diff options
Diffstat (limited to 'net')
425 files changed, 17316 insertions, 6600 deletions
diff --git a/net/6lowpan/debugfs.c b/net/6lowpan/debugfs.c index 1c140af06d52..600b9563bfc5 100644 --- a/net/6lowpan/debugfs.c +++ b/net/6lowpan/debugfs.c @@ -170,7 +170,8 @@ static void lowpan_dev_debugfs_ctx_init(struct net_device *dev, struct dentry *root; char buf[32]; - WARN_ON_ONCE(id > LOWPAN_IPHC_CTX_TABLE_SIZE); + if (WARN_ON_ONCE(id >= LOWPAN_IPHC_CTX_TABLE_SIZE)) + return; sprintf(buf, "%d", id); diff --git a/net/802/Makefile b/net/802/Makefile index 19406a87bdaa..bfed80221b8b 100644 --- a/net/802/Makefile +++ b/net/802/Makefile @@ -8,7 +8,6 @@ obj-$(CONFIG_LLC) += p8022.o psnap.o obj-$(CONFIG_NET_FC) += fc.o obj-$(CONFIG_FDDI) += fddi.o obj-$(CONFIG_HIPPI) += hippi.o -obj-$(CONFIG_IPX) += p8022.o psnap.o p8023.o obj-$(CONFIG_ATALK) += p8022.o psnap.o obj-$(CONFIG_STP) += stp.o obj-$(CONFIG_GARP) += garp.o diff --git a/net/802/p8023.c b/net/802/p8023.c deleted file mode 100644 index 19cd56990db2..000000000000 --- a/net/802/p8023.c +++ /dev/null @@ -1,60 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * NET3: 802.3 data link hooks used for IPX 802.3 - * - * 802.3 isn't really a protocol data link layer. Some old IPX stuff - * uses it however. Note that there is only one 802.3 protocol layer - * in the system. We don't currently support different protocols - * running raw 802.3 on different devices. Thankfully nobody else - * has done anything like the old IPX. - */ - -#include <linux/in.h> -#include <linux/mm.h> -#include <linux/module.h> -#include <linux/netdevice.h> -#include <linux/skbuff.h> -#include <linux/slab.h> - -#include <net/datalink.h> -#include <net/p8022.h> - -/* - * Place an 802.3 header on a packet. The driver will do the mac - * addresses, we just need to give it the buffer length. - */ -static int p8023_request(struct datalink_proto *dl, - struct sk_buff *skb, unsigned char *dest_node) -{ - struct net_device *dev = skb->dev; - - dev_hard_header(skb, dev, ETH_P_802_3, dest_node, NULL, skb->len); - return dev_queue_xmit(skb); -} - -/* - * Create an 802.3 client. Note there can be only one 802.3 client - */ -struct datalink_proto *make_8023_client(void) -{ - struct datalink_proto *proto = kmalloc(sizeof(*proto), GFP_ATOMIC); - - if (proto) { - proto->header_length = 0; - proto->request = p8023_request; - } - return proto; -} - -/* - * Destroy the 802.3 client. - */ -void destroy_8023_client(struct datalink_proto *dl) -{ - kfree(dl); -} - -EXPORT_SYMBOL(destroy_8023_client); -EXPORT_SYMBOL(make_8023_client); - -MODULE_LICENSE("GPL"); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 4cdf8416869d..55275ef9a31a 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -67,7 +67,7 @@ static int vlan_group_prealloc_vid(struct vlan_group *vg, return 0; size = sizeof(struct net_device *) * VLAN_GROUP_ARRAY_PART_LEN; - array = kzalloc(size, GFP_KERNEL); + array = kzalloc(size, GFP_KERNEL_ACCOUNT); if (array == NULL) return -ENOBUFS; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index a0367b37512d..0c21d1fec852 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -372,8 +372,8 @@ static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCGMIIREG: case SIOCSMIIREG: case SIOCGHWTSTAMP: - if (netif_device_present(real_dev) && ops->ndo_do_ioctl) - err = ops->ndo_do_ioctl(real_dev, &ifrr, cmd); + if (netif_device_present(real_dev) && ops->ndo_eth_ioctl) + err = ops->ndo_eth_ioctl(real_dev, &ifrr, cmd); break; } @@ -814,7 +814,7 @@ static const struct net_device_ops vlan_netdev_ops = { .ndo_set_mac_address = vlan_dev_set_mac_address, .ndo_set_rx_mode = vlan_dev_set_rx_mode, .ndo_change_rx_flags = vlan_dev_change_rx_flags, - .ndo_do_ioctl = vlan_dev_ioctl, + .ndo_eth_ioctl = vlan_dev_ioctl, .ndo_neigh_setup = vlan_dev_neigh_setup, .ndo_get_stats64 = vlan_dev_get_stats64, #if IS_ENABLED(CONFIG_FCOE) diff --git a/net/Kconfig b/net/Kconfig index c7392c449b25..fb13460c6dab 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -363,6 +363,7 @@ source "net/bluetooth/Kconfig" source "net/rxrpc/Kconfig" source "net/kcm/Kconfig" source "net/strparser/Kconfig" +source "net/mctp/Kconfig" config FIB_RULES bool diff --git a/net/Makefile b/net/Makefile index 9ca9572188fe..fbfeb8a0bb37 100644 --- a/net/Makefile +++ b/net/Makefile @@ -78,3 +78,4 @@ obj-$(CONFIG_QRTR) += qrtr/ obj-$(CONFIG_NET_NCSI) += ncsi/ obj-$(CONFIG_XDP_SOCKETS) += xdp/ obj-$(CONFIG_MPTCP) += mptcp/ +obj-$(CONFIG_MCTP) += mctp/ diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 8ade5a4ceaf5..bf5736c1d458 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -666,7 +666,7 @@ static int atif_ioctl(int cmd, void __user *arg) struct rtentry rtdef; int add_route; - if (copy_from_user(&atreq, arg, sizeof(atreq))) + if (get_user_ifreq(&atreq, NULL, arg)) return -EFAULT; dev = __dev_get_by_name(&init_net, atreq.ifr_name); @@ -865,7 +865,7 @@ static int atif_ioctl(int cmd, void __user *arg) return 0; } - return copy_to_user(arg, &atreq, sizeof(atreq)) ? -EFAULT : 0; + return put_user_ifreq(&atreq, arg); } static int atrtr_ioctl_addrt(struct rtentry *rt) diff --git a/net/ax25/ax25_ip.c b/net/ax25/ax25_ip.c index e4f63dd43cb5..36249776c021 100644 --- a/net/ax25/ax25_ip.c +++ b/net/ax25/ax25_ip.c @@ -193,10 +193,8 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff *skb) skb_pull(skb, AX25_KISS_HEADER_LEN); if (digipeat != NULL) { - if ((ourskb = ax25_rt_build_path(skb, src, dst, route->digipeat)) == NULL) { - kfree_skb(skb); + if ((ourskb = ax25_rt_build_path(skb, src, dst, route->digipeat)) == NULL) goto put; - } skb = ourskb; } diff --git a/net/ax25/ax25_out.c b/net/ax25/ax25_out.c index f53751ba81b3..22f2f66c6e0a 100644 --- a/net/ax25/ax25_out.c +++ b/net/ax25/ax25_out.c @@ -325,7 +325,6 @@ void ax25_kick(ax25_cb *ax25) void ax25_transmit_buffer(ax25_cb *ax25, struct sk_buff *skb, int type) { - struct sk_buff *skbn; unsigned char *ptr; int headroom; @@ -336,18 +335,12 @@ void ax25_transmit_buffer(ax25_cb *ax25, struct sk_buff *skb, int type) headroom = ax25_addr_size(ax25->digipeat); - if (skb_headroom(skb) < headroom) { - if ((skbn = skb_realloc_headroom(skb, headroom)) == NULL) { + if (unlikely(skb_headroom(skb) < headroom)) { + skb = skb_expand_head(skb, headroom); + if (!skb) { printk(KERN_CRIT "AX.25: ax25_transmit_buffer - out of memory\n"); - kfree_skb(skb); return; } - - if (skb->sk != NULL) - skb_set_owner_w(skbn, skb->sk); - - consume_skb(skb); - skb = skbn; } ptr = skb_push(skb, headroom); diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c index b40e0bce67ea..d0b2e094bd55 100644 --- a/net/ax25/ax25_route.c +++ b/net/ax25/ax25_route.c @@ -441,24 +441,17 @@ put: struct sk_buff *ax25_rt_build_path(struct sk_buff *skb, ax25_address *src, ax25_address *dest, ax25_digi *digi) { - struct sk_buff *skbn; unsigned char *bp; int len; len = digi->ndigi * AX25_ADDR_LEN; - if (skb_headroom(skb) < len) { - if ((skbn = skb_realloc_headroom(skb, len)) == NULL) { + if (unlikely(skb_headroom(skb) < len)) { + skb = skb_expand_head(skb, len); + if (!skb) { printk(KERN_CRIT "AX.25: ax25_dg_build_path - out of memory\n"); return NULL; } - - if (skb->sk != NULL) - skb_set_owner_w(skbn, skb->sk); - - consume_skb(skb); - - skb = skbn; } bp = skb_push(skb, len); diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 12022378f892..f94f538fa382 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -519,8 +519,7 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet, } out: - if (primary_if) - batadv_hardif_put(primary_if); + batadv_hardif_put(primary_if); return res; } @@ -857,8 +856,7 @@ static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface) rcu_read_unlock(); out: - if (primary_if) - batadv_hardif_put(primary_if); + batadv_hardif_put(primary_if); } static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) @@ -1046,14 +1044,10 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, unlock: rcu_read_unlock(); out: - if (neigh_node) - batadv_neigh_node_put(neigh_node); - if (router) - batadv_neigh_node_put(router); - if (neigh_ifinfo) - batadv_neigh_ifinfo_put(neigh_ifinfo); - if (router_ifinfo) - batadv_neigh_ifinfo_put(router_ifinfo); + batadv_neigh_node_put(neigh_node); + batadv_neigh_node_put(router); + batadv_neigh_ifinfo_put(neigh_ifinfo); + batadv_neigh_ifinfo_put(router_ifinfo); } /** @@ -1194,8 +1188,7 @@ static bool batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, ret = true; out: - if (neigh_node) - batadv_neigh_node_put(neigh_node); + batadv_neigh_node_put(neigh_node); return ret; } @@ -1496,16 +1489,11 @@ out_neigh: if (orig_neigh_node && !is_single_hop_neigh) batadv_orig_node_put(orig_neigh_node); out: - if (router_ifinfo) - batadv_neigh_ifinfo_put(router_ifinfo); - if (router) - batadv_neigh_node_put(router); - if (router_router) - batadv_neigh_node_put(router_router); - if (orig_neigh_router) - batadv_neigh_node_put(orig_neigh_router); - if (hardif_neigh) - batadv_hardif_neigh_put(hardif_neigh); + batadv_neigh_ifinfo_put(router_ifinfo); + batadv_neigh_node_put(router); + batadv_neigh_node_put(router_router); + batadv_neigh_node_put(orig_neigh_router); + batadv_hardif_neigh_put(hardif_neigh); consume_skb(skb_priv); } @@ -1926,8 +1914,7 @@ batadv_iv_ogm_orig_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, } out: - if (neigh_node_best) - batadv_neigh_node_put(neigh_node_best); + batadv_neigh_node_put(neigh_node_best); *sub_s = 0; return 0; @@ -2049,10 +2036,8 @@ static bool batadv_iv_ogm_neigh_diff(struct batadv_neigh_node *neigh1, *diff = (int)tq1 - (int)tq2; out: - if (neigh1_ifinfo) - batadv_neigh_ifinfo_put(neigh1_ifinfo); - if (neigh2_ifinfo) - batadv_neigh_ifinfo_put(neigh2_ifinfo); + batadv_neigh_ifinfo_put(neigh1_ifinfo); + batadv_neigh_ifinfo_put(neigh2_ifinfo); return ret; } @@ -2299,8 +2284,7 @@ batadv_iv_gw_get_best_gw_node(struct batadv_priv *bat_priv) 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); + batadv_gw_node_put(curr_gw); curr_gw = gw_node; kref_get(&curr_gw->refcount); } @@ -2314,8 +2298,7 @@ batadv_iv_gw_get_best_gw_node(struct batadv_priv *bat_priv) * $routing_class more tq points) */ if (tq_avg > max_tq) { - if (curr_gw) - batadv_gw_node_put(curr_gw); + batadv_gw_node_put(curr_gw); curr_gw = gw_node; kref_get(&curr_gw->refcount); } @@ -2332,8 +2315,7 @@ batadv_iv_gw_get_best_gw_node(struct batadv_priv *bat_priv) next: batadv_neigh_node_put(router); - if (router_ifinfo) - batadv_neigh_ifinfo_put(router_ifinfo); + batadv_neigh_ifinfo_put(router_ifinfo); } rcu_read_unlock(); @@ -2397,14 +2379,10 @@ static bool batadv_iv_gw_is_eligible(struct batadv_priv *bat_priv, ret = true; out: - if (router_gw_ifinfo) - batadv_neigh_ifinfo_put(router_gw_ifinfo); - if (router_orig_ifinfo) - batadv_neigh_ifinfo_put(router_orig_ifinfo); - if (router_gw) - batadv_neigh_node_put(router_gw); - if (router_orig) - batadv_neigh_node_put(router_orig); + batadv_neigh_ifinfo_put(router_gw_ifinfo); + batadv_neigh_ifinfo_put(router_orig_ifinfo); + batadv_neigh_node_put(router_gw); + batadv_neigh_node_put(router_orig); return ret; } @@ -2479,12 +2457,9 @@ static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid, ret = 0; out: - if (curr_gw) - batadv_gw_node_put(curr_gw); - if (router_ifinfo) - batadv_neigh_ifinfo_put(router_ifinfo); - if (router) - batadv_neigh_node_put(router); + batadv_gw_node_put(curr_gw); + batadv_neigh_ifinfo_put(router_ifinfo); + batadv_neigh_node_put(router); return ret; } diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index b98aea958e3d..54e41fc709c3 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -106,8 +106,7 @@ static void batadv_v_iface_update_mac(struct batadv_hard_iface *hard_iface) batadv_v_primary_iface_set(hard_iface); out: - if (primary_if) - batadv_hardif_put(primary_if); + batadv_hardif_put(primary_if); } static void @@ -366,8 +365,7 @@ batadv_v_orig_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, } out: - if (neigh_node_best) - batadv_neigh_node_put(neigh_node_best); + batadv_neigh_node_put(neigh_node_best); *sub_s = 0; return 0; @@ -568,10 +566,8 @@ static int batadv_v_gw_throughput_get(struct batadv_gw_node *gw_node, u32 *bw) ret = 0; out: - if (router) - batadv_neigh_node_put(router); - if (router_ifinfo) - batadv_neigh_ifinfo_put(router_ifinfo); + batadv_neigh_node_put(router); + batadv_neigh_ifinfo_put(router_ifinfo); return ret; } @@ -599,8 +595,7 @@ batadv_v_gw_get_best_gw_node(struct batadv_priv *bat_priv) if (curr_gw && bw <= max_bw) goto next; - if (curr_gw) - batadv_gw_node_put(curr_gw); + batadv_gw_node_put(curr_gw); curr_gw = gw_node; kref_get(&curr_gw->refcount); @@ -662,10 +657,8 @@ static bool batadv_v_gw_is_eligible(struct batadv_priv *bat_priv, ret = true; out: - if (curr_gw) - batadv_gw_node_put(curr_gw); - if (orig_gw) - batadv_gw_node_put(orig_gw); + batadv_gw_node_put(curr_gw); + batadv_gw_node_put(orig_gw); return ret; } @@ -764,12 +757,9 @@ static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid, ret = 0; out: - if (curr_gw) - batadv_gw_node_put(curr_gw); - if (router_ifinfo) - batadv_neigh_ifinfo_put(router_ifinfo); - if (router) - batadv_neigh_node_put(router); + batadv_gw_node_put(curr_gw); + batadv_neigh_ifinfo_put(router_ifinfo); + batadv_neigh_node_put(router); return ret; } diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index 423c2d171703..71999e13f729 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -486,14 +486,11 @@ static void batadv_v_elp_neigh_update(struct batadv_priv *bat_priv, hardif_neigh->bat_v.elp_interval = ntohl(elp_packet->elp_interval); hardif_free: - if (hardif_neigh) - batadv_hardif_neigh_put(hardif_neigh); + batadv_hardif_neigh_put(hardif_neigh); neigh_free: - if (neigh) - batadv_neigh_node_put(neigh); + batadv_neigh_node_put(neigh); orig_free: - if (orig_neigh) - batadv_orig_node_put(orig_neigh); + batadv_orig_node_put(orig_neigh); } /** diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index a0a9636d1740..1d750f3cb2e4 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -584,12 +584,9 @@ static void batadv_v_ogm_forward(struct batadv_priv *bat_priv, batadv_v_ogm_queue_on_if(skb, if_outgoing); out: - if (orig_ifinfo) - batadv_orig_ifinfo_put(orig_ifinfo); - if (router) - batadv_neigh_node_put(router); - if (neigh_ifinfo) - batadv_neigh_ifinfo_put(neigh_ifinfo); + batadv_orig_ifinfo_put(orig_ifinfo); + batadv_neigh_node_put(router); + batadv_neigh_ifinfo_put(neigh_ifinfo); } /** @@ -669,10 +666,8 @@ static int batadv_v_ogm_metric_update(struct batadv_priv *bat_priv, else ret = 0; out: - if (orig_ifinfo) - batadv_orig_ifinfo_put(orig_ifinfo); - if (neigh_ifinfo) - batadv_neigh_ifinfo_put(neigh_ifinfo); + batadv_orig_ifinfo_put(orig_ifinfo); + batadv_neigh_ifinfo_put(neigh_ifinfo); return ret; } @@ -763,16 +758,11 @@ static bool batadv_v_ogm_route_update(struct batadv_priv *bat_priv, batadv_update_route(bat_priv, orig_node, if_outgoing, neigh_node); out: - if (router) - batadv_neigh_node_put(router); - if (orig_neigh_router) - batadv_neigh_node_put(orig_neigh_router); - if (orig_neigh_node) - batadv_orig_node_put(orig_neigh_node); - if (router_ifinfo) - batadv_neigh_ifinfo_put(router_ifinfo); - if (neigh_ifinfo) - batadv_neigh_ifinfo_put(neigh_ifinfo); + batadv_neigh_node_put(router); + batadv_neigh_node_put(orig_neigh_router); + batadv_orig_node_put(orig_neigh_node); + batadv_neigh_ifinfo_put(router_ifinfo); + batadv_neigh_ifinfo_put(neigh_ifinfo); return forward; } @@ -978,12 +968,9 @@ static void batadv_v_ogm_process(const struct sk_buff *skb, int ogm_offset, } rcu_read_unlock(); out: - if (orig_node) - batadv_orig_node_put(orig_node); - if (neigh_node) - batadv_neigh_node_put(neigh_node); - if (hardif_neigh) - batadv_hardif_neigh_put(hardif_neigh); + batadv_orig_node_put(orig_node); + batadv_neigh_node_put(neigh_node); + batadv_hardif_neigh_put(hardif_neigh); } /** diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 63d42dcc9324..1669744304c5 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -162,6 +162,9 @@ static void batadv_backbone_gw_release(struct kref *ref) */ static void batadv_backbone_gw_put(struct batadv_bla_backbone_gw *backbone_gw) { + if (!backbone_gw) + return; + kref_put(&backbone_gw->refcount, batadv_backbone_gw_release); } @@ -197,6 +200,9 @@ static void batadv_claim_release(struct kref *ref) */ static void batadv_claim_put(struct batadv_bla_claim *claim) { + if (!claim) + return; + kref_put(&claim->refcount, batadv_claim_release); } @@ -439,8 +445,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac, netif_rx_any_context(skb); out: - if (primary_if) - batadv_hardif_put(primary_if); + batadv_hardif_put(primary_if); } /** @@ -1498,8 +1503,7 @@ static void batadv_bla_periodic_work(struct work_struct *work) rcu_read_unlock(); } out: - if (primary_if) - batadv_hardif_put(primary_if); + batadv_hardif_put(primary_if); queue_delayed_work(batadv_event_workqueue, &bat_priv->bla.work, msecs_to_jiffies(BATADV_BLA_PERIOD_LENGTH)); @@ -1808,8 +1812,7 @@ void batadv_bla_free(struct batadv_priv *bat_priv) batadv_hash_destroy(bat_priv->bla.backbone_hash); bat_priv->bla.backbone_hash = NULL; } - if (primary_if) - batadv_hardif_put(primary_if); + batadv_hardif_put(primary_if); } /** @@ -1996,10 +1999,8 @@ handled: ret = true; out: - if (primary_if) - batadv_hardif_put(primary_if); - if (claim) - batadv_claim_put(claim); + batadv_hardif_put(primary_if); + batadv_claim_put(claim); return ret; } @@ -2103,10 +2104,8 @@ allow: handled: ret = true; out: - if (primary_if) - batadv_hardif_put(primary_if); - if (claim) - batadv_claim_put(claim); + batadv_hardif_put(primary_if); + batadv_claim_put(claim); return ret; } @@ -2271,11 +2270,9 @@ int batadv_bla_claim_dump(struct sk_buff *msg, struct netlink_callback *cb) ret = msg->len; out: - if (primary_if) - batadv_hardif_put(primary_if); + batadv_hardif_put(primary_if); - if (soft_iface) - dev_put(soft_iface); + dev_put(soft_iface); return ret; } @@ -2443,11 +2440,9 @@ int batadv_bla_backbone_dump(struct sk_buff *msg, struct netlink_callback *cb) ret = msg->len; out: - if (primary_if) - batadv_hardif_put(primary_if); + batadv_hardif_put(primary_if); - if (soft_iface) - dev_put(soft_iface); + dev_put(soft_iface); return ret; } diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 8c95a11a830a..2f008e329007 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -127,6 +127,9 @@ static void batadv_dat_entry_release(struct kref *ref) */ static void batadv_dat_entry_put(struct batadv_dat_entry *dat_entry) { + if (!dat_entry) + return; + kref_put(&dat_entry->refcount, batadv_dat_entry_release); } @@ -405,8 +408,7 @@ static void batadv_dat_entry_add(struct batadv_priv *bat_priv, __be32 ip, &dat_entry->ip, dat_entry->mac_addr, batadv_print_vid(vid)); out: - if (dat_entry) - batadv_dat_entry_put(dat_entry); + batadv_dat_entry_put(dat_entry); } #ifdef CONFIG_BATMAN_ADV_DEBUG @@ -594,8 +596,7 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv, continue; max = tmp_max; - if (max_orig_node) - batadv_orig_node_put(max_orig_node); + batadv_orig_node_put(max_orig_node); max_orig_node = orig_node; } rcu_read_unlock(); @@ -981,11 +982,9 @@ int batadv_dat_cache_dump(struct sk_buff *msg, struct netlink_callback *cb) ret = msg->len; out: - if (primary_if) - batadv_hardif_put(primary_if); + batadv_hardif_put(primary_if); - if (soft_iface) - dev_put(soft_iface); + dev_put(soft_iface); return ret; } @@ -1218,8 +1217,7 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv, BATADV_P_DAT_DHT_GET); } out: - if (dat_entry) - batadv_dat_entry_put(dat_entry); + batadv_dat_entry_put(dat_entry); return ret; } @@ -1286,8 +1284,7 @@ bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv, ret = true; } out: - if (dat_entry) - batadv_dat_entry_put(dat_entry); + batadv_dat_entry_put(dat_entry); if (ret) kfree_skb(skb); return ret; @@ -1420,8 +1417,7 @@ bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv, out: if (dropped) kfree_skb(skb); - if (dat_entry) - batadv_dat_entry_put(dat_entry); + batadv_dat_entry_put(dat_entry); /* if dropped == false -> deliver to the interface */ return dropped; } @@ -1830,7 +1826,6 @@ bool batadv_dat_drop_broadcast_packet(struct batadv_priv *bat_priv, ret = true; out: - if (dat_entry) - batadv_dat_entry_put(dat_entry); + batadv_dat_entry_put(dat_entry); return ret; } diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index a5d9d800082b..0899a729a23f 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -381,10 +381,8 @@ bool batadv_frag_skb_fwd(struct sk_buff *skb, } out: - if (orig_node_dst) - batadv_orig_node_put(orig_node_dst); - if (neigh_node) - batadv_neigh_node_put(neigh_node); + batadv_orig_node_put(orig_node_dst); + batadv_neigh_node_put(neigh_node); return ret; } diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 007f2827935d..b7466136e292 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -59,7 +59,7 @@ * after rcu grace period * @ref: kref pointer of the gw_node */ -static void batadv_gw_node_release(struct kref *ref) +void batadv_gw_node_release(struct kref *ref) { struct batadv_gw_node *gw_node; @@ -70,16 +70,6 @@ static void batadv_gw_node_release(struct kref *ref) } /** - * batadv_gw_node_put() - decrement the gw_node refcounter and possibly release - * it - * @gw_node: gateway node to free - */ -void batadv_gw_node_put(struct batadv_gw_node *gw_node) -{ - kref_put(&gw_node->refcount, batadv_gw_node_release); -} - -/** * batadv_gw_get_selected_gw_node() - Get currently selected gateway * @bat_priv: the bat priv with all the soft interface information * @@ -130,8 +120,7 @@ batadv_gw_get_selected_orig(struct batadv_priv *bat_priv) unlock: rcu_read_unlock(); out: - if (gw_node) - batadv_gw_node_put(gw_node); + batadv_gw_node_put(gw_node); return orig_node; } @@ -148,8 +137,7 @@ static void batadv_gw_select(struct batadv_priv *bat_priv, curr_gw_node = rcu_replace_pointer(bat_priv->gw.curr_gw, new_gw_node, true); - if (curr_gw_node) - batadv_gw_node_put(curr_gw_node); + batadv_gw_node_put(curr_gw_node); spin_unlock_bh(&bat_priv->gw.list_lock); } @@ -284,14 +272,10 @@ void batadv_gw_election(struct batadv_priv *bat_priv) batadv_gw_select(bat_priv, next_gw); out: - if (curr_gw) - batadv_gw_node_put(curr_gw); - if (next_gw) - batadv_gw_node_put(next_gw); - if (router) - batadv_neigh_node_put(router); - if (router_ifinfo) - batadv_neigh_ifinfo_put(router_ifinfo); + batadv_gw_node_put(curr_gw); + batadv_gw_node_put(next_gw); + batadv_neigh_node_put(router); + batadv_neigh_ifinfo_put(router_ifinfo); } /** @@ -325,8 +309,7 @@ void batadv_gw_check_election(struct batadv_priv *bat_priv, reselect: batadv_gw_reselect(bat_priv); out: - if (curr_gw_orig) - batadv_orig_node_put(curr_gw_orig); + batadv_orig_node_put(curr_gw_orig); } /** @@ -466,13 +449,11 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv, if (gw_node == curr_gw) batadv_gw_reselect(bat_priv); - if (curr_gw) - batadv_gw_node_put(curr_gw); + batadv_gw_node_put(curr_gw); } out: - if (gw_node) - batadv_gw_node_put(gw_node); + batadv_gw_node_put(gw_node); } /** @@ -555,10 +536,8 @@ int batadv_gw_dump(struct sk_buff *msg, struct netlink_callback *cb) ret = msg->len; out: - if (primary_if) - batadv_hardif_put(primary_if); - if (soft_iface) - dev_put(soft_iface); + batadv_hardif_put(primary_if); + dev_put(soft_iface); return ret; } @@ -780,15 +759,10 @@ bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, batadv_neigh_ifinfo_put(old_ifinfo); out: - if (orig_dst_node) - batadv_orig_node_put(orig_dst_node); - if (curr_gw) - batadv_gw_node_put(curr_gw); - if (gw_node) - batadv_gw_node_put(gw_node); - if (neigh_old) - batadv_neigh_node_put(neigh_old); - if (neigh_curr) - batadv_neigh_node_put(neigh_curr); + batadv_orig_node_put(orig_dst_node); + batadv_gw_node_put(curr_gw); + batadv_gw_node_put(gw_node); + batadv_neigh_node_put(neigh_old); + batadv_neigh_node_put(neigh_curr); return out_of_range; } diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index 2ae5846ef958..95c2ccdaa554 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -9,6 +9,7 @@ #include "main.h" +#include <linux/kref.h> #include <linux/netlink.h> #include <linux/skbuff.h> #include <linux/types.h> @@ -27,7 +28,7 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv, void batadv_gw_node_delete(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node); void batadv_gw_node_free(struct batadv_priv *bat_priv); -void batadv_gw_node_put(struct batadv_gw_node *gw_node); +void batadv_gw_node_release(struct kref *ref); struct batadv_gw_node * batadv_gw_get_selected_gw_node(struct batadv_priv *bat_priv); int batadv_gw_dump(struct sk_buff *msg, struct netlink_callback *cb); @@ -38,4 +39,17 @@ batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len, struct batadv_gw_node *batadv_gw_node_get(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node); +/** + * batadv_gw_node_put() - decrement the gw_node refcounter and possibly release + * it + * @gw_node: gateway node to free + */ +static inline void batadv_gw_node_put(struct batadv_gw_node *gw_node) +{ + if (!gw_node) + return; + + kref_put(&gw_node->refcount, batadv_gw_node_release); +} + #endif /* _NET_BATMAN_ADV_GATEWAY_CLIENT_H_ */ diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index fdde305a198e..9349c76f30c5 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -10,7 +10,7 @@ #include <linux/atomic.h> #include <linux/byteorder/generic.h> #include <linux/errno.h> -#include <linux/kernel.h> +#include <linux/kstrtox.h> #include <linux/limits.h> #include <linux/math64.h> #include <linux/netdevice.h> diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 55d97e18aa4a..8a2b78f9c4b2 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -236,8 +236,7 @@ static struct net_device *batadv_get_real_netdevice(struct net_device *netdev) real_netdev = dev_get_by_index(real_net, ifindex); out: - if (hard_iface) - batadv_hardif_put(hard_iface); + batadv_hardif_put(hard_iface); return real_netdev; } @@ -457,8 +456,7 @@ static void batadv_primary_if_update_addr(struct batadv_priv *bat_priv, batadv_dat_init_own_addr(bat_priv, primary_if); batadv_bla_update_orig_address(bat_priv, primary_if, oldif); out: - if (primary_if) - batadv_hardif_put(primary_if); + batadv_hardif_put(primary_if); } static void batadv_primary_if_select(struct batadv_priv *bat_priv, @@ -481,8 +479,7 @@ static void batadv_primary_if_select(struct batadv_priv *bat_priv, batadv_primary_if_update_addr(bat_priv, curr_hard_iface); out: - if (curr_hard_iface) - batadv_hardif_put(curr_hard_iface); + batadv_hardif_put(curr_hard_iface); } static bool @@ -657,8 +654,7 @@ batadv_hardif_activate_interface(struct batadv_hard_iface *hard_iface) bat_priv->algo_ops->iface.activate(hard_iface); out: - if (primary_if) - batadv_hardif_put(primary_if); + batadv_hardif_put(primary_if); } static void @@ -811,8 +807,7 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface) new_if = batadv_hardif_get_active(hard_iface->soft_iface); batadv_primary_if_select(bat_priv, new_if); - if (new_if) - batadv_hardif_put(new_if); + batadv_hardif_put(new_if); } bat_priv->algo_ops->iface.disable(hard_iface); @@ -834,8 +829,7 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface) batadv_hardif_put(hard_iface); out: - if (primary_if) - batadv_hardif_put(primary_if); + batadv_hardif_put(primary_if); } static struct batadv_hard_iface * @@ -990,8 +984,7 @@ static int batadv_hard_if_event(struct notifier_block *this, hardif_put: batadv_hardif_put(hard_iface); out: - if (primary_if) - batadv_hardif_put(primary_if); + batadv_hardif_put(primary_if); return NOTIFY_DONE; } diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index 8cb2a1f10080..64f660dbbe54 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -89,6 +89,9 @@ int batadv_hardif_no_broadcast(struct batadv_hard_iface *if_outgoing, */ static inline void batadv_hardif_put(struct batadv_hard_iface *hard_iface) { + if (!hard_iface) + return; + kref_put(&hard_iface->refcount, batadv_hardif_release); } diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c index f0e5d1429662..7a93a1e94c40 100644 --- a/net/batman-adv/log.c +++ b/net/batman-adv/log.c @@ -7,7 +7,7 @@ #include "log.h" #include "main.h" -#include <stdarg.h> +#include <linux/stdarg.h> #include "trace.h" diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 014235fd4681..058b8f2eef65 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -13,7 +13,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2021.2" +#define BATADV_SOURCE_VERSION "2021.3" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index 923e2197c2db..a3b6658ed789 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -91,8 +91,7 @@ static struct net_device *batadv_mcast_get_bridge(struct net_device *soft_iface) upper = netdev_master_upper_dev_get_rcu(upper); } while (upper && !(upper->priv_flags & IFF_EBRIDGE)); - if (upper) - dev_hold(upper); + dev_hold(upper); rcu_read_unlock(); return upper; @@ -509,8 +508,7 @@ batadv_mcast_mla_softif_get(struct net_device *dev, } out: - if (bridge) - dev_put(bridge); + dev_put(bridge); return ret4 + ret6; } @@ -2239,12 +2237,11 @@ batadv_mcast_netlink_get_primary(struct netlink_callback *cb, } out: - if (soft_iface) - dev_put(soft_iface); + dev_put(soft_iface); if (!ret && primary_if) *primary_if = hard_iface; - else if (hard_iface) + else batadv_hardif_put(hard_iface); return ret; diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index b6cc746e01a6..29276284d281 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -359,15 +359,13 @@ static int batadv_netlink_mesh_fill(struct sk_buff *msg, atomic_read(&bat_priv->orig_interval))) goto nla_put_failure; - if (primary_if) - batadv_hardif_put(primary_if); + batadv_hardif_put(primary_if); genlmsg_end(msg, hdr); return 0; nla_put_failure: - if (primary_if) - batadv_hardif_put(primary_if); + batadv_hardif_put(primary_if); genlmsg_cancel(msg, hdr); return -EMSGSIZE; diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 4bb76b434d07..9f06132e007d 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -217,6 +217,9 @@ static void batadv_nc_node_release(struct kref *ref) */ static void batadv_nc_node_put(struct batadv_nc_node *nc_node) { + if (!nc_node) + return; + kref_put(&nc_node->refcount, batadv_nc_node_release); } @@ -241,6 +244,9 @@ static void batadv_nc_path_release(struct kref *ref) */ static void batadv_nc_path_put(struct batadv_nc_path *nc_path) { + if (!nc_path) + return; + kref_put(&nc_path->refcount, batadv_nc_path_release); } @@ -930,10 +936,8 @@ void batadv_nc_update_nc_node(struct batadv_priv *bat_priv, out_nc_node->last_seen = jiffies; out: - if (in_nc_node) - batadv_nc_node_put(in_nc_node); - if (out_nc_node) - batadv_nc_node_put(out_nc_node); + batadv_nc_node_put(in_nc_node); + batadv_nc_node_put(out_nc_node); } /** @@ -1209,14 +1213,10 @@ static bool batadv_nc_code_packets(struct batadv_priv *bat_priv, batadv_send_unicast_skb(skb_dest, first_dest); res = true; out: - if (router_neigh) - batadv_neigh_node_put(router_neigh); - if (router_coding) - batadv_neigh_node_put(router_coding); - if (router_neigh_ifinfo) - batadv_neigh_ifinfo_put(router_neigh_ifinfo); - if (router_coding_ifinfo) - batadv_neigh_ifinfo_put(router_coding_ifinfo); + batadv_neigh_node_put(router_neigh); + batadv_neigh_node_put(router_coding); + batadv_neigh_ifinfo_put(router_neigh_ifinfo); + batadv_neigh_ifinfo_put(router_coding_ifinfo); return res; } diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index da7249448474..aadc653ca1d8 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -177,7 +177,7 @@ out: * and queue for free after rcu grace period * @ref: kref pointer of the originator-vlan object */ -static void batadv_orig_node_vlan_release(struct kref *ref) +void batadv_orig_node_vlan_release(struct kref *ref) { struct batadv_orig_node_vlan *orig_vlan; @@ -187,16 +187,6 @@ static void batadv_orig_node_vlan_release(struct kref *ref) } /** - * batadv_orig_node_vlan_put() - decrement the refcounter and possibly release - * the originator-vlan object - * @orig_vlan: the originator-vlan object to release - */ -void batadv_orig_node_vlan_put(struct batadv_orig_node_vlan *orig_vlan) -{ - kref_put(&orig_vlan->refcount, batadv_orig_node_vlan_release); -} - -/** * batadv_originator_init() - Initialize all originator structures * @bat_priv: the bat priv with all the soft interface information * @@ -231,7 +221,7 @@ err: * free after rcu grace period * @ref: kref pointer of the neigh_ifinfo */ -static void batadv_neigh_ifinfo_release(struct kref *ref) +void batadv_neigh_ifinfo_release(struct kref *ref) { struct batadv_neigh_ifinfo *neigh_ifinfo; @@ -244,21 +234,11 @@ static void batadv_neigh_ifinfo_release(struct kref *ref) } /** - * batadv_neigh_ifinfo_put() - decrement the refcounter and possibly release - * the neigh_ifinfo - * @neigh_ifinfo: the neigh_ifinfo object to release - */ -void batadv_neigh_ifinfo_put(struct batadv_neigh_ifinfo *neigh_ifinfo) -{ - kref_put(&neigh_ifinfo->refcount, batadv_neigh_ifinfo_release); -} - -/** * batadv_hardif_neigh_release() - release hardif neigh node from lists and * queue for free after rcu grace period * @ref: kref pointer of the neigh_node */ -static void batadv_hardif_neigh_release(struct kref *ref) +void batadv_hardif_neigh_release(struct kref *ref) { struct batadv_hardif_neigh_node *hardif_neigh; @@ -274,21 +254,11 @@ static void batadv_hardif_neigh_release(struct kref *ref) } /** - * batadv_hardif_neigh_put() - decrement the hardif neighbors refcounter - * and possibly release it - * @hardif_neigh: hardif neigh neighbor to free - */ -void batadv_hardif_neigh_put(struct batadv_hardif_neigh_node *hardif_neigh) -{ - kref_put(&hardif_neigh->refcount, batadv_hardif_neigh_release); -} - -/** * batadv_neigh_node_release() - release neigh_node from lists and queue for * free after rcu grace period * @ref: kref pointer of the neigh_node */ -static void batadv_neigh_node_release(struct kref *ref) +void batadv_neigh_node_release(struct kref *ref) { struct hlist_node *node_tmp; struct batadv_neigh_node *neigh_node; @@ -309,16 +279,6 @@ static void batadv_neigh_node_release(struct kref *ref) } /** - * batadv_neigh_node_put() - decrement the neighbors refcounter and possibly - * release it - * @neigh_node: neigh neighbor to free - */ -void batadv_neigh_node_put(struct batadv_neigh_node *neigh_node) -{ - kref_put(&neigh_node->refcount, batadv_neigh_node_release); -} - -/** * batadv_orig_router_get() - router to the originator depending on iface * @orig_node: the orig node for the router * @if_outgoing: the interface where the payload packet has been received or @@ -704,8 +664,7 @@ batadv_neigh_node_create(struct batadv_orig_node *orig_node, out: spin_unlock_bh(&orig_node->neigh_list_lock); - if (hardif_neigh) - batadv_hardif_neigh_put(hardif_neigh); + batadv_hardif_neigh_put(hardif_neigh); return neigh_node; } @@ -797,14 +756,10 @@ int batadv_hardif_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb) ret = msg->len; out: - if (hardif) - batadv_hardif_put(hardif); - if (hard_iface) - dev_put(hard_iface); - if (primary_if) - batadv_hardif_put(primary_if); - if (soft_iface) - dev_put(soft_iface); + batadv_hardif_put(hardif); + dev_put(hard_iface); + batadv_hardif_put(primary_if); + dev_put(soft_iface); return ret; } @@ -814,7 +769,7 @@ int batadv_hardif_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb) * free after rcu grace period * @ref: kref pointer of the orig_ifinfo */ -static void batadv_orig_ifinfo_release(struct kref *ref) +void batadv_orig_ifinfo_release(struct kref *ref) { struct batadv_orig_ifinfo *orig_ifinfo; struct batadv_neigh_node *router; @@ -826,23 +781,12 @@ static void batadv_orig_ifinfo_release(struct kref *ref) /* this is the last reference to this object */ router = rcu_dereference_protected(orig_ifinfo->router, true); - if (router) - batadv_neigh_node_put(router); + batadv_neigh_node_put(router); kfree_rcu(orig_ifinfo, rcu); } /** - * batadv_orig_ifinfo_put() - decrement the refcounter and possibly release - * the orig_ifinfo - * @orig_ifinfo: the orig_ifinfo object to release - */ -void batadv_orig_ifinfo_put(struct batadv_orig_ifinfo *orig_ifinfo) -{ - kref_put(&orig_ifinfo->refcount, batadv_orig_ifinfo_release); -} - -/** * batadv_orig_node_free_rcu() - free the orig_node * @rcu: rcu pointer of the orig_node */ @@ -865,7 +809,7 @@ static void batadv_orig_node_free_rcu(struct rcu_head *rcu) * free after rcu grace period * @ref: kref pointer of the orig_node */ -static void batadv_orig_node_release(struct kref *ref) +void batadv_orig_node_release(struct kref *ref) { struct hlist_node *node_tmp; struct batadv_neigh_node *neigh_node; @@ -895,8 +839,7 @@ static void batadv_orig_node_release(struct kref *ref) orig_node->last_bonding_candidate = NULL; spin_unlock_bh(&orig_node->neigh_list_lock); - if (last_candidate) - batadv_orig_ifinfo_put(last_candidate); + batadv_orig_ifinfo_put(last_candidate); spin_lock_bh(&orig_node->vlan_list_lock); hlist_for_each_entry_safe(vlan, node_tmp, &orig_node->vlan_list, list) { @@ -912,16 +855,6 @@ static void batadv_orig_node_release(struct kref *ref) } /** - * batadv_orig_node_put() - decrement the orig node refcounter and possibly - * release it - * @orig_node: the orig node to free - */ -void batadv_orig_node_put(struct batadv_orig_node *orig_node) -{ - kref_put(&orig_node->refcount, batadv_orig_node_release); -} - -/** * batadv_originator_free() - Free all originator structures * @bat_priv: the bat priv with all the soft interface information */ @@ -1213,8 +1146,7 @@ batadv_find_best_neighbor(struct batadv_priv *bat_priv, if (!kref_get_unless_zero(&neigh->refcount)) continue; - if (best) - batadv_neigh_node_put(best); + batadv_neigh_node_put(best); best = neigh; } @@ -1259,8 +1191,7 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv, BATADV_IF_DEFAULT); batadv_update_route(bat_priv, orig_node, BATADV_IF_DEFAULT, best_neigh_node); - if (best_neigh_node) - batadv_neigh_node_put(best_neigh_node); + batadv_neigh_node_put(best_neigh_node); /* ... then for all other interfaces. */ rcu_read_lock(); @@ -1279,8 +1210,7 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv, hard_iface); batadv_update_route(bat_priv, orig_node, hard_iface, best_neigh_node); - if (best_neigh_node) - batadv_neigh_node_put(best_neigh_node); + batadv_neigh_node_put(best_neigh_node); batadv_hardif_put(hard_iface); } @@ -1410,14 +1340,10 @@ int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb) ret = msg->len; out: - if (hardif) - batadv_hardif_put(hardif); - if (hard_iface) - dev_put(hard_iface); - if (primary_if) - batadv_hardif_put(primary_if); - if (soft_iface) - dev_put(soft_iface); + batadv_hardif_put(hardif); + dev_put(hard_iface); + batadv_hardif_put(primary_if); + dev_put(soft_iface); return ret; } diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 805be87d55b8..ea3d69e4e670 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -12,6 +12,7 @@ #include <linux/compiler.h> #include <linux/if_ether.h> #include <linux/jhash.h> +#include <linux/kref.h> #include <linux/netlink.h> #include <linux/skbuff.h> #include <linux/types.h> @@ -20,19 +21,18 @@ bool batadv_compare_orig(const struct hlist_node *node, const void *data2); int batadv_originator_init(struct batadv_priv *bat_priv); void batadv_originator_free(struct batadv_priv *bat_priv); void batadv_purge_orig_ref(struct batadv_priv *bat_priv); -void batadv_orig_node_put(struct batadv_orig_node *orig_node); +void batadv_orig_node_release(struct kref *ref); struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, const u8 *addr); struct batadv_hardif_neigh_node * batadv_hardif_neigh_get(const struct batadv_hard_iface *hard_iface, const u8 *neigh_addr); -void -batadv_hardif_neigh_put(struct batadv_hardif_neigh_node *hardif_neigh); +void batadv_hardif_neigh_release(struct kref *ref); struct batadv_neigh_node * batadv_neigh_node_get_or_create(struct batadv_orig_node *orig_node, struct batadv_hard_iface *hard_iface, const u8 *neigh_addr); -void batadv_neigh_node_put(struct batadv_neigh_node *neigh_node); +void batadv_neigh_node_release(struct kref *ref); struct batadv_neigh_node * batadv_orig_router_get(struct batadv_orig_node *orig_node, const struct batadv_hard_iface *if_outgoing); @@ -42,7 +42,7 @@ batadv_neigh_ifinfo_new(struct batadv_neigh_node *neigh, struct batadv_neigh_ifinfo * batadv_neigh_ifinfo_get(struct batadv_neigh_node *neigh, struct batadv_hard_iface *if_outgoing); -void batadv_neigh_ifinfo_put(struct batadv_neigh_ifinfo *neigh_ifinfo); +void batadv_neigh_ifinfo_release(struct kref *ref); int batadv_hardif_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb); @@ -52,7 +52,7 @@ batadv_orig_ifinfo_get(struct batadv_orig_node *orig_node, struct batadv_orig_ifinfo * batadv_orig_ifinfo_new(struct batadv_orig_node *orig_node, struct batadv_hard_iface *if_outgoing); -void batadv_orig_ifinfo_put(struct batadv_orig_ifinfo *orig_ifinfo); +void batadv_orig_ifinfo_release(struct kref *ref); int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb); struct batadv_orig_node_vlan * @@ -61,7 +61,7 @@ batadv_orig_node_vlan_new(struct batadv_orig_node *orig_node, struct batadv_orig_node_vlan * batadv_orig_node_vlan_get(struct batadv_orig_node *orig_node, unsigned short vid); -void batadv_orig_node_vlan_put(struct batadv_orig_node_vlan *orig_vlan); +void batadv_orig_node_vlan_release(struct kref *ref); /** * batadv_choose_orig() - Return the index of the orig entry in the hash table @@ -82,4 +82,86 @@ static inline u32 batadv_choose_orig(const void *data, u32 size) struct batadv_orig_node * batadv_orig_hash_find(struct batadv_priv *bat_priv, const void *data); +/** + * batadv_orig_node_vlan_put() - decrement the refcounter and possibly release + * the originator-vlan object + * @orig_vlan: the originator-vlan object to release + */ +static inline void +batadv_orig_node_vlan_put(struct batadv_orig_node_vlan *orig_vlan) +{ + if (!orig_vlan) + return; + + kref_put(&orig_vlan->refcount, batadv_orig_node_vlan_release); +} + +/** + * batadv_neigh_ifinfo_put() - decrement the refcounter and possibly release + * the neigh_ifinfo + * @neigh_ifinfo: the neigh_ifinfo object to release + */ +static inline void +batadv_neigh_ifinfo_put(struct batadv_neigh_ifinfo *neigh_ifinfo) +{ + if (!neigh_ifinfo) + return; + + kref_put(&neigh_ifinfo->refcount, batadv_neigh_ifinfo_release); +} + +/** + * batadv_hardif_neigh_put() - decrement the hardif neighbors refcounter + * and possibly release it + * @hardif_neigh: hardif neigh neighbor to free + */ +static inline void +batadv_hardif_neigh_put(struct batadv_hardif_neigh_node *hardif_neigh) +{ + if (!hardif_neigh) + return; + + kref_put(&hardif_neigh->refcount, batadv_hardif_neigh_release); +} + +/** + * batadv_neigh_node_put() - decrement the neighbors refcounter and possibly + * release it + * @neigh_node: neigh neighbor to free + */ +static inline void batadv_neigh_node_put(struct batadv_neigh_node *neigh_node) +{ + if (!neigh_node) + return; + + kref_put(&neigh_node->refcount, batadv_neigh_node_release); +} + +/** + * batadv_orig_ifinfo_put() - decrement the refcounter and possibly release + * the orig_ifinfo + * @orig_ifinfo: the orig_ifinfo object to release + */ +static inline void +batadv_orig_ifinfo_put(struct batadv_orig_ifinfo *orig_ifinfo) +{ + if (!orig_ifinfo) + return; + + kref_put(&orig_ifinfo->refcount, batadv_orig_ifinfo_release); +} + +/** + * batadv_orig_node_put() - decrement the orig node refcounter and possibly + * release it + * @orig_node: the orig node to free + */ +static inline void batadv_orig_node_put(struct batadv_orig_node *orig_node) +{ + if (!orig_node) + return; + + kref_put(&orig_node->refcount, batadv_orig_node_release); +} + #endif /* _NET_BATMAN_ADV_ORIGINATOR_H_ */ diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index bb9e93e3d98c..970d0d7ccc98 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -101,8 +101,7 @@ static void _batadv_update_route(struct batadv_priv *bat_priv, } /* decrease refcount of previous best neighbor */ - if (curr_router) - batadv_neigh_node_put(curr_router); + batadv_neigh_node_put(curr_router); } /** @@ -128,8 +127,7 @@ void batadv_update_route(struct batadv_priv *bat_priv, _batadv_update_route(bat_priv, orig_node, recv_if, neigh_node); out: - if (router) - batadv_neigh_node_put(router); + batadv_neigh_node_put(router); } /** @@ -269,10 +267,8 @@ static int batadv_recv_my_icmp_packet(struct batadv_priv *bat_priv, goto out; } out: - if (primary_if) - batadv_hardif_put(primary_if); - if (orig_node) - batadv_orig_node_put(orig_node); + batadv_hardif_put(primary_if); + batadv_orig_node_put(orig_node); kfree_skb(skb); @@ -324,10 +320,8 @@ static int batadv_recv_icmp_ttl_exceeded(struct batadv_priv *bat_priv, skb = NULL; out: - if (primary_if) - batadv_hardif_put(primary_if); - if (orig_node) - batadv_orig_node_put(orig_node); + batadv_hardif_put(primary_if); + batadv_orig_node_put(orig_node); kfree_skb(skb); @@ -425,8 +419,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb, skb = NULL; put_orig_node: - if (orig_node) - batadv_orig_node_put(orig_node); + batadv_orig_node_put(orig_node); free_skb: kfree_skb(skb); @@ -513,8 +506,7 @@ batadv_last_bonding_replace(struct batadv_orig_node *orig_node, orig_node->last_bonding_candidate = new_candidate; spin_unlock_bh(&orig_node->neigh_list_lock); - if (old_candidate) - batadv_orig_ifinfo_put(old_candidate); + batadv_orig_ifinfo_put(old_candidate); } /** @@ -656,8 +648,7 @@ next: batadv_orig_ifinfo_put(next_candidate); } - if (last_candidate) - batadv_orig_ifinfo_put(last_candidate); + batadv_orig_ifinfo_put(last_candidate); return router; } @@ -785,10 +776,8 @@ batadv_reroute_unicast_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, ret = true; out: - if (primary_if) - batadv_hardif_put(primary_if); - if (orig_node) - batadv_orig_node_put(orig_node); + batadv_hardif_put(primary_if); + batadv_orig_node_put(orig_node); return ret; } @@ -1031,8 +1020,7 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, orig_node); rx_success: - if (orig_node) - batadv_orig_node_put(orig_node); + batadv_orig_node_put(orig_node); return NET_RX_SUCCESS; } @@ -1279,7 +1267,6 @@ free_skb: kfree_skb(skb); ret = NET_RX_DROP; out: - if (orig_node) - batadv_orig_node_put(orig_node); + batadv_orig_node_put(orig_node); return ret; } diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 0b9dd29d3b6a..477d85a3b558 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -152,8 +152,7 @@ int batadv_send_unicast_skb(struct sk_buff *skb, if (hardif_neigh && ret != NET_XMIT_DROP) hardif_neigh->bat_v.last_unicast_tx = jiffies; - if (hardif_neigh) - batadv_hardif_neigh_put(hardif_neigh); + batadv_hardif_neigh_put(hardif_neigh); #endif return ret; @@ -309,8 +308,7 @@ bool batadv_send_skb_prepare_unicast_4addr(struct batadv_priv *bat_priv, ret = true; out: - if (primary_if) - batadv_hardif_put(primary_if); + batadv_hardif_put(primary_if); return ret; } @@ -425,8 +423,7 @@ int batadv_send_skb_via_tt_generic(struct batadv_priv *bat_priv, ret = batadv_send_skb_unicast(bat_priv, skb, packet_type, packet_subtype, orig_node, vid); - if (orig_node) - batadv_orig_node_put(orig_node); + batadv_orig_node_put(orig_node); return ret; } @@ -452,8 +449,7 @@ int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb, ret = batadv_send_skb_unicast(bat_priv, skb, BATADV_UNICAST_4ADDR, BATADV_P_DATA, orig_node, vid); - if (orig_node) - batadv_orig_node_put(orig_node); + batadv_orig_node_put(orig_node); return ret; } @@ -474,10 +470,8 @@ void batadv_forw_packet_free(struct batadv_forw_packet *forw_packet, else consume_skb(forw_packet->skb); - if (forw_packet->if_incoming) - batadv_hardif_put(forw_packet->if_incoming); - if (forw_packet->if_outgoing) - batadv_hardif_put(forw_packet->if_outgoing); + batadv_hardif_put(forw_packet->if_incoming); + batadv_hardif_put(forw_packet->if_outgoing); if (forw_packet->queue_left) atomic_inc(forw_packet->queue_left); kfree(forw_packet); @@ -748,6 +742,10 @@ void batadv_forw_packet_ogmv1_queue(struct batadv_priv *bat_priv, * Adds a broadcast packet to the queue and sets up timers. Broadcast packets * are sent multiple times to increase probability for being received. * + * This call clones the given skb, hence the caller needs to take into + * account that the data segment of the original skb might not be + * modifiable anymore. + * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ static int batadv_forw_bcast_packet_to_list(struct batadv_priv *bat_priv, @@ -761,7 +759,7 @@ static int batadv_forw_bcast_packet_to_list(struct batadv_priv *bat_priv, unsigned long send_time = jiffies; struct sk_buff *newskb; - newskb = skb_copy(skb, GFP_ATOMIC); + newskb = skb_clone(skb, GFP_ATOMIC); if (!newskb) goto err; @@ -800,6 +798,10 @@ err: * or if a delay is given after that. Furthermore, queues additional * retransmissions if this interface is a wireless one. * + * This call clones the given skb, hence the caller needs to take into + * account that the data segment of the original skb might not be + * modifiable anymore. + * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ static int batadv_forw_bcast_packet_if(struct batadv_priv *bat_priv, @@ -814,7 +816,7 @@ static int batadv_forw_bcast_packet_if(struct batadv_priv *bat_priv, int ret = NETDEV_TX_OK; if (!delay) { - newskb = skb_copy(skb, GFP_ATOMIC); + newskb = skb_clone(skb, GFP_ATOMIC); if (!newskb) return NETDEV_TX_BUSY; @@ -867,8 +869,7 @@ static bool batadv_send_no_broadcast(struct batadv_priv *bat_priv, ret = batadv_hardif_no_broadcast(if_out, bcast_packet->orig, orig_neigh); - if (neigh_node) - batadv_hardif_neigh_put(neigh_node); + batadv_hardif_neigh_put(neigh_node); /* ok, may broadcast */ if (!ret) diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index ae368a42a4ad..0604b0279573 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -383,10 +383,8 @@ dropped: dropped_freed: batadv_inc_counter(bat_priv, BATADV_CNT_TX_DROPPED); end: - if (mcast_single_orig) - batadv_orig_node_put(mcast_single_orig); - if (primary_if) - batadv_hardif_put(primary_if); + batadv_orig_node_put(mcast_single_orig); + batadv_hardif_put(primary_if); return NETDEV_TX_OK; } @@ -501,7 +499,7 @@ out: * after rcu grace period * @ref: kref pointer of the vlan object */ -static void batadv_softif_vlan_release(struct kref *ref) +void batadv_softif_vlan_release(struct kref *ref) { struct batadv_softif_vlan *vlan; @@ -515,19 +513,6 @@ static void batadv_softif_vlan_release(struct kref *ref) } /** - * batadv_softif_vlan_put() - decrease the vlan object refcounter and - * possibly release it - * @vlan: the vlan object to release - */ -void batadv_softif_vlan_put(struct batadv_softif_vlan *vlan) -{ - if (!vlan) - return; - - kref_put(&vlan->refcount, batadv_softif_vlan_release); -} - -/** * batadv_softif_vlan_get() - get the vlan object for a specific vid * @bat_priv: the bat priv with all the soft interface information * @vid: the identifier of the vlan object to retrieve @@ -851,8 +836,7 @@ static int batadv_softif_slave_add(struct net_device *dev, ret = batadv_hardif_enable_interface(hard_iface, dev); out: - if (hard_iface) - batadv_hardif_put(hard_iface); + batadv_hardif_put(hard_iface); return ret; } @@ -878,8 +862,7 @@ static int batadv_softif_slave_del(struct net_device *dev, ret = 0; out: - if (hard_iface) - batadv_hardif_put(hard_iface); + batadv_hardif_put(hard_iface); return ret; } diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index 67a2ddd6832f..9f2003f1a497 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -9,6 +9,7 @@ #include "main.h" +#include <linux/kref.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/types.h> @@ -21,8 +22,21 @@ void batadv_interface_rx(struct net_device *soft_iface, bool batadv_softif_is_valid(const struct net_device *net_dev); extern struct rtnl_link_ops batadv_link_ops; int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid); -void batadv_softif_vlan_put(struct batadv_softif_vlan *softif_vlan); +void batadv_softif_vlan_release(struct kref *ref); struct batadv_softif_vlan *batadv_softif_vlan_get(struct batadv_priv *bat_priv, unsigned short vid); +/** + * batadv_softif_vlan_put() - decrease the vlan object refcounter and + * possibly release it + * @vlan: the vlan object to release + */ +static inline void batadv_softif_vlan_put(struct batadv_softif_vlan *vlan) +{ + if (!vlan) + return; + + kref_put(&vlan->refcount, batadv_softif_vlan_release); +} + #endif /* _NET_BATMAN_ADV_SOFT_INTERFACE_H_ */ diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index 789c851732b7..56b9fe97b3b4 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -358,6 +358,9 @@ static void batadv_tp_vars_release(struct kref *ref) */ static void batadv_tp_vars_put(struct batadv_tp_vars *tp_vars) { + if (!tp_vars) + return; + kref_put(&tp_vars->refcount, batadv_tp_vars_release); } @@ -748,12 +751,9 @@ move_twnd: wake_up(&tp_vars->more_bytes); out: - if (likely(primary_if)) - batadv_hardif_put(primary_if); - if (likely(orig_node)) - batadv_orig_node_put(orig_node); - if (likely(tp_vars)) - batadv_tp_vars_put(tp_vars); + batadv_hardif_put(primary_if); + batadv_orig_node_put(orig_node); + batadv_tp_vars_put(tp_vars); } /** @@ -882,10 +882,8 @@ static int batadv_tp_send(void *arg) } out: - if (likely(primary_if)) - batadv_hardif_put(primary_if); - if (likely(orig_node)) - batadv_orig_node_put(orig_node); + batadv_hardif_put(primary_if); + batadv_orig_node_put(orig_node); batadv_tp_sender_end(bat_priv, tp_vars); batadv_tp_sender_cleanup(bat_priv, tp_vars); @@ -1205,10 +1203,8 @@ static int batadv_tp_send_ack(struct batadv_priv *bat_priv, const u8 *dst, ret = 0; out: - if (likely(orig_node)) - batadv_orig_node_put(orig_node); - if (likely(primary_if)) - batadv_hardif_put(primary_if); + batadv_orig_node_put(orig_node); + batadv_hardif_put(primary_if); return ret; } @@ -1456,8 +1452,7 @@ send_ack: batadv_tp_send_ack(bat_priv, icmp->orig, tp_vars->last_recv, icmp->timestamp, icmp->session, icmp->uid); out: - if (likely(tp_vars)) - batadv_tp_vars_put(tp_vars); + batadv_tp_vars_put(tp_vars); } /** diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 434b4f042909..e0b3dace2020 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -247,6 +247,9 @@ static void batadv_tt_local_entry_release(struct kref *ref) static void batadv_tt_local_entry_put(struct batadv_tt_local_entry *tt_local_entry) { + if (!tt_local_entry) + return; + kref_put(&tt_local_entry->common.refcount, batadv_tt_local_entry_release); } @@ -270,7 +273,7 @@ static void batadv_tt_global_entry_free_rcu(struct rcu_head *rcu) * queue for free after rcu grace period * @ref: kref pointer of the nc_node */ -static void batadv_tt_global_entry_release(struct kref *ref) +void batadv_tt_global_entry_release(struct kref *ref) { struct batadv_tt_global_entry *tt_global_entry; @@ -283,17 +286,6 @@ static void batadv_tt_global_entry_release(struct kref *ref) } /** - * batadv_tt_global_entry_put() - decrement the tt_global_entry refcounter and - * possibly release it - * @tt_global_entry: tt_global_entry to be free'd - */ -void batadv_tt_global_entry_put(struct batadv_tt_global_entry *tt_global_entry) -{ - kref_put(&tt_global_entry->common.refcount, - batadv_tt_global_entry_release); -} - -/** * batadv_tt_global_hash_count() - count the number of orig entries * @bat_priv: the bat priv with all the soft interface information * @addr: the mac address of the client to count entries for @@ -452,6 +444,9 @@ static void batadv_tt_orig_list_entry_release(struct kref *ref) static void batadv_tt_orig_list_entry_put(struct batadv_tt_orig_list_entry *orig_entry) { + if (!orig_entry) + return; + kref_put(&orig_entry->refcount, batadv_tt_orig_list_entry_release); } @@ -818,14 +813,10 @@ check_roaming: ret = true; out: - if (in_hardif) - batadv_hardif_put(in_hardif); - if (in_dev) - dev_put(in_dev); - if (tt_local) - batadv_tt_local_entry_put(tt_local); - if (tt_global) - batadv_tt_global_entry_put(tt_global); + batadv_hardif_put(in_hardif); + dev_put(in_dev); + batadv_tt_local_entry_put(tt_local); + batadv_tt_global_entry_put(tt_global); return ret; } @@ -1215,10 +1206,8 @@ int batadv_tt_local_dump(struct sk_buff *msg, struct netlink_callback *cb) ret = msg->len; out: - if (primary_if) - batadv_hardif_put(primary_if); - if (soft_iface) - dev_put(soft_iface); + batadv_hardif_put(primary_if); + dev_put(soft_iface); cb->args[0] = bucket; cb->args[1] = idx; @@ -1305,8 +1294,7 @@ u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const u8 *addr, batadv_tt_local_entry_put(tt_removed_entry); out: - if (tt_local_entry) - batadv_tt_local_entry_put(tt_local_entry); + batadv_tt_local_entry_put(tt_local_entry); return curr_flags; } @@ -1576,8 +1564,7 @@ batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, sync_flags: batadv_tt_global_sync_flags(tt_global); out: - if (orig_entry) - batadv_tt_orig_list_entry_put(orig_entry); + batadv_tt_orig_list_entry_put(orig_entry); spin_unlock_bh(&tt_global->list_lock); } @@ -1750,10 +1737,8 @@ out_remove: tt_global_entry->common.flags &= ~BATADV_TT_CLIENT_ROAM; out: - if (tt_global_entry) - batadv_tt_global_entry_put(tt_global_entry); - if (tt_local_entry) - batadv_tt_local_entry_put(tt_local_entry); + batadv_tt_global_entry_put(tt_global_entry); + batadv_tt_local_entry_put(tt_local_entry); return ret; } @@ -1789,15 +1774,13 @@ batadv_transtable_best_orig(struct batadv_priv *bat_priv, } /* release the refcount for the "old" best */ - if (best_router) - batadv_neigh_node_put(best_router); + batadv_neigh_node_put(best_router); best_entry = orig_entry; best_router = router; } - if (best_router) - batadv_neigh_node_put(best_router); + batadv_neigh_node_put(best_router); return best_entry; } @@ -2003,10 +1986,8 @@ int batadv_tt_global_dump(struct sk_buff *msg, struct netlink_callback *cb) ret = msg->len; out: - if (primary_if) - batadv_hardif_put(primary_if); - if (soft_iface) - dev_put(soft_iface); + batadv_hardif_put(primary_if); + dev_put(soft_iface); cb->args[0] = bucket; cb->args[1] = idx; @@ -2196,10 +2177,8 @@ static void batadv_tt_global_del(struct batadv_priv *bat_priv, } out: - if (tt_global_entry) - batadv_tt_global_entry_put(tt_global_entry); - if (local_entry) - batadv_tt_local_entry_put(local_entry); + batadv_tt_global_entry_put(tt_global_entry); + batadv_tt_local_entry_put(local_entry); } /** @@ -2426,10 +2405,8 @@ struct batadv_orig_node *batadv_transtable_search(struct batadv_priv *bat_priv, rcu_read_unlock(); out: - if (tt_global_entry) - batadv_tt_global_entry_put(tt_global_entry); - if (tt_local_entry) - batadv_tt_local_entry_put(tt_local_entry); + batadv_tt_global_entry_put(tt_global_entry); + batadv_tt_local_entry_put(tt_local_entry); return orig_node; } @@ -2606,6 +2583,9 @@ static void batadv_tt_req_node_release(struct kref *ref) */ static void batadv_tt_req_node_put(struct batadv_tt_req_node *tt_req_node) { + if (!tt_req_node) + return; + kref_put(&tt_req_node->refcount, batadv_tt_req_node_release); } @@ -2987,8 +2967,7 @@ static bool batadv_send_tt_request(struct batadv_priv *bat_priv, ret = true; out: - if (primary_if) - batadv_hardif_put(primary_if); + batadv_hardif_put(primary_if); if (ret && tt_req_node) { spin_lock_bh(&bat_priv->tt.req_list_lock); @@ -2999,8 +2978,7 @@ out: spin_unlock_bh(&bat_priv->tt.req_list_lock); } - if (tt_req_node) - batadv_tt_req_node_put(tt_req_node); + batadv_tt_req_node_put(tt_req_node); kfree(tvlv_tt_data); return ret; @@ -3131,10 +3109,8 @@ unlock: spin_unlock_bh(&req_dst_orig_node->tt_buff_lock); out: - if (res_dst_orig_node) - batadv_orig_node_put(res_dst_orig_node); - if (req_dst_orig_node) - batadv_orig_node_put(req_dst_orig_node); + batadv_orig_node_put(res_dst_orig_node); + batadv_orig_node_put(req_dst_orig_node); kfree(tvlv_tt_data); return ret; } @@ -3248,10 +3224,8 @@ unlock: spin_unlock_bh(&bat_priv->tt.last_changeset_lock); out: spin_unlock_bh(&bat_priv->tt.commit_lock); - if (orig_node) - batadv_orig_node_put(orig_node); - if (primary_if) - batadv_hardif_put(primary_if); + batadv_orig_node_put(orig_node); + batadv_hardif_put(primary_if); kfree(tvlv_tt_data); /* The packet was for this host, so it doesn't need to be re-routed */ return true; @@ -3336,8 +3310,7 @@ static void batadv_tt_fill_gtable(struct batadv_priv *bat_priv, atomic_set(&orig_node->last_ttvn, ttvn); out: - if (orig_node) - batadv_orig_node_put(orig_node); + batadv_orig_node_put(orig_node); } static void batadv_tt_update_changes(struct batadv_priv *bat_priv, @@ -3378,8 +3351,7 @@ bool batadv_is_my_client(struct batadv_priv *bat_priv, const u8 *addr, goto out; ret = true; out: - if (tt_local_entry) - batadv_tt_local_entry_put(tt_local_entry); + batadv_tt_local_entry_put(tt_local_entry); return ret; } @@ -3442,8 +3414,7 @@ static void batadv_handle_tt_response(struct batadv_priv *bat_priv, spin_unlock_bh(&bat_priv->tt.req_list_lock); out: - if (orig_node) - batadv_orig_node_put(orig_node); + batadv_orig_node_put(orig_node); } static void batadv_tt_roam_list_free(struct batadv_priv *bat_priv) @@ -3574,8 +3545,7 @@ static void batadv_send_roam_adv(struct batadv_priv *bat_priv, u8 *client, &tvlv_roam, sizeof(tvlv_roam)); out: - if (primary_if) - batadv_hardif_put(primary_if); + batadv_hardif_put(primary_if); } static void batadv_tt_purge(struct work_struct *work) @@ -4170,8 +4140,7 @@ static int batadv_roam_tvlv_unicast_handler_v1(struct batadv_priv *bat_priv, atomic_read(&orig_node->last_ttvn) + 1); out: - if (orig_node) - batadv_orig_node_put(orig_node); + batadv_orig_node_put(orig_node); return NET_RX_SUCCESS; } diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index e1285904f885..d18740d9a22b 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -9,6 +9,7 @@ #include "main.h" +#include <linux/kref.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/skbuff.h> @@ -28,7 +29,7 @@ void batadv_tt_global_del_orig(struct batadv_priv *bat_priv, struct batadv_tt_global_entry * batadv_tt_global_hash_find(struct batadv_priv *bat_priv, const u8 *addr, unsigned short vid); -void batadv_tt_global_entry_put(struct batadv_tt_global_entry *tt_global_entry); +void batadv_tt_global_entry_release(struct kref *ref); int batadv_tt_global_hash_count(struct batadv_priv *bat_priv, const u8 *addr, unsigned short vid); struct batadv_orig_node *batadv_transtable_search(struct batadv_priv *bat_priv, @@ -55,4 +56,19 @@ bool batadv_tt_global_is_isolated(struct batadv_priv *bat_priv, int batadv_tt_cache_init(void); void batadv_tt_cache_destroy(void); +/** + * batadv_tt_global_entry_put() - decrement the tt_global_entry refcounter and + * possibly release it + * @tt_global_entry: tt_global_entry to be free'd + */ +static inline void +batadv_tt_global_entry_put(struct batadv_tt_global_entry *tt_global_entry) +{ + if (!tt_global_entry) + return; + + kref_put(&tt_global_entry->common.refcount, + batadv_tt_global_entry_release); +} + #endif /* _NET_BATMAN_ADV_TRANSLATION_TABLE_H_ */ diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c index 253f5a33a914..992773376e51 100644 --- a/net/batman-adv/tvlv.c +++ b/net/batman-adv/tvlv.c @@ -50,6 +50,9 @@ static void batadv_tvlv_handler_release(struct kref *ref) */ static void batadv_tvlv_handler_put(struct batadv_tvlv_handler *tvlv_handler) { + if (!tvlv_handler) + return; + kref_put(&tvlv_handler->refcount, batadv_tvlv_handler_release); } @@ -106,6 +109,9 @@ static void batadv_tvlv_container_release(struct kref *ref) */ static void batadv_tvlv_container_put(struct batadv_tvlv_container *tvlv) { + if (!tvlv) + return; + kref_put(&tvlv->refcount, batadv_tvlv_container_release); } @@ -438,8 +444,7 @@ int batadv_tvlv_containers_process(struct batadv_priv *bat_priv, ogm_source, orig_node, src, dst, tvlv_value, tvlv_value_cont_len); - if (tvlv_handler) - batadv_tvlv_handler_put(tvlv_handler); + batadv_tvlv_handler_put(tvlv_handler); tvlv_value = (u8 *)tvlv_value + tvlv_value_cont_len; tvlv_value_len -= tvlv_value_cont_len; } diff --git a/net/bluetooth/cmtp/cmtp.h b/net/bluetooth/cmtp/cmtp.h index c32638dddbf9..f6b9dc4e408f 100644 --- a/net/bluetooth/cmtp/cmtp.h +++ b/net/bluetooth/cmtp/cmtp.h @@ -26,7 +26,7 @@ #include <linux/types.h> #include <net/bluetooth/bluetooth.h> -#define BTNAMSIZ 18 +#define BTNAMSIZ 21 /* CMTP ioctl defines */ #define CMTPCONNADD _IOW('C', 200, int) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 2560ed2f144d..8a47a3017d61 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1343,6 +1343,12 @@ int hci_inquiry(void __user *arg) goto done; } + /* Restrict maximum inquiry length to 60 seconds */ + if (ir.length > 60) { + err = -EINVAL; + goto done; + } + hci_dev_lock(hdev); if (inquiry_cache_age(hdev) > INQUIRY_CACHE_AGE_MAX || inquiry_cache_empty(hdev) || ir.flags & IREQ_CACHE_FLUSH) { @@ -1718,6 +1724,7 @@ static void hci_pend_le_actions_clear(struct hci_dev *hdev) int hci_dev_do_close(struct hci_dev *hdev) { bool auto_off; + int err = 0; BT_DBG("%s %p", hdev->name, hdev); @@ -1727,10 +1734,18 @@ int hci_dev_do_close(struct hci_dev *hdev) hci_request_cancel_all(hdev); hci_req_sync_lock(hdev); + if (!hci_dev_test_flag(hdev, HCI_UNREGISTER) && + !hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && + test_bit(HCI_UP, &hdev->flags)) { + /* Execute vendor specific shutdown routine */ + if (hdev->shutdown) + err = hdev->shutdown(hdev); + } + if (!test_and_clear_bit(HCI_UP, &hdev->flags)) { cancel_delayed_work_sync(&hdev->cmd_timer); hci_req_sync_unlock(hdev); - return 0; + return err; } hci_leds_update_powered(hdev, false); @@ -1798,14 +1813,6 @@ int hci_dev_do_close(struct hci_dev *hdev) clear_bit(HCI_INIT, &hdev->flags); } - if (!hci_dev_test_flag(hdev, HCI_UNREGISTER) && - !hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && - test_bit(HCI_UP, &hdev->flags)) { - /* Execute vendor specific shutdown routine */ - if (hdev->shutdown) - hdev->shutdown(hdev); - } - /* flush cmd work */ flush_work(&hdev->cmd_work); @@ -1845,7 +1852,7 @@ int hci_dev_do_close(struct hci_dev *hdev) hci_req_sync_unlock(hdev); hci_dev_put(hdev); - return 0; + return err; } int hci_dev_close(__u16 dev) @@ -3751,11 +3758,18 @@ done: } /* Alloc HCI device */ -struct hci_dev *hci_alloc_dev(void) +struct hci_dev *hci_alloc_dev_priv(int sizeof_priv) { struct hci_dev *hdev; + unsigned int alloc_size; - hdev = kzalloc(sizeof(*hdev), GFP_KERNEL); + alloc_size = sizeof(*hdev); + if (sizeof_priv) { + /* Fixme: May need ALIGN-ment? */ + alloc_size += sizeof_priv; + } + + hdev = kzalloc(alloc_size, GFP_KERNEL); if (!hdev) return NULL; @@ -3869,7 +3883,7 @@ struct hci_dev *hci_alloc_dev(void) return hdev; } -EXPORT_SYMBOL(hci_alloc_dev); +EXPORT_SYMBOL(hci_alloc_dev_priv); /* Free HCI device */ void hci_free_dev(struct hci_dev *hdev) @@ -3996,14 +4010,10 @@ EXPORT_SYMBOL(hci_register_dev); /* Unregister HCI device */ void hci_unregister_dev(struct hci_dev *hdev) { - int id; - BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); hci_dev_set_flag(hdev, HCI_UNREGISTER); - id = hdev->id; - write_lock(&hci_dev_list_lock); list_del(&hdev->list); write_unlock(&hci_dev_list_lock); @@ -4038,7 +4048,14 @@ void hci_unregister_dev(struct hci_dev *hdev) } device_del(&hdev->dev); + /* Actual cleanup is deferred until hci_release_dev(). */ + hci_dev_put(hdev); +} +EXPORT_SYMBOL(hci_unregister_dev); +/* Release HCI device */ +void hci_release_dev(struct hci_dev *hdev) +{ debugfs_remove_recursive(hdev->debugfs); kfree_const(hdev->hw_info); kfree_const(hdev->fw_info); @@ -4063,11 +4080,10 @@ void hci_unregister_dev(struct hci_dev *hdev) hci_blocked_keys_clear(hdev); hci_dev_unlock(hdev); - hci_dev_put(hdev); - - ida_simple_remove(&hci_index_ida, id); + ida_simple_remove(&hci_index_ida, hdev->id); + kfree(hdev); } -EXPORT_SYMBOL(hci_unregister_dev); +EXPORT_SYMBOL(hci_release_dev); /* Suspend HCI device */ int hci_suspend_dev(struct hci_dev *hdev) diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 1c3018202564..0bca035bf2dc 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -40,6 +40,8 @@ #define ZERO_KEY "\x00\x00\x00\x00\x00\x00\x00\x00" \ "\x00\x00\x00\x00\x00\x00\x00\x00" +#define secs_to_jiffies(_secs) msecs_to_jiffies((_secs) * 1000) + /* Handle HCI Event packets */ static void hci_cc_inquiry_cancel(struct hci_dev *hdev, struct sk_buff *skb, @@ -1171,6 +1173,12 @@ static void hci_cc_le_set_random_addr(struct hci_dev *hdev, struct sk_buff *skb) bacpy(&hdev->random_addr, sent); + if (!bacmp(&hdev->rpa, sent)) { + hci_dev_clear_flag(hdev, HCI_RPA_EXPIRED); + queue_delayed_work(hdev->workqueue, &hdev->rpa_expired, + secs_to_jiffies(hdev->rpa_timeout)); + } + hci_dev_unlock(hdev); } @@ -1201,24 +1209,30 @@ static void hci_cc_le_set_adv_set_random_addr(struct hci_dev *hdev, { __u8 status = *((__u8 *) skb->data); struct hci_cp_le_set_adv_set_rand_addr *cp; - struct adv_info *adv_instance; + struct adv_info *adv; if (status) return; cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_ADV_SET_RAND_ADDR); - if (!cp) + /* Update only in case the adv instance since handle 0x00 shall be using + * HCI_OP_LE_SET_RANDOM_ADDR since that allows both extended and + * non-extended adverting. + */ + if (!cp || !cp->handle) return; hci_dev_lock(hdev); - if (!cp->handle) { - /* Store in hdev for instance 0 (Set adv and Directed advs) */ - bacpy(&hdev->random_addr, &cp->bdaddr); - } else { - adv_instance = hci_find_adv_instance(hdev, cp->handle); - if (adv_instance) - bacpy(&adv_instance->random_addr, &cp->bdaddr); + adv = hci_find_adv_instance(hdev, cp->handle); + if (adv) { + bacpy(&adv->random_addr, &cp->bdaddr); + if (!bacmp(&hdev->rpa, &cp->bdaddr)) { + adv->rpa_expired = false; + queue_delayed_work(hdev->workqueue, + &adv->rpa_expired_cb, + secs_to_jiffies(hdev->rpa_timeout)); + } } hci_dev_unlock(hdev); @@ -1277,7 +1291,9 @@ static void hci_cc_le_set_ext_adv_enable(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_cp_le_set_ext_adv_enable *cp; + struct hci_cp_ext_adv_set *set; __u8 status = *((__u8 *) skb->data); + struct adv_info *adv = NULL, *n; BT_DBG("%s status 0x%2.2x", hdev->name, status); @@ -1288,22 +1304,48 @@ static void hci_cc_le_set_ext_adv_enable(struct hci_dev *hdev, if (!cp) return; + set = (void *)cp->data; + hci_dev_lock(hdev); + if (cp->num_of_sets) + adv = hci_find_adv_instance(hdev, set->handle); + if (cp->enable) { struct hci_conn *conn; hci_dev_set_flag(hdev, HCI_LE_ADV); + if (adv) + adv->enabled = true; + conn = hci_lookup_le_connect(hdev); if (conn) queue_delayed_work(hdev->workqueue, &conn->le_conn_timeout, conn->conn_timeout); } else { + if (adv) { + adv->enabled = false; + /* If just one instance was disabled check if there are + * any other instance enabled before clearing HCI_LE_ADV + */ + list_for_each_entry_safe(adv, n, &hdev->adv_instances, + list) { + if (adv->enabled) + goto unlock; + } + } else { + /* All instances shall be considered disabled */ + list_for_each_entry_safe(adv, n, &hdev->adv_instances, + list) + adv->enabled = false; + } + hci_dev_clear_flag(hdev, HCI_LE_ADV); } +unlock: hci_dev_unlock(hdev); } @@ -2306,19 +2348,20 @@ static void hci_cs_disconnect(struct hci_dev *hdev, u8 status) conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle)); if (conn) { - u8 type = conn->type; - mgmt_disconnect_failed(hdev, &conn->dst, conn->type, conn->dst_type, status); + if (conn->type == LE_LINK) { + hdev->cur_adv_instance = conn->adv_instance; + hci_req_reenable_advertising(hdev); + } + /* If the disconnection failed for any reason, the upper layer * does not retry to disconnect in current implementation. * Hence, we need to do some basic cleanup here and re-enable * advertising if necessary. */ hci_conn_del(conn); - if (type == LE_LINK) - hci_req_reenable_advertising(hdev); } hci_dev_unlock(hdev); @@ -2844,7 +2887,6 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) struct hci_conn_params *params; struct hci_conn *conn; bool mgmt_connected; - u8 type; BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); @@ -2899,10 +2941,7 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) } } - type = conn->type; - hci_disconn_cfm(conn, ev->reason); - hci_conn_del(conn); /* The suspend notifier is waiting for all devices to disconnect so * clear the bit from pending tasks and inform the wait queue. @@ -2922,8 +2961,12 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) * or until a connection is created or until the Advertising * is timed out due to Directed Advertising." */ - if (type == LE_LINK) + if (conn->type == LE_LINK) { + hdev->cur_adv_instance = conn->adv_instance; hci_req_reenable_advertising(hdev); + } + + hci_conn_del(conn); unlock: hci_dev_unlock(hdev); @@ -3268,11 +3311,9 @@ unlock: hci_dev_unlock(hdev); } -static inline void handle_cmd_cnt_and_timer(struct hci_dev *hdev, - u16 opcode, u8 ncmd) +static inline void handle_cmd_cnt_and_timer(struct hci_dev *hdev, u8 ncmd) { - if (opcode != HCI_OP_NOP) - cancel_delayed_work(&hdev->cmd_timer); + cancel_delayed_work(&hdev->cmd_timer); if (!test_bit(HCI_RESET, &hdev->flags)) { if (ncmd) { @@ -3647,7 +3688,7 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, break; } - handle_cmd_cnt_and_timer(hdev, *opcode, ev->ncmd); + handle_cmd_cnt_and_timer(hdev, ev->ncmd); hci_req_cmd_complete(hdev, *opcode, *status, req_complete, req_complete_skb); @@ -3748,7 +3789,7 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb, break; } - handle_cmd_cnt_and_timer(hdev, *opcode, ev->ncmd); + handle_cmd_cnt_and_timer(hdev, ev->ncmd); /* Indicate request completion if the command failed. Also, if * we're not waiting for a special event and we get a success @@ -4382,6 +4423,21 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, switch (ev->status) { case 0x00: + /* The synchronous connection complete event should only be + * sent once per new connection. Receiving a successful + * complete event when the connection status is already + * BT_CONNECTED means that the device is misbehaving and sent + * multiple complete event packets for the same new connection. + * + * Registering the device more than once can corrupt kernel + * memory, hence upon detecting this invalid event, we report + * an error and ignore the packet. + */ + if (conn->state == BT_CONNECTED) { + bt_dev_err(hdev, "Ignoring connect complete event for existing connection"); + goto unlock; + } + conn->handle = __le16_to_cpu(ev->handle); conn->state = BT_CONNECTED; conn->type = ev->link_type; @@ -5104,9 +5160,64 @@ static void hci_disconn_phylink_complete_evt(struct hci_dev *hdev, } #endif +static void le_conn_update_addr(struct hci_conn *conn, bdaddr_t *bdaddr, + u8 bdaddr_type, bdaddr_t *local_rpa) +{ + if (conn->out) { + conn->dst_type = bdaddr_type; + conn->resp_addr_type = bdaddr_type; + bacpy(&conn->resp_addr, bdaddr); + + /* Check if the controller has set a Local RPA then it must be + * used instead or hdev->rpa. + */ + if (local_rpa && bacmp(local_rpa, BDADDR_ANY)) { + conn->init_addr_type = ADDR_LE_DEV_RANDOM; + bacpy(&conn->init_addr, local_rpa); + } else if (hci_dev_test_flag(conn->hdev, HCI_PRIVACY)) { + conn->init_addr_type = ADDR_LE_DEV_RANDOM; + bacpy(&conn->init_addr, &conn->hdev->rpa); + } else { + hci_copy_identity_address(conn->hdev, &conn->init_addr, + &conn->init_addr_type); + } + } else { + conn->resp_addr_type = conn->hdev->adv_addr_type; + /* Check if the controller has set a Local RPA then it must be + * used instead or hdev->rpa. + */ + if (local_rpa && bacmp(local_rpa, BDADDR_ANY)) { + conn->resp_addr_type = ADDR_LE_DEV_RANDOM; + bacpy(&conn->resp_addr, local_rpa); + } else if (conn->hdev->adv_addr_type == ADDR_LE_DEV_RANDOM) { + /* In case of ext adv, resp_addr will be updated in + * Adv Terminated event. + */ + if (!ext_adv_capable(conn->hdev)) + bacpy(&conn->resp_addr, + &conn->hdev->random_addr); + } else { + bacpy(&conn->resp_addr, &conn->hdev->bdaddr); + } + + conn->init_addr_type = bdaddr_type; + bacpy(&conn->init_addr, bdaddr); + + /* For incoming connections, set the default minimum + * and maximum connection interval. They will be used + * to check if the parameters are in range and if not + * trigger the connection update procedure. + */ + conn->le_conn_min_interval = conn->hdev->le_conn_min_interval; + conn->le_conn_max_interval = conn->hdev->le_conn_max_interval; + } +} + static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, - bdaddr_t *bdaddr, u8 bdaddr_type, u8 role, u16 handle, - u16 interval, u16 latency, u16 supervision_timeout) + bdaddr_t *bdaddr, u8 bdaddr_type, + bdaddr_t *local_rpa, u8 role, u16 handle, + u16 interval, u16 latency, + u16 supervision_timeout) { struct hci_conn_params *params; struct hci_conn *conn; @@ -5154,32 +5265,7 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, cancel_delayed_work(&conn->le_conn_timeout); } - if (!conn->out) { - /* Set the responder (our side) address type based on - * the advertising address type. - */ - conn->resp_addr_type = hdev->adv_addr_type; - if (hdev->adv_addr_type == ADDR_LE_DEV_RANDOM) { - /* In case of ext adv, resp_addr will be updated in - * Adv Terminated event. - */ - if (!ext_adv_capable(hdev)) - bacpy(&conn->resp_addr, &hdev->random_addr); - } else { - bacpy(&conn->resp_addr, &hdev->bdaddr); - } - - conn->init_addr_type = bdaddr_type; - bacpy(&conn->init_addr, bdaddr); - - /* For incoming connections, set the default minimum - * and maximum connection interval. They will be used - * to check if the parameters are in range and if not - * trigger the connection update procedure. - */ - conn->le_conn_min_interval = hdev->le_conn_min_interval; - conn->le_conn_max_interval = hdev->le_conn_max_interval; - } + le_conn_update_addr(conn, bdaddr, bdaddr_type, local_rpa); /* Lookup the identity address from the stored connection * address and address type. @@ -5236,6 +5322,13 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, conn->handle = handle; conn->state = BT_CONFIG; + /* Store current advertising instance as connection advertising instance + * when sotfware rotation is in use so it can be re-enabled when + * disconnected. + */ + if (!ext_adv_capable(hdev)) + conn->adv_instance = hdev->cur_adv_instance; + conn->le_conn_interval = interval; conn->le_conn_latency = latency; conn->le_supv_timeout = supervision_timeout; @@ -5290,7 +5383,7 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); le_conn_complete_evt(hdev, ev->status, &ev->bdaddr, ev->bdaddr_type, - ev->role, le16_to_cpu(ev->handle), + NULL, ev->role, le16_to_cpu(ev->handle), le16_to_cpu(ev->interval), le16_to_cpu(ev->latency), le16_to_cpu(ev->supervision_timeout)); @@ -5304,7 +5397,7 @@ static void hci_le_enh_conn_complete_evt(struct hci_dev *hdev, BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); le_conn_complete_evt(hdev, ev->status, &ev->bdaddr, ev->bdaddr_type, - ev->role, le16_to_cpu(ev->handle), + &ev->local_rpa, ev->role, le16_to_cpu(ev->handle), le16_to_cpu(ev->interval), le16_to_cpu(ev->latency), le16_to_cpu(ev->supervision_timeout)); @@ -5319,13 +5412,13 @@ static void hci_le_ext_adv_term_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_evt_le_ext_adv_set_term *ev = (void *) skb->data; struct hci_conn *conn; + struct adv_info *adv; BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); - if (ev->status) { - struct adv_info *adv; + adv = hci_find_adv_instance(hdev, ev->handle); - adv = hci_find_adv_instance(hdev, ev->handle); + if (ev->status) { if (!adv) return; @@ -5336,11 +5429,18 @@ static void hci_le_ext_adv_term_evt(struct hci_dev *hdev, struct sk_buff *skb) return; } + if (adv) + adv->enabled = false; + conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->conn_handle)); if (conn) { - struct adv_info *adv_instance; + /* Store handle in the connection so the correct advertising + * instance can be re-enabled when disconnected. + */ + conn->adv_instance = ev->handle; - if (hdev->adv_addr_type != ADDR_LE_DEV_RANDOM) + if (hdev->adv_addr_type != ADDR_LE_DEV_RANDOM || + bacmp(&conn->resp_addr, BDADDR_ANY)) return; if (!ev->handle) { @@ -5348,9 +5448,8 @@ static void hci_le_ext_adv_term_evt(struct hci_dev *hdev, struct sk_buff *skb) return; } - adv_instance = hci_find_adv_instance(hdev, ev->handle); - if (adv_instance) - bacpy(&conn->resp_addr, &adv_instance->random_addr); + if (adv) + bacpy(&conn->resp_addr, &adv->random_addr); } } diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 1d14adc023e9..f15626607b2d 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -2072,8 +2072,6 @@ int hci_get_random_address(struct hci_dev *hdev, bool require_privacy, * current RPA has expired then generate a new one. */ if (use_rpa) { - int to; - /* If Controller supports LL Privacy use own address type is * 0x03 */ @@ -2084,14 +2082,10 @@ int hci_get_random_address(struct hci_dev *hdev, bool require_privacy, *own_addr_type = ADDR_LE_DEV_RANDOM; if (adv_instance) { - if (!adv_instance->rpa_expired && - !bacmp(&adv_instance->random_addr, &hdev->rpa)) + if (adv_rpa_valid(adv_instance)) return 0; - - adv_instance->rpa_expired = false; } else { - if (!hci_dev_test_and_clear_flag(hdev, HCI_RPA_EXPIRED) && - !bacmp(&hdev->random_addr, &hdev->rpa)) + if (rpa_valid(hdev)) return 0; } @@ -2103,14 +2097,6 @@ int hci_get_random_address(struct hci_dev *hdev, bool require_privacy, bacpy(rand_addr, &hdev->rpa); - to = msecs_to_jiffies(hdev->rpa_timeout * 1000); - if (adv_instance) - queue_delayed_work(hdev->workqueue, - &adv_instance->rpa_expired_cb, to); - else - queue_delayed_work(hdev->workqueue, - &hdev->rpa_expired, to); - return 0; } @@ -2153,6 +2139,30 @@ void __hci_req_clear_ext_adv_sets(struct hci_request *req) hci_req_add(req, HCI_OP_LE_CLEAR_ADV_SETS, 0, NULL); } +static void set_random_addr(struct hci_request *req, bdaddr_t *rpa) +{ + struct hci_dev *hdev = req->hdev; + + /* If we're advertising or initiating an LE connection we can't + * go ahead and change the random address at this time. This is + * because the eventual initiator address used for the + * subsequently created connection will be undefined (some + * controllers use the new address and others the one we had + * when the operation started). + * + * In this kind of scenario skip the update and let the random + * address be updated at the next cycle. + */ + if (hci_dev_test_flag(hdev, HCI_LE_ADV) || + hci_lookup_le_connect(hdev)) { + bt_dev_dbg(hdev, "Deferring random address update"); + hci_dev_set_flag(hdev, HCI_RPA_EXPIRED); + return; + } + + hci_req_add(req, HCI_OP_LE_SET_RANDOM_ADDR, 6, rpa); +} + int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance) { struct hci_cp_le_set_ext_adv_params cp; @@ -2255,6 +2265,13 @@ int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance) } else { if (!bacmp(&random_addr, &hdev->random_addr)) return 0; + /* Instance 0x00 doesn't have an adv_info, instead it + * uses hdev->random_addr to track its address so + * whenever it needs to be updated this also set the + * random address since hdev->random_addr is shared with + * scan state machine. + */ + set_random_addr(req, &random_addr); } memset(&cp, 0, sizeof(cp)); @@ -2512,30 +2529,6 @@ void hci_req_clear_adv_instance(struct hci_dev *hdev, struct sock *sk, false); } -static void set_random_addr(struct hci_request *req, bdaddr_t *rpa) -{ - struct hci_dev *hdev = req->hdev; - - /* If we're advertising or initiating an LE connection we can't - * go ahead and change the random address at this time. This is - * because the eventual initiator address used for the - * subsequently created connection will be undefined (some - * controllers use the new address and others the one we had - * when the operation started). - * - * In this kind of scenario skip the update and let the random - * address be updated at the next cycle. - */ - if (hci_dev_test_flag(hdev, HCI_LE_ADV) || - hci_lookup_le_connect(hdev)) { - bt_dev_dbg(hdev, "Deferring random address update"); - hci_dev_set_flag(hdev, HCI_RPA_EXPIRED); - return; - } - - hci_req_add(req, HCI_OP_LE_SET_RANDOM_ADDR, 6, rpa); -} - int hci_update_random_address(struct hci_request *req, bool require_privacy, bool use_rpa, u8 *own_addr_type) { @@ -2547,8 +2540,6 @@ int hci_update_random_address(struct hci_request *req, bool require_privacy, * the current RPA in use, then generate a new one. */ if (use_rpa) { - int to; - /* If Controller supports LL Privacy use own address type is * 0x03 */ @@ -2558,8 +2549,7 @@ int hci_update_random_address(struct hci_request *req, bool require_privacy, else *own_addr_type = ADDR_LE_DEV_RANDOM; - if (!hci_dev_test_and_clear_flag(hdev, HCI_RPA_EXPIRED) && - !bacmp(&hdev->random_addr, &hdev->rpa)) + if (rpa_valid(hdev)) return 0; err = smp_generate_rpa(hdev, hdev->irk, &hdev->rpa); @@ -2570,9 +2560,6 @@ int hci_update_random_address(struct hci_request *req, bool require_privacy, set_random_addr(req, &hdev->rpa); - to = msecs_to_jiffies(hdev->rpa_timeout * 1000); - queue_delayed_work(hdev->workqueue, &hdev->rpa_expired, to); - return 0; } diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index b04a5a02ecf3..f1128c2134f0 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -59,6 +59,17 @@ struct hci_pinfo { char comm[TASK_COMM_LEN]; }; +static struct hci_dev *hci_hdev_from_sock(struct sock *sk) +{ + struct hci_dev *hdev = hci_pi(sk)->hdev; + + if (!hdev) + return ERR_PTR(-EBADFD); + if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) + return ERR_PTR(-EPIPE); + return hdev; +} + void hci_sock_set_flag(struct sock *sk, int nr) { set_bit(nr, &hci_pi(sk)->flags); @@ -759,19 +770,13 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event) if (event == HCI_DEV_UNREG) { struct sock *sk; - /* Detach sockets from device */ + /* Wake up sockets using this dead device */ read_lock(&hci_sk_list.lock); sk_for_each(sk, &hci_sk_list.head) { - lock_sock(sk); if (hci_pi(sk)->hdev == hdev) { - hci_pi(sk)->hdev = NULL; sk->sk_err = EPIPE; - sk->sk_state = BT_OPEN; sk->sk_state_change(sk); - - hci_dev_put(hdev); } - release_sock(sk); } read_unlock(&hci_sk_list.lock); } @@ -930,10 +935,10 @@ static int hci_sock_reject_list_del(struct hci_dev *hdev, void __user *arg) static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg) { - struct hci_dev *hdev = hci_pi(sk)->hdev; + struct hci_dev *hdev = hci_hdev_from_sock(sk); - if (!hdev) - return -EBADFD; + if (IS_ERR(hdev)) + return PTR_ERR(hdev); if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) return -EBUSY; @@ -1103,6 +1108,18 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, lock_sock(sk); + /* Allow detaching from dead device and attaching to alive device, if + * the caller wants to re-bind (instead of close) this socket in + * response to hci_sock_dev_event(HCI_DEV_UNREG) notification. + */ + hdev = hci_pi(sk)->hdev; + if (hdev && hci_dev_test_flag(hdev, HCI_UNREGISTER)) { + hci_pi(sk)->hdev = NULL; + sk->sk_state = BT_OPEN; + hci_dev_put(hdev); + } + hdev = NULL; + if (sk->sk_state == BT_BOUND) { err = -EALREADY; goto done; @@ -1379,9 +1396,9 @@ static int hci_sock_getname(struct socket *sock, struct sockaddr *addr, lock_sock(sk); - hdev = hci_pi(sk)->hdev; - if (!hdev) { - err = -EBADFD; + hdev = hci_hdev_from_sock(sk); + if (IS_ERR(hdev)) { + err = PTR_ERR(hdev); goto done; } @@ -1743,9 +1760,9 @@ static int hci_sock_sendmsg(struct socket *sock, struct msghdr *msg, goto done; } - hdev = hci_pi(sk)->hdev; - if (!hdev) { - err = -EBADFD; + hdev = hci_hdev_from_sock(sk); + if (IS_ERR(hdev)) { + err = PTR_ERR(hdev); goto done; } diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 9874844a95a9..7827639ecf5c 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -83,7 +83,9 @@ void hci_conn_del_sysfs(struct hci_conn *conn) static void bt_host_release(struct device *dev) { struct hci_dev *hdev = to_hci_dev(dev); - kfree(hdev); + + if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) + hci_release_dev(hdev); module_put(THIS_MODULE); } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 3663f880df11..cea01e275f1e 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -7204,7 +7204,7 @@ static void read_local_oob_ext_data_complete(struct hci_dev *hdev, u8 status, if (!mgmt_rp) goto done; - if (status) + if (eir_len == 0) goto send_rsp; eir_len = eir_append_data(mgmt_rp->eir, 0, EIR_CLASS_OF_DEV, @@ -7725,7 +7725,7 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev, * advertising. */ if (hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY)) - return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING, + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING, MGMT_STATUS_NOT_SUPPORTED); if (cp->instance < 1 || cp->instance > hdev->le_num_of_adv_sets) diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index ae6f80730561..2c95bb58f901 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -70,7 +70,7 @@ static void rfcomm_sk_state_change(struct rfcomm_dlc *d, int err) BT_DBG("dlc %p state %ld err %d", d, d->state, err); - spin_lock_bh(&sk->sk_lock.slock); + lock_sock(sk); if (err) sk->sk_err = err; @@ -91,7 +91,7 @@ static void rfcomm_sk_state_change(struct rfcomm_dlc *d, int err) sk->sk_state_change(sk); } - spin_unlock_bh(&sk->sk_lock.slock); + release_sock(sk); if (parent && sock_flag(sk, SOCK_ZAPPED)) { /* We have to drop DLC lock here, otherwise @@ -974,7 +974,7 @@ int rfcomm_connect_ind(struct rfcomm_session *s, u8 channel, struct rfcomm_dlc * if (!parent) return 0; - bh_lock_sock(parent); + lock_sock(parent); /* Check for backlog size */ if (sk_acceptq_is_full(parent)) { @@ -1001,7 +1001,7 @@ int rfcomm_connect_ind(struct rfcomm_session *s, u8 channel, struct rfcomm_dlc * result = 1; done: - bh_unlock_sock(parent); + release_sock(parent); if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags)) parent->sk_state_change(parent); diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index 4e095746e002..ebd78fdbd6e8 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -1127,9 +1127,10 @@ int __init rfcomm_init_ttys(void) { int error; - rfcomm_tty_driver = alloc_tty_driver(RFCOMM_TTY_PORTS); - if (!rfcomm_tty_driver) - return -ENOMEM; + rfcomm_tty_driver = tty_alloc_driver(RFCOMM_TTY_PORTS, + TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV); + if (IS_ERR(rfcomm_tty_driver)) + return PTR_ERR(rfcomm_tty_driver); rfcomm_tty_driver->driver_name = "rfcomm"; rfcomm_tty_driver->name = "rfcomm"; @@ -1137,7 +1138,6 @@ int __init rfcomm_init_ttys(void) rfcomm_tty_driver->minor_start = RFCOMM_TTY_MINOR; rfcomm_tty_driver->type = TTY_DRIVER_TYPE_SERIAL; rfcomm_tty_driver->subtype = SERIAL_TYPE_NORMAL; - rfcomm_tty_driver->flags = TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV; rfcomm_tty_driver->init_termios = tty_std_termios; rfcomm_tty_driver->init_termios.c_cflag = B9600 | CS8 | CREAD | HUPCL; rfcomm_tty_driver->init_termios.c_lflag &= ~ICANON; @@ -1146,7 +1146,7 @@ int __init rfcomm_init_ttys(void) error = tty_register_driver(rfcomm_tty_driver); if (error) { BT_ERR("Can't register RFCOMM TTY driver"); - put_tty_driver(rfcomm_tty_driver); + tty_driver_kref_put(rfcomm_tty_driver); return error; } @@ -1158,5 +1158,5 @@ int __init rfcomm_init_ttys(void) void rfcomm_cleanup_ttys(void) { tty_unregister_driver(rfcomm_tty_driver); - put_tty_driver(rfcomm_tty_driver); + tty_driver_kref_put(rfcomm_tty_driver); } diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index d9a4e88dacbb..98a881586512 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -48,6 +48,8 @@ struct sco_conn { spinlock_t lock; struct sock *sk; + struct delayed_work timeout_work; + unsigned int mtu; }; @@ -74,31 +76,47 @@ struct sco_pinfo { #define SCO_CONN_TIMEOUT (HZ * 40) #define SCO_DISCONN_TIMEOUT (HZ * 2) -static void sco_sock_timeout(struct timer_list *t) +static void sco_sock_timeout(struct work_struct *work) { - struct sock *sk = from_timer(sk, t, sk_timer); + struct sco_conn *conn = container_of(work, struct sco_conn, + timeout_work.work); + struct sock *sk; + + sco_conn_lock(conn); + sk = conn->sk; + if (sk) + sock_hold(sk); + sco_conn_unlock(conn); + + if (!sk) + return; BT_DBG("sock %p state %d", sk, sk->sk_state); - bh_lock_sock(sk); + lock_sock(sk); sk->sk_err = ETIMEDOUT; sk->sk_state_change(sk); - bh_unlock_sock(sk); - - sco_sock_kill(sk); + release_sock(sk); sock_put(sk); } static void sco_sock_set_timer(struct sock *sk, long timeout) { + if (!sco_pi(sk)->conn) + return; + BT_DBG("sock %p state %d timeout %ld", sk, sk->sk_state, timeout); - sk_reset_timer(sk, &sk->sk_timer, jiffies + timeout); + cancel_delayed_work(&sco_pi(sk)->conn->timeout_work); + schedule_delayed_work(&sco_pi(sk)->conn->timeout_work, timeout); } static void sco_sock_clear_timer(struct sock *sk) { + if (!sco_pi(sk)->conn) + return; + BT_DBG("sock %p state %d", sk, sk->sk_state); - sk_stop_timer(sk, &sk->sk_timer); + cancel_delayed_work(&sco_pi(sk)->conn->timeout_work); } /* ---- SCO connections ---- */ @@ -173,12 +191,14 @@ static void sco_conn_del(struct hci_conn *hcon, int err) if (sk) { sock_hold(sk); - bh_lock_sock(sk); + lock_sock(sk); sco_sock_clear_timer(sk); sco_chan_del(sk, err); - bh_unlock_sock(sk); - sco_sock_kill(sk); + release_sock(sk); sock_put(sk); + + /* Ensure no more work items will run before freeing conn. */ + cancel_delayed_work_sync(&conn->timeout_work); } hcon->sco_data = NULL; @@ -193,6 +213,8 @@ static void __sco_chan_add(struct sco_conn *conn, struct sock *sk, sco_pi(sk)->conn = conn; conn->sk = sk; + INIT_DELAYED_WORK(&conn->timeout_work, sco_sock_timeout); + if (parent) bt_accept_enqueue(parent, sk, true); } @@ -212,44 +234,32 @@ static int sco_chan_add(struct sco_conn *conn, struct sock *sk, return err; } -static int sco_connect(struct sock *sk) +static int sco_connect(struct hci_dev *hdev, struct sock *sk) { struct sco_conn *conn; struct hci_conn *hcon; - struct hci_dev *hdev; int err, type; BT_DBG("%pMR -> %pMR", &sco_pi(sk)->src, &sco_pi(sk)->dst); - hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); - if (!hdev) - return -EHOSTUNREACH; - - hci_dev_lock(hdev); - if (lmp_esco_capable(hdev) && !disable_esco) type = ESCO_LINK; else type = SCO_LINK; if (sco_pi(sk)->setting == BT_VOICE_TRANSPARENT && - (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev))) { - err = -EOPNOTSUPP; - goto done; - } + (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev))) + return -EOPNOTSUPP; hcon = hci_connect_sco(hdev, type, &sco_pi(sk)->dst, sco_pi(sk)->setting); - if (IS_ERR(hcon)) { - err = PTR_ERR(hcon); - goto done; - } + if (IS_ERR(hcon)) + return PTR_ERR(hcon); conn = sco_conn_add(hcon); if (!conn) { hci_conn_drop(hcon); - err = -ENOMEM; - goto done; + return -ENOMEM; } /* Update source addr of the socket */ @@ -257,7 +267,7 @@ static int sco_connect(struct sock *sk) err = sco_chan_add(conn, sk, NULL); if (err) - goto done; + return err; if (hcon->state == BT_CONNECTED) { sco_sock_clear_timer(sk); @@ -267,9 +277,6 @@ static int sco_connect(struct sock *sk) sco_sock_set_timer(sk, sk->sk_sndtimeo); } -done: - hci_dev_unlock(hdev); - hci_dev_put(hdev); return err; } @@ -394,8 +401,7 @@ static void sco_sock_cleanup_listen(struct sock *parent) */ static void sco_sock_kill(struct sock *sk) { - if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket || - sock_flag(sk, SOCK_DEAD)) + if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket) return; BT_DBG("sk %p state %d", sk, sk->sk_state); @@ -443,11 +449,10 @@ static void __sco_sock_close(struct sock *sk) /* Must be called on unlocked socket. */ static void sco_sock_close(struct sock *sk) { - sco_sock_clear_timer(sk); lock_sock(sk); + sco_sock_clear_timer(sk); __sco_sock_close(sk); release_sock(sk); - sco_sock_kill(sk); } static void sco_skb_put_cmsg(struct sk_buff *skb, struct msghdr *msg, @@ -500,8 +505,6 @@ static struct sock *sco_sock_alloc(struct net *net, struct socket *sock, sco_pi(sk)->setting = BT_VOICE_CVSD_16BIT; - timer_setup(&sk->sk_timer, sco_sock_timeout, 0); - bt_sock_link(&sco_sk_list, sk); return sk; } @@ -566,6 +569,7 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; struct sock *sk = sock->sk; + struct hci_dev *hdev; int err; BT_DBG("sk %p", sk); @@ -580,12 +584,19 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen if (sk->sk_type != SOCK_SEQPACKET) return -EINVAL; + hdev = hci_get_route(&sa->sco_bdaddr, &sco_pi(sk)->src, BDADDR_BREDR); + if (!hdev) + return -EHOSTUNREACH; + hci_dev_lock(hdev); + lock_sock(sk); /* Set destination address and psm */ bacpy(&sco_pi(sk)->dst, &sa->sco_bdaddr); - err = sco_connect(sk); + err = sco_connect(hdev, sk); + hci_dev_unlock(hdev); + hci_dev_put(hdev); if (err) goto done; @@ -773,6 +784,11 @@ static void sco_conn_defer_accept(struct hci_conn *conn, u16 setting) cp.max_latency = cpu_to_le16(0xffff); cp.retrans_effort = 0xff; break; + default: + /* use CVSD settings as fallback */ + cp.max_latency = cpu_to_le16(0xffff); + cp.retrans_effort = 0xff; + break; } hci_send_cmd(hdev, HCI_OP_ACCEPT_SYNC_CONN_REQ, @@ -1083,11 +1099,11 @@ static void sco_conn_ready(struct sco_conn *conn) BT_DBG("conn %p", conn); if (sk) { + lock_sock(sk); sco_sock_clear_timer(sk); - bh_lock_sock(sk); sk->sk_state = BT_CONNECTED; sk->sk_state_change(sk); - bh_unlock_sock(sk); + release_sock(sk); } else { sco_conn_lock(conn); @@ -1102,12 +1118,12 @@ static void sco_conn_ready(struct sco_conn *conn) return; } - bh_lock_sock(parent); + lock_sock(parent); sk = sco_sock_alloc(sock_net(parent), NULL, BTPROTO_SCO, GFP_ATOMIC, 0); if (!sk) { - bh_unlock_sock(parent); + release_sock(parent); sco_conn_unlock(conn); return; } @@ -1128,7 +1144,7 @@ static void sco_conn_ready(struct sco_conn *conn) /* Wake up parent */ parent->sk_data_ready(parent); - bh_unlock_sock(parent); + release_sock(parent); sco_conn_unlock(conn); } diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 1cc75c811e24..2eb0e55ef54d 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -7,6 +7,7 @@ #include <linux/vmalloc.h> #include <linux/etherdevice.h> #include <linux/filter.h> +#include <linux/rcupdate_trace.h> #include <linux/sched/signal.h> #include <net/bpf_sk_storage.h> #include <net/sock.h> @@ -15,6 +16,7 @@ #include <linux/error-injection.h> #include <linux/smp.h> #include <linux/sock_diag.h> +#include <net/xdp.h> #define CREATE_TRACE_POINTS #include <trace/events/bpf_test_run.h> @@ -87,17 +89,19 @@ reset: static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *retval, u32 *time, bool xdp) { - struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = { NULL }; + struct bpf_prog_array_item item = {.prog = prog}; + struct bpf_run_ctx *old_ctx; + struct bpf_cg_run_ctx run_ctx; struct bpf_test_timer t = { NO_MIGRATE }; enum bpf_cgroup_storage_type stype; int ret; for_each_cgroup_storage_type(stype) { - storage[stype] = bpf_cgroup_storage_alloc(prog, stype); - if (IS_ERR(storage[stype])) { - storage[stype] = NULL; + item.cgroup_storage[stype] = bpf_cgroup_storage_alloc(prog, stype); + if (IS_ERR(item.cgroup_storage[stype])) { + item.cgroup_storage[stype] = NULL; for_each_cgroup_storage_type(stype) - bpf_cgroup_storage_free(storage[stype]); + bpf_cgroup_storage_free(item.cgroup_storage[stype]); return -ENOMEM; } } @@ -106,22 +110,19 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, repeat = 1; bpf_test_timer_enter(&t); + old_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); do { - ret = bpf_cgroup_storage_set(storage); - if (ret) - break; - + run_ctx.prog_item = &item; if (xdp) *retval = bpf_prog_run_xdp(prog, ctx); else - *retval = BPF_PROG_RUN(prog, ctx); - - bpf_cgroup_storage_unset(); + *retval = bpf_prog_run(prog, ctx); } while (bpf_test_timer_continue(&t, repeat, &ret, time)); + bpf_reset_run_ctx(old_ctx); bpf_test_timer_leave(&t); for_each_cgroup_storage_type(stype) - bpf_cgroup_storage_free(storage[stype]); + bpf_cgroup_storage_free(item.cgroup_storage[stype]); return ret; } @@ -326,7 +327,7 @@ __bpf_prog_test_run_raw_tp(void *data) struct bpf_raw_tp_test_run_info *info = data; rcu_read_lock(); - info->retval = BPF_PROG_RUN(info->prog, info->ctx); + info->retval = bpf_prog_run(info->prog, info->ctx); rcu_read_unlock(); } @@ -687,6 +688,64 @@ out: return ret; } +static int xdp_convert_md_to_buff(struct xdp_md *xdp_md, struct xdp_buff *xdp) +{ + unsigned int ingress_ifindex, rx_queue_index; + struct netdev_rx_queue *rxqueue; + struct net_device *device; + + if (!xdp_md) + return 0; + + if (xdp_md->egress_ifindex != 0) + return -EINVAL; + + ingress_ifindex = xdp_md->ingress_ifindex; + rx_queue_index = xdp_md->rx_queue_index; + + if (!ingress_ifindex && rx_queue_index) + return -EINVAL; + + if (ingress_ifindex) { + device = dev_get_by_index(current->nsproxy->net_ns, + ingress_ifindex); + if (!device) + return -ENODEV; + + if (rx_queue_index >= device->real_num_rx_queues) + goto free_dev; + + rxqueue = __netif_get_rx_queue(device, rx_queue_index); + + if (!xdp_rxq_info_is_reg(&rxqueue->xdp_rxq)) + goto free_dev; + + xdp->rxq = &rxqueue->xdp_rxq; + /* The device is now tracked in the xdp->rxq for later + * dev_put() + */ + } + + xdp->data = xdp->data_meta + xdp_md->data; + return 0; + +free_dev: + dev_put(device); + return -EINVAL; +} + +static void xdp_convert_buff_to_md(struct xdp_buff *xdp, struct xdp_md *xdp_md) +{ + if (!xdp_md) + return; + + xdp_md->data = xdp->data - xdp->data_meta; + xdp_md->data_end = xdp->data_end - xdp->data_meta; + + if (xdp_md->ingress_ifindex) + dev_put(xdp->rxq->dev); +} + int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { @@ -697,38 +756,73 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, struct netdev_rx_queue *rxqueue; struct xdp_buff xdp = {}; u32 retval, duration; + struct xdp_md *ctx; u32 max_data_sz; void *data; - int ret; + int ret = -EINVAL; if (prog->expected_attach_type == BPF_XDP_DEVMAP || prog->expected_attach_type == BPF_XDP_CPUMAP) return -EINVAL; - if (kattr->test.ctx_in || kattr->test.ctx_out) - return -EINVAL; + + ctx = bpf_ctx_init(kattr, sizeof(struct xdp_md)); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + if (ctx) { + /* There can't be user provided data before the meta data */ + if (ctx->data_meta || ctx->data_end != size || + ctx->data > ctx->data_end || + unlikely(xdp_metalen_invalid(ctx->data))) + goto free_ctx; + /* Meta data is allocated from the headroom */ + headroom -= ctx->data; + } /* XDP have extra tailroom as (most) drivers use full page */ max_data_sz = 4096 - headroom - tailroom; data = bpf_test_init(kattr, max_data_sz, headroom, tailroom); - if (IS_ERR(data)) - return PTR_ERR(data); + if (IS_ERR(data)) { + ret = PTR_ERR(data); + goto free_ctx; + } rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0); xdp_init_buff(&xdp, headroom + max_data_sz + tailroom, &rxqueue->xdp_rxq); xdp_prepare_buff(&xdp, data, headroom, size, true); + ret = xdp_convert_md_to_buff(ctx, &xdp); + if (ret) + goto free_data; + bpf_prog_change_xdp(NULL, prog); ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true); + /* We convert the xdp_buff back to an xdp_md before checking the return + * code so the reference count of any held netdevice will be decremented + * even if the test run failed. + */ + xdp_convert_buff_to_md(&xdp, ctx); if (ret) goto out; - if (xdp.data != data + headroom || xdp.data_end != xdp.data + size) - size = xdp.data_end - xdp.data; - ret = bpf_test_finish(kattr, uattr, xdp.data, size, retval, duration); + + if (xdp.data_meta != data + headroom || + xdp.data_end != xdp.data_meta + size) + size = xdp.data_end - xdp.data_meta; + + ret = bpf_test_finish(kattr, uattr, xdp.data_meta, size, retval, + duration); + if (!ret) + ret = bpf_ctx_finish(kattr, uattr, ctx, + sizeof(struct xdp_md)); + out: bpf_prog_change_xdp(prog, NULL); +free_data: kfree(data); +free_ctx: + kfree(ctx); return ret; } @@ -895,7 +989,7 @@ int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kat bpf_test_timer_enter(&t); do { ctx.selected_sk = NULL; - retval = BPF_PROG_SK_LOOKUP_RUN_ARRAY(progs, ctx, BPF_PROG_RUN); + retval = BPF_PROG_SK_LOOKUP_RUN_ARRAY(progs, ctx, bpf_prog_run); } while (bpf_test_timer_continue(&t, repeat, &ret, &duration)); bpf_test_timer_leave(&t); @@ -951,7 +1045,10 @@ int bpf_prog_test_run_syscall(struct bpf_prog *prog, goto out; } } + + rcu_read_lock_trace(); retval = bpf_prog_run_pin_on_cpu(prog, ctx); + rcu_read_unlock_trace(); if (copy_to_user(&uattr->test.retval, &retval, sizeof(u32))) { err = -EFAULT; diff --git a/net/bridge/br.c b/net/bridge/br.c index ef743f94254d..d3a32c6813e0 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -201,6 +201,48 @@ static struct notifier_block br_switchdev_notifier = { .notifier_call = br_switchdev_event, }; +/* called under rtnl_mutex */ +static int br_switchdev_blocking_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr); + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); + struct switchdev_notifier_brport_info *brport_info; + const struct switchdev_brport *b; + struct net_bridge_port *p; + int err = NOTIFY_DONE; + + p = br_port_get_rtnl(dev); + if (!p) + goto out; + + switch (event) { + case SWITCHDEV_BRPORT_OFFLOADED: + brport_info = ptr; + b = &brport_info->brport; + + err = br_switchdev_port_offload(p, b->dev, b->ctx, + b->atomic_nb, b->blocking_nb, + b->tx_fwd_offload, extack); + err = notifier_from_errno(err); + break; + case SWITCHDEV_BRPORT_UNOFFLOADED: + brport_info = ptr; + b = &brport_info->brport; + + br_switchdev_port_unoffload(p, b->ctx, b->atomic_nb, + b->blocking_nb); + break; + } + +out: + return err; +} + +static struct notifier_block br_switchdev_blocking_notifier = { + .notifier_call = br_switchdev_blocking_event, +}; + /* br_boolopt_toggle - change user-controlled boolean option * * @br: bridge device @@ -214,17 +256,22 @@ static struct notifier_block br_switchdev_notifier = { int br_boolopt_toggle(struct net_bridge *br, enum br_boolopt_id opt, bool on, struct netlink_ext_ack *extack) { + int err = 0; + switch (opt) { case BR_BOOLOPT_NO_LL_LEARN: br_opt_toggle(br, BROPT_NO_LL_LEARN, on); break; + case BR_BOOLOPT_MCAST_VLAN_SNOOPING: + err = br_multicast_toggle_vlan_snooping(br, on, extack); + break; default: /* shouldn't be called with unsupported options */ WARN_ON(1); break; } - return 0; + return err; } int br_boolopt_get(const struct net_bridge *br, enum br_boolopt_id opt) @@ -232,6 +279,8 @@ int br_boolopt_get(const struct net_bridge *br, enum br_boolopt_id opt) switch (opt) { case BR_BOOLOPT_NO_LL_LEARN: return br_opt_get(br, BROPT_NO_LL_LEARN); + case BR_BOOLOPT_MCAST_VLAN_SNOOPING: + return br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED); default: /* shouldn't be called with unsupported options */ WARN_ON(1); @@ -348,11 +397,15 @@ static int __init br_init(void) if (err) goto err_out4; - err = br_netlink_init(); + err = register_switchdev_blocking_notifier(&br_switchdev_blocking_notifier); if (err) goto err_out5; - brioctl_set(br_ioctl_deviceless_stub); + err = br_netlink_init(); + if (err) + goto err_out6; + + brioctl_set(br_ioctl_stub); #if IS_ENABLED(CONFIG_ATM_LANE) br_fdb_test_addr_hook = br_fdb_test_addr; @@ -366,6 +419,8 @@ static int __init br_init(void) return 0; +err_out6: + unregister_switchdev_blocking_notifier(&br_switchdev_blocking_notifier); err_out5: unregister_switchdev_notifier(&br_switchdev_notifier); err_out4: @@ -385,6 +440,7 @@ static void __exit br_deinit(void) { stp_proto_unregister(&br_stp_proto); br_netlink_fini(); + unregister_switchdev_blocking_notifier(&br_switchdev_blocking_notifier); unregister_switchdev_notifier(&br_switchdev_notifier); unregister_netdevice_notifier(&br_device_notifier); brioctl_set(NULL); diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index e8b626cc6bfd..8d6bab244c4a 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -27,11 +27,14 @@ EXPORT_SYMBOL_GPL(nf_br_ops); /* net device transmit always called with BH disabled */ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) { + struct net_bridge_mcast_port *pmctx_null = NULL; struct net_bridge *br = netdev_priv(dev); + struct net_bridge_mcast *brmctx = &br->multicast_ctx; struct net_bridge_fdb_entry *dst; struct net_bridge_mdb_entry *mdst; const struct nf_br_ops *nf_ops; u8 state = BR_STATE_FORWARDING; + struct net_bridge_vlan *vlan; const unsigned char *dest; u16 vid = 0; @@ -53,7 +56,8 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) skb_reset_mac_header(skb); skb_pull(skb, ETH_HLEN); - if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid, &state)) + if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid, + &state, &vlan)) goto out; if (IS_ENABLED(CONFIG_INET) && @@ -82,15 +86,15 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) br_flood(br, skb, BR_PKT_MULTICAST, false, true); goto out; } - if (br_multicast_rcv(br, NULL, skb, vid)) { + if (br_multicast_rcv(&brmctx, &pmctx_null, vlan, skb, vid)) { kfree_skb(skb); goto out; } - mdst = br_mdb_get(br, skb, vid); + mdst = br_mdb_get(brmctx, skb, vid); if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) && - br_multicast_querier_exists(br, eth_hdr(skb), mdst)) - br_multicast_flood(mdst, skb, false, true); + br_multicast_querier_exists(brmctx, eth_hdr(skb), mdst)) + br_multicast_flood(mdst, skb, brmctx, false, true); else br_flood(br, skb, BR_PKT_MULTICAST, false, true); } else if ((dst = br_fdb_find_rcu(br, dest, vid)) != NULL) { @@ -450,7 +454,7 @@ static const struct net_device_ops br_netdev_ops = { .ndo_set_rx_mode = br_dev_set_multicast_list, .ndo_change_rx_flags = br_dev_change_rx_flags, .ndo_change_mtu = br_change_mtu, - .ndo_do_ioctl = br_dev_ioctl, + .ndo_siocdevprivate = br_dev_siocdevprivate, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_netpoll_setup = br_netpoll_setup, .ndo_netpoll_cleanup = br_netpoll_cleanup, diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index a16191dcaed1..46812b659710 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -732,11 +732,11 @@ static inline size_t fdb_nlmsg_size(void) + nla_total_size(sizeof(u8)); /* NFEA_ACTIVITY_NOTIFY */ } -static int br_fdb_replay_one(struct notifier_block *nb, +static int br_fdb_replay_one(struct net_bridge *br, struct notifier_block *nb, const struct net_bridge_fdb_entry *fdb, - struct net_device *dev, unsigned long action, - const void *ctx) + unsigned long action, const void *ctx) { + const struct net_bridge_port *p = READ_ONCE(fdb->dst); struct switchdev_notifier_fdb_info item; int err; @@ -745,25 +745,25 @@ static int br_fdb_replay_one(struct notifier_block *nb, item.added_by_user = test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags); item.offloaded = test_bit(BR_FDB_OFFLOADED, &fdb->flags); item.is_local = test_bit(BR_FDB_LOCAL, &fdb->flags); - item.info.dev = dev; + item.info.dev = (!p || item.is_local) ? br->dev : p->dev; item.info.ctx = ctx; err = nb->notifier_call(nb, action, &item); return notifier_to_errno(err); } -int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, - const void *ctx, bool adding, struct notifier_block *nb) +int br_fdb_replay(const struct net_device *br_dev, const void *ctx, bool adding, + struct notifier_block *nb) { struct net_bridge_fdb_entry *fdb; struct net_bridge *br; unsigned long action; int err = 0; - if (!netif_is_bridge_master(br_dev)) - return -EINVAL; + if (!nb) + return 0; - if (!netif_is_bridge_port(dev) && !netif_is_bridge_master(dev)) + if (!netif_is_bridge_master(br_dev)) return -EINVAL; br = netdev_priv(br_dev); @@ -776,14 +776,7 @@ int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, rcu_read_lock(); hlist_for_each_entry_rcu(fdb, &br->fdb_list, fdb_node) { - const struct net_bridge_port *dst = READ_ONCE(fdb->dst); - struct net_device *dst_dev; - - dst_dev = dst ? dst->dev : br->dev; - if (dst_dev && dst_dev != dev) - continue; - - err = br_fdb_replay_one(nb, fdb, dst_dev, action, ctx); + err = br_fdb_replay_one(br, nb, fdb, action, ctx); if (err) break; } @@ -792,7 +785,6 @@ int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, return err; } -EXPORT_SYMBOL_GPL(br_fdb_replay); static void fdb_notify(struct net_bridge *br, const struct net_bridge_fdb_entry *fdb, int type, @@ -1019,7 +1011,8 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, - u16 nlh_flags, u16 vid, struct nlattr *nfea_tb[]) + u16 nlh_flags, u16 vid, struct nlattr *nfea_tb[], + struct netlink_ext_ack *extack) { int err = 0; @@ -1038,6 +1031,11 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, rcu_read_unlock(); local_bh_enable(); } else if (ndm->ndm_flags & NTF_EXT_LEARNED) { + if (!p && !