); diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index f3a3e507422b..213b586a06a0 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -130,15 +130,7 @@ static struct netdev_queue *mq_queue_get(struct Qdisc *sch, unsigned long cl) static struct netdev_queue *mq_select_queue(struct Qdisc *sch, struct tcmsg *tcm) { - unsigned int ntx = TC_H_MIN(tcm->tcm_parent); - struct netdev_queue *dev_queue = mq_queue_get(sch, ntx); - - if (!dev_queue) { - struct net_device *dev = qdisc_dev(sch); - - return netdev_get_tx_queue(dev, 0); - } - return dev_queue; + return mq_queue_get(sch, TC_H_MIN(tcm->tcm_parent)); } static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 6bcdfe6e7b63..b85885a9d8a1 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -18,10 +18,16 @@ #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/sch_generic.h> +#include <net/pkt_cls.h> struct mqprio_sched { struct Qdisc **qdiscs; + u16 mode; + u16 shaper; int hw_offload; + u32 flags; + u64 min_rate[TC_QOPT_MAX_QUEUE]; + u64 max_rate[TC_QOPT_MAX_QUEUE]; }; static void mqprio_destroy(struct Qdisc *sch) @@ -39,9 +45,18 @@ static void mqprio_destroy(struct Qdisc *sch) } if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) { - struct tc_mqprio_qopt mqprio = {}; - - dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_MQPRIO, &mqprio); + struct tc_mqprio_qopt_offload mqprio = { { 0 } }; + + switch (priv->mode) { + case TC_MQPRIO_MODE_DCB: + case TC_MQPRIO_MODE_CHANNEL: + dev->netdev_ops->ndo_setup_tc(dev, + TC_SETUP_QDISC_MQPRIO, + &mqprio); + break; + default: + return; + } } else { netdev_set_num_tc(dev, 0); } @@ -97,6 +112,26 @@ static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt) return 0; } +static const struct nla_policy mqprio_policy[TCA_MQPRIO_MAX + 1] = { + [TCA_MQPRIO_MODE] = { .len = sizeof(u16) }, + [TCA_MQPRIO_SHAPER] = { .len = sizeof(u16) }, + [TCA_MQPRIO_MIN_RATE64] = { .type = NLA_NESTED }, + [TCA_MQPRIO_MAX_RATE64] = { .type = NLA_NESTED }, +}; + +static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, + const struct nla_policy *policy, int len) +{ + int nested_len = nla_len(nla) - NLA_ALIGN(len); + + if (nested_len >= nla_attr_size(0)) + return nla_parse(tb, maxtype, nla_data(nla) + NLA_ALIGN(len), + nested_len, policy, NULL); + + memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); + return 0; +} + static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) { struct net_device *dev = qdisc_dev(sch); @@ -105,6 +140,10 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) struct Qdisc *qdisc; int i, err = -EOPNOTSUPP; struct tc_mqprio_qopt *qopt = NULL; + struct nlattr *tb[TCA_MQPRIO_MAX + 1]; + struct nlattr *attr; + int rem; + int len; BUILD_BUG_ON(TC_MAX_QUEUE != TC_QOPT_MAX_QUEUE); BUILD_BUG_ON(TC_BITMASK != TC_QOPT_BITMASK); @@ -115,6 +154,10 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) if (!netif_is_multiqueue(dev)) return -EOPNOTSUPP; + /* make certain can allocate enough classids to handle queues */ + if (dev->num_tx_queues >= TC_H_MIN_PRIORITY) + return -ENOMEM; + if (!opt || nla_len(opt) < sizeof(*qopt)) return -EINVAL; @@ -122,6 +165,59 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) if (mqprio_parse_opt(dev, qopt)) return -EINVAL; + len = nla_len(opt) - NLA_ALIGN(sizeof(*qopt)); + if (len > 0) { + err = parse_attr(tb, TCA_MQPRIO_MAX, opt, mqprio_policy, + sizeof(*qopt)); + if (err < 0) + return err; + + if (!qopt->hw) + return -EINVAL; + + if (tb[TCA_MQPRIO_MODE]) { + priv->flags |= TC_MQPRIO_F_MODE; + priv->mode = *(u16 *)nla_data(tb[TCA_MQPRIO_MODE]); + } + + if (tb[TCA_MQPRIO_SHAPER]) { + priv->flags |= TC_MQPRIO_F_SHAPER; + priv->shaper = *(u16 *)nla_data(tb[TCA_MQPRIO_SHAPER]); + } + + if (tb[TCA_MQPRIO_MIN_RATE64]) { + if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) + return -EINVAL; + i = 0; + nla_for_each_nested(attr, tb[TCA_MQPRIO_MIN_RATE64], + rem) { + if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64) + return -EINVAL; + if (i >= qopt->num_tc) + break; + priv->min_rate[i] = *(u64 *)nla_data(attr); + i++; + } + priv->flags |= TC_MQPRIO_F_MIN_RATE; + } + + if (tb[TCA_MQPRIO_MAX_RATE64]) { + if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) + return -EINVAL; + i = 0; + nla_for_each_nested(attr, tb[TCA_MQPRIO_MAX_RATE64], + rem) { + if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64) + return -EINVAL; + if (i >= qopt->num_tc) + break; + priv->max_rate[i] = *(u64 *)nla_data(attr); + i++; + } + priv->flags |= TC_MQPRIO_F_MAX_RATE; + } + } + /* pre-allocate qdisc, attachment can't fail */ priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]), GFP_KERNEL); @@ -146,14 +242,36 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) * supplied and verified mapping */ if (qopt->hw) { - struct tc_mqprio_qopt mqprio = *qopt; + struct tc_mqprio_qopt_offload mqprio = {.qopt = *qopt}; - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_MQPRIO, + switch (priv->mode) { + case TC_MQPRIO_MODE_DCB: + if (priv->shaper != TC_MQPRIO_SHAPER_DCB) + return -EINVAL; + break; + case TC_MQPRIO_MODE_CHANNEL: + mqprio.flags = priv->flags; + if (priv->flags & TC_MQPRIO_F_MODE) + mqprio.mode = priv->mode; + if (priv->flags & TC_MQPRIO_F_SHAPER) + mqprio.shaper = priv->shaper; + if (priv->flags & TC_MQPRIO_F_MIN_RATE) + for (i = 0; i < mqprio.qopt.num_tc; i++) + mqprio.min_rate[i] = priv->min_rate[i]; + if (priv->flags & TC_MQPRIO_F_MAX_RATE) + for (i = 0; i < mqprio.qopt.num_tc; i++) + mqprio.max_rate[i] = priv->max_rate[i]; + break; + default: + return -EINVAL; + } + err = dev->netdev_ops->ndo_setup_tc(dev, + TC_SETUP_QDISC_MQPRIO, &mqprio); if (err) return err; - priv->hw_offload = mqprio.hw; + priv->hw_offload = mqprio.qopt.hw; } else { netdev_set_num_tc(dev, qopt->num_tc); for (i = 0; i < qopt->num_tc; i++) @@ -193,7 +311,7 @@ static struct netdev_queue *mqprio_queue_get(struct Qdisc *sch, unsigned long cl) { struct net_device *dev = qdisc_dev(sch); - unsigned long ntx = cl - 1 - netdev_get_num_tc(dev); + unsigned long ntx = cl - 1; if (ntx >= dev->num_tx_queues) return NULL; @@ -223,11 +341,51 @@ static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, return 0; } +static int dump_rates(struct mqprio_sched *priv, + struct tc_mqprio_qopt *opt, struct sk_buff *skb) +{ + struct nlattr *nest; + int i; + + if (priv->flags & TC_MQPRIO_F_MIN_RATE) { + nest = nla_nest_start(skb, TCA_MQPRIO_MIN_RATE64); + if (!nest) + goto nla_put_failure; + + for (i = 0; i < opt->num_tc; i++) { + if (nla_put(skb, TCA_MQPRIO_MIN_RATE64, + sizeof(priv->min_rate[i]), + &priv->min_rate[i])) + goto nla_put_failure; + } + nla_nest_end(skb, nest); + } + + if (priv->flags & TC_MQPRIO_F_MAX_RATE) { + nest = nla_nest_start(skb, TCA_MQPRIO_MAX_RATE64); + if (!nest) + goto nla_put_failure; + + for (i = 0; i < opt->num_tc; i++) { + if (nla_put(skb, TCA_MQPRIO_MAX_RATE64, + sizeof(priv->max_rate[i]), + &priv->max_rate[i])) + goto nla_put_failure; + } + nla_nest_end(skb, nest); + } + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -1; +} + static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) { struct net_device *dev = qdisc_dev(sch); struct mqprio_sched *priv = qdisc_priv(sch); - unsigned char *b = skb_tail_pointer(skb); + struct nlattr *nla = (struct nlattr *)skb_tail_pointer(skb); struct tc_mqprio_qopt opt = { 0 }; struct Qdisc *qdisc; unsigned int i; @@ -258,12 +416,25 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) opt.offset[i] = dev->tc_to_txq[i].offset; } - if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) + if (nla_put(skb, TCA_OPTIONS, NLA_ALIGN(sizeof(opt)), &opt)) + goto nla_put_failure; + + if ((priv->flags & TC_MQPRIO_F_MODE) && + nla_put_u16(skb, TCA_MQPRIO_MODE, priv->mode)) goto nla_put_failure; - return skb->len; + if ((priv->flags & TC_MQPRIO_F_SHAPER) && + nla_put_u16(skb, TCA_MQPRIO_SHAPER, priv->shaper)) + goto nla_put_failure; + + if ((priv->flags & TC_MQPRIO_F_MIN_RATE || + priv->flags & TC_MQPRIO_F_MAX_RATE) && + (dump_rates(priv, &opt, skb) != 0)) + goto nla_put_failure; + + return nla_nest_end(skb, nla); nla_put_failure: - nlmsg_trim(skb, b); + nlmsg_trim(skb, nla); return -1; } @@ -282,38 +453,35 @@ static unsigned long mqprio_find(struct Qdisc *sch, u32 classid) struct net_device *dev = qdisc_dev(sch); unsigned int ntx = TC_H_MIN(classid); - if (ntx > dev->num_tx_queues + netdev_get_num_tc(dev)) - return 0; - return ntx; + /* There are essentially two regions here that have valid classid + * values. The first region will have a classid value of 1 through + * num_tx_queues. All of these are backed by actual Qdiscs. + */ + if (ntx < TC_H_MIN_PRIORITY) + return (ntx <= dev->num_tx_queues) ? ntx : 0; + + /* The second region represents the hardware traffic classes. These + * are represented by classid values of TC_H_MIN_PRIORITY through + * TC_H_MIN_PRIORITY + netdev_get_num_tc - 1 + */ + return ((ntx - TC_H_MIN_PRIORITY) < netdev_get_num_tc(dev)) ? ntx : 0; } static int mqprio_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { - struct net_device *dev = qdisc_dev(sch); + if (cl < TC_H_MIN_PRIORITY) { + struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); + struct net_device *dev = qdisc_dev(sch); + int tc = netdev_txq_to_tc(dev, cl - 1); - if (cl <= netdev_get_num_tc(dev)) { + tcm->tcm_parent = (tc < 0) ? 0 : + TC_H_MAKE(TC_H_MAJ(sch->handle), + TC_H_MIN(tc + TC_H_MIN_PRIORITY)); + tcm->tcm_info = dev_queue->qdisc_sleeping->handle; + } else { tcm->tcm_parent = TC_H_ROOT; tcm->tcm_info = 0; - } else { - int i; - struct netdev_queue *dev_queue; - - dev_queue = mqprio_queue_get(sch, cl); - tcm->tcm_parent = 0; - for (i = 0; i < netdev_get_num_tc(dev); i++) { - struct netdev_tc_txq tc = dev->tc_to_txq[i]; - int q_idx = cl - netdev_get_num_tc(dev); - - if (q_idx > tc.offset && - q_idx <= tc.offset + tc.count) { - tcm->tcm_parent = - TC_H_MAKE(TC_H_MAJ(sch->handle), - TC_H_MIN(i + 1)); - break; - } - } - tcm->tcm_info = dev_queue->qdisc_sleeping->handle; } tcm->tcm_handle |= TC_H_MIN(cl); return 0; @@ -324,15 +492,14 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, __releases(d->lock) __acquires(d->lock) { - struct net_device *dev = qdisc_dev(sch); - - if (cl <= netdev_get_num_tc(dev)) { + if (cl >= TC_H_MIN_PRIORITY) { int i; __u32 qlen = 0; struct Qdisc *qdisc; struct gnet_stats_queue qstats = {0}; struct gnet_stats_basic_packed bstats = {0}; - struct netdev_tc_txq tc = dev->tc_to_txq[cl - 1]; + struct net_device *dev = qdisc_dev(sch); + struct netdev_tc_txq tc = dev->tc_to_txq[cl & TC_BITMASK]; /* Drop lock here it will be reclaimed before touching * statistics this is required because the d->lock we @@ -385,17 +552,36 @@ static void mqprio_walk(struct Qdisc *sch, struct qdisc_walker *arg) /* Walk hierarchy with a virtual class per tc */ arg->count = arg->skip; - for (ntx = arg->skip; - ntx < dev->num_tx_queues + netdev_get_num_tc(dev); - ntx++) { + for (ntx = arg->skip; ntx < netdev_get_num_tc(dev); ntx++) { + if (arg->fn(sch, ntx + TC_H_MIN_PRIORITY, arg) < 0) { + arg->stop = 1; + return; + } + arg->count++; + } + + /* Pad the values and skip over unused traffic classes */ + if (ntx < TC_MAX_QUEUE) { + arg->count = TC_MAX_QUEUE; + ntx = TC_MAX_QUEUE; + } + + /* Reset offset, sort out remaining per-queue qdiscs */ + for (ntx -= TC_MAX_QUEUE; ntx < dev->num_tx_queues; ntx++) { if (arg->fn(sch, ntx + 1, arg) < 0) { arg->stop = 1; - break; + return; } arg->count++; } } +static struct netdev_queue *mqprio_select_queue(struct Qdisc *sch, + struct tcmsg *tcm) +{ + return mqprio_queue_get(sch, TC_H_MIN(tcm->tcm_parent)); +} + static const struct Qdisc_class_ops mqprio_class_ops = { .graft = mqprio_graft, .leaf = mqprio_leaf, @@ -403,6 +589,7 @@ static const struct Qdisc_class_ops mqprio_class_ops = { .walk = mqprio_walk, .dump = mqprio_dump_class, .dump_stats = mqprio_dump_class_stats, + .select_queue = mqprio_select_queue, }; static struct Qdisc_ops mqprio_qdisc_ops __read_mostly = { diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index ff4fc3e0facd..012216386c0b 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -54,6 +54,7 @@ multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ case TC_ACT_SHOT: return NULL; } @@ -245,7 +246,7 @@ static int multiq_init(struct Qdisc *sch, struct nlattr *opt) if (opt == NULL) return -EINVAL; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index b1266e75ca43..dd70924cbcdf 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -77,8 +77,8 @@ struct netem_sched_data { struct qdisc_watchdog watchdog; - psched_tdiff_t latency; - psched_tdiff_t jitter; + s64 latency; + s64 jitter; u32 loss; u32 ecn; @@ -135,6 +135,13 @@ struct netem_sched_data { u32 a5; /* p23 used only in 4-states */ } clg; + struct tc_netem_slot slot_config; + struct slotstate { + u64 slot_next; + s32 packets_left; + s32 bytes_left; + } slot; + }; /* Time stamp put into socket buffer control block @@ -145,16 +152,9 @@ struct netem_sched_data { * we save skb->tstamp value in skb->cb[] before destroying it. */ struct netem_skb_cb { - psched_time_t time_to_send; - ktime_t tstamp_save; + u64 time_to_send; }; - -static struct sk_buff *netem_rb_to_skb(struct rb_node *rb) -{ - return rb_entry(rb, struct sk_buff, rbnode); -} - static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb) { /* we assume we can use skb next/prev/tstamp as storage for rb_node */ @@ -312,11 +312,11 @@ static bool loss_event(struct netem_sched_data *q) * std deviation sigma. Uses table lookup to approximate the desired * distribution, and a uniformly-distributed pseudo-random source. */ -static psched_tdiff_t tabledist(psched_tdiff_t mu, psched_tdiff_t sigma, - struct crndstate *state, - const struct disttable *dist) +static s64 tabledist(s64 mu, s32 sigma, + struct crndstate *state, + const struct disttable *dist) { - psched_tdiff_t x; + s64 x; long t; u32 rnd; @@ -327,7 +327,7 @@ static psched_tdiff_t tabledist(psched_tdiff_t mu, psched_tdiff_t sigma, /* default uniform distribution */ if (dist == NULL) - return (rnd % (2*sigma)) - sigma + mu; + return (rnd % (2 * sigma)) - sigma + mu; t = dist->table[rnd % dist->size]; x = (sigma % NETEM_DIST_SCALE) * t; @@ -339,10 +339,8 @@ static psched_tdiff_t tabledist(psched_tdiff_t mu, psched_tdiff_t sigma, return x / NETEM_DIST_SCALE + (sigma / NETEM_DIST_SCALE) * t + mu; } -static psched_time_t packet_len_2_sched_time(unsigned int len, struct netem_sched_data *q) +static u64 packet_time_ns(u64 len, const struct netem_sched_data *q) { - u64 ticks; - len += q->packet_overhead; if (q->cell_size) { @@ -353,21 +351,19 @@ static psched_time_t packet_len_2_sched_time(unsigned int len, struct netem_sche len = cells * (q->cell_size + q->cell_overhead); } - ticks = (u64)len * NSEC_PER_SEC; - - do_div(ticks, q->rate); - return PSCHED_NS2TICKS(ticks); + return div64_u64(len * NSEC_PER_SEC, q->rate); } static void tfifo_reset(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); - struct rb_node *p; + struct rb_node *p = rb_first(&q->t_root); - while ((p = rb_first(&q->t_root))) { - struct sk_buff *skb = netem_rb_to_skb(p); + while (p) { + struct sk_buff *skb = rb_to_skb(p); - rb_erase(p, &q->t_root); + p = rb_next(p); + rb_erase(&skb->rbnode, &q->t_root); rtnl_kfree_skbs(skb, skb); } } @@ -375,14 +371,14 @@ static void tfifo_reset(struct Qdisc *sch) static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); - psched_time_t tnext = netem_skb_cb(nskb)->time_to_send; + u64 tnext = netem_skb_cb(nskb)->time_to_send; struct rb_node **p = &q->t_root.rb_node, *parent = NULL; while (*p) { struct sk_buff *skb; parent = *p; - skb = netem_rb_to_skb(parent); + skb = rb_to_skb(parent); if (tnext >= netem_skb_cb(skb)->time_to_send) p = &parent->rb_right; else @@ -521,13 +517,13 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (q->gap == 0 || /* not doing reordering */ q->counter < q->gap - 1 || /* inside last reordering gap */ q->reorder < get_crandom(&q->reorder_cor)) { - psched_time_t now; - psched_tdiff_t delay; + u64 now; + s64 delay; delay = tabledist(q->latency, q->jitter, &q->delay_cor, q->delay_dist); - now = psched_get_time(); + now = ktime_get_ns(); if (q->rate) { struct netem_skb_cb *last = NULL; @@ -538,7 +534,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff *t_skb; struct netem_skb_cb *t_last; - t_skb = netem_rb_to_skb(rb_last(&q->t_root)); + t_skb = skb_rb_last(&q->t_root); t_last = netem_skb_cb(t_skb); if (!last || t_last->time_to_send > last->time_to_send) { @@ -553,15 +549,14 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, * from delay. */ delay -= last->time_to_send - now; - delay = max_t(psched_tdiff_t, 0, delay); + delay = max_t(s64, 0, delay); now = last->time_to_send; } - delay += packet_len_2_sched_time(qdisc_pkt_len(skb), q); + delay += packet_time_ns(qdisc_pkt_len(skb), q); } cb->time_to_send = now + delay; - cb->tstamp_save = skb->tstamp; ++q->counter; tfifo_enqueue(skb, sch); } else { @@ -569,7 +564,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, * Do re-ordering by putting one out of N packets at the front * of the queue. */ - cb->time_to_send = psched_get_time(); + cb->time_to_send = ktime_get_ns(); q->counter = 0; netem_enqueue_skb_head(&sch->q, skb); @@ -600,6 +595,20 @@ finish_segs: return NET_XMIT_SUCCESS; } +/* Delay the next round with a new future slot with a + * correct number of bytes and packets. + */ + +static void get_slot_next(struct netem_sched_data *q, u64 now) +{ + q->slot.slot_next = now + q->slot_config.min_delay + + (prandom_u32() * + (q->slot_config.max_delay - + q->slot_config.min_delay) >> 32); + q->slot.packets_left = q->slot_config.max_packets; + q->slot.bytes_left = q->slot_config.max_bytes; +} + static struct sk_buff *netem_dequeue(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); @@ -616,20 +625,26 @@ deliver: } p = rb_first(&q->t_root); if (p) { - psched_time_t time_to_send; + u64 time_to_send; + u64 now = ktime_get_ns(); - skb = netem_rb_to_skb(p); + skb = rb_to_skb(p); /* if more time remaining? */ time_to_send = netem_skb_cb(skb)->time_to_send; - if (time_to_send <= psched_get_time()) { - rb_erase(p, &q->t_root); + if (q->slot.slot_next && q->slot.slot_next < time_to_send) + get_slot_next(q, now); + if (time_to_send <= now && q->slot.slot_next <= now) { + rb_erase(p, &q->t_root); sch->q.qlen--; qdisc_qstats_backlog_dec(sch, skb); skb->next = NULL; skb->prev = NULL; - skb->tstamp = netem_skb_cb(skb)->tstamp_save; + /* skb->dev shares skb->rbnode area, + * we need to restore its value. + */ + skb->dev = qdisc_dev(sch); #ifdef CONFIG_NET_CLS_ACT /* @@ -640,6 +655,14 @@ deliver: skb->tstamp = 0; #endif + if (q->slot.slot_next) { + q->slot.packets_left--; + q->slot.bytes_left -= qdisc_pkt_len(skb); + if (q->slot.packets_left <= 0 || + q->slot.bytes_left <= 0) + get_slot_next(q, now); + } + if (q->qdisc) { unsigned int pkt_len = qdisc_pkt_len(skb); struct sk_buff *to_free = NULL; @@ -663,7 +686,10 @@ deliver: if (skb) goto deliver; } - qdisc_watchdog_schedule(&q->watchdog, time_to_send); + + qdisc_watchdog_schedule_ns(&q->watchdog, + max(time_to_send, + q->slot.slot_next)); } if (q->qdisc) { @@ -694,6 +720,7 @@ static void dist_free(struct disttable *d) * Distribution data is a variable size payload containing * signed 16 bit values. */ + static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr) { struct netem_sched_data *q = qdisc_priv(sch); @@ -724,6 +751,23 @@ static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr) return 0; } +static void get_slot(struct netem_sched_data *q, const struct nlattr *attr) +{ + const struct tc_netem_slot *c = nla_data(attr); + + q->slot_config = *c; + if (q->slot_config.max_packets == 0) + q->slot_config.max_packets = INT_MAX; + if (q->slot_config.max_bytes == 0) + q->slot_config.max_bytes = INT_MAX; + q->slot.packets_left = q->slot_config.max_packets; + q->slot.bytes_left = q->slot_config.max_bytes; + if (q->slot_config.min_delay | q->slot_config.max_delay) + q->slot.slot_next = ktime_get_ns(); + else + q->slot.slot_next = 0; +} + static void get_correlation(struct netem_sched_data *q, const struct nlattr *attr) { const struct tc_netem_corr *c = nla_data(attr); @@ -825,6 +869,9 @@ static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = { [TCA_NETEM_LOSS] = { .type = NLA_NESTED }, [TCA_NETEM_ECN] = { .type = NLA_U32 }, [TCA_NETEM_RATE64] = { .type = NLA_U64 }, + [TCA_NETEM_LATENCY64] = { .type = NLA_S64 }, + [TCA_NETEM_JITTER64] = { .type = NLA_S64 }, + [TCA_NETEM_SLOT] = { .len = sizeof(struct tc_netem_slot) }, }; static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, @@ -892,8 +939,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) sch->limit = qopt->limit; - q->latency = qopt->latency; - q->jitter = qopt->jitter; + q->latency = PSCHED_TICKS2NS(qopt->latency); + q->jitter = PSCHED_TICKS2NS(qopt->jitter); q->limit = qopt->limit; q->gap = qopt->gap; q->counter = 0; @@ -922,9 +969,18 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) q->rate = max_t(u64, q->rate, nla_get_u64(tb[TCA_NETEM_RATE64])); + if (tb[TCA_NETEM_LATENCY64]) + q->latency = nla_get_s64(tb[TCA_NETEM_LATENCY64]); + + if (tb[TCA_NETEM_JITTER64]) + q->jitter = nla_get_s64(tb[TCA_NETEM_JITTER64]); + if (tb[TCA_NETEM_ECN]) q->ecn = nla_get_u32(tb[TCA_NETEM_ECN]); + if (tb[TCA_NETEM_SLOT]) + get_slot(q, tb[TCA_NETEM_SLOT]); + return ret; } @@ -1014,9 +1070,12 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) struct tc_netem_reorder reorder; struct tc_netem_corrupt corrupt; struct tc_netem_rate rate; + struct tc_netem_slot slot; - qopt.latency = q->latency; - qopt.jitter = q->jitter; + qopt.latency = min_t(psched_tdiff_t, PSCHED_NS2TICKS(q->latency), + UINT_MAX); + qopt.jitter = min_t(psched_tdiff_t, PSCHED_NS2TICKS(q->jitter), + UINT_MAX); qopt.limit = q->limit; qopt.loss = q->loss; qopt.gap = q->gap; @@ -1024,6 +1083,12 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) if (nla_put(skb, TCA_OPTIONS, sizeof(qopt), &qopt)) goto nla_put_failure; + if (nla_put(skb, TCA_NETEM_LATENCY64, sizeof(q->latency), &q->latency)) + goto nla_put_failure; + + if (nla_put(skb, TCA_NETEM_JITTER64, sizeof(q->jitter), &q->jitter)) + goto nla_put_failure; + cor.delay_corr = q->delay_cor.rho; cor.loss_corr = q->loss_cor.rho; cor.dup_corr = q->dup_cor.rho; @@ -1060,6 +1125,16 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) if (dump_loss_model(q, skb) != 0) goto nla_put_failure; + if (q->slot_config.min_delay | q->slot_config.max_delay) { + slot = q->slot_config; + if (slot.max_packets == INT_MAX) + slot.max_packets = 0; + if (slot.max_bytes == INT_MAX) + slot.max_bytes = 0; + if (nla_put(skb, TCA_NETEM_SLOT, sizeof(slot), &slot)) + goto nla_put_failure; + } + return nla_nest_end(skb, nla); nla_put_failure: diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index 6c2791d6102d..776c694c77c7 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -74,6 +74,7 @@ struct pie_sched_data { struct pie_vars vars; struct pie_stats stats; struct timer_list adapt_timer; + struct Qdisc *sch; }; static void pie_params_init(struct pie_params *params) @@ -422,10 +423,10 @@ static void calculate_probability(struct Qdisc *sch) pie_vars_init(&q->vars); } -static void pie_timer(unsigned long arg) +static void pie_timer(struct timer_list *t) { - struct Qdisc *sch = (struct Qdisc *)arg; - struct pie_sched_data *q = qdisc_priv(sch); + struct pie_sched_data *q = from_timer(q, t, adapt_timer); + struct Qdisc *sch = q->sch; spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); @@ -446,7 +447,8 @@ static int pie_init(struct Qdisc *sch, struct nlattr *opt) pie_vars_init(&q->vars); sch->limit = q->params.limit; - setup_timer(&q->adapt_timer, pie_timer, (unsigned long)sch); + q->sch = sch; + timer_setup(&q->adapt_timer, pie_timer, 0); if (opt) { int err = pie_change(sch, opt); diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 2dd6c68ae91e..2c79559a0d31 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -50,6 +50,7 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ case TC_ACT_SHOT: return NULL; } @@ -212,7 +213,7 @@ static int prio_init(struct Qdisc *sch, struct nlattr *opt) if (!opt) return -EINVAL; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 6ddfd4991108..6962b37a3ad3 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -709,6 +709,7 @@ static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_STOLEN: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ case TC_ACT_SHOT: return NULL; } @@ -1419,7 +1420,7 @@ static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt) int i, j, err; u32 max_cl_shift, maxbudg_shift, max_classes; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 93b9d70a9b28..7f8ea9e297c3 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -19,6 +19,7 @@ #include <linux/kernel.h> #include <linux/skbuff.h> #include <net/pkt_sched.h> +#include <net/pkt_cls.h> #include <net/inet_ecn.h> #include <net/red.h> @@ -40,6 +41,7 @@ struct red_sched_data { u32 limit; /* HARD maximal queue length */ unsigned char flags; struct timer_list adapt_timer; + struct Qdisc *sch; struct red_parms parms; struct red_vars vars; struct red_stats stats; @@ -147,11 +149,37 @@ static void red_reset(struct Qdisc *sch) red_restart(&q->vars); } +static int red_offload(struct Qdisc *sch, bool enable) +{ + struct red_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct tc_red_qopt_offload opt = { + .handle = sch->handle, + .parent = sch->parent, + }; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return -EOPNOTSUPP; + + if (enable) { + opt.command = TC_RED_REPLACE; + opt.set.min = q->parms.qth_min >> q->parms.Wlog; + opt.set.max = q->parms.qth_max >> q->parms.Wlog; + opt.set.probability = q->parms.max_P; + opt.set.is_ecn = red_use_ecn(q); + } else { + opt.command = TC_RED_DESTROY; + } + + return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, &opt); +} + static void red_destroy(struct Qdisc *sch) { struct red_sched_data *q = qdisc_priv(sch); del_timer_sync(&q->adapt_timer); + red_offload(sch, false); qdisc_destroy(q->qdisc); } @@ -218,13 +246,14 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt) red_start_of_idle_period(&q->vars); sch_tree_unlock(sch); + red_offload(sch, true); return 0; } -static inline void red_adaptative_timer(unsigned long arg) +static inline void red_adaptative_timer(struct timer_list *t) { - struct Qdisc *sch = (struct Qdisc *)arg; - struct red_sched_data *q = qdisc_priv(sch); + struct red_sched_data *q = from_timer(q, t, adapt_timer); + struct Qdisc *sch = q->sch; spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); @@ -238,10 +267,40 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt) struct red_sched_data *q = qdisc_priv(sch); q->qdisc = &noop_qdisc; - setup_timer(&q->adapt_timer, red_adaptative_timer, (unsigned long)sch); + q->sch = sch; + timer_setup(&q->adapt_timer, red_adaptative_timer, 0); return red_change(sch, opt); } +static int red_dump_offload(struct Qdisc *sch, struct tc_red_qopt *opt) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_red_qopt_offload hw_stats = { + .command = TC_RED_STATS, + .handle = sch->handle, + .parent = sch->parent, + { + .stats.bstats = &sch->bstats, + .stats.qstats = &sch->qstats, + }, + }; + int err; + + opt->flags &= ~TC_RED_OFFLOADED; + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return 0; + + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, + &hw_stats); + if (err == -EOPNOTSUPP) + return 0; + + if (!err) + opt->flags |= TC_RED_OFFLOADED; + + return err; +} + static int red_dump(struct Qdisc *sch, struct sk_buff *skb) { struct red_sched_data *q = qdisc_priv(sch); @@ -255,8 +314,13 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb) .Plog = q->parms.Plog, .Scell_log = q->parms.Scell_log, }; + int err; sch->qstats.backlog = q->qdisc->qstats.backlog; + err = red_dump_offload(sch, &opt); + if (err) + goto nla_put_failure; + opts = nla_nest_start(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; @@ -273,6 +337,7 @@ nla_put_failure: static int red_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct red_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); struct tc_red_xstats st = { .early = q->stats.prob_drop + q->stats.forced_drop, .pdrop = q->stats.pdrop, @@ -280,6 +345,26 @@ static int red_dump_stats(struct Qdisc *sch, struct gnet_dump *d) .marked = q->stats.prob_mark + q->stats.forced_mark, }; + if (tc_can_offload(dev) && dev->netdev_ops->ndo_setup_tc) { + struct red_stats hw_stats = {0}; + struct tc_red_qopt_offload hw_stats_request = { + .command = TC_RED_XSTATS, + .handle = sch->handle, + .parent = sch->parent, + { + .xstats = &hw_stats, + }, + }; + if (!dev->netdev_ops->ndo_setup_tc(dev, + TC_SETUP_QDISC_RED, + &hw_stats_request)) { + st.early += hw_stats.prob_drop + hw_stats.forced_drop; + st.pdrop += hw_stats.pdrop; + st.other += hw_stats.other; + st.marked += hw_stats.prob_mark + hw_stats.forced_mark; + } + } + return gnet_stats_copy_app(d, &st, sizeof(st)); } diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index cc39e170b4aa..0678debdd856 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -268,6 +268,7 @@ static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl, case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ case TC_ACT_SHOT: return false; } @@ -553,7 +554,7 @@ static int sfb_init(struct Qdisc *sch, struct nlattr *opt) struct sfb_sched_data *q = qdisc_priv(sch); int err; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 74ea863b8240..890f4a4564e7 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -145,6 +145,7 @@ struct sfq_sched_data { int perturb_period; unsigned int quantum; /* Allotment per round: MUST BE >= MTU */ struct timer_list perturb_timer; + struct Qdisc *sch; }; /* @@ -189,6 +190,7 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + /* fall through */ case TC_ACT_SHOT: return 0; } @@ -604,10 +606,10 @@ drop: qdisc_tree_reduce_backlog(sch, dropped, drop_len); } -static void sfq_perturbation(unsigned long arg) +static void sfq_perturbation(struct timer_list *t) { - struct Qdisc *sch = (struct Qdisc *)arg; - struct sfq_sched_data *q = qdisc_priv(sch); + struct sfq_sched_data *q = from_timer(q, t, perturb_timer); + struct Qdisc *sch = q->sch; spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); @@ -722,10 +724,9 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt) int i; int err; - setup_deferrable_timer(&q->perturb_timer, sfq_perturbation, - (unsigned long)sch); + timer_setup(&q->perturb_timer, sfq_perturbation, TIMER_DEFERRABLE); - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; diff --git a/net/sctp/Makefile b/net/sctp/Makefile index 8c434af3e68f..1ca84a288443 100644 --- a/net/sctp/Makefile +++ b/net/sctp/Makefile @@ -13,7 +13,8 @@ sctp-y := sm_statetable.o sm_statefuns.o sm_sideeffect.o \ inqueue.o outqueue.o ulpqueue.o \ tsnmap.o bind_addr.o socket.o primitive.o \ output.o input.o debug.o stream.o auth.o \ - offload.o + offload.o stream_sched.o stream_sched_prio.o \ + stream_sched_rr.o sctp_probe-y := probe.o diff --git a/net/sctp/associola.c b/net/sctp/associola.c index dfb9651e818b..69394f4d6091 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -149,8 +149,7 @@ static struct sctp_association *sctp_association_init( /* Initializes the timers */ for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i) - setup_timer(&asoc->timers[i], sctp_timer_events[i], - (unsigned long)asoc); + timer_setup(&asoc->timers[i], sctp_timer_events[i], 0); /* Pull default initialization values from the sock options. * Note: This assumes that the values have already been diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 3afac275ee82..7b261afc47b9 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -311,10 +311,10 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk) if (chunk->sent_count) { chunk->asoc->abandoned_sent[SCTP_PR_INDEX(TTL)]++; - streamout->abandoned_sent[SCTP_PR_INDEX(TTL)]++; + streamout->ext->abandoned_sent[SCTP_PR_INDEX(TTL)]++; } else { chunk->asoc->abandoned_unsent[SCTP_PR_INDEX(TTL)]++; - streamout->abandoned_unsent[SCTP_PR_INDEX(TTL)]++; + streamout->ext->abandoned_unsent[SCTP_PR_INDEX(TTL)]++; } return 1; } else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) && @@ -323,7 +323,7 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk) &chunk->asoc->stream.out[chunk->sinfo.sinfo_stream]; chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++; - streamout->abandoned_sent[SCTP_PR_INDEX(RTX)]++; + streamout->ext->abandoned_sent[SCTP_PR_INDEX(RTX)]++; return 1; } else if (!SCTP_PR_POLICY(chunk->sinfo.sinfo_flags) && chunk->msg->expires_at && diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index a6dfa86c0201..3b18085e3b10 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -807,9 +807,10 @@ static void sctp_inet6_skb_msgname(struct sk_buff *skb, char *msgname, addr->v6.sin6_flowinfo = 0; addr->v6.sin6_port = sh->source; addr->v6.sin6_addr = ipv6_hdr(skb)->saddr; - if (ipv6_addr_type(&addr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) { + if (ipv6_addr_type(&addr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) addr->v6.sin6_scope_id = sctp_v6_skb_iif(skb); - } + else + addr->v6.sin6_scope_id = 0; } *addr_len = sctp_v6_addr_to_user(sctp_sk(skb->sk), addr); diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 2966ff400755..4db012aa25f7 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -50,6 +50,7 @@ #include <net/sctp/sctp.h> #include <net/sctp/sm.h> +#include <net/sctp/stream_sched.h> /* Declare internal functions here. */ static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn); @@ -72,32 +73,38 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp); /* Add data to the front of the queue. */ static inline void sctp_outq_head_data(struct sctp_outq *q, - struct sctp_chunk *ch) + struct sctp_chunk *ch) { + struct sctp_stream_out_ext *oute; + __u16 stream; + list_add(&ch->list, &q->out_chunk_list); q->out_qlen += ch->skb->len; + + stream = sctp_chunk_stream_no(ch); + oute = q->asoc->stream.out[stream].ext; + list_add(&ch->stream_list, &oute->outq); } /* Take data from the front of the queue. */ static inline struct sctp_chunk *sctp_outq_dequeue_data(struct sctp_outq *q) { - struct sctp_chunk *ch = NULL; - - if (!list_empty(&q->out_chunk_list)) { - struct list_head *entry = q->out_chunk_list.next; - - ch = list_entry(entry, struct sctp_chunk, list); - list_del_init(entry); - q->out_qlen -= ch->skb->len; - } - return ch; + return q->sched->dequeue(q); } + /* Add data chunk to the end of the queue. */ static inline void sctp_outq_tail_data(struct sctp_outq *q, struct sctp_chunk *ch) { + struct sctp_stream_out_ext *oute; + __u16 stream; + list_add_tail(&ch->list, &q->out_chunk_list); q->out_qlen += ch->skb->len; + + stream = sctp_chunk_stream_no(ch); + oute = q->asoc->stream.out[stream].ext; + list_add_tail(&ch->stream_list, &oute->outq); } /* @@ -207,6 +214,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) INIT_LIST_HEAD(&q->retransmit); INIT_LIST_HEAD(&q->sacked); INIT_LIST_HEAD(&q->abandoned); + sctp_sched_set_sched(asoc, SCTP_SS_FCFS); } /* Free the outqueue structure and any related pending chunks. @@ -258,6 +266,7 @@ static void __sctp_outq_teardown(struct sctp_outq *q) /* Throw away any leftover data chunks. */ while ((chunk = sctp_outq_dequeue_data(q)) != NULL) { + sctp_sched_dequeue_done(q, chunk); /* Mark as send failure. */ sctp_chunk_fail(chunk, q->error); @@ -366,7 +375,7 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc, streamout = &asoc->stream.out[chk->sinfo.sinfo_stream]; asoc->sent_cnt_removable--; asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; - streamout->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; + streamout->ext->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; if (!chk->tsn_gap_acked) { if (chk->transport) @@ -391,20 +400,21 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, struct sctp_outq *q = &asoc->outqueue; struct sctp_chunk *chk, *temp; + q->sched->unsched_all(&asoc->stream); + list_for_each_entry_safe(chk, temp, &q->out_chunk_list, list) { if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive) continue; - list_del_init(&chk->list); - q->out_qlen -= chk->skb->len; + sctp_sched_dequeue_common(q, chk); asoc->sent_cnt_removable--; asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; if (chk->sinfo.sinfo_stream < asoc->stream.outcnt) { struct sctp_stream_out *streamout = &asoc->stream.out[chk->sinfo.sinfo_stream]; - streamout->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; + streamout->ext->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; } msg_len -= SCTP_DATA_SNDSIZE(chk) + @@ -415,6 +425,8 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, break; } + q->sched->sched_all(&asoc->stream); + return msg_len; } @@ -1033,22 +1045,9 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) while ((chunk = sctp_outq_dequeue_data(q)) != NULL) { __u32 sid = ntohs(chunk->subh.data_hdr->stream); - /* RFC 2960 6.5 Every DATA chunk MUST carry a valid - * stream identifier. - */ - if (chunk->sinfo.sinfo_stream >= asoc->stream.outcnt) { - - /* Mark as failed send. */ - sctp_chunk_fail(chunk, SCTP_ERROR_INV_STRM); - if (asoc->peer.prsctp_capable && - SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags)) - asoc->sent_cnt_removable--; - sctp_chunk_free(chunk); - continue; - } - /* Has this chunk expired? */ if (sctp_chunk_abandoned(chunk)) { + sctp_sched_dequeue_done(q, chunk); sctp_chunk_fail(chunk, 0); sctp_chunk_free(chunk); continue; @@ -1070,6 +1069,7 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) new_transport = asoc->peer.active_path; if (new_transport->state == SCTP_UNCONFIRMED) { WARN_ONCE(1, "Attempt to send packet on unconfirmed path."); + sctp_sched_dequeue_done(q, chunk); sctp_chunk_fail(chunk, 0); sctp_chunk_free(chunk); continue; @@ -1133,6 +1133,11 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) else asoc->stats.oodchunks++; + /* Only now it's safe to consider this + * chunk as sent, sched-wise. + */ + sctp_sched_dequeue_done(q, chunk); + break; default: diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index fcd80feb293f..f5172c21349b 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -622,9 +622,9 @@ static void sctp_v4_ecn_capable(struct sock *sk) INET_ECN_xmit(sk); } -static void sctp_addr_wq_timeout_handler(unsigned long arg) +static void sctp_addr_wq_timeout_handler(struct timer_list *t) { - struct net *net = (struct net *)arg; + struct net *net = from_timer(net, t, sctp.addr_wq_timer); struct sctp_sockaddr_entry *addrw, *temp; struct sctp_sock *sp; @@ -1304,8 +1304,7 @@ static int __net_init sctp_defaults_init(struct net *net) INIT_LIST_HEAD(&net->sctp.auto_asconf_splist); spin_lock_init(&net->sctp.addr_wq_lock); net->sctp.addr_wq_timer.expires = 0; - setup_timer(&net->sctp.addr_wq_timer, sctp_addr_wq_timeout_handler, - (unsigned long)net); + timer_setup(&net->sctp.addr_wq_timer, sctp_addr_wq_timeout_handler, 0); return 0; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 514465b03829..9bf575f2e8ed 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -3594,8 +3594,8 @@ struct sctp_chunk *sctp_make_strreset_req( __u16 stream_num, __be16 *stream_list, bool out, bool in) { + __u16 stream_len = stream_num * sizeof(__u16); struct sctp_strreset_outreq outreq; - __u16 stream_len = stream_num * 2; struct sctp_strreset_inreq inreq; struct sctp_chunk *retval; __u16 outlen, inlen; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index e2d9a4b49c9c..df94d77401e7 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -50,6 +50,7 @@ #include <net/sock.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> +#include <net/sctp/stream_sched.h> static int sctp_cmd_interpreter(enum sctp_event event_type, union sctp_subtype subtype, @@ -242,9 +243,10 @@ nomem: /* When the T3-RTX timer expires, it calls this function to create the * relevant state machine event. */ -void sctp_generate_t3_rtx_event(unsigned long peer) +void sctp_generate_t3_rtx_event(struct timer_list *t) { - struct sctp_transport *transport = (struct sctp_transport *) peer; + struct sctp_transport *transport = + from_timer(transport, t, T3_rtx_timer); struct sctp_association *asoc = transport->asoc; struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); @@ -318,50 +320,63 @@ out_unlock: sctp_association_put(asoc); } -static void sctp_generate_t1_cookie_event(unsigned long data) +static void sctp_generate_t1_cookie_event(struct timer_list *t) { - struct sctp_association *asoc = (struct sctp_association *) data; + struct sctp_association *asoc = + from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_T1_COOKIE]); + sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_T1_COOKIE); } -static void sctp_generate_t1_init_event(unsigned long data) +static void sctp_generate_t1_init_event(struct timer_list *t) { - struct sctp_association *asoc = (struct sctp_association *) data; + struct sctp_association *asoc = + from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_T1_INIT]); + sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_T1_INIT); } -static void sctp_generate_t2_shutdown_event(unsigned long data) +static void sctp_generate_t2_shutdown_event(struct timer_list *t) { - struct sctp_association *asoc = (struct sctp_association *) data; + struct sctp_association *asoc = + from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_T2_SHUTDOWN]); + sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_T2_SHUTDOWN); } -static void sctp_generate_t4_rto_event(unsigned long data) +static void sctp_generate_t4_rto_event(struct timer_list *t) { - struct sctp_association *asoc = (struct sctp_association *) data; + struct sctp_association *asoc = + from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_T4_RTO]); + sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_T4_RTO); } -static void sctp_generate_t5_shutdown_guard_event(unsigned long data) +static void sctp_generate_t5_shutdown_guard_event(struct timer_list *t) { - struct sctp_association *asoc = (struct sctp_association *)data; + struct sctp_association *asoc = + from_timer(asoc, t, + timers[SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD]); + sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD); } /* sctp_generate_t5_shutdown_guard_event() */ -static void sctp_generate_autoclose_event(unsigned long data) +static void sctp_generate_autoclose_event(struct timer_list *t) { - struct sctp_association *asoc = (struct sctp_association *) data; + struct sctp_association *asoc = + from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_AUTOCLOSE]); + sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_AUTOCLOSE); } /* Generate a heart beat event. If the sock is busy, reschedule. Make * sure that the transport is still valid. */ -void sctp_generate_heartbeat_event(unsigned long data) +void sctp_generate_heartbeat_event(struct timer_list *t) { - struct sctp_transport *transport = (struct sctp_transport *) data; + struct sctp_transport *transport = from_timer(transport, t, hb_timer); struct sctp_association *asoc = transport->asoc; struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); @@ -404,9 +419,10 @@ out_unlock: /* Handle the timeout of the ICMP protocol unreachable timer. Trigger * the correct state machine transition that will close the association. */ -void sctp_generate_proto_unreach_event(unsigned long data) +void sctp_generate_proto_unreach_event(struct timer_list *t) { - struct sctp_transport *transport = (struct sctp_transport *)data; + struct sctp_transport *transport = + from_timer(transport, t, proto_unreach_timer); struct sctp_association *asoc = transport->asoc; struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); @@ -438,9 +454,10 @@ out_unlock: } /* Handle the timeout of the RE-CONFIG timer. */ -void sctp_generate_reconf_event(unsigned long data) +void sctp_generate_reconf_event(struct timer_list *t) { - struct sctp_transport *transport = (struct sctp_transport *)data; + struct sctp_transport *transport = + from_timer(transport, t, reconf_timer); struct sctp_association *asoc = transport->asoc; struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); @@ -470,24 +487,27 @@ out_unlock: } /* Inject a SACK Timeout event into the state machine. */ -static void sctp_generate_sack_event(unsigned long data) +static void sctp_generate_sack_event(struct timer_list *t) { - struct sctp_association *asoc = (struct sctp_association *)data; + struct sctp_association *asoc = + from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_SACK]); + sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_SACK); } sctp_timer_event_t *sctp_timer_events[SCTP_NUM_TIMEOUT_TYPES] = { - NULL, - sctp_generate_t1_cookie_event, - sctp_generate_t1_init_event, - sctp_generate_t2_shutdown_event, - NULL, - sctp_generate_t4_rto_event, - sctp_generate_t5_shutdown_guard_event, - NULL, - NULL, - sctp_generate_sack_event, - sctp_generate_autoclose_event, + [SCTP_EVENT_TIMEOUT_NONE] = NULL, + [SCTP_EVENT_TIMEOUT_T1_COOKIE] = sctp_generate_t1_cookie_event, + [SCTP_EVENT_TIMEOUT_T1_INIT] = sctp_generate_t1_init_event, + [SCTP_EVENT_TIMEOUT_T2_SHUTDOWN] = sctp_generate_t2_shutdown_event, + [SCTP_EVENT_TIMEOUT_T3_RTX] = NULL, + [SCTP_EVENT_TIMEOUT_T4_RTO] = sctp_generate_t4_rto_event, + [SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD] = + sctp_generate_t5_shutdown_guard_event, + [SCTP_EVENT_TIMEOUT_HEARTBEAT] = NULL, + [SCTP_EVENT_TIMEOUT_RECONF] = NULL, + [SCTP_EVENT_TIMEOUT_SACK] = sctp_generate_sack_event, + [SCTP_EVENT_TIMEOUT_AUTOCLOSE] = sctp_generate_autoclose_event, }; @@ -1089,6 +1109,8 @@ static void sctp_cmd_send_msg(struct sctp_association *asoc, list_for_each_entry(chunk, &msg->chunks, frag_list) sctp_outq_tail(&asoc->outqueue, chunk, gfp); + + asoc->outqueue.sched->enqueue(&asoc->outqueue, msg); } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6f45d1713452..3204a9b29407 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -79,12 +79,13 @@ #include <net/sock.