(ndm->ndm_state & NUD_PERMANENT)) { + NL_SET_ERR_MSG_MOD(extack, + "FDB entry towards bridge must be permanent"); + return -EINVAL; + } err = br_fdb_external_learn_add(br, p, addr, vid, true); } else { spin_lock_bh(&br->hash_lock); @@ -1110,9 +1108,11 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], } /* VID was specified, so use it. */ - err = __br_fdb_add(ndm, br, p, addr, nlh_flags, vid, nfea_tb); + err = __br_fdb_add(ndm, br, p, addr, nlh_flags, vid, nfea_tb, + extack); } else { - err = __br_fdb_add(ndm, br, p, addr, nlh_flags, 0, nfea_tb); + err = __br_fdb_add(ndm, br, p, addr, nlh_flags, 0, nfea_tb, + extack); if (err || !vg || !vg->num_vlans) goto out; @@ -1124,7 +1124,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], if (!br_vlan_should_use(v)) continue; err = __br_fdb_add(ndm, br, p, addr, nlh_flags, v->vid, - nfea_tb); + nfea_tb, extack); if (err) goto out; } @@ -1281,6 +1281,10 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, if (swdev_notify) flags |= BIT(BR_FDB_ADDED_BY_USER); + + if (!p) + flags |= BIT(BR_FDB_LOCAL); + fdb = fdb_create(br, p, addr, vid, flags); if (!fdb) { err = -ENOMEM; @@ -1307,6 +1311,9 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, if (swdev_notify) set_bit(BR_FDB_ADDED_BY_USER, &fdb->flags); + if (!p) + set_bit(BR_FDB_LOCAL, &fdb->flags); + if (modified) fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify); } diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 07856362538f..ec646656dbf1 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -48,6 +48,8 @@ int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb skb_set_network_header(skb, depth); } + br_switchdev_frame_set_offload_fwd_mark(skb); + dev_queue_xmit(skb); return 0; @@ -76,6 +78,11 @@ static void __br_forward(const struct net_bridge_port *to, struct net *net; int br_hook; + /* Mark the skb for forwarding offload early so that br_handle_vlan() + * can know whether to pop the VLAN header on egress or keep it. + */ + nbp_switchdev_frame_mark_tx_fwd_offload(to, skb); + vg = nbp_vlan_group_rcu(to); skb = br_handle_vlan(to->br, to, vg, skb); if (!skb) @@ -174,6 +181,8 @@ static struct net_bridge_port *maybe_deliver( if (!should_deliver(p, skb)) return prev; + nbp_switchdev_frame_mark_tx_fwd_to_hwdom(p, skb); + if (!prev) goto out; @@ -267,20 +276,19 @@ static void maybe_deliver_addr(struct net_bridge_port *p, struct sk_buff *skb, /* called with rcu_read_lock */ void br_multicast_flood(struct net_bridge_mdb_entry *mdst, struct sk_buff *skb, + struct net_bridge_mcast *brmctx, bool local_rcv, bool local_orig) { - struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev; - struct net_bridge *br = netdev_priv(dev); struct net_bridge_port *prev = NULL; struct net_bridge_port_group *p; bool allow_mode_include = true; struct hlist_node *rp; - rp = br_multicast_get_first_rport_node(br, skb); + rp = br_multicast_get_first_rport_node(brmctx, skb); if (mdst) { p = rcu_dereference(mdst->ports); - if (br_multicast_should_handle_mode(br, mdst->addr.proto) && + if (br_multicast_should_handle_mode(brmctx, mdst->addr.proto) && br_multicast_is_star_g(&mdst->addr)) allow_mode_include = false; } else { diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 6e4a32354a13..4a02f8bb278a 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -456,7 +456,7 @@ int br_add_bridge(struct net *net, const char *name) dev_net_set(dev, net); dev->rtnl_link_ops = &br_link_ops; - res = register_netdev(dev); + res = register_netdevice(dev); if (res) free_netdev(dev); return res; @@ -467,7 +467,6 @@ int br_del_bridge(struct net *net, const char *name) struct net_device *dev; int ret = 0; - rtnl_lock(); dev = __dev_get_by_name(net, name); if (dev == NULL) ret = -ENXIO; /* Could not find device */ @@ -485,7 +484,6 @@ int br_del_bridge(struct net *net, const char *name) else br_dev_delete(dev, NULL); - rtnl_unlock(); return ret; } @@ -616,6 +614,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, err = dev_set_allmulti(dev, 1); if (err) { + br_multicast_del_port(p); kfree(p); /* kobject not yet init'd, manually free */ goto err1; } @@ -643,10 +642,6 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, if (err) goto err5; - err = nbp_switchdev_mark_set(p); - if (err) - goto err6; - dev_disable_lro(dev); list_add_rcu(&p->list, &br->port_list); @@ -684,13 +679,13 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, */ err = dev_pre_changeaddr_notify(br->dev, dev->dev_addr, extack); if (err) - goto err7; + goto err6; } err = nbp_vlan_init(p, extack); if (err) { netdev_err(dev, "failed to initialize vlan filtering on this port\n"); - goto err7; + goto err6; } spin_lock_bh(&br->lock); @@ -713,13 +708,12 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, return 0; -err7: +err6: if (fdb_synced) br_fdb_unsync_static(br, p); list_del_rcu(&p->list); br_fdb_delete_by_port(br, p, 0, 1); nbp_update_port_count(br); -err6: netdev_upper_dev_unlink(dev, br->dev); err5: dev->priv_flags &= ~IFF_BRIDGE_PORT; @@ -729,6 +723,7 @@ err4: err3: sysfs_remove_link(br->ifobj, p->dev->name); err2: + br_multicast_del_port(p); kobject_put(&p->kobj); dev_set_allmulti(dev, -1); err1: diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 1f506309efa8..b50382f957c1 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -69,8 +69,11 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb struct net_bridge_port *p = br_port_get_rcu(skb->dev); enum br_pkt_type pkt_type = BR_PKT_UNICAST; struct net_bridge_fdb_entry *dst = NULL; + struct net_bridge_mcast_port *pmctx; struct net_bridge_mdb_entry *mdst; bool local_rcv, mcast_hit = false; + struct net_bridge_mcast *brmctx; + struct net_bridge_vlan *vlan; struct net_bridge *br; u16 vid = 0; u8 state; @@ -78,9 +81,11 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if (!p || p->state == BR_STATE_DISABLED) goto drop; + brmctx = &p->br->multicast_ctx; + pmctx = &p->multicast_ctx; state = p->state; if (!br_allowed_ingress(p->br, nbp_vlan_group_rcu(p), skb, &vid, - &state)) + &state, &vlan)) goto out; nbp_switchdev_frame_mark(p, skb); @@ -98,7 +103,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb local_rcv = true; } else { pkt_type = BR_PKT_MULTICAST; - if (br_multicast_rcv(br, p, skb, vid)) + if (br_multicast_rcv(&brmctx, &pmctx, vlan, skb, vid)) goto drop; } } @@ -128,11 +133,11 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb switch (pkt_type) { case BR_PKT_MULTICAST: - mdst = br_mdb_get(br, skb, vid); + mdst = br_mdb_get(brmctx, skb, vid); if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) && - br_multicast_querier_exists(br, eth_hdr(skb), mdst)) { + br_multicast_querier_exists(brmctx, eth_hdr(skb), mdst)) { if ((mdst && mdst->host_joined) || - br_multicast_is_router(br, skb)) { + br_multicast_is_router(brmctx, skb)) { local_rcv = true; br->dev->stats.multicast++; } @@ -162,7 +167,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if (!mcast_hit) br_flood(br, skb, pkt_type, local_rcv, false); else - br_multicast_flood(mdst, skb, local_rcv, false); + br_multicast_flood(mdst, skb, brmctx, local_rcv, false); } if (local_rcv) @@ -289,11 +294,8 @@ static rx_handler_result_t br_handle_frame(struct sk_buff **pskb) memset(skb->cb, 0, sizeof(struct br_input_skb_cb)); p = br_port_get_rcu(skb->dev); - if (p->flags & BR_VLAN_TUNNEL) { - if (br_handle_ingress_vlan_tunnel(skb, p, - nbp_vlan_group_rcu(p))) - goto drop; - } + if (p->flags & BR_VLAN_TUNNEL) + br_handle_ingress_vlan_tunnel(skb, p, nbp_vlan_group_rcu(p)); if (unlikely(is_link_local_ether_addr(dest))) { u16 fwd_mask = p->br->group_fwd_mask_required; diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c index 2db800fc27ca..793b0db9d9a3 100644 --- a/net/bridge/br_ioctl.c +++ b/net/bridge/br_ioctl.c @@ -106,15 +106,32 @@ static int add_del_if(struct net_bridge *br, int ifindex, int isadd) * This interface is deprecated because it was too difficult * to do the translation for 32/64bit ioctl compatibility. */ -static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) +int br_dev_siocdevprivate(struct net_device *dev, struct ifreq *rq, void __user *data, int cmd) { struct net_bridge *br = netdev_priv(dev); struct net_bridge_port *p = NULL; unsigned long args[4]; + void __user *argp; int ret = -EOPNOTSUPP; - if (copy_from_user(args, rq->ifr_data, sizeof(args))) - return -EFAULT; + if (in_compat_syscall()) { + unsigned int cargs[4]; + + if (copy_from_user(cargs, data, sizeof(cargs))) + return -EFAULT; + + args[0] = cargs[0]; + args[1] = cargs[1]; + args[2] = cargs[2]; + args[3] = cargs[3]; + + argp = compat_ptr(args[1]); + } else { + if (copy_from_user(args, data, sizeof(args))) + return -EFAULT; + + argp = (void __user *)args[1]; + } switch (args[0]) { case BRCTL_ADD_IF: @@ -171,7 +188,7 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) return -ENOMEM; get_port_ifindices(br, indices, num); - if (copy_to_user((void __user *)args[1], indices, num*sizeof(int))) + if (copy_to_user(argp, indices, num * sizeof(int))) num = -EFAULT; kfree(indices); return num; @@ -232,7 +249,7 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) rcu_read_unlock(); - if (copy_to_user((void __user *)args[1], &p, sizeof(p))) + if (copy_to_user(argp, &p, sizeof(p))) return -EFAULT; return 0; @@ -282,8 +299,7 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) } case BRCTL_GET_FDB_ENTRIES: - return get_fdb_entries(br, (void __user *)args[1], - args[2], args[3]); + return get_fdb_entries(br, argp, args[2], args[3]); } if (!ret) { @@ -320,7 +336,7 @@ static int old_deviceless(struct net *net, void __user *uarg) args[2] = get_bridge_ifindices(net, indices, args[2]); - ret = copy_to_user((void __user *)args[1], indices, args[2]*sizeof(int)) + ret = copy_to_user(uarg, indices, args[2]*sizeof(int)) ? -EFAULT : args[2]; kfree(indices); @@ -350,48 +366,47 @@ static int old_deviceless(struct net *net, void __user *uarg) return -EOPNOTSUPP; } -int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, void __user *uarg) +int br_ioctl_stub(struct net *net, struct net_bridge *br, unsigned int cmd, + struct ifreq *ifr, void __user *uarg) { + int ret = -EOPNOTSUPP; + + rtnl_lock(); + switch (cmd) { case SIOCGIFBR: case SIOCSIFBR: - return old_deviceless(net, uarg); - + ret = old_deviceless(net, uarg); + break; case SIOCBRADDBR: case SIOCBRDELBR: { char buf[IFNAMSIZ]; - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) - return -EPERM; + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) { + ret = -EPERM; + break; + } - if (copy_from_user(buf, uarg, IFNAMSIZ)) - return -EFAULT; + if (copy_from_user(buf, uarg, IFNAMSIZ)) { + ret = -EFAULT; + break; + } buf[IFNAMSIZ-1] = 0; if (cmd == SIOCBRADDBR) - return br_add_bridge(net, buf); - - return br_del_bridge(net, buf); - } + ret = br_add_bridge(net, buf); + else + ret = br_del_bridge(net, buf); } - return -EOPNOTSUPP; -} - -int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) -{ - struct net_bridge *br = netdev_priv(dev); - - switch (cmd) { - case SIOCDEVPRIVATE: - return old_dev_ioctl(dev, rq, cmd); - + break; case SIOCBRADDIF: case SIOCBRDELIF: - return add_del_if(br, rq->ifr_ifindex, cmd == SIOCBRADDIF); - + ret = add_del_if(br, ifr->ifr_ifindex, cmd == SIOCBRADDIF); + break; } - br_debug(br, "Bridge does not support ioctl 0x%x\n", cmd); - return -EOPNOTSUPP; + rtnl_unlock(); + + return ret; } diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 17a720b4473f..0281453f7766 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -16,57 +16,89 @@ #include "br_private.h" -static bool br_rports_have_mc_router(struct net_bridge *br) +static bool +br_ip4_rports_get_timer(struct net_bridge_mcast_port *pmctx, + unsigned long *timer) +{ + *timer = br_timer_value(&pmctx->ip4_mc_router_timer); + return !hlist_unhashed(&pmctx->ip4_rlist); +} + +static bool +br_ip6_rports_get_timer(struct net_bridge_mcast_port *pmctx, + unsigned long *timer) { #if IS_ENABLED(CONFIG_IPV6) - return !hlist_empty(&br->ip4_mc_router_list) || - !hlist_empty(&br->ip6_mc_router_list); + *timer = br_timer_value(&pmctx->ip6_mc_router_timer); + return !hlist_unhashed(&pmctx->ip6_rlist); #else - return !hlist_empty(&br->ip4_mc_router_list); + *timer = 0; + return false; #endif } -static bool -br_ip4_rports_get_timer(struct net_bridge_port *port, unsigned long *timer) +static size_t __br_rports_one_size(void) { - *timer = br_timer_value(&port->ip4_mc_router_timer); - return !hlist_unhashed(&port->ip4_rlist); + return nla_total_size(sizeof(u32)) + /* MDBA_ROUTER_PORT */ + nla_total_size(sizeof(u32)) + /* MDBA_ROUTER_PATTR_TIMER */ + nla_total_size(sizeof(u8)) + /* MDBA_ROUTER_PATTR_TYPE */ + nla_total_size(sizeof(u32)) + /* MDBA_ROUTER_PATTR_INET_TIMER */ + nla_total_size(sizeof(u32)) + /* MDBA_ROUTER_PATTR_INET6_TIMER */ + nla_total_size(sizeof(u32)); /* MDBA_ROUTER_PATTR_VID */ } -static bool -br_ip6_rports_get_timer(struct net_bridge_port *port, unsigned long *timer) +size_t br_rports_size(const struct net_bridge_mcast *brmctx) { + struct net_bridge_mcast_port *pmctx; + size_t size = nla_total_size(0); /* MDBA_ROUTER */ + + rcu_read_lock(); + hlist_for_each_entry_rcu(pmctx, &brmctx->ip4_mc_router_list, + ip4_rlist) + size += __br_rports_one_size(); + #if IS_ENABLED(CONFIG_IPV6) - *timer = br_timer_value(&port->ip6_mc_router_timer); - return !hlist_unhashed(&port->ip6_rlist); -#else - *timer = 0; - return false; + hlist_for_each_entry_rcu(pmctx, &brmctx->ip6_mc_router_list, + ip6_rlist) + size += __br_rports_one_size(); #endif + rcu_read_unlock(); + + return size; } -static int br_rports_fill_info(struct sk_buff *skb, struct netlink_callback *cb, - struct net_device *dev) +int br_rports_fill_info(struct sk_buff *skb, + const struct net_bridge_mcast *brmctx) { - struct net_bridge *br = netdev_priv(dev); + u16 vid = brmctx->vlan ? brmctx->vlan->vid : 0; bool have_ip4_mc_rtr, have_ip6_mc_rtr; unsigned long ip4_timer, ip6_timer; struct nlattr *nest, *port_nest; struct net_bridge_port *p; - if (!br->multicast_router) - return 0; - - if (!br_rports_have_mc_router(br)) + if (!brmctx->multicast_router || !br_rports_have_mc_router(brmctx)) return 0; nest = nla_nest_start_noflag(skb, MDBA_ROUTER); if (nest == NULL) return -EMSGSIZE; - list_for_each_entry_rcu(p, &br->port_list, list) { - have_ip4_mc_rtr = br_ip4_rports_get_timer(p, &ip4_timer); - have_ip6_mc_rtr = br_ip6_rports_get_timer(p, &ip6_timer); + list_for_each_entry_rcu(p, &brmctx->br->port_list, list) { + struct net_bridge_mcast_port *pmctx; + + if (vid) { + struct net_bridge_vlan *v; + + v = br_vlan_find(nbp_vlan_group(p), vid); + if (!v) + continue; + pmctx = &v->port_mcast_ctx; + } else { + pmctx = &p->multicast_ctx; + } + + have_ip4_mc_rtr = br_ip4_rports_get_timer(pmctx, &ip4_timer); + have_ip6_mc_rtr = br_ip6_rports_get_timer(pmctx, &ip6_timer); if (!have_ip4_mc_rtr && !have_ip6_mc_rtr) continue; @@ -79,13 +111,14 @@ static int br_rports_fill_info(struct sk_buff *skb, struct netlink_callback *cb, nla_put_u32(skb, MDBA_ROUTER_PATTR_TIMER, max(ip4_timer, ip6_timer)) || nla_put_u8(skb, MDBA_ROUTER_PATTR_TYPE, - p->multicast_router) || + p->multicast_ctx.multicast_router) || (have_ip4_mc_rtr && nla_put_u32(skb, MDBA_ROUTER_PATTR_INET_TIMER, ip4_timer)) || (have_ip6_mc_rtr && nla_put_u32(skb, MDBA_ROUTER_PATTR_INET6_TIMER, - ip6_timer))) { + ip6_timer)) || + (vid && nla_put_u16(skb, MDBA_ROUTER_PATTR_VID, vid))) { nla_nest_cancel(skb, port_nest); goto fail; } @@ -240,7 +273,7 @@ static int __mdb_fill_info(struct sk_buff *skb, switch (mp->addr.proto) { case htons(ETH_P_IP): - dump_srcs_mode = !!(mp->br->multicast_igmp_version == 3); + dump_srcs_mode = !!(mp->br->multicast_ctx.multicast_igmp_version == 3); if (mp->addr.src.ip4) { if (nla_put_in_addr(skb, MDBA_MDB_EATTR_SOURCE, mp->addr.src.ip4)) @@ -250,7 +283,7 @@ static int __mdb_fill_info(struct sk_buff *skb, break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): - dump_srcs_mode = !!(mp->br->multicast_mld_version == 2); + dump_srcs_mode = !!(mp->br->multicast_ctx.multicast_mld_version == 2); if (!ipv6_addr_any(&mp->addr.src.ip6)) { if (nla_put_in6_addr(skb, MDBA_MDB_EATTR_SOURCE, &mp->addr.src.ip6)) @@ -390,6 +423,7 @@ static int br_mdb_dump(struct sk_buff *skb, struct netlink_callback *cb) for_each_netdev_rcu(net, dev) { if (dev->priv_flags & IFF_EBRIDGE) { + struct net_bridge *br = netdev_priv(dev); struct br_port_msg *bpm; if (idx < s_idx) @@ -406,7 +440,7 @@ static int br_mdb_dump(struct sk_buff *skb, struct netlink_callback *cb) bpm->ifindex = dev->ifindex; if (br_mdb_fill_info(skb, cb, dev) < 0) goto out; - if (br_rports_fill_info(skb, cb, dev) < 0) + if (br_rports_fill_info(skb, &br->multicast_ctx) < 0) goto out; cb->args[1] = 0; @@ -483,7 +517,7 @@ static size_t rtnl_mdb_nlmsg_size(struct net_bridge_port_group *pg) /* MDBA_MDB_EATTR_SOURCE */ if (pg->key.addr.src.ip4) nlmsg_size += nla_total_size(sizeof(__be32)); - if (pg->key.port->br->multicast_igmp_version == 2) + if (pg->key.port->br->multicast_ctx.multicast_igmp_version == 2) goto out; addr_size = sizeof(__be32); break; @@ -492,7 +526,7 @@ static size_t rtnl_mdb_nlmsg_size(struct net_bridge_port_group *pg) /* MDBA_MDB_EATTR_SOURCE */ if (!ipv6_addr_any(&pg->key.addr.src.ip6)) nlmsg_size += nla_total_size(sizeof(struct in6_addr)); - if (pg->key.port->br->multicast_mld_version == 1) + if (pg->key.port->br->multicast_ctx.multicast_mld_version == 1) goto out; addr_size = sizeof(struct in6_addr); break; @@ -617,6 +651,9 @@ int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, ASSERT_RTNL(); + if (!nb) + return 0; + if (!netif_is_bridge_master(br_dev) || !netif_is_bridge_port(dev)) return -EINVAL; @@ -686,7 +723,6 @@ out_free_mdb: return err; } -EXPORT_SYMBOL_GPL(br_mdb_replay); static void br_mdb_switchdev_host_port(struct net_device *dev, struct net_device *lower_dev, @@ -781,12 +817,12 @@ errout: static int nlmsg_populate_rtr_fill(struct sk_buff *skb, struct net_device *dev, - int ifindex, u32 pid, + int ifindex, u16 vid, u32 pid, u32 seq, int type, unsigned int flags) { + struct nlattr *nest, *port_nest; struct br_port_msg *bpm; struct nlmsghdr *nlh; - struct nlattr *nest; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), 0); if (!nlh) @@ -800,8 +836,18 @@ static int nlmsg_populate_rtr_fill(struct sk_buff *skb, if (!nest) goto cancel; - if (nla_put_u32(skb, MDBA_ROUTER_PORT, ifindex)) + port_nest = nla_nest_start_noflag(skb, MDBA_ROUTER_PORT); + if (!port_nest) + goto end; + if (nla_put_nohdr(skb, sizeof(u32), &ifindex)) { + nla_nest_cancel(skb, port_nest); + goto end; + } + if (vid && nla_put_u16(skb, MDBA_ROUTER_PATTR_VID, vid)) { + nla_nest_cancel(skb, port_nest); goto end; + } + nla_nest_end(skb, port_nest); nla_nest_end(skb, nest); nlmsg_end(skb, nlh); @@ -817,23 +863,28 @@ cancel: static inline size_t rtnl_rtr_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct br_port_msg)) - + nla_total_size(sizeof(__u32)); + + nla_total_size(sizeof(__u32)) + + nla_total_size(sizeof(u16)); } -void br_rtr_notify(struct net_device *dev, struct net_bridge_port *port, +void br_rtr_notify(struct net_device *dev, struct net_bridge_mcast_port *pmctx, int type) { struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOBUFS; int ifindex; + u16 vid; - ifindex = port ? port->dev->ifindex : 0; + ifindex = pmctx ? pmctx->port->dev->ifindex : 0; + vid = pmctx && br_multicast_port_ctx_is_vlan(pmctx) ? pmctx->vlan->vid : + 0; skb = nlmsg_new(rtnl_rtr_nlmsg_size(), GFP_ATOMIC); if (!skb) goto errout; - err = nlmsg_populate_rtr_fill(skb, dev, ifindex, 0, 0, type, NTF_SELF); + err = nlmsg_populate_rtr_fill(skb, dev, ifindex, vid, 0, 0, type, + NTF_SELF); if (err < 0) { kfree_skb(skb); goto errout; @@ -1004,14 +1055,47 @@ static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh, return 0; } +static struct net_bridge_mcast * +__br_mdb_choose_context(struct net_bridge *br, + const struct br_mdb_entry *entry, + struct netlink_ext_ack *extack) +{ + struct net_bridge_mcast *brmctx = NULL; + struct net_bridge_vlan *v; + + if (!br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) { + brmctx = &br->multicast_ctx; + goto out; + } + + if (!entry->vid) { + NL_SET_ERR_MSG_MOD(extack, "Cannot add an entry without a vlan when vlan snooping is enabled"); + goto out; + } + + v = br_vlan_find(br_vlan_group(br), entry->vid); + if (!v) { + NL_SET_ERR_MSG_MOD(extack, "Vlan is not configured"); + goto out; + } + if (br_multicast_ctx_vlan_global_disabled(&v->br_mcast_ctx)) { + NL_SET_ERR_MSG_MOD(extack, "Vlan's multicast processing is disabled"); + goto out; + } + brmctx = &v->br_mcast_ctx; +out: + return brmctx; +} + static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, struct br_mdb_entry *entry, struct nlattr **mdb_attrs, struct netlink_ext_ack *extack) { struct net_bridge_mdb_entry *mp, *star_mp; - struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; + struct net_bridge_port_group *p; + struct net_bridge_mcast *brmctx; struct br_ip group, star_group; unsigned long now = jiffies; unsigned char flags = 0; @@ -1020,6 +1104,10 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, __mdb_entry_to_br_ip(entry, &group, mdb_attrs); + brmctx = __br_mdb_choose_context(br, entry, extack); + if (!brmctx) + return -EINVAL; + /* host join errors which can happen before creating the group */ if (!port) { /* don't allow any flags for host-joined groups */ @@ -1053,7 +1141,7 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, return -EEXIST; } - br_multicast_host_join(mp, false); + br_multicast_host_join(brmctx, mp, false); br_mdb_notify(br->dev, mp, NULL, RTM_NEWMDB); return 0; @@ -1084,14 +1172,15 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, } rcu_assign_pointer(*pp, p); if (entry->state == MDB_TEMPORARY) - mod_timer(&p->timer, now + br->multicast_membership_interval); + mod_timer(&p->timer, + now + brmctx->multicast_membership_interval); br_mdb_notify(br->dev, mp, p, RTM_NEWMDB); /* if we are adding a new EXCLUDE port group (*,G) it needs to be also * added to all S,G entries for proper replication, if we are adding * a new INCLUDE port (S,G) then all of *,G EXCLUDE ports need to be * added to it for proper replication */ - if (br_multicast_should_handle_mode(br, group.proto)) { + if (br_multicast_should_handle_mode(brmctx, group.proto)) { switch (filter_mode) { case MCAST_EXCLUDE: br_multicast_star_g_handle_mode(p, MCAST_EXCLUDE); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index d0434dc8c03b..3523c8c7068f 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -49,30 +49,30 @@ static const struct rhashtable_params br_sg_port_rht_params = { .automatic_shrinking = true, }; -static void br_multicast_start_querier(struct net_bridge *br, +static void br_multicast_start_querier(struct net_bridge_mcast *brmctx, struct bridge_mcast_own_query *query); -static void br_ip4_multicast_add_router(struct net_bridge *br, - struct net_bridge_port *port); -static void br_ip4_multicast_leave_group(struct net_bridge *br, - struct net_bridge_port *port, +static void br_ip4_multicast_add_router(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx); +static void br_ip4_multicast_leave_group(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, __be32 group, __u16 vid, const unsigned char *src); static void br_multicast_port_group_rexmit(struct timer_list *t); static void -br_multicast_rport_del_notify(struct net_bridge_port *p, bool deleted); -static void br_ip6_multicast_add_router(struct net_bridge *br, - struct net_bridge_port *port); +br_multicast_rport_del_notify(struct net_bridge_mcast_port *pmctx, bool deleted); +static void br_ip6_multicast_add_router(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx); #if IS_ENABLED(CONFIG_IPV6) -static void br_ip6_multicast_leave_group(struct net_bridge *br, - struct net_bridge_port *port, +static void br_ip6_multicast_leave_group(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, const struct in6_addr *group, __u16 vid, const unsigned char *src); #endif static struct net_bridge_port_group * -__br_multicast_add_group(struct net_bridge *br, - struct net_bridge_port *port, +__br_multicast_add_group(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, struct br_ip *group, const unsigned char *src, u8 filter_mode, @@ -80,6 +80,7 @@ __br_multicast_add_group(struct net_bridge *br, bool blocked); static void br_multicast_find_del_pg(struct net_bridge *br, struct net_bridge_port_group *pg); +static void __br_multicast_stop(struct net_bridge_mcast *brmctx); static struct net_bridge_port_group * br_sg_port_find(struct net_bridge *br, @@ -140,12 +141,14 @@ static struct net_bridge_mdb_entry *br_mdb_ip6_get(struct net_bridge *br, } #endif -struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, +struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge_mcast *brmctx, struct sk_buff *skb, u16 vid) { + struct net_bridge *br = brmctx->br; struct br_ip ip; - if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) + if (!br_opt_get(br, BROPT_MULTICAST_ENABLED) || + br_multicast_ctx_vlan_global_disabled(brmctx)) return NULL; if (BR_INPUT_SKB_CB(skb)->igmp) @@ -158,7 +161,7 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, switch (skb->protocol) { case htons(ETH_P_IP): ip.dst.ip4 = ip_hdr(skb)->daddr; - if (br->multicast_igmp_version == 3) { + if (brmctx->multicast_igmp_version == 3) { struct net_bridge_mdb_entry *mdb; ip.src.ip4 = ip_hdr(skb)->saddr; @@ -171,7 +174,7 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): ip.dst.ip6 = ipv6_hdr(skb)->daddr; - if (br->multicast_mld_version == 2) { + if (brmctx->multicast_mld_version == 2) { struct net_bridge_mdb_entry *mdb; ip.src.ip6 = ipv6_hdr(skb)->saddr; @@ -190,6 +193,62 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, return br_mdb_ip_get_rcu(br, &ip); } +/* IMPORTANT: this function must be used only when the contexts cannot be + * passed down (e.g. timer) and must be used for read-only purposes because + * the vlan snooping option can change, so it can return any context + * (non-vlan or vlan). Its initial intended purpose is to read timer values + * from the *current* context based on the option. At worst that could lead + * to inconsistent timers when the contexts are changed, i.e. src timer + * which needs to re-arm with a specific delay taken from the old context + */ +static struct net_bridge_mcast_port * +br_multicast_pg_to_port_ctx(const struct net_bridge_port_group *pg) +{ + struct net_bridge_mcast_port *pmctx = &pg->key.port->multicast_ctx; + struct net_bridge_vlan *vlan; + + lockdep_assert_held_once(&pg->key.port->br->multicast_lock); + + /* if vlan snooping is disabled use the port's multicast context */ + if (!pg->key.addr.vid || + !br_opt_get(pg->key.port->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) + goto out; + + /* locking is tricky here, due to different rules for multicast and + * vlans we need to take rcu to find the vlan and make sure it has + * the BR_VLFLAG_MCAST_ENABLED flag set, it can only change under + * multicast_lock which must be already held here, so the vlan's pmctx + * can safely be used on return + */ + rcu_read_lock(); + vlan = br_vlan_find(nbp_vlan_group_rcu(pg->key.port), pg->key.addr.vid); + if (vlan && !br_multicast_port_ctx_vlan_disabled(&vlan->port_mcast_ctx)) + pmctx = &vlan->port_mcast_ctx; + else + pmctx = NULL; + rcu_read_unlock(); +out: + return pmctx; +} + +/* when snooping we need to check if the contexts should be used + * in the following order: + * - if pmctx is non-NULL (port), check if it should be used + * - if pmctx is NULL (bridge), check if brmctx should be used + */ +static bool +br_multicast_ctx_should_use(const struct net_bridge_mcast *brmctx, + const struct net_bridge_mcast_port *pmctx) +{ + if (!netif_running(brmctx->br->dev)) + return false; + + if (pmctx) + return !br_multicast_port_ctx_state_disabled(pmctx); + else + return !br_multicast_ctx_vlan_disabled(brmctx); +} + static bool br_port_group_equal(struct net_bridge_port_group *p, struct net_bridge_port *port, const unsigned char *src) @@ -203,20 +262,23 @@ static bool br_port_group_equal(struct net_bridge_port_group *p, return ether_addr_equal(src, p->eth_addr); } -static void __fwd_add_star_excl(struct net_bridge_port_group *pg, +static void __fwd_add_star_excl(struct net_bridge_mcast_port *pmctx, + struct net_bridge_port_group *pg, struct br_ip *sg_ip) { struct net_bridge_port_group_sg_key sg_key; - struct net_bridge *br = pg->key.port->br; struct net_bridge_port_group *src_pg; + struct net_bridge_mcast *brmctx; memset(&sg_key, 0, sizeof(sg_key)); + brmctx = br_multicast_port_ctx_get_global(pmctx); sg_key.port = pg->key.port; sg_key.addr = *sg_ip; - if (br_sg_port_find(br, &sg_key)) + if (br_sg_port_find(brmctx->br, &sg_key)) return; - src_pg = __br_multicast_add_group(br, pg->key.port, sg_ip, pg->eth_addr, + src_pg = __br_multicast_add_group(brmctx, pmctx, + sg_ip, pg->eth_addr, MCAST_INCLUDE, false, false); if (IS_ERR_OR_NULL(src_pg) || src_pg->rt_protocol != RTPROT_KERNEL) @@ -256,6 +318,7 @@ void br_multicast_star_g_handle_mode(struct net_bridge_port_group *pg, { struct net_bridge *br = pg->key.port->br; struct net_bridge_port_group *pg_lst; + struct net_bridge_mcast_port *pmctx; struct net_bridge_mdb_entry *mp; struct br_ip sg_ip; @@ -265,9 +328,13 @@ void br_multicast_star_g_handle_mode(struct net_bridge_port_group *pg, mp = br_mdb_ip_get(br, &pg->key.addr); if (!mp) return; + pmctx = br_multicast_pg_to_port_ctx(pg); + if (!pmctx) + return; memset(&sg_ip, 0, sizeof(sg_ip)); sg_ip = pg->key.addr; + for (pg_lst = mlock_dereference(mp->ports, br); pg_lst; pg_lst = mlock_dereference(pg_lst->next, br)) { @@ -284,7 +351,7 @@ void br_multicast_star_g_handle_mode(struct net_bridge_port_group *pg, __fwd_del_star_excl(pg, &sg_ip); break; case MCAST_EXCLUDE: - __fwd_add_star_excl(pg, &sg_ip); + __fwd_add_star_excl(pmctx, pg, &sg_ip); break; } } @@ -377,7 +444,9 @@ void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp, { struct net_bridge_port_group_sg_key sg_key; struct net_bridge *br = star_mp->br; + struct net_bridge_mcast_port *pmctx; struct net_bridge_port_group *pg; + struct net_bridge_mcast *brmctx; if (WARN_ON(br_multicast_is_star_g(&sg->key.addr))) return; @@ -400,7 +469,12 @@ void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp, if (br_sg_port_find(br, &sg_key)) continue; - src_pg = __br_multicast_add_group(br, pg->key.port, + pmctx = br_multicast_pg_to_port_ctx(pg); + if (!pmctx) + continue; + brmctx = br_multicast_port_ctx_get_global(pmctx); + + src_pg = __br_multicast_add_group(brmctx, pmctx, &sg->key.addr, sg->eth_addr, MCAST_INCLUDE, false, false); @@ -414,16 +488,23 @@ void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp, static void br_multicast_fwd_src_add(struct net_bridge_group_src *src) { struct net_bridge_mdb_entry *star_mp; + struct net_bridge_mcast_port *pmctx; struct net_bridge_port_group *sg; + struct net_bridge_mcast *brmctx; struct br_ip sg_ip; if (src->flags & BR_SGRP_F_INSTALLED) return; memset(&sg_ip, 0, sizeof(sg_ip)); + pmctx = br_multicast_pg_to_port_ctx(src->pg); + if (!pmctx) + return; + brmctx = br_multicast_port_ctx_get_global(pmctx); sg_ip = src->pg->key.addr; sg_ip.src = src->addr.src; - sg = __br_multicast_add_group(src->br, src->pg->key.port, &sg_ip, + + sg = __br_multicast_add_group(brmctx, pmctx, &sg_ip, src->pg->eth_addr, MCAST_INCLUDE, false, !timer_pending(&src->timer)); if (IS_ERR_OR_NULL(sg)) @@ -692,7 +773,28 @@ static void br_multicast_gc(struct hlist_head *head) } } -static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, +static void __br_multicast_query_handle_vlan(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, + struct sk_buff *skb) +{ + struct net_bridge_vlan *vlan = NULL; + + if (pmctx && br_multicast_port_ctx_is_vlan(pmctx)) + vlan = pmctx->vlan; + else if (br_multicast_ctx_is_vlan(brmctx)) + vlan = brmctx->vlan; + + if (vlan && !(vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED)) { + u16 vlan_proto; + + if (br_vlan_get_proto(brmctx->br->dev, &vlan_proto) != 0) + return; + __vlan_hwaccel_put_tag(skb, htons(vlan_proto), vlan->vid); + } +} + +static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, __be32 ip_dst, __be32 group, bool with_srcs, bool over_lmqt, @@ -714,11 +816,11 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, u16 lmqt_srcs = 0; igmp_hdr_size = sizeof(*ih); - if (br->multicast_igmp_version == 3) { + if (brmctx->multicast_igmp_version == 3) { igmp_hdr_size = sizeof(*ihv3); if (pg && with_srcs) { - lmqt = now + (br->multicast_last_member_interval * - br->multicast_last_member_count); + lmqt = now + (brmctx->multicast_last_member_interval * + brmctx->multicast_last_member_count); hlist_for_each_entry(ent, &pg->src_list, node) { if (over_lmqt == time_after(ent->timer.expires, lmqt) && @@ -734,19 +836,20 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, pkt_size = sizeof(*eth) + sizeof(*iph) + 4 + igmp_hdr_size; if ((p && pkt_size > p->dev->mtu) || - pkt_size > br->dev->mtu) + pkt_size > brmctx->br->dev->mtu) return NULL; - skb = netdev_alloc_skb_ip_align(br->dev, pkt_size); + skb = netdev_alloc_skb_ip_align(brmctx->br->dev, pkt_size); if (!skb) goto out; + __br_multicast_query_handle_vlan(brmctx, pmctx, skb); skb->protocol = htons(ETH_P_IP); skb_reset_mac_header(skb); eth = eth_hdr(skb); - ether_addr_copy(eth->h_source, br->dev->dev_addr); + ether_addr_copy(eth->h_source, brmctx->br->dev->dev_addr); ip_eth_mc_map(ip_dst, eth->h_dest); eth->h_proto = htons(ETH_P_IP); skb_put(skb, sizeof(*eth)); @@ -762,8 +865,8 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, iph->frag_off = htons(IP_DF); iph->ttl = 1; iph->protocol = IPPROTO_IGMP; - iph->saddr = br_opt_get(br, BROPT_MULTICAST_QUERY_USE_IFADDR) ? - inet_select_addr(br->dev, 0, RT_SCOPE_LINK) : 0; + iph->saddr = br_opt_get(brmctx->br, BROPT_MULTICAST_QUERY_USE_IFADDR) ? + inet_select_addr(brmctx->br->dev, 0, RT_SCOPE_LINK) : 0; iph->daddr = ip_dst; ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; @@ -775,12 +878,12 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, skb_set_transport_header(skb, skb->len); *igmp_type = IGMP_HOST_MEMBERSHIP_QUERY; - switch (br->multicast_igmp_version) { + switch (brmctx->multicast_igmp_version) { case 2: ih = igmp_hdr(skb); ih->type = IGMP_HOST_MEMBERSHIP_QUERY; - ih->code = (group ? br->multicast_last_member_interval : - br->multicast_query_response_interval) / + ih->code = (group ? brmctx->multicast_last_member_interval : + brmctx->multicast_query_response_interval) / (HZ / IGMP_TIMER_SCALE); ih->group = group; ih->csum = 0; @@ -790,11 +893,11 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, case 3: ihv3 = igmpv3_query_hdr(skb); ihv3->type = IGMP_HOST_MEMBERSHIP_QUERY; - ihv3->code = (group ? br->multicast_last_member_interval : - br->multicast_query_response_interval) / + ihv3->code = (group ? brmctx->multicast_last_member_interval : + brmctx->multicast_query_response_interval) / (HZ / IGMP_TIMER_SCALE); ihv3->group = group; - ihv3->qqic = br->multicast_query_interval / HZ; + ihv3->qqic = brmctx->multicast_query_interval / HZ; ihv3->nsrcs = htons(lmqt_srcs); ihv3->resv = 0; ihv3->suppress = sflag; @@ -837,7 +940,8 @@ out: } #if IS_ENABLED(CONFIG_IPV6) -static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, +static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, const struct in6_addr *ip6_dst, const struct in6_addr *group, @@ -862,11 +966,11 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, u8 *hopopt; mld_hdr_size = sizeof(*mldq); - if (br->multicast_mld_version == 2) { + if (brmctx->multicast_mld_version == 2) { mld_hdr_size = sizeof(*mld2q); if (pg && with_srcs) { - llqt = now + (br->multicast_last_member_interval * - br->multicast_last_member_count); + llqt = now + (brmctx->multicast_last_member_interval * + brmctx->multicast_last_member_count); hlist_for_each_entry(ent, &pg->src_list, node) { if (over_llqt == time_after(ent->timer.expires, llqt) && @@ -882,20 +986,21 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, pkt_size = sizeof(*eth) + sizeof(*ip6h) + 8 + mld_hdr_size; if ((p && pkt_size > p->dev->mtu) || - pkt_size > br->dev->mtu) + pkt_size > brmctx->br->dev->mtu) return NULL; - skb = netdev_alloc_skb_ip_align(br->dev, pkt_size); + skb = netdev_alloc_skb_ip_align(brmctx->br->dev, pkt_size); if (!skb) goto out; + __br_multicast_query_handle_vlan(brmctx, pmctx, skb); skb->protocol = htons(ETH_P_IPV6); /* Ethernet header */ skb_reset_mac_header(skb); eth = eth_hdr(skb); - ether_addr_copy(eth->h_source, br->dev->dev_addr); + ether_addr_copy(eth->h_source, brmctx->br->dev->dev_addr); eth->h_proto = htons(ETH_P_IPV6); skb_put(skb, sizeof(*eth)); @@ -908,14 +1013,14 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, ip6h->nexthdr = IPPROTO_HOPOPTS; ip6h->hop_limit = 1; ip6h->daddr = *ip6_dst; - if (ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0, - &ip6h->saddr)) { + if (ipv6_dev_get_saddr(dev_net(brmctx->br->dev), brmctx->br->dev, + &ip6h->daddr, 0, &ip6h->saddr)) { kfree_skb(skb); - br_opt_toggle(br, BROPT_HAS_IPV6_ADDR, false); + br_opt_toggle(brmctx->br, BROPT_HAS_IPV6_ADDR, false); return NULL; } - br_opt_toggle(br, BROPT_HAS_IPV6_ADDR, true); + br_opt_toggle(brmctx->br, BROPT_HAS_IPV6_ADDR, true); ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest); hopopt = (u8 *)(ip6h + 1); @@ -933,10 +1038,10 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, /* ICMPv6 */ skb_set_transport_header(skb, skb->len); interval = ipv6_addr_any(group) ? - br->multicast_query_response_interval : - br->multicast_last_member_interval; + brmctx->multicast_query_response_interval : + brmctx->multicast_last_member_interval; *igmp_type = ICMPV6_MGM_QUERY; - switch (br->multicast_mld_version) { + switch (brmctx->multicast_mld_version) { case 1: mldq = (struct mld_msg *)icmp6_hdr(skb); mldq->mld_type = ICMPV6_MGM_QUERY; @@ -959,7 +1064,7 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, mld2q->mld2q_suppress = sflag; mld2q->mld2q_qrv = 2; mld2q->mld2q_nsrcs = htons(llqt_srcs); - mld2q->mld2q_qqic = br->multicast_query_interval / HZ; + mld2q->mld2q_qqic = brmctx->multicast_query_interval / HZ; mld2q->mld2q_mca = *group; csum = &mld2q->mld2q_cksum; csum_start = (void *)mld2q; @@ -1000,7 +1105,8 @@ out: } #endif -static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br, +static struct sk_buff *br_multicast_alloc_query(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, struct br_ip *ip_dst, struct br_ip *group, @@ -1013,7 +1119,7 @@ static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br, switch (group->proto) { case htons(ETH_P_IP): ip4_dst = ip_dst ? ip_dst->dst.ip4 : htonl(INADDR_ALLHOSTS_GROUP); - return br_ip4_multicast_alloc_query(br, pg, + return br_ip4_multicast_alloc_query(brmctx, pmctx, pg, ip4_dst, group->dst.ip4, with_srcs, over_lmqt, sflag, igmp_type, @@ -1028,7 +1134,7 @@ static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br, ipv6_addr_set(&ip6_dst, htonl(0xff020000), 0, 0, htonl(1)); - return br_ip6_multicast_alloc_query(br, pg, + return br_ip6_multicast_alloc_query(brmctx, pmctx, pg, &ip6_dst, &group->dst.ip6, with_srcs, over_lmqt, sflag, igmp_type, @@ -1206,7 +1312,8 @@ struct net_bridge_port_group *br_multicast_new_port_group( return p; } -void br_multicast_host_join(struct net_bridge_mdb_entry *mp, bool notify) +void br_multicast_host_join(const struct net_bridge_mcast *brmctx, + struct net_bridge_mdb_entry *mp, bool notify) { if (!mp->host_joined) { mp->host_joined = true; @@ -1219,7 +1326,7 @@ void br_multicast_host_join(struct net_bridge_mdb_entry *mp, bool notify) if (br_group_is_l2(&mp->addr)) return; - mod_timer(&mp->timer, jiffies + mp->br->multicast_membership_interval); + mod_timer(&mp->timer, jiffies + brmctx->multicast_membership_interval); } void br_multicast_host_leave(struct net_bridge_mdb_entry *mp, bool notify) @@ -1235,8 +1342,8 @@ void br_multicast_host_leave(struct net_bridge_mdb_entry *mp, bool notify) } static struct net_bridge_port_group * -__br_multicast_add_group(struct net_bridge *br, - struct net_bridge_port *port, +__br_multicast_add_group(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, struct br_ip *group, const unsigned char *src, u8 filter_mode, @@ -1248,29 +1355,28 @@ __br_multicast_add_group(struct net_bridge *br, struct net_bridge_mdb_entry *mp; unsigned long now = jiffies; - if (!netif_running(br->dev) || - (port && port->state == BR_STATE_DISABLED)) + if (!br_multicast_ctx_should_use(brmctx, pmctx)) goto out; - mp = br_multicast_new_group(br, group); + mp = br_multicast_new_group(brmctx->br, group); if (IS_ERR(mp)) return ERR_CAST(mp); - if (!port) { - br_multicast_host_join(mp, true); + if (!pmctx) { + br_multicast_host_join(brmctx, mp, true); goto out; } for (pp = &mp->ports; - (p = mlock_dereference(*pp, br)) != NULL; + (p = mlock_dereference(*pp, brmctx->br)) != NULL; pp = &p->next) { - if (br_port_group_equal(p, port, src)) + if (br_port_group_equal(p, pmctx->port, src)) goto found; - if ((unsigned long)p->key.port < (unsigned long)port) + if ((unsigned long)p->key.port < (unsigned long)pmctx->port) break; } - p = br_multicast_new_port_group(port, group, *pp, 0, src, + p = br_multicast_new_port_group(pmctx->port, group, *pp, 0, src, filter_mode, RTPROT_KERNEL); if (unlikely(!p)) { p = ERR_PTR(-ENOMEM); @@ -1279,18 +1385,19 @@ __br_multicast_add_group(struct net_bridge *br, rcu_assign_pointer(*pp, p); if (blocked) p->flags |= MDB_PG_FLAGS_BLOCKED; - br_mdb_notify(br->dev, mp, p, RTM_NEWMDB); + br_mdb_notify(brmctx->br->dev, mp, p, RTM_NEWMDB); found: if (igmpv2_mldv1) - mod_timer(&p->timer, now + br->multicast_membership_interval); + mod_timer(&p->timer, + now + brmctx->multicast_membership_interval); out: return p; } -static int br_multicast_add_group(struct net_bridge *br, - struct net_bridge_port *port, +static int br_multicast_add_group(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, struct br_ip *group, const unsigned char *src, u8 filter_mode, @@ -1299,18 +1406,18 @@ static int br_multicast_add_group(struct net_bridge *br, struct net_bridge_port_group *pg; int err; - spin_lock(&br->multicast_lock); - pg = __br_multicast_add_group(br, port, group, src, filter_mode, + spin_lock(&brmctx->br->multicast_lock); + pg = __br_multicast_add_group(brmctx, pmctx, group, src, filter_mode, igmpv2_mldv1, false); /* NULL is considered valid for host joined groups */ err = PTR_ERR_OR_ZERO(pg); - spin_unlock(&br->multicast_lock); + spin_unlock(&brmctx->br->multicast_lock); return err; } -static int br_ip4_multicast_add_group(struct net_bridge *br, - struct net_bridge_port *port, +static int br_ip4_multicast_add_group(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, __be32 group, __u16 vid, const unsigned char *src, @@ -1328,13 +1435,13 @@ static int br_ip4_multicast_add_group(struct net_bridge *br, br_group.vid = vid; filter_mode = igmpv2 ? MCAST_EXCLUDE : MCAST_INCLUDE; - return br_multicast_add_group(br, port, &br_group, src, filter_mode, - igmpv2); + return br_multicast_add_group(brmctx, pmctx, &br_group, src, + filter_mode, igmpv2); } #if IS_ENABLED(CONFIG_IPV6) -static int br_ip6_multicast_add_group(struct net_bridge *br, - struct net_bridge_port *port, +static int br_ip6_multicast_add_group(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, const struct in6_addr *group, __u16 vid, const unsigned char *src, @@ -1352,8 +1459,8 @@ static int br_ip6_multicast_add_group(struct net_bridge *br, br_group.vid = vid; filter_mode = mldv1 ? MCAST_EXCLUDE : MCAST_INCLUDE; - return br_multicast_add_group(br, port, &br_group, src, filter_mode, - mldv1); + return br_multicast_add_group(brmctx, pmctx, &br_group, src, + filter_mode, mldv1); } #endif @@ -1366,52 +1473,54 @@ static bool br_multicast_rport_del(struct hlist_node *rlist) return true; } -static bool br_ip4_multicast_rport_del(struct net_bridge_port *p) +static bool br_ip4_multicast_rport_del(struct net_bridge_mcast_port *pmctx) { - return br_multicast_rport_del(&p->ip4_rlist); + return br_multicast_rport_del(&pmctx->ip4_rlist); } -static bool br_ip6_multicast_rport_del(struct net_bridge_port *p) +static bool br_ip6_multicast_rport_del(struct net_bridge_mcast_port *pmctx) { #if IS_ENABLED(CONFIG_IPV6) - return br_multicast_rport_del(&p->ip6_rlist); + return br_multicast_rport_del(&pmctx->ip6_rlist); #else return false; #endif } -static void br_multicast_router_expired(struct net_bridge_port *port, +static void br_multicast_router_expired(struct net_bridge_mcast_port *pmctx, struct timer_list *t, struct hlist_node *rlist) { - struct net_bridge *br = port->br; + struct net_bridge *br = pmctx->port->br; bool del; spin_lock(&br->multicast_lock); - if (port->multicast_router == MDB_RTR_TYPE_DISABLED || - port->multicast_router == MDB_RTR_TYPE_PERM || + if (pmctx->multicast_router == MDB_RTR_TYPE_DISABLED || + pmctx->multicast_router == MDB_RTR_TYPE_PERM || timer_pending(t)) goto out; del = br_multicast_rport_del(rlist); - br_multicast_rport_del_notify(port, del); + br_multicast_rport_del_notify(pmctx, del); out: spin_unlock(&br->multicast_lock); } static void br_ip4_multicast_router_expired(struct timer_list *t) { - struct net_bridge_port *port = from_timer(port, t, ip4_mc_router_timer); + struct net_bridge_mcast_port *pmctx = from_timer(pmctx, t, + ip4_mc_router_timer); - br_multicast_router_expired(port, t, &port->ip4_rlist); + br_multicast_router_expired(pmctx, t, &pmctx->ip4_rlist); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_router_expired(struct timer_list *t) { - struct net_bridge_port *port = from_timer(port, t, ip6_mc_router_timer); + struct net_bridge_mcast_port *pmctx = from_timer(pmctx, t, + ip6_mc_router_timer); - br_multicast_router_expired(port, t, &port->ip6_rlist); + br_multicast_router_expired(pmctx, t, &pmctx->ip6_rlist); } #endif @@ -1428,80 +1537,86 @@ static void br_mc_router_state_change(struct net_bridge *p, switchdev_port_attr_set(p->dev, &attr, NULL); } -static void br_multicast_local_router_expired(struct net_bridge *br, +static void br_multicast_local_router_expired(struct net_bridge_mcast *brmctx, struct timer_list *timer) { - spin_lock(&br->multicast_lock); - if (br->multicast_router == MDB_RTR_TYPE_DISABLED || - br->multicast_router == MDB_RTR_TYPE_PERM || - br_ip4_multicast_is_router(br) || - br_ip6_multicast_is_router(br)) + spin_lock(&brmctx->br->multicast_lock); + if (brmctx->multicast_router == MDB_RTR_TYPE_DISABLED || + brmctx->multicast_router == MDB_RTR_TYPE_PERM || + br_ip4_multicast_is_router(brmctx) || + br_ip6_multicast_is_router(brmctx)) goto out; - br_mc_router_state_change(br, false); + br_mc_router_state_change(brmctx->br, false); out: - spin_unlock(&br->multicast_lock); + spin_unlock(&brmctx->br->multicast_lock); } static void br_ip4_multicast_local_router_expired(struct timer_list *t) { - struct net_bridge *br = from_timer(br, t, ip4_mc_router_timer); + struct net_bridge_mcast *brmctx = from_timer(brmctx, t, + ip4_mc_router_timer); - br_multicast_local_router_expired(br, t); + br_multicast_local_router_expired(brmctx, t); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_local_router_expired(struct timer_list *t) { - struct net_bridge *br = from_timer(br, t, ip6_mc_router_timer); + struct net_bridge_mcast *brmctx = from_timer(brmctx, t, + ip6_mc_router_timer); - br_multicast_local_router_expired(br, t); + br_multicast_local_router_expired(brmctx, t); } #endif -static void br_multicast_querier_expired(struct net_bridge *br, +static void br_multicast_querier_expired(struct net_bridge_mcast *brmctx, struct bridge_mcast_own_query *query) { - spin_lock(&br->multicast_lock); - if (!netif_running(br->dev) || !br_opt_get(br, BROPT_MULTICAST_ENABLED)) + spin_lock(&brmctx->br->multicast_lock); + if (!netif_running(brmctx->br->dev) || + br_multicast_ctx_vlan_global_disabled(brmctx) || + !br_opt_get(brmctx->br, BROPT_MULTICAST_ENABLED)) goto out; - br_multicast_start_querier(br, query); + br_multicast_start_querier(brmctx, query); out: - spin_unlock(&br->multicast_lock); + spin_unlock(&brmctx->br->multicast_lock); } static void br_ip4_multicast_querier_expired(struct timer_list *t) { - struct net_bridge *br = from_timer(br, t, ip4_other_query.timer); + struct net_bridge_mcast *brmctx = from_timer(brmctx, t, + ip4_other_query.timer); - br_multicast_querier_expired(br, &br->ip4_own_query); + br_multicast_querier_expired(brmctx, &brmctx->ip4_own_query); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_querier_expired(struct timer_list *t) { - struct net_bridge *br = from_timer(br, t, ip6_other_query.timer); + struct net_bridge_mcast *brmctx = from_timer(brmctx, t, + ip6_other_query.timer); - br_multicast_querier_expired(br, &br->ip6_own_query); + br_multicast_querier_expired(brmctx, &brmctx->ip6_own_query); } #endif -static void br_multicast_select_own_querier(struct net_bridge *br, +static void br_multicast_select_own_querier(struct net_bridge_mcast *brmctx, struct br_ip *ip, struct sk_buff *skb) { if (ip->proto == htons(ETH_P_IP)) - br->ip4_querier.addr.src.ip4 = ip_hdr(skb)->saddr; + brmctx->ip4_querier.addr.src.ip4 = ip_hdr(skb)->saddr; #if IS_ENABLED(CONFIG_IPV6) else - br->ip6_querier.addr.src.ip6 = ipv6_hdr(skb)->saddr; + brmctx->ip6_querier.addr.src.ip6 = ipv6_hdr(skb)->saddr; #endif } -static void __br_multicast_send_query(struct net_bridge *br, - struct net_bridge_port *port, +static void __br_multicast_send_query(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, struct br_ip *ip_dst, struct br_ip *group, @@ -1513,19 +1628,23 @@ static void __br_multicast_send_query(struct net_bridge *br, struct sk_buff *skb; u8 igmp_type; + if (!br_multicast_ctx_should_use(brmctx, pmctx) || + !br_multicast_ctx_matches_vlan_snooping(brmctx)) + return; + again_under_lmqt: - skb = br_multicast_alloc_query(br, pg, ip_dst, group, with_srcs, - over_lmqt, sflag, &igmp_type, + skb = br_multicast_alloc_query(brmctx, pmctx, pg, ip_dst, group, + with_srcs, over_lmqt, sflag, &igmp_type, need_rexmit); if (!skb) return; - if (port) { - skb->dev = port->dev; - br_multicast_count(br, port, skb, igmp_type, + if (pmctx) { + skb->dev = pmctx->port->dev; + br_multicast_count(brmctx->br, pmctx->port, skb, igmp_type, BR_MCAST_DIR_TX); NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, - dev_net(port->dev), NULL, skb, NULL, skb->dev, + dev_net(pmctx->port->dev), NULL, skb, NULL, skb->dev, br_dev_queue_push_xmit); if (over_lmqt && with_srcs && sflag) { @@ -1533,35 +1652,64 @@ again_under_lmqt: goto again_under_lmqt; } } else { - br_multicast_select_own_querier(br, group, skb); - br_multicast_count(br, port, skb, igmp_type, + br_multicast_select_own_querier(brmctx, group, skb); + br_multicast_count(brmctx->br, NULL, skb, igmp_type, BR_MCAST_DIR_RX); netif_rx(skb); } } -static void br_multicast_send_query(struct net_bridge *br, - struct net_bridge_port *port, +static void br_multicast_read_querier(const struct bridge_mcast_querier *querier, + struct bridge_mcast_querier *dest) +{ + unsigned int seq; + + memset(dest, 0, sizeof(*dest)); + do { + seq = read_seqcount_begin(&querier->seq); + dest->port_ifidx = querier->port_ifidx; + memcpy(&dest->addr, &querier->addr, sizeof(struct br_ip)); + } while (read_seqcount_retry(&querier->seq, seq)); +} + +static void br_multicast_update_querier(struct net_bridge_mcast *brmctx, + struct bridge_mcast_querier *querier, + int ifindex, + struct br_ip *saddr) +{ + lockdep_assert_held_once(&brmctx->br->multicast_lock); + + write_seqcount_begin(&querier->seq); + querier->port_ifidx = ifindex; + memcpy(&querier->addr, saddr, sizeof(*saddr)); + write_seqcount_end(&querier->seq); +} + +static void br_multicast_send_query(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, struct bridge_mcast_own_query *own_query) { struct bridge_mcast_other_query *other_query = NULL; + struct bridge_mcast_querier *querier; struct br_ip br_group; unsigned long time; - if (!netif_running(br->dev) || - !br_opt_get(br, BROPT_MULTICAST_ENABLED) || - !br_opt_get(br, BROPT_MULTICAST_QUERIER)) + if (!br_multicast_ctx_should_use(brmctx, pmctx) || + !br_opt_get(brmctx->br, BROPT_MULTICAST_ENABLED) || + !brmctx->multicast_querier) return; memset(&br_group.dst, 0, sizeof(br_group.dst)); - if (port ? (own_query == &port->ip4_own_query) : - (own_query == &br->ip4_own_query)) { - other_query = &br->ip4_other_query; + if (pmctx ? (own_query == &pmctx->ip4_own_query) : + (own_query == &brmctx->ip4_own_query)) { + querier = &brmctx->ip4_querier; + other_query = &brmctx->ip4_other_query; br_group.proto = htons(ETH_P_IP); #if IS_ENABLED(CONFIG_IPV6) } else { - other_query = &br->ip6_other_query; + querier = &brmctx->ip6_querier; + other_query = &brmctx->ip6_other_query; br_group.proto = htons(ETH_P_IPV6); #endif } @@ -1569,31 +1717,39 @@ static void br_multicast_send_query(struct net_bridge *br, if (!other_query || timer_pending(&other_query->timer)) return; - __br_multicast_send_query(br, port, NULL, NULL, &br_group, false, 0, - NULL); + /* we're about to select ourselves as querier */ + if (!pmctx && querier->port_ifidx) { + struct br_ip zeroip = {}; + + br_multicast_update_querier(brmctx, querier, 0, &zeroip); + } + + __br_multicast_send_query(brmctx, pmctx, NULL, NULL, &br_group, false, + 0, NULL); time = jiffies; - time += own_query->startup_sent < br->multicast_startup_query_count ? - br->multicast_startup_query_interval : - br->multicast_query_interval; + time += own_query->startup_sent < brmctx->multicast_startup_query_count ? + brmctx->multicast_startup_query_interval : + brmctx->multicast_query_interval; mod_timer(&own_query->timer, time); } static void -br_multicast_port_query_expired(struct net_bridge_port *port, +br_multicast_port_query_expired(struct net_bridge_mcast_port *pmctx, struct bridge_mcast_own_query *query) { - struct net_bridge *br = port->br; + struct net_bridge *br = pmctx->port->br; + struct net_bridge_mcast *brmctx; spin_lock(&br->multicast_lock); - if (port->state == BR_STATE_DISABLED || - port->state == BR_STATE_BLOCKING) + if (br_multicast_port_ctx_state_stopped(pmctx)) goto out; - if (query->startup_sent < br->multicast_startup_query_count) + brmctx = br_multicast_port_ctx_get_global(pmctx); + if (query->startup_sent < brmctx->multicast_startup_query_count) query->startup_sent++; - br_multicast_send_query(port->br, port, query); + br_multicast_send_query(brmctx, pmctx, query); out: spin_unlock(&br->multicast_lock); @@ -1601,17 +1757,19 @@ out: static void br_ip4_multicast_port_query_expired(struct timer_list *t) { - struct net_bridge_port *port = from_timer(port, t, ip4_own_query.timer); + struct net_bridge_mcast_port *pmctx = from_timer(pmctx, t, + ip4_own_query.timer); - br_multicast_port_query_expired(port, &port->ip4_own_query); + br_multicast_port_query_expired(pmctx, &pmctx->ip4_own_query); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_port_query_expired(struct timer_list *t) { - struct net_bridge_port *port = from_timer(port, t, ip6_own_query.timer); + struct net_bridge_mcast_port *pmctx = from_timer(pmctx, t, + ip6_own_query.timer); - br_multicast_port_query_expired(port, &port->ip6_own_query); + br_multicast_port_query_expired(pmctx, &pmctx->ip6_own_query); } #endif @@ -1620,19 +1778,27 @@ static void br_multicast_port_group_rexmit(struct timer_list *t) struct net_bridge_port_group *pg = from_timer(pg, t, rexmit_timer); struct bridge_mcast_other_query *other_query = NULL; struct net_bridge *br = pg->key.port->br; + struct net_bridge_mcast_port *pmctx; + struct net_bridge_mcast *brmctx; bool need_rexmit = false; spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || hlist_unhashed(&pg->mglist) || - !br_opt_get(br, BROPT_MULTICAST_ENABLED) || - !br_opt_get(br, BROPT_MULTICAST_QUERIER)) + !br_opt_get(br, BROPT_MULTICAST_ENABLED)) + goto out; + + pmctx = br_multicast_pg_to_port_ctx(pg); + if (!pmctx) + goto out; + brmctx = br_multicast_port_ctx_get_global(pmctx); + if (!brmctx->multicast_querier) goto out; if (pg->key.addr.proto == htons(ETH_P_IP)) - other_query = &br->ip4_other_query; + other_query = &brmctx->ip4_other_query; #if IS_ENABLED(CONFIG_IPV6) else - other_query = &br->ip6_other_query; + other_query = &brmctx->ip6_other_query; #endif if (!other_query || timer_pending(&other_query->timer)) @@ -1640,15 +1806,15 @@ static void br_multicast_port_group_rexmit(struct timer_list *t) if (pg->grp_query_rexmit_cnt) { pg->grp_query_rexmit_cnt--; - __br_multicast_send_query(br, pg->key.port, pg, &pg->key.addr, + __br_multicast_send_query(brmctx, pmctx, pg, &pg->key.addr, &pg->key.addr, false, 1, NULL); } - __br_multicast_send_query(br, pg->key.port, pg, &pg->key.addr, + __br_multicast_send_query(brmctx, pmctx, pg, &pg->key.addr, &pg->key.addr, true, 0, &need_rexmit); if (pg->grp_query_rexmit_cnt || need_rexmit) mod_timer(&pg->rexmit_timer, jiffies + - br->multicast_last_member_interval); + brmctx->multicast_last_member_interval); out: spin_unlock(&br->multicast_lock); } @@ -1666,23 +1832,40 @@ static int br_mc_disabled_update(struct net_device *dev, bool value, return switchdev_port_attr_set(dev, &attr, extack); } -int br_multicast_add_port(struct net_bridge_port *port) +void br_multicast_port_ctx_init(struct net_bridge_port *port, + struct net_bridge_vlan *vlan, + struct net_bridge_mcast_port *pmctx) { - int err; - - port->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; - port->multicast_eht_hosts_limit = BR_MCAST_DEFAULT_EHT_HOSTS_LIMIT; - - timer_setup(&port->ip4_mc_router_timer, + pmctx->port = port; + pmctx->vlan = vlan; + pmctx->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; + timer_setup(&pmctx->ip4_mc_router_timer, br_ip4_multicast_router_expired, 0); - timer_setup(&port->ip4_own_query.timer, + timer_setup(&pmctx->ip4_own_query.timer, br_ip4_multicast_port_query_expired, 0); #if IS_ENABLED(CONFIG_IPV6) - timer_setup(&port->ip6_mc_router_timer, + timer_setup(&pmctx->ip6_mc_router_timer, br_ip6_multicast_router_expired, 0); - timer_setup(&port->ip6_own_query.timer, + timer_setup(&pmctx->ip6_own_query.timer, br_ip6_multicast_port_query_expired, 0); #endif +} + +void br_multicast_port_ctx_deinit(struct net_bridge_mcast_port *pmctx) +{ +#if IS_ENABLED(CONFIG_IPV6) + del_timer_sync(&pmctx->ip6_mc_router_timer); +#endif + del_timer_sync(&pmctx->ip4_mc_router_timer); +} + +int br_multicast_add_port(struct net_bridge_port *port) +{ + int err; + + port->multicast_eht_hosts_limit = BR_MCAST_DEFAULT_EHT_HOSTS_LIMIT; + br_multicast_port_ctx_init(port, NULL, &port->multicast_ctx); + err = br_mc_disabled_update(port->dev, br_opt_get(port->br, BROPT_MULTICAST_ENABLED), @@ -1711,10 +1894,7 @@ void br_multicast_del_port(struct net_bridge_port *port) hlist_move_list(&br->mcast_gc_list, &deleted_head); spin_unlock_bh(&br->multicast_lock); br_multicast_gc(&deleted_head); - del_timer_sync(&port->ip4_mc_router_timer); -#if IS_ENABLED(CONFIG_IPV6) - del_timer_sync(&port->ip6_mc_router_timer); -#endif + br_multicast_port_ctx_deinit(&port->multicast_ctx); free_percpu(port->mcast_stats); } @@ -1727,20 +1907,23 @@ static void br_multicast_enable(struct bridge_mcast_own_query *query) mod_timer(&query->timer, jiffies); } -static void __br_multicast_enable_port(struct net_bridge_port *port) +static void __br_multicast_enable_port_ctx(struct net_bridge_mcast_port *pmctx) { - struct net_bridge *br = port->br; + struct net_bridge *br = pmctx->port->br; + struct net_bridge_mcast *brmctx; - if (!br_opt_get(br, BROPT_MULTICAST_ENABLED) || !netif_running(br->dev)) + brmctx = br_multicast_port_ctx_get_global(pmctx); + if (!br_opt_get(br, BROPT_MULTICAST_ENABLED) || + !netif_running(br->dev)) return; - br_multicast_enable(&port->ip4_own_query); + br_multicast_enable(&pmctx->ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) - br_multicast_enable(&port->ip6_own_query); + br_multicast_enable(&pmctx->ip6_own_query); #endif - if (port->multicast_router == MDB_RTR_TYPE_PERM) { - br_ip4_multicast_add_router(br, port); - br_ip6_multicast_add_router(br, port); + if (pmctx->multicast_router == MDB_RTR_TYPE_PERM) { + br_ip4_multicast_add_router(brmctx, pmctx); + br_ip6_multicast_add_router(brmctx, pmctx); } } @@ -1748,33 +1931,39 @@ void br_multicast_enable_port(struct net_bridge_port *port) { struct net_bridge *br = port->br; - spin_lock(&br->multicast_lock); - __br_multicast_enable_port(port); - spin_unlock(&br->multicast_lock); + spin_lock_bh(&br->multicast_lock); + __br_multicast_enable_port_ctx(&port->multicast_ctx); + spin_unlock_bh(&br->multicast_lock); } -void br_multicast_disable_port(struct net_bridge_port *port) +static void __br_multicast_disable_port_ctx(struct net_bridge_mcast_port *pmctx) { - struct net_bridge *br = port->br; struct net_bridge_port_group *pg; struct hlist_node *n; bool del = false; - spin_lock(&br->multicast_lock); - hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) - if (!(pg->flags & MDB_PG_FLAGS_PERMANENT)) - br_multicast_find_del_pg(br, pg); + hlist_for_each_entry_safe(pg, n, &pmctx->port->mglist, mglist) + if (!(pg->flags & MDB_PG_FLAGS_PERMANENT) && + (!br_multicast_port_ctx_is_vlan(pmctx) || + pg->key.addr.vid == pmctx->vlan->vid)) + br_multicast_find_del_pg(pmctx->port->br, pg); - del |= br_ip4_multicast_rport_del(port); - del_timer(&port->ip4_mc_router_timer); - del_timer(&port->ip4_own_query.timer); - del |= br_ip6_multicast_rport_del(port); + del |= br_ip4_multicast_rport_del(pmctx); + del_timer(&pmctx->ip4_mc_router_timer); + del_timer(&pmctx->ip4_own_query.timer); + del |= br_ip6_multicast_rport_del(pmctx); #if IS_ENABLED(CONFIG_IPV6) - del_timer(&port->ip6_mc_router_timer); - del_timer(&port->ip6_own_query.timer); + del_timer(&pmctx->ip6_mc_router_timer); + del_timer(&pmctx->ip6_own_query.timer); #endif - br_multicast_rport_del_notify(port, del); - spin_unlock(&br->multicast_lock); + br_multicast_rport_del_notify(pmctx, del); +} + +void br_multicast_disable_port(struct net_bridge_port *port) +{ + spin_lock_bh(&port->br->multicast_lock); + __br_multicast_disable_port_ctx(&port->multicast_ctx); + spin_unlock_bh(&port->br->multicast_lock); } static int __grp_src_delete_marked(struct net_bridge_port_group *pg) @@ -1799,31 +1988,32 @@ static void __grp_src_mod_timer(struct net_bridge_group_src *src, br_multicast_fwd_src_handle(src); } -static void __grp_src_query_marked_and_rexmit(struct net_bridge_port_group *pg) +static void __grp_src_query_marked_and_rexmit(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, + struct net_bridge_port_group *pg) { struct bridge_mcast_other_query *other_query = NULL; - struct net_bridge *br = pg->key.port->br; - u32 lmqc = br->multicast_last_member_count; + u32 lmqc = brmctx->multicast_last_member_count; unsigned long lmqt, lmi, now = jiffies; struct net_bridge_group_src *ent; - if (!netif_running(br->dev) || - !br_opt_get(br, BROPT_MULTICAST_ENABLED)) + if (!netif_running(brmctx->br->dev) || + !br_opt_get(brmctx->br, BROPT_MULTICAST_ENABLED)) return; if (pg->key.addr.proto == htons(ETH_P_IP)) - other_query = &br->ip4_other_query; + other_query = &brmctx->ip4_other_query; #if IS_ENABLED(CONFIG_IPV6) else - other_query = &br->ip6_other_query; + other_query = &brmctx->ip6_other_query; #endif - lmqt = now + br_multicast_lmqt(br); + lmqt = now + br_multicast_lmqt(brmctx); hlist_for_each_entry(ent, &pg->src_list, node) { if (ent->flags & BR_SGRP_F_SEND) { ent->flags &= ~BR_SGRP_F_SEND; if (ent->timer.expires > lmqt) { - if (br_opt_get(br, BROPT_MULTICAST_QUERIER) && + if (brmctx->multicast_querier && other_query && !timer_pending(&other_query->timer)) ent->src_query_rexmit_cnt = lmqc; @@ -1832,41 +2022,42 @@ static void __grp_src_query_marked_and_rexmit(struct net_bridge_port_group *pg) } } - if (!br_opt_get(br, BROPT_MULTICAST_QUERIER) || + if (!brmctx->multicast_querier || !other_query || timer_pending(&other_query->timer)) return; - __br_multicast_send_query(br, pg->key.port, pg, &pg->key.addr, + __br_multicast_send_query(brmctx, pmctx, pg, &pg->key.addr, &pg->key.addr, true, 1, NULL); - lmi = now + br->multicast_last_member_interval; + lmi = now + brmctx->multicast_last_member_interval; if (!timer_pending(&pg->rexmit_timer) || time_after(pg->rexmit_timer.expires, lmi)) mod_timer(&pg->rexmit_timer, lmi); } -static void __grp_send_query_and_rexmit(struct net_bridge_port_group *pg) +static void __grp_send_query_and_rexmit(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, + struct net_bridge_port_group *pg) { struct bridge_mcast_other_query *other_query = NULL; - struct net_bridge *br = pg->key.port->br; unsigned long now = jiffies, lmi; - if (!netif_running(br->dev) || - !br_opt_get(br, BROPT_MULTICAST_ENABLED)) + if (!netif_running(brmctx->br->dev) || + !br_opt_get(brmctx->br, BROPT_MULTICAST_ENABLED)) return; if (pg->key.addr.proto == htons(ETH_P_IP)) - other_query = &br->ip4_other_query; + other_query = &brmctx->ip4_other_query; #if IS_ENABLED(CONFIG_IPV6) else - other_query = &br->ip6_other_query; + other_query = &brmctx->ip6_other_query; #endif - if (br_opt_get(br, BROPT_MULTICAST_QUERIER) && + if (brmctx->multicast_querier && other_query && !timer_pending(&other_query->timer)) { - lmi = now + br->multicast_last_member_interval; - pg->grp_query_rexmit_cnt = br->multicast_last_member_count - 1; - __br_multicast_send_query(br, pg->key.port, pg, &pg->key.addr, + lmi = now + brmctx->multicast_last_member_interval; + pg->grp_query_rexmit_cnt = brmctx->multicast_last_member_count - 1; + __br_multicast_send_query(brmctx, pmctx, pg, &pg->key.addr, &pg->key.addr, false, 0, NULL); if (!timer_pending(&pg->rexmit_timer) || time_after(pg->rexmit_timer.expires, lmi)) @@ -1875,8 +2066,8 @@ static void __grp_send_query_and_rexmit(struct net_bridge_port_group *pg) if (pg->filter_mode == MCAST_EXCLUDE && (!timer_pending(&pg->timer) || - time_after(pg->timer.expires, now + br_multicast_lmqt(br)))) - mod_timer(&pg->timer, now + br_multicast_lmqt(br)); + time_after(pg->timer.expires, now + br_multicast_lmqt(brmctx)))) + mod_timer(&pg->timer, now + br_multicast_lmqt(brmctx)); } /* State Msg type New state Actions @@ -1884,11 +2075,11 @@ static void __grp_send_query_and_rexmit(struct net_bridge_port_group *pg) * INCLUDE (A) ALLOW (B) INCLUDE (A+B) (B)=GMI * EXCLUDE (X,Y) ALLOW (A) EXCLUDE (X+A,Y-A) (A)=GMI */ -static bool br_multicast_isinc_allow(struct net_bridge_port_group *pg, void *h_addr, +static bool br_multicast_isinc_allow(const struct net_bridge_mcast *brmctx, + struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { - struct net_bridge *br = pg->key.port->br; struct net_bridge_group_src *ent; unsigned long now = jiffies; bool changed = false; @@ -1907,10 +2098,11 @@ static bool br_multicast_isinc_allow(struct net_bridge_port_group *pg, void *h_a } if (ent) - __grp_src_mod_timer(ent, now + br_multicast_gmi(br)); + __grp_src_mod_timer(ent, now + br_multicast_gmi(brmctx)); } - if (br_multicast_eht_handle(pg, h_addr, srcs, nsrcs, addr_size, grec_type)) + if (br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, + grec_type)) changed = true; return changed; @@ -1921,7 +2113,8 @@ static bool br_multicast_isinc_allow(struct net_bridge_port_group *pg, void *h_a * Delete (A-B) * Group Timer=GMI */ -static void __grp_src_isexc_incl(struct net_bridge_port_group *pg, void *h_addr, +static void __grp_src_isexc_incl(const struct net_bridge_mcast *brmctx, + struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { @@ -1945,7 +2138,8 @@ static void __grp_src_isexc_incl(struct net_bridge_port_group *pg, void *h_addr, br_multicast_fwd_src_handle(ent); } - br_multicast_eht_handle(pg, h_addr, srcs, nsrcs, addr_size, grec_type); + br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, + grec_type); __grp_src_delete_marked(pg); } @@ -1956,11 +2150,11 @@ static void __grp_src_isexc_incl(struct net_bridge_port_group *pg, void *h_addr, * Delete (Y-A) * Group Timer=GMI */ -static bool __grp_src_isexc_excl(struct net_bridge_port_group *pg, void *h_addr, +static bool __grp_src_isexc_excl(const struct net_bridge_mcast *brmctx, + struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { - struct net_bridge *br = pg->key.port->br; struct net_bridge_group_src *ent; unsigned long now = jiffies; bool changed = false; @@ -1981,13 +2175,14 @@ static bool __grp_src_isexc_excl(struct net_bridge_port_group *pg, void *h_addr, ent = br_multicast_new_group_src(pg, &src_ip); if (ent) { __grp_src_mod_timer(ent, - now + br_multicast_gmi(br)); + now + br_multicast_gmi(brmctx)); changed = true; } } } - if (br_multicast_eht_handle(pg, h_addr, srcs, nsrcs, addr_size, grec_type)) + if (br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, + grec_type)) changed = true; if (__grp_src_delete_marked(pg)) @@ -1996,28 +2191,28 @@ static bool __grp_src_isexc_excl(struct net_bridge_port_group *pg, void *h_addr, return changed; } -static bool br_multicast_isexc(struct net_bridge_port_group *pg, void *h_addr, +static bool br_multicast_isexc(const struct net_bridge_mcast *brmctx, + struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { - struct net_bridge *br = pg->key.port->br; bool changed = false; switch (pg->filter_mode) { case MCAST_INCLUDE: - __grp_src_isexc_incl(pg, h_addr, srcs, nsrcs, addr_size, + __grp_src_isexc_incl(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type); br_multicast_star_g_handle_mode(pg, MCAST_EXCLUDE); changed = true; break; case MCAST_EXCLUDE: - changed = __grp_src_isexc_excl(pg, h_addr, srcs, nsrcs, addr_size, - grec_type); + changed = __grp_src_isexc_excl(brmctx, pg, h_addr, srcs, nsrcs, + addr_size, grec_type); break; } pg->filter_mode = MCAST_EXCLUDE; - mod_timer(&pg->timer, jiffies + br_multicast_gmi(br)); + mod_timer(&pg->timer, jiffies + br_multicast_gmi(brmctx)); return changed; } @@ -2026,11 +2221,12 @@ static bool br_multicast_isexc(struct net_bridge_port_group *pg, void *h_addr, * INCLUDE (A) TO_IN (B) INCLUDE (A+B) (B)=GMI * Send Q(G,A-B) */ -static bool __grp_src_toin_incl(struct net_bridge_port_group *pg, void *h_addr, +static bool __grp_src_toin_incl(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, + struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { - struct net_bridge *br = pg->key.port->br; u32 src_idx, to_send = pg->src_ents; struct net_bridge_group_src *ent; unsigned long now = jiffies; @@ -2054,14 +2250,15 @@ static bool __grp_src_toin_incl(struct net_bridge_port_group *pg, void *h_addr, changed = true; } if (ent) - __grp_src_mod_timer(ent, now + br_multicast_gmi(br)); + __grp_src_mod_timer(ent, now + br_multicast_gmi(brmctx)); } - if (br_multicast_eht_handle(pg, h_addr, srcs, nsrcs, addr_size, grec_type)) + if (br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, + grec_type)) changed = true; if (to_send) - __grp_src_query_marked_and_rexmit(pg); + __grp_src_query_marked_and_rexmit(brmctx, pmctx, pg); return changed; } @@ -2071,11 +2268,12 @@ static bool __grp_src_toin_incl(struct net_bridge_port_group *pg, void *h_addr, * Send Q(G,X-A) * Send Q(G) */ -static bool __grp_src_toin_excl(struct net_bridge_port_group *pg, void *h_addr, +static bool __grp_src_toin_excl(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, + struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { - struct net_bridge *br = pg->key.port->br; u32 src_idx, to_send = pg->src_ents; struct net_bridge_group_src *ent; unsigned long now = jiffies; @@ -2102,21 +2300,24 @@ static bool __grp_src_toin_excl(struct net_bridge_port_group *pg, void *h_addr, changed = true; } if (ent) - __grp_src_mod_timer(ent, now + br_multicast_gmi(br)); + __grp_src_mod_timer(ent, now + br_multicast_gmi(brmctx)); } - if (br_multicast_eht_handle(pg, h_addr, srcs, nsrcs, addr_size, grec_type)) + if (br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, + grec_type)) changed = true; if (to_send) - __grp_src_query_marked_and_rexmit(pg); + __grp_src_query_marked_and_rexmit(brmctx, pmctx, pg); - __grp_send_query_and_rexmit(pg); + __grp_send_query_and_rexmit(brmctx, pmctx, pg); return changed; } -static bool br_multicast_toin(struct net_bridge_port_group *pg, void *h_addr, +static bool br_multicast_toin(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, + struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { @@ -2124,12 +2325,12 @@ static bool br_multicast_toin(struct net_bridge_port_group *pg, void *h_addr, switch (pg->filter_mode) { case MCAST_INCLUDE: - changed = __grp_src_toin_incl(pg, h_addr, srcs, nsrcs, addr_size, - grec_type); + changed = __grp_src_toin_incl(brmctx, pmctx, pg, h_addr, srcs, + nsrcs, addr_size, grec_type); break; case MCAST_EXCLUDE: - changed = __grp_src_toin_excl(pg, h_addr, srcs, nsrcs, addr_size, - grec_type); + changed = __grp_src_toin_excl(brmctx, pmctx, pg, h_addr, srcs, + nsrcs, addr_size, grec_type); break; } @@ -2151,7 +2352,9 @@ static bool br_multicast_toin(struct net_bridge_port_group *pg, void *h_addr, * Send Q(G,A*B) * Group Timer=GMI */ -static void __grp_src_toex_incl(struct net_bridge_port_group *pg, void *h_addr, +static void __grp_src_toex_incl(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, + struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { @@ -2178,11 +2381,12 @@ static void __grp_src_toex_incl(struct net_bridge_port_group *pg, void *h_addr, br_multicast_fwd_src_handle(ent); } - br_multicast_eht_handle(pg, h_addr, srcs, nsrcs, addr_size, grec_type); + br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, + grec_type); __grp_src_delete_marked(pg); if (to_send) - __grp_src_query_marked_and_rexmit(pg); + __grp_src_query_marked_and_rexmit(brmctx, pmctx, pg); } /* State Msg type New state Actions @@ -2192,7 +2396,9 @@ static void __grp_src_toex_incl(struct net_bridge_port_group *pg, void *h_addr, * Send Q(G,A-Y) * Group Timer=GMI */ -static bool __grp_src_toex_excl(struct net_bridge_port_group *pg, void *h_addr, +static bool __grp_src_toex_excl(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, + struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { @@ -2224,39 +2430,41 @@ static bool __grp_src_toex_excl(struct net_bridge_port_group *pg, void *h_addr, } } - if (br_multicast_eht_handle(pg, h_addr, srcs, nsrcs, addr_size, grec_type)) + if (br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, + grec_type)) changed = true; if (__grp_src_delete_marked(pg)) changed = true; if (to_send) - __grp_src_query_marked_and_rexmit(pg); + __grp_src_query_marked_and_rexmit(brmctx, pmctx, pg); return changed; } -static bool br_multicast_toex(struct net_bridge_port_group *pg, void *h_addr, +static bool br_multicast_toex(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, + struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { - struct net_bridge *br = pg->key.port->br; bool changed = false; switch (pg->filter_mode) { case MCAST_INCLUDE: - __grp_src_toex_incl(pg, h_addr, srcs, nsrcs, addr_size, - grec_type); + __grp_src_toex_incl(brmctx, pmctx, pg, h_addr, srcs, nsrcs, + addr_size, grec_type); br_multicast_star_g_handle_mode(pg, MCAST_EXCLUDE); changed = true; break; case MCAST_EXCLUDE: - changed = __grp_src_toex_excl(pg, h_addr, srcs, nsrcs, addr_size, - grec_type); + changed = __grp_src_toex_excl(brmctx, pmctx, pg, h_addr, srcs, + nsrcs, addr_size, grec_type); break; } pg->filter_mode = MCAST_EXCLUDE; - mod_timer(&pg->timer, jiffies + br_multicast_gmi(br)); + mod_timer(&pg->timer, jiffies + br_multicast_gmi(brmctx)); return changed; } @@ -2264,7 +2472,9 @@ static bool br_multicast_toex(struct net_bridge_port_group *pg, void *h_addr, /* State Msg type New state Actions * INCLUDE (A) BLOCK (B) INCLUDE (A) Send Q(G,A*B) */ -static bool __grp_src_block_incl(struct net_bridge_port_group *pg, void *h_addr, +static bool __grp_src_block_incl(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, + struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { struct net_bridge_group_src *ent; @@ -2286,11 +2496,12 @@ static bool __grp_src_block_incl(struct net_bridge_port_group *pg, void *h_addr, } } - if (br_multicast_eht_handle(pg, h_addr, srcs, nsrcs, addr_size, grec_type)) + if (br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, + grec_type)) changed = true; if (to_send) - __grp_src_query_marked_and_rexmit(pg); + __grp_src_query_marked_and_rexmit(brmctx, pmctx, pg); return changed; } @@ -2299,7 +2510,9 @@ static bool __grp_src_block_incl(struct net_bridge_port_group *pg, void *h_addr, * EXCLUDE (X,Y) BLOCK (A) EXCLUDE (X+(A-Y),Y) (A-X-Y)=Group Timer * Send Q(G,A-Y) */ -static bool __grp_src_block_excl(struct net_bridge_port_group *pg, void *h_addr, +static bool __grp_src_block_excl(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, + struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { struct net_bridge_group_src *ent; @@ -2328,28 +2541,31 @@ static bool __grp_src_block_excl(struct net_bridge_port_group *pg, void *h_addr, } } - if (br_multicast_eht_handle(pg, h_addr, srcs, nsrcs, addr_size, grec_type)) + if (br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, + grec_type)) changed = true; if (to_send) - __grp_src_query_marked_and_rexmit(pg); + __grp_src_query_marked_and_rexmit(brmctx, pmctx, pg); return changed; } -static bool br_multicast_block(struct net_bridge_port_group *pg, void *h_addr, +static bool br_multicast_block(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, + struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { bool changed = false; switch (pg->filter_mode) { case MCAST_INCLUDE: - changed = __grp_src_block_incl(pg, h_addr, srcs, nsrcs, addr_size, - grec_type); + changed = __grp_src_block_incl(brmctx, pmctx, pg, h_addr, srcs, + nsrcs, addr_size, grec_type); break; case MCAST_EXCLUDE: - changed = __grp_src_block_excl(pg, h_addr, srcs, nsrcs, addr_size, - grec_type); + changed = __grp_src_block_excl(brmctx, pmctx, pg, h_addr, srcs, + nsrcs, addr_size, grec_type); break; } @@ -2384,12 +2600,12 @@ br_multicast_find_port(struct net_bridge_mdb_entry *mp, return NULL; } -static int br_ip4_multicast_igmp3_report(struct net_bridge *br, - struct net_bridge_port *port, +static int br_ip4_multicast_igmp3_report(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, struct sk_buff *skb, u16 vid) { - bool igmpv2 = br->multicast_igmp_version == 2; + bool igmpv2 = brmctx->multicast_igmp_version == 2; struct net_bridge_mdb_entry *mdst; struct net_bridge_port_group *pg; const unsigned char *src; @@ -2436,25 +2652,29 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, if (nsrcs == 0 && (type == IGMPV3_CHANGE_TO_INCLUDE || type == IGMPV3_MODE_IS_INCLUDE)) { - if (!port || igmpv2) { - br_ip4_multicast_leave_group(br, port, group, vid, src); + if (!pmctx || igmpv2) { + br_ip4_multicast_leave_group(brmctx, pmctx, + group, vid, src); continue; } } else { - err = br_ip4_multicast_add_group(br, port, group, vid, - src, igmpv2); + err = br_ip4_multicast_add_group(brmctx, pmctx, group, + vid, src, igmpv2); if (err) break; } - if (!port || igmpv2) + if (!pmctx || igmpv2) continue; - spin_lock_bh(&br->multicast_lock); - mdst = br_mdb_ip4_get(br, group, vid); + spin_lock_bh(&brmctx->br->multicast_lock); + if (!br_multicast_ctx_should_use(brmctx, pmctx)) + goto unlock_continue; + + mdst = br_mdb_ip4_get(brmctx->br, group, vid); if (!mdst) goto unlock_continue; - pg = br_multicast_find_port(mdst, port, src); + pg = br_multicast_find_port(mdst, pmctx->port, src); if (!pg || (pg->flags & MDB_PG_FLAGS_PERMANENT)) goto unlock_continue; /* reload grec and host addr */ @@ -2462,51 +2682,57 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, h_addr = &ip_hdr(skb)->saddr; switch (type) { case IGMPV3_ALLOW_NEW_SOURCES: - changed = br_multicast_isinc_allow(pg, h_addr, grec->grec_src, + changed = br_multicast_isinc_allow(brmctx, pg, h_addr, + grec->grec_src, nsrcs, sizeof(__be32), type); break; case IGMPV3_MODE_IS_INCLUDE: - changed = br_multicast_isinc_allow(pg, h_addr, grec->grec_src, + changed = br_multicast_isinc_allow(brmctx, pg, h_addr, + grec->grec_src, nsrcs, sizeof(__be32), type); break; case IGMPV3_MODE_IS_EXCLUDE: - changed = br_multicast_isexc(pg, h_addr, grec->grec_src, + changed = br_multicast_isexc(brmctx, pg, h_addr, + grec->grec_src, nsrcs, sizeof(__be32), type); break; case IGMPV3_CHANGE_TO_INCLUDE: - changed = br_multicast_toin(pg, h_addr, grec->grec_src, + changed = br_multicast_toin(brmctx, pmctx, pg, h_addr, + grec->grec_src, nsrcs, sizeof(__be32), type); break; case IGMPV3_CHANGE_TO_EXCLUDE: - changed = br_multicast_toex(pg, h_addr, grec->grec_src, + changed = br_multicast_toex(brmctx, pmctx, pg, h_addr, + grec->grec_src, nsrcs, sizeof(__be32), type); break; case IGMPV3_BLOCK_OLD_SOURCES: - changed = br_multicast_block(pg, h_addr, grec->grec_src, + changed = br_multicast_block(brmctx, pmctx, pg, h_addr, + grec->grec_src, nsrcs, sizeof(__be32), type); break; } if (changed) - br_mdb_notify(br->dev, mdst, pg, RTM_NEWMDB); + br_mdb_notify(brmctx->br->dev, mdst, pg, RTM_NEWMDB); unlock_continue: - spin_unlock_bh(&br->multicast_lock); + spin_unlock_bh(&brmctx->br->multicast_lock); } return err; } #if IS_ENABLED(CONFIG_IPV6) -static int br_ip6_multicast_mld2_report(struct net_bridge *br, - struct net_bridge_port *port, +static int br_ip6_multicast_mld2_report(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, struct sk_buff *skb, u16 vid) { - bool mldv1 = br->multicast_mld_version == 1; + bool mldv1 = brmctx->multicast_mld_version == 1; struct net_bridge_mdb_entry *mdst; struct net_bridge_port_group *pg; unsigned int nsrcs_offset; + struct mld2_report *mld2r; const unsigned char *src; - struct icmp6hdr *icmp6h; struct in6_addr *h_addr; struct mld2_grec *grec; unsigned int grec_len; @@ -2514,12 +2740,12 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, int i, len, num; int err = 0; - if (!ipv6_mc_may_pull(skb, sizeof(*icmp6h))) + if (!ipv6_mc_may_pull(skb, sizeof(*mld2r))) return -EINVAL; - icmp6h = icmp6_hdr(skb); - num = ntohs(icmp6h->icmp6_dataun.un_data16[1]); - len = skb_transport_offset(skb) + sizeof(*icmp6h); + mld2r = (struct mld2_report *)icmp6_hdr(skb); + num = ntohs(mld2r->mld2r_ngrec); + len = skb_transport_offset(skb) + sizeof(*mld2r); for (i = 0; i < num; i++) { __be16 *_nsrcs, __nsrcs; @@ -2562,137 +2788,243 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, if ((grec->grec_type == MLD2_CHANGE_TO_INCLUDE || grec->grec_type == MLD2_MODE_IS_INCLUDE) && nsrcs == 0) { - if (!port || mldv1) { - br_ip6_multicast_leave_group(br, port, + if (!pmctx || mldv1) { + br_ip6_multicast_leave_group(brmctx, pmctx, &grec->grec_mca, vid, src); continue; } } else { - err = br_ip6_multicast_add_group(br, port, + err = br_ip6_multicast_add_group(brmctx, pmctx, &grec->grec_mca, vid, src, mldv1); if (err) break; } - if (!port || mldv1) + if (!pmctx || mldv1) continue; - spin_lock_bh(&br->multicast_lock); - mdst = br_mdb_ip6_get(br, &grec->grec_mca, vid); + spin_lock_bh(&brmctx->br->multicast_lock); + if (!br_multicast_ctx_should_use(brmctx, pmctx)) + goto unlock_continue; + + mdst = br_mdb_ip6_get(brmctx->br, &grec->grec_mca, vid); if (!mdst) goto unlock_continue; - pg = br_multicast_find_port(mdst, port, src); + pg = br_multicast_find_port(mdst, pmctx->port, src); if (!pg || (pg->flags & MDB_PG_FLAGS_PERMANENT)) goto unlock_continue; h_addr = &ipv6_hdr(skb)->saddr; switch (grec->grec_type) { case MLD2_ALLOW_NEW_SOURCES: - changed = br_multicast_isinc_allow(pg, h_addr, + changed = br_multicast_isinc_allow(brmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(struct in6_addr), grec->grec_type); break; case MLD2_MODE_IS_INCLUDE: - changed = br_multicast_isinc_allow(pg, h_addr, + changed = br_multicast_isinc_allow(brmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(struct in6_addr), grec->grec_type); break; case MLD2_MODE_IS_EXCLUDE: - changed = br_multicast_isexc(pg, h_addr, + changed = br_multicast_isexc(brmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(struct in6_addr), grec->grec_type); break; case MLD2_CHANGE_TO_INCLUDE: - changed = br_multicast_toin(pg, h_addr, + changed = br_multicast_toin(brmctx, pmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(struct in6_addr), grec->grec_type); break; case MLD2_CHANGE_TO_EXCLUDE: - changed = br_multicast_toex(pg, h_addr, + changed = br_multicast_toex(brmctx, pmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(struct in6_addr), grec->grec_type); break; case MLD2_BLOCK_OLD_SOURCES: - changed = br_multicast_block(pg, h_addr, + changed = br_multicast_block(brmctx, pmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(struct in6_addr), grec->grec_type); break; } if (changed) - br_mdb_notify(br->dev, mdst, pg, RTM_NEWMDB); + br_mdb_notify(brmctx->br->dev, mdst, pg, RTM_NEWMDB); unlock_continue: - spin_unlock_bh(&br->multicast_lock); + spin_unlock_bh(&brmctx->br->multicast_lock); } return err; } #endif -static bool br_ip4_multicast_select_querier(struct net_bridge *br, - struct net_bridge_port *port, - __be32 saddr) +static bool br_multicast_select_querier(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, + struct br_ip *saddr) { - if (!timer_pending(&br->ip4_own_query.timer) && - !timer_pending(&br->ip4_other_query.timer)) - goto update; + int port_ifidx = pmctx ? pmctx->port->dev->ifindex : 0; + struct timer_list *own_timer, *other_timer; + struct bridge_mcast_querier *querier; - if (!br->ip4_querier.addr.src.ip4) - goto update; + switch (saddr->proto) { + case htons(ETH_P_IP): + querier = &brmctx->ip4_querier; + own_timer = &brmctx->ip4_own_query.timer; + other_timer = &brmctx->ip4_other_query.timer; + if (!querier->addr.src.ip4 || + ntohl(saddr->src.ip4) <= ntohl(querier->addr.src.ip4)) + goto update; + break; +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + querier = &brmctx->ip6_querier; + own_timer = &brmctx->ip6_own_query.timer; + other_timer = &brmctx->ip6_other_query.timer; + if (ipv6_addr_cmp(&saddr->src.ip6, &querier->addr.src.ip6) <= 0) + goto update; + break; +#endif + default: + return false; + } - if (ntohl(saddr) <= ntohl(br->ip4_querier.addr.src.ip4)) + if (!timer_pending(own_timer) && !timer_pending(other_timer)) goto update; return false; update: - br->ip4_querier.addr.src.ip4 = saddr; - - /* update protected by general multicast_lock by caller */ - rcu_assign_pointer(br->ip4_querier.port, port); + br_multicast_update_querier(brmctx, querier, port_ifidx, saddr); return true; } +static struct net_bridge_port * +__br_multicast_get_querier_port(struct net_bridge *br, + const struct bridge_mcast_querier *querier) +{ + int port_ifidx = READ_ONCE(querier->port_ifidx); + struct net_bridge_port *p; + struct net_device *dev; + + if (port_ifidx == 0) + return NULL; + + dev = dev_get_by_index_rcu(dev_net(br->dev), port_ifidx); + if (!dev) + return NULL; + p = br_port_get_rtnl_rcu(dev); + if (!p || p->br != br) + return NULL; + + return p; +} + +size_t br_multicast_querier_state_size(void) +{ + return nla_total_size(0) + /* nest attribute */ + nla_total_size(sizeof(__be32)) + /* BRIDGE_QUERIER_IP_ADDRESS */ + nla_total_size(sizeof(int)) + /* BRIDGE_QUERIER_IP_PORT */ + nla_total_size_64bit(sizeof(u64)) + /* BRIDGE_QUERIER_IP_OTHER_TIMER */ #if IS_ENABLED(CONFIG_IPV6) -static bool br_ip6_multicast_select_querier(struct net_bridge *br, - struct net_bridge_port *port, - struct in6_addr *saddr) + nla_total_size(sizeof(struct in6_addr)) + /* BRIDGE_QUERIER_IPV6_ADDRESS */ + nla_total_size(sizeof(int)) + /* BRIDGE_QUERIER_IPV6_PORT */ + nla_total_size_64bit(sizeof(u64)) + /* BRIDGE_QUERIER_IPV6_OTHER_TIMER */ +#endif + 0; +} + +/* protected by rtnl or rcu */ +int br_multicast_dump_querier_state(struct sk_buff *skb, + const struct net_bridge_mcast *brmctx, + int nest_attr) { - if (!timer_pending(&br->ip6_own_query.timer) && - !timer_pending(&br->ip6_other_query.timer)) - goto update; + struct bridge_mcast_querier querier = {}; + struct net_bridge_port *p; + struct nlattr *nest; - if (ipv6_addr_cmp(saddr, &br->ip6_querier.addr.src.ip6) <= 0) - goto update; + if (!br_opt_get(brmctx->br, BROPT_MULTICAST_ENABLED) || + br_multicast_ctx_vlan_global_disabled(brmctx)) + return 0; - return false; + nest = nla_nest_start(skb, nest_attr); + if (!nest) + return -EMSGSIZE; -update: - br->ip6_querier.addr.src.ip6 = *saddr; + rcu_read_lock(); + if (!brmctx->multicast_querier && + !timer_pending(&brmctx->ip4_other_query.timer)) + goto out_v6; + + br_multicast_read_querier(&brmctx->ip4_querier, &querier); + if (nla_put_in_addr(skb, BRIDGE_QUERIER_IP_ADDRESS, + querier.addr.src.ip4)) { + rcu_read_unlock(); + goto out_err; + } - /* update protected by general multicast_lock by caller */ - rcu_assign_pointer(br->ip6_querier.port, port); + p = __br_multicast_get_querier_port(brmctx->br, &querier); + if (timer_pending(&brmctx->ip4_other_query.timer) && + (nla_put_u64_64bit(skb, BRIDGE_QUERIER_IP_OTHER_TIMER, + br_timer_value(&brmctx->ip4_other_query.timer), + BRIDGE_QUERIER_PAD) || + (p && nla_put_u32(skb, BRIDGE_QUERIER_IP_PORT, p->dev->ifindex)))) { + rcu_read_unlock(); + goto out_err; + } - return true; -} +out_v6: +#if IS_ENABLED(CONFIG_IPV6) + if (!brmctx->multicast_querier && + !timer_pending(&brmctx->ip6_other_query.timer)) + goto out; + + br_multicast_read_querier(&brmctx->ip6_querier, &querier); + if (nla_put_in6_addr(skb, BRIDGE_QUERIER_IPV6_ADDRESS, + &querier.addr.src.ip6)) { + rcu_read_unlock(); + goto out_err; + } + + p = __br_multicast_get_querier_port(brmctx->br, &querier); + if (timer_pending(&brmctx->ip6_other_query.timer) && + (nla_put_u64_64bit(skb, BRIDGE_QUERIER_IPV6_OTHER_TIMER, + br_timer_value(&brmctx->ip6_other_query.timer), + BRIDGE_QUERIER_PAD) || + (p && nla_put_u32(skb, BRIDGE_QUERIER_IPV6_PORT, + p->dev->ifindex)))) { + rcu_read_unlock(); + goto out_err; + } +out: #endif + rcu_read_unlock(); + nla_nest_end(skb, nest); + if (!nla_len(nest)) + nla_nest_cancel(skb, nest); + + return 0; + +out_err: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} static void -br_multicast_update_query_timer(struct net_bridge *br, +br_multicast_update_query_timer(struct net_bridge_mcast *brmctx, struct bridge_mcast_other_query *query, unsigned long max_delay) { if (!timer_pending(&query->timer)) query->delay_time = jiffies + max_delay; - mod_timer(&query->timer, jiffies + br->multicast_querier_interval); + mod_timer(&query->timer, jiffies + brmctx->multicast_querier_interval); } static void br_port_mc_router_state_change(struct net_bridge_port *p, @@ -2709,19 +3041,26 @@ static void br_port_mc_router_state_change(struct net_bridge_port *p, } static struct net_bridge_port * -br_multicast_rport_from_node(struct net_bridge *br, +br_multicast_rport_from_node(struct net_bridge_mcast *brmctx, struct hlist_head *mc_router_list, struct hlist_node *rlist) { + struct net_bridge_mcast_port *pmctx; + #if IS_ENABLED(CONFIG_IPV6) - if (mc_router_list == &br->ip6_mc_router_list) - return hlist_entry(rlist, struct net_bridge_port, ip6_rlist); + if (mc_router_list == &brmctx->ip6_mc_router_list) + pmctx = hlist_entry(rlist, struct net_bridge_mcast_port, + ip6_rlist); + else #endif - return hlist_entry(rlist, struct net_bridge_port, ip4_rlist); + pmctx = hlist_entry(rlist, struct net_bridge_mcast_port, + ip4_rlist); + + return pmctx->port; } static struct hlist_node * -br_multicast_get_rport_slot(struct net_bridge *br, +br_multicast_get_rport_slot(struct net_bridge_mcast *brmctx, struct net_bridge_port *port, struct hlist_head *mc_router_list) @@ -2731,7 +3070,7 @@ br_multicast_get_rport_slot(struct net_bridge *br, struct hlist_node *rlist; hlist_for_each(rlist, mc_router_list) { - p = br_multicast_rport_from_node(br, mc_router_list, rlist); + p = br_multicast_rport_from_node(brmctx, mc_router_list, rlist); if ((unsigned long)port >= (unsigned long)p) break; @@ -2742,14 +3081,14 @@ br_multicast_get_rport_slot(struct net_bridge *br, return slot; } -static bool br_multicast_no_router_otherpf(struct net_bridge_port *port, +static bool br_multicast_no_router_otherpf(struct net_bridge_mcast_port *pmctx, struct hlist_node *rnode) { #if IS_ENABLED(CONFIG_IPV6) - if (rnode != &port->ip6_rlist) - return hlist_unhashed(&port->ip6_rlist); + if (rnode != &pmctx->ip6_rlist) + return hlist_unhashed(&pmctx->ip6_rlist); else - return hlist_unhashed(&port->ip4_rlist); + return hlist_unhashed(&pmctx->ip4_rlist); #else return true; #endif @@ -2759,8 +3098,8 @@ static bool br_multicast_no_router_otherpf(struct net_bridge_port *port, * list is maintained ordered by pointer value * and locked by br->multicast_lock and RCU */ -static void br_multicast_add_router(struct net_bridge *br, - struct net_bridge_port *port, +static void br_multicast_add_router(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, struct hlist_node *rlist, struct hlist_head *mc_router_list) { @@ -2769,7 +3108,7 @@ static void br_multicast_add_router(struct net_bridge *br, if (!hlist_unhashed(rlist)) return; - slot = br_multicast_get_rport_slot(br, port, mc_router_list); + slot = br_multicast_get_rport_slot(brmctx, pmctx->port, mc_router_list); if (slot) hlist_add_behind_rcu(rlist, slot); @@ -2780,9 +3119,9 @@ static void br_multicast_add_router(struct net_bridge *br, * switched from no IPv4/IPv6 multicast router to a new * IPv4 or IPv6 multicast router. */ - if (br_multicast_no_router_otherpf(port, rlist)) { - br_rtr_notify(br->dev, port, RTM_NEWMDB); - br_port_mc_router_state_change(port, true); + if (br_multicast_no_router_otherpf(pmctx, rlist)) { + br_rtr_notify(pmctx->port->br->dev, pmctx, RTM_NEWMDB); + br_port_mc_router_state_change(pmctx->port, true); } } @@ -2790,116 +3129,119 @@ static void br_multicast_add_router(struct net_bridge *br, * list is maintained ordered by pointer value * and locked by br->multicast_lock and RCU */ -static void br_ip4_multicast_add_router(struct net_bridge *br, - struct net_bridge_port *port) +static void br_ip4_multicast_add_router(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx) { - br_multicast_add_router(br, port, &port->ip4_rlist, - &br->ip4_mc_router_list); + br_multicast_add_router(brmctx, pmctx, &pmctx->ip4_rlist, + &brmctx->ip4_mc_router_list); } /* Add port to router_list * list is maintained ordered by pointer value * and locked by br->multicast_lock and RCU */ -static void br_ip6_multicast_add_router(struct net_bridge *br, - struct net_bridge_port *port) +static void br_ip6_multicast_add_router(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx) { #if IS_ENABLED(CONFIG_IPV6) - br_multicast_add_router(br, port, &port->ip6_rlist, - &br->ip6_mc_router_list); + br_multicast_add_router(brmctx, pmctx, &pmctx->ip6_rlist, + &brmctx->ip6_mc_router_list); #endif } -static void br_multicast_mark_router(struct net_bridge *br, - struct net_bridge_port *port, +static void br_multicast_mark_router(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, struct timer_list *timer, struct hlist_node *rlist, struct hlist_head *mc_router_list) { unsigned long now = jiffies; - if (!port) { - if (br->multicast_router == MDB_RTR_TYPE_TEMP_QUERY) { - if (!br_ip4_multicast_is_router(br) && - !br_ip6_multicast_is_router(br)) - br_mc_router_state_change(br, true); - mod_timer(timer, now + br->multicast_querier_interval); + if (!br_multicast_ctx_should_use(brmctx, pmctx)) + return; + + if (!pmctx) { + if (brmctx->multicast_router == MDB_RTR_TYPE_TEMP_QUERY) { + if (!br_ip4_multicast_is_router(brmctx) && + !br_ip6_multicast_is_router(brmctx)) + br_mc_router_state_change(brmctx->br, true); + mod_timer(timer, now + brmctx->multicast_querier_interval); } return; } - if (port->multicast_router == MDB_RTR_TYPE_DISABLED || - port->multicast_router == MDB_RTR_TYPE_PERM) + if (pmctx->multicast_router == MDB_RTR_TYPE_DISABLED || + pmctx->multicast_router == MDB_RTR_TYPE_PERM) return; - br_multicast_add_router(br, port, rlist, mc_router_list); - mod_timer(timer, now + br->multicast_querier_interval); + br_multicast_add_router(brmctx, pmctx, rlist, mc_router_list); + mod_timer(timer, now + brmctx->multicast_querier_interval); } -static void br_ip4_multicast_mark_router(struct net_bridge *br, - struct net_bridge_port *port) +static void br_ip4_multicast_mark_router(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx) { - struct timer_list *timer = &br->ip4_mc_router_timer; + struct timer_list *timer = &brmctx->ip4_mc_router_timer; struct hlist_node *rlist = NULL; - if (port) { - timer = &port->ip4_mc_router_timer; - rlist = &port->ip4_rlist; + if (pmctx) { + timer = &pmctx->ip4_mc_router_timer; + rlist = &pmctx->ip4_rlist; } - br_multicast_mark_router(br, port, timer, rlist, - &br->ip4_mc_router_list); + br_multicast_mark_router(brmctx, pmctx, timer, rlist, + &brmctx->ip4_mc_router_list); } -static void br_ip6_multicast_mark_router(struct net_bridge *br, - struct net_bridge_port *port) +static void br_ip6_multicast_mark_router(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx) { #if IS_ENABLED(CONFIG_IPV6) - struct timer_list *timer = &br->ip6_mc_router_timer; + struct timer_list *timer = &brmctx->ip6_mc_router_timer; struct hlist_node *rlist = NULL; - if (port) { - timer = &port->ip6_mc_router_timer; - rlist = &port->ip6_rlist; + if (pmctx) { + timer = &pmctx->ip6_mc_router_timer; + rlist = &pmctx->ip6_rlist; } - br_multicast_mark_router(br, port, timer, rlist, - &br->ip6_mc_router_list); + br_multicast_mark_router(brmctx, pmctx, timer, rlist, + &brmctx->ip6_mc_router_list); #endif } static void -br_ip4_multicast_query_received(struct net_bridge *br, - struct net_bridge_port *port, +br_ip4_multicast_query_received(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, struct bridge_mcast_other_query *query, struct br_ip *saddr, unsigned long max_delay) { - if (!br_ip4_multicast_select_querier(br, port, saddr->src.ip4)) + if (!br_multicast_select_querier(brmctx, pmctx, saddr)) return; - br_multicast_update_query_timer(br, query, max_delay); - br_ip4_multicast_mark_router(br, port); + br_multicast_update_query_timer(brmctx, query, max_delay); + br_ip4_multicast_mark_router(brmctx, pmctx); } #if IS_ENABLED(CONFIG_IPV6) static void -br_ip6_multicast_query_received(struct net_bridge *br, - struct net_bridge_port *port, +br_ip6_multicast_query_received(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, struct bridge_mcast_other_query *query, struct br_ip *saddr, unsigned long max_delay) { - if (!br_ip6_multicast_select_querier(br, port, &saddr->src.ip6)) + if (!br_multicast_select_querier(brmctx, pmctx, saddr)) return; - br_multicast_update_query_timer(br, query, max_delay); - br_ip6_multicast_mark_router(br, port); + br_multicast_update_query_timer(brmctx, query, max_delay); + br_ip6_multicast_mark_router(brmctx, pmctx); } #endif -static void br_ip4_multicast_query(struct net_bridge *br, - struct net_bridge_port *port, +static void br_ip4_multicast_query(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, struct sk_buff *skb, u16 vid) { @@ -2910,14 +3252,13 @@ static void br_ip4_multicast_query(struct net_bridge *br, struct igmpv3_query *ih3; struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; - struct br_ip saddr; + struct br_ip saddr = {}; unsigned long max_delay; unsigned long now = jiffies; __be32 group; - spin_lock(&br->multicast_lock); - if (!netif_running(br->dev) || - (port && port->state == BR_STATE_DISABLED)) + spin_lock(&brmctx->br->multicast_lock); + if (!br_multicast_ctx_should_use(brmctx, pmctx)) goto out; group = ih->group; @@ -2932,7 +3273,8 @@ static void br_ip4_multicast_query(struct net_bridge *br, } else if (transport_len >= sizeof(*ih3)) { ih3 = igmpv3_query_hdr(skb); if (ih3->nsrcs || - (br->multicast_igmp_version == 3 && group && ih3->suppress)) + (brmctx->multicast_igmp_version == 3 && group && + ih3->suppress)) goto out; max_delay = ih3->code ? @@ -2945,16 +3287,17 @@ static void br_ip4_multicast_query(struct net_bridge *br, saddr.proto = htons(ETH_P_IP); saddr.src.ip4 = iph->saddr; - br_ip4_multicast_query_received(br, port, &br->ip4_other_query, + br_ip4_multicast_query_received(brmctx, pmctx, + &brmctx->ip4_other_query, &saddr, max_delay); goto out; } - mp = br_mdb_ip4_get(br, group, vid); + mp = br_mdb_ip4_get(brmctx->br, group, vid); if (!mp) goto out; - max_delay *= br->multicast_last_member_count; + max_delay *= brmctx->multicast_last_member_count; if (mp->host_joined && (timer_pending(&mp->timer) ? @@ -2963,23 +3306,23 @@ static void br_ip4_multicast_query(struct net_bridge *br, mod_timer(&mp->timer, now + max_delay); for (pp = &mp->ports; - (p = mlock_dereference(*pp, br)) != NULL; + (p = mlock_dereference(*pp, brmctx->br)) != NULL; pp = &p->next) { if (timer_pending(&p->timer) ? time_after(p->timer.expires, now + max_delay) : try_to_del_timer_sync(&p->timer) >= 0 && - (br->multicast_igmp_version == 2 || + (brmctx->multicast_igmp_version == 2 || p->filter_mode == MCAST_EXCLUDE)) mod_timer(&p->timer, now + max_delay); } out: - spin_unlock(&br->multicast_lock); + spin_unlock(&brmctx->br->multicast_lock); } #if IS_ENABLED(CONFIG_IPV6) -static int br_ip6_multicast_query(struct net_bridge *br, - struct net_bridge_port *port, +static int br_ip6_multicast_query(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, struct sk_buff *skb, u16 vid) { @@ -2989,7 +3332,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, struct mld2_query *mld2q; struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; - struct br_ip saddr; + struct br_ip saddr = {}; unsigned long max_delay; unsigned long now = jiffies; unsigned int offset = skb_transport_offset(skb); @@ -2997,9 +3340,8 @@ static int br_ip6_multicast_query(struct net_bridge *br, bool is_general_query; int err = 0; - spin_lock(&br->multicast_lock); - if (!netif_running(br->dev) || - (port && port->state == BR_STATE_DISABLED)) + spin_lock(&brmctx->br->multicast_lock); + if (!br_multicast_ctx_should_use(brmctx, pmctx)) goto out; if (transport_len == sizeof(*mld)) { @@ -3019,7 +3361,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, mld2q = (struct mld2_query *)icmp6_hdr(skb); if (!mld2q->mld2q_nsrcs) group = &mld2q->mld2q_mca; - if (br->multicast_mld_version == 2 && + if (brmctx->multicast_mld_version == 2 && !ipv6_addr_any(&mld2q->mld2q_mca) && mld2q->mld2q_suppress) goto out; @@ -3033,18 +3375,19 @@ static int br_ip6_multicast_query(struct net_bridge *br, saddr.proto = htons(ETH_P_IPV6); saddr.src.ip6 = ipv6_hdr(skb)->saddr; - br_ip6_multicast_query_received(br, port, &br->ip6_other_query, + br_ip6_multicast_query_received(brmctx, pmctx, + &brmctx->ip6_other_query, &saddr, max_delay); goto out; } else if (!group) { goto out; } - mp = br_mdb_ip6_get(br, group, vid); + mp = br_mdb_ip6_get(brmctx->br, group, vid); if (!mp) goto out; - max_delay *= br->multicast_last_member_count; + max_delay *= brmctx->multicast_last_member_count; if (mp->host_joined && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, now + max_delay) : @@ -3052,25 +3395,25 @@ static int br_ip6_multicast_query(struct net_bridge *br, mod_timer(&mp->timer, now + max_delay); for (pp = &mp->ports; - (p = mlock_dereference(*pp, br)) != NULL; + (p = mlock_dereference(*pp, brmctx->br)) != NULL; pp = &p->next) { if (timer_pending(&p->timer) ? time_after(p->timer.expires, now + max_delay) : try_to_del_timer_sync(&p->timer) >= 0 && - (br->multicast_mld_version == 1 || + (brmctx->multicast_mld_version == 1 || p->filter_mode == MCAST_EXCLUDE)) mod_timer(&p->timer, now + max_delay); } out: - spin_unlock(&br->multicast_lock); + spin_unlock(&brmctx->br->multicast_lock); return err; } #endif static void -br_multicast_leave_group(struct net_bridge *br, - struct net_bridge_port *port, +br_multicast_leave_group(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, struct br_ip *group, struct bridge_mcast_other_query *other_query, struct bridge_mcast_own_query *own_query, @@ -3081,22 +3424,21 @@ br_multicast_leave_group(struct net_bridge *br, unsigned long now; unsigned long time; - spin_lock(&br->multicast_lock); - if (!netif_running(br->dev) || - (port && port->state == BR_STATE_DISABLED)) + spin_lock(&brmctx->br->multicast_lock); + if (!br_multicast_ctx_should_use(brmctx, pmctx)) goto out; - mp = br_mdb_ip_get(br, group); + mp = br_mdb_ip_get(brmctx->br, group); if (!mp) goto out; - if (port && (port->flags & BR_MULTICAST_FAST_LEAVE)) { + if (pmctx && (pmctx->port->flags & BR_MULTICAST_FAST_LEAVE)) { struct net_bridge_port_group __rcu **pp; for (pp = &mp->ports; - (p = mlock_dereference(*pp, br)) != NULL; + (p = mlock_dereference(*pp, brmctx->br)) != NULL; pp = &p->next) { - if (!br_port_group_equal(p, port, src)) + if (!br_port_group_equal(p, pmctx->port, src)) continue; if (p->flags & MDB_PG_FLAGS_PERMANENT) @@ -3111,19 +3453,19 @@ br_multicast_leave_group(struct net_bridge *br, if (timer_pending(&other_query->timer)) goto out; - if (br_opt_get(br, BROPT_MULTICAST_QUERIER)) { - __br_multicast_send_query(br, port, NULL, NULL, &mp->addr, + if (brmctx->multicast_querier) { + __br_multicast_send_query(brmctx, pmctx, NULL, NULL, &mp->addr, false, 0, NULL); - time = jiffies + br->multicast_last_member_count * - br->multicast_last_member_interval; + time = jiffies + brmctx->multicast_last_member_count * + brmctx->multicast_last_member_interval; mod_timer(&own_query->timer, time); - for (p = mlock_dereference(mp->ports, br); - p != NULL; - p = mlock_dereference(p->next, br)) { - if (!br_port_group_equal(p, port, src)) + for (p = mlock_dereference(mp->ports, brmctx->br); + p != NULL && pmctx != NULL; + p = mlock_dereference(p->next, brmctx->br)) { + if (!br_port_group_equal(p, pmctx->port, src)) continue; if (!hlist_unhashed(&p->mglist) && @@ -3138,10 +3480,10 @@ br_multicast_leave_group(struct net_bridge *br, } now = jiffies; - time = now + br->multicast_last_member_count * - br->multicast_last_member_interval; + time = now + brmctx->multicast_last_member_count * + brmctx->multicast_last_member_interval; - if (!port) { + if (!pmctx) { if (mp->host_joined && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, time) : @@ -3152,10 +3494,10 @@ br_multicast_leave_group(struct net_bridge *br, goto out; } - for (p = mlock_dereference(mp->ports, br); + for (p = mlock_dereference(mp->ports, brmctx->br); p != NULL; - p = mlock_dereference(p->next, br)) { - if (p->key.port != port) + p = mlock_dereference(p->next, brmctx->br)) { + if (p->key.port != pmctx->port) continue; if (!hlist_unhashed(&p->mglist) && @@ -3168,11 +3510,11 @@ br_multicast_leave_group(struct net_bridge *br, break; } out: - spin_unlock(&br->multicast_lock); + spin_unlock(&brmctx->br->multicast_lock); } -static void br_ip4_multicast_leave_group(struct net_bridge *br, - struct net_bridge_port *port, +static void br_ip4_multicast_leave_group(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, __be32 group, __u16 vid, const unsigned char *src) @@ -3183,20 +3525,21 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br, if (ipv4_is_local_multicast(group)) return; - own_query = port ? &port->ip4_own_query : &br->ip4_own_query; + own_query = pmctx ? &pmctx->ip4_own_query : &brmctx->ip4_own_query; memset(&br_group, 0, sizeof(br_group)); br_group.dst.ip4 = group; br_group.proto = htons(ETH_P_IP); br_group.vid = vid; - br_multicast_leave_group(br, port, &br_group, &br->ip4_other_query, + br_multicast_leave_group(brmctx, pmctx, &br_group, + &brmctx->ip4_other_query, own_query, src); } #if IS_ENABLED(CONFIG_IPV6) -static void br_ip6_multicast_leave_group(struct net_bridge *br, - struct net_bridge_port *port, +static void br_ip6_multicast_leave_group(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, const struct in6_addr *group, __u16 vid, const unsigned char *src) @@ -3207,14 +3550,15 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br, if (ipv6_addr_is_ll_all_nodes(group)) return; - own_query = port ? &port->ip6_own_query : &br->ip6_own_query; + own_query = pmctx ? &pmctx->ip6_own_query : &brmctx->ip6_own_query; memset(&br_group, 0, sizeof(br_group)); br_group.dst.ip6 = *group; br_group.proto = htons(ETH_P_IPV6); br_group.vid = vid; - br_multicast_leave_group(br, port, &br_group, &br->ip6_other_query, + br_multicast_leave_group(brmctx, pmctx, &br_group, + &brmctx->ip6_other_query, own_query, src); } #endif @@ -3252,8 +3596,8 @@ static void br_multicast_err_count(const struct net_bridge *br, u64_stats_update_end(&pstats->syncp); } -static void br_multicast_pim(struct net_bridge *br, - struct net_bridge_port *port, +static void br_multicast_pim(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, const struct sk_buff *skb) { unsigned int offset = skb_transport_offset(skb); @@ -3264,31 +3608,32 @@ static void br_multicast_pim(struct net_bridge *br, pim_hdr_type(pimhdr) != PIM_TYPE_HELLO) return; - spin_lock(&br->multicast_lock); - br_ip4_multicast_mark_router(br, port); - spin_unlock(&br->multicast_lock); + spin_lock(&brmctx->br->multicast_lock); + br_ip4_multicast_mark_router(brmctx, pmctx); + spin_unlock(&brmctx->br->multicast_lock); } -static int br_ip4_multicast_mrd_rcv(struct net_bridge *br, - struct net_bridge_port *port, +static int br_ip4_multicast_mrd_rcv(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, struct sk_buff *skb) { if (ip_hdr(skb)->protocol != IPPROTO_IGMP || igmp_hdr(skb)->type != IGMP_MRDISC_ADV) return -ENOMSG; - spin_lock(&br->multicast_lock); - br_ip4_multicast_mark_router(br, port); - spin_unlock(&br->multicast_lock); + spin_lock(&brmctx->br->multicast_lock); + br_ip4_multicast_mark_router(brmctx, pmctx); + spin_unlock(&brmctx->br->multicast_lock); return 0; } -static int br_multicast_ipv4_rcv(struct net_bridge *br, - struct net_bridge_port *port, +static int br_multicast_ipv4_rcv(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, struct sk_buff *skb, u16 vid) { + struct net_bridge_port *p = pmctx ? pmctx->port : NULL; const unsigned char *src; struct igmphdr *ih; int err; @@ -3300,14 +3645,14 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, BR_INPUT_SKB_CB(skb)->mrouters_only = 1; } else if (pim_ipv4_all_pim_routers(ip_hdr(skb)->daddr)) { if (ip_hdr(skb)->protocol == IPPROTO_PIM) - br_multicast_pim(br, port, skb); + br_multicast_pim(brmctx, pmctx, skb); } else if (ipv4_is_all_snoopers(ip_hdr(skb)->daddr)) { - br_ip4_multicast_mrd_rcv(br, port, skb); + br_ip4_multicast_mrd_rcv(brmctx, pmctx, skb); } return 0; } else if (err < 0) { - br_multicast_err_count(br, port, skb->protocol); + br_multicast_err_count(brmctx->br, p, skb->protocol); return err; } @@ -3319,44 +3664,45 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: BR_INPUT_SKB_CB(skb)->mrouters_only = 1; - err = br_ip4_multicast_add_group(br, port, ih->group, vid, src, - true); + err = br_ip4_multicast_add_group(brmctx, pmctx, ih->group, vid, + src, true); break; case IGMPV3_HOST_MEMBERSHIP_REPORT: - err = br_ip4_multicast_igmp3_report(br, port, skb, vid); + err = br_ip4_multicast_igmp3_report(brmctx, pmctx, skb, vid); break; case IGMP_HOST_MEMBERSHIP_QUERY: - br_ip4_multicast_query(br, port, skb, vid); + br_ip4_multicast_query(brmctx, pmctx, skb, vid); break; case IGMP_HOST_LEAVE_MESSAGE: - br_ip4_multicast_leave_group(br, port, ih->group, vid, src); + br_ip4_multicast_leave_group(brmctx, pmctx, ih->group, vid, src); break; } - br_multicast_count(br, port, skb, BR_INPUT_SKB_CB(skb)->igmp, + br_multicast_count(brmctx->br, p, skb, BR_INPUT_SKB_CB(skb)->igmp, BR_MCAST_DIR_RX); return err; } #if IS_ENABLED(CONFIG_IPV6) -static void br_ip6_multicast_mrd_rcv(struct net_bridge *br, - struct net_bridge_port *port, +static void br_ip6_multicast_mrd_rcv(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, struct sk_buff *skb) { if (icmp6_hdr(skb)->icmp6_type != ICMPV6_MRDISC_ADV) return; - spin_lock(&br->multicast_lock); - br_ip6_multicast_mark_router(br, port); - spin_unlock(&br->multicast_lock); + spin_lock(&brmctx->br->multicast_lock); + br_ip6_multicast_mark_router(brmctx, pmctx); + spin_unlock(&brmctx->br->multicast_lock); } -static int br_multicast_ipv6_rcv(struct net_bridge *br, - struct net_bridge_port *port, +static int br_multicast_ipv6_rcv(struct net_bridge_mcast *brmctx, + struct net_bridge_mcast_port *pmctx, struct sk_buff *skb, u16 vid) { + struct net_bridge_port *p = pmctx ? pmctx->port : NULL; const unsigned char *src; struct mld_msg *mld; int err; @@ -3368,11 +3714,11 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, BR_INPUT_SKB_CB(skb)->mrouters_only = 1; if (err == -ENODATA && ipv6_addr_is_all_snoopers(&ipv6_hdr(skb)->daddr)) - br_ip6_multicast_mrd_rcv(br, port, skb); + br_ip6_multicast_mrd_rcv(brmctx, pmctx, skb); return 0; } else if (err < 0) { - br_multicast_err_count(br, port, skb->protocol); + br_multicast_err_count(brmctx->br, p, skb->protocol); return err; } @@ -3383,29 +3729,32 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, case ICMPV6_MGM_REPORT: src = eth_hdr(skb)->h_source; BR_INPUT_SKB_CB(skb)->mrouters_only = 1; - err = br_ip6_multicast_add_group(br, port, &mld->mld_mca, vid, - src, true); + err = br_ip6_multicast_add_group(brmctx, pmctx, &mld->mld_mca, + vid, src, true); break; case ICMPV6_MLD2_REPORT: - err = br_ip6_multicast_mld2_report(br, port, skb, vid); + err = br_ip6_multicast_mld2_report(brmctx, pmctx, skb, vid); break; case ICMPV6_MGM_QUERY: - err = br_ip6_multicast_query(br, port, skb, vid); + err = br_ip6_multicast_query(brmctx, pmctx, skb, vid); break; case ICMPV6_MGM_REDUCTION: src = eth_hdr(skb)->h_source; - br_ip6_multicast_leave_group(br, port, &mld->mld_mca, vid, src); + br_ip6_multicast_leave_group(brmctx, pmctx, &mld->mld_mca, vid, + src); break; } - br_multicast_count(br, port, skb, BR_INPUT_SKB_CB(skb)->igmp, + br_multicast_count(brmctx->br, p, skb, BR_INPUT_SKB_CB(skb)->igmp, BR_MCAST_DIR_RX); return err; } #endif -int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, +int br_multicast_rcv(struct net_bridge_mcast **brmctx, + struct net_bridge_mcast_port **pmctx, + struct net_bridge_vlan *vlan, struct sk_buff *skb, u16 vid) { int ret = 0; @@ -3413,16 +3762,36 @@ int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, BR_INPUT_SKB_CB(skb)->igmp = 0; BR_INPUT_SKB_CB(skb)->mrouters_only = 0; - if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) + if (!br_opt_get((*brmctx)->br, BROPT_MULTICAST_ENABLED)) return 0; + if (br_opt_get((*brmctx)->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED) && vlan) { + const struct net_bridge_vlan *masterv; + + /* the vlan has the master flag set only when transmitting + * through the bridge device + */ + if (br_vlan_is_master(vlan)) { + masterv = vlan; + *brmctx = &vlan->br_mcast_ctx; + *pmctx = NULL; + } else { + masterv = vlan->brvlan; + *brmctx = &vlan->brvlan->br_mcast_ctx; + *pmctx = &vlan->port_mcast_ctx; + } + + if (!(masterv->priv_flags & BR_VLFLAG_GLOBAL_MCAST_ENABLED)) + return 0; + } + switch (skb->protocol) { case htons(ETH_P_IP): - ret = br_multicast_ipv4_rcv(br, port, skb, vid); + ret = br_multicast_ipv4_rcv(*brmctx, *pmctx, skb, vid); break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): - ret = br_multicast_ipv6_rcv(br, port, skb, vid); + ret = br_multicast_ipv6_rcv(*brmctx, *pmctx, skb, vid); break; #endif } @@ -3430,32 +3799,39 @@ int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, return ret; } -static void br_multicast_query_expired(struct net_bridge *br, +static void br_multicast_query_expired(struct net_bridge_mcast *brmctx, struct bridge_mcast_own_query *query, struct bridge_mcast_querier *querier) { - spin_lock(&br->multicast_lock); - if (query->startup_sent < br->multicast_startup_query_count) + spin_lock(&brmctx->br->multicast_lock); + if (br_multicast_ctx_vlan_disabled(brmctx)) + goto out; + + if (query->startup_sent < brmctx->multicast_startup_query_count) query->startup_sent++; - RCU_INIT_POINTER(querier->port, NULL); - br_multicast_send_query(br, NULL, query); - spin_unlock(&br->multicast_lock); + br_multicast_send_query(brmctx, NULL, query); +out: + spin_unlock(&brmctx->br->multicast_lock); } static void br_ip4_multicast_query_expired(struct timer_list *t) { - struct net_bridge *br = from_timer(br, t, ip4_own_query.timer); + struct net_bridge_mcast *brmctx = from_timer(brmctx, t, + ip4_own_query.timer); - br_multicast_query_expired(br, &br->ip4_own_query, &br->ip4_querier); + br_multicast_query_expired(brmctx, &brmctx->ip4_own_query, + &brmctx->ip4_querier); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_query_expired(struct timer_list *t) { - struct net_bridge *br = from_timer(br, t, ip6_own_query.timer); + struct net_bridge_mcast *brmctx = from_timer(brmctx, t, + ip6_own_query.timer); - br_multicast_query_expired(br, &br->ip6_own_query, &br->ip6_querier); + br_multicast_query_expired(brmctx, &brmctx->ip6_own_query, + &brmctx->ip6_querier); } #endif @@ -3472,47 +3848,65 @@ static void br_multicast_gc_work(struct work_struct *work) br_multicast_gc(&deleted_head); } -void br_multicast_init(struct net_bridge *br) +void br_multicast_ctx_init(struct net_bridge *br, + struct net_bridge_vlan *vlan, + struct net_bridge_mcast *brmctx) { - br->hash_max = BR_MULTICAST_DEFAULT_HASH_MAX; + brmctx->br = br; + brmctx->vlan = vlan; + brmctx->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; + brmctx->multicast_last_member_count = 2; + brmctx->multicast_startup_query_count = 2; - br->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; - br->multicast_last_member_count = 2; - br->multicast_startup_query_count = 2; + brmctx->multicast_last_member_interval = HZ; + brmctx->multicast_query_response_interval = 10 * HZ; + brmctx->multicast_startup_query_interval = 125 * HZ / 4; + brmctx->multicast_query_interval = 125 * HZ; + brmctx->multicast_querier_interval = 255 * HZ; + brmctx->multicast_membership_interval = 260 * HZ; - br->multicast_last_member_interval = HZ; - br->multicast_query_response_interval = 10 * HZ; - br->multicast_startup_query_interval = 125 * HZ / 4; - br->multicast_query_interval = 125 * HZ; - br->multicast_querier_interval = 255 * HZ; - br->multicast_membership_interval = 260 * HZ; - - br->ip4_other_query.delay_time = 0; - br->ip4_querier.port = NULL; - br->multicast_igmp_version = 2; + brmctx->ip4_other_query.delay_time = 0; + brmctx->ip4_querier.port_ifidx = 0; + seqcount_init(&brmctx->ip4_querier.seq); + brmctx->multicast_igmp_version = 2; #if IS_ENABLED(CONFIG_IPV6) - br->multicast_mld_version = 1; - br->ip6_other_query.delay_time = 0; - br->ip6_querier.port = NULL; + brmctx->multicast_mld_version = 1; + brmctx->ip6_other_query.delay_time = 0; + brmctx->ip6_querier.port_ifidx = 0; + seqcount_init(&brmctx->ip6_querier.seq); #endif - br_opt_toggle(br, BROPT_MULTICAST_ENABLED, true); - br_opt_toggle(br, BROPT_HAS_IPV6_ADDR, true); - spin_lock_init(&br->multicast_lock); - timer_setup(&br->ip4_mc_router_timer, + timer_setup(&brmctx->ip4_mc_router_timer, br_ip4_multicast_local_router_expired, 0); - timer_setup(&br->ip4_other_query.timer, + timer_setup(&brmctx->ip4_other_query.timer, br_ip4_multicast_querier_expired, 0); - timer_setup(&br->ip4_own_query.timer, + timer_setup(&brmctx->ip4_own_query.timer, br_ip4_multicast_query_expired, 0); #if IS_ENABLED(CONFIG_IPV6) - timer_setup(&br->ip6_mc_router_timer, + timer_setup(&brmctx->ip6_mc_router_timer, br_ip6_multicast_local_router_expired, 0); - timer_setup(&br->ip6_other_query.timer, + timer_setup(&brmctx->ip6_other_query.timer, br_ip6_multicast_querier_expired, 0); - timer_setup(&br->ip6_own_query.timer, + timer_setup(&brmctx->ip6_own_query.timer, br_ip6_multicast_query_expired, 0); #endif +} + +void br_multicast_ctx_deinit(struct net_bridge_mcast *brmctx) +{ + __br_multicast_stop(brmctx); +} + +void br_multicast_init(struct net_bridge *br) +{ + br->hash_max = BR_MULTICAST_DEFAULT_HASH_MAX; + + br_multicast_ctx_init(br, NULL, &br->multicast_ctx); + + br_opt_toggle(br, BROPT_MULTICAST_ENABLED, true); + br_opt_toggle(br, BROPT_HAS_IPV6_ADDR, true); + + spin_lock_init(&br->multicast_lock); INIT_HLIST_HEAD(&br->mdb_list); INIT_HLIST_HEAD(&br->mcast_gc_list); INIT_WORK(&br->mcast_gc_work, br_multicast_gc_work); @@ -3580,8 +3974,8 @@ void br_multicast_leave_snoopers(struct net_bridge *br) br_ip6_multicast_leave_snoopers(br); } -static void __br_multicast_open(struct net_bridge *br, - struct bridge_mcast_own_query *query) +static void __br_multicast_open_query(struct net_bridge *br, + struct bridge_mcast_own_query *query) { query->startup_sent = 0; @@ -3591,26 +3985,194 @@ static void __br_multicast_open(struct net_bridge *br, mod_timer(&query->timer, jiffies); } -void br_multicast_open(struct net_bridge *br) +static void __br_multicast_open(struct net_bridge_mcast *brmctx) { - __br_multicast_open(br, &br->ip4_own_query); + __br_multicast_open_query(brmctx->br, &brmctx->ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) - __br_multicast_open(br, &br->ip6_own_query); + __br_multicast_open_query(brmctx->br, &brmctx->ip6_own_query); #endif } -void br_multicast_stop(struct net_bridge *br) +void br_multicast_open(struct net_bridge *br) { - del_timer_sync(&br->ip4_mc_router_timer); - del_timer_sync(&br->ip4_other_query.timer); - del_timer_sync(&br->ip4_own_query.timer); + ASSERT_RTNL(); + + if (br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) { + struct net_bridge_vlan_group *vg; + struct net_bridge_vlan *vlan; + + vg = br_vlan_group(br); + if (vg) { + list_for_each_entry(vlan, &vg->vlan_list, vlist) { + struct net_bridge_mcast *brmctx; + + brmctx = &vlan->br_mcast_ctx; + if (br_vlan_is_brentry(vlan) && + !br_multicast_ctx_vlan_disabled(brmctx)) + __br_multicast_open(&vlan->br_mcast_ctx); + } + } + } else { + __br_multicast_open(&br->multicast_ctx); + } +} + +static void __br_multicast_stop(struct net_bridge_mcast *brmctx) +{ + del_timer_sync(&brmctx->ip4_mc_router_timer); + del_timer_sync(&brmctx->ip4_other_query.timer); + del_timer_sync(&brmctx->ip4_own_query.timer); #if IS_ENABLED(CONFIG_IPV6) - del_timer_sync(&br->ip6_mc_router_timer); - del_timer_sync(&br->ip6_other_query.timer); - del_timer_sync(&br->ip6_own_query.timer); + del_timer_sync(&brmctx->ip6_mc_router_timer); + del_timer_sync(&brmctx->ip6_other_query.timer); + del_timer_sync(&brmctx->ip6_own_query.timer); #endif } +void br_multicast_toggle_one_vlan(struct net_bridge_vlan *vlan, bool on) +{ + struct net_bridge *br; + + /* it's okay to check for the flag without the multicast lock because it + * can only change under RTNL -> multicast_lock, we need the latter to + * sync with timers and packets + */ + if (on == !!(vlan->priv_flags & BR_VLFLAG_MCAST_ENABLED)) + return; + + if (br_vlan_is_master(vlan)) { + br = vlan->br; + + if (!br_vlan_is_brentry(vlan) || + (on && + br_multicast_ctx_vlan_global_disabled(&vlan->br_mcast_ctx))) + return; + + spin_lock_bh(&br->multicast_lock); + vlan->priv_flags ^= BR_VLFLAG_MCAST_ENABLED; + spin_unlock_bh(&br->multicast_lock); + + if (on) + __br_multicast_open(&vlan->br_mcast_ctx); + else + __br_multicast_stop(&vlan->br_mcast_ctx); + } else { + struct net_bridge_mcast *brmctx; + + brmctx = br_multicast_port_ctx_get_global(&vlan->port_mcast_ctx); + if (on && br_multicast_ctx_vlan_global_disabled(brmctx)) + return; + + br = vlan->port->br; + spin_lock_bh(&br->multicast_lock); + vlan->priv_flags ^= BR_VLFLAG_MCAST_ENABLED; + if (on) + __br_multicast_enable_port_ctx(&vlan->port_mcast_ctx); + else + __br_multicast_disable_port_ctx(&vlan->port_mcast_ctx); + spin_unlock_bh(&br->multicast_lock); + } +} + +static void br_multicast_toggle_vlan(struct net_bridge_vlan *vlan, bool on) +{ + struct net_bridge_port *p; + + if (WARN_ON_ONCE(!br_vlan_is_master(vlan))) + return; + + list_for_each_entry(p, &vlan->br->port_list, list) { + struct net_bridge_vlan *vport; + + vport = br_vlan_find(nbp_vlan_group(p), vlan->vid); + if (!vport) + continue; + br_multicast_toggle_one_vlan(vport, on); + } + + if (br_vlan_is_brentry(vlan)) + br_multicast_toggle_one_vlan(vlan, on); +} + +int br_multicast_toggle_vlan_snooping(struct net_bridge *br, bool on, + struct netlink_ext_ack *extack) +{ + struct net_bridge_vlan_group *vg; + struct net_bridge_vlan *vlan; + struct net_bridge_port *p; + + if (br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED) == on) + return 0; + + if (on && !br_opt_get(br, BROPT_VLAN_ENABLED)) { + NL_SET_ERR_MSG_MOD(extack, "Cannot enable multicast vlan snooping with vlan filtering disabled"); + return -EINVAL; + } + + vg = br_vlan_group(br); + if (!vg) + return 0; + + br_opt_toggle(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED, on); + + /* disable/enable non-vlan mcast contexts based on vlan snooping */ + if (on) + __br_multicast_stop(&br->multicast_ctx); + else + __br_multicast_open(&br->multicast_ctx); + list_for_each_entry(p, &br->port_list, list) { + if (on) + br_multicast_disable_port(p); + else + br_multicast_enable_port(p); + } + + list_for_each_entry(vlan, &vg->vlan_list, vlist) + br_multicast_toggle_vlan(vlan, on); + + return 0; +} + +bool br_multicast_toggle_global_vlan(struct net_bridge_vlan *vlan, bool on) +{ + ASSERT_RTNL(); + + /* BR_VLFLAG_GLOBAL_MCAST_ENABLED relies on eventual consistency and + * requires only RTNL to change + */ + if (on == !!(vlan->priv_flags & BR_VLFLAG_GLOBAL_MCAST_ENABLED)) + return false; + + vlan->priv_flags ^= BR_VLFLAG_GLOBAL_MCAST_ENABLED; + br_multicast_toggle_vlan(vlan, on); + + return true; +} + +void br_multicast_stop(struct net_bridge *br) +{ + ASSERT_RTNL(); + + if (br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) { + struct net_bridge_vlan_group *vg; + struct net_bridge_vlan *vlan; + + vg = br_vlan_group(br); + if (vg) { + list_for_each_entry(vlan, &vg->vlan_list, vlist) { + struct net_bridge_mcast *brmctx; + + brmctx = &vlan->br_mcast_ctx; + if (br_vlan_is_brentry(vlan) && + !br_multicast_ctx_vlan_disabled(brmctx)) + __br_multicast_stop(&vlan->br_mcast_ctx); + } + } + } else { + __br_multicast_stop(&br->multicast_ctx); + } +} + void br_multicast_dev_del(struct net_bridge *br) { struct net_bridge_mdb_entry *mp; @@ -3623,44 +4185,45 @@ void br_multicast_dev_del(struct net_bridge *br) hlist_move_list(&br->mcast_gc_list, &deleted_head); spin_unlock_bh(&br->multicast_lock); + br_multicast_ctx_deinit(&br->multicast_ctx); br_multicast_gc(&deleted_head); cancel_work_sync(&br->mcast_gc_work); rcu_barrier(); } -int br_multicast_set_router(struct net_bridge *br, unsigned long val) +int br_multicast_set_router(struct net_bridge_mcast *brmctx, unsigned long val) { int err = -EINVAL; - spin_lock_bh(&br->multicast_lock); + spin_lock_bh(&brmctx->br->multicast_lock); 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->ip4_mc_router_timer); + br_mc_router_state_change(brmctx->br, val == MDB_RTR_TYPE_PERM); + del_timer(&brmctx->ip4_mc_router_timer); #if IS_ENABLED(CONFIG_IPV6) - del_timer(&br->ip6_mc_router_timer); + del_timer(&brmctx->ip6_mc_router_timer); #endif - br->multicast_router = val; + brmctx->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; + if (brmctx->multicast_router != MDB_RTR_TYPE_TEMP_QUERY) + br_mc_router_state_change(brmctx->br, false); + brmctx->multicast_router = val; err = 0; break; } - spin_unlock_bh(&br->multicast_lock); + spin_unlock_bh(&brmctx->br->multicast_lock); return err; } static void -br_multicast_rport_del_notify(struct net_bridge_port *p, bool deleted) +br_multicast_rport_del_notify(struct net_bridge_mcast_port *pmctx, bool deleted) { if (!deleted) return; @@ -3668,37 +4231,39 @@ br_multicast_rport_del_notify(struct net_bridge_port *p, bool deleted) /* For backwards compatibility for now, only notify if there is * no multicast router anymore for both IPv4 and IPv6. */ - if (!hlist_unhashed(&p->ip4_rlist)) + if (!hlist_unhashed(&pmctx->ip4_rlist)) return; #if IS_ENABLED(CONFIG_IPV6) - if (!hlist_unhashed(&p->ip6_rlist)) + if (!hlist_unhashed(&pmctx->ip6_rlist)) return; #endif - br_rtr_notify(p->br->dev, p, RTM_DELMDB); - br_port_mc_router_state_change(p, false); + br_rtr_notify(pmctx->port->br->dev, pmctx, RTM_DELMDB); + br_port_mc_router_state_change(pmctx->port, false); /* don't allow timer refresh */ - if (p->multicast_router == MDB_RTR_TYPE_TEMP) - p->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; + if (pmctx->multicast_router == MDB_RTR_TYPE_TEMP) + pmctx->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; } -int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val) +int br_multicast_set_port_router(struct net_bridge_mcast_port *pmctx, + unsigned long val) { - struct net_bridge *br = p->br; + struct net_bridge_mcast *brmctx; unsigned long now = jiffies; int err = -EINVAL; bool del = false; - spin_lock(&br->multicast_lock); - if (p->multicast_router == val) { + brmctx = br_multicast_port_ctx_get_global(pmctx); + spin_lock_bh(&brmctx->br->multicast_lock); + if (pmctx->multicast_router == val) { /* Refresh the temp router port timer */ - if (p->multicast_router == MDB_RTR_TYPE_TEMP) { - mod_timer(&p->ip4_mc_router_timer, - now + br->multicast_querier_interval); + if (pmctx->multicast_router == MDB_RTR_TYPE_TEMP) { + mod_timer(&pmctx->ip4_mc_router_timer, + now + brmctx->multicast_querier_interval); #if IS_ENABLED(CONFIG_IPV6) - mod_timer(&p->ip6_mc_router_timer, - now + br->multicast_querier_interval); + mod_timer(&pmctx->ip6_mc_router_timer, + now + brmctx->multicast_querier_interval); #endif } err = 0; @@ -3706,63 +4271,103 @@ int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val) } switch (val) { case MDB_RTR_TYPE_DISABLED: - p->multicast_router = MDB_RTR_TYPE_DISABLED; - del |= br_ip4_multicast_rport_del(p); - del_timer(&p->ip4_mc_router_timer); - del |= br_ip6_multicast_rport_del(p); + pmctx->multicast_router = MDB_RTR_TYPE_DISABLED; + del |= br_ip4_multicast_rport_del(pmctx); + del_timer(&pmctx->ip4_mc_router_timer); + del |= br_ip6_multicast_rport_del(pmctx); #if IS_ENABLED(CONFIG_IPV6) - del_timer(&p->ip6_mc_router_timer); + del_timer(&pmctx->ip6_mc_router_timer); #endif - br_multicast_rport_del_notify(p, del); + br_multicast_rport_del_notify(pmctx, del); break; case MDB_RTR_TYPE_TEMP_QUERY: - p->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; - del |= br_ip4_multicast_rport_del(p); - del |= br_ip6_multicast_rport_del(p); - br_multicast_rport_del_notify(p, del); + pmctx->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; + del |= br_ip4_multicast_rport_del(pmctx); + del |= br_ip6_multicast_rport_del(pmctx); + br_multicast_rport_del_notify(pmctx, del); break; case MDB_RTR_TYPE_PERM: - p->multicast_router = MDB_RTR_TYPE_PERM; - del_timer(&p->ip4_mc_router_timer); - br_ip4_multicast_add_router(br, p); + pmctx->multicast_router = MDB_RTR_TYPE_PERM; + del_timer(&pmctx->ip4_mc_router_timer); + br_ip4_multicast_add_router(brmctx, pmctx); #if IS_ENABLED(CONFIG_IPV6) - del_timer(&p->ip6_mc_router_timer); + del_timer(&pmctx->ip6_mc_router_timer); #endif - br_ip6_multicast_add_router(br, p); + br_ip6_multicast_add_router(brmctx, pmctx); break; case MDB_RTR_TYPE_TEMP: - p->multicast_router = MDB_RTR_TYPE_TEMP; - br_ip4_multicast_mark_router(br, p); - br_ip6_multicast_mark_router(br, p); + pmctx->multicast_router = MDB_RTR_TYPE_TEMP; + br_ip4_multicast_mark_router(brmctx, pmctx); + br_ip6_multicast_mark_router(brmctx, pmctx); break; default: goto unlock; } err = 0; unlock: - spin_unlock(&br->multicast_lock); + spin_unlock_bh(&brmctx->br->multicast_lock); return err; } -static void br_multicast_start_querier(struct net_bridge *br, +int br_multicast_set_vlan_router(struct net_bridge_vlan *v, u8 mcast_router) +{ + int err; + + if (br_vlan_is_master(v)) + err = br_multicast_set_router(&v->br_mcast_ctx, mcast_router); + else + err = br_multicast_set_port_router(&v->port_mcast_ctx, + mcast_router); + + return err; +} + +static void br_multicast_start_querier(struct net_bridge_mcast *brmctx, struct bridge_mcast_own_query *query) { struct net_bridge_port *port; - __br_multicast_open(br, query); + if (!br_multicast_ctx_matches_vlan_snooping(brmctx)) + return; + + __br_multicast_open_query(brmctx->br, query); rcu_read_lock(); - list_for_each_entry_rcu(port, &br->port_list, list) { - if (port->state == BR_STATE_DISABLED || - port->state == BR_STATE_BLOCKING) + list_for_each_entry_rcu(port, &brmctx->br->port_list, list) { + struct bridge_mcast_own_query *ip4_own_query; +#if IS_ENABLED(CONFIG_IPV6) + struct bridge_mcast_own_query *ip6_own_query; +#endif + + if (br_multicast_port_ctx_state_stopped(&port->multicast_ctx)) continue; - if (query == &br->ip4_own_query) - br_multicast_enable(&port->ip4_own_query); + if (br_multicast_ctx_is_vlan(brmctx)) { + struct net_bridge_vlan *vlan; + + vlan = br_vlan_find(nbp_vlan_group_rcu(port), + brmctx->vlan->vid); + if (!vlan || + br_multicast_port_ctx_state_stopped(&vlan->port_mcast_ctx)) + continue; + + ip4_own_query = &vlan->port_mcast_ctx.ip4_own_query; +#if IS_ENABLED(CONFIG_IPV6) + ip6_own_query = &vlan->port_mcast_ctx.ip6_own_query; +#endif + } else { + ip4_own_query = &port->multicast_ctx.ip4_own_query; +#if IS_ENABLED(CONFIG_IPV6) + ip6_own_query = &port->multicast_ctx.ip6_own_query; +#endif + } + + if (query == &brmctx->ip4_own_query) + br_multicast_enable(ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) else - br_multicast_enable(&port->ip6_own_query); + br_multicast_enable(ip6_own_query); #endif } rcu_read_unlock(); @@ -3796,7 +4401,7 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val, br_multicast_open(br); list_for_each_entry(port, &br->port_list, list) - __br_multicast_enable_port(port); + __br_multicast_enable_port_ctx(&port->multicast_ctx); change_snoopers = true; @@ -3839,47 +4444,48 @@ bool br_multicast_router(const struct net_device *dev) bool is_router; spin_lock_bh(&br->multicast_lock); - is_router = br_multicast_is_router(br, NULL); + is_router = br_multicast_is_router(&br->multicast_ctx, NULL); 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) +int br_multicast_set_querier(struct net_bridge_mcast *brmctx, unsigned long val) { unsigned long max_delay; val = !!val; - spin_lock_bh(&br->multicast_lock); - if (br_opt_get(br, BROPT_MULTICAST_QUERIER) == val) + spin_lock_bh(&brmctx->br->multicast_lock); + if (brmctx->multicast_querier == val) goto unlock; - br_opt_toggle(br, BROPT_MULTICAST_QUERIER, !!val); + WRITE_ONCE(brmctx->multicast_querier, val); if (!val) goto unlock; - max_delay = br->multicast_query_response_interval; + max_delay = brmctx->multicast_query_response_interval; - if (!timer_pending(&br->ip4_other_query.timer)) - br->ip4_other_query.delay_time = jiffies + max_delay; + if (!timer_pending(&brmctx->ip4_other_query.timer)) + brmctx->ip4_other_query.delay_time = jiffies + max_delay; - br_multicast_start_querier(br, &br->ip4_own_query); + br_multicast_start_querier(brmctx, &brmctx->ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) - if (!timer_pending(&br->ip6_other_query.timer)) - br->ip6_other_query.delay_time = jiffies + max_delay; + if (!timer_pending(&brmctx->ip6_other_query.timer)) + brmctx->ip6_other_query.delay_time = jiffies + max_delay; - br_multicast_start_querier(br, &br->ip6_own_query); + br_multicast_start_querier(brmctx, &brmctx->ip6_own_query); #endif unlock: - spin_unlock_bh(&br->multicast_lock); + spin_unlock_bh(&brmctx->br->multicast_lock); return 0; } -int br_multicast_set_igmp_version(struct net_bridge *br, unsigned long val) +int br_multicast_set_igmp_version(struct net_bridge_mcast *brmctx, + unsigned long val) { /* Currently we support only version 2 and 3 */ switch (val) { @@ -3890,15 +4496,16 @@ int br_multicast_set_igmp_version(struct net_bridge *br, unsigned long val) return -EINVAL; } - spin_lock_bh(&br->multicast_lock); - br->multicast_igmp_version = val; - spin_unlock_bh(&br->multicast_lock); + spin_lock_bh(&brmctx->br->multicast_lock); + brmctx->multicast_igmp_version = val; + spin_unlock_bh(&brmctx->br->multicast_lock); return 0; } #if IS_ENABLED(CONFIG_IPV6) -int br_multicast_set_mld_version(struct net_bridge *br, unsigned long val) +int br_multicast_set_mld_version(struct net_bridge_mcast *brmctx, + unsigned long val) { /* Currently we support version 1 and 2 */ switch (val) { @@ -3909,9 +4516,9 @@ int br_multicast_set_mld_version(struct net_bridge *br, unsigned long val) return -EINVAL; } - spin_lock_bh(&br->multicast_lock); - br->multicast_mld_version = val; - spin_unlock_bh(&br->multicast_lock); + spin_lock_bh(&brmctx->br->multicast_lock); + brmctx->multicast_mld_version = val; + spin_unlock_bh(&brmctx->br->multicast_lock); return 0; } @@ -4003,7 +4610,7 @@ bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto) memset(ð, 0, sizeof(eth)); eth.h_proto = htons(proto); - ret = br_multicast_querier_exists(br, ð, NULL); + ret = br_multicast_querier_exists(&br->multicast_ctx, ð, NULL); unlock: rcu_read_unlock(); @@ -4022,9 +4629,11 @@ EXPORT_SYMBOL_GPL(br_multicast_has_querier_anywhere); */ bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto) { + struct net_bridge_mcast *brmctx; struct net_bridge *br; struct net_bridge_port *port; bool ret = false; + int port_ifidx; rcu_read_lock(); if (!netif_is_bridge_port(dev)) @@ -4035,17 +4644,20 @@ bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto) goto unlock; br = port->br; + brmctx = &br->multicast_ctx; switch (proto) { case ETH_P_IP: - if (!timer_pending(&br->ip4_other_query.timer) || - rcu_dereference(br->ip4_querier.port) == port) + port_ifidx = brmctx->ip4_querier.port_ifidx; + if (!timer_pending(&brmctx->ip4_other_query.timer) || + port_ifidx == port->dev->ifindex) goto unlock; break; #if IS_ENABLED(CONFIG_IPV6) case ETH_P_IPV6: - if (!timer_pending(&br->ip6_other_query.timer) || - rcu_dereference(br->ip6_querier.port) == port) + port_ifidx = brmctx->ip6_querier.port_ifidx; + if (!timer_pending(&brmctx->ip6_other_query.timer) || + port_ifidx == port->dev->ifindex) goto unlock; break; #endif @@ -4071,7 +4683,9 @@ EXPORT_SYMBOL_GPL(br_multicast_has_querier_adjacent); */ bool br_multicast_has_router_adjacent(struct net_device *dev, int proto) { - struct net_bridge_port *port, *p; + struct net_bridge_mcast_port *pmctx; + struct net_bridge_mcast *brmctx; + struct net_bridge_port *port; bool ret = false; rcu_read_lock(); @@ -4079,11 +4693,12 @@ bool br_multicast_has_router_adjacent(struct net_device *dev, int proto) if (!port) goto unlock; + brmctx = &port->br->multicast_ctx; switch (proto) { case ETH_P_IP: - hlist_for_each_entry_rcu(p, &port->br->ip4_mc_router_list, + hlist_for_each_entry_rcu(pmctx, &brmctx->ip4_mc_router_list, ip4_rlist) { - if (p == port) + if (pmctx->port == port) continue; ret = true; @@ -4092,9 +4707,9 @@ bool br_multicast_has_router_adjacent(struct net_device *dev, int proto) break; #if IS_ENABLED(CONFIG_IPV6) case ETH_P_IPV6: - hlist_for_each_entry_rcu(p, &port->br->ip6_mc_router_list, + hlist_for_each_entry_rcu(pmctx, &brmctx->ip6_mc_router_list, ip6_rlist) { - if (p == port) + if (pmctx->port == port) continue; ret = true; @@ -4186,7 +4801,8 @@ static void br_mcast_stats_add(struct bridge_mcast_stats __percpu *stats, u64_stats_update_end(&pstats->syncp); } -void br_multicast_count(struct net_bridge *br, const struct net_bridge_port *p, +void br_multicast_count(struct net_bridge *br, + const struct net_bridge_port *p, const struct sk_buff *skb, u8 type, u8 dir) { struct bridge_mcast_stats __percpu *stats; diff --git a/net/bridge/br_multicast_eht.c b/net/bridge/br_multicast_eht.c index 13290a749d09..f91c071d1608 100644 --- a/net/bridge/br_multicast_eht.c +++ b/net/bridge/br_multicast_eht.c @@ -33,7 +33,8 @@ static bool br_multicast_del_eht_set_entry(struct net_bridge_port_group *pg, union net_bridge_eht_addr *src_addr, union net_bridge_eht_addr *h_addr); -static void br_multicast_create_eht_set_entry(struct net_bridge_port_group *pg, +static void br_multicast_create_eht_set_entry(const struct net_bridge_mcast *brmctx, + struct net_bridge_port_group *pg, union net_bridge_eht_addr *src_addr, union net_bridge_eht_addr *h_addr, int filter_mode, @@ -388,7 +389,8 @@ static void br_multicast_ip_src_to_eht_addr(const struct br_ip *src, } } -static void br_eht_convert_host_filter_mode(struct net_bridge_port_group *pg, +static void br_eht_convert_host_filter_mode(const struct net_bridge_mcast *brmctx, + struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, int filter_mode) { @@ -405,14 +407,15 @@ static void br_eht_convert_host_filter_mode(struct net_bridge_port_group *pg, br_multicast_del_eht_set_entry(pg, &zero_addr, h_addr); break; case MCAST_EXCLUDE: - br_multicast_create_eht_set_entry(pg, &zero_addr, h_addr, - MCAST_EXCLUDE, + br_multicast_create_eht_set_entry(brmctx, pg, &zero_addr, + h_addr, MCAST_EXCLUDE, true); break; } } -static void br_multicast_create_eht_set_entry(struct net_bridge_port_group *pg, +static void br_multicast_create_eht_set_entry(const struct net_bridge_mcast *brmctx, + struct net_bridge_port_group *pg, union net_bridge_eht_addr *src_addr, union net_bridge_eht_addr *h_addr, int filter_mode, @@ -441,8 +444,8 @@ static void br_multicast_create_eht_set_entry(struct net_bridge_port_group *pg, if (!set_h) goto fail_set_entry; - mod_timer(&set_h->timer, jiffies + br_multicast_gmi(br)); - mod_timer(&eht_set->timer, jiffies + br_multicast_gmi(br)); + mod_timer(&set_h->timer, jiffies + br_multicast_gmi(brmctx)); + mod_timer(&eht_set->timer, jiffies + br_multicast_gmi(brmctx)); return; @@ -499,7 +502,8 @@ static void br_multicast_del_eht_host(struct net_bridge_port_group *pg, } /* create new set entries from reports */ -static void __eht_create_set_entries(struct net_bridge_port_group *pg, +static void __eht_create_set_entries(const struct net_bridge_mcast *brmctx, + struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, @@ -512,8 +516,8 @@ static void __eht_create_set_entries(struct net_bridge_port_group *pg, memset(&eht_src_addr, 0, sizeof(eht_src_addr)); for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&eht_src_addr, srcs + (src_idx * addr_size), addr_size); - br_multicast_create_eht_set_entry(pg, &eht_src_addr, h_addr, - filter_mode, + br_multicast_create_eht_set_entry(brmctx, pg, &eht_src_addr, + h_addr, filter_mode, false); } } @@ -549,7 +553,8 @@ static bool __eht_del_set_entries(struct net_bridge_port_group *pg, return changed; } -static bool br_multicast_eht_allow(struct net_bridge_port_group *pg, +static bool br_multicast_eht_allow(const struct net_bridge_mcast *brmctx, + struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, @@ -559,8 +564,8 @@ static bool br_multicast_eht_allow(struct net_bridge_port_group *pg, switch (br_multicast_eht_host_filter_mode(pg, h_addr)) { case MCAST_INCLUDE: - __eht_create_set_entries(pg, h_addr, srcs, nsrcs, addr_size, - MCAST_INCLUDE); + __eht_create_set_entries(brmctx, pg, h_addr, srcs, nsrcs, + addr_size, MCAST_INCLUDE); break; case MCAST_EXCLUDE: changed = __eht_del_set_entries(pg, h_addr, srcs, nsrcs, @@ -571,7 +576,8 @@ static bool br_multicast_eht_allow(struct net_bridge_port_group *pg, return changed; } -static bool br_multicast_eht_block(struct net_bridge_port_group *pg, +static bool br_multicast_eht_block(const struct net_bridge_mcast *brmctx, + struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, @@ -585,7 +591,7 @@ static bool br_multicast_eht_block(struct net_bridge_port_group *pg, addr_size); break; case MCAST_EXCLUDE: - __eht_create_set_entries(pg, h_addr, srcs, nsrcs, addr_size, + __eht_create_set_entries(brmctx, pg, h_addr, srcs, nsrcs, addr_size, MCAST_EXCLUDE); break; } @@ -594,7 +600,8 @@ static bool br_multicast_eht_block(struct net_bridge_port_group *pg, } /* flush_entries is true when changing mode */ -static bool __eht_inc_exc(struct net_bridge_port_group *pg, +static bool __eht_inc_exc(const struct net_bridge_mcast *brmctx, + struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, @@ -612,11 +619,10 @@ static bool __eht_inc_exc(struct net_bridge_port_group *pg, /* if we're changing mode del host and its entries */ if (flush_entries) br_multicast_del_eht_host(pg, h_addr); - __eht_create_set_entries(pg, h_addr, srcs, nsrcs, addr_size, + __eht_create_set_entries(brmctx, pg, h_addr, srcs, nsrcs, addr_size, filter_mode); /* we can be missing sets only if we've deleted some entries */ if (flush_entries) { - struct net_bridge *br = pg->key.port->br; struct net_bridge_group_eht_set *eht_set; struct net_bridge_group_src *src_ent; struct hlist_node *tmp; @@ -647,14 +653,15 @@ static bool __eht_inc_exc(struct net_bridge_port_group *pg, &eht_src_addr); if (!eht_set) continue; - mod_timer(&eht_set->timer, jiffies + br_multicast_lmqt(br)); + mod_timer(&eht_set->timer, jiffies + br_multicast_lmqt(brmctx)); } } return changed; } -static bool br_multicast_eht_inc(struct net_bridge_port_group *pg, +static bool br_multicast_eht_inc(const struct net_bridge_mcast *brmctx, + struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, @@ -663,14 +670,15 @@ static bool br_multicast_eht_inc(struct net_bridge_port_group *pg, { bool changed; - changed = __eht_inc_exc(pg, h_addr, srcs, nsrcs, addr_size, + changed = __eht_inc_exc(brmctx, pg, h_addr, srcs, nsrcs, addr_size, MCAST_INCLUDE, to_report); - br_eht_convert_host_filter_mode(pg, h_addr, MCAST_INCLUDE); + br_eht_convert_host_filter_mode(brmctx, pg, h_addr, MCAST_INCLUDE); return changed; } -static bool br_multicast_eht_exc(struct net_bridge_port_group *pg, +static bool br_multicast_eht_exc(const struct net_bridge_mcast *brmctx, + struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, @@ -679,14 +687,15 @@ static bool br_multicast_eht_exc(struct net_bridge_port_group *pg, { bool changed; - changed = __eht_inc_exc(pg, h_addr, srcs, nsrcs, addr_size, + changed = __eht_inc_exc(brmctx, pg, h_addr, srcs, nsrcs, addr_size, MCAST_EXCLUDE, to_report); - br_eht_convert_host_filter_mode(pg, h_addr, MCAST_EXCLUDE); + br_eht_convert_host_filter_mode(brmctx, pg, h_addr, MCAST_EXCLUDE); return changed; } -static bool __eht_ip4_handle(struct net_bridge_port_group *pg, +static bool __eht_ip4_handle(const struct net_bridge_mcast *brmctx, + struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, @@ -696,24 +705,25 @@ static bool __eht_ip4_handle(struct net_bridge_port_group *pg, switch (grec_type) { case IGMPV3_ALLOW_NEW_SOURCES: - br_multicast_eht_allow(pg, h_addr, srcs, nsrcs, sizeof(__be32)); + br_multicast_eht_allow(brmctx, pg, h_addr, srcs, nsrcs, + sizeof(__be32)); break; case IGMPV3_BLOCK_OLD_SOURCES: - changed = br_multicast_eht_block(pg, h_addr, srcs, nsrcs, + changed = br_multicast_eht_block(brmctx, pg, h_addr, srcs, nsrcs, sizeof(__be32)); break; case IGMPV3_CHANGE_TO_INCLUDE: to_report = true; fallthrough; case IGMPV3_MODE_IS_INCLUDE: - changed = br_multicast_eht_inc(pg, h_addr, srcs, nsrcs, + changed = br_multicast_eht_inc(brmctx, pg, h_addr, srcs, nsrcs, sizeof(__be32), to_report); break; case IGMPV3_CHANGE_TO_EXCLUDE: to_report = true; fallthrough; case IGMPV3_MODE_IS_EXCLUDE: - changed = br_multicast_eht_exc(pg, h_addr, srcs, nsrcs, + changed = br_multicast_eht_exc(brmctx, pg, h_addr, srcs, nsrcs, sizeof(__be32), to_report); break; } @@ -722,7 +732,8 @@ static bool __eht_ip4_handle(struct net_bridge_port_group *pg, } #if IS_ENABLED(CONFIG_IPV6) -static bool __eht_ip6_handle(struct net_bridge_port_group *pg, +static bool __eht_ip6_handle(const struct net_bridge_mcast *brmctx, + struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, @@ -732,18 +743,18 @@ static bool __eht_ip6_handle(struct net_bridge_port_group *pg, switch (grec_type) { case MLD2_ALLOW_NEW_SOURCES: - br_multicast_eht_allow(pg, h_addr, srcs, nsrcs, + br_multicast_eht_allow(brmctx, pg, h_addr, srcs, nsrcs, sizeof(struct in6_addr)); break; case MLD2_BLOCK_OLD_SOURCES: - changed = br_multicast_eht_block(pg, h_addr, srcs, nsrcs, + changed = br_multicast_eht_block(brmctx, pg, h_addr, srcs, nsrcs, sizeof(struct in6_addr)); break; case MLD2_CHANGE_TO_INCLUDE: to_report = true; fallthrough; case MLD2_MODE_IS_INCLUDE: - changed = br_multicast_eht_inc(pg, h_addr, srcs, nsrcs, + changed = br_multicast_eht_inc(brmctx, pg, h_addr, srcs, nsrcs, sizeof(struct in6_addr), to_report); break; @@ -751,7 +762,7 @@ static bool __eht_ip6_handle(struct net_bridge_port_group *pg, to_report = true; fallthrough; case MLD2_MODE_IS_EXCLUDE: - changed = br_multicast_eht_exc(pg, h_addr, srcs, nsrcs, + changed = br_multicast_eht_exc(brmctx, pg, h_addr, srcs, nsrcs, sizeof(struct in6_addr), to_report); break; @@ -762,7 +773,8 @@ static bool __eht_ip6_handle(struct net_bridge_port_group *pg, #endif /* true means an entry was deleted */ -bool br_multicast_eht_handle(struct net_bridge_port_group *pg, +bool br_multicast_eht_handle(const struct net_bridge_mcast *brmctx, + struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, @@ -779,12 +791,12 @@ bool br_multicast_eht_handle(struct net_bridge_port_group *pg, memset(&eht_host_addr, 0, sizeof(eht_host_addr)); memcpy(&eht_host_addr, h_addr, addr_size); if (addr_size == sizeof(__be32)) - changed = __eht_ip4_handle(pg, &eht_host_addr, srcs, nsrcs, - grec_type); + changed = __eht_ip4_handle(brmctx, pg, &eht_host_addr, srcs, + nsrcs, grec_type); #if IS_ENABLED(CONFIG_IPV6) else - changed = __eht_ip6_handle(pg, &eht_host_addr, srcs, nsrcs, - grec_type); + changed = __eht_ip6_handle(brmctx, pg, &eht_host_addr, srcs, + nsrcs, grec_type); #endif out: diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 8642e56059fb..6c58fc14d2cb 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -287,7 +287,7 @@ static int br_port_fill_attrs(struct sk_buff *skb, #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (nla_put_u8(skb, IFLA_BRPORT_MULTICAST_ROUTER, - p->multicast_router) || + p->multicast_ctx.multicast_router) || nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, p->multicast_eht_hosts_limit) || nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, @@ -932,7 +932,8 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[], if (tb[IFLA_BRPORT_MULTICAST_ROUTER]) { u8 mcast_router = nla_get_u8(tb[IFLA_BRPORT_MULTICAST_ROUTER]); - err = br_multicast_set_port_router(p, mcast_router); + err = br_multicast_set_port_router(&p->multicast_ctx, + mcast_router); if (err) return err; } @@ -1286,7 +1287,8 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], if (data[IFLA_BR_MCAST_ROUTER]) { u8 multicast_router = nla_get_u8(data[IFLA_BR_MCAST_ROUTER]); - err = br_multicast_set_router(br, multicast_router); + err = br_multicast_set_router(&br->multicast_ctx, + multicast_router); if (err) return err; } @@ -1309,7 +1311,8 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], if (data[IFLA_BR_MCAST_QUERIER]) { u8 mcast_querier = nla_get_u8(data[IFLA_BR_MCAST_QUERIER]); - err = br_multicast_set_querier(br, mcast_querier); + err = br_multicast_set_querier(&br->multicast_ctx, + mcast_querier); if (err) return err; } @@ -1324,49 +1327,49 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], if (data[IFLA_BR_MCAST_LAST_MEMBER_CNT]) { u32 val = nla_get_u32(data[IFLA_BR_MCAST_LAST_MEMBER_CNT]); - br->multicast_last_member_count = val; + br->multicast_ctx.multicast_last_member_count = val; } if (data[IFLA_BR_MCAST_STARTUP_QUERY_CNT]) { u32 val = nla_get_u32(data[IFLA_BR_MCAST_STARTUP_QUERY_CNT]); - br->multicast_startup_query_count = val; + br->multicast_ctx.multicast_startup_query_count = val; } if (data[IFLA_BR_MCAST_LAST_MEMBER_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_LAST_MEMBER_INTVL]); - br->multicast_last_member_interval = clock_t_to_jiffies(val); + br->multicast_ctx.multicast_last_member_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_MEMBERSHIP_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_MEMBERSHIP_INTVL]); - br->multicast_membership_interval = clock_t_to_jiffies(val); + br->multicast_ctx.multicast_membership_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_QUERIER_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERIER_INTVL]); - br->multicast_querier_interval = clock_t_to_jiffies(val); + br->multicast_ctx.multicast_querier_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_QUERY_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERY_INTVL]); - br->multicast_query_interval = clock_t_to_jiffies(val); + br->multicast_ctx.multicast_query_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL]); - br->multicast_query_response_interval = clock_t_to_jiffies(val); + br->multicast_ctx.multicast_query_response_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]); - br->multicast_startup_query_interval = clock_t_to_jiffies(val); + br->multicast_ctx.multicast_startup_query_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_STATS_ENABLED]) { @@ -1380,7 +1383,8 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], __u8 igmp_version; igmp_version = nla_get_u8(data[IFLA_BR_MCAST_IGMP_VERSION]); - err = br_multicast_set_igmp_version(br, igmp_version); + err = br_multicast_set_igmp_version(&br->multicast_ctx, + igmp_version); if (err) return err; } @@ -1390,7 +1394,8 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], __u8 mld_version; mld_version = nla_get_u8(data[IFLA_BR_MCAST_MLD_VERSION]); - err = br_multicast_set_mld_version(br, mld_version); + err = br_multicast_set_mld_version(&br->multicast_ctx, + mld_version); if (err) return err; } @@ -1497,6 +1502,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_STARTUP_QUERY_INTVL */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_IGMP_VERSION */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_MLD_VERSION */ + br_multicast_querier_state_size() + /* IFLA_BR_MCAST_QUERIER_STATE */ #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_IPTABLES */ @@ -1566,50 +1572,53 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) return -EMSGSIZE; #endif #ifdef CONFIG_BRIDGE_IGMP_SNOOPING - if (nla_put_u8(skb, IFLA_BR_MCAST_ROUTER, br->multicast_router) || + if (nla_put_u8(skb, IFLA_BR_MCAST_ROUTER, + br->multicast_ctx.multicast_router) || nla_put_u8(skb, IFLA_BR_MCAST_SNOOPING, br_opt_get(br, BROPT_MULTICAST_ENABLED)) || nla_put_u8(skb, IFLA_BR_MCAST_QUERY_USE_IFADDR, br_opt_get(br, BROPT_MULTICAST_QUERY_USE_IFADDR)) || nla_put_u8(skb, IFLA_BR_MCAST_QUERIER, - br_opt_get(br, BROPT_MULTICAST_QUERIER)) || + br->multicast_ctx.multicast_querier) || nla_put_u8(skb, IFLA_BR_MCAST_STATS_ENABLED, br_opt_get(br, BROPT_MULTICAST_STATS_ENABLED)) || nla_put_u32(skb, IFLA_BR_MCAST_HASH_ELASTICITY, RHT_ELASTICITY) || nla_put_u32(skb, IFLA_BR_MCAST_HASH_MAX, br->hash_max) || nla_put_u32(skb, IFLA_BR_MCAST_LAST_MEMBER_CNT, - br->multicast_last_member_count) || + br->multicast_ctx.multicast_last_member_count) || nla_put_u32(skb, IFLA_BR_MCAST_STARTUP_QUERY_CNT, - br->multicast_startup_query_count) || + br->multicast_ctx.multicast_startup_query_count) || nla_put_u8(skb, IFLA_BR_MCAST_IGMP_VERSION, - br->multicast_igmp_version)) + br->multicast_ctx.multicast_igmp_version) || + br_multicast_dump_querier_state(skb, &br->multicast_ctx, + IFLA_BR_MCAST_QUERIER_STATE)) return -EMSGSIZE; #if IS_ENABLED(CONFIG_IPV6) if (nla_put_u8(skb, IFLA_BR_MCAST_MLD_VERSION, - br->multicast_mld_version)) + br->multicast_ctx.multicast_mld_version)) return -EMSGSIZE; #endif - clockval = jiffies_to_clock_t(br->multicast_last_member_interval); + clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_last_member_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_LAST_MEMBER_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; - clockval = jiffies_to_clock_t(br->multicast_membership_interval); + clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_membership_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_MEMBERSHIP_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; - clockval = jiffies_to_clock_t(br->multicast_querier_interval); + clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_querier_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_QUERIER_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; - clockval = jiffies_to_clock_t(br->multicast_query_interval); + clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_query_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_QUERY_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; - clockval = jiffies_to_clock_t(br->multicast_query_response_interval); + clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_query_response_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_QUERY_RESPONSE_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; - clockval = jiffies_to_clock_t(br->multicast_startup_query_interval); + clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_startup_query_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_STARTUP_QUERY_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 2b48b204205e..b4cef3a97f12 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -29,6 +29,8 @@ #define BR_MULTICAST_DEFAULT_HASH_MAX 4096 +#define BR_HWDOM_MAX BITS_PER_LONG + #define BR_VERSION "2.3" /* Control of forwarding link local multicast */ @@ -79,7 +81,8 @@ struct bridge_mcast_other_query { /* selected querier */ struct bridge_mcast_querier { struct br_ip addr; - struct net_bridge_port __rcu *port; + int port_ifidx; + seqcount_t seq; }; /* IGMP/MLD statistics */ @@ -89,6 +92,60 @@ struct bridge_mcast_stats { }; #endif +/* net_bridge_mcast_port must be always defined due to forwarding stubs */ +struct net_bridge_mcast_port { +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + struct net_bridge_port *port; + struct net_bridge_vlan *vlan; + + struct bridge_mcast_own_query ip4_own_query; + struct timer_list ip4_mc_router_timer; + struct hlist_node ip4_rlist; +#if IS_ENABLED(CONFIG_IPV6) + struct bridge_mcast_own_query ip6_own_query; + struct timer_list ip6_mc_router_timer; + struct hlist_node ip6_rlist; +#endif /* IS_ENABLED(CONFIG_IPV6) */ + unsigned char multicast_router; +#endif /* CONFIG_BRIDGE_IGMP_SNOOPING */ +}; + +/* net_bridge_mcast must be always defined due to forwarding stubs */ +struct net_bridge_mcast { +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + struct net_bridge *br; + struct net_bridge_vlan *vlan; + + u32 multicast_last_member_count; + u32 multicast_startup_query_count; + + u8 multicast_querier; + u8 multicast_igmp_version; + u8 multicast_router; +#if IS_ENABLED(CONFIG_IPV6) + u8 multicast_mld_version; +#endif + unsigned long multicast_last_member_interval; + unsigned long multicast_membership_interval; + unsigned long multicast_querier_interval; + unsigned long multicast_query_interval; + unsigned long multicast_query_response_interval; + unsigned long multicast_startup_query_interval; + struct hlist_head ip4_mc_router_list; + struct timer_list ip4_mc_router_timer; + struct bridge_mcast_other_query ip4_other_query; + struct bridge_mcast_own_query ip4_own_query; + struct bridge_mcast_querier ip4_querier; +#if IS_ENABLED(CONFIG_IPV6) + struct hlist_head ip6_mc_router_list; + struct timer_list ip6_mc_router_timer; + struct bridge_mcast_other_query ip6_other_query; + struct bridge_mcast_own_query ip6_own_query; + struct bridge_mcast_querier ip6_querier; +#endif /* IS_ENABLED(CONFIG_IPV6) */ +#endif /* CONFIG_BRIDGE_IGMP_SNOOPING */ +}; + struct br_tunnel_info { __be64 tunnel_id; struct metadata_dst __rcu *tunnel_dst; @@ -98,6 +155,8 @@ struct br_tunnel_info { enum { BR_VLFLAG_PER_PORT_STATS = BIT(0), BR_VLFLAG_ADDED_BY_SWITCHDEV = BIT(1), + BR_VLFLAG_MCAST_ENABLED = BIT(2), + BR_VLFLAG_GLOBAL_MCAST_ENABLED = BIT(3), }; /** @@ -114,6 +173,9 @@ enum { * @refcnt: if MASTER flag set, this is bumped for each port referencing it * @brvlan: if MASTER flag unset, this points to the global per-VLAN context * for this VLAN entry + * @br_mcast_ctx: if MASTER flag set, this is the global vlan multicast context + * @port_mcast_ctx: if MASTER flag unset, this is the per-port/vlan multicast + * context * @vlist: sorted list of VLAN entries * @rcu: used for entry destruction * @@ -141,6 +203,11 @@ struct net_bridge_vlan { struct br_tunnel_info tinfo; + union { + struct net_bridge_mcast br_mcast_ctx; + struct net_bridge_mcast_port port_mcast_ctx; + }; + struct list_head vlist; struct rcu_head rcu; @@ -305,19 +372,13 @@ struct net_bridge_port { struct kobject kobj; struct rcu_head rcu; + struct net_bridge_mcast_port multicast_ctx; + #ifdef CONFIG_BRIDGE_IGMP_SNOOPING - struct bridge_mcast_own_query ip4_own_query; - struct timer_list ip4_mc_router_timer; - struct hlist_node ip4_rlist; -#if IS_ENABLED(CONFIG_IPV6) - struct bridge_mcast_own_query ip6_own_query; - struct timer_list ip6_mc_router_timer; - struct hlist_node ip6_rlist; -#endif /* IS_ENABLED(CONFIG_IPV6) */ + struct bridge_mcast_stats __percpu *mcast_stats; + u32 multicast_eht_hosts_limit; u32 multicast_eht_hosts_cnt; - unsigned char multicast_router; - struct bridge_mcast_stats __percpu *mcast_stats; struct hlist_head mglist; #endif @@ -329,7 +390,12 @@ struct net_bridge_port { struct netpoll *np; #endif #ifdef CONFIG_NET_SWITCHDEV - int offload_fwd_mark; + /* Identifier used to group ports that share the same switchdev + * hardware domain. + */ + int hwdom; + int offload_count; + struct netdev_phys_item_id ppid; #endif u16 group_fwd_mask; u16 backup_redirected_cnt; @@ -367,7 +433,6 @@ enum net_bridge_opts { BROPT_NF_CALL_ARPTABLES, BROPT_GROUP_ADDR_SET, BROPT_MULTICAST_ENABLED, - BROPT_MULTICAST_QUERIER, BROPT_MULTICAST_QUERY_USE_IFADDR, BROPT_MULTICAST_STATS_ENABLED, BROPT_HAS_IPV6_ADDR, @@ -376,6 +441,7 @@ enum net_bridge_opts { BROPT_VLAN_STATS_PER_PORT, BROPT_NO_LL_LEARN, BROPT_VLAN_BRIDGE_BINDING, + BROPT_MCAST_VLAN_SNOOPING_ENABLED, }; struct net_bridge { @@ -426,25 +492,14 @@ struct net_bridge { BR_USER_STP, /* new RSTP in userspace */ } stp_enabled; + struct net_bridge_mcast multicast_ctx; + #ifdef CONFIG_BRIDGE_IGMP_SNOOPING + struct bridge_mcast_stats __percpu *mcast_stats; u32 hash_max; - u32 multicast_last_member_count; - u32 multicast_startup_query_count; - - u8 multicast_igmp_version; - u8 multicast_router; -#if IS_ENABLED(CONFIG_IPV6) - u8 multicast_mld_version; -#endif spinlock_t multicast_lock; - unsigned long multicast_last_member_interval; - unsigned long multicast_membership_interval; - unsigned long multicast_querier_interval; - unsigned long multicast_query_interval; - unsigned long multicast_query_response_interval; - unsigned long multicast_startup_query_interval; struct rhashtable mdb_hash_tbl; struct rhashtable sg_port_tbl; @@ -452,19 +507,6 @@ struct net_bridge { struct hlist_head mcast_gc_list; struct hlist_head mdb_list; - struct hlist_head ip4_mc_router_list; - struct timer_list ip4_mc_router_timer; - struct bridge_mcast_other_query ip4_other_query; - struct bridge_mcast_own_query ip4_own_query; - struct bridge_mcast_querier ip4_querier; - struct bridge_mcast_stats __percpu *mcast_stats; -#if IS_ENABLED(CONFIG_IPV6) - struct hlist_head ip6_mc_router_list; - struct timer_list ip6_mc_router_timer; - struct bridge_mcast_other_query ip6_other_query; - struct bridge_mcast_own_query ip6_own_query; - struct bridge_mcast_querier ip6_querier; -#endif /* IS_ENABLED(CONFIG_IPV6) */ struct work_struct mcast_gc_work; #endif @@ -476,7 +518,12 @@ struct net_bridge { u32 auto_cnt; #ifdef CONFIG_NET_SWITCHDEV - int offload_fwd_mark; + /* Counter used to make sure that hardware domains get unique + * identifiers in case a bridge spans multiple switchdev instances. + */ + int last_hwdom; + /* Bit mask of hardware domain numbers in use */ + unsigned long busy_hwdoms; #endif struct hlist_head fdb_list; @@ -506,7 +553,20 @@ struct br_input_skb_cb { #endif #ifdef CONFIG_NET_SWITCHDEV - int offload_fwd_mark; + /* Set if TX data plane offloading is used towards at least one + * hardware domain. + */ + u8 tx_fwd_offload:1; + /* The switchdev hardware domain from which this packet was received. + * If skb->offload_fwd_mark was set, then this packet was already + * forwarded by hardware to the other ports in the source hardware + * domain, otherwise it wasn't. + */ + int src_hwdom; + /* Bit mask of hardware domains towards this packet has already been + * transmitted using the TX data plane offload. + */ + unsigned long fwd_hwdoms; #endif }; @@ -616,6 +676,20 @@ static inline bool br_vlan_valid_range(const struct bridge_vlan_info *cur, return true; } +static inline u8 br_vlan_multicast_router(const struct net_bridge_vlan *v) +{ + u8 mcast_router = MDB_RTR_TYPE_DISABLED; + +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + if (!br_vlan_is_master(v)) + mcast_router = v->port_mcast_ctx.multicast_router; + else + mcast_router = v->br_mcast_ctx.multicast_router; +#endif + + return mcast_router; +} + static inline int br_afspec_cmd_to_rtm(int cmd) { switch (cmd) { @@ -718,6 +792,8 @@ int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, bool swdev_notify); void br_fdb_offloaded_set(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid, bool offloaded); +int br_fdb_replay(const struct net_device *br_dev, const void *ctx, bool adding, + struct notifier_block *nb); /* br_forward.c */ enum br_pkt_type { @@ -790,15 +866,18 @@ br_port_get_check_rtnl(const struct net_device *dev) } /* br_ioctl.c */ -int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); -int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, - void __user *arg); +int br_dev_siocdevprivate(struct net_device *dev, struct ifreq *rq, + void __user *data, int cmd); +int br_ioctl_stub(struct net *net, struct net_bridge *br, unsigned int cmd, + struct ifreq *ifr, void __user *uarg); /* br_multicast.c */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING -int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, +int br_multicast_rcv(struct net_bridge_mcast **brmctx, + struct net_bridge_mcast_port **pmctx, + struct net_bridge_vlan *vlan, struct sk_buff *skb, u16 vid); -struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, +struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge_mcast *brmctx, struct sk_buff *skb, u16 vid); int br_multicast_add_port(struct net_bridge_port *port); void br_multicast_del_port(struct net_bridge_port *port); @@ -810,17 +889,22 @@ void br_multicast_leave_snoopers(struct net_bridge *br); void br_multicast_open(struct net_bridge *br); void br_multicast_stop(struct net_bridge *br); void br_multicast_dev_del(struct net_bridge *br); -void br_multicast_flood(struct net_bridge_mdb_entry *mdst, - struct sk_buff *skb, bool local_rcv, bool local_orig); -int br_multicast_set_router(struct net_bridge *br, unsigned long val); -int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val); +void br_multicast_flood(struct net_bridge_mdb_entry *mdst, struct sk_buff *skb, + struct net_bridge_mcast *brmctx, + bool local_rcv, bool local_orig); +int br_multicast_set_router(struct net_bridge_mcast *brmctx, unsigned long val); +int br_multicast_set_port_router(struct net_bridge_mcast_port *pmctx, + unsigned long val); +int br_multicast_set_vlan_router(struct net_bridge_vlan *v, u8 mcast_router); int br_multicast_toggle(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack); -int br_multicast_set_querier(struct net_bridge *br, unsigned long val); +int br_multicast_set_querier(struct net_bridge_mcast *brmctx, unsigned long val); int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val); -int br_multicast_set_igmp_version(struct net_bridge *br, unsigned long val); +int br_multicast_set_igmp_version(struct net_bridge_mcast *brmctx, + unsigned long val); #if IS_ENABLED(CONFIG_IPV6) -int br_multicast_set_mld_version(struct net_bridge *br, unsigned long val); +int br_multicast_set_mld_version(struct net_bridge_mcast *brmctx, + unsigned long val); #endif struct net_bridge_mdb_entry * br_mdb_ip_get(struct net_bridge *br, struct br_ip *dst); @@ -835,12 +919,13 @@ int br_mdb_hash_init(struct net_bridge *br); void br_mdb_hash_fini(struct net_bridge *br); void br_mdb_notify(struct net_device *dev, struct net_bridge_mdb_entry *mp, struct net_bridge_port_group *pg, int type); -void br_rtr_notify(struct net_device *dev, struct net_bridge_port *port, +void br_rtr_notify(struct net_device *dev, struct net_bridge_mcast_port *pmctx, int type); void br_multicast_del_pg(struct net_bridge_mdb_entry *mp, struct net_bridge_port_group *pg, struct net_bridge_port_group __rcu **pp); -void br_multicast_count(struct net_bridge *br, const struct net_bridge_port *p, +void br_multicast_count(struct net_bridge *br, + const struct net_bridge_port *p, const struct sk_buff *skb, u8 type, u8 dir); int br_multicast_init_stats(struct net_bridge *br); void br_multicast_uninit_stats(struct net_bridge *br); @@ -849,7 +934,8 @@ void br_multicast_get_stats(const struct net_bridge *br, struct br_mcast_stats *dest); void br_mdb_init(void); void br_mdb_uninit(void); -void br_multicast_host_join(struct net_bridge_mdb_entry *mp, bool notify); +void br_multicast_host_join(const struct net_bridge_mcast *brmctx, + struct net_bridge_mdb_entry *mp, bool notify); void br_multicast_host_leave(struct net_bridge_mdb_entry *mp, bool notify); void br_multicast_star_g_handle_mode(struct net_bridge_port_group *pg, u8 filter_mode); @@ -859,6 +945,29 @@ struct net_bridge_group_src * br_multicast_find_group_src(struct net_bridge_port_group *pg, struct br_ip *ip); void br_multicast_del_group_src(struct net_bridge_group_src *src, bool fastleave); +void br_multicast_ctx_init(struct net_bridge *br, + struct net_bridge_vlan *vlan, + struct net_bridge_mcast *brmctx); +void br_multicast_ctx_deinit(struct net_bridge_mcast *brmctx); +void br_multicast_port_ctx_init(struct net_bridge_port *port, + struct net_bridge_vlan *vlan, + struct net_bridge_mcast_port *pmctx); +void br_multicast_port_ctx_deinit(struct net_bridge_mcast_port *pmctx); +void br_multicast_toggle_one_vlan(struct net_bridge_vlan *vlan, bool on); +int br_multicast_toggle_vlan_snooping(struct net_bridge *br, bool on, + struct netlink_ext_ack *extack); +bool br_multicast_toggle_global_vlan(struct net_bridge_vlan *vlan, bool on); + +int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, + const void *ctx, bool adding, struct notifier_block *nb, + struct netlink_ext_ack *extack); +int br_rports_fill_info(struct sk_buff *skb, + const struct net_bridge_mcast *brmctx); +int br_multicast_dump_querier_state(struct sk_buff *skb, + const struct net_bridge_mcast *brmctx, + int nest_attr); +size_t br_multicast_querier_state_size(void); +size_t br_rports_size(const struct net_bridge_mcast *brmctx); static inline bool br_group_is_l2(const struct br_ip *group) { @@ -869,52 +978,65 @@ static inline bool br_group_is_l2(const struct br_ip *group) rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock)) static inline struct hlist_node * -br_multicast_get_first_rport_node(struct net_bridge *b, struct sk_buff *skb) { +br_multicast_get_first_rport_node(struct net_bridge_mcast *brmctx, + struct sk_buff *skb) +{ #if IS_ENABLED(CONFIG_IPV6) if (skb->protocol == htons(ETH_P_IPV6)) - return rcu_dereference(hlist_first_rcu(&b->ip6_mc_router_list)); + return rcu_dereference(hlist_first_rcu(&brmctx->ip6_mc_router_list)); #endif - return rcu_dereference(hlist_first_rcu(&b->ip4_mc_router_list)); + return rcu_dereference(hlist_first_rcu(&brmctx->ip4_mc_router_list)); } static inline struct net_bridge_port * -br_multicast_rport_from_node_skb(struct hlist_node *rp, struct sk_buff *skb) { +br_multicast_rport_from_node_skb(struct hlist_node *rp, struct sk_buff *skb) +{ + struct net_bridge_mcast_port *mctx; + #if IS_ENABLED(CONFIG_IPV6) if (skb->protocol == htons(ETH_P_IPV6)) - return hlist_entry_safe(rp, struct net_bridge_port, ip6_rlist); + mctx = hlist_entry_safe(rp, struct net_bridge_mcast_port, + ip6_rlist); + else #endif - return hlist_entry_safe(rp, struct net_bridge_port, ip4_rlist); + mctx = hlist_entry_safe(rp, struct net_bridge_mcast_port, + ip4_rlist); + + if (mctx) + return mctx->port; + else + return NULL; } -static inline bool br_ip4_multicast_is_router(struct net_bridge *br) +static inline bool br_ip4_multicast_is_router(struct net_bridge_mcast *brmctx) { - return timer_pending(&br->ip4_mc_router_timer); + return timer_pending(&brmctx->ip4_mc_router_timer); } -static inline bool br_ip6_multicast_is_router(struct net_bridge *br) +static inline bool br_ip6_multicast_is_router(struct net_bridge_mcast *brmctx) { #if IS_ENABLED(CONFIG_IPV6) - return timer_pending(&br->ip6_mc_router_timer); + return timer_pending(&brmctx->ip6_mc_router_timer); #else return false; #endif } static inline bool -br_multicast_is_router(struct net_bridge *br, struct sk_buff *skb) +br_multicast_is_router(struct net_bridge_mcast *brmctx, struct sk_buff *skb) { - switch (br->multicast_router) { + switch (brmctx->multicast_router) { case MDB_RTR_TYPE_PERM: return true; case MDB_RTR_TYPE_TEMP_QUERY: if (skb) { if (skb->protocol == htons(ETH_P_IP)) - return br_ip4_multicast_is_router(br); + return br_ip4_multicast_is_router(brmctx); else if (skb->protocol == htons(ETH_P_IPV6)) - return br_ip6_multicast_is_router(br); + return br_ip6_multicast_is_router(brmctx); } else { - return br_ip4_multicast_is_router(br) || - br_ip6_multicast_is_router(br); + return br_ip4_multicast_is_router(brmctx) || + br_ip6_multicast_is_router(brmctx); } fallthrough; default: @@ -923,14 +1045,14 @@ br_multicast_is_router(struct net_bridge *br, struct sk_buff *skb) } static inline bool -__br_multicast_querier_exists(struct net_bridge *br, - struct bridge_mcast_other_query *querier, - const bool is_ipv6) +__br_multicast_querier_exists(struct net_bridge_mcast *brmctx, + struct bridge_mcast_other_query *querier, + const bool is_ipv6) { bool own_querier_enabled; - if (br_opt_get(br, BROPT_MULTICAST_QUERIER)) { - if (is_ipv6 && !br_opt_get(br, BROPT_HAS_IPV6_ADDR)) + if (brmctx->multicast_querier) { + if (is_ipv6 && !br_opt_get(brmctx->br, BROPT_HAS_IPV6_ADDR)) own_querier_enabled = false; else own_querier_enabled = true; @@ -942,18 +1064,18 @@ __br_multicast_querier_exists(struct net_bridge *br, (own_querier_enabled || timer_pending(&querier->timer)); } -static inline bool br_multicast_querier_exists(struct net_bridge *br, +static inline bool br_multicast_querier_exists(struct net_bridge_mcast *brmctx, struct ethhdr *eth, const struct net_bridge_mdb_entry *mdb) { switch (eth->h_proto) { case (htons(ETH_P_IP)): - return __br_multicast_querier_exists(br, - &br->ip4_other_query, false); + return __br_multicast_querier_exists(brmctx, + &brmctx->ip4_other_query, false); #if IS_ENABLED(CONFIG_IPV6) case (htons(ETH_P_IPV6)): - return __br_multicast_querier_exists(br, - &br->ip6_other_query, true); + return __br_multicast_querier_exists(brmctx, + &brmctx->ip6_other_query, true); #endif default: return !!mdb && br_group_is_l2(&mdb->addr); @@ -974,15 +1096,16 @@ static inline bool br_multicast_is_star_g(const struct br_ip *ip) } } -static inline bool br_multicast_should_handle_mode(const struct net_bridge *br, - __be16 proto) +static inline bool +br_multicast_should_handle_mode(const struct net_bridge_mcast *brmctx, + __be16 proto) { switch (proto) { case htons(ETH_P_IP): - return !!(br->multicast_igmp_version == 3); + return !!(brmctx->multicast_igmp_version == 3); #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): - return !!(br->multicast_mld_version == 2); + return !!(brmctx->multicast_mld_version == 2); #endif default: return false; @@ -994,28 +1117,145 @@ static inline int br_multicast_igmp_type(const struct sk_buff *skb) return BR_INPUT_SKB_CB(skb)->igmp; } -static inline unsigned long br_multicast_lmqt(const struct net_bridge *br) +static inline unsigned long br_multicast_lmqt(const struct net_bridge_mcast *brmctx) { - return br->multicast_last_member_interval * - br->multicast_last_member_count; + return brmctx->multicast_last_member_interval * + brmctx->multicast_last_member_count; } -static inline unsigned long br_multicast_gmi(const struct net_bridge *br) +static inline unsigned long br_multicast_gmi(const struct net_bridge_mcast *brmctx) { /* use the RFC default of 2 for QRV */ - return 2 * br->multicast_query_interval + - br->multicast_query_response_interval; + return 2 * brmctx->multicast_query_interval + + brmctx->multicast_query_response_interval; +} + +static inline bool +br_multicast_ctx_is_vlan(const struct net_bridge_mcast *brmctx) +{ + return !!brmctx->vlan; +} + +static inline bool +br_multicast_port_ctx_is_vlan(const struct net_bridge_mcast_port *pmctx) +{ + return !!pmctx->vlan; +} + +static inline struct net_bridge_mcast * +br_multicast_port_ctx_get_global(const struct net_bridge_mcast_port *pmctx) +{ + if (!br_multicast_port_ctx_is_vlan(pmctx)) + return &pmctx->port->br->multicast_ctx; + else + return &pmctx->vlan->brvlan->br_mcast_ctx; +} + +static inline bool +br_multicast_ctx_vlan_global_disabled(const struct net_bridge_mcast *brmctx) +{ + return br_opt_get(brmctx->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED) && + br_multicast_ctx_is_vlan(brmctx) && + !(brmctx->vlan->priv_flags & BR_VLFLAG_GLOBAL_MCAST_ENABLED); +} + +static inline bool +br_multicast_ctx_vlan_disabled(const struct net_bridge_mcast *brmctx) +{ + return br_multicast_ctx_is_vlan(brmctx) && + !(brmctx->vlan->priv_flags & BR_VLFLAG_MCAST_ENABLED); +} + +static inline bool +br_multicast_port_ctx_vlan_disabled(const struct net_bridge_mcast_port *pmctx) +{ + return br_multicast_port_ctx_is_vlan(pmctx) && + !(pmctx->vlan->priv_flags & BR_VLFLAG_MCAST_ENABLED); +} + +static inline bool +br_multicast_port_ctx_state_disabled(const struct net_bridge_mcast_port *pmctx) +{ + return pmctx->port->state == BR_STATE_DISABLED || + (br_multicast_port_ctx_is_vlan(pmctx) && + (br_multicast_port_ctx_vlan_disabled(pmctx) || + pmctx->vlan->state == BR_STATE_DISABLED)); +} + +static inline bool +br_multicast_port_ctx_state_stopped(const struct net_bridge_mcast_port *pmctx) +{ + return br_multicast_port_ctx_state_disabled(pmctx) || + pmctx->port->state == BR_STATE_BLOCKING || + (br_multicast_port_ctx_is_vlan(pmctx) && + pmctx->vlan->state == BR_STATE_BLOCKING); +} + +static inline bool +br_rports_have_mc_router(const struct net_bridge_mcast *brmctx) +{ +#if IS_ENABLED(CONFIG_IPV6) + return !hlist_empty(&brmctx->ip4_mc_router_list) || + !hlist_empty(&brmctx->ip6_mc_router_list); +#else + return !hlist_empty(&brmctx->ip4_mc_router_list); +#endif +} + +static inline bool +br_multicast_ctx_options_equal(const struct net_bridge_mcast *brmctx1, + const struct net_bridge_mcast *brmctx2) +{ + return brmctx1->multicast_igmp_version == + brmctx2->multicast_igmp_version && + brmctx1->multicast_last_member_count == + brmctx2->multicast_last_member_count && + brmctx1->multicast_startup_query_count == + brmctx2->multicast_startup_query_count && + brmctx1->multicast_last_member_interval == + brmctx2->multicast_last_member_interval && + brmctx1->multicast_membership_interval == + brmctx2->multicast_membership_interval && + brmctx1->multicast_querier_interval == + brmctx2->multicast_querier_interval && + brmctx1->multicast_query_interval == + brmctx2->multicast_query_interval && + brmctx1->multicast_query_response_interval == + brmctx2->multicast_query_response_interval && + brmctx1->multicast_startup_query_interval == + brmctx2->multicast_startup_query_interval && + brmctx1->multicast_querier == brmctx2->multicast_querier && + brmctx1->multicast_router == brmctx2->multicast_router && + !br_rports_have_mc_router(brmctx1) && + !br_rports_have_mc_router(brmctx2) && +#if IS_ENABLED(CONFIG_IPV6) + brmctx1->multicast_mld_version == + brmctx2->multicast_mld_version && +#endif + true; +} + +static inline bool +br_multicast_ctx_matches_vlan_snooping(const struct net_bridge_mcast *brmctx) +{ + bool vlan_snooping_enabled; + + vlan_snooping_enabled = !!br_opt_get(brmctx->br, + BROPT_MCAST_VLAN_SNOOPING_ENABLED); + + return !!