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> +#include <net/sctp/stream_sched.h> /* Forward declarations for internal helper functions. */ static int sctp_writeable(struct sock *sk); static void sctp_wfree(struct sk_buff *skb); -static int sctp_wait_for_sndbuf(struct sctp_association *, long *timeo_p, - size_t msg_len); +static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, + size_t msg_len, struct sock **orig_sk); static int sctp_wait_for_packet(struct sock *sk, int *err, long *timeo_p); static int sctp_wait_for_connect(struct sctp_association *, long *timeo_p); static int sctp_wait_for_accept(struct sock *sk, long timeo); @@ -1957,14 +1958,28 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) goto out_free; } + /* Allocate sctp_stream_out_ext if not already done */ + if (unlikely(!asoc->stream.out[sinfo->sinfo_stream].ext)) { + err = sctp_stream_init_ext(&asoc->stream, sinfo->sinfo_stream); + if (err) + goto out_free; + } + if (sctp_wspace(asoc) < msg_len) sctp_prsctp_prune(asoc, sinfo, msg_len - sctp_wspace(asoc)); timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); if (!sctp_wspace(asoc)) { - err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len); - if (err) + /* sk can be changed by peel off when waiting for buf. */ + err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len, &sk); + if (err) { + if (err == -ESRCH) { + /* asoc is already dead. */ + new_asoc = NULL; + err = -EPIPE; + } goto out_free; + } } /* If an address is passed with the sendto/sendmsg call, it is used @@ -3125,9 +3140,9 @@ static int sctp_setsockopt_mappedv4(struct sock *sk, char __user *optval, unsign */ static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned int optlen) { + struct sctp_sock *sp = sctp_sk(sk); struct sctp_assoc_value params; struct sctp_association *asoc; - struct sctp_sock *sp = sctp_sk(sk); int val; if (optlen == sizeof(int)) { @@ -3143,26 +3158,35 @@ static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned if (copy_from_user(¶ms, optval, optlen)) return -EFAULT; val = params.assoc_value; - } else + } else { return -EINVAL; + } - if ((val != 0) && ((val < 8) || (val > SCTP_MAX_CHUNK_LEN))) - return -EINVAL; + if (val) { + int min_len, max_len; - asoc = sctp_id2assoc(sk, params.assoc_id); - if (!asoc && params.assoc_id && sctp_style(sk, UDP)) - return -EINVAL; + min_len = SCTP_DEFAULT_MINSEGMENT - sp->pf->af->net_header_len; + min_len -= sizeof(struct sctphdr) + + sizeof(struct sctp_data_chunk); + + max_len = SCTP_MAX_CHUNK_LEN - sizeof(struct sctp_data_chunk); + + if (val < min_len || val > max_len) + return -EINVAL; + } + asoc = sctp_id2assoc(sk, params.assoc_id); if (asoc) { if (val == 0) { - val = asoc->pathmtu; - val -= sp->pf->af->net_header_len; + val = asoc->pathmtu - sp->pf->af->net_header_len; val -= sizeof(struct sctphdr) + - sizeof(struct sctp_data_chunk); + sizeof(struct sctp_data_chunk); } asoc->user_frag = val; asoc->frag_point = sctp_frag_point(asoc, asoc->pathmtu); } else { + if (params.assoc_id && sctp_style(sk, UDP)) + return -EINVAL; sp->user_frag = val; } @@ -3937,6 +3961,64 @@ out: return retval; } +static int sctp_setsockopt_scheduler(struct sock *sk, + char __user *optval, + unsigned int optlen) +{ + struct sctp_association *asoc; + struct sctp_assoc_value params; + int retval = -EINVAL; + + if (optlen < sizeof(params)) + goto out; + + optlen = sizeof(params); + if (copy_from_user(¶ms, optval, optlen)) { + retval = -EFAULT; + goto out; + } + + if (params.assoc_value > SCTP_SS_MAX) + goto out; + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc) + goto out; + + retval = sctp_sched_set_sched(asoc, params.assoc_value); + +out: + return retval; +} + +static int sctp_setsockopt_scheduler_value(struct sock *sk, + char __user *optval, + unsigned int optlen) +{ + struct sctp_association *asoc; + struct sctp_stream_value params; + int retval = -EINVAL; + + if (optlen < sizeof(params)) + goto out; + + optlen = sizeof(params); + if (copy_from_user(¶ms, optval, optlen)) { + retval = -EFAULT; + goto out; + } + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc) + goto out; + + retval = sctp_sched_set_value(asoc, params.stream_id, + params.stream_value, GFP_KERNEL); + +out: + return retval; +} + /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve @@ -4118,6 +4200,12 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, case SCTP_ADD_STREAMS: retval = sctp_setsockopt_add_streams(sk, optval, optlen); break; + case SCTP_STREAM_SCHEDULER: + retval = sctp_setsockopt_scheduler(sk, optval, optlen); + break; + case SCTP_STREAM_SCHEDULER_VALUE: + retval = sctp_setsockopt_scheduler_value(sk, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -4943,12 +5031,6 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp) if (!asoc) return -EINVAL; - /* If there is a thread waiting on more sndbuf space for - * sending on this asoc, it cannot be peeled. - */ - if (waitqueue_active(&asoc->wait)) - return -EBUSY; - /* An association cannot be branched off from an already peeled-off * socket, nor is this supported for tcp style sockets. */ @@ -6679,7 +6761,7 @@ static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len, char __user *optval, int __user *optlen) { - struct sctp_stream_out *streamout; + struct sctp_stream_out_ext *streamoute; struct sctp_association *asoc; struct sctp_prstatus params; int retval = -EINVAL; @@ -6702,21 +6784,29 @@ static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len, if (!asoc || params.sprstat_sid >= asoc->stream.outcnt) goto out; - streamout = &asoc->stream.out[params.sprstat_sid]; + streamoute = asoc->stream.out[params.sprstat_sid].ext; + if (!streamoute) { + /* Not allocated yet, means all stats are 0 */ + params.sprstat_abandoned_unsent = 0; + params.sprstat_abandoned_sent = 0; + retval = 0; + goto out; + } + if (policy == SCTP_PR_SCTP_NONE) { params.sprstat_abandoned_unsent = 0; params.sprstat_abandoned_sent = 0; for (policy = 0; policy <= SCTP_PR_INDEX(MAX); policy++) { params.sprstat_abandoned_unsent += - streamout->abandoned_unsent[policy]; + streamoute->abandoned_unsent[policy]; params.sprstat_abandoned_sent += - streamout->abandoned_sent[policy]; + streamoute->abandoned_sent[policy]; } } else { params.sprstat_abandoned_unsent = - streamout->abandoned_unsent[__SCTP_PR_INDEX(policy)]; + streamoute->abandoned_unsent[__SCTP_PR_INDEX(policy)]; params.sprstat_abandoned_sent = - streamout->abandoned_sent[__SCTP_PR_INDEX(policy)]; + streamoute->abandoned_sent[__SCTP_PR_INDEX(policy)]; } if (put_user(len, optlen) || copy_to_user(optval, ¶ms, len)) { @@ -6812,6 +6902,85 @@ out: return retval; } +static int sctp_getsockopt_scheduler(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + struct sctp_assoc_value params; + struct sctp_association *asoc; + int retval = -EFAULT; + + if (len < sizeof(params)) { + retval = -EINVAL; + goto out; + } + + len = sizeof(params); + if (copy_from_user(¶ms, optval, len)) + goto out; + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc) { + retval = -EINVAL; + goto out; + } + + params.assoc_value = sctp_sched_get_sched(asoc); + + if (put_user(len, optlen)) + goto out; + + if (copy_to_user(optval, ¶ms, len)) + goto out; + + retval = 0; + +out: + return retval; +} + +static int sctp_getsockopt_scheduler_value(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + struct sctp_stream_value params; + struct sctp_association *asoc; + int retval = -EFAULT; + + if (len < sizeof(params)) { + retval = -EINVAL; + goto out; + } + + len = sizeof(params); + if (copy_from_user(¶ms, optval, len)) + goto out; + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc) { + retval = -EINVAL; + goto out; + } + + retval = sctp_sched_get_value(asoc, params.stream_id, + ¶ms.stream_value); + if (retval) + goto out; + + if (put_user(len, optlen)) { + retval = -EFAULT; + goto out; + } + + if (copy_to_user(optval, ¶ms, len)) { + retval = -EFAULT; + goto out; + } + +out: + return retval; +} + static int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -6994,6 +7163,14 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, retval = sctp_getsockopt_enable_strreset(sk, len, optval, optlen); break; + case SCTP_STREAM_SCHEDULER: + retval = sctp_getsockopt_scheduler(sk, len, optval, + optlen); + break; + case SCTP_STREAM_SCHEDULER_VALUE: + retval = sctp_getsockopt_scheduler_value(sk, len, optval, + optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -7822,7 +7999,7 @@ void sctp_sock_rfree(struct sk_buff *skb) /* Helper function to wait for space in the sndbuf. */ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, - size_t msg_len) + size_t msg_len, struct sock **orig_sk) { struct sock *sk = asoc->base.sk; int err = 0; @@ -7839,10 +8016,11 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, for (;;) { prepare_to_wait_exclusive(&asoc->wait, &wait, TASK_INTERRUPTIBLE); + if (asoc->base.dead) + goto do_dead; if (!*timeo_p) goto do_nonblock; - if (sk->sk_err || asoc->state >= SCTP_STATE_SHUTDOWN_PENDING || - asoc->base.dead) + if (sk->sk_err || asoc->state >= SCTP_STATE_SHUTDOWN_PENDING) goto do_error; if (signal_pending(current)) goto do_interrupted; @@ -7855,11 +8033,17 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, release_sock(sk); current_timeo = schedule_timeout(current_timeo); lock_sock(sk); + if (sk != asoc->base.sk) { + release_sock(sk); + sk = asoc->base.sk; + lock_sock(sk); + } *timeo_p = current_timeo; } out: + *orig_sk = sk; finish_wait(&asoc->wait, &wait); /* Release the association's refcnt. */ @@ -7867,6 +8051,10 @@ out: return err; +do_dead: + err = -ESRCH; + goto out; + do_error: err = -EPIPE; goto out; diff --git a/net/sctp/stream.c b/net/sctp/stream.c index fa8371ff05c4..a11db21dc8a0 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -32,44 +32,181 @@ * Xin Long <lucien.xin@gmail.com> */ +#include <linux/list.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> +#include <net/sctp/stream_sched.h> + +/* Migrates chunks from stream queues to new stream queues if needed, + * but not across associations. Also, removes those chunks to streams + * higher than the new max. + */ +static void sctp_stream_outq_migrate(struct sctp_stream *stream, + struct sctp_stream *new, __u16 outcnt) +{ + struct sctp_association *asoc; + struct sctp_chunk *ch, *temp; + struct sctp_outq *outq; + int i; + + asoc = container_of(stream, struct sctp_association, stream); + outq = &asoc->outqueue; + + list_for_each_entry_safe(ch, temp, &outq->out_chunk_list, list) { + __u16 sid = sctp_chunk_stream_no(ch); + + if (sid < outcnt) + continue; + + sctp_sched_dequeue_common(outq, ch); + /* No need to call dequeue_done here because + * the chunks are not scheduled by now. + */ + + /* Mark as failed send. */ + sctp_chunk_fail(ch, SCTP_ERROR_INV_STRM); + if (asoc->peer.prsctp_capable && + SCTP_PR_PRIO_ENABLED(ch->sinfo.sinfo_flags)) + asoc->sent_cnt_removable--; + + sctp_chunk_free(ch); + } + + if (new) { + /* Here we actually move the old ext stuff into the new + * buffer, because we want to keep it. Then + * sctp_stream_update will swap ->out pointers. + */ + for (i = 0; i < outcnt; i++) { + kfree(new->out[i].ext); + new->out[i].ext = stream->out[i].ext; + stream->out[i].ext = NULL; + } + } + + for (i = outcnt; i < stream->outcnt; i++) + kfree(stream->out[i].ext); +} + +static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, + gfp_t gfp) +{ + struct sctp_stream_out *out; + + out = kmalloc_array(outcnt, sizeof(*out), gfp); + if (!out) + return -ENOMEM; + + if (stream->out) { + memcpy(out, stream->out, min(outcnt, stream->outcnt) * + sizeof(*out)); + kfree(stream->out); + } + + if (outcnt > stream->outcnt) + memset(out + stream->outcnt, 0, + (outcnt - stream->outcnt) * sizeof(*out)); + + stream->out = out; + + return 0; +} + +static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt, + gfp_t gfp) +{ + struct sctp_stream_in *in; + + in = kmalloc_array(incnt, sizeof(*stream->in), gfp); + + if (!in) + return -ENOMEM; + + if (stream->in) { + memcpy(in, stream->in, min(incnt, stream->incnt) * + sizeof(*in)); + kfree(stream->in); + } + + if (incnt > stream->incnt) + memset(in + stream->incnt, 0, + (incnt - stream->incnt) * sizeof(*in)); + + stream->in = in; + + return 0; +} int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, gfp_t gfp) { - int i; + struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); + int i, ret = 0; + + gfp |= __GFP_NOWARN; /* Initial stream->out size may be very big, so free it and alloc - * a new one with new outcnt to save memory. + * a new one with new outcnt to save memory if needed. */ - kfree(stream->out); + if (outcnt == stream->outcnt) + goto in; - stream->out = kcalloc(outcnt, sizeof(*stream->out), gfp); - if (!stream->out) - return -ENOMEM; + /* Filter out chunks queued on streams that won't exist anymore */ + sched->unsched_all(stream); + sctp_stream_outq_migrate(stream, NULL, outcnt); + sched->sched_all(stream); + + i = sctp_stream_alloc_out(stream, outcnt, gfp); + if (i) + return i; stream->outcnt = outcnt; for (i = 0; i < stream->outcnt; i++) stream->out[i].state = SCTP_STREAM_OPEN; + sched->init(stream); + +in: if (!incnt) - return 0; + goto out; - stream->in = kcalloc(incnt, sizeof(*stream->in), gfp); - if (!stream->in) { - kfree(stream->out); - stream->out = NULL; - return -ENOMEM; + i = sctp_stream_alloc_in(stream, incnt, gfp); + if (i) { + ret = -ENOMEM; + goto free; } stream->incnt = incnt; + goto out; - return 0; +free: + sched->free(stream); + kfree(stream->out); + stream->out = NULL; +out: + return ret; +} + +int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid) +{ + struct sctp_stream_out_ext *soute; + + soute = kzalloc(sizeof(*soute), GFP_KERNEL); + if (!soute) + return -ENOMEM; + stream->out[sid].ext = soute; + + return sctp_sched_init_sid(stream, sid, GFP_KERNEL); } void sctp_stream_free(struct sctp_stream *stream) { + struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); + int i; + + sched->free(stream); + for (i = 0; i < stream->outcnt; i++) + kfree(stream->out[i].ext); kfree(stream->out); kfree(stream->in); } @@ -87,6 +224,10 @@ void sctp_stream_clear(struct sctp_stream *stream) void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new) { + struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); + + sched->unsched_all(stream); + sctp_stream_outq_migrate(stream, new, new->outcnt); sctp_stream_free(stream); stream->out = new->out; @@ -94,6 +235,8 @@ void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new) stream->outcnt = new->outcnt; stream->incnt = new->incnt; + sched->sched_all(stream); + new->out = NULL; new->in = NULL; } @@ -139,15 +282,31 @@ int sctp_send_reset_streams(struct sctp_association *asoc, str_nums = params->srs_number_streams; str_list = params->srs_stream_list; - if (out && str_nums) - for (i = 0; i < str_nums; i++) - if (str_list[i] >= stream->outcnt) - goto out; + if (str_nums) { + int param_len = 0; - if (in && str_nums) - for (i = 0; i < str_nums; i++) - if (str_list[i] >= stream->incnt) - goto out; + if (out) { + for (i = 0; i < str_nums; i++) + if (str_list[i] >= stream->outcnt) + goto out; + + param_len = str_nums * sizeof(__u16) + + sizeof(struct sctp_strreset_outreq); + } + + if (in) { + for (i = 0; i < str_nums; i++) + if (str_list[i] >= stream->incnt) + goto out; + + param_len += str_nums * sizeof(__u16) + + sizeof(struct sctp_strreset_inreq); + } + + if (param_len > SCTP_MAX_CHUNK_LEN - + sizeof(struct sctp_reconf_chunk)) + goto out; + } nstr_list = kcalloc(str_nums, sizeof(__be16), GFP_KERNEL); if (!nstr_list) { @@ -250,7 +409,7 @@ int sctp_send_add_streams(struct sctp_association *asoc, { struct sctp_stream *stream = &asoc->stream; struct sctp_chunk *chunk = NULL; - int retval = -ENOMEM; + int retval; __u32 outcnt, incnt; __u16 out, in; @@ -276,20 +435,16 @@ int sctp_send_add_streams(struct sctp_association *asoc, } if (out) { - struct sctp_stream_out *streamout; - - streamout = krealloc(stream->out, outcnt * sizeof(*streamout), - GFP_KERNEL); - if (!streamout) + retval = sctp_stream_alloc_out(stream, outcnt, GFP_KERNEL); + if (retval) goto out; - - memset(streamout + stream->outcnt, 0, out * sizeof(*streamout)); - stream->out = streamout; } chunk = sctp_make_strreset_addstrm(asoc, out, in); - if (!chunk) + if (!chunk) { + retval = -ENOMEM; goto out; + } asoc->strreset_chunk = chunk; sctp_chunk_hold(asoc->strreset_chunk); @@ -609,7 +764,6 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out( struct sctp_strreset_addstrm *addstrm = param.v; struct sctp_stream *stream = &asoc->stream; __u32 result = SCTP_STRRESET_DENIED; - struct sctp_stream_in *streamin; __u32 request_seq, incnt; __u16 in, i; @@ -656,13 +810,9 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out( if (!in || incnt > SCTP_MAX_STREAM) goto out; - streamin = krealloc(stream->in, incnt * sizeof(*streamin), - GFP_ATOMIC); - if (!streamin) + if (sctp_stream_alloc_in(stream, incnt, GFP_ATOMIC)) goto out; - memset(streamin + stream->incnt, 0, in * sizeof(*streamin)); - stream->in = streamin; stream->incnt = incnt; result = SCTP_STRRESET_PERFORMED; @@ -684,10 +834,10 @@ struct sctp_chunk *sctp_process_strreset_addstrm_in( struct sctp_strreset_addstrm *addstrm = param.v; struct sctp_stream *stream = &asoc->stream; __u32 result = SCTP_STRRESET_DENIED; - struct sctp_stream_out *streamout; struct sctp_chunk *chunk = NULL; __u32 request_seq, outcnt; __u16 out, i; + int ret; request_seq = ntohl(addstrm->request_seq); if (TSN_lt(asoc->strreset_inseq, request_seq) || @@ -716,14 +866,10 @@ struct sctp_chunk *sctp_process_strreset_addstrm_in( if (!out || outcnt > SCTP_MAX_STREAM) goto out; - streamout = krealloc(stream->out, outcnt * sizeof(*streamout), - GFP_ATOMIC); - if (!streamout) + ret = sctp_stream_alloc_out(stream, outcnt, GFP_ATOMIC); + if (ret) goto out; - memset(streamout + stream->outcnt, 0, out * sizeof(*streamout)); - stream->out = streamout; - chunk = sctp_make_strreset_addstrm(asoc, out, 0); if (!chunk) goto out; diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c new file mode 100644 index 000000000000..0b83ec51e43b --- /dev/null +++ b/net/sctp/stream_sched.c @@ -0,0 +1,275 @@ +/* SCTP kernel implementation + * (C) Copyright Red Hat Inc. 2017 + * + * This file is part of the SCTP kernel implementation + * + * These functions manipulate sctp stream queue/scheduling. + * + * This SCTP implementation is free software; + * you can redistribute it and/or modify it under the terms of + * the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * This SCTP implementation is distributed in the hope that it + * will be useful, but WITHOUT ANY WARRANTY; without even the implied + * ************************ + * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * See the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. + * + * Please send any bug reports or fixes you make to the + * email addresched(es): + * lksctp developers <linux-sctp@vger.kernel.org> + * + * Written or modified by: + * Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> + */ + +#include <linux/list.h> +#include <net/sctp/sctp.h> +#include <net/sctp/sm.h> +#include <net/sctp/stream_sched.h> + +/* First Come First Serve (a.k.a. FIFO) + * RFC DRAFT ndata Section 3.1 + */ +static int sctp_sched_fcfs_set(struct sctp_stream *stream, __u16 sid, + __u16 value, gfp_t gfp) +{ + return 0; +} + +static int sctp_sched_fcfs_get(struct sctp_stream *stream, __u16 sid, + __u16 *value) +{ + *value = 0; + return 0; +} + +static int sctp_sched_fcfs_init(struct sctp_stream *stream) +{ + return 0; +} + +static int sctp_sched_fcfs_init_sid(struct sctp_stream *stream, __u16 sid, + gfp_t gfp) +{ + return 0; +} + +static void sctp_sched_fcfs_free(struct sctp_stream *stream) +{ +} + +static void sctp_sched_fcfs_enqueue(struct sctp_outq *q, + struct sctp_datamsg *msg) +{ +} + +static struct sctp_chunk *sctp_sched_fcfs_dequeue(struct sctp_outq *q) +{ + struct sctp_stream *stream = &q->asoc->stream; + struct sctp_chunk *ch = NULL; + struct list_head *entry; + + if (list_empty(&q->out_chunk_list)) + goto out; + + if (stream->out_curr) { + ch = list_entry(stream->out_curr->ext->outq.next, + struct sctp_chunk, stream_list); + } else { + entry = q->out_chunk_list.next; + ch = list_entry(entry, struct sctp_chunk, list); + } + + sctp_sched_dequeue_common(q, ch); + +out: + return ch; +} + +static void sctp_sched_fcfs_dequeue_done(struct sctp_outq *q, + struct sctp_chunk *chunk) +{ +} + +static void sctp_sched_fcfs_sched_all(struct sctp_stream *stream) +{ +} + +static void sctp_sched_fcfs_unsched_all(struct sctp_stream *stream) +{ +} + +static struct sctp_sched_ops sctp_sched_fcfs = { + .set = sctp_sched_fcfs_set, + .get = sctp_sched_fcfs_get, + .init = sctp_sched_fcfs_init, + .init_sid = sctp_sched_fcfs_init_sid, + .free = sctp_sched_fcfs_free, + .enqueue = sctp_sched_fcfs_enqueue, + .dequeue = sctp_sched_fcfs_dequeue, + .dequeue_done = sctp_sched_fcfs_dequeue_done, + .sched_all = sctp_sched_fcfs_sched_all, + .unsched_all = sctp_sched_fcfs_unsched_all, +}; + +/* API to other parts of the stack */ + +extern struct sctp_sched_ops sctp_sched_prio; +extern struct sctp_sched_ops sctp_sched_rr; + +static struct sctp_sched_ops *sctp_sched_ops[] = { + &sctp_sched_fcfs, + &sctp_sched_prio, + &sctp_sched_rr, +}; + +int sctp_sched_set_sched(struct sctp_association *asoc, + enum sctp_sched_type sched) +{ + struct sctp_sched_ops *n = sctp_sched_ops[sched]; + struct sctp_sched_ops *old = asoc->outqueue.sched; + struct sctp_datamsg *msg = NULL; + struct sctp_chunk *ch; + int i, ret = 0; + + if (old == n) + return ret; + + if (sched > SCTP_SS_MAX) + return -EINVAL; + + if (old) { + old->free(&asoc->stream); + + /* Give the next scheduler a clean slate. */ + for (i = 0; i < asoc->stream.outcnt; i++) { + void *p = asoc->stream.out[i].ext; + + if (!p) + continue; + + p += offsetofend(struct sctp_stream_out_ext, outq); + memset(p, 0, sizeof(struct sctp_stream_out_ext) - + offsetofend(struct sctp_stream_out_ext, outq)); + } + } + + asoc->outqueue.sched = n; + n->init(&asoc->stream); + for (i = 0; i < asoc->stream.outcnt; i++) { + if (!asoc->stream.out[i].ext) + continue; + + ret = n->init_sid(&asoc->stream, i, GFP_KERNEL); + if (ret) + goto err; + } + + /* We have to requeue all chunks already queued. */ + list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) { + if (ch->msg == msg) + continue; + msg = ch->msg; + n->enqueue(&asoc->outqueue, msg); + } + + return ret; + +err: + n->free(&asoc->stream); + asoc->outqueue.sched = &sctp_sched_fcfs; /* Always safe */ + + return ret; +} + +int sctp_sched_get_sched(struct sctp_association *asoc) +{ + int i; + + for (i = 0; i <= SCTP_SS_MAX; i++) + if (asoc->outqueue.sched == sctp_sched_ops[i]) + return i; + + return 0; +} + +int sctp_sched_set_value(struct sctp_association *asoc, __u16 sid, + __u16 value, gfp_t gfp) +{ + if (sid >= asoc->stream.outcnt) + return -EINVAL; + + if (!asoc->stream.out[sid].ext) { + int ret; + + ret = sctp_stream_init_ext(&asoc->stream, sid); + if (ret) + return ret; + } + + return asoc->outqueue.sched->set(&asoc->stream, sid, value, gfp); +} + +int sctp_sched_get_value(struct sctp_association *asoc, __u16 sid, + __u16 *value) +{ + if (sid >= asoc->stream.outcnt) + return -EINVAL; + + if (!asoc->stream.out[sid].ext) + return 0; + + return asoc->outqueue.sched->get(&asoc->stream, sid, value); +} + +void sctp_sched_dequeue_done(struct sctp_outq *q, struct sctp_chunk *ch) +{ + if (!list_is_last(&ch->frag_list, &ch->msg->chunks)) { + struct sctp_stream_out *sout; + __u16 sid; + + /* datamsg is not finish, so save it as current one, + * in case application switch scheduler or a higher + * priority stream comes in. + */ + sid = sctp_chunk_stream_no(ch); + sout = &q->asoc->stream.out[sid]; + q->asoc->stream.out_curr = sout; + return; + } + + q->asoc->stream.out_curr = NULL; + q->sched->dequeue_done(q, ch); +} + +/* Auxiliary functions for the schedulers */ +void sctp_sched_dequeue_common(struct sctp_outq *q, struct sctp_chunk *ch) +{ + list_del_init(&ch->list); + list_del_init(&ch->stream_list); + q->out_qlen -= ch->skb->len; +} + +int sctp_sched_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp) +{ + struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); + + INIT_LIST_HEAD(&stream->out[sid].ext->outq); + return sched->init_sid(stream, sid, gfp); +} + +struct sctp_sched_ops *sctp_sched_ops_from_stream(struct sctp_stream *stream) +{ + struct sctp_association *asoc; + + asoc = container_of(stream, struct sctp_association, stream); + + return asoc->outqueue.sched; +} diff --git a/net/sctp/stream_sched_prio.c b/net/sctp/stream_sched_prio.c new file mode 100644 index 000000000000..384dbf3c8760 --- /dev/null +++ b/net/sctp/stream_sched_prio.c @@ -0,0 +1,347 @@ +/* SCTP kernel implementation + * (C) Copyright Red Hat Inc. 2017 + * + * This file is part of the SCTP kernel implementation + * + * These functions manipulate sctp stream queue/scheduling. + * + * This SCTP implementation is free software; + * you can redistribute it and/or modify it under the terms of + * the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * This SCTP implementation is distributed in the hope that it + * will be useful, but WITHOUT ANY WARRANTY; without even the implied + * ************************ + * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * See the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. + * + * Please send any bug reports or fixes you make to the + * email addresched(es): + * lksctp developers <linux-sctp@vger.kernel.org> + * + * Written or modified by: + * Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> + */ + +#include <linux/list.h> +#include <net/sctp/sctp.h> +#include <net/sctp/sm.h> +#include <net/sctp/stream_sched.h> + +/* Priority handling + * RFC DRAFT ndata section 3.4 + */ + +static void sctp_sched_prio_unsched_all(struct sctp_stream *stream); + +static struct sctp_stream_priorities *sctp_sched_prio_new_head( + struct sctp_stream *stream, int prio, gfp_t gfp) +{ + struct sctp_stream_priorities *p; + + p = kmalloc(sizeof(*p), gfp); + if (!p) + return NULL; + + INIT_LIST_HEAD(&p->prio_sched); + INIT_LIST_HEAD(&p->active); + p->next = NULL; + p->prio = prio; + + return p; +} + +static struct sctp_stream_priorities *sctp_sched_prio_get_head( + struct sctp_stream *stream, int prio, gfp_t gfp) +{ + struct sctp_stream_priorities *p; + int i; + + /* Look into scheduled priorities first, as they are sorted and + * we can find it fast IF it's scheduled. + */ + list_for_each_entry(p, &stream->prio_list, prio_sched) { + if (p->prio == prio) + return p; + if (p->prio > prio) + break; + } + + /* No luck. So we search on all streams now. */ + for (i = 0; i < stream->outcnt; i++) { + if (!stream->out[i].ext) + continue; + + p = stream->out[i].ext->prio_head; + if (!p) + /* Means all other streams won't be initialized + * as well. + */ + break; + if (p->prio == prio) + return p; + } + + /* If not even there, allocate a new one. */ + return sctp_sched_prio_new_head(stream, prio, gfp); +} + +static void sctp_sched_prio_next_stream(struct sctp_stream_priorities *p) +{ + struct list_head *pos; + + pos = p->next->prio_list.next; + if (pos == &p->active) + pos = pos->next; + p->next = list_entry(pos, struct sctp_stream_out_ext, prio_list); +} + +static bool sctp_sched_prio_unsched(struct sctp_stream_out_ext *soute) +{ + bool scheduled = false; + + if (!list_empty(&soute->prio_list)) { + struct sctp_stream_priorities *prio_head = soute->prio_head; + + /* Scheduled */ + scheduled = true; + + if (prio_head->next == soute) + /* Try to move to the next stream */ + sctp_sched_prio_next_stream(prio_head); + + list_del_init(&soute->prio_list); + + /* Also unsched the priority if this was the last stream */ + if (list_empty(&prio_head->active)) { + list_del_init(&prio_head->prio_sched); + /* If there is no stream left, clear next */ + prio_head->next = NULL; + } + } + + return scheduled; +} + +static void sctp_sched_prio_sched(struct sctp_stream *stream, + struct sctp_stream_out_ext *soute) +{ + struct sctp_stream_priorities *prio, *prio_head; + + prio_head = soute->prio_head; + + /* Nothing to do if already scheduled */ + if (!list_empty(&soute->prio_list)) + return; + + /* Schedule the stream. If there is a next, we schedule the new + * one before it, so it's the last in round robin order. + * If there isn't, we also have to schedule the priority. + */ + if (prio_head->next) { + list_add(&soute->prio_list, prio_head->next->prio_list.prev); + return; + } + + list_add(&soute->prio_list, &prio_head->active); + prio_head->next = soute; + + list_for_each_entry(prio, &stream->prio_list, prio_sched) { + if (prio->prio > prio_head->prio) { + list_add(&prio_head->prio_sched, prio->prio_sched.prev); + return; + } + } + + list_add_tail(&prio_head->prio_sched, &stream->prio_list); +} + +static int sctp_sched_prio_set(struct sctp_stream *stream, __u16 sid, + __u16 prio, gfp_t gfp) +{ + struct sctp_stream_out *sout = &stream->out[sid]; + struct sctp_stream_out_ext *soute = sout->ext; + struct sctp_stream_priorities *prio_head, *old; + bool reschedule = false; + int i; + + prio_head = sctp_sched_prio_get_head(stream, prio, gfp); + if (!prio_head) + return -ENOMEM; + + reschedule = sctp_sched_prio_unsched(soute); + old = soute->prio_head; + soute->prio_head = prio_head; + if (reschedule) + sctp_sched_prio_sched(stream, soute); + + if (!old) + /* Happens when we set the priority for the first time */ + return 0; + + for (i = 0; i < stream->outcnt; i++) { + soute = stream->out[i].ext; + if (soute && soute->prio_head == old) + /* It's still in use, nothing else to do here. */ + return 0; + } + + /* No hits, we are good to free it. */ + kfree(old); + + return 0; +} + +static int sctp_sched_prio_get(struct sctp_stream *stream, __u16 sid, + __u16 *value) +{ + *value = stream->out[sid].ext->prio_head->prio; + return 0; +} + +static int sctp_sched_prio_init(struct sctp_stream *stream) +{ + INIT_LIST_HEAD(&stream->prio_list); + + return 0; +} + +static int sctp_sched_prio_init_sid(struct sctp_stream *stream, __u16 sid, + gfp_t gfp) +{ + INIT_LIST_HEAD(&stream->out[sid].ext->prio_list); + return sctp_sched_prio_set(stream, sid, 0, gfp); +} + +static void sctp_sched_prio_free(struct sctp_stream *stream) +{ + struct sctp_stream_priorities *prio, *n; + LIST_HEAD(list); + int i; + + /* As we don't keep a list of priorities, to avoid multiple + * frees we have to do it in 3 steps: + * 1. unsched everyone, so the lists are free to use in 2. + * 2. build the list of the priorities + * 3. free the list + */ + sctp_sched_prio_unsched_all(stream); + for (i = 0; i < stream->outcnt; i++) { + if (!stream->out[i].ext) + continue; + prio = stream->out[i].ext->prio_head; + if (prio && list_empty(&prio->prio_sched)) + list_add(&prio->prio_sched, &list); + } + list_for_each_entry_safe(prio, n, &list, prio_sched) { + list_del_init(&prio->prio_sched); + kfree(prio); + } +} + +static void sctp_sched_prio_enqueue(struct sctp_outq *q, + struct sctp_datamsg *msg) +{ + struct sctp_stream *stream; + struct sctp_chunk *ch; + __u16 sid; + + ch = list_first_entry(&msg->chunks, struct sctp_chunk, frag_list); + sid = sctp_chunk_stream_no(ch); + stream = &q->asoc->stream; + sctp_sched_prio_sched(stream, stream->out[sid].ext); +} + +static struct sctp_chunk *sctp_sched_prio_dequeue(struct sctp_outq *q) +{ + struct sctp_stream *stream = &q->asoc->stream; + struct sctp_stream_priorities *prio; + struct sctp_stream_out_ext *soute; + struct sctp_chunk *ch = NULL; + + /* Bail out quickly if queue is empty */ + if (list_empty(&q->out_chunk_list)) + goto out; + + /* Find which chunk is next. It's easy, it's either the current + * one or the first chunk on the next active stream. + */ + if (stream->out_curr) { + soute = stream->out_curr->ext; + } else { + prio = list_entry(stream->prio_list.next, + struct sctp_stream_priorities, prio_sched); + soute = prio->next; + } + ch = list_entry(soute->outq.next, struct sctp_chunk, stream_list); + sctp_sched_dequeue_common(q, ch); + +out: + return ch; +} + +static void sctp_sched_prio_dequeue_done(struct sctp_outq *q, + struct sctp_chunk *ch) +{ + struct sctp_stream_priorities *prio; + struct sctp_stream_out_ext *soute; + __u16 sid; + + /* Last chunk on that msg, move to the next stream on + * this priority. + */ + sid = sctp_chunk_stream_no(ch); + soute = q->asoc->stream.out[sid].ext; + prio = soute->prio_head; + + sctp_sched_prio_next_stream(prio); + + if (list_empty(&soute->outq)) + sctp_sched_prio_unsched(soute); +} + +static void sctp_sched_prio_sched_all(struct sctp_stream *stream) +{ + struct sctp_association *asoc; + struct sctp_stream_out *sout; + struct sctp_chunk *ch; + + asoc = container_of(stream, struct sctp_association, stream); + list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) { + __u16 sid; + + sid = sctp_chunk_stream_no(ch); + sout = &stream->out[sid]; + if (sout->ext) + sctp_sched_prio_sched(stream, sout->ext); + } +} + +static void sctp_sched_prio_unsched_all(struct sctp_stream *stream) +{ + struct sctp_stream_priorities *p, *tmp; + struct sctp_stream_out_ext *soute, *souttmp; + + list_for_each_entry_safe(p, tmp, &stream->prio_list, prio_sched) + list_for_each_entry_safe(soute, souttmp, &p->active, prio_list) + sctp_sched_prio_unsched(soute); +} + +struct sctp_sched_ops sctp_sched_prio = { + .set = sctp_sched_prio_set, + .get = sctp_sched_prio_get, + .init = sctp_sched_prio_init, + .init_sid = sctp_sched_prio_init_sid, + .free = sctp_sched_prio_free, + .enqueue = sctp_sched_prio_enqueue, + .dequeue = sctp_sched_prio_dequeue, + .dequeue_done = sctp_sched_prio_dequeue_done, + .sched_all = sctp_sched_prio_sched_all, + .unsched_all = sctp_sched_prio_unsched_all, +}; diff --git a/net/sctp/stream_sched_rr.c b/net/sctp/stream_sched_rr.c new file mode 100644 index 000000000000..7612a438c5b9 --- /dev/null +++ b/net/sctp/stream_sched_rr.c @@ -0,0 +1,201 @@ +/* SCTP kernel implementation + * (C) Copyright Red Hat Inc. 2017 + * + * This file is part of the SCTP kernel implementation + * + * These functions manipulate sctp stream queue/scheduling. + * + * This SCTP implementation is free software; + * you can redistribute it and/or modify it under the terms of + * the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * This SCTP implementation is distributed in the hope that it + * will be useful, but WITHOUT ANY WARRANTY; without even the implied + * ************************ + * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * See the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with GNU CC; see the file COPYING. If not, see + * <http://www.gnu.org/licenses/>. + * + * Please send any bug reports or fixes you make to the + * email addresched(es): + * lksctp developers <linux-sctp@vger.kernel.org> + * + * Written or modified by: + * Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> + */ + +#include <linux/list.h> +#include <net/sctp/sctp.h> +#include <net/sctp/sm.h> +#include <net/sctp/stream_sched.h> + +/* Priority handling + * RFC DRAFT ndata section 3.2 + */ +static void sctp_sched_rr_unsched_all(struct sctp_stream *stream); + +static void sctp_sched_rr_next_stream(struct sctp_stream *stream) +{ + struct list_head *pos; + + pos = stream->rr_next->rr_list.next; + if (pos == &stream->rr_list) + pos = pos->next; + stream->rr_next = list_entry(pos, struct sctp_stream_out_ext, rr_list); +} + +static void sctp_sched_rr_unsched(struct sctp_stream *stream, + struct sctp_stream_out_ext *soute) +{ + if (stream->rr_next == soute) + /* Try to move to the next stream */ + sctp_sched_rr_next_stream(stream); + + list_del_init(&soute->rr_list); + + /* If we have no other stream queued, clear next */ + if (list_empty(&stream->rr_list)) + stream->rr_next = NULL; +} + +static void sctp_sched_rr_sched(struct sctp_stream *stream, + struct sctp_stream_out_ext *soute) +{ + if (!list_empty(&soute->rr_list)) + /* Already scheduled. */ + return; + + /* Schedule the stream */ + list_add_tail(&soute->rr_list, &stream->rr_list); + + if (!stream->rr_next) + stream->rr_next = soute; +} + +static int sctp_sched_rr_set(struct sctp_stream *stream, __u16 sid, + __u16 prio, gfp_t gfp) +{ + return 0; +} + +static int sctp_sched_rr_get(struct sctp_stream *stream, __u16 sid, + __u16 *value) +{ + return 0; +} + +static int sctp_sched_rr_init(struct sctp_stream *stream) +{ + INIT_LIST_HEAD(&stream->rr_list); + stream->rr_next = NULL; + + return 0; +} + +static int sctp_sched_rr_init_sid(struct sctp_stream *stream, __u16 sid, + gfp_t gfp) +{ + INIT_LIST_HEAD(&stream->out[sid].ext->rr_list); + + return 0; +} + +static void sctp_sched_rr_free(struct sctp_stream *stream) +{ + sctp_sched_rr_unsched_all(stream); +} + +static void sctp_sched_rr_enqueue(struct sctp_outq *q, + struct sctp_datamsg *msg) +{ + struct sctp_stream *stream; + struct sctp_chunk *ch; + __u16 sid; + + ch = list_first_entry(&msg->chunks, struct sctp_chunk, frag_list); + sid = sctp_chunk_stream_no(ch); + stream = &q->asoc->stream; + sctp_sched_rr_sched(stream, stream->out[sid].ext); +} + +static struct sctp_chunk *sctp_sched_rr_dequeue(struct sctp_outq *q) +{ + struct sctp_stream *stream = &q->asoc->stream; + struct sctp_stream_out_ext *soute; + struct sctp_chunk *ch = NULL; + + /* Bail out quickly if queue is empty */ + if (list_empty(&q->out_chunk_list)) + goto out; + + /* Find which chunk is next */ + if (stream->out_curr) + soute = stream->out_curr->ext; + else + soute = stream->rr_next; + ch = list_entry(soute->outq.next, struct sctp_chunk, stream_list); + + sctp_sched_dequeue_common(q, ch); + +out: + return ch; +} + +static void sctp_sched_rr_dequeue_done(struct sctp_outq *q, + struct sctp_chunk *ch) +{ + struct sctp_stream_out_ext *soute; + __u16 sid; + + /* Last chunk on that msg, move to the next stream */ + sid = sctp_chunk_stream_no(ch); + soute = q->asoc->stream.out[sid].ext; + + sctp_sched_rr_next_stream(&q->asoc->stream); + + if (list_empty(&soute->outq)) + sctp_sched_rr_unsched(&q->asoc->stream, soute); +} + +static void sctp_sched_rr_sched_all(struct sctp_stream *stream) +{ + struct sctp_association *asoc; + struct sctp_stream_out_ext *soute; + struct sctp_chunk *ch; + + asoc = container_of(stream, struct sctp_association, stream); + list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) { + __u16 sid; + + sid = sctp_chunk_stream_no(ch); + soute = stream->out[sid].ext; + if (soute) + sctp_sched_rr_sched(stream, soute); + } +} + +static void sctp_sched_rr_unsched_all(struct sctp_stream *stream) +{ + struct sctp_stream_out_ext *soute, *tmp; + + list_for_each_entry_safe(soute, tmp, &stream->rr_list, rr_list) + sctp_sched_rr_unsched(stream, soute); +} + +struct sctp_sched_ops sctp_sched_rr = { + .set = sctp_sched_rr_set, + .get = sctp_sched_rr_get, + .init = sctp_sched_rr_init, + .init_sid = sctp_sched_rr_init_sid, + .free = sctp_sched_rr_free, + .enqueue = sctp_sched_rr_enqueue, + .dequeue = sctp_sched_rr_dequeue, + .dequeue_done = sctp_sched_rr_dequeue_done, + .sched_all = sctp_sched_rr_sched_all, + .unsched_all = sctp_sched_rr_unsched_all, +}; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 2d9bd3776bc8..1e5a22430cf5 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -87,14 +87,11 @@ static struct sctp_transport *sctp_transport_init(struct net *net, INIT_LIST_HEAD(&peer->send_ready); INIT_LIST_HEAD(&peer->transports); - setup_timer(&peer->T3_rtx_timer, sctp_generate_t3_rtx_event, - (unsigned long)peer); - setup_timer(&peer->hb_timer, sctp_generate_heartbeat_event, - (unsigned long)peer); - setup_timer(&peer->reconf_timer, sctp_generate_reconf_event, - (unsigned long)peer); - setup_timer(&peer->proto_unreach_timer, - sctp_generate_proto_unreach_event, (unsigned long)peer); + timer_setup(&peer->T3_rtx_timer, sctp_generate_t3_rtx_event, 0); + timer_setup(&peer->hb_timer, sctp_generate_heartbeat_event, 0); + timer_setup(&peer->reconf_timer, sctp_generate_reconf_event, 0); + timer_setup(&peer->proto_unreach_timer, + sctp_generate_proto_unreach_event, 0); /* Initialize the 64-bit random nonce sent with heartbeat. */ get_random_bytes(&peer->hb_nonce, sizeof(peer->hb_nonce)); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 745f145d4c4d..6451c5013e06 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -390,6 +390,12 @@ static int smc_connect_rdma(struct smc_sock *smc) int rc = 0; u8 ibport; + if (!tcp_sk(smc->clcsock->sk)->syn_smc) { + /* peer has not signalled SMC-capability */ + smc->use_fallback = true; + goto out_connected; + } + /* IPSec connections opt out of SMC-R optimizations */ if (using_ipsec(smc)) { reason_code = SMC_CLC_DECL_IPSEC; @@ -555,6 +561,7 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr, } smc_copy_sock_settings_to_clc(smc); + tcp_sk(smc->clcsock->sk)->syn_smc = 1; rc = kernel_connect(smc->clcsock, addr, alen, flags); if (rc) goto out; @@ -759,6 +766,12 @@ static void smc_listen_work(struct work_struct *work) u8 prefix_len; u8 ibport; + /* check if peer is smc capable */ + if (!tcp_sk(newclcsock->sk)->syn_smc) { + new_smc->use_fallback = true; + goto out_connected; + } + /* do inband token exchange - *wait for and receive SMC Proposal CLC message */ @@ -808,7 +821,7 @@ static void smc_listen_work(struct work_struct *work) rc = local_contact; if (rc == -ENOMEM) reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/ - goto decline_rdma; + goto decline_rdma_unlock; } link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK]; @@ -816,7 +829,7 @@ static void smc_listen_work(struct work_struct *work) rc = smc_buf_create(new_smc); if (rc) { reason_code = SMC_CLC_DECL_MEM; - goto decline_rdma; + goto decline_rdma_unlock; } smc_close_init(new_smc); @@ -831,7 +844,7 @@ static void smc_listen_work(struct work_struct *work) buf_desc->mr_rx[SMC_SINGLE_LINK]); if (rc) { reason_code = SMC_CLC_DECL_INTERR; - goto decline_rdma; + goto decline_rdma_unlock; } } } @@ -839,15 +852,15 @@ static void smc_listen_work(struct work_struct *work) rc = smc_clc_send_accept(new_smc, local_contact); if (rc) - goto out_err; + goto out_err_unlock; /* receive SMC Confirm CLC message */ reason_code = smc_clc_wait_msg(new_smc, &cclc, sizeof(cclc), SMC_CLC_CONFIRM); if (reason_code < 0) - goto out_err; + goto out_err_unlock; if (reason_code > 0) - goto decline_rdma; + goto decline_rdma_unlock; smc_conn_save_peer_info(new_smc, &cclc); if (local_contact == SMC_FIRST_CONTACT) smc_link_save_peer_info(link, &cclc); @@ -855,34 +868,34 @@ static void smc_listen_work(struct work_struct *work) rc = smc_rmb_rtoken_handling(&new_smc->conn, &cclc); if (rc) { reason_code = SMC_CLC_DECL_INTERR; - goto decline_rdma; + goto decline_rdma_unlock; } if (local_contact == SMC_FIRST_CONTACT) { rc = smc_ib_ready_link(link); if (rc) { reason_code = SMC_CLC_DECL_INTERR; - goto decline_rdma; + goto decline_rdma_unlock; } /* QP confirmation over RoCE fabric */ reason_code = smc_serv_conf_first_link(new_smc); if (reason_code < 0) { /* peer is not aware of a problem */ rc = reason_code; - goto out_err; + goto out_err_unlock; } if (reason_code > 0) - goto decline_rdma; + goto decline_rdma_unlock; } smc_tx_init(new_smc); + mutex_unlock(&smc_create_lgr_pending); out_connected: sk_refcnt_debug_inc(newsmcsk); if (newsmcsk->sk_state == SMC_INIT) newsmcsk->sk_state = SMC_ACTIVE; enqueue: - mutex_unlock(&smc_create_lgr_pending); lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING); if (lsmc->sk.sk_state == SMC_LISTEN) { smc_accept_enqueue(&lsmc->sk, newsmcsk); @@ -896,6 +909,8 @@ enqueue: sock_put(&lsmc->sk); /* sock_hold in smc_tcp_listen_work */ return; +decline_rdma_unlock: + mutex_unlock(&smc_create_lgr_pending); decline_rdma: /* RDMA setup failed, switch back to TCP */ smc_conn_free(&new_smc->conn); @@ -907,6 +922,8 @@ decline_rdma: } goto out_connected; +out_err_unlock: + mutex_unlock(&smc_create_lgr_pending); out_err: newsmcsk->sk_state = SMC_CLOSED; smc_conn_free(&new_smc->conn); @@ -963,6 +980,7 @@ static int smc_listen(struct socket *sock, int backlog) * them to the clc socket -- copy smc socket options to clc socket */ smc_copy_sock_settings_to_clc(smc); + tcp_sk(smc->clcsock->sk)->syn_smc = 1; rc = kernel_listen(smc->clcsock, backlog); if (rc) @@ -1405,6 +1423,7 @@ static int __init smc_init(void) goto out_sock; } + static_branch_enable(&tcp_have_smc); return 0; out_sock: @@ -1429,6 +1448,7 @@ static void __exit smc_exit(void) list_del_init(&lgr->list); smc_lgr_free(lgr); /* free link group */ } + static_branch_disable(&tcp_have_smc); smc_ib_unregister_client(); sock_unregister(PF_SMC); proto_unregister(&smc_proto); diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index 535e72cfc64b..87f7bede6eab 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -63,10 +63,12 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd, bh_unlock_sock(&smc->sk); } -int smc_cdc_get_free_slot(struct smc_link *link, +int smc_cdc_get_free_slot(struct smc_connection *conn, struct smc_wr_buf **wr_buf, struct smc_cdc_tx_pend **pend) { + struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK]; + return smc_wr_tx_get_free_slot(link, smc_cdc_tx_handler, wr_buf, (struct smc_wr_tx_pend_priv **)pend); } @@ -119,8 +121,7 @@ int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn) struct smc_wr_buf *wr_buf; int rc; - rc = smc_cdc_get_free_slot(&conn->lgr->lnk[SMC_SINGLE_LINK], &wr_buf, - &pend); + rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend); if (rc) return rc; diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h index bea61dadaf36..149ceda1b088 100644 --- a/net/smc/smc_cdc.h +++ b/net/smc/smc_cdc.h @@ -207,7 +207,8 @@ static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local, struct smc_cdc_tx_pend; -int smc_cdc_get_free_slot(struct smc_link *link, struct smc_wr_buf **wr_buf, +int smc_cdc_get_free_slot(struct smc_connection *conn, + struct smc_wr_buf **wr_buf, struct smc_cdc_tx_pend **pend); void smc_cdc_tx_dismiss_slots(struct smc_connection *conn); int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf, diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 2427a1f3d0d1..48615d2ac4aa 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -361,7 +361,8 @@ static void smc_close_passive_work(struct work_struct *work) case SMC_PEERCLOSEWAIT1: if (rxflags->peer_done_writing) sk->sk_state = SMC_PEERCLOSEWAIT2; - /* fall through to check for closing */ + /* fall through */ + /* to check for closing */ case SMC_PEERCLOSEWAIT2: case SMC_PEERFINCLOSEWAIT: if (!smc_cdc_rxed_any_close(&smc->conn)) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 413e3868fbf3..2578fbd95664 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -381,10 +381,14 @@ static int smc_link_determine_gid(struct smc_link_group *lgr) if (ib_query_gid(lnk->smcibdev->ibdev, lnk->ibport, i, &gid, &gattr)) continue; - if (gattr.ndev && - (vlan_dev_vlan_id(gattr.ndev) == lgr->vlan_id)) { - lnk->gid = gid; - return 0; + if (gattr.ndev) { + if (is_vlan_dev(gattr.ndev) && + vlan_dev_vlan_id(gattr.ndev) == lgr->vlan_id) { + lnk->gid = gid; + dev_put(gattr.ndev); + return 0; + } + dev_put(gattr.ndev); } } return -ENODEV; diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 9033b8a36fe1..90f1a7f9085c 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -370,26 +370,17 @@ void smc_ib_buf_unmap_sg(struct smc_ib_device *smcibdev, static int smc_ib_fill_gid_and_mac(struct smc_ib_device *smcibdev, u8 ibport) { - struct net_device *ndev; + struct ib_gid_attr gattr; int rc; rc = ib_query_gid(smcibdev->ibdev, ibport, 0, - &smcibdev->gid[ibport - 1], NULL); - /* the SMC protocol requires specification of the roce MAC address; - * if net_device cannot be determined, it can be derived from gid 0 - */ - ndev = smcibdev->ibdev->get_netdev(smcibdev->ibdev, ibport); - if (ndev) { - memcpy(&smcibdev->mac, ndev->dev_addr, ETH_ALEN); - dev_put(ndev); - } else if (!rc) { - memcpy(&smcibdev->mac[ibport - 1][0], - &smcibdev->gid[ibport - 1].raw[8], 3); - memcpy(&smcibdev->mac[ibport - 1][3], - &smcibdev->gid[ibport - 1].raw[13], 3); - smcibdev->mac[ibport - 1][0] &= ~0x02; - } - return rc; + &smcibdev->gid[ibport - 1], &gattr); + if (rc || !gattr.ndev) + return -ENODEV; + + memcpy(smcibdev->mac[ibport - 1], gattr.ndev->dev_addr, ETH_ALEN); + dev_put(gattr.ndev); + return 0; } /* Create an identifier unique for this instance of SMC-R. @@ -420,6 +411,7 @@ int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport) &smcibdev->pattr[ibport - 1]); if (rc) goto out; + /* the SMC protocol requires specification of the RoCE MAC address */ rc = smc_ib_fill_gid_and_mac(smcibdev, ibport); if (rc) goto out; diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index 710ab3fbf607..c48dc2d5fd3a 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -397,8 +397,7 @@ int smc_tx_sndbuf_nonempty(struct smc_connection *conn) int rc; spin_lock_bh(&conn->send_lock); - rc = smc_cdc_get_free_slot(&conn->lgr->lnk[SMC_SINGLE_LINK], &wr_buf, - &pend); + rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend); if (rc < 0) { if (rc == -EBUSY) { struct smc_sock *smc = @@ -467,8 +466,7 @@ void smc_tx_consumer_update(struct smc_connection *conn) ((to_confirm > conn->rmbe_update_limit) && ((to_confirm > (conn->rmbe_size / 2)) || conn->local_rx_ctrl.prod_flags.write_blocked))) { - rc = smc_cdc_get_free_slot(&conn->lgr->lnk[SMC_SINGLE_LINK], - &wr_buf, &pend); + rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend); if (!rc) rc = smc_cdc_msg_send(conn, wr_buf, pend); if (rc < 0) { diff --git a/net/socket.c b/net/socket.c index c729625eb5d3..42d8e9c9ccd5 100644 --- a/net/socket.c +++ b/net/socket.c @@ -568,7 +568,6 @@ struct socket *sock_alloc(void) sock = SOCKET_I(inode); - kmemcheck_annotate_bitfield(sock, type); inode->i_ino = get_next_ino(); inode->i_mode = S_IFSOCK | S_IRWXUGO; inode->i_uid = current_fsuid(); diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 7b1ee5a0b03c..73165e9ca5bf 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -855,11 +855,13 @@ unwrap_integ_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct g return stat; if (integ_len > buf->len) return stat; - if (xdr_buf_subsegment(buf, &integ_buf, 0, integ_len)) - BUG(); + if (xdr_buf_subsegment(buf, &integ_buf, 0, integ_len)) { + WARN_ON_ONCE(1); + return stat; + } /* copy out mic... */ if (read_u32_from_xdr_buf(buf, integ_len, &mic.len)) - BUG(); + return stat; if (mic.len > RPC_MAX_AUTH_SIZE) return stat; mic.data = kmalloc(mic.len, GFP_KERNEL); @@ -1611,8 +1613,10 @@ svcauth_gss_wrap_resp_integ(struct svc_rqst *rqstp) BUG_ON(integ_len % 4); *p++ = htonl(integ_len); *p++ = htonl(gc->gc_seq); - if (xdr_buf_subsegment(resbuf, &integ_buf, integ_offset, integ_len)) - BUG(); + if (xdr_buf_subsegment(resbuf, &integ_buf, integ_offset, integ_len)) { + WARN_ON_ONCE(1); + goto out_err; + } if (resbuf->tail[0].iov_base == NULL) { if (resbuf->head[0].iov_len + RPC_MAX_AUTH_SIZE > PAGE_SIZE) goto out_err; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 2ad827db2704..a801da812f86 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1491,7 +1491,6 @@ rpc_restart_call(struct rpc_task *task) } EXPORT_SYMBOL_GPL(rpc_restart_call); -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) const char *rpc_proc_name(const struct rpc_task *task) { @@ -1505,7 +1504,6 @@ const char } else return "no proc"; } -#endif /* * 0. Initial state @@ -1519,6 +1517,7 @@ call_start(struct rpc_task *task) struct rpc_clnt *clnt = task->tk_client; int idx = task->tk_msg.rpc_proc->p_statidx; + trace_rpc_request(task); dprintk("RPC: %5u call_start %s%d proc %s (%s)\n", task->tk_pid, clnt->cl_program->name, clnt->cl_vers, rpc_proc_name(task), @@ -1586,6 +1585,7 @@ call_reserveresult(struct rpc_task *task) switch (status) { case -ENOMEM: rpc_delay(task, HZ >> 2); + /* fall through */ case -EAGAIN: /* woken up; retry */ task->tk_action = call_retry_reserve; return; @@ -1647,10 +1647,13 @@ call_refreshresult(struct rpc_task *task) /* Use rate-limiting and a max number of retries if refresh * had status 0 but failed to update the cred. */ + /* fall through */ case -ETIMEDOUT: rpc_delay(task, 3*HZ); + /* fall through */ case -EAGAIN: status = -EACCES; + /* fall through */ case -EKEYEXPIRED: if (!task->tk_cred_retry) break; @@ -1911,6 +1914,7 @@ call_connect_status(struct rpc_task *task) task->tk_action = call_bind; return; } + /* fall through */ case -ECONNRESET: case -ECONNABORTED: case -ENETUNREACH: @@ -1924,6 +1928,7 @@ call_connect_status(struct rpc_task *task) break; /* retry with existing socket, after a delay */ rpc_delay(task, 3*HZ); + /* fall through */ case -EAGAIN: /* Check for timeouts before looping back to call_bind */ case -ETIMEDOUT: @@ -2025,6 +2030,7 @@ call_transmit_status(struct rpc_task *task) rpc_exit(task, task->tk_status); break; } + /* fall through */ case -ECONNRESET: case -ECONNABORTED: case -EADDRINUSE: @@ -2145,6 +2151,7 @@ call_status(struct rpc_task *task) * were a timeout. */ rpc_delay(task, 3*HZ); + /* fall through */ case -ETIMEDOUT: task->tk_action = call_timeout; break; @@ -2152,14 +2159,17 @@ call_status(struct rpc_task *task) case -ECONNRESET: case -ECONNABORTED: rpc_force_rebind(clnt); + /* fall through */ case -EADDRINUSE: rpc_delay(task, 3*HZ); + /* fall through */ case -EPIPE: case -ENOTCONN: task->tk_action = call_bind; break; case -ENOBUFS: rpc_delay(task, HZ>>2); + /* fall through */ case -EAGAIN: task->tk_action = call_transmit; break; diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 61a504fb1ae2..7803f3b6aa53 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -1410,8 +1410,8 @@ rpc_fill_super(struct super_block *sb, void *data, int silent) return PTR_ERR(gssd_dentry); } - dprintk("RPC: sending pipefs MOUNT notification for net %p%s\n", - net, NET_NAME(net)); + dprintk("RPC: sending pipefs MOUNT notification for net %x%s\n", + net->ns.inum, NET_NAME(net)); mutex_lock(&sn->pipefs_sb_lock); sn->pipefs_sb = sb; err = blocking_notifier_call_chain(&rpc_pipefs_notifier_list, @@ -1462,8 +1462,8 @@ static void rpc_kill_sb(struct super_block *sb) goto out; } sn->pipefs_sb = NULL; - dprintk("RPC: sending pipefs UMOUNT notification for net %p%s\n", - net, NET_NAME(net)); + dprintk("RPC: sending pipefs UMOUNT notification for net %x%s\n", + net->ns.inum, NET_NAME(net)); blocking_notifier_call_chain(&rpc_pipefs_notifier_list, RPC_PIPEFS_UMOUNT, sb); diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index ea0676f199c8..c526f8fb37c9 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -216,9 +216,9 @@ static void rpcb_set_local(struct net *net, struct rpc_clnt *clnt, smp_wmb(); sn->rpcb_users = 1; dprintk("RPC: created new rpcb local clients (rpcb_local_clnt: " - "%p, rpcb_local_clnt4: %p) for net %p%s\n", - sn->rpcb_local_clnt, sn->rpcb_local_clnt4, - net, (net == &init_net) ? " (init_net)" : ""); + "%p, rpcb_local_clnt4: %p) for net %x%s\n", + sn->rpcb_local_clnt, sn->rpcb_local_clnt4, + net->ns.inum, (net == &init_net) ? " (init_net)" : ""); } /* diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 0cc83839c13c..b1b49edd7c4d 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -44,7 +44,7 @@ static mempool_t *rpc_buffer_mempool __read_mostly; static void rpc_async_schedule(struct work_struct *); static void rpc_release_task(struct rpc_task *task); -static void __rpc_queue_timer_fn(unsigned long ptr); +static void __rpc_queue_timer_fn(struct timer_list *t); /* * RPC tasks sit here while waiting for conditions to improve. @@ -228,7 +228,7 @@ static void __rpc_init_priority_wait_queue(struct rpc_wait_queue *queue, const c queue->maxpriority = nr_queues - 1; rpc_reset_waitqueue_priority(queue); queue->qlen = 0; - setup_timer(&queue->timer_list.timer, __rpc_queue_timer_fn, (unsigned long)queue); + timer_setup(&queue->timer_list.timer, __rpc_queue_timer_fn, 0); INIT_LIST_HEAD(&queue->timer_list.list); rpc_assign_waitqueue_name(queue, qname); } @@ -274,10 +274,9 @@ static inline void rpc_task_set_debuginfo(struct rpc_task *task) static void rpc_set_active(struct rpc_task *task) { - trace_rpc_task_begin(task->tk_client, task, NULL); - rpc_task_set_debuginfo(task); set_bit(RPC_TASK_ACTIVE, &task->tk_runstate); + trace_rpc_task_begin(task->tk_client, task, NULL); } /* @@ -635,9 +634,9 @@ void rpc_wake_up_status(struct rpc_wait_queue *queue, int status) } EXPORT_SYMBOL_GPL(rpc_wake_up_status); -static void __rpc_queue_timer_fn(unsigned long ptr) +static void __rpc_queue_timer_fn(struct timer_list *t) { - struct rpc_wait_queue *queue = (struct rpc_wait_queue *)ptr; + struct rpc_wait_queue *queue = from_timer(queue, t, timer_list.timer); struct rpc_task *task, *n; unsigned long expires, now, timeo; diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index c73de181467a..56f9eff74150 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -65,10 +65,13 @@ err_proc: static __net_exit void sunrpc_exit_net(struct net *net) { + struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); + rpc_pipefs_exit_net(net); unix_gid_cache_destroy(net); ip_map_cache_destroy(net); rpc_proc_exit(net); + WARN_ON_ONCE(!list_empty(&sn->all_clients)); } static struct pernet_operations sunrpc_net_ops = { diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index aa04666f929d..387cc4add6f6 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -50,7 +50,7 @@ EXPORT_SYMBOL_GPL(svc_pool_map); static DEFINE_MUTEX(svc_pool_map_mutex);/* protects svc_pool_map.count only */ static int -param_set_pool_mode(const char *val, struct kernel_param *kp) +param_set_pool_mode(const char *val, const struct kernel_param *kp) { int *ip = (int *)kp->arg; struct svc_pool_map *m = &svc_pool_map; @@ -80,7 +80,7 @@ out: } static int -param_get_pool_mode(char *buf, struct kernel_param *kp) +param_get_pool_mode(char *buf, const struct kernel_param *kp) { int *ip = (int *)kp->arg; @@ -455,7 +455,7 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, serv->sv_xdrsize = xdrsize; INIT_LIST_HEAD(&serv->sv_tempsocks); INIT_LIST_HEAD(&serv->sv_permsocks); - init_timer(&serv->sv_temptimer); + timer_setup(&serv->sv_temptimer, NULL, 0); spin_lock_init(&serv->sv_lock); __svc_init_bc(serv); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index d16a8b423c20..e8e0831229cf 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -28,7 +28,7 @@ module_param(svc_rpc_per_connection_limit, uint, 0644); static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt); static int svc_deferred_recv(struct svc_rqst *rqstp); static struct cache_deferred_req *svc_defer(struct cache_req *req); -static void svc_age_temp_xprts(unsigned long closure); +static void svc_age_temp_xprts(struct timer_list *t); static void svc_delete_xprt(struct svc_xprt *xprt); /* apparently the "standard" is that clients close @@ -250,9 +250,9 @@ void svc_add_new_perm_xprt(struct svc_serv *serv, struct svc_xprt *new) svc_xprt_received(new); } -int _svc_create_xprt(struct svc_serv *serv, const char *xprt_name, - struct net *net, const int family, - const unsigned short port, int flags) +static int _svc_create_xprt(struct svc_serv *serv, const char *xprt_name, + struct net *net, const int family, + const unsigned short port, int flags) { struct svc_xprt_class *xcl; @@ -380,7 +380,6 @@ void svc_xprt_do_enqueue(struct svc_xprt *xprt) struct svc_pool *pool; struct svc_rqst *rqstp = NULL; int cpu; - bool queued = false; if (!svc_xprt_has_something_to_do(xprt)) goto out; @@ -401,58 +400,25 @@ void svc_xprt_do_enqueue(struct svc_xprt *xprt) atomic_long_inc(&pool->sp_stats.packets); -redo_search: + dprintk("svc: transport %p put into queue\n", xprt); + spin_lock_bh(&pool->sp_lock); + list_add_tail(&xprt->xpt_ready, &pool->sp_sockets); + pool->sp_stats.sockets_queued++; + spin_unlock_bh(&pool->sp_lock); + /* find a thread for this xprt */ rcu_read_lock(); list_for_each_entry_rcu(rqstp, &pool->sp_all_threads, rq_all) { - /* Do a lockless check first */ - if (test_bit(RQ_BUSY, &rqstp->rq_flags)) + if (test_and_set_bit(RQ_BUSY, &rqstp->rq_flags)) continue; - - /* - * Once the xprt has been queued, it can only be dequeued by - * the task that intends to service it. All we can do at that - * point is to try to wake this thread back up so that it can - * do so. - */ - if (!queued) { - spin_lock_bh(&rqstp->rq_lock); - if (test_and_set_bit(RQ_BUSY, &rqstp->rq_flags)) { - /* already busy, move on... */ - spin_unlock_bh(&rqstp->rq_lock); - continue; - } - - /* this one will do */ - rqstp->rq_xprt = xprt; - svc_xprt_get(xprt); - spin_unlock_bh(&rqstp->rq_lock); - } - rcu_read_unlock(); - atomic_long_inc(&pool->sp_stats.threads_woken); wake_up_process(rqstp->rq_task); - put_cpu(); - goto out; - } - rcu_read_unlock(); - - /* - * We didn't find an idle thread to use, so we need to queue the xprt. - * Do so and then search again. If we find one, we can't hook this one - * up to it directly but we can wake the thread up in the hopes that it - * will pick it up once it searches for a xprt to service. - */ - if (!queued) { - queued = true; - dprintk("svc: transport %p put into queue\n", xprt); - spin_lock_bh(&pool->sp_lock); - list_add_tail(&xprt->xpt_ready, &pool->sp_sockets); - pool->sp_stats.sockets_queued++; - spin_unlock_bh(&pool->sp_lock); - goto redo_search; + goto out_unlock; } + set_bit(SP_CONGESTED, &pool->sp_flags); rqstp = NULL; +out_unlock: + rcu_read_unlock(); put_cpu(); out: trace_svc_xprt_do_enqueue(xprt, rqstp); @@ -721,38 +687,25 @@ rqst_should_sleep(struct svc_rqst *rqstp) static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout) { - struct svc_xprt *xprt; struct svc_pool *pool = rqstp->rq_pool; long time_left = 0; /* rq_xprt should be clear on entry */ WARN_ON_ONCE(rqstp->rq_xprt); - /* Normally we will wait up to 5 seconds for any required - * cache information to be provided. - */ - rqstp->rq_chandle.thread_wait = 5*HZ; - - xprt = svc_xprt_dequeue(pool); - if (xprt) { - rqstp->rq_xprt = xprt; - - /* As there is a shortage of threads and this request - * had to be queued, don't allow the thread to wait so - * long for cache updates. - */ - rqstp->rq_chandle.thread_wait = 1*HZ; - clear_bit(SP_TASK_PENDING, &pool->sp_flags); - return xprt; - } + rqstp->rq_xprt = svc_xprt_dequeue(pool); + if (rqstp->rq_xprt) + goto out_found; /* * We have to be able to interrupt this wait * to bring down the daemons ... */ set_current_state(TASK_INTERRUPTIBLE); + smp_mb__before_atomic(); + clear_bit(SP_CONGESTED, &pool->sp_flags); clear_bit(RQ_BUSY, &rqstp->rq_flags); - smp_mb(); + smp_mb__after_atomic(); if (likely(rqst_should_sleep(rqstp))) time_left = schedule_timeout(timeout); @@ -761,13 +714,11 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout) try_to_freeze(); - spin_lock_bh(&rqstp->rq_lock); set_bit(RQ_BUSY, &rqstp->rq_flags); - spin_unlock_bh(&rqstp->rq_lock); - - xprt = rqstp->rq_xprt; - if (xprt != NULL) - return xprt; + smp_mb__after_atomic(); + rqstp->rq_xprt = svc_xprt_dequeue(pool); + if (rqstp->rq_xprt) + goto out_found; if (!time_left) atomic_long_inc(&pool->sp_stats.threads_timedout); @@ -775,6 +726,15 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout) if (signalled() || kthread_should_stop()) return ERR_PTR(-EINTR); return ERR_PTR(-EAGAIN); +out_found: + /* Normally we will wait up to 5 seconds for any required + * cache information to be provided. + */ + if (!test_bit(SP_CONGESTED, &pool->sp_flags)) + rqstp->rq_chandle.thread_wait = 5*HZ; + else + rqstp->rq_chandle.thread_wait = 1*HZ; + return rqstp->rq_xprt; } static void svc_add_new_temp_xprt(struct svc_serv *serv, struct svc_xprt *newxpt) @@ -785,8 +745,7 @@ static void svc_add_new_temp_xprt(struct svc_serv *serv, struct svc_xprt *newxpt serv->sv_tmpcnt++; if (serv->sv_temptimer.function == NULL) { /* setup timer to age temp transports */ - setup_timer(&serv->sv_temptimer, svc_age_temp_xprts, - (unsigned long)serv); + serv->sv_temptimer.function = (TIMER_FUNC_TYPE)svc_age_temp_xprts; mod_timer(&serv->sv_temptimer, jiffies + svc_conn_age_period * HZ); } @@ -960,9 +919,9 @@ out: * Timer function to close old temporary transports, using * a mark-and-sweep algorithm. */ -static void svc_age_temp_xprts(unsigned long closure) +static void svc_age_temp_xprts(struct timer_list *t) { - struct svc_serv *serv = (struct svc_serv *)closure; + struct svc_serv *serv = from_timer(serv, t, sv_temptimer); struct svc_xprt *xprt; struct list_head *le, *next; diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 898485e3ece4..333b9d697ae5 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -696,9 +696,9 @@ xprt_schedule_autodisconnect(struct rpc_xprt *xprt) } static void -xprt_init_autodisconnect(unsigned long data) +xprt_init_autodisconnect(struct timer_list *t) { - struct rpc_xprt *xprt = (struct rpc_xprt *)data; + struct rpc_xprt *xprt = from_timer(xprt, t, timer); spin_lock(&xprt->transport_lock); if (!list_empty(&xprt->recv)) @@ -1139,6 +1139,7 @@ void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task) case -EAGAIN: xprt_add_backlog(xprt, task); dprintk("RPC: waiting for request slot\n"); + /* fall through */ default: task->tk_status = -EAGAIN; } @@ -1422,10 +1423,9 @@ found: xprt->idle_timeout = 0; INIT_WORK(&xprt->task_cleanup, xprt_autoclose); if (xprt_has_timer(xprt)) - setup_timer(&xprt->timer, xprt_init_autodisconnect, - (unsigned long)xprt); + timer_setup(&xprt->timer, xprt_init_autodisconnect, 0); else - init_timer(&xprt->timer); + timer_setup(&xprt->timer, NULL, 0); if (strlen(args->servername) > RPC_MAXNETNAMELEN) { xprt_destroy(xprt); diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index 823a781ec89c..8b818bb3518a 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -43,7 +43,7 @@ static int rpcrdma_bc_setup_rqst(struct rpcrdma_xprt *r_xprt, req = rpcrdma_create_req(r_xprt); if (IS_ERR(req)) return PTR_ERR(req); - req->rl_backchannel = true; + __set_bit(RPCRDMA_REQ_F_BACKCHANNEL, &req->rl_flags); rb = rpcrdma_alloc_regbuf(RPCRDMA_HDRBUF_SIZE, DMA_TO_DEVICE, GFP_KERNEL); @@ -223,8 +223,8 @@ int rpcrdma_bc_marshal_reply(struct rpc_rqst *rqst) *p++ = xdr_zero; *p = xdr_zero; - if (!rpcrdma_prepare_send_sges(&r_xprt->rx_ia, req, RPCRDMA_HDRLEN_MIN, - &rqst->rq_snd_buf, rpcrdma_noch)) + if (rpcrdma_prepare_send_sges(r_xprt, req, RPCRDMA_HDRLEN_MIN, + &rqst->rq_snd_buf, rpcrdma_noch)) return -EIO; return 0; } diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index fa759dd2b0f3..29fc84c7ff98 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -306,28 +306,9 @@ out_reset: } } -/* Use a slow, safe mechanism to invalidate all memory regions - * that were registered for "req". - */ -static void -fmr_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, - bool sync) -{ - struct rpcrdma_mw *mw; - - while (!list_empty(&req->rl_registered)) { - mw = rpcrdma_pop_mw(&req->rl_registered); - if (sync) - fmr_op_recover_mr(mw); - else - rpcrdma_defer_mr_recovery(mw); - } -} - const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops = { .ro_map = fmr_op_map, .ro_unmap_sync = fmr_op_unmap_sync, - .ro_unmap_safe = fmr_op_unmap_safe, .ro_recover_mr = fmr_op_recover_mr, .ro_open = fmr_op_open, .ro_maxpages = fmr_op_maxpages, diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 35d7517ef0e6..773e66e10a15 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -420,7 +420,6 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE : IB_ACCESS_REMOTE_READ; - rpcrdma_set_signaled(&r_xprt->rx_ep, ®_wr->wr); rc = ib_post_send(ia->ri_id->qp, ®_wr->wr, &bad_wr); if (rc) goto out_senderr; @@ -508,12 +507,6 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct list_head *mws) f->fr_cqe.done = frwr_wc_localinv_wake; reinit_completion(&f->fr_linv_done); - /* Initialize CQ count, since there is always a signaled - * WR being posted here. The new cqcount depends on how - * many SQEs are about to be consumed. - */ - rpcrdma_init_cqcount(&r_xprt->rx_ep, count); - /* Transport disconnect drains the receive CQ before it * replaces the QP. The RPC reply handler won't call us * unless ri_id->qp is a valid pointer. @@ -546,7 +539,6 @@ reset_mrs: /* Find and reset the MRs in the LOCAL_INV WRs that did not * get posted. */ - rpcrdma_init_cqcount(&r_xprt->rx_ep, -count); while (bad_wr) { f = container_of(bad_wr, struct rpcrdma_frmr, fr_invwr); @@ -559,28 +551,9 @@ reset_mrs: goto unmap; } -/* Use a slow, safe mechanism to invalidate all memory regions - * that were registered for "req". - */ -static void -frwr_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, - bool sync) -{ - struct rpcrdma_mw *mw; - - while (!list_empty(&req->rl_registered)) { - mw = rpcrdma_pop_mw(&req->rl_registered); - if (sync) - frwr_op_recover_mr(mw); - else - rpcrdma_defer_mr_recovery(mw); - } -} - const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops = { .ro_map = frwr_op_map, .ro_unmap_sync = frwr_op_unmap_sync, - .ro_unmap_safe = frwr_op_unmap_safe, .ro_recover_mr = frwr_op_recover_mr, .ro_open = frwr_op_open, .ro_maxpages = frwr_op_maxpages, diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index f1889f4d4803..ed34dc0f144c 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -1,4 +1,5 @@ /* + * Copyright (c) 2014-2017 Oracle. All rights reserved. * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved. * * This software is available to you under a choice of one of two @@ -75,11 +76,11 @@ static unsigned int rpcrdma_max_call_header_size(unsigned int maxsegs) /* Maximum Read list size */ maxsegs += 2; /* segment for head and tail buffers */ - size = maxsegs * sizeof(struct rpcrdma_read_chunk); + size = maxsegs * rpcrdma_readchunk_maxsz * sizeof(__be32); /* Minimal Read chunk size */ size += sizeof(__be32); /* segment count */ - size += sizeof(struct rpcrdma_segment); + size += rpcrdma_segment_maxsz * sizeof(__be32); size += sizeof(__be32); /* list discriminator */ dprintk("RPC: %s: max call header size = %u\n", @@ -102,7 +103,7 @@ static unsigned int rpcrdma_max_reply_header_size(unsigned int maxsegs) /* Maximum Write list size */ maxsegs += 2; /* segment for head and tail buffers */ size = sizeof(__be32); /* segment count */ - size += maxsegs * sizeof(struct rpcrdma_segment); + size += maxsegs * rpcrdma_segment_maxsz * sizeof(__be32); size += sizeof(__be32); /* list discriminator */ dprintk("RPC: %s: max reply header size = %u\n", @@ -511,27 +512,60 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, return 0; } -/* Prepare the RPC-over-RDMA header SGE. +/** + * rpcrdma_unmap_sendctx - DMA-unmap Send buffers + * @sc: sendctx containing SGEs to unmap + * + */ +void +rpcrdma_unmap_sendctx(struct rpcrdma_sendctx *sc) +{ + struct rpcrdma_ia *ia = &sc->sc_xprt->rx_ia; + struct ib_sge *sge; + unsigned int count; + + dprintk("RPC: %s: unmapping %u sges for sc=%p\n", + __func__, sc->sc_unmap_count, sc); + + /* The first two SGEs contain the transport header and + * the inline buffer. These are always left mapped so + * they can be cheaply re-used. + */ + sge = &sc->sc_sges[2]; + for (count = sc->sc_unmap_count; count; ++sge, --count) + ib_dma_unmap_page(ia->ri_device, + sge->addr, sge->length, DMA_TO_DEVICE); + + if (test_and_clear_bit(RPCRDMA_REQ_F_TX_RESOURCES, &sc->sc_req->rl_flags)) { + smp_mb__after_atomic(); + wake_up_bit(&sc->sc_req->rl_flags, RPCRDMA_REQ_F_TX_RESOURCES); + } +} + +/* Prepare an SGE for the RPC-over-RDMA transport header. */ static bool rpcrdma_prepare_hdr_sge(struct rpcrdma_ia *ia, struct rpcrdma_req *req, u32 len) { + struct rpcrdma_sendctx *sc = req->rl_sendctx; struct rpcrdma_regbuf *rb = req->rl_rdmabuf; - struct ib_sge *sge = &req->rl_send_sge[0]; + struct ib_sge *sge = sc->sc_sges; - if (unlikely(!rpcrdma_regbuf_is_mapped(rb))) { - if (!__rpcrdma_dma_map_regbuf(ia, rb)) - return false; - sge->addr = rdmab_addr(rb); - sge->lkey = rdmab_lkey(rb); - } + if (!rpcrdma_dma_map_regbuf(ia, rb)) + goto out_regbuf; + sge->addr = rdmab_addr(rb); sge->length = len; + sge->lkey = rdmab_lkey(rb); ib_dma_sync_single_for_device(rdmab_device(rb), sge->addr, sge->length, DMA_TO_DEVICE); - req->rl_send_wr.num_sge++; + sc->sc_wr.num_sge++; return true; + +out_regbuf: + pr_err("rpcrdma: failed to DMA map a Send buffer\n"); + return false; } /* Prepare the Send SGEs. The head and tail iovec, and each entry @@ -541,10 +575,11 @@ static bool rpcrdma_prepare_msg_sges(struct rpcrdma_ia *ia, struct rpcrdma_req *req, struct xdr_buf *xdr, enum rpcrdma_chunktype rtype) { + struct rpcrdma_sendctx *sc = req->rl_sendctx; unsigned int sge_no, page_base, len, remaining; struct rpcrdma_regbuf *rb = req->rl_sendbuf; struct ib_device *device = ia->ri_device; - struct ib_sge *sge = req->rl_send_sge; + struct ib_sge *sge = sc->sc_sges; u32 lkey = ia->ri_pd->local_dma_lkey; struct page *page, **ppages; @@ -552,7 +587,7 @@ rpcrdma_prepare_msg_sges(struct rpcrdma_ia *ia, struct rpcrdma_req *req, * DMA-mapped. Sync the content that has changed. */ if (!rpcrdma_dma_map_regbuf(ia, rb)) - return false; + goto out_regbuf; sge_no = 1; sge[sge_no].addr = rdmab_addr(rb); sge[sge_no].length = xdr->head[0].iov_len; @@ -607,7 +642,7 @@ rpcrdma_prepare_msg_sges(struct rpcrdma_ia *ia, struct rpcrdma_req *req, sge[sge_no].length = len; sge[sge_no].lkey = lkey; - req->rl_mapped_sges++; + sc->sc_unmap_count++; ppages++; remaining -= len; page_base = 0; @@ -633,56 +668,61 @@ map_tail: goto out_mapping_err; sge[sge_no].length = len; sge[sge_no].lkey = lkey; - req->rl_mapped_sges++; + sc->sc_unmap_count++; } out: - req->rl_send_wr.num_sge = sge_no + 1; + sc->sc_wr.num_sge += sge_no; + if (sc->sc_unmap_count) + __set_bit(RPCRDMA_REQ_F_TX_RESOURCES, &req->rl_flags); return true; +out_regbuf: + pr_err("rpcrdma: failed to DMA map a Send buffer\n"); + return false; + out_mapping_overflow: + rpcrdma_unmap_sendctx(sc); pr_err("rpcrdma: too many Send SGEs (%u)\n", sge_no); return false; out_mapping_err: + rpcrdma_unmap_sendctx(sc); pr_err("rpcrdma: Send mapping error\n"); return false; } -bool -rpcrdma_prepare_send_sges(struct rpcrdma_ia *ia, struct rpcrdma_req *req, - u32 hdrlen, struct xdr_buf *xdr, - enum rpcrdma_chunktype rtype) +/** + * rpcrdma_prepare_send_sges - Construct SGEs for a Send WR + * @r_xprt: controlling transport + * @req: context of RPC Call being marshalled + * @hdrlen: size of transport header, in bytes + * @xdr: xdr_buf containing RPC Call + * @rtype: chunk type being encoded + * + * Returns 0 on success; otherwise a negative errno is returned. + */ +int +rpcrdma_prepare_send_sges(struct rpcrdma_xprt *r_xprt, + struct rpcrdma_req *req, u32 hdrlen, + struct xdr_buf *xdr, enum rpcrdma_chunktype rtype) { - req->rl_send_wr.num_sge = 0; - req->rl_mapped_sges = 0; - - if (!rpcrdma_prepare_hdr_sge(ia, req, hdrlen)) - goto out_map; + req->rl_sendctx = rpcrdma_sendctx_get_locked(&r_xprt->rx_buf); + if (!req->rl_sendctx) + return -ENOBUFS; + req->rl_sendctx->sc_wr.num_sge = 0; + req->rl_sendctx->sc_unmap_count = 0; + req->rl_sendctx->sc_req = req; + __clear_bit(RPCRDMA_REQ_F_TX_RESOURCES, &req->rl_flags); + + if (!rpcrdma_prepare_hdr_sge(&r_xprt->rx_ia, req, hdrlen)) + return -EIO; if (rtype != rpcrdma_areadch) - if (!rpcrdma_prepare_msg_sges(ia, req, xdr, rtype)) - goto out_map; - - return true; - -out_map: - pr_err("rpcrdma: failed to DMA map a Send buffer\n"); - return false; -} - -void -rpcrdma_unmap_sges(struct rpcrdma_ia *ia, struct rpcrdma_req *req) -{ - struct ib_device *device = ia->ri_device; - struct ib_sge *sge; - int count; + if (!rpcrdma_prepare_msg_sges(&r_xprt->rx_ia, req, xdr, rtype)) + return -EIO; - sge = &req->rl_send_sge[2]; - for (count = req->rl_mapped_sges; count--; sge++) - ib_dma_unmap_page(device, sge->addr, sge->length, - DMA_TO_DEVICE); - req->rl_mapped_sges = 0; + return 0; } /** @@ -833,12 +873,10 @@ rpcrdma_marshal_req(struct rpcrdma_xprt *r_xprt, struct rpc_rqst *rqst) transfertypes[rtype], transfertypes[wtype], xdr_stream_pos(xdr)); - if (!rpcrdma_prepare_send_sges(&r_xprt->rx_ia, req, - xdr_stream_pos(xdr), - &rqst->rq_snd_buf, rtype)) { - ret = -EIO; + ret = rpcrdma_prepare_send_sges(r_xprt, req, xdr_stream_pos(xdr), + &rqst->rq_snd_buf, rtype); + if (ret) goto out_err; - } return 0; out_err: @@ -970,14 +1008,13 @@ rpcrdma_mark_remote_invalidation(struct list_head *mws, * straightforward to check the RPC header's direction field. */ static bool -rpcrdma_is_bcall(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep, - __be32 xid, __be32 proc) +rpcrdma_is_bcall(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep) #if defined(CONFIG_SUNRPC_BACKCHANNEL) { struct xdr_stream *xdr = &rep->rr_stream; __be32 *p; - if (proc != rdma_msg) + if (rep->rr_proc != rdma_msg) return false; /* Peek at stream contents without advancing. */ @@ -992,7 +1029,7 @@ rpcrdma_is_bcall(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep, return false; /* RPC header */ - if (*p++ != xid) + if (*p++ != rep->rr_xid) return false; if (*p != cpu_to_be32(RPC_CALL)) return false; @@ -1212,105 +1249,170 @@ rpcrdma_decode_error(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep, return -EREMOTEIO; } +/* Perform XID lookup, reconstruction of the RPC reply, and + * RPC completion while holding the transport lock to ensure + * the rep, rqst, and rq_task pointers remain stable. + */ +void rpcrdma_complete_rqst(struct rpcrdma_rep *rep) +{ + struct rpcrdma_xprt *r_xprt = rep->rr_rxprt; + struct rpc_xprt *xprt = &r_xprt->rx_xprt; + struct rpc_rqst *rqst = rep->rr_rqst; + unsigned long cwnd; + int status; + + xprt->reestablish_timeout = 0; + + switch (rep->rr_proc) { + case rdma_msg: + status = rpcrdma_decode_msg(r_xprt, rep, rqst); + break; + case rdma_nomsg: + status = rpcrdma_decode_nomsg(r_xprt, rep); + break; + case rdma_error: + status = rpcrdma_decode_error(r_xprt, rep, rqst); + break; + default: + status = -EIO; + } + if (status < 0) + goto out_badheader; + +out: + spin_lock(&xprt->recv_lock); + cwnd = xprt->cwnd; + xprt->cwnd = r_xprt->rx_buf.rb_credits << RPC_CWNDSHIFT; + if (xprt->cwnd > cwnd) + xprt_release_rqst_cong(rqst->rq_task); + + xprt_complete_rqst(rqst->rq_task, status); + xprt_unpin_rqst(rqst); + spin_unlock(&xprt->recv_lock); + return; + +/* If the incoming reply terminated a pending RPC, the next + * RPC call will post a replacement receive buffer as it is + * being marshaled. + */ +out_badheader: + dprintk("RPC: %5u %s: invalid rpcrdma reply (type %u)\n", + rqst->rq_task->tk_pid, __func__, be32_to_cpu(rep->rr_proc)); + r_xprt->rx_stats.bad_reply_count++; + status = -EIO; + goto out; +} + +void rpcrdma_release_rqst(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) +{ + /* Invalidate and unmap the data payloads before waking + * the waiting application. This guarantees the memory + * regions are properly fenced from the server before the + * application accesses the data. It also ensures proper + * send flow control: waking the next RPC waits until this + * RPC has relinquished all its Send Queue entries. + */ + if (!list_empty(&req->rl_registered)) + r_xprt->rx_ia.ri_ops->ro_unmap_sync(r_xprt, + &req->rl_registered); + + /* Ensure that any DMA mapped pages associated with + * the Send of the RPC Call have been unmapped before + * allowing the RPC to complete. This protects argument + * memory not controlled by the RPC client from being + * re-used before we're done with it. + */ + if (test_bit(RPCRDMA_REQ_F_TX_RESOURCES, &req->rl_flags)) { + r_xprt->rx_stats.reply_waits_for_send++; + out_of_line_wait_on_bit(&req->rl_flags, + RPCRDMA_REQ_F_TX_RESOURCES, + bit_wait, + TASK_UNINTERRUPTIBLE); + } +} + +/* Reply handling runs in the poll worker thread. Anything that + * might wait is deferred to a separate workqueue. + */ +void rpcrdma_deferred_completion(struct work_struct *work) +{ + struct rpcrdma_rep *rep = + container_of(work, struct rpcrdma_rep, rr_work); + struct rpcrdma_req *req = rpcr_to_rdmar(rep->rr_rqst); + + rpcrdma_mark_remote_invalidation(&req->rl_registered, rep); + rpcrdma_release_rqst(rep->rr_rxprt, req); + rpcrdma_complete_rqst(rep); +} + /* Process received RPC/RDMA messages. * * Errors must result in the RPC task either being awakened, or * allowed to timeout, to discover the errors at that time. */ -void -rpcrdma_reply_handler(struct work_struct *work) +void rpcrdma_reply_handler(struct rpcrdma_rep *rep) { - struct rpcrdma_rep *rep = - container_of(work, struct rpcrdma_rep, rr_work); struct rpcrdma_xprt *r_xprt = rep->rr_rxprt; struct rpc_xprt *xprt = &r_xprt->rx_xprt; - struct xdr_stream *xdr = &rep->rr_stream; + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; struct rpcrdma_req *req; struct rpc_rqst *rqst; - __be32 *p, xid, vers, proc; - unsigned long cwnd; - int status; + u32 credits; + __be32 *p; dprintk("RPC: %s: incoming rep %p\n", __func__, rep); if (rep->rr_hdrbuf.head[0].iov_len == 0) goto out_badstatus; - xdr_init_decode(xdr, &rep->rr_hdrbuf, + xdr_init_decode(&rep->rr_stream, &rep->rr_hdrbuf, rep->rr_hdrbuf.head[0].iov_base); /* Fixed transport header fields */ - p = xdr_inline_decode(xdr, 4 * sizeof(*p)); + p = xdr_inline_decode(&rep->rr_stream, 4 * sizeof(*p)); if (unlikely(!p)) goto out_shortreply; - xid = *p++; - vers = *p++; - p++; /* credits */ - proc = *p++; + rep->rr_xid = *p++; + rep->rr_vers = *p++; + credits = be32_to_cpu(*p++); + rep->rr_proc = *p++; + + if (rep->rr_vers != rpcrdma_version) + goto out_badversion; - if (rpcrdma_is_bcall(r_xprt, rep, xid, proc)) + if (rpcrdma_is_bcall(r_xprt, rep)) return; /* Match incoming rpcrdma_rep to an rpcrdma_req to * get context for handling any incoming chunks. */ spin_lock(&xprt->recv_lock); - rqst = xprt_lookup_rqst(xprt, xid); + rqst = xprt_lookup_rqst(xprt, rep->rr_xid); if (!rqst) goto out_norqst; xprt_pin_rqst(rqst); + + if (credits == 0) + credits = 1; /* don't deadlock */ + else if (credits > buf->rb_max_requests) + credits = buf->rb_max_requests; + buf->rb_credits = credits; + spin_unlock(&xprt->recv_lock); + req = rpcr_to_rdmar(rqst); req->rl_reply = rep; + rep->rr_rqst = rqst; + clear_bit(RPCRDMA_REQ_F_PENDING, &req->rl_flags); dprintk("RPC: %s: reply %p completes request %p (xid 0x%08x)\n", - __func__, rep, req, be32_to_cpu(xid)); - - /* Invalidate and unmap the data payloads before waking the - * waiting application. This guarantees the memory regions - * are properly fenced from the server before the application - * accesses the data. It also ensures proper send flow control: - * waking the next RPC waits until this RPC has relinquished - * all its Send Queue entries. - */ - if (!list_empty(&req->rl_registered)) { - rpcrdma_mark_remote_invalidation(&req->rl_registered, rep); - r_xprt->rx_ia.ri_ops->ro_unmap_sync(r_xprt, - &req->rl_registered); - } - - xprt->reestablish_timeout = 0; - if (vers != rpcrdma_version) - goto out_badversion; + __func__, rep, req, be32_to_cpu(rep->rr_xid)); - switch (proc) { - case rdma_msg: - status = rpcrdma_decode_msg(r_xprt, rep, rqst); - break; - case rdma_nomsg: - status = rpcrdma_decode_nomsg(r_xprt, rep); - break; - case rdma_error: - status = rpcrdma_decode_error(r_xprt, rep, rqst); - break; - default: - status = -EIO; - } - if (status < 0) - goto out_badheader; - -out: - spin_lock(&xprt->recv_lock); - cwnd = xprt->cwnd; - xprt->cwnd = atomic_read(&r_xprt->rx_buf.rb_credits) << RPC_CWNDSHIFT; - if (xprt->cwnd > cwnd) - xprt_release_rqst_cong(rqst->rq_task); - - xprt_complete_rqst(rqst->rq_task, status); - xprt_unpin_rqst(rqst); - spin_unlock(&xprt->recv_lock); - dprintk("RPC: %s: xprt_complete_rqst(0x%p, 