(vlan_snooping_enabled == br_multicast_ctx_is_vlan(brmctx)); } #else -static inline int br_multicast_rcv(struct net_bridge *br, - struct net_bridge_port *port, +static inline int br_multicast_rcv(struct net_bridge_mcast **brmctx, + struct net_bridge_mcast_port **pmctx, + struct net_bridge_vlan *vlan, struct sk_buff *skb, u16 vid) { return 0; } -static inline struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, +static inline struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge_mcast *brmctx, struct sk_buff *skb, u16 vid) { return NULL; @@ -1064,17 +1304,18 @@ static inline void br_multicast_dev_del(struct net_bridge *br) static inline void br_multicast_flood(struct net_bridge_mdb_entry *mdst, struct sk_buff *skb, + struct net_bridge_mcast *brmctx, bool local_rcv, bool local_orig) { } -static inline bool br_multicast_is_router(struct net_bridge *br, +static inline bool br_multicast_is_router(struct net_bridge_mcast *brmctx, struct sk_buff *skb) { return false; } -static inline bool br_multicast_querier_exists(struct net_bridge *br, +static inline bool br_multicast_querier_exists(struct net_bridge_mcast *brmctx, struct ethhdr *eth, const struct net_bridge_mdb_entry *mdb) { @@ -1118,13 +1359,67 @@ static inline int br_multicast_igmp_type(const struct sk_buff *skb) { return 0; } + +static inline void br_multicast_ctx_init(struct net_bridge *br, + struct net_bridge_vlan *vlan, + struct net_bridge_mcast *brmctx) +{ +} + +static inline void br_multicast_ctx_deinit(struct net_bridge_mcast *brmctx) +{ +} + +static inline void br_multicast_port_ctx_init(struct net_bridge_port *port, + struct net_bridge_vlan *vlan, + struct net_bridge_mcast_port *pmctx) +{ +} + +static inline void br_multicast_port_ctx_deinit(struct net_bridge_mcast_port *pmctx) +{ +} + +static inline void br_multicast_toggle_one_vlan(struct net_bridge_vlan *vlan, + bool on) +{ +} + +static inline int br_multicast_toggle_vlan_snooping(struct net_bridge *br, + bool on, + struct netlink_ext_ack *extack) +{ + return -EOPNOTSUPP; +} + +static inline bool br_multicast_toggle_global_vlan(struct net_bridge_vlan *vlan, + bool on) +{ + return false; +} + +static inline int br_mdb_replay(struct net_device *br_dev, + struct net_device *dev, const void *ctx, + bool adding, struct notifier_block *nb, + struct netlink_ext_ack *extack) +{ + return -EOPNOTSUPP; +} + +static inline bool +br_multicast_ctx_options_equal(const struct net_bridge_mcast *brmctx1, + const struct net_bridge_mcast *brmctx2) +{ + return true; +} #endif /* br_vlan.c */ #ifdef CONFIG_BRIDGE_VLAN_FILTERING bool br_allowed_ingress(const struct net_bridge *br, struct net_bridge_vlan_group *vg, struct sk_buff *skb, - u16 *vid, u8 *state); + u16 *vid, u8 *state, + struct net_bridge_vlan **vlan); bool br_allowed_egress(struct net_bridge_vlan_group *vg, const struct sk_buff *skb); bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid); @@ -1168,6 +1463,9 @@ void br_vlan_notify(const struct net_bridge *br, const struct net_bridge_port *p, u16 vid, u16 vid_range, int cmd); +int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, + const void *ctx, bool adding, struct notifier_block *nb, + struct netlink_ext_ack *extack); bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, const struct net_bridge_vlan *range_end); @@ -1236,8 +1534,11 @@ static inline u16 br_vlan_flags(const struct net_bridge_vlan *v, u16 pvid) static inline bool br_allowed_ingress(const struct net_bridge *br, struct net_bridge_vlan_group *vg, struct sk_buff *skb, - u16 *vid, u8 *state) + u16 *vid, u8 *state, + struct net_bridge_vlan **vlan) + { + *vlan = NULL; return true; } @@ -1410,6 +1711,14 @@ static inline bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, { return true; } + +static inline int br_vlan_replay(struct net_device *br_dev, + struct net_device *dev, const void *ctx, + bool adding, struct notifier_block *nb, + struct netlink_ext_ack *extack) +{ + return -EOPNOTSUPP; +} #endif /* br_vlan_options.c */ @@ -1424,6 +1733,14 @@ int br_vlan_process_options(const struct net_bridge *br, struct net_bridge_vlan *range_end, struct nlattr **tb, struct netlink_ext_ack *extack); +int br_vlan_rtm_process_global_options(struct net_device *dev, + const struct nlattr *attr, + int cmd, + struct netlink_ext_ack *extack); +bool br_vlan_global_opts_can_enter_range(const struct net_bridge_vlan *v_curr, + const struct net_bridge_vlan *r_end); +bool br_vlan_global_opts_fill(struct sk_buff *skb, u16 vid, u16 vid_range, + const struct net_bridge_vlan *v_opts); /* vlan state manipulation helpers using *_ONCE to annotate lock-free access */ static inline u8 br_vlan_get_state(const struct net_bridge_vlan *v) @@ -1645,7 +1962,25 @@ static inline void br_sysfs_delbr(struct net_device *dev) { return; } /* br_switchdev.c */ #ifdef CONFIG_NET_SWITCHDEV -int nbp_switchdev_mark_set(struct net_bridge_port *p); +int br_switchdev_port_offload(struct net_bridge_port *p, + struct net_device *dev, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb, + bool tx_fwd_offload, + struct netlink_ext_ack *extack); + +void br_switchdev_port_unoffload(struct net_bridge_port *p, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb); + +bool br_switchdev_frame_uses_tx_fwd_offload(struct sk_buff *skb); + +void br_switchdev_frame_set_offload_fwd_mark(struct sk_buff *skb); + +void nbp_switchdev_frame_mark_tx_fwd_offload(const struct net_bridge_port *p, + struct sk_buff *skb); +void nbp_switchdev_frame_mark_tx_fwd_to_hwdom(const struct net_bridge_port *p, + struct sk_buff *skb); void nbp_switchdev_frame_mark(const struct net_bridge_port *p, struct sk_buff *skb); bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p, @@ -1659,15 +1994,50 @@ void br_switchdev_fdb_notify(struct net_bridge *br, int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags, struct netlink_ext_ack *extack); int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid); +void br_switchdev_init(struct net_bridge *br); static inline void br_switchdev_frame_unmark(struct sk_buff *skb) { skb->offload_fwd_mark = 0; } #else -static inline int nbp_switchdev_mark_set(struct net_bridge_port *p) +static inline int +br_switchdev_port_offload(struct net_bridge_port *p, + struct net_device *dev, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb, + bool tx_fwd_offload, + struct netlink_ext_ack *extack) +{ + return -EOPNOTSUPP; +} + +static inline void +br_switchdev_port_unoffload(struct net_bridge_port *p, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb) +{ +} + +static inline bool br_switchdev_frame_uses_tx_fwd_offload(struct sk_buff *skb) +{ + return false; +} + +static inline void br_switchdev_frame_set_offload_fwd_mark(struct sk_buff *skb) +{ +} + +static inline void +nbp_switchdev_frame_mark_tx_fwd_offload(const struct net_bridge_port *p, + struct sk_buff *skb) +{ +} + +static inline void +nbp_switchdev_frame_mark_tx_fwd_to_hwdom(const struct net_bridge_port *p, + struct sk_buff *skb) { - return 0; } static inline void nbp_switchdev_frame_mark(const struct net_bridge_port *p, @@ -1710,6 +2080,11 @@ br_switchdev_fdb_notify(struct net_bridge *br, static inline void br_switchdev_frame_unmark(struct sk_buff *skb) { } + +static inline void br_switchdev_init(struct net_bridge *br) +{ +} + #endif /* CONFIG_NET_SWITCHDEV */ /* br_arp_nd_proxy.c */ diff --git a/net/bridge/br_private_mcast_eht.h b/net/bridge/br_private_mcast_eht.h index f89049f4892c..adf82a05515a 100644 --- a/net/bridge/br_private_mcast_eht.h +++ b/net/bridge/br_private_mcast_eht.h @@ -51,7 +51,8 @@ struct net_bridge_group_eht_set { #ifdef CONFIG_BRIDGE_IGMP_SNOOPING void br_multicast_eht_clean_sets(struct net_bridge_port_group *pg); -bool br_multicast_eht_handle(struct net_bridge_port_group *pg, +bool br_multicast_eht_handle(const struct net_bridge_mcast *brmctx, + struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, diff --git a/net/bridge/br_private_tunnel.h b/net/bridge/br_private_tunnel.h index c54cc26211d7..2b053289f016 100644 --- a/net/bridge/br_private_tunnel.h +++ b/net/bridge/br_private_tunnel.h @@ -38,9 +38,9 @@ int nbp_vlan_tunnel_info_add(const struct net_bridge_port *port, u16 vid, void nbp_vlan_tunnel_info_flush(struct net_bridge_port *port); void vlan_tunnel_info_del(struct net_bridge_vlan_group *vg, struct net_bridge_vlan *vlan); -int br_handle_ingress_vlan_tunnel(struct sk_buff *skb, - struct net_bridge_port *p, - struct net_bridge_vlan_group *vg); +void br_handle_ingress_vlan_tunnel(struct sk_buff *skb, + struct net_bridge_port *p, + struct net_bridge_vlan_group *vg); int br_handle_egress_vlan_tunnel(struct sk_buff *skb, struct net_bridge_vlan *vlan); bool vlan_tunid_inrange(const struct net_bridge_vlan *v_curr, diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index d3adee0f91f9..6bf518d78f02 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -8,50 +8,65 @@ #include "br_private.h" -static int br_switchdev_mark_get(struct net_bridge *br, struct net_device *dev) -{ - struct net_bridge_port *p; +static struct static_key_false br_switchdev_tx_fwd_offload; - /* dev is yet to be added to the port list. */ - list_for_each_entry(p, &br->port_list, list) { - if (netdev_port_same_parent_id(dev, p->dev)) - return p->offload_fwd_mark; - } +static bool nbp_switchdev_can_offload_tx_fwd(const struct net_bridge_port *p, + const struct sk_buff *skb) +{ + if (!static_branch_unlikely(&br_switchdev_tx_fwd_offload)) + return false; - return ++br->offload_fwd_mark; + return (p->flags & BR_TX_FWD_OFFLOAD) && + (p->hwdom != BR_INPUT_SKB_CB(skb)->src_hwdom); } -int nbp_switchdev_mark_set(struct net_bridge_port *p) +bool br_switchdev_frame_uses_tx_fwd_offload(struct sk_buff *skb) { - struct netdev_phys_item_id ppid = { }; - int err; + if (!static_branch_unlikely(&br_switchdev_tx_fwd_offload)) + return false; - ASSERT_RTNL(); + return BR_INPUT_SKB_CB(skb)->tx_fwd_offload; +} - err = dev_get_port_parent_id(p->dev, &ppid, true); - if (err) { - if (err == -EOPNOTSUPP) - return 0; - return err; - } +void br_switchdev_frame_set_offload_fwd_mark(struct sk_buff *skb) +{ + skb->offload_fwd_mark = br_switchdev_frame_uses_tx_fwd_offload(skb); +} - p->offload_fwd_mark = br_switchdev_mark_get(p->br, p->dev); +/* Mark the frame for TX forwarding offload if this egress port supports it */ +void nbp_switchdev_frame_mark_tx_fwd_offload(const struct net_bridge_port *p, + struct sk_buff *skb) +{ + if (nbp_switchdev_can_offload_tx_fwd(p, skb)) + BR_INPUT_SKB_CB(skb)->tx_fwd_offload = true; +} - return 0; +/* Lazily adds the hwdom of the egress bridge port to the bit mask of hwdoms + * that the skb has been already forwarded to, to avoid further cloning to + * other ports in the same hwdom by making nbp_switchdev_allowed_egress() + * return false. + */ +void nbp_switchdev_frame_mark_tx_fwd_to_hwdom(const struct net_bridge_port *p, + struct sk_buff *skb) +{ + if (nbp_switchdev_can_offload_tx_fwd(p, skb)) + set_bit(p->hwdom, &BR_INPUT_SKB_CB(skb)->fwd_hwdoms); } void nbp_switchdev_frame_mark(const struct net_bridge_port *p, struct sk_buff *skb) { - if (skb->offload_fwd_mark && !WARN_ON_ONCE(!p->offload_fwd_mark)) - BR_INPUT_SKB_CB(skb)->offload_fwd_mark = p->offload_fwd_mark; + if (p->hwdom) + BR_INPUT_SKB_CB(skb)->src_hwdom = p->hwdom; } bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p, const struct sk_buff *skb) { - return !skb->offload_fwd_mark || - BR_INPUT_SKB_CB(skb)->offload_fwd_mark != p->offload_fwd_mark; + struct br_input_skb_cb *cb = BR_INPUT_SKB_CB(skb); + + return !test_bit(p->hwdom, &cb->fwd_hwdoms) && + (!skb->offload_fwd_mark || cb->src_hwdom != p->hwdom); } /* Flags that can be offloaded to hardware */ @@ -112,7 +127,6 @@ br_switchdev_fdb_notify(struct net_bridge *br, const struct net_bridge_fdb_entry *fdb, int type) { const struct net_bridge_port *dst = READ_ONCE(fdb->dst); - struct net_device *dev = dst ? dst->dev : br->dev; struct switchdev_notifier_fdb_info info = { .addr = fdb->key.addr.addr, .vid = fdb->key.vlan_id, @@ -120,6 +134,7 @@ br_switchdev_fdb_notify(struct net_bridge *br, .is_local = test_bit(BR_FDB_LOCAL, &fdb->flags), .offloaded = test_bit(BR_FDB_OFFLOADED, &fdb->flags), }; + struct net_device *dev = (!dst || info.is_local) ? br->dev : dst->dev; switch (type) { case RTM_DELNEIGH: @@ -156,3 +171,182 @@ int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid) return switchdev_port_obj_del(dev, &v.obj); } + +static int nbp_switchdev_hwdom_set(struct net_bridge_port *joining) +{ + struct net_bridge *br = joining->br; + struct net_bridge_port *p; + int hwdom; + + /* joining is yet to be added to the port list. */ + list_for_each_entry(p, &br->port_list, list) { + if (netdev_phys_item_id_same(&joining->ppid, &p->ppid)) { + joining->hwdom = p->hwdom; + return 0; + } + } + + hwdom = find_next_zero_bit(&br->busy_hwdoms, BR_HWDOM_MAX, 1); + if (hwdom >= BR_HWDOM_MAX) + return -EBUSY; + + set_bit(hwdom, &br->busy_hwdoms); + joining->hwdom = hwdom; + return 0; +} + +static void nbp_switchdev_hwdom_put(struct net_bridge_port *leaving) +{ + struct net_bridge *br = leaving->br; + struct net_bridge_port *p; + + /* leaving is no longer in the port list. */ + list_for_each_entry(p, &br->port_list, list) { + if (p->hwdom == leaving->hwdom) + return; + } + + clear_bit(leaving->hwdom, &br->busy_hwdoms); +} + +static int nbp_switchdev_add(struct net_bridge_port *p, + struct netdev_phys_item_id ppid, + bool tx_fwd_offload, + struct netlink_ext_ack *extack) +{ + int err; + + if (p->offload_count) { + /* Prevent unsupported configurations such as a bridge port + * which is a bonding interface, and the member ports are from + * different hardware switches. + */ + if (!netdev_phys_item_id_same(&p->ppid, &ppid)) { + NL_SET_ERR_MSG_MOD(extack, + "Same bridge port cannot be offloaded by two physical switches"); + return -EBUSY; + } + + /* Tolerate drivers that call switchdev_bridge_port_offload() + * more than once for the same bridge port, such as when the + * bridge port is an offloaded bonding/team interface. + */ + p->offload_count++; + + return 0; + } + + p->ppid = ppid; + p->offload_count = 1; + + err = nbp_switchdev_hwdom_set(p); + if (err) + return err; + + if (tx_fwd_offload) { + p->flags |= BR_TX_FWD_OFFLOAD; + static_branch_inc(&br_switchdev_tx_fwd_offload); + } + + return 0; +} + +static void nbp_switchdev_del(struct net_bridge_port *p) +{ + if (WARN_ON(!p->offload_count)) + return; + + p->offload_count--; + + if (p->offload_count) + return; + + if (p->hwdom) + nbp_switchdev_hwdom_put(p); + + if (p->flags & BR_TX_FWD_OFFLOAD) { + p->flags &= ~BR_TX_FWD_OFFLOAD; + static_branch_dec(&br_switchdev_tx_fwd_offload); + } +} + +static int nbp_switchdev_sync_objs(struct net_bridge_port *p, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb, + struct netlink_ext_ack *extack) +{ + struct net_device *br_dev = p->br->dev; + struct net_device *dev = p->dev; + int err; + + err = br_vlan_replay(br_dev, dev, ctx, true, blocking_nb, extack); + if (err && err != -EOPNOTSUPP) + return err; + + err = br_mdb_replay(br_dev, dev, ctx, true, blocking_nb, extack); + if (err && err != -EOPNOTSUPP) + return err; + + err = br_fdb_replay(br_dev, ctx, true, atomic_nb); + if (err && err != -EOPNOTSUPP) + return err; + + return 0; +} + +static void nbp_switchdev_unsync_objs(struct net_bridge_port *p, + const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb) +{ + struct net_device *br_dev = p->br->dev; + struct net_device *dev = p->dev; + + br_vlan_replay(br_dev, dev, ctx, false, blocking_nb, NULL); + + br_mdb_replay(br_dev, dev, ctx, false, blocking_nb, NULL); + + br_fdb_replay(br_dev, ctx, false, atomic_nb); +} + +/* Let the bridge know that this port is offloaded, so that it can assign a + * switchdev hardware domain to it. + */ +int br_switchdev_port_offload(struct net_bridge_port *p, + struct net_device *dev, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb, + bool tx_fwd_offload, + struct netlink_ext_ack *extack) +{ + struct netdev_phys_item_id ppid; + int err; + + err = dev_get_port_parent_id(dev, &ppid, false); + if (err) + return err; + + err = nbp_switchdev_add(p, ppid, tx_fwd_offload, extack); + if (err) + return err; + + err = nbp_switchdev_sync_objs(p, ctx, atomic_nb, blocking_nb, extack); + if (err) + goto out_switchdev_del; + + return 0; + +out_switchdev_del: + nbp_switchdev_del(p); + + return err; +} + +void br_switchdev_port_unoffload(struct net_bridge_port *p, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb) +{ + nbp_switchdev_unsync_objs(p, ctx, atomic_nb, blocking_nb); + + nbp_switchdev_del(p); +} diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index 381467b691d5..d9a89ddd0331 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -384,13 +384,13 @@ static ssize_t multicast_router_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); - return sprintf(buf, "%d\n", br->multicast_router); + return sprintf(buf, "%d\n", br->multicast_ctx.multicast_router); } static int set_multicast_router(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { - return br_multicast_set_router(br, val); + return br_multicast_set_router(&br->multicast_ctx, val); } static ssize_t multicast_router_store(struct device *d, @@ -447,13 +447,13 @@ static ssize_t multicast_querier_show(struct device *d, char *buf) { struct net_bridge *br = to_bridge(d); - return sprintf(buf, "%d\n", br_opt_get(br, BROPT_MULTICAST_QUERIER)); + return sprintf(buf, "%d\n", br->multicast_ctx.multicast_querier); } static int set_multicast_querier(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { - return br_multicast_set_querier(br, val); + return br_multicast_set_querier(&br->multicast_ctx, val); } static ssize_t multicast_querier_store(struct device *d, @@ -514,13 +514,13 @@ static ssize_t multicast_igmp_version_show(struct device *d, { struct net_bridge *br = to_bridge(d); - return sprintf(buf, "%u\n", br->multicast_igmp_version); + return sprintf(buf, "%u\n", br->multicast_ctx.multicast_igmp_version); } static int set_multicast_igmp_version(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { - return br_multicast_set_igmp_version(br, val); + return br_multicast_set_igmp_version(&br->multicast_ctx, val); } static ssize_t multicast_igmp_version_store(struct device *d, @@ -536,13 +536,13 @@ static ssize_t multicast_last_member_count_show(struct device *d, char *buf) { struct net_bridge *br = to_bridge(d); - return sprintf(buf, "%u\n", br->multicast_last_member_count); + return sprintf(buf, "%u\n", br->multicast_ctx.multicast_last_member_count); } static int set_last_member_count(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { - br->multicast_last_member_count = val; + br->multicast_ctx.multicast_last_member_count = val; return 0; } @@ -558,13 +558,13 @@ static ssize_t multicast_startup_query_count_show( struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); - return sprintf(buf, "%u\n", br->multicast_startup_query_count); + return sprintf(buf, "%u\n", br->multicast_ctx.multicast_startup_query_count); } static int set_startup_query_count(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { - br->multicast_startup_query_count = val; + br->multicast_ctx.multicast_startup_query_count = val; return 0; } @@ -581,13 +581,13 @@ static ssize_t multicast_last_member_interval_show( { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%lu\n", - jiffies_to_clock_t(br->multicast_last_member_interval)); + jiffies_to_clock_t(br->multicast_ctx.multicast_last_member_interval)); } static int set_last_member_interval(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { - br->multicast_last_member_interval = clock_t_to_jiffies(val); + br->multicast_ctx.multicast_last_member_interval = clock_t_to_jiffies(val); return 0; } @@ -604,13 +604,13 @@ static ssize_t multicast_membership_interval_show( { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%lu\n", - jiffies_to_clock_t(br->multicast_membership_interval)); + jiffies_to_clock_t(br->multicast_ctx.multicast_membership_interval)); } static int set_membership_interval(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { - br->multicast_membership_interval = clock_t_to_jiffies(val); + br->multicast_ctx.multicast_membership_interval = clock_t_to_jiffies(val); return 0; } @@ -628,13 +628,13 @@ static ssize_t multicast_querier_interval_show(struct device *d, { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%lu\n", - jiffies_to_clock_t(br->multicast_querier_interval)); + jiffies_to_clock_t(br->multicast_ctx.multicast_querier_interval)); } static int set_querier_interval(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { - br->multicast_querier_interval = clock_t_to_jiffies(val); + br->multicast_ctx.multicast_querier_interval = clock_t_to_jiffies(val); return 0; } @@ -652,13 +652,13 @@ static ssize_t multicast_query_interval_show(struct device *d, { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%lu\n", - jiffies_to_clock_t(br->multicast_query_interval)); + jiffies_to_clock_t(br->multicast_ctx.multicast_query_interval)); } static int set_query_interval(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { - br->multicast_query_interval = clock_t_to_jiffies(val); + br->multicast_ctx.multicast_query_interval = clock_t_to_jiffies(val); return 0; } @@ -676,13 +676,13 @@ static ssize_t multicast_query_response_interval_show( struct net_bridge *br = to_bridge(d); return sprintf( buf, "%lu\n", - jiffies_to_clock_t(br->multicast_query_response_interval)); + jiffies_to_clock_t(br->multicast_ctx.multicast_query_response_interval)); } static int set_query_response_interval(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { - br->multicast_query_response_interval = clock_t_to_jiffies(val); + br->multicast_ctx.multicast_query_response_interval = clock_t_to_jiffies(val); return 0; } @@ -700,13 +700,13 @@ static ssize_t multicast_startup_query_interval_show( struct net_bridge *br = to_bridge(d); return sprintf( buf, "%lu\n", - jiffies_to_clock_t(br->multicast_startup_query_interval)); + jiffies_to_clock_t(br->multicast_ctx.multicast_startup_query_interval)); } static int set_startup_query_interval(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { - br->multicast_startup_query_interval = clock_t_to_jiffies(val); + br->multicast_ctx.multicast_startup_query_interval = clock_t_to_jiffies(val); return 0; } @@ -751,13 +751,13 @@ static ssize_t multicast_mld_version_show(struct device *d, { struct net_bridge *br = to_bridge(d); - return sprintf(buf, "%u\n", br->multicast_mld_version); + return sprintf(buf, "%u\n", br->multicast_ctx.multicast_mld_version); } static int set_multicast_mld_version(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { - return br_multicast_set_mld_version(br, val); + return br_multicast_set_mld_version(&br->multicast_ctx, val); } static ssize_t multicast_mld_version_store(struct device *d, diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 72e92376eef1..07fa76080512 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -244,13 +244,13 @@ BRPORT_ATTR_FLAG(isolated, BR_ISOLATED); #ifdef CONFIG_BRIDGE_IGMP_SNOOPING static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf) { - return sprintf(buf, "%d\n", p->multicast_router); + return sprintf(buf, "%d\n", p->multicast_ctx.multicast_router); } static int store_multicast_router(struct net_bridge_port *p, unsigned long v) { - return br_multicast_set_port_router(p, v); + return br_multicast_set_port_router(&p->multicast_ctx, v); } static BRPORT_ATTR(multicast_router, 0644, show_multicast_router, store_multicast_router); diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index a08e9f193009..19f65ab91a02 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -190,6 +190,8 @@ static void br_vlan_put_master(struct net_bridge_vlan *masterv) rhashtable_remove_fast(&vg->vlan_hash, &masterv->vnode, br_vlan_rht_params); __vlan_del_list(masterv); + br_multicast_toggle_one_vlan(masterv, false); + br_multicast_ctx_deinit(&masterv->br_mcast_ctx); call_rcu(&masterv->rcu, br_master_vlan_rcu_free); } } @@ -280,10 +282,13 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags, } else { v->stats = masterv->stats; } + br_multicast_port_ctx_init(p, v, &v->port_mcast_ctx); } else { err = br_switchdev_port_vlan_add(dev, v->vid, flags, extack); if (err && err != -EOPNOTSUPP) goto out; + br_multicast_ctx_init(br, v, &v->br_mcast_ctx); + v->priv_flags |= BR_VLFLAG_GLOBAL_MCAST_ENABLED; } /* Add the dev mac and count the vlan only if it's usable */ @@ -306,6 +311,7 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags, __vlan_add_list(v); __vlan_add_flags(v, flags); + br_multicast_toggle_one_vlan(v, true); if (p) nbp_vlan_set_vlan_dev_state(p, v->vid); @@ -374,6 +380,8 @@ static int __vlan_del(struct net_bridge_vlan *v) br_vlan_rht_params); __vlan_del_list(v); nbp_vlan_set_vlan_dev_state(p, v->vid); + br_multicast_toggle_one_vlan(v, false); + br_multicast_port_ctx_deinit(&v->port_mcast_ctx); call_rcu(&v->rcu, nbp_vlan_rcu_free); } @@ -457,7 +465,15 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br, u64_stats_update_end(&stats->syncp); } - if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) + /* If the skb will be sent using forwarding offload, the assumption is + * that the switchdev will inject the packet into hardware together + * with the bridge VLAN, so that it can be forwarded according to that + * VLAN. The switchdev should deal with popping the VLAN header in + * hardware on each egress port as appropriate. So only strip the VLAN + * header if forwarding offload is not being used. + */ + if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED && + !br_switchdev_frame_uses_tx_fwd_offload(skb)) __vlan_hwaccel_clear_tag(skb); if (p && (p->flags & BR_VLAN_TUNNEL) && @@ -473,7 +489,8 @@ out: static bool __allowed_ingress(const struct net_bridge *br, struct net_bridge_vlan_group *vg, struct sk_buff *skb, u16 *vid, - u8 *state) + u8 *state, + struct net_bridge_vlan **vlan) { struct pcpu_sw_netstats *stats; struct net_bridge_vlan *v; @@ -538,8 +555,9 @@ static bool __allowed_ingress(const struct net_bridge *br, */ skb->vlan_tci |= pvid; - /* if stats are disabled we can avoid the lookup */ - if (!br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { + /* if snooping and stats are disabled we can avoid the lookup */ + if (!br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED) && + !br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { if (*state == BR_STATE_FORWARDING) { *state = br_vlan_get_pvid_state(vg); return br_vlan_state_allowed(*state, true); @@ -566,6 +584,8 @@ static bool __allowed_ingress(const struct net_bridge *br, u64_stats_update_end(&stats->syncp); } + *vlan = v; + return true; drop: @@ -575,17 +595,19 @@ drop: bool br_allowed_ingress(const struct net_bridge *br, struct net_bridge_vlan_group *vg, struct sk_buff *skb, - u16 *vid, u8 *state) + u16 *vid, u8 *state, + struct net_bridge_vlan **vlan) { /* If VLAN filtering is disabled on the bridge, all packets are * permitted. */ + *vlan = NULL; if (!br_opt_get(br, BROPT_VLAN_ENABLED)) { BR_INPUT_SKB_CB(skb)->vlan_filtered = false; return true; } - return __allowed_ingress(br, vg, skb, vid, state); + return __allowed_ingress(br, vg, skb, vid, state, vlan); } /* Called under RCU. */ @@ -672,6 +694,7 @@ static int br_vlan_add_existing(struct net_bridge *br, vlan->flags |= BRIDGE_VLAN_INFO_BRENTRY; vg->num_vlans++; *changed = true; + br_multicast_toggle_one_vlan(vlan, true); } if (__vlan_add_flags(vlan, flags)) @@ -818,14 +841,21 @@ int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val, if (br_opt_get(br, BROPT_VLAN_ENABLED) == !!val) return 0; + br_opt_toggle(br, BROPT_VLAN_ENABLED, !!val); + err = switchdev_port_attr_set(br->dev, &attr, extack); - if (err && err != -EOPNOTSUPP) + if (err && err != -EOPNOTSUPP) { + br_opt_toggle(br, BROPT_VLAN_ENABLED, !val); return err; + } - br_opt_toggle(br, BROPT_VLAN_ENABLED, !!val); br_manage_promisc(br); recalculate_group_addr(br); br_recalculate_fwd_mask(br); + if (!val && br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) { + br_info(br, "vlan filtering disabled, automatically disabling multicast vlan snooping\n"); + br_multicast_toggle_vlan_snooping(br, false, NULL); + } return 0; } @@ -1420,6 +1450,33 @@ int br_vlan_get_info(const struct net_device *dev, u16 vid, } EXPORT_SYMBOL_GPL(br_vlan_get_info); +int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid, + struct bridge_vlan_info *p_vinfo) +{ + struct net_bridge_vlan_group *vg; + struct net_bridge_vlan *v; + struct net_bridge_port *p; + + p = br_port_get_check_rcu(dev); + if (p) + vg = nbp_vlan_group_rcu(p); + else if (netif_is_bridge_master(dev)) + vg = br_vlan_group_rcu(netdev_priv(dev)); + else + return -EINVAL; + + v = br_vlan_find(vg, vid); + if (!v) + return -ENOENT; + + p_vinfo->vid = vid; + p_vinfo->flags = v->flags; + if (vid == br_get_pvid(vg)) + p_vinfo->flags |= BRIDGE_VLAN_INFO_PVID; + return 0; +} +EXPORT_SYMBOL_GPL(br_vlan_get_info_rcu); + static int br_vlan_is_bind_vlan_dev(const struct net_device *dev) { return is_vlan_dev(dev) && @@ -1838,6 +1895,9 @@ int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, ASSERT_RTNL(); + if (!nb) + return 0; + if (!netif_is_bridge_master(br_dev)) return -EINVAL; @@ -1884,7 +1944,6 @@ int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, return err; } -EXPORT_SYMBOL_GPL(br_vlan_replay); /* check if v_curr can enter a range ending in range_end */ bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, @@ -1901,6 +1960,7 @@ static int br_vlan_dump_dev(const struct net_device *dev, u32 dump_flags) { struct net_bridge_vlan *v, *range_start = NULL, *range_end = NULL; + bool dump_global = !!(dump_flags & BRIDGE_VLANDB_DUMPF_GLOBAL); bool dump_stats = !!(dump_flags & BRIDGE_VLANDB_DUMPF_STATS); struct net_bridge_vlan_group *vg; int idx = 0, s_idx = cb->args[1]; @@ -1919,6 +1979,10 @@ static int br_vlan_dump_dev(const struct net_device *dev, vg = br_vlan_group_rcu(br); p = NULL; } else { + /* global options are dumped only for bridge devices */ + if (dump_global) + return 0; + p = br_port_get_rcu(dev); if (WARN_ON(!p)) return -EINVAL; @@ -1941,7 +2005,7 @@ static int br_vlan_dump_dev(const struct net_device *dev, /* idx must stay at range's beginning until it is filled in */ list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { - if (!br_vlan_should_use(v)) + if (!dump_global && !br_vlan_should_use(v)) continue; if (idx < s_idx) { idx++; @@ -1954,8 +2018,21 @@ static int br_vlan_dump_dev(const struct net_device *dev, continue; } - if (dump_stats || v->vid == pvid || - !br_vlan_can_enter_range(v, range_end)) { + if (dump_global) { + if (br_vlan_global_opts_can_enter_range(v, range_end)) + goto update_end; + if (!br_vlan_global_opts_fill(skb, range_start->vid, + range_end->vid, + range_start)) { + err = -EMSGSIZE; + break; + } + /* advance number of filled vlans */ + idx += range_end->vid - range_start->vid + 1; + + range_start = v; + } else if (dump_stats || v->vid == pvid || + !br_vlan_can_enter_range(v, range_end)) { u16 vlan_flags = br_vlan_flags(range_start, pvid); if (!br_vlan_fill_vids(skb, range_start->vid, @@ -1969,6 +2046,7 @@ static int br_vlan_dump_dev(const struct net_device *dev, range_start = v; } +update_end: range_end = v; } @@ -1977,11 +2055,18 @@ static int br_vlan_dump_dev(const struct net_device *dev, * - last vlan (range_start == range_end, not in range) * - last vlan range (range_start != range_end, in range) */ - if (!err && range_start && - !br_vlan_fill_vids(skb, range_start->vid, range_end->vid, - range_start, br_vlan_flags(range_start, pvid), - dump_stats)) - err = -EMSGSIZE; + if (!err && range_start) { + if (dump_global && + !br_vlan_global_opts_fill(skb, range_start->vid, + range_end->vid, range_start)) + err = -EMSGSIZE; + else if (!dump_global && + !br_vlan_fill_vids(skb, range_start->vid, + range_end->vid, range_start, + br_vlan_flags(range_start, pvid), + dump_stats)) + err = -EMSGSIZE; + } cb->args[1] = err ? idx : 0; @@ -2051,6 +2136,7 @@ static const struct nla_policy br_vlan_db_policy[BRIDGE_VLANDB_ENTRY_MAX + 1] = [BRIDGE_VLANDB_ENTRY_RANGE] = { .type = NLA_U16 }, [BRIDGE_VLANDB_ENTRY_STATE] = { .type = NLA_U8 }, [BRIDGE_VLANDB_ENTRY_TUNNEL_INFO] = { .type = NLA_NESTED }, + [BRIDGE_VLANDB_ENTRY_MCAST_ROUTER] = { .type = NLA_U8 }, }; static int br_vlan_rtm_process_one(struct net_device *dev, @@ -2185,12 +2271,22 @@ static int br_vlan_rtm_process(struct sk_buff *skb, struct nlmsghdr *nlh, } nlmsg_for_each_attr(attr, nlh, sizeof(*bvm), rem) { - if (nla_type(attr) != BRIDGE_VLANDB_ENTRY) + switch (nla_type(attr)) { + case BRIDGE_VLANDB_ENTRY: + err = br_vlan_rtm_process_one(dev, attr, + nlh->nlmsg_type, + extack); + break; + case BRIDGE_VLANDB_GLOBAL_OPTIONS: + err = br_vlan_rtm_process_global_options(dev, attr, + nlh->nlmsg_type, + extack); + break; + default: continue; + } vlans++; - err = br_vlan_rtm_process_one(dev, attr, nlh->nlmsg_type, - extack); if (err) break; } diff --git a/net/bridge/br_vlan_options.c b/net/bridge/br_vlan_options.c index b4add9ea8964..8ffd4ed2563c 100644 --- a/net/bridge/br_vlan_options.c +++ b/net/bridge/br_vlan_options.c @@ -40,22 +40,38 @@ static bool __vlan_tun_can_enter_range(const struct net_bridge_vlan *v_curr, bool br_vlan_opts_eq_range(const struct net_bridge_vlan *v_curr, const struct net_bridge_vlan *range_end) { + u8 range_mc_rtr = br_vlan_multicast_router(range_end); + u8 curr_mc_rtr = br_vlan_multicast_router(v_curr); + return v_curr->state == range_end->state && - __vlan_tun_can_enter_range(v_curr, range_end); + __vlan_tun_can_enter_range(v_curr, range_end) && + curr_mc_rtr == range_mc_rtr; } bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v) { - return !nla_put_u8(skb, BRIDGE_VLANDB_ENTRY_STATE, - br_vlan_get_state(v)) && - __vlan_tun_put(skb, v); + if (nla_put_u8(skb, BRIDGE_VLANDB_ENTRY_STATE, br_vlan_get_state(v)) || + !__vlan_tun_put(skb, v)) + return false; + +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + if (nla_put_u8(skb, BRIDGE_VLANDB_ENTRY_MCAST_ROUTER, + br_vlan_multicast_router(v))) + return false; +#endif + + return true; } size_t br_vlan_opts_nl_size(void) { return nla_total_size(sizeof(u8)) /* BRIDGE_VLANDB_ENTRY_STATE */ + nla_total_size(0) /* BRIDGE_VLANDB_ENTRY_TUNNEL_INFO */ - + nla_total_size(sizeof(u32)); /* BRIDGE_VLANDB_TINFO_ID */ + + nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_TINFO_ID */ +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + + nla_total_size(sizeof(u8)) /* BRIDGE_VLANDB_ENTRY_MCAST_ROUTER */ +#endif + + 0; } static int br_vlan_modify_state(struct net_bridge_vlan_group *vg, @@ -181,6 +197,18 @@ static int br_vlan_process_one_opts(const struct net_bridge *br, return err; } +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + if (tb[BRIDGE_VLANDB_ENTRY_MCAST_ROUTER]) { + u8 val; + + val = nla_get_u8(tb[BRIDGE_VLANDB_ENTRY_MCAST_ROUTER]); + err = br_multicast_set_vlan_router(v, val); + if (err) + return err; + *changed = true; + } +#endif + return 0; } @@ -258,3 +286,392 @@ int br_vlan_process_options(const struct net_bridge *br, return err; } + +bool br_vlan_global_opts_can_enter_range(const struct net_bridge_vlan *v_curr, + const struct net_bridge_vlan *r_end) +{ + return v_curr->vid - r_end->vid == 1 && + ((v_curr->priv_flags ^ r_end->priv_flags) & + BR_VLFLAG_GLOBAL_MCAST_ENABLED) == 0 && + br_multicast_ctx_options_equal(&v_curr->br_mcast_ctx, + &r_end->br_mcast_ctx); +} + +bool br_vlan_global_opts_fill(struct sk_buff *skb, u16 vid, u16 vid_range, + const struct net_bridge_vlan *v_opts) +{ + struct nlattr *nest2 __maybe_unused; + u64 clockval __maybe_unused; + struct nlattr *nest; + + nest = nla_nest_start(skb, BRIDGE_VLANDB_GLOBAL_OPTIONS); + if (!nest) + return false; + + if (nla_put_u16(skb, BRIDGE_VLANDB_GOPTS_ID, vid)) + goto out_err; + + if (vid_range && vid < vid_range && + nla_put_u16(skb, BRIDGE_VLANDB_GOPTS_RANGE, vid_range)) + goto out_err; + +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + if (nla_put_u8(skb, BRIDGE_VLANDB_GOPTS_MCAST_SNOOPING, + !!(v_opts->priv_flags & BR_VLFLAG_GLOBAL_MCAST_ENABLED)) || + nla_put_u8(skb, BRIDGE_VLANDB_GOPTS_MCAST_IGMP_VERSION, + v_opts->br_mcast_ctx.multicast_igmp_version) || + nla_put_u32(skb, BRIDGE_VLANDB_GOPTS_MCAST_LAST_MEMBER_CNT, + v_opts->br_mcast_ctx.multicast_last_member_count) || + nla_put_u32(skb, BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_CNT, + v_opts->br_mcast_ctx.multicast_startup_query_count) || + nla_put_u8(skb, BRIDGE_VLANDB_GOPTS_MCAST_QUERIER, + v_opts->br_mcast_ctx.multicast_querier) || + br_multicast_dump_querier_state(skb, &v_opts->br_mcast_ctx, + BRIDGE_VLANDB_GOPTS_MCAST_QUERIER_STATE)) + goto out_err; + + clockval = jiffies_to_clock_t(v_opts->br_mcast_ctx.multicast_last_member_interval); + if (nla_put_u64_64bit(skb, BRIDGE_VLANDB_GOPTS_MCAST_LAST_MEMBER_INTVL, + clockval, BRIDGE_VLANDB_GOPTS_PAD)) + goto out_err; + clockval = jiffies_to_clock_t(v_opts->br_mcast_ctx.multicast_membership_interval); + if (nla_put_u64_64bit(skb, BRIDGE_VLANDB_GOPTS_MCAST_MEMBERSHIP_INTVL, + clockval, BRIDGE_VLANDB_GOPTS_PAD)) + goto out_err; + clockval = jiffies_to_clock_t(v_opts->br_mcast_ctx.multicast_querier_interval); + if (nla_put_u64_64bit(skb, BRIDGE_VLANDB_GOPTS_MCAST_QUERIER_INTVL, + clockval, BRIDGE_VLANDB_GOPTS_PAD)) + goto out_err; + clockval = jiffies_to_clock_t(v_opts->br_mcast_ctx.multicast_query_interval); + if (nla_put_u64_64bit(skb, BRIDGE_VLANDB_GOPTS_MCAST_QUERY_INTVL, + clockval, BRIDGE_VLANDB_GOPTS_PAD)) + goto out_err; + clockval = jiffies_to_clock_t(v_opts->br_mcast_ctx.multicast_query_response_interval); + if (nla_put_u64_64bit(skb, BRIDGE_VLANDB_GOPTS_MCAST_QUERY_RESPONSE_INTVL, + clockval, BRIDGE_VLANDB_GOPTS_PAD)) + goto out_err; + clockval = jiffies_to_clock_t(v_opts->br_mcast_ctx.multicast_startup_query_interval); + if (nla_put_u64_64bit(skb, BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_INTVL, + clockval, BRIDGE_VLANDB_GOPTS_PAD)) + goto out_err; + + if (br_rports_have_mc_router(&v_opts->br_mcast_ctx)) { + nest2 = nla_nest_start(skb, + BRIDGE_VLANDB_GOPTS_MCAST_ROUTER_PORTS); + if (!nest2) + goto out_err; + + rcu_read_lock(); + if (br_rports_fill_info(skb, &v_opts->br_mcast_ctx)) { + rcu_read_unlock(); + nla_nest_cancel(skb, nest2); + goto out_err; + } + rcu_read_unlock(); + + nla_nest_end(skb, nest2); + } + +#if IS_ENABLED(CONFIG_IPV6) + if (nla_put_u8(skb, BRIDGE_VLANDB_GOPTS_MCAST_MLD_VERSION, + v_opts->br_mcast_ctx.multicast_mld_version)) + goto out_err; +#endif +#endif + + nla_nest_end(skb, nest); + + return true; + +out_err: + nla_nest_cancel(skb, nest); + return false; +} + +static size_t rtnl_vlan_global_opts_nlmsg_size(const struct net_bridge_vlan *v) +{ + return NLMSG_ALIGN(sizeof(struct br_vlan_msg)) + + nla_total_size(0) /* BRIDGE_VLANDB_GLOBAL_OPTIONS */ + + nla_total_size(sizeof(u16)) /* BRIDGE_VLANDB_GOPTS_ID */ +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + + nla_total_size(sizeof(u8)) /* BRIDGE_VLANDB_GOPTS_MCAST_SNOOPING */ + + nla_total_size(sizeof(u8)) /* BRIDGE_VLANDB_GOPTS_MCAST_IGMP_VERSION */ + + nla_total_size(sizeof(u8)) /* BRIDGE_VLANDB_GOPTS_MCAST_MLD_VERSION */ + + nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_GOPTS_MCAST_LAST_MEMBER_CNT */ + + nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_CNT */ + + nla_total_size(sizeof(u64)) /* BRIDGE_VLANDB_GOPTS_MCAST_LAST_MEMBER_INTVL */ + + nla_total_size(sizeof(u64)) /* BRIDGE_VLANDB_GOPTS_MCAST_MEMBERSHIP_INTVL */ + + nla_total_size(sizeof(u64)) /* BRIDGE_VLANDB_GOPTS_MCAST_QUERIER_INTVL */ + + nla_total_size(sizeof(u64)) /* BRIDGE_VLANDB_GOPTS_MCAST_QUERY_INTVL */ + + nla_total_size(sizeof(u64)) /* BRIDGE_VLANDB_GOPTS_MCAST_QUERY_RESPONSE_INTVL */ + + nla_total_size(sizeof(u64)) /* BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_INTVL */ + + nla_total_size(sizeof(u8)) /* BRIDGE_VLANDB_GOPTS_MCAST_QUERIER */ + + br_multicast_querier_state_size() /* BRIDGE_VLANDB_GOPTS_MCAST_QUERIER_STATE */ + + nla_total_size(0) /* BRIDGE_VLANDB_GOPTS_MCAST_ROUTER_PORTS */ + + br_rports_size(&v->br_mcast_ctx) /* BRIDGE_VLANDB_GOPTS_MCAST_ROUTER_PORTS */ +#endif + + nla_total_size(sizeof(u16)); /* BRIDGE_VLANDB_GOPTS_RANGE */ +} + +static void br_vlan_global_opts_notify(const struct net_bridge *br, + u16 vid, u16 vid_range) +{ + struct net_bridge_vlan *v; + struct br_vlan_msg *bvm; + struct nlmsghdr *nlh; + struct sk_buff *skb; + int err = -ENOBUFS; + + /* right now notifications are done only with rtnl held */ + ASSERT_RTNL(); + + /* need to find the vlan due to flags/options */ + v = br_vlan_find(br_vlan_group(br), vid); + if (!v) + return; + + skb = nlmsg_new(rtnl_vlan_global_opts_nlmsg_size(v), GFP_KERNEL); + if (!skb) + goto out_err; + + err = -EMSGSIZE; + nlh = nlmsg_put(skb, 0, 0, RTM_NEWVLAN, sizeof(*bvm), 0); + if (!nlh) + goto out_err; + bvm = nlmsg_data(nlh); + memset(bvm, 0, sizeof(*bvm)); + bvm->family = AF_BRIDGE; + bvm->ifindex = br->dev->ifindex; + + if (!br_vlan_global_opts_fill(skb, vid, vid_range, v)) + goto out_err; + + nlmsg_end(skb, nlh); + rtnl_notify(skb, dev_net(br->dev), 0, RTNLGRP_BRVLAN, NULL, GFP_KERNEL); + return; + +out_err: + rtnl_set_sk_err(dev_net(br->dev), RTNLGRP_BRVLAN, err); + kfree_skb(skb); +} + +static int br_vlan_process_global_one_opts(const struct net_bridge *br, + struct net_bridge_vlan_group *vg, + struct net_bridge_vlan *v, + struct nlattr **tb, + bool *changed, + struct netlink_ext_ack *extack) +{ + int err __maybe_unused; + + *changed = false; +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + if (tb[BRIDGE_VLANDB_GOPTS_MCAST_SNOOPING]) { + u8 mc_snooping; + + mc_snooping = nla_get_u8(tb[BRIDGE_VLANDB_GOPTS_MCAST_SNOOPING]); + if (br_multicast_toggle_global_vlan(v, !!mc_snooping)) + *changed = true; + } + if (tb[BRIDGE_VLANDB_GOPTS_MCAST_IGMP_VERSION]) { + u8 ver; + + ver = nla_get_u8(tb[BRIDGE_VLANDB_GOPTS_MCAST_IGMP_VERSION]); + err = br_multicast_set_igmp_version(&v->br_mcast_ctx, ver); + if (err) + return err; + *changed = true; + } + if (tb[BRIDGE_VLANDB_GOPTS_MCAST_LAST_MEMBER_CNT]) { + u32 cnt; + + cnt = nla_get_u32(tb[BRIDGE_VLANDB_GOPTS_MCAST_LAST_MEMBER_CNT]); + v->br_mcast_ctx.multicast_last_member_count = cnt; + *changed = true; + } + if (tb[BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_CNT]) { + u32 cnt; + + cnt = nla_get_u32(tb[BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_CNT]); + v->br_mcast_ctx.multicast_startup_query_count = cnt; + *changed = true; + } + if (tb[BRIDGE_VLANDB_GOPTS_MCAST_LAST_MEMBER_INTVL]) { + u64 val; + + val = nla_get_u64(tb[BRIDGE_VLANDB_GOPTS_MCAST_LAST_MEMBER_INTVL]); + v->br_mcast_ctx.multicast_last_member_interval = clock_t_to_jiffies(val); + *changed = true; + } + if (tb[BRIDGE_VLANDB_GOPTS_MCAST_MEMBERSHIP_INTVL]) { + u64 val; + + val = nla_get_u64(tb[BRIDGE_VLANDB_GOPTS_MCAST_MEMBERSHIP_INTVL]); + v->br_mcast_ctx.multicast_membership_interval = clock_t_to_jiffies(val); + *changed = true; + } + if (tb[BRIDGE_VLANDB_GOPTS_MCAST_QUERIER_INTVL]) { + u64 val; + + val = nla_get_u64(tb[BRIDGE_VLANDB_GOPTS_MCAST_QUERIER_INTVL]); + v->br_mcast_ctx.multicast_querier_interval = clock_t_to_jiffies(val); + *changed = true; + } + if (tb[BRIDGE_VLANDB_GOPTS_MCAST_QUERY_INTVL]) { + u64 val; + + val = nla_get_u64(tb[BRIDGE_VLANDB_GOPTS_MCAST_QUERY_INTVL]); + v->br_mcast_ctx.multicast_query_interval = clock_t_to_jiffies(val); + *changed = true; + } + if (tb[BRIDGE_VLANDB_GOPTS_MCAST_QUERY_RESPONSE_INTVL]) { + u64 val; + + val = nla_get_u64(tb[BRIDGE_VLANDB_GOPTS_MCAST_QUERY_RESPONSE_INTVL]); + v->br_mcast_ctx.multicast_query_response_interval = clock_t_to_jiffies(val); + *changed = true; + } + if (tb[BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_INTVL]) { + u64 val; + + val = nla_get_u64(tb[BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_INTVL]); + v->br_mcast_ctx.multicast_startup_query_interval = clock_t_to_jiffies(val); + *changed = true; + } + if (tb[BRIDGE_VLANDB_GOPTS_MCAST_QUERIER]) { + u8 val; + + val = nla_get_u8(tb[BRIDGE_VLANDB_GOPTS_MCAST_QUERIER]); + err = br_multicast_set_querier(&v->br_mcast_ctx, val); + if (err) + return err; + *changed = true; + } +#if IS_ENABLED(CONFIG_IPV6) + if (tb[BRIDGE_VLANDB_GOPTS_MCAST_MLD_VERSION]) { + u8 ver; + + ver = nla_get_u8(tb[BRIDGE_VLANDB_GOPTS_MCAST_MLD_VERSION]); + err = br_multicast_set_mld_version(&v->br_mcast_ctx, ver); + if (err) + return err; + *changed = true; + } +#endif +#endif + + return 0; +} + +static const struct nla_policy br_vlan_db_gpol[BRIDGE_VLANDB_GOPTS_MAX + 1] = { + [BRIDGE_VLANDB_GOPTS_ID] = { .type = NLA_U16 }, + [BRIDGE_VLANDB_GOPTS_RANGE] = { .type = NLA_U16 }, + [BRIDGE_VLANDB_GOPTS_MCAST_SNOOPING] = { .type = NLA_U8 }, + [BRIDGE_VLANDB_GOPTS_MCAST_MLD_VERSION] = { .type = NLA_U8 }, + [BRIDGE_VLANDB_GOPTS_MCAST_QUERY_INTVL] = { .type = NLA_U64 }, + [BRIDGE_VLANDB_GOPTS_MCAST_QUERIER] = { .type = NLA_U8 }, + [BRIDGE_VLANDB_GOPTS_MCAST_IGMP_VERSION] = { .type = NLA_U8 }, + [BRIDGE_VLANDB_GOPTS_MCAST_LAST_MEMBER_CNT] = { .type = NLA_U32 }, + [BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_CNT] = { .type = NLA_U32 }, + [BRIDGE_VLANDB_GOPTS_MCAST_LAST_MEMBER_INTVL] = { .type = NLA_U64 }, + [BRIDGE_VLANDB_GOPTS_MCAST_MEMBERSHIP_INTVL] = { .type = NLA_U64 }, + [BRIDGE_VLANDB_GOPTS_MCAST_QUERIER_INTVL] = { .type = NLA_U64 }, + [BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_INTVL] = { .type = NLA_U64 }, + [BRIDGE_VLANDB_GOPTS_MCAST_QUERY_RESPONSE_INTVL] = { .type = NLA_U64 }, +}; + +int br_vlan_rtm_process_global_options(struct net_device *dev, + const struct nlattr *attr, + int cmd, + struct netlink_ext_ack *extack) +{ + struct net_bridge_vlan *v, *curr_start = NULL, *curr_end = NULL; + struct nlattr *tb[BRIDGE_VLANDB_GOPTS_MAX + 1]; + struct net_bridge_vlan_group *vg; + u16 vid, vid_range = 0; + struct net_bridge *br; + int err = 0; + + if (cmd != RTM_NEWVLAN) { + NL_SET_ERR_MSG_MOD(extack, "Global vlan options support only set operation"); + return -EINVAL; + } + if (!netif_is_bridge_master(dev)) { + NL_SET_ERR_MSG_MOD(extack, "Global vlan options can only be set on bridge device"); + return -EINVAL; + } + br = netdev_priv(dev); + vg = br_vlan_group(br); + if (WARN_ON(!vg)) + return -ENODEV; + + err = nla_parse_nested(tb, BRIDGE_VLANDB_GOPTS_MAX, attr, + br_vlan_db_gpol, extack); + if (err) + return err; + + if (!tb[BRIDGE_VLANDB_GOPTS_ID]) { + NL_SET_ERR_MSG_MOD(extack, "Missing vlan entry id"); + return -EINVAL; + } + vid = nla_get_u16(tb[BRIDGE_VLANDB_GOPTS_ID]); + if (!br_vlan_valid_id(vid, extack)) + return -EINVAL; + + if (tb[BRIDGE_VLANDB_GOPTS_RANGE]) { + vid_range = nla_get_u16(tb[BRIDGE_VLANDB_GOPTS_RANGE]); + if (!br_vlan_valid_id(vid_range, extack)) + return -EINVAL; + if (vid >= vid_range) { + NL_SET_ERR_MSG_MOD(extack, "End vlan id is less than or equal to start vlan id"); + return -EINVAL; + } + } else { + vid_range = vid; + } + + for (; vid <= vid_range; vid++) { + bool changed = false; + + v = br_vlan_find(vg, vid); + if (!v) { + NL_SET_ERR_MSG_MOD(extack, "Vlan in range doesn't exist, can't process global options"); + err = -ENOENT; + break; + } + + err = br_vlan_process_global_one_opts(br, vg, v, tb, &changed, + extack); + if (err) + break; + + if (changed) { + /* vlan options changed, check for range */ + if (!curr_start) { + curr_start = v; + curr_end = v; + continue; + } + + if (!br_vlan_global_opts_can_enter_range(v, curr_end)) { + br_vlan_global_opts_notify(br, curr_start->vid, + curr_end->vid); + curr_start = v; + } + curr_end = v; + } else { + /* nothing changed and nothing to notify yet */ + if (!curr_start) + continue; + + br_vlan_global_opts_notify(br, curr_start->vid, + curr_end->vid); + curr_start = NULL; + curr_end = NULL; + } + } + if (curr_start) + br_vlan_global_opts_notify(br, curr_start->vid, curr_end->vid); + + return err; +} diff --git a/net/bridge/br_vlan_tunnel.c b/net/bridge/br_vlan_tunnel.c index 01017448ebde..6399a8a69d07 100644 --- a/net/bridge/br_vlan_tunnel.c +++ b/net/bridge/br_vlan_tunnel.c @@ -158,30 +158,28 @@ void vlan_tunnel_deinit(struct net_bridge_vlan_group *vg) rhashtable_destroy(&vg->tunnel_hash); } -int br_handle_ingress_vlan_tunnel(struct sk_buff *skb, - struct net_bridge_port *p, - struct net_bridge_vlan_group *vg) +void br_handle_ingress_vlan_tunnel(struct sk_buff *skb, + struct net_bridge_port *p, + struct net_bridge_vlan_group *vg) { struct ip_tunnel_info *tinfo = skb_tunnel_info(skb); struct net_bridge_vlan *vlan; if (!vg || !tinfo) - return 0; + return; /* if already tagged, ignore */ if (skb_vlan_tagged(skb)) - return 0; + return; /* lookup vid, given tunnel id */ vlan = br_vlan_tunnel_lookup(&vg->tunnel_hash, tinfo->key.tun_id); if (!vlan) - return 0; + return; skb_dst_drop(skb); __vlan_hwaccel_put_tag(skb, p->br->vlan_proto, vlan->vid); - - return 0; } int br_handle_egress_vlan_tunnel(struct sk_buff *skb, diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index 020b1487ee0c..a7af4eaff17d 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -98,7 +98,7 @@ static const struct nf_hook_ops ebt_ops_broute = { .priority = NF_BR_PRI_FIRST, }; -static int __net_init broute_net_init(struct net *net) +static int broute_table_init(struct net *net) { return ebt_register_table(net, &broute_table, &ebt_ops_broute); } @@ -114,19 +114,30 @@ static void __net_exit broute_net_exit(struct net *net) } static struct pernet_operations broute_net_ops = { - .init = broute_net_init, .exit = broute_net_exit, .pre_exit = broute_net_pre_exit, }; static int __init ebtable_broute_init(void) { - return register_pernet_subsys(&broute_net_ops); + int ret = ebt_register_template(&broute_table, broute_table_init); + + if (ret) + return ret; + + ret = register_pernet_subsys(&broute_net_ops); + if (ret) { + ebt_unregister_template(&broute_table); + return ret; + } + + return 0; } static void __exit ebtable_broute_fini(void) { unregister_pernet_subsys(&broute_net_ops); + ebt_unregister_template(&broute_table); } module_init(ebtable_broute_init); diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index 8ec0b3736803..c0b121df4a9a 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -86,7 +86,7 @@ static const struct nf_hook_ops ebt_ops_filter[] = { }, }; -static int __net_init frame_filter_net_init(struct net *net) +static int frame_filter_table_init(struct net *net) { return ebt_register_table(net, &frame_filter, ebt_ops_filter); } @@ -102,19 +102,30 @@ static void __net_exit frame_filter_net_exit(struct net *net) } static struct pernet_operations frame_filter_net_ops = { - .init = frame_filter_net_init, .exit = frame_filter_net_exit, .pre_exit = frame_filter_net_pre_exit, }; static int __init ebtable_filter_init(void) { - return register_pernet_subsys(&frame_filter_net_ops); + int ret = ebt_register_template(&frame_filter, frame_filter_table_init); + + if (ret) + return ret; + + ret = register_pernet_subsys(&frame_filter_net_ops); + if (ret) { + ebt_unregister_template(&frame_filter); + return ret; + } + + return 0; } static void __exit ebtable_filter_fini(void) { unregister_pernet_subsys(&frame_filter_net_ops); + ebt_unregister_template(&frame_filter); } module_init(ebtable_filter_init); diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 7c8a1064a531..4078151c224f 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -85,7 +85,7 @@ static const struct nf_hook_ops ebt_ops_nat[] = { }, }; -static int __net_init frame_nat_net_init(struct net *net) +static int frame_nat_table_init(struct net *net) { return ebt_register_table(net, &frame_nat, ebt_ops_nat); } @@ -101,19 +101,30 @@ static void __net_exit frame_nat_net_exit(struct net *net) } static struct pernet_operations frame_nat_net_ops = { - .init = frame_nat_net_init, .exit = frame_nat_net_exit, .pre_exit = frame_nat_net_pre_exit, }; static int __init ebtable_nat_init(void) { - return register_pernet_subsys(&frame_nat_net_ops); + int ret = ebt_register_template(&frame_nat, frame_nat_table_init); + + if (ret) + return ret; + + ret = register_pernet_subsys(&frame_nat_net_ops); + if (ret) { + ebt_unregister_template(&frame_nat); + return ret; + } + + return ret; } static void __exit ebtable_nat_fini(void) { unregister_pernet_subsys(&frame_nat_net_ops); + ebt_unregister_template(&frame_nat); } module_init(ebtable_nat_init); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index f022deb3721e..83d1798dfbb4 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -44,7 +44,16 @@ struct ebt_pernet { struct list_head tables; }; +struct ebt_template { + struct list_head list; + char name[EBT_TABLE_MAXNAMELEN]; + struct module *owner; + /* called when table is needed in the given netns */ + int (*table_init)(struct net *net); +}; + static unsigned int ebt_pernet_id __read_mostly; +static LIST_HEAD(template_tables); static DEFINE_MUTEX(ebt_mutex); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT @@ -309,30 +318,57 @@ letscontinue: /* If it succeeds, returns element and locks mutex */ static inline void * -find_inlist_lock_noload(struct list_head *head, const char *name, int *error, +find_inlist_lock_noload(struct net *net, const char *name, int *error, struct mutex *mutex) { - struct { - struct list_head list; - char name[EBT_FUNCTION_MAXNAMELEN]; - } *e; + struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id); + struct ebt_template *tmpl; + struct ebt_table *table; mutex_lock(mutex); - list_for_each_entry(e, head, list) { - if (strcmp(e->name, name) == 0) - return e; + list_for_each_entry(table, &ebt_net->tables, list) { + if (strcmp(table->name, name) == 0) + return table; } + + list_for_each_entry(tmpl, &template_tables, list) { + if (strcmp(name, tmpl->name) == 0) { + struct module *owner = tmpl->owner; + + if (!try_module_get(owner)) + goto out; + + mutex_unlock(mutex); + + *error = tmpl->table_init(net); + if (*error) { + module_put(owner); + return NULL; + } + + mutex_lock(mutex); + module_put(owner); + break; + } + } + + list_for_each_entry(table, &ebt_net->tables, list) { + if (strcmp(table->name, name) == 0) + return table; + } + +out: *error = -ENOENT; mutex_unlock(mutex); return NULL; } static void * -find_inlist_lock(struct list_head *head, const char *name, const char *prefix, +find_inlist_lock(struct net *net, const char *name, const char *prefix, int *error, struct mutex *mutex) { return try_then_request_module( - find_inlist_lock_noload(head, name, error, mutex), + find_inlist_lock_noload(net, name, error, mutex), "%s%s", prefix, name); } @@ -340,10 +376,7 @@ static inline struct ebt_table * find_table_lock(struct net *net, const char *name, int *error, struct mutex *mutex) { - struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id); - - return find_inlist_lock(&ebt_net->tables, name, - "ebtable_", error, mutex); + return find_inlist_lock(net, name, "ebtable_", error, mutex); } static inline void ebt_free_table_info(struct ebt_table_info *info) @@ -1258,6 +1291,54 @@ out: return ret; } +int ebt_register_template(const struct ebt_table *t, int (*table_init)(struct net *net)) +{ + struct ebt_template *tmpl; + + mutex_lock(&ebt_mutex); + list_for_each_entry(tmpl, &template_tables, list) { + if (WARN_ON_ONCE(strcmp(t->name, tmpl->name) == 0)) { + mutex_unlock(&ebt_mutex); + return -EEXIST; + } + } + + tmpl = kzalloc(sizeof(*tmpl), GFP_KERNEL); + if (!tmpl) { + mutex_unlock(&ebt_mutex); + return -ENOMEM; + } + + tmpl->table_init = table_init; + strscpy(tmpl->name, t->name, sizeof(tmpl->name)); + tmpl->owner = t->me; + list_add(&tmpl->list, &template_tables); + + mutex_unlock(&ebt_mutex); + return 0; +} +EXPORT_SYMBOL(ebt_register_template); + +void ebt_unregister_template(const struct ebt_table *t) +{ + struct ebt_template *tmpl; + + mutex_lock(&ebt_mutex); + list_for_each_entry(tmpl, &template_tables, list) { + if (strcmp(t->name, tmpl->name)) + continue; + + list_del(&tmpl->list); + mutex_unlock(&ebt_mutex); + kfree(tmpl); + return; + } + + mutex_unlock(&ebt_mutex); + WARN_ON_ONCE(1); +} +EXPORT_SYMBOL(ebt_unregister_template); + static struct ebt_table *__ebt_find_table(struct net *net, const char *name) { struct ebt_pernet *ebt_net = net_generic(net, ebt_pernet_id); diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 8d033a75a766..fdbed3158555 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -88,6 +88,12 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk, skb = ip_fraglist_next(&iter); } + + if (!err) + return 0; + + kfree_skb_list(iter.frag); + return err; } slow_path: diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h index 12369b604ce9..f6df20808f5e 100644 --- a/net/can/j1939/j1939-priv.h +++ b/net/can/j1939/j1939-priv.h @@ -20,9 +20,12 @@ struct j1939_session; enum j1939_sk_errqueue_type { - J1939_ERRQUEUE_ACK, - J1939_ERRQUEUE_SCHED, - J1939_ERRQUEUE_ABORT, + J1939_ERRQUEUE_TX_ACK, + J1939_ERRQUEUE_TX_SCHED, + J1939_ERRQUEUE_TX_ABORT, + J1939_ERRQUEUE_RX_RTS, + J1939_ERRQUEUE_RX_DPO, + J1939_ERRQUEUE_RX_ABORT, }; /* j1939 devices */ @@ -87,6 +90,7 @@ struct j1939_priv { struct list_head j1939_socks; struct kref rx_kref; + u32 rx_tskey; }; void j1939_ecu_put(struct j1939_ecu *ecu); diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 54f6d521492f..6dff4510687a 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -352,7 +352,7 @@ static void j1939_sk_sock_destruct(struct sock *sk) { struct j1939_sock *jsk = j1939_sk(sk); - /* This function will be call by the generic networking code, when then + /* This function will be called by the generic networking code, when * the socket is ultimately closed (sk->sk_destruct). * * The race between @@ -905,20 +905,33 @@ failure: return NULL; } -static size_t j1939_sk_opt_stats_get_size(void) +static size_t j1939_sk_opt_stats_get_size(enum j1939_sk_errqueue_type type) { - return - nla_total_size(sizeof(u32)) + /* J1939_NLA_BYTES_ACKED */ - 0; + switch (type) { + case J1939_ERRQUEUE_RX_RTS: + return + nla_total_size(sizeof(u32)) + /* J1939_NLA_TOTAL_SIZE */ + nla_total_size(sizeof(u32)) + /* J1939_NLA_PGN */ + nla_total_size(sizeof(u64)) + /* J1939_NLA_SRC_NAME */ + nla_total_size(sizeof(u64)) + /* J1939_NLA_DEST_NAME */ + nla_total_size(sizeof(u8)) + /* J1939_NLA_SRC_ADDR */ + nla_total_size(sizeof(u8)) + /* J1939_NLA_DEST_ADDR */ + 0; + default: + return + nla_total_size(sizeof(u32)) + /* J1939_NLA_BYTES_ACKED */ + 0; + } } static struct sk_buff * -j1939_sk_get_timestamping_opt_stats(struct j1939_session *session) +j1939_sk_get_timestamping_opt_stats(struct j1939_session *session, + enum j1939_sk_errqueue_type type) { struct sk_buff *stats; u32 size; - stats = alloc_skb(j1939_sk_opt_stats_get_size(), GFP_ATOMIC); + stats = alloc_skb(j1939_sk_opt_stats_get_size(type), GFP_ATOMIC); if (!stats) return NULL; @@ -928,32 +941,67 @@ j1939_sk_get_timestamping_opt_stats(struct j1939_session *session) size = min(session->pkt.tx_acked * 7, session->total_message_size); - nla_put_u32(stats, J1939_NLA_BYTES_ACKED, size); + switch (type) { + case J1939_ERRQUEUE_RX_RTS: + nla_put_u32(stats, J1939_NLA_TOTAL_SIZE, + session->total_message_size); + nla_put_u32(stats, J1939_NLA_PGN, + session->skcb.addr.pgn); + nla_put_u64_64bit(stats, J1939_NLA_SRC_NAME, + session->skcb.addr.src_name, J1939_NLA_PAD); + nla_put_u64_64bit(stats, J1939_NLA_DEST_NAME, + session->skcb.addr.dst_name, J1939_NLA_PAD); + nla_put_u8(stats, J1939_NLA_SRC_ADDR, + session->skcb.addr.sa); + nla_put_u8(stats, J1939_NLA_DEST_ADDR, + session->skcb.addr.da); + break; + default: + nla_put_u32(stats, J1939_NLA_BYTES_ACKED, size); + } return stats; } -void j1939_sk_errqueue(struct j1939_session *session, - enum j1939_sk_errqueue_type type) +static void __j1939_sk_errqueue(struct j1939_session *session, struct sock *sk, + enum j1939_sk_errqueue_type type) { struct j1939_priv *priv = session->priv; - struct sock *sk = session->sk; struct j1939_sock *jsk; struct sock_exterr_skb *serr; struct sk_buff *skb; char *state = "UNK"; int err; - /* currently we have no sk for the RX session */ - if (!sk) - return; - jsk = j1939_sk(sk); if (!(jsk->state & J1939_SOCK_ERRQUEUE)) return; - skb = j1939_sk_get_timestamping_opt_stats(session); + switch (type) { + case J1939_ERRQUEUE_TX_ACK: + if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK)) + return; + break; + case J1939_ERRQUEUE_TX_SCHED: + if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_SCHED)) + return; + break; + case J1939_ERRQUEUE_TX_ABORT: + break; + case J1939_ERRQUEUE_RX_RTS: + fallthrough; + case J1939_ERRQUEUE_RX_DPO: + fallthrough; + case J1939_ERRQUEUE_RX_ABORT: + if (!(sk->sk_tsflags & SOF_TIMESTAMPING_RX_SOFTWARE)) + return; + break; + default: + netdev_err(priv->ndev, "Unknown errqueue type %i\n", type); + } + + skb = j1939_sk_get_timestamping_opt_stats(session, type); if (!skb) return; @@ -964,36 +1012,42 @@ void j1939_sk_errqueue(struct j1939_session *session, serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); switch (type) { - case J1939_ERRQUEUE_ACK: - if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK)) { - kfree_skb(skb); - return; - } - + case J1939_ERRQUEUE_TX_ACK: serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; serr->ee.ee_info = SCM_TSTAMP_ACK; - state = "ACK"; + state = "TX ACK"; break; - case J1939_ERRQUEUE_SCHED: - if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_SCHED)) { - kfree_skb(skb); - return; - } - + case J1939_ERRQUEUE_TX_SCHED: serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; serr->ee.ee_info = SCM_TSTAMP_SCHED; - state = "SCH"; + state = "TX SCH"; break; - case J1939_ERRQUEUE_ABORT: + case J1939_ERRQUEUE_TX_ABORT: serr->ee.ee_errno = session->err; serr->ee.ee_origin = SO_EE_ORIGIN_LOCAL; serr->ee.ee_info = J1939_EE_INFO_TX_ABORT; - state = "ABT"; + state = "TX ABT"; + break; + case J1939_ERRQUEUE_RX_RTS: + serr->ee.ee_errno = ENOMSG; + serr->ee.ee_origin = SO_EE_ORIGIN_LOCAL; + serr->ee.ee_info = J1939_EE_INFO_RX_RTS; + state = "RX RTS"; + break; + case J1939_ERRQUEUE_RX_DPO: + serr->ee.ee_errno = ENOMSG; + serr->ee.ee_origin = SO_EE_ORIGIN_LOCAL; + serr->ee.ee_info = J1939_EE_INFO_RX_DPO; + state = "RX DPO"; + break; + case J1939_ERRQUEUE_RX_ABORT: + serr->ee.ee_errno = session->err; + serr->ee.ee_origin = SO_EE_ORIGIN_LOCAL; + serr->ee.ee_info = J1939_EE_INFO_RX_ABORT; + state = "RX ABT"; break; - default: - netdev_err(priv->ndev, "Unknown errqueue type %i\n", type); } serr->opt_stats = true; @@ -1008,6 +1062,27 @@ void j1939_sk_errqueue(struct j1939_session *session, kfree_skb(skb); }; +void j1939_sk_errqueue(struct j1939_session *session, + enum j1939_sk_errqueue_type type) +{ + struct j1939_priv *priv = session->priv; + struct j1939_sock *jsk; + + if (session->sk) { + /* send TX notifications to the socket of origin */ + __j1939_sk_errqueue(session, session->sk, type); + return; + } + + /* spread RX notifications to all sockets subscribed to this session */ + spin_lock_bh(&priv->j1939_socks_lock); + list_for_each_entry(jsk, &priv->j1939_socks, list) { + if (j1939_sk_recv_match_one(jsk, &session->skcb)) + __j1939_sk_errqueue(session, &jsk->sk, type); + } + spin_unlock_bh(&priv->j1939_socks_lock); +}; + void j1939_sk_send_loop_abort(struct sock *sk, int err) { sk->sk_err = err; diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index c3946c355882..bb5c4b8979be 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -260,10 +260,14 @@ static void __j1939_session_drop(struct j1939_session *session) static void j1939_session_destroy(struct j1939_session *session) { - if (session->err) - j1939_sk_errqueue(session, J1939_ERRQUEUE_ABORT); - else - j1939_sk_errqueue(session, J1939_ERRQUEUE_ACK); + if (session->transmission) { + if (session->err) + j1939_sk_errqueue(session, J1939_ERRQUEUE_TX_ABORT); + else + j1939_sk_errqueue(session, J1939_ERRQUEUE_TX_ACK); + } else if (session->err) { + j1939_sk_errqueue(session, J1939_ERRQUEUE_RX_ABORT); + } netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session); @@ -776,7 +780,7 @@ static int j1939_session_tx_dpo(struct j1939_session *session) static int j1939_session_tx_dat(struct j1939_session *session) { struct j1939_priv *priv = session->priv; - struct j1939_sk_buff_cb *skcb; + struct j1939_sk_buff_cb *se_skcb; int offset, pkt_done, pkt_end; unsigned int len, pdelay; struct sk_buff *se_skb; @@ -788,7 +792,7 @@ static int j1939_session_tx_dat(struct j1939_session *session) if (!se_skb) return -ENOBUFS; - skcb = j1939_skb_to_cb(se_skb); + se_skcb = j1939_skb_to_cb(se_skb); tpdat = se_skb->data; ret = 0; pkt_done = 0; @@ -800,7 +804,7 @@ static int j1939_session_tx_dat(struct j1939_session *session) while (session->pkt.tx < pkt_end) { dat[0] = session->pkt.tx - session->pkt.dpo + 1; - offset = (session->pkt.tx * 7) - skcb->offset; + offset = (session->pkt.tx * 7) - se_skcb->offset; len = se_skb->len - offset; if (len > 7) len = 7; @@ -808,7 +812,8 @@ static int j1939_session_tx_dat(struct j1939_session *session) if (offset + len > se_skb->len) { netdev_err_once(priv->ndev, "%s: 0x%p: requested data outside of queued buffer: offset %i, len %i, pkt.tx: %i\n", - __func__, session, skcb->offset, se_skb->len , session->pkt.tx); + __func__, session, se_skcb->offset, + se_skb->len , session->pkt.tx); ret = -EOVERFLOW; goto out_free; } @@ -821,7 +826,7 @@ static int j1939_session_tx_dat(struct j1939_session *session) memcpy(&dat[1], &tpdat[offset], len); ret = j1939_tp_tx_dat(session, dat, len + 1); if (ret < 0) { - /* ENOBUS == CAN interface TX queue is full */ + /* ENOBUFS == CAN interface TX queue is full */ if (ret != -ENOBUFS) netdev_alert(priv->ndev, "%s: 0x%p: queue data error: %i\n", @@ -1043,7 +1048,7 @@ static int j1939_simple_txnext(struct j1939_session *session) if (ret) goto out_free; - j1939_sk_errqueue(session, J1939_ERRQUEUE_SCHED); + j1939_sk_errqueue(session, J1939_ERRQUEUE_TX_SCHED); j1939_sk_queue_activate_next(session); out_free: @@ -1075,11 +1080,16 @@ static bool j1939_session_deactivate_locked(struct j1939_session *session) static bool j1939_session_deactivate(struct j1939_session *session) { + struct j1939_priv *priv = session->priv; bool active; - j1939_session_list_lock(session->priv); + j1939_session_list_lock(priv); + /* This function should be called with a session ref-count of at + * least 2. + */ + WARN_ON_ONCE(kref_read(&session->kref) < 2); active = j1939_session_deactivate_locked(session); - j1939_session_list_unlock(session->priv); + j1939_session_list_unlock(priv); return active; } @@ -1092,7 +1102,7 @@ j1939_session_deactivate_activate_next(struct j1939_session *session) } static void __j1939_session_cancel(struct j1939_session *session, - enum j1939_xtp_abort err) + enum j1939_xtp_abort err) { struct j1939_priv *priv = session->priv; @@ -1110,6 +1120,8 @@ static void __j1939_session_cancel(struct j1939_session *session, if (session->sk) j1939_sk_send_loop_abort(session->sk, session->err); + else + j1939_sk_errqueue(session, J1939_ERRQUEUE_RX_ABORT); } static void j1939_session_cancel(struct j1939_session *session, @@ -1190,13 +1202,13 @@ static enum hrtimer_restart j1939_tp_txtimer(struct hrtimer *hrtimer) static void j1939_session_completed(struct j1939_session *session) { - struct sk_buff *skb; + struct sk_buff *se_skb; if (!session->transmission) { - skb = j1939_session_skb_get(session); + se_skb = j1939_session_skb_get(session); /* distribute among j1939 receivers */ - j1939_sk_recv(session->priv, skb); - consume_skb(skb); + j1939_sk_recv(session->priv, se_skb); + consume_skb(se_skb); } j1939_session_deactivate_activate_next(session); @@ -1263,12 +1275,14 @@ static bool j1939_xtp_rx_cmd_bad_pgn(struct j1939_session *session, break; case J1939_ETP_CMD_RTS: - case J1939_TP_CMD_RTS: /* fall through */ + fallthrough; + case J1939_TP_CMD_RTS: abort = J1939_XTP_ABORT_BUSY; break; case J1939_ETP_CMD_CTS: - case J1939_TP_CMD_CTS: /* fall through */ + fallthrough; + case J1939_TP_CMD_CTS: abort = J1939_XTP_ABORT_ECTS_UNXPECTED_PGN; break; @@ -1277,7 +1291,8 @@ static bool j1939_xtp_rx_cmd_bad_pgn(struct j1939_session *session, break; case J1939_ETP_CMD_EOMA: - case J1939_TP_CMD_EOMA: /* fall through */ + fallthrough; + case J1939_TP_CMD_EOMA: abort = J1939_XTP_ABORT_OTHER; break; @@ -1321,6 +1336,8 @@ static void j1939_xtp_rx_abort_one(struct j1939_priv *priv, struct sk_buff *skb, session->err = j1939_xtp_abort_to_errno(priv, abort); if (session->sk) j1939_sk_send_loop_abort(session->sk, session->err); + else + j1939_sk_errqueue(session, J1939_ERRQUEUE_RX_ABORT); j1939_session_deactivate_activate_next(session); abort_put: @@ -1429,7 +1446,7 @@ j1939_xtp_rx_cts_one(struct j1939_session *session, struct sk_buff *skb) if (session->transmission) { if (session->pkt.tx_acked) j1939_sk_errqueue(session, - J1939_ERRQUEUE_SCHED); + J1939_ERRQUEUE_TX_SCHED); j1939_session_txtimer_cancel(session); j1939_tp_schedule_txtimer(session, 0); } @@ -1621,6 +1638,9 @@ j1939_session *j1939_xtp_rx_rts_session_new(struct j1939_priv *priv, session->pkt.rx = 0; session->pkt.tx = 0; + session->tskey = priv->rx_tskey++; + j1939_sk_errqueue(session, J1939_ERRQUEUE_RX_RTS); + WARN_ON_ONCE(j1939_session_activate(session)); return session; @@ -1743,6 +1763,9 @@ static void j1939_xtp_rx_dpo_one(struct j1939_session *session, session->pkt.dpo = j1939_etp_ctl_to_packet(skb->data); session->last_cmd = dat[0]; j1939_tp_set_rxtimeout(session, 750); + + if (!session->transmission) + j1939_sk_errqueue(session, J1939_ERRQUEUE_RX_DPO); } static void j1939_xtp_rx_dpo(struct j1939_priv *priv, struct sk_buff *skb, @@ -1767,7 +1790,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, struct sk_buff *skb) { struct j1939_priv *priv = session->priv; - struct j1939_sk_buff_cb *skcb; + struct j1939_sk_buff_cb *skcb, *se_skcb; struct sk_buff *se_skb = NULL; const u8 *dat; u8 *tpdat; @@ -1792,7 +1815,8 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, break; fallthrough; case J1939_TP_CMD_BAM: - case J1939_TP_CMD_CTS: /* fall through */ + fallthrough; + case J1939_TP_CMD_CTS: if (skcb->addr.type != J1939_ETP) break; fallthrough; @@ -1817,8 +1841,8 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, goto out_session_cancel; } - skcb = j1939_skb_to_cb(se_skb); - offset = packet * 7 - skcb->offset; + se_skcb = j1939_skb_to_cb(se_skb); + offset = packet * 7 - se_skcb->offset; nbytes = se_skb->len - offset; if (nbytes > 7) nbytes = 7; @@ -1846,7 +1870,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, if (packet == session->pkt.rx) session->pkt.rx++; - if (skcb->addr.type != J1939_ETP && + if (se_skcb->addr.type != J1939_ETP && j1939_cb_is_broadcast(&session->skcb)) { if (session->pkt.rx >= session->pkt.total) final = true; @@ -1869,7 +1893,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, if (!session->transmission) j1939_tp_schedule_txtimer(session, 0); } else { - j1939_tp_set_rxtimeout(session, 250); + j1939_tp_set_rxtimeout(session, 750); } session->last_cmd = 0xff; consume_skb(se_skb); @@ -1995,7 +2019,8 @@ static void j1939_tp_cmd_recv(struct j1939_priv *priv, struct sk_buff *skb) extd = J1939_ETP; fallthrough; case J1939_TP_CMD_BAM: - case J1939_TP_CMD_RTS: /* fall through */ + fallthrough; + case J1939_TP_CMD_RTS: if (skcb->addr.type != extd) return; diff --git a/net/can/raw.c b/net/can/raw.c index ed4fcb7ab0c3..7105fa4824e4 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -546,10 +546,18 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, return -EFAULT; } + rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) + if (ro->bound && ro->ifindex) { dev = dev_get_by_index(sock_net(sk), ro->ifindex); + if (!dev) { + if (count > 1) + kfree(filter); + err = -ENODEV; + goto out_fil; + } + } if (ro->bound) { /* (try to) register the new filters */ @@ -584,10 +592,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, ro->count = count; out_fil: - if (dev) - dev_put(dev); - + dev_put(dev); release_sock(sk); + rtnl_unlock(); break; @@ -600,10 +607,16 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, err_mask &= CAN_ERR_MASK; + rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) + if (ro->bound && ro->ifindex) { dev = dev_get_by_index(sock_net(sk), ro->ifindex); + if (!dev) { + err = -ENODEV; + goto out_err; + } + } /* remove current error mask */ if (ro->bound) { @@ -623,10 +636,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, ro->err_mask = err_mask; out_err: - if (dev) - dev_put(dev); - + dev_put(dev); release_sock(sk); + rtnl_unlock(); break; diff --git a/net/core/Makefile b/net/core/Makefile index f7f16650fe9e..35ced6201814 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -33,8 +33,6 @@ obj-$(CONFIG_HWBM) += hwbm.o obj-$(CONFIG_NET_DEVLINK) += devlink.o obj-$(CONFIG_GRO_CELLS) += gro_cells.o obj-$(CONFIG_FAILOVER) += failover.o -ifeq ($(CONFIG_INET),y) obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o obj-$(CONFIG_BPF_SYSCALL) += sock_map.o -endif obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index f564f82e91d9..68d2cbf8331a 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -416,7 +416,7 @@ static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog) BPF_CALL_4(bpf_sk_storage_get_tracing, struct bpf_map *, map, struct sock *, sk, void *, value, u64, flags) { - if (in_irq() || in_nmi()) + if (in_hardirq() || in_nmi()) return (unsigned long)NULL; return (unsigned long)____bpf_sk_storage_get(map, sk, value, flags); @@ -425,7 +425,7 @@ BPF_CALL_4(bpf_sk_storage_get_tracing, struct bpf_map *, map, struct sock *, sk, BPF_CALL_2(bpf_sk_storage_delete_tracing, struct bpf_map *, map, struct sock *, sk) { - if (in_irq() || in_nmi()) + if (in_hardirq() || in_nmi()) return -EPERM; return ____bpf_sk_storage_delete(map, sk); diff --git a/net/core/dev.c b/net/core/dev.c index 8f1a47ad6781..74fd402d26dd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -676,131 +676,6 @@ void dev_remove_offload(struct packet_offload *po) } EXPORT_SYMBOL(dev_remove_offload); -/****************************************************************************** - * - * Device Boot-time Settings Routines - * - ******************************************************************************/ - -/* Boot time configuration table */ -static struct netdev_boot_setup dev_boot_setup[NETDEV_BOOT_SETUP_MAX]; - -/** - * netdev_boot_setup_add - add new setup entry - * @name: name of the device - * @map: configured settings for the device - * - * Adds new setup entry to the dev_boot_setup list. The function - * returns 0 on error and 1 on success. This is a generic routine to - * all netdevices. - */ -static int netdev_boot_setup_add(char *name, struct ifmap *map) -{ - struct netdev_boot_setup *s; - int i; - - s = dev_boot_setup; - for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) { - if (s[i].name[0] == '\0' || s[i].name[0] == ' ') { - memset(s[i].name, 0, sizeof(s[i].name)); - strlcpy(s[i].name, name, IFNAMSIZ); - memcpy(&s[i].map, map, sizeof(s[i].map)); - break; - } - } - - return i >= NETDEV_BOOT_SETUP_MAX ? 0 : 1; -} - -/** - * netdev_boot_setup_check - check boot time settings - * @dev: the netdevice - * - * Check boot time settings for the device. - * The found settings are set for the device to be used - * later in the device probing. - * Returns 0 if no settings found, 1 if they are. - */ -int netdev_boot_setup_check(struct net_device *dev) -{ - struct netdev_boot_setup *s = dev_boot_setup; - int i; - - for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) { - if (s[i].name[0] != '\0' && s[i].name[0] != ' ' && - !strcmp(dev->name, s[i].name)) { - dev->irq = s[i].map.irq; - dev->base_addr = s[i].map.base_addr; - dev->mem_start = s[i].map.mem_start; - dev->mem_end = s[i].map.mem_end; - return 1; - } - } - return 0; -} -EXPORT_SYMBOL(netdev_boot_setup_check); - - -/** - * netdev_boot_base - get address from boot time settings - * @prefix: prefix for network device - * @unit: id for network device - * - * Check boot time settings for the base address of device. - * The found settings are set for the device to be used - * later in the device probing. - * Returns 0 if no settings found. - */ -unsigned long netdev_boot_base(const char *prefix, int unit) -{ - const struct netdev_boot_setup *s = dev_boot_setup; - char name[IFNAMSIZ]; - int i; - - sprintf(name, "%s%d", prefix, unit); - - /* - * If device already registered then return base of 1 - * to indicate not to probe for this interface - */ - if (__dev_get_by_name(&init_net, name)) - return 1; - - for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) - if (!strcmp(name, s[i].name)) - return s[i].map.base_addr; - return 0; -} - -/* - * Saves at boot time configured settings for any netdevice. - */ -int __init netdev_boot_setup(char *str) -{ - int ints[5]; - struct ifmap map; - - str = get_options(str, ARRAY_SIZE(ints), ints); - if (!str || !*str) - return 0; - - /* Save settings */ - memset(&map, 0, sizeof(map)); - if (ints[0] > 0) - map.irq = ints[1]; - if (ints[0] > 1) - map.base_addr = ints[2]; - if (ints[0] > 2) - map.mem_start = ints[3]; - if (ints[0] > 3) - map.mem_end = ints[4]; - - /* Add new entry to the list */ - return netdev_boot_setup_add(str, &map); -} - -__setup("netdev=", netdev_boot_setup); - /******************************************************************************* * * Device Interface Subroutines @@ -956,8 +831,7 @@ struct net_device *dev_get_by_name(struct net *net, const char *name) rcu_read_lock(); dev = dev_get_by_name_rcu(net, name); - if (dev) - dev_hold(dev); + dev_hold(dev); rcu_read_unlock(); return dev; } @@ -1030,8 +904,7 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex) rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); - if (dev) - dev_hold(dev); + dev_hold(dev); rcu_read_unlock(); return dev; } @@ -3099,6 +2972,50 @@ EXPORT_SYMBOL(netif_set_real_num_rx_queues); #endif /** + * netif_set_real_num_queues - set actual number of RX and TX queues used + * @dev: Network device + * @txq: Actual number of TX queues + * @rxq: Actual number of RX queues + * + * Set the real number of both TX and RX queues. + * Does nothing if the number of queues is already correct. + */ +int netif_set_real_num_queues(struct net_device *dev, + unsigned int txq, unsigned int rxq) +{ + unsigned int old_rxq = dev->real_num_rx_queues; + int err; + + if (txq < 1 || txq > dev->num_tx_queues || + rxq < 1 || rxq > dev->num_rx_queues) + return -EINVAL; + + /* Start from increases, so the error path only does decreases - + * decreases can't fail. + */ + if (rxq > dev->real_num_rx_queues) { + err = netif_set_real_num_rx_queues(dev, rxq); + if (err) + return err; + } + if (txq > dev->real_num_tx_queues) { + err = netif_set_real_num_tx_queues(dev, txq); + if (err) + goto undo_rx; + } + if (rxq < dev->real_num_rx_queues) + WARN_ON(netif_set_real_num_rx_queues(dev, rxq)); + if (txq < dev->real_num_tx_queues) + WARN_ON(netif_set_real_num_tx_queues(dev, txq)); + + return 0; +undo_rx: + WARN_ON(netif_set_real_num_rx_queues(dev, old_rxq)); + return err; +} +EXPORT_SYMBOL(netif_set_real_num_queues); + +/** * netif_get_num_default_rss_queues - default number of RSS queues * * This routine should set an upper limit on the number of RSS queues @@ -3190,7 +3107,7 @@ EXPORT_SYMBOL(__dev_kfree_skb_irq); void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason) { - if (in_irq() || irqs_disabled()) + if (in_hardirq() || irqs_disabled()) __dev_kfree_skb_irq(skb, reason); else dev_kfree_skb(skb); @@ -4012,7 +3929,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) qdisc_skb_cb(skb)->post_ct = false; mini_qdisc_bstats_cpu_update(miniq, skb); - switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) { + switch (tcf_classify(skb, miniq->block, miniq->filter_list, &cl_res, false)) { case TC_ACT_OK: case TC_ACT_RECLASSIFY: skb->tc_index = TC_H_MIN(cl_res.classid); @@ -4756,45 +4673,18 @@ static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb) return rxqueue; } -static u32 netif_receive_generic_xdp(struct sk_buff *skb, - struct xdp_buff *xdp, - struct bpf_prog *xdp_prog) +u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, + struct bpf_prog *xdp_prog) { void *orig_data, *orig_data_end, *hard_start; struct netdev_rx_queue *rxqueue; - u32 metalen, act = XDP_DROP; bool orig_bcast, orig_host; u32 mac_len, frame_sz; __be16 orig_eth_type; struct ethhdr *eth; + u32 metalen, act; int off; - /* Reinjected packets coming from act_mirred or similar should - * not get XDP generic processing. - */ - if (skb_is_redirected(skb)) - return XDP_PASS; - - /* 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_cloned(skb) || 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 (skb_linearize(skb)) - goto do_drop; - } - /* The XDP program wants to see the packet starting at the MAC * header. */ @@ -4849,6 +4739,13 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, skb->protocol = eth_type_trans(skb, skb->dev); } + /* Redirect/Tx gives L2 packet, code that will reuse skb must __skb_pull + * before calling us again on redirect path. We do not call do_redirect + * as we leave that up to the caller. + * + * Caller is responsible for managing lifetime of skb (i.e. calling + * kfree_skb in response to actions it cannot handle/XDP_DROP). + */ switch (act) { case XDP_REDIRECT: case XDP_TX: @@ -4859,6 +4756,49 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, if (metalen) skb_metadata_set(skb, metalen); break; + } + + return act; +} + +static u32 netif_receive_generic_xdp(struct sk_buff *skb, + struct xdp_buff *xdp, + struct bpf_prog *xdp_prog) +{ + u32 act = XDP_DROP; + + /* Reinjected packets coming from act_mirred or similar should + * not get XDP generic processing. + */ + if (skb_is_redirected(skb)) + return XDP_PASS; + + /* 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_cloned(skb) || 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 (skb_linearize(skb)) + goto do_drop; + } + + act = bpf_prog_run_generic_xdp(skb, xdp, xdp_prog); + switch (act) { + case XDP_REDIRECT: + case XDP_TX: + case XDP_PASS: + break; default: bpf_warn_invalid_xdp_action(act); fallthrough; @@ -5141,8 +5081,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, skb->tc_at_ingress = 1; mini_qdisc_bstats_cpu_update(miniq, skb); - switch (tcf_classify_ingress(skb, miniq->block, miniq->filter_list, - &cl_res, false)) { + switch (tcf_classify(skb, miniq->block, miniq->filter_list, &cl_res, false)) { case TC_ACT_OK: case TC_ACT_RECLASSIFY: skb->tc_index = TC_H_MIN(cl_res.classid); @@ -5324,7 +5263,6 @@ another_round: ret = NET_RX_DROP; goto out; } - skb_reset_mac_len(skb); } if (eth_type_vlan(skb->protocol)) { @@ -5650,25 +5588,6 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) struct bpf_prog *new = xdp->prog; int ret = 0; - if (new) { - u32 i; - - mutex_lock(&new->aux->used_maps_mutex); - - /* generic XDP does not work with DEVMAPs that can - * have a bpf_prog installed on an entry - */ - for (i = 0; i < new->aux->used_map_cnt; i++) { - if (dev_map_can_have_prog(new->aux->used_maps[i]) || - cpu_map_prog_allowed(new->aux->used_maps[i])) { - mutex_unlock(&new->aux->used_maps_mutex); - return -EINVAL; - } - } - - mutex_unlock(&new->aux->used_maps_mutex); - } - switch (xdp->command) { case XDP_SETUP_PROG: rcu_assign_pointer(dev->xdp_prog, new); @@ -5876,7 +5795,7 @@ static void flush_all_backlogs(void) */ ASSERT_RTNL(); - get_online_cpus(); + cpus_read_lock(); cpumask_clear(&flush_cpus); for_each_online_cpu(cpu) { @@ -5894,7 +5813,7 @@ static void flush_all_backlogs(void) for_each_cpu(cpu, &flush_cpus) flush_work(per_cpu_ptr(&flush_works, cpu)); - put_online_cpus(); + cpus_read_unlock(); } /* Pass the currently batched GRO_NORMAL SKBs up to the stack. */ @@ -6011,7 +5930,6 @@ static void gro_list_prepare(const struct list_head *head, diffs |= skb_vlan_tag_present(p) ^ skb_vlan_tag_present(skb); if (skb_vlan_tag_present(p)) diffs |= skb_vlan_tag_get(p) ^ skb_vlan_tag_get(skb); - 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), @@ -6021,17 +5939,30 @@ static void gro_list_prepare(const struct list_head *head, skb_mac_header(skb), maclen); - diffs |= skb_get_nfct(p) ^ skb_get_nfct(skb); + /* in most common scenarions 'slow_gro' is 0 + * otherwise we are already on some slower paths + * either skip all the infrequent tests altogether or + * avoid trying too hard to skip each of them individually + */ + if (!diffs && unlikely(skb->slow_gro | p->slow_gro)) { #if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT) - if (!diffs) { - struct tc_skb_ext *skb_ext = skb_ext_find(skb, TC_SKB_EXT); - struct tc_skb_ext *p_ext = skb_ext_find(p, TC_SKB_EXT); + struct tc_skb_ext *skb_ext; + struct tc_skb_ext *p_ext; +#endif + + diffs |= p->sk != skb->sk; + diffs |= skb_metadata_dst_cmp(p, skb); + diffs |= skb_get_nfct(p) ^ skb_get_nfct(skb); + +#if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT) + skb_ext = skb_ext_find(skb, TC_SKB_EXT); + p_ext = skb_ext_find(p, TC_SKB_EXT); diffs |= (!!p_ext) ^ (!!skb_ext); if (!diffs && unlikely(skb_ext)) diffs |= p_ext->chain ^ skb_ext->chain; - } #endif + } NAPI_GRO_CB(p)->same_flow = !diffs; } @@ -6296,8 +6227,12 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb->encapsulation = 0; skb_shinfo(skb)->gso_type = 0; skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); - skb_ext_reset(skb); - nf_reset_ct(skb); + if (unlikely(skb->slow_gro)) { + skb_orphan(skb); + skb_ext_reset(skb); + nf_reset_ct(skb); + skb->slow_gro = 0; + } napi->skb = skb; } @@ -7597,7 +7532,7 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev, { struct netdev_adjacent *lower; - WARN_ON_ONCE(!rcu_read_lock_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); @@ -9362,7 +9297,7 @@ static struct bpf_prog *dev_xdp_prog(struct net_device *dev, return dev->xdp_state[mode].prog; } -static u8 dev_xdp_prog_count(struct net_device *dev) +u8 dev_xdp_prog_count(struct net_device *dev) { u8 count = 0; int i; @@ -9372,6 +9307,7 @@ static u8 dev_xdp_prog_count(struct net_device *dev) count++; return count; } +EXPORT_SYMBOL_GPL(dev_xdp_prog_count); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode) { @@ -9465,6 +9401,8 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack { unsigned int num_modes = hweight32(flags & XDP_FLAGS_MODES); struct bpf_prog *cur_prog; + struct net_device *upper; + struct list_head *iter; enum bpf_xdp_mode mode; bpf_op_t bpf_op; int err; @@ -9503,6 +9441,14 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack return -EBUSY; } + /* don't allow if an upper device already has a program */ + netdev_for_each_upper_dev_rcu(dev, upper, iter) { + if (dev_xdp_prog_count(upper) > 0) { + NL_SET_ERR_MSG(extack, "Cannot attach when an upper device already has a program"); + return -EEXIST; + } + } + cur_prog = dev_xdp_prog(dev, mode); /* can't replace attached prog with link */ if (link && cur_prog) { @@ -10134,7 +10080,7 @@ static int netif_alloc_rx_queues(struct net_device *dev) BUG_ON(count < 1); - rx = kvzalloc(sz, GFP_KERNEL | __GFP_RETRY_MAYFAIL); + rx = kvzalloc(sz, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!rx) return -ENOMEM; @@ -10201,7 +10147,7 @@ static int netif_alloc_netdev_queues(struct net_device *dev) if (count < 1 || count > 0xffff) return -EINVAL; - tx = kvzalloc(sz, GFP_KERNEL | __GFP_RETRY_MAYFAIL); + tx = kvzalloc(sz, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!tx) return -ENOMEM; @@ -10841,7 +10787,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, /* ensure 32-byte alignment of whole construct */ alloc_size += NETDEV_ALIGN - 1; - p = kvzalloc(alloc_size, GFP_KERNEL | __GFP_RETRY_MAYFAIL); + p = kvzalloc(alloc_size, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!p) return NULL; diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 45ae6eeb2964..8c39283c26ae 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -16,10 +16,9 @@ * General list handling functions */ -static int __hw_addr_create_ex(struct netdev_hw_addr_list *list, - const unsigned char *addr, int addr_len, - unsigned char addr_type, bool global, - bool sync) +static struct netdev_hw_addr* +__hw_addr_create(const unsigned char *addr, int addr_len, + unsigned char addr_type, bool global, bool sync) { struct netdev_hw_addr *ha; int alloc_size; @@ -29,32 +28,44 @@ static int __hw_addr_create_ex(struct netdev_hw_addr_list *list, alloc_size = L1_CACHE_BYTES; ha = kmalloc(alloc_size, GFP_ATOMIC); if (!ha) - return -ENOMEM; + return NULL; memcpy(ha->addr, addr, addr_len); ha->type = addr_type; ha->refcount = 1; ha->global_use = global; ha->synced = sync ? 1 : 0; ha->sync_cnt = 0; - list_add_tail_rcu(&ha->list, &list->list); - list->count++; - return 0; + return ha; } static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type, bool global, bool sync, - int sync_count) + int sync_count, bool exclusive) { + struct rb_node **ins_point = &list->tree.rb_node, *parent = NULL; struct netdev_hw_addr *ha; if (addr_len > MAX_ADDR_LEN) return -EINVAL; - list_for_each_entry(ha, &list->list, list) { - if (ha->type == addr_type && - !memcmp(ha->addr, addr, addr_len)) { + while (*ins_point) { + int diff; + + ha = rb_entry(*ins_point, struct netdev_hw_addr, node); + diff = memcmp(addr, ha->addr, addr_len); + if (diff == 0) + diff = memcmp(&addr_type, &ha->type, sizeof(addr_type)); + + parent = *ins_point; + if (diff < 0) { + ins_point = &parent->rb_left; + } else if (diff > 0) { + ins_point = &parent->rb_right; + } else { + if (exclusive) + return -EEXIST; if (global) { /* check if addr is already used as global */ if (ha->global_use) @@ -73,8 +84,25 @@ static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, } } - return __hw_addr_create_ex(list, addr, addr_len, addr_type, global, - sync); + ha = __hw_addr_create(addr, addr_len, addr_type, global, sync); + if (!ha) + return -ENOMEM; + + /* The first address in dev->dev_addrs is pointed to by dev->dev_addr + * and mutated freely by device drivers and netdev ops, so if we insert + * it into the tree we'll end up with an invalid rbtree. + */ + if (list->count > 0) { + rb_link_node(&ha->node, parent, ins_point); + rb_insert_color(&ha->node, &list->tree); + } else { + RB_CLEAR_NODE(&ha->node); + } + + list_add_tail_rcu(&ha->list, &list->list); + list->count++; + + return 0; } static int __hw_addr_add(struct netdev_hw_addr_list *list, @@ -82,7 +110,7 @@ static int __hw_addr_add(struct netdev_hw_addr_list *list, unsigned char addr_type) { return __hw_addr_add_ex(list, addr, addr_len, addr_type, false, false, - 0); + 0, false); } static int __hw_addr_del_entry(struct netdev_hw_addr_list *list, @@ -103,24 +131,61 @@ static int __hw_addr_del_entry(struct netdev_hw_addr_list *list, if (--ha->refcount) return 0; + + if (!RB_EMPTY_NODE(&ha->node)) + rb_erase(&ha->node, &list->tree); + list_del_rcu(&ha->list); kfree_rcu(ha, rcu_head); list->count--; return 0; } +static struct netdev_hw_addr *__hw_addr_lookup(struct netdev_hw_addr_list *list, + const unsigned char *addr, int addr_len, + unsigned char addr_type) +{ + struct netdev_hw_addr *ha; + struct rb_node *node; + + /* The first address isn't inserted into the tree because in the dev->dev_addrs + * list it's the address pointed to by dev->dev_addr which is freely mutated + * in place, so we need to check it separately. + */ + ha = list_first_entry(&list->list, struct netdev_hw_addr, list); + if (ha && !memcmp(addr, ha->addr, addr_len) && + (!addr_type || addr_type == ha->type)) + return ha; + + node = list->tree.rb_node; + + while (node) { + struct netdev_hw_addr *ha = rb_entry(node, struct netdev_hw_addr, node); + int diff = memcmp(addr, ha->addr, addr_len); + + if (diff == 0 && addr_type) + diff = memcmp(&addr_type, &ha->type, sizeof(addr_type)); + + if (diff < 0) + node = node->rb_left; + else if (diff > 0) + node = node->rb_right; + else + return ha; + } + + return NULL; +} + static int __hw_addr_del_ex(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type, bool global, bool sync) { - struct netdev_hw_addr *ha; + struct netdev_hw_addr *ha = __hw_addr_lookup(list, addr, addr_len, addr_type); - list_for_each_entry(ha, &list->list, list) { - if (!memcmp(ha->addr, addr, addr_len) && - (ha->type == addr_type || !addr_type)) - return __hw_addr_del_entry(list, ha, global, sync); - } - return -ENOENT; + if (!ha) + return -ENOENT; + return __hw_addr_del_entry(list, ha, global, sync); } static int __hw_addr_del(struct netdev_hw_addr_list *list, @@ -137,7 +202,7 @@ static int __hw_addr_sync_one(struct netdev_hw_addr_list *to_list, int err; err = __hw_addr_add_ex(to_list, ha->addr, addr_len, ha->type, - false, true, ha->sync_cnt); + false, true, ha->sync_cnt, false); if (err && err != -EEXIST) return err; @@ -407,6 +472,7 @@ static void __hw_addr_flush(struct netdev_hw_addr_list *list) { struct netdev_hw_addr *ha, *tmp; + list->tree = RB_ROOT; list_for_each_entry_safe(ha, tmp, &list->list, list) { list_del_rcu(&ha->list); kfree_rcu(ha, rcu_head); @@ -418,6 +484,7 @@ void __hw_addr_init(struct netdev_hw_addr_list *list) { INIT_LIST_HEAD(&list->list); list->count = 0; + list->tree = RB_ROOT; } EXPORT_SYMBOL(__hw_addr_init); @@ -552,22 +619,14 @@ EXPORT_SYMBOL(dev_addr_del); */ int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr) { - struct netdev_hw_addr *ha; int err; netif_addr_lock_bh(dev); - list_for_each_entry(ha, &dev->uc.list, list) { - if (!memcmp(ha->addr, addr, dev->addr_len) && - ha->type == NETDEV_HW_ADDR_T_UNICAST) { - err = -EEXIST; - goto out; - } - } - err = __hw_addr_create_ex(&dev->uc, addr, dev->addr_len, - NETDEV_HW_ADDR_T_UNICAST, true, false); + err = __hw_addr_add_ex(&dev->uc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_UNICAST, true, false, + 0, true); if (!err) __dev_set_rx_mode(dev); -out: netif_addr_unlock_bh(dev); return err; } @@ -745,22 +804,14 @@ EXPORT_SYMBOL(dev_uc_init); */ int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr) { - struct netdev_hw_addr *ha; int err; netif_addr_lock_bh(dev); - list_for_each_entry(ha, &dev->mc.list, list) { - if (!memcmp(ha->addr, addr, dev->addr_len) && - ha->type == NETDEV_HW_ADDR_T_MULTICAST) { - err = -EEXIST; - goto out; - } - } - err = __hw_addr_create_ex(&dev->mc, addr, dev->addr_len, - NETDEV_HW_ADDR_T_MULTICAST, true, false); + err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_MULTICAST, true, false, + 0, true); if (!err) __dev_set_rx_mode(dev); -out: netif_addr_unlock_bh(dev); return err; } @@ -773,7 +824,8 @@ static int __dev_mc_add(struct net_device *dev, const unsigned char *addr, netif_addr_lock_bh(dev); err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, - NETDEV_HW_ADDR_T_MULTICAST, global, false, 0); + NETDEV_HW_ADDR_T_MULTICAST, global, false, + 0, false); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 478d032f34ac..0e87237fd871 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -1,10 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/kmod.h> #include <linux/netdevice.h> +#include <linux/inetdevice.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <linux/net_tstamp.h> #include <linux/wireless.h> +#include <linux/if_bridge.h> #include <net/dsa.h> #include <net/wext.h> @@ -25,79 +27,108 @@ static int dev_ifname(struct net *net, struct ifreq *ifr) return netdev_get_name(net, ifr->ifr_name, ifr->ifr_ifindex); } -static gifconf_func_t *gifconf_list[NPROTO]; - -/** - * register_gifconf - register a SIOCGIF handler - * @family: Address family - * @gifconf: Function handler - * - * Register protocol dependent address dumping routines. The handler - * that is passed must not be freed or reused until it has been replaced - * by another handler. - */ -int register_gifconf(unsigned int family, gifconf_func_t *gifconf) -{ - if (family >= NPROTO) - return -EINVAL; - gifconf_list[family] = gifconf; - return 0; -} -EXPORT_SYMBOL(register_gifconf); - /* * Perform a SIOCGIFCONF call. This structure will change * size eventually, and there is nothing I can do about it. * Thus we will need a 'compatibility mode'. */ - -int dev_ifconf(struct net *net, struct ifconf *ifc, int size) +int dev_ifconf(struct net *net, struct ifconf __user *uifc) { struct net_device *dev; - char __user *pos; - int len; - int total; - int i; + void __user *pos; + size_t size; + int len, total = 0, done; - /* - * Fetch the caller's info block. - */ + /* both the ifconf and the ifreq structures are slightly different */ + if (in_compat_syscall()) { + struct compat_ifconf ifc32; - pos = ifc->ifc_buf; - len = ifc->ifc_len; + if (copy_from_user(&ifc32, uifc, sizeof(struct compat_ifconf))) + return -EFAULT; - /* - * Loop over the interfaces, and write an info block for each. - */ + pos = compat_ptr(ifc32.ifcbuf); + len = ifc32.ifc_len; + size = sizeof(struct compat_ifreq); + } else { + struct ifconf ifc; + + if (copy_from_user(&ifc, uifc, sizeof(struct ifconf))) + return -EFAULT; - total = 0; + pos = ifc.ifc_buf; + len = ifc.ifc_len; + size = sizeof(struct ifreq); + } + + /* Loop over the interfaces, and write an info block for each. */ + rtnl_lock(); for_each_netdev(net, dev) { - for (i = 0; i < NPROTO; i++) { - if (gifconf_list[i]) { - int done; - if (!pos) - done = gifconf_list[i](dev, NULL, 0, size); - else - done = gifconf_list[i](dev, pos + total, - len - total, size); - if (done < 0) - return -EFAULT; - total += done; - } + if (!pos) + done = inet_gifconf(dev, NULL, 0, size); + else + done = inet_gifconf(dev, pos + total, + len - total, size); + if (done < 0) { + rtnl_unlock(); + return -EFAULT; } + total += done; } + rtnl_unlock(); - /* - * All done. Write the updated control block back to the caller. - */ - ifc->ifc_len = total; + return put_user(total, &uifc->ifc_len); +} + +static int dev_getifmap(struct net_device *dev, struct ifreq *ifr) +{ + struct ifmap *ifmap = &ifr->ifr_map; + + if (in_compat_syscall()) { + struct compat_ifmap *cifmap = (struct compat_ifmap *)ifmap; + + cifmap->mem_start = dev->mem_start; + cifmap->mem_end = dev->mem_end; + cifmap->base_addr = dev->base_addr; + cifmap->irq = dev->irq; + cifmap->dma = dev->dma; + cifmap->port = dev->if_port; + + return 0; + } + + ifmap->mem_start = dev->mem_start; + ifmap->mem_end = dev->mem_end; + ifmap->base_addr = dev->base_addr; + ifmap->irq = dev->irq; + ifmap->dma = dev->dma; + ifmap->port = dev->if_port; - /* - * Both BSD and Solaris return 0 here, so we do too. - */ return 0; } +static int dev_setifmap(struct net_device *dev, struct ifreq *ifr) +{ + struct compat_ifmap *cifmap = (struct compat_ifmap *)&ifr->ifr_map; + + if (!dev->netdev_ops->ndo_set_config) + return -EOPNOTSUPP; + + if (in_compat_syscall()) { + struct ifmap ifmap = { + .mem_start = cifmap->mem_start, + .mem_end = cifmap->mem_end, + .base_addr = cifmap->base_addr, + .irq = cifmap->irq, + .dma = cifmap->dma, + .port = cifmap->port, + }; + + return dev->netdev_ops->ndo_set_config(dev, &ifmap); + } + + return dev->netdev_ops->ndo_set_config(dev, &ifr->ifr_map); +} + /* * Perform the SIOCxIFxxx calls, inside rcu_read_lock() */ @@ -128,13 +159,7 @@ static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cm break; case SIOCGIFMAP: - ifr->ifr_map.mem_start = dev->mem_start; - ifr->ifr_map.mem_end = dev->mem_end; - ifr->ifr_map.base_addr = dev->base_addr; - ifr->ifr_map.irq = dev->irq; - ifr->ifr_map.dma = dev->dma; - ifr->ifr_map.port = dev->if_port; - return 0; + return dev_getifmap(dev, ifr); case SIOCGIFINDEX: ifr->ifr_ifindex = dev->ifindex; @@ -215,19 +240,19 @@ static int net_hwtstamp_validate(struct ifreq *ifr) return 0; } -static int dev_do_ioctl(struct net_device *dev, - struct ifreq *ifr, unsigned int cmd) +static int dev_eth_ioctl(struct net_device *dev, + struct ifreq *ifr, unsigned int cmd) { const struct net_device_ops *ops = dev->netdev_ops; int err; - err = dsa_ndo_do_ioctl(dev, ifr, cmd); + err = dsa_ndo_eth_ioctl(dev, ifr, cmd); if (err == 0 || err != -EOPNOTSUPP) return err; - if (ops->ndo_do_ioctl) { + if (ops->ndo_eth_ioctl) { if (netif_device_present(dev)) - err = ops->ndo_do_ioctl(dev, ifr, cmd); + err = ops->ndo_eth_ioctl(dev, ifr, cmd); else err = -ENODEV; } @@ -235,10 +260,55 @@ static int dev_do_ioctl(struct net_device *dev, return err; } +static int dev_siocbond(struct net_device *dev, + struct ifreq *ifr, unsigned int cmd) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (ops->ndo_siocbond) { + if (netif_device_present(dev)) + return ops->ndo_siocbond(dev, ifr, cmd); + else + return -ENODEV; + } + + return -EOPNOTSUPP; +} + +static int dev_siocdevprivate(struct net_device *dev, struct ifreq *ifr, + void __user *data, unsigned int cmd) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (ops->ndo_siocdevprivate) { + if (netif_device_present(dev)) + return ops->ndo_siocdevprivate(dev, ifr, data, cmd); + else + return -ENODEV; + } + + return -EOPNOTSUPP; +} + +static int dev_siocwandev(struct net_device *dev, struct if_settings *ifs) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (ops->ndo_siocwandev) { + if (netif_device_present(dev)) + return ops->ndo_siocwandev(dev, ifs); + else + return -ENODEV; + } + + return -EOPNOTSUPP; +} + /* * Perform the SIOCxIFxxx calls, inside rtnl_lock() */ -static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) +static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, + unsigned int cmd) { int err; struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name); @@ -275,12 +345,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) return 0; case SIOCSIFMAP: - if (ops->ndo_set_config) { - if (!netif_device_present(dev)) - return -ENODEV; - return ops->ndo_set_config(dev, &ifr->ifr_map); - } - return -EOPNOTSUPP; + return dev_setifmap(dev, ifr); case SIOCADDMULTI: if (!ops->ndo_set_rx_mode || @@ -307,6 +372,22 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) ifr->ifr_newname[IFNAMSIZ-1] = '\0'; return dev_change_name(dev, ifr->ifr_newname); + case SIOCWANDEV: + return dev_siocwandev(dev, &ifr->ifr_settings); + + case SIOCBRADDIF: + case SIOCBRDELIF: + if (!netif_device_present(dev)) + return -ENODEV; + if (!netif_is_bridge_master(dev)) + return -EOPNOTSUPP; + dev_hold(dev); + rtnl_unlock(); + err = br_ioctl_call(net, netdev_priv(dev), cmd, ifr, NULL); + dev_put(dev); + rtnl_lock(); + return err; + case SIOCSHWTSTAMP: err = net_hwtstamp_validate(ifr); if (err) @@ -317,23 +398,23 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) * Unknown or private ioctl */ default: - if ((cmd >= SIOCDEVPRIVATE && - cmd <= SIOCDEVPRIVATE + 15) || - cmd == SIOCBONDENSLAVE || + if (cmd >= SIOCDEVPRIVATE && + cmd <= SIOCDEVPRIVATE + 15) + return dev_siocdevprivate(dev, ifr, data, cmd); + + if (cmd == SIOCGMIIPHY || + cmd == SIOCGMIIREG || + cmd == SIOCSMIIREG || + cmd == SIOCSHWTSTAMP || + cmd == SIOCGHWTSTAMP) { + err = dev_eth_ioctl(dev, ifr, cmd); + } else if (cmd == SIOCBONDENSLAVE || cmd == SIOCBONDRELEASE || cmd == SIOCBONDSETHWADDR || cmd == SIOCBONDSLAVEINFOQUERY || cmd == SIOCBONDINFOQUERY || - cmd == SIOCBONDCHANGEACTIVE || - cmd == SIOCGMIIPHY || - cmd == SIOCGMIIREG || - cmd == SIOCSMIIREG || - cmd == SIOCBRADDIF || - cmd == SIOCBRDELIF || - cmd == SIOCSHWTSTAMP || - cmd == SIOCGHWTSTAMP || - cmd == SIOCWANDEV) { - err = dev_do_ioctl(dev, ifr, cmd); + cmd == SIOCBONDCHANGEACTIVE) { + err = dev_siocbond(dev, ifr, cmd); } else err = -EINVAL; @@ -386,7 +467,8 @@ EXPORT_SYMBOL(dev_load); * positive or a negative errno code on error. */ -int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_copyout) +int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, + void __user *data, bool *need_copyout) { int ret; char *colon; @@ -437,7 +519,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c case SIOCETHTOOL: dev_load(net, ifr->ifr_name); rtnl_lock(); - ret = dev_ethtool(net, ifr); + ret = dev_ethtool(net, ifr, data); rtnl_unlock(); if (colon) *colon = ':'; @@ -456,7 +538,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; rtnl_lock(); - ret = dev_ifsioc(net, ifr, cmd); + ret = dev_ifsioc(net, ifr, data, cmd); rtnl_unlock(); if (colon) *colon = ':'; @@ -502,7 +584,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c case SIOCBONDINFOQUERY: dev_load(net, ifr->ifr_name); rtnl_lock(); - ret = dev_ifsioc(net, ifr, cmd); + ret = dev_ifsioc(net, ifr, data, cmd); rtnl_unlock(); if (need_copyout) *need_copyout = false; @@ -527,7 +609,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c cmd <= SIOCDEVPRIVATE + 15)) { dev_load(net, ifr->ifr_name); rtnl_lock(); - ret = dev_ifsioc(net, ifr, cmd); + ret = dev_ifsioc(net, ifr, data, cmd); rtnl_unlock(); return ret; } diff --git a/net/core/devlink.c b/net/core/devlink.c index 8fdd04f00fd7..a856ae401ea5 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -92,7 +92,8 @@ static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ DEVLINK_PORT_FN_STATE_ACTIVE), }; -static LIST_HEAD(devlink_list); +static DEFINE_XARRAY_FLAGS(devlinks, XA_FLAGS_ALLOC); +#define DEVLINK_REGISTERED XA_MARK_1 /* devlink_mutex * @@ -108,23 +109,23 @@ struct net *devlink_net(const struct devlink *devlink) } EXPORT_SYMBOL_GPL(devlink_net); -static void __devlink_net_set(struct devlink *devlink, struct net *net) +static void devlink_put(struct devlink *devlink) { - write_pnet(&devlink->_net, net); + if (refcount_dec_and_test(&devlink->refcount)) + complete(&devlink->comp); } -void devlink_net_set(struct devlink *devlink, struct net *net) +static bool __must_check devlink_try_get(struct devlink *devlink) { - if (WARN_ON(devlink->registered)) - return; - __devlink_net_set(devlink, net); + return refcount_inc_not_zero(&devlink->refcount); } -EXPORT_SYMBOL_GPL(devlink_net_set); static struct devlink *devlink_get_from_attrs(struct net *net, struct nlattr **attrs) { struct devlink *devlink; + unsigned long index; + bool found = false; char *busname; char *devname; @@ -136,19 +137,19 @@ static struct devlink *devlink_get_from_attrs(struct net *net, lockdep_assert_held(&devlink_mutex); - list_for_each_entry(devlink, &devlink_list, list) { + xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) { if (strcmp(devlink->dev->bus->name, busname) == 0 && strcmp(dev_name(devlink->dev), devname) == 0 && - net_eq(devlink_net(devlink), net)) - return devlink; + net_eq(devlink_net(devlink), net)) { + found = true; + break; + } } - return ERR_PTR(-ENODEV); -} + if (!found || !devlink_try_get(devlink)) + devlink = ERR_PTR(-ENODEV); -static struct devlink *devlink_get_from_info(struct genl_info *info) -{ - return devlink_get_from_attrs(genl_info_net(info), info->attrs); + return devlink; } static struct devlink_port *devlink_port_get_by_index(struct devlink *devlink, @@ -499,7 +500,7 @@ static int devlink_nl_pre_doit(const struct genl_ops *ops, int err; mutex_lock(&devlink_mutex); - devlink = devlink_get_from_info(info); + devlink = devlink_get_from_attrs(genl_info_net(info), info->attrs); if (IS_ERR(devlink)) { mutex_unlock(&devlink_mutex); return PTR_ERR(devlink); @@ -542,6 +543,7 @@ static int devlink_nl_pre_doit(const struct genl_ops *ops, unlock: if (~ops->internal_flags & DEVLINK_NL_FLAG_NO_LOCK) mutex_unlock(&devlink->lock); + devlink_put(devlink); mutex_unlock(&devlink_mutex); return err; } @@ -554,6 +556,7 @@ static void devlink_nl_post_doit(const struct genl_ops *ops, devlink = info->user_ptr[0]; if (~ops->internal_flags & DEVLINK_NL_FLAG_NO_LOCK) mutex_unlock(&devlink->lock); + devlink_put(devlink); mutex_unlock(&devlink_mutex); } @@ -817,10 +820,11 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg, return 0; } -static int -devlink_port_fn_hw_addr_fill(struct devlink *devlink, const struct devlink_ops *ops, - struct devlink_port *port, struct sk_buff *msg, - struct netlink_ext_ack *extack, bool *msg_updated) +static int devlink_port_fn_hw_addr_fill(const struct devlink_ops *ops, + struct devlink_port *port, + struct sk_buff *msg, + struct netlink_ext_ack *extack, + bool *msg_updated) { u8 hw_addr[MAX_ADDR_LEN]; int hw_addr_len; @@ -829,7 +833,8 @@ devlink_port_fn_hw_addr_fill(struct devlink *devlink, const struct devlink_ops * if (!ops->port_function_hw_addr_get) return 0; - err = ops->port_function_hw_addr_get(devlink, port, hw_addr, &hw_addr_len, extack); + err = ops->port_function_hw_addr_get(port, hw_addr, &hw_addr_len, + extack); if (err) { if (err == -EOPNOTSUPP) return 0; @@ -843,12 +848,11 @@ devlink_port_fn_hw_addr_fill(struct devlink *devlink, const struct devlink_ops * } static int devlink_nl_rate_fill(struct sk_buff *msg, - struct devlink *devlink, struct devlink_rate *devlink_rate, - enum devlink_command cmd, u32 portid, - u32 seq, int flags, - struct netlink_ext_ack *extack) + enum devlink_command cmd, u32 portid, u32 seq, + int flags, struct netlink_ext_ack *extack) { + struct devlink *devlink = devlink_rate->devlink; void *hdr; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); @@ -906,12 +910,11 @@ devlink_port_fn_opstate_valid(enum devlink_port_fn_opstate opstate) opstate == DEVLINK_PORT_FN_OPSTATE_ATTACHED; } -static int -devlink_port_fn_state_fill(struct devlink *devlink, - const struct devlink_ops *ops, - struct devlink_port *port, struct sk_buff *msg, - struct netlink_ext_ack *extack, - bool *msg_updated) +static int devlink_port_fn_state_fill(const struct devlink_ops *ops, + struct devlink_port *port, + struct sk_buff *msg, + struct netlink_ext_ack *extack, + bool *msg_updated) { enum devlink_port_fn_opstate opstate; enum devlink_port_fn_state state; @@ -920,7 +923,7 @@ devlink_port_fn_state_fill(struct devlink *devlink, if (!ops->port_fn_state_get) return 0; - err = ops->port_fn_state_get(devlink, port, &state, &opstate, extack); + err = ops->port_fn_state_get(port, &state, &opstate, extack); if (err) { if (err == -EOPNOTSUPP) return 0; @@ -948,7 +951,6 @@ static int devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port, struct netlink_ext_ack *extack) { - struct devlink *devlink = port->devlink; const struct devlink_ops *ops; struct nlattr *function_attr; bool msg_updated = false; @@ -958,13 +960,12 @@ devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *por if (!function_attr) return -EMSGSIZE; - ops = devlink->ops; - err = devlink_port_fn_hw_addr_fill(devlink, ops, port, msg, - extack, &msg_updated); + ops = port->devlink->ops; + err = devlink_port_fn_hw_addr_fill(ops, port, msg, extack, + &msg_updated); if (err) goto out; - err = devlink_port_fn_state_fill(devlink, ops, port, msg, extack, - &msg_updated); + err = devlink_port_fn_state_fill(ops, port, msg, extack, &msg_updated); out: if (err || !msg_updated) nla_nest_cancel(msg, function_attr); @@ -973,12 +974,12 @@ out: return err; } -static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, +static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink_port *devlink_port, - enum devlink_command cmd, u32 portid, - u32 seq, int flags, - struct netlink_ext_ack *extack) + enum devlink_command cmd, u32 portid, u32 seq, + int flags, struct netlink_ext_ack *extack) { + struct devlink *devlink = devlink_port->devlink; void *hdr; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); @@ -1039,53 +1040,47 @@ nla_put_failure: static void devlink_port_notify(struct devlink_port *devlink_port, enum devlink_command cmd) { - struct devlink *devlink = devlink_port->devlink; struct sk_buff *msg; int err; - if (!devlink_port->registered) - return; - WARN_ON(cmd != DEVLINK_CMD_PORT_NEW && cmd != DEVLINK_CMD_PORT_DEL); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; - err = devlink_nl_port_fill(msg, devlink, devlink_port, cmd, 0, 0, 0, - NULL); + err = devlink_nl_port_fill(msg, devlink_port, cmd, 0, 0, 0, NULL); if (err) { nlmsg_free(msg); return; } - genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), - msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); + genlmsg_multicast_netns(&devlink_nl_family, + devlink_net(devlink_port->devlink), msg, 0, + DEVLINK_MCGRP_CONFIG, GFP_KERNEL); } static void devlink_rate_notify(struct devlink_rate *devlink_rate, enum devlink_command cmd) { - struct devlink *devlink = devlink_rate->devlink; struct sk_buff *msg; int err; - WARN_ON(cmd != DEVLINK_CMD_RATE_NEW && - cmd != DEVLINK_CMD_RATE_DEL); + WARN_ON(cmd != DEVLINK_CMD_RATE_NEW && cmd != DEVLINK_CMD_RATE_DEL); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; - err = devlink_nl_rate_fill(msg, devlink, devlink_rate, - cmd, 0, 0, 0, NULL); + err = devlink_nl_rate_fill(msg, devlink_rate, cmd, 0, 0, 0, NULL); if (err) { nlmsg_free(msg); return; } - genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), - msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); + genlmsg_multicast_netns(&devlink_nl_family, + devlink_net(devlink_rate->devlink), msg, 0, + DEVLINK_MCGRP_CONFIG, GFP_KERNEL); } static int devlink_nl_cmd_rate_get_dumpit(struct sk_buff *msg, @@ -1094,13 +1089,18 @@ static int devlink_nl_cmd_rate_get_dumpit(struct sk_buff *msg, struct devlink_rate *devlink_rate; struct devlink *devlink; int start = cb->args[0]; + unsigned long index; int idx = 0; int err = 0; mutex_lock(&devlink_mutex); - list_for_each_entry(devlink, &devlink_list, list) { - if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) { + if (!devlink_try_get(devlink)) continue; + + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + goto retry; + mutex_lock(&devlink->lock); list_for_each_entry(devlink_rate, &devlink->rate_list, list) { enum devlink_command cmd = DEVLINK_CMD_RATE_NEW; @@ -1110,18 +1110,19 @@ static int devlink_nl_cmd_rate_get_dumpit(struct sk_buff *msg, idx++; continue; } - err = devlink_nl_rate_fill(msg, devlink, - devlink_rate, - cmd, id, + err = devlink_nl_rate_fill(msg, devlink_rate, cmd, id, cb->nlh->nlmsg_seq, NLM_F_MULTI, NULL); if (err) { mutex_unlock(&devlink->lock); + devlink_put(devlink); goto out; } idx++; } mutex_unlock(&devlink->lock); +retry: + devlink_put(devlink); } out: mutex_unlock(&devlink_mutex); @@ -1136,7 +1137,6 @@ static int devlink_nl_cmd_rate_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_rate *devlink_rate = info->user_ptr[1]; - struct devlink *devlink = devlink_rate->devlink; struct sk_buff *msg; int err; @@ -1144,8 +1144,7 @@ static int devlink_nl_cmd_rate_get_doit(struct sk_buff *skb, if (!msg) return -ENOMEM; - err = devlink_nl_rate_fill(msg, devlink, devlink_rate, - DEVLINK_CMD_RATE_NEW, + err = devlink_nl_rate_fill(msg, devlink_rate, DEVLINK_CMD_RATE_NEW, info->snd_portid, info->snd_seq, 0, info->extack); if (err) { @@ -1193,20 +1192,30 @@ static int devlink_nl_cmd_get_dumpit(struct sk_buff *msg, { struct devlink *devlink; int start = cb->args[0]; + unsigned long index; int idx = 0; int err; mutex_lock(&devlink_mutex); - list_for_each_entry(devlink, &devlink_list, list) { - if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) { + if (!devlink_try_get(devlink)) + continue; + + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) { + devlink_put(devlink); continue; + } + if (idx < start) { idx++; + devlink_put(devlink); continue; } + err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI); + devlink_put(devlink); if (err) goto out; idx++; @@ -1222,7 +1231,6 @@ static int devlink_nl_cmd_port_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; - struct devlink *devlink = devlink_port->devlink; struct sk_buff *msg; int err; @@ -1230,8 +1238,7 @@ static int devlink_nl_cmd_port_get_doit(struct sk_buff *skb, if (!msg) return -ENOMEM; - err = devlink_nl_port_fill(msg, devlink, devlink_port, - DEVLINK_CMD_PORT_NEW, + err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_PORT_NEW, info->snd_portid, info->snd_seq, 0, info->extack); if (err) { @@ -1248,32 +1255,39 @@ static int devlink_nl_cmd_port_get_dumpit(struct sk_buff *msg, struct devlink *devlink; struct devlink_port *devlink_port; int start = cb->args[0]; + unsigned long index; int idx = 0; int err; mutex_lock(&devlink_mutex); - list_for_each_entry(devlink, &devlink_list, list) { - if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) { + if (!devlink_try_get(devlink)) continue; + + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + goto retry; + mutex_lock(&devlink->lock); list_for_each_entry(devlink_port, &devlink->port_list, list) { if (idx < start) { idx++; continue; } - err = devlink_nl_port_fill(msg, devlink, devlink_port, + err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_NEW, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - NLM_F_MULTI, - cb->extack); + NLM_F_MULTI, cb->extack); if (err) { mutex_unlock(&devlink->lock); + devlink_put(devlink); goto out; } idx++; } mutex_unlock(&devlink->lock); +retry: + devlink_put(devlink); } out: mutex_unlock(&devlink_mutex); @@ -1282,31 +1296,33 @@ out: return msg->len; } -static int devlink_port_type_set(struct devlink *devlink, - struct devlink_port *devlink_port, +static int devlink_port_type_set(struct devlink_port *devlink_port, enum devlink_port_type port_type) { int err; - if (devlink->ops->port_type_set) { - if (port_type == devlink_port->type) - return 0; - err = devlink->ops->port_type_set(devlink_port, port_type); - if (err) - return err; - devlink_port->desired_type = port_type; - devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); + if (!devlink_port->devlink->ops->port_type_set) + return -EOPNOTSUPP; + + if (port_type == devlink_port->type) return 0; - } - return -EOPNOTSUPP; + + err = devlink_port->devlink->ops->port_type_set(devlink_port, + port_type); + if (err) + return err; + + devlink_port->desired_type = port_type; + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); + return 0; } -static int -devlink_port_function_hw_addr_set(struct devlink *devlink, struct devlink_port *port, - const struct nlattr *attr, struct netlink_ext_ack *extack) +static int devlink_port_function_hw_addr_set(struct devlink_port *port, + const struct nlattr *attr, + struct netlink_ext_ack *extack) { - const struct devlink_ops *ops; + const struct devlink_ops *ops = port->devlink->ops; const u8 *hw_addr; int hw_addr_len; @@ -1327,17 +1343,16 @@ devlink_port_function_hw_addr_set(struct devlink *devlink, struct devlink_port * } } - ops = devlink->ops; if (!ops->port_function_hw_addr_set) { NL_SET_ERR_MSG_MOD(extack, "Port doesn't support function attributes"); return -EOPNOTSUPP; } - return ops->port_function_hw_addr_set(devlink, port, hw_addr, hw_addr_len, extack); + return ops->port_function_hw_addr_set(port, hw_addr, hw_addr_len, + extack); } -static int devlink_port_fn_state_set(struct devlink *devlink, - struct devlink_port *port, +static int devlink_port_fn_state_set(struct devlink_port *port, const struct nlattr *attr, struct netlink_ext_ack *extack) { @@ -1345,18 +1360,18 @@ static int devlink_port_fn_state_set(struct devlink *devlink, const struct devlink_ops *ops; state = nla_get_u8(attr); - ops = devlink->ops; + ops = port->devlink->ops; if (!ops->port_fn_state_set) { NL_SET_ERR_MSG_MOD(extack, "Function does not support state setting"); return -EOPNOTSUPP; } - return ops->port_fn_state_set(devlink, port, state, extack); + return ops->port_fn_state_set(port, state, extack); } -static int -devlink_port_function_set(struct devlink *devlink, struct devlink_port *port, - const struct nlattr *attr, struct netlink_ext_ack *extack) +static int devlink_port_function_set(struct devlink_port *port, + const struct nlattr *attr, + struct netlink_ext_ack *extack) { struct nlattr *tb[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1]; int err; @@ -1370,7 +1385,7 @@ devlink_port_function_set(struct devlink *devlink, struct devlink_port *port, attr = tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR]; if (attr) { - err = devlink_port_function_hw_addr_set(devlink, port, attr, extack); + err = devlink_port_function_hw_addr_set(port, attr, extack); if (err) return err; } @@ -1380,7 +1395,7 @@ devlink_port_function_set(struct devlink *devlink, struct devlink_port *port, */ attr = tb[DEVLINK_PORT_FN_ATTR_STATE]; if (attr) - err = devlink_port_fn_state_set(devlink, port, attr, extack); + err = devlink_port_fn_state_set(port, attr, extack); if (!err) devlink_port_notify(port, DEVLINK_CMD_PORT_NEW); @@ -1391,14 +1406,13 @@ static int devlink_nl_cmd_port_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; - struct devlink *devlink = devlink_port->devlink; int err; if (info->attrs[DEVLINK_ATTR_PORT_TYPE]) { enum devlink_port_type port_type; port_type = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_TYPE]); - err = devlink_port_type_set(devlink, devlink_port, port_type); + err = devlink_port_type_set(devlink_port, port_type); if (err) return err; } @@ -1407,7 +1421,7 @@ static int devlink_nl_cmd_port_set_doit(struct sk_buff *skb, struct nlattr *attr = info->attrs[DEVLINK_ATTR_PORT_FUNCTION]; struct netlink_ext_ack *extack = info->extack; - err = devlink_port_function_set(devlink, devlink_port, attr, extack); + err = devlink_port_function_set(devlink_port, attr, extack); if (err) return err; } @@ -1502,9 +1516,8 @@ static int devlink_port_new_notifiy(struct devlink *devlink, goto out; } - err = devlink_nl_port_fill(msg, devlink, devlink_port, - DEVLINK_CMD_NEW, info->snd_portid, - info->snd_seq, 0, NULL); + err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_NEW, + info->snd_portid, info->snd_seq, 0, NULL); if (err) goto out; @@ -1908,13 +1921,18 @@ static int devlink_nl_cmd_sb_get_dumpit(struct sk_buff *msg, struct devlink *devlink; struct devlink_sb *devlink_sb; int start = cb->args[0]; + unsigned long index; int idx = 0; int err; mutex_lock(&devlink_mutex); - list_for_each_entry(devlink, &devlink_list, list) { - if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) { + if (!devlink_try_get(devlink)) continue; + + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + goto retry; + mutex_lock(&devlink->lock); list_for_each_entry(devlink_sb, &devlink->sb_list, list) { if (idx < start) { @@ -1928,11 +1946,14 @@ static int devlink_nl_cmd_sb_get_dumpit(struct sk_buff *msg, NLM_F_MULTI); if (err) { mutex_unlock(&devlink->lock); + devlink_put(devlink); goto out; } idx++; } mutex_unlock(&devlink->lock); +retry: + devlink_put(devlink); } out: mutex_unlock(&devlink_mutex); @@ -2052,14 +2073,19 @@ static int devlink_nl_cmd_sb_pool_get_dumpit(struct sk_buff *msg, struct devlink *devlink; struct devlink_sb *devlink_sb; int start = cb->args[0]; + unsigned long index; int idx = 0; int err = 0; mutex_lock(&devlink_mutex); - list_for_each_entry(devlink, &devlink_list, list) { + xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) { + if (!devlink_try_get(devlink)) + continue; + if (!net_eq(devlink_net(devlink), sock_net(msg->sk)) || !devlink->ops->sb_pool_get) - continue; + goto retry; + mutex_lock(&devlink->lock); list_for_each_entry(devlink_sb, &devlink->sb_list, list) { err = __sb_pool_get_dumpit(msg, start, &idx, devlink, @@ -2070,10 +2096,13 @@ static int devlink_nl_cmd_sb_pool_get_dumpit(struct sk_buff *msg, err = 0; } else if (err) { mutex_unlock(&devlink->lock); + devlink_put(devlink); goto out; } } mutex_unlock(&devlink->lock); +retry: + devlink_put(devlink); } out: mutex_unlock(&devlink_mutex); @@ -2265,14 +2294,19 @@ static int devlink_nl_cmd_sb_port_pool_get_dumpit(struct sk_buff *msg, struct devlink *devlink; struct devlink_sb *devlink_sb; int start = cb->args[0]; + unsigned long index; int idx = 0; int err = 0; mutex_lock(&devlink_mutex); - list_for_each_entry(devlink, &devlink_list, list) { + xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) { + if (!devlink_try_get(devlink)) + continue; + if (!net_eq(devlink_net(devlink), sock_net(msg->sk)) || !devlink->ops->sb_port_pool_get) - continue; + goto retry; + mutex_lock(&devlink->lock); list_for_each_entry(devlink_sb, &devlink->sb_list, list) { err = __sb_port_pool_get_dumpit(msg, start, &idx, @@ -2283,10 +2317,13 @@ static int devlink_nl_cmd_sb_port_pool_get_dumpit(struct sk_buff *msg, err = 0; } else if (err) { mutex_unlock(&devlink->lock); + devlink_put(devlink); goto out; } } mutex_unlock(&devlink->lock); +retry: + devlink_put(devlink); } out: mutex_unlock(&devlink_mutex); @@ -2506,14 +2543,18 @@ devlink_nl_cmd_sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, struct devlink *devlink; struct devlink_sb *devlink_sb; int start = cb->args[0]; + unsigned long index; int idx = 0; int err = 0; mutex_lock(&devlink_mutex); - list_for_each_entry(devlink, &devlink_list, list) { + xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) { + if (!devlink_try_get(devlink)) + continue; + if (!net_eq(devlink_net(devlink), sock_net(msg->sk)) || !devlink->ops->sb_tc_pool_bind_get) - continue; + goto retry; mutex_lock(&devlink->lock); list_for_each_entry(devlink_sb, &devlink->sb_list, list) { @@ -2526,10 +2567,13 @@ devlink_nl_cmd_sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, err = 0; } else if (err) { mutex_unlock(&devlink->lock); + devlink_put(devlink); goto out; } } mutex_unlock(&devlink->lock); +retry: + devlink_put(devlink); } out: mutex_unlock(&devlink_mutex); @@ -3801,10 +3845,12 @@ static void devlink_param_notify(struct devlink *devlink, struct devlink_param_item *param_item, enum devlink_command cmd); -static void devlink_reload_netns_change(struct devlink *devlink, - struct net *dest_net) +static void devlink_ns_change_notify(struct devlink *devlink, + struct net *dest_net, struct net *curr_net, + bool new) { struct devlink_param_item *param_item; + enum devlink_command cmd; /* Userspace needs to be notified about devlink objects * removed from original and entering new network namespace. @@ -3812,17 +3858,18 @@ static void devlink_reload_netns_change(struct devlink *devlink, * reload process so the notifications are generated separatelly. */ - list_for_each_entry(param_item, &devlink->param_list, list) - devlink_param_notify(devlink, 0, param_item, - DEVLINK_CMD_PARAM_DEL); - devlink_notify(devlink, DEVLINK_CMD_DEL); + if (!dest_net || net_eq(dest_net, curr_net)) + return; - __devlink_net_set(devlink, dest_net); + if (new) + devlink_notify(devlink, DEVLINK_CMD_NEW); - devlink_notify(devlink, DEVLINK_CMD_NEW); + cmd = new ? DEVLINK_CMD_PARAM_NEW : DEVLINK_CMD_PARAM_DEL; list_for_each_entry(param_item, &devlink->param_list, list) - devlink_param_notify(devlink, 0, param_item, - DEVLINK_CMD_PARAM_NEW); + devlink_param_notify(devlink, 0, param_item, cmd); + + if (!new) + devlink_notify(devlink, DEVLINK_CMD_DEL); } static bool devlink_reload_supported(const struct devlink_ops *ops) @@ -3902,6 +3949,7 @@ static int devlink_reload(struct devlink *devlink, struct net *dest_net, u32 *actions_performed, struct netlink_ext_ack *extack) { u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; + struct net *curr_net; int err; if (!devlink->reload_enabled) @@ -3909,18 +3957,22 @@ static int devlink_reload(struct devlink *devlink, struct net *dest_net, memcpy(remote_reload_stats, devlink->stats.remote_reload_stats, sizeof(remote_reload_stats)); + + curr_net = devlink_net(devlink); + devlink_ns_change_notify(devlink, dest_net, curr_net, false); err = devlink->ops->reload_down(devlink, !!dest_net, action, limit, extack); if (err) return err; - if (dest_net && !net_eq(dest_net, devlink_net(devlink))) - devlink_reload_netns_change(devlink, dest_net); + if (dest_net && !net_eq(dest_net, curr_net)) + write_pnet(&devlink->_net, dest_net); err = devlink->ops->reload_up(devlink, action, limit, actions_performed, extack); devlink_reload_failed_set(devlink, !!err); if (err) return err; + devlink_ns_change_notify(devlink, dest_net, curr_net, true); WARN_ON(!(*actions_performed & BIT(action))); /* Catch driver on updating the remote action within devlink reload */ WARN_ON(memcmp(remote_reload_stats, devlink->stats.remote_reload_stats, @@ -4117,7 +4169,7 @@ out_free_msg: static void devlink_flash_update_begin_notify(struct devlink *devlink) { - struct devlink_flash_notify params = { 0 }; + struct devlink_flash_notify params = {}; __devlink_flash_update_notify(devlink, DEVLINK_CMD_FLASH_UPDATE, @@ -4126,7 +4178,7 @@ static void devlink_flash_update_begin_notify(struct devlink *devlink) static void devlink_flash_update_end_notify(struct devlink *devlink) { - struct devlink_flash_notify params = { 0 }; + struct devlink_flash_notify params = {}; __devlink_flash_update_notify(devlink, DEVLINK_CMD_FLASH_UPDATE_END, @@ -4283,6 +4335,21 @@ static const struct devlink_param devlink_param_generic[] = { .name = DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_NAME, .type = DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_TYPE, }, + { + .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_ETH, + .name = DEVLINK_PARAM_GENERIC_ENABLE_ETH_NAME, + .type = DEVLINK_PARAM_GENERIC_ENABLE_ETH_TYPE, + }, + { + .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA, + .name = DEVLINK_PARAM_GENERIC_ENABLE_RDMA_NAME, + .type = DEVLINK_PARAM_GENERIC_ENABLE_RDMA_TYPE, + }, + { + .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_VNET, + .name = DEVLINK_PARAM_GENERIC_ENABLE_VNET_NAME, + .type = DEVLINK_PARAM_GENERIC_ENABLE_VNET_TYPE, + }, }; static int devlink_param_generic_verify(const struct devlink_param *param) @@ -4553,13 +4620,18 @@ static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg, struct devlink_param_item *param_item; struct devlink *devlink; int start = cb->args[0]; + unsigned long index; int idx = 0; int err = 0; mutex_lock(&devlink_mutex); - list_for_each_entry(devlink, &devlink_list, list) { - if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) { + if (!devlink_try_get(devlink)) continue; + + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + goto retry; + mutex_lock(&devlink->lock); list_for_each_entry(param_item, &devlink->param_list, list) { if (idx < start) { @@ -4575,11 +4647,14 @@ static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg, err = 0; } else if (err) { mutex_unlock(&devlink->lock); + devlink_put(devlink); goto out; } idx++; } mutex_unlock(&devlink->lock); +retry: + devlink_put(devlink); } out: mutex_unlock(&devlink_mutex); @@ -4821,13 +4896,18 @@ static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg, struct devlink_port *devlink_port; struct devlink *devlink; int start = cb->args[0]; + unsigned long index; int idx = 0; int err = 0; mutex_lock(&devlink_mutex); - list_for_each_entry(devlink, &devlink_list, list) { - if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) { + if (!devlink_try_get(devlink)) continue; + + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + goto retry; + mutex_lock(&devlink->lock); list_for_each_entry(devlink_port, &devlink->port_list, list) { list_for_each_entry(param_item, @@ -4847,12 +4927,15 @@ static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg, err = 0; } else if (err) { mutex_unlock(&devlink->lock); + devlink_put(devlink); goto out; } idx++; } } mutex_unlock(&devlink->lock); +retry: + devlink_put(devlink); } out: mutex_unlock(&devlink_mutex); @@ -5062,7 +5145,6 @@ static void devlink_nl_region_notify(struct devlink_region *region, struct devlink_snapshot *snapshot, enum devlink_command cmd) { - struct devlink *devlink = region->devlink; struct sk_buff *msg; WARN_ON(cmd != DEVLINK_CMD_REGION_NEW && cmd != DEVLINK_CMD_REGION_DEL); @@ -5071,8 +5153,9 @@ static void devlink_nl_region_notify(struct devlink_region *region, if (IS_ERR(msg)) return; - genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), - msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); + genlmsg_multicast_netns(&devlink_nl_family, + devlink_net(region->devlink), msg, 0, + DEVLINK_MCGRP_CONFIG, GFP_KERNEL); } /** @@ -5390,15 +5473,22 @@ static int devlink_nl_cmd_region_get_dumpit(struct sk_buff *msg, { struct devlink *devlink; int start = cb->args[0]; + unsigned long index; int idx = 0; - int err; + int err = 0; mutex_lock(&devlink_mutex); - list_for_each_entry(devlink, &devlink_list, list) { - if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) { + if (!devlink_try_get(devlink)) continue; + + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + goto retry; + err = devlink_nl_cmd_region_get_devlink_dumpit(msg, cb, devlink, &idx, start); +retry: + devlink_put(devlink); if (err) goto out; } @@ -5761,6 +5851,7 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, nla_nest_end(skb, chunks_attr); genlmsg_end(skb, hdr); mutex_unlock(&devlink->lock); + devlink_put(devlink); mutex_unlock(&devlink_mutex); return skb->len; @@ -5769,6 +5860,7 @@ nla_put_failure: genlmsg_cancel(skb, hdr); out_unlock: mutex_unlock(&devlink->lock); + devlink_put(devlink); out_dev: mutex_unlock(&devlink_mutex); return err; @@ -5915,22 +6007,20 @@ static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg, { struct devlink *devlink; int start = cb->args[0]; + unsigned long index; int idx = 0; int err = 0; mutex_lock(&devlink_mutex); - list_for_each_entry(devlink, &devlink_list, list) { - if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) { + if (!devlink_try_get(devlink)) continue; - if (idx < start) { - idx++; - continue; - } - if (!devlink->ops->info_get) { - idx++; - continue; - } + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + goto retry; + + if (idx < start || !devlink->ops->info_get) + goto inc; mutex_lock(&devlink->lock); err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, @@ -5940,9 +6030,14 @@ static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg, mutex_unlock(&devlink->lock); if (err == -EOPNOTSUPP) err = 0; - else if (err) + else if (err) { + devlink_put(devlink); break; + } +inc: idx++; +retry: + devlink_put(devlink); } mutex_unlock(&devlink_mutex); @@ -6756,11 +6851,11 @@ EXPORT_SYMBOL_GPL(devlink_port_health_reporter_destroy); static int devlink_nl_health_reporter_fill(struct sk_buff *msg, - struct devlink *devlink, struct devlink_health_reporter *reporter, enum devlink_command cmd, u32 portid, u32 seq, int flags) { + struct devlink *devlink = reporter->devlink; struct nlattr *reporter_attr; void *hdr; @@ -6837,8 +6932,7 @@ static void devlink_recover_notify(struct devlink_health_reporter *reporter, if (!msg) return; - err = devlink_nl_health_reporter_fill(msg, reporter->devlink, - reporter, cmd, 0, 0, 0); + err = devlink_nl_health_reporter_fill(msg, reporter, cmd, 0, 0, 0); if (err) { nlmsg_free(msg); return; @@ -7028,6 +7122,7 @@ devlink_health_reporter_get_from_cb(struct netlink_callback *cb) goto unlock; reporter = devlink_health_reporter_get_from_attrs(devlink, attrs); + devlink_put(devlink); mutex_unlock(&devlink_mutex); return reporter; unlock: @@ -7071,7 +7166,7 @@ static int devlink_nl_cmd_health_reporter_get_doit(struct sk_buff *skb, goto out; } - err = devlink_nl_health_reporter_fill(msg, devlink, reporter, + err = devlink_nl_health_reporter_fill(msg, reporter, DEVLINK_CMD_HEALTH_REPORTER_GET, info->snd_portid, info->snd_seq, 0); @@ -7094,13 +7189,18 @@ devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg, struct devlink_port *port; struct devlink *devlink; int start = cb->args[0]; + unsigned long index; int idx = 0; int err; mutex_lock(&devlink_mutex); - list_for_each_entry(devlink, &devlink_list, list) { - if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) { + if (!devlink_try_get(devlink)) continue; + + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + goto retry_rep; + mutex_lock(&devlink->reporters_lock); list_for_each_entry(reporter, &devlink->reporter_list, list) { @@ -7108,24 +7208,29 @@ devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg, idx++; continue; } - err = devlink_nl_health_reporter_fill(msg, devlink, - reporter, - DEVLINK_CMD_HEALTH_REPORTER_GET, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI); + err = devlink_nl_health_reporter_fill( + msg, reporter, DEVLINK_CMD_HEALTH_REPORTER_GET, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + NLM_F_MULTI); if (err) { mutex_unlock(&devlink->reporters_lock); + devlink_put(devlink); goto out; } idx++; } mutex_unlock(&devlink->reporters_lock); +retry_rep: + devlink_put(devlink); } - list_for_each_entry(devlink, &devlink_list, list) { - if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) { + if (!devlink_try_get(devlink)) continue; + + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + goto retry_port; + mutex_lock(&devlink->lock); list_for_each_entry(port, &devlink->port_list, list) { mutex_lock(&port->reporters_lock); @@ -7134,14 +7239,15 @@ devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg, idx++; continue; } - err = devlink_nl_health_reporter_fill(msg, devlink, reporter, - DEVLINK_CMD_HEALTH_REPORTER_GET, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI); + err = devlink_nl_health_reporter_fill( + msg, reporter, + DEVLINK_CMD_HEALTH_REPORTER_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI); if (err) { mutex_unlock(&port->reporters_lock); mutex_unlock(&devlink->lock); + devlink_put(devlink); goto out; } idx++; @@ -7149,6 +7255,8 @@ devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg, mutex_unlock(&port->reporters_lock); } mutex_unlock(&devlink->lock); +retry_port: + devlink_put(devlink); } out: mutex_unlock(&devlink_mutex); @@ -7677,13 +7785,18 @@ static int devlink_nl_cmd_trap_get_dumpit(struct sk_buff *msg, struct devlink_trap_item *trap_item; struct devlink *devlink; int start = cb->args[0]; + unsigned long index; int idx = 0; int err; mutex_lock(&devlink_mutex); - list_for_each_entry(devlink, &devlink_list, list) { - if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) { + if (!devlink_try_get(devlink)) continue; + + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + goto retry; + mutex_lock(&devlink->lock); list_for_each_entry(trap_item, &devlink->trap_list, list) { if (idx < start) { @@ -7697,11 +7810,14 @@ static int devlink_nl_cmd_trap_get_dumpit(struct sk_buff *msg, NLM_F_MULTI); if (err) { mutex_unlock(&devlink->lock); + devlink_put(devlink); goto out; } idx++; } mutex_unlock(&devlink->lock); +retry: + devlink_put(devlink); } out: mutex_unlock(&devlink_mutex); @@ -7896,13 +8012,18 @@ static int devlink_nl_cmd_trap_group_get_dumpit(struct sk_buff *msg, u32 portid = NETLINK_CB(cb->skb).portid; struct devlink *devlink; int start = cb->args[0]; + unsigned long index; int idx = 0; int err; mutex_lock(&devlink_mutex); - list_for_each_entry(devlink, &devlink_list, list) { - if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) { + if (!devlink_try_get(devlink)) continue; + + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + goto retry; + mutex_lock(&devlink->lock); list_for_each_entry(group_item, &devlink->trap_group_list, list) { @@ -7917,11 +8038,14 @@ static int devlink_nl_cmd_trap_group_get_dumpit(struct sk_buff *msg, NLM_F_MULTI); if (err) { mutex_unlock(&devlink->lock); + devlink_put(devlink); goto out; } idx++; } mutex_unlock(&devlink->lock); +retry: + devlink_put(devlink); } out: mutex_unlock(&devlink_mutex); @@ -8202,13 +8326,18 @@ static int devlink_nl_cmd_trap_policer_get_dumpit(struct sk_buff *msg, u32 portid = NETLINK_CB(cb->skb).portid; struct devlink *devlink; int start = cb->args[0]; + unsigned long index; int idx = 0; int err; mutex_lock(&devlink_mutex); - list_for_each_entry(devlink, &devlink_list, list) { - if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) { + if (!devlink_try_get(devlink)) continue; + + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + goto retry; + mutex_lock(&devlink->lock); list_for_each_entry(policer_item, &devlink->trap_policer_list, list) { @@ -8223,11 +8352,14 @@ static int devlink_nl_cmd_trap_policer_get_dumpit(struct sk_buff *msg, NLM_F_MULTI); if (err) { mutex_unlock(&devlink->lock); + devlink_put(devlink); goto out; } idx++; } mutex_unlock(&devlink->lock); +retry: + devlink_put(devlink); } out: mutex_unlock(&devlink_mutex); @@ -8768,30 +8900,44 @@ static bool devlink_reload_actions_valid(const struct devlink_ops *ops) } /** - * devlink_alloc - Allocate new devlink instance resources + * devlink_alloc_ns - Allocate new devlink instance resources + * in specific namespace * * @ops: ops * @priv_size: size of user private data + * @net: net namespace + * @dev: parent device * * Allocate new devlink instance resources, including devlink index * and name. */ -struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) +struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, + size_t priv_size, struct net *net, + struct device *dev) { struct devlink *devlink; + static u32 last_id; + int ret; - if (WARN_ON(!ops)) - return NULL; - + WARN_ON(!ops || !dev); if (!devlink_reload_actions_valid(ops)) return NULL; devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL); if (!devlink) return NULL; + + ret = xa_alloc_cyclic(&devlinks, &devlink->index, devlink, xa_limit_31b, + &last_id, GFP_KERNEL); + if (ret < 0) { + kfree(devlink); + return NULL; + } + + devlink->dev = dev; devlink->ops = ops; xa_init_flags(&devlink->snapshot_ids, XA_FLAGS_ALLOC); - __devlink_net_set(devlink, &init_net); + write_pnet(&devlink->_net, net); INIT_LIST_HEAD(&devlink->port_list); INIT_LIST_HEAD(&devlink->rate_list); INIT_LIST_HEAD(&devlink->sb_list); @@ -8805,22 +8951,22 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) INIT_LIST_HEAD(&devlink->trap_policer_list); mutex_init(&devlink->lock); mutex_init(&devlink->reporters_lock); + refcount_set(&devlink->refcount, 1); + init_completion(&devlink->comp); + return devlink; } -EXPORT_SYMBOL_GPL(devlink_alloc); +EXPORT_SYMBOL_GPL(devlink_alloc_ns); /** * devlink_register - Register devlink instance * * @devlink: devlink - * @dev: parent device */ -int devlink_register(struct devlink *devlink, struct device *dev) +int devlink_register(struct devlink *devlink) { - devlink->dev = dev; - devlink->registered = true; mutex_lock(&devlink_mutex); - list_add_tail(&devlink->list, &devlink_list); + xa_set_mark(&devlinks, devlink->index, DEVLINK_REGISTERED); devlink_notify(devlink, DEVLINK_CMD_NEW); mutex_unlock(&devlink_mutex); return 0; @@ -8834,11 +8980,14 @@ EXPORT_SYMBOL_GPL(devlink_register); */ void devlink_unregister(struct devlink *devlink) { + devlink_put(devlink); + wait_for_completion(&devlink->comp); + mutex_lock(&devlink_mutex); WARN_ON(devlink_reload_supported(devlink->ops) && devlink->reload_enabled); devlink_notify(devlink, DEVLINK_CMD_DEL); - list_del(&devlink->list); + xa_clear_mark(&devlinks, devlink->index, DEVLINK_REGISTERED); mutex_unlock(&devlink_mutex); } EXPORT_SYMBOL_GPL(devlink_unregister); @@ -8900,6 +9049,7 @@ void devlink_free(struct devlink *devlink) WARN_ON(!list_empty(&devlink->port_list)); xa_destroy(&devlink->snapshot_ids); + xa_erase(&devlinks, devlink->index); kfree(devlink); } @@ -8960,9 +9110,10 @@ int devlink_port_register(struct devlink *devlink, mutex_unlock(&devlink->lock); return -EEXIST; } + + WARN_ON(devlink_port->devlink); devlink_port->devlink = devlink; devlink_port->index = port_index; - devlink_port->registered = true; spin_lock_init(&devlink_port->type_lock); INIT_LIST_HEAD(&devlink_port->reporter_list); mutex_init(&devlink_port->reporters_lock); @@ -9001,7 +9152,7 @@ static void __devlink_port_type_set(struct devlink_port *devlink_port, enum devlink_port_type type, void *type_dev) { - if (WARN_ON(!devlink_port->registered)) + if (WARN_ON(!devlink_port->devlink)) return; devlink_port_type_warn_cancel(devlink_port); spin_lock_bh(&devlink_port->type_lock); @@ -9121,7 +9272,7 @@ void devlink_port_attrs_set(struct devlink_port *devlink_port, { int ret; - if (WARN_ON(devlink_port->registered)) + if (WARN_ON(devlink_port->devlink)) return; devlink_port->attrs = *attrs; ret = __devlink_port_attrs_set(devlink_port, attrs->flavour); @@ -9145,7 +9296,7 @@ void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 contro struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; - if (WARN_ON(devlink_port->registered)) + if (WARN_ON(devlink_port->devlink)) return; ret = __devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PCI_PF); @@ -9172,7 +9323,7 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 contro struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; - if (WARN_ON(devlink_port->registered)) + if (WARN_ON(devlink_port->devlink)) return; ret = __devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PCI_VF); @@ -9200,7 +9351,7 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 contro struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; - if (WARN_ON(devlink_port->registered)) + if (WARN_ON(devlink_port->devlink)) return; ret = __devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PCI_SF); @@ -9328,18 +9479,10 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, switch (attrs->flavour) { case DEVLINK_PORT_FLAVOUR_PHYSICAL: - case DEVLINK_PORT_FLAVOUR_VIRTUAL: n = snprintf(name, len, "p%u", attrs->phys.port_number); if (n < len && attrs->split) n += snprintf(name + n, len - n, "s%u", attrs->phys.split_subport_number); - if (!attrs->split) - n = snprintf(name, len, "p%u", attrs->phys.port_number); - else - n = snprintf(name, len, "p%us%u", - attrs->phys.port_number, - attrs->phys.split_subport_number); - break; case DEVLINK_PORT_FLAVOUR_CPU: case DEVLINK_PORT_FLAVOUR_DSA: @@ -9381,6 +9524,8 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf, attrs->pci_sf.sf); break; + case DEVLINK_PORT_FLAVOUR_VIRTUAL: + return -EOPNOTSUPP; } if (n >= len) @@ -9794,6 +9939,22 @@ static int devlink_param_verify(const struct devlink_param *param) return devlink_param_driver_verify(param); } +static int __devlink_param_register_one(struct devlink *devlink, + unsigned int port_index, + struct list_head *param_list, + const struct devlink_param *param, + enum devlink_command reg_cmd) +{ + int err; + + err = devlink_param_verify(param); + if (err) + return err; + + return devlink_param_register_one(devlink, port_index, + param_list, param, reg_cmd); +} + static int __devlink_params_register(struct devlink *devlink, unsigned int port_index, struct list_head *param_list, @@ -9808,12 +9969,8 @@ static int __devlink_params_register(struct devlink *devlink, mutex_lock(&devlink->lock); for (i = 0; i < params_count; i++, param++) { - err = devlink_param_verify(param); - if (err) - goto rollback; - - err = devlink_param_register_one(devlink, port_index, - param_list, param, reg_cmd); + err = __devlink_param_register_one(devlink, port_index, + param_list, param, reg_cmd); if (err) goto rollback; } @@ -9886,6 +10043,43 @@ void devlink_params_unregister(struct devlink *devlink, EXPORT_SYMBOL_GPL(devlink_params_unregister); /** + * devlink_param_register - register one configuration parameter + * + * @devlink: devlink + * @param: one configuration parameter + * + * Register the configuration parameter supported by the driver. + * Return: returns 0 on successful registration or error code otherwise. + */ +int devlink_param_register(struct devlink *devlink, + const struct devlink_param *param) +{ + int err; + + mutex_lock(&devlink->lock); + err = __devlink_param_register_one(devlink, 0, &devlink->param_list, + param, DEVLINK_CMD_PARAM_NEW); + mutex_unlock(&devlink->lock); + return err; +} +EXPORT_SYMBOL_GPL(devlink_param_register); + +/** + * devlink_param_unregister - unregister one configuration parameter + * @devlink: devlink + * @param: configuration parameter to unregister + */ +void devlink_param_unregister(struct devlink *devlink, + const struct devlink_param *param) +{ + mutex_lock(&devlink->lock); + devlink_param_unregister_one(devlink, 0, &devlink->param_list, param, + DEVLINK_CMD_PARAM_DEL); + mutex_unlock(&devlink->lock); +} +EXPORT_SYMBOL_GPL(devlink_param_unregister); + +/** * devlink_params_publish - publish configuration parameters * * @devlink: devlink @@ -9928,6 +10122,54 @@ void devlink_params_unpublish(struct devlink *devlink) EXPORT_SYMBOL_GPL(devlink_params_unpublish); /** + * devlink_param_publish - publish one configuration parameter + * + * @devlink: devlink + * @param: one configuration parameter + * + * Publish previously registered configuration parameter. + */ +void devlink_param_publish(struct devlink *devlink, + const struct devlink_param *param) +{ + struct devlink_param_item *param_item; + + list_for_each_entry(param_item, &devlink->param_list, list) { + if (param_item->param != param || param_item->published) + continue; + param_item->published = true; + devlink_param_notify(devlink, 0, param_item, + DEVLINK_CMD_PARAM_NEW); + break; + } +} +EXPORT_SYMBOL_GPL(devlink_param_publish); + +/** + * devlink_param_unpublish - unpublish one configuration parameter + * + * @devlink: devlink + * @param: one configuration parameter + * + * Unpublish previously registered configuration parameter. + */ +void devlink_param_unpublish(struct devlink *devlink, + const struct devlink_param *param) +{ + struct devlink_param_item *param_item; + + list_for_each_entry(param_item, &devlink->param_list, list) { + if (param_item->param != param || !param_item->published) + continue; + param_item->published = false; + devlink_param_notify(devlink, 0, param_item, + DEVLINK_CMD_PARAM_DEL); + break; + } +} +EXPORT_SYMBOL_GPL(devlink_param_unpublish); + +/** * devlink_port_params_register - register port configuration parameters * * @devlink_port: devlink port @@ -11282,23 +11524,29 @@ static void __net_exit devlink_pernet_pre_exit(struct net *net) { struct devlink *devlink; u32 actions_performed; + unsigned long index; int err; /* In case network namespace is getting destroyed, reload * all devlink instances from this namespace into init_net. */ mutex_lock(&devlink_mutex); - list_for_each_entry(devlink, &devlink_list, list) { - if (net_eq(devlink_net(devlink), net)) { - if (WARN_ON(!devlink_reload_supported(devlink->ops))) - continue; - err = devlink_reload(devlink, &init_net, - DEVLINK_RELOAD_ACTION_DRIVER_REINIT, - DEVLINK_RELOAD_LIMIT_UNSPEC, - &actions_performed, NULL); - if (err && err != -EOPNOTSUPP) - pr_warn("Failed to reload devlink instance into init_net\n"); - } + xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) { + if (!devlink_try_get(devlink)) + continue; + + if (!net_eq(devlink_net(devlink), net)) + goto retry; + + WARN_ON(!devlink_reload_supported(devlink->ops)); + err = devlink_reload(devlink, &init_net, + DEVLINK_RELOAD_ACTION_DRIVER_REINIT, + DEVLINK_RELOAD_LIMIT_UNSPEC, + &actions_performed, NULL); + if (err && err != -EOPNOTSUPP) + pr_warn("Failed to reload devlink instance into init_net\n"); +retry: + devlink_put(devlink); } mutex_unlock(&devlink_mutex); } diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index ead2a8aa57b4..49442cae6f69 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -850,8 +850,7 @@ net_dm_hw_metadata_copy(const struct devlink_trap_metadata *metadata) } hw_metadata->input_dev = metadata->input_dev; - if (hw_metadata->input_dev) - dev_hold(hw_metadata->input_dev); + dev_hold(hw_metadata->input_dev); return hw_metadata; @@ -867,8 +866,7 @@ free_hw_metadata: static void net_dm_hw_metadata_free(const struct devlink_trap_metadata *hw_metadata) { - if (hw_metadata->input_dev) - dev_put(hw_metadata->input_dev); + dev_put(hw_metadata->input_dev); kfree(hw_metadata->fa_cookie); kfree(hw_metadata->trap_name); kfree(hw_metadata->trap_group_name); diff --git a/net/core/dst.c b/net/core/dst.c index fb3bcba87744..497ef9b3fc6a 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -49,8 +49,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops, unsigned short flags) { dst->dev = dev; - if (dev) - dev_hold(dev); + dev_hold(dev); dst->ops = ops; dst_init_metrics(dst, dst_default_metrics.metrics, true); dst->expires = 0UL; @@ -118,8 +117,7 @@ struct dst_entry *dst_destroy(struct dst_entry * dst) if (dst->ops->destroy) dst->ops->destroy(dst); - if (dst->dev) - dev_put(dst->dev); + dev_put(dst->dev); lwtstate_put(dst->lwtstate); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index a9f937975080..79df7cd9dbc1 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -57,7 +57,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops, { struct fib_rule *r; - r = kzalloc(ops->rule_size, GFP_KERNEL); + r = kzalloc(ops->rule_size, GFP_KERNEL_ACCOUNT); if (r == NULL) return -ENOMEM; @@ -541,7 +541,7 @@ static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh, goto errout; } - nlrule = kzalloc(ops->rule_size, GFP_KERNEL); + nlrule = kzalloc(ops->rule_size, GFP_KERNEL_ACCOUNT); if (!nlrule) { err = -ENOMEM; goto errout; diff --git a/net/core/filter.c b/net/core/filter.c index d70187ce851b..2e32cee2c469 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -77,6 +77,7 @@ #include <net/transp_v6.h> #include <linux/btf_ids.h> #include <net/tls.h> +#include <net/xdp.h> static const struct bpf_func_proto * bpf_sk_base_func_proto(enum bpf_func_id func_id); @@ -113,7 +114,7 @@ EXPORT_SYMBOL_GPL(copy_bpf_fprog_from_user); * Run the eBPF program and then cut skb->data to correct size returned by * the program. If pkt_len is 0 we toss packet. If skb->len is smaller * than pkt_len we keep whole skb->data. This is the socket level - * wrapper to BPF_PROG_RUN. It returns 0 if the packet should + * wrapper to bpf_prog_run. It returns 0 if the packet should * be accepted or -EPERM if the packet should be tossed. * */ @@ -2179,17 +2180,9 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb, skb->tstamp = 0; if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { - struct sk_buff *skb2; - - skb2 = skb_realloc_headroom(skb, hh_len); - if (unlikely(!skb2)) { - kfree_skb(skb); + skb = skb_expand_head(skb, hh_len); + if (!skb) return -ENOMEM; - } - if (skb->sk) - skb_set_owner_w(skb2, skb->sk); - consume_skb(skb); - skb = skb2; } rcu_read_lock_bh(); @@ -2213,8 +2206,7 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb, } rcu_read_unlock_bh(); if (dst) - IP6_INC_STATS(dev_net(dst->dev), - ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); + IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); out_drop: kfree_skb(skb); return -ENETDOWN; @@ -2286,17 +2278,9 @@ static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb, skb->tstamp = 0; if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { - struct sk_buff *skb2; - - skb2 = skb_realloc_headroom(skb, hh_len); - if (unlikely(!skb2)) { - kfree_skb(skb); + skb = skb_expand_head(skb, hh_len); + if (!skb) return -ENOMEM; - } - if (skb->sk) - skb_set_owner_w(skb2, skb->sk); - consume_skb(skb); - skb = skb2; } rcu_read_lock_bh(); @@ -3880,8 +3864,7 @@ BPF_CALL_2(bpf_xdp_adjust_meta, struct xdp_buff *, xdp, int, offset) if (unlikely(meta < xdp_frame_end || meta > xdp->data)) return -EINVAL; - if (unlikely((metalen & (sizeof(__u32) - 1)) || - (metalen > 32))) + if (unlikely(xdp_metalen_invalid(metalen))) return -EACCES; xdp->data_meta = meta; @@ -3950,6 +3933,31 @@ void bpf_clear_redirect_map(struct bpf_map *map) } } +DEFINE_STATIC_KEY_FALSE(bpf_master_redirect_enabled_key); +EXPORT_SYMBOL_GPL(bpf_master_redirect_enabled_key); + +u32 xdp_master_redirect(struct xdp_buff *xdp) +{ + struct net_device *master, *slave; + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + + master = netdev_master_upper_dev_get_rcu(xdp->rxq->dev); + slave = master->netdev_ops->ndo_xdp_get_xmit_slave(master, xdp); + if (slave && slave != xdp->rxq->dev) { + /* The target device is different from the receiving device, so + * redirect it to the new device. + * Using XDP_REDIRECT gets the correct behaviour from XDP enabled + * drivers to unmap the packet from their rx ring. + */ + ri->tgt_index = slave->ifindex; + ri->map_id = INT_MAX; + ri->map_type = BPF_MAP_TYPE_UNSPEC; + return XDP_REDIRECT; + } + return XDP_TX; +} +EXPORT_SYMBOL_GPL(xdp_master_redirect); + int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { @@ -4040,8 +4048,12 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, goto err; consume_skb(skb); break; + case BPF_MAP_TYPE_CPUMAP: + err = cpu_map_generic_redirect(fwd, skb); + if (unlikely(err)) + goto err; + break; default: - /* TODO: Handle BPF_MAP_TYPE_CPUMAP */ err = -EBADRQC; goto err; } @@ -4664,6 +4676,30 @@ static const struct bpf_func_proto bpf_get_netns_cookie_sock_addr_proto = { .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; +BPF_CALL_1(bpf_get_netns_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx) +{ + return __bpf_get_netns_cookie(ctx ? ctx->sk : NULL); +} + +static const struct bpf_func_proto bpf_get_netns_cookie_sock_ops_proto = { + .func = bpf_get_netns_cookie_sock_ops, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX_OR_NULL, +}; + +BPF_CALL_1(bpf_get_netns_cookie_sk_msg, struct sk_msg *, ctx) +{ + return __bpf_get_netns_cookie(ctx ? ctx->sk : NULL); +} + +static const struct bpf_func_proto bpf_get_netns_cookie_sk_msg_proto = { + .func = bpf_get_netns_cookie_sk_msg, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX_OR_NULL, +}; + BPF_CALL_1(bpf_get_socket_uid, struct sk_buff *, skb) { struct sock *sk = sk_to_full_sk(skb->sk); @@ -5012,6 +5048,46 @@ err_clear: return -EINVAL; } +BPF_CALL_5(bpf_sk_setsockopt, struct sock *, sk, int, level, + int, optname, char *, optval, int, optlen) +{ + if (level == SOL_TCP && optname == TCP_CONGESTION) { + if (optlen >= sizeof("cdg") - 1 && + !strncmp("cdg", optval, optlen)) + return -ENOTSUPP; + } + + return _bpf_setsockopt(sk, level, optname, optval, optlen); +} + +const struct bpf_func_proto bpf_sk_setsockopt_proto = { + .func = bpf_sk_setsockopt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_MEM, + .arg5_type = ARG_CONST_SIZE, +}; + +BPF_CALL_5(bpf_sk_getsockopt, struct sock *, sk, int, level, + int, optname, char *, optval, int, optlen) +{ + return _bpf_getsockopt(sk, level, optname, optval, optlen); +} + +const struct bpf_func_proto bpf_sk_getsockopt_proto = { + .func = bpf_sk_getsockopt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_UNINIT_MEM, + .arg5_type = ARG_CONST_SIZE, +}; + BPF_CALL_5(bpf_sock_addr_setsockopt, struct bpf_sock_addr_kern *, ctx, int, level, int, optname, char *, optval, int, optlen) { @@ -7445,6 +7521,8 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; + case BPF_FUNC_get_netns_cookie: + return &bpf_get_netns_cookie_sock_ops_proto; #ifdef CONFIG_INET case BPF_FUNC_load_hdr_opt: return &bpf_sock_ops_load_hdr_opt_proto; @@ -7491,6 +7569,8 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; + case BPF_FUNC_get_netns_cookie: + return &bpf_get_netns_cookie_sk_msg_proto; #ifdef CONFIG_CGROUPS case BPF_FUNC_get_current_cgroup_id: return &bpf_get_current_cgroup_id_proto; @@ -10069,7 +10149,7 @@ struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, enum sk_action action; bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, migrating_sk, hash); - action = BPF_PROG_RUN(prog, &reuse_kern); + action = bpf_prog_run(prog, &reuse_kern); if (action == SK_PASS) return reuse_kern.selected_sk; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 2aadbfc5193b..bac0184cf3de 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1056,8 +1056,10 @@ proto_again: FLOW_DISSECTOR_KEY_IPV4_ADDRS, target_container); - memcpy(&key_addrs->v4addrs, &iph->saddr, - sizeof(key_addrs->v4addrs)); + memcpy(&key_addrs->v4addrs.src, &iph->saddr, + sizeof(key_addrs->v4addrs.src)); + memcpy(&key_addrs->v4addrs.dst, &iph->daddr, + sizeof(key_addrs->v4addrs.dst)); key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; } @@ -1101,8 +1103,10 @@ proto_again: FLOW_DISSECTOR_KEY_IPV6_ADDRS, target_container); - memcpy(&key_addrs->v6addrs, &iph->saddr, - sizeof(key_addrs->v6addrs)); + memcpy(&key_addrs->v6addrs.src, &iph->saddr, + sizeof(key_addrs->v6addrs.src)); + memcpy(&key_addrs->v6addrs.dst, &iph->daddr, + sizeof(key_addrs->v6addrs.dst)); key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } @@ -1504,7 +1508,7 @@ __be32 flow_get_u32_dst(const struct flow_keys *flow) } EXPORT_SYMBOL(flow_get_u32_dst); -/* Sort the source and destination IP (and the ports if the IP are the same), +/* Sort the source and destination IP and the ports, * to have consistent hash within the two directions */ static inline void __flow_hash_consistentify(struct flow_keys *keys) @@ -1515,11 +1519,11 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys) case FLOW_DISSECTOR_KEY_IPV4_ADDRS: addr_diff = (__force u32)keys->addrs.v4addrs.dst - (__force u32)keys->addrs.v4addrs.src; - if ((addr_diff < 0) || - (addr_diff == 0 && - ((__force u16)keys->ports.dst < - (__force u16)keys->ports.src))) { + if (addr_diff < 0) swap(keys->addrs.v4addrs.src, keys->addrs.v4addrs.dst); + + if ((__force u16)keys->ports.dst < + (__force u16)keys->ports.src) { swap(keys->ports.src, keys->ports.dst); } break; @@ -1527,13 +1531,13 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys) addr_diff = memcmp(&keys->addrs.v6addrs.dst, &keys->addrs.v6addrs.src, sizeof(keys->addrs.v6addrs.dst)); - if ((addr_diff < 0) || - (addr_diff == 0 && - ((__force u16)keys->ports.dst < - (__force u16)keys->ports.src))) { + if (addr_diff < 0) { for (i = 0; i < 4; i++) swap(keys->addrs.v6addrs.src.s6_addr32[i], keys->addrs.v6addrs.dst.s6_addr32[i]); + } + if ((__force u16)keys->ports.dst < + (__force u16)keys->ports.src) { swap(keys->ports.src, keys->ports.dst); } break; diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index 715b67f6c62f..6beaea13564a 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -321,13 +321,13 @@ EXPORT_SYMBOL(flow_block_cb_setup_simple); static DEFINE_MUTEX(flow_indr_block_lock); static LIST_HEAD(flow_block_indr_list); static LIST_HEAD(flow_block_indr_dev_list); +static LIST_HEAD(flow_indir_dev_list); struct flow_indr_dev { struct list_head list; flow_indr_block_bind_cb_t *cb; void *cb_priv; refcount_t refcnt; - struct rcu_head rcu; }; static struct flow_indr_dev *flow_indr_dev_alloc(flow_indr_block_bind_cb_t *cb, @@ -346,6 +346,33 @@ static struct flow_indr_dev *flow_indr_dev_alloc(flow_indr_block_bind_cb_t *cb, return indr_dev; } +struct flow_indir_dev_info { + void *data; + struct net_device *dev; + struct Qdisc *sch; + enum tc_setup_type type; + void (*cleanup)(struct flow_block_cb *block_cb); + struct list_head list; + enum flow_block_command command; + enum flow_block_binder_type binder_type; + struct list_head *cb_list; +}; + +static void existing_qdiscs_register(flow_indr_block_bind_cb_t *cb, void *cb_priv) +{ + struct flow_block_offload bo; + struct flow_indir_dev_info *cur; + + list_for_each_entry(cur, &flow_indir_dev_list, list) { + memset(&bo, 0, sizeof(bo)); + bo.command = cur->command; + bo.binder_type = cur->binder_type; + INIT_LIST_HEAD(&bo.cb_list); + cb(cur->dev, cur->sch, cb_priv, cur->type, &bo, cur->data, cur->cleanup); + list_splice(&bo.cb_list, cur->cb_list); + } +} + int flow_indr_dev_register(flow_indr_block_bind_cb_t *cb, void *cb_priv) { struct flow_indr_dev *indr_dev; @@ -367,6 +394,7 @@ int flow_indr_dev_register(flow_indr_block_bind_cb_t *cb, void *cb_priv) } list_add(&indr_dev->list, &flow_block_indr_dev_list); + existing_qdiscs_register(cb, cb_priv); mutex_unlock(&flow_indr_block_lock); return 0; @@ -463,7 +491,59 @@ out: } EXPORT_SYMBOL(flow_indr_block_cb_alloc); -int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch, +static struct flow_indir_dev_info *find_indir_dev(void *data) +{ + struct flow_indir_dev_info *cur; + + list_for_each_entry(cur, &flow_indir_dev_list, list) { + if (cur->data == data) + return cur; + } + return NULL; +} + +static int indir_dev_add(void *data, struct net_device *dev, struct Qdisc *sch, + enum tc_setup_type type, void (*cleanup)(struct flow_block_cb *block_cb), + struct flow_block_offload *bo) +{ + struct flow_indir_dev_info *info; + + info = find_indir_dev(data); + if (info) + return -EEXIST; + + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (!info) + return -ENOMEM; + + info->data = data; + info->dev = dev; + info->sch = sch; + info->type = type; + info->cleanup = cleanup; + info->command = bo->command; + info->binder_type = bo->binder_type; + info->cb_list = bo->cb_list_head; + + list_add(&info->list, &flow_indir_dev_list); + return 0; +} + +static int indir_dev_remove(void *data) +{ + struct flow_indir_dev_info *info; + + info = find_indir_dev(data); + if (!info) + return -ENOENT; + + list_del(&info->list); + + kfree(info); + return 0; +} + +int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch, enum tc_setup_type type, void *data, struct flow_block_offload *bo, void (*cleanup)(struct flow_block_cb *block_cb)) @@ -471,6 +551,12 @@ int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch, struct flow_indr_dev *this; mutex_lock(&flow_indr_block_lock); + + if (bo->command == FLOW_BLOCK_BIND) + indir_dev_add(data, dev, sch, type, cleanup, bo); + else if (bo->command == FLOW_BLOCK_UNBIND) + indir_dev_remove(data); + list_for_each_entry(this, &flow_block_indr_dev_list, list) this->cb(dev, sch, this->cb_priv, type, bo, data, cleanup); diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 75431ca9300f..1a455847da54 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -158,7 +158,7 @@ static void linkwatch_do_dev(struct net_device *dev) clear_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state); rfc2863_policy(dev); - if (dev->flags & IFF_UP && netif_device_present(dev)) { + if (dev->flags & IFF_UP) { if (netif_carrier_ok(dev)) dev_activate(dev); else @@ -204,7 +204,8 @@ static void __linkwatch_run_queue(int urgent_only) dev = list_first_entry(&wrk, struct net_device, link_watch_list); list_del_init(&dev->link_watch_list); - if (urgent_only && !linkwatch_urgent_event(dev)) { + if (!netif_device_present(dev) || + (urgent_only && !linkwatch_urgent_event(dev))) { list_add_tail(&dev->link_watch_list, &lweventlist); continue; } diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index 8ec7d13d2860..2820aca2173a 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -23,6 +23,9 @@ #include <net/ip6_fib.h> #include <net/rtnh.h> +DEFINE_STATIC_KEY_FALSE(nf_hooks_lwtunnel_enabled); +EXPORT_SYMBOL_GPL(nf_hooks_lwtunnel_enabled); + #ifdef CONFIG_MODULES static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type) @@ -43,6 +46,8 @@ static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type) return "SEG6LOCAL"; case LWTUNNEL_ENCAP_RPL: return "RPL"; + case LWTUNNEL_ENCAP_IOAM6: + return "IOAM6"; case LWTUNNEL_ENCAP_IP6: case LWTUNNEL_ENCAP_IP: case LWTUNNEL_ENCAP_NONE: diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 53e85c70c6e5..2d5bc3a75fae 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -741,12 +741,10 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, write_pnet(&n->net, net); memcpy(n->key, pkey, key_len); n->dev = dev; - if (dev) - dev_hold(dev); + dev_hold(dev); if (tbl->pconstructor && tbl->pconstructor(n)) { - if (dev) - dev_put(dev); + dev_put(dev); kfree(n); n = NULL; goto out; @@ -778,8 +776,7 @@ int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey, write_unlock_bh(&tbl->lock); if (tbl->pdestructor) tbl->pdestructor(n); - if (n->dev) - dev_put(n->dev); + dev_put(n->dev); kfree(n); return 0; } @@ -812,8 +809,7 @@ static int pneigh_ifdown_and_unlock(struct neigh_table *tbl, n->next = NULL; if (tbl->pdestructor) tbl->pdestructor(n); - if (n->dev) - dev_put(n->dev); + dev_put(n->dev); kfree(n); } return -ENOENT; @@ -1662,8 +1658,7 @@ void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms) list_del(&parms->list); parms->dead = 1; write_unlock_bh(&tbl->lock); - if (parms->dev) - dev_put(parms->dev); + dev_put(parms->dev); call_rcu(&parms->rcu_head, neigh_rcu_free_parms); } EXPORT_SYMBOL(neigh_parms_release); @@ -2533,6 +2528,13 @@ static bool neigh_master_filtered(struct net_device *dev, int master_idx) return false; master = dev ? netdev_master_upper_dev_get(dev) : NULL; + + /* 0 is already used to denote NDA_MASTER wasn't passed, therefore need another + * invalid value for ifindex to denote "no master". + */ + if (master_idx == -1) + return !!master; + if (!master || master->ifindex != master_idx) return true; @@ -3315,12 +3317,13 @@ static int neigh_stat_seq_show(struct seq_file *seq, void *v) struct neigh_statistics *st = v; if (v == SEQ_START_TOKEN) { - seq_printf(seq, "entries allocs destroys hash_grows lookups hits res_failed rcv_probes_mcast rcv_probes_ucast periodic_gc_runs forced_gc_runs unresolved_discards table_fulls\n"); + seq_puts(seq, "entries allocs destroys hash_grows lookups hits res_failed rcv_probes_mcast rcv_probes_ucast periodic_gc_runs forced_gc_runs unresolved_discards table_fulls\n"); return 0; } - seq_printf(seq, "%08x %08lx %08lx %08lx %08lx %08lx %08lx " - "%08lx %08lx %08lx %08lx %08lx %08lx\n", + seq_printf(seq, "%08x %08lx %08lx %08lx %08lx %08lx %08lx " + "%08lx %08lx %08lx " + "%08lx %08lx %08lx\n", atomic_read(&tbl->entries), st->allocs, diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index d8b9dbabd4a4..eab5fc88a002 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -77,8 +77,8 @@ static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) struct rtnl_link_stats64 temp; const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); - seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu " - "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n", + seq_printf(seq, "%9s: %16llu %12llu %4llu %6llu %4llu %5llu %10llu %9llu " + "%16llu %12llu %4llu %6llu %4llu %5llu %7llu %10llu\n", dev->name, stats->rx_bytes, stats->rx_packets, stats->rx_errors, stats->rx_dropped + stats->rx_missed_errors, @@ -103,11 +103,11 @@ static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) static int dev_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) - seq_puts(seq, "Inter-| Receive " - " | Transmit\n" - " face |bytes packets errs drop fifo frame " - "compressed multicast|bytes packets errs " - "drop fifo colls carrier compressed\n"); + seq_puts(seq, "Interface| Receive " + " | Transmit\n" + " | bytes packets errs drop fifo frame " + "compressed multicast| bytes packets errs " + " drop fifo colls carrier compressed\n"); else dev_seq_printf_stats(seq, v); return 0; @@ -259,14 +259,14 @@ static int ptype_seq_show(struct seq_file *seq, void *v) struct packet_type *pt = v; if (v == SEQ_START_TOKEN) - seq_puts(seq, "Type Device Function\n"); + seq_puts(seq, "Type Device Function\n"); else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) { if (pt->type == htons(ETH_P_ALL)) seq_puts(seq, "ALL "); else seq_printf(seq, "%04x", ntohs(pt->type)); - seq_printf(seq, " %-8s %ps\n", + seq_printf(seq, " %-9s %ps\n", pt->dev ? pt->dev->name : "", pt->func); } @@ -327,12 +327,14 @@ static int dev_mc_seq_show(struct seq_file *seq, void *v) struct netdev_hw_addr *ha; struct net_device *dev = v; - if (v == SEQ_START_TOKEN) + if (v == SEQ_START_TOKEN) { + seq_puts(seq, "Ifindex Interface Refcount Global_use Address\n"); return 0; + } netif_addr_lock_bh(dev); netdev_for_each_mc_addr(ha, dev) { - seq_printf(seq, "%-4d %-15s %-5d %-5d %*phN\n", + seq_printf(seq, "%-7d %-9s %-8d %-10d %*phN\n", dev->ifindex, dev->name, ha->refcount, ha->global_use, (int)dev->addr_len, ha->addr); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 9b5a767eddd5..a448a9b5bb2d 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -98,7 +98,7 @@ static int net_assign_generic(struct net *net, unsigned int id, void *data) } ng = net_alloc_generic(); - if (ng == NULL) + if (!ng) return -ENOMEM; /* @@ -148,13 +148,6 @@ out: return err; } -static void ops_free(const struct pernet_operations *ops, struct net *net) -{ - if (ops->id && ops->size) { - kfree(net_generic(net, *ops->id)); - } -} - static void ops_pre_exit_list(const struct pernet_operations *ops, struct list_head *net_exit_list) { @@ -184,7 +177,7 @@ static void ops_free_list(const struct pernet_operations *ops, struct net *net; if (ops->size && ops->id) { list_for_each_entry(net, net_exit_list, exit_list) - ops_free(ops, net); + kfree(net_generic(net, *ops->id)); } } @@ -433,15 +426,18 @@ out_free: static void net_free(struct net *net) { - kfree(rcu_access_pointer(net->gen)); - kmem_cache_free(net_cachep, net); + if (refcount_dec_and_test(&net->passive)) { + kfree(rcu_access_pointer(net->gen)); + kmem_cache_free(net_cachep, net); + } } void net_drop_ns(void *p) { - struct net *ns = p; - if (ns && refcount_dec_and_test(&ns->passive)) - net_free(ns); + struct net *net = (struct net *)p; + + if (net) + net_free(net); } struct net *copy_net_ns(unsigned long flags, @@ -479,7 +475,7 @@ struct net *copy_net_ns(unsigned long flags, put_userns: key_remove_domain(net->key_domain); put_user_ns(user_ns); - net_drop_ns(net); + net_free(net); dec_ucounts: dec_net_namespaces(ucounts); return ERR_PTR(rv); @@ -611,7 +607,7 @@ static void cleanup_net(struct work_struct *work) dec_net_namespaces(net->ucounts); key_remove_domain(net->key_domain); put_user_ns(net->user_ns); - net_drop_ns(net); + net_free(net); } } @@ -1120,6 +1116,14 @@ static int __init net_ns_init(void) pure_initcall(net_ns_init); +static void free_exit_list(struct pernet_operations *ops, struct list_head *net_exit_list) +{ + ops_pre_exit_list(ops, net_exit_list); + synchronize_rcu(); + ops_exit_list(ops, net_exit_list); + ops_free_list(ops, net_exit_list); +} + #ifdef CONFIG_NET_NS static int __register_pernet_operations(struct list_head *list, struct pernet_operations *ops) @@ -1145,10 +1149,7 @@ static int __register_pernet_operations(struct list_head *list, out_undo: /* If I have an error cleanup all namespaces I initialized */ list_del(&ops->list); - ops_pre_exit_list(ops, &net_exit_list); - synchronize_rcu(); - ops_exit_list(ops, &net_exit_list); - ops_free_list(ops, &net_exit_list); + free_exit_list(ops, &net_exit_list); return error; } @@ -1161,10 +1162,8 @@ static void __unregister_pernet_operations(struct pernet_operations *ops) /* See comment in __register_pernet_operations() */ for_each_net(net) list_add_tail(&net->exit_list, &net_exit_list); - ops_pre_exit_list(ops, &net_exit_list); - synchronize_rcu(); - ops_exit_list(ops, &net_exit_list); - ops_free_list(ops, &net_exit_list); + + free_exit_list(ops, &net_exit_list); } #else @@ -1187,10 +1186,7 @@ static void __unregister_pernet_operations(struct pernet_operations *ops) } else { LIST_HEAD(net_exit_list); list_add(&init_net.exit_list, &net_exit_list); - ops_pre_exit_list(ops, &net_exit_list); - synchronize_rcu(); - ops_exit_list(ops, &net_exit_list); - ops_free_list(ops, &net_exit_list); + free_exit_list(ops, &net_exit_list); } } diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 5e4eb45b139c..1a6978427d6c 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -24,6 +24,8 @@ #define DEFER_TIME (msecs_to_jiffies(1000)) #define DEFER_WARN_INTERVAL (60 * HZ) +#define BIAS_MAX LONG_MAX + static int page_pool_init(struct page_pool *pool, const struct page_pool_params *params) { @@ -67,6 +69,10 @@ static int page_pool_init(struct page_pool *pool, */ } + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT && + pool->p.flags & PP_FLAG_PAGE_FRAG) + return -EINVAL; + if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) return -ENOMEM; @@ -206,6 +212,19 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page) return true; } +static void page_pool_set_pp_info(struct page_pool *pool, + struct page *page) +{ + page->pp = pool; + page->pp_magic |= PP_SIGNATURE; +} + +static void page_pool_clear_pp_info(struct page *page) +{ + page->pp_magic = 0; + page->pp = NULL; +} + static struct page *__page_pool_alloc_page_order(struct page_pool *pool, gfp_t gfp) { @@ -222,7 +241,7 @@ static struct page *__page_pool_alloc_page_order(struct page_pool *pool, return NULL; } - page->pp_magic |= PP_SIGNATURE; + page_pool_set_pp_info(pool, page); /* Track how many pages are held 'in-flight' */ pool->pages_state_hold_cnt++; @@ -266,7 +285,8 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, put_page(page); continue; } - page->pp_magic |= PP_SIGNATURE; + + page_pool_set_pp_info(pool, page); pool->alloc.cache[pool->alloc.count++] = page; /* Track how many pages are held 'in-flight' */ pool->pages_state_hold_cnt++; @@ -345,12 +365,12 @@ void page_pool_release_page(struct page_pool *pool, struct page *page) DMA_ATTR_SKIP_CPU_SYNC); page_pool_set_dma_addr(page, 0); skip_dma_unmap: - page->pp_magic = 0; + page_pool_clear_pp_info(page); /* This may be the last page returned, releasing the pool, so * it is not safe to reference pool afterwards. */ - count = atomic_inc_return(&pool->pages_state_release_cnt); + count = atomic_inc_return_relaxed(&pool->pages_state_release_cnt); trace_page_pool_state_release(pool, page, count); } EXPORT_SYMBOL(page_pool_release_page); @@ -405,6 +425,11 @@ static __always_inline struct page * __page_pool_put_page(struct page_pool *pool, struct page *page, unsigned int dma_sync_size, bool allow_direct) { + /* It is not the last user for the page frag case */ + if (pool->p.flags & PP_FLAG_PAGE_FRAG && + page_pool_atomic_sub_frag_count_return(page, 1)) + return NULL; + /* This allocator is optimized for the XDP mode that uses * one-frame-per-page, but have fallbacks that act like the * regular page allocator APIs. @@ -497,6 +522,84 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, } EXPORT_SYMBOL(page_pool_put_page_bulk); +static struct page *page_pool_drain_frag(struct page_pool *pool, + struct page *page) +{ + long drain_count = BIAS_MAX - pool->frag_users; + + /* Some user is still using the page frag */ + if (likely(page_pool_atomic_sub_frag_count_return(page, + drain_count))) + return NULL; + + if (page_ref_count(page) == 1 && !page_is_pfmemalloc(page)) { + if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) + page_pool_dma_sync_for_device(pool, page, -1); + + return page; + } + + page_pool_return_page(pool, page); + return NULL; +} + +static void page_pool_free_frag(struct page_pool *pool) +{ + long drain_count = BIAS_MAX - pool->frag_users; + struct page *page = pool->frag_page; + + pool->frag_page = NULL; + + if (!page || + page_pool_atomic_sub_frag_count_return(page, drain_count)) + return; + + page_pool_return_page(pool, page); +} + +struct page *page_pool_alloc_frag(struct page_pool *pool, + unsigned int *offset, + unsigned int size, gfp_t gfp) +{ + unsigned int max_size = PAGE_SIZE << pool->p.order; + struct page *page = pool->frag_page; + + if (WARN_ON(!(pool->p.flags & PP_FLAG_PAGE_FRAG) || + size > max_size)) + return NULL; + + size = ALIGN(size, dma_get_cache_alignment()); + *offset = pool->frag_offset; + + if (page && *offset + size > max_size) { + page = page_pool_drain_frag(pool, page); + if (page) + goto frag_reset; + } + + if (!page) { + page = page_pool_alloc_pages(pool, gfp); + if (unlikely(!page)) { + pool->frag_page = NULL; + return NULL; + } + + pool->frag_page = page; + +frag_reset: + pool->frag_users = 1; + *offset = 0; + pool->frag_offset = size; + page_pool_set_frag_count(page, BIAS_MAX); + return page; + } + + pool->frag_users++; + pool->frag_offset = *offset + size; + return page; +} +EXPORT_SYMBOL(page_pool_alloc_frag); + static void page_pool_empty_ring(struct page_pool *pool) { struct page *page; @@ -602,6 +705,8 @@ void page_pool_destroy(struct page_pool *pool) if (!page_pool_put(pool)) return; + page_pool_free_frag(pool); + if (!page_pool_release(pool)) return; @@ -634,7 +739,15 @@ bool page_pool_return_skb_page(struct page *page) struct page_pool *pp; page = compound_head(page); - if (unlikely(page->pp_magic != PP_SIGNATURE)) + + /* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation + * in order to preserve any existing bits, such as bit 0 for the + * head page of compound page and bit 1 for pfmemalloc page, so + * mask those bits for freeing side when doing below checking, + * and page_is_pfmemalloc() is checked in __page_pool_put_page() + * to avoid recycling the pfmemalloc page. + */ + if (unlikely((page->pp_magic & ~0x3UL) != PP_SIGNATURE)) return false; pp = page->pp; @@ -644,7 +757,6 @@ bool page_pool_return_skb_page(struct page *page) * The page will be returned to the pool here regardless of the * 'flipped' fragment being in use or not. */ - page->pp = NULL; page_pool_put_full_page(pp, page, false); return true; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 7e258d255e90..a3d74e2704c4 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -175,6 +175,9 @@ #define IP_NAME_SZ 32 #define MAX_MPLS_LABELS 16 /* This is the max label stack depth */ #define MPLS_STACK_BOTTOM htonl(0x00000100) +/* Max number of internet mix entries that can be specified in imix_weights. */ +#define MAX_IMIX_ENTRIES 20 +#define IMIX_PRECISION 100 /* Precision of IMIX distribution */ #define func_enter() pr_debug("entering %s\n", __func__); @@ -242,6 +245,12 @@ static char *pkt_flag_names[] = { #define VLAN_TAG_SIZE(x) ((x)->vlan_id == 0xffff ? 0 : 4) #define SVLAN_TAG_SIZE(x) ((x)->svlan_id == 0xffff ? 0 : 4) +struct imix_pkt { + u64 size; + u64 weight; + u64 count_so_far; +}; + struct flow_state { __be32 cur_daddr; int count; @@ -343,6 +352,12 @@ struct pktgen_dev { __u8 traffic_class; /* ditto for the (former) Traffic Class in IPv6 (see RFC 3260, sec. 4) */ + /* IMIX */ + unsigned int n_imix_entries; + struct imix_pkt imix_entries[MAX_IMIX_ENTRIES]; + /* Maps 0-IMIX_PRECISION range to imix_entry based on probability*/ + __u8 imix_distribution[IMIX_PRECISION]; + /* MPLS */ unsigned int nr_labels; /* Depth of stack, 0 = no MPLS */ __be32 labels[MAX_MPLS_LABELS]; @@ -471,6 +486,7 @@ static void pktgen_stop_all_threads(struct pktgen_net *pn); static void pktgen_stop(struct pktgen_thread *t); static void pktgen_clear_counters(struct pktgen_dev *pkt_dev); +static void fill_imix_distribution(struct pktgen_dev *pkt_dev); /* Module parameters, defaults. */ static int pg_count_d __read_mostly = 1000; @@ -552,6 +568,16 @@ static int pktgen_if_show(struct seq_file *seq, void *v) (unsigned long long)pkt_dev->count, pkt_dev->min_pkt_size, pkt_dev->max_pkt_size); + if (pkt_dev->n_imix_entries > 0) { + seq_puts(seq, " imix_weights: "); + for (i = 0; i < pkt_dev->n_imix_entries; i++) { + seq_printf(seq, "%llu,%llu ", + pkt_dev->imix_entries[i].size, + pkt_dev->imix_entries[i].weight); + } + seq_puts(seq, "\n"); + } + seq_printf(seq, " frags: %d delay: %llu clone_skb: %d ifname: %s\n", pkt_dev->nfrags, (unsigned long long) pkt_dev->delay, @@ -669,6 +695,18 @@ static int pktgen_if_show(struct seq_file *seq, void *v) (unsigned long long)pkt_dev->sofar, (unsigned long long)pkt_dev->errors); + if (pkt_dev->n_imix_entries > 0) { + int i; + + seq_puts(seq, " imix_size_counts: "); + for (i = 0; i < pkt_dev->n_imix_entries; i++) { + seq_printf(seq, "%llu,%llu ", + pkt_dev->imix_entries[i].size, + pkt_dev->imix_entries[i].count_so_far); + } + seq_puts(seq, "\n"); + } + seq_printf(seq, " started: %lluus stopped: %lluus idle: %lluus\n", (unsigned long long) ktime_to_us(pkt_dev->started_at), @@ -792,6 +830,62 @@ done_str: return i; } +/* Parses imix entries from user buffer. + * The user buffer should consist of imix entries separated by spaces + * where each entry consists of size and weight delimited by commas. + * "size1,weight_1 size2,weight_2 ... size_n,weight_n" for example. + */ +static ssize_t get_imix_entries(const char __user *buffer, + struct pktgen_dev *pkt_dev) +{ + const int max_digits = 10; + int i = 0; + long len; + char c; + + pkt_dev->n_imix_entries = 0; + + do { + unsigned long weight; + unsigned long size; + + len = num_arg(&buffer[i], max_digits, &size); + if (len < 0) + return len; + i += len; + if (get_user(c, &buffer[i])) + return -EFAULT; + /* Check for comma between size_i and weight_i */ + if (c != ',') + return -EINVAL; + i++; + + if (size < 14 + 20 + 8) + size = 14 + 20 + 8; + + len = num_arg(&buffer[i], max_digits, &weight); + if (len < 0) + return len; + if (weight <= 0) + return -EINVAL; + + pkt_dev->imix_entries[pkt_dev->n_imix_entries].size = size; + pkt_dev->imix_entries[pkt_dev->n_imix_entries].weight = weight; + + i += len; + if (get_user(c, &buffer[i])) + return -EFAULT; + + i++; + pkt_dev->n_imix_entries++; + + if (pkt_dev->n_imix_entries > MAX_IMIX_ENTRIES) + return -E2BIG; + } while (c == ' '); + + return i; +} + static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev) { unsigned int n = 0; @@ -960,6 +1054,20 @@ static ssize_t pktgen_if_write(struct file *file, return count; } + if (!strcmp(name, "imix_weights")) { + if (pkt_dev->clone_skb > 0) + return -EINVAL; + + len = get_imix_entries(&user_buffer[i], pkt_dev); + if (len < 0) + return len; + + fill_imix_distribution(pkt_dev); + + i += len; + return count; + } + if (!strcmp(name, "debug")) { len = num_arg(&user_buffer[i], 10, &value); if (len < 0) @@ -1082,10 +1190,16 @@ static ssize_t pktgen_if_write(struct file *file, len = num_arg(&user_buffer[i], 10, &value); if (len < 0) return len; + /* clone_skb is not supported for netif_receive xmit_mode and + * IMIX mode. + */ if ((value > 0) && ((pkt_dev->xmit_mode == M_NETIF_RECEIVE) || !(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING))) return -ENOTSUPP; + if (value > 0 && pkt_dev->n_imix_entries > 0) + return -EINVAL; + i += len; pkt_dev->clone_skb = value; @@ -1190,11 +1304,6 @@ static ssize_t pktgen_if_write(struct file *file, * pktgen_xmit() is called */ pkt_dev->last_ok = 1; - - /* override clone_skb if user passed default value - * at module loading time - */ - pkt_dev->clone_skb = 0; } else if (strcmp(f, "queue_xmit") == 0) { pkt_dev->xmit_mode = M_QUEUE_XMIT; pkt_dev->last_ok = 1; @@ -2477,6 +2586,14 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) t = pkt_dev->min_pkt_size; } pkt_dev->cur_pkt_size = t; + } else if (pkt_dev->n_imix_entries > 0) { + struct imix_pkt *entry; + __u32 t = prandom_u32() % IMIX_PRECISION; + __u8 entry_index = pkt_dev->imix_distribution[t]; + + entry = &pkt_dev->imix_entries[entry_index]; + entry->count_so_far++; + pkt_dev->cur_pkt_size = entry->size; } set_cur_queue_map(pkt_dev); @@ -2484,6 +2601,32 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) pkt_dev->flows[flow].count++; } +static void fill_imix_distribution(struct pktgen_dev *pkt_dev) +{ + int cumulative_probabilites[MAX_IMIX_ENTRIES]; + int j = 0; + __u64 cumulative_prob = 0; + __u64 total_weight = 0; + int i = 0; + + for (i = 0; i < pkt_dev->n_imix_entries; i++) + total_weight += pkt_dev->imix_entries[i].weight; + + /* Fill cumulative_probabilites with sum of normalized probabilities */ + for (i = 0; i < pkt_dev->n_imix_entries - 1; i++) { + cumulative_prob += div64_u64(pkt_dev->imix_entries[i].weight * + IMIX_PRECISION, + total_weight); + cumulative_probabilites[i] = cumulative_prob; + } + cumulative_probabilites[pkt_dev->n_imix_entries - 1] = 100; + + for (i = 0; i < IMIX_PRECISION; i++) { + if (i == cumulative_probabilites[j]) + j++; + pkt_dev->imix_distribution[i] = j; + } +} #ifdef CONFIG_XFRM static u32 pktgen_dst_metrics[RTAX_MAX + 1] = { @@ -3145,7 +3288,19 @@ static void show_results(struct pktgen_dev *pkt_dev, int nr_frags) pps = div64_u64(pkt_dev->sofar * NSEC_PER_SEC, ktime_to_ns(elapsed)); - bps = pps * 8 * pkt_dev->cur_pkt_size; + if (pkt_dev->n_imix_entries > 0) { + int i; + struct imix_pkt *entry; + + bps = 0; + for (i = 0; i < pkt_dev->n_imix_entries; i++) { + entry = &pkt_dev->imix_entries[i]; + bps += entry->size * entry->count_so_far; + } + bps = div64_u64(bps * 8 * NSEC_PER_SEC, ktime_to_ns(elapsed)); + } else { + bps = pps * 8 * pkt_dev->cur_pkt_size; + } mbps = bps; do_div(mbps, 1000000); @@ -3447,7 +3602,6 @@ out: static int pktgen_thread_worker(void *arg) { - DEFINE_WAIT(wait); struct pktgen_thread *t = arg; struct pktgen_dev *pkt_dev = NULL; int cpu = t->cpu; diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c index e33fde06d528..dd4cf01d1e0a 100644 --- a/net/core/ptp_classifier.c +++ b/net/core/ptp_classifier.c @@ -103,7 +103,7 @@ static struct bpf_prog *ptp_insns __read_mostly; unsigned int ptp_classify_raw(const struct sk_buff *skb) { - return BPF_PROG_RUN(ptp_insns, skb); + return bpf_prog_run(ptp_insns, skb); } EXPORT_SYMBOL_GPL(ptp_classify_raw); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index f6af3e74fc44..972c8cb303a5 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -710,15 +710,8 @@ out: int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned int group, int echo) { struct sock *rtnl = net->rtnl; - int err = 0; - NETLINK_CB(skb).dst_group = group; - if (echo) - refcount_inc(&skb->users); - netlink_broadcast(rtnl, skb, pid, group, GFP_KERNEL); - if (echo) - err = netlink_unicast(rtnl, skb, pid, MSG_DONTWAIT); - return err; + return nlmsg_notify(rtnl, skb, pid, group, echo, GFP_KERNEL); } int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid) @@ -733,12 +726,8 @@ void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group, struct nlmsghdr *nlh, gfp_t flags) { struct sock *rtnl = net->rtnl; - int report = 0; - if (nlh) - report = nlmsg_report(nlh); - - nlmsg_notify(rtnl, skb, pid, group, report, flags); + nlmsg_notify(rtnl, skb, pid, group, nlmsg_report(nlh), flags); } EXPORT_SYMBOL(rtnl_notify); @@ -1970,6 +1959,13 @@ static bool link_master_filtered(struct net_device *dev, int master_idx) return false; master = netdev_master_upper_dev_get(dev); + + /* 0 is already used to denote IFLA_MASTER wasn't passed, therefore need + * another invalid value for ifindex to denote "no master". + */ + if (master_idx == -1) + return !!master; + if (!master || master->ifindex != master_idx) return true; @@ -2268,7 +2264,8 @@ invalid_attr: return -EINVAL; } -static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) +static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[], + struct netlink_ext_ack *extack) { if (dev) { if (tb[IFLA_ADDRESS] && @@ -2295,7 +2292,7 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) return -EOPNOTSUPP; if (af_ops->validate_link_af) { - err = af_ops->validate_link_af(dev, af); + err = af_ops->validate_link_af(dev, af, extack); if (err < 0) return err; } @@ -2603,11 +2600,12 @@ static int do_setlink(const struct sk_buff *skb, const struct net_device_ops *ops = dev->netdev_ops; int err; - err = validate_linkmsg(dev, tb); + err = validate_linkmsg(dev, tb, extack); if (err < 0) return err; if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD] || tb[IFLA_TARGET_NETNSID]) { + const char *pat = ifname && ifname[0] ? ifname : NULL; struct net *net; int new_ifindex; @@ -2623,7 +2621,7 @@ static int do_setlink(const struct sk_buff *skb, else new_ifindex = 0; - err = __dev_change_net_namespace(dev, net, ifname, new_ifindex); + err = __dev_change_net_namespace(dev, net, pat, new_ifindex); put_net(net); if (err) goto errout; @@ -3301,7 +3299,7 @@ replay: m_ops = master_dev->rtnl_link_ops; } - err = validate_linkmsg(dev, tb); + err = validate_linkmsg(dev, tb, extack); if (err < 0) return err; diff --git a/net/core/scm.c b/net/core/scm.c index ae3085d9aae8..5c356f0dee30 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -79,7 +79,7 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) if (!fpl) { - fpl = kmalloc(sizeof(struct scm_fp_list), GFP_KERNEL); + fpl = kmalloc(sizeof(struct scm_fp_list), GFP_KERNEL_ACCOUNT); if (!fpl) return -ENOMEM; *fplp = fpl; @@ -355,7 +355,7 @@ struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl) return NULL; new_fpl = kmemdup(fpl, offsetof(struct scm_fp_list, fp[fpl->count]), - GFP_KERNEL); + GFP_KERNEL_ACCOUNT); if (new_fpl) { for (i = 0; i < fpl->count; i++) get_file(fpl->fp[i]); diff --git a/net/core/selftests.c b/net/core/selftests.c index ba7b0171974c..9077fa969892 100644 --- a/net/core/selftests.c +++ b/net/core/selftests.c @@ -318,6 +318,15 @@ static int net_test_phy_loopback_udp(struct net_device *ndev) return __net_test_loopback(ndev, &attr); } +static int net_test_phy_loopback_udp_mtu(struct net_device *ndev) +{ + struct net_packet_attrs attr = { }; + + attr.dst = ndev->dev_addr; + attr.max_size = ndev->mtu; + return __net_test_loopback(ndev, &attr); +} + static int net_test_phy_loopback_tcp(struct net_device *ndev) { struct net_packet_attrs attr = { }; @@ -345,6 +354,9 @@ static const struct net_test { .name = "PHY internal loopback, UDP ", .fn = net_test_phy_loopback_udp, }, { + .name = "PHY internal loopback, MTU ", + .fn = net_test_phy_loopback_udp_mtu, + }, { .name = "PHY internal loopback, TCP ", .fn = net_test_phy_loopback_tcp, }, { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index fc7942c0dddc..2170bea2c7de 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -156,7 +156,7 @@ void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) void *data; fragsz = SKB_DATA_ALIGN(fragsz); - if (in_irq() || irqs_disabled()) { + if (in_hardirq() || irqs_disabled()) { nc = this_cpu_ptr(&netdev_alloc_cache); data = page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, align_mask); } else { @@ -502,7 +502,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; - if (in_irq() || irqs_disabled()) { + if (in_hardirq() || irqs_disabled()) { nc = this_cpu_ptr(&netdev_alloc_cache); data = page_frag_alloc(nc, len, gfp_mask); pfmemalloc = nc->pfmemalloc; @@ -724,7 +724,7 @@ void skb_release_head_state(struct sk_buff *skb) { skb_dst_drop(skb); if (skb->destructor) { - WARN_ON(in_irq()); + WARN_ON(in_hardirq()); skb->destructor(skb); } #if IS_ENABLED(CONFIG_NF_CONNTRACK) @@ -954,9 +954,13 @@ void __kfree_skb_defer(struct sk_buff *skb) void napi_skb_free_stolen_head(struct sk_buff *skb) { - nf_reset_ct(skb); - skb_dst_drop(skb); - skb_ext_put(skb); + if (unlikely(skb->slow_gro)) { + nf_reset_ct(skb); + skb_dst_drop(skb); + skb_ext_put(skb); + skb_orphan(skb); + skb->slow_gro = 0; + } napi_skb_cache_put(skb); } @@ -1786,6 +1790,48 @@ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom) EXPORT_SYMBOL(skb_realloc_headroom); /** + * skb_expand_head - reallocate header of &sk_buff + * @skb: buffer to reallocate + * @headroom: needed headroom + * + * Unlike skb_realloc_headroom, this one does not allocate a new skb + * if possible; copies skb->sk to new skb as needed + * and frees original skb in case of failures. + * + * It expect increased headroom and generates warning otherwise. + */ + +struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom) +{ + int delta = headroom - skb_headroom(skb); + + if (WARN_ONCE(delta <= 0, + "%s is expecting an increase in the headroom", __func__)) + return skb; + + /* pskb_expand_head() might crash, if skb is shared */ + if (skb_shared(skb)) { + struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); + + if (likely(nskb)) { + if (skb->sk) + skb_set_owner_w(nskb, skb->sk); + consume_skb(skb); + } else { + kfree_skb(skb); + } + skb = nskb; + } + if (skb && + pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) { + kfree_skb(skb); + skb = NULL; + } + return skb; +} +EXPORT_SYMBOL(skb_expand_head); + +/** * skb_copy_expand - copy and expand sk_buff * @skb: buffer to copy * @newheadroom: new free bytes at head @@ -3838,7 +3884,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, skb_push(nskb, -skb_network_offset(nskb) + offset); skb_release_head_state(nskb); - __copy_skb_header(nskb, skb); + __copy_skb_header(nskb, skb); skb_headers_offset_update(nskb, skb_headroom(nskb) - skb_headroom(skb)); skb_copy_from_linear_data_offset(skb, -tnl_hlen, @@ -3889,6 +3935,9 @@ int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) NAPI_GRO_CB(p)->last = skb; NAPI_GRO_CB(p)->count++; p->data_len += skb->len; + + /* sk owenrship - if any - completely transferred to the aggregated packet */ + skb->destructor = NULL; p->truesize += skb->truesize; p->len += skb->len; @@ -4256,6 +4305,7 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) unsigned int headlen = skb_headlen(skb); unsigned int len = skb_gro_len(skb); unsigned int delta_truesize; + unsigned int new_truesize; struct sk_buff *lp; if (unlikely(p->len + len >= 65536 || NAPI_GRO_CB(skb)->flush)) @@ -4287,10 +4337,10 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) skb_frag_size_sub(frag, offset); /* all fragments truesize : remove (head size + sk_buff) */ - delta_truesize = skb->truesize - - SKB_TRUESIZE(skb_end_offset(skb)); + new_truesize = SKB_TRUESIZE(skb_end_offset(skb)); + delta_truesize = skb->truesize - new_truesize; - skb->truesize -= skb->data_len; + skb->truesize = new_truesize; skb->len -= skb->data_len; skb->data_len = 0; @@ -4319,12 +4369,16 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags); /* We dont need to clear skbinfo->nr_frags here */ - delta_truesize = skb->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff)); + new_truesize = SKB_DATA_ALIGN(sizeof(struct sk_buff)); + delta_truesize = skb->truesize - new_truesize; + skb->truesize = new_truesize; NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD; goto done; } merge: + /* sk owenrship - if any - completely transferred to the aggregated packet */ + skb->destructor = NULL; delta_truesize = skb->truesize; if (offset > headlen) { unsigned int eat = offset - headlen; @@ -6449,6 +6503,7 @@ void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id) new->chunks = newlen; new->offset[id] = newoff; set_active: + skb->slow_gro = 1; skb->extensions = new; skb->active_extensions |= 1 << id; return skb_ext_get_ptr(new, id); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 15d71288e741..2d6249b28928 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -584,29 +584,42 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, return sk_psock_skb_ingress(psock, skb); } -static void sock_drop(struct sock *sk, struct sk_buff *skb) +static void sk_psock_skb_state(struct sk_psock *psock, + struct sk_psock_work_state *state, + struct sk_buff *skb, + int len, int off) { - sk_drops_add(sk, skb); - kfree_skb(skb); + spin_lock_bh(&psock->ingress_lock); + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { + state->skb = skb; + state->len = len; + state->off = off; + } else { + sock_drop(psock->sk, skb); + } + spin_unlock_bh(&psock->ingress_lock); } static void sk_psock_backlog(struct work_struct *work) { struct sk_psock *psock = container_of(work, struct sk_psock, work); struct sk_psock_work_state *state = &psock->work_state; - struct sk_buff *skb; + struct sk_buff *skb = NULL; bool ingress; u32 len, off; int ret; mutex_lock(&psock->work_mutex); - if (state->skb) { + if (unlikely(state->skb)) { + spin_lock_bh(&psock->ingress_lock); skb = state->skb; len = state->len; off = state->off; state->skb = NULL; - goto start; + spin_unlock_bh(&psock->ingress_lock); } + if (skb) + goto start; while ((skb = skb_dequeue(&psock->ingress_skb))) { len = skb->len; @@ -621,9 +634,8 @@ start: len, ingress); if (ret <= 0) { if (ret == -EAGAIN) { - state->skb = skb; - state->len = len; - state->off = off; + sk_psock_skb_state(psock, state, skb, + len, off); goto end; } /* Hard errors break pipe and stop xmit. */ @@ -722,6 +734,11 @@ static void __sk_psock_zap_ingress(struct sk_psock *psock) skb_bpf_redirect_clear(skb); sock_drop(psock->sk, skb); } + kfree_skb(psock->work_state.skb); + /* We null the skb here to ensure that calls to sk_psock_backlog + * do not pick up the free'd skb. + */ + psock->work_state.skb = NULL; __sk_psock_purge_ingress_msg(psock); } @@ -773,8 +790,6 @@ static void sk_psock_destroy(struct work_struct *work) void sk_psock_drop(struct sock *sk, struct sk_psock *psock) { - sk_psock_stop(psock, false); - write_lock_bh(&sk->sk_callback_lock); sk_psock_restore_proto(sk, psock); rcu_assign_sk_user_data(sk, NULL); @@ -784,6 +799,8 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock) sk_psock_stop_verdict(sk, psock); write_unlock_bh(&sk->sk_callback_lock); + sk_psock_stop(psock, false); + INIT_RCU_WORK(&psock->rwork, sk_psock_destroy); queue_rcu_work(system_wq, &psock->rwork); } diff --git a/net/core/sock.c b/net/core/sock.c index a3eea6e0b30a..62627e868e03 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -226,6 +226,7 @@ static struct lock_class_key af_family_kern_slock_keys[AF_MAX]; x "AF_IEEE802154", x "AF_CAIF" , x "AF_ALG" , \ x "AF_NFC" , x "AF_VSOCK" , x "AF_KCM" , \ x "AF_QIPCRTR", x "AF_SMC" , x "AF_XDP" , \ + x "AF_MCTP" , \ x "AF_MAX" static const char *const af_family_key_strings[AF_MAX+1] = { @@ -1357,6 +1358,15 @@ set_sndbuf: ret = sock_bindtoindex_locked(sk, val); break; + case SO_BUF_LOCK: + if (val & ~SOCK_BUF_LOCK_MASK) { + ret = -EINVAL; + break; + } + sk->sk_userlocks = val | (sk->sk_userlocks & + ~SOCK_BUF_LOCK_MASK); + break; + default: ret = -ENOPROTOOPT; break; @@ -1719,6 +1729,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val64 = sock_net(sk)->net_cookie; break; + case SO_BUF_LOCK: + v.val = sk->sk_userlocks & SOCK_BUF_LOCK_MASK; + break; + default: /* We implement the SO_SNDLOWAT etc to not be settable * (1003.1g 7). @@ -2560,7 +2574,6 @@ static void sk_leave_memory_pressure(struct sock *sk) } } -#define SKB_FRAG_PAGE_ORDER get_order(32768) DEFINE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key); /** @@ -2714,10 +2727,12 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) { struct proto *prot = sk->sk_prot; long allocated = sk_memory_allocated_add(sk, amt); + bool memcg_charge = mem_cgroup_sockets_enabled && sk->sk_memcg; bool charged = true; - if (mem_cgroup_sockets_enabled && sk->sk_memcg && - !