0x%p, %d)\n", - __func__, xprt, rqst, status); + if (list_empty(&req->rl_registered) && + !test_bit(RPCRDMA_REQ_F_TX_RESOURCES, &req->rl_flags)) + rpcrdma_complete_rqst(rep); + else + queue_work(rpcrdma_receive_wq, &rep->rr_work); return; out_badstatus: @@ -1321,37 +1423,22 @@ out_badstatus: } return; -/* If the incoming reply terminated a pending RPC, the next - * RPC call will post a replacement receive buffer as it is - * being marshaled. - */ out_badversion: dprintk("RPC: %s: invalid version %d\n", - __func__, be32_to_cpu(vers)); - status = -EIO; - r_xprt->rx_stats.bad_reply_count++; - goto out; - -out_badheader: - dprintk("RPC: %5u %s: invalid rpcrdma reply (type %u)\n", - rqst->rq_task->tk_pid, __func__, be32_to_cpu(proc)); - r_xprt->rx_stats.bad_reply_count++; - status = -EIO; - goto out; + __func__, be32_to_cpu(rep->rr_vers)); + goto repost; -/* The req was still available, but by the time the recv_lock - * was acquired, the rqst and task had been released. Thus the RPC - * has already been terminated. +/* The RPC transaction has already been terminated, or the header + * is corrupt. */ out_norqst: spin_unlock(&xprt->recv_lock); dprintk("RPC: %s: no match for incoming xid 0x%08x\n", - __func__, be32_to_cpu(xid)); + __func__, be32_to_cpu(rep->rr_xid)); goto repost; out_shortreply: dprintk("RPC: %s: short/invalid reply\n", __func__); - goto repost; /* If no pending RPC transaction was matched, post a replacement * receive buffer before returning. diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index 992594b7cc6b..af7893501e40 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -133,6 +133,10 @@ static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma, if (ret) goto out_err; + /* Bump page refcnt so Send completion doesn't release + * the rq_buffer before all retransmits are complete. + */ + get_page(virt_to_page(rqst->rq_buffer)); ret = svc_rdma_post_send_wr(rdma, ctxt, 1, 0); if (ret) goto out_unmap; @@ -165,7 +169,6 @@ xprt_rdma_bc_allocate(struct rpc_task *task) return -EINVAL; } - /* svc_rdma_sendto releases this page */ page = alloc_page(RPCRDMA_DEF_GFP); if (!page) return -ENOMEM; @@ -184,6 +187,7 @@ xprt_rdma_bc_free(struct rpc_task *task) { struct rpc_rqst *rqst = task->tk_rqstp; + put_page(virt_to_page(rqst->rq_buffer)); kfree(rqst->rq_rbuffer); } diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 5caf8e722a11..46ec069150d5 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -290,6 +290,7 @@ static void qp_event_handler(struct ib_event *event, void *context) ib_event_msg(event->event), event->event, event->element.qp); set_bit(XPT_CLOSE, &xprt->xpt_flags); + svc_xprt_enqueue(xprt); break; } } @@ -322,8 +323,7 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags); if (test_bit(RDMAXPRT_CONN_PENDING, &xprt->sc_flags)) goto out; - svc_xprt_enqueue(&xprt->sc_xprt); - goto out; + goto out_enqueue; flushed: if (wc->status != IB_WC_WR_FLUSH_ERR) @@ -333,6 +333,8 @@ flushed: set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); svc_rdma_put_context(ctxt, 1); +out_enqueue: + svc_xprt_enqueue(&xprt->sc_xprt); out: svc_xprt_put(&xprt->sc_xprt); } @@ -358,6 +360,7 @@ void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc) if (unlikely(wc->status != IB_WC_SUCCESS)) { set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); + svc_xprt_enqueue(&xprt->sc_xprt); if (wc->status != IB_WC_WR_FLUSH_ERR) pr_err("svcrdma: Send: %s (%u/0x%x)\n", ib_wc_status_msg(wc->status), @@ -569,8 +572,10 @@ static int rdma_listen_handler(struct rdma_cm_id *cma_id, case RDMA_CM_EVENT_DEVICE_REMOVAL: dprintk("svcrdma: Device removal xprt=%p, cm_id=%p\n", xprt, cma_id); - if (xprt) + if (xprt) { set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); + svc_xprt_enqueue(&xprt->sc_xprt); + } break; default: diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index c84e2b644e13..646c24494ea7 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -1,4 +1,5 @@ /* + * Copyright (c) 2014-2017 Oracle. All rights reserved. * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved. * * This software is available to you under a choice of one of two @@ -678,16 +679,14 @@ xprt_rdma_free(struct rpc_task *task) struct rpc_rqst *rqst = task->tk_rqstp; struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(rqst->rq_xprt); struct rpcrdma_req *req = rpcr_to_rdmar(rqst); - struct rpcrdma_ia *ia = &r_xprt->rx_ia; - if (req->rl_backchannel) + if (test_bit(RPCRDMA_REQ_F_BACKCHANNEL, &req->rl_flags)) return; dprintk("RPC: %s: called on 0x%p\n", __func__, req->rl_reply); - if (!list_empty(&req->rl_registered)) - ia->ri_ops->ro_unmap_safe(r_xprt, req, !RPC_IS_ASYNC(task)); - rpcrdma_unmap_sges(ia, req); + if (test_bit(RPCRDMA_REQ_F_PENDING, &req->rl_flags)) + rpcrdma_release_rqst(r_xprt, req); rpcrdma_buffer_put(req); } @@ -728,7 +727,8 @@ xprt_rdma_send_request(struct rpc_task *task) /* On retransmit, remove any previously registered chunks */ if (unlikely(!list_empty(&req->rl_registered))) - r_xprt->rx_ia.ri_ops->ro_unmap_safe(r_xprt, req, false); + r_xprt->rx_ia.ri_ops->ro_unmap_sync(r_xprt, + &req->rl_registered); rc = rpcrdma_marshal_req(r_xprt, rqst); if (rc < 0) @@ -742,6 +742,7 @@ xprt_rdma_send_request(struct rpc_task *task) goto drop_connection; req->rl_connect_cookie = xprt->connect_cookie; + set_bit(RPCRDMA_REQ_F_PENDING, &req->rl_flags); if (rpcrdma_ep_post(&r_xprt->rx_ia, &r_xprt->rx_ep, req)) goto drop_connection; @@ -789,11 +790,13 @@ void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) r_xprt->rx_stats.failed_marshal_count, r_xprt->rx_stats.bad_reply_count, r_xprt->rx_stats.nomsg_call_count); - seq_printf(seq, "%lu %lu %lu %lu\n", + seq_printf(seq, "%lu %lu %lu %lu %lu %lu\n", r_xprt->rx_stats.mrs_recovered, r_xprt->rx_stats.mrs_orphaned, r_xprt->rx_stats.mrs_allocated, - r_xprt->rx_stats.local_inv_needed); + r_xprt->rx_stats.local_inv_needed, + r_xprt->rx_stats.empty_sendctx_q, + r_xprt->rx_stats.reply_waits_for_send); } static int diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 11a1fbf7e59e..710b3f77db82 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1,4 +1,5 @@ /* + * Copyright (c) 2014-2017 Oracle. All rights reserved. * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved. * * This software is available to you under a choice of one of two @@ -49,9 +50,10 @@ #include <linux/interrupt.h> #include <linux/slab.h> -#include <linux/prefetch.h> #include <linux/sunrpc/addr.h> #include <linux/sunrpc/svc_rdma.h> + +#include <asm-generic/barrier.h> #include <asm/bitops.h> #include <rdma/ib_cm.h> @@ -73,7 +75,7 @@ static void rpcrdma_create_mrs(struct rpcrdma_xprt *r_xprt); static void rpcrdma_destroy_mrs(struct rpcrdma_buffer *buf); static void rpcrdma_dma_unmap_regbuf(struct rpcrdma_regbuf *rb); -static struct workqueue_struct *rpcrdma_receive_wq __read_mostly; +struct workqueue_struct *rpcrdma_receive_wq __read_mostly; int rpcrdma_alloc_wq(void) @@ -126,30 +128,17 @@ rpcrdma_qp_async_error_upcall(struct ib_event *event, void *context) static void rpcrdma_wc_send(struct ib_cq *cq, struct ib_wc *wc) { + struct ib_cqe *cqe = wc->wr_cqe; + struct rpcrdma_sendctx *sc = + container_of(cqe, struct rpcrdma_sendctx, sc_cqe); + /* WARNING: Only wr_cqe and status are reliable at this point */ if (wc->status != IB_WC_SUCCESS && wc->status != IB_WC_WR_FLUSH_ERR) pr_err("rpcrdma: Send: %s (%u/0x%x)\n", ib_wc_status_msg(wc->status), wc->status, wc->vendor_err); -} - -/* Perform basic sanity checking to avoid using garbage - * to update the credit grant value. - */ -static void -rpcrdma_update_granted_credits(struct rpcrdma_rep *rep) -{ - struct rpcrdma_buffer *buffer = &rep->rr_rxprt->rx_buf; - __be32 *p = rep->rr_rdmabuf->rg_base; - u32 credits; - credits = be32_to_cpup(p + 2); - if (credits == 0) - credits = 1; /* don't deadlock */ - else if (credits > buffer->rb_max_requests) - credits = buffer->rb_max_requests; - - atomic_set(&buffer->rb_credits, credits); + rpcrdma_sendctx_put_locked(sc); } /** @@ -181,11 +170,8 @@ rpcrdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) rdmab_addr(rep->rr_rdmabuf), wc->byte_len, DMA_FROM_DEVICE); - if (wc->byte_len >= RPCRDMA_HDRLEN_ERR) - rpcrdma_update_granted_credits(rep); - out_schedule: - queue_work(rpcrdma_receive_wq, &rep->rr_work); + rpcrdma_reply_handler(rep); return; out_fail: @@ -295,7 +281,7 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event) case RDMA_CM_EVENT_DISCONNECTED: connstate = -ECONNABORTED; connected: - atomic_set(&xprt->rx_buf.rb_credits, 1); + xprt->rx_buf.rb_credits = 1; ep->rep_connected = connstate; rpcrdma_conn_func(ep); wake_up_all(&ep->rep_connect_wait); @@ -564,16 +550,15 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, ep->rep_attr.cap.max_recv_sge); /* set trigger for requesting send completion */ - ep->rep_cqinit = ep->rep_attr.cap.max_send_wr/2 - 1; - if (ep->rep_cqinit <= 2) - ep->rep_cqinit = 0; /* always signal? */ - rpcrdma_init_cqcount(ep, 0); + ep->rep_send_batch = min_t(unsigned int, RPCRDMA_MAX_SEND_BATCH, + cdata->max_requests >> 2); + ep->rep_send_count = ep->rep_send_batch; init_waitqueue_head(&ep->rep_connect_wait); INIT_DELAYED_WORK(&ep->rep_connect_worker, rpcrdma_connect_worker); sendcq = ib_alloc_cq(ia->ri_device, NULL, ep->rep_attr.cap.max_send_wr + 1, - 0, IB_POLL_SOFTIRQ); + 1, IB_POLL_WORKQUEUE); if (IS_ERR(sendcq)) { rc = PTR_ERR(sendcq); dprintk("RPC: %s: failed to create send CQ: %i\n", @@ -583,7 +568,7 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, recvcq = ib_alloc_cq(ia->ri_device, NULL, ep->rep_attr.cap.max_recv_wr + 1, - 0, IB_POLL_SOFTIRQ); + 0, IB_POLL_WORKQUEUE); if (IS_ERR(recvcq)) { rc = PTR_ERR(recvcq); dprintk("RPC: %s: failed to create recv CQ: %i\n", @@ -846,6 +831,168 @@ rpcrdma_ep_disconnect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) ib_drain_qp(ia->ri_id->qp); } +/* Fixed-size circular FIFO queue. This implementation is wait-free and + * lock-free. + * + * Consumer is the code path that posts Sends. This path dequeues a + * sendctx for use by a Send operation. Multiple consumer threads + * are serialized by the RPC transport lock, which allows only one + * ->send_request call at a time. + * + * Producer is the code path that handles Send completions. This path + * enqueues a sendctx that has been completed. Multiple producer + * threads are serialized by the ib_poll_cq() function. + */ + +/* rpcrdma_sendctxs_destroy() assumes caller has already quiesced + * queue activity, and ib_drain_qp has flushed all remaining Send + * requests. + */ +static void rpcrdma_sendctxs_destroy(struct rpcrdma_buffer *buf) +{ + unsigned long i; + + for (i = 0; i <= buf->rb_sc_last; i++) + kfree(buf->rb_sc_ctxs[i]); + kfree(buf->rb_sc_ctxs); +} + +static struct rpcrdma_sendctx *rpcrdma_sendctx_create(struct rpcrdma_ia *ia) +{ + struct rpcrdma_sendctx *sc; + + sc = kzalloc(sizeof(*sc) + + ia->ri_max_send_sges * sizeof(struct ib_sge), + GFP_KERNEL); + if (!sc) + return NULL; + + sc->sc_wr.wr_cqe = &sc->sc_cqe; + sc->sc_wr.sg_list = sc->sc_sges; + sc->sc_wr.opcode = IB_WR_SEND; + sc->sc_cqe.done = rpcrdma_wc_send; + return sc; +} + +static int rpcrdma_sendctxs_create(struct rpcrdma_xprt *r_xprt) +{ + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + struct rpcrdma_sendctx *sc; + unsigned long i; + + /* Maximum number of concurrent outstanding Send WRs. Capping + * the circular queue size stops Send Queue overflow by causing + * the ->send_request call to fail temporarily before too many + * Sends are posted. + */ + i = buf->rb_max_requests + RPCRDMA_MAX_BC_REQUESTS; + dprintk("RPC: %s: allocating %lu send_ctxs\n", __func__, i); + buf->rb_sc_ctxs = kcalloc(i, sizeof(sc), GFP_KERNEL); + if (!buf->rb_sc_ctxs) + return -ENOMEM; + + buf->rb_sc_last = i - 1; + for (i = 0; i <= buf->rb_sc_last; i++) { + sc = rpcrdma_sendctx_create(&r_xprt->rx_ia); + if (!sc) + goto out_destroy; + + sc->sc_xprt = r_xprt; + buf->rb_sc_ctxs[i] = sc; + } + + return 0; + +out_destroy: + rpcrdma_sendctxs_destroy(buf); + return -ENOMEM; +} + +/* The sendctx queue is not guaranteed to have a size that is a + * power of two, thus the helpers in circ_buf.h cannot be used. + * The other option is to use modulus (%), which can be expensive. + */ +static unsigned long rpcrdma_sendctx_next(struct rpcrdma_buffer *buf, + unsigned long item) +{ + return likely(item < buf->rb_sc_last) ? item + 1 : 0; +} + +/** + * rpcrdma_sendctx_get_locked - Acquire a send context + * @buf: transport buffers from which to acquire an unused context + * + * Returns pointer to a free send completion context; or NULL if + * the queue is empty. + * + * Usage: Called to acquire an SGE array before preparing a Send WR. + * + * The caller serializes calls to this function (per rpcrdma_buffer), + * and provides an effective memory barrier that flushes the new value + * of rb_sc_head. + */ +struct rpcrdma_sendctx *rpcrdma_sendctx_get_locked(struct rpcrdma_buffer *buf) +{ + struct rpcrdma_xprt *r_xprt; + struct rpcrdma_sendctx *sc; + unsigned long next_head; + + next_head = rpcrdma_sendctx_next(buf, buf->rb_sc_head); + + if (next_head == READ_ONCE(buf->rb_sc_tail)) + goto out_emptyq; + + /* ORDER: item must be accessed _before_ head is updated */ + sc = buf->rb_sc_ctxs[next_head]; + + /* Releasing the lock in the caller acts as a memory + * barrier that flushes rb_sc_head. + */ + buf->rb_sc_head = next_head; + + return sc; + +out_emptyq: + /* The queue is "empty" if there have not been enough Send + * completions recently. This is a sign the Send Queue is + * backing up. Cause the caller to pause and try again. + */ + dprintk("RPC: %s: empty sendctx queue\n", __func__); + r_xprt = container_of(buf, struct rpcrdma_xprt, rx_buf); + r_xprt->rx_stats.empty_sendctx_q++; + return NULL; +} + +/** + * rpcrdma_sendctx_put_locked - Release a send context + * @sc: send context to release + * + * Usage: Called from Send completion to return a sendctxt + * to the queue. + * + * The caller serializes calls to this function (per rpcrdma_buffer). + */ +void rpcrdma_sendctx_put_locked(struct rpcrdma_sendctx *sc) +{ + struct rpcrdma_buffer *buf = &sc->sc_xprt->rx_buf; + unsigned long next_tail; + + /* Unmap SGEs of previously completed by unsignaled + * Sends by walking up the queue until @sc is found. + */ + next_tail = buf->rb_sc_tail; + do { + next_tail = rpcrdma_sendctx_next(buf, next_tail); + + /* ORDER: item must be accessed _before_ tail is updated */ + rpcrdma_unmap_sendctx(buf->rb_sc_ctxs[next_tail]); + + } while (buf->rb_sc_ctxs[next_tail] != sc); + + /* Paired with READ_ONCE */ + smp_store_release(&buf->rb_sc_tail, next_tail); +} + static void rpcrdma_mr_recovery_worker(struct work_struct *work) { @@ -941,13 +1088,8 @@ rpcrdma_create_req(struct rpcrdma_xprt *r_xprt) spin_lock(&buffer->rb_reqslock); list_add(&req->rl_all, &buffer->rb_allreqs); spin_unlock(&buffer->rb_reqslock); - req->rl_cqe.done = rpcrdma_wc_send; req->rl_buffer = &r_xprt->rx_buf; INIT_LIST_HEAD(&req->rl_registered); - req->rl_send_wr.next = NULL; - req->rl_send_wr.wr_cqe = &req->rl_cqe; - req->rl_send_wr.sg_list = req->rl_send_sge; - req->rl_send_wr.opcode = IB_WR_SEND; return req; } @@ -974,7 +1116,7 @@ rpcrdma_create_rep(struct rpcrdma_xprt *r_xprt) rep->rr_cqe.done = rpcrdma_wc_receive; rep->rr_rxprt = r_xprt; - INIT_WORK(&rep->rr_work, rpcrdma_reply_handler); + INIT_WORK(&rep->rr_work, rpcrdma_deferred_completion); rep->rr_recv_wr.next = NULL; rep->rr_recv_wr.wr_cqe = &rep->rr_cqe; rep->rr_recv_wr.sg_list = &rep->rr_rdmabuf->rg_iov; @@ -995,7 +1137,6 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) buf->rb_max_requests = r_xprt->rx_data.max_requests; buf->rb_bc_srv_max_requests = 0; - atomic_set(&buf->rb_credits, 1); spin_lock_init(&buf->rb_mwlock); spin_lock_init(&buf->rb_lock); spin_lock_init(&buf->rb_recovery_lock); @@ -1022,7 +1163,6 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) rc = PTR_ERR(req); goto out; } - req->rl_backchannel = false; list_add(&req->rl_list, &buf->rb_send_bufs); } @@ -1040,6 +1180,10 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) list_add(&rep->rr_list, &buf->rb_recv_bufs); } + rc = rpcrdma_sendctxs_create(r_xprt); + if (rc) + goto out; + return 0; out: rpcrdma_buffer_destroy(buf); @@ -1116,6 +1260,8 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf) cancel_delayed_work_sync(&buf->rb_recovery_worker); cancel_delayed_work_sync(&buf->rb_refresh_worker); + rpcrdma_sendctxs_destroy(buf); + while (!list_empty(&buf->rb_recv_bufs)) { struct rpcrdma_rep *rep; @@ -1231,7 +1377,6 @@ rpcrdma_buffer_put(struct rpcrdma_req *req) struct rpcrdma_buffer *buffers = req->rl_buffer; struct rpcrdma_rep *rep = req->rl_reply; - req->rl_send_wr.num_sge = 0; req->rl_reply = NULL; spin_lock(&buffers->rb_lock); @@ -1363,7 +1508,7 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, struct rpcrdma_req *req) { - struct ib_send_wr *send_wr = &req->rl_send_wr; + struct ib_send_wr *send_wr = &req->rl_sendctx->sc_wr; struct ib_send_wr *send_wr_fail; int rc; @@ -1377,7 +1522,14 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia, dprintk("RPC: %s: posting %d s/g entries\n", __func__, send_wr->num_sge); - rpcrdma_set_signaled(ep, send_wr); + if (!ep->rep_send_count || + test_bit(RPCRDMA_REQ_F_TX_RESOURCES, &req->rl_flags)) { + send_wr->send_flags |= IB_SEND_SIGNALED; + ep->rep_send_count = ep->rep_send_batch; + } else { + send_wr->send_flags &= ~IB_SEND_SIGNALED; + --ep->rep_send_count; + } rc = ib_post_send(ia->ri_id->qp, send_wr, &send_wr_fail); if (rc) goto out_postsend_err; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index e26a97d2f922..51686d9eac5f 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -1,4 +1,5 @@ /* + * Copyright (c) 2014-2017 Oracle. All rights reserved. * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved. * * This software is available to you under a choice of one of two @@ -93,8 +94,8 @@ enum { */ struct rpcrdma_ep { - atomic_t rep_cqcount; - int rep_cqinit; + unsigned int rep_send_count; + unsigned int rep_send_batch; int rep_connected; struct ib_qp_init_attr rep_attr; wait_queue_head_t rep_connect_wait; @@ -104,25 +105,6 @@ struct rpcrdma_ep { struct delayed_work rep_connect_worker; }; -static inline void -rpcrdma_init_cqcount(struct rpcrdma_ep *ep, int count) -{ - atomic_set(&ep->rep_cqcount, ep->rep_cqinit - count); -} - -/* To update send queue accounting, provider must take a - * send completion every now and then. - */ -static inline void -rpcrdma_set_signaled(struct rpcrdma_ep *ep, struct ib_send_wr *send_wr) -{ - send_wr->send_flags = 0; - if (unlikely(atomic_sub_return(1, &ep->rep_cqcount) <= 0)) { - rpcrdma_init_cqcount(ep, 0); - send_wr->send_flags = IB_SEND_SIGNALED; - } -} - /* Pre-allocate extra Work Requests for handling backward receives * and sends. This is a fixed value because the Work Queues are * allocated when the forward channel is set up. @@ -164,12 +146,6 @@ rdmab_lkey(struct rpcrdma_regbuf *rb) return rb->rg_iov.lkey; } -static inline struct rpcrdma_msg * -rdmab_to_msg(struct rpcrdma_regbuf *rb) -{ - return (struct rpcrdma_msg *)rb->rg_base; -} - static inline struct ib_device * rdmab_device(struct rpcrdma_regbuf *rb) { @@ -202,22 +178,24 @@ enum { }; /* - * struct rpcrdma_rep -- this structure encapsulates state required to recv - * and complete a reply, asychronously. It needs several pieces of - * state: - * o recv buffer (posted to provider) - * o ib_sge (also donated to provider) - * o status of reply (length, success or not) - * o bookkeeping state to get run by reply handler (list, etc) + * struct rpcrdma_rep -- this structure encapsulates state required + * to receive and complete an RPC Reply, asychronously. It needs + * several pieces of state: * - * These are allocated during initialization, per-transport instance. + * o receive buffer and ib_sge (donated to provider) + * o status of receive (success or not, length, inv rkey) + * o bookkeeping state to get run by reply handler (XDR stream) * - * N of these are associated with a transport instance, and stored in - * struct rpcrdma_buffer. N is the max number of outstanding requests. + * These structures are allocated during transport initialization. + * N of these are associated with a transport instance, managed by + * struct rpcrdma_buffer. N is the max number of outstanding RPCs. */ struct rpcrdma_rep { struct ib_cqe rr_cqe; + __be32 rr_xid; + __be32 rr_vers; + __be32 rr_proc; int rr_wc_flags; u32 rr_inv_rkey; struct rpcrdma_regbuf *rr_rdmabuf; @@ -225,10 +203,34 @@ struct rpcrdma_rep { struct work_struct rr_work; struct xdr_buf rr_hdrbuf; struct xdr_stream rr_stream; + struct rpc_rqst *rr_rqst; struct list_head rr_list; struct ib_recv_wr rr_recv_wr; }; +/* struct rpcrdma_sendctx - DMA mapped SGEs to unmap after Send completes + */ +struct rpcrdma_req; +struct rpcrdma_xprt; +struct rpcrdma_sendctx { + struct ib_send_wr sc_wr; + struct ib_cqe sc_cqe; + struct rpcrdma_xprt *sc_xprt; + struct rpcrdma_req *sc_req; + unsigned int sc_unmap_count; + struct ib_sge sc_sges[]; +}; + +/* Limit the number of SGEs that can be unmapped during one + * Send completion. This caps the amount of work a single + * completion can do before returning to the provider. + * + * Setting this to zero disables Send completion batching. + */ +enum { + RPCRDMA_MAX_SEND_BATCH = 7, +}; + /* * struct rpcrdma_mw - external memory region metadata * @@ -340,26 +342,30 @@ enum { struct rpcrdma_buffer; struct rpcrdma_req { struct list_head rl_list; - unsigned int rl_mapped_sges; unsigned int rl_connect_cookie; struct rpcrdma_buffer *rl_buffer; struct rpcrdma_rep *rl_reply; struct xdr_stream rl_stream; struct xdr_buf rl_hdrbuf; - struct ib_send_wr rl_send_wr; - struct ib_sge rl_send_sge[RPCRDMA_MAX_SEND_SGES]; + struct rpcrdma_sendctx *rl_sendctx; struct rpcrdma_regbuf *rl_rdmabuf; /* xprt header */ struct rpcrdma_regbuf *rl_sendbuf; /* rq_snd_buf */ struct rpcrdma_regbuf *rl_recvbuf; /* rq_rcv_buf */ - struct ib_cqe rl_cqe; struct list_head rl_all; - bool rl_backchannel; + unsigned long rl_flags; struct list_head rl_registered; /* registered segments */ struct rpcrdma_mr_seg rl_segments[RPCRDMA_MAX_SEGS]; }; +/* rl_flags */ +enum { + RPCRDMA_REQ_F_BACKCHANNEL = 0, + RPCRDMA_REQ_F_PENDING, + RPCRDMA_REQ_F_TX_RESOURCES, +}; + static inline void rpcrdma_set_xprtdata(struct rpc_rqst *rqst, struct rpcrdma_req *req) { @@ -399,12 +405,17 @@ struct rpcrdma_buffer { struct list_head rb_mws; struct list_head rb_all; + unsigned long rb_sc_head; + unsigned long rb_sc_tail; + unsigned long rb_sc_last; + struct rpcrdma_sendctx **rb_sc_ctxs; + spinlock_t rb_lock; /* protect buf lists */ int rb_send_count, rb_recv_count; struct list_head rb_send_bufs; struct list_head rb_recv_bufs; u32 rb_max_requests; - atomic_t rb_credits; /* most recent credit grant */ + u32 rb_credits; /* most recent credit grant */ u32 rb_bc_srv_max_requests; spinlock_t rb_reqslock; /* protect rb_allreqs */ @@ -453,10 +464,12 @@ struct rpcrdma_stats { unsigned long mrs_recovered; unsigned long mrs_orphaned; unsigned long mrs_allocated; + unsigned long empty_sendctx_q; /* accessed when receiving a reply */ unsigned long long total_rdma_reply; unsigned long long fixup_copy_count; + unsigned long reply_waits_for_send; unsigned long local_inv_needed; unsigned long nomsg_call_count; unsigned long bcall_count; @@ -473,8 +486,6 @@ struct rpcrdma_memreg_ops { struct rpcrdma_mw **); void (*ro_unmap_sync)(struct rpcrdma_xprt *, struct list_head *); - void (*ro_unmap_safe)(struct rpcrdma_xprt *, - struct rpcrdma_req *, bool); void (*ro_recover_mr)(struct rpcrdma_mw *); int (*ro_open)(struct rpcrdma_ia *, struct rpcrdma_ep *, @@ -532,6 +543,8 @@ void rpcrdma_ia_close(struct rpcrdma_ia *); bool frwr_is_supported(struct rpcrdma_ia *); bool fmr_is_supported(struct rpcrdma_ia *); +extern struct workqueue_struct *rpcrdma_receive_wq; + /* * Endpoint calls - xprtrdma/verbs.c */ @@ -554,6 +567,8 @@ struct rpcrdma_rep *rpcrdma_create_rep(struct rpcrdma_xprt *); void rpcrdma_destroy_req(struct rpcrdma_req *); int rpcrdma_buffer_create(struct rpcrdma_xprt *); void rpcrdma_buffer_destroy(struct rpcrdma_buffer *); +struct rpcrdma_sendctx *rpcrdma_sendctx_get_locked(struct rpcrdma_buffer *buf); +void rpcrdma_sendctx_put_locked(struct rpcrdma_sendctx *sc); struct rpcrdma_mw *rpcrdma_get_mw(struct rpcrdma_xprt *); void rpcrdma_put_mw(struct rpcrdma_xprt *, struct rpcrdma_mw *); @@ -610,12 +625,18 @@ enum rpcrdma_chunktype { rpcrdma_replych }; -bool rpcrdma_prepare_send_sges(struct rpcrdma_ia *, struct rpcrdma_req *, - u32, struct xdr_buf *, enum rpcrdma_chunktype); -void rpcrdma_unmap_sges(struct rpcrdma_ia *, struct rpcrdma_req *); +int rpcrdma_prepare_send_sges(struct rpcrdma_xprt *r_xprt, + struct rpcrdma_req *req, u32 hdrlen, + struct xdr_buf *xdr, + enum rpcrdma_chunktype rtype); +void rpcrdma_unmap_sendctx(struct rpcrdma_sendctx *sc); int rpcrdma_marshal_req(struct rpcrdma_xprt *r_xprt, struct rpc_rqst *rqst); void rpcrdma_set_max_header_sizes(struct rpcrdma_xprt *); -void rpcrdma_reply_handler(struct work_struct *work); +void rpcrdma_complete_rqst(struct rpcrdma_rep *rep); +void rpcrdma_reply_handler(struct rpcrdma_rep *rep); +void rpcrdma_release_rqst(struct rpcrdma_xprt *r_xprt, + struct rpcrdma_req *req); +void rpcrdma_deferred_completion(struct work_struct *work); static inline void rpcrdma_set_xdrlen(struct xdr_buf *xdr, size_t len) { diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 4dad5da388d6..9cc850c2719e 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -552,6 +552,7 @@ static int xs_local_send_request(struct rpc_task *task) default: dprintk("RPC: sendmsg returned unrecognized error %d\n", -status); + /* fall through */ case -EPIPE: xs_close(xprt); status = -ENOTCONN; @@ -1611,6 +1612,7 @@ static void xs_tcp_state_change(struct sock *sk) xprt->connect_cookie++; clear_bit(XPRT_CONNECTED, &xprt->state); xs_tcp_force_close(xprt); + /* fall through */ case TCP_CLOSING: /* * If the server closed down the connection, make sure that @@ -2368,6 +2370,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) switch (ret) { case 0: xs_set_srcport(transport, sock); + /* fall through */ case -EINPROGRESS: /* SYN_SENT! */ if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) @@ -2419,6 +2422,7 @@ static void xs_tcp_setup_socket(struct work_struct *work) default: printk("%s: connect returned unhandled error %d\n", __func__, status); + /* fall through */ case -EADDRNOTAVAIL: /* We're probably in TIME_WAIT. Get rid of existing socket, * and retry diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 0531b41d1f2d..74b9d916a58b 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -345,6 +345,8 @@ static size_t switchdev_obj_size(const struct switchdev_obj *obj) return sizeof(struct switchdev_obj_port_vlan); case SWITCHDEV_OBJ_ID_PORT_MDB: return sizeof(struct switchdev_obj_port_mdb); + case SWITCHDEV_OBJ_ID_HOST_MDB: + return sizeof(struct switchdev_obj_port_mdb); default: BUG(); } diff --git a/net/tipc/Makefile b/net/tipc/Makefile index 2bfaa9d4b403..37bb0bfbd936 100644 --- a/net/tipc/Makefile +++ b/net/tipc/Makefile @@ -9,7 +9,7 @@ tipc-y += addr.o bcast.o bearer.o \ core.o link.o discover.o msg.o \ name_distr.o subscr.o monitor.o name_table.o net.o \ netlink.o netlink_compat.o node.o socket.o eth_media.o \ - server.o socket.o + server.o socket.o group.o tipc-$(CONFIG_TIPC_MEDIA_UDP) += udp_media.o tipc-$(CONFIG_TIPC_MEDIA_IB) += ib_media.o diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index a140dd4a84af..329325bd553e 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -258,20 +258,20 @@ static int tipc_bcast_xmit(struct net *net, struct sk_buff_head *pkts, static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts, struct tipc_nlist *dests, u16 *cong_link_cnt) { + struct tipc_dest *dst, *tmp; struct sk_buff_head _pkts; - struct u32_item *n, *tmp; - u32 dst, selector; + u32 dnode, selector; selector = msg_link_selector(buf_msg(skb_peek(pkts))); skb_queue_head_init(&_pkts); - list_for_each_entry_safe(n, tmp, &dests->list, list) { - dst = n->value; - if (!tipc_msg_pskb_copy(dst, pkts, &_pkts)) + list_for_each_entry_safe(dst, tmp, &dests->list, list) { + dnode = dst->node; + if (!tipc_msg_pskb_copy(dnode, pkts, &_pkts)) return -ENOMEM; /* Any other return value than -ELINKCONG is ignored */ - if (tipc_node_xmit(net, &_pkts, dst, selector) == -ELINKCONG) + if (tipc_node_xmit(net, &_pkts, dnode, selector) == -ELINKCONG) (*cong_link_cnt)++; } return 0; @@ -554,7 +554,7 @@ void tipc_nlist_add(struct tipc_nlist *nl, u32 node) { if (node == nl->self) nl->local = true; - else if (u32_push(&nl->list, node)) + else if (tipc_dest_push(&nl->list, node, 0)) nl->remote++; } @@ -562,13 +562,13 @@ void tipc_nlist_del(struct tipc_nlist *nl, u32 node) { if (node == nl->self) nl->local = false; - else if (u32_del(&nl->list, node)) + else if (tipc_dest_del(&nl->list, node, 0)) nl->remote--; } void tipc_nlist_purge(struct tipc_nlist *nl) { - u32_list_purge(&nl->list); + tipc_dest_list_purge(&nl->list); nl->remote = 0; nl->local = 0; } diff --git a/net/tipc/core.h b/net/tipc/core.h index 5cc5398be722..964342689f2c 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -132,6 +132,11 @@ static inline struct list_head *tipc_nodes(struct net *net) return &tipc_net(net)->node_list; } +static inline struct tipc_server *tipc_topsrv(struct net *net) +{ + return tipc_net(net)->topsrv; +} + static inline unsigned int tipc_hashfn(u32 addr) { return addr & (NODE_HTABLE_SIZE - 1); diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 02462d67d191..92e4828c6b09 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -224,9 +224,9 @@ void tipc_disc_remove_dest(struct tipc_link_req *req) * * Called whenever a link setup request timer associated with a bearer expires. */ -static void disc_timeout(unsigned long data) +static void disc_timeout(struct timer_list *t) { - struct tipc_link_req *req = (struct tipc_link_req *)data; + struct tipc_link_req *req = from_timer(req, t, timer); struct sk_buff *skb; int max_delay; @@ -292,7 +292,7 @@ int tipc_disc_create(struct net *net, struct tipc_bearer *b, req->num_nodes = 0; req->timer_intv = TIPC_LINK_REQ_INIT; spin_lock_init(&req->lock); - setup_timer(&req->timer, disc_timeout, (unsigned long)req); + timer_setup(&req->timer, disc_timeout, 0); mod_timer(&req->timer, jiffies + req->timer_intv); b->link_req = req; *skb = skb_clone(req->buf, GFP_ATOMIC); diff --git a/net/tipc/group.c b/net/tipc/group.c new file mode 100644 index 000000000000..7821085a7dd8 --- /dev/null +++ b/net/tipc/group.c @@ -0,0 +1,871 @@ +/* + * net/tipc/group.c: TIPC group messaging code + * + * Copyright (c) 2017, Ericsson AB + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "addr.h" +#include "group.h" +#include "bcast.h" +#include "server.h" +#include "msg.h" +#include "socket.h" +#include "node.h" +#include "name_table.h" +#include "subscr.h" + +#define ADV_UNIT (((MAX_MSG_SIZE + MAX_H_SIZE) / FLOWCTL_BLK_SZ) + 1) +#define ADV_IDLE ADV_UNIT +#define ADV_ACTIVE (ADV_UNIT * 12) + +enum mbr_state { + MBR_QUARANTINED, + MBR_DISCOVERED, + MBR_JOINING, + MBR_PUBLISHED, + MBR_JOINED, + MBR_PENDING, + MBR_ACTIVE, + MBR_RECLAIMING, + MBR_REMITTED, + MBR_LEAVING +}; + +struct tipc_member { + struct rb_node tree_node; + struct list_head list; + struct list_head congested; + struct sk_buff *event_msg; + struct sk_buff_head deferredq; + struct tipc_group *group; + u32 node; + u32 port; + u32 instance; + enum mbr_state state; + u16 advertised; + u16 window; + u16 bc_rcv_nxt; + u16 bc_syncpt; + u16 bc_acked; + bool usr_pending; +}; + +struct tipc_group { + struct rb_root members; + struct list_head congested; + struct list_head pending; + struct list_head active; + struct list_head reclaiming; + struct tipc_nlist dests; + struct net *net; + int subid; + u32 type; + u32 instance; + u32 domain; + u32 scope; + u32 portid; + u16 member_cnt; + u16 active_cnt; + u16 max_active; + u16 bc_snd_nxt; + u16 bc_ackers; + bool loopback; + bool events; +}; + +static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, + int mtyp, struct sk_buff_head *xmitq); + +static void tipc_group_decr_active(struct tipc_group *grp, + struct tipc_member *m) +{ + if (m->state == MBR_ACTIVE || m->state == MBR_RECLAIMING) + grp->active_cnt--; +} + +static int tipc_group_rcvbuf_limit(struct tipc_group *grp) +{ + int max_active, active_pool, idle_pool; + int mcnt = grp->member_cnt + 1; + + /* Limit simultaneous reception from other members */ + max_active = min(mcnt / 8, 64); + max_active = max(max_active, 16); + grp->max_active = max_active; + + /* Reserve blocks for active and idle members */ + active_pool = max_active * ADV_ACTIVE; + idle_pool = (mcnt - max_active) * ADV_IDLE; + + /* Scale to bytes, considering worst-case truesize/msgsize ratio */ + return (active_pool + idle_pool) * FLOWCTL_BLK_SZ * 4; +} + +u16 tipc_group_bc_snd_nxt(struct tipc_group *grp) +{ + return grp->bc_snd_nxt; +} + +static bool tipc_group_is_enabled(struct tipc_member *m) +{ + return m->state != MBR_QUARANTINED && m->state != MBR_LEAVING; +} + +static bool tipc_group_is_receiver(struct tipc_member *m) +{ + return m && m->state >= MBR_JOINED; +} + +u32 tipc_group_exclude(struct tipc_group *grp) +{ + if (!grp->loopback) + return grp->portid; + return 0; +} + +int tipc_group_size(struct tipc_group *grp) +{ + return grp->member_cnt; +} + +struct tipc_group *tipc_group_create(struct net *net, u32 portid, + struct tipc_group_req *mreq) +{ + struct tipc_group *grp; + u32 type = mreq->type; + + grp = kzalloc(sizeof(*grp), GFP_ATOMIC); + if (!grp) + return NULL; + tipc_nlist_init(&grp->dests, tipc_own_addr(net)); + INIT_LIST_HEAD(&grp->congested); + INIT_LIST_HEAD(&grp->active); + INIT_LIST_HEAD(&grp->pending); + INIT_LIST_HEAD(&grp->reclaiming); + grp->members = RB_ROOT; + grp->net = net; + grp->portid = portid; + grp->domain = addr_domain(net, mreq->scope); + grp->type = type; + grp->instance = mreq->instance; + grp->scope = mreq->scope; + grp->loopback = mreq->flags & TIPC_GROUP_LOOPBACK; + grp->events = mreq->flags & TIPC_GROUP_MEMBER_EVTS; + if (tipc_topsrv_kern_subscr(net, portid, type, 0, ~0, &grp->subid)) + return grp; + kfree(grp); + return NULL; +} + +void tipc_group_delete(struct net *net, struct tipc_group *grp) +{ + struct rb_root *tree = &grp->members; + struct tipc_member *m, *tmp; + struct sk_buff_head xmitq; + + __skb_queue_head_init(&xmitq); + + rbtree_postorder_for_each_entry_safe(m, tmp, tree, tree_node) { + tipc_group_proto_xmit(grp, m, GRP_LEAVE_MSG, &xmitq); + list_del(&m->list); + kfree(m); + } + tipc_node_distr_xmit(net, &xmitq); + tipc_nlist_purge(&grp->dests); + tipc_topsrv_kern_unsubscr(net, grp->subid); + kfree(grp); +} + +struct tipc_member *tipc_group_find_member(struct tipc_group *grp, + u32 node, u32 port) +{ + struct rb_node *n = grp->members.rb_node; + u64 nkey, key = (u64)node << 32 | port; + struct tipc_member *m; + + while (n) { + m = container_of(n, struct tipc_member, tree_node); + nkey = (u64)m->node << 32 | m->port; + if (key < nkey) + n = n->rb_left; + else if (key > nkey) + n = n->rb_right; + else + return m; + } + return NULL; +} + +static struct tipc_member *tipc_group_find_dest(struct tipc_group *grp, + u32 node, u32 port) +{ + struct tipc_member *m; + + m = tipc_group_find_member(grp, node, port); + if (m && tipc_group_is_enabled(m)) + return m; + return NULL; +} + +static struct tipc_member *tipc_group_find_node(struct tipc_group *grp, + u32 node) +{ + struct tipc_member *m; + struct rb_node *n; + + for (n = rb_first(&grp->members); n; n = rb_next(n)) { + m = container_of(n, struct tipc_member, tree_node); + if (m->node == node) + return m; + } + return NULL; +} + +static void tipc_group_add_to_tree(struct tipc_group *grp, + struct tipc_member *m) +{ + u64 nkey, key = (u64)m->node << 32 | m->port; + struct rb_node **n, *parent = NULL; + struct tipc_member *tmp; + + n = &grp->members.rb_node; + while (*n) { + tmp = container_of(*n, struct tipc_member, tree_node); + parent = *n; + tmp = container_of(parent, struct tipc_member, tree_node); + nkey = (u64)tmp->node << 32 | tmp->port; + if (key < nkey) + n = &(*n)->rb_left; + else if (key > nkey) + n = &(*n)->rb_right; + else + return; + } + rb_link_node(&m->tree_node, parent, n); + rb_insert_color(&m->tree_node, &grp->members); +} + +static struct tipc_member *tipc_group_create_member(struct tipc_group *grp, + u32 node, u32 port, + int state) +{ + struct tipc_member *m; + + m = kzalloc(sizeof(*m), GFP_ATOMIC); + if (!m) + return NULL; + INIT_LIST_HEAD(&m->list); + INIT_LIST_HEAD(&m->congested); + __skb_queue_head_init(&m->deferredq); + m->group = grp; + m->node = node; + m->port = port; + m->bc_acked = grp->bc_snd_nxt - 1; + grp->member_cnt++; + tipc_group_add_to_tree(grp, m); + tipc_nlist_add(&grp->dests, m->node); + m->state = state; + return m; +} + +void tipc_group_add_member(struct tipc_group *grp, u32 node, u32 port) +{ + tipc_group_create_member(grp, node, port, MBR_DISCOVERED); +} + +static void tipc_group_delete_member(struct tipc_group *grp, + struct tipc_member *m) +{ + rb_erase(&m->tree_node, &grp->members); + grp->member_cnt--; + + /* Check if we were waiting for replicast ack from this member */ + if (grp->bc_ackers && less(m->bc_acked, grp->bc_snd_nxt - 1)) + grp->bc_ackers--; + + list_del_init(&m->list); + list_del_init(&m->congested); + tipc_group_decr_active(grp, m); + + /* If last member on a node, remove node from dest list */ + if (!tipc_group_find_node(grp, m->node)) + tipc_nlist_del(&grp->dests, m->node); + + kfree(m); +} + +struct tipc_nlist *tipc_group_dests(struct tipc_group *grp) +{ + return &grp->dests; +} + +void tipc_group_self(struct tipc_group *grp, struct tipc_name_seq *seq, + int *scope) +{ + seq->type = grp->type; + seq->lower = grp->instance; + seq->upper = grp->instance; + *scope = grp->scope; +} + +void tipc_group_update_member(struct tipc_member *m, int len) +{ + struct tipc_group *grp = m->group; + struct tipc_member *_m, *tmp; + + if (!tipc_group_is_enabled(m)) + return; + + m->window -= len; + + if (m->window >= ADV_IDLE) + return; + + if (!list_empty(&m->congested)) + return; + + /* Sort member into congested members' list */ + list_for_each_entry_safe(_m, tmp, &grp->congested, congested) { + if (m->window > _m->window) + continue; + list_add_tail(&m->congested, &_m->congested); + return; + } + list_add_tail(&m->congested, &grp->congested); +} + +void tipc_group_update_bc_members(struct tipc_group *grp, int len, bool ack) +{ + u16 prev = grp->bc_snd_nxt - 1; + struct tipc_member *m; + struct rb_node *n; + + for (n = rb_first(&grp->members); n; n = rb_next(n)) { + m = container_of(n, struct tipc_member, tree_node); + if (tipc_group_is_enabled(m)) { + tipc_group_update_member(m, len); + m->bc_acked = prev; + } + } + + /* Mark number of acknowledges to expect, if any */ + if (ack) + grp->bc_ackers = grp->member_cnt; + grp->bc_snd_nxt++; +} + +bool tipc_group_cong(struct tipc_group *grp, u32 dnode, u32 dport, + int len, struct tipc_member **mbr) +{ + struct sk_buff_head xmitq; + struct tipc_member *m; + int adv, state; + + m = tipc_group_find_dest(grp, dnode, dport); + *mbr = m; + if (!m) + return false; + if (m->usr_pending) + return true; + if (m->window >= len) + return false; + m->usr_pending = true; + + /* If not fully advertised, do it now to prevent mutual blocking */ + adv = m->advertised; + state = m->state; + if (state < MBR_JOINED) + return true; + if (state == MBR_JOINED && adv == ADV_IDLE) + return true; + if (state == MBR_ACTIVE && adv == ADV_ACTIVE) + return true; + if (state == MBR_PENDING && adv == ADV_IDLE) + return true; + skb_queue_head_init(&xmitq); + tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, &xmitq); + tipc_node_distr_xmit(grp->net, &xmitq); + return true; +} + +bool tipc_group_bc_cong(struct tipc_group *grp, int len) +{ + struct tipc_member *m = NULL; + + /* If prev bcast was replicast, reject until all receivers have acked */ + if (grp->bc_ackers) + return true; + + if (list_empty(&grp->congested)) + return false; + + m = list_first_entry(&grp->congested, struct tipc_member, congested); + if (m->window >= len) + return false; + + return tipc_group_cong(grp, m->node, m->port, len, &m); +} + +/* tipc_group_sort_msg() - sort msg into queue by bcast sequence number + */ +static void tipc_group_sort_msg(struct sk_buff *skb, struct sk_buff_head *defq) +{ + struct tipc_msg *_hdr, *hdr = buf_msg(skb); + u16 bc_seqno = msg_grp_bc_seqno(hdr); + struct sk_buff *_skb, *tmp; + int mtyp = msg_type(hdr); + + /* Bcast/mcast may be bypassed by ucast or other bcast, - sort it in */ + if (mtyp == TIPC_GRP_BCAST_MSG || mtyp == TIPC_GRP_MCAST_MSG) { + skb_queue_walk_safe(defq, _skb, tmp) { + _hdr = buf_msg(_skb); + if (!less(bc_seqno, msg_grp_bc_seqno(_hdr))) + continue; + __skb_queue_before(defq, _skb, skb); + return; + } + /* Bcast was not bypassed, - add to tail */ + } + /* Unicasts are never bypassed, - always add to tail */ + __skb_queue_tail(defq, skb); +} + +/* tipc_group_filter_msg() - determine if we should accept arriving message + */ +void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, + struct sk_buff_head *xmitq) +{ + struct sk_buff *skb = __skb_dequeue(inputq); + bool ack, deliver, update, leave = false; + struct sk_buff_head *defq; + struct tipc_member *m; + struct tipc_msg *hdr; + u32 node, port; + int mtyp, blks; + + if (!skb) + return; + + hdr = buf_msg(skb); + node = msg_orignode(hdr); + port = msg_origport(hdr); + + if (!msg_in_group(hdr)) + goto drop; + + m = tipc_group_find_member(grp, node, port); + if (!tipc_group_is_receiver(m)) + goto drop; + + if (less(msg_grp_bc_seqno(hdr), m->bc_rcv_nxt)) + goto drop; + + TIPC_SKB_CB(skb)->orig_member = m->instance; + defq = &m->deferredq; + tipc_group_sort_msg(skb, defq); + + while ((skb = skb_peek(defq))) { + hdr = buf_msg(skb); + mtyp = msg_type(hdr); + deliver = true; + ack = false; + update = false; + + if (more(msg_grp_bc_seqno(hdr), m->bc_rcv_nxt)) + break; + + /* Decide what to do with message */ + switch (mtyp) { + case TIPC_GRP_MCAST_MSG: + if (msg_nameinst(hdr) != grp->instance) { + update = true; + deliver = false; + } + /* Fall thru */ + case TIPC_GRP_BCAST_MSG: + m->bc_rcv_nxt++; + ack = msg_grp_bc_ack_req(hdr); + break; + case TIPC_GRP_UCAST_MSG: + break; + case TIPC_GRP_MEMBER_EVT: + if (m->state == MBR_LEAVING) + leave = true; + if (!grp->events) + deliver = false; + break; + default: + break; + } + + /* Execute decisions */ + __skb_dequeue(defq); + if (deliver) + __skb_queue_tail(inputq, skb); + else + kfree_skb(skb); + + if (ack) + tipc_group_proto_xmit(grp, m, GRP_ACK_MSG, xmitq); + + if (leave) { + tipc_group_delete_member(grp, m); + __skb_queue_purge(defq); + break; + } + if (!update) + continue; + + blks = msg_blocks(hdr); + tipc_group_update_rcv_win(grp, blks, node, port, xmitq); + } + return; +drop: + kfree_skb(skb); +} + +void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node, + u32 port, struct sk_buff_head *xmitq) +{ + struct list_head *active = &grp->active; + int max_active = grp->max_active; + int reclaim_limit = max_active * 3 / 4; + int active_cnt = grp->active_cnt; + struct tipc_member *m, *rm; + + m = tipc_group_find_member(grp, node, port); + if (!m) + return; + + m->advertised -= blks; + + switch (m->state) { + case MBR_JOINED: + /* Reclaim advertised space from least active member */ + if (!list_empty(active) && active_cnt >= reclaim_limit) { + rm = list_first_entry(active, struct tipc_member, list); + rm->state = MBR_RECLAIMING; + list_move_tail(&rm->list, &grp->reclaiming); + tipc_group_proto_xmit(grp, rm, GRP_RECLAIM_MSG, xmitq); + } + /* If max active, become pending and wait for reclaimed space */ + if (active_cnt >= max_active) { + m->state = MBR_PENDING; + list_add_tail(&m->list, &grp->pending); + break; + } + /* Otherwise become active */ + m->state = MBR_ACTIVE; + list_add_tail(&m->list, &grp->active); + grp->active_cnt++; + /* Fall through */ + case MBR_ACTIVE: + if (!list_is_last(&m->list, &grp->active)) + list_move_tail(&m->list, &grp->active); + if (m->advertised > (ADV_ACTIVE * 3 / 4)) + break; + tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); + break; + case MBR_REMITTED: + if (m->advertised > ADV_IDLE) + break; + m->state = MBR_JOINED; + if (m->advertised < ADV_IDLE) { + pr_warn_ratelimited("Rcv unexpected msg after REMIT\n"); + tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); + } + break; + case MBR_RECLAIMING: + case MBR_DISCOVERED: + case MBR_JOINING: + case MBR_LEAVING: + default: + break; + } +} + +static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, + int mtyp, struct sk_buff_head *xmitq) +{ + struct tipc_msg *hdr; + struct sk_buff *skb; + int adv = 0; + + skb = tipc_msg_create(GROUP_PROTOCOL, mtyp, INT_H_SIZE, 0, + m->node, tipc_own_addr(grp->net), + m->port, grp->portid, 0); + if (!skb) + return; + + if (m->state == MBR_ACTIVE) + adv = ADV_ACTIVE - m->advertised; + else if (m->state == MBR_JOINED || m->state == MBR_PENDING) + adv = ADV_IDLE - m->advertised; + + hdr = buf_msg(skb); + + if (mtyp == GRP_JOIN_MSG) { + msg_set_grp_bc_syncpt(hdr, grp->bc_snd_nxt); + msg_set_adv_win(hdr, adv); + m->advertised += adv; + } else if (mtyp == GRP_LEAVE_MSG) { + msg_set_grp_bc_syncpt(hdr, grp->bc_snd_nxt); + } else if (mtyp == GRP_ADV_MSG) { + msg_set_adv_win(hdr, adv); + m->advertised += adv; + } else if (mtyp == GRP_ACK_MSG) { + msg_set_grp_bc_acked(hdr, m->bc_rcv_nxt); + } else if (mtyp == GRP_REMIT_MSG) { + msg_set_grp_remitted(hdr, m->window); + } + __skb_queue_tail(xmitq, skb); +} + +void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup, + struct tipc_msg *hdr, struct sk_buff_head *inputq, + struct sk_buff_head *xmitq) +{ + u32 node = msg_orignode(hdr); + u32 port = msg_origport(hdr); + struct tipc_member *m, *pm; + struct tipc_msg *ehdr; + u16 remitted, in_flight; + + if (!grp) + return; + + m = tipc_group_find_member(grp, node, port); + + switch (msg_type(hdr)) { + case GRP_JOIN_MSG: + if (!m) + m = tipc_group_create_member(grp, node, port, + MBR_QUARANTINED); + if (!m) + return; + m->bc_syncpt = msg_grp_bc_syncpt(hdr); + m->bc_rcv_nxt = m->bc_syncpt; + m->window += msg_adv_win(hdr); + + /* Wait until PUBLISH event is received */ + if (m->state == MBR_DISCOVERED) { + m->state = MBR_JOINING; + } else if (m->state == MBR_PUBLISHED) { + m->state = MBR_JOINED; + *usr_wakeup = true; + m->usr_pending = false; + tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); + ehdr = buf_msg(m->event_msg); + msg_set_grp_bc_seqno(ehdr, m->bc_syncpt); + __skb_queue_tail(inputq, m->event_msg); + } + if (m->window < ADV_IDLE) + tipc_group_update_member(m, 0); + else + list_del_init(&m->congested); + return; + case GRP_LEAVE_MSG: + if (!m) + return; + m->bc_syncpt = msg_grp_bc_syncpt(hdr); + + /* Wait until WITHDRAW event is received */ + if (m->state != MBR_LEAVING) { + tipc_group_decr_active(grp, m); + m->state = MBR_LEAVING; + return; + } + /* Otherwise deliver already received WITHDRAW event */ + ehdr = buf_msg(m->event_msg); + msg_set_grp_bc_seqno(ehdr, m->bc_syncpt); + __skb_queue_tail(inputq, m->event_msg); + *usr_wakeup = true; + list_del_init(&m->congested); + return; + case GRP_ADV_MSG: + if (!m) + return; + m->window += msg_adv_win(hdr); + *usr_wakeup = m->usr_pending; + m->usr_pending = false; + list_del_init(&m->congested); + return; + case GRP_ACK_MSG: + if (!m) + return; + m->bc_acked = msg_grp_bc_acked(hdr); + if (--grp->bc_ackers) + break; + *usr_wakeup = true; + m->usr_pending = false; + return; + case GRP_RECLAIM_MSG: + if (!m) + return; + *usr_wakeup = m->usr_pending; + m->usr_pending = false; + tipc_group_proto_xmit(grp, m, GRP_REMIT_MSG, xmitq); + m->window = ADV_IDLE; + return; + case GRP_REMIT_MSG: + if (!m || m->state != MBR_RECLAIMING) + return; + + list_del_init(&m->list); + grp->active_cnt--; + remitted = msg_grp_remitted(hdr); + + /* Messages preceding the REMIT still in receive queue */ + if (m->advertised > remitted) { + m->state = MBR_REMITTED; + in_flight = m->advertised - remitted; + } + /* All messages preceding the REMIT have been read */ + if (m->advertised <= remitted) { + m->state = MBR_JOINED; + in_flight = 0; + } + /* ..and the REMIT overtaken by more messages => re-advertise */ + if (m->advertised < remitted) + tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); + + m->advertised = ADV_IDLE + in_flight; + + /* Set oldest pending member to active and advertise */ + if (list_empty(&grp->pending)) + return; + pm = list_first_entry(&grp->pending, struct tipc_member, list); + pm->state = MBR_ACTIVE; + list_move_tail(&pm->list, &grp->active); + grp->active_cnt++; + if (pm->advertised <= (ADV_ACTIVE * 3 / 4)) + tipc_group_proto_xmit(grp, pm, GRP_ADV_MSG, xmitq); + return; + default: + pr_warn("Received unknown GROUP_PROTO message\n"); + } +} + +/* tipc_group_member_evt() - receive and handle a member up/down event + */ +void tipc_group_member_evt(struct tipc_group *grp, + bool *usr_wakeup, + int *sk_rcvbuf, + struct sk_buff *skb, + struct sk_buff_head *inputq, + struct sk_buff_head *xmitq) +{ + struct tipc_msg *hdr = buf_msg(skb); + struct tipc_event *evt = (void *)msg_data(hdr); + u32 instance = evt->found_lower; + u32 node = evt->port.node; + u32 port = evt->port.ref; + int event = evt->event; + struct tipc_member *m; + struct net *net; + bool node_up; + u32 self; + + if (!grp) + goto drop; + + net = grp->net; + self = tipc_own_addr(net); + if (!grp->loopback && node == self && port == grp->portid) + goto drop; + + /* Convert message before delivery to user */ + msg_set_hdr_sz(hdr, GROUP_H_SIZE); + msg_set_user(hdr, TIPC_CRITICAL_IMPORTANCE); + msg_set_type(hdr, TIPC_GRP_MEMBER_EVT); + msg_set_origport(hdr, port); + msg_set_orignode(hdr, node); + msg_set_nametype(hdr, grp->type); + msg_set_grp_evt(hdr, event); + + m = tipc_group_find_member(grp, node, port); + + if (event == TIPC_PUBLISHED) { + if (!m) + m = tipc_group_create_member(grp, node, port, + MBR_DISCOVERED); + if (!m) + goto drop; + + /* Hold back event if JOIN message not yet received */ + if (m->state == MBR_DISCOVERED) { + m->event_msg = skb; + m->state = MBR_PUBLISHED; + } else { + msg_set_grp_bc_seqno(hdr, m->bc_syncpt); + __skb_queue_tail(inputq, skb); + m->state = MBR_JOINED; + *usr_wakeup = true; + m->usr_pending = false; + } + m->instance = instance; + TIPC_SKB_CB(skb)->orig_member = m->instance; + tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, xmitq); + if (m->window < ADV_IDLE) + tipc_group_update_member(m, 0); + else + list_del_init(&m->congested); + } else if (event == TIPC_WITHDRAWN) { + if (!m) + goto drop; + + TIPC_SKB_CB(skb)->orig_member = m->instance; + + *usr_wakeup = true; + m->usr_pending = false; + node_up = tipc_node_is_up(net, node); + + /* Hold back event if more messages might be expected */ + if (m->state != MBR_LEAVING && node_up) { + m->event_msg = skb; + tipc_group_decr_active(grp, m); + m->state = MBR_LEAVING; + } else { + if (node_up) + msg_set_grp_bc_seqno(hdr, m->bc_syncpt); + else + msg_set_grp_bc_seqno(hdr, m->bc_rcv_nxt); + __skb_queue_tail(inputq, skb); + } + list_del_init(&m->congested); + } + *sk_rcvbuf = tipc_group_rcvbuf_limit(grp); + return; +drop: + kfree_skb(skb); +} diff --git a/net/tipc/group.h b/net/tipc/group.h new file mode 100644 index 000000000000..d525e1cd7de5 --- /dev/null +++ b/net/tipc/group.h @@ -0,0 +1,73 @@ +/* + * net/tipc/group.h: Include file for TIPC group unicast/multicast functions + * + * Copyright (c) 2017, Ericsson AB + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_GROUP_H +#define _TIPC_GROUP_H + +#include "core.h" + +struct tipc_group; +struct tipc_member; +struct tipc_msg; + +struct tipc_group *tipc_group_create(struct net *net, u32 portid, + struct tipc_group_req *mreq); +void tipc_group_delete(struct net *net, struct tipc_group *grp); +void tipc_group_add_member(struct tipc_group *grp, u32 node, u32 port); +struct tipc_nlist *tipc_group_dests(struct tipc_group *grp); +void tipc_group_self(struct tipc_group *grp, struct tipc_name_seq *seq, + int *scope); +u32 tipc_group_exclude(struct tipc_group *grp); +void tipc_group_filter_msg(struct tipc_group *grp, + struct sk_buff_head *inputq, + struct sk_buff_head *xmitq); +void tipc_group_member_evt(struct tipc_group *grp, bool *wakeup, + int *sk_rcvbuf, struct sk_buff *skb, + struct sk_buff_head *inputq, + struct sk_buff_head *xmitq); +void tipc_group_proto_rcv(struct tipc_group *grp, bool *wakeup, + struct tipc_msg *hdr, + struct sk_buff_head *inputq, + struct sk_buff_head *xmitq); +void tipc_group_update_bc_members(struct tipc_group *grp, int len, bool ack); +bool tipc_group_cong(struct tipc_group *grp, u32 dnode, u32 dport, + int len, struct tipc_member **m); +bool tipc_group_bc_cong(struct tipc_group *grp, int len); +void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node, + u32 port, struct sk_buff_head *xmitq); +u16 tipc_group_bc_snd_nxt(struct tipc_group *grp); +void tipc_group_update_member(struct tipc_member *m, int len); +int tipc_group_size(struct tipc_group *grp); +#endif diff --git a/net/tipc/link.c b/net/tipc/link.c index ac0144f532aa..6bce0b1117bd 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -239,7 +239,8 @@ static int link_is_up(struct tipc_link *l) static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *xmitq); static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, - u16 rcvgap, int tolerance, int priority, + bool probe_reply, u16 rcvgap, + int tolerance, int priority, struct sk_buff_head *xmitq); static void link_print(struct tipc_link *l, const char *str); static int tipc_link_build_nack_msg(struct tipc_link *l, @@ -773,7 +774,7 @@ int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq) } if (state || probe || setup) - tipc_link_build_proto_msg(l, mtyp, probe, 0, 0, 0, xmitq); + tipc_link_build_proto_msg(l, mtyp, probe, 0, 0, 0, 0, xmitq); return rc; } @@ -1039,6 +1040,7 @@ int tipc_link_retrans(struct tipc_link *l, struct tipc_link *nacker, static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *inputq) { + struct sk_buff_head *mc_inputq = l->bc_rcvlink->inputq; struct tipc_msg *hdr = buf_msg(skb); switch (msg_user(hdr)) { @@ -1046,13 +1048,16 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, case TIPC_MEDIUM_IMPORTANCE: case TIPC_HIGH_IMPORTANCE: case TIPC_CRITICAL_IMPORTANCE: - if (unlikely(msg_type(hdr) == TIPC_MCAST_MSG)) { - skb_queue_tail(l->bc_rcvlink->inputq, skb); + if (unlikely(msg_in_group(hdr) || msg_mcast(hdr))) { + skb_queue_tail(mc_inputq, skb); return true; } case CONN_MANAGER: skb_queue_tail(inputq, skb); return true; + case GROUP_PROTOCOL: + skb_queue_tail(mc_inputq, skb); + return true; case NAME_DISTRIBUTOR: l->bc_rcvlink->state = LINK_ESTABLISHED; skb_queue_tail(l->namedq, skb); @@ -1170,7 +1175,7 @@ int tipc_link_build_state_msg(struct tipc_link *l, struct sk_buff_head *xmitq) /* Unicast ACK */ l->rcv_unacked = 0; l->stats.sent_acks++; - tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, xmitq); + tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, 0, xmitq); return 0; } @@ -1184,7 +1189,7 @@ void tipc_link_build_reset_msg(struct tipc_link *l, struct sk_buff_head *xmitq) if (l->state == LINK_ESTABLISHING) mtyp = ACTIVATE_MSG; - tipc_link_build_proto_msg(l, mtyp, 0, 0, 0, 0, xmitq); + tipc_link_build_proto_msg(l, mtyp, 0, 0, 0, 0, 0, xmitq); /* Inform peer that this endpoint is going down if applicable */ skb = skb_peek_tail(xmitq); @@ -1211,7 +1216,7 @@ static int tipc_link_build_nack_msg(struct tipc_link *l, } if ((skb_queue_len(&l->deferdq) == 1) || !(def_cnt % TIPC_NACK_INTV)) - tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, xmitq); + tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, 0, xmitq); return 0; } @@ -1285,7 +1290,8 @@ drop: } static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, - u16 rcvgap, int tolerance, int priority, + bool probe_reply, u16 rcvgap, + int tolerance, int priority, struct sk_buff_head *xmitq) { struct tipc_link *bcl = l->bc_rcvlink; @@ -1333,6 +1339,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, msg_set_seq_gap(hdr, rcvgap); msg_set_bc_gap(hdr, link_bc_rcv_gap(bcl)); msg_set_probe(hdr, probe); + msg_set_is_keepalive(hdr, probe || probe_reply); tipc_mon_prep(l->net, data, &dlen, mstate, l->bearer_id); msg_set_size(hdr, INT_H_SIZE + dlen); skb_trim(skb, INT_H_SIZE + dlen); @@ -1438,6 +1445,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, u16 rcv_nxt = l->rcv_nxt; u16 dlen = msg_data_sz(hdr); int mtyp = msg_type(hdr); + bool reply = msg_probe(hdr); void *data; char *if_name; int rc = 0; @@ -1524,9 +1532,9 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, /* Send NACK if peer has sent pkts we haven't received yet */ if (more(peers_snd_nxt, rcv_nxt) && !tipc_link_is_synching(l)) rcvgap = peers_snd_nxt - l->rcv_nxt; - if (rcvgap || (msg_probe(hdr))) - tipc_link_build_proto_msg(l, STATE_MSG, 0, rcvgap, - 0, 0, xmitq); + if (rcvgap || reply) + tipc_link_build_proto_msg(l, STATE_MSG, 0, reply, + rcvgap, 0, 0, xmitq); tipc_link_release_pkts(l, ack); /* If NACK, retransmit will now start at right position */ @@ -2118,14 +2126,14 @@ void tipc_link_set_tolerance(struct tipc_link *l, u32 tol, struct sk_buff_head *xmitq) { l->tolerance = tol; - tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, tol, 0, xmitq); + tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, tol, 0, xmitq); } void tipc_link_set_prio(struct tipc_link *l, u32 prio, struct sk_buff_head *xmitq) { l->priority = prio; - tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, prio, xmitq); + tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, prio, xmitq); } void tipc_link_set_abort_limit(struct tipc_link *l, u32 limit) diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index 9e109bb1a207..8e884ed06d4b 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -530,8 +530,11 @@ void tipc_mon_prep(struct net *net, void *data, int *dlen, u16 gen = mon->dom_gen; u16 len; - if (!tipc_mon_is_active(net, mon)) + /* Send invalid record if not active */ + if (!tipc_mon_is_active(net, mon)) { + dom->len = 0; return; + } /* Send only a dummy record with ack if peer has acked our last sent */ if (likely(state->acked_gen == gen)) { @@ -559,6 +562,12 @@ void tipc_mon_get_state(struct net *net, u32 addr, struct tipc_monitor *mon = tipc_monitor(net, bearer_id); struct tipc_peer *peer; + if (!tipc_mon_is_active(net, mon)) { + state->probing = false; + state->monitoring = true; + return; + } + /* Used cached state if table has not changed */ if (!state->probing && (state->list_gen == mon->list_gen) && @@ -578,9 +587,9 @@ void tipc_mon_get_state(struct net *net, u32 addr, read_unlock_bh(&mon->lock); } -static void mon_timeout(unsigned long m) +static void mon_timeout(struct timer_list *t) { - struct tipc_monitor *mon = (void *)m; + struct tipc_monitor *mon = from_timer(mon, t, timer); struct tipc_peer *self; int best_member_cnt = dom_size(mon->peer_cnt) - 1; @@ -623,7 +632,7 @@ int tipc_mon_create(struct net *net, int bearer_id) self->is_up = true; self->is_head = true; INIT_LIST_HEAD(&self->list); - setup_timer(&mon->timer, mon_timeout, (unsigned long)mon); + timer_setup(&mon->timer, mon_timeout, 0); mon->timer_intv = msecs_to_jiffies(MON_TIMEOUT + (tn->random & 0xffff)); mod_timer(&mon->timer, jiffies + mon->timer_intv); return 0; diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 17146c16ee2d..b0d07b35909d 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -174,7 +174,7 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) if (fragid == LAST_FRAGMENT) { TIPC_SKB_CB(head)->validated = false; - if (unlikely(!tipc_msg_validate(head))) + if (unlikely(!tipc_msg_validate(&head))) goto err; *buf = head; TIPC_SKB_CB(head)->tail = NULL; @@ -201,11 +201,21 @@ err: * TIPC will ignore the excess, under the assumption that it is optional info * introduced by a later release of the protocol. */ -bool tipc_msg_validate(struct sk_buff *skb) +bool tipc_msg_validate(struct sk_buff **_skb) { - struct tipc_msg *msg; + struct sk_buff *skb = *_skb; + struct tipc_msg *hdr; int msz, hsz; + /* Ensure that flow control ratio condition is satisfied */ + if (unlikely(skb->truesize / buf_roundup_len(skb) > 4)) { + skb = skb_copy(skb, GFP_ATOMIC); + if (!skb) + return false; + kfree_skb(*_skb); + *_skb = skb; + } + if (unlikely(TIPC_SKB_CB(skb)->validated)) return true; if (unlikely(!pskb_may_pull(skb, MIN_H_SIZE))) @@ -217,11 +227,11 @@ bool tipc_msg_validate(struct sk_buff *skb) if (unlikely(!pskb_may_pull(skb, hsz))) return false; - msg = buf_msg(skb); - if (unlikely(msg_version(msg) != TIPC_VERSION)) + hdr = buf_msg(skb); + if (unlikely(msg_version(hdr) != TIPC_VERSION)) return false; - msz = msg_size(msg); + msz = msg_size(hdr); if (unlikely(msz < hsz)) return false; if (unlikely((msz - hsz) > TIPC_MAX_USER_MSG_SIZE)) @@ -411,7 +421,7 @@ bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos) skb_pull(*iskb, offset); imsz = msg_size(buf_msg(*iskb)); skb_trim(*iskb, imsz); - if (unlikely(!tipc_msg_validate(*iskb))) + if (unlikely(!tipc_msg_validate(iskb))) goto none; *pos += align(imsz); return true; @@ -666,3 +676,10 @@ void __tipc_skb_queue_sorted(struct sk_buff_head *list, u16 seqno, } kfree_skb(skb); } + +void tipc_skb_reject(struct net *net, int err, struct sk_buff *skb, + struct sk_buff_head *xmitq) +{ + if (tipc_msg_reverse(tipc_own_addr(net), &skb, err)) + __skb_queue_tail(xmitq, skb); +} diff --git a/net/tipc/msg.h b/net/tipc/msg.h index c843fd2bc48d..3e4384c222f7 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -1,7 +1,7 @@ /* * net/tipc/msg.h: Include file for TIPC message header routines * - * Copyright (c) 2000-2007, 2014-2015 Ericsson AB + * Copyright (c) 2000-2007, 2014-2017 Ericsson AB * Copyright (c) 2005-2008, 2010-2011, Wind River Systems * All rights reserved. * @@ -61,10 +61,14 @@ struct plist; /* * Payload message types */ -#define TIPC_CONN_MSG 0 -#define TIPC_MCAST_MSG 1 -#define TIPC_NAMED_MSG 2 -#define TIPC_DIRECT_MSG 3 +#define TIPC_CONN_MSG 0 +#define TIPC_MCAST_MSG 1 +#define TIPC_NAMED_MSG 2 +#define TIPC_DIRECT_MSG 3 +#define TIPC_GRP_MEMBER_EVT 4 +#define TIPC_GRP_BCAST_MSG 5 +#define TIPC_GRP_MCAST_MSG 6 +#define TIPC_GRP_UCAST_MSG 7 /* * Internal message users @@ -73,11 +77,13 @@ struct plist; #define MSG_BUNDLER 6 #define LINK_PROTOCOL 7 #define CONN_MANAGER 8 +#define GROUP_PROTOCOL 9 #define TUNNEL_PROTOCOL 10 #define NAME_DISTRIBUTOR 11 #define MSG_FRAGMENTER 12 #define LINK_CONFIG 13 #define SOCK_WAKEUP 14 /* pseudo user */ +#define TOP_SRV 15 /* pseudo user */ /* * Message header sizes @@ -86,6 +92,7 @@ struct plist; #define BASIC_H_SIZE 32 /* Basic payload message */ #define NAMED_H_SIZE 40 /* Named payload message */ #define MCAST_H_SIZE 44 /* Multicast payload message */ +#define GROUP_H_SIZE 44 /* Group payload message */ #define INT_H_SIZE 40 /* Internal messages */ #define MIN_H_SIZE 24 /* Smallest legal TIPC header size */ #define MAX_H_SIZE 60 /* Largest possible TIPC header size */ @@ -96,6 +103,7 @@ struct plist; struct tipc_skb_cb { u32 bytes_read; + u32 orig_member; struct sk_buff *tail; bool validated; u16 chain_imp; @@ -188,6 +196,11 @@ static inline u32 msg_size(struct tipc_msg *m) return msg_bits(m, 0, 0, 0x1ffff); } +static inline u32 msg_blocks(struct tipc_msg *m) +{ + return (msg_size(m) / 1024) + 1; +} + static inline u32 msg_data_sz(struct tipc_msg *m) { return msg_size(m) - msg_hdr_sz(m); @@ -213,6 +226,16 @@ static inline void msg_set_dest_droppable(struct tipc_msg *m, u32 d) msg_set_bits(m, 0, 19, 1, d); } +static inline int msg_is_keepalive(struct tipc_msg *m) +{ + return msg_bits(m, 0, 19, 1); +} + +static inline void msg_set_is_keepalive(struct tipc_msg *m, u32 d) +{ + msg_set_bits(m, 0, 19, 1, d); +} + static inline int msg_src_droppable(struct tipc_msg *m) { return msg_bits(m, 0, 18, 1); @@ -251,6 +274,18 @@ static inline void msg_set_type(struct tipc_msg *m, u32 n) msg_set_bits(m, 1, 29, 0x7, n); } +static inline int msg_in_group(struct tipc_msg *m) +{ + int mtyp = msg_type(m); + + return mtyp >= TIPC_GRP_MEMBER_EVT && mtyp <= TIPC_GRP_UCAST_MSG; +} + +static inline bool msg_is_grp_evt(struct tipc_msg *m) +{ + return msg_type(m) == TIPC_GRP_MEMBER_EVT; +} + static inline u32 msg_named(struct tipc_msg *m) { return msg_type(m) == TIPC_NAMED_MSG; @@ -258,7 +293,10 @@ static inline u32 msg_named(struct tipc_msg *m) static inline u32 msg_mcast(struct tipc_msg *m) { - return msg_type(m) == TIPC_MCAST_MSG; + int mtyp = msg_type(m); + + return ((mtyp == TIPC_MCAST_MSG) || (mtyp == TIPC_GRP_BCAST_MSG) || + (mtyp == TIPC_GRP_MCAST_MSG)); } static inline u32 msg_connected(struct tipc_msg *m) @@ -514,6 +552,16 @@ static inline void msg_set_nameupper(struct tipc_msg *m, u32 n) #define DSC_RESP_MSG 1 /* + * Group protocol message types + */ +#define GRP_JOIN_MSG 0 +#define GRP_LEAVE_MSG 1 +#define GRP_ADV_MSG 2 +#define GRP_ACK_MSG 3 +#define GRP_RECLAIM_MSG 4 +#define GRP_REMIT_MSG 5 + +/* * Word 1 */ static inline u32 msg_seq_gap(struct tipc_msg *m) @@ -764,12 +812,12 @@ static inline void msg_set_conn_ack(struct tipc_msg *m, u32 n) msg_set_bits(m, 9, 16, 0xffff, n); } -static inline u32 msg_adv_win(struct tipc_msg *m) +static inline u16 msg_adv_win(struct tipc_msg *m) { return msg_bits(m, 9, 0, 0xffff); } -static inline void msg_set_adv_win(struct tipc_msg *m, u32 n) +static inline void msg_set_adv_win(struct tipc_msg *m, u16 n) { msg_set_bits(m, 9, 0, 0xffff, n); } @@ -794,6 +842,68 @@ static inline void msg_set_link_tolerance(struct tipc_msg *m, u32 n) msg_set_bits(m, 9, 0, 0xffff, n); } +static inline u16 msg_grp_bc_syncpt(struct tipc_msg *m) +{ + return msg_bits(m, 9, 16, 0xffff); +} + +static inline void msg_set_grp_bc_syncpt(struct tipc_msg *m, u16 n) +{ + msg_set_bits(m, 9, 16, 0xffff, n); +} + +static inline u16 msg_grp_bc_acked(struct tipc_msg *m) +{ + return msg_bits(m, 9, 16, 0xffff); +} + +static inline void msg_set_grp_bc_acked(struct tipc_msg *m, u16 n) +{ + msg_set_bits(m, 9, 16, 0xffff, n); +} + +static inline u16 msg_grp_remitted(struct tipc_msg *m) +{ + return msg_bits(m, 9, 16, 0xffff); +} + +static inline void msg_set_grp_remitted(struct tipc_msg *m, u16 n) +{ + msg_set_bits(m, 9, 16, 0xffff, n); +} + +/* Word 10 + */ +static inline u16 msg_grp_evt(struct tipc_msg *m) +{ + return msg_bits(m, 10, 0, 0x3); +} + +static inline void msg_set_grp_evt(struct tipc_msg *m, int n) +{ + msg_set_bits(m, 10, 0, 0x3, n); +} + +static inline u16 msg_grp_bc_ack_req(struct tipc_msg *m) +{ + return msg_bits(m, 10, 0, 0x1); +} + +static inline void msg_set_grp_bc_ack_req(struct tipc_msg *m, bool n) +{ + msg_set_bits(m, 10, 0, 0x1, n); +} + +static inline u16 msg_grp_bc_seqno(struct tipc_msg *m) +{ + return msg_bits(m, 10, 16, 0xffff); +} + +static inline void msg_set_grp_bc_seqno(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 10, 16, 0xffff, n); +} + static inline bool msg_peer_link_is_up(struct tipc_msg *m) { if (likely(msg_user(m) != LINK_PROTOCOL)) @@ -816,8 +926,10 @@ static inline bool msg_is_reset(struct tipc_msg *hdr) } struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp); -bool tipc_msg_validate(struct sk_buff *skb); +bool tipc_msg_validate(struct sk_buff **_skb); bool tipc_msg_reverse(u32 own_addr, struct sk_buff **skb, int err); +void tipc_skb_reject(struct net *net, int err, struct sk_buff *skb, + struct sk_buff_head *xmitq); void tipc_msg_init(u32 own_addr, struct tipc_msg *m, u32 user, u32 type, u32 hsize, u32 destnode); struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz, @@ -842,6 +954,11 @@ static inline u16 buf_seqno(struct sk_buff *skb) return msg_seqno(buf_msg(skb)); } +static inline int buf_roundup_len(struct sk_buff *skb) +{ + return (skb->len / 1024 + 1) * 1024; +} + /* tipc_skb_peek(): peek and reserve first buffer in list * @list: list to be peeked in * Returns pointer to first buffer in list, if any diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index bd0aac87b41a..b3829bcf63c7 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -43,6 +43,7 @@ #include "bcast.h" #include "addr.h" #include "node.h" +#include "group.h" #include <net/genetlink.h> #define TIPC_NAMETBL_SIZE 1024 /* must be a power of 2 */ @@ -596,18 +597,47 @@ not_found: return ref; } -/** - * tipc_nametbl_mc_translate - find multicast destinations - * - * Creates list of all local ports that overlap the given multicast address; - * also determines if any off-node ports overlap. - * - * Note: Publications with a scope narrower than 'limit' are ignored. - * (i.e. local node-scope publications mustn't receive messages arriving - * from another node, even if the multcast link brought it here) - * - * Returns non-zero if any off-node ports overlap - */ +bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 domain, + struct list_head *dsts, int *dstcnt, u32 exclude, + bool all) +{ + u32 self = tipc_own_addr(net); + struct publication *publ; + struct name_info *info; + struct name_seq *seq; + struct sub_seq *sseq; + + if (!tipc_in_scope(domain, self)) + return false; + + *dstcnt = 0; + rcu_read_lock(); + seq = nametbl_find_seq(net, type); + if (unlikely(!seq)) + goto exit; + spin_lock_bh(&seq->lock); + sseq = nameseq_find_subseq(seq, instance); + if (likely(sseq)) { + info = sseq->info; + list_for_each_entry(publ, &info->zone_list, zone_list) { + if (!tipc_in_scope(domain, publ->node)) + continue; + if (publ->ref == exclude && publ->node == self) + continue; + tipc_dest_push(dsts, publ->node, publ->ref); + (*dstcnt)++; + if (all) + continue; + list_move_tail(&publ->zone_list, &info->zone_list); + break; + } + } + spin_unlock_bh(&seq->lock); +exit: + rcu_read_unlock(); + return !list_empty(dsts); +} + int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper, u32 limit, struct list_head *dports) { @@ -634,7 +664,7 @@ int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper, info = sseq->info; list_for_each_entry(publ, &info->node_list, node_list) { if (publ->scope <= limit) - u32_push(dports, publ->ref); + tipc_dest_push(dports, 0, publ->ref); } if (info->cluster_list_size != info->node_list_size) @@ -667,7 +697,7 @@ void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower, spin_lock_bh(&seq->lock); sseq = seq->sseqs + nameseq_locate_subseq(seq, lower); stop = seq->sseqs + seq->first_free; - for (; sseq->lower <= upper && sseq != stop; sseq++) { + for (; sseq != stop && sseq->lower <= upper; sseq++) { info = sseq->info; list_for_each_entry(publ, &info->zone_list, zone_list) { if (tipc_in_scope(domain, publ->node)) @@ -679,6 +709,37 @@ exit: rcu_read_unlock(); } +/* 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 domain) +{ + struct sub_seq *sseq, *stop; + struct name_info *info; + struct publication *p; + struct name_seq *seq; + + rcu_read_lock(); + seq = nametbl_find_seq(net, type); + if (!seq) + goto exit; + + spin_lock_bh(&seq->lock); + sseq = seq->sseqs; + stop = seq->sseqs + seq->first_free; + for (; sseq != stop; sseq++) { + info = sseq->info; + list_for_each_entry(p, &info->zone_list, zone_list) { + if (!tipc_in_scope(domain, p->node)) + continue; + tipc_group_add_member(grp, p->node, p->ref); + } + } + spin_unlock_bh(&seq->lock); +exit: + rcu_read_unlock(); +} + /* * tipc_nametbl_publish - add name publication to network name tables */ @@ -1057,78 +1118,79 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } -bool u32_find(struct list_head *l, u32 value) +struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port) { - struct u32_item *item; + u64 value = (u64)node << 32 | port; + struct tipc_dest *dst; - list_for_each_entry(item, l, list) { - if (item->value == value) - return true; + list_for_each_entry(dst, l, list) { + if (dst->value != value) + continue; + return dst; } - return false; + return NULL; } -bool u32_push(struct list_head *l, u32 value) +bool tipc_dest_push(struct list_head *l, u32 node, u32 port) { - struct u32_item *item; + u64 value = (u64)node << 32 | port; + struct tipc_dest *dst; - list_for_each_entry(item, l, list) { - if (item->value == value) - return false; - } - item = kmalloc(sizeof(*item), GFP_ATOMIC); - if (unlikely(!item)) + if (tipc_dest_find(l, node, port)) return false; - item->value = value; - list_add(&item->list, l); + dst = kmalloc(sizeof(*dst), GFP_ATOMIC); + if (unlikely(!dst)) + return false; + dst->value = value; + list_add(&dst->list, l); return true; } -u32 u32_pop(struct list_head *l) +bool tipc_dest_pop(struct list_head *l, u32 *node, u32 *port) { - struct u32_item *item; - u32 value = 0; + struct tipc_dest *dst; if (list_empty(l)) - return 0; - item = list_first_entry(l, typeof(*item), list); - value = item->value; - list_del(&item->list); - kfree(item); - return value; + return false; + dst = list_first_entry(l, typeof(*dst), list); + if (port) + *port = dst->port; + if (node) + *node = dst->node; + list_del(&dst->list); + kfree(dst); + return true; } -bool u32_del(struct list_head *l, u32 value) +bool tipc_dest_del(struct list_head *l, u32 node, u32 port) { - struct u32_item *item, *tmp; + struct tipc_dest *dst; - list_for_each_entry_safe(item, tmp, l, list) { - if (item->value != value) - continue; - list_del(&item->list); - kfree(item); - return true; - } - return false; + dst = tipc_dest_find(l, node, port); + if (!dst) + return false; + list_del(&dst->list); + kfree(dst); + return true; } -void u32_list_purge(struct list_head *l) +void tipc_dest_list_purge(struct list_head *l) { - struct u32_item *item, *tmp; + struct tipc_dest *dst, *tmp; - list_for_each_entry_safe(item, tmp, l, list) { - list_del(&item->list); - kfree(item); + list_for_each_entry_safe(dst, tmp, l, list) { + list_del(&dst->list); + kfree(dst); } } -int u32_list_len(struct list_head *l) +int tipc_dest_list_len(struct list_head *l) { - struct u32_item *item; + struct tipc_dest *dst; int i = 0; - list_for_each_entry(item, l, list) { + list_for_each_entry(dst, l, list) { i++; } return i; diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index 6ebdeb1d84a5..71926e429446 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -40,6 +40,7 @@ struct tipc_subscription; struct tipc_plist; struct tipc_nlist; +struct tipc_group; /* * TIPC name types reserved for internal TIPC use (both current and planned) @@ -101,9 +102,14 @@ 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); int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper, u32 limit, struct list_head *dports); +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, u32 domain, 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_ref, u32 key); @@ -120,16 +126,22 @@ void tipc_nametbl_unsubscribe(struct tipc_subscription *s); int tipc_nametbl_init(struct net *net); void tipc_nametbl_stop(struct net *net); -struct u32_item { +struct tipc_dest { struct list_head list; - u32 value; + union { + struct { + u32 port; + u32 node; + }; + u64 value; + }; }; -bool u32_push(struct list_head *l, u32 value); -u32 u32_pop(struct list_head *l); -bool u32_find(struct list_head *l, u32 value); -bool u32_del(struct list_head *l, u32 value); -void u32_list_purge(struct list_head *l); -int u32_list_len(struct list_head *l); +struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port); +bool tipc_dest_push(struct list_head *l, u32 node, u32 port); +bool tipc_dest_pop(struct list_head *l, u32 *node, u32 *port); +bool tipc_dest_del(struct list_head *l, u32 node, u32 port); +void tipc_dest_list_purge(struct list_head *l); +int tipc_dest_list_len(struct list_head *l); #endif diff --git a/net/tipc/node.c b/net/tipc/node.c index 198dbc7adbe1..507017fe0f1b 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -153,11 +153,11 @@ static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete); static void node_lost_contact(struct tipc_node *n, struct sk_buff_head *inputq); static void tipc_node_delete(struct tipc_node *node); -static void tipc_node_timeout(unsigned long data); +static void tipc_node_timeout(struct timer_list *t); static void tipc_node_fsm_evt(struct tipc_node *n, int evt); static struct tipc_node *tipc_node_find(struct net *net, u32 addr); static void tipc_node_put(struct tipc_node *node); -static bool tipc_node_is_up(struct tipc_node *n); +static bool node_is_up(struct tipc_node *n); struct tipc_sock_conn { u32 port; @@ -361,7 +361,7 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities) goto exit; } tipc_node_get(n); - setup_timer(&n->timer, tipc_node_timeout, (unsigned long)n); + timer_setup(&n->timer, tipc_node_timeout, 0); n->keepalive_intv = U32_MAX; hlist_add_head_rcu(&n->hash, &tn->node_htable[tipc_hashfn(addr)]); list_for_each_entry_rcu(temp_node, &tn->node_list, list) { @@ -500,9 +500,9 @@ void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port) /* tipc_node_timeout - handle expiration of node timer */ -static void tipc_node_timeout(unsigned long data) +static void tipc_node_timeout(struct timer_list *t) { - struct tipc_node *n = (struct tipc_node *)data; + struct tipc_node *n = from_timer(n, t, timer); struct tipc_link_entry *le; struct sk_buff_head xmitq; int bearer_id; @@ -657,7 +657,7 @@ static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id, *slot1 = i; } - if (!tipc_node_is_up(n)) { + if (!node_is_up(n)) { if (tipc_link_peer_is_down(l)) tipc_node_fsm_evt(n, PEER_LOST_CONTACT_EVT); tipc_node_fsm_evt(n, SELF_LOST_CONTACT_EVT); @@ -717,11 +717,27 @@ static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete) tipc_sk_rcv(n->net, &le->inputq); } -static bool tipc_node_is_up(struct tipc_node *n) +static bool node_is_up(struct tipc_node *n) { return n->active_links[0] != INVALID_BEARER_ID; } +bool tipc_node_is_up(struct net *net, u32 addr) +{ + struct tipc_node *n; + bool retval = false; + + if (in_own_node(net, addr)) + return true; + + n = tipc_node_find(net, addr); + if (!n) + return false; + retval = node_is_up(n); + tipc_node_put(n); + return retval; +} + void tipc_node_check_dest(struct net *net, u32 onode, struct tipc_bearer *b, u16 capabilities, u32 signature, @@ -1149,7 +1165,7 @@ static int __tipc_nl_add_node(struct tipc_nl_msg *msg, struct tipc_node *node) if (nla_put_u32(msg->skb, TIPC_NLA_NODE_ADDR, node->addr)) goto attr_msg_full; - if (tipc_node_is_up(node)) + if (node_is_up(node)) if (nla_put_flag(msg->skb, TIPC_NLA_NODE_UP)) goto attr_msg_full; @@ -1238,6 +1254,22 @@ int tipc_node_xmit_skb(struct net *net, struct sk_buff *skb, u32 dnode, return 0; } +/* tipc_node_distr_xmit(): send single buffer msgs to individual destinations + * Note: this is only for SYSTEM_IMPORTANCE messages, which cannot be rejected + */ +int tipc_node_distr_xmit(struct net *net, struct sk_buff_head *xmitq) +{ + struct sk_buff *skb; + u32 selector, dnode; + + while ((skb = __skb_dequeue(xmitq))) { + selector = msg_origport(buf_msg(skb)); + dnode = msg_destnode(buf_msg(skb)); + tipc_node_xmit_skb(net, skb, dnode, selector); + } + return 0; +} + void tipc_node_broadcast(struct net *net, struct sk_buff *skb) { struct sk_buff *txskb; @@ -1249,7 +1281,7 @@ void tipc_node_broadcast(struct net *net, struct sk_buff *skb) dst = n->addr; if (in_own_node(net, dst)) continue; - if (!tipc_node_is_up(n)) + if (!node_is_up(n)) continue; txskb = pskb_copy(skb, GFP_ATOMIC); if (!txskb) @@ -1507,7 +1539,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b) __skb_queue_head_init(&xmitq); /* Ensure message is well-formed before touching the header */ - if (unlikely(!tipc_msg_validate(skb))) + if (unlikely(!tipc_msg_validate(&skb))) goto discard; hdr = buf_msg(skb); usr = msg_user(hdr); diff --git a/net/tipc/node.h b/net/tipc/node.h index 898c22916984..acd58d23a70e 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -48,7 +48,8 @@ enum { TIPC_BCAST_SYNCH = (1 << 1), TIPC_BCAST_STATE_NACK = (1 << 2), TIPC_BLOCK_FLOWCTL = (1 << 3), - TIPC_BCAST_RCAST = (1 << 4) + TIPC_BCAST_RCAST = (1 << 4), + TIPC_MCAST_GROUPS = (1 << 5) }; #define TIPC_NODE_CAPABILITIES (TIPC_BCAST_SYNCH | \ @@ -68,6 +69,7 @@ int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 node, char *linkname, size_t len); int tipc_node_xmit(struct net *net, struct sk_buff_head *list, u32 dnode, int selector); +int tipc_node_distr_xmit(struct net *net, struct sk_buff_head *list); int tipc_node_xmit_skb(struct net *net, struct sk_buff *skb, u32 dest, u32 selector); void tipc_node_subscribe(struct net *net, struct list_head *subscr, u32 addr); @@ -76,6 +78,7 @@ void tipc_node_broadcast(struct net *net, struct sk_buff *skb); int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port); void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port); int tipc_node_get_mtu(struct net *net, u32 addr, u32 sel); +bool tipc_node_is_up(struct net *net, u32 addr); u16 tipc_node_get_capabilities(struct net *net, u32 addr); int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_node_dump_link(struct sk_buff *skb, struct netlink_callback *cb); diff --git a/net/tipc/server.c b/net/tipc/server.c index 3cd6402e812c..acaef80fb88c 100644 --- a/net/tipc/server.c +++ b/net/tipc/server.c @@ -36,6 +36,8 @@ #include "server.h" #include "core.h" #include "socket.h" +#include "addr.h" +#include "msg.h" #include <net/sock.h> #include <linux/module.h> @@ -105,13 +107,11 @@ static void tipc_conn_kref_release(struct kref *kref) kernel_bind(sock, (struct sockaddr *)saddr, sizeof(*saddr)); sock_release(sock); con->sock = NULL; - - spin_lock_bh(&s->idr_lock); - idr_remove(&s->conn_idr, con->conid); - s->idr_in_use--; - spin_unlock_bh(&s->idr_lock); } - + spin_lock_bh(&s->idr_lock); + idr_remove(&s->conn_idr, con->conid); + s->idr_in_use--; + spin_unlock_bh(&s->idr_lock); tipc_clean_outqueues(con); kfree(con); } @@ -197,7 +197,8 @@ static void tipc_close_conn(struct tipc_conn *con) struct tipc_server *s = con->server; if (test_and_clear_bit(CF_CONNECTED, &con->flags)) { - tipc_unregister_callbacks(con); + if (con->sock) + tipc_unregister_callbacks(con); if (con->conid) s->tipc_conn_release(con->conid, con->usr_data); @@ -207,8 +208,8 @@ static void tipc_close_conn(struct tipc_conn *con) * are harmless for us here as we have already deleted this * connection from server connection list. */ - kernel_sock_shutdown(con->sock, SHUT_RDWR); - + if (con->sock) + kernel_sock_shutdown(con->sock, SHUT_RDWR); conn_put(con); } } @@ -487,38 +488,104 @@ void tipc_conn_terminate(struct tipc_server *s, int conid) } } +bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, + u32 lower, u32 upper, int *conid) +{ + struct tipc_subscriber *scbr; + struct tipc_subscr sub; + struct tipc_server *s; + struct tipc_conn *con; + + sub.seq.type = type; + sub.seq.lower = lower; + sub.seq.upper = upper; + sub.timeout = TIPC_WAIT_FOREVER; + sub.filter = TIPC_SUB_PORTS; + *(u32 *)&sub.usr_handle = port; + + con = tipc_alloc_conn(tipc_topsrv(net)); + if (IS_ERR(con)) + return false; + + *conid = con->conid; + s = con->server; + scbr = s->tipc_conn_new(*conid); + if (!scbr) { + tipc_close_conn(con); + return false; + } + + con->usr_data = scbr; + con->sock = NULL; + s->tipc_conn_recvmsg(net, *conid, NULL, scbr, &sub, sizeof(sub)); + return true; +} + +void tipc_topsrv_kern_unsubscr(struct net *net, int conid) +{ + struct tipc_conn *con; + + con = tipc_conn_lookup(tipc_topsrv(net), conid); + if (!con) + return; + tipc_close_conn(con); + conn_put(con); +} + +static void tipc_send_kern_top_evt(struct net *net, struct tipc_event *evt) +{ + u32 port = *(u32 *)&evt->s.usr_handle; + u32 self = tipc_own_addr(net); + struct sk_buff_head evtq; + struct sk_buff *skb; + + skb = tipc_msg_create(TOP_SRV, 0, INT_H_SIZE, sizeof(*evt), + self, self, port, port, 0); + if (!skb) + return; + msg_set_dest_droppable(buf_msg(skb), true); + memcpy(msg_data(buf_msg(skb)), evt, sizeof(*evt)); + skb_queue_head_init(&evtq); + __skb_queue_tail(&evtq, skb); + tipc_sk_rcv(net, &evtq); +} + static void tipc_send_to_sock(struct tipc_conn *con) { - int count = 0; struct tipc_server *s = con->server; struct outqueue_entry *e; + struct tipc_event *evt; struct msghdr msg; + int count = 0; int ret; spin_lock_bh(&con->outqueue_lock); while (test_bit(CF_CONNECTED, &con->flags)) { - e = list_entry(con->outqueue.next, struct outqueue_entry, - list); + e = list_entry(con->outqueue.next, struct outqueue_entry, list); if ((struct list_head *) e == &con->outqueue) break; - spin_unlock_bh(&con->outqueue_lock); - memset(&msg, 0, sizeof(msg)); - msg.msg_flags = MSG_DONTWAIT; + spin_unlock_bh(&con->outqueue_lock); - if (s->type == SOCK_DGRAM || s->type == SOCK_RDM) { - msg.msg_name = &e->dest; - msg.msg_namelen = sizeof(struct sockaddr_tipc); - } - ret = kernel_sendmsg(con->sock, &msg, &e->iov, 1, - e->iov.iov_len); - if (ret == -EWOULDBLOCK || ret == 0) { - cond_resched(); - goto out; - } else if (ret < 0) { - goto send_err; + if (con->sock) { + memset(&msg, 0, sizeof(msg)); + msg.msg_flags = MSG_DONTWAIT; + if (s->type == SOCK_DGRAM || s->type == SOCK_RDM) { + msg.msg_name = &e->dest; + msg.msg_namelen = sizeof(struct sockaddr_tipc); + } + ret = kernel_sendmsg(con->sock, &msg, &e->iov, 1, + e->iov.iov_len); + if (ret == -EWOULDBLOCK || ret == 0) { + cond_resched(); + goto out; + } else if (ret < 0) { + goto send_err; + } + } else { + evt = e->iov.iov_base; + tipc_send_kern_top_evt(s->net, evt); } - /* Don't starve users filling buffers */ if (++count >= MAX_SEND_MSG_COUNT) { cond_resched(); diff --git a/net/tipc/server.h b/net/tipc/server.h index 34f8055afa3b..2113c9192633 100644 --- a/net/tipc/server.h +++ b/net/tipc/server.h @@ -83,13 +83,16 @@ struct tipc_server { int tipc_conn_sendmsg(struct tipc_server *s, int conid, struct sockaddr_tipc *addr, void *data, size_t len); +bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, + u32 lower, u32 upper, int *conid); +void tipc_topsrv_kern_unsubscr(struct net *net, int conid); + /** * tipc_conn_terminate - terminate connection with server * * Note: Must call it in process context since it might sleep */ void tipc_conn_terminate(struct tipc_server *s, int conid); - int tipc_server_start(struct tipc_server *s); void tipc_server_stop(struct tipc_server *s); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index d50edd6e0019..5d18c0caa92b 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1,7 +1,7 @@ /* * net/tipc/socket.c: TIPC socket API * - * Copyright (c) 2001-2007, 2012-2016, Ericsson AB + * Copyright (c) 2001-2007, 2012-2017, Ericsson AB * Copyright (c) 2004-2008, 2010-2013, Wind River Systems * All rights reserved. * @@ -45,9 +45,10 @@ #include "socket.h" #include "bcast.h" #include "netlink.h" +#include "group.h" #define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */ -#define CONN_PROBING_INTERVAL msecs_to_jiffies(3600000) /* [ms] => 1 h */ +#define CONN_PROBING_INTV msecs_to_jiffies(3600000) /* [ms] => 1 h */ #define TIPC_FWD_MSG 1 #define TIPC_MAX_PORT 0xffffffff #define TIPC_MIN_PORT 1 @@ -61,6 +62,11 @@ enum { TIPC_CONNECTING = TCP_SYN_SENT, }; +struct sockaddr_pair { + struct sockaddr_tipc sock; + struct sockaddr_tipc member; +}; + /** * struct tipc_sock - TIPC socket structure * @sk: socket - interacts with 'port' and with user via the socket API @@ -78,7 +84,7 @@ enum { * @conn_timeout: the time we can wait for an unresponded setup request * @dupl_rcvcnt: number of bytes counted twice, in both backlog and rcv queue * @cong_link_cnt: number of congested links - * @sent_unacked: # messages sent by socket, and not yet acked by peer + * @snt_unacked: # messages sent by socket, and not yet acked by peer * @rcv_unacked: # messages read by user, but not yet acked back to peer * @peer: 'connected' peer for dgram/rdm * @node: hash table node @@ -109,20 +115,22 @@ struct tipc_sock { struct rhash_head node; struct tipc_mc_method mc_method; struct rcu_head rcu; + struct tipc_group *group; }; -static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb); +static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb); static void tipc_data_ready(struct sock *sk); static void tipc_write_space(struct sock *sk); static void tipc_sock_destruct(struct sock *sk); 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(unsigned long data); +static void tipc_sk_timeout(struct timer_list *t); static int tipc_sk_publish(struct tipc_sock *tsk, uint scope, struct tipc_name_seq const *seq); static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope, struct tipc_name_seq const *seq); +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); static void tipc_sk_remove(struct tipc_sock *tsk); @@ -193,6 +201,11 @@ static bool tsk_conn_cong(struct tipc_sock *tsk) return tsk->snt_unacked > tsk->snd_win; } +static u16 tsk_blocks(int len) +{ + return ((len / FLOWCTL_BLK_SZ) + 1); +} + /* tsk_blocks(): translate a buffer size in bytes to number of * advertisable blocks, taking into account the ratio truesize(len)/len * We can trust that this ratio is always < 4 for len >= FLOWCTL_BLK_SZ @@ -451,9 +464,9 @@ static int tipc_sk_create(struct net *net, struct socket *sock, NAMED_H_SIZE, 0); msg_set_origport(msg, tsk->portid); - setup_timer(&sk->sk_timer, tipc_sk_timeout, (unsigned long)tsk); + timer_setup(&sk->sk_timer, tipc_sk_timeout, 0); sk->sk_shutdown = 0; - sk->sk_backlog_rcv = tipc_backlog_rcv; + sk->sk_backlog_rcv = tipc_sk_backlog_rcv; sk->sk_rcvbuf = sysctl_tipc_rmem[1]; sk->sk_data_ready = tipc_data_ready; sk->sk_write_space = tipc_write_space; @@ -559,13 +572,14 @@ 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); sk_stop_timer(sk, &sk->sk_timer); tipc_sk_remove(tsk); /* Reject any messages that accumulated in backlog queue */ release_sock(sk); - u32_list_purge(&tsk->cong_links); + tipc_dest_list_purge(&tsk->cong_links); tsk->cong_link_cnt = 0; call_rcu(&tsk->rcu, tipc_sk_callback); sock->sk = NULL; @@ -601,7 +615,10 @@ static int tipc_bind(struct socket *sock, struct sockaddr *uaddr, res = tipc_sk_withdraw(tsk, 0, NULL); goto exit; } - + if (tsk->group) { + res = -EACCES; + goto exit; + } if (uaddr_len < sizeof(struct sockaddr_tipc)) { res = -EINVAL; goto exit; @@ -698,38 +715,41 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock, { struct sock *sk = sock->sk; struct tipc_sock *tsk = tipc_sk(sk); - u32 mask = 0; + struct tipc_group *grp = tsk->group; + u32 revents = 0; sock_poll_wait(file, sk_sleep(sk), wait); if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLRDHUP | POLLIN | POLLRDNORM; + revents |= POLLRDHUP | POLLIN | POLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) - mask |= POLLHUP; + revents |= POLLHUP; switch (sk->sk_state) { case TIPC_ESTABLISHED: if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk)) - mask |= POLLOUT; + revents |= POLLOUT; /* fall thru' */ case TIPC_LISTEN: case TIPC_CONNECTING: if (!skb_queue_empty(&sk->sk_receive_queue)) - mask |= (POLLIN | POLLRDNORM); + revents |= POLLIN | POLLRDNORM; break; case TIPC_OPEN: - if (!tsk->cong_link_cnt) - mask |= POLLOUT; - if (tipc_sk_type_connectionless(sk) && - (!skb_queue_empty(&sk->sk_receive_queue))) - mask |= (POLLIN | POLLRDNORM); + if (!grp || tipc_group_size(grp)) + if (!tsk->cong_link_cnt) + revents |= POLLOUT; + if (!tipc_sk_type_connectionless(sk)) + break; + if (skb_queue_empty(&sk->sk_receive_queue)) + break; + revents |= POLLIN | POLLRDNORM; break; case TIPC_DISCONNECTING: - mask = (POLLIN | POLLRDNORM | POLLHUP); + revents = POLLIN | POLLRDNORM | POLLHUP; break; } - - return mask; + return revents; } /** @@ -757,6 +777,9 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, struct tipc_nlist dsts; int rc; + if (tsk->group) + return -EACCES; + /* Block or return if any destination link is congested */ rc = tipc_wait_for_cond(sock, &timeout, !tsk->cong_link_cnt); if (unlikely(rc)) @@ -794,6 +817,296 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, } /** + * tipc_send_group_msg - send a message to a member in the group + * @net: network namespace + * @m: message to send + * @mb: group member + * @dnode: destination node + * @dport: destination port + * @dlen: total length of message data + */ +static int tipc_send_group_msg(struct net *net, struct tipc_sock *tsk, + struct msghdr *m, struct tipc_member *mb, + u32 dnode, u32 dport, int dlen) +{ + u16 bc_snd_nxt = tipc_group_bc_snd_nxt(tsk->group); + struct tipc_mc_method *method = &tsk->mc_method; + int blks = tsk_blocks(GROUP_H_SIZE + dlen); + struct tipc_msg *hdr = &tsk->phdr; + struct sk_buff_head pkts; + int mtu, rc; + + /* Complete message header */ + msg_set_type(hdr, TIPC_GRP_UCAST_MSG); + msg_set_hdr_sz(hdr, GROUP_H_SIZE); + msg_set_destport(hdr, dport); + msg_set_destnode(hdr, dnode); + msg_set_grp_bc_seqno(hdr, bc_snd_nxt); + + /* Build message as chain of buffers */ + skb_queue_head_init(&pkts); + mtu = tipc_node_get_mtu(net, dnode, tsk->portid); + rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts); + if (unlikely(rc != dlen)) + return rc; + + /* Send message */ + rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid); + if (unlikely(rc == -ELINKCONG)) { + tipc_dest_push(&tsk->cong_links, dnode, 0); + tsk->cong_link_cnt++; + } + + /* Update send window */ + tipc_group_update_member(mb, blks); + + /* A broadcast sent within next EXPIRE period must follow same path */ + method->rcast = true; + method->mandatory = true; + return dlen; +} + +/** + * tipc_send_group_unicast - send message to a member in the group + * @sock: socket structure + * @m: message to send + * @dlen: total length of message data + * @timeout: timeout to wait for wakeup + * + * Called from function tipc_sendmsg(), which has done all sanity checks + * Returns the number of bytes sent on success, or errno + */ +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); + int blks = tsk_blocks(GROUP_H_SIZE + dlen); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_group *grp = tsk->group; + struct net *net = sock_net(sk); + struct tipc_member *mb = NULL; + u32 node, port; + int rc; + + node = dest->addr.id.node; + port = dest->addr.id.ref; + if (!port && !node) + return -EHOSTUNREACH; + + /* Block or return if destination link or member is congested */ + rc = tipc_wait_for_cond(sock, &timeout, + !tipc_dest_find(&tsk->cong_links, node, 0) && + !tipc_group_cong(grp, node, port, blks, &mb)); + if (unlikely(rc)) + return rc; + + if (unlikely(!mb)) + return -EHOSTUNREACH; + + rc = tipc_send_group_msg(net, tsk, m, mb, node, port, dlen); + + return rc ? rc : dlen; +} + +/** + * tipc_send_group_anycast - send message to any member with given identity + * @sock: socket structure + * @m: message to send + * @dlen: total length of message data + * @timeout: timeout to wait for wakeup + * + * Called from function tipc_sendmsg(), which has done all sanity checks + * Returns the number of bytes sent on success, or errno + */ +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 sock *sk = sock->sk; + struct tipc_sock *tsk = tipc_sk(sk); + struct list_head *cong_links = &tsk->cong_links; + int blks = tsk_blocks(GROUP_H_SIZE + dlen); + struct tipc_group *grp = tsk->group; + struct tipc_member *first = NULL; + struct tipc_member *mbr = NULL; + struct net *net = sock_net(sk); + u32 node, port, exclude; + u32 type, inst, domain; + struct list_head dsts; + int lookups = 0; + int dstcnt, rc; + bool cong; + + INIT_LIST_HEAD(&dsts); + + type = dest->addr.name.name.type; + inst = dest->addr.name.name.instance; + domain = addr_domain(net, dest->scope); + exclude = tipc_group_exclude(grp); + + while (++lookups < 4) { + first = NULL; + + /* Look for a non-congested destination member, if any */ + while (1) { + if (!tipc_nametbl_lookup(net, type, inst, domain, &dsts, + &dstcnt, exclude, false)) + return -EHOSTUNREACH; + tipc_dest_pop(&dsts, &node, &port); + cong = tipc_group_cong(grp, node, port, blks, &mbr); + if (!cong) + break; + if (mbr == first) + break; + if (!first) + first = mbr; + } + + /* Start over if destination was not in member list */ + if (unlikely(!mbr)) + continue; + + if (likely(!cong && !tipc_dest_find(cong_links, node, 0))) + break; + + /* Block or return if destination link or member is congested */ + rc = tipc_wait_for_cond(sock, &timeout, + !tipc_dest_find(cong_links, node, 0) && + !tipc_group_cong(grp, node, port, + blks, &mbr)); + if (unlikely(rc)) + return rc; + + /* Send, unless destination disappeared while waiting */ + if (likely(mbr)) + break; + } + + if (unlikely(lookups >= 4)) + return -EHOSTUNREACH; + + rc = tipc_send_group_msg(net, tsk, m, mbr, node, port, dlen); + + return rc ? rc : dlen; +} + +/** + * tipc_send_group_bcast - send message to all members in communication group + * @sk: socket structure + * @m: message to send + * @dlen: total length of message data + * @timeout: timeout to wait for wakeup + * + * Called from function tipc_sendmsg(), which has done all sanity checks + * Returns the number of bytes sent on success, or errno + */ +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 sock *sk = sock->sk; + struct net *net = sock_net(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_group *grp = tsk->group; + struct tipc_nlist *dsts = tipc_group_dests(grp); + struct tipc_mc_method *method = &tsk->mc_method; + bool ack = method->mandatory && method->rcast; + int blks = tsk_blocks(MCAST_H_SIZE + dlen); + struct tipc_msg *hdr = &tsk->phdr; + int mtu = tipc_bcast_get_mtu(net); + struct sk_buff_head pkts; + int rc = -EHOSTUNREACH; + + if (!dsts->local && !dsts->remote) + return -EHOSTUNREACH; + + /* Block or return if any destination link or member is congested */ + rc = tipc_wait_for_cond(sock, &timeout, !tsk->cong_link_cnt && + !tipc_group_bc_cong(grp, blks)); + if (unlikely(rc)) + return rc; + + /* Complete message header */ + if (dest) { + msg_set_type(hdr, TIPC_GRP_MCAST_MSG); + msg_set_nameinst(hdr, dest->addr.name.name.instance); + } else { + msg_set_type(hdr, TIPC_GRP_BCAST_MSG); + msg_set_nameinst(hdr, 0); + } + msg_set_hdr_sz(hdr, GROUP_H_SIZE); + msg_set_destport(hdr, 0); + msg_set_destnode(hdr, 0); + msg_set_grp_bc_seqno(hdr, tipc_group_bc_snd_nxt(grp)); + + /* Avoid getting stuck with repeated forced replicasts */ + msg_set_grp_bc_ack_req(hdr, ack); + + /* Build message as chain of buffers */ + skb_queue_head_init(&pkts); + rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts); + if (unlikely(rc != dlen)) + return rc; + + /* Send message */ + rc = tipc_mcast_xmit(net, &pkts, method, dsts, &tsk->cong_link_cnt); + if (unlikely(rc)) + return rc; + + /* Update broadcast sequence number and send windows */ + tipc_group_update_bc_members(tsk->group, blks, ack); + + /* Broadcast link is now free to choose method for next broadcast */ + method->mandatory = false; + method->expires = jiffies; + + return dlen; +} + +/** + * tipc_send_group_mcast - send message to all members with given identity + * @sock: socket structure + * @m: message to send + * @dlen: total length of message data + * @timeout: timeout to wait for wakeup + * + * Called from function tipc_sendmsg(), which has done all sanity checks + * Returns the number of bytes sent on success, or errno + */ +static int tipc_send_group_mcast(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_name_seq *seq = &dest->addr.nameseq; + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_group *grp = tsk->group; + struct net *net = sock_net(sk); + u32 domain, exclude, dstcnt; + struct list_head dsts; + + INIT_LIST_HEAD(&dsts); + + if (seq->lower != seq->upper) + return -ENOTSUPP; + + domain = addr_domain(net, dest->scope); + exclude = tipc_group_exclude(grp); + if (!tipc_nametbl_lookup(net, seq->type, seq->lower, domain, + &dsts, &dstcnt, exclude, true)) + return -EHOSTUNREACH; + + if (dstcnt == 1) { + tipc_dest_pop(&dsts, &dest->addr.id.node, &dest->addr.id.ref); + return tipc_send_group_unicast(sock, m, dlen, timeout); + } + + tipc_dest_list_purge(&dsts); + return tipc_send_group_bcast(sock, m, dlen, timeout); +} + +/** * tipc_sk_mcast_rcv - Deliver multicast messages to all destination sockets * @arrvq: queue with arriving messages, to be cloned after destination lookup * @inputq: queue with cloned messages, delivered to socket after dest lookup @@ -803,13 +1116,15 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, struct sk_buff_head *inputq) { - struct tipc_msg *msg; - struct list_head dports; - u32 portid; u32 scope = TIPC_CLUSTER_SCOPE; - struct sk_buff_head tmpq; - uint hsz; + u32 self = tipc_own_addr(net); struct sk_buff *skb, *_skb; + u32 lower = 0, upper = ~0; + struct sk_buff_head tmpq; + u32 portid, oport, onode; + struct list_head dports; + struct tipc_msg *msg; + int user, mtyp, hsz; __skb_queue_head_init(&tmpq); INIT_LIST_HEAD(&dports); @@ -817,17 +1132,32 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, skb = tipc_skb_peek(arrvq, &inputq->lock); for (; skb; skb = tipc_skb_peek(arrvq, &inputq->lock)) { msg = buf_msg(skb); + user = msg_user(msg); + mtyp = msg_type(msg); + if (mtyp == TIPC_GRP_UCAST_MSG || user == GROUP_PROTOCOL) { + spin_lock_bh(&inputq->lock); + if (skb_peek(arrvq) == skb) { + __skb_dequeue(arrvq); + __skb_queue_tail(inputq, skb); + } + refcount_dec(&skb->users); + spin_unlock_bh(&inputq->lock); + continue; + } hsz = skb_headroom(skb) + msg_hdr_sz(msg); - - if (in_own_node(net, msg_orignode(msg))) + oport = msg_origport(msg); + onode = msg_orignode(msg); + if (onode == self) scope = TIPC_NODE_SCOPE; /* Create destination port list and message clones: */ - tipc_nametbl_mc_translate(net, - msg_nametype(msg), msg_namelower(msg), - msg_nameupper(msg), scope, &dports); - portid = u32_pop(&dports); - for (; portid; portid = u32_pop(&dports)) { + if (!msg_in_group(msg)) { + lower = msg_namelower(msg); + upper = msg_nameupper(msg); + } + tipc_nametbl_mc_translate(net, msg_nametype(msg), lower, upper, + scope, &dports); + while (tipc_dest_pop(&dports, NULL, &portid)) { _skb = __pskb_copy(skb, hsz, GFP_ATOMIC); if (_skb) { msg_set_destport(buf_msg(_skb), portid); @@ -850,16 +1180,16 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, } /** - * tipc_sk_proto_rcv - receive a connection mng protocol message + * tipc_sk_conn_proto_rcv - receive a connection mng protocol message * @tsk: receiving socket * @skb: pointer to message buffer. */ -static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb, - struct sk_buff_head *xmitq) +static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb, + struct sk_buff_head *xmitq) { - struct sock *sk = &tsk->sk; - u32 onode = tsk_own_node(tsk); struct tipc_msg *hdr = buf_msg(skb); + u32 onode = tsk_own_node(tsk); + struct sock *sk = &tsk->sk; int mtyp = msg_type(hdr); bool conn_cong; @@ -931,6 +1261,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) 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_name_seq *seq; struct sk_buff_head pkts; @@ -941,18 +1272,31 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) 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)) + return -EINVAL; + } + + if (grp) { + if (!dest) + return tipc_send_group_bcast(sock, m, dlen, timeout); + if (dest->addrtype == TIPC_ADDR_NAME) + return tipc_send_group_anycast(sock, m, dlen, timeout); + if (dest->addrtype == TIPC_ADDR_ID) + return tipc_send_group_unicast(sock, m, dlen, timeout); + if (dest->addrtype == TIPC_ADDR_MCAST) + return tipc_send_group_mcast(sock, m, dlen, timeout); + return -EINVAL; + } + if (unlikely(!dest)) { dest = &tsk->peer; if (!syn || dest->family != AF_TIPC) return -EDESTADDRREQ; } - if (unlikely(m->msg_namelen < sizeof(*dest))) - return -EINVAL; - - if (unlikely(dest->family != AF_TIPC)) - return -EINVAL; - if (unlikely(syn)) { if (sk->sk_state == TIPC_LISTEN) return -EPIPE; @@ -985,7 +1329,6 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) msg_set_destport(hdr, dport); if (unlikely(!dport && !dnode)) return -EHOSTUNREACH; - } else if (dest->addrtype == TIPC_ADDR_ID) { dnode = dest->addr.id.node; msg_set_type(hdr, TIPC_DIRECT_MSG); @@ -996,7 +1339,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) } /* Block or return if destination link is congested */ - rc = tipc_wait_for_cond(sock, &timeout, !u32_find(clinks, dnode)); + rc = tipc_wait_for_cond(sock, &timeout, + !tipc_dest_find(clinks, dnode, 0)); if (unlikely(rc)) return rc; @@ -1008,7 +1352,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid); if (unlikely(rc == -ELINKCONG)) { - u32_push(clinks, dnode); + tipc_dest_push(clinks, dnode, 0); tsk->cong_link_cnt++; rc = 0; } @@ -1128,7 +1472,7 @@ static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port, msg_set_lookup_scope(msg, 0); msg_set_hdr_sz(msg, SHORT_H_SIZE); - sk_reset_timer(sk, &sk->sk_timer, jiffies + CONN_PROBING_INTERVAL); + sk_reset_timer(sk, &sk->sk_timer, jiffies + CONN_PROBING_INTV); tipc_set_sk_state(sk, TIPC_ESTABLISHED); tipc_node_add_conn(net, peer_node, tsk->portid, peer_port); tsk->max_pkt = tipc_node_get_mtu(net, peer_node, tsk->portid); @@ -1142,26 +1486,38 @@ static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port, } /** - * set_orig_addr - capture sender's address for received message + * tipc_sk_set_orig_addr - capture sender's address for received message * @m: descriptor for message info - * @msg: received message header + * @hdr: received message header * * Note: Address is not captured if not requested by receiver. */ -static void set_orig_addr(struct msghdr *m, struct tipc_msg *msg) +static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb) { - DECLARE_SOCKADDR(struct sockaddr_tipc *, addr, m->msg_name); + DECLARE_SOCKADDR(struct sockaddr_pair *, srcaddr, m->msg_name); + struct tipc_msg *hdr = buf_msg(skb); - if (addr) { - addr->family = AF_TIPC; - addr->addrtype = TIPC_ADDR_ID; - memset(&addr->addr, 0, sizeof(addr->addr)); - addr->addr.id.ref = msg_origport(msg); - addr->addr.id.node = msg_orignode(msg); - addr->addr.name.domain = 0; /* could leave uninitialized */ - addr->scope = 0; /* could leave uninitialized */ - m->msg_namelen = sizeof(struct sockaddr_tipc); - } + if (!srcaddr) + return; + + srcaddr->sock.family = AF_TIPC; + srcaddr->sock.addrtype = TIPC_ADDR_ID; + srcaddr->sock.addr.id.ref = msg_origport(hdr); + srcaddr->sock.addr.id.node = msg_orignode(hdr); + srcaddr->sock.addr.name.domain = 0; + srcaddr->sock.scope = 0; + m->msg_namelen = sizeof(struct sockaddr_tipc); + + if (!msg_in_group(hdr)) + return; + + /* Group message users may also want to know sending member's id */ + srcaddr->member.family = AF_TIPC; + srcaddr->member.addrtype = TIPC_ADDR_NAME; + srcaddr->member.addr.name.name.type = msg_nametype(hdr); + srcaddr->member.addr.name.name.instance = TIPC_SKB_CB(skb)->orig_member; + srcaddr->member.addr.name.domain = 0; + m->msg_namelen = sizeof(*srcaddr); } /** @@ -1318,11 +1674,13 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, size_t buflen, int flags) { struct sock *sk = sock->sk; - struct tipc_sock *tsk = tipc_sk(sk); - struct sk_buff *skb; - struct tipc_msg *hdr; bool connected = !tipc_sk_type_connectionless(sk); + struct tipc_sock *tsk = tipc_sk(sk); int rc, err, hlen, dlen, copy; + struct sk_buff_head xmitq; + struct tipc_msg *hdr; + struct sk_buff *skb; + bool grp_evt; long timeout; /* Catch invalid receive requests */ @@ -1336,8 +1694,8 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, } timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + /* Step rcv queue to first msg with data or error; wait if necessary */ do { - /* Look at first msg in receive queue; wait if necessary */ rc = tipc_wait_for_rcvmsg(sock, &timeout); if (unlikely(rc)) goto exit; @@ -1346,13 +1704,14 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, dlen = msg_data_sz(hdr); hlen = msg_hdr_sz(hdr); err = msg_errcode(hdr); + grp_evt = msg_is_grp_evt(hdr); if (likely(dlen || err)) break; tsk_advance_rx_queue(sk); } while (1); /* Collect msg meta data, including error code and rejected data */ - set_orig_addr(m, hdr); + tipc_sk_set_orig_addr(m, skb); rc = tipc_sk_anc_data_recv(m, hdr, tsk); if (unlikely(rc)) goto exit; @@ -1372,15 +1731,33 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, if (unlikely(rc)) goto exit; + /* Mark message as group event if applicable */ + if (unlikely(grp_evt)) { + if (msg_grp_evt(hdr) == TIPC_WITHDRAWN) + m->msg_flags |= MSG_EOR; + m->msg_flags |= MSG_OOB; + copy = 0; + } + /* Caption of data or error code/rejected data was successful */ if (unlikely(flags & MSG_PEEK)) goto exit; + /* Send group flow control advertisement when applicable */ + if (tsk->group && msg_in_group(hdr) && !grp_evt) { + skb_queue_head_init(&xmitq); + tipc_group_update_rcv_win(tsk->group, tsk_blocks(hlen + dlen), + msg_orignode(hdr), msg_origport(hdr), + &xmitq); + tipc_node_distr_xmit(sock_net(sk), &xmitq); + } + tsk_advance_rx_queue(sk); + if (likely(!connected)) goto exit; - /* Send connection flow control ack when applicable */ + /* Send connection flow control advertisement when applicable */ tsk->rcv_unacked += tsk_inc(tsk, hlen + dlen); if (tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE) tipc_sk_send_ack(tsk); @@ -1446,7 +1823,7 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m, /* Collect msg meta data, incl. error code and rejected data */ if (!copied) { - set_orig_addr(m, hdr); + tipc_sk_set_orig_addr(m, skb); rc = tipc_sk_anc_data_recv(m, hdr, tsk); if (rc) break; @@ -1532,14 +1909,51 @@ static void tipc_sock_destruct(struct sock *sk) __skb_queue_purge(&sk->sk_receive_queue); } +static void tipc_sk_proto_rcv(struct sock *sk, + struct sk_buff_head *inputq, + struct sk_buff_head *xmitq) +{ + struct sk_buff *skb = __skb_dequeue(inputq); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_msg *hdr = buf_msg(skb); + struct tipc_group *grp = tsk->group; + bool wakeup = false; + + switch (msg_user(hdr)) { + case CONN_MANAGER: + tipc_sk_conn_proto_rcv(tsk, skb, xmitq); + return; + case SOCK_WAKEUP: + tipc_dest_del(&tsk->cong_links, msg_orignode(hdr), 0); + tsk->cong_link_cnt--; + wakeup = true; + break; + case GROUP_PROTOCOL: + tipc_group_proto_rcv(grp, &wakeup, hdr, inputq, xmitq); + break; + case TOP_SRV: + tipc_group_member_evt(tsk->group, &wakeup, &sk->sk_rcvbuf, + skb, inputq, xmitq); + skb = NULL; + break; + default: + break; + } + + if (wakeup) + sk->sk_write_space(sk); + + kfree_skb(skb); +} + /** - * filter_connect - Handle all incoming messages for a connection-based socket + * tipc_filter_connect - Handle incoming message for a connection-based socket * @tsk: TIPC socket * @skb: pointer to message buffer. Set to NULL if buffer is consumed * * Returns true if everything ok, false otherwise */ -static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb) +static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb) { struct sock *sk = &tsk->sk; struct net *net = sock_net(sk); @@ -1643,6 +2057,9 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb) struct tipc_sock *tsk = tipc_sk(sk); struct tipc_msg *hdr = buf_msg(skb); + if (unlikely(msg_in_group(hdr))) + return sk->sk_rcvbuf; + if (unlikely(!msg_connected(hdr))) return sk->sk_rcvbuf << msg_importance(hdr); @@ -1653,7 +2070,7 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb) } /** - * filter_rcv - validate incoming message + * tipc_sk_filter_rcv - validate incoming message * @sk: socket * @skb: pointer to message. * @@ -1662,99 +2079,71 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb) * * Called with socket lock already taken * - * Returns true if message was added to socket receive queue, otherwise false */ -static bool filter_rcv(struct sock *sk, struct sk_buff *skb, - struct sk_buff_head *xmitq) +static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb, + struct sk_buff_head *xmitq) { + bool sk_conn = !tipc_sk_type_connectionless(sk); struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_group *grp = tsk->group; struct tipc_msg *hdr = buf_msg(skb); - unsigned int limit = rcvbuf_limit(sk, skb); - int err = TIPC_OK; - int usr = msg_user(hdr); - u32 onode; + struct net *net = sock_net(sk); + struct sk_buff_head inputq; + int limit, err = TIPC_OK; - if (unlikely(msg_user(hdr) == CONN_MANAGER)) { - tipc_sk_proto_rcv(tsk, skb, xmitq); - return false; - } + TIPC_SKB_CB(skb)->bytes_read = 0; + __skb_queue_head_init(&inputq); + __skb_queue_tail(&inputq, skb); - if (unlikely(usr == SOCK_WAKEUP)) { - onode = msg_orignode(hdr); - kfree_skb(skb); - u32_del(&tsk->cong_links, onode); - tsk->cong_link_cnt--; - sk->sk_write_space(sk); - return false; - } + if (unlikely(!msg_isdata(hdr))) + tipc_sk_proto_rcv(sk, &inputq, xmitq); - /* Drop if illegal message type */ - if (unlikely(msg_type(hdr) > TIPC_DIRECT_MSG)) { - kfree_skb(skb); - return false; - } + if (unlikely(grp)) + tipc_group_filter_msg(grp, &inputq, xmitq); - /* Reject if wrong message type for current socket state */ - if (tipc_sk_type_connectionless(sk)) { - if (msg_connected(hdr)) { + /* Validate and add to receive buffer if there is space */ + while ((skb = __skb_dequeue(&inputq))) { + hdr = buf_msg(skb); + limit = rcvbuf_limit(sk, skb); + if ((sk_conn && !tipc_sk_filter_connect(tsk, skb)) || + (!sk_conn && msg_connected(hdr)) || + (!grp && msg_in_group(hdr))) err = TIPC_ERR_NO_PORT; - goto reject; - } - } else if (unlikely(!filter_connect(tsk, skb))) { - err = TIPC_ERR_NO_PORT; - goto reject; - } + else if (sk_rmem_alloc_get(sk) + skb->truesize >= limit) + err = TIPC_ERR_OVERLOAD; - /* Reject message if there isn't room to queue it */ - if (unlikely(sk_rmem_alloc_get(sk) + skb->truesize >= limit)) { - err = TIPC_ERR_OVERLOAD; - goto reject; + if (unlikely(err)) { + tipc_skb_reject(net, err, skb, xmitq); + err = TIPC_OK; + continue; + } + __skb_queue_tail(&sk->sk_receive_queue, skb); + skb_set_owner_r(skb, sk); + sk->sk_data_ready(sk); } - - /* Enqueue message */ - TIPC_SKB_CB(skb)->bytes_read = 0; - __skb_queue_tail(&sk->sk_receive_queue, skb); - skb_set_owner_r(skb, sk); - - sk->sk_data_ready(sk); - return true; - -reject: - if (tipc_msg_reverse(tsk_own_node(tsk), &skb, err)) - __skb_queue_tail(xmitq, skb); - return false; } /** - * tipc_backlog_rcv - handle incoming message from backlog queue + * tipc_sk_backlog_rcv - handle incoming message from backlog queue * @sk: socket * @skb: message * * Caller must hold socket lock - * - * Returns 0 */ -static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb) +static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) { - unsigned int truesize = skb->truesize; + unsigned int before = sk_rmem_alloc_get(sk); struct sk_buff_head xmitq; - u32 dnode, selector; + unsigned int added; __skb_queue_head_init(&xmitq); - if (likely(filter_rcv(sk, skb, &xmitq))) { - atomic_add(truesize, &tipc_sk(sk)->dupl_rcvcnt); - return 0; - } + tipc_sk_filter_rcv(sk, skb, &xmitq); + added = sk_rmem_alloc_get(sk) - before; + atomic_add(added, &tipc_sk(sk)->dupl_rcvcnt); - if (skb_queue_empty(&xmitq)) - return 0; - - /* Send response/rejected message */ - skb = __skb_dequeue(&xmitq); - dnode = msg_destnode(buf_msg(skb)); - selector = msg_origport(buf_msg(skb)); - tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector); + /* Send pending response/rejected messages, if any */ + tipc_node_distr_xmit(sock_net(sk), &xmitq); return 0; } @@ -1786,7 +2175,7 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, /* Add message directly to receive queue if possible */ if (!sock_owned_by_user(sk)) { - filter_rcv(sk, skb, xmitq); + tipc_sk_filter_rcv(sk, skb, xmitq); continue; } @@ -1833,14 +2222,10 @@ void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq) spin_unlock_bh(&sk->sk_lock.slock); } /* Send pending response/rejected messages, if any */ - while ((skb = __skb_dequeue(&xmitq))) { - dnode = msg_destnode(buf_msg(skb)); - tipc_node_xmit_skb(net, skb, dnode, dport); - } + tipc_node_distr_xmit(sock_net(sk), &xmitq); sock_put(sk); continue; } - /* No destination socket => dequeue skb if still there */ skb = tipc_skb_dequeue(inputq, dport); if (!skb) @@ -1903,28 +2288,32 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest, int previous; int res = 0; + if (destlen != sizeof(struct sockaddr_tipc)) + return -EINVAL; + lock_sock(sk); - /* DGRAM/RDM connect(), just save the destaddr */ - if (tipc_sk_type_connectionless(sk)) { - if (dst->family == AF_UNSPEC) { - memset(&tsk->peer, 0, sizeof(struct sockaddr_tipc)); - } else if (destlen != sizeof(struct sockaddr_tipc)) { - res = -EINVAL; - } else { - memcpy(&tsk->peer, dest, destlen); - } + if (tsk->group) { + res = -EINVAL; goto exit; } - /* - * Reject connection attempt using multicast address - * - * Note: send_msg() validates the rest of the address fields, - * so there's no need to do it here - */ - if (dst->addrtype == TIPC_ADDR_MCAST) { + if (dst->family == AF_UNSPEC) { + memset(&tsk->peer, 0, sizeof(struct sockaddr_tipc)); + if (!tipc_sk_type_connectionless(sk)) + res = -EINVAL; + goto exit; + } else if (dst->family != AF_TIPC) { res = -EINVAL; + } + if (dst->addrtype != TIPC_ADDR_ID && dst->addrtype != TIPC_ADDR_NAME) + res = -EINVAL; + if (res) + goto exit; + + /* DGRAM/RDM connect(), just save the destaddr */ + if (tipc_sk_type_connectionless(sk)) { + memcpy(&tsk->peer, dest, destlen); goto exit; } @@ -2141,46 +2530,43 @@ static int tipc_shutdown(struct socket *sock, int how) return res; } -static void tipc_sk_timeout(unsigned long data) +static void tipc_sk_timeout(struct timer_list *t) { - struct tipc_sock *tsk = (struct tipc_sock *)data; - struct sock *sk = &tsk->sk; - struct sk_buff *skb = NULL; - u32 peer_port, peer_node; + struct sock *sk = from_timer(sk, t, sk_timer); + struct tipc_sock *tsk = tipc_sk(sk); + u32 peer_port = tsk_peer_port(tsk); + u32 peer_node = tsk_peer_node(tsk); u32 own_node = tsk_own_node(tsk); + u32 own_port = tsk->portid; + struct net *net = sock_net(sk); + struct sk_buff *skb = NULL; bh_lock_sock(sk); - if (!tipc_sk_connected(sk)) { - bh_unlock_sock(sk); + if (!tipc_sk_connected(sk)) + goto exit; + + /* Try again later if socket is busy */ + if (sock_owned_by_user(sk)) { + sk_reset_timer(sk, &sk->sk_timer, jiffies + HZ / 20); goto exit; } - peer_port = tsk_peer_port(tsk); - peer_node = tsk_peer_node(tsk); if (tsk->probe_unacked) { - if (!sock_owned_by_user(sk)) { - tipc_set_sk_state(sk, TIPC_DISCONNECTING); - tipc_node_remove_conn(sock_net(sk), tsk_peer_node(tsk), - tsk_peer_port(tsk)); - sk->sk_state_change(sk); - } else { - /* Try again later */ - sk_reset_timer(sk, &sk->sk_timer, (HZ / 20)); - } - - bh_unlock_sock(sk); + tipc_set_sk_state(sk, TIPC_DISCONNECTING); + tipc_node_remove_conn(net, peer_node, peer_port); + sk->sk_state_change(sk); goto exit; } - - skb = tipc_msg_create(CONN_MANAGER, CONN_PROBE, - INT_H_SIZE, 0, peer_node, own_node, - peer_port, tsk->portid, TIPC_OK); + /* Send new probe */ + skb = tipc_msg_create(CONN_MANAGER, CONN_PROBE, INT_H_SIZE, 0, + peer_node, own_node, peer_port, own_port, + TIPC_OK); tsk->probe_unacked = true; - sk_reset_timer(sk, &sk->sk_timer, jiffies + CONN_PROBING_INTERVAL); + sk_reset_timer(sk, &sk->sk_timer, jiffies + CONN_PROBING_INTV); +exit: bh_unlock_sock(sk); if (skb) - tipc_node_xmit_skb(sock_net(sk), skb, peer_node, tsk->portid); -exit: + tipc_node_xmit_skb(net, skb, peer_node, own_port); sock_put(sk); } @@ -2345,6 +2731,58 @@ void tipc_sk_rht_destroy(struct net *net) rhashtable_destroy(&tn->sk_rht); } +static int tipc_sk_join(struct tipc_sock *tsk, struct tipc_group_req *mreq) +{ + struct net *net = sock_net(&tsk->sk); + u32 domain = addr_domain(net, mreq->scope); + struct tipc_group *grp = tsk->group; + struct tipc_msg *hdr = &tsk->phdr; + struct tipc_name_seq seq; + int rc; + + if (mreq->type < TIPC_RESERVED_TYPES) + return -EACCES; + if (grp) + return -EACCES; + grp = tipc_group_create(net, tsk->portid, mreq); + if (!grp) + return -ENOMEM; + tsk->group = grp; + 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, domain); + rc = tipc_sk_publish(tsk, mreq->scope, &seq); + if (rc) { + tipc_group_delete(net, grp); + tsk->group = NULL; + } + + /* Eliminate any risk that a broadcast overtakes the sent JOIN */ + tsk->mc_method.rcast = true; + tsk->mc_method.mandatory = true; + return rc; +} + +static int tipc_sk_leave(struct tipc_sock *tsk) +{ + struct net *net = sock_net(&tsk->sk); + struct tipc_group *grp = tsk->group; + struct tipc_name_seq seq; + int scope; + + if (!grp) + return -EINVAL; + tipc_group_self(grp, &seq, &scope); + tipc_group_delete(net, grp); + tsk->group = NULL; + tipc_sk_withdraw(tsk, scope, &seq); + return 0; +} + /** * tipc_setsockopt - set socket option * @sock: socket structure @@ -2363,6 +2801,7 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt, { struct sock *sk = sock->sk; struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_group_req mreq; u32 value = 0; int res = 0; @@ -2378,9 +2817,14 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt, case TIPC_CONN_TIMEOUT: if (ol < sizeof(value)) return -EINVAL; - res = get_user(value, (u32 __user *)ov); - if (res) - return res; + if (get_user(value, (u32 __user *)ov)) + return -EFAULT; + break; + case TIPC_GROUP_JOIN: + if (ol < sizeof(mreq)) + return -EINVAL; + if (copy_from_user(&mreq, ov, sizeof(mreq))) + return -EFAULT; break; default: if (ov || ol) @@ -2413,6 +2857,12 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt, tsk->mc_method.rcast = true; tsk->mc_method.mandatory = true; break; + case TIPC_GROUP_JOIN: + res = tipc_sk_join(tsk, &mreq); + break; + case TIPC_GROUP_LEAVE: + res = tipc_sk_leave(tsk); + break; default: res = -EINVAL; } @@ -2440,7 +2890,8 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt, { struct sock *sk = sock->sk; struct tipc_sock *tsk = tipc_sk(sk); - int len; + struct tipc_name_seq seq; + int len, scope; u32 value; int res; @@ -2474,6 +2925,12 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt, case TIPC_SOCK_RECVQ_DEPTH: value = skb_queue_len(&sk->sk_receive_queue); break; + case TIPC_GROUP_JOIN: + seq.type = 0; + if (tsk->group) + tipc_group_self(tsk->group, &seq, &scope); + value = seq.type; + break; default: res = -EINVAL; } diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index be3d9e3183dc..251065dfd8df 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -133,9 +133,9 @@ void tipc_subscrp_report_overlap(struct tipc_subscription *sub, u32 found_lower, node); } -static void tipc_subscrp_timeout(unsigned long data) +static void tipc_subscrp_timeout(struct timer_list *t) { - struct tipc_subscription *sub = (struct tipc_subscription *)data; + struct tipc_subscription *sub = from_timer(sub, t, timer); struct tipc_subscriber *subscriber = sub->subscriber; spin_lock_bh(&subscriber->lock); @@ -303,7 +303,7 @@ static void tipc_subscrp_subscribe(struct net *net, struct tipc_subscr *s, tipc_subscrb_get(subscriber); spin_unlock_bh(&subscriber->lock); - setup_timer(&sub->timer, tipc_subscrp_timeout, (unsigned long)sub); + timer_setup(&sub->timer, tipc_subscrp_timeout, 0); timeout = htohl(sub->evt.s.timeout, swap); if (timeout != TIPC_WAIT_FOREVER) diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 60aff60e30ad..e07ee3ae0023 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -45,8 +45,18 @@ MODULE_AUTHOR("Mellanox Technologies"); MODULE_DESCRIPTION("Transport Layer Security Support"); MODULE_LICENSE("Dual BSD/GPL"); -static struct proto tls_base_prot; -static struct proto tls_sw_prot; +enum { + TLS_BASE_TX, + TLS_SW_TX, + TLS_NUM_CONFIG, +}; + +static struct proto tls_prots[TLS_NUM_CONFIG]; + +static inline void update_sk_prot(struct sock *sk, struct tls_context *ctx) +{ + sk->sk_prot = &tls_prots[ctx->tx_conf]; +} int wait_on_pending_writer(struct sock *sk, long *timeo) { @@ -216,6 +226,12 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) void (*sk_proto_close)(struct sock *sk, long timeout); lock_sock(sk); + sk_proto_close = ctx->sk_proto_close; + + if (ctx->tx_conf == TLS_BASE_TX) { + kfree(ctx); + goto skip_tx_cleanup; + } if (!tls_complete_pending_work(sk, ctx, 0, &timeo)) tls_handle_open_record(sk, 0); @@ -232,13 +248,14 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) sg++; } } - ctx->free_resources(sk); + kfree(ctx->rec_seq); kfree(ctx->iv); - sk_proto_close = ctx->sk_proto_close; - kfree(ctx); + if (ctx->tx_conf == TLS_SW_TX) + tls_sw_free_tx_resources(sk); +skip_tx_cleanup: release_sock(sk); sk_proto_close(sk, timeout); } @@ -338,46 +355,41 @@ static int tls_getsockopt(struct sock *sk, int level, int optname, static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval, unsigned int optlen) { - struct tls_crypto_info *crypto_info, tmp_crypto_info; + struct tls_crypto_info *crypto_info; struct tls_context *ctx = tls_get_ctx(sk); - struct proto *prot = NULL; int rc = 0; + int tx_conf; if (!optval || (optlen < sizeof(*crypto_info))) { rc = -EINVAL; goto out; } - rc = copy_from_user(&tmp_crypto_info, optval, sizeof(*crypto_info)); + crypto_info = &ctx->crypto_send; + /* Currently we don't support set crypto info more than one time */ + if (TLS_CRYPTO_INFO_READY(crypto_info)) + goto out; + + rc = copy_from_user(crypto_info, optval, sizeof(*crypto_info)); if (rc) { rc = -EFAULT; goto out; } /* check version */ - if (tmp_crypto_info.version != TLS_1_2_VERSION) { + if (crypto_info->version != TLS_1_2_VERSION) { rc = -ENOTSUPP; - goto out; + goto err_crypto_info; } - /* get user crypto info */ - crypto_info = &ctx->crypto_send; - - /* Currently we don't support set crypto info more than one time */ - if (TLS_CRYPTO_INFO_READY(crypto_info)) - goto out; - - switch (tmp_crypto_info.cipher_type) { + switch (crypto_info->cipher_type) { case TLS_CIPHER_AES_GCM_128: { if (optlen != sizeof(struct tls12_crypto_info_aes_gcm_128)) { rc = -EINVAL; goto out; } - rc = copy_from_user( - crypto_info, - optval, - sizeof(struct tls12_crypto_info_aes_gcm_128)); - + rc = copy_from_user(crypto_info + 1, optval + sizeof(*crypto_info), + optlen - sizeof(*crypto_info)); if (rc) { rc = -EFAULT; goto err_crypto_info; @@ -389,18 +401,16 @@ static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval, goto out; } - ctx->sk_write_space = sk->sk_write_space; - sk->sk_write_space = tls_write_space; - - ctx->sk_proto_close = sk->sk_prot->close; - /* currently SW is default, we will have ethtool in future */ rc = tls_set_sw_offload(sk, ctx); - prot = &tls_sw_prot; + tx_conf = TLS_SW_TX; if (rc) goto err_crypto_info; - sk->sk_prot = prot; + ctx->tx_conf = tx_conf; + update_sk_prot(sk, ctx); + ctx->sk_write_space = sk->sk_write_space; + sk->sk_write_space = tls_write_space; goto out; err_crypto_info: @@ -453,7 +463,10 @@ static int tls_init(struct sock *sk) icsk->icsk_ulp_data = ctx; ctx->setsockopt = sk->sk_prot->setsockopt; ctx->getsockopt = sk->sk_prot->getsockopt; - sk->sk_prot = &tls_base_prot; + ctx->sk_proto_close = sk->sk_prot->close; + + ctx->tx_conf = TLS_BASE_TX; + update_sk_prot(sk, ctx); out: return rc; } @@ -464,16 +477,21 @@ static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = { .init = tls_init, }; +static void build_protos(struct proto *prot, struct proto *base) +{ + prot[TLS_BASE_TX] = *base; + prot[TLS_BASE_TX].setsockopt = tls_setsockopt; + prot[TLS_BASE_TX].getsockopt = tls_getsockopt; + prot[TLS_BASE_TX].close = tls_sk_proto_close; + + prot[TLS_SW_TX] = prot[TLS_BASE_TX]; + prot[TLS_SW_TX].sendmsg = tls_sw_sendmsg; + prot[TLS_SW_TX].sendpage = tls_sw_sendpage; +} + static int __init tls_register(void) { - tls_base_prot = tcp_prot; - tls_base_prot.setsockopt = tls_setsockopt; - tls_base_prot.getsockopt = tls_getsockopt; - - tls_sw_prot = tls_base_prot; - tls_sw_prot.sendmsg = tls_sw_sendmsg; - tls_sw_prot.sendpage = tls_sw_sendpage; - tls_sw_prot.close = tls_sk_proto_close; + build_protos(tls_prots, &tcp_prot); tcp_register_ulp(&tcp_tls_ulp_ops); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 7d80040a37b6..73d19210dd49 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -39,22 +39,6 @@ #include <net/tls.h> -static inline void tls_make_aad(int recv, - char *buf, - size_t size, - char *record_sequence, - int record_sequence_size, - unsigned char record_type) -{ - memcpy(buf, record_sequence, record_sequence_size); - - buf[8] = record_type; - buf[9] = TLS_1_2_VERSION_MAJOR; - buf[10] = TLS_1_2_VERSION_MINOR; - buf[11] = size >> 8; - buf[12] = size & 0xFF; -} - static void trim_sg(struct sock *sk, struct scatterlist *sg, int *sg_num_elem, unsigned int *sg_size, int target_size) { @@ -219,7 +203,7 @@ static int tls_do_encryption(struct tls_context *tls_ctx, struct aead_request *aead_req; int rc; - aead_req = kmalloc(req_size, flags); + aead_req = kzalloc(req_size, flags); if (!aead_req) return -ENOMEM; @@ -249,7 +233,7 @@ static int tls_push_record(struct sock *sk, int flags, sg_mark_end(ctx->sg_plaintext_data + ctx->sg_plaintext_num_elem - 1); sg_mark_end(ctx->sg_encrypted_data + ctx->sg_encrypted_num_elem - 1); - tls_make_aad(0, ctx->aad_space, ctx->sg_plaintext_size, + tls_make_aad(ctx->aad_space, ctx->sg_plaintext_size, tls_ctx->rec_seq, tls_ctx->rec_seq_size, record_type); @@ -639,7 +623,7 @@ sendpage_end: return ret; } -static void tls_sw_free_resources(struct sock *sk) +void tls_sw_free_tx_resources(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); @@ -650,6 +634,7 @@ static void tls_sw_free_resources(struct sock *sk) tls_free_both_sg(sk); kfree(ctx); + kfree(tls_ctx); } int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx) @@ -679,7 +664,6 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx) } ctx->priv_ctx = (struct tls_offload_context *)sw_ctx; - ctx->free_resources = tls_sw_free_resources; crypto_info = &ctx->crypto_send; switch (crypto_info->cipher_type) { diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 7f46bab4ce5c..a9ee634f3c42 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -814,6 +814,7 @@ static int unix_create(struct net *net, struct socket *sock, int protocol, */ case SOCK_RAW: sock->type = SOCK_DGRAM; + /* fall through */ case SOCK_DGRAM: sock->ops = &unix_dgram_ops; break; diff --git a/net/vmw_vsock/Kconfig b/net/vmw_vsock/Kconfig index a24369d175fd..970f96489fe7 100644 --- a/net/vmw_vsock/Kconfig +++ b/net/vmw_vsock/Kconfig @@ -15,6 +15,16 @@ config VSOCKETS To compile this driver as a module, choose M here: the module will be called vsock. If unsure, say N. +config VSOCKETS_DIAG + tristate "Virtual Sockets monitoring interface" + depends on VSOCKETS + default y + help + Support for PF_VSOCK sockets monitoring interface used by the ss tool. + If unsure, say Y. + + Enable this module so userspace applications can query open sockets. + config VMWARE_VMCI_VSOCKETS tristate "VMware VMCI transport for Virtual Sockets" depends on VSOCKETS && VMWARE_VMCI diff --git a/net/vmw_vsock/Makefile b/net/vmw_vsock/Makefile index 30a263320e4f..7c6f9a0b67b0 100644 --- a/net/vmw_vsock/Makefile +++ b/net/vmw_vsock/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_VSOCKETS) += vsock.o +obj-$(CONFIG_VSOCKETS_DIAG) += vsock_diag.o obj-$(CONFIG_VMWARE_VMCI_VSOCKETS) += vmw_vsock_vmci_transport.o obj-$(CONFIG_VIRTIO_VSOCKETS) += vmw_vsock_virtio_transport.o obj-$(CONFIG_VIRTIO_VSOCKETS_COMMON) += vmw_vsock_virtio_transport_common.o @@ -7,6 +8,8 @@ obj-$(CONFIG_HYPERV_VSOCKETS) += hv_sock.o vsock-y += af_vsock.o af_vsock_tap.o vsock_addr.o +vsock_diag-y += diag.o + vmw_vsock_vmci_transport-y += vmci_transport.o vmci_transport_notify.o \ vmci_transport_notify_qstate.o diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index dfc8c51e4d74..5d28abf87fbf 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -36,7 +36,7 @@ * not support simultaneous connects (two "client" sockets connecting). * * - "Server" sockets are referred to as listener sockets throughout this - * implementation because they are in the VSOCK_SS_LISTEN state. When a + * implementation because they are in the TCP_LISTEN state. When a * connection request is received (the second kind of socket mentioned above), * we create a new socket and refer to it as a pending socket. These pending * sockets are placed on the pending connection list of the listener socket. @@ -82,6 +82,15 @@ * argument, we must ensure the reference count is increased to ensure the * socket isn't freed before the function is run; the deferred function will * then drop the reference. + * + * - sk->sk_state uses the TCP state constants because they are widely used by + * other address families and exposed to userspace tools like ss(8): + * + * TCP_CLOSE - unconnected + * TCP_SYN_SENT - connecting + * TCP_ESTABLISHED - connected + * TCP_CLOSING - disconnecting + * TCP_LISTEN - listening */ #include <linux/types.h> @@ -153,7 +162,6 @@ EXPORT_SYMBOL_GPL(vm_sockets_get_local_cid); * vsock_bind_table[VSOCK_HASH_SIZE] is for unbound sockets. The hash function * mods with VSOCK_HASH_SIZE to ensure this. */ -#define VSOCK_HASH_SIZE 251 #define MAX_PORT_RETRIES 24 #define VSOCK_HASH(addr) ((addr)->svm_port % VSOCK_HASH_SIZE) @@ -168,9 +176,12 @@ EXPORT_SYMBOL_GPL(vm_sockets_get_local_cid); #define vsock_connected_sockets_vsk(vsk) \ vsock_connected_sockets(&(vsk)->remote_addr, &(vsk)->local_addr) -static struct list_head vsock_bind_table[VSOCK_HASH_SIZE + 1]; -static struct list_head vsock_connected_table[VSOCK_HASH_SIZE]; -static DEFINE_SPINLOCK(vsock_table_lock); +struct list_head vsock_bind_table[VSOCK_HASH_SIZE + 1]; +EXPORT_SYMBOL_GPL(vsock_bind_table); +struct list_head vsock_connected_table[VSOCK_HASH_SIZE]; +EXPORT_SYMBOL_GPL(vsock_connected_table); +DEFINE_SPINLOCK(vsock_table_lock); +EXPORT_SYMBOL_GPL(vsock_table_lock); /* Autobind this socket to the local address if necessary. */ static int vsock_auto_bind(struct vsock_sock *vsk) @@ -184,7 +195,7 @@ static int vsock_auto_bind(struct vsock_sock *vsk) return __vsock_bind(sk, &local_addr); } -static void vsock_init_tables(void) +static int __init vsock_init_tables(void) { int i; @@ -193,6 +204,7 @@ static void vsock_init_tables(void) for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++) INIT_LIST_HEAD(&vsock_connected_table[i]); + return 0; } static void __vsock_insert_bound(struct list_head *list, @@ -248,16 +260,6 @@ static struct sock *__vsock_find_connected_socket(struct sockaddr_vm *src, return NULL; } -static bool __vsock_in_bound_table(struct vsock_sock *vsk) -{ - return !list_empty(&vsk->bound_table); -} - -static bool __vsock_in_connected_table(struct vsock_sock *vsk) -{ - return !list_empty(&vsk->connected_table); -} - static void vsock_insert_unbound(struct vsock_sock *vsk) { spin_lock_bh(&vsock_table_lock); @@ -485,7 +487,7 @@ void vsock_pending_work(struct work_struct *work) if (vsock_in_connected_table(vsk)) vsock_remove_connected(vsk); - sk->sk_state = SS_FREE; + sk->sk_state = TCP_CLOSE; out: release_sock(sk); @@ -625,7 +627,6 @@ struct sock *__vsock_create(struct net *net, sk->sk_destruct = vsock_sk_destruct; sk->sk_backlog_rcv = vsock_queue_rcv_skb; - sk->sk_state = 0; sock_reset_flag(sk, SOCK_DONE); INIT_LIST_HEAD(&vsk->bound_table); @@ -899,7 +900,7 @@ static unsigned int vsock_poll(struct file *file, struct socket *sock, /* Listening sockets that have connections in their accept * queue can be read. */ - if (sk->sk_state == VSOCK_SS_LISTEN + if (sk->sk_state == TCP_LISTEN && !vsock_is_accept_queue_empty(sk)) mask |= POLLIN | POLLRDNORM; @@ -928,7 +929,7 @@ static unsigned int vsock_poll(struct file *file, struct socket *sock, } /* Connected sockets that can produce data can be written. */ - if (sk->sk_state == SS_CONNECTED) { + if (sk->sk_state == TCP_ESTABLISHED) { if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { bool space_avail_now = false; int ret = transport->notify_poll_out( @@ -950,7 +951,7 @@ static unsigned int vsock_poll(struct file *file, struct socket *sock, * POLLOUT|POLLWRNORM when peer is closed and nothing to read, * but local send is not shutdown. */ - if (sk->sk_state == SS_UNCONNECTED) { + if (sk->sk_state == TCP_CLOSE) { if (!