(charged = mem_cgroup_charge_skmem(sk->sk_memcg, amt))) + if (memcg_charge && + !(charged = mem_cgroup_charge_skmem(sk->sk_memcg, amt, + gfp_memcg_charge()))) goto suppress_allocation; /* Under limit. */ @@ -2771,8 +2786,14 @@ suppress_allocation: /* Fail only if socket is _under_ its sndbuf. * In this case we cannot block, so that we have to fail. */ - if (sk->sk_wmem_queued + size >= sk->sk_sndbuf) + if (sk->sk_wmem_queued + size >= sk->sk_sndbuf) { + /* Force charge with __GFP_NOFAIL */ + if (memcg_charge && !charged) { + mem_cgroup_charge_skmem(sk->sk_memcg, amt, + gfp_memcg_charge() | __GFP_NOFAIL); + } return 1; + } } if (kind == SK_MEM_SEND || (kind == SK_MEM_RECV && charged)) @@ -2780,7 +2801,7 @@ suppress_allocation: sk_memory_allocated_sub(sk, amt); - if (mem_cgroup_sockets_enabled && sk->sk_memcg) + if (memcg_charge && charged) mem_cgroup_uncharge_skmem(sk->sk_memcg, amt); return 0; diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 60decd6420ca..e252b8ec2b85 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -211,8 +211,6 @@ out: return psock; } -static bool sock_map_redirect_allowed(const struct sock *sk); - static int sock_map_link(struct bpf_map *map, struct sock *sk) { struct sk_psock_progs *progs = sock_map_progs(map); @@ -223,13 +221,6 @@ static int sock_map_link(struct bpf_map *map, struct sock *sk) struct sk_psock *psock; int ret; - /* Only sockets we can redirect into/from in BPF need to hold - * refs to parser/verdict progs and have their sk_data_ready - * and sk_write_space callbacks overridden. - */ - if (!sock_map_redirect_allowed(sk)) - goto no_progs; - stream_verdict = READ_ONCE(progs->stream_verdict); if (stream_verdict) { stream_verdict = bpf_prog_inc_not_zero(stream_verdict); @@ -264,7 +255,6 @@ static int sock_map_link(struct bpf_map *map, struct sock *sk) } } -no_progs: psock = sock_map_psock_get_checked(sk); if (IS_ERR(psock)) { ret = PTR_ERR(psock); @@ -527,12 +517,6 @@ static bool sk_is_tcp(const struct sock *sk) sk->sk_protocol == IPPROTO_TCP; } -static bool sk_is_udp(const struct sock *sk) -{ - return sk->sk_type == SOCK_DGRAM && - sk->sk_protocol == IPPROTO_UDP; -} - static bool sock_map_redirect_allowed(const struct sock *sk) { if (sk_is_tcp(sk)) @@ -550,10 +534,7 @@ static bool sock_map_sk_state_allowed(const struct sock *sk) { if (sk_is_tcp(sk)) return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN); - else if (sk_is_udp(sk)) - return sk_hashed(sk); - - return false; + return true; } static int sock_hash_update_common(struct bpf_map *map, void *key, @@ -1513,6 +1494,7 @@ void sock_map_unhash(struct sock *sk) rcu_read_unlock(); saved_unhash(sk); } +EXPORT_SYMBOL_GPL(sock_map_unhash); void sock_map_close(struct sock *sk, long timeout) { @@ -1536,6 +1518,7 @@ void sock_map_close(struct sock *sk, long timeout) release_sock(sk); saved_close(sk, timeout); } +EXPORT_SYMBOL_GPL(sock_map_close); static int sock_map_iter_attach_target(struct bpf_prog *prog, union bpf_iter_link_info *linfo, diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 9cc9d1ee6cdb..c5c1d2b8045e 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -41,9 +41,9 @@ extern bool dccp_debug; #define dccp_pr_debug_cat(format, a...) DCCP_PRINTK(dccp_debug, format, ##a) #define dccp_debug(fmt, a...) dccp_pr_debug_cat(KERN_DEBUG fmt, ##a) #else -#define dccp_pr_debug(format, a...) -#define dccp_pr_debug_cat(format, a...) -#define dccp_debug(format, a...) +#define dccp_pr_debug(format, a...) do {} while (0) +#define dccp_pr_debug_cat(format, a...) do {} while (0) +#define dccp_debug(format, a...) do {} while (0) #endif extern struct inet_hashinfo dccp_hashinfo; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 7eb0fb231940..abb5c596a817 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -1126,7 +1126,7 @@ static int __init dccp_init(void) dccp_hashinfo.bind_bucket_cachep = kmem_cache_create("dccp_bind_bucket", sizeof(struct inet_bind_bucket), 0, - SLAB_HWCACHE_ALIGN, NULL); + SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); if (!dccp_hashinfo.bind_bucket_cachep) goto out_free_hashinfo2; diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index d1c50a48614b..0ee7d4c0c955 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -521,8 +521,7 @@ int dn_dev_set_default(struct net_device *dev, int force) } spin_unlock(&dndev_lock); - if (old) - dev_put(old); + dev_put(old); return rv; } @@ -536,8 +535,7 @@ static void dn_dev_check_default(struct net_device *dev) } spin_unlock(&dndev_lock); - if (dev) - dev_put(dev); + dev_put(dev); } /* diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index 77fbf8e9df4b..269c029ad74f 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -92,8 +92,7 @@ void dn_fib_free_info(struct dn_fib_info *fi) } change_nexthops(fi) { - if (nh->nh_dev) - dev_put(nh->nh_dev); + dev_put(nh->nh_dev); nh->nh_dev = NULL; } endfor_nexthops(fi); kfree(fi); @@ -102,7 +101,7 @@ void dn_fib_free_info(struct dn_fib_info *fi) void dn_fib_release_info(struct dn_fib_info *fi) { spin_lock(&dn_fib_info_lock); - if (fi && --fi->fib_treeref == 0) { + if (fi && refcount_dec_and_test(&fi->fib_treeref)) { if (fi->fib_next) fi->fib_next->fib_prev = fi->fib_prev; if (fi->fib_prev) @@ -385,11 +384,11 @@ link_it: if ((ofi = dn_fib_find_info(fi)) != NULL) { fi->fib_dead = 1; dn_fib_free_info(fi); - ofi->fib_treeref++; + refcount_inc(&ofi->fib_treeref); return ofi; } - fi->fib_treeref++; + refcount_set(&fi->fib_treeref, 1); refcount_set(&fi->fib_clntref, 1); spin_lock(&dn_fib_info_lock); fi->fib_next = dn_fib_info_list; diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 729d3de6020d..7e85f2a1ae25 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1026,8 +1026,7 @@ source_ok: if (!fld.daddr) { fld.daddr = fld.saddr; - if (dev_out) - dev_put(dev_out); + dev_put(dev_out); err = -EINVAL; dev_out = init_net.loopback_dev; if (!dev_out->dn_ptr) @@ -1084,8 +1083,7 @@ source_ok: neigh_release(neigh); neigh = NULL; } else { - if (dev_out) - dev_put(dev_out); + dev_put(dev_out); if (dn_dev_islocal(neigh->dev, fld.daddr)) { dev_out = init_net.loopback_dev; res.type = RTN_LOCAL; @@ -1144,8 +1142,7 @@ select_source: if (res.type == RTN_LOCAL) { if (!fld.saddr) fld.saddr = fld.daddr; - if (dev_out) - dev_put(dev_out); + dev_put(dev_out); dev_out = init_net.loopback_dev; dev_hold(dev_out); if (!dev_out->dn_ptr) @@ -1168,8 +1165,7 @@ select_source: if (!fld.saddr) fld.saddr = DN_FIB_RES_PREFSRC(res); - if (dev_out) - dev_put(dev_out); + dev_put(dev_out); dev_out = DN_FIB_RES_DEV(res); dev_hold(dev_out); fld.flowidn_oif = dev_out->ifindex; @@ -1222,8 +1218,7 @@ done: neigh_release(neigh); if (free_res) dn_fib_res_put(&res); - if (dev_out) - dev_put(dev_out); + dev_put(dev_out); out: return err; @@ -1503,8 +1498,7 @@ done: if (free_res) dn_fib_res_put(&res); dev_put(in_dev); - if (out_dev) - dev_put(out_dev); + dev_put(out_dev); out: return err; diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 00bb89b2d86f..548285539752 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -18,16 +18,6 @@ if NET_DSA # Drivers must select the appropriate tagging format(s) -config NET_DSA_TAG_8021Q - tristate - select VLAN_8021Q - help - Unlike the other tagging protocols, the 802.1Q config option simply - provides helpers for other tagging implementations that might rely on - VLAN in one way or another. It is not a complete solution. - - Drivers which use these helpers should select this as dependency. - config NET_DSA_TAG_AR9331 tristate "Tag driver for Atheros AR9331 SoC with built-in switch" help @@ -126,7 +116,6 @@ config NET_DSA_TAG_OCELOT_8021Q tristate "Tag driver for Ocelot family of switches, using VLAN" depends on MSCC_OCELOT_SWITCH_LIB || \ (MSCC_OCELOT_SWITCH_LIB=n && COMPILE_TEST) - select NET_DSA_TAG_8021Q help Say Y or M if you want to enable support for tagging frames with a custom VLAN-based header. Frames that require timestamping, such as @@ -149,7 +138,7 @@ config NET_DSA_TAG_LAN9303 config NET_DSA_TAG_SJA1105 tristate "Tag driver for NXP SJA1105 switches" - select NET_DSA_TAG_8021Q + depends on NET_DSA_SJA1105 || !NET_DSA_SJA1105 select PACKING help Say Y or M if you want to enable support for tagging frames with the diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 44bc79952b8b..67ea009f242c 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -1,10 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 # the core obj-$(CONFIG_NET_DSA) += dsa_core.o -dsa_core-y += dsa.o dsa2.o master.o port.o slave.o switch.o +dsa_core-y += dsa.o dsa2.o master.o port.o slave.o switch.o tag_8021q.o # tagging formats -obj-$(CONFIG_NET_DSA_TAG_8021Q) += tag_8021q.o obj-$(CONFIG_NET_DSA_TAG_AR9331) += tag_ar9331.o obj-$(CONFIG_NET_DSA_TAG_BRCM_COMMON) += tag_brcm.o obj-$(CONFIG_NET_DSA_TAG_DSA_COMMON) += tag_dsa.o diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 84cad1be9ce4..1dc45e40f961 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -238,7 +238,7 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, if (!skb) return 0; - nskb = cpu_dp->rcv(skb, dev, pt); + nskb = cpu_dp->rcv(skb, dev); if (!nskb) { kfree_skb(skb); return 0; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 185629f27f80..1b2b25d7bd02 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -21,6 +21,9 @@ static DEFINE_MUTEX(dsa2_mutex); LIST_HEAD(dsa_tree_list); +/* Track the bridges with forwarding offload enabled */ +static unsigned long dsa_fwd_offloading_bridges; + /** * dsa_tree_notify - Execute code for all switches in a DSA switch tree. * @dst: collection of struct dsa_switch devices to notify. @@ -49,6 +52,9 @@ int dsa_tree_notify(struct dsa_switch_tree *dst, unsigned long e, void *v) * Can be used to notify the switching fabric of events such as cross-chip * bridging between disjoint trees (such as islands of tagger-compatible * switches bridged by an incompatible middle switch). + * + * WARNING: this function is not reliable during probe time, because probing + * between trees is asynchronous and not all DSA trees might have probed. */ int dsa_broadcast(unsigned long e, void *v) { @@ -123,6 +129,51 @@ void dsa_lag_unmap(struct dsa_switch_tree *dst, struct net_device *lag) } } +static int dsa_bridge_num_find(const struct net_device *bridge_dev) +{ + struct dsa_switch_tree *dst; + struct dsa_port *dp; + + /* When preparing the offload for a port, it will have a valid + * dp->bridge_dev pointer but a not yet valid dp->bridge_num. + * However there might be other ports having the same dp->bridge_dev + * and a valid dp->bridge_num, so just ignore this port. + */ + list_for_each_entry(dst, &dsa_tree_list, list) + list_for_each_entry(dp, &dst->ports, list) + if (dp->bridge_dev == bridge_dev && + dp->bridge_num != -1) + return dp->bridge_num; + + return -1; +} + +int dsa_bridge_num_get(const struct net_device *bridge_dev, int max) +{ + int bridge_num = dsa_bridge_num_find(bridge_dev); + + if (bridge_num < 0) { + /* First port that offloads TX forwarding for this bridge */ + bridge_num = find_first_zero_bit(&dsa_fwd_offloading_bridges, + DSA_MAX_NUM_OFFLOADING_BRIDGES); + if (bridge_num >= max) + return -1; + + set_bit(bridge_num, &dsa_fwd_offloading_bridges); + } + + return bridge_num; +} + +void dsa_bridge_num_put(const struct net_device *bridge_dev, int bridge_num) +{ + /* Check if the bridge is still in use, otherwise it is time + * to clean it up so we can reuse this bridge_num later. + */ + if (!dsa_bridge_num_find(bridge_dev)) + clear_bit(bridge_num, &dsa_fwd_offloading_bridges); +} + struct dsa_switch *dsa_switch_find(int tree_index, int sw_index) { struct dsa_switch_tree *dst; @@ -311,6 +362,9 @@ static struct dsa_port *dsa_tree_find_first_cpu(struct dsa_switch_tree *dst) return NULL; } +/* Assign the default CPU port (the first one in the tree) to all ports of the + * fabric which don't already have one as part of their own switch. + */ static int dsa_tree_setup_default_cpu(struct dsa_switch_tree *dst) { struct dsa_port *cpu_dp, *dp; @@ -321,15 +375,48 @@ static int dsa_tree_setup_default_cpu(struct dsa_switch_tree *dst) return -EINVAL; } - /* Assign the default CPU port to all ports of the fabric */ - list_for_each_entry(dp, &dst->ports, list) + list_for_each_entry(dp, &dst->ports, list) { + if (dp->cpu_dp) + continue; + if (dsa_port_is_user(dp) || dsa_port_is_dsa(dp)) dp->cpu_dp = cpu_dp; + } return 0; } -static void dsa_tree_teardown_default_cpu(struct dsa_switch_tree *dst) +/* Perform initial assignment of CPU ports to user ports and DSA links in the + * fabric, giving preference to CPU ports local to each switch. Default to + * using the first CPU port in the switch tree if the port does not have a CPU + * port local to this switch. + */ +static int dsa_tree_setup_cpu_ports(struct dsa_switch_tree *dst) +{ + struct dsa_port *cpu_dp, *dp; + + list_for_each_entry(cpu_dp, &dst->ports, list) { + if (!dsa_port_is_cpu(cpu_dp)) + continue; + + list_for_each_entry(dp, &dst->ports, list) { + /* Prefer a local CPU port */ + if (dp->ds != cpu_dp->ds) + continue; + + /* Prefer the first local CPU port found */ + if (dp->cpu_dp) + continue; + + if (dsa_port_is_user(dp) || dsa_port_is_dsa(dp)) + dp->cpu_dp = cpu_dp; + } + } + + return dsa_tree_setup_default_cpu(dst); +} + +static void dsa_tree_teardown_cpu_ports(struct dsa_switch_tree *dst) { struct dsa_port *dp; @@ -710,13 +797,14 @@ static int dsa_switch_setup(struct dsa_switch *ds) /* Add the switch to devlink before calling setup, so that setup can * add dpipe tables */ - ds->devlink = devlink_alloc(&dsa_devlink_ops, sizeof(*dl_priv)); + ds->devlink = + devlink_alloc(&dsa_devlink_ops, sizeof(*dl_priv), ds->dev); if (!ds->devlink) return -ENOMEM; dl_priv = devlink_priv(ds->devlink); dl_priv->ds = ds; - err = devlink_register(ds->devlink, ds->dev); + err = devlink_register(ds->devlink); if (err) goto free_devlink; @@ -921,13 +1009,13 @@ static int dsa_tree_setup(struct dsa_switch_tree *dst) if (!complete) return 0; - err = dsa_tree_setup_default_cpu(dst); + err = dsa_tree_setup_cpu_ports(dst); if (err) return err; err = dsa_tree_setup_switches(dst); if (err) - goto teardown_default_cpu; + goto teardown_cpu_ports; err = dsa_tree_setup_master(dst); if (err) @@ -947,8 +1035,8 @@ teardown_master: dsa_tree_teardown_master(dst); teardown_switches: dsa_tree_teardown_switches(dst); -teardown_default_cpu: - dsa_tree_teardown_default_cpu(dst); +teardown_cpu_ports: + dsa_tree_teardown_cpu_ports(dst); return err; } @@ -966,7 +1054,7 @@ static void dsa_tree_teardown(struct dsa_switch_tree *dst) dsa_tree_teardown_switches(dst); - dsa_tree_teardown_default_cpu(dst); + dsa_tree_teardown_cpu_ports(dst); list_for_each_entry_safe(dl, next, &dst->rtable, list) { list_del(&dl->list); @@ -1044,6 +1132,7 @@ static struct dsa_port *dsa_port_touch(struct dsa_switch *ds, int index) dp->ds = ds; dp->index = index; + dp->bridge_num = -1; INIT_LIST_HEAD(&dp->list); list_add_tail(&dp->list, &dst->ports); @@ -1265,6 +1354,9 @@ static int dsa_switch_parse_member_of(struct dsa_switch *ds, return -EEXIST; } + if (ds->dst->last_switch < ds->index) + ds->dst->last_switch = ds->index; + return 0; } diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index f201c33980bf..33ab7d7af9eb 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -14,6 +14,8 @@ #include <net/dsa.h> #include <net/gro_cells.h> +#define DSA_MAX_NUM_OFFLOADING_BRIDGES BITS_PER_LONG + enum { DSA_NOTIFIER_AGEING_TIME, DSA_NOTIFIER_BRIDGE_JOIN, @@ -39,6 +41,8 @@ enum { DSA_NOTIFIER_MRP_DEL, DSA_NOTIFIER_MRP_ADD_RING_ROLE, DSA_NOTIFIER_MRP_DEL_RING_ROLE, + DSA_NOTIFIER_TAG_8021Q_VLAN_ADD, + DSA_NOTIFIER_TAG_8021Q_VLAN_DEL, }; /* DSA_NOTIFIER_AGEING_TIME */ @@ -113,6 +117,14 @@ struct dsa_notifier_mrp_ring_role_info { int port; }; +/* DSA_NOTIFIER_TAG_8021Q_VLAN_* */ +struct dsa_notifier_tag_8021q_vlan_info { + int tree_index; + int sw_index; + int port; + u16 vid; +}; + struct dsa_switchdev_event_work { struct dsa_switch *ds; int port; @@ -187,23 +199,21 @@ static inline struct net_device *dsa_master_find_slave(struct net_device *dev, /* port.c */ void dsa_port_set_tag_protocol(struct dsa_port *cpu_dp, const struct dsa_device_ops *tag_ops); -int dsa_port_set_state(struct dsa_port *dp, u8 state); +int dsa_port_set_state(struct dsa_port *dp, u8 state, bool do_fast_age); int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy); int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy); void dsa_port_disable_rt(struct dsa_port *dp); void dsa_port_disable(struct dsa_port *dp); int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, struct netlink_ext_ack *extack); -int dsa_port_pre_bridge_leave(struct dsa_port *dp, struct net_device *br, - struct netlink_ext_ack *extack); +void dsa_port_pre_bridge_leave(struct dsa_port *dp, struct net_device *br); void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br); int dsa_port_lag_change(struct dsa_port *dp, struct netdev_lag_lower_state_info *linfo); int dsa_port_lag_join(struct dsa_port *dp, struct net_device *lag_dev, struct netdev_lag_upper_info *uinfo, struct netlink_ext_ack *extack); -int dsa_port_pre_lag_leave(struct dsa_port *dp, struct net_device *lag_dev, - struct netlink_ext_ack *extack); +void dsa_port_pre_lag_leave(struct dsa_port *dp, struct net_device *lag_dev); void dsa_port_lag_leave(struct dsa_port *dp, struct net_device *lag_dev); int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, struct netlink_ext_ack *extack); @@ -231,11 +241,9 @@ int dsa_port_host_mdb_del(const struct dsa_port *dp, int dsa_port_pre_bridge_flags(const struct dsa_port *dp, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); -int dsa_port_bridge_flags(const struct dsa_port *dp, +int dsa_port_bridge_flags(struct dsa_port *dp, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); -int dsa_port_mrouter(struct dsa_port *dp, bool mrouter, - struct netlink_ext_ack *extack); int dsa_port_vlan_add(struct dsa_port *dp, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack); @@ -253,16 +261,18 @@ int dsa_port_link_register_of(struct dsa_port *dp); void dsa_port_link_unregister_of(struct dsa_port *dp); int dsa_port_hsr_join(struct dsa_port *dp, struct net_device *hsr); void dsa_port_hsr_leave(struct dsa_port *dp, struct net_device *hsr); +int dsa_port_tag_8021q_vlan_add(struct dsa_port *dp, u16 vid, bool broadcast); +void dsa_port_tag_8021q_vlan_del(struct dsa_port *dp, u16 vid, bool broadcast); extern const struct phylink_mac_ops dsa_port_phylink_mac_ops; static inline bool dsa_port_offloads_bridge_port(struct dsa_port *dp, - struct net_device *dev) + const struct net_device *dev) { return dsa_port_to_bridge_port(dp) == dev; } static inline bool dsa_port_offloads_bridge(struct dsa_port *dp, - struct net_device *bridge_dev) + const struct net_device *bridge_dev) { /* DSA ports connected to a bridge, and event was emitted * for the bridge. @@ -272,7 +282,7 @@ static inline bool dsa_port_offloads_bridge(struct dsa_port *dp, /* Returns true if any port of this tree offloads the given net_device */ static inline bool dsa_tree_offloads_bridge_port(struct dsa_switch_tree *dst, - struct net_device *dev) + const struct net_device *dev) { struct dsa_port *dp; @@ -283,6 +293,19 @@ static inline bool dsa_tree_offloads_bridge_port(struct dsa_switch_tree *dst, return false; } +/* Returns true if any port of this tree offloads the given bridge */ +static inline bool dsa_tree_offloads_bridge(struct dsa_switch_tree *dst, + const struct net_device *bridge_dev) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_offloads_bridge(dp, bridge_dev)) + return true; + + return false; +} + /* slave.c */ extern const struct dsa_device_ops notag_netdev_ops; extern struct notifier_block dsa_slave_switchdev_notifier; @@ -297,6 +320,8 @@ int dsa_slave_register_notifier(void); void dsa_slave_unregister_notifier(void); void dsa_slave_setup_tagger(struct net_device *slave); int dsa_slave_change_mtu(struct net_device *dev, int new_mtu); +int dsa_slave_manage_vlan_filtering(struct net_device *dev, + bool vlan_filtering); static inline struct dsa_port *dsa_slave_to_port(const struct net_device *dev) { @@ -372,6 +397,141 @@ static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb) return skb; } +/* For switches without hardware support for DSA tagging to be able + * to support termination through the bridge. + */ +static inline struct net_device * +dsa_find_designated_bridge_port_by_vid(struct net_device *master, u16 vid) +{ + struct dsa_port *cpu_dp = master->dsa_ptr; + struct dsa_switch_tree *dst = cpu_dp->dst; + struct bridge_vlan_info vinfo; + struct net_device *slave; + struct dsa_port *dp; + int err; + + list_for_each_entry(dp, &dst->ports, list) { + if (dp->type != DSA_PORT_TYPE_USER) + continue; + + if (!dp->bridge_dev) + continue; + + if (dp->stp_state != BR_STATE_LEARNING && + dp->stp_state != BR_STATE_FORWARDING) + continue; + + /* Since the bridge might learn this packet, keep the CPU port + * affinity with the port that will be used for the reply on + * xmit. + */ + if (dp->cpu_dp != cpu_dp) + continue; + + slave = dp->slave; + + err = br_vlan_get_info_rcu(slave, vid, &vinfo); + if (err) + continue; + + return slave; + } + + return NULL; +} + +/* If the ingress port offloads the bridge, we mark the frame as autonomously + * forwarded by hardware, so the software bridge doesn't forward in twice, back + * to us, because we already did. However, if we're in fallback mode and we do + * software bridging, we are not offloading it, therefore the dp->bridge_dev + * pointer is not populated, and flooding needs to be done by software (we are + * effectively operating in standalone ports mode). + */ +static inline void dsa_default_offload_fwd_mark(struct sk_buff *skb) +{ + struct dsa_port *dp = dsa_slave_to_port(skb->dev); + + skb->offload_fwd_mark = !!(dp->bridge_dev); +} + +/* Helper for removing DSA header tags from packets in the RX path. + * Must not be called before skb_pull(len). + * skb->data + * | + * v + * | | | | | | | | | | | | | | | | | | | + * +-----------------------+-----------------------+---------------+-------+ + * | Destination MAC | Source MAC | DSA header | EType | + * +-----------------------+-----------------------+---------------+-------+ + * | | + * <----- len -----> <----- len -----> + * | + * >>>>>>> v + * >>>>>>> | | | | | | | | | | | | | | | + * >>>>>>> +-----------------------+-----------------------+-------+ + * >>>>>>> | Destination MAC | Source MAC | EType | + * +-----------------------+-----------------------+-------+ + * ^ + * | + * skb->data + */ +static inline void dsa_strip_etype_header(struct sk_buff *skb, int len) +{ + memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - len, 2 * ETH_ALEN); +} + +/* Helper for creating space for DSA header tags in TX path packets. + * Must not be called before skb_push(len). + * + * Before: + * + * <<<<<<< | | | | | | | | | | | | | | | + * ^ <<<<<<< +-----------------------+-----------------------+-------+ + * | <<<<<<< | Destination MAC | Source MAC | EType | + * | +-----------------------+-----------------------+-------+ + * <----- len -----> + * | + * | + * skb->data + * + * After: + * + * | | | | | | | | | | | | | | | | | | | + * +-----------------------+-----------------------+---------------+-------+ + * | Destination MAC | Source MAC | DSA header | EType | + * +-----------------------+-----------------------+---------------+-------+ + * ^ | | + * | <----- len -----> + * skb->data + */ +static inline void dsa_alloc_etype_header(struct sk_buff *skb, int len) +{ + memmove(skb->data, skb->data + len, 2 * ETH_ALEN); +} + +/* On RX, eth_type_trans() on the DSA master pulls ETH_HLEN bytes starting from + * skb_mac_header(skb), which leaves skb->data pointing at the first byte after + * what the DSA master perceives as the EtherType (the beginning of the L3 + * protocol). Since DSA EtherType header taggers treat the EtherType as part of + * the DSA tag itself, and the EtherType is 2 bytes in length, the DSA header + * is located 2 bytes behind skb->data. Note that EtherType in this context + * means the first 2 bytes of the DSA header, not the encapsulated EtherType + * that will become visible after the DSA header is stripped. + */ +static inline void *dsa_etype_header_pos_rx(struct sk_buff *skb) +{ + return skb->data - 2; +} + +/* On TX, skb->data points to skb_mac_header(skb), which means that EtherType + * header taggers start exactly where the EtherType is (the EtherType is + * treated as part of the DSA header). + */ +static inline void *dsa_etype_header_pos_tx(struct sk_buff *skb) +{ + return skb->data + 2 * ETH_ALEN; +} + /* switch.c */ int dsa_switch_register_notifier(struct dsa_switch *ds); void dsa_switch_unregister_notifier(struct dsa_switch *ds); @@ -385,6 +545,18 @@ int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, struct net_device *master, const struct dsa_device_ops *tag_ops, const struct dsa_device_ops *old_tag_ops); +int dsa_bridge_num_get(const struct net_device *bridge_dev, int max); +void dsa_bridge_num_put(const struct net_device *bridge_dev, int bridge_num); + +/* tag_8021q.c */ +int dsa_tag_8021q_bridge_join(struct dsa_switch *ds, + struct dsa_notifier_bridge_info *info); +int dsa_tag_8021q_bridge_leave(struct dsa_switch *ds, + struct dsa_notifier_bridge_info *info); +int dsa_switch_tag_8021q_vlan_add(struct dsa_switch *ds, + struct dsa_notifier_tag_8021q_vlan_info *info); +int dsa_switch_tag_8021q_vlan_del(struct dsa_switch *ds, + struct dsa_notifier_tag_8021q_vlan_info *info); extern struct list_head dsa_tree_list; diff --git a/net/dsa/master.c b/net/dsa/master.c index 3fc90e36772d..e8e19857621b 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -210,14 +210,14 @@ static int dsa_master_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) break; } - if (dev->netdev_ops->ndo_do_ioctl) - err = dev->netdev_ops->ndo_do_ioctl(dev, ifr, cmd); + if (dev->netdev_ops->ndo_eth_ioctl) + err = dev->netdev_ops->ndo_eth_ioctl(dev, ifr, cmd); return err; } static const struct dsa_netdevice_ops dsa_netdev_ops = { - .ndo_do_ioctl = dsa_master_ioctl, + .ndo_eth_ioctl = dsa_master_ioctl, }; static int dsa_master_ethtool_setup(struct net_device *dev) diff --git a/net/dsa/port.c b/net/dsa/port.c index 28b45b7e66df..616330a16d31 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -30,7 +30,52 @@ static int dsa_port_notify(const struct dsa_port *dp, unsigned long e, void *v) return dsa_tree_notify(dp->ds->dst, e, v); } -int dsa_port_set_state(struct dsa_port *dp, u8 state) +static void dsa_port_notify_bridge_fdb_flush(const struct dsa_port *dp) +{ + struct net_device *brport_dev = dsa_port_to_bridge_port(dp); + struct switchdev_notifier_fdb_info info = { + /* flush all VLANs */ + .vid = 0, + }; + + /* When the port becomes standalone it has already left the bridge. + * Don't notify the bridge in that case. + */ + if (!brport_dev) + return; + + call_switchdev_notifiers(SWITCHDEV_FDB_FLUSH_TO_BRIDGE, + brport_dev, &info.info, NULL); +} + +static void dsa_port_fast_age(const struct dsa_port *dp) +{ + struct dsa_switch *ds = dp->ds; + + if (!ds->ops->port_fast_age) + return; + + ds->ops->port_fast_age(ds, dp->index); + + dsa_port_notify_bridge_fdb_flush(dp); +} + +static bool dsa_port_can_configure_learning(struct dsa_port *dp) +{ + struct switchdev_brport_flags flags = { + .mask = BR_LEARNING, + }; + struct dsa_switch *ds = dp->ds; + int err; + + if (!ds->ops->port_bridge_flags || !ds->ops->port_pre_bridge_flags) + return false; + + err = ds->ops->port_pre_bridge_flags(ds, dp->index, flags, NULL); + return !err; +} + +int dsa_port_set_state(struct dsa_port *dp, u8 state, bool do_fast_age) { struct dsa_switch *ds = dp->ds; int port = dp->index; @@ -40,10 +85,14 @@ int dsa_port_set_state(struct dsa_port *dp, u8 state) ds->ops->port_stp_state_set(ds, port, state); - if (ds->ops->port_fast_age) { + if (!dsa_port_can_configure_learning(dp) || + (do_fast_age && dp->learning)) { /* Fast age FDB entries or flush appropriate forwarding database * for the given port, if we are moving it from Learning or * Forwarding state, to Disabled or Blocking or Listening state. + * Ports that were standalone before the STP state change don't + * need to fast age the FDB, since address learning is off in + * standalone mode. */ if ((dp->stp_state == BR_STATE_LEARNING || @@ -51,7 +100,7 @@ int dsa_port_set_state(struct dsa_port *dp, u8 state) (state == BR_STATE_DISABLED || state == BR_STATE_BLOCKING || state == BR_STATE_LISTENING)) - ds->ops->port_fast_age(ds, port); + dsa_port_fast_age(dp); } dp->stp_state = state; @@ -59,11 +108,12 @@ int dsa_port_set_state(struct dsa_port *dp, u8 state) return 0; } -static 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, + bool do_fast_age) { int err; - err = dsa_port_set_state(dp, state); + err = dsa_port_set_state(dp, state, do_fast_age); if (err) pr_err("DSA: failed to set STP state %u (%d)\n", state, err); } @@ -81,7 +131,7 @@ int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy) } if (!dp->bridge_dev) - dsa_port_set_state_now(dp, BR_STATE_FORWARDING); + dsa_port_set_state_now(dp, BR_STATE_FORWARDING, false); if (dp->pl) phylink_start(dp->pl); @@ -109,7 +159,7 @@ void dsa_port_disable_rt(struct dsa_port *dp) phylink_stop(dp->pl); if (!dp->bridge_dev) - dsa_port_set_state_now(dp, BR_STATE_DISABLED); + dsa_port_set_state_now(dp, BR_STATE_DISABLED, false); if (ds->ops->port_disable) ds->ops->port_disable(ds, port); @@ -167,8 +217,8 @@ static void dsa_port_clear_brport_flags(struct dsa_port *dp) } } -static int dsa_port_switchdev_sync(struct dsa_port *dp, - struct netlink_ext_ack *extack) +static int dsa_port_switchdev_sync_attrs(struct dsa_port *dp, + struct netlink_ext_ack *extack) { struct net_device *brport_dev = dsa_port_to_bridge_port(dp); struct net_device *br = dp->bridge_dev; @@ -178,7 +228,7 @@ static int dsa_port_switchdev_sync(struct dsa_port *dp, if (err) return err; - err = dsa_port_set_state(dp, br_port_get_stp_state(brport_dev)); + err = dsa_port_set_state(dp, br_port_get_stp_state(brport_dev), false); if (err && err != -EOPNOTSUPP) return err; @@ -186,67 +236,10 @@ static int dsa_port_switchdev_sync(struct dsa_port *dp, if (err && err != -EOPNOTSUPP) return err; - err = dsa_port_mrouter(dp->cpu_dp, br_multicast_router(br), extack); - if (err && err != -EOPNOTSUPP) - return err; - err = dsa_port_ageing_time(dp, br_get_ageing_time(br)); if (err && err != -EOPNOTSUPP) return err; - err = br_mdb_replay(br, brport_dev, dp, true, - &dsa_slave_switchdev_blocking_notifier, extack); - if (err && err != -EOPNOTSUPP) - return err; - - /* Forwarding and termination FDB entries on the port */ - err = br_fdb_replay(br, brport_dev, dp, true, - &dsa_slave_switchdev_notifier); - if (err && err != -EOPNOTSUPP) - return err; - - /* Termination FDB entries on the bridge itself */ - err = br_fdb_replay(br, br, dp, true, &dsa_slave_switchdev_notifier); - if (err && err != -EOPNOTSUPP) - return err; - - err = br_vlan_replay(br, brport_dev, dp, true, - &dsa_slave_switchdev_blocking_notifier, extack); - if (err && err != -EOPNOTSUPP) - return err; - - return 0; -} - -static int dsa_port_switchdev_unsync_objs(struct dsa_port *dp, - struct net_device *br, - struct netlink_ext_ack *extack) -{ - struct net_device *brport_dev = dsa_port_to_bridge_port(dp); - int err; - - /* Delete the switchdev objects left on this port */ - err = br_mdb_replay(br, brport_dev, dp, false, - &dsa_slave_switchdev_blocking_notifier, extack); - if (err && err != -EOPNOTSUPP) - return err; - - /* Forwarding and termination FDB entries on the port */ - err = br_fdb_replay(br, brport_dev, dp, false, - &dsa_slave_switchdev_notifier); - if (err && err != -EOPNOTSUPP) - return err; - - /* Termination FDB entries on the bridge itself */ - err = br_fdb_replay(br, br, dp, false, &dsa_slave_switchdev_notifier); - if (err && err != -EOPNOTSUPP) - return err; - - err = br_vlan_replay(br, brport_dev, dp, false, - &dsa_slave_switchdev_blocking_notifier, extack); - if (err && err != -EOPNOTSUPP) - return err; - return 0; } @@ -268,21 +261,63 @@ static void dsa_port_switchdev_unsync_attrs(struct dsa_port *dp) /* Port left the bridge, put in BR_STATE_DISABLED by the bridge layer, * so allow it to be in BR_STATE_FORWARDING to be kept functional */ - dsa_port_set_state_now(dp, BR_STATE_FORWARDING); + dsa_port_set_state_now(dp, BR_STATE_FORWARDING, true); /* VLAN filtering is handled by dsa_switch_bridge_leave */ - /* Some drivers treat the notification for having a local multicast - * router by allowing multicast to be flooded to the CPU, so we should - * allow this in standalone mode too. - */ - dsa_port_mrouter(dp->cpu_dp, true, NULL); - /* Ageing time may be global to the switch chip, so don't change it * here because we have no good reason (or value) to change it to. */ } +static void dsa_port_bridge_tx_fwd_unoffload(struct dsa_port *dp, + struct net_device *bridge_dev) +{ + int bridge_num = dp->bridge_num; + struct dsa_switch *ds = dp->ds; + + /* No bridge TX forwarding offload => do nothing */ + if (!ds->ops->port_bridge_tx_fwd_unoffload || dp->bridge_num == -1) + return; + + dp->bridge_num = -1; + + dsa_bridge_num_put(bridge_dev, bridge_num); + + /* Notify the chips only once the offload has been deactivated, so + * that they can update their configuration accordingly. + */ + ds->ops->port_bridge_tx_fwd_unoffload(ds, dp->index, bridge_dev, + bridge_num); +} + +static bool dsa_port_bridge_tx_fwd_offload(struct dsa_port *dp, + struct net_device *bridge_dev) +{ + struct dsa_switch *ds = dp->ds; + int bridge_num, err; + + if (!ds->ops->port_bridge_tx_fwd_offload) + return false; + + bridge_num = dsa_bridge_num_get(bridge_dev, + ds->num_fwd_offloading_bridges); + if (bridge_num < 0) + return false; + + dp->bridge_num = bridge_num; + + /* Notify the driver */ + err = ds->ops->port_bridge_tx_fwd_offload(ds, dp->index, bridge_dev, + bridge_num); + if (err) { + dsa_port_bridge_tx_fwd_unoffload(dp, bridge_dev); + return false; + } + + return true; +} + int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, struct netlink_ext_ack *extack) { @@ -292,6 +327,9 @@ int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, .port = dp->index, .br = br, }; + struct net_device *dev = dp->slave; + struct net_device *brport_dev; + bool tx_fwd_offload; int err; /* Here the interface is already bridged. Reflect the current @@ -299,16 +337,31 @@ int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, */ dp->bridge_dev = br; + brport_dev = dsa_port_to_bridge_port(dp); + err = dsa_broadcast(DSA_NOTIFIER_BRIDGE_JOIN, &info); if (err) goto out_rollback; - err = dsa_port_switchdev_sync(dp, extack); + tx_fwd_offload = dsa_port_bridge_tx_fwd_offload(dp, br); + + err = switchdev_bridge_port_offload(brport_dev, dev, dp, + &dsa_slave_switchdev_notifier, + &dsa_slave_switchdev_blocking_notifier, + tx_fwd_offload, extack); if (err) goto out_rollback_unbridge; + err = dsa_port_switchdev_sync_attrs(dp, extack); + if (err) + goto out_rollback_unoffload; + return 0; +out_rollback_unoffload: + switchdev_bridge_port_unoffload(brport_dev, dp, + &dsa_slave_switchdev_notifier, + &dsa_slave_switchdev_blocking_notifier); out_rollback_unbridge: dsa_broadcast(DSA_NOTIFIER_BRIDGE_LEAVE, &info); out_rollback: @@ -316,10 +369,17 @@ out_rollback: return err; } -int dsa_port_pre_bridge_leave(struct dsa_port *dp, struct net_device *br, - struct netlink_ext_ack *extack) +void dsa_port_pre_bridge_leave(struct dsa_port *dp, struct net_device *br) { - return dsa_port_switchdev_unsync_objs(dp, br, extack); + struct net_device *brport_dev = dsa_port_to_bridge_port(dp); + + /* Don't try to unoffload something that is not offloaded */ + if (!brport_dev) + return; + + switchdev_bridge_port_unoffload(brport_dev, dp, + &dsa_slave_switchdev_notifier, + &dsa_slave_switchdev_blocking_notifier); } void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br) @@ -337,9 +397,13 @@ void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br) */ dp->bridge_dev = NULL; + dsa_port_bridge_tx_fwd_unoffload(dp, br); + err = dsa_broadcast(DSA_NOTIFIER_BRIDGE_LEAVE, &info); if (err) - pr_err("DSA: failed to notify DSA_NOTIFIER_BRIDGE_LEAVE\n"); + dev_err(dp->ds->dev, + "port %d failed to notify DSA_NOTIFIER_BRIDGE_LEAVE: %pe\n", + dp->index, ERR_PTR(err)); dsa_port_switchdev_unsync_attrs(dp); } @@ -409,13 +473,10 @@ err_lag_join: return err; } -int dsa_port_pre_lag_leave(struct dsa_port *dp, struct net_device *lag, - struct netlink_ext_ack *extack) +void dsa_port_pre_lag_leave(struct dsa_port *dp, struct net_device *lag) { if (dp->bridge_dev) - return dsa_port_pre_bridge_leave(dp, dp->bridge_dev, extack); - - return 0; + dsa_port_pre_bridge_leave(dp, dp->bridge_dev); } void dsa_port_lag_leave(struct dsa_port *dp, struct net_device *lag) @@ -441,8 +502,9 @@ void dsa_port_lag_leave(struct dsa_port *dp, struct net_device *lag) err = dsa_port_notify(dp, DSA_NOTIFIER_LAG_LEAVE, &info); if (err) - pr_err("DSA: failed to notify DSA_NOTIFIER_LAG_LEAVE: %d\n", - err); + dev_err(dp->ds->dev, + "port %d failed to notify DSA_NOTIFIER_LAG_LEAVE: %pe\n", + dp->index, ERR_PTR(err)); dsa_lag_unmap(dp->ds->dst, lag); } @@ -518,6 +580,7 @@ static bool dsa_port_can_apply_vlan_filtering(struct dsa_port *dp, int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, struct netlink_ext_ack *extack) { + bool old_vlan_filtering = dsa_port_is_vlan_filtering(dp); struct dsa_switch *ds = dp->ds; bool apply; int err; @@ -543,12 +606,49 @@ int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, if (err) return err; - if (ds->vlan_filtering_is_global) + if (ds->vlan_filtering_is_global) { + int port; + ds->vlan_filtering = vlan_filtering; - else + + for (port = 0; port < ds->num_ports; port++) { + struct net_device *slave; + + if (!dsa_is_user_port(ds, port)) + continue; + + /* We might be called in the unbind path, so not + * all slave devices might still be registered. + */ + slave = dsa_to_port(ds, port)->slave; + if (!slave) + continue; + + err = dsa_slave_manage_vlan_filtering(slave, + vlan_filtering); + if (err) + goto restore; + } + } else { dp->vlan_filtering = vlan_filtering; + err = dsa_slave_manage_vlan_filtering(dp->slave, + vlan_filtering); + if (err) + goto restore; + } + return 0; + +restore: + ds->ops->port_vlan_filtering(ds, dp->index, old_vlan_filtering, NULL); + + if (ds->vlan_filtering_is_global) + ds->vlan_filtering = old_vlan_filtering; + else + dp->vlan_filtering = old_vlan_filtering; + + return err; } /* This enforces legacy behavior for switch drivers which assume they can't @@ -595,27 +695,35 @@ int dsa_port_pre_bridge_flags(const struct dsa_port *dp, return ds->ops->port_pre_bridge_flags(ds, dp->index, flags, extack); } -int dsa_port_bridge_flags(const struct dsa_port *dp, +int dsa_port_bridge_flags(struct dsa_port *dp, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack) { struct dsa_switch *ds = dp->ds; + int err; if (!ds->ops->port_bridge_flags) return -EOPNOTSUPP; - return ds->ops->port_bridge_flags(ds, dp->index, flags, extack); -} + err = ds->ops->port_bridge_flags(ds, dp->index, flags, extack); + if (err) + return err; -int dsa_port_mrouter(struct dsa_port *dp, bool mrouter, - struct netlink_ext_ack *extack) -{ - struct dsa_switch *ds = dp->ds; + if (flags.mask & BR_LEARNING) { + bool learning = flags.val & BR_LEARNING; - if (!ds->ops->port_set_mrouter) - return -EOPNOTSUPP; + if (learning == dp->learning) + return 0; + + if ((dp->learning && !learning) && + (dp->stp_state == BR_STATE_LEARNING || + dp->stp_state == BR_STATE_FORWARDING)) + dsa_port_fast_age(dp); + + dp->learning = learning; + } - return ds->ops->port_set_mrouter(ds, dp->index, mrouter, extack); + return 0; } int dsa_port_mtu_change(struct dsa_port *dp, int new_mtu, @@ -844,7 +952,6 @@ int dsa_port_mrp_del_ring_role(const struct dsa_port *dp, void dsa_port_set_tag_protocol(struct dsa_port *cpu_dp, const struct dsa_device_ops *tag_ops) { - cpu_dp->filter = tag_ops->filter; cpu_dp->rcv = tag_ops->rcv; cpu_dp->tag_ops = tag_ops; } @@ -1215,5 +1322,42 @@ void dsa_port_hsr_leave(struct dsa_port *dp, struct net_device *hsr) err = dsa_port_notify(dp, DSA_NOTIFIER_HSR_LEAVE, &info); if (err) - pr_err("DSA: failed to notify DSA_NOTIFIER_HSR_LEAVE\n"); + dev_err(dp->ds->dev, + "port %d failed to notify DSA_NOTIFIER_HSR_LEAVE: %pe\n", + dp->index, ERR_PTR(err)); +} + +int dsa_port_tag_8021q_vlan_add(struct dsa_port *dp, u16 vid, bool broadcast) +{ + struct dsa_notifier_tag_8021q_vlan_info info = { + .tree_index = dp->ds->dst->index, + .sw_index = dp->ds->index, + .port = dp->index, + .vid = vid, + }; + + if (broadcast) + return dsa_broadcast(DSA_NOTIFIER_TAG_8021Q_VLAN_ADD, &info); + + return dsa_port_notify(dp, DSA_NOTIFIER_TAG_8021Q_VLAN_ADD, &info); +} + +void dsa_port_tag_8021q_vlan_del(struct dsa_port *dp, u16 vid, bool broadcast) +{ + struct dsa_notifier_tag_8021q_vlan_info info = { + .tree_index = dp->ds->dst->index, + .sw_index = dp->ds->index, + .port = dp->index, + .vid = vid, + }; + int err; + + if (broadcast) + err = dsa_broadcast(DSA_NOTIFIER_TAG_8021Q_VLAN_DEL, &info); + else + err = dsa_port_notify(dp, DSA_NOTIFIER_TAG_8021Q_VLAN_DEL, &info); + if (err) + dev_err(dp->ds->dev, + "port %d failed to notify tag_8021q VLAN %d deletion: %pe\n", + dp->index, vid, ERR_PTR(err)); } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 532085da8d8f..662ff531d4e2 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -286,7 +286,7 @@ static int dsa_slave_port_attr_set(struct net_device *dev, const void *ctx, if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) return -EOPNOTSUPP; - ret = dsa_port_set_state(dp, attr->u.stp_state); + ret = dsa_port_set_state(dp, attr->u.stp_state, true); break; case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: if (!dsa_port_offloads_bridge(dp, attr->orig_dev)) @@ -314,12 +314,6 @@ static int dsa_slave_port_attr_set(struct net_device *dev, const void *ctx, ret = dsa_port_bridge_flags(dp, attr->u.brport_flags, extack); break; - case SWITCHDEV_ATTR_ID_BRIDGE_MROUTER: - if (!dsa_port_offloads_bridge(dp, attr->orig_dev)) - return -EOPNOTSUPP; - - ret = dsa_port_mrouter(dp->cpu_dp, attr->u.mrouter, extack); - break; default: ret = -EOPNOTSUPP; break; @@ -1415,6 +1409,76 @@ static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, return 0; } +static int dsa_slave_restore_vlan(struct net_device *vdev, int vid, void *arg) +{ + __be16 proto = vdev ? vlan_dev_vlan_proto(vdev) : htons(ETH_P_8021Q); + + return dsa_slave_vlan_rx_add_vid(arg, proto, vid); +} + +static int dsa_slave_clear_vlan(struct net_device *vdev, int vid, void *arg) +{ + __be16 proto = vdev ? vlan_dev_vlan_proto(vdev) : htons(ETH_P_8021Q); + + return dsa_slave_vlan_rx_kill_vid(arg, proto, vid); +} + +/* Keep the VLAN RX filtering list in sync with the hardware only if VLAN + * filtering is enabled. The baseline is that only ports that offload a + * VLAN-aware bridge are VLAN-aware, and standalone ports are VLAN-unaware, + * but there are exceptions for quirky hardware. + * + * If ds->vlan_filtering_is_global = true, then standalone ports which share + * the same switch with other ports that offload a VLAN-aware bridge are also + * inevitably VLAN-aware. + * + * To summarize, a DSA switch port offloads: + * + * - If standalone (this includes software bridge, software LAG): + * - if ds->needs_standalone_vlan_filtering = true, OR if + * (ds->vlan_filtering_is_global = true AND there are bridges spanning + * this switch chip which have vlan_filtering=1) + * - the 8021q upper VLANs + * - else (standalone VLAN filtering is not needed, VLAN filtering is not + * global, or it is, but no port is under a VLAN-aware bridge): + * - no VLAN (any 8021q upper is a software VLAN) + * + * - If under a vlan_filtering=0 bridge which it offload: + * - if ds->configure_vlan_while_not_filtering = true (default): + * - the bridge VLANs. These VLANs are committed to hardware but inactive. + * - else (deprecated): + * - no VLAN. The bridge VLANs are not restored when VLAN awareness is + * enabled, so this behavior is broken and discouraged. + * + * - If under a vlan_filtering=1 bridge which it offload: + * - the bridge VLANs + * - the 8021q upper VLANs + */ +int dsa_slave_manage_vlan_filtering(struct net_device *slave, + bool vlan_filtering) +{ + int err; + + if (vlan_filtering) { + slave->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + + err = vlan_for_each(slave, dsa_slave_restore_vlan, slave); + if (err) { + vlan_for_each(slave, dsa_slave_clear_vlan, slave); + slave->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; + return err; + } + } else { + err = vlan_for_each(slave, dsa_slave_clear_vlan, slave); + if (err) + return err; + + slave->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; + } + + return 0; +} + struct dsa_hw_port { struct list_head list; struct net_device *dev; @@ -1687,7 +1751,7 @@ static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_set_rx_mode = dsa_slave_set_rx_mode, .ndo_set_mac_address = dsa_slave_set_mac_address, .ndo_fdb_dump = dsa_slave_fdb_dump, - .ndo_do_ioctl = dsa_slave_ioctl, + .ndo_eth_ioctl = dsa_slave_ioctl, .ndo_get_iflink = dsa_slave_get_iflink, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_netpoll_setup = dsa_slave_netpoll_setup, @@ -1822,12 +1886,12 @@ void dsa_slave_setup_tagger(struct net_device *slave) p->xmit = cpu_dp->tag_ops->xmit; slave->features = master->vlan_features | NETIF_F_HW_TC; - if (ds->ops->port_vlan_add && ds->ops->port_vlan_del) - slave->features |= NETIF_F_HW_VLAN_CTAG_FILTER; slave->hw_features |= NETIF_F_HW_TC; slave->features |= NETIF_F_LLTX; if (slave->needed_tailroom) slave->features &= ~(NETIF_F_SG | NETIF_F_FRAGLIST); + if (ds->needs_standalone_vlan_filtering) + slave->features |= NETIF_F_HW_VLAN_CTAG_FILTER; } static struct lock_class_key dsa_slave_netdev_xmit_lock_key; @@ -2015,6 +2079,11 @@ static int dsa_slave_changeupper(struct net_device *dev, err = dsa_port_bridge_join(dp, info->upper_dev, extack); if (!err) dsa_bridge_mtu_normalization(dp); + if (err == -EOPNOTSUPP) { + NL_SET_ERR_MSG_MOD(extack, + "Offloading not supported"); + err = 0; + } err = notifier_from_errno(err); } else { dsa_port_bridge_leave(dp, info->upper_dev); @@ -2056,20 +2125,16 @@ static int dsa_slave_prechangeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct dsa_port *dp = dsa_slave_to_port(dev); - struct netlink_ext_ack *extack; - int err = 0; - - extack = netdev_notifier_info_to_extack(&info->info); if (netif_is_bridge_master(info->upper_dev) && !info->linking) - err = dsa_port_pre_bridge_leave(dp, info->upper_dev, extack); + dsa_port_pre_bridge_leave(dp, info->upper_dev); else if (netif_is_lag_master(info->upper_dev) && !info->linking) - err = dsa_port_pre_lag_leave(dp, info->upper_dev, extack); + dsa_port_pre_lag_leave(dp, info->upper_dev); /* dsa_port_pre_hsr_leave is not yet necessary since hsr cannot be * meaningfully enslaved to a bridge yet */ - return notifier_from_errno(err); + return NOTIFY_DONE; } static int @@ -2291,8 +2356,8 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, static void dsa_fdb_offload_notify(struct dsa_switchdev_event_work *switchdev_work) { + struct switchdev_notifier_fdb_info info = {}; struct dsa_switch *ds = switchdev_work->ds; - struct switchdev_notifier_fdb_info info; struct dsa_port *dp; if (!dsa_is_user_port(ds, switchdev_work->port)) @@ -2357,26 +2422,98 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) kfree(switchdev_work); } -static int dsa_lower_dev_walk(struct net_device *lower_dev, - struct netdev_nested_priv *priv) +static bool dsa_foreign_dev_check(const struct net_device *dev, + const struct net_device *foreign_dev) { - if (dsa_slave_dev_check(lower_dev)) { - priv->data = (void *)netdev_priv(lower_dev); - return 1; - } + const struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch_tree *dst = dp->ds->dst; - return 0; + if (netif_is_bridge_master(foreign_dev)) + return !dsa_tree_offloads_bridge(dst, foreign_dev); + + if (netif_is_bridge_port(foreign_dev)) + return !dsa_tree_offloads_bridge_port(dst, foreign_dev); + + /* Everything else is foreign */ + return true; } -static struct dsa_slave_priv *dsa_slave_dev_lower_find(struct net_device *dev) +static int dsa_slave_fdb_event(struct net_device *dev, + const struct net_device *orig_dev, + const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info, + unsigned long event) { - struct netdev_nested_priv priv = { - .data = NULL, - }; + struct dsa_switchdev_event_work *switchdev_work; + struct dsa_port *dp = dsa_slave_to_port(dev); + bool host_addr = fdb_info->is_local; + struct dsa_switch *ds = dp->ds; + + if (ctx && ctx != dp) + return 0; + + if (!ds->ops->port_fdb_add || !ds->ops->port_fdb_del) + return -EOPNOTSUPP; + + if (dsa_slave_dev_check(orig_dev) && + switchdev_fdb_is_dynamically_learned(fdb_info)) + return 0; + + /* FDB entries learned by the software bridge should be installed as + * host addresses only if the driver requests assisted learning. + */ + if (switchdev_fdb_is_dynamically_learned(fdb_info) && + !ds->assisted_learning_on_cpu_port) + return 0; + + /* Also treat FDB entries on foreign interfaces bridged with us as host + * addresses. + */ + if (dsa_foreign_dev_check(dev, orig_dev)) + host_addr = true; + + switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC); + if (!switchdev_work) + return -ENOMEM; - netdev_walk_all_lower_dev_rcu(dev, dsa_lower_dev_walk, &priv); + netdev_dbg(dev, "%s FDB entry towards %s, addr %pM vid %d%s\n", + event == SWITCHDEV_FDB_ADD_TO_DEVICE ? "Adding" : "Deleting", + orig_dev->name, fdb_info->addr, fdb_info->vid, + host_addr ? " as host address" : ""); - return (struct dsa_slave_priv *)priv.data; + INIT_WORK(&switchdev_work->work, dsa_slave_switchdev_event_work); + switchdev_work->ds = ds; + switchdev_work->port = dp->index; + switchdev_work->event = event; + switchdev_work->dev = dev; + + ether_addr_copy(switchdev_work->addr, fdb_info->addr); + switchdev_work->vid = fdb_info->vid; + switchdev_work->host_addr = host_addr; + + /* Hold a reference for dsa_fdb_offload_notify */ + dev_hold(dev); + dsa_schedule_work(&switchdev_work->work); + + return 0; +} + +static int +dsa_slave_fdb_add_to_device(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info) +{ + return dsa_slave_fdb_event(dev, orig_dev, ctx, fdb_info, + SWITCHDEV_FDB_ADD_TO_DEVICE); +} + +static int +dsa_slave_fdb_del_to_device(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info) +{ + return dsa_slave_fdb_event(dev, orig_dev, ctx, fdb_info, + SWITCHDEV_FDB_DEL_TO_DEVICE); } /* Called under rcu_read_lock() */ @@ -2384,10 +2521,6 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); - const struct switchdev_notifier_fdb_info *fdb_info; - struct dsa_switchdev_event_work *switchdev_work; - bool host_addr = false; - struct dsa_port *dp; int err; switch (event) { @@ -2397,92 +2530,19 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused, dsa_slave_port_attr_set); return notifier_from_errno(err); case SWITCHDEV_FDB_ADD_TO_DEVICE: + err = switchdev_handle_fdb_add_to_device(dev, ptr, + dsa_slave_dev_check, + dsa_foreign_dev_check, + dsa_slave_fdb_add_to_device, + NULL); + return notifier_from_errno(err); case SWITCHDEV_FDB_DEL_TO_DEVICE: - fdb_info = ptr; - - if (dsa_slave_dev_check(dev)) { - dp = dsa_slave_to_port(dev); - - if (fdb_info->is_local) - host_addr = true; - else if (!fdb_info->added_by_user) - return NOTIFY_OK; - } else { - /* Snoop addresses added to foreign interfaces - * bridged with us, or the bridge - * itself. Dynamically learned addresses can - * also be added for switches that don't - * automatically learn SA from CPU-injected - * traffic. - */ - struct net_device *br_dev; - struct dsa_slave_priv *p; - - if (netif_is_bridge_master(dev)) - br_dev = dev; - else - br_dev = netdev_master_upper_dev_get_rcu(dev); - - if (!br_dev) - return NOTIFY_DONE; - - if (!netif_is_bridge_master(br_dev)) - return NOTIFY_DONE; - - p = dsa_slave_dev_lower_find(br_dev); - if (!p) - return NOTIFY_DONE; - - dp = p->dp; - host_addr = fdb_info->is_local; - - /* FDB entries learned by the software bridge should - * be installed as host addresses only if the driver - * requests assisted learning. - * On the other hand, FDB entries for local termination - * should always be installed. - */ - if (!fdb_info->added_by_user && !fdb_info->is_local && - !dp->ds->assisted_learning_on_cpu_port) - return NOTIFY_DONE; - - /* When the bridge learns an address on an offloaded - * LAG we don't want to send traffic to the CPU, the - * other ports bridged with the LAG should be able to - * autonomously forward towards it. - * On the other hand, if the address is local - * (therefore not learned) then we want to trap it to - * the CPU regardless of whether the interface it - * belongs to is offloaded or not. - */ - if (dsa_tree_offloads_bridge_port(dp->ds->dst, dev) && - !fdb_info->is_local) - return NOTIFY_DONE; - } - - if (!dp->ds->ops->port_fdb_add || !dp->ds->ops->port_fdb_del) - return NOTIFY_DONE; - - switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC); - if (!switchdev_work) - return NOTIFY_BAD; - - INIT_WORK(&switchdev_work->work, - dsa_slave_switchdev_event_work); - switchdev_work->ds = dp->ds; - switchdev_work->port = dp->index; - switchdev_work->event = event; - switchdev_work->dev = dev; - - ether_addr_copy(switchdev_work->addr, - fdb_info->addr); - switchdev_work->vid = fdb_info->vid; - switchdev_work->host_addr = host_addr; - - /* Hold a reference for dsa_fdb_offload_notify */ - dev_hold(dev); - dsa_schedule_work(&switchdev_work->work); - break; + err = switchdev_handle_fdb_del_to_device(dev, ptr, + dsa_slave_dev_check, + dsa_foreign_dev_check, + dsa_slave_fdb_del_to_device, + NULL); + return notifier_from_errno(err); default: return NOTIFY_DONE; } diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 5ece05dfd8f2..1c797ec8e2c2 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -90,26 +90,36 @@ static int dsa_switch_bridge_join(struct dsa_switch *ds, struct dsa_notifier_bridge_info *info) { struct dsa_switch_tree *dst = ds->dst; + int err; - if (dst->index == info->tree_index && ds->index == info->sw_index && - ds->ops->port_bridge_join) - return ds->ops->port_bridge_join(ds, info->port, info->br); + if (dst->index == info->tree_index && ds->index == info->sw_index) { + if (!ds->ops->port_bridge_join) + return -EOPNOTSUPP; + + err = ds->ops->port_bridge_join(ds, info->port, info->br); + if (err) + return err; + } if ((dst->index != info->tree_index || ds->index != info->sw_index) && - ds->ops->crosschip_bridge_join) - return ds->ops->crosschip_bridge_join(ds, info->tree_index, - info->sw_index, - info->port, info->br); + ds->ops->crosschip_bridge_join) { + err = ds->ops->crosschip_bridge_join(ds, info->tree_index, + info->sw_index, + info->port, info->br); + if (err) + return err; + } - return 0; + return dsa_tag_8021q_bridge_join(ds, info); } static int dsa_switch_bridge_leave(struct dsa_switch *ds, struct dsa_notifier_bridge_info *info) { - bool unset_vlan_filtering = br_vlan_enabled(info->br); struct dsa_switch_tree *dst = ds->dst; struct netlink_ext_ack extack = {0}; + bool change_vlan_filtering = false; + bool vlan_filtering; int err, port; if (dst->index == info->tree_index && ds->index == info->sw_index && @@ -122,6 +132,15 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, info->sw_index, info->port, info->br); + if (ds->needs_standalone_vlan_filtering && !br_vlan_enabled(info->br)) { + change_vlan_filtering = true; + vlan_filtering = true; + } else if (!ds->needs_standalone_vlan_filtering && + br_vlan_enabled(info->br)) { + change_vlan_filtering = true; + vlan_filtering = false; + } + /* If the bridge was vlan_filtering, the bridge core doesn't trigger an * event for changing vlan_filtering setting upon slave ports leaving * it. That is a good thing, because that lets us handle it and also @@ -130,28 +149,30 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, * vlan_filtering callback is only when the last port leaves the last * VLAN-aware bridge. */ - if (unset_vlan_filtering && ds->vlan_filtering_is_global) { + if (change_vlan_filtering && ds->vlan_filtering_is_global) { for (port = 0; port < ds->num_ports; port++) { struct net_device *bridge_dev; bridge_dev = dsa_to_port(ds, port)->bridge_dev; if (bridge_dev && br_vlan_enabled(bridge_dev)) { - unset_vlan_filtering = false; + change_vlan_filtering = false; break; } } } - if (unset_vlan_filtering) { + + if (change_vlan_filtering) { err = dsa_port_vlan_filtering(dsa_to_port(ds, info->port), - false, &extack); + vlan_filtering, &extack); if (extack._msg) dev_err(ds->dev, "port %d: %s\n", info->port, extack._msg); if (err && err != EOPNOTSUPP) return err; } - return 0; + + return dsa_tag_8021q_bridge_leave(ds, info); } /* Matches for all upstream-facing ports (the CPU port and all upstream-facing @@ -726,6 +747,12 @@ static int dsa_switch_event(struct notifier_block *nb, case DSA_NOTIFIER_MRP_DEL_RING_ROLE: err = dsa_switch_mrp_del_ring_role(ds, info); break; + case DSA_NOTIFIER_TAG_8021Q_VLAN_ADD: + err = dsa_switch_tag_8021q_vlan_add(ds, info); + break; + case DSA_NOTIFIER_TAG_8021Q_VLAN_DEL: + err = dsa_switch_tag_8021q_vlan_del(ds, info); + break; default: err = -EOPNOTSUPP; break; diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 4aa29f90ecea..f8f7b7c34e7d 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -17,7 +17,7 @@ * * | 11 | 10 | 9 | 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 | * +-----------+-----+-----------------+-----------+-----------------------+ - * | DIR | SVL | SWITCH_ID | SUBVLAN | PORT | + * | DIR | VBID| SWITCH_ID | VBID | PORT | * +-----------+-----+-----------------+-----------+-----------------------+ * * DIR - VID[11:10]: @@ -27,24 +27,14 @@ * These values make the special VIDs of 0, 1 and 4095 to be left * unused by this coding scheme. * - * SVL/SUBVLAN - { VID[9], VID[5:4] }: - * Sub-VLAN encoding. Valid only when DIR indicates an RX VLAN. - * * 0 (0b000): Field does not encode a sub-VLAN, either because - * received traffic is untagged, PVID-tagged or because a second - * VLAN tag is present after this tag and not inside of it. - * * 1 (0b001): Received traffic is tagged with a VID value private - * to the host. This field encodes the index in the host's lookup - * table through which the value of the ingress VLAN ID can be - * recovered. - * * 2 (0b010): Field encodes a sub-VLAN. - * ... - * * 7 (0b111): Field encodes a sub-VLAN. - * When DIR indicates a TX VLAN, SUBVLAN must be transmitted as zero - * (by the host) and ignored on receive (by the switch). - * * SWITCH_ID - VID[8:6]: * Index of switch within DSA tree. Must be between 0 and 7. * + * VBID - { VID[9], VID[5:4] }: + * Virtual bridge ID. If between 1 and 7, packet targets the broadcast + * domain of a bridge. If transmitted as zero, packet targets a single + * port. Field only valid on transmit, must be ignored on receive. + * * PORT - VID[3:0]: * Index of switch port. Must be between 0 and 15. */ @@ -61,23 +51,30 @@ #define DSA_8021Q_SWITCH_ID(x) (((x) << DSA_8021Q_SWITCH_ID_SHIFT) & \ DSA_8021Q_SWITCH_ID_MASK) -#define DSA_8021Q_SUBVLAN_HI_SHIFT 9 -#define DSA_8021Q_SUBVLAN_HI_MASK GENMASK(9, 9) -#define DSA_8021Q_SUBVLAN_LO_SHIFT 4 -#define DSA_8021Q_SUBVLAN_LO_MASK GENMASK(5, 4) -#define DSA_8021Q_SUBVLAN_HI(x) (((x) & GENMASK(2, 2)) >> 2) -#define DSA_8021Q_SUBVLAN_LO(x) ((x) & GENMASK(1, 0)) -#define DSA_8021Q_SUBVLAN(x) \ - (((DSA_8021Q_SUBVLAN_LO(x) << DSA_8021Q_SUBVLAN_LO_SHIFT) & \ - DSA_8021Q_SUBVLAN_LO_MASK) | \ - ((DSA_8021Q_SUBVLAN_HI(x) << DSA_8021Q_SUBVLAN_HI_SHIFT) & \ - DSA_8021Q_SUBVLAN_HI_MASK)) +#define DSA_8021Q_VBID_HI_SHIFT 9 +#define DSA_8021Q_VBID_HI_MASK GENMASK(9, 9) +#define DSA_8021Q_VBID_LO_SHIFT 4 +#define DSA_8021Q_VBID_LO_MASK GENMASK(5, 4) +#define DSA_8021Q_VBID_HI(x) (((x) & GENMASK(2, 2)) >> 2) +#define DSA_8021Q_VBID_LO(x) ((x) & GENMASK(1, 0)) +#define DSA_8021Q_VBID(x) \ + (((DSA_8021Q_VBID_LO(x) << DSA_8021Q_VBID_LO_SHIFT) & \ + DSA_8021Q_VBID_LO_MASK) | \ + ((DSA_8021Q_VBID_HI(x) << DSA_8021Q_VBID_HI_SHIFT) & \ + DSA_8021Q_VBID_HI_MASK)) #define DSA_8021Q_PORT_SHIFT 0 #define DSA_8021Q_PORT_MASK GENMASK(3, 0) #define DSA_8021Q_PORT(x) (((x) << DSA_8021Q_PORT_SHIFT) & \ DSA_8021Q_PORT_MASK) +u16 dsa_8021q_bridge_tx_fwd_offload_vid(int bridge_num) +{ + /* The VBID value of 0 is reserved for precise TX */ + return DSA_8021Q_DIR_TX | DSA_8021Q_VBID(bridge_num + 1); +} +EXPORT_SYMBOL_GPL(dsa_8021q_bridge_tx_fwd_offload_vid); + /* Returns the VID to be inserted into the frame from xmit for switch steering * instructions on egress. Encodes switch ID and port ID. */ @@ -98,13 +95,6 @@ u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port) } EXPORT_SYMBOL_GPL(dsa_8021q_rx_vid); -u16 dsa_8021q_rx_vid_subvlan(struct dsa_switch *ds, int port, u16 subvlan) -{ - return DSA_8021Q_DIR_RX | DSA_8021Q_SWITCH_ID(ds->index) | - DSA_8021Q_PORT(port) | DSA_8021Q_SUBVLAN(subvlan); -} -EXPORT_SYMBOL_GPL(dsa_8021q_rx_vid_subvlan); - /* Returns the decoded switch ID from the RX VID. */ int dsa_8021q_rx_switch_id(u16 vid) { @@ -119,20 +109,6 @@ int dsa_8021q_rx_source_port(u16 vid) } EXPORT_SYMBOL_GPL(dsa_8021q_rx_source_port); -/* Returns the decoded subvlan from the RX VID. */ -u16 dsa_8021q_rx_subvlan(u16 vid) -{ - u16 svl_hi, svl_lo; - - svl_hi = (vid & DSA_8021Q_SUBVLAN_HI_MASK) >> - DSA_8021Q_SUBVLAN_HI_SHIFT; - svl_lo = (vid & DSA_8021Q_SUBVLAN_LO_MASK) >> - DSA_8021Q_SUBVLAN_LO_SHIFT; - - return (svl_hi << 2) | svl_lo; -} -EXPORT_SYMBOL_GPL(dsa_8021q_rx_subvlan); - bool vid_is_dsa_8021q_rxvlan(u16 vid) { return (vid & DSA_8021Q_DIR_MASK) == DSA_8021Q_DIR_RX; @@ -151,21 +127,152 @@ bool vid_is_dsa_8021q(u16 vid) } EXPORT_SYMBOL_GPL(vid_is_dsa_8021q); -/* If @enabled is true, installs @vid with @flags into the switch port's HW - * filter. - * If @enabled is false, deletes @vid (ignores @flags) from the port. Had the - * user explicitly configured this @vid through the bridge core, then the @vid - * is installed again, but this time with the flags from the bridge layer. - */ -static int dsa_8021q_vid_apply(struct dsa_8021q_context *ctx, int port, u16 vid, - u16 flags, bool enabled) +static struct dsa_tag_8021q_vlan * +dsa_tag_8021q_vlan_find(struct dsa_8021q_context *ctx, int port, u16 vid) { - struct dsa_port *dp = dsa_to_port(ctx->ds, port); + struct dsa_tag_8021q_vlan *v; - if (enabled) - return ctx->ops->vlan_add(ctx->ds, dp->index, vid, flags); + list_for_each_entry(v, &ctx->vlans, list) + if (v->vid == vid && v->port == port) + return v; - return ctx->ops->vlan_del(ctx->ds, dp->index, vid); + return NULL; +} + +static int dsa_switch_do_tag_8021q_vlan_add(struct dsa_switch *ds, int port, + u16 vid, u16 flags) +{ + struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; + struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_tag_8021q_vlan *v; + int err; + + /* No need to bother with refcounting for user ports */ + if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))) + return ds->ops->tag_8021q_vlan_add(ds, port, vid, flags); + + v = dsa_tag_8021q_vlan_find(ctx, port, vid); + if (v) { + refcount_inc(&v->refcount); + return 0; + } + + v = kzalloc(sizeof(*v), GFP_KERNEL); + if (!v) + return -ENOMEM; + + err = ds->ops->tag_8021q_vlan_add(ds, port, vid, flags); + if (err) { + kfree(v); + return err; + } + + v->vid = vid; + v->port = port; + refcount_set(&v->refcount, 1); + list_add_tail(&v->list, &ctx->vlans); + + return 0; +} + +static int dsa_switch_do_tag_8021q_vlan_del(struct dsa_switch *ds, int port, + u16 vid) +{ + struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; + struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_tag_8021q_vlan *v; + int err; + + /* No need to bother with refcounting for user ports */ + if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))) + return ds->ops->tag_8021q_vlan_del(ds, port, vid); + + v = dsa_tag_8021q_vlan_find(ctx, port, vid); + if (!v) + return -ENOENT; + + if (!refcount_dec_and_test(&v->refcount)) + return 0; + + err = ds->ops->tag_8021q_vlan_del(ds, port, vid); + if (err) { + refcount_inc(&v->refcount); + return err; + } + + list_del(&v->list); + kfree(v); + + return 0; +} + +static bool +dsa_switch_tag_8021q_vlan_match(struct dsa_switch *ds, int port, + struct dsa_notifier_tag_8021q_vlan_info *info) +{ + if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port)) + return true; + + if (ds->dst->index == info->tree_index && ds->index == info->sw_index) + return port == info->port; + + return false; +} + +int dsa_switch_tag_8021q_vlan_add(struct dsa_switch *ds, + struct dsa_notifier_tag_8021q_vlan_info *info) +{ + int port, err; + + /* Since we use dsa_broadcast(), there might be other switches in other + * trees which don't support tag_8021q, so don't return an error. + * Or they might even support tag_8021q but have not registered yet to + * use it (maybe they use another tagger currently). + */ + if (!ds->ops->tag_8021q_vlan_add || !ds->tag_8021q_ctx) + return 0; + + for (port = 0; port < ds->num_ports; port++) { + if (dsa_switch_tag_8021q_vlan_match(ds, port, info)) { + u16 flags = 0; + + if (dsa_is_user_port(ds, port)) + flags |= BRIDGE_VLAN_INFO_UNTAGGED; + + if (vid_is_dsa_8021q_rxvlan(info->vid) && + dsa_8021q_rx_switch_id(info->vid) == ds->index && + dsa_8021q_rx_source_port(info->vid) == port) + flags |= BRIDGE_VLAN_INFO_PVID; + + err = dsa_switch_do_tag_8021q_vlan_add(ds, port, + info->vid, + flags); + if (err) + return err; + } + } + + return 0; +} + +int dsa_switch_tag_8021q_vlan_del(struct dsa_switch *ds, + struct dsa_notifier_tag_8021q_vlan_info *info) +{ + int port, err; + + if (!ds->ops->tag_8021q_vlan_del || !ds->tag_8021q_ctx) + return 0; + + for (port = 0; port < ds->num_ports; port++) { + if (dsa_switch_tag_8021q_vlan_match(ds, port, info)) { + err = dsa_switch_do_tag_8021q_vlan_del(ds, port, + info->vid); + if (err) + return err; + } + } + + return 0; } /* RX VLAN tagging (left) and TX VLAN tagging (right) setup shown for a single @@ -181,12 +288,6 @@ static int dsa_8021q_vid_apply(struct dsa_8021q_context *ctx, int port, u16 vid, * force all switched traffic to pass through the CPU. So we must also make * the other front-panel ports members of this VID we're adding, albeit * we're not making it their PVID (they'll still have their own). - * By the way - just because we're installing the same VID in multiple - * switch ports doesn't mean that they'll start to talk to one another, even - * while not bridged: the final forwarding decision is still an AND between - * the L2 forwarding information (which is limiting forwarding in this case) - * and the VLAN-based restrictions (of which there are none in this case, - * since all ports are members). * - On TX (ingress from CPU and towards network) we are faced with a problem. * If we were to tag traffic (from within DSA) with the port's pvid, all * would be well, assuming the switch ports were standalone. Frames would @@ -200,9 +301,10 @@ static int dsa_8021q_vid_apply(struct dsa_8021q_context *ctx, int port, u16 vid, * a member of the VID we're tagging the traffic with - the desired one. * * So at the end, each front-panel port will have one RX VID (also the PVID), - * the RX VID of all other front-panel ports, and one TX VID. Whereas the CPU - * port will have the RX and TX VIDs of all front-panel ports, and on top of - * that, is also tagged-input and tagged-output (VLAN trunk). + * the RX VID of all other front-panel ports that are in the same bridge, and + * one TX VID. Whereas the CPU port will have the RX and TX VIDs of all + * front-panel ports, and on top of that, is also tagged-input and + * tagged-output (VLAN trunk). * * CPU port CPU port * +-------------+-----+-------------+ +-------------+-----+-------------+ @@ -220,246 +322,246 @@ static int dsa_8021q_vid_apply(struct dsa_8021q_context *ctx, int port, u16 vid, * +-+-----+-+-----+-+-----+-+-----+-+ +-+-----+-+-----+-+-----+-+-----+-+ * swp0 swp1 swp2 swp3 swp0 swp1 swp2 swp3 */ -static int dsa_8021q_setup_port(struct dsa_8021q_context *ctx, int port, - bool enabled) +static bool dsa_tag_8021q_bridge_match(struct dsa_switch *ds, int port, + struct dsa_notifier_bridge_info *info) +{ + struct dsa_port *dp = dsa_to_port(ds, port); + + /* Don't match on self */ + if (ds->dst->index == info->tree_index && + ds->index == info->sw_index && + port == info->port) + return false; + + if (dsa_port_is_user(dp)) + return dp->bridge_dev == info->br; + + return false; +} + +int dsa_tag_8021q_bridge_join(struct dsa_switch *ds, + struct dsa_notifier_bridge_info *info) +{ + struct dsa_switch *targeted_ds; + struct dsa_port *targeted_dp; + u16 targeted_rx_vid; + int err, port; + + if (!ds->tag_8021q_ctx) + return 0; + + targeted_ds = dsa_switch_find(info->tree_index, info->sw_index); + targeted_dp = dsa_to_port(targeted_ds, info->port); + targeted_rx_vid = dsa_8021q_rx_vid(targeted_ds, info->port); + + for (port = 0; port < ds->num_ports; port++) { + struct dsa_port *dp = dsa_to_port(ds, port); + u16 rx_vid = dsa_8021q_rx_vid(ds, port); + + if (!dsa_tag_8021q_bridge_match(ds, port, info)) + continue; + + /* Install the RX VID of the targeted port in our VLAN table */ + err = dsa_port_tag_8021q_vlan_add(dp, targeted_rx_vid, true); + if (err) + return err; + + /* Install our RX VID into the targeted port's VLAN table */ + err = dsa_port_tag_8021q_vlan_add(targeted_dp, rx_vid, true); + if (err) + return err; + } + + return 0; +} + +int dsa_tag_8021q_bridge_leave(struct dsa_switch *ds, + struct dsa_notifier_bridge_info *info) { - int upstream = dsa_upstream_port(ctx->ds, port); - u16 rx_vid = dsa_8021q_rx_vid(ctx->ds, port); - u16 tx_vid = dsa_8021q_tx_vid(ctx->ds, port); + struct dsa_switch *targeted_ds; + struct dsa_port *targeted_dp; + u16 targeted_rx_vid; + int port; + + if (!ds->tag_8021q_ctx) + return 0; + + targeted_ds = dsa_switch_find(info->tree_index, info->sw_index); + targeted_dp = dsa_to_port(targeted_ds, info->port); + targeted_rx_vid = dsa_8021q_rx_vid(targeted_ds, info->port); + + for (port = 0; port < ds->num_ports; port++) { + struct dsa_port *dp = dsa_to_port(ds, port); + u16 rx_vid = dsa_8021q_rx_vid(ds, port); + + if (!dsa_tag_8021q_bridge_match(ds, port, info)) + continue; + + /* Remove the RX VID of the targeted port from our VLAN table */ + dsa_port_tag_8021q_vlan_del(dp, targeted_rx_vid, true); + + /* Remove our RX VID from the targeted port's VLAN table */ + dsa_port_tag_8021q_vlan_del(targeted_dp, rx_vid, true); + } + + return 0; +} + +int dsa_tag_8021q_bridge_tx_fwd_offload(struct dsa_switch *ds, int port, + struct net_device *br, + int bridge_num) +{ + u16 tx_vid = dsa_8021q_bridge_tx_fwd_offload_vid(bridge_num); + + return dsa_port_tag_8021q_vlan_add(dsa_to_port(ds, port), tx_vid, + true); +} +EXPORT_SYMBOL_GPL(dsa_tag_8021q_bridge_tx_fwd_offload); + +void dsa_tag_8021q_bridge_tx_fwd_unoffload(struct dsa_switch *ds, int port, + struct net_device *br, + int bridge_num) +{ + u16 tx_vid = dsa_8021q_bridge_tx_fwd_offload_vid(bridge_num); + + dsa_port_tag_8021q_vlan_del(dsa_to_port(ds, port), tx_vid, true); +} +EXPORT_SYMBOL_GPL(dsa_tag_8021q_bridge_tx_fwd_unoffload); + +/* Set up a port's tag_8021q RX and TX VLAN for standalone mode operation */ +static int dsa_tag_8021q_port_setup(struct dsa_switch *ds, int port) +{ + struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; + struct dsa_port *dp = dsa_to_port(ds, port); + u16 rx_vid = dsa_8021q_rx_vid(ds, port); + u16 tx_vid = dsa_8021q_tx_vid(ds, port); struct net_device *master; - int i, err, subvlan; + int err; /* The CPU port is implicitly configured by * configuring the front-panel ports */ - if (!dsa_is_user_port(ctx->ds, port)) + if (!dsa_port_is_user(dp)) return 0; - master = dsa_to_port(ctx->ds, port)->cpu_dp->master; + master = dp->cpu_dp->master; /* Add this user port's RX VID to the membership list of all others * (including itself). This is so that bridging will not be hindered. * L2 forwarding rules still take precedence when there are no VLAN * restrictions, so there are no concerns about leaking traffic. */ - for (i = 0; i < ctx->ds->num_ports; i++) { - u16 flags; - - if (i == upstream) - continue; - else if (i == port) - /* The RX VID is pvid on this port */ - flags = BRIDGE_VLAN_INFO_UNTAGGED | - BRIDGE_VLAN_INFO_PVID; - else - /* The RX VID is a regular VLAN on all others */ - flags = BRIDGE_VLAN_INFO_UNTAGGED; - - err = dsa_8021q_vid_apply(ctx, i, rx_vid, flags, enabled); - if (err) { - dev_err(ctx->ds->dev, - "Failed to apply RX VID %d to port %d: %d\n", - rx_vid, port, err); - return err; - } - } - - /* CPU port needs to see this port's RX VID - * as tagged egress. - */ - err = dsa_8021q_vid_apply(ctx, upstream, rx_vid, 0, enabled); + err = dsa_port_tag_8021q_vlan_add(dp, rx_vid, false); if (err) { - dev_err(ctx->ds->dev, - "Failed to apply RX VID %d to port %d: %d\n", - rx_vid, port, err); + dev_err(ds->dev, + "Failed to apply RX VID %d to port %d: %pe\n", + rx_vid, port, ERR_PTR(err)); return err; } - /* Add to the master's RX filter not only @rx_vid, but in fact - * the entire subvlan range, just in case this DSA switch might - * want to use sub-VLANs. - */ - for (subvlan = 0; subvlan < DSA_8021Q_N_SUBVLAN; subvlan++) { - u16 vid = dsa_8021q_rx_vid_subvlan(ctx->ds, port, subvlan); - - if (enabled) - vlan_vid_add(master, ctx->proto, vid); - else - vlan_vid_del(master, ctx->proto, vid); - } + /* Add @rx_vid to the master's RX filter. */ + vlan_vid_add(master, ctx->proto, rx_vid); /* Finally apply the TX VID on this port and on the CPU port */ - err = dsa_8021q_vid_apply(ctx, port, tx_vid, BRIDGE_VLAN_INFO_UNTAGGED, - enabled); - if (err) { - dev_err(ctx->ds->dev, - "Failed to apply TX VID %d on port %d: %d\n", - tx_vid, port, err); - return err; - } - err = dsa_8021q_vid_apply(ctx, upstream, tx_vid, 0, enabled); + err = dsa_port_tag_8021q_vlan_add(dp, tx_vid, false); if (err) { - dev_err(ctx->ds->dev, - "Failed to apply TX VID %d on port %d: %d\n", - tx_vid, upstream, err); + dev_err(ds->dev, + "Failed to apply TX VID %d on port %d: %pe\n", + tx_vid, port, ERR_PTR(err)); return err; } return err; } -int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled) +static void dsa_tag_8021q_port_teardown(struct dsa_switch *ds, int port) { - int rc, port; + struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; + struct dsa_port *dp = dsa_to_port(ds, port); + u16 rx_vid = dsa_8021q_rx_vid(ds, port); + u16 tx_vid = dsa_8021q_tx_vid(ds, port); + struct net_device *master; - ASSERT_RTNL(); + /* The CPU port is implicitly configured by + * configuring the front-panel ports + */ + if (!dsa_port_is_user(dp)) + return; - for (port = 0; port < ctx->ds->num_ports; port++) { - rc = dsa_8021q_setup_port(ctx, port, enabled); - if (rc < 0) { - dev_err(ctx->ds->dev, - "Failed to setup VLAN tagging for port %d: %d\n", - port, rc); - return rc; - } - } + master = dp->cpu_dp->master; - return 0; -} -EXPORT_SYMBOL_GPL(dsa_8021q_setup); + dsa_port_tag_8021q_vlan_del(dp, rx_vid, false); -static int dsa_8021q_crosschip_link_apply(struct dsa_8021q_context *ctx, - int port, - struct dsa_8021q_context *other_ctx, - int other_port, bool enabled) -{ - u16 rx_vid = dsa_8021q_rx_vid(ctx->ds, port); + vlan_vid_del(master, ctx->proto, rx_vid); - /* @rx_vid of local @ds port @port goes to @other_port of - * @other_ds - */ - return dsa_8021q_vid_apply(other_ctx, other_port, rx_vid, - BRIDGE_VLAN_INFO_UNTAGGED, enabled); + dsa_port_tag_8021q_vlan_del(dp, tx_vid, false); } -static int dsa_8021q_crosschip_link_add(struct dsa_8021q_context *ctx, int port, - struct dsa_8021q_context *other_ctx, - int other_port) +static int dsa_tag_8021q_setup(struct dsa_switch *ds) { - struct dsa_8021q_crosschip_link *c; + int err, port; + + ASSERT_RTNL(); - list_for_each_entry(c, &ctx->crosschip_links, list) { - if (c->port == port && c->other_ctx == other_ctx && - c->other_port == other_port) { - refcount_inc(&c->refcount); - return 0; + for (port = 0; port < ds->num_ports; port++) { + err = dsa_tag_8021q_port_setup(ds, port); + if (err < 0) { + dev_err(ds->dev, + "Failed to setup VLAN tagging for port %d: %pe\n", + port, ERR_PTR(err)); + return err; } } - dev_dbg(ctx->ds->dev, - "adding crosschip link from port %d to %s port %d\n", - port, dev_name(other_ctx->ds->dev), other_port); - - c = kzalloc(sizeof(*c), GFP_KERNEL); - if (!c) - return -ENOMEM; - - c->port = port; - c->other_ctx = other_ctx; - c->other_port = other_port; - refcount_set(&c->refcount, 1); - - list_add(&c->list, &ctx->crosschip_links); - return 0; } -static void dsa_8021q_crosschip_link_del(struct dsa_8021q_context *ctx, - struct dsa_8021q_crosschip_link *c, - bool *keep) +static void dsa_tag_8021q_teardown(struct dsa_switch *ds) { - *keep = !refcount_dec_and_test(&c->refcount); + int port; - if (*keep) - return; - - dev_dbg(ctx->ds->dev, - "deleting crosschip link from port %d to %s port %d\n", - c->port, dev_name(c->other_ctx->ds->dev), c->other_port); + ASSERT_RTNL(); - list_del(&c->list); - kfree(c); + for (port = 0; port < ds->num_ports; port++) + dsa_tag_8021q_port_teardown(ds, port); } -/* Make traffic from local port @port be received by remote port @other_port. - * This means that our @rx_vid needs to be installed on @other_ds's upstream - * and user ports. The user ports should be egress-untagged so that they can - * pop the dsa_8021q VLAN. But the @other_upstream can be either egress-tagged - * or untagged: it doesn't matter, since it should never egress a frame having - * our @rx_vid. - */ -int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, - struct dsa_8021q_context *other_ctx, - int other_port) +int dsa_tag_8021q_register(struct dsa_switch *ds, __be16 proto) { - /* @other_upstream is how @other_ds reaches us. If we are part - * of disjoint trees, then we are probably connected through - * our CPU ports. If we're part of the same tree though, we should - * probably use dsa_towards_port. - */ - int other_upstream = dsa_upstream_port(other_ctx->ds, other_port); - int rc; + struct dsa_8021q_context *ctx; - rc = dsa_8021q_crosschip_link_add(ctx, port, other_ctx, other_port); - if (rc) - return rc; + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; - rc = dsa_8021q_crosschip_link_apply(ctx, port, other_ctx, - other_port, true); - if (rc) - return rc; + ctx->proto = proto; + ctx->ds = ds; - rc = dsa_8021q_crosschip_link_add(ctx, port, other_ctx, other_upstream); - if (rc) - return rc; + INIT_LIST_HEAD(&ctx->vlans); - return dsa_8021q_crosschip_link_apply(ctx, port, other_ctx, - other_upstream, true); + ds->tag_8021q_ctx = ctx; + + return dsa_tag_8021q_setup(ds); } -EXPORT_SYMBOL_GPL(dsa_8021q_crosschip_bridge_join); +EXPORT_SYMBOL_GPL(dsa_tag_8021q_register); -int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, - struct dsa_8021q_context *other_ctx, - int other_port) +void dsa_tag_8021q_unregister(struct dsa_switch *ds) { - int other_upstream = dsa_upstream_port(other_ctx->ds, other_port); - struct dsa_8021q_crosschip_link *c, *n; - - list_for_each_entry_safe(c, n, &ctx->crosschip_links, list) { - if (c->port == port && c->other_ctx == other_ctx && - (c->other_port == other_port || - c->other_port == other_upstream)) { - struct dsa_8021q_context *other_ctx = c->other_ctx; - int other_port = c->other_port; - bool keep; - int rc; - - dsa_8021q_crosschip_link_del(ctx, c, &keep); - if (keep) - continue; - - rc = dsa_8021q_crosschip_link_apply(ctx, port, - other_ctx, - other_port, - false); - if (rc) - return rc; - } + struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; + struct dsa_tag_8021q_vlan *v, *n; + + dsa_tag_8021q_teardown(ds); + + list_for_each_entry_safe(v, n, &ctx->vlans, list) { + list_del(&v->list); + kfree(v); } - return 0; + ds->tag_8021q_ctx = NULL; + + kfree(ctx); } -EXPORT_SYMBOL_GPL(dsa_8021q_crosschip_bridge_leave); +EXPORT_SYMBOL_GPL(dsa_tag_8021q_unregister); struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci) @@ -471,8 +573,7 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, } EXPORT_SYMBOL_GPL(dsa_8021q_xmit); -void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, - int *subvlan) +void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id) { u16 vid, tci; @@ -489,9 +590,6 @@ void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, *source_port = dsa_8021q_rx_source_port(vid); *switch_id = dsa_8021q_rx_switch_id(vid); - *subvlan = dsa_8021q_rx_subvlan(vid); skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; } EXPORT_SYMBOL_GPL(dsa_8021q_rcv); - -MODULE_LICENSE("GPL v2"); diff --git a/net/dsa/tag_ar9331.c b/net/dsa/tag_ar9331.c index 0efae1a372b3..8a02ac44282f 100644 --- a/net/dsa/tag_ar9331.c +++ b/net/dsa/tag_ar9331.c @@ -44,8 +44,7 @@ static struct sk_buff *ar9331_tag_xmit(struct sk_buff *skb, } static struct sk_buff *ar9331_tag_rcv(struct sk_buff *skb, - struct net_device *ndev, - struct packet_type *pt) + struct net_device *ndev) { u8 ver, port; u16 hdr; diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index 0750af951fc9..96dbb8ee2fee 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -99,7 +99,7 @@ static struct sk_buff *brcm_tag_xmit_ll(struct sk_buff *skb, skb_push(skb, BRCM_TAG_LEN); if (offset) - memmove(skb->data, skb->data + BRCM_TAG_LEN, offset); + dsa_alloc_etype_header(skb, BRCM_TAG_LEN); brcm_tag = skb->data + offset; @@ -136,7 +136,6 @@ static struct sk_buff *brcm_tag_xmit_ll(struct sk_buff *skb, */ static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, unsigned int offset) { int source_port; @@ -167,7 +166,7 @@ static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb, /* Remove Broadcom tag and update checksum */ skb_pull_rcsum(skb, BRCM_TAG_LEN); - skb->offload_fwd_mark = 1; + dsa_default_offload_fwd_mark(skb); return skb; } @@ -182,20 +181,16 @@ static struct sk_buff *brcm_tag_xmit(struct sk_buff *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(struct sk_buff *skb, struct net_device *dev) { 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); + nskb = brcm_tag_rcv_ll(skb, dev, 2); if (!nskb) return nskb; - /* Move the Ethernet DA and SA */ - memmove(nskb->data - ETH_HLEN, - nskb->data - ETH_HLEN - BRCM_TAG_LEN, - 2 * ETH_ALEN); + dsa_strip_etype_header(skb, BRCM_TAG_LEN); return nskb; } @@ -233,7 +228,7 @@ static struct sk_buff *brcm_leg_tag_xmit(struct sk_buff *skb, skb_push(skb, BRCM_LEG_TAG_LEN); - memmove(skb->data, skb->data + BRCM_LEG_TAG_LEN, 2 * ETH_ALEN); + dsa_alloc_etype_header(skb, BRCM_LEG_TAG_LEN); brcm_tag = skb->data + 2 * ETH_ALEN; @@ -251,8 +246,7 @@ static struct sk_buff *brcm_leg_tag_xmit(struct sk_buff *skb, } static struct sk_buff *brcm_leg_tag_rcv(struct sk_buff *skb, - struct net_device *dev, - struct packet_type *pt) + struct net_device *dev) { int source_port; u8 *brcm_tag; @@ -260,7 +254,7 @@ static struct sk_buff *brcm_leg_tag_rcv(struct sk_buff *skb, if (unlikely(!pskb_may_pull(skb, BRCM_LEG_PORT_ID))) return NULL; - brcm_tag = skb->data - 2; + brcm_tag = dsa_etype_header_pos_rx(skb); source_port = brcm_tag[5] & BRCM_LEG_PORT_ID; @@ -271,12 +265,9 @@ static struct sk_buff *brcm_leg_tag_rcv(struct sk_buff *skb, /* Remove Broadcom tag and update checksum */ skb_pull_rcsum(skb, BRCM_LEG_TAG_LEN); - skb->offload_fwd_mark = 1; + dsa_default_offload_fwd_mark(skb); - /* Move the Ethernet DA and SA */ - memmove(skb->data - ETH_HLEN, - skb->data - ETH_HLEN - BRCM_LEG_TAG_LEN, - 2 * ETH_ALEN); + dsa_strip_etype_header(skb, BRCM_LEG_TAG_LEN); return skb; } @@ -302,11 +293,10 @@ static struct sk_buff *brcm_tag_xmit_prepend(struct sk_buff *skb, } static struct sk_buff *brcm_tag_rcv_prepend(struct sk_buff *skb, - struct net_device *dev, - struct packet_type *pt) + struct net_device *dev) { /* tag is prepended to the packet */ - return brcm_tag_rcv_ll(skb, dev, pt, ETH_HLEN); + return brcm_tag_rcv_ll(skb, dev, ETH_HLEN); } static const struct dsa_device_ops brcm_prepend_netdev_ops = { diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index a822355afc90..77d0ce89ab77 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -126,18 +126,53 @@ static struct sk_buff *dsa_xmit_ll(struct sk_buff *skb, struct net_device *dev, u8 extra) { struct dsa_port *dp = dsa_slave_to_port(dev); + u8 tag_dev, tag_port; + enum dsa_cmd cmd; u8 *dsa_header; + u16 pvid = 0; + int err; + + if (skb->offload_fwd_mark) { + struct dsa_switch_tree *dst = dp->ds->dst; + struct net_device *br = dp->bridge_dev; + + cmd = DSA_CMD_FORWARD; + + /* When offloading forwarding for a bridge, inject FORWARD + * packets on behalf of a virtual switch device with an index + * past the physical switches. + */ + tag_dev = dst->last_switch + 1 + dp->bridge_num; + tag_port = 0; + + /* If we are offloading forwarding for a VLAN-unaware bridge, + * inject packets to hardware using the bridge's pvid, since + * that's where the packets ingressed from. + */ + if (!br_vlan_enabled(br)) { + /* Safe because __dev_queue_xmit() runs under + * rcu_read_lock_bh() + */ + err = br_vlan_get_pvid_rcu(br, &pvid); + if (err) + return NULL; + } + } else { + cmd = DSA_CMD_FROM_CPU; + tag_dev = dp->ds->index; + tag_port = dp->index; + } if (skb->protocol == htons(ETH_P_8021Q)) { if (extra) { skb_push(skb, extra); - memmove(skb->data, skb->data + extra, 2 * ETH_ALEN); + dsa_alloc_etype_header(skb, extra); } - /* Construct tagged FROM_CPU DSA tag from 802.1Q tag. */ - dsa_header = skb->data + 2 * ETH_ALEN + extra; - dsa_header[0] = (DSA_CMD_FROM_CPU << 6) | 0x20 | dp->ds->index; - dsa_header[1] = dp->index << 3; + /* Construct tagged DSA tag from 802.1Q tag. */ + dsa_header = dsa_etype_header_pos_tx(skb) + extra; + dsa_header[0] = (cmd << 6) | 0x20 | tag_dev; + dsa_header[1] = tag_port << 3; /* Move CFI field from byte 2 to byte 1. */ if (dsa_header[2] & 0x10) { @@ -146,14 +181,15 @@ static struct sk_buff *dsa_xmit_ll(struct sk_buff *skb, struct net_device *dev, } } else { skb_push(skb, DSA_HLEN + extra); - memmove(skb->data, skb->data + DSA_HLEN + extra, 2 * ETH_ALEN); - - /* Construct untagged FROM_CPU DSA tag. */ - dsa_header = skb->data + 2 * ETH_ALEN + extra; - dsa_header[0] = (DSA_CMD_FROM_CPU << 6) | dp->ds->index; - dsa_header[1] = dp->index << 3; - dsa_header[2] = 0x00; - dsa_header[3] = 0x00; + dsa_alloc_etype_header(skb, DSA_HLEN + extra); + + /* Construct untagged DSA tag. */ + dsa_header = dsa_etype_header_pos_tx(skb) + extra; + + dsa_header[0] = (cmd << 6) | tag_dev; + dsa_header[1] = tag_port << 3; + dsa_header[2] = pvid >> 8; + dsa_header[3] = pvid & 0xff; } return skb; @@ -162,20 +198,18 @@ static struct sk_buff *dsa_xmit_ll(struct sk_buff *skb, struct net_device *dev, static struct sk_buff *dsa_rcv_ll(struct sk_buff *skb, struct net_device *dev, u8 extra) { + bool trap = false, trunk = false; int source_device, source_port; - bool trunk = false; enum dsa_code code; enum dsa_cmd cmd; u8 *dsa_header; /* The ethertype field is part of the DSA header. */ - dsa_header = skb->data - 2; + dsa_header = dsa_etype_header_pos_rx(skb); cmd = dsa_header[0] >> 6; switch (cmd) { case DSA_CMD_FORWARD: - skb->offload_fwd_mark = 1; - trunk = !!(dsa_header[1] & 7); break; @@ -194,7 +228,6 @@ static struct sk_buff *dsa_rcv_ll(struct sk_buff *skb, struct net_device *dev, * device (like a bridge) that forwarding has * already been done by hardware. */ - skb->offload_fwd_mark = 1; break; case DSA_CODE_MGMT_TRAP: case DSA_CODE_IGMP_MLD_TRAP: @@ -202,6 +235,7 @@ static struct sk_buff *dsa_rcv_ll(struct sk_buff *skb, struct net_device *dev, /* Traps have, by definition, not been * forwarded by hardware, so don't mark them. */ + trap = true; break; default: /* Reserved code, this could be anything. Drop @@ -235,6 +269,15 @@ static struct sk_buff *dsa_rcv_ll(struct sk_buff *skb, struct net_device *dev, if (!skb->dev) return NULL; + /* When using LAG offload, skb->dev is not a DSA slave interface, + * so we cannot call dsa_default_offload_fwd_mark and we need to + * special-case it. + */ + if (trunk) + skb->offload_fwd_mark = true; + else if (!trap) + dsa_default_offload_fwd_mark(skb); + /* If the 'tagged' bit is set; convert the DSA tag to a 802.1Q * tag, and delete the ethertype (extra) if applicable. If the * 'tagged' bit is cleared; delete the DSA tag, and ethertype @@ -269,14 +312,10 @@ static struct sk_buff *dsa_rcv_ll(struct sk_buff *skb, struct net_device *dev, memcpy(dsa_header, new_header, DSA_HLEN); if (extra) - memmove(skb->data - ETH_HLEN, - skb->data - ETH_HLEN - extra, - 2 * ETH_ALEN); + dsa_strip_etype_header(skb, extra); } else { skb_pull_rcsum(skb, DSA_HLEN); - memmove(skb->data - ETH_HLEN, - skb->data - ETH_HLEN - DSA_HLEN - extra, - 2 * ETH_ALEN); + dsa_strip_etype_header(skb, DSA_HLEN + extra); } return skb; @@ -289,8 +328,7 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev) return dsa_xmit_ll(skb, dev, 0); } -static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt) +static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev) { if (unlikely(!pskb_may_pull(skb, DSA_HLEN))) return NULL; @@ -322,7 +360,7 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) if (!skb) return NULL; - edsa_header = skb->data + 2 * ETH_ALEN; + edsa_header = dsa_etype_header_pos_tx(skb); edsa_header[0] = (ETH_P_EDSA >> 8) & 0xff; edsa_header[1] = ETH_P_EDSA & 0xff; edsa_header[2] = 0x00; @@ -330,8 +368,7 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) return skb; } -static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt) +static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev) { if (unlikely(!pskb_may_pull(skb, EDSA_HLEN))) return NULL; diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c index 5985dab06ab8..df7140984da3 100644 --- a/net/dsa/tag_gswip.c +++ b/net/dsa/tag_gswip.c @@ -75,8 +75,7 @@ static struct sk_buff *gswip_tag_xmit(struct sk_buff *skb, } static struct sk_buff *gswip_tag_rcv(struct sk_buff *skb, - struct net_device *dev, - struct packet_type *pt) + struct net_device *dev) { int port; u8 *gswip_tag; diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c index 424130f85f59..f64b805303cd 100644 --- a/net/dsa/tag_hellcreek.c +++ b/net/dsa/tag_hellcreek.c @@ -29,8 +29,7 @@ static struct sk_buff *hellcreek_xmit(struct sk_buff *skb, } static struct sk_buff *hellcreek_rcv(struct sk_buff *skb, - struct net_device *dev, - struct packet_type *pt) + struct net_device *dev) { /* Tag decoding */ u8 *tag = skb_tail_pointer(skb) - HELLCREEK_TAG_LEN; @@ -44,7 +43,7 @@ static struct sk_buff *hellcreek_rcv(struct sk_buff *skb, pskb_trim_rcsum(skb, skb->len - HELLCREEK_TAG_LEN); - skb->offload_fwd_mark = true; + dsa_default_offload_fwd_mark(skb); return skb; } diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index a201ccf2435d..fa1d60d13ad9 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -24,7 +24,7 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, pskb_trim_rcsum(skb, skb->len - len); - skb->offload_fwd_mark = true; + dsa_default_offload_fwd_mark(skb); return skb; } @@ -67,8 +67,7 @@ static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev) return skb; } -static struct sk_buff *ksz8795_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt) +static struct sk_buff *ksz8795_rcv(struct sk_buff *skb, struct net_device *dev) { u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; @@ -134,8 +133,7 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb, return skb; } -static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt) +static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev) { /* Tag decoding */ u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c index 26207ef39ebc..cb548188f813 100644 --- a/net/dsa/tag_lan9303.c +++ b/net/dsa/tag_lan9303.c @@ -62,9 +62,10 @@ static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev) skb_push(skb, LAN9303_TAG_LEN); /* make room between MACs and Ether-Type */ - memmove(skb->data, skb->data + LAN9303_TAG_LEN, 2 * ETH_ALEN); + dsa_alloc_etype_header(skb, LAN9303_TAG_LEN); + + lan9303_tag = dsa_etype_header_pos_tx(skb); - lan9303_tag = (__be16 *)(skb->data + 2 * ETH_ALEN); tag = lan9303_xmit_use_arl(dp, skb->data) ? LAN9303_TAG_TX_USE_ALR : dp->index | LAN9303_TAG_TX_STP_OVERRIDE; @@ -74,8 +75,7 @@ static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev) return skb; } -static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt) +static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev) { __be16 *lan9303_tag; u16 lan9303_tag1; @@ -87,13 +87,7 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev, return NULL; } - /* '->data' points into the middle of our special VLAN tag information: - * - * ~ MAC src | 0x81 | 0x00 | 0xyy | 0xzz | ether type - * ^ - * ->data - */ - lan9303_tag = (__be16 *)(skb->data - 2); + lan9303_tag = dsa_etype_header_pos_rx(skb); if (lan9303_tag[0] != htons(ETH_P_8021Q)) { dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid VLAN marker\n"); @@ -113,9 +107,11 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev, * 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); - skb->offload_fwd_mark = !(lan9303_tag1 & LAN9303_TAG_RX_TRAPPED_TO_CPU); + + dsa_strip_etype_header(skb, LAN9303_TAG_LEN); + + if (!