(sk->sk_shutdown & SEND_SHUTDOWN)) mask |= POLLOUT | POLLWRNORM; @@ -1120,9 +1121,9 @@ static void vsock_connect_timeout(struct work_struct *work) sk = sk_vsock(vsk); lock_sock(sk); - if (sk->sk_state == SS_CONNECTING && + if (sk->sk_state == TCP_SYN_SENT && (sk->sk_shutdown != SHUTDOWN_MASK)) { - sk->sk_state = SS_UNCONNECTED; + sk->sk_state = TCP_CLOSE; sk->sk_err = ETIMEDOUT; sk->sk_error_report(sk); cancel = 1; @@ -1168,7 +1169,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, err = -EALREADY; break; default: - if ((sk->sk_state == VSOCK_SS_LISTEN) || + if ((sk->sk_state == TCP_LISTEN) || vsock_addr_cast(addr, addr_len, &remote_addr) != 0) { err = -EINVAL; goto out; @@ -1191,7 +1192,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, if (err) goto out; - sk->sk_state = SS_CONNECTING; + sk->sk_state = TCP_SYN_SENT; err = transport->connect(vsk); if (err < 0) @@ -1211,7 +1212,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, timeout = vsk->connect_timeout; prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - while (sk->sk_state != SS_CONNECTED && sk->sk_err == 0) { + while (sk->sk_state != TCP_ESTABLISHED && sk->sk_err == 0) { if (flags & O_NONBLOCK) { /* If we're not going to block, we schedule a timeout * function to generate a timeout on the connection @@ -1234,13 +1235,13 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, if (signal_pending(current)) { err = sock_intr_errno(timeout); - sk->sk_state = SS_UNCONNECTED; + sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; vsock_transport_cancel_pkt(vsk); goto out_wait; } else if (timeout == 0) { err = -ETIMEDOUT; - sk->sk_state = SS_UNCONNECTED; + sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; vsock_transport_cancel_pkt(vsk); goto out_wait; @@ -1251,7 +1252,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, if (sk->sk_err) { err = -sk->sk_err; - sk->sk_state = SS_UNCONNECTED; + sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; } else { err = 0; @@ -1284,7 +1285,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags, goto out; } - if (listener->sk_state != VSOCK_SS_LISTEN) { + if (listener->sk_state != TCP_LISTEN) { err = -EINVAL; goto out; } @@ -1374,7 +1375,7 @@ static int vsock_listen(struct socket *sock, int backlog) } sk->sk_max_ack_backlog = backlog; - sk->sk_state = VSOCK_SS_LISTEN; + sk->sk_state = TCP_LISTEN; err = 0; @@ -1554,7 +1555,7 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, /* Callers should not provide a destination with stream sockets. */ if (msg->msg_namelen) { - err = sk->sk_state == SS_CONNECTED ? -EISCONN : -EOPNOTSUPP; + err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP; goto out; } @@ -1565,7 +1566,7 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, goto out; } - if (sk->sk_state != SS_CONNECTED || + if (sk->sk_state != TCP_ESTABLISHED || !vsock_addr_bound(&vsk->local_addr)) { err = -ENOTCONN; goto out; @@ -1689,7 +1690,7 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, lock_sock(sk); - if (sk->sk_state != SS_CONNECTED) { + if (sk->sk_state != TCP_ESTABLISHED) { /* Recvmsg is supposed to return 0 if a peer performs an * orderly shutdown. Differentiate between that case and when a * peer has not connected or a local shutdown occured with the @@ -1957,8 +1958,6 @@ int __vsock_core_init(const struct vsock_transport *t, struct module *owner) vsock_proto.owner = owner; transport = t; - vsock_init_tables(); - vsock_device.minor = MISC_DYNAMIC_MINOR; err = misc_register(&vsock_device); if (err) { @@ -2019,6 +2018,8 @@ const struct vsock_transport *vsock_core_get_transport(void) } EXPORT_SYMBOL_GPL(vsock_core_get_transport); +module_init(vsock_init_tables); + MODULE_AUTHOR("VMware, Inc."); MODULE_DESCRIPTION("VMware Virtual Socket Family"); MODULE_VERSION("1.0.2.0-k"); diff --git a/net/vmw_vsock/diag.c b/net/vmw_vsock/diag.c new file mode 100644 index 000000000000..31b567652250 --- /dev/null +++ b/net/vmw_vsock/diag.c @@ -0,0 +1,186 @@ +/* + * vsock sock_diag(7) module + * + * Copyright (C) 2017 Red Hat, Inc. + * Author: Stefan Hajnoczi <stefanha@redhat.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation version 2 and no later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include <linux/module.h> +#include <linux/sock_diag.h> +#include <linux/vm_sockets_diag.h> +#include <net/af_vsock.h> + +static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, + u32 portid, u32 seq, u32 flags) +{ + struct vsock_sock *vsk = vsock_sk(sk); + struct vsock_diag_msg *rep; + struct nlmsghdr *nlh; + + nlh = nlmsg_put(skb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep), + flags); + if (!nlh) + return -EMSGSIZE; + + rep = nlmsg_data(nlh); + rep->vdiag_family = AF_VSOCK; + + /* Lock order dictates that sk_lock is acquired before + * vsock_table_lock, so we cannot lock here. Simply don't take + * sk_lock; sk is guaranteed to stay alive since vsock_table_lock is + * held. + */ + rep->vdiag_type = sk->sk_type; + rep->vdiag_state = sk->sk_state; + rep->vdiag_shutdown = sk->sk_shutdown; + rep->vdiag_src_cid = vsk->local_addr.svm_cid; + rep->vdiag_src_port = vsk->local_addr.svm_port; + rep->vdiag_dst_cid = vsk->remote_addr.svm_cid; + rep->vdiag_dst_port = vsk->remote_addr.svm_port; + rep->vdiag_ino = sock_i_ino(sk); + + sock_diag_save_cookie(sk, rep->vdiag_cookie); + + return 0; +} + +static int vsock_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct vsock_diag_req *req; + struct vsock_sock *vsk; + unsigned int bucket; + unsigned int last_i; + unsigned int table; + struct net *net; + unsigned int i; + + req = nlmsg_data(cb->nlh); + net = sock_net(skb->sk); + + /* State saved between calls: */ + table = cb->args[0]; + bucket = cb->args[1]; + i = last_i = cb->args[2]; + + /* TODO VMCI pending sockets? */ + + spin_lock_bh(&vsock_table_lock); + + /* Bind table (locally created sockets) */ + if (table == 0) { + while (bucket < ARRAY_SIZE(vsock_bind_table)) { + struct list_head *head = &vsock_bind_table[bucket]; + + i = 0; + list_for_each_entry(vsk, head, bound_table) { + struct sock *sk = sk_vsock(vsk); + + if (!net_eq(sock_net(sk), net)) + continue; + if (i < last_i) + goto next_bind; + if (!(req->vdiag_states & (1 << sk->sk_state))) + goto next_bind; + if (sk_diag_fill(sk, skb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI) < 0) + goto done; +next_bind: + i++; + } + last_i = 0; + bucket++; + } + + table++; + bucket = 0; + } + + /* Connected table (accepted connections) */ + while (bucket < ARRAY_SIZE(vsock_connected_table)) { + struct list_head *head = &vsock_connected_table[bucket]; + + i = 0; + list_for_each_entry(vsk, head, connected_table) { + struct sock *sk = sk_vsock(vsk); + + /* Skip sockets we've already seen above */ + if (__vsock_in_bound_table(vsk)) + continue; + + if (!net_eq(sock_net(sk), net)) + continue; + if (i < last_i) + goto next_connected; + if (!(req->vdiag_states & (1 << sk->sk_state))) + goto next_connected; + if (sk_diag_fill(sk, skb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI) < 0) + goto done; +next_connected: + i++; + } + last_i = 0; + bucket++; + } + +done: + spin_unlock_bh(&vsock_table_lock); + + cb->args[0] = table; + cb->args[1] = bucket; + cb->args[2] = i; + + return skb->len; +} + +static int vsock_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) +{ + int hdrlen = sizeof(struct vsock_diag_req); + struct net *net = sock_net(skb->sk); + + if (nlmsg_len(h) < hdrlen) + return -EINVAL; + + if (h->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .dump = vsock_diag_dump, + }; + return netlink_dump_start(net->diag_nlsk, skb, h, &c); + } + + return -EOPNOTSUPP; +} + +static const struct sock_diag_handler vsock_diag_handler = { + .family = AF_VSOCK, + .dump = vsock_diag_handler_dump, +}; + +static int __init vsock_diag_init(void) +{ + return sock_diag_register(&vsock_diag_handler); +} + +static void __exit vsock_diag_exit(void) +{ + sock_diag_unregister(&vsock_diag_handler); +} + +module_init(vsock_diag_init); +module_exit(vsock_diag_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, + 40 /* AF_VSOCK */); diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index e21991fe883a..5583df708b8c 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -312,7 +312,7 @@ static void hvs_close_connection(struct vmbus_channel *chan) lock_sock(sk); - sk->sk_state = SS_UNCONNECTED; + sk->sk_state = TCP_CLOSE; sock_set_flag(sk, SOCK_DONE); vsk->peer_shutdown |= SEND_SHUTDOWN | RCV_SHUTDOWN; @@ -349,9 +349,8 @@ static void hvs_open_connection(struct vmbus_channel *chan) return; lock_sock(sk); - - if ((conn_from_host && sk->sk_state != VSOCK_SS_LISTEN) || - (!conn_from_host && sk->sk_state != SS_CONNECTING)) + if ((conn_from_host && sk->sk_state != TCP_LISTEN) || + (!conn_from_host && sk->sk_state != TCP_SYN_SENT)) goto out; if (conn_from_host) { @@ -363,7 +362,7 @@ static void hvs_open_connection(struct vmbus_channel *chan) if (!new) goto out; - new->sk_state = SS_CONNECTING; + new->sk_state = TCP_SYN_SENT; vnew = vsock_sk(new); hvs_new = vnew->trans; hvs_new->chan = chan; @@ -390,7 +389,7 @@ static void hvs_open_connection(struct vmbus_channel *chan) vmbus_set_chn_rescind_callback(chan, hvs_close_connection); if (conn_from_host) { - new->sk_state = SS_CONNECTED; + new->sk_state = TCP_ESTABLISHED; sk->sk_ack_backlog++; hvs_addr_init(&vnew->local_addr, if_type); @@ -403,7 +402,7 @@ static void hvs_open_connection(struct vmbus_channel *chan) vsock_enqueue_accept(sk, new); } else { - sk->sk_state = SS_CONNECTED; + sk->sk_state = TCP_ESTABLISHED; sk->sk_socket->state = SS_CONNECTED; vsock_insert_connected(vsock_sk(sk)); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 403d86e80162..8e03bd3f3668 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -414,7 +414,7 @@ static void virtio_vsock_event_fill(struct virtio_vsock *vsock) static void virtio_vsock_reset_sock(struct sock *sk) { lock_sock(sk); - sk->sk_state = SS_UNCONNECTED; + sk->sk_state = TCP_CLOSE; sk->sk_err = ECONNRESET; sk->sk_error_report(sk); release_sock(sk); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index edba7ab97563..3ae3a33da70b 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -708,7 +708,7 @@ static void virtio_transport_do_close(struct vsock_sock *vsk, sock_set_flag(sk, SOCK_DONE); vsk->peer_shutdown = SHUTDOWN_MASK; if (vsock_stream_has_data(vsk) <= 0) - sk->sk_state = SS_DISCONNECTING; + sk->sk_state = TCP_CLOSING; sk->sk_state_change(sk); if (vsk->close_work_scheduled && @@ -748,8 +748,8 @@ static bool virtio_transport_close(struct vsock_sock *vsk) { struct sock *sk = &vsk->sk; - if (!(sk->sk_state == SS_CONNECTED || - sk->sk_state == SS_DISCONNECTING)) + if (!(sk->sk_state == TCP_ESTABLISHED || + sk->sk_state == TCP_CLOSING)) return true; /* Already received SHUTDOWN from peer, reply with RST */ @@ -801,7 +801,7 @@ virtio_transport_recv_connecting(struct sock *sk, switch (le16_to_cpu(pkt->hdr.op)) { case VIRTIO_VSOCK_OP_RESPONSE: - sk->sk_state = SS_CONNECTED; + sk->sk_state = TCP_ESTABLISHED; sk->sk_socket->state = SS_CONNECTED; vsock_insert_connected(vsk); sk->sk_state_change(sk); @@ -821,7 +821,7 @@ virtio_transport_recv_connecting(struct sock *sk, destroy: virtio_transport_reset(vsk, pkt); - sk->sk_state = SS_UNCONNECTED; + sk->sk_state = TCP_CLOSE; sk->sk_err = skerr; sk->sk_error_report(sk); return err; @@ -857,7 +857,7 @@ virtio_transport_recv_connected(struct sock *sk, vsk->peer_shutdown |= SEND_SHUTDOWN; if (vsk->peer_shutdown == SHUTDOWN_MASK && vsock_stream_has_data(vsk) <= 0) - sk->sk_state = SS_DISCONNECTING; + sk->sk_state = TCP_CLOSING; if (le32_to_cpu(pkt->hdr.flags)) sk->sk_state_change(sk); break; @@ -928,7 +928,7 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt) lock_sock_nested(child, SINGLE_DEPTH_NESTING); - child->sk_state = SS_CONNECTED; + child->sk_state = TCP_ESTABLISHED; vchild = vsock_sk(child); vsock_addr_init(&vchild->local_addr, le64_to_cpu(pkt->hdr.dst_cid), @@ -1016,18 +1016,18 @@ void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt) sk->sk_write_space(sk); switch (sk->sk_state) { - case VSOCK_SS_LISTEN: + case TCP_LISTEN: virtio_transport_recv_listen(sk, pkt); virtio_transport_free_pkt(pkt); break; - case SS_CONNECTING: + case TCP_SYN_SENT: virtio_transport_recv_connecting(sk, pkt); virtio_transport_free_pkt(pkt); break; - case SS_CONNECTED: + case TCP_ESTABLISHED: virtio_transport_recv_connected(sk, pkt); break; - case SS_DISCONNECTING: + case TCP_CLOSING: virtio_transport_recv_disconnecting(sk, pkt); virtio_transport_free_pkt(pkt); break; diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 10ae7823a19d..391775e3575c 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -21,7 +21,6 @@ #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/list.h> -#include <linux/miscdevice.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/net.h> @@ -743,7 +742,7 @@ static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg) /* The local context ID may be out of date, update it. */ vsk->local_addr.svm_cid = dst.svm_cid; - if (sk->sk_state == SS_CONNECTED) + if (sk->sk_state == TCP_ESTABLISHED) vmci_trans(vsk)->notify_ops->handle_notify_pkt( sk, pkt, true, &dst, &src, &bh_process_pkt); @@ -801,7 +800,9 @@ static void vmci_transport_handle_detach(struct sock *sk) * left in our consume queue. */ if (vsock_stream_has_data(vsk) <= 0) { - if (sk->sk_state == SS_CONNECTING) { + sk->sk_state = TCP_CLOSE; + + if (sk->sk_state == TCP_SYN_SENT) { /* The peer may detach from a queue pair while * we are still in the connecting state, i.e., * if the peer VM is killed after attaching to @@ -810,12 +811,10 @@ static void vmci_transport_handle_detach(struct sock *sk) * event like a reset. */ - sk->sk_state = SS_UNCONNECTED; sk->sk_err = ECONNRESET; sk->sk_error_report(sk); return; } - sk->sk_state = SS_UNCONNECTED; } sk->sk_state_change(sk); } @@ -883,17 +882,17 @@ static void vmci_transport_recv_pkt_work(struct work_struct *work) vsock_sk(sk)->local_addr.svm_cid = pkt->dg.dst.context; switch (sk->sk_state) { - case VSOCK_SS_LISTEN: + case TCP_LISTEN: vmci_transport_recv_listen(sk, pkt); break; - case SS_CONNECTING: + case TCP_SYN_SENT: /* Processing of pending connections for servers goes through * the listening socket, so see vmci_transport_recv_listen() * for that path. */ vmci_transport_recv_connecting_client(sk, pkt); break; - case SS_CONNECTED: + case TCP_ESTABLISHED: vmci_transport_recv_connected(sk, pkt); break; default: @@ -942,7 +941,7 @@ static int vmci_transport_recv_listen(struct sock *sk, vsock_sk(pending)->local_addr.svm_cid = pkt->dg.dst.context; switch (pending->sk_state) { - case SS_CONNECTING: + case TCP_SYN_SENT: err = vmci_transport_recv_connecting_server(sk, pending, pkt); @@ -1072,7 +1071,7 @@ static int vmci_transport_recv_listen(struct sock *sk, vsock_add_pending(sk, pending); sk->sk_ack_backlog++; - pending->sk_state = SS_CONNECTING; + pending->sk_state = TCP_SYN_SENT; vmci_trans(vpending)->produce_size = vmci_trans(vpending)->consume_size = qp_size; vmci_trans(vpending)->queue_pair_size = qp_size; @@ -1197,11 +1196,11 @@ vmci_transport_recv_connecting_server(struct sock *listener, * the socket will be valid until it is removed from the queue. * * If we fail sending the attach below, we remove the socket from the - * connected list and move the socket to SS_UNCONNECTED before + * connected list and move the socket to TCP_CLOSE before * releasing the lock, so a pending slow path processing of an incoming * packet will not see the socket in the connected state in that case. */ - pending->sk_state = SS_CONNECTED; + pending->sk_state = TCP_ESTABLISHED; vsock_insert_connected(vpending); @@ -1232,7 +1231,7 @@ vmci_transport_recv_connecting_server(struct sock *listener, destroy: pending->sk_err = skerr; - pending->sk_state = SS_UNCONNECTED; + pending->sk_state = TCP_CLOSE; /* As long as we drop our reference, all necessary cleanup will handle * when the cleanup function drops its reference and our destruct * implementation is called. Note that since the listen handler will @@ -1270,7 +1269,7 @@ vmci_transport_recv_connecting_client(struct sock *sk, * accounting (it can already be found since it's in the bound * table). */ - sk->sk_state = SS_CONNECTED; + sk->sk_state = TCP_ESTABLISHED; sk->sk_socket->state = SS_CONNECTED; vsock_insert_connected(vsk); sk->sk_state_change(sk); @@ -1338,7 +1337,7 @@ vmci_transport_recv_connecting_client(struct sock *sk, destroy: vmci_transport_send_reset(sk, pkt); - sk->sk_state = SS_UNCONNECTED; + sk->sk_state = TCP_CLOSE; sk->sk_err = skerr; sk->sk_error_report(sk); return err; @@ -1526,7 +1525,7 @@ static int vmci_transport_recv_connected(struct sock *sk, sock_set_flag(sk, SOCK_DONE); vsk->peer_shutdown = SHUTDOWN_MASK; if (vsock_stream_has_data(vsk) <= 0) - sk->sk_state = SS_DISCONNECTING; + sk->sk_state = TCP_CLOSING; sk->sk_state_change(sk); break; @@ -1790,7 +1789,7 @@ static int vmci_transport_connect(struct vsock_sock *vsk) err = vmci_transport_send_conn_request( sk, vmci_trans(vsk)->queue_pair_size); if (err < 0) { - sk->sk_state = SS_UNCONNECTED; + sk->sk_state = TCP_CLOSE; return err; } } else { @@ -1800,7 +1799,7 @@ static int vmci_transport_connect(struct vsock_sock *vsk) sk, vmci_trans(vsk)->queue_pair_size, supported_proto_versions); if (err < 0) { - sk->sk_state = SS_UNCONNECTED; + sk->sk_state = TCP_CLOSE; return err; } diff --git a/net/vmw_vsock/vmci_transport_notify.c b/net/vmw_vsock/vmci_transport_notify.c index 1406db4d97d1..41fb427f150a 100644 --- a/net/vmw_vsock/vmci_transport_notify.c +++ b/net/vmw_vsock/vmci_transport_notify.c @@ -355,7 +355,7 @@ vmci_transport_notify_pkt_poll_in(struct sock *sk, * queue. Ask for notifications when there is something to * read. */ - if (sk->sk_state == SS_CONNECTED) { + if (sk->sk_state == TCP_ESTABLISHED) { if (!send_waiting_read(sk, 1)) return -1; diff --git a/net/vmw_vsock/vmci_transport_notify_qstate.c b/net/vmw_vsock/vmci_transport_notify_qstate.c index f3a0afc46208..0cc84f2bb05e 100644 --- a/net/vmw_vsock/vmci_transport_notify_qstate.c +++ b/net/vmw_vsock/vmci_transport_notify_qstate.c @@ -176,7 +176,7 @@ vmci_transport_notify_pkt_poll_in(struct sock *sk, * queue. Ask for notifications when there is something to * read. */ - if (sk->sk_state == SS_CONNECTED) + if (sk->sk_state == TCP_ESTABLISHED) vsock_block_update_write_window(sk); *data_ready_now = false; } diff --git a/net/wireless/.gitignore b/net/wireless/.gitignore index c33451b896d9..61cbc304a3d3 100644 --- a/net/wireless/.gitignore +++ b/net/wireless/.gitignore @@ -1 +1,2 @@ -regdb.c +shipped-certs.c +extra-certs.c diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index 6c606120abfe..da91bb547db3 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -19,6 +19,7 @@ config WEXT_PRIV config CFG80211 tristate "cfg80211 - wireless configuration API" depends on RFKILL || !RFKILL + select FW_LOADER ---help--- cfg80211 is the Linux wireless LAN (802.11) configuration API. Enable this if you have a wireless device. @@ -82,6 +83,36 @@ config CFG80211_CERTIFICATION_ONUS you are a wireless researcher and are working in a controlled and approved environment by your local regulatory agency. +config CFG80211_REQUIRE_SIGNED_REGDB + bool "require regdb signature" if CFG80211_CERTIFICATION_ONUS + default y + select SYSTEM_DATA_VERIFICATION + help + Require that in addition to the "regulatory.db" file a + "regulatory.db.p7s" can be loaded with a valid PKCS#7 + signature for the regulatory.db file made by one of the + keys in the certs/ directory. + +config CFG80211_USE_KERNEL_REGDB_KEYS + bool "allow regdb keys shipped with the kernel" if CFG80211_CERTIFICATION_ONUS + default y + depends on CFG80211_REQUIRE_SIGNED_REGDB + help + Allow the regulatory database to be signed by one of the keys for + which certificates are part of the kernel sources + (in net/wireless/certs/). + + This is currently only Seth Forshee's key, who is the regulatory + database maintainer. + +config CFG80211_EXTRA_REGDB_KEYDIR + string "additional regdb key directory" if CFG80211_CERTIFICATION_ONUS + depends on CFG80211_REQUIRE_SIGNED_REGDB + help + If selected, point to a directory with DER-encoded X.509 + certificates like in the kernel sources (net/wireless/certs/) + that shall be accepted for a signed regulatory database. + config CFG80211_REG_CELLULAR_HINTS bool "cfg80211 regulatory support for cellular base station hints" depends on CFG80211_CERTIFICATION_ONUS @@ -139,35 +170,14 @@ config CFG80211_DEBUGFS If unsure, say N. -config CFG80211_INTERNAL_REGDB - bool "use statically compiled regulatory rules database" if EXPERT - default n - depends on CFG80211 - ---help--- - This option generates an internal data structure representing - the wireless regulatory rules described in net/wireless/db.txt - and includes code to query that database. This is an alternative - to using CRDA for defining regulatory rules for the kernel. - - Using this option requires some parsing of the db.txt at build time, - the parser will be upkept with the latest wireless-regdb updates but - older wireless-regdb formats will be ignored. The parser may later - be replaced to avoid issues with conflicts on versions of - wireless-regdb. - - For details see: - - http://wireless.kernel.org/en/developers/Regulatory - - Most distributions have a CRDA package. So if unsure, say N. - config CFG80211_CRDA_SUPPORT - bool "support CRDA" if CFG80211_INTERNAL_REGDB + bool "support CRDA" if EXPERT default y depends on CFG80211 help You should enable this option unless you know for sure you have no - need for it, for example when using internal regdb (above.) + need for it, for example when using internal regdb (above) or the + database loaded as a firmware file. If unsure, say Y. diff --git a/net/wireless/Makefile b/net/wireless/Makefile index b7c0300e0b08..278d979c211a 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -15,11 +15,27 @@ cfg80211-y += mlme.o ibss.o sme.o chan.o ethtool.o mesh.o ap.o trace.o ocb.o cfg80211-$(CONFIG_OF) += of.o cfg80211-$(CONFIG_CFG80211_DEBUGFS) += debugfs.o cfg80211-$(CONFIG_CFG80211_WEXT) += wext-compat.o wext-sme.o -cfg80211-$(CONFIG_CFG80211_INTERNAL_REGDB) += regdb.o CFLAGS_trace.o := -I$(src) -$(obj)/regdb.c: $(src)/db.txt $(src)/genregdb.awk - @$(AWK) -f $(srctree)/$(src)/genregdb.awk < $< > $@ +cfg80211-$(CONFIG_CFG80211_USE_KERNEL_REGDB_KEYS) += shipped-certs.o +ifneq ($(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR),) +cfg80211-y += extra-certs.o +endif -clean-files := regdb.c +$(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.x509) + @$(kecho) " GEN $@" + @echo '#include "reg.h"' > $@ + @echo 'const u8 shipped_regdb_certs[] = {' >> $@ + @for f in $^ ; do hexdump -v -e '1/1 "0x%.2x," "\n"' < $$f >> $@ ; done + @echo '};' >> $@ + @echo 'unsigned int shipped_regdb_certs_len = sizeof(shipped_regdb_certs);' >> $@ + +$(obj)/extra-certs.c: $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%) \ + $(wildcard $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%)/*.x509) + @$(kecho) " GEN $@" + @echo '#include "reg.h"' > $@ + @echo 'const u8 extra_regdb_certs[] = {' >> $@ + @for f in $^ ; do test -f $$f && hexdump -v -e '1/1 "0x%.2x," "\n"' < $$f >> $@ || true ; done + @echo '};' >> $@ + @echo 'unsigned int extra_regdb_certs_len = sizeof(extra_regdb_certs);' >> $@ diff --git a/net/wireless/certs/sforshee.x509 b/net/wireless/certs/sforshee.x509 Binary files differnew file mode 100644 index 000000000000..c6f8f9d6b988 --- /dev/null +++ b/net/wireless/certs/sforshee.x509 diff --git a/net/wireless/chan.c b/net/wireless/chan.c index fad1b5baf8ff..a48859982a32 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -465,7 +465,7 @@ bool cfg80211_is_sub_chan(struct cfg80211_chan_def *chandef, struct ieee80211_channel *chan) { int width; - u32 cf_offset, freq; + u32 freq; if (chandef->chan->center_freq == chan->center_freq) return true; @@ -474,8 +474,6 @@ bool cfg80211_is_sub_chan(struct cfg80211_chan_def *chandef, if (width <= 20) return false; - cf_offset = width / 2 - 10; - for (freq = chandef->center_freq1 - width / 2 + 10; freq <= chandef->center_freq1 + width / 2 - 10; freq += 20) { if (chan->center_freq == freq) diff --git a/net/wireless/core.c b/net/wireless/core.c index 7b33e8c366bc..fdde0d98fde1 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1384,7 +1384,7 @@ out_fail_sysfs: out_fail_pernet: return err; } -subsys_initcall(cfg80211_init); +fs_initcall(cfg80211_init); static void __exit cfg80211_exit(void) { diff --git a/net/wireless/core.h b/net/wireless/core.h index 705835047f98..d2f7e8b8a097 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -217,6 +217,7 @@ enum cfg80211_event_type { EVENT_DISCONNECTED, EVENT_IBSS_JOINED, EVENT_STOPPED, + EVENT_PORT_AUTHORIZED, }; struct cfg80211_event { @@ -236,6 +237,9 @@ struct cfg80211_event { u8 bssid[ETH_ALEN]; struct ieee80211_channel *channel; } ij; + struct { + u8 bssid[ETH_ALEN]; + } pa; }; }; @@ -386,6 +390,7 @@ int cfg80211_disconnect(struct cfg80211_registered_device *rdev, bool wextev); void __cfg80211_roamed(struct wireless_dev *wdev, struct cfg80211_roam_info *info); +void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid); int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); void cfg80211_autodisconnect_wk(struct work_struct *work); diff --git a/net/wireless/db.txt b/net/wireless/db.txt deleted file mode 100644 index a2fc3a09ccdc..000000000000 --- a/net/wireless/db.txt +++ /dev/null @@ -1,17 +0,0 @@ -# -# This file is a placeholder to prevent accidental build breakage if someone -# enables CONFIG_CFG80211_INTERNAL_REGDB. Almost no one actually needs to -# enable that build option. -# -# You should be using CRDA instead. It is even better if you use the CRDA -# package provided by your distribution, since they will probably keep it -# up-to-date on your behalf. -# -# If you _really_ intend to use CONFIG_CFG80211_INTERNAL_REGDB then you will -# need to replace this file with one containing appropriately formatted -# regulatory rules that cover the regulatory domains you will be using. Your -# best option is to extract the db.txt file from the wireless-regdb git -# repository: -# -# git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-regdb.git -# diff --git a/net/wireless/genregdb.awk b/net/wireless/genregdb.awk deleted file mode 100644 index baf2426b555a..000000000000 --- a/net/wireless/genregdb.awk +++ /dev/null @@ -1,158 +0,0 @@ -#!/usr/bin/awk -f -# -# genregdb.awk -- generate regdb.c from db.txt -# -# Actually, it reads from stdin (presumed to be db.txt) and writes -# to stdout (presumed to be regdb.c), but close enough... -# -# Copyright 2009 John W. Linville <linville@tuxdriver.com> -# -# Permission to use, copy, modify, and/or distribute this software for any -# purpose with or without fee is hereby granted, provided that the above -# copyright notice and this permission notice appear in all copies. -# -# THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES -# WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF -# MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR -# ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES -# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN -# ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF -# OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. - -BEGIN { - active = 0 - rules = 0; - print "/*" - print " * DO NOT EDIT -- file generated from data in db.txt" - print " */" - print "" - print "#include <linux/nl80211.h>" - print "#include <net/cfg80211.h>" - print "#include \"regdb.h\"" - print "" - regdb = "const struct ieee80211_regdomain *reg_regdb[] = {\n" -} - -function parse_country_head() { - country=$2 - sub(/:/, "", country) - printf "static const struct ieee80211_regdomain regdom_%s = {\n", country - printf "\t.alpha2 = \"%s\",\n", country - if ($NF ~ /DFS-ETSI/) - printf "\t.dfs_region = NL80211_DFS_ETSI,\n" - else if ($NF ~ /DFS-FCC/) - printf "\t.dfs_region = NL80211_DFS_FCC,\n" - else if ($NF ~ /DFS-JP/) - printf "\t.dfs_region = NL80211_DFS_JP,\n" - printf "\t.reg_rules = {\n" - active = 1 - regdb = regdb "\t®dom_" country ",\n" -} - -function parse_reg_rule() -{ - flag_starts_at = 7 - - start = $1 - sub(/\(/, "", start) - end = $3 - bw = $5 - sub(/\),/, "", bw) - gain = 0 - power = $6 - # power might be in mW... - units = $7 - dfs_cac = 0 - - sub(/\(/, "", power) - sub(/\),/, "", power) - sub(/\),/, "", units) - sub(/\)/, "", units) - - if (units == "mW") { - flag_starts_at = 8 - power = 10 * log(power)/log(10) - if ($8 ~ /[[:digit:]]/) { - flag_starts_at = 9 - dfs_cac = $8 - } - } else { - if ($7 ~ /[[:digit:]]/) { - flag_starts_at = 8 - dfs_cac = $7 - } - } - sub(/\(/, "", dfs_cac) - sub(/\),/, "", dfs_cac) - flagstr = "" - for (i=flag_starts_at; i<=NF; i++) - flagstr = flagstr $i - split(flagstr, flagarray, ",") - flags = "" - for (arg in flagarray) { - if (flagarray[arg] == "NO-OFDM") { - flags = flags "\n\t\t\tNL80211_RRF_NO_OFDM | " - } else if (flagarray[arg] == "NO-CCK") { - flags = flags "\n\t\t\tNL80211_RRF_NO_CCK | " - } else if (flagarray[arg] == "NO-INDOOR") { - flags = flags "\n\t\t\tNL80211_RRF_NO_INDOOR | " - } else if (flagarray[arg] == "NO-OUTDOOR") { - flags = flags "\n\t\t\tNL80211_RRF_NO_OUTDOOR | " - } else if (flagarray[arg] == "DFS") { - flags = flags "\n\t\t\tNL80211_RRF_DFS | " - } else if (flagarray[arg] == "PTP-ONLY") { - flags = flags "\n\t\t\tNL80211_RRF_PTP_ONLY | " - } else if (flagarray[arg] == "PTMP-ONLY") { - flags = flags "\n\t\t\tNL80211_RRF_PTMP_ONLY | " - } else if (flagarray[arg] == "PASSIVE-SCAN") { - flags = flags "\n\t\t\tNL80211_RRF_NO_IR | " - } else if (flagarray[arg] == "NO-IBSS") { - flags = flags "\n\t\t\tNL80211_RRF_NO_IR | " - } else if (flagarray[arg] == "NO-IR") { - flags = flags "\n\t\t\tNL80211_RRF_NO_IR | " - } else if (flagarray[arg] == "AUTO-BW") { - flags = flags "\n\t\t\tNL80211_RRF_AUTO_BW | " - } - - } - flags = flags "0" - printf "\t\tREG_RULE_EXT(%d, %d, %d, %d, %.0f, %d, %s),\n", start, end, bw, gain, power, dfs_cac, flags - rules++ -} - -function print_tail_country() -{ - active = 0 - printf "\t},\n" - printf "\t.n_reg_rules = %d\n", rules - printf "};\n\n" - rules = 0; -} - -/^[ \t]*#/ { - # Ignore -} - -!active && /^[ \t]*$/ { - # Ignore -} - -!active && /country/ { - parse_country_head() -} - -active && /^[ \t]*\(/ { - parse_reg_rule() -} - -active && /^[ \t]*$/ { - print_tail_country() -} - -END { - if (active) - print_tail_country() - print regdb "};" - print "" - print "int reg_regdb_size = ARRAY_SIZE(reg_regdb);" -} diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index d396cb61a280..a0e1951227fa 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2130,6 +2130,15 @@ static int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, case NL80211_CHAN_HT40MINUS: cfg80211_chandef_create(chandef, chandef->chan, chantype); + /* user input for center_freq is incorrect */ + if (info->attrs[NL80211_ATTR_CENTER_FREQ1] && + chandef->center_freq1 != nla_get_u32( + info->attrs[NL80211_ATTR_CENTER_FREQ1])) + return -EINVAL; + /* center_freq2 must be zero */ + if (info->attrs[NL80211_ATTR_CENTER_FREQ2] && + nla_get_u32(info->attrs[NL80211_ATTR_CENTER_FREQ2])) + return -EINVAL; break; default: return -EINVAL; @@ -5677,6 +5686,11 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info) } } +static int nl80211_reload_regdb(struct sk_buff *skb, struct genl_info *info) +{ + return reg_reload_regdb(); +} + static int nl80211_get_mesh_config(struct sk_buff *skb, struct genl_info *info) { @@ -6277,7 +6291,7 @@ static int nl80211_send_regdom(struct sk_buff *msg, struct netlink_callback *cb, if (!hdr) return -1; - genl_dump_check_consistent(cb, hdr, &nl80211_fam); + genl_dump_check_consistent(cb, hdr); if (nl80211_put_regdom(regdom, msg)) goto nla_put_failure; @@ -6618,6 +6632,77 @@ static bool cfg80211_off_channel_oper_allowed(struct wireless_dev *wdev) return regulatory_pre_cac_allowed(wdev->wiphy); } +static int +nl80211_check_scan_flags(struct wiphy *wiphy, struct wireless_dev *wdev, + void *request, struct nlattr **attrs, + bool is_sched_scan) +{ + u8 *mac_addr, *mac_addr_mask; + u32 *flags; + enum nl80211_feature_flags randomness_flag; + + if (!attrs[NL80211_ATTR_SCAN_FLAGS]) + return 0; + + if (is_sched_scan) { + struct cfg80211_sched_scan_request *req = request; + + randomness_flag = wdev ? + NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR : + NL80211_FEATURE_ND_RANDOM_MAC_ADDR; + flags = &req->flags; + mac_addr = req->mac_addr; + mac_addr_mask = req->mac_addr_mask; + } else { + struct cfg80211_scan_request *req = request; + + randomness_flag = NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR; + flags = &req->flags; + mac_addr = req->mac_addr; + mac_addr_mask = req->mac_addr_mask; + } + + *flags = nla_get_u32(attrs[NL80211_ATTR_SCAN_FLAGS]); + + if ((*flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && + !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) + return -EOPNOTSUPP; + + if (*flags & NL80211_SCAN_FLAG_RANDOM_ADDR) { + int err; + + if (!(wiphy->features & randomness_flag) || + (wdev && wdev->current_bss)) + return -EOPNOTSUPP; + + err = nl80211_parse_random_mac(attrs, mac_addr, mac_addr_mask); + if (err) + return err; + } + + if ((*flags & NL80211_SCAN_FLAG_FILS_MAX_CHANNEL_TIME) && + !wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_FILS_MAX_CHANNEL_TIME)) + return -EOPNOTSUPP; + + if ((*flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP) && + !wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP)) + return -EOPNOTSUPP; + + if ((*flags & NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION) && + !wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION)) + return -EOPNOTSUPP; + + if ((*flags & NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE) && + !wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE)) + return -EOPNOTSUPP; + + return 0; +} + static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; @@ -6823,34 +6908,10 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) nla_get_flag(info->attrs[NL80211_ATTR_MEASUREMENT_DURATION_MANDATORY]); } - if (info->attrs[NL80211_ATTR_SCAN_FLAGS]) { - request->flags = nla_get_u32( - info->attrs[NL80211_ATTR_SCAN_FLAGS]); - if ((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && - !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) { - err = -EOPNOTSUPP; - goto out_free; - } - - if (request->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) { - if (!(wiphy->features & - NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR)) { - err = -EOPNOTSUPP; - goto out_free; - } - - if (wdev->current_bss) { - err = -EOPNOTSUPP; - goto out_free; - } - - err = nl80211_parse_random_mac(info->attrs, - request->mac_addr, - request->mac_addr_mask); - if (err) - goto out_free; - } - } + err = nl80211_check_scan_flags(wiphy, wdev, request, info->attrs, + false); + if (err) + goto out_free; request->no_cck = nla_get_flag(info->attrs[NL80211_ATTR_TX_NO_CCK_RATE]); @@ -7298,37 +7359,9 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, request->ie_len); } - if (attrs[NL80211_ATTR_SCAN_FLAGS]) { - request->flags = nla_get_u32( - attrs[NL80211_ATTR_SCAN_FLAGS]); - if ((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && - !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) { - err = -EOPNOTSUPP; - goto out_free; - } - - if (request->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) { - u32 flg = NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR; - - if (!wdev) /* must be net-detect */ - flg = NL80211_FEATURE_ND_RANDOM_MAC_ADDR; - - if (!