(lan9303_tag1 & LAN9303_TAG_RX_TRAPPED_TO_CPU)) + dsa_default_offload_fwd_mark(skb); return skb; } diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index cc3ba864ad5b..415d8ece242a 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -41,10 +41,10 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, default: xmit_tpid = MTK_HDR_XMIT_UNTAGGED; skb_push(skb, MTK_HDR_LEN); - memmove(skb->data, skb->data + MTK_HDR_LEN, 2 * ETH_ALEN); + dsa_alloc_etype_header(skb, MTK_HDR_LEN); } - mtk_tag = skb->data + 2 * ETH_ALEN; + mtk_tag = dsa_etype_header_pos_tx(skb); /* Mark tag attribute on special tag insertion to notify hardware * whether that's a combined special tag with 802.1Q header. @@ -61,8 +61,7 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, return skb; } -static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt) +static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev) { u16 hdr; int port; @@ -71,19 +70,13 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, if (unlikely(!pskb_may_pull(skb, MTK_HDR_LEN))) return NULL; - /* The MTK header is added by the switch between src addr - * and ethertype at this point, skb->data points to 2 bytes - * after src addr so header should be 2 bytes right before. - */ - phdr = (__be16 *)(skb->data - 2); + phdr = dsa_etype_header_pos_rx(skb); hdr = ntohs(*phdr); /* Remove MTK tag and recalculate checksum. */ skb_pull_rcsum(skb, MTK_HDR_LEN); - memmove(skb->data - ETH_HLEN, - skb->data - ETH_HLEN - MTK_HDR_LEN, - 2 * ETH_ALEN); + dsa_strip_etype_header(skb, MTK_HDR_LEN); /* Get source port information */ port = (hdr & MTK_HDR_RECV_SOURCE_PORT_MASK); @@ -92,7 +85,7 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, if (!skb->dev) return NULL; - skb->offload_fwd_mark = 1; + dsa_default_offload_fwd_mark(skb); return skb; } diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index 190f4bfd3bef..d37ab98e7fe1 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -55,8 +55,7 @@ static struct sk_buff *seville_xmit(struct sk_buff *skb, } static struct sk_buff *ocelot_rcv(struct sk_buff *skb, - struct net_device *netdev, - struct packet_type *pt) + struct net_device *netdev) { u64 src_port, qos_class; u64 vlan_tci, tag_type; @@ -104,7 +103,7 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, */ return NULL; - skb->offload_fwd_mark = 1; + dsa_default_offload_fwd_mark(skb); skb->priority = qos_class; /* Ocelot switches copy frames unmodified to the CPU. However, it is diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index 85ac85c3af8c..3038a257ba05 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -38,18 +38,17 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb, } static struct sk_buff *ocelot_rcv(struct sk_buff *skb, - struct net_device *netdev, - struct packet_type *pt) + struct net_device *netdev) { - int src_port, switch_id, subvlan; + int src_port, switch_id; - dsa_8021q_rcv(skb, &src_port, &switch_id, &subvlan); + dsa_8021q_rcv(skb, &src_port, &switch_id); skb->dev = dsa_master_find_slave(netdev, switch_id, src_port); if (!skb->dev) return NULL; - skb->offload_fwd_mark = 1; + dsa_default_offload_fwd_mark(skb); return skb; } diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index 693bda013065..1ea9401b8ace 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -36,8 +36,8 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) skb_push(skb, QCA_HDR_LEN); - memmove(skb->data, skb->data + QCA_HDR_LEN, 2 * ETH_ALEN); - phdr = (__be16 *)(skb->data + 2 * ETH_ALEN); + dsa_alloc_etype_header(skb, QCA_HDR_LEN); + phdr = dsa_etype_header_pos_tx(skb); /* Set the version field, and set destination port information */ hdr = QCA_HDR_VERSION << QCA_HDR_XMIT_VERSION_S | @@ -48,8 +48,7 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) return skb; } -static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt) +static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev) { u8 ver; u16 hdr; @@ -59,11 +58,7 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, if (unlikely(!pskb_may_pull(skb, QCA_HDR_LEN))) return NULL; - /* The QCA header is added by the switch between src addr and Ethertype - * At this point, skb->data points to ethertype so header should be - * right before - */ - phdr = (__be16 *)(skb->data - 2); + phdr = dsa_etype_header_pos_rx(skb); hdr = ntohs(*phdr); /* Make sure the version is correct */ @@ -73,8 +68,7 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, /* Remove QCA tag and recalculate checksum */ skb_pull_rcsum(skb, QCA_HDR_LEN); - memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - QCA_HDR_LEN, - ETH_HLEN - QCA_HDR_LEN); + dsa_strip_etype_header(skb, QCA_HDR_LEN); /* Get source port information */ port = (hdr & QCA_HDR_RECV_SOURCE_PORT_MASK); diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c index 57c46b4ab2b3..f920487ae145 100644 --- a/net/dsa/tag_rtl4_a.c +++ b/net/dsa/tag_rtl4_a.c @@ -47,16 +47,17 @@ static struct sk_buff *rtl4a_tag_xmit(struct sk_buff *skb, dp->index); skb_push(skb, RTL4_A_HDR_LEN); - memmove(skb->data, skb->data + RTL4_A_HDR_LEN, 2 * ETH_ALEN); - tag = skb->data + 2 * ETH_ALEN; + dsa_alloc_etype_header(skb, RTL4_A_HDR_LEN); + tag = dsa_etype_header_pos_tx(skb); /* Set Ethertype */ p = (__be16 *)tag; *p = htons(RTL4_A_ETHERTYPE); - out = (RTL4_A_PROTOCOL_RTL8366RB << 12) | (2 << 8); - /* The lower bits is the port number */ - out |= (u8)dp->index; + out = (RTL4_A_PROTOCOL_RTL8366RB << RTL4_A_PROTOCOL_SHIFT) | (2 << 8); + /* The lower bits indicate the port number */ + out |= BIT(dp->index); + p = (__be16 *)(tag + 2); *p = htons(out); @@ -64,8 +65,7 @@ static struct sk_buff *rtl4a_tag_xmit(struct sk_buff *skb, } static struct sk_buff *rtl4a_tag_rcv(struct sk_buff *skb, - struct net_device *dev, - struct packet_type *pt) + struct net_device *dev) { u16 protport; __be16 *p; @@ -77,12 +77,7 @@ static struct sk_buff *rtl4a_tag_rcv(struct sk_buff *skb, if (unlikely(!pskb_may_pull(skb, RTL4_A_HDR_LEN))) return NULL; - /* The RTL4 header has its own custom Ethertype 0x8899 and that - * starts right at the beginning of the packet, after the src - * ethernet addr. Apparently skb->data always points 2 bytes in, - * behind the Ethertype. - */ - tag = skb->data - 2; + tag = dsa_etype_header_pos_rx(skb); p = (__be16 *)tag; etype = ntohs(*p); if (etype != RTL4_A_ETHERTYPE) { @@ -109,12 +104,9 @@ static struct sk_buff *rtl4a_tag_rcv(struct sk_buff *skb, /* Remove RTL4 tag and recalculate checksum */ skb_pull_rcsum(skb, RTL4_A_HDR_LEN); - /* Move ethernet DA and SA in front of the data */ - memmove(skb->data - ETH_HLEN, - skb->data - ETH_HLEN - RTL4_A_HDR_LEN, - 2 * ETH_ALEN); + dsa_strip_etype_header(skb, RTL4_A_HDR_LEN); - skb->offload_fwd_mark = 1; + dsa_default_offload_fwd_mark(skb); return skb; } diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 9c2df9ece01b..c054f48541c8 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -115,56 +115,117 @@ static inline bool sja1105_is_meta_frame(const struct sk_buff *skb) return true; } -static bool sja1105_can_use_vlan_as_tags(const struct sk_buff *skb) +/* Calls sja1105_port_deferred_xmit in sja1105_main.c */ +static struct sk_buff *sja1105_defer_xmit(struct dsa_port *dp, + struct sk_buff *skb) { - struct vlan_ethhdr *hdr = vlan_eth_hdr(skb); - u16 vlan_tci; - - if (hdr->h_vlan_proto == htons(ETH_P_SJA1105)) - return true; + struct sja1105_port *sp = dp->priv; - if (hdr->h_vlan_proto != htons(ETH_P_8021Q) && - !skb_vlan_tag_present(skb)) - return false; + if (!dsa_port_is_sja1105(dp)) + return skb; - if (skb_vlan_tag_present(skb)) - vlan_tci = skb_vlan_tag_get(skb); - else - vlan_tci = ntohs(hdr->h_vlan_TCI); + /* Increase refcount so the kfree_skb in dsa_slave_xmit + * won't really free the packet. + */ + skb_queue_tail(&sp->xmit_queue, skb_get(skb)); + kthread_queue_work(sp->xmit_worker, &sp->xmit_work); - return vid_is_dsa_8021q(vlan_tci & VLAN_VID_MASK); + return NULL; } -/* This is the first time the tagger sees the frame on RX. - * Figure out if we can decode it. +/* Send VLAN tags with a TPID that blends in with whatever VLAN protocol a + * bridge spanning ports of this switch might have. */ -static bool sja1105_filter(const struct sk_buff *skb, struct net_device *dev) +static u16 sja1105_xmit_tpid(struct dsa_port *dp) { - if (sja1105_can_use_vlan_as_tags(skb)) - return true; - if (sja1105_is_link_local(skb)) - return true; - if (sja1105_is_meta_frame(skb)) - return true; - return false; + struct dsa_switch *ds = dp->ds; + struct dsa_port *other_dp; + u16 proto; + + /* Since VLAN awareness is global, then if this port is VLAN-unaware, + * all ports are. Use the VLAN-unaware TPID used for tag_8021q. + */ + if (!dsa_port_is_vlan_filtering(dp)) + return ETH_P_SJA1105; + + /* Port is VLAN-aware, so there is a bridge somewhere (a single one, + * we're sure about that). It may not be on this port though, so we + * need to find it. + */ + list_for_each_entry(other_dp, &ds->dst->ports, list) { + if (other_dp->ds != ds) + continue; + + if (!other_dp->bridge_dev) + continue; + + /* Error is returned only if CONFIG_BRIDGE_VLAN_FILTERING, + * which seems pointless to handle, as our port cannot become + * VLAN-aware in that case. + */ + br_vlan_get_proto(other_dp->bridge_dev, &proto); + + return proto; + } + + WARN_ONCE(1, "Port is VLAN-aware but cannot find associated bridge!\n"); + + return ETH_P_SJA1105; } -/* Calls sja1105_port_deferred_xmit in sja1105_main.c */ -static struct sk_buff *sja1105_defer_xmit(struct sja1105_port *sp, - struct sk_buff *skb) +static struct sk_buff *sja1105_imprecise_xmit(struct sk_buff *skb, + struct net_device *netdev) { - /* Increase refcount so the kfree_skb in dsa_slave_xmit - * won't really free the packet. + struct dsa_port *dp = dsa_slave_to_port(netdev); + struct net_device *br = dp->bridge_dev; + u16 tx_vid; + + /* If the port is under a VLAN-aware bridge, just slide the + * VLAN-tagged packet into the FDB and hope for the best. + * This works because we support a single VLAN-aware bridge + * across the entire dst, and its VLANs cannot be shared with + * any standalone port. */ - skb_queue_tail(&sp->xmit_queue, skb_get(skb)); - kthread_queue_work(sp->xmit_worker, &sp->xmit_work); + if (br_vlan_enabled(br)) + return skb; - return NULL; + /* If the port is under a VLAN-unaware bridge, use an imprecise + * TX VLAN that targets the bridge's entire broadcast domain, + * instead of just the specific port. + */ + tx_vid = dsa_8021q_bridge_tx_fwd_offload_vid(dp->bridge_num); + + return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp), tx_vid); } -static u16 sja1105_xmit_tpid(struct sja1105_port *sp) +/* Transform untagged control packets into pvid-tagged control packets so that + * all packets sent by this tagger are VLAN-tagged and we can configure the + * switch to drop untagged packets coming from the DSA master. + */ +static struct sk_buff *sja1105_pvid_tag_control_pkt(struct dsa_port *dp, + struct sk_buff *skb, u8 pcp) { - return sp->xmit_tpid; + __be16 xmit_tpid = htons(sja1105_xmit_tpid(dp)); + struct vlan_ethhdr *hdr; + + /* If VLAN tag is in hwaccel area, move it to the payload + * to deal with both cases uniformly and to ensure that + * the VLANs are added in the right order. + */ + if (unlikely(skb_vlan_tag_present(skb))) { + skb = __vlan_hwaccel_push_inside(skb); + if (!skb) + return NULL; + } + + hdr = (struct vlan_ethhdr *)skb_mac_header(skb); + + /* If skb is already VLAN-tagged, leave that VLAN ID in place */ + if (hdr->h_vlan_proto == xmit_tpid) + return skb; + + return vlan_insert_tag(skb, xmit_tpid, (pcp << VLAN_PRIO_SHIFT) | + SJA1105_DEFAULT_VLAN); } static struct sk_buff *sja1105_xmit(struct sk_buff *skb, @@ -175,14 +236,22 @@ static struct sk_buff *sja1105_xmit(struct sk_buff *skb, u16 queue_mapping = skb_get_queue_mapping(skb); u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); + if (skb->offload_fwd_mark) + return sja1105_imprecise_xmit(skb, netdev); + /* Transmitting management traffic does not rely upon switch tagging, * but instead SPI-installed management routes. Part 2 of this * is the .port_deferred_xmit driver callback. */ - if (unlikely(sja1105_is_link_local(skb))) - return sja1105_defer_xmit(dp->priv, skb); + if (unlikely(sja1105_is_link_local(skb))) { + skb = sja1105_pvid_tag_control_pkt(dp, skb, pcp); + if (!skb) + return NULL; + + return sja1105_defer_xmit(dp, skb); + } - return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp->priv), + return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp), ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); } @@ -194,43 +263,45 @@ static struct sk_buff *sja1110_xmit(struct sk_buff *skb, u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index); u16 queue_mapping = skb_get_queue_mapping(skb); u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); - struct ethhdr *eth_hdr; __be32 *tx_trailer; __be16 *tx_header; int trailer_pos; + if (skb->offload_fwd_mark) + return sja1105_imprecise_xmit(skb, netdev); + /* Transmitting control packets is done using in-band control * extensions, while data packets are transmitted using * tag_8021q TX VLANs. */ if (likely(!sja1105_is_link_local(skb))) - return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp->priv), + return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp), ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); + skb = sja1105_pvid_tag_control_pkt(dp, skb, pcp); + if (!skb) + return NULL; + skb_push(skb, SJA1110_HEADER_LEN); - /* Move Ethernet header to the left, making space for DSA tag */ - memmove(skb->data, skb->data + SJA1110_HEADER_LEN, 2 * ETH_ALEN); + dsa_alloc_etype_header(skb, SJA1110_HEADER_LEN); trailer_pos = skb->len; - /* On TX, skb->data points to skb_mac_header(skb) */ - eth_hdr = (struct ethhdr *)skb->data; - tx_header = (__be16 *)(eth_hdr + 1); + tx_header = dsa_etype_header_pos_tx(skb); tx_trailer = skb_put(skb, SJA1110_TX_TRAILER_LEN); - eth_hdr->h_proto = htons(ETH_P_SJA1110); - - *tx_header = htons(SJA1110_HEADER_HOST_TO_SWITCH | - SJA1110_TX_HEADER_HAS_TRAILER | - SJA1110_TX_HEADER_TRAILER_POS(trailer_pos)); + tx_header[0] = htons(ETH_P_SJA1110); + tx_header[1] = htons(SJA1110_HEADER_HOST_TO_SWITCH | + SJA1110_TX_HEADER_HAS_TRAILER | + SJA1110_TX_HEADER_TRAILER_POS(trailer_pos)); *tx_trailer = cpu_to_be32(SJA1110_TX_TRAILER_PRIO(pcp) | SJA1110_TX_TRAILER_SWITCHID(dp->ds->index) | SJA1110_TX_TRAILER_DESTPORTS(BIT(dp->index))); if (clone) { u8 ts_id = SJA1105_SKB_CB(clone)->ts_id; - *tx_header |= htons(SJA1110_TX_HEADER_TAKE_TS); + tx_header[1] |= htons(SJA1110_TX_HEADER_TAKE_TS); *tx_trailer |= cpu_to_be32(SJA1110_TX_TRAILER_TSTAMP_ID(ts_id)); } @@ -273,16 +344,16 @@ static struct sk_buff bool is_link_local, bool is_meta) { - struct sja1105_port *sp; - struct dsa_port *dp; - - dp = dsa_slave_to_port(skb->dev); - sp = dp->priv; - /* Step 1: A timestampable frame was received. * Buffer it until we get its meta frame. */ if (is_link_local) { + struct dsa_port *dp = dsa_slave_to_port(skb->dev); + struct sja1105_port *sp = dp->priv; + + if (unlikely(!dsa_port_is_sja1105(dp))) + return skb; + if (!test_bit(SJA1105_HWTS_RX_EN, &sp->data->state)) /* Do normal processing. */ return skb; @@ -315,8 +386,13 @@ static struct sk_buff * frame, which serves no further purpose). */ } else if (is_meta) { + struct dsa_port *dp = dsa_slave_to_port(skb->dev); + struct sja1105_port *sp = dp->priv; struct sk_buff *stampable_skb; + if (unlikely(!dsa_port_is_sja1105(dp))) + return skb; + /* Drop the meta frame if we're not in the right state * to process it. */ @@ -358,20 +434,6 @@ static struct sk_buff return skb; } -static void sja1105_decode_subvlan(struct sk_buff *skb, u16 subvlan) -{ - struct dsa_port *dp = dsa_slave_to_port(skb->dev); - struct sja1105_port *sp = dp->priv; - u16 vid = sp->subvlan_map[subvlan]; - u16 vlan_tci; - - if (vid == VLAN_N_VID) - return; - - vlan_tci = (skb->priority << VLAN_PRIO_SHIFT) | vid; - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci); -} - static bool sja1105_skb_has_tag_8021q(const struct sk_buff *skb) { u16 tpid = ntohs(eth_hdr(skb)->h_proto); @@ -385,25 +447,45 @@ static bool sja1110_skb_has_inband_control_extension(const struct sk_buff *skb) return ntohs(eth_hdr(skb)->h_proto) == ETH_P_SJA1110; } +/* If the VLAN in the packet is a tag_8021q one, set @source_port and + * @switch_id and strip the header. Otherwise set @vid and keep it in the + * packet. + */ +static void sja1105_vlan_rcv(struct sk_buff *skb, int *source_port, + int *switch_id, u16 *vid) +{ + struct vlan_ethhdr *hdr = (struct vlan_ethhdr *)skb_mac_header(skb); + u16 vlan_tci; + + if (skb_vlan_tag_present(skb)) + vlan_tci = skb_vlan_tag_get(skb); + else + vlan_tci = ntohs(hdr->h_vlan_TCI); + + if (vid_is_dsa_8021q_rxvlan(vlan_tci & VLAN_VID_MASK)) + return dsa_8021q_rcv(skb, source_port, switch_id); + + /* Try our best with imprecise RX */ + *vid = vlan_tci & VLAN_VID_MASK; +} + static struct sk_buff *sja1105_rcv(struct sk_buff *skb, - struct net_device *netdev, - struct packet_type *pt) + struct net_device *netdev) { - int source_port, switch_id, subvlan = 0; + int source_port = -1, switch_id = -1; struct sja1105_meta meta = {0}; struct ethhdr *hdr; bool is_link_local; bool is_meta; + u16 vid; hdr = eth_hdr(skb); is_link_local = sja1105_is_link_local(skb); is_meta = sja1105_is_meta_frame(skb); - skb->offload_fwd_mark = 1; - if (sja1105_skb_has_tag_8021q(skb)) { /* Normal traffic path. */ - dsa_8021q_rcv(skb, &source_port, &switch_id, &subvlan); + sja1105_vlan_rcv(skb, &source_port, &switch_id, &vid); } else if (is_link_local) { /* Management traffic path. Switch embeds the switch ID and * port ID into bytes of the destination MAC, courtesy of @@ -422,14 +504,17 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, return NULL; } - skb->dev = dsa_master_find_slave(netdev, switch_id, source_port); + if (source_port == -1 || switch_id == -1) + skb->dev = dsa_find_designated_bridge_port_by_vid(netdev, vid); + else + skb->dev = dsa_master_find_slave(netdev, switch_id, source_port); if (!skb->dev) { netdev_warn(netdev, "Couldn't decode source port\n"); return NULL; } - if (subvlan) - sja1105_decode_subvlan(skb, subvlan); + if (!is_link_local) + dsa_default_offload_fwd_mark(skb); return sja1105_rcv_meta_state_machine(skb, &meta, is_link_local, is_meta); @@ -437,11 +522,11 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, static struct sk_buff *sja1110_rcv_meta(struct sk_buff *skb, u16 rx_header) { + u8 *buf = dsa_etype_header_pos_rx(skb) + SJA1110_HEADER_LEN; int switch_id = SJA1110_RX_HEADER_SWITCH_ID(rx_header); int n_ts = SJA1110_RX_HEADER_N_TS(rx_header); struct net_device *master = skb->dev; struct dsa_port *cpu_dp; - u8 *buf = skb->data + 2; struct dsa_switch *ds; int i; @@ -474,7 +559,8 @@ static struct sk_buff *sja1110_rcv_meta(struct sk_buff *skb, u16 rx_header) static struct sk_buff *sja1110_rcv_inband_control_extension(struct sk_buff *skb, int *source_port, - int *switch_id) + int *switch_id, + bool *host_only) { u16 rx_header; @@ -488,6 +574,9 @@ static struct sk_buff *sja1110_rcv_inband_control_extension(struct sk_buff *skb, */ rx_header = ntohs(*(__be16 *)skb->data); + if (rx_header & SJA1110_RX_HEADER_HOST_ONLY) + *host_only = true; + if (rx_header & SJA1110_RX_HEADER_IS_METADATA) return sja1110_rcv_meta(skb, rx_header); @@ -522,9 +611,7 @@ static struct sk_buff *sja1110_rcv_inband_control_extension(struct sk_buff *skb, /* Advance skb->data past the DSA header */ skb_pull_rcsum(skb, SJA1110_HEADER_LEN); - /* Remove the DSA header */ - memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - SJA1110_HEADER_LEN, - 2 * ETH_ALEN); + dsa_strip_etype_header(skb, SJA1110_HEADER_LEN); /* With skb->data in its final place, update the MAC header * so that eth_hdr() continues to works properly. @@ -535,34 +622,35 @@ static struct sk_buff *sja1110_rcv_inband_control_extension(struct sk_buff *skb, } static struct sk_buff *sja1110_rcv(struct sk_buff *skb, - struct net_device *netdev, - struct packet_type *pt) + struct net_device *netdev) { - int source_port = -1, switch_id = -1, subvlan = 0; - - skb->offload_fwd_mark = 1; + int source_port = -1, switch_id = -1; + bool host_only = false; + u16 vid = 0; if (sja1110_skb_has_inband_control_extension(skb)) { skb = sja1110_rcv_inband_control_extension(skb, &source_port, - &switch_id); + &switch_id, + &host_only); if (!skb) return NULL; } /* Packets with in-band control extensions might still have RX VLANs */ if (likely(sja1105_skb_has_tag_8021q(skb))) - dsa_8021q_rcv(skb, &source_port, &switch_id, &subvlan); + sja1105_vlan_rcv(skb, &source_port, &switch_id, &vid); - skb->dev = dsa_master_find_slave(netdev, switch_id, source_port); + if (source_port == -1 || switch_id == -1) + skb->dev = dsa_find_designated_bridge_port_by_vid(netdev, vid); + else + skb->dev = dsa_master_find_slave(netdev, switch_id, source_port); if (!skb->dev) { - netdev_warn(netdev, - "Couldn't decode source port %d and switch id %d\n", - source_port, switch_id); + netdev_warn(netdev, "Couldn't decode source port\n"); return NULL; } - if (subvlan) - sja1105_decode_subvlan(skb, subvlan); + if (!host_only) + dsa_default_offload_fwd_mark(skb); return skb; } @@ -596,7 +684,6 @@ static const struct dsa_device_ops sja1105_netdev_ops = { .proto = DSA_TAG_PROTO_SJA1105, .xmit = sja1105_xmit, .rcv = sja1105_rcv, - .filter = sja1105_filter, .needed_headroom = VLAN_HLEN, .flow_dissect = sja1105_flow_dissect, .promisc_on_master = true, @@ -610,7 +697,6 @@ static const struct dsa_device_ops sja1110_netdev_ops = { .proto = DSA_TAG_PROTO_SJA1110, .xmit = sja1110_xmit, .rcv = sja1110_rcv, - .filter = sja1105_filter, .flow_dissect = sja1110_flow_dissect, .needed_headroom = SJA1110_HEADER_LEN + VLAN_HLEN, .needed_tailroom = SJA1110_RX_TRAILER_LEN + SJA1110_MAX_PADDING_LEN, diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index ba73804340a5..5749ba85c2b8 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -24,8 +24,7 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) return skb; } -static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt) +static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev) { u8 *trailer; int source_port; diff --git a/net/dsa/tag_xrs700x.c b/net/dsa/tag_xrs700x.c index a31ff7fcb45f..ff442b8af636 100644 --- a/net/dsa/tag_xrs700x.c +++ b/net/dsa/tag_xrs700x.c @@ -25,8 +25,7 @@ static struct sk_buff *xrs700x_xmit(struct sk_buff *skb, struct net_device *dev) return skb; } -static struct sk_buff *xrs700x_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt) +static struct sk_buff *xrs700x_rcv(struct sk_buff *skb, struct net_device *dev) { int source_port; u8 *trailer; @@ -46,7 +45,7 @@ static struct sk_buff *xrs700x_rcv(struct sk_buff *skb, struct net_device *dev, return NULL; /* Frame is forwarded by hardware, don't forward in software. */ - skb->offload_fwd_mark = 1; + dsa_default_offload_fwd_mark(skb); return skb; } diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 9cce612e8976..73fce9467467 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -62,8 +62,6 @@ #include <linux/uaccess.h> #include <net/pkt_sched.h> -__setup("ether=", netdev_boot_setup); - /** * eth_header - create the Ethernet header * @skb: buffer to alter @@ -182,12 +180,8 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) * at all, so we check here whether one of those tagging * variants has been configured on the receiving interface, * and if so, set skb->protocol without looking at the packet. - * The DSA tagging protocol may be able to decode some but not all - * traffic (for example only for management). In that case give it the - * option to filter the packets from which it can decode source port - * information. */ - if (unlikely(netdev_uses_dsa(dev)) && dsa_can_decode(skb, dev)) + if (unlikely(netdev_uses_dsa(dev))) return htons(ETH_P_XDSA); if (likely(eth_proto_is_802_3(eth->h_proto))) diff --git a/net/ethtool/coalesce.c b/net/ethtool/coalesce.c index 1d6bc132aa4d..46776ea42a92 100644 --- a/net/ethtool/coalesce.c +++ b/net/ethtool/coalesce.c @@ -10,6 +10,7 @@ struct coalesce_req_info { struct coalesce_reply_data { struct ethnl_reply_data base; struct ethtool_coalesce coalesce; + struct kernel_ethtool_coalesce kernel_coalesce; u32 supported_params; }; @@ -61,6 +62,7 @@ static int coalesce_prepare_data(const struct ethnl_req_info *req_base, struct genl_info *info) { struct coalesce_reply_data *data = COALESCE_REPDATA(reply_base); + struct netlink_ext_ack *extack = info ? info->extack : NULL; struct net_device *dev = reply_base->dev; int ret; @@ -70,7 +72,8 @@ static int coalesce_prepare_data(const struct ethnl_req_info *req_base, ret = ethnl_ops_begin(dev); if (ret < 0) return ret; - ret = dev->ethtool_ops->get_coalesce(dev, &data->coalesce); + ret = dev->ethtool_ops->get_coalesce(dev, &data->coalesce, + &data->kernel_coalesce, extack); ethnl_ops_complete(dev); return ret; @@ -100,7 +103,9 @@ static int coalesce_reply_size(const struct ethnl_req_info *req_base, nla_total_size(sizeof(u32)) + /* _RX_MAX_FRAMES_HIGH */ nla_total_size(sizeof(u32)) + /* _TX_USECS_HIGH */ nla_total_size(sizeof(u32)) + /* _TX_MAX_FRAMES_HIGH */ - nla_total_size(sizeof(u32)); /* _RATE_SAMPLE_INTERVAL */ + nla_total_size(sizeof(u32)) + /* _RATE_SAMPLE_INTERVAL */ + nla_total_size(sizeof(u8)) + /* _USE_CQE_MODE_TX */ + nla_total_size(sizeof(u8)); /* _USE_CQE_MODE_RX */ } static bool coalesce_put_u32(struct sk_buff *skb, u16 attr_type, u32 val, @@ -124,6 +129,7 @@ static int coalesce_fill_reply(struct sk_buff *skb, const struct ethnl_reply_data *reply_base) { const struct coalesce_reply_data *data = COALESCE_REPDATA(reply_base); + const struct kernel_ethtool_coalesce *kcoal = &data->kernel_coalesce; const struct ethtool_coalesce *coal = &data->coalesce; u32 supported = data->supported_params; @@ -170,7 +176,11 @@ static int coalesce_fill_reply(struct sk_buff *skb, coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH, coal->tx_max_coalesced_frames_high, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL, - coal->rate_sample_interval, supported)) + coal->rate_sample_interval, supported) || + coalesce_put_bool(skb, ETHTOOL_A_COALESCE_USE_CQE_MODE_TX, + kcoal->use_cqe_mode_tx, supported) || + coalesce_put_bool(skb, ETHTOOL_A_COALESCE_USE_CQE_MODE_RX, + kcoal->use_cqe_mode_rx, supported)) return -EMSGSIZE; return 0; @@ -215,10 +225,13 @@ const struct nla_policy ethnl_coalesce_set_policy[] = { [ETHTOOL_A_COALESCE_TX_USECS_HIGH] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_USE_CQE_MODE_TX] = NLA_POLICY_MAX(NLA_U8, 1), + [ETHTOOL_A_COALESCE_USE_CQE_MODE_RX] = NLA_POLICY_MAX(NLA_U8, 1), }; int ethnl_set_coalesce(struct sk_buff *skb, struct genl_info *info) { + struct kernel_ethtool_coalesce kernel_coalesce = {}; struct ethtool_coalesce coalesce = {}; struct ethnl_req_info req_info = {}; struct nlattr **tb = info->attrs; @@ -255,7 +268,8 @@ int ethnl_set_coalesce(struct sk_buff *skb, struct genl_info *info) ret = ethnl_ops_begin(dev); if (ret < 0) goto out_rtnl; - ret = ops->get_coalesce(dev, &coalesce); + ret = ops->get_coalesce(dev, &coalesce, &kernel_coalesce, + info->extack); if (ret < 0) goto out_ops; @@ -303,11 +317,16 @@ int ethnl_set_coalesce(struct sk_buff *skb, struct genl_info *info) tb[ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH], &mod); ethnl_update_u32(&coalesce.rate_sample_interval, tb[ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL], &mod); + ethnl_update_u8(&kernel_coalesce.use_cqe_mode_tx, + tb[ETHTOOL_A_COALESCE_USE_CQE_MODE_TX], &mod); + ethnl_update_u8(&kernel_coalesce.use_cqe_mode_rx, + tb[ETHTOOL_A_COALESCE_USE_CQE_MODE_RX], &mod); ret = 0; if (!mod) goto out_ops; - ret = dev->ethtool_ops->set_coalesce(dev, &coalesce); + ret = dev->ethtool_ops->set_coalesce(dev, &coalesce, &kernel_coalesce, + info->extack); if (ret < 0) goto out_ops; ethtool_notify(dev, ETHTOOL_MSG_COALESCE_NTF, NULL); diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index baa5d10043cb..f2abc3152888 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -7,6 +7,7 @@ * the information ethtool needs. */ +#include <linux/compat.h> #include <linux/module.h> #include <linux/types.h> #include <linux/capability.h> @@ -23,6 +24,7 @@ #include <linux/rtnetlink.h> #include <linux/sched/signal.h> #include <linux/net.h> +#include <linux/pm_runtime.h> #include <net/devlink.h> #include <net/xdp_sock_drv.h> #include <net/flow_offload.h> @@ -807,6 +809,120 @@ out: return ret; } +static noinline_for_stack int +ethtool_rxnfc_copy_from_compat(struct ethtool_rxnfc *rxnfc, + const struct compat_ethtool_rxnfc __user *useraddr, + size_t size) +{ + struct compat_ethtool_rxnfc crxnfc = {}; + + /* We expect there to be holes between fs.m_ext and + * fs.ring_cookie and at the end of fs, but nowhere else. + * On non-x86, no conversion should be needed. + */ + BUILD_BUG_ON(!IS_ENABLED(CONFIG_X86_64) && + sizeof(struct compat_ethtool_rxnfc) != + sizeof(struct ethtool_rxnfc)); + BUILD_BUG_ON(offsetof(struct compat_ethtool_rxnfc, fs.m_ext) + + sizeof(useraddr->fs.m_ext) != + offsetof(struct ethtool_rxnfc, fs.m_ext) + + sizeof(rxnfc->fs.m_ext)); + BUILD_BUG_ON(offsetof(struct compat_ethtool_rxnfc, fs.location) - + offsetof(struct compat_ethtool_rxnfc, fs.ring_cookie) != + offsetof(struct ethtool_rxnfc, fs.location) - + offsetof(struct ethtool_rxnfc, fs.ring_cookie)); + + if (copy_from_user(&crxnfc, useraddr, min(size, sizeof(crxnfc)))) + return -EFAULT; + + *rxnfc = (struct ethtool_rxnfc) { + .cmd = crxnfc.cmd, + .flow_type = crxnfc.flow_type, + .data = crxnfc.data, + .fs = { + .flow_type = crxnfc.fs.flow_type, + .h_u = crxnfc.fs.h_u, + .h_ext = crxnfc.fs.h_ext, + .m_u = crxnfc.fs.m_u, + .m_ext = crxnfc.fs.m_ext, + .ring_cookie = crxnfc.fs.ring_cookie, + .location = crxnfc.fs.location, + }, + .rule_cnt = crxnfc.rule_cnt, + }; + + return 0; +} + +static int ethtool_rxnfc_copy_from_user(struct ethtool_rxnfc *rxnfc, + const void __user *useraddr, + size_t size) +{ + if (compat_need_64bit_alignment_fixup()) + return ethtool_rxnfc_copy_from_compat(rxnfc, useraddr, size); + + if (copy_from_user(rxnfc, useraddr, size)) + return -EFAULT; + + return 0; +} + +static int ethtool_rxnfc_copy_to_compat(void __user *useraddr, + const struct ethtool_rxnfc *rxnfc, + size_t size, const u32 *rule_buf) +{ + struct compat_ethtool_rxnfc crxnfc; + + memset(&crxnfc, 0, sizeof(crxnfc)); + crxnfc = (struct compat_ethtool_rxnfc) { + .cmd = rxnfc->cmd, + .flow_type = rxnfc->flow_type, + .data = rxnfc->data, + .fs = { + .flow_type = rxnfc->fs.flow_type, + .h_u = rxnfc->fs.h_u, + .h_ext = rxnfc->fs.h_ext, + .m_u = rxnfc->fs.m_u, + .m_ext = rxnfc->fs.m_ext, + .ring_cookie = rxnfc->fs.ring_cookie, + .location = rxnfc->fs.location, + }, + .rule_cnt = rxnfc->rule_cnt, + }; + + if (copy_to_user(useraddr, &crxnfc, min(size, sizeof(crxnfc)))) + return -EFAULT; + + return 0; +} + +static int ethtool_rxnfc_copy_to_user(void __user *useraddr, + const struct ethtool_rxnfc *rxnfc, + size_t size, const u32 *rule_buf) +{ + int ret; + + if (compat_need_64bit_alignment_fixup()) { + ret = ethtool_rxnfc_copy_to_compat(useraddr, rxnfc, size, + rule_buf); + useraddr += offsetof(struct compat_ethtool_rxnfc, rule_locs); + } else { + ret = copy_to_user(useraddr, rxnfc, size); + useraddr += offsetof(struct ethtool_rxnfc, rule_locs); + } + + if (ret) + return -EFAULT; + + if (rule_buf) { + if (copy_to_user(useraddr, rule_buf, + rxnfc->rule_cnt * sizeof(u32))) + return -EFAULT; + } + + return 0; +} + static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, u32 cmd, void __user *useraddr) { @@ -825,7 +941,7 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, info_size = (offsetof(struct ethtool_rxnfc, data) + sizeof(info.data)); - if (copy_from_user(&info, useraddr, info_size)) + if (ethtool_rxnfc_copy_from_user(&info, useraddr, info_size)) return -EFAULT; rc = dev->ethtool_ops->set_rxnfc(dev, &info); @@ -833,7 +949,7 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, return rc; if (cmd == ETHTOOL_SRXCLSRLINS && - copy_to_user(useraddr, &info, info_size)) + ethtool_rxnfc_copy_to_user(useraddr, &info, info_size, NULL)) return -EFAULT; return 0; @@ -859,7 +975,7 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, info_size = (offsetof(struct ethtool_rxnfc, data) + sizeof(info.data)); - if (copy_from_user(&info, useraddr, info_size)) + if (ethtool_rxnfc_copy_from_user(&info, useraddr, info_size)) return -EFAULT; /* If FLOW_RSS was requested then user-space must be using the @@ -867,7 +983,7 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, */ if (cmd == ETHTOOL_GRXFH && info.flow_type & FLOW_RSS) { info_size = sizeof(info); - if (copy_from_user(&info, useraddr, info_size)) + if (ethtool_rxnfc_copy_from_user(&info, useraddr, info_size)) return -EFAULT; /* Since malicious users may modify the original data, * we need to check whether FLOW_RSS is still requested. @@ -893,18 +1009,7 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, if (ret < 0) goto err_out; - ret = -EFAULT; - if (copy_to_user(useraddr, &info, info_size)) - goto err_out; - - if (rule_buf) { - useraddr += offsetof(struct ethtool_rxnfc, rule_locs); - if (copy_to_user(useraddr, rule_buf, - info.rule_cnt * sizeof(u32))) - goto err_out; - } - ret = 0; - + ret = ethtool_rxnfc_copy_to_user(useraddr, &info, info_size, rule_buf); err_out: kfree(rule_buf); @@ -1514,12 +1619,14 @@ static noinline_for_stack int ethtool_get_coalesce(struct net_device *dev, void __user *useraddr) { struct ethtool_coalesce coalesce = { .cmd = ETHTOOL_GCOALESCE }; + struct kernel_ethtool_coalesce kernel_coalesce = {}; int ret; if (!dev->ethtool_ops->get_coalesce) return -EOPNOTSUPP; - ret = dev->ethtool_ops->get_coalesce(dev, &coalesce); + ret = dev->ethtool_ops->get_coalesce(dev, &coalesce, &kernel_coalesce, + NULL); if (ret) return ret; @@ -1586,19 +1693,26 @@ ethtool_set_coalesce_supported(struct net_device *dev, static noinline_for_stack int ethtool_set_coalesce(struct net_device *dev, void __user *useraddr) { + struct kernel_ethtool_coalesce kernel_coalesce = {}; struct ethtool_coalesce coalesce; int ret; - if (!dev->ethtool_ops->set_coalesce) + if (!dev->ethtool_ops->set_coalesce && !dev->ethtool_ops->get_coalesce) return -EOPNOTSUPP; + ret = dev->ethtool_ops->get_coalesce(dev, &coalesce, &kernel_coalesce, + NULL); + if (ret) + return ret; + if (copy_from_user(&coalesce, useraddr, sizeof(coalesce))) return -EFAULT; if (!ethtool_set_coalesce_supported(dev, &coalesce)) return -EOPNOTSUPP; - ret = dev->ethtool_ops->set_coalesce(dev, &coalesce); + ret = dev->ethtool_ops->set_coalesce(dev, &coalesce, &kernel_coalesce, + NULL); if (!ret) ethtool_notify(dev, ETHTOOL_MSG_COALESCE_NTF, NULL); return ret; @@ -2581,15 +2695,14 @@ static int ethtool_set_fecparam(struct net_device *dev, void __user *useraddr) /* The main entry point in this file. Called from net/core/dev_ioctl.c */ -int dev_ethtool(struct net *net, struct ifreq *ifr) +int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *useraddr) { struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name); - void __user *useraddr = ifr->ifr_data; u32 ethcmd, sub_cmd; int rc; netdev_features_t old_features; - if (!dev || !netif_device_present(dev)) + if (!dev) return -ENODEV; if (copy_from_user(ðcmd, useraddr, sizeof(ethcmd))) @@ -2645,10 +2758,18 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) return -EPERM; } + if (dev->dev.parent) + pm_runtime_get_sync(dev->dev.parent); + + if (!netif_device_present(dev)) { + rc = -ENODEV; + goto out; + } + if (dev->ethtool_ops->begin) { rc = dev->ethtool_ops->begin(dev); - if (rc < 0) - return rc; + if (rc < 0) + goto out; } old_features = dev->features; @@ -2867,6 +2988,9 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) if (old_features != dev->features) netdev_features_change(dev); +out: + if (dev->dev.parent) + pm_runtime_put(dev->dev.parent); return rc; } diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 73e0f5b626bf..1797a0a90019 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -2,6 +2,7 @@ #include <net/sock.h> #include <linux/ethtool_netlink.h> +#include <linux/pm_runtime.h> #include "netlink.h" static struct genl_family ethtool_genl_family; @@ -29,6 +30,44 @@ const struct nla_policy ethnl_header_policy_stats[] = { ETHTOOL_FLAGS_STATS), }; +int ethnl_ops_begin(struct net_device *dev) +{ + int ret; + + if (!dev) + return -ENODEV; + + if (dev->dev.parent) + pm_runtime_get_sync(dev->dev.parent); + + if (!netif_device_present(dev)) { + ret = -ENODEV; + goto err; + } + + if (dev->ethtool_ops->begin) { + ret = dev->ethtool_ops->begin(dev); + if (ret) + goto err; + } + + return 0; +err: + if (dev->dev.parent) + pm_runtime_put(dev->dev.parent); + + return ret; +} + +void ethnl_ops_complete(struct net_device *dev) +{ + if (dev->ethtool_ops->complete) + dev->ethtool_ops->complete(dev); + + if (dev->dev.parent) + pm_runtime_put(dev->dev.parent); +} + /** * ethnl_parse_header_dev_get() - parse request header * @req_info: structure to put results into @@ -101,12 +140,6 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, return -EINVAL; } - if (dev && !netif_device_present(dev)) { - dev_put(dev); - NL_SET_ERR_MSG(extack, "device not present"); - return -ENODEV; - } - req_info->dev = dev; req_info->flags = flags; return 0; @@ -365,8 +398,7 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info) ops->cleanup_data(reply_data); genlmsg_end(rskb, reply_payload); - if (req_info->dev) - dev_put(req_info->dev); + dev_put(req_info->dev); kfree(reply_data); kfree(req_info); return genlmsg_reply(rskb, info); @@ -378,8 +410,7 @@ err_cleanup: if (ops->cleanup_data) ops->cleanup_data(reply_data); err_dev: - if (req_info->dev) - dev_put(req_info->dev); + dev_put(req_info->dev); kfree(reply_data); kfree(req_info); return ret; diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 3fc395c86702..e8987e28036f 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -247,19 +247,8 @@ struct ethnl_reply_data { struct net_device *dev; }; -static inline int ethnl_ops_begin(struct net_device *dev) -{ - if (dev && dev->ethtool_ops->begin) - return dev->ethtool_ops->begin(dev); - else - return 0; -} - -static inline void ethnl_ops_complete(struct net_device *dev) -{ - if (dev && dev->ethtool_ops->complete) - dev->ethtool_ops->complete(dev); -} +int ethnl_ops_begin(struct net_device *dev); +void ethnl_ops_complete(struct net_device *dev); /** * struct ethnl_request_ops - unified handling of GET requests @@ -370,7 +359,7 @@ extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_TX + 1]; extern const struct nla_policy ethnl_channels_get_policy[ETHTOOL_A_CHANNELS_HEADER + 1]; extern const struct nla_policy ethnl_channels_set_policy[ETHTOOL_A_CHANNELS_COMBINED_COUNT + 1]; extern const struct nla_policy ethnl_coalesce_get_policy[ETHTOOL_A_COALESCE_HEADER + 1]; -extern const struct nla_policy ethnl_coalesce_set_policy[ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL + 1]; +extern const struct nla_policy ethnl_coalesce_set_policy[ETHTOOL_A_COALESCE_MAX + 1]; extern const struct nla_policy ethnl_pause_get_policy[ETHTOOL_A_PAUSE_HEADER + 1]; extern const struct nla_policy ethnl_pause_set_policy[ETHTOOL_A_PAUSE_TX + 1]; extern const struct nla_policy ethnl_eee_get_policy[ETHTOOL_A_EEE_HEADER + 1]; diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c index 88215b5c93aa..dd5a45f8a78a 100644 --- a/net/ieee802154/nl-phy.c +++ b/net/ieee802154/nl-phy.c @@ -340,8 +340,7 @@ nla_put_failure: out_dev: wpan_phy_put(phy); out: - if (dev) - dev_put(dev); + dev_put(dev); return rc; } diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index 0cf2374c143b..277124f206e0 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -2226,8 +2226,7 @@ static void nl802154_post_doit(const struct genl_ops *ops, struct sk_buff *skb, if (ops->internal_flags & NL802154_FLAG_NEED_WPAN_DEV) { struct wpan_dev *wpan_dev = info->user_ptr[1]; - if (wpan_dev->netdev) - dev_put(wpan_dev->netdev); + dev_put(wpan_dev->netdev); } else { dev_put(info->user_ptr[1]); } diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index a45a0401adc5..7bb9ef35c570 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -41,8 +41,7 @@ ieee802154_get_dev(struct net *net, const struct ieee802154_addr *addr) ieee802154_devaddr_to_raw(hwaddr, addr->extended_addr); rcu_read_lock(); dev = dev_getbyhwaddr_rcu(net, ARPHRD_IEEE802154, hwaddr); - if (dev) - dev_hold(dev); + dev_hold(dev); rcu_read_unlock(); break; case IEEE802154_ADDR_SHORT: @@ -129,7 +128,7 @@ static int ieee802154_dev_ioctl(struct sock *sk, struct ifreq __user *arg, int ret = -ENOIOCTLCMD; struct net_device *dev; - if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) + if (get_user_ifreq(&ifr, NULL, arg)) return -EFAULT; ifr.ifr_name[IFNAMSIZ-1] = 0; @@ -143,7 +142,7 @@ static int ieee802154_dev_ioctl(struct sock *sk, struct ifreq __user *arg, if (dev->type == ARPHRD_IEEE802154 && dev->netdev_ops->ndo_do_ioctl) ret = dev->netdev_ops->ndo_do_ioctl(dev, &ifr, cmd); - if (!ret && copy_to_user(arg, &ifr, sizeof(struct ifreq))) + if (!ret && put_user_ifreq(&ifr, arg)) ret = -EFAULT; dev_put(dev); @@ -984,6 +983,11 @@ static const struct proto_ops ieee802154_dgram_ops = { .sendpage = sock_no_sendpage, }; +static void ieee802154_sock_destruct(struct sock *sk) +{ + skb_queue_purge(&sk->sk_receive_queue); +} + /* Create a socket. Initialise the socket, blank the addresses * set the state. */ @@ -1024,7 +1028,7 @@ static int ieee802154_create(struct net *net, struct socket *sock, sock->ops = ops; sock_init_data(sock, sk); - /* FIXME: sk->sk_destruct */ + sk->sk_destruct = ieee802154_sock_destruct; sk->sk_family = PF_IEEE802154; /* Checksums on by default */ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 54648181dd56..1d816a5fd3eb 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -452,7 +452,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) * changes context in a wrong way it will be caught. */ err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, - BPF_CGROUP_INET4_BIND, &flags); + CGROUP_INET4_BIND, &flags); if (err) return err; @@ -781,7 +781,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin_port = inet->inet_dport; sin->sin_addr.s_addr = inet->inet_daddr; BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin, - BPF_CGROUP_INET4_GETPEERNAME, + CGROUP_INET4_GETPEERNAME, NULL); } else { __be32 addr = inet->inet_rcv_saddr; @@ -790,7 +790,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin_port = inet->inet_sport; sin->sin_addr.s_addr = addr; BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin, - BPF_CGROUP_INET4_GETSOCKNAME, + CGROUP_INET4_GETSOCKNAME, NULL); } memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); @@ -953,10 +953,10 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) case SIOCGIFNETMASK: case SIOCGIFDSTADDR: case SIOCGIFPFLAGS: - if (copy_from_user(&ifr, p, sizeof(struct ifreq))) + if (get_user_ifreq(&ifr, NULL, p)) return -EFAULT; err = devinet_ioctl(net, cmd, &ifr); - if (!err && copy_to_user(p, &ifr, sizeof(struct ifreq))) + if (!err && put_user_ifreq(&ifr, p)) err = -EFAULT; break; @@ -966,7 +966,7 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) case SIOCSIFDSTADDR: case SIOCSIFPFLAGS: case SIOCSIFFLAGS: - if (copy_from_user(&ifr, p, sizeof(struct ifreq))) + if (get_user_ifreq(&ifr, NULL, p)) return -EFAULT; err = devinet_ioctl(net, cmd, &ifr); break; diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 9e41eff4a685..0dcee9df1326 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -10,6 +10,9 @@ #include <net/tcp.h> #include <net/bpf_sk_storage.h> +/* "extern" is to avoid sparse warning. It is only used in bpf_struct_ops.c. */ +extern struct bpf_struct_ops bpf_tcp_congestion_ops; + static u32 optional_ops[] = { offsetof(struct tcp_congestion_ops, init), offsetof(struct tcp_congestion_ops, release), @@ -163,6 +166,19 @@ static const struct bpf_func_proto bpf_tcp_send_ack_proto = { .arg2_type = ARG_ANYTHING, }; +static u32 prog_ops_moff(const struct bpf_prog *prog) +{ + const struct btf_member *m; + const struct btf_type *t; + u32 midx; + + midx = prog->expected_attach_type; + t = bpf_tcp_congestion_ops.type; + m = &btf_type_member(t)[midx]; + + return btf_member_bit_offset(t, m) / 8; +} + static const struct bpf_func_proto * bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) @@ -174,6 +190,28 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; + case BPF_FUNC_setsockopt: + /* Does not allow release() to call setsockopt. + * release() is called when the current bpf-tcp-cc + * is retiring. It is not allowed to call + * setsockopt() to make further changes which + * may potentially allocate new resources. + */ + if (prog_ops_moff(prog) != + offsetof(struct tcp_congestion_ops, release)) + return &bpf_sk_setsockopt_proto; + return NULL; + case BPF_FUNC_getsockopt: + /* Since get/setsockopt is usually expected to + * be available together, disable getsockopt for + * release also to avoid usage surprise. + * The bpf-tcp-cc already has a more powerful way + * to read tcp_sock from the PTR_TO_BTF_ID. + */ + if (prog_ops_moff(prog) != + offsetof(struct tcp_congestion_ops, release)) + return &bpf_sk_getsockopt_proto; + return NULL; default: return bpf_base_func_proto(func_id); } @@ -286,9 +324,6 @@ static void bpf_tcp_ca_unreg(void *kdata) tcp_unregister_congestion_control(kdata); } -/* Avoid sparse warning. It is only used in bpf_struct_ops.c. */ -extern struct bpf_struct_ops bpf_tcp_congestion_ops; - struct bpf_struct_ops bpf_tcp_congestion_ops = { .verifier_ops = &bpf_tcp_ca_verifier_ops, .reg = bpf_tcp_ca_reg, diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 73721a4448bd..f4468980b675 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -215,7 +215,7 @@ static void devinet_sysctl_unregister(struct in_device *idev) static struct in_ifaddr *inet_alloc_ifa(void) { - return kzalloc(sizeof(struct in_ifaddr), GFP_KERNEL); + return kzalloc(sizeof(struct in_ifaddr), GFP_KERNEL_ACCOUNT); } static void inet_rcu_free_ifa(struct rcu_head *head) @@ -1243,7 +1243,7 @@ out: return ret; } -static int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) +int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) { struct in_device *in_dev = __in_dev_get_rtnl(dev); const struct in_ifaddr *ifa; @@ -1950,7 +1950,8 @@ static const struct nla_policy inet_af_policy[IFLA_INET_MAX+1] = { }; static int inet_validate_link_af(const struct net_device *dev, - const struct nlattr *nla) + const struct nlattr *nla, + struct netlink_ext_ack *extack) { struct nlattr *a, *tb[IFLA_INET_MAX+1]; int err, rem; @@ -1959,7 +1960,7 @@ static int inet_validate_link_af(const struct net_device *dev, return -EAFNOSUPPORT; err = nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla, - inet_af_policy, NULL); + inet_af_policy, extack); if (err < 0) return err; @@ -2424,11 +2425,15 @@ static int devinet_sysctl_forward(struct ctl_table *ctl, int write, int *valp = ctl->data; int val = *valp; loff_t pos = *ppos; - int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + struct net *net = ctl->extra2; + int ret; - if (write && *valp != val) { - struct net *net = ctl->extra2; + if (write && !ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + + ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + if (write && *valp != val) { if (valp != &IPV4_DEVCONF_DFLT(net, FORWARDING)) { if (!rtnl_trylock()) { /* Restore the original values before restarting */ @@ -2762,8 +2767,6 @@ void __init devinet_init(void) INIT_HLIST_HEAD(&inet_addr_lst[i]); register_pernet_subsys(&devinet_ops); - - register_gifconf(PF_INET, inet_gifconf); register_netdevice_notifier(&ip_netdev_notifier); queue_delayed_work(system_power_efficient_wq, &check_lifetime_work, 0); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index a09e36c4a413..851f542928a3 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -97,7 +97,6 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead, static void esp_ssg_unref(struct xfrm_state *x, void *tmp) { - struct esp_output_extra *extra = esp_tmp_extra(tmp); struct crypto_aead *aead = x->data; int extralen = 0; u8 *iv; @@ -105,9 +104,8 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp) struct scatterlist *sg; if (x->props.flags & XFRM_STATE_ESN) - extralen += sizeof(*extra); + extralen += sizeof(struct esp_output_extra); - extra = esp_tmp_extra(tmp); iv = esp_tmp_iv(aead, tmp, extralen); req = esp_tmp_req(aead, iv); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 4c0c33e4710d..b42c429cebbe 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -208,9 +208,7 @@ static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp) void fib_nh_common_release(struct fib_nh_common *nhc) { - if (nhc->nhc_dev) - dev_put(nhc->nhc_dev); - + dev_put(nhc->nhc_dev); lwtstate_put(nhc->nhc_lwtstate); rt_fibinfo_free_cpus(nhc->nhc_pcpu_rth_output); rt_fibinfo_free(&nhc->nhc_rth_input); @@ -260,7 +258,7 @@ EXPORT_SYMBOL_GPL(free_fib_info); void fib_release_info(struct fib_info *fi) { spin_lock_bh(&fib_info_lock); - if (fi && --fi->fib_treeref == 0) { + if (fi && refcount_dec_and_test(&fi->fib_treeref)) { hlist_del(&fi->fib_hash); if (fi->fib_prefsrc) hlist_del(&fi->fib_lhash); @@ -1373,7 +1371,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg, if (!cfg->fc_mx) { fi = fib_find_info_nh(net, cfg); if (fi) { - fi->fib_treeref++; + refcount_inc(&fi->fib_treeref); return fi; } } @@ -1547,11 +1545,11 @@ link_it: if (ofi) { fi->fib_dead = 1; free_fib_info(fi); - ofi->fib_treeref++; + refcount_inc(&ofi->fib_treeref); return ofi; } - fi->fib_treeref++; + refcount_set(&fi->fib_treeref, 1); refcount_set(&fi->fib_clntref, 1); spin_lock_bh(&fib_info_lock); hlist_add_head(&fi->fib_hash, diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 25cf387cca5b..8060524f4256 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2380,11 +2380,11 @@ void __init fib_trie_init(void) { fn_alias_kmem = kmem_cache_create("ip_fib_alias", sizeof(struct fib_alias), - 0, SLAB_PANIC, NULL); + 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); trie_leaf_kmem = kmem_cache_create("ip_fib_trie", LEAF_SIZE, - 0, SLAB_PANIC, NULL); + 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); } struct fib_table *fib_trie_table(u32 id, struct fib_table *alias) diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index e5f69b0bf3df..8fcbc6258ec5 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -230,8 +230,8 @@ static struct sk_buff *fou_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { + const struct net_offload __rcu **offloads; u8 proto = fou_from_sock(sk)->protocol; - const struct net_offload **offloads; const struct net_offload *ops; struct sk_buff *pp = NULL; @@ -263,10 +263,10 @@ out_unlock: static int fou_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { - const struct net_offload *ops; + const struct net_offload __rcu **offloads; u8 proto = fou_from_sock(sk)->protocol; + const struct net_offload *ops; int err = -ENOSYS; - const struct net_offload **offloads; rcu_read_lock(); offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; @@ -311,7 +311,7 @@ static struct sk_buff *gue_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { - const struct net_offload **offloads; + const struct net_offload __rcu **offloads; const struct net_offload *ops; struct sk_buff *pp = NULL; struct sk_buff *p; @@ -457,8 +457,8 @@ out: static int gue_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { - const struct net_offload **offloads; struct guehdr *guehdr = (struct guehdr *)(skb->data + nhoff); + const struct net_offload __rcu **offloads; const struct net_offload *ops; unsigned int guehlen = 0; u8 proto; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index c695d294a5df..8b30cadff708 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -1095,8 +1095,7 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr) sizeof(struct in6_addr)) goto send_mal_query; dev = ipv6_stub->ipv6_dev_find(net, &iio->ident.addr.ip_addr.ipv6_addr, dev); - if (dev) - dev_hold(dev); + dev_hold(dev); break; #endif default: diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 6b3c558a4f23..d2e2b3d18c66 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -803,10 +803,17 @@ static void igmp_gq_timer_expire(struct timer_list *t) static void igmp_ifc_timer_expire(struct timer_list *t) { struct in_device *in_dev = from_timer(in_dev, t, mr_ifc_timer); + u32 mr_ifc_count; igmpv3_send_cr(in_dev); - if (in_dev->mr_ifc_count) { - in_dev->mr_ifc_count--; +restart: + mr_ifc_count = READ_ONCE(in_dev->mr_ifc_count); + + if (mr_ifc_count) { + if (cmpxchg(&in_dev->mr_ifc_count, + mr_ifc_count, + mr_ifc_count - 1) != mr_ifc_count) + goto restart; igmp_ifc_start_timer(in_dev, unsolicited_report_interval(in_dev)); } @@ -818,7 +825,7 @@ static void igmp_ifc_event(struct in_device *in_dev) struct net *net = dev_net(in_dev->dev); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) return; - in_dev->mr_ifc_count = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv); igmp_ifc_start_timer(in_dev, 1); } @@ -957,7 +964,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, in_dev->mr_qri; } /* cancel the interface change timer */ - in_dev->mr_ifc_count = 0; + WRITE_ONCE(in_dev->mr_ifc_count, 0); if (del_timer(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); /* clear deleted report items */ @@ -1724,7 +1731,7 @@ void ip_mc_down(struct in_device *in_dev) igmp_group_dropped(pmc); #ifdef CONFIG_IP_MULTICAST - in_dev->mr_ifc_count = 0; + WRITE_ONCE(in_dev->mr_ifc_count, 0); if (del_timer(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); in_dev->mr_gq_running = 0; @@ -1941,7 +1948,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; - in_dev->mr_ifc_count = pmc->crcount; + WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(pmc->interface); @@ -2120,7 +2127,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, /* else no filters; keep old mode for reports */ pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; - in_dev->mr_ifc_count = pmc->crcount; + WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(in_dev); @@ -2233,7 +2240,7 @@ static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, iml->sfmode, psf->sl_count, psf->sl_addr, 0); RCU_INIT_POINTER(iml->sflist, NULL); /* decrease mem now to avoid the memleak warning */ - atomic_sub(IP_SFLSIZE(psf->sl_max), &sk->sk_omem_alloc); + atomic_sub(struct_size(psf, sl_addr, psf->sl_max), &sk->sk_omem_alloc); kfree_rcu(psf, rcu); return err; } @@ -2382,7 +2389,8 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct if (psl) count += psl->sl_max; - newpsl = sock_kmalloc(sk, IP_SFLSIZE(count), GFP_KERNEL); + newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, count), + GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; @@ -2393,7 +2401,8 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct for (i = 0; i < psl->sl_count; i++) newpsl->sl_addr[i] = psl->sl_addr[i]; /* decrease mem now to avoid the memleak warning */ - atomic_sub(IP_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc); + atomic_sub(struct_size(psl, sl_addr, psl->sl_max), + &sk->sk_omem_alloc); kfree_rcu(psl, rcu); } rcu_assign_pointer(pmc->sflist, newpsl); @@ -2468,19 +2477,22 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) goto done; } if (msf->imsf_numsrc) { - newpsl = sock_kmalloc(sk, IP_SFLSIZE(msf->imsf_numsrc), - GFP_KERNEL); + newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, + msf->imsf_numsrc), + GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = newpsl->sl_count = msf->imsf_numsrc; - memcpy(newpsl->sl_addr, msf->imsf_slist, - msf->imsf_numsrc * sizeof(msf->imsf_slist[0])); + memcpy(newpsl->sl_addr, msf->imsf_slist_flex, + flex_array_size(msf, imsf_slist_flex, msf->imsf_numsrc)); err = ip_mc_add_src(in_dev, &msf->imsf_multiaddr, msf->imsf_fmode, newpsl->sl_count, newpsl->sl_addr, 0); if (err) { - sock_kfree_s(sk, newpsl, IP_SFLSIZE(newpsl->sl_max)); + sock_kfree_s(sk, newpsl, + struct_size(newpsl, sl_addr, + newpsl->sl_max)); goto done; } } else { @@ -2493,7 +2505,8 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, psl->sl_count, psl->sl_addr, 0); /* decrease mem now to avoid the memleak warning */ - atomic_sub(IP_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc); + atomic_sub(struct_size(psl, sl_addr, psl->sl_max), + &sk->sk_omem_alloc); kfree_rcu(psl, rcu); } else (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, @@ -2551,14 +2564,14 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, count = psl->sl_count; } copycount = count < msf->imsf_numsrc ? count : msf->imsf_numsrc; - len = copycount * sizeof(psl->sl_addr[0]); + len = flex_array_size(psl, sl_addr, copycount); msf->imsf_numsrc = count; if (put_user(IP_MSFILTER_SIZE(copycount), optlen) || copy_to_user(optval, msf, IP_MSFILTER_SIZE(0))) { return -EFAULT; } if (len && - copy_to_user(&optval->imsf_slist[0], psl->sl_addr, len)) + copy_to_user(&optval->imsf_slist_flex[0], psl->sl_addr, len)) return -EFAULT; return 0; done: @@ -2713,6 +2726,7 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u rv = 1; } else if (im) { if (src_addr) { + spin_lock_bh(&im->lock); for (psf = im->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == src_addr) break; @@ -2723,6 +2737,7 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u im->sfcount[MCAST_EXCLUDE]; else rv = im->sfcount[MCAST_EXCLUDE] != 0; + spin_unlock_bh(&im->lock); } else rv = 1; /* unspecified source; tentatively allow */ } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 754013fa393b..f25d02ad4a8a 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -534,7 +534,8 @@ out: atomic_read(&newsk->sk_rmem_alloc)); mem_cgroup_sk_alloc(newsk); if (newsk->sk_memcg && amt) - mem_cgroup_charge_skmem(newsk->sk_memcg, amt); + mem_cgroup_charge_skmem(newsk->sk_memcg, amt, + GFP_KERNEL | __GFP_NOFAIL); release_sock(newsk); } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 12dca0c85f3c..0fe6c936dc54 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -630,15 +630,20 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, } if (dev->header_ops) { + const int pull_len = tunnel->hlen + sizeof(struct iphdr); + if (skb_cow_head(skb, 0)) goto free_skb; tnl_params = (const struct iphdr *)skb->data; + if (pull_len > skb_transport_offset(skb)) + goto free_skb; + /* Pull skb since ip_tunnel_xmit() needs skb->data pointing * to gre header. */ - skb_pull(skb, tunnel->hlen + sizeof(struct iphdr)); + skb_pull(skb, pull_len); skb_reset_mac_header(skb); } else { if (skb_cow_head(skb, dev->needed_headroom)) @@ -923,7 +928,7 @@ static const struct net_device_ops ipgre_netdev_ops = { .ndo_stop = ipgre_close, #endif .ndo_start_xmit = ipgre_xmit, - .ndo_do_ioctl = ip_tunnel_ioctl, + .ndo_siocdevprivate = ip_tunnel_siocdevprivate, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 8d8a8da3ae7e..9bca57ef8b83 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -198,19 +198,10 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s } else if (rt->rt_type == RTN_BROADCAST) IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTBCAST, skb->len); - /* Be paranoid, rather than too clever. */ if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { - struct sk_buff *skb2; - - skb2 = skb_realloc_headroom(skb, LL_RESERVED_SPACE(dev)); - if (!skb2) { - kfree_skb(skb); + skb = skb_expand_head(skb, hh_len); + if (!skb) return -ENOMEM; - } - if (skb->sk) - skb_set_owner_w(skb2, skb->sk); - consume_skb(skb); - skb = skb2; } if (lwtunnel_xmit_redirect(dst->lwtstate)) { @@ -446,8 +437,9 @@ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4) { BUILD_BUG_ON(offsetof(typeof(*fl4), daddr) != offsetof(typeof(*fl4), saddr) + sizeof(fl4->saddr)); - memcpy(&iph->saddr, &fl4->saddr, - sizeof(fl4->saddr) + sizeof(fl4->daddr)); + + iph->saddr = fl4->saddr; + iph->daddr = fl4->daddr; } /* Note: skb->sk can be different from sk, in case of tunnels */ @@ -614,18 +606,6 @@ void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph, } EXPORT_SYMBOL(ip_fraglist_init); -static void ip_fraglist_ipcb_prepare(struct sk_buff *skb, - struct ip_fraglist_iter *iter) -{ - struct sk_buff *to = iter->frag; - - /* Copy the flags to each fragment. */ - IPCB(to)->flags = IPCB(skb)->flags; - - if (iter->offset == 0) - ip_options_fragment(to); -} - void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter) { unsigned int hlen = iter->hlen; @@ -671,7 +651,7 @@ void ip_frag_init(struct sk_buff *skb, unsigned int hlen, EXPORT_SYMBOL(ip_frag_init); static void ip_frag_ipcb(struct sk_buff *from, struct sk_buff *to, - bool first_frag, struct ip_frag_state *state) + bool first_frag) { /* Copy the flags to each fragment. */ IPCB(to)->flags = IPCB(from)->flags; @@ -846,11 +826,14 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, /* Everything is OK. Generate! */ ip_fraglist_init(skb, iph, hlen, &iter); + if (iter.frag) + ip_options_fragment(iter.frag); + for (;;) { /* Prepare header of the next frame, * before previous one went down. */ if (iter.frag) { - ip_fraglist_ipcb_prepare(skb, &iter); + IPCB(iter.frag)->flags = IPCB(skb)->flags; ip_fraglist_prepare(skb, &iter); } @@ -905,7 +888,7 @@ slow_path: err = PTR_ERR(skb2); goto fail; } - ip_frag_ipcb(skb, skb2, first_frag, &state); + ip_frag_ipcb(skb, skb2, first_frag); /* * Put this fragment into the sending queue. diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index ec6036713e2c..b297bb28556e 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -663,12 +663,11 @@ static int set_mcast_msfilter(struct sock *sk, int ifindex, struct sockaddr_storage *group, struct sockaddr_storage *list) { - int msize = IP_MSFILTER_SIZE(numsrc); struct ip_msfilter *msf; struct sockaddr_in *psin; int err, i; - msf = kmalloc(msize, GFP_KERNEL); + msf = kmalloc(IP_MSFILTER_SIZE(numsrc), GFP_KERNEL); if (!msf) return -ENOBUFS; @@ -684,7 +683,7 @@ static int set_mcast_msfilter(struct sock *sk, int ifindex, if (psin->sin_family != AF_INET) goto Eaddrnotavail; - msf->imsf_slist[i] = psin->sin_addr.s_addr; + msf->imsf_slist_flex[i] = psin->sin_addr.s_addr; } err = ip_mc_msfilter(sk, msf, ifindex); kfree(msf); @@ -791,7 +790,8 @@ static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen) goto out_free_gsf; err = set_mcast_msfilter(sk, gsf->gf_interface, gsf->gf_numsrc, - gsf->gf_fmode, &gsf->gf_group, gsf->gf_slist); + gsf->gf_fmode, &gsf->gf_group, + gsf->gf_slist_flex); out_free_gsf: kfree(gsf); return err; @@ -800,7 +800,7 @@ out_free_gsf: static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen) { - const int size0 = offsetof(struct compat_group_filter, gf_slist); + const int size0 = offsetof(struct compat_group_filter, gf_slist_flex); struct compat_group_filter *gf32; unsigned int n; void *p; @@ -814,7 +814,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, p = kmalloc(optlen + 4, GFP_KERNEL); if (!p) return -ENOMEM; - gf32 = p + 4; /* we want ->gf_group and ->gf_slist aligned */ + gf32 = p + 4; /* we want ->gf_group and ->gf_slist_flex aligned */ err = -EFAULT; if (copy_from_sockptr(gf32, optval, optlen)) @@ -827,7 +827,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, goto out_free_gsf; err = -EINVAL; - if (offsetof(struct compat_group_filter, gf_slist[n]) > optlen) + if (offsetof(struct compat_group_filter, gf_slist_flex[n]) > optlen) goto out_free_gsf; /* numsrc >= (4G-140)/128 overflow in 32 bits */ @@ -835,7 +835,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, if (n > sock_net(sk)->ipv4.sysctl_igmp_max_msf) goto out_free_gsf; err = set_mcast_msfilter(sk, gf32->gf_interface, n, gf32->gf_fmode, - &gf32->gf_group, gf32->gf_slist); + &gf32->gf_group, gf32->gf_slist_flex); out_free_gsf: kfree(p); return err; @@ -1456,7 +1456,7 @@ static bool getsockopt_needs_rtnl(int optname) static int ip_get_mcast_msfilter(struct sock *sk, void __user *optval, int __user *optlen, int len) { - const int size0 = offsetof(struct group_filter, gf_slist); + const int size0 = offsetof(struct group_filter, gf_slist_flex); struct group_filter __user *p = optval; struct group_filter gsf; int num; @@ -1468,7 +1468,7 @@ static int ip_get_mcast_msfilter(struct sock *sk, void __user *optval, return -EFAULT; num = gsf.gf_numsrc; - err = ip_mc_gsfget(sk, &gsf, p->gf_slist); + err = ip_mc_gsfget(sk, &gsf, p->gf_slist_flex); if (err) return err; if (gsf.gf_numsrc < num) @@ -1482,7 +1482,7 @@ static int ip_get_mcast_msfilter(struct sock *sk, void __user *optval, static int compat_ip_get_mcast_msfilter(struct sock *sk, void __user *optval, int __user *optlen, int len) { - const int size0 = offsetof(struct compat_group_filter, gf_slist); + const int size0 = offsetof(struct compat_group_filter, gf_slist_flex); struct compat_group_filter __user *p = optval; struct compat_group_filter gf32; struct group_filter gf; @@ -1499,7 +1499,7 @@ static int compat_ip_get_mcast_msfilter(struct sock *sk, void __user *optval, num = gf.gf_numsrc = gf32.gf_numsrc; gf.gf_group = gf32.gf_group; - err = ip_mc_gsfget(sk, &gf, p->gf_slist); + err = ip_mc_gsfget(sk, &gf, p->gf_slist_flex); if (err) return err; if (gf.gf_numsrc < num) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 0dca00745ac3..fe9101d3d69e 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -390,7 +390,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, tunnel->i_seqno = ntohl(tpi->seq) + 1; } - skb_reset_network_header(skb); + skb_set_network_header(skb, (tunnel->dev->type == ARPHRD_ETHER) ? ETH_HLEN : 0); err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { @@ -958,19 +958,20 @@ done: } EXPORT_SYMBOL_GPL(ip_tunnel_ctl); -int ip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +int ip_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr, + void __user *data, int cmd) { struct ip_tunnel_parm p; int err; - if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) + if (copy_from_user(&p, data, sizeof(p))) return -EFAULT; err = dev->netdev_ops->ndo_tunnel_ctl(dev, &p, cmd); - if (!err && copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) + if (!err && copy_to_user(data, &p, sizeof(p))) return -EFAULT; return err; } -EXPORT_SYMBOL_GPL(ip_tunnel_ioctl); +EXPORT_SYMBOL_GPL(ip_tunnel_siocdevprivate); int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict) { diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index eb560eecee08..efe25a0172e6 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -405,7 +405,7 @@ static const struct net_device_ops vti_netdev_ops = { .ndo_init = vti_tunnel_init, .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = vti_tunnel_xmit, - .ndo_do_ioctl = ip_tunnel_ioctl, + .ndo_siocdevprivate = ip_tunnel_siocdevprivate, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 266c65577ba6..3aa78ccbec3e 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -347,7 +347,7 @@ static const struct net_device_ops ipip_netdev_ops = { .ndo_init = ipip_tunnel_init, .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = ipip_tunnel_xmit, - .ndo_do_ioctl = ip_tunnel_ioctl, + .ndo_siocdevprivate = ip_tunnel_siocdevprivate, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index 6922612df456..3de78416ec76 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -18,15 +18,12 @@ MODULE_DESCRIPTION("arptables filter table"); #define FILTER_VALID_HOOKS ((1 << NF_ARP_IN) | (1 << NF_ARP_OUT) | \ (1 << NF_ARP_FORWARD)) -static int __net_init arptable_filter_table_init(struct net *net); - static const struct xt_table packet_filter = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_ARP, .priority = NF_IP_PRI_FILTER, - .table_init = arptable_filter_table_init, }; /* The work comes in here from netfilter.c */ @@ -39,7 +36,7 @@ arptable_filter_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *arpfilter_ops __read_mostly; -static int __net_init arptable_filter_table_init(struct net *net) +static int arptable_filter_table_init(struct net *net) { struct arpt_replace *repl; int err; @@ -69,30 +66,32 @@ static struct pernet_operations arptable_filter_net_ops = { static int __init arptable_filter_init(void) { - int ret; + int ret = xt_register_template(&packet_filter, + arptable_filter_table_init); + + if (ret < 0) + return ret; arpfilter_ops = xt_hook_ops_alloc(&packet_filter, arptable_filter_hook); - if (IS_ERR(arpfilter_ops)) + if (IS_ERR(arpfilter_ops)) { + xt_unregister_template(&packet_filter); return PTR_ERR(arpfilter_ops); + } ret = register_pernet_subsys(&arptable_filter_net_ops); if (ret < 0) { + xt_unregister_template(&packet_filter); kfree(arpfilter_ops); return ret; } - ret = arptable_filter_table_init(&init_net); - if (ret) { - unregister_pernet_subsys(&arptable_filter_net_ops); - kfree(arpfilter_ops); - } - return ret; } static void __exit arptable_filter_fini(void) { unregister_pernet_subsys(&arptable_filter_net_ops); + xt_unregister_template(&packet_filter); kfree(arpfilter_ops); } diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 8f7ca67475b7..8fd1aba8af31 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -66,11 +66,22 @@ struct clusterip_net { /* lock protects the configs list */ spinlock_t lock; + bool clusterip_deprecated_warning; #ifdef CONFIG_PROC_FS struct proc_dir_entry *procdir; /* mutex protects the config->pde*/ struct mutex mutex; #endif + unsigned int hook_users; +}; + +static unsigned int clusterip_arp_mangle(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); + +static const struct nf_hook_ops cip_arp_ops = { + .hook = clusterip_arp_mangle, + .pf = NFPROTO_ARP, + .hooknum = NF_ARP_OUT, + .priority = -1 }; static unsigned int clusterip_net_id __read_mostly; @@ -458,6 +469,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) static int clusterip_tg_check(const struct xt_tgchk_param *par) { struct ipt_clusterip_tgt_info *cipinfo = par->targinfo; + struct clusterip_net *cn = clusterip_pernet(par->net); const struct ipt_entry *e = par->entryinfo; struct clusterip_config *config; int ret, i; @@ -467,6 +479,9 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) return -EOPNOTSUPP; } + if (cn->hook_users == UINT_MAX) + return -EOVERFLOW; + if (cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP && cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP_SPT && cipinfo->hash_mode != CLUSTERIP_HASHMODE_SIP_SPT_DPT) { @@ -517,10 +532,23 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) return ret; } - if (!par->net->xt.clusterip_deprecated_warning) { + if (cn->hook_users == 0) { + ret = nf_register_net_hook(par->net, &cip_arp_ops); + + if (ret < 0) { + clusterip_config_entry_put(config); + clusterip_config_put(config); + nf_ct_netns_put(par->net, par->family); + return ret; + } + } + + cn->hook_users++; + + if (!cn->clusterip_deprecated_warning) { pr_info("ipt_CLUSTERIP is deprecated and it will removed soon, " "use xt_cluster instead\n"); - par->net->xt.clusterip_deprecated_warning = true; + cn->clusterip_deprecated_warning = true; } cipinfo->config = config; @@ -531,6 +559,7 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) static void clusterip_tg_destroy(const struct xt_tgdtor_param *par) { const struct ipt_clusterip_tgt_info *cipinfo = par->targinfo; + struct clusterip_net *cn = clusterip_pernet(par->net); /* if no more entries are referencing the config, remove it * from the list and destroy the proc entry */ @@ -539,6 +568,10 @@ static void clusterip_tg_destroy(const struct xt_tgdtor_param *par) clusterip_config_put(cipinfo->config); nf_ct_netns_put(par->net, par->family); + cn->hook_users--; + + if (cn->hook_users == 0) + nf_unregister_net_hook(par->net, &cip_arp_ops); } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT @@ -602,9 +635,8 @@ static void arp_print(struct arp_payload *payload) #endif static unsigned int -arp_mangle(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) +clusterip_arp_mangle(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) { struct arphdr *arp = arp_hdr(skb); struct arp_payload *payload; @@ -654,13 +686,6 @@ arp_mangle(void *priv, return NF_ACCEPT; } -static const struct nf_hook_ops cip_arp_ops = { - .hook = arp_mangle, - .pf = NFPROTO_ARP, - .hooknum = NF_ARP_OUT, - .priority = -1 -}; - /*********************************************************************** * PROC DIR HANDLING ***********************************************************************/ @@ -817,20 +842,14 @@ static const struct proc_ops clusterip_proc_ops = { static int clusterip_net_init(struct net *net) { struct clusterip_net *cn = clusterip_pernet(net); - int ret; INIT_LIST_HEAD(&cn->configs); spin_lock_init(&cn->lock); - ret = nf_register_net_hook(net, &cip_arp_ops); - if (ret < 0) - return ret; - #ifdef CONFIG_PROC_FS cn->procdir = proc_mkdir("ipt_CLUSTERIP", net->proc_net); if (!cn->procdir) { - nf_unregister_net_hook(net, &cip_arp_ops); pr_err("Unable to proc dir entry\n"); return -ENOMEM; } @@ -850,7 +869,6 @@ static void clusterip_net_exit(struct net *net) cn->procdir = NULL; mutex_unlock(&cn->mutex); #endif - nf_unregister_net_hook(net, &cip_arp_ops); } static struct pernet_operations clusterip_net_ops = { diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 8272df7c6ad5..0eb0e2ab9bfc 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -19,7 +19,6 @@ MODULE_DESCRIPTION("iptables filter table"); #define FILTER_VALID_HOOKS ((1 << NF_INET_LOCAL_IN) | \ (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT)) -static int __net_init iptable_filter_table_init(struct net *net); static const struct xt_table packet_filter = { .name = "filter", @@ -27,7 +26,6 @@ static const struct xt_table packet_filter = { .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_FILTER, - .table_init = iptable_filter_table_init, }; static unsigned int @@ -43,7 +41,7 @@ static struct nf_hook_ops *filter_ops __read_mostly; static bool forward __read_mostly = true; module_param(forward, bool, 0000); -static int __net_init iptable_filter_table_init(struct net *net) +static int iptable_filter_table_init(struct net *net) { struct ipt_replace *repl; int err; @@ -62,7 +60,7 @@ static int __net_init iptable_filter_table_init(struct net *net) static int __net_init iptable_filter_net_init(struct net *net) { - if (net == &init_net || !forward) + if (!forward) return iptable_filter_table_init(net); return 0; @@ -86,22 +84,32 @@ static struct pernet_operations iptable_filter_net_ops = { static int __init iptable_filter_init(void) { - int ret; + int ret = xt_register_template(&packet_filter, + iptable_filter_table_init); + + if (ret < 0) + return ret; filter_ops = xt_hook_ops_alloc(&packet_filter, iptable_filter_hook); - if (IS_ERR(filter_ops)) + if (IS_ERR(filter_ops)) { + xt_unregister_template(&packet_filter); return PTR_ERR(filter_ops); + } ret = register_pernet_subsys(&iptable_filter_net_ops); - if (ret < 0) + if (ret < 0) { + xt_unregister_template(&packet_filter); kfree(filter_ops); + return ret; + } - return ret; + return 0; } static void __exit iptable_filter_fini(void) { unregister_pernet_subsys(&iptable_filter_net_ops); + xt_unregister_template(&packet_filter); kfree(filter_ops); } diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 2abc3836f391..40417a3f930b 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -25,15 +25,12 @@ MODULE_DESCRIPTION("iptables mangle table"); (1 << NF_INET_LOCAL_OUT) | \ (1 << NF_INET_POST_ROUTING)) -static int __net_init iptable_mangle_table_init(struct net *net); - static const struct xt_table packet_mangler = { .name = "mangle", .valid_hooks = MANGLE_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_MANGLE, - .table_init = iptable_mangle_table_init, }; static unsigned int @@ -83,7 +80,7 @@ iptable_mangle_hook(void *priv, } static struct nf_hook_ops *mangle_ops __read_mostly; -static int __net_init iptable_mangle_table_init(struct net *net) +static int iptable_mangle_table_init(struct net *net) { struct ipt_replace *repl; int ret; @@ -113,32 +110,32 @@ static struct pernet_operations iptable_mangle_net_ops = { static int __init iptable_mangle_init(void) { - int ret; + int ret = xt_register_template(&packet_mangler, + iptable_mangle_table_init); + if (ret < 0) + return ret; mangle_ops = xt_hook_ops_alloc(&packet_mangler, iptable_mangle_hook); if (IS_ERR(mangle_ops)) { + xt_unregister_template(&packet_mangler); ret = PTR_ERR(mangle_ops); return ret; } ret = register_pernet_subsys(&iptable_mangle_net_ops); if (ret < 0) { + xt_unregister_template(&packet_mangler); kfree(mangle_ops); return ret; } - ret = iptable_mangle_table_init(&init_net); - if (ret) { - unregister_pernet_subsys(&iptable_mangle_net_ops); - kfree(mangle_ops); - } - return ret; } static void __exit iptable_mangle_fini(void) { unregister_pernet_subsys(&iptable_mangle_net_ops); + xt_unregister_template(&packet_mangler); kfree(mangle_ops); } diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index a9913842ef18..45d7e072e6a5 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -17,8 +17,6 @@ struct iptable_nat_pernet { struct nf_hook_ops *nf_nat_ops; }; -static int __net_init iptable_nat_table_init(struct net *net); - static unsigned int iptable_nat_net_id __read_mostly; static const struct xt_table nf_nat_ipv4_table = { @@ -29,7 +27,6 @@ static const struct xt_table nf_nat_ipv4_table = { (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, .af = NFPROTO_IPV4, - .table_init = iptable_nat_table_init, }; static unsigned int iptable_nat_do_chain(void *priv, @@ -113,7 +110,7 @@ static void ipt_nat_unregister_lookups(struct net *net) kfree(ops); } -static int __net_init iptable_nat_table_init(struct net *net) +static int iptable_nat_table_init(struct net *net) { struct ipt_replace *repl; int ret; @@ -155,20 +152,25 @@ static struct pernet_operations iptable_nat_net_ops = { static int __init iptable_nat_init(void) { - int ret = register_pernet_subsys(&iptable_nat_net_ops); + int ret = xt_register_template(&nf_nat_ipv4_table, + iptable_nat_table_init); + + if (ret < 0) + return ret; - if (ret) + ret = register_pernet_subsys(&iptable_nat_net_ops); + if (ret < 0) { + xt_unregister_template(&nf_nat_ipv4_table); return ret; + } - ret = iptable_nat_table_init(&init_net); - if (ret) - unregister_pernet_subsys(&iptable_nat_net_ops); return ret; } static void __exit iptable_nat_exit(void) { unregister_pernet_subsys(&iptable_nat_net_ops); + xt_unregister_template(&nf_nat_ipv4_table); } module_init(iptable_nat_init); diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index ceef397c1f5f..b88e0f36cd05 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -12,8 +12,6 @@ #define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT)) -static int __net_init iptable_raw_table_init(struct net *net); - static bool raw_before_defrag __read_mostly; MODULE_PARM_DESC(raw_before_defrag, "Enable raw table before defrag"); module_param(raw_before_defrag, bool, 0000); @@ -24,7 +22,6 @@ static const struct xt_table packet_raw = { .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_RAW, - .table_init = iptable_raw_table_init, }; static const struct xt_table packet_raw_before_defrag = { @@ -33,7 +30,6 @@ static const struct xt_table packet_raw_before_defrag = { .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_RAW_BEFORE_DEFRAG, - .table_init = iptable_raw_table_init, }; /* The work comes in here from netfilter.c. */ @@ -89,22 +85,24 @@ static int __init iptable_raw_init(void) pr_info("Enabling raw table before defrag\n"); } + ret = xt_register_template(table, + iptable_raw_table_init); + if (ret < 0) + return ret; + rawtable_ops = xt_hook_ops_alloc(table, iptable_raw_hook); - if (IS_ERR(rawtable_ops)) + if (IS_ERR(rawtable_ops)) { + xt_unregister_template(table); return PTR_ERR(rawtable_ops); + } ret = register_pernet_subsys(&iptable_raw_net_ops); if (ret < 0) { + xt_unregister_template(table); kfree(rawtable_ops); return ret; } - ret = iptable_raw_table_init(&init_net); - if (ret) { - unregister_pernet_subsys(&iptable_raw_net_ops); - kfree(rawtable_ops); - } - return ret; } @@ -112,6 +110,7 @@ static void __exit iptable_raw_fini(void) { unregister_pernet_subsys(&iptable_raw_net_ops); kfree(rawtable_ops); + xt_unregister_template(&packet_raw); } module_init(iptable_raw_init); diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index 77973f5fd8f6..f519162a2fa5 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -25,15 +25,12 @@ MODULE_DESCRIPTION("iptables security table, for MAC rules"); (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT) -static int __net_init iptable_security_table_init(struct net *net); - static const struct xt_table security_table = { .name = "security", .valid_hooks = SECURITY_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_SECURITY, - .table_init = iptable_security_table_init, }; static unsigned int @@ -45,7 +42,7 @@ iptable_security_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *sectbl_ops __read_mostly; -static int __net_init iptable_security_table_init(struct net *net) +static int iptable_security_table_init(struct net *net) { struct ipt_replace *repl; int ret; @@ -75,24 +72,25 @@ static struct pernet_operations iptable_security_net_ops = { static int __init iptable_security_init(void) { - int ret; + int ret = xt_register_template(&security_table, + iptable_security_table_init); + + if (ret < 0) + return ret; sectbl_ops = xt_hook_ops_alloc(&security_table, iptable_security_hook); - if (IS_ERR(sectbl_ops)) + if (IS_ERR(sectbl_ops)) { + xt_unregister_template(&security_table); return PTR_ERR(sectbl_ops); + } ret = register_pernet_subsys(&iptable_security_net_ops); if (ret < 0) { + xt_unregister_template(&security_table); kfree(sectbl_ops); return ret; } - ret = iptable_security_table_init(&init_net); - if (ret) { - unregister_pernet_subsys(&iptable_security_net_ops); - kfree(sectbl_ops); - } - return ret; } @@ -100,6 +98,7 @@ static void __exit iptable_security_fini(void) { unregister_pernet_subsys(&iptable_security_net_ops); kfree(sectbl_ops); + xt_unregister_template(&security_table); } module_init(iptable_security_init); diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 4075230b14c6..75ca4b6e484f 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -2490,6 +2490,7 @@ static int nh_create_ipv4(struct net *net, struct nexthop *nh, .fc_gw4 = cfg->gw.ipv4, .fc_gw_family = cfg->gw.ipv4 ? AF_INET : 0, .fc_flags = cfg->nh_flags, + .fc_nlinfo = cfg->nlinfo, .fc_encap = cfg->nh_encap, .fc_encap_type = cfg->nh_encap_type, }; @@ -2528,6 +2529,7 @@ static int nh_create_ipv6(struct net *net, struct nexthop *nh, .fc_ifindex = cfg->nh_ifindex, .fc_gateway = cfg->gw.ipv6, .fc_flags = cfg->nh_flags, + .fc_nlinfo = cfg->nlinfo, .fc_encap = cfg->nh_encap, .fc_encap_type = cfg->nh_encap_type, .fc_is_fdb = cfg->nh_fdb, diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 99c06944501a..d6899ab5fb39 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -276,12 +276,13 @@ static int rt_cpu_seq_show(struct seq_file *seq, void *v) struct rt_cache_stat *st = v; if (v == SEQ_START_TOKEN) { - seq_printf(seq, "entries in_hit in_slow_tot in_slow_mc in_no_route in_brd in_martian_dst in_martian_src out_hit out_slow_tot out_slow_mc gc_total gc_ignored gc_goal_miss gc_dst_overflow in_hlist_search out_hlist_search\n"); + seq_puts(seq, "entries in_hit in_slow_tot in_slow_mc in_no_route in_brd in_martian_dst in_martian_src out_hit out_slow_tot out_slow_mc gc_total gc_ignored gc_goal_miss gc_dst_overflow in_hlist_search out_hlist_search\n"); return 0; } - seq_printf(seq,"%08x %08x %08x %08x %08x %08x %08x %08x " - " %08x %08x %08x %08x %08x %08x %08x %08x %08x \n", + seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x " + "%08x %08x %08x %08x %08x %08x " + "%08x %08x %08x %08x\n", dst_entries_get_slow(&ipv4_dst_ops), 0, /* st->in_hit */ st->in_slow_tot, @@ -586,28 +587,35 @@ static void fnhe_flush_routes(struct fib_nh_exception *fnhe) } } -static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash) +static void fnhe_remove_oldest(struct fnhe_hash_bucket *hash) { - struct fib_nh_exception *fnhe, *oldest; + struct fib_nh_exception __rcu **fnhe_p, **oldest_p; + struct fib_nh_exception *fnhe, *oldest = NULL; - oldest = rcu_dereference(hash->chain); - for (fnhe = rcu_dereference(oldest->fnhe_next); fnhe; - fnhe = rcu_dereference(fnhe->fnhe_next)) { - if (time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp)) + for (fnhe_p = &hash->chain; ; fnhe_p = &fnhe->fnhe_next) { + fnhe = rcu_dereference_protected(*fnhe_p, + lockdep_is_held(&fnhe_lock)); + if (!fnhe) + break; + if (!oldest || + time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp)) { oldest = fnhe; + oldest_p = fnhe_p; + } } fnhe_flush_routes(oldest); - return oldest; + *oldest_p = oldest->fnhe_next; + kfree_rcu(oldest, rcu); } -static inline u32 fnhe_hashfun(__be32 daddr) +static u32 fnhe_hashfun(__be32 daddr) { - static u32 fnhe_hashrnd __read_mostly; - u32 hval; + static siphash_key_t fnhe_hash_key __read_mostly; + u64 hval; - net_get_random_once(&fnhe_hashrnd, sizeof(fnhe_hashrnd)); - hval = jhash_1word((__force u32)daddr, fnhe_hashrnd); - return hash_32(hval, FNHE_HASH_SHIFT); + net_get_random_once(&fnhe_hash_key, sizeof(fnhe_hash_key)); + hval = siphash_1u32((__force u32)daddr, &fnhe_hash_key); + return hash_64(hval, FNHE_HASH_SHIFT); } static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe) @@ -676,16 +684,21 @@ static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr, if (rt) fill_route_from_fnhe(rt, fnhe); } else { - if (depth > FNHE_RECLAIM_DEPTH) - fnhe = fnhe_oldest(hash); - else { - fnhe = kzalloc(sizeof(*fnhe), GFP_ATOMIC); - if (!fnhe) - goto out_unlock; - - fnhe->fnhe_next = hash->chain; - rcu_assign_pointer(hash->chain, fnhe); + /* Randomize max depth to avoid some side channels attacks. */ + int max_depth = FNHE_RECLAIM_DEPTH + + prandom_u32_max(FNHE_RECLAIM_DEPTH); + + while (depth > max_depth) { + fnhe_remove_oldest(hash); + depth--; } + + fnhe = kzalloc(sizeof(*fnhe), GFP_ATOMIC); + if (!fnhe) + goto out_unlock; + + fnhe->fnhe_next = hash->chain; + fnhe->fnhe_genid = genid; fnhe->fnhe_daddr = daddr; fnhe->fnhe_gw = gw; @@ -693,6 +706,8 @@ static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr, fnhe->fnhe_mtu_locked = lock; fnhe->fnhe_expires = max(1UL, expires); + rcu_assign_pointer(hash->chain, fnhe); + /* Exception created; mark the cached routes for the nexthop * stale, so anyone caching it rechecks if this exception * applies to them. @@ -1299,26 +1314,7 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst) INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst) { - const struct rtable *rt = (const struct rtable *)dst; - unsigned int mtu = rt->rt_pmtu; - - if (!mtu || time_after_eq(jiffies, rt->dst.expires)) - mtu = dst_metric_raw(dst, RTAX_MTU); - - if (mtu) - goto out; - - mtu = READ_ONCE(dst->dev->mtu); - - if (unlikely(ip_mtu_locked(dst))) { - if (rt->rt_uses_gateway && mtu > 576) - mtu = 576; - } - -out: - mtu = min_t(unsigned int, mtu, IP_MAX_MTU); - - return mtu - lwtunnel_headroom(dst->lwtstate, mtu); + return ip_dst_mtu_maybe_forward(dst, false); } EXPORT_INDIRECT_CALLABLE(ipv4_mtu); @@ -2831,8 +2827,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or new->output = dst_discard_out; new->dev = net->loopback_dev; - if (new->dev) - dev_hold(new->dev); + dev_hold(new->dev); rt->rt_is_input = ort->rt_is_input; rt->rt_iif = ort->rt_iif; @@ -3170,7 +3165,7 @@ static struct sk_buff *inet_rtm_getroute_build_skb(__be32 src, __be32 dst, udph = skb_put_zero(skb, sizeof(struct udphdr)); udph->source = sport; udph->dest = dport; - udph->len = sizeof(struct udphdr); + udph->len = htons(sizeof(struct udphdr)); udph->check = 0; break; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8cb44040ec68..e8b48df73c85 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3338,6 +3338,7 @@ int tcp_set_window_clamp(struct sock *sk, int val) } else { tp->window_clamp = val < SOCK_MIN_RCVBUF / 2 ? SOCK_MIN_RCVBUF / 2 : val; + tp->rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp); } return 0; } @@ -4512,7 +4513,9 @@ void __init tcp_init(void) tcp_hashinfo.bind_bucket_cachep = kmem_cache_create("tcp_bind_bucket", sizeof(struct inet_bind_bucket), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + SLAB_HWCACHE_ALIGN | SLAB_PANIC | + SLAB_ACCOUNT, + NULL); /* Size and allocate the main established and bind bucket * hash tables. diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 6ea3dc2e4219..6274462b86b4 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -1041,7 +1041,7 @@ static void bbr_init(struct sock *sk) bbr->prior_cwnd = 0; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; bbr->rtt_cnt = 0; - bbr->next_rtt_delivered = 0; + bbr->next_rtt_delivered = tp->delivered; bbr->prev_ca_state = TCP_CA_Open; bbr->packet_conservation = 0; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 25fa4c01a17f..59412d6354a0 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -55,12 +55,7 @@ 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); + ctxt = xchg((__force struct tcp_fastopen_context **)&net->ipv4.tcp_fastopen_ctx, NULL); if (ctxt) call_rcu(&ctxt->rcu, tcp_fastopen_ctx_free); @@ -89,18 +84,12 @@ int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk, ctx->num = 1; } - 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); + octx = xchg((__force struct tcp_fastopen_context **)&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); + octx = xchg((__force struct tcp_fastopen_context **)&net->ipv4.tcp_fastopen_ctx, ctx); } - spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock); if (octx) call_rcu(&octx->rcu, tcp_fastopen_ctx_free); @@ -379,8 +368,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, return NULL; } - if (syn_data && - tcp_fastopen_no_cookie(sk, dst, TFO_SERVER_COOKIE_NOT_REQD)) + if (tcp_fastopen_no_cookie(sk, dst, TFO_SERVER_COOKIE_NOT_REQD)) goto fastopen; if (foc->len == 0) { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 149ceb5c94ff..3f7bd7ae7d7a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -100,6 +100,7 @@ int sysctl_tcp_max_orphans __read_mostly = NR_FILE; #define FLAG_UPDATE_TS_RECENT 0x4000 /* tcp_replace_ts_recent() */ #define FLAG_NO_CHALLENGE_ACK 0x8000 /* do not call tcp_send_challenge_ack() */ #define FLAG_ACK_MAYBE_DELAYED 0x10000 /* Likely a delayed ACK */ +#define FLAG_DSACK_TLP 0x20000 /* DSACK for tail loss probe */ #define FLAG_ACKED (FLAG_DATA_ACKED|FLAG_SYN_ACKED) #define FLAG_NOT_DUP (FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED) @@ -454,11 +455,12 @@ static void tcp_sndbuf_expand(struct sock *sk) */ /* Slow part of check#2. */ -static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb) +static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb, + unsigned int skbtruesize) { struct tcp_sock *tp = tcp_sk(sk); /* Optimize this! */ - int truesize = tcp_win_from_space(sk, skb->truesize) >> 1; + int truesize = tcp_win_from_space(sk, skbtruesize) >> 1; int window = tcp_win_from_space(sk, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1; while (tp->rcv_ssthresh <= window) { @@ -471,7 +473,27 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb) return 0; } -static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) +/* Even if skb appears to have a bad len/truesize ratio, TCP coalescing + * can play nice with us, as sk_buff and skb->head might be either + * freed or shared with up to MAX_SKB_FRAGS segments. + * Only give a boost to drivers using page frag(s) to hold the frame(s), + * and if no payload was pulled in skb->head before reaching us. + */ +static u32 truesize_adjust(bool adjust, const struct sk_buff *skb) +{ + u32 truesize = skb->truesize; + + if (adjust && !skb_headlen(skb)) { + truesize -= SKB_TRUESIZE(skb_end_offset(skb)); + /* paranoid check, some drivers might be buggy */ + if (unlikely((int)truesize < (int)skb->len)) + truesize = skb->truesize; + } + return truesize; +} + +static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb, + bool adjust) { struct tcp_sock *tp = tcp_sk(sk); int room; @@ -480,15 +502,16 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) /* Check #1 */ if (room > 0 && !tcp_under_memory_pressure(sk)) { + unsigned int truesize = truesize_adjust(adjust, skb); int incr; /* Check #2. Increase window, if skb with such overhead * will fit to rcvbuf in future. */ - if (tcp_win_from_space(sk, skb->truesize) <= skb->len) + if (tcp_win_from_space(sk, truesize) <= skb->len) incr = 2 * tp->advmss; else - incr = __tcp_grow_window(sk, skb); + incr = __tcp_grow_window(sk, skb, truesize); if (incr) { incr = max_t(int, incr, 2 * skb->len); @@ -782,7 +805,7 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb) tcp_ecn_check_ce(sk, skb); if (skb->len >= 128) - tcp_grow_window(sk, skb); + tcp_grow_window(sk, skb, true); } /* Called to compute a smoothed rtt estimate. The data fed to this @@ -969,6 +992,8 @@ static u32 tcp_dsack_seen(struct tcp_sock *tp, u32 start_seq, return 0; if (seq_len > tp->mss_cache) dup_segs = DIV_ROUND_UP(seq_len, tp->mss_cache); + else if (tp->tlp_high_seq && tp->tlp_high_seq == end_seq) + state->flag |= FLAG_DSACK_TLP; tp->dsack_dups += dup_segs; /* Skip the DSACK if dup segs weren't retransmitted by sender */ @@ -976,7 +1001,14 @@ static u32 tcp_dsack_seen(struct tcp_sock *tp, u32 start_seq, return 0; tp->rx_opt.sack_ok |= TCP_DSACK_SEEN; - tp->rack.dsack_seen = 1; + /* We increase the RACK ordering window in rounds where we receive + * DSACKs that may have been due to reordering causing RACK to trigger + * a spurious fast recovery. Thus RACK ignores DSACKs that happen + * without having seen reordering, or that match TLP probes (TLP + * is timer-driven, not triggered by RACK). + */ + if (tp->reord_seen && !(state->flag & FLAG_DSACK_TLP)) + tp->rack.dsack_seen = 1; state->flag |= FLAG_DSACKING_ACK; /* A spurious retransmission is delivered */ @@ -3628,7 +3660,7 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) if (!tp->tlp_retrans) { /* TLP of new data has been acknowledged */ tp->tlp_high_seq = 0; - } else if (flag & FLAG_DSACKING_ACK) { + } else if (flag & FLAG_DSACK_TLP) { /* This DSACK means original and TLP probe arrived; no loss */ tp->tlp_high_seq = 0; } else if (after(ack, tp->tlp_high_seq)) { @@ -4769,7 +4801,7 @@ coalesce_done: * and trigger fast retransmit. */ if (tcp_is_sack(tp)) - tcp_grow_window(sk, skb); + tcp_grow_window(sk, skb, true); kfree_skb_partial(skb, fragstolen); skb = NULL; goto add_sack; @@ -4857,7 +4889,7 @@ end: * and trigger fast retransmit. */ if (tcp_is_sack(tp)) - tcp_grow_window(sk, skb); + tcp_grow_window(sk, skb, false); skb_condense(skb); skb_set_owner_r(skb, sk); } @@ -5383,7 +5415,7 @@ static void tcp_new_space(struct sock *sk) tp->snd_cwnd_stamp = tcp_jiffies32; } - sk->sk_write_space(sk); + INDIRECT_CALL_1(sk->sk_write_space, sk_stream_write_space, sk); } static void tcp_check_space(struct sock *sk) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a692626c19e4..2e62e0d6373a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2277,51 +2277,72 @@ EXPORT_SYMBOL(tcp_v4_destroy_sock); #ifdef CONFIG_PROC_FS /* Proc filesystem TCP sock list dumping. */ -/* - * Get next listener socket follow cur. If cur is NULL, get first socket - * starting from bucket given in st->bucket; when st->bucket is zero the - * very first socket in the hash table is returned. +static unsigned short seq_file_family(const struct seq_file *seq); + +static bool seq_sk_match(struct seq_file *seq, const struct sock *sk) +{ + unsigned short family = seq_file_family(seq); + + /* AF_UNSPEC is used as a match all */ + return ((family == AF_UNSPEC || family == sk->sk_family) && + net_eq(sock_net(sk), seq_file_net(seq))); +} + +/* Find a non empty bucket (starting from st->bucket) + * and return the first sk from it. */ -static void *listening_get_next(struct seq_file *seq, void *cur) +static void *listening_get_first(struct seq_file *seq) { - struct tcp_seq_afinfo *afinfo; struct tcp_iter_state *st = seq->private; - struct net *net = seq_file_net(seq); - struct inet_listen_hashbucket *ilb; - struct hlist_nulls_node *node; - struct sock *sk = cur; - if (st->bpf_seq_afinfo) - afinfo = st->bpf_seq_afinfo; - else - afinfo = PDE_DATA(file_inode(seq->file)); + st->offset = 0; + for (; st->bucket <= tcp_hashinfo.lhash2_mask; st->bucket++) { + struct inet_listen_hashbucket *ilb2; + struct inet_connection_sock *icsk; + struct sock *sk; - if (!sk) { -get_head: - ilb = &tcp_hashinfo.listening_hash[st->bucket]; - spin_lock(&ilb->lock); - sk = sk_nulls_head(&ilb->nulls_head); - st->offset = 0; - goto get_sk; + ilb2 = &tcp_hashinfo.lhash2[st->bucket]; + if (hlist_empty(&ilb2->head)) + continue; + + spin_lock(&ilb2->lock); + inet_lhash2_for_each_icsk(icsk, &ilb2->head) { + sk = (struct sock *)icsk; + if (seq_sk_match(seq, sk)) + return sk; + } + spin_unlock(&ilb2->lock); } - ilb = &tcp_hashinfo.listening_hash[st->bucket]; + + return NULL; +} + +/* Find the next sk of "cur" within the same bucket (i.e. st->bucket). + * If "cur" is the last one in the st->bucket, + * call listening_get_first() to return the first sk of the next + * non empty bucket. + */ +static void *listening_get_next(struct seq_file *seq, void *cur) +{ + struct tcp_iter_state *st = seq->private; + struct inet_listen_hashbucket *ilb2; + struct inet_connection_sock *icsk; + struct sock *sk = cur; + ++st->num; ++st->offset; - sk = sk_nulls_next(sk); -get_sk: - sk_nulls_for_each_from(sk, node) { - if (!net_eq(sock_net(sk), net)) - continue; - if (afinfo->family == AF_UNSPEC || - sk->sk_family == afinfo->family) + icsk = inet_csk(sk); + inet_lhash2_for_each_icsk_continue(icsk) { + sk = (struct sock *)icsk; + if (seq_sk_match(seq, sk)) return sk; } - spin_unlock(&ilb->lock); - st->offset = 0; - if (++st->bucket < INET_LHTABLE_SIZE) - goto get_head; - return NULL; + + ilb2 = &tcp_hashinfo.lhash2[st->bucket]; + spin_unlock(&ilb2->lock); + ++st->bucket; + return listening_get_first(seq); } static void *listening_get_idx(struct seq_file *seq, loff_t *pos) @@ -2331,7 +2352,7 @@ static void *listening_get_idx(struct seq_file *seq, loff_t *pos) st->bucket = 0; st->offset = 0; - rc = listening_get_next(seq, NULL); + rc = listening_get_first(seq); while (rc && *pos) { rc = listening_get_next(seq, rc); @@ -2351,15 +2372,7 @@ static inline bool empty_bucket(const struct tcp_iter_state *st) */ static void *established_get_first(struct seq_file *seq) { - struct tcp_seq_afinfo *afinfo; struct tcp_iter_state *st = seq->private; - struct net *net = seq_file_net(seq); - void *rc = NULL; - - if (st->bpf_seq_afinfo) - afinfo = st->bpf_seq_afinfo; - else - afinfo = PDE_DATA(file_inode(seq->file)); st->offset = 0; for (; st->bucket <= tcp_hashinfo.ehash_mask; ++st->bucket) { @@ -2373,32 +2386,20 @@ static void *established_get_first(struct seq_file *seq) spin_lock_bh(lock); sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) { - if ((afinfo->family != AF_UNSPEC && - sk->sk_family != afinfo->family) || - !net_eq(sock_net(sk), net)) { - continue; - } - rc = sk; - goto out; + if (seq_sk_match(seq, sk)) + return sk; } spin_unlock_bh(lock); } -out: - return rc; + + return NULL; } static void *established_get_next(struct seq_file *seq, void *cur) { - struct tcp_seq_afinfo *afinfo; struct sock *sk = cur; struct hlist_nulls_node *node; struct tcp_iter_state *st = seq->private; - struct net *net = seq_file_net(seq); - - if (st->bpf_seq_afinfo) - afinfo = st->bpf_seq_afinfo; - else - afinfo = PDE_DATA(file_inode(seq->file)); ++st->num; ++st->offset; @@ -2406,9 +2407,7 @@ static void *established_get_next(struct seq_file *seq, void *cur) sk = sk_nulls_next(sk); sk_nulls_for_each_from(sk, node) { - if ((afinfo->family == AF_UNSPEC || - sk->sk_family == afinfo->family) && - net_eq(sock_net(sk), net)) + if (seq_sk_match(seq, sk)) return sk; } @@ -2451,17 +2450,18 @@ static void *tcp_get_idx(struct seq_file *seq, loff_t pos) static void *tcp_seek_last_pos(struct seq_file *seq) { struct tcp_iter_state *st = seq->private; + int bucket = st->bucket; int offset = st->offset; int orig_num = st->num; void *rc = NULL; switch (st->state) { case TCP_SEQ_STATE_LISTENING: - if (st->bucket >= INET_LHTABLE_SIZE) + if (st->bucket > tcp_hashinfo.lhash2_mask) break; st->state = TCP_SEQ_STATE_LISTENING; - rc = listening_get_next(seq, NULL); - while (offset-- && rc) + rc = listening_get_first(seq); + while (offset-- && rc && bucket == st->bucket) rc = listening_get_next(seq, rc); if (rc) break; @@ -2472,7 +2472,7 @@ static void *tcp_seek_last_pos(struct seq_file *seq) if (st->bucket > tcp_hashinfo.ehash_mask) break; rc = established_get_first(seq); - while (offset-- && rc) + while (offset-- && rc && bucket == st->bucket) rc = established_get_next(seq, rc); } @@ -2542,7 +2542,7 @@ void tcp_seq_stop(struct seq_file *seq, void *v) switch (st->state) { case TCP_SEQ_STATE_LISTENING: if (v != SEQ_START_TOKEN) - spin_unlock(&tcp_hashinfo.listening_hash[st->bucket].lock); + spin_unlock(&tcp_hashinfo.lhash2[st->bucket].lock); break; case TCP_SEQ_STATE_ESTABLISHED: if (v) @@ -2687,6 +2687,15 @@ out: } #ifdef CONFIG_BPF_SYSCALL +struct bpf_tcp_iter_state { + struct tcp_iter_state state; + unsigned int cur_sk; + unsigned int end_sk; + unsigned int max_sk; + struct sock **batch; + bool st_bucket_done; +}; + struct bpf_iter__tcp { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct sock_common *, sk_common); @@ -2705,16 +2714,204 @@ static int tcp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, return bpf_iter_run_prog(prog, &ctx); } +static void bpf_iter_tcp_put_batch(struct bpf_tcp_iter_state *iter) +{ + while (iter->cur_sk < iter->end_sk) + sock_put(iter->batch[iter->cur_sk++]); +} + +static int bpf_iter_tcp_realloc_batch(struct bpf_tcp_iter_state *iter, + unsigned int new_batch_sz) +{ + struct sock **new_batch; + + new_batch = kvmalloc(sizeof(*new_batch) * new_batch_sz, + GFP_USER | __GFP_NOWARN); + if (!new_batch) + return -ENOMEM; + + bpf_iter_tcp_put_batch(iter); + kvfree(iter->batch); + iter->batch = new_batch; + iter->max_sk = new_batch_sz; + + return 0; +} + +static unsigned int bpf_iter_tcp_listening_batch(struct seq_file *seq, + struct sock *start_sk) +{ + struct bpf_tcp_iter_state *iter = seq->private; + struct tcp_iter_state *st = &iter->state; + struct inet_connection_sock *icsk; + unsigned int expected = 1; + struct sock *sk; + + sock_hold(start_sk); + iter->batch[iter->end_sk++] = start_sk; + + icsk = inet_csk(start_sk); + inet_lhash2_for_each_icsk_continue(icsk) { + sk = (struct sock *)icsk; + if (seq_sk_match(seq, sk)) { + if (iter->end_sk < iter->max_sk) { + sock_hold(sk); + iter->batch[iter->end_sk++] = sk; + } + expected++; + } + } + spin_unlock(&tcp_hashinfo.lhash2[st->bucket].lock); + + return expected; +} + +static unsigned int bpf_iter_tcp_established_batch(struct seq_file *seq, + struct sock *start_sk) +{ + struct bpf_tcp_iter_state *iter = seq->private; + struct tcp_iter_state *st = &iter->state; + struct hlist_nulls_node *node; + unsigned int expected = 1; + struct sock *sk; + + sock_hold(start_sk); + iter->batch[iter->end_sk++] = start_sk; + + sk = sk_nulls_next(start_sk); + sk_nulls_for_each_from(sk, node) { + if (seq_sk_match(seq, sk)) { + if (iter->end_sk < iter->max_sk) { + sock_hold(sk); + iter->batch[iter->end_sk++] = sk; + } + expected++; + } + } + spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); + + return expected; +} + +static struct sock *bpf_iter_tcp_batch(struct seq_file *seq) +{ + struct bpf_tcp_iter_state *iter = seq->private; + struct tcp_iter_state *st = &iter->state; + unsigned int expected; + bool resized = false; + struct sock *sk; + + /* The st->bucket is done. Directly advance to the next + * bucket instead of having the tcp_seek_last_pos() to skip + * one by one in the current bucket and eventually find out + * it has to advance to the next bucket. + */ + if (iter->st_bucket_done) { + st->offset = 0; + st->bucket++; + if (st->state == TCP_SEQ_STATE_LISTENING && + st->bucket > tcp_hashinfo.lhash2_mask) { + st->state = TCP_SEQ_STATE_ESTABLISHED; + st->bucket = 0; + } + } + +again: + /* Get a new batch */ + iter->cur_sk = 0; + iter->end_sk = 0; + iter->st_bucket_done = false; + + sk = tcp_seek_last_pos(seq); + if (!sk) + return NULL; /* Done */ + + if (st->state == TCP_SEQ_STATE_LISTENING) + expected = bpf_iter_tcp_listening_batch(seq, sk); + else + expected = bpf_iter_tcp_established_batch(seq, sk); + + if (iter->end_sk == expected) { + iter->st_bucket_done = true; + return sk; + } + + if (!resized && !bpf_iter_tcp_realloc_batch(iter, expected * 3 / 2)) { + resized = true; + goto again; + } + + return sk; +} + +static void *bpf_iter_tcp_seq_start(struct seq_file *seq, loff_t *pos) +{ + /* bpf iter does not support lseek, so it always + * continue from where it was stop()-ped. + */ + if (*pos) + return bpf_iter_tcp_batch(seq); + + return SEQ_START_TOKEN; +} + +static void *bpf_iter_tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct bpf_tcp_iter_state *iter = seq->private; + struct tcp_iter_state *st = &iter->state; + struct sock *sk; + + /* Whenever seq_next() is called, the iter->cur_sk is + * done with seq_show(), so advance to the next sk in + * the batch. + */ + if (iter->cur_sk < iter->end_sk) { + /* Keeping st->num consistent in tcp_iter_state. + * bpf_iter_tcp does not use st->num. + * meta.seq_num is used instead. + */ + st->num++; + /* Move st->offset to the next sk in the bucket such that + * the future start() will resume at st->offset in + * st->bucket. See tcp_seek_last_pos(). + */ + st->offset++; + sock_put(iter->batch[iter->cur_sk++]); + } + + if (iter->cur_sk < iter->end_sk) + sk = iter->batch[iter->cur_sk]; + else + sk = bpf_iter_tcp_batch(seq); + + ++*pos; + /* Keeping st->last_pos consistent in tcp_iter_state. + * bpf iter does not do lseek, so st->last_pos always equals to *pos. + */ + st->last_pos = *pos; + return sk; +} + static int bpf_iter_tcp_seq_show(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; struct sock *sk = v; + bool slow; uid_t uid; + int ret; if (v == SEQ_START_TOKEN) return 0; + if (sk_fullsock(sk)) + slow = lock_sock_fast(sk); + + if (unlikely(sk_unhashed(sk))) { + ret = SEQ_SKIP; + goto unlock; + } + if (sk->sk_state == TCP_TIME_WAIT) { uid = 0; } else if (sk->sk_state == TCP_NEW_SYN_RECV) { @@ -2728,11 +2925,18 @@ static int bpf_iter_tcp_seq_show(struct seq_file *seq, void *v) meta.seq = seq; prog = bpf_iter_get_info(&meta, false); - return tcp_prog_seq_show(prog, &meta, v, uid); + ret = tcp_prog_seq_show(prog, &meta, v, uid); + +unlock: + if (sk_fullsock(sk)) + unlock_sock_fast(sk, slow); + return ret; + } static void bpf_iter_tcp_seq_stop(struct seq_file *seq, void *v) { + struct bpf_tcp_iter_state *iter = seq->private; struct bpf_iter_meta meta; struct bpf_prog *prog; @@ -2743,16 +2947,33 @@ static void bpf_iter_tcp_seq_stop(struct seq_file *seq, void *v) (void)tcp_prog_seq_show(prog, &meta, v, 0); } - tcp_seq_stop(seq, v); + if (iter->cur_sk < iter->end_sk) { + bpf_iter_tcp_put_batch(iter); + iter->st_bucket_done = false; + } } static const struct seq_operations bpf_iter_tcp_seq_ops = { .show = bpf_iter_tcp_seq_show, - .start = tcp_seq_start, - .next = tcp_seq_next, + .start = bpf_iter_tcp_seq_start, + .next = bpf_iter_tcp_seq_next, .stop = bpf_iter_tcp_seq_stop, }; #endif +static unsigned short seq_file_family(const struct seq_file *seq) +{ + const struct tcp_seq_afinfo *afinfo; + +#ifdef CONFIG_BPF_SYSCALL + /* Iterated from bpf_iter. Let the bpf prog to filter instead. */ + if (seq->op == &bpf_iter_tcp_seq_ops) + return AF_UNSPEC; +#endif + + /* Iterated from proc fs */ + afinfo = PDE_DATA(file_inode(seq->file)); + return afinfo->family; +} static const struct seq_operations tcp4_seq_ops = { .show = tcp4_seq_show, @@ -2964,7 +3185,6 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_comp_sack_slack_ns = 100 * NSEC_PER_USEC; net->ipv4.sysctl_tcp_comp_sack_nr = 44; net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE; - spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock); net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 0; atomic_set(&net->ipv4.tfo_active_disable_times, 0); @@ -3003,39 +3223,55 @@ static struct pernet_operations __net_initdata tcp_sk_ops = { DEFINE_BPF_ITER_FUNC(tcp, struct bpf_iter_meta *meta, struct sock_common *sk_common, uid_t uid) +#define INIT_BATCH_SZ 16 + static int bpf_iter_init_tcp(void *priv_data, struct bpf_iter_aux_info *aux) { - struct tcp_iter_state *st = priv_data; - struct tcp_seq_afinfo *afinfo; - int ret; + struct bpf_tcp_iter_state *iter = priv_data; + int err; - afinfo = kmalloc(sizeof(*afinfo), GFP_USER | __GFP_NOWARN); - if (!afinfo) - return -ENOMEM; + err = bpf_iter_init_seq_net(priv_data, aux); + if (err) + return err; - afinfo->family = AF_UNSPEC; - st->bpf_seq_afinfo = afinfo; - ret = bpf_iter_init_seq_net(priv_data, aux); - if (ret) - kfree(afinfo); - return ret; + err = bpf_iter_tcp_realloc_batch(iter, INIT_BATCH_SZ); + if (err) { + bpf_iter_fini_seq_net(priv_data); + return err; + } + + return 0; } static void bpf_iter_fini_tcp(void *priv_data) { - struct tcp_iter_state *st = priv_data; + struct bpf_tcp_iter_state *iter = priv_data; - kfree(st->bpf_seq_afinfo); bpf_iter_fini_seq_net(priv_data); + kvfree(iter->batch); } static const struct bpf_iter_seq_info tcp_seq_info = { .seq_ops = &bpf_iter_tcp_seq_ops, .init_seq_private = bpf_iter_init_tcp, .fini_seq_private = bpf_iter_fini_tcp, - .seq_priv_size = sizeof(struct tcp_iter_state), + .seq_priv_size = sizeof(struct bpf_tcp_iter_state), }; +static const struct bpf_func_proto * +bpf_iter_tcp_get_func_proto(enum bpf_func_id func_id, + const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_setsockopt: + return &bpf_sk_setsockopt_proto; + case BPF_FUNC_getsockopt: + return &bpf_sk_getsockopt_proto; + default: + return NULL; + } +} + static struct bpf_iter_reg tcp_reg_info = { .target = "tcp", .ctx_arg_info_size = 1, @@ -3043,6 +3279,7 @@ static struct bpf_iter_reg tcp_reg_info = { { offsetof(struct bpf_iter__tcp, sk_common), PTR_TO_BTF_ID_OR_NULL }, }, + .get_func_proto = bpf_iter_tcp_get_func_proto, .seq_info = &tcp_seq_info, }; diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index e09147ac9a99..fc61cd3fea65 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -298,6 +298,9 @@ int tcp_gro_complete(struct sk_buff *skb) if (th->cwr) skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; + if (skb->encapsulation) + skb->inner_transport_header = skb->transport_header; + return 0; } EXPORT_SYMBOL(tcp_gro_complete); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 29553fce8502..6d72f3ea48c4 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3373,7 +3373,8 @@ void sk_forced_mem_schedule(struct sock *sk, int size) sk_memory_allocated_add(sk, amt); if (mem_cgroup_sockets_enabled && sk->sk_memcg) - mem_cgroup_charge_skmem(sk->sk_memcg, amt); + mem_cgroup_charge_skmem(sk->sk_memcg, amt, + gfp_memcg_charge() | __GFP_NOFAIL); } /* Send a FIN. The caller locks the socket for us. diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index 6f1b4ac7fe99..fd113f6226ef 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -172,7 +172,8 @@ void tcp_rack_reo_timeout(struct sock *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 + * If a DSACK is received that seems like it may have been due to reordering + * triggering fast recovery, 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. * diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1a742b710e54..8851c9463b4b 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1143,7 +1143,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) rcu_read_unlock(); } - if (cgroup_bpf_enabled(BPF_CGROUP_UDP4_SENDMSG) && !connected) { + if (cgroup_bpf_enabled(CGROUP_UDP4_SENDMSG) && !connected) { err = BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, (struct sockaddr *)usin, &ipc.addr); if (err) diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c index 9f5a5cdc38e6..7a1d5f473878 100644 --- a/net/ipv4/udp_bpf.c +++ b/net/ipv4/udp_bpf.c @@ -112,7 +112,6 @@ static struct proto udp_bpf_prots[UDP_BPF_NUM_PROTS]; static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base) { *prot = *base; - prot->unhash = sock_map_unhash; prot->close = sock_map_close; prot->recvmsg = udp_bpf_recvmsg; } diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 9dde1e5fb449..86d32a1e62ac 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -152,8 +152,8 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, netdev_features_t features, bool is_ipv6) { + const struct net_offload __rcu **offloads; __be16 protocol = skb->protocol; - const struct net_offload **offloads; const struct net_offload *ops; struct sk_buff *segs = ERR_PTR(-EINVAL); struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb, @@ -624,6 +624,10 @@ static int udp_gro_complete_segment(struct sk_buff *skb) skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_L4; + + if (skb->encapsulation) + skb->inner_transport_header = skb->transport_header; + return 0; } diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 747f56e0c636..e504204bca92 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -328,4 +328,15 @@ config IPV6_RPL_LWTUNNEL If unsure, say N. +config IPV6_IOAM6_LWTUNNEL + bool "IPv6: IOAM Pre-allocated Trace insertion support" + depends on IPV6 + select LWTUNNEL + help + Support for the inline insertion of IOAM Pre-allocated + Trace Header (only on locally generated packets), using + the lightweight tunnels mechanism. + + If unsure, say N. + endif # IPV6 diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index cf7b47bdb9b3..1bc7e143217b 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -10,7 +10,7 @@ ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \ route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \ raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o ping.o \ exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o \ - udp_offload.o seg6.o fib6_notifier.o rpl.o + udp_offload.o seg6.o fib6_notifier.o rpl.o ioam6.o ipv6-offload := ip6_offload.o tcpv6_offload.o exthdrs_offload.o @@ -27,6 +27,7 @@ ipv6-$(CONFIG_NETLABEL) += calipso.o ipv6-$(CONFIG_IPV6_SEG6_LWTUNNEL) += seg6_iptunnel.o seg6_local.o ipv6-$(CONFIG_IPV6_SEG6_HMAC) += seg6_hmac.o ipv6-$(CONFIG_IPV6_RPL_LWTUNNEL) += rpl_iptunnel.o +ipv6-$(CONFIG_IPV6_IOAM6_LWTUNNEL) += ioam6_iptunnel.o ipv6-objs += $(ipv6-y) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 3bf685fe64b9..c6a90b7bbb70 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -89,6 +89,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/export.h> +#include <linux/ioam6.h> #define INFINITY_LIFE_TIME 0xFFFFFFFF @@ -237,6 +238,9 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64, .disable_policy = 0, .rpl_seg_enabled = 0, + .ioam6_enabled = 0, + .ioam6_id = IOAM6_DEFAULT_IF_ID, + .ioam6_id_wide = IOAM6_DEFAULT_IF_ID_WIDE, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -293,6 +297,9 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64, .disable_policy = 0, .rpl_seg_enabled = 0, + .ioam6_enabled = 0, + .ioam6_id = IOAM6_DEFAULT_IF_ID, + .ioam6_id_wide = IOAM6_DEFAULT_IF_ID_WIDE, }; /* Check if link is ready: is it up and is a valid qdisc available */ @@ -387,6 +394,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) ndev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY; ndev->cnf.mtu6 = dev->mtu; + ndev->ra_mtu = 0; ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl); if (!ndev->nd_parms) { kfree(ndev); @@ -694,8 +702,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, errout: if (in6_dev) in6_dev_put(in6_dev); - if (dev) - dev_put(dev); + dev_put(dev); return err; } @@ -1080,7 +1087,7 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg, goto out; } - ifa = kzalloc(sizeof(*ifa), gfp_flags); + ifa = kzalloc(sizeof(*ifa), gfp_flags | __GFP_ACCOUNT); if (!ifa) { err = -ENOBUFS; goto out; @@ -3085,19 +3092,22 @@ static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr, } } -#if IS_ENABLED(CONFIG_IPV6_SIT) -static void sit_add_v4_addrs(struct inet6_dev *idev) +#if IS_ENABLED(CONFIG_IPV6_SIT) || IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE) +static void add_v4_addrs(struct inet6_dev *idev) { struct in6_addr addr; struct net_device *dev; struct net *net = dev_net(idev->dev); - int scope, plen; + int scope, plen, offset = 0; u32 pflags = 0; ASSERT_RTNL(); memset(&addr, 0, sizeof(struct in6_addr)); - memcpy(&addr.s6_addr32[3], idev->dev->dev_addr, 4); + /* in case of IP6GRE the dev_addr is an IPv6 and therefore we use only the last 4 bytes */ + if (idev->dev->addr_len == sizeof(struct in6_addr)) + offset = sizeof(struct in6_addr) - 4; + memcpy(&addr.s6_addr32[3], idev->dev->dev_addr + offset, 4); if (idev->dev->flags&IFF_POINTOPOINT) { addr.s6_addr32[0] = htonl(0xfe800000); @@ -3335,8 +3345,6 @@ static void addrconf_dev_config(struct net_device *dev) (dev->type != ARPHRD_IEEE1394) && (dev->type != ARPHRD_TUNNEL6) && (dev->type != ARPHRD_6LOWPAN) && - (dev->type != ARPHRD_IP6GRE) && - (dev->type != ARPHRD_IPGRE) && (dev->type != ARPHRD_TUNNEL) && (dev->type != ARPHRD_NONE) && (dev->type != ARPHRD_RAWIP)) { @@ -3384,14 +3392,14 @@ static void addrconf_sit_config(struct net_device *dev) return; } - sit_add_v4_addrs(idev); + add_v4_addrs(idev); if (dev->flags&IFF_POINTOPOINT) addrconf_add_mroute(dev); } #endif -#if IS_ENABLED(CONFIG_NET_IPGRE) +#if IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE) static void addrconf_gre_config(struct net_device *dev) { struct inet6_dev *idev; @@ -3404,7 +3412,13 @@ static void addrconf_gre_config(struct net_device *dev) return; } - addrconf_addr_gen(idev, true); + if (dev->type == ARPHRD_ETHER) { + addrconf_addr_gen(idev, true); + return; + } + + add_v4_addrs(idev); + if (dev->flags & IFF_POINTOPOINT) addrconf_add_mroute(dev); } @@ -3580,7 +3594,8 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, addrconf_sit_config(dev); break; #endif -#if IS_ENABLED(CONFIG_NET_IPGRE) +#if IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE) + case ARPHRD_IP6GRE: case ARPHRD_IPGRE: addrconf_gre_config(dev); break; @@ -3843,6 +3858,7 @@ restart: } idev->tstamp = jiffies; + idev->ra_mtu = 0; /* Last: Shot the device (if unregistered) */ if (unregister) { @@ -5211,8 +5227,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, .netnsid = -1, .type = type, }; - struct net *net = sock_net(skb->sk); - struct net *tgt_net = net; + struct net *tgt_net = sock_net(skb->sk); int idx, s_idx, s_ip_idx; int h, s_h; struct net_device *dev; @@ -5351,7 +5366,7 @@ static int inet6_rtm_valid_getaddr_req(struct sk_buff *skb, static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { - struct net *net = sock_net(in_skb->sk); + struct net *tgt_net = sock_net(in_skb->sk); struct inet6_fill_args fillargs = { .portid = NETLINK_CB(in_skb).portid, .seq = nlh->nlmsg_seq, @@ -5359,7 +5374,6 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, .flags = 0, .netnsid = -1, }; - struct net *tgt_net = net; struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; struct in6_addr *addr = NULL, *peer; @@ -5412,8 +5426,7 @@ 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); + dev_put(dev); if (fillargs.netnsid >= 0) put_net(tgt_net); @@ -5526,6 +5539,9 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_DISABLE_POLICY] = cnf->disable_policy; array[DEVCONF_NDISC_TCLASS] = cnf->ndisc_tclass; array[DEVCONF_RPL_SEG_ENABLED] = cnf->rpl_seg_enabled; + array[DEVCONF_IOAM6_ENABLED] = cnf->ioam6_enabled; + array[DEVCONF_IOAM6_ID] = cnf->ioam6_id; + array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide; } static inline size_t inet6_ifla6_size(void) @@ -5537,6 +5553,7 @@ static inline size_t inet6_ifla6_size(void) + nla_total_size(ICMP6_MIB_MAX * 8) /* IFLA_INET6_ICMP6STATS */ + nla_total_size(sizeof(struct in6_addr)) /* IFLA_INET6_TOKEN */ + nla_total_size(1) /* IFLA_INET6_ADDR_GEN_MODE */ + + nla_total_size(4) /* IFLA_INET6_RA_MTU */ + 0; } @@ -5645,6 +5662,10 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev, if (nla_put_u8(skb, IFLA_INET6_ADDR_GEN_MODE, idev->cnf.addr_gen_mode)) goto nla_put_failure; + if (idev->ra_mtu && + nla_put_u32(skb, IFLA_INET6_RA_MTU, idev->ra_mtu)) + goto nla_put_failure; + return 0; nla_put_failure: @@ -5761,6 +5782,9 @@ update_lft: static const struct nla_policy inet6_af_policy[IFLA_INET6_MAX + 1] = { [IFLA_INET6_ADDR_GEN_MODE] = { .type = NLA_U8 }, [IFLA_INET6_TOKEN] = { .len = sizeof(struct in6_addr) }, + [IFLA_INET6_RA_MTU] = { .type = NLA_REJECT, + .reject_message = + "IFLA_INET6_RA_MTU can not be set" }, }; static int check_addr_gen_mode(int mode) @@ -5784,7 +5808,8 @@ static int check_stable_privacy(struct inet6_dev *idev, struct net *net, } static int inet6_validate_link_af(const struct net_device *dev, - const struct nlattr *nla) + const struct nlattr *nla, + struct netlink_ext_ack *extack) { struct nlattr *tb[IFLA_INET6_MAX + 1]; struct inet6_dev *idev = NULL; @@ -5797,7 +5822,7 @@ static int inet6_validate_link_af(const struct net_device *dev, } err = nla_parse_nested_deprecated(tb, IFLA_INET6_MAX, nla, - inet6_af_policy, NULL); + inet6_af_policy, extack); if (err) return err; @@ -6540,6 +6565,7 @@ static int addrconf_sysctl_disable_policy(struct ctl_table *ctl, int write, static int minus_one = -1; static const int two_five_five = 255; +static u32 ioam6_if_id_max = U16_MAX; static const struct ctl_table addrconf_sysctl[] = { { @@ -6933,6 +6959,31 @@ static const struct ctl_table addrconf_sysctl[] = { .proc_handler = proc_dointvec, }, { + .procname = "ioam6_enabled", + .data = &ipv6_devconf.ioam6_enabled, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = (void *)SYSCTL_ZERO, + .extra2 = (void *)SYSCTL_ONE, + }, + { + .procname = "ioam6_id", + .data = &ipv6_devconf.ioam6_id, + .maxlen = sizeof(u32), + .mode = 0644, + .proc_handler = proc_douintvec_minmax, + .extra1 = (void *)SYSCTL_ZERO, + .extra2 = (void *)&ioam6_if_id_max, + }, + { + .procname = "ioam6_id_wide", + .data = &ipv6_devconf.ioam6_id_wide, + .maxlen = sizeof(u32), + .mode = 0644, + .proc_handler = proc_douintvec, + }, + { /* sentinel */ } }; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 2389ff702f51..b5878bb8e419 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -62,6 +62,7 @@ #include <net/rpl.h> #include <net/compat.h> #include <net/xfrm.h> +#include <net/ioam6.h> #include <linux/uaccess.h> #include <linux/mroute6.h> @@ -454,7 +455,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) * changes context in a wrong way it will be caught. */ err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, - BPF_CGROUP_INET6_BIND, &flags); + CGROUP_INET6_BIND, &flags); if (err) return err; @@ -531,7 +532,7 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, if (np->sndflow) sin->sin6_flowinfo = np->flow_label; BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin, - BPF_CGROUP_INET6_GETPEERNAME, + CGROUP_INET6_GETPEERNAME, NULL); } else { if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) @@ -540,7 +541,7 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin6_addr = sk->sk_v6_rcv_saddr; sin->sin6_port = inet->inet_sport; BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin, - BPF_CGROUP_INET6_GETSOCKNAME, + CGROUP_INET6_GETSOCKNAME, NULL); } sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr, @@ -961,6 +962,9 @@ static int __net_init inet6_net_init(struct net *net) net->ipv6.sysctl.fib_notify_on_flag_change = 0; atomic_set(&net->ipv6.fib6_sernum, 1); + net->ipv6.sysctl.ioam6_id = IOAM6_DEFAULT_ID; + net->ipv6.sysctl.ioam6_id_wide = IOAM6_DEFAULT_ID_WIDE; + err = ipv6_init_mibs(net); if (err) return err; @@ -1191,6 +1195,10 @@ static int __init inet6_init(void) if (err) goto rpl_fail; + err = ioam6_init(); + if (err) + goto ioam6_fail; + err = igmp6_late_init(); if (err) goto igmp6_late_err; @@ -1213,6 +1221,8 @@ sysctl_fail: igmp6_late_cleanup(); #endif igmp6_late_err: + ioam6_exit(); +ioam6_fail: rpl_exit(); rpl_fail: seg6_exit(); diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 26882e165c9e..3a871a09f962 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -49,22 +49,12 @@ #include <net/seg6_hmac.h> #endif #include <net/rpl.h> +#include <linux/ioam6.h> +#include <net/ioam6.h> +#include <net/dst_metadata.h> #include <linux/uaccess.h> -/* - * Parsing tlv encoded headers. - * - * Parsing function "func" returns true, if parsing succeed - * and false, if it failed. - * It MUST NOT touch skb->h. - */ - -struct tlvtype_proc { - int type; - bool (*func)(struct sk_buff *skb, int offset); -}; - /********************* Generic functions *********************/ @@ -109,16 +99,23 @@ drop: return false; } +static bool ipv6_hop_ra(struct sk_buff *skb, int optoff); +static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff); +static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff); +static bool ipv6_hop_calipso(struct sk_buff *skb, int optoff); +#if IS_ENABLED(CONFIG_IPV6_MIP6) +static bool ipv6_dest_hao(struct sk_buff *skb, int optoff); +#endif + /* Parse tlv encoded option header (hop-by-hop or destination) */ -static bool ip6_parse_tlv(const struct tlvtype_proc *procs, +static bool ip6_parse_tlv(bool hopbyhop, struct sk_buff *skb, int max_count) { int len = (skb_transport_header(skb)[1] + 1) << 3; const unsigned char *nh = skb_network_header(skb); int off = skb_network_header_len(skb); - const struct tlvtype_proc *curr; bool disallow_unknowns = false; int tlv_count = 0; int padlen = 0; @@ -173,20 +170,45 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, if (tlv_count > max_count) goto bad; - for (curr = procs; curr->type >= 0; curr++) { - if (curr->type == nh[off]) { - /* type specific length/alignment - checks will be performed in the - func(). */ - if (curr->func(skb, off) == false) + if (hopbyhop) { + switch (nh[off]) { + case IPV6_TLV_ROUTERALERT: + if (!ipv6_hop_ra(skb, off)) + return false; + break; + case IPV6_TLV_IOAM: + if (!ipv6_hop_ioam(skb, off)) + return false; + break; + case IPV6_TLV_JUMBO: + if (!ipv6_hop_jumbo(skb, off)) + return false; + break; + case IPV6_TLV_CALIPSO: + if (!ipv6_hop_calipso(skb, off)) + return false; + break; + default: + if (!ip6_tlvopt_unknown(skb, off, + disallow_unknowns)) + return false; + break; + } + } else { + switch (nh[off]) { +#if IS_ENABLED(CONFIG_IPV6_MIP6) + case IPV6_TLV_HAO: + if (!ipv6_dest_hao(skb, off)) + return false; + break; +#endif + default: + if (!ip6_tlvopt_unknown(skb, off, + disallow_unknowns)) return false; break; } } - if (curr->type < 0 && - !ip6_tlvopt_unknown(skb, off, disallow_unknowns)) - return false; - padlen = 0; } off += optlen; @@ -264,16 +286,6 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff) } #endif -static const struct tlvtype_proc tlvprocdestopt_lst[] = { -#if IS_ENABLED(CONFIG_IPV6_MIP6) - { - .type = IPV6_TLV_HAO, - .func = ipv6_dest_hao, - }, -#endif - {-1, NULL} -}; - static int ipv6_destopt_rcv(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); @@ -304,8 +316,7 @@ fail_and_free: dstbuf = opt->dst1; #endif - if (ip6_parse_tlv(tlvprocdestopt_lst, skb, - net->ipv6.sysctl.max_dst_opts_cnt)) { + if (ip6_parse_tlv(false, skb, net->ipv6.sysctl.max_dst_opts_cnt)) { skb->transport_header += extlen; opt = IP6CB(skb); #if IS_ENABLED(CONFIG_IPV6_MIP6) @@ -928,6 +939,60 @@ static bool ipv6_hop_ra(struct sk_buff *skb, int optoff) return false; } +/* IOAM */ + +static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) +{ + struct ioam6_trace_hdr *trace; + struct ioam6_namespace *ns; + struct ioam6_hdr *hdr; + + /* Bad alignment (must be 4n-aligned) */ + if (optoff & 3) + goto drop; + + /* Ignore if IOAM is not enabled on ingress */ + if (!__in6_dev_get(skb->dev)->cnf.ioam6_enabled) + goto ignore; + + /* Truncated Option header */ + hdr = (struct ioam6_hdr *)(skb_network_header(skb) + optoff); + if (hdr->opt_len < 2) + goto drop; + + switch (hdr->type) { + case IOAM6_TYPE_PREALLOC: + /* Truncated Pre-allocated Trace header */ + if (hdr->opt_len < 2 + sizeof(*trace)) + goto drop; + + /* Malformed Pre-allocated Trace header */ + trace = (struct ioam6_trace_hdr *)((u8 *)hdr + sizeof(*hdr)); + if (hdr->opt_len < 2 + sizeof(*trace) + trace->remlen * 4) + goto drop; + + /* Ignore if the IOAM namespace is unknown */ + ns = ioam6_namespace(ipv6_skb_net(skb), trace->namespace_id); + if (!ns) + goto ignore; + + if (!skb_valid_dst(skb)) + ip6_route_input(skb); + + ioam6_fill_trace_data(skb, ns, trace); + break; + default: + break; + } + +ignore: + return true; + +drop: + kfree_skb(skb); + return false; +} + /* Jumbo payload */ static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff) @@ -994,22 +1059,6 @@ drop: return false; } -static const struct tlvtype_proc tlvprochopopt_lst[] = { - { - .type = IPV6_TLV_ROUTERALERT, - .func = ipv6_hop_ra, - }, - { - .type = IPV6_TLV_JUMBO, - .func = ipv6_hop_jumbo, - }, - { - .type = IPV6_TLV_CALIPSO, - .func = ipv6_hop_calipso, - }, - { -1, } -}; - int ipv6_parse_hopopts(struct sk_buff *skb) { struct inet6_skb_parm *opt = IP6CB(skb); @@ -1035,8 +1084,7 @@ fail_and_free: goto fail_and_free; opt->flags |= IP6SKB_HOPBYHOP; - if (ip6_parse_tlv(tlvprochopopt_lst, skb, - net->ipv6.sysctl.max_hbh_opts_cnt)) { + if (ip6_parse_tlv(true, skb, net->ipv6.sysctl.max_hbh_opts_cnt)) { skb->transport_header += extlen; opt = IP6CB(skb); opt->nhoff = sizeof(struct ipv6hdr); diff --git a/net/ipv6/ioam6.c b/net/ipv6/ioam6.c new file mode 100644 index 000000000000..5e8961004832 --- /dev/null +++ b/net/ipv6/ioam6.c @@ -0,0 +1,910 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * IPv6 IOAM implementation + * + * Author: + * Justin Iurman <justin.iurman@uliege.be> + */ + +#include <linux/errno.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/net.h> +#include <linux/ioam6.h> +#include <linux/ioam6_genl.h> +#include <linux/rhashtable.h> + +#include <net/addrconf.h> +#include <net/genetlink.h> +#include <net/ioam6.h> + +static void ioam6_ns_release(struct ioam6_namespace *ns) +{ + kfree_rcu(ns, rcu); +} + +static void ioam6_sc_release(struct ioam6_schema *sc) +{ + kfree_rcu(sc, rcu); +} + +static void ioam6_free_ns(void *ptr, void *arg) +{ + struct ioam6_namespace *ns = (struct ioam6_namespace *)ptr; + + if (ns) + ioam6_ns_release(ns); +} + +static void ioam6_free_sc(void *ptr, void *arg) +{ + struct ioam6_schema *sc = (struct ioam6_schema *)ptr; + + if (sc) + ioam6_sc_release(sc); +} + +static int ioam6_ns_cmpfn(struct rhashtable_compare_arg *arg, const void *obj) +{ + const struct ioam6_namespace *ns = obj; + + return (ns->id != *(__be16 *)arg->key); +} + +static int ioam6_sc_cmpfn(struct rhashtable_compare_arg *arg, const void *obj) +{ + const struct ioam6_schema *sc = obj; + + return (sc->id != *(u32 *)arg->key); +} + +static const struct rhashtable_params rht_ns_params = { + .key_len = sizeof(__be16), + .key_offset = offsetof(struct ioam6_namespace, id), + .head_offset = offsetof(struct ioam6_namespace, head), + .automatic_shrinking = true, + .obj_cmpfn = ioam6_ns_cmpfn, +}; + +static const struct rhashtable_params rht_sc_params = { + .key_len = sizeof(u32), + .key_offset = offsetof(struct ioam6_schema, id), + .head_offset = offsetof(struct ioam6_schema, head), + .automatic_shrinking = true, + .obj_cmpfn = ioam6_sc_cmpfn, +}; + +static struct genl_family ioam6_genl_family; + +static const struct nla_policy ioam6_genl_policy_addns[] = { + [IOAM6_ATTR_NS_ID] = { .type = NLA_U16 }, + [IOAM6_ATTR_NS_DATA] = { .type = NLA_U32 }, + [IOAM6_ATTR_NS_DATA_WIDE] = { .type = NLA_U64 }, +}; + +static const struct nla_policy ioam6_genl_policy_delns[] = { + [IOAM6_ATTR_NS_ID] = { .type = NLA_U16 }, +}; + +static const struct nla_policy ioam6_genl_policy_addsc[] = { + [IOAM6_ATTR_SC_ID] = { .type = NLA_U32 }, + [IOAM6_ATTR_SC_DATA] = { .type = NLA_BINARY, + .len = IOAM6_MAX_SCHEMA_DATA_LEN }, +}; + +static const struct nla_policy ioam6_genl_policy_delsc[] = { + [IOAM6_ATTR_SC_ID] = { .type = NLA_U32 }, +}; + +static const struct nla_policy ioam6_genl_policy_ns_sc[] = { + [IOAM6_ATTR_NS_ID] = { .type = NLA_U16 }, + [IOAM6_ATTR_SC_ID] = { .type = NLA_U32 }, + [IOAM6_ATTR_SC_NONE] = { .type = NLA_FLAG }, +}; + +static int ioam6_genl_addns(struct sk_buff *skb, struct genl_info *info) +{ + struct ioam6_pernet_data *nsdata; + struct ioam6_namespace *ns; + u64 data64; + u32 data32; + __be16 id; + int err; + + if (!info->attrs[IOAM6_ATTR_NS_ID]) + return -EINVAL; + + id = cpu_to_be16(nla_get_u16(info->attrs[IOAM6_ATTR_NS_ID])); + nsdata = ioam6_pernet(genl_info_net(info)); + + mutex_lock(&nsdata->lock); + + ns = rhashtable_lookup_fast(&nsdata->namespaces, &id, rht_ns_params); + if (ns) { + err = -EEXIST; + goto out_unlock; + } + + ns = kzalloc(sizeof(*ns), GFP_KERNEL); + if (!ns) { + err = -ENOMEM; + goto out_unlock; + } + + ns->id = id; + + if (!info->attrs[IOAM6_ATTR_NS_DATA]) + data32 = IOAM6_U32_UNAVAILABLE; + else + data32 = nla_get_u32(info->attrs[IOAM6_ATTR_NS_DATA]); + + if (!info->attrs[IOAM6_ATTR_NS_DATA_WIDE]) + data64 = IOAM6_U64_UNAVAILABLE; + else + data64 = nla_get_u64(info->attrs[IOAM6_ATTR_NS_DATA_WIDE]); + + ns->data = cpu_to_be32(data32); + ns->data_wide = cpu_to_be64(data64); + + err = rhashtable_lookup_insert_fast(&nsdata->namespaces, &ns->head, + rht_ns_params); + if (err) + kfree(ns); + +out_unlock: + mutex_unlock(&nsdata->lock); + return err; +} + +static int ioam6_genl_delns(struct sk_buff *skb, struct genl_info *info) +{ + struct ioam6_pernet_data *nsdata; + struct ioam6_namespace *ns; + struct ioam6_schema *sc; + __be16 id; + int err; + + if (!info->attrs[IOAM6_ATTR_NS_ID]) + return -EINVAL; + + id = cpu_to_be16(nla_get_u16(info->attrs[IOAM6_ATTR_NS_ID])); + nsdata = ioam6_pernet(genl_info_net(info)); + + mutex_lock(&nsdata->lock); + + ns = rhashtable_lookup_fast(&nsdata->namespaces, &id, rht_ns_params); + if (!ns) { + err = -ENOENT; + goto out_unlock; + } + + sc = rcu_dereference_protected(ns->schema, + lockdep_is_held(&nsdata->lock)); + + err = rhashtable_remove_fast(&nsdata->namespaces, &ns->head, + rht_ns_params); + if (err) + goto out_unlock; + + if (sc) + rcu_assign_pointer(sc->ns, NULL); + + ioam6_ns_release(ns); + +out_unlock: + mutex_unlock(&nsdata->lock); + return err; +} + +static int __ioam6_genl_dumpns_element(struct ioam6_namespace *ns, + u32 portid, + u32 seq, + u32 flags, + struct sk_buff *skb, + u8 cmd) +{ + struct ioam6_schema *sc; + u64 data64; + u32 data32; + void *hdr; + + hdr = genlmsg_put(skb, portid, seq, &ioam6_genl_family, flags, cmd); + if (!hdr) + return -ENOMEM; + + data32 = be32_to_cpu(ns->data); + data64 = be64_to_cpu(ns->data_wide); + + if (nla_put_u16(skb, IOAM6_ATTR_NS_ID, be16_to_cpu(ns->id)) || + (data32 != IOAM6_U32_UNAVAILABLE && + nla_put_u32(skb, IOAM6_ATTR_NS_DATA, data32)) || + (data64 != IOAM6_U64_UNAVAILABLE && + nla_put_u64_64bit(skb, IOAM6_ATTR_NS_DATA_WIDE, + data64, IOAM6_ATTR_PAD))) + goto nla_put_failure; + + rcu_read_lock(); + + sc = rcu_dereference(ns->schema); + if (sc && nla_put_u32(skb, IOAM6_ATTR_SC_ID, sc->id)) { + rcu_read_unlock(); + goto nla_put_failure; + } + + rcu_read_unlock(); + + genlmsg_end(skb, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; +} + +static int ioam6_genl_dumpns_start(struct netlink_callback *cb) +{ + struct ioam6_pernet_data *nsdata = ioam6_pernet(sock_net(cb->skb->sk)); + struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0]; + + if (!iter) { + iter = kmalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) + return -ENOMEM; + + cb->args[0] = (long)iter; + } + + rhashtable_walk_enter(&nsdata->namespaces, iter); + + return 0; +} + +static int ioam6_genl_dumpns_done(struct netlink_callback *cb) +{ + struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0]; + + rhashtable_walk_exit(iter); + kfree(iter); + + return 0; +} + +static int ioam6_genl_dumpns(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct rhashtable_iter *iter; + struct ioam6_namespace *ns; + int err; + + iter = (struct rhashtable_iter *)cb->args[0]; + rhashtable_walk_start(iter); + + for (;;) { + ns = rhashtable_walk_next(iter); + + if (IS_ERR(ns)) { + if (PTR_ERR(ns) == -EAGAIN) + continue; + err = PTR_ERR(ns); + goto done; + } else if (!ns) { + break; + } + + err = __ioam6_genl_dumpns_element(ns, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, + skb, + IOAM6_CMD_DUMP_NAMESPACES); + if (err) + goto done; + } + + err = skb->len; + +done: + rhashtable_walk_stop(iter); + return err; +} + +static int ioam6_genl_addsc(struct sk_buff *skb, struct genl_info *info) +{ + struct ioam6_pernet_data *nsdata; + int len, len_aligned, err; + struct ioam6_schema *sc; + u32 id; + + if (!info->attrs[IOAM6_ATTR_SC_ID] || !info->attrs[IOAM6_ATTR_SC_DATA]) + return -EINVAL; + + id = nla_get_u32(info->attrs[IOAM6_ATTR_SC_ID]); + nsdata = ioam6_pernet(genl_info_net(info)); + + mutex_lock(&nsdata->lock); + + sc = rhashtable_lookup_fast(&nsdata->schemas, &id, rht_sc_params); + if (sc) { + err = -EEXIST; + goto out_unlock; + } + + len = nla_len(info->attrs[IOAM6_ATTR_SC_DATA]); + len_aligned = ALIGN(len, 4); + + sc = kzalloc(sizeof(*sc) + len_aligned, GFP_KERNEL); + if (!sc) { + err = -ENOMEM; + goto out_unlock; + } + + sc->id = id; + sc->len = len_aligned; + sc->hdr = cpu_to_be32(sc->id | ((u8)(sc->len / 4) << 24)); + nla_memcpy(sc->data, info->attrs[IOAM6_ATTR_SC_DATA], len); + + err = rhashtable_lookup_insert_fast(&nsdata->schemas, &sc->head, + rht_sc_params); + if (err) + goto free_sc; + +out_unlock: + mutex_unlock(&nsdata->lock); + return err; +free_sc: + kfree(sc); + goto out_unlock; +} + +static int ioam6_genl_delsc(struct sk_buff *skb, struct genl_info *info) +{ + struct ioam6_pernet_data *nsdata; + struct ioam6_namespace *ns; + struct ioam6_schema *sc; + int err; + u32 id; + + if (!info->attrs[IOAM6_ATTR_SC_ID]) + return -EINVAL; + + id = nla_get_u32(info->attrs[IOAM6_ATTR_SC_ID]); + nsdata = ioam6_pernet(genl_info_net(info)); + + mutex_lock(&nsdata->lock); + + sc = rhashtable_lookup_fast(&nsdata->schemas, &id, rht_sc_params); + if (!sc) { + err = -ENOENT; + goto out_unlock; + } + + ns = rcu_dereference_protected(sc->ns, lockdep_is_held(&nsdata->lock)); + + err = rhashtable_remove_fast(&nsdata->schemas, &sc->head, + rht_sc_params); + if (err) + goto out_unlock; + + if (ns) + rcu_assign_pointer(ns->schema, NULL); + + ioam6_sc_release(sc); + +out_unlock: + mutex_unlock(&nsdata->lock); + return err; +} + +static int __ioam6_genl_dumpsc_element(struct ioam6_schema *sc, + u32 portid, u32 seq, u32 flags, + struct sk_buff *skb, u8 cmd) +{ + struct ioam6_namespace *ns; + void *hdr; + + hdr = genlmsg_put(skb, portid, seq, &ioam6_genl_family, flags, cmd); + if (!hdr) + return -ENOMEM; + + if (nla_put_u32(skb, IOAM6_ATTR_SC_ID, sc->id) || + nla_put(skb, IOAM6_ATTR_SC_DATA, sc->len, sc->data)) + goto nla_put_failure; + + rcu_read_lock(); + + ns = rcu_dereference(sc->ns); + if (ns && nla_put_u16(skb, IOAM6_ATTR_NS_ID, be16_to_cpu(ns->id))) { + rcu_read_unlock(); + goto nla_put_failure; + } + + rcu_read_unlock(); + + genlmsg_end(skb, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; +} + +static int ioam6_genl_dumpsc_start(struct netlink_callback *cb) +{ + struct ioam6_pernet_data *nsdata = ioam6_pernet(sock_net(cb->skb->sk)); + struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0]; + + if (!iter) { + iter = kmalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) + return -ENOMEM; + + cb->args[0] = (long)iter; + } + + rhashtable_walk_enter(&nsdata->schemas, iter); + + return 0; +} + +static int ioam6_genl_dumpsc_done(struct netlink_callback *cb) +{ + struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0]; + + rhashtable_walk_exit(iter); + kfree(iter); + + return 0; +} + +static int ioam6_genl_dumpsc(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct rhashtable_iter *iter; + struct ioam6_schema *sc; + int err; + + iter = (struct rhashtable_iter *)cb->args[0]; + rhashtable_walk_start(iter); + + for (;;) { + sc = rhashtable_walk_next(iter); + + if (IS_ERR(sc)) { + if (PTR_ERR(sc) == -EAGAIN) + continue; + err = PTR_ERR(sc); + goto done; + } else if (!sc) { + break; + } + + err = __ioam6_genl_dumpsc_element(sc, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, + skb, + IOAM6_CMD_DUMP_SCHEMAS); + if (err) + goto done; + } + + err = skb->len; + +done: + rhashtable_walk_stop(iter); + return err; +} + +static int ioam6_genl_ns_set_schema(struct sk_buff *skb, struct genl_info *info) +{ + struct ioam6_namespace *ns, *ns_ref; + struct ioam6_schema *sc, *sc_ref; + struct ioam6_pernet_data *nsdata; + __be16 ns_id; + u32 sc_id; + int err; + + if (!info->attrs[IOAM6_ATTR_NS_ID] || + (!info->attrs[IOAM6_ATTR_SC_ID] && + !info->attrs[IOAM6_ATTR_SC_NONE])) + return -EINVAL; + + ns_id = cpu_to_be16(nla_get_u16(info->attrs[IOAM6_ATTR_NS_ID])); + nsdata = ioam6_pernet(genl_info_net(info)); + + mutex_lock(&nsdata->lock); + + ns = rhashtable_lookup_fast(&nsdata->namespaces, &ns_id, rht_ns_params); + if (!ns) { + err = -ENOENT; + goto out_unlock; + } + + if (info->attrs[IOAM6_ATTR_SC_NONE]) { + sc = NULL; + } else { + sc_id = nla_get_u32(info->attrs[IOAM6_ATTR_SC_ID]); + sc = rhashtable_lookup_fast(&nsdata->schemas, &sc_id, + rht_sc_params); + if (!sc) { + err = -ENOENT; + goto out_unlock; + } + } + + sc_ref = rcu_dereference_protected(ns->schema, + lockdep_is_held(&nsdata->lock)); + if (sc_ref) + rcu_assign_pointer(sc_ref->ns, NULL); + rcu_assign_pointer(ns->schema, sc); + + if (sc) { + ns_ref = rcu_dereference_protected(sc->ns, + lockdep_is_held(&nsdata->lock)); + if (ns_ref) + rcu_assign_pointer(ns_ref->schema, NULL); + rcu_assign_pointer(sc->ns, ns); + } + + err = 0; + +out_unlock: + mutex_unlock(&nsdata->lock); + return err; +} + +static const struct genl_ops ioam6_genl_ops[] = { + { + .cmd = IOAM6_CMD_ADD_NAMESPACE, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = ioam6_genl_addns, + .flags = GENL_ADMIN_PERM, + .policy = ioam6_genl_policy_addns, + .maxattr = ARRAY_SIZE(ioam6_genl_policy_addns) - 1, + }, + { + .cmd = IOAM6_CMD_DEL_NAMESPACE, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = ioam6_genl_delns, + .flags = GENL_ADMIN_PERM, + .policy = ioam6_genl_policy_delns, + .maxattr = ARRAY_SIZE(ioam6_genl_policy_delns) - 1, + }, + { + .cmd = IOAM6_CMD_DUMP_NAMESPACES, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .start = ioam6_genl_dumpns_start, + .dumpit = ioam6_genl_dumpns, + .done = ioam6_genl_dumpns_done, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = IOAM6_CMD_ADD_SCHEMA, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = ioam6_genl_addsc, + .flags = GENL_ADMIN_PERM, + .policy = ioam6_genl_policy_addsc, + .maxattr = ARRAY_SIZE(ioam6_genl_policy_addsc) - 1, + }, + { + .cmd = IOAM6_CMD_DEL_SCHEMA, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = ioam6_genl_delsc, + .flags = GENL_ADMIN_PERM, + .policy = ioam6_genl_policy_delsc, + .maxattr = ARRAY_SIZE(ioam6_genl_policy_delsc) - 1, + }, + { + .cmd = IOAM6_CMD_DUMP_SCHEMAS, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .start = ioam6_genl_dumpsc_start, + .dumpit = ioam6_genl_dumpsc, + .done = ioam6_genl_dumpsc_done, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = IOAM6_CMD_NS_SET_SCHEMA, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = ioam6_genl_ns_set_schema, + .flags = GENL_ADMIN_PERM, + .policy = ioam6_genl_policy_ns_sc, + .maxattr = ARRAY_SIZE(ioam6_genl_policy_ns_sc) - 1, + }, +}; + +static struct genl_family ioam6_genl_family __ro_after_init = { + .name = IOAM6_GENL_NAME, + .version = IOAM6_GENL_VERSION, + .netnsok = true, + .parallel_ops = true, + .ops = ioam6_genl_ops, + .n_ops = ARRAY_SIZE(ioam6_genl_ops), + .module = THIS_MODULE, +}; + +struct ioam6_namespace *ioam6_namespace(struct net *net, __be16 id) +{ + struct ioam6_pernet_data *nsdata = ioam6_pernet(net); + + return rhashtable_lookup_fast(&nsdata->namespaces, &id, rht_ns_params); +} + +static void __ioam6_fill_trace_data(struct sk_buff *skb, + struct ioam6_namespace *ns, + struct ioam6_trace_hdr *trace, + struct ioam6_schema *sc, + u8 sclen) +{ + struct __kernel_sock_timeval ts; + u64 raw64; + u32 raw32; + u16 raw16; + u8 *data; + u8 byte; + + data = trace->data + trace->remlen * 4 - trace->nodelen * 4 - sclen * 4; + + /* hop_lim and node_id */ + if (trace->type.bit0) { + byte = ipv6_hdr(skb)->hop_limit; + if (skb->dev) + byte--; + + raw32 = dev_net(skb_dst(skb)->dev)->ipv6.sysctl.ioam6_id; + + *(__be32 *)data = cpu_to_be32((byte << 24) | raw32); + data += sizeof(__be32); + } + + /* ingress_if_id and egress_if_id */ + if (trace->type.bit1) { + if (!skb->dev) + raw16 = IOAM6_U16_UNAVAILABLE; + else + raw16 = (__force u16)__in6_dev_get(skb->dev)->cnf.ioam6_id; + + *(__be16 *)data = cpu_to_be16(raw16); + data += sizeof(__be16); + + if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) + raw16 = IOAM6_U16_UNAVAILABLE; + else + raw16 = (__force u16)__in6_dev_get(skb_dst(skb)->dev)->cnf.ioam6_id; + + *(__be16 *)data = cpu_to_be16(raw16); + data += sizeof(__be16); + } + + /* timestamp seconds */ + if (trace->type.bit2) { + if (!skb->dev) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); + } else { + if (!skb->tstamp) + __net_timestamp(skb); + + skb_get_new_timestamp(skb, &ts); + *(__be32 *)data = cpu_to_be32((u32)ts.tv_sec); + } + data += sizeof(__be32); + } + + /* timestamp subseconds */ + if (trace->type.bit3) { + if (!skb->dev) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); + } else { + if (!skb->tstamp) + __net_timestamp(skb); + + if (!trace->type.bit2) + skb_get_new_timestamp(skb, &ts); + + *(__be32 *)data = cpu_to_be32((u32)ts.tv_usec); + } + data += sizeof(__be32); + } + + /* transit delay */ + if (trace->type.bit4) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); + data += sizeof(__be32); + } + + /* namespace data */ + if (trace->type.bit5) { + *(__be32 *)data = ns->data; + data += sizeof(__be32); + } + + /* queue depth */ + if (trace->type.bit6) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); + data += sizeof(__be32); + } + + /* checksum complement */ + if (trace->type.bit7) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); + data += sizeof(__be32); + } + + /* hop_lim and node_id (wide) */ + if (trace->type.bit8) { + byte = ipv6_hdr(skb)->hop_limit; + if (skb->dev) + byte--; + + raw64 = dev_net(skb_dst(skb)->dev)->ipv6.sysctl.ioam6_id_wide; + + *(__be64 *)data = cpu_to_be64(((u64)byte << 56) | raw64); + data += sizeof(__be64); + } + + /* ingress_if_id and egress_if_id (wide) */ + if (trace->type.bit9) { + if (!skb->dev) + raw32 = IOAM6_U32_UNAVAILABLE; + else + raw32 = __in6_dev_get(skb->dev)->cnf.ioam6_id_wide; + + *(__be32 *)data = cpu_to_be32(raw32); + data += sizeof(__be32); + + if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) + raw32 = IOAM6_U32_UNAVAILABLE; + else + raw32 = __in6_dev_get(skb_dst(skb)->dev)->cnf.ioam6_id_wide; + + *(__be32 *)data = cpu_to_be32(raw32); + data += sizeof(__be32); + } + + /* namespace data (wide) */ + if (trace->type.bit10) { + *(__be64 *)data = ns->data_wide; + data += sizeof(__be64); + } + + /* buffer occupancy */ + if (trace->type.bit11) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); + data += sizeof(__be32); + } + + /* opaque state snapshot */ + if (trace->type.bit22) { + if (!sc) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE >> 8); + } else { + *(__be32 *)data = sc->hdr; + data += sizeof(__be32); + + memcpy(data, sc->data, sc->len); + } + } +} + +/* called with rcu_read_lock() */ +void ioam6_fill_trace_data(struct sk_buff *skb, + struct ioam6_namespace *ns, + struct ioam6_trace_hdr *trace) +{ + struct ioam6_schema *sc; + u8 sclen = 0; + + /* Skip if Overflow flag is set OR + * if an unknown type (bit 12-21) is set + */ + if (trace->overflow || + trace->type.bit12 | trace->type.bit13 | trace->type.bit14 | + trace->type.bit15 | trace->type.bit16 | trace->type.bit17 | + trace->type.bit18 | trace->type.bit19 | trace->type.bit20 | + trace->type.bit21) { + return; + } + + /* NodeLen does not include Opaque State Snapshot length. We need to + * take it into account if the corresponding bit is set (bit 22) and + * if the current IOAM namespace has an active schema attached to it + */ + sc = rcu_dereference(ns->schema); + if (trace->type.bit22) { + sclen = sizeof_field(struct ioam6_schema, hdr) / 4; + + if (sc) + sclen += sc->len / 4; + } + + /* If there is no space remaining, we set the Overflow flag and we + * skip without filling the trace + */ + if (!trace->remlen || trace->remlen < trace->nodelen + sclen) { + trace->overflow = 1; + return; + } + + __ioam6_fill_trace_data(skb, ns, trace, sc, sclen); + trace->remlen -= trace->nodelen + sclen; +} + +static int __net_init ioam6_net_init(struct net *net) +{ + struct ioam6_pernet_data *nsdata; + int err = -ENOMEM; + + nsdata = kzalloc(sizeof(*nsdata), GFP_KERNEL); + if (!nsdata) + goto out; + + mutex_init(&nsdata->lock); + net->ipv6.ioam6_data = nsdata; + + err = rhashtable_init(&nsdata->namespaces, &rht_ns_params); + if (err) + goto free_nsdata; + + err = rhashtable_init(&nsdata->schemas, &rht_sc_params); + if (err) + goto free_rht_ns; + +out: + return err; +free_rht_ns: + rhashtable_destroy(&nsdata->namespaces); +free_nsdata: + kfree(nsdata); + net->ipv6.ioam6_data = NULL; + goto out; +} + +static void __net_exit ioam6_net_exit(struct net *net) +{ + struct ioam6_pernet_data *nsdata = ioam6_pernet(net); + + rhashtable_free_and_destroy(&nsdata->namespaces, ioam6_free_ns, NULL); + rhashtable_free_and_destroy(&nsdata->schemas, ioam6_free_sc, NULL); + + kfree(nsdata); +} + +static struct pernet_operations ioam6_net_ops = { + .init = ioam6_net_init, + .exit = ioam6_net_exit, +}; + +int __init ioam6_init(void) +{ + int err = register_pernet_subsys(&ioam6_net_ops); + if (err) + goto out; + + err = genl_register_family(&ioam6_genl_family); + if (err) + goto out_unregister_pernet_subsys; + +#ifdef CONFIG_IPV6_IOAM6_LWTUNNEL + err = ioam6_iptunnel_init(); + if (err) + goto out_unregister_genl; +#endif + + pr_info("In-situ OAM (IOAM) with IPv6\n"); + +out: + return err; +#ifdef CONFIG_IPV6_IOAM6_LWTUNNEL +out_unregister_genl: + genl_unregister_family(&ioam6_genl_family); +#endif +out_unregister_pernet_subsys: + unregister_pernet_subsys(&ioam6_net_ops); + goto out; +} + +void ioam6_exit(void) +{ +#ifdef CONFIG_IPV6_IOAM6_LWTUNNEL + ioam6_iptunnel_exit(); +#endif + genl_unregister_family(&ioam6_genl_family); + unregister_pernet_subsys(&ioam6_net_ops); +} diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c new file mode 100644 index 000000000000..f9ee04541c17 --- /dev/null +++ b/net/ipv6/ioam6_iptunnel.c @@ -0,0 +1,274 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * IPv6 IOAM Lightweight Tunnel implementation + * + * Author: + * Justin Iurman <justin.iurman@uliege.be> + */ + +#include <linux/kernel.h> +#include <linux/skbuff.h> +#include <linux/net.h> +#include <linux/netlink.h> +#include <linux/in6.h> +#include <linux/ioam6.h> +#include <linux/ioam6_iptunnel.h> +#include <net/dst.h> +#include <net/sock.h> +#include <net/lwtunnel.h> +#include <net/ioam6.h> + +#define IOAM6_MASK_SHORT_FIELDS 0xff100000 +#define IOAM6_MASK_WIDE_FIELDS 0xe00000 + +struct ioam6_lwt_encap { + struct ipv6_hopopt_hdr eh; + u8 pad[2]; /* 2-octet padding for 4n-alignment */ + struct ioam6_hdr ioamh; + struct ioam6_trace_hdr traceh; +} __packed; + +struct ioam6_lwt { + struct ioam6_lwt_encap tuninfo; +}; + +static struct ioam6_lwt *ioam6_lwt_state(struct lwtunnel_state *lwt) +{ + return (struct ioam6_lwt *)lwt->data; +} + +static struct ioam6_lwt_encap *ioam6_lwt_info(struct lwtunnel_state *lwt) +{ + return &ioam6_lwt_state(lwt)->tuninfo; +} + +static struct ioam6_trace_hdr *ioam6_trace(struct lwtunnel_state *lwt) +{ + return &(ioam6_lwt_state(lwt)->tuninfo.traceh); +} + +static const struct nla_policy ioam6_iptunnel_policy[IOAM6_IPTUNNEL_MAX + 1] = { + [IOAM6_IPTUNNEL_TRACE] = NLA_POLICY_EXACT_LEN(sizeof(struct ioam6_trace_hdr)), +}; + +static int nla_put_ioam6_trace(struct sk_buff *skb, int attrtype, + struct ioam6_trace_hdr *trace) +{ + struct ioam6_trace_hdr *data; + struct nlattr *nla; + int len; + + len = sizeof(*trace); + + nla = nla_reserve(skb, attrtype, len); + if (!nla) + return -EMSGSIZE; + + data = nla_data(nla); + memcpy(data, trace, len); + + return 0; +} + +static bool ioam6_validate_trace_hdr(struct ioam6_trace_hdr *trace) +{ + u32 fields; + + if (!trace->type_be32 || !trace->remlen || + trace->remlen > IOAM6_TRACE_DATA_SIZE_MAX / 4) + return false; + + trace->nodelen = 0; + fields = be32_to_cpu(trace->type_be32); + + trace->nodelen += hweight32(fields & IOAM6_MASK_SHORT_FIELDS) + * (sizeof(__be32) / 4); + trace->nodelen += hweight32(fields & IOAM6_MASK_WIDE_FIELDS) + * (sizeof(__be64) / 4); + + return true; +} + +static int ioam6_build_state(struct net *net, struct nlattr *nla, + unsigned int family, const void *cfg, + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IOAM6_IPTUNNEL_MAX + 1]; + struct ioam6_lwt_encap *tuninfo; + struct ioam6_trace_hdr *trace; + struct lwtunnel_state *s; + int len_aligned; + int len, err; + + if (family != AF_INET6) + return -EINVAL; + + err = nla_parse_nested(tb, IOAM6_IPTUNNEL_MAX, nla, + ioam6_iptunnel_policy, extack); + if (err < 0) + return err; + + if (!tb[IOAM6_IPTUNNEL_TRACE]) { + NL_SET_ERR_MSG(extack, "missing trace"); + return -EINVAL; + } + + trace = nla_data(tb[IOAM6_IPTUNNEL_TRACE]); + if (!ioam6_validate_trace_hdr(trace)) { + NL_SET_ERR_MSG_ATTR(extack, tb[IOAM6_IPTUNNEL_TRACE], + "invalid trace validation"); + return -EINVAL; + } + + len = sizeof(*tuninfo) + trace->remlen * 4; + len_aligned = ALIGN(len, 8); + + s = lwtunnel_state_alloc(len_aligned); + if (!s) + return -ENOMEM; + + tuninfo = ioam6_lwt_info(s); + tuninfo->eh.hdrlen = (len_aligned >> 3) - 1; + tuninfo->pad[0] = IPV6_TLV_PADN; + tuninfo->ioamh.type = IOAM6_TYPE_PREALLOC; + tuninfo->ioamh.opt_type = IPV6_TLV_IOAM; + tuninfo->ioamh.opt_len = sizeof(tuninfo->ioamh) - 2 + sizeof(*trace) + + trace->remlen * 4; + + memcpy(&tuninfo->traceh, trace, sizeof(*trace)); + + len = len_aligned - len; + if (len == 1) { + tuninfo->traceh.data[trace->remlen * 4] = IPV6_TLV_PAD1; + } else if (len > 0) { + tuninfo->traceh.data[trace->remlen * 4] = IPV6_TLV_PADN; + tuninfo->traceh.data[trace->remlen * 4 + 1] = len - 2; + } + + s->type = LWTUNNEL_ENCAP_IOAM6; + s->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT; + + *ts = s; + + return 0; +} + +static int ioam6_do_inline(struct sk_buff *skb, struct ioam6_lwt_encap *tuninfo) +{ + struct ioam6_trace_hdr *trace; + struct ipv6hdr *oldhdr, *hdr; + struct ioam6_namespace *ns; + int hdrlen, err; + + hdrlen = (tuninfo->eh.hdrlen + 1) << 3; + + err = skb_cow_head(skb, hdrlen + skb->mac_len); + if (unlikely(err)) + return err; + + oldhdr = ipv6_hdr(skb); + skb_pull(skb, sizeof(*oldhdr)); + skb_postpull_rcsum(skb, skb_network_header(skb), sizeof(*oldhdr)); + + skb_push(skb, sizeof(*oldhdr) + hdrlen); + skb_reset_network_header(skb); + skb_mac_header_rebuild(skb); + + hdr = ipv6_hdr(skb); + memmove(hdr, oldhdr, sizeof(*oldhdr)); + tuninfo->eh.nexthdr = hdr->nexthdr; + + skb_set_transport_header(skb, sizeof(*hdr)); + skb_postpush_rcsum(skb, hdr, sizeof(*hdr) + hdrlen); + + memcpy(skb_transport_header(skb), (u8 *)tuninfo, hdrlen); + + hdr->nexthdr = NEXTHDR_HOP; + hdr->payload_len = cpu_to_be16(skb->len - sizeof(*hdr)); + + trace = (struct ioam6_trace_hdr *)(skb_transport_header(skb) + + sizeof(struct ipv6_hopopt_hdr) + 2 + + sizeof(struct ioam6_hdr)); + + ns = ioam6_namespace(dev_net(skb_dst(skb)->dev), trace->namespace_id); + if (ns) + ioam6_fill_trace_data(skb, ns, trace); + + return 0; +} + +static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + struct lwtunnel_state *lwt = skb_dst(skb)->lwtstate; + int err = -EINVAL; + + if (skb->protocol != htons(ETH_P_IPV6)) + goto drop; + + /* Only for packets we send and + * that do not contain a Hop-by-Hop yet + */ + if (skb->dev || ipv6_hdr(skb)->nexthdr == NEXTHDR_HOP) + goto out; + + err = ioam6_do_inline(skb, ioam6_lwt_info(lwt)); + if (unlikely(err)) + goto drop; + + err = skb_cow_head(skb, LL_RESERVED_SPACE(skb_dst(skb)->dev)); + if (unlikely(err)) + goto drop; + +out: + return lwt->orig_output(net, sk, skb); + +drop: + kfree_skb(skb); + return err; +} + +static int ioam6_fill_encap_info(struct sk_buff *skb, + struct lwtunnel_state *lwtstate) +{ + struct ioam6_trace_hdr *trace = ioam6_trace(lwtstate); + + if (nla_put_ioam6_trace(skb, IOAM6_IPTUNNEL_TRACE, trace)) + return -EMSGSIZE; + + return 0; +} + +static int ioam6_encap_nlsize(struct lwtunnel_state *lwtstate) +{ + struct ioam6_trace_hdr *trace = ioam6_trace(lwtstate); + + return nla_total_size(sizeof(*trace)); +} + +static int ioam6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) +{ + struct ioam6_trace_hdr *a_hdr = ioam6_trace(a); + struct ioam6_trace_hdr *b_hdr = ioam6_trace(b); + + return (a_hdr->namespace_id != b_hdr->namespace_id); +} + +static const struct lwtunnel_encap_ops ioam6_iptun_ops = { + .build_state = ioam6_build_state, + .output = ioam6_output, + .fill_encap = ioam6_fill_encap_info, + .get_encap_size = ioam6_encap_nlsize, + .cmp_encap = ioam6_encap_cmp, + .owner = THIS_MODULE, +}; + +int __init ioam6_iptunnel_init(void) +{ + return lwtunnel_encap_add_ops(&ioam6_iptun_ops, LWTUNNEL_ENCAP_IOAM6); +} + +void ioam6_iptunnel_exit(void) +{ + lwtunnel_encap_del_ops(&ioam6_iptun_ops, LWTUNNEL_ENCAP_IOAM6); +} diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 2d650dc24349..1bec5b22f80d 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1341,7 +1341,7 @@ static void __fib6_update_sernum_upto_root(struct fib6_info *rt, struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node, lockdep_is_held(&rt->fib6_table->tb6_lock)); - /* paired with smp_rmb() in rt6_get_cookie_safe() */ + /* paired with smp_rmb() in fib6_get_cookie_safe() */ smp_wmb(); while (fn) { fn->fn_sernum = sernum; @@ -2449,8 +2449,8 @@ int __init fib6_init(void) int ret = -ENOMEM; fib6_node_kmem = kmem_cache_create("fib6_nodes", - sizeof(struct fib6_node), - 0, SLAB_HWCACHE_ALIGN, + sizeof(struct fib6_node), 0, + SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); if (!fib6_node_kmem) goto out; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index bc224f917bbd..3ad201d372d8 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1244,8 +1244,9 @@ static void ip6gre_tnl_parm_to_user(struct ip6_tnl_parm2 *u, memcpy(u->name, p->name, sizeof(u->name)); } -static int ip6gre_tunnel_ioctl(struct net_device *dev, - struct ifreq *ifr, int cmd) +static int ip6gre_tunnel_siocdevprivate(struct net_device *dev, + struct ifreq *ifr, void __user *data, + int cmd) { int err = 0; struct ip6_tnl_parm2 p; @@ -1259,7 +1260,7 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev, switch (cmd) { case SIOCGETTUNNEL: if (dev == ign->fb_tunnel_dev) { - if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) { + if (copy_from_user(&p, data, sizeof(p))) { err = -EFAULT; break; } @@ -1270,7 +1271,7 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev, } memset(&p, 0, sizeof(p)); ip6gre_tnl_parm_to_user(&p, &t->parms); - if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) + if (copy_to_user(data, &p, sizeof(p))) err = -EFAULT; break; @@ -1281,7 +1282,7 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev, goto done; err = -EFAULT; - if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) + if (copy_from_user(&p, data, sizeof(p))) goto done; err = -EINVAL; @@ -1318,7 +1319,7 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev, memset(&p, 0, sizeof(p)); ip6gre_tnl_parm_to_user(&p, &t->parms); - if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) + if (copy_to_user(data, &p, sizeof(p))) err = -EFAULT; } else err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT); @@ -1331,7 +1332,7 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev, if (dev == ign->fb_tunnel_dev) { err = -EFAULT; - if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) + if (copy_from_user(&p, data, sizeof(p))) goto done; err = -ENOENT; ip6gre_tnl_parm_from_user(&p1, &p); @@ -1398,7 +1399,7 @@ static const struct net_device_ops ip6gre_netdev_ops = { .ndo_init = ip6gre_tunnel_init, .ndo_uninit = ip6gre_tunnel_uninit, .ndo_start_xmit = ip6gre_tunnel_xmit, - .ndo_do_ioctl = ip6gre_tunnel_ioctl, + .ndo_siocdevprivate = ip6gre_tunnel_siocdevprivate, .ndo_change_mtu = ip6_tnl_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip6_tnl_get_iflink, diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index e1b9f7ac8bad..12f985f43bcc 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -60,46 +60,29 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; + struct inet6_dev *idev = ip6_dst_idev(dst); unsigned int hh_len = LL_RESERVED_SPACE(dev); - int delta = hh_len - skb_headroom(skb); - const struct in6_addr *nexthop; + const struct in6_addr *daddr, *nexthop; + struct ipv6hdr *hdr; struct neighbour *neigh; int ret; /* Be paranoid, rather than too clever. */ - if (unlikely(delta > 0) && dev->header_ops) { - /* pskb_expand_head() might crash, if skb is shared */ - if (skb_shared(skb)) { - struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); - - if (likely(nskb)) { - if (skb->sk) - skb_set_owner_w(nskb, skb->sk); - consume_skb(skb); - } else { - kfree_skb(skb); - } - skb = nskb; - } - if (skb && - pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) { - kfree_skb(skb); - skb = NULL; - } + if (unlikely(hh_len > skb_headroom(skb)) && dev->header_ops) { + skb = skb_expand_head(skb, hh_len); if (!skb) { - IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS); + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); return -ENOMEM; } } - if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) { - struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); - + hdr = ipv6_hdr(skb); + daddr = &hdr->daddr; + if (ipv6_addr_is_multicast(daddr)) { if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(sk) && ((mroute6_is_socket(net, skb) && !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) || - ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr, - &ipv6_hdr(skb)->saddr))) { + ipv6_chk_mcast_addr(dev, daddr, &hdr->saddr))) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); /* Do not check for IFF_ALLMULTI; multicast routing @@ -110,7 +93,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * net, sk, newskb, NULL, newskb->dev, dev_loopback_xmit); - if (ipv6_hdr(skb)->hop_limit == 0) { + if (hdr->hop_limit == 0) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); @@ -119,9 +102,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * } IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, skb->len); - - if (IPV6_ADDR_MC_SCOPE(&ipv6_hdr(skb)->daddr) <= - IPV6_ADDR_SCOPE_NODELOCAL && + if (IPV6_ADDR_MC_SCOPE(daddr) <= IPV6_ADDR_SCOPE_NODELOCAL && !(dev->flags & IFF_LOOPBACK)) { kfree_skb(skb); return 0; @@ -136,10 +117,10 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * } rcu_read_lock_bh(); - nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr); - neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); + nexthop = rt6_nexthop((struct rt6_info *)dst, daddr); + neigh = __ipv6_neigh_lookup_noref(dev, nexthop); if (unlikely(!neigh)) - neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false); + neigh = __neigh_create(&nd_tbl, nexthop, dev, false); if (!IS_ERR(neigh)) { sock_confirm_neigh(skb, neigh); ret = neigh_output(neigh, skb, false); @@ -148,7 +129,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * } rcu_read_unlock_bh(); - IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); return -EINVAL; } @@ -268,6 +249,8 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, const struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *first_hop = &fl6->daddr; struct dst_entry *dst = skb_dst(skb); + struct net_device *dev = dst->dev; + struct inet6_dev *idev = ip6_dst_idev(dst); unsigned int head_room; struct ipv6hdr *hdr; u8 proto = fl6->flowi6_proto; @@ -275,22 +258,16 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, int hlimit = -1; u32 mtu; - head_room = sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev); + head_room = sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dev); if (opt) head_room += opt->opt_nflen + opt->opt_flen; - if (unlikely(skb_headroom(skb) < head_room)) { - struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room); - if (!skb2) { - IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_OUTDISCARDS); - kfree_skb(skb); + if (unlikely(head_room > skb_headroom(skb))) { + skb = skb_expand_head(skb, head_room); + if (!skb) { + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); return -ENOBUFS; } - if (skb->sk) - skb_set_owner_w(skb2, skb->sk); - consume_skb(skb); - skb = skb2; } if (opt) { @@ -332,8 +309,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, mtu = dst_mtu(dst); if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) { - IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_OUT, skb->len); + IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing @@ -346,17 +322,17 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, * we promote our socket to non const */ return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, - net, (struct sock *)sk, skb, NULL, dst->dev, + net, (struct sock *)sk, skb, NULL, dev, dst_output); } - skb->dev = dst->dev; + skb->dev = dev; /* ipv6_local_error() does not require socket lock, * we promote our socket to non const */ ipv6_local_error((struct sock *)sk, EMSGSIZE, fl6, mtu); - IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); + IP6_INC_STATS(net, idev, IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; } @@ -549,9 +525,10 @@ int ip6_forward(struct sk_buff *skb) if (net->ipv6.devconf_all->proxy_ndp && pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) { int proxied = ip6_forward_proxy_check(skb); - if (proxied > 0) + if (proxied > 0) { + hdr->hop_limit--; return ip6_input(skb); - else if (proxied < 0) { + } else if (proxied < 0) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } @@ -607,7 +584,7 @@ int ip6_forward(struct sk_buff *skb) } } - mtu = ip6_dst_mtu_forward(dst); + mtu = ip6_dst_mtu_maybe_forward(dst, true); if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 322698d9fcf4..20a67efda47f 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1581,9 +1581,10 @@ ip6_tnl_parm_to_user(struct ip6_tnl_parm *u, const struct __ip6_tnl_parm *p) } /** - * ip6_tnl_ioctl - configure ipv6 tunnels from userspace + * ip6_tnl_siocdevprivate - configure ipv6 tunnels from userspace * @dev: virtual device associated with tunnel - * @ifr: parameters passed from userspace + * @ifr: unused + * @data: parameters passed from userspace * @cmd: command to be performed * * Description: @@ -1609,7 +1610,8 @@ ip6_tnl_parm_to_user(struct ip6_tnl_parm *u, const struct __ip6_tnl_parm *p) **/ static int -ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +ip6_tnl_siocdevprivate(struct net_device *dev, struct ifreq *ifr, + void __user *data, int cmd) { int err = 0; struct ip6_tnl_parm p; @@ -1623,7 +1625,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) switch (cmd) { case SIOCGETTUNNEL: if (dev == ip6n->fb_tnl_dev) { - if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) { + if (copy_from_user(&p, data, sizeof(p))) { err = -EFAULT; break; } @@ -1635,9 +1637,8 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) memset(&p, 0, sizeof(p)); } ip6_tnl_parm_to_user(&p, &t->parms); - if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) { + if (copy_to_user(data, &p, sizeof(p))) err = -EFAULT; - } break; case SIOCADDTUNNEL: case SIOCCHGTUNNEL: @@ -1645,7 +1646,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = -EFAULT; - if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) + if (copy_from_user(&p, data, sizeof(p))) break; err = -EINVAL; if (p.proto != IPPROTO_IPV6 && p.proto != IPPROTO_IPIP && @@ -1669,7 +1670,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (!IS_ERR(t)) { err = 0; ip6_tnl_parm_to_user(&p, &t->parms); - if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) + if (copy_to_user(data, &p, sizeof(p))) err = -EFAULT; } else { @@ -1683,7 +1684,7 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (dev == ip6n->fb_tnl_dev) { err = -EFAULT; - if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) + if (copy_from_user(&p, data, sizeof(p))) break; err = -ENOENT; ip6_tnl_parm_from_user(&p1, &p); @@ -1802,7 +1803,7 @@ static const struct net_device_ops ip6_tnl_netdev_ops = { .ndo_init = ip6_tnl_dev_init, .ndo_uninit = ip6_tnl_dev_uninit, .ndo_start_xmit = ip6_tnl_start_xmit, - .ndo_do_ioctl = ip6_tnl_ioctl, + .ndo_siocdevprivate = ip6_tnl_siocdevprivate, .ndo_change_mtu = ip6_tnl_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip6_tnl_get_iflink, diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 2d048e21abbb..1d8e3ffa225d 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -771,13 +771,14 @@ vti6_parm_to_user(struct ip6_tnl_parm2 *u, const struct __ip6_tnl_parm *p) } /** - * vti6_ioctl - configure vti6 tunnels from userspace + * vti6_siocdevprivate - configure vti6 tunnels from userspace * @dev: virtual device associated with tunnel - * @ifr: parameters passed from userspace + * @ifr: unused + * @data: parameters passed from userspace * @cmd: command to be performed * * Description: - * vti6_ioctl() is used for managing vti6 tunnels + * vti6_siocdevprivate() is used for managing vti6 tunnels * from userspace. * * The possible commands are the following: @@ -798,7 +799,7 @@ vti6_parm_to_user(struct ip6_tnl_parm2 *u, const struct __ip6_tnl_parm *p) * %-ENODEV if attempting to change or delete a nonexisting device **/ static int -vti6_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +vti6_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd) { int err = 0; struct ip6_tnl_parm2 p; @@ -810,7 +811,7 @@ vti6_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) switch (cmd) { case SIOCGETTUNNEL: if (dev == ip6n->fb_tnl_dev) { - if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) { + if (copy_from_user(&p, data, sizeof(p))) { err = -EFAULT; break; } @@ -822,7 +823,7 @@ vti6_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (!t) t = netdev_priv(dev); vti6_parm_to_user(&p, &t->parms); - if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) + if (copy_to_user(data, &p, sizeof(p))) err = -EFAULT; break; case SIOCADDTUNNEL: @@ -831,7 +832,7 @@ vti6_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = -EFAULT; - if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) + if (copy_from_user(&p, data, sizeof(p))) break; err = -EINVAL; if (p.proto != IPPROTO_IPV6 && p.proto != 0) @@ -852,7 +853,7 @@ vti6_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (t) { err = 0; vti6_parm_to_user(&p, &t->parms); - if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) + if (copy_to_user(data, &p, sizeof(p))) err = -EFAULT; } else @@ -865,7 +866,7 @@ vti6_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (dev == ip6n->fb_tnl_dev) { err = -EFAULT; - if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) + if (copy_from_user(&p, data, sizeof(p))) break; err = -ENOENT; vti6_parm_from_user(&p1, &p); @@ -890,7 +891,7 @@ static const struct net_device_ops vti6_netdev_ops = { .ndo_init = vti6_dev_init, .ndo_uninit = vti6_dev_uninit, .ndo_start_xmit = vti6_tnl_xmit, - .ndo_do_ioctl = vti6_ioctl, + .ndo_siocdevprivate = vti6_siocdevprivate, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip6_tnl_get_iflink, }; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 06b0d2c329b9..36ed9efb8825 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -559,8 +559,7 @@ static int pim6_rcv(struct sk_buff *skb) read_lock(&mrt_lock); if (reg_vif_num >= 0) reg_dev = mrt->vif_table[reg_vif_num].dev; - if (reg_dev) - dev_hold(reg_dev); + dev_hold(reg_dev); read_unlock(&mrt_lock); if (!reg_dev) diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index a6804a7e34c1..e4bdb09c5586 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -225,7 +225,7 @@ static int ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval, if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) goto out_free_gsf; - ret = ip6_mc_msfilter(sk, gsf, gsf->gf_slist); + ret = ip6_mc_msfilter(sk, gsf, gsf->gf_slist_flex); out_free_gsf: kfree(gsf); return ret; @@ -234,7 +234,7 @@ out_free_gsf: static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen) { - const int size0 = offsetof(struct compat_group_filter, gf_slist); + const int size0 = offsetof(struct compat_group_filter, gf_slist_flex); struct compat_group_filter *gf32; void *p; int ret; @@ -249,7 +249,7 @@ static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval, if (!p) return -ENOMEM; - gf32 = p + 4; /* we want ->gf_group and ->gf_slist aligned */ + gf32 = p + 4; /* we want ->gf_group and ->gf_slist_flex aligned */ ret = -EFAULT; if (copy_from_sockptr(gf32, optval, optlen)) goto out_free_p; @@ -261,14 +261,14 @@ static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval, goto out_free_p; ret = -EINVAL; - if (offsetof(struct compat_group_filter, gf_slist[n]) > optlen) + if (offsetof(struct compat_group_filter, gf_slist_flex[n]) > optlen) goto out_free_p; ret = ip6_mc_msfilter(sk, &(struct group_filter){ .gf_interface = gf32->gf_interface, .gf_group = gf32->gf_group, .gf_fmode = gf32->gf_fmode, - .gf_numsrc = gf32->gf_numsrc}, gf32->gf_slist); + .gf_numsrc = gf32->gf_numsrc}, gf32->gf_slist_flex); out_free_p: kfree(p); @@ -1048,7 +1048,7 @@ static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_txoptions *opt, static int ipv6_get_msfilter(struct sock *sk, void __user *optval, int __user *optlen, int len) { - const int size0 = offsetof(struct group_filter, gf_slist); + const int size0 = offsetof(struct group_filter, gf_slist_flex); struct group_filter __user *p = optval; struct group_filter gsf; int num; @@ -1062,7 +1062,7 @@ static int ipv6_get_msfilter(struct sock *sk, void __user *optval, return -EADDRNOTAVAIL; num = gsf.gf_numsrc; lock_sock(sk); - err = ip6_mc_msfget(sk, &gsf, p->gf_slist); + err = ip6_mc_msfget(sk, &gsf, p->gf_slist_flex); if (!err) { if (num > gsf.gf_numsrc) num = gsf.gf_numsrc; @@ -1077,7 +1077,7 @@ static int ipv6_get_msfilter(struct sock *sk, void __user *optval, static int compat_ipv6_get_msfilter(struct sock *sk, void __user *optval, int __user *optlen) { - const int size0 = offsetof(struct compat_group_filter, gf_slist); + const int size0 = offsetof(struct compat_group_filter, gf_slist_flex); struct compat_group_filter __user *p = optval; struct compat_group_filter gf32; struct group_filter gf; @@ -1100,7 +1100,7 @@ static int compat_ipv6_get_msfilter(struct sock *sk, void __user *optval, return -EADDRNOTAVAIL; lock_sock(sk); - err = ip6_mc_msfget(sk, &gf, p->gf_slist); + err = ip6_mc_msfget(sk, &gf, p->gf_slist_flex); release_sock(sk); if (err) return err; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 54ec163fbafa..bed8155508c8 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -447,7 +447,8 @@ int ip6_mc_source(int add, int omode, struct sock *sk, if (psl) count += psl->sl_max; - newpsl = sock_kmalloc(sk, IP6_SFLSIZE(count), GFP_KERNEL); + newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, count), + GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; @@ -457,7 +458,8 @@ int ip6_mc_source(int add, int omode, struct sock *sk, if (psl) { for (i = 0; i < psl->sl_count; i++) newpsl->sl_addr[i] = psl->sl_addr[i]; - atomic_sub(IP6_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc); + atomic_sub(struct_size(psl, sl_addr, psl->sl_max), + &sk->sk_omem_alloc); kfree_rcu(psl, rcu); } psl = newpsl; @@ -525,8 +527,9 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf, goto done; } if (gsf->gf_numsrc) { - newpsl = sock_kmalloc(sk, IP6_SFLSIZE(gsf->gf_numsrc), - GFP_KERNEL); + newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, + gsf->gf_numsrc), + GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; @@ -543,7 +546,8 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf, newpsl->sl_count, newpsl->sl_addr, 0); if (err) { mutex_unlock(&idev->mc_lock); - sock_kfree_s(sk, newpsl, IP6_SFLSIZE(newpsl->sl_max)); + sock_kfree_s(sk, newpsl, struct_size(newpsl, sl_addr, + newpsl->sl_max)); goto done; } mutex_unlock(&idev->mc_lock); @@ -559,7 +563,8 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf, if (psl) { ip6_mc_del_src(idev, group, pmc->sfmode, psl->sl_count, psl->sl_addr, 0); - atomic_sub(IP6_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc); + atomic_sub(struct_size(psl, sl_addr, psl->sl_max), + &sk->sk_omem_alloc); kfree_rcu(psl, rcu); } else { ip6_mc_del_src(idev, group, pmc->sfmode, 0, NULL, 0); @@ -1351,8 +1356,8 @@ static int mld_process_v1(struct inet6_dev *idev, struct mld_msg *mld, return 0; } -static int mld_process_v2(struct inet6_dev *idev, struct mld2_query *mld, - unsigned long *max_delay) +static void mld_process_v2(struct inet6_dev *idev, struct mld2_query *mld, + unsigned long *max_delay) { *max_delay = max(msecs_to_jiffies(mldv2_mrc(mld)), 1UL); @@ -1362,7 +1367,7 @@ static int mld_process_v2(struct inet6_dev *idev, struct mld2_query *mld, idev->mc_maxdelay = *max_delay; - return 0; + return; } /* called with rcu_read_lock() */ @@ -1449,9 +1454,7 @@ static void __mld_query_work(struct sk_buff *skb) mlh2 = (struct mld2_query *)skb_transport_header(skb); - err = mld_process_v2(idev, mlh2, &max_delay); - if (err < 0) - goto out; + mld_process_v2(idev, mlh2, &max_delay); if (group_type == IPV6_ADDR_ANY) { /* general query */ if (mlh2->mld2q_nsrcs) @@ -2607,7 +2610,8 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, err = ip6_mc_del_src(idev, &iml->addr, iml->sfmode, psl->sl_count, psl->sl_addr, 0); RCU_INIT_POINTER(iml->sflist, NULL); - atomic_sub(IP6_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc); + atomic_sub(struct_size(psl, sl_addr, psl->sl_max), + &sk->sk_omem_alloc); kfree_rcu(psl, rcu); } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index c467c6419893..4b098521a44c 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1391,12 +1391,6 @@ skip_defrtr: } } - /* - * Send a notify if RA changed managed/otherconf flags or timer settings - */ - if (send_ifinfo_notify) - inet6_ifinfo_notify(RTM_NEWLINK, in6_dev); - skip_linkparms: /* @@ -1496,6 +1490,11 @@ skip_routeinfo: memcpy(&n, ((u8 *)(ndopts.nd_opts_mtu+1))+2, sizeof(mtu)); mtu = ntohl(n); + if (in6_dev->ra_mtu != mtu) { + in6_dev->ra_mtu = mtu; + send_ifinfo_notify = true; + } + if (mtu < IPV6_MIN_MTU || mtu > skb->dev->mtu) { ND_PRINTK(2, warn, "RA: invalid mtu: %d\n", mtu); } else if (in6_dev->cnf.mtu6 != mtu) { @@ -1519,6 +1518,12 @@ skip_routeinfo: ND_PRINTK(2, warn, "RA: invalid RA options\n"); } out: + /* Send a notify if RA changed managed/otherconf flags or + * timer settings or ra_mtu value + */ + if (send_ifinfo_notify) + inet6_ifinfo_notify(RTM_NEWLINK, in6_dev); + fib6_info_release(rt); if (neigh) neigh_release(neigh); diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index bb784ea7bbd3..727ee8097012 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -19,15 +19,12 @@ MODULE_DESCRIPTION("ip6tables filter table"); (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT)) -static int __net_init ip6table_filter_table_init(struct net *net); - static const struct xt_table packet_filter = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_FILTER, - .table_init = ip6table_filter_table_init, }; /* The work comes in here from netfilter.c. */ @@ -44,7 +41,7 @@ static struct nf_hook_ops *filter_ops __read_mostly; static bool forward = true; module_param(forward, bool, 0000); -static int __net_init ip6table_filter_table_init(struct net *net) +static int ip6table_filter_table_init(struct net *net) { struct ip6t_replace *repl; int err; @@ -63,7 +60,7 @@ static int __net_init ip6table_filter_table_init(struct net *net) static int __net_init ip6table_filter_net_init(struct net *net) { - if (net == &init_net || !forward) + if (!forward) return ip6table_filter_table_init(net); return 0; @@ -87,15 +84,24 @@ static struct pernet_operations ip6table_filter_net_ops = { static int __init ip6table_filter_init(void) { - int ret; + int ret = xt_register_template(&packet_filter, + ip6table_filter_table_init); + + if (ret < 0) + return ret; filter_ops = xt_hook_ops_alloc(&packet_filter, ip6table_filter_hook); - if (IS_ERR(filter_ops)) + if (IS_ERR(filter_ops)) { + xt_unregister_template(&packet_filter); return PTR_ERR(filter_ops); + } ret = register_pernet_subsys(&ip6table_filter_net_ops); - if (ret < 0) + if (ret < 0) { + xt_unregister_template(&packet_filter); kfree(filter_ops); + return ret; + } return ret; } @@ -103,6 +109,7 @@ static int __init ip6table_filter_init(void) static void __exit ip6table_filter_fini(void) { unregister_pernet_subsys(&ip6table_filter_net_ops); + xt_unregister_template(&packet_filter); kfree(filter_ops); } diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index c76cffd63041..9b518ce37d6a 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -20,15 +20,12 @@ MODULE_DESCRIPTION("ip6tables mangle table"); (1 << NF_INET_LOCAL_OUT) | \ (1 << NF_INET_POST_ROUTING)) -static int __net_init ip6table_mangle_table_init(struct net *net); - static const struct xt_table packet_mangler = { .name = "mangle", .valid_hooks = MANGLE_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_MANGLE, - .table_init = ip6table_mangle_table_init, }; static unsigned int @@ -76,7 +73,7 @@ ip6table_mangle_hook(void *priv, struct sk_buff *skb, } static struct nf_hook_ops *mangle_ops __read_mostly; -static int __net_init ip6table_mangle_table_init(struct net *net) +static int ip6table_mangle_table_init(struct net *net) { struct ip6t_replace *repl; int ret; @@ -106,29 +103,32 @@ static struct pernet_operations ip6table_mangle_net_ops = { static int __init ip6table_mangle_init(void) { - int ret; + int ret = xt_register_template(&packet_mangler, + ip6table_mangle_table_init); + + if (ret < 0) + return ret; mangle_ops = xt_hook_ops_alloc(&packet_mangler, ip6table_mangle_hook); - if (IS_ERR(mangle_ops)) + if (IS_ERR(mangle_ops)) { + xt_unregister_template(&packet_mangler); return PTR_ERR(mangle_ops); + } ret = register_pernet_subsys(&ip6table_mangle_net_ops); if (ret < 0) { + xt_unregister_template(&packet_mangler); kfree(mangle_ops); return ret; } - ret = ip6table_mangle_table_init(&init_net); - if (ret) { - unregister_pernet_subsys(&ip6table_mangle_net_ops); - kfree(mangle_ops); - } return ret; } static void __exit ip6table_mangle_fini(void) { unregister_pernet_subsys(&ip6table_mangle_net_ops); + xt_unregister_template(&packet_mangler); kfree(mangle_ops); } diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index b0292251e655..921c1723a01e 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -19,8 +19,6 @@ struct ip6table_nat_pernet { struct nf_hook_ops *nf_nat_ops; }; -static int __net_init ip6table_nat_table_init(struct net *net); - static unsigned int ip6table_nat_net_id __read_mostly; static const struct xt_table nf_nat_ipv6_table = { @@ -31,7 +29,6 @@ static const struct xt_table nf_nat_ipv6_table = { (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, .af = NFPROTO_IPV6, - .table_init = ip6table_nat_table_init, }; static unsigned int ip6table_nat_do_chain(void *priv, @@ -115,7 +112,7 @@ static void ip6t_nat_unregister_lookups(struct net *net) kfree(ops); } -static int __net_init ip6table_nat_table_init(struct net *net) +static int ip6table_nat_table_init(struct net *net) { struct ip6t_replace *repl; int ret; @@ -157,20 +154,23 @@ static struct pernet_operations ip6table_nat_net_ops = { static int __init ip6table_nat_init(void) { - int ret = register_pernet_subsys(&ip6table_nat_net_ops); + int ret = xt_register_template(&nf_nat_ipv6_table, + ip6table_nat_table_init); - if (ret) + if (ret < 0) return ret; - ret = ip6table_nat_table_init(&init_net); + ret = register_pernet_subsys(&ip6table_nat_net_ops); if (ret) - unregister_pernet_subsys(&ip6table_nat_net_ops); + xt_unregister_template(&nf_nat_ipv6_table); + return ret; } static void __exit ip6table_nat_exit(void) { unregister_pernet_subsys(&ip6table_nat_net_ops); + xt_unregister_template(&nf_nat_ipv6_table); } module_init(ip6table_nat_init); diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index f63c106c521e..4f2a04af71d3 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -11,8 +11,6 @@ #define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT)) -static int __net_init ip6table_raw_table_init(struct net *net); - static bool raw_before_defrag __read_mostly; MODULE_PARM_DESC(raw_before_defrag, "Enable raw table before defrag"); module_param(raw_before_defrag, bool, 0000); @@ -23,7 +21,6 @@ static const struct xt_table packet_raw = { .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_RAW, - .table_init = ip6table_raw_table_init, }; static const struct xt_table packet_raw_before_defrag = { @@ -32,7 +29,6 @@ static const struct xt_table packet_raw_before_defrag = { .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_RAW_BEFORE_DEFRAG, - .table_init = ip6table_raw_table_init, }; /* The work comes in here from netfilter.c. */ @@ -45,7 +41,7 @@ ip6table_raw_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *rawtable_ops __read_mostly; -static int __net_init ip6table_raw_table_init(struct net *net) +static int ip6table_raw_table_init(struct net *net) { struct ip6t_replace *repl; const struct xt_table *table = &packet_raw; @@ -79,37 +75,39 @@ static struct pernet_operations ip6table_raw_net_ops = { static int __init ip6table_raw_init(void) { - int ret; const struct xt_table *table = &packet_raw; + int ret; if (raw_before_defrag) { table = &packet_raw_before_defrag; - pr_info("Enabling raw table before defrag\n"); } + ret = xt_register_template(table, ip6table_raw_table_init); + if (ret < 0) + return ret; + /* Register hooks */ rawtable_ops = xt_hook_ops_alloc(table, ip6table_raw_hook); - if (IS_ERR(rawtable_ops)) + if (IS_ERR(rawtable_ops)) { + xt_unregister_template(table); return PTR_ERR(rawtable_ops); + } ret = register_pernet_subsys(&ip6table_raw_net_ops); if (ret < 0) { kfree(rawtable_ops); + xt_unregister_template(table); return ret; } - ret = ip6table_raw_table_init(&init_net); - if (ret) { - unregister_pernet_subsys(&ip6table_raw_net_ops); - kfree(rawtable_ops); - } return ret; } static void __exit ip6table_raw_fini(void) { unregister_pernet_subsys(&ip6table_raw_net_ops); + xt_unregister_template(&packet_raw); kfree(rawtable_ops); } diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index 8dc335cf450b..931674034d8b 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -24,15 +24,12 @@ MODULE_DESCRIPTION("ip6tables security table, for MAC rules"); (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT) -static int __net_init ip6table_security_table_init(struct net *net); - static const struct xt_table security_table = { .name = "security", .valid_hooks = SECURITY_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_SECURITY, - .table_init = ip6table_security_table_init, }; static unsigned int @@ -44,7 +41,7 @@ ip6table_security_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *sectbl_ops __read_mostly; -static int __net_init ip6table_security_table_init(struct net *net) +static int ip6table_security_table_init(struct net *net) { struct ip6t_replace *repl; int ret; @@ -74,29 +71,32 @@ static struct pernet_operations ip6table_security_net_ops = { static int __init ip6table_security_init(void) { - int ret; + int ret = xt_register_template(&security_table, + ip6table_security_table_init); + + if (ret < 0) + return ret; sectbl_ops = xt_hook_ops_alloc(&security_table, ip6table_security_hook); - if (IS_ERR(sectbl_ops)) + if (IS_ERR(sectbl_ops)) { + xt_unregister_template(&security_table); return PTR_ERR(sectbl_ops); + } ret = register_pernet_subsys(&ip6table_security_net_ops); if (ret < 0) { kfree(sectbl_ops); + xt_unregister_template(&security_table); return ret; } - ret = ip6table_security_table_init(&init_net); - if (ret) { - unregister_pernet_subsys(&ip6table_security_net_ops); - kfree(sectbl_ops); - } return ret; } static void __exit ip6table_security_fini(void) { unregister_pernet_subsys(&ip6table_security_net_ops); + xt_unregister_template(&security_table); kfree(sectbl_ops); } diff --git a/net/ipv6/netfilter/nf_socket_ipv6.c b/net/ipv6/netfilter/nf_socket_ipv6.c index 6fd54744cbc3..aa5bb8789ba0 100644 --- a/net/ipv6/netfilter/nf_socket_ipv6.c +++ b/net/ipv6/netfilter/nf_socket_ipv6.c @@ -99,7 +99,7 @@ struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb, { __be16 dport, sport; const struct in6_addr *daddr = NULL, *saddr = NULL; - struct ipv6hdr *iph = ipv6_hdr(skb); + struct ipv6hdr *iph = ipv6_hdr(skb), ipv6_var; struct sk_buff *data_skb = NULL; int doff = 0; int thoff = 0, tproto; @@ -129,8 +129,6 @@ struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb, thoff + sizeof(*hp); } else if (tproto == IPPROTO_ICMPV6) { - struct ipv6hdr ipv6_var; - if (extract_icmp6_fields(skb, thoff, &tproto, &saddr, &daddr, &sport, &dport, &ipv6_var)) return NULL; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b6ddf23d3833..dbc224023977 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -41,6 +41,7 @@ #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/jhash.h> +#include <linux/siphash.h> #include <net/net_namespace.h> #include <net/snmp.h> #include <net/ipv6.h> @@ -1484,17 +1485,24 @@ static void rt6_exception_remove_oldest(struct rt6_exception_bucket *bucket) static u32 rt6_exception_hash(const struct in6_addr *dst, const struct in6_addr *src) { - static u32 seed __read_mostly; - u32 val; + static siphash_key_t rt6_exception_key __read_mostly; + struct { + struct in6_addr dst; + struct in6_addr src; + } __aligned(SIPHASH_ALIGNMENT) combined = { + .dst = *dst, + }; + u64 val; - net_get_random_once(&seed, sizeof(seed)); - val = jhash2((const u32 *)dst, sizeof(*dst)/sizeof(u32), seed); + net_get_random_once(&rt6_exception_key, sizeof(rt6_exception_key)); #ifdef CONFIG_IPV6_SUBTREES if (src) - val = jhash2((const u32 *)src, sizeof(*src)/sizeof(u32), val); + combined.src = *src; #endif - return hash_32(val, FIB6_EXCEPTION_BUCKET_SIZE_SHIFT); + val = siphash(&combined, sizeof(combined), &rt6_exception_key); + + return hash_64(val, FIB6_EXCEPTION_BUCKET_SIZE_SHIFT); } /* Helper function to find the cached rt in the hash table @@ -1649,6 +1657,7 @@ static int rt6_insert_exception(struct rt6_info *nrt, struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; struct fib6_nh *nh = res->nh; + int max_depth; int err = 0; spin_lock_bh(&rt6_exception_lock); @@ -1703,7 +1712,9 @@ static int rt6_insert_exception(struct rt6_info *nrt, bucket->depth++; net->ipv6.rt6_stats->fib_rt_cache++; - if (bucket->depth > FIB6_MAX_DEPTH) + /* Randomize max depth to avoid some side channels attacks. */ + max_depth = FIB6_MAX_DEPTH + prandom_u32_max(FIB6_MAX_DEPTH); + while (bucket->depth > max_depth) rt6_exception_remove_oldest(bucket); out: @@ -3201,25 +3212,7 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst) INDIRECT_CALLABLE_SCOPE unsigned int ip6_mtu(const struct dst_entry *dst) { - struct inet6_dev *idev; - unsigned int mtu; - - mtu = dst_metric_raw(dst, RTAX_MTU); - if (mtu) - goto out; - - mtu = IPV6_MIN_MTU; - - rcu_read_lock(); - idev = __in6_dev_get(dst->dev); - if (idev) - mtu = idev->cnf.mtu6; - rcu_read_unlock(); - -out: - mtu = min_t(unsigned int, mtu, IP6_MAX_MTU); - - return mtu - lwtunnel_headroom(dst->lwtstate, mtu); + return ip6_dst_mtu_maybe_forward(dst, false); } EXPORT_INDIRECT_CALLABLE(ip6_mtu); @@ -3644,8 +3637,7 @@ out: if (err) { lwtstate_put(fib6_nh->fib_nh_lws); fib6_nh->fib_nh_lws = NULL; - if (dev) - dev_put(dev); + dev_put(dev); } return err; @@ -6638,7 +6630,7 @@ int __init ip6_route_init(void) ret = -ENOMEM; ip6_dst_ops_template.kmem_cachep = kmem_cache_create("ip6_dst_cache", sizeof(struct rt6_info), 0, - SLAB_HWCACHE_ALIGN, NULL); + SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); if (!ip6_dst_ops_template.kmem_cachep) goto out; diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 897fa59c47de..3adc5d9211ad 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -26,6 +26,7 @@ #ifdef CONFIG_IPV6_SEG6_HMAC #include <net/seg6_hmac.h> #endif +#include <linux/netfilter.h> static size_t seg6_lwt_headroom(struct seg6_iptunnel_encap *tuninfo) { @@ -295,11 +296,19 @@ static int seg6_do_srh(struct sk_buff *skb) ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + nf_reset_ct(skb); return 0; } -static int seg6_input(struct sk_buff *skb) +static int seg6_input_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + return dst_input(skb); +} + +static int seg6_input_core(struct net *net, struct sock *sk, + struct sk_buff *skb) { struct dst_entry *orig_dst = skb_dst(skb); struct dst_entry *dst = NULL; @@ -337,15 +346,46 @@ static int seg6_input(struct sk_buff *skb) if (unlikely(err)) return err; - return dst_input(skb); + if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) + return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, + dev_net(skb->dev), NULL, skb, NULL, + skb_dst(skb)->dev, seg6_input_finish); + + return seg6_input_finish(dev_net(skb->dev), NULL, skb); } -static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb) +static int seg6_input_nf(struct sk_buff *skb) +{ + struct net_device *dev = skb_dst(skb)->dev; + struct net *net = dev_net(skb->dev); + + switch (skb->protocol) { + case htons(ETH_P_IP): + return NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, NULL, + skb, NULL, dev, seg6_input_core); + case htons(ETH_P_IPV6): + return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, NULL, + skb, NULL, dev, seg6_input_core); + } + + return -EINVAL; +} + +static int seg6_input(struct sk_buff *skb) +{ + if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) + return seg6_input_nf(skb); + + return seg6_input_core(dev_net(skb->dev), NULL, skb); +} + +static int seg6_output_core(struct net *net, struct sock *sk, + struct sk_buff *skb) { struct dst_entry *orig_dst = skb_dst(skb); struct dst_entry *dst = NULL; struct seg6_lwt *slwt; - int err = -EINVAL; + int err; err = seg6_do_srh(skb); if (unlikely(err)) @@ -387,12 +427,40 @@ static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb) if (unlikely(err)) goto drop; + if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) + return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, + NULL, skb_dst(skb)->dev, dst_output); + return dst_output(net, sk, skb); drop: kfree_skb(skb); return err; } +static int seg6_output_nf(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + struct net_device *dev = skb_dst(skb)->dev; + + switch (skb->protocol) { + case htons(ETH_P_IP): + return NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, + NULL, dev, seg6_output_core); + case htons(ETH_P_IPV6): + return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, + NULL, dev, seg6_output_core); + } + + return -EINVAL; +} + +static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) + return seg6_output_nf(net, sk, skb); + + return seg6_output_core(net, sk, skb); +} + static int seg6_build_state(struct net *net, struct nlattr *nla, unsigned int family, const void *cfg, struct lwtunnel_state **ts, diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 60bf3b877957..2dc40b3f373e 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -30,6 +30,7 @@ #include <net/seg6_local.h> #include <linux/etherdevice.h> #include <linux/bpf.h> +#include <linux/netfilter.h> #define SEG6_F_ATTR(i) BIT(i) @@ -413,12 +414,33 @@ drop: return -EINVAL; } +static int input_action_end_dx6_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + struct dst_entry *orig_dst = skb_dst(skb); + struct in6_addr *nhaddr = NULL; + struct seg6_local_lwt *slwt; + + slwt = seg6_local_lwtunnel(orig_dst->lwtstate); + + /* The inner packet is not associated to any local interface, + * so we do not call netif_rx(). + * + * If slwt->nh6 is set to ::, then lookup the nexthop for the + * inner packet's DA. Otherwise, use the specified nexthop. + */ + if (!ipv6_addr_any(&slwt->nh6)) + nhaddr = &slwt->nh6; + + seg6_lookup_nexthop(skb, nhaddr, 0); + + return dst_input(skb); +} + /* decapsulate and forward to specified nexthop */ static int input_action_end_dx6(struct sk_buff *skb, struct seg6_local_lwt *slwt) { - struct in6_addr *nhaddr = NULL; - /* this function accepts IPv6 encapsulated packets, with either * an SRH with SL=0, or no SRH. */ @@ -429,40 +451,30 @@ static int input_action_end_dx6(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto drop; - /* The inner packet is not associated to any local interface, - * so we do not call netif_rx(). - * - * If slwt->nh6 is set to ::, then lookup the nexthop for the - * inner packet's DA. Otherwise, use the specified nexthop. - */ - - if (!ipv6_addr_any(&slwt->nh6)) - nhaddr = &slwt->nh6; - skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + nf_reset_ct(skb); - seg6_lookup_nexthop(skb, nhaddr, 0); + if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) + return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, + dev_net(skb->dev), NULL, skb, NULL, + skb_dst(skb)->dev, input_action_end_dx6_finish); - return dst_input(skb); + return input_action_end_dx6_finish(dev_net(skb->dev), NULL, skb); drop: kfree_skb(skb); return -EINVAL; } -static int input_action_end_dx4(struct sk_buff *skb, - struct seg6_local_lwt *slwt) +static int input_action_end_dx4_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) { + struct dst_entry *orig_dst = skb_dst(skb); + struct seg6_local_lwt *slwt; struct iphdr *iph; __be32 nhaddr; int err; - if (!decap_and_validate(skb, IPPROTO_IPIP)) - goto drop; - - if (!pskb_may_pull(skb, sizeof(struct iphdr))) - goto drop; - - skb->protocol = htons(ETH_P_IP); + slwt = seg6_local_lwtunnel(orig_dst->lwtstate); iph = ip_hdr(skb); @@ -470,14 +482,34 @@ static int input_action_end_dx4(struct sk_buff *skb, skb_dst_drop(skb); - skb_set_transport_header(skb, sizeof(struct iphdr)); - err = ip_route_input(skb, nhaddr, iph->saddr, 0, skb->dev); - if (err) - goto drop; + if (err) { + kfree_skb(skb); + return -EINVAL; + } return dst_input(skb); +} + +static int input_action_end_dx4(struct sk_buff *skb, + struct seg6_