(wiphy->features & flg)) { - err = -EOPNOTSUPP; - goto out_free; - } - - if (wdev && wdev->current_bss) { - err = -EOPNOTSUPP; - goto out_free; - } - - err = nl80211_parse_random_mac(attrs, request->mac_addr, - request->mac_addr_mask); - if (err) - goto out_free; - } - } + err = nl80211_check_scan_flags(wiphy, wdev, request, attrs, true); + if (err) + goto out_free; if (attrs[NL80211_ATTR_SCHED_SCAN_DELAY]) request->delay = @@ -7689,7 +7722,7 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb, if (!hdr) return -1; - genl_dump_check_consistent(cb, hdr, &nl80211_fam); + genl_dump_check_consistent(cb, hdr); if (nla_put_u32(msg, NL80211_ATTR_GENERATION, rdev->bss_generation)) goto nla_put_failure; @@ -8932,8 +8965,14 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_USE_MFP]) { connect.mfp = nla_get_u32(info->attrs[NL80211_ATTR_USE_MFP]); + if (connect.mfp == NL80211_MFP_OPTIONAL && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_MFP_OPTIONAL)) + return -EOPNOTSUPP; + if (connect.mfp != NL80211_MFP_REQUIRED && - connect.mfp != NL80211_MFP_NO) + connect.mfp != NL80211_MFP_NO && + connect.mfp != NL80211_MFP_OPTIONAL) return -EINVAL; } else { connect.mfp = NL80211_MFP_NO; @@ -12685,6 +12724,12 @@ static const struct genl_ops nl80211_ops[] = { .flags = GENL_ADMIN_PERM, }, { + .cmd = NL80211_CMD_RELOAD_REGDB, + .doit = nl80211_reload_regdb, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + }, + { .cmd = NL80211_CMD_GET_MESH_CONFIG, .doit = nl80211_get_mesh_config, .policy = nl80211_policy, @@ -13812,9 +13857,7 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, info->req_ie)) || (info->resp_ie && nla_put(msg, NL80211_ATTR_RESP_IE, info->resp_ie_len, - info->resp_ie)) || - (info->authorized && - nla_put_flag(msg, NL80211_ATTR_PORT_AUTHORIZED))) + info->resp_ie))) goto nla_put_failure; genlmsg_end(msg, hdr); @@ -13828,6 +13871,36 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, nlmsg_free(msg); } +void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *bssid) +{ + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_PORT_AUTHORIZED); + if (!hdr) { + nlmsg_free(msg); + return; + } + + if (nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0, + NL80211_MCGRP_MLME, GFP_KERNEL); + return; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + nlmsg_free(msg); +} + void nl80211_send_disconnected(struct cfg80211_registered_device *rdev, struct net_device *netdev, u16 reason, const u8 *ie, size_t ie_len, bool from_ap) @@ -14201,7 +14274,7 @@ static bool __nl80211_unexpected_frame(struct net_device *dev, u8 cmd, struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct sk_buff *msg; void *hdr; - u32 nlportid = ACCESS_ONCE(wdev->ap_unexpected_nlportid); + u32 nlportid = READ_ONCE(wdev->ap_unexpected_nlportid); if (!nlportid) return false; diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index fc415c8f7aac..79e47fe60c35 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -59,6 +59,8 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, void nl80211_send_roamed(struct cfg80211_registered_device *rdev, struct net_device *netdev, struct cfg80211_roam_info *info, gfp_t gfp); +void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *bssid); void nl80211_send_disconnected(struct cfg80211_registered_device *rdev, struct net_device *netdev, u16 reason, const u8 *ie, size_t ie_len, bool from_ap); diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 6e94f6934a0e..3871998059de 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -53,12 +53,13 @@ #include <linux/ctype.h> #include <linux/nl80211.h> #include <linux/platform_device.h> +#include <linux/verification.h> #include <linux/moduleparam.h> +#include <linux/firmware.h> #include <net/cfg80211.h> #include "core.h" #include "reg.h" #include "rdev-ops.h" -#include "regdb.h" #include "nl80211.h" /* @@ -100,7 +101,7 @@ static struct regulatory_request core_request_world = { static struct regulatory_request __rcu *last_request = (void __force __rcu *)&core_request_world; -/* To trigger userspace events */ +/* To trigger userspace events and load firmware */ static struct platform_device *reg_pdev; /* @@ -443,7 +444,6 @@ reg_copy_regd(const struct ieee80211_regdomain *src_regd) return regd; } -#ifdef CONFIG_CFG80211_INTERNAL_REGDB struct reg_regdb_apply_request { struct list_head list; const struct ieee80211_regdomain *regdom; @@ -475,55 +475,26 @@ static void reg_regdb_apply(struct work_struct *work) static DECLARE_WORK(reg_regdb_work, reg_regdb_apply); -static int reg_query_builtin(const char *alpha2) +static int reg_schedule_apply(const struct ieee80211_regdomain *regdom) { - const struct ieee80211_regdomain *regdom = NULL; struct reg_regdb_apply_request *request; - unsigned int i; - - for (i = 0; i < reg_regdb_size; i++) { - if (alpha2_equal(alpha2, reg_regdb[i]->alpha2)) { - regdom = reg_regdb[i]; - break; - } - } - - if (!regdom) - return -ENODATA; request = kzalloc(sizeof(struct reg_regdb_apply_request), GFP_KERNEL); - if (!request) - return -ENOMEM; - - request->regdom = reg_copy_regd(regdom); - if (IS_ERR_OR_NULL(request->regdom)) { - kfree(request); + if (!request) { + kfree(regdom); return -ENOMEM; } + request->regdom = regdom; + mutex_lock(®_regdb_apply_mutex); list_add_tail(&request->list, ®_regdb_apply_list); mutex_unlock(®_regdb_apply_mutex); schedule_work(®_regdb_work); - return 0; } -/* Feel free to add any other sanity checks here */ -static void reg_regdb_size_check(void) -{ - /* We should ideally BUILD_BUG_ON() but then random builds would fail */ - WARN_ONCE(!reg_regdb_size, "db.txt is empty, you should update it..."); -} -#else -static inline void reg_regdb_size_check(void) {} -static inline int reg_query_builtin(const char *alpha2) -{ - return -ENODATA; -} -#endif /* CONFIG_CFG80211_INTERNAL_REGDB */ - #ifdef CONFIG_CFG80211_CRDA_SUPPORT /* Max number of consecutive attempts to communicate with CRDA */ #define REG_MAX_CRDA_TIMEOUTS 10 @@ -599,10 +570,402 @@ static inline int call_crda(const char *alpha2) } #endif /* CONFIG_CFG80211_CRDA_SUPPORT */ +/* code to directly load a firmware database through request_firmware */ +static const struct fwdb_header *regdb; + +struct fwdb_country { + u8 alpha2[2]; + __be16 coll_ptr; + /* this struct cannot be extended */ +} __packed __aligned(4); + +struct fwdb_collection { + u8 len; + u8 n_rules; + u8 dfs_region; + /* no optional data yet */ + /* aligned to 2, then followed by __be16 array of rule pointers */ +} __packed __aligned(4); + +enum fwdb_flags { + FWDB_FLAG_NO_OFDM = BIT(0), + FWDB_FLAG_NO_OUTDOOR = BIT(1), + FWDB_FLAG_DFS = BIT(2), + FWDB_FLAG_NO_IR = BIT(3), + FWDB_FLAG_AUTO_BW = BIT(4), +}; + +struct fwdb_rule { + u8 len; + u8 flags; + __be16 max_eirp; + __be32 start, end, max_bw; + /* start of optional data */ + __be16 cac_timeout; +} __packed __aligned(4); + +#define FWDB_MAGIC 0x52474442 +#define FWDB_VERSION 20 + +struct fwdb_header { + __be32 magic; + __be32 version; + struct fwdb_country country[]; +} __packed __aligned(4); + +static bool valid_rule(const u8 *data, unsigned int size, u16 rule_ptr) +{ + struct fwdb_rule *rule = (void *)(data + (rule_ptr << 2)); + + if ((u8 *)rule + sizeof(rule->len) > data + size) + return false; + + /* mandatory fields */ + if (rule->len < offsetofend(struct fwdb_rule, max_bw)) + return false; + + return true; +} + +static bool valid_country(const u8 *data, unsigned int size, + const struct fwdb_country *country) +{ + unsigned int ptr = be16_to_cpu(country->coll_ptr) << 2; + struct fwdb_collection *coll = (void *)(data + ptr); + __be16 *rules_ptr; + unsigned int i; + + /* make sure we can read len/n_rules */ + if ((u8 *)coll + offsetofend(typeof(*coll), n_rules) > data + size) + return false; + + /* make sure base struct and all rules fit */ + if ((u8 *)coll + ALIGN(coll->len, 2) + + (coll->n_rules * 2) > data + size) + return false; + + /* mandatory fields must exist */ + if (coll->len < offsetofend(struct fwdb_collection, dfs_region)) + return false; + + rules_ptr = (void *)((u8 *)coll + ALIGN(coll->len, 2)); + + for (i = 0; i < coll->n_rules; i++) { + u16 rule_ptr = be16_to_cpu(rules_ptr[i]); + + if (!valid_rule(data, size, rule_ptr)) + return false; + } + + return true; +} + +#ifdef CONFIG_CFG80211_REQUIRE_SIGNED_REGDB +static struct key *builtin_regdb_keys; + +static void __init load_keys_from_buffer(const u8 *p, unsigned int buflen) +{ + const u8 *end = p + buflen; + size_t plen; + key_ref_t key; + + while (p < end) { + /* Each cert begins with an ASN.1 SEQUENCE tag and must be more + * than 256 bytes in size. + */ + if (end - p < 4) + goto dodgy_cert; + if (p[0] != 0x30 && + p[1] != 0x82) + goto dodgy_cert; + plen = (p[2] << 8) | p[3]; + plen += 4; + if (plen > end - p) + goto dodgy_cert; + + key = key_create_or_update(make_key_ref(builtin_regdb_keys, 1), + "asymmetric", NULL, p, plen, + ((KEY_POS_ALL & ~KEY_POS_SETATTR) | + KEY_USR_VIEW | KEY_USR_READ), + KEY_ALLOC_NOT_IN_QUOTA | + KEY_ALLOC_BUILT_IN | + KEY_ALLOC_BYPASS_RESTRICTION); + if (IS_ERR(key)) { + pr_err("Problem loading in-kernel X.509 certificate (%ld)\n", + PTR_ERR(key)); + } else { + pr_notice("Loaded X.509 cert '%s'\n", + key_ref_to_ptr(key)->description); + key_ref_put(key); + } + p += plen; + } + + return; + +dodgy_cert: + pr_err("Problem parsing in-kernel X.509 certificate list\n"); +} + +static int __init load_builtin_regdb_keys(void) +{ + builtin_regdb_keys = + keyring_alloc(".builtin_regdb_keys", + KUIDT_INIT(0), KGIDT_INIT(0), current_cred(), + ((KEY_POS_ALL & ~KEY_POS_SETATTR) | + KEY_USR_VIEW | KEY_USR_READ | KEY_USR_SEARCH), + KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL); + if (IS_ERR(builtin_regdb_keys)) + return PTR_ERR(builtin_regdb_keys); + + pr_notice("Loading compiled-in X.509 certificates for regulatory database\n"); + +#ifdef CONFIG_CFG80211_USE_KERNEL_REGDB_KEYS + load_keys_from_buffer(shipped_regdb_certs, shipped_regdb_certs_len); +#endif +#ifdef CONFIG_CFG80211_EXTRA_REGDB_KEYDIR + if (CONFIG_CFG80211_EXTRA_REGDB_KEYDIR[0] != '\0') + load_keys_from_buffer(extra_regdb_certs, extra_regdb_certs_len); +#endif + + return 0; +} + +static bool regdb_has_valid_signature(const u8 *data, unsigned int size) +{ + const struct firmware *sig; + bool result; + + if (request_firmware(&sig, "regulatory.db.p7s", ®_pdev->dev)) + return false; + + result = verify_pkcs7_signature(data, size, sig->data, sig->size, + builtin_regdb_keys, + VERIFYING_UNSPECIFIED_SIGNATURE, + NULL, NULL) == 0; + + release_firmware(sig); + + return result; +} + +static void free_regdb_keyring(void) +{ + key_put(builtin_regdb_keys); +} +#else +static int load_builtin_regdb_keys(void) +{ + return 0; +} + +static bool regdb_has_valid_signature(const u8 *data, unsigned int size) +{ + return true; +} + +static void free_regdb_keyring(void) +{ +} +#endif /* CONFIG_CFG80211_REQUIRE_SIGNED_REGDB */ + +static bool valid_regdb(const u8 *data, unsigned int size) +{ + const struct fwdb_header *hdr = (void *)data; + const struct fwdb_country *country; + + if (size < sizeof(*hdr)) + return false; + + if (hdr->magic != cpu_to_be32(FWDB_MAGIC)) + return false; + + if (hdr->version != cpu_to_be32(FWDB_VERSION)) + return false; + + if (!regdb_has_valid_signature(data, size)) + return false; + + country = &hdr->country[0]; + while ((u8 *)(country + 1) <= data + size) { + if (!country->coll_ptr) + break; + if (!valid_country(data, size, country)) + return false; + country++; + } + + return true; +} + +static int regdb_query_country(const struct fwdb_header *db, + const struct fwdb_country *country) +{ + unsigned int ptr = be16_to_cpu(country->coll_ptr) << 2; + struct fwdb_collection *coll = (void *)((u8 *)db + ptr); + struct ieee80211_regdomain *regdom; + unsigned int size_of_regd; + unsigned int i; + + size_of_regd = + sizeof(struct ieee80211_regdomain) + + coll->n_rules * sizeof(struct ieee80211_reg_rule); + + regdom = kzalloc(size_of_regd, GFP_KERNEL); + if (!regdom) + return -ENOMEM; + + regdom->n_reg_rules = coll->n_rules; + regdom->alpha2[0] = country->alpha2[0]; + regdom->alpha2[1] = country->alpha2[1]; + regdom->dfs_region = coll->dfs_region; + + for (i = 0; i < regdom->n_reg_rules; i++) { + __be16 *rules_ptr = (void *)((u8 *)coll + ALIGN(coll->len, 2)); + unsigned int rule_ptr = be16_to_cpu(rules_ptr[i]) << 2; + struct fwdb_rule *rule = (void *)((u8 *)db + rule_ptr); + struct ieee80211_reg_rule *rrule = ®dom->reg_rules[i]; + + rrule->freq_range.start_freq_khz = be32_to_cpu(rule->start); + rrule->freq_range.end_freq_khz = be32_to_cpu(rule->end); + rrule->freq_range.max_bandwidth_khz = be32_to_cpu(rule->max_bw); + + rrule->power_rule.max_antenna_gain = 0; + rrule->power_rule.max_eirp = be16_to_cpu(rule->max_eirp); + + rrule->flags = 0; + if (rule->flags & FWDB_FLAG_NO_OFDM) + rrule->flags |= NL80211_RRF_NO_OFDM; + if (rule->flags & FWDB_FLAG_NO_OUTDOOR) + rrule->flags |= NL80211_RRF_NO_OUTDOOR; + if (rule->flags & FWDB_FLAG_DFS) + rrule->flags |= NL80211_RRF_DFS; + if (rule->flags & FWDB_FLAG_NO_IR) + rrule->flags |= NL80211_RRF_NO_IR; + if (rule->flags & FWDB_FLAG_AUTO_BW) + rrule->flags |= NL80211_RRF_AUTO_BW; + + rrule->dfs_cac_ms = 0; + + /* handle optional data */ + if (rule->len >= offsetofend(struct fwdb_rule, cac_timeout)) + rrule->dfs_cac_ms = + 1000 * be16_to_cpu(rule->cac_timeout); + } + + return reg_schedule_apply(regdom); +} + +static int query_regdb(const char *alpha2) +{ + const struct fwdb_header *hdr = regdb; + const struct fwdb_country *country; + + ASSERT_RTNL(); + + if (IS_ERR(regdb)) + return PTR_ERR(regdb); + + country = &hdr->country[0]; + while (country->coll_ptr) { + if (alpha2_equal(alpha2, country->alpha2)) + return regdb_query_country(regdb, country); + country++; + } + + return -ENODATA; +} + +static void regdb_fw_cb(const struct firmware *fw, void *context) +{ + int set_error = 0; + bool restore = true; + void *db; + + if (!fw) { + pr_info("failed to load regulatory.db\n"); + set_error = -ENODATA; + } else if (!valid_regdb(fw->data, fw->size)) { + pr_info("loaded regulatory.db is malformed or signature is missing/invalid\n"); + set_error = -EINVAL; + } + + rtnl_lock(); + if (WARN_ON(regdb && !IS_ERR(regdb))) { + /* just restore and free new db */ + } else if (set_error) { + regdb = ERR_PTR(set_error); + } else if (fw) { + db = kmemdup(fw->data, fw->size, GFP_KERNEL); + if (db) { + regdb = db; + restore = context && query_regdb(context); + } else { + restore = true; + } + } + + if (restore) + restore_regulatory_settings(true); + + rtnl_unlock(); + + kfree(context); + + release_firmware(fw); +} + +static int query_regdb_file(const char *alpha2) +{ + ASSERT_RTNL(); + + if (regdb) + return query_regdb(alpha2); + + alpha2 = kmemdup(alpha2, 2, GFP_KERNEL); + if (!alpha2) + return -ENOMEM; + + return request_firmware_nowait(THIS_MODULE, true, "regulatory.db", + ®_pdev->dev, GFP_KERNEL, + (void *)alpha2, regdb_fw_cb); +} + +int reg_reload_regdb(void) +{ + const struct firmware *fw; + void *db; + int err; + + err = request_firmware(&fw, "regulatory.db", ®_pdev->dev); + if (err) + return err; + + if (!valid_regdb(fw->data, fw->size)) { + err = -ENODATA; + goto out; + } + + db = kmemdup(fw->data, fw->size, GFP_KERNEL); + if (!db) { + err = -ENOMEM; + goto out; + } + + rtnl_lock(); + if (!IS_ERR_OR_NULL(regdb)) + kfree(regdb); + regdb = db; + rtnl_unlock(); + + out: + release_firmware(fw); + return err; +} + static bool reg_query_database(struct regulatory_request *request) { - /* query internal regulatory database (if it exists) */ - if (reg_query_builtin(request->alpha2) == 0) + if (query_regdb_file(request->alpha2) == 0) return true; if (call_crda(request->alpha2) == 0) @@ -3285,6 +3648,10 @@ int __init regulatory_init(void) { int err = 0; + err = load_builtin_regdb_keys(); + if (err) + return err; + reg_pdev = platform_device_register_simple("regulatory", 0, NULL, 0); if (IS_ERR(reg_pdev)) return PTR_ERR(reg_pdev); @@ -3293,8 +3660,6 @@ int __init regulatory_init(void) spin_lock_init(®_pending_beacons_lock); spin_lock_init(®_indoor_lock); - reg_regdb_size_check(); - rcu_assign_pointer(cfg80211_regdomain, cfg80211_world_regdom); user_alpha2[0] = '9'; @@ -3360,4 +3725,9 @@ void regulatory_exit(void) list_del(®_request->list); kfree(reg_request); } + + if (!IS_ERR_OR_NULL(regdb)) + kfree(regdb); + + free_regdb_keyring(); } diff --git a/net/wireless/reg.h b/net/wireless/reg.h index ca7fedf2e7a1..9ceeb5f3a7cb 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -1,5 +1,8 @@ #ifndef __NET_WIRELESS_REG_H #define __NET_WIRELESS_REG_H + +#include <net/cfg80211.h> + /* * Copyright 2008-2011 Luis R. Rodriguez <mcgrof@qca.qualcomm.com> * @@ -179,4 +182,15 @@ void regulatory_propagate_dfs_state(struct wiphy *wiphy, * @wiphy2 - wiphy it's dfs_region to be checked against that of wiphy1 */ bool reg_dfs_domain_same(struct wiphy *wiphy1, struct wiphy *wiphy2); + +/** + * reg_reload_regdb - reload the regulatory.db firmware file + */ +int reg_reload_regdb(void); + +extern const u8 shipped_regdb_certs[]; +extern unsigned int shipped_regdb_certs_len; +extern const u8 extra_regdb_certs[]; +extern unsigned int extra_regdb_certs_len; + #endif /* __NET_WIRELESS_REG_H */ diff --git a/net/wireless/regdb.h b/net/wireless/regdb.h deleted file mode 100644 index 3279cfcefb0c..000000000000 --- a/net/wireless/regdb.h +++ /dev/null @@ -1,23 +0,0 @@ -#ifndef __REGDB_H__ -#define __REGDB_H__ - -/* - * Copyright 2009 John W. Linville <linville@tuxdriver.com> - * - * Permission to use, copy, modify, and/or distribute this software for any - * purpose with or without fee is hereby granted, provided that the above - * copyright notice and this permission notice appear in all copies. - * - * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES - * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR - * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES - * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN - * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF - * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. - */ - -extern const struct ieee80211_regdomain *reg_regdb[]; -extern int reg_regdb_size; - -#endif /* __REGDB_H__ */ diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 3dd05a08c60a..fdb3646274a5 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -956,7 +956,6 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, ev->rm.resp_ie_len = info->resp_ie_len; memcpy((void *)ev->rm.resp_ie, info->resp_ie, info->resp_ie_len); ev->rm.bss = info->bss; - ev->rm.authorized = info->authorized; spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); @@ -965,6 +964,50 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, } EXPORT_SYMBOL(cfg80211_roamed); +void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid) +{ + ASSERT_WDEV_LOCK(wdev); + + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) + return; + + if (WARN_ON(!wdev->current_bss) || + WARN_ON(!ether_addr_equal(wdev->current_bss->pub.bssid, bssid))) + return; + + nl80211_send_port_authorized(wiphy_to_rdev(wdev->wiphy), wdev->netdev, + bssid); +} + +void cfg80211_port_authorized(struct net_device *dev, const u8 *bssid, + gfp_t gfp) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + struct cfg80211_event *ev; + unsigned long flags; + + if (WARN_ON(!bssid)) + return; + + ev = kzalloc(sizeof(*ev), gfp); + if (!ev) + return; + + ev->type = EVENT_PORT_AUTHORIZED; + memcpy(ev->pa.bssid, bssid, ETH_ALEN); + + /* + * Use the wdev event list so that if there are pending + * connected/roamed events, they will be reported first. + */ + spin_lock_irqsave(&wdev->event_lock, flags); + list_add_tail(&ev->list, &wdev->event_list); + spin_unlock_irqrestore(&wdev->event_lock, flags); + queue_work(cfg80211_wq, &rdev->event_work); +} +EXPORT_SYMBOL(cfg80211_port_authorized); + void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, size_t ie_len, u16 reason, bool from_ap) { diff --git a/net/wireless/util.c b/net/wireless/util.c index c1238d582fd1..c69160694b6c 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -158,32 +158,30 @@ static void set_mandatory_flags_band(struct ieee80211_supported_band *sband) case NL80211_BAND_2GHZ: want = 7; for (i = 0; i < sband->n_bitrates; i++) { - if (sband->bitrates[i].bitrate == 10) { + switch (sband->bitrates[i].bitrate) { + case 10: + case 20: + case 55: + case 110: sband->bitrates[i].flags |= IEEE80211_RATE_MANDATORY_B | IEEE80211_RATE_MANDATORY_G; want--; - } - - if (sband->bitrates[i].bitrate == 20 || - sband->bitrates[i].bitrate == 55 || - sband->bitrates[i].bitrate == 110 || - sband->bitrates[i].bitrate == 60 || - sband->bitrates[i].bitrate == 120 || - sband->bitrates[i].bitrate == 240) { + break; + case 60: + case 120: + case 240: sband->bitrates[i].flags |= IEEE80211_RATE_MANDATORY_G; want--; - } - - if (sband->bitrates[i].bitrate != 10 && - sband->bitrates[i].bitrate != 20 && - sband->bitrates[i].bitrate != 55 && - sband->bitrates[i].bitrate != 110) + /* fall through */ + default: sband->bitrates[i].flags |= IEEE80211_RATE_ERP_G; + break; + } } - WARN_ON(want != 0 && want != 3 && want != 6); + WARN_ON(want != 0 && want != 3); break; case NL80211_BAND_60GHZ: /* check for mandatory HT MCS 1..4 */ @@ -530,121 +528,6 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, } EXPORT_SYMBOL(ieee80211_data_to_8023_exthdr); -int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr, - enum nl80211_iftype iftype, - const u8 *bssid, bool qos) -{ - struct ieee80211_hdr hdr; - u16 hdrlen, ethertype; - __le16 fc; - const u8 *encaps_data; - int encaps_len, skip_header_bytes; - int nh_pos, h_pos; - int head_need; - - if (unlikely(skb->len < ETH_HLEN)) - return -EINVAL; - - nh_pos = skb_network_header(skb) - skb->data; - h_pos = skb_transport_header(skb) - skb->data; - - /* convert Ethernet header to proper 802.11 header (based on - * operation mode) */ - ethertype = (skb->data[12] << 8) | skb->data[13]; - fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_DATA); - - switch (iftype) { - case NL80211_IFTYPE_AP: - case NL80211_IFTYPE_AP_VLAN: - case NL80211_IFTYPE_P2P_GO: - fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS); - /* DA BSSID SA */ - memcpy(hdr.addr1, skb->data, ETH_ALEN); - memcpy(hdr.addr2, addr, ETH_ALEN); - memcpy(hdr.addr3, skb->data + ETH_ALEN, ETH_ALEN); - hdrlen = 24; - break; - case NL80211_IFTYPE_STATION: - case NL80211_IFTYPE_P2P_CLIENT: - fc |= cpu_to_le16(IEEE80211_FCTL_TODS); - /* BSSID SA DA */ - memcpy(hdr.addr1, bssid, ETH_ALEN); - memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN); - memcpy(hdr.addr3, skb->data, ETH_ALEN); - hdrlen = 24; - break; - case NL80211_IFTYPE_OCB: - case NL80211_IFTYPE_ADHOC: - /* DA SA BSSID */ - memcpy(hdr.addr1, skb->data, ETH_ALEN); - memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN); - memcpy(hdr.addr3, bssid, ETH_ALEN); - hdrlen = 24; - break; - default: - return -EOPNOTSUPP; - } - - if (qos) { - fc |= cpu_to_le16(IEEE80211_STYPE_QOS_DATA); - hdrlen += 2; - } - - hdr.frame_control = fc; - hdr.duration_id = 0; - hdr.seq_ctrl = 0; - - skip_header_bytes = ETH_HLEN; - if (ethertype == ETH_P_AARP || ethertype == ETH_P_IPX) { - encaps_data = bridge_tunnel_header; - encaps_len = sizeof(bridge_tunnel_header); - skip_header_bytes -= 2; - } else if (ethertype >= ETH_P_802_3_MIN) { - encaps_data = rfc1042_header; - encaps_len = sizeof(rfc1042_header); - skip_header_bytes -= 2; - } else { - encaps_data = NULL; - encaps_len = 0; - } - - skb_pull(skb, skip_header_bytes); - nh_pos -= skip_header_bytes; - h_pos -= skip_header_bytes; - - head_need = hdrlen + encaps_len - skb_headroom(skb); - - if (head_need > 0 || skb_cloned(skb)) { - head_need = max(head_need, 0); - if (head_need) - skb_orphan(skb); - - if (pskb_expand_head(skb, head_need, 0, GFP_ATOMIC)) - return -ENOMEM; - } - - if (encaps_data) { - memcpy(skb_push(skb, encaps_len), encaps_data, encaps_len); - nh_pos += encaps_len; - h_pos += encaps_len; - } - - memcpy(skb_push(skb, hdrlen), &hdr, hdrlen); - - nh_pos += hdrlen; - h_pos += hdrlen; - - /* Update skb pointers to various headers since this modified frame - * is going to go through Linux networking code that may potentially - * need things like pointer to IP header. */ - skb_reset_mac_header(skb); - skb_set_network_header(skb, nh_pos); - skb_set_transport_header(skb, h_pos); - - return 0; -} -EXPORT_SYMBOL(ieee80211_data_from_8023); - static void __frame_add_frag(struct sk_buff *skb, struct page *page, void *ptr, int len, int size) @@ -964,6 +847,9 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev) case EVENT_STOPPED: __cfg80211_leave(wiphy_to_rdev(wdev->wiphy), wdev); break; + case EVENT_PORT_AUTHORIZED: + __cfg80211_port_authorized(wdev, ev->pa.bssid); + break; } wdev_unlock(wdev); @@ -1368,13 +1254,29 @@ int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len, } EXPORT_SYMBOL(cfg80211_get_p2p_attr); -static bool ieee80211_id_in_list(const u8 *ids, int n_ids, u8 id) +static bool ieee80211_id_in_list(const u8 *ids, int n_ids, u8 id, bool id_ext) { int i; - for (i = 0; i < n_ids; i++) - if (ids[i] == id) + /* Make sure array values are legal */ + if (WARN_ON(ids[n_ids - 1] == WLAN_EID_EXTENSION)) + return false; + + i = 0; + while (i < n_ids) { + if (ids[i] == WLAN_EID_EXTENSION) { + if (id_ext && (ids[i + 1] == id)) + return true; + + i += 2; + continue; + } + + if (ids[i] == id && !id_ext) return true; + + i++; + } return false; } @@ -1404,14 +1306,36 @@ size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen, { size_t pos = offset; - while (pos < ielen && ieee80211_id_in_list(ids, n_ids, ies[pos])) { + while (pos < ielen) { + u8 ext = 0; + + if (ies[pos] == WLAN_EID_EXTENSION) + ext = 2; + if ((pos + ext) >= ielen) + break; + + if (!ieee80211_id_in_list(ids, n_ids, ies[pos + ext], + ies[pos] == WLAN_EID_EXTENSION)) + break; + if (ies[pos] == WLAN_EID_RIC_DATA && n_after_ric) { pos = skip_ie(ies, ielen, pos); - while (pos < ielen && - !ieee80211_id_in_list(after_ric, n_after_ric, - ies[pos])) - pos = skip_ie(ies, ielen, pos); + while (pos < ielen) { + if (ies[pos] == WLAN_EID_EXTENSION) + ext = 2; + else + ext = 0; + + if ((pos + ext) >= ielen) + break; + + if (!ieee80211_id_in_list(after_ric, + n_after_ric, + ies[pos + ext], + ext == 2)) + pos = skip_ie(ies, ielen, pos); + } } else { pos = skip_ie(ies, ielen, pos); } diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index ac095936552d..ea87143314f3 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -374,9 +374,11 @@ static void __x25_destroy_socket(struct sock *); /* * handler for deferred kills. */ -static void x25_destroy_timer(unsigned long data) +static void x25_destroy_timer(struct timer_list *t) { - x25_destroy_socket_from_timer((struct sock *)data); + struct sock *sk = from_timer(sk, t, sk_timer); + + x25_destroy_socket_from_timer(sk); } /* @@ -413,8 +415,7 @@ static void __x25_destroy_socket(struct sock *sk) if (sk_has_allocations(sk)) { /* Defer: outstanding buffers */ sk->sk_timer.expires = jiffies + 10 * HZ; - sk->sk_timer.function = x25_destroy_timer; - sk->sk_timer.data = (unsigned long)sk; + sk->sk_timer.function = (TIMER_FUNC_TYPE)x25_destroy_timer; add_timer(&sk->sk_timer); } else { /* drop last reference so sock_put will free */ diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c index 997ff7b2509b..ad1734d36ed7 100644 --- a/net/x25/x25_facilities.c +++ b/net/x25/x25_facilities.c @@ -103,7 +103,7 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, *vc_fac_mask |= X25_MASK_REVERSE; break; } - + /*fall through */ case X25_FAC_THROUGHPUT: facilities->throughput = p[1]; *vc_fac_mask |= X25_MASK_THROUGHPUT; diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c index 7ac50098a375..3c12cae32001 100644 --- a/net/x25/x25_in.c +++ b/net/x25/x25_in.c @@ -345,6 +345,7 @@ static int x25_state4_machine(struct sock *sk, struct sk_buff *skb, int frametyp case X25_RESET_REQUEST: x25_write_internal(sk, X25_RESET_CONFIRMATION); + /* fall through */ case X25_RESET_CONFIRMATION: { x25_stop_timer(sk); x25->condition = 0x00; diff --git a/net/x25/x25_timer.c b/net/x25/x25_timer.c index 5c5db1a36399..1dfba3c23459 100644 --- a/net/x25/x25_timer.c +++ b/net/x25/x25_timer.c @@ -26,18 +26,17 @@ #include <net/tcp_states.h> #include <net/x25.h> -static void x25_heartbeat_expiry(unsigned long); -static void x25_timer_expiry(unsigned long); +static void x25_heartbeat_expiry(struct timer_list *t); +static void x25_timer_expiry(struct timer_list *t); void x25_init_timers(struct sock *sk) { struct x25_sock *x25 = x25_sk(sk); - setup_timer(&x25->timer, x25_timer_expiry, (unsigned long)sk); + timer_setup(&x25->timer, x25_timer_expiry, 0); /* initialized by sock_init_data */ - sk->sk_timer.data = (unsigned long)sk; - sk->sk_timer.function = &x25_heartbeat_expiry; + sk->sk_timer.function = (TIMER_FUNC_TYPE)x25_heartbeat_expiry; } void x25_start_heartbeat(struct sock *sk) @@ -93,9 +92,9 @@ unsigned long x25_display_timer(struct sock *sk) return x25->timer.expires - jiffies; } -static void x25_heartbeat_expiry(unsigned long param) +static void x25_heartbeat_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; + struct sock *sk = from_timer(sk, t, sk_timer); bh_lock_sock(sk); if (sock_owned_by_user(sk)) /* can currently only occur in state 3 */ @@ -160,9 +159,10 @@ static inline void x25_do_timer_expiry(struct sock * sk) } } -static void x25_timer_expiry(unsigned long param) +static void x25_timer_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; + struct x25_sock *x25 = from_timer(x25, t, timer); + struct sock *sk = &x25->sk; bh_lock_sock(sk); if (sock_owned_by_user(sk)) { /* can currently only occur in state 3 */ diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 6eb228a70131..9542975eb2f9 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -57,7 +57,7 @@ static __read_mostly seqcount_t xfrm_policy_hash_generation; static void xfrm_init_pmtu(struct dst_entry *dst); static int stale_bundle(struct dst_entry *dst); static int xfrm_bundle_ok(struct xfrm_dst *xdst); -static void xfrm_policy_queue_process(unsigned long arg); +static void xfrm_policy_queue_process(struct timer_list *t); static void __xfrm_policy_link(struct xfrm_policy *pol, int dir); static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, @@ -179,9 +179,9 @@ static inline unsigned long make_jiffies(long secs) return secs*HZ; } -static void xfrm_policy_timer(unsigned long data) +static void xfrm_policy_timer(struct timer_list *t) { - struct xfrm_policy *xp = (struct xfrm_policy *)data; + struct xfrm_policy *xp = from_timer(xp, t, timer); unsigned long now = get_seconds(); long next = LONG_MAX; int warn = 0; @@ -267,10 +267,9 @@ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp) rwlock_init(&policy->lock); refcount_set(&policy->refcnt, 1); skb_queue_head_init(&policy->polq.hold_queue); - setup_timer(&policy->timer, xfrm_policy_timer, - (unsigned long)policy); - setup_timer(&policy->polq.hold_timer, xfrm_policy_queue_process, - (unsigned long)policy); + timer_setup(&policy->timer, xfrm_policy_timer, 0); + timer_setup(&policy->polq.hold_timer, + xfrm_policy_queue_process, 0); } return policy; } @@ -1306,6 +1305,7 @@ static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir) newp->xfrm_nr = old->xfrm_nr; newp->index = old->index; newp->type = old->type; + newp->family = old->family; memcpy(newp->xfrm_vec, old->xfrm_vec, newp->xfrm_nr*sizeof(struct xfrm_tmpl)); spin_lock_bh(&net->xfrm.xfrm_policy_lock); @@ -1361,29 +1361,36 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, struct net *net = xp_net(policy); int nx; int i, error; + xfrm_address_t *daddr = xfrm_flowi_daddr(fl, family); + xfrm_address_t *saddr = xfrm_flowi_saddr(fl, family); xfrm_address_t tmp; for (nx = 0, i = 0; i < policy->xfrm_nr; i++) { struct xfrm_state *x; - xfrm_address_t *local; - xfrm_address_t *remote; + xfrm_address_t *remote = daddr; + xfrm_address_t *local = saddr; struct xfrm_tmpl *tmpl = &policy->xfrm_vec[i]; - remote = &tmpl->id.daddr; - local = &tmpl->saddr; - if (xfrm_addr_any(local, tmpl->encap_family)) { - error = xfrm_get_saddr(net, fl->flowi_oif, - &tmp, remote, - tmpl->encap_family, 0); - if (error) - goto fail; - local = &tmp; + if (tmpl->mode == XFRM_MODE_TUNNEL || + tmpl->mode == XFRM_MODE_BEET) { + remote = &tmpl->id.daddr; + local = &tmpl->saddr; + if (xfrm_addr_any(local, tmpl->encap_family)) { + error = xfrm_get_saddr(net, fl->flowi_oif, + &tmp, remote, + tmpl->encap_family, 0); + if (error) + goto fail; + local = &tmp; + } } x = xfrm_state_find(remote, local, fl, tmpl, policy, &error, family); if (x && x->km.state == XFRM_STATE_VALID) { xfrm[nx++] = x; + daddr = remote; + saddr = local; continue; } if (x) { @@ -1851,12 +1858,12 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, return xdst; } -static void xfrm_policy_queue_process(unsigned long arg) +static void xfrm_policy_queue_process(struct timer_list *t) { struct sk_buff *skb; struct sock *sk; struct dst_entry *dst; - struct xfrm_policy *pol = (struct xfrm_policy *)arg; + struct xfrm_policy *pol = from_timer(pol, t, polq.hold_timer); struct net *net = xp_net(pol); struct xfrm_policy_queue *pq = &pol->polq; struct flowi fl; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index e44a0fed48dd..983b0233767b 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -42,7 +42,7 @@ static int verify_one_alg(struct nlattr **attrs, enum xfrm_attr_type_t type) return 0; algp = nla_data(rt); - if (nla_len(rt) < xfrm_alg_len(algp)) + if (nla_len(rt) < (int)xfrm_alg_len(algp)) return -EINVAL; switch (type) { @@ -68,7 +68,7 @@ static int verify_auth_trunc(struct nlattr **attrs) return 0; algp = nla_data(rt); - if (nla_len(rt) < xfrm_alg_auth_len(algp)) + if (nla_len(rt) < (int)xfrm_alg_auth_len(algp)) return -EINVAL; algp->alg_name[sizeof(algp->alg_name) - 1] = '\0'; @@ -84,7 +84,7 @@ static int verify_aead(struct nlattr **attrs) return 0; algp = nla_data(rt); - if (nla_len(rt) < aead_len(algp)) + if (nla_len(rt) < (int)aead_len(algp)) return -EINVAL; algp->alg_name[sizeof(algp->alg_name) - 1] = '\0'; @@ -130,7 +130,7 @@ static inline int verify_replay(struct xfrm_usersa_info *p, if (rs->bmp_len > XFRMA_REPLAY_ESN_MAX / sizeof(rs->bmp[0]) / 8) return -EINVAL; - if (nla_len(rt) < xfrm_replay_state_esn_len(rs) && + if (nla_len(rt) < (int)xfrm_replay_state_esn_len(rs) && nla_len(rt) != sizeof(*rs)) return -EINVAL; } @@ -404,7 +404,7 @@ static inline int xfrm_replay_verify_len(struct xfrm_replay_state_esn *replay_es struct nlattr *rp) { struct xfrm_replay_state_esn *up; - int ulen; + unsigned int ulen; if (!replay_esn || !rp) return 0; @@ -414,7 +414,7 @@ static inline int xfrm_replay_verify_len(struct xfrm_replay_state_esn *replay_es /* Check the overall length and the internal bitmap length to avoid * potential overflow. */ - if (nla_len(rp) < ulen || + if (nla_len(rp) < (int)ulen || xfrm_replay_state_esn_len(replay_esn) != ulen || replay_esn->bmp_len != up->bmp_len) return -EINVAL; @@ -430,14 +430,14 @@ static int xfrm_alloc_replay_state_esn(struct xfrm_replay_state_esn **replay_esn struct nlattr *rta) { struct xfrm_replay_state_esn *p, *pp, *up; - int klen, ulen; + unsigned int klen, ulen; if (!rta) return 0; up = nla_data(rta); klen = xfrm_replay_state_esn_len(up); - ulen = nla_len(rta) >= klen ? klen : sizeof(*up); + ulen = nla_len(rta) >= (int)klen ? klen : sizeof(*up); p = kzalloc(klen, GFP_KERNEL); if (!p) @@ -458,9 +458,9 @@ static int xfrm_alloc_replay_state_esn(struct xfrm_replay_state_esn **replay_esn return 0; } -static inline int xfrm_user_sec_ctx_size(struct xfrm_sec_ctx *xfrm_ctx) +static inline unsigned int xfrm_user_sec_ctx_size(struct xfrm_sec_ctx *xfrm_ctx) { - int len = 0; + unsigned int len = 0; if (xfrm_ctx) { len += sizeof(struct xfrm_user_sec_ctx); @@ -1032,7 +1032,7 @@ static inline int xfrm_nlmsg_multicast(struct net *net, struct sk_buff *skb, return -1; } -static inline size_t xfrm_spdinfo_msgsize(void) +static inline unsigned int xfrm_spdinfo_msgsize(void) { return NLMSG_ALIGN(4) + nla_total_size(sizeof(struct xfrmu_spdinfo)) @@ -1147,18 +1147,19 @@ static int xfrm_get_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh, u32 *flags = nlmsg_data(nlh); u32 sportid = NETLINK_CB(skb).portid; u32 seq = nlh->nlmsg_seq; + int err; r_skb = nlmsg_new(xfrm_spdinfo_msgsize(), GFP_ATOMIC); if (r_skb == NULL) return -ENOMEM; - if (build_spdinfo(r_skb, net, sportid, seq, *flags) < 0) - BUG(); + err = build_spdinfo(r_skb, net, sportid, seq, *flags); + BUG_ON(err < 0); return nlmsg_unicast(net->xfrm.nlsk, r_skb, sportid); } -static inline size_t xfrm_sadinfo_msgsize(void) +static inline unsigned int xfrm_sadinfo_msgsize(void) { return NLMSG_ALIGN(4) + nla_total_size(sizeof(struct xfrmu_sadhinfo)) @@ -1205,13 +1206,14 @@ static int xfrm_get_sadinfo(struct sk_buff *skb, struct nlmsghdr *nlh, u32 *flags = nlmsg_data(nlh); u32 sportid = NETLINK_CB(skb).portid; u32 seq = nlh->nlmsg_seq; + int err; r_skb = nlmsg_new(xfrm_sadinfo_msgsize(), GFP_ATOMIC); if (r_skb == NULL) return -ENOMEM; - if (build_sadinfo(r_skb, net, sportid, seq, *flags) < 0) - BUG(); + err = build_sadinfo(r_skb, net, sportid, seq, *flags); + BUG_ON(err < 0); return nlmsg_unicast(net->xfrm.nlsk, r_skb, sportid); } @@ -1634,7 +1636,7 @@ static inline int copy_to_user_sec_ctx(struct xfrm_policy *xp, struct sk_buff *s return copy_sec_ctx(xp->security, skb); return 0; } -static inline size_t userpolicy_type_attrsize(void) +static inline unsigned int userpolicy_type_attrsize(void) { #ifdef CONFIG_XFRM_SUB_POLICY return nla_total_size(sizeof(struct xfrm_userpolicy_type)); @@ -1853,9 +1855,9 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh, return 0; } -static inline size_t xfrm_aevent_msgsize(struct xfrm_state *x) +static inline unsigned int xfrm_aevent_msgsize(struct xfrm_state *x) { - size_t replay_size = x->replay_esn ? + unsigned int replay_size = x->replay_esn ? xfrm_replay_state_esn_len(x->replay_esn) : sizeof(struct xfrm_replay_state); @@ -1960,8 +1962,9 @@ static int xfrm_get_ae(struct sk_buff *skb, struct nlmsghdr *nlh, c.seq = nlh->nlmsg_seq; c.portid = nlh->nlmsg_pid; - if (build_aevent(r_skb, x, &c) < 0) - BUG(); + err = build_aevent(r_skb, x, &c); + BUG_ON(err < 0); + err = nlmsg_unicast(net->xfrm.nlsk, r_skb, NETLINK_CB(skb).portid); spin_unlock_bh(&x->lock); xfrm_state_put(x); @@ -2324,8 +2327,8 @@ static int copy_to_user_kmaddress(const struct xfrm_kmaddress *k, struct sk_buff return nla_put(skb, XFRMA_KMADDRESS, sizeof(uk), &uk); } -static inline size_t xfrm_migrate_msgsize(int num_migrate, int with_kma, - int with_encp) +static inline unsigned int xfrm_migrate_msgsize(int num_migrate, int with_kma, + int with_encp) { return NLMSG_ALIGN(sizeof(struct xfrm_userpolicy_id)) + (with_kma ? nla_total_size(sizeof(struct xfrm_kmaddress)) : 0) @@ -2388,6 +2391,7 @@ static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, { struct net *net = &init_net; struct sk_buff *skb; + int err; skb = nlmsg_new(xfrm_migrate_msgsize(num_migrate, !!k, !!encap), GFP_ATOMIC); @@ -2395,8 +2399,8 @@ static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, return -ENOMEM; /* build migrate */ - if (build_migrate(skb, m, num_migrate, k, sel, encap, dir, type) < 0) - BUG(); + err = build_migrate(skb, m, num_migrate, k, sel, encap, dir, type); + BUG_ON(err < 0); return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MIGRATE); } @@ -2572,7 +2576,7 @@ static void xfrm_netlink_rcv(struct sk_buff *skb) mutex_unlock(&net->xfrm.xfrm_cfg_mutex); } -static inline size_t xfrm_expire_msgsize(void) +static inline unsigned int xfrm_expire_msgsize(void) { return NLMSG_ALIGN(sizeof(struct xfrm_user_expire)) + nla_total_size(sizeof(struct xfrm_mark)); @@ -2623,13 +2627,14 @@ static int xfrm_aevent_state_notify(struct xfrm_state *x, const struct km_event { struct net *net = xs_net(x); struct sk_buff *skb; + int err; skb = nlmsg_new(xfrm_aevent_msgsize(x), GFP_ATOMIC); if (skb == NULL) return -ENOMEM; - if (build_aevent(skb, x, c) < 0) - BUG(); + err = build_aevent(skb, x, c); + BUG_ON(err < 0); return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_AEVENTS); } @@ -2660,9 +2665,9 @@ static int xfrm_notify_sa_flush(const struct km_event *c) return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_SA); } -static inline size_t xfrm_sa_len(struct xfrm_state *x) +static inline unsigned int xfrm_sa_len(struct xfrm_state *x) { - size_t l = 0; + unsigned int l = 0; if (x->aead) l += nla_total_size(aead_len(x->aead)); if (x->aalg) { @@ -2707,8 +2712,9 @@ static int xfrm_notify_sa(struct xfrm_state *x, const struct km_event *c) struct xfrm_usersa_id *id; struct nlmsghdr *nlh; struct sk_buff *skb; - int len = xfrm_sa_len(x); - int headlen, err; + unsigned int len = xfrm_sa_len(x); + unsigned int headlen; + int err; headlen = sizeof(*p); if (c->event == XFRM_MSG_DELSA) { @@ -2782,8 +2788,8 @@ static int xfrm_send_state_notify(struct xfrm_state *x, const struct km_event *c } -static inline size_t xfrm_acquire_msgsize(struct xfrm_state *x, - struct xfrm_policy *xp) +static inline unsigned int xfrm_acquire_msgsize(struct xfrm_state *x, + struct xfrm_policy *xp) { return NLMSG_ALIGN(sizeof(struct xfrm_user_acquire)) + nla_total_size(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr) @@ -2835,13 +2841,14 @@ static int xfrm_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *xt, { struct net *net = xs_net(x); struct sk_buff *skb; + int err; skb = nlmsg_new(xfrm_acquire_msgsize(x, xp), GFP_ATOMIC); if (skb == NULL) return -ENOMEM; - if (build_acquire(skb, x, xt, xp) < 0) - BUG(); + err = build_acquire(skb, x, xt, xp); + BUG_ON(err < 0); return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_ACQUIRE); } @@ -2906,7 +2913,7 @@ static struct xfrm_policy *xfrm_compile_policy(struct sock *sk, int opt, return xp; } -static inline size_t xfrm_polexpire_msgsize(struct xfrm_policy *xp) +static inline unsigned int xfrm_polexpire_msgsize(struct xfrm_policy *xp) { return NLMSG_ALIGN(sizeof(struct xfrm_user_polexpire)) + nla_total_size(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr) @@ -2950,26 +2957,28 @@ static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, const struct { struct net *net = xp_net(xp); struct sk_buff *skb; + int err; skb = nlmsg_new(xfrm_polexpire_msgsize(xp), GFP_ATOMIC); if (skb == NULL) return -ENOMEM; - if (build_polexpire(skb, xp, dir, c) < 0) - BUG(); + err = build_polexpire(skb, xp, dir, c); + BUG_ON(err < 0); return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_EXPIRE); } static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_event *c) { - int len = nla_total_size(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr); + unsigned int len = nla_total_size(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr); struct net *net = xp_net(xp); struct xfrm_userpolicy_info *p; struct xfrm_userpolicy_id *id; struct nlmsghdr *nlh; struct sk_buff *skb; - int headlen, err; + unsigned int headlen; + int err; headlen = sizeof(*p); if (c->event == XFRM_MSG_DELPOLICY) { @@ -3076,7 +3085,7 @@ static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, const struct } -static inline size_t xfrm_report_msgsize(void) +static inline unsigned int xfrm_report_msgsize(void) { return NLMSG_ALIGN(sizeof(struct xfrm_user_report)); } @@ -3110,18 +3119,19 @@ static int xfrm_send_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr) { struct sk_buff *skb; + int err; skb = nlmsg_new(xfrm_report_msgsize(), GFP_ATOMIC); if (skb == NULL) return -ENOMEM; - if (build_report(skb, proto, sel, addr) < 0) - BUG(); + err = build_report(skb, proto, sel, addr); + BUG_ON(err < 0); return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_REPORT); } -static inline size_t xfrm_mapping_msgsize(void) +static inline unsigned int xfrm_mapping_msgsize(void) { return NLMSG_ALIGN(sizeof(struct xfrm_user_mapping)); } @@ -3157,6 +3167,7 @@ static int xfrm_send_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, { struct net *net = xs_net(x); struct sk_buff *skb; + int err; if (x->id.proto != IPPROTO_ESP) return -EINVAL; @@ -3168,8 +3179,8 @@ static int xfrm_send_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, if (skb == NULL) return -ENOMEM; - if (build_mapping(skb, x, ipaddr, sport) < 0) - BUG(); + err = build_mapping(skb, x, ipaddr, sport); + BUG_ON(err < 0); return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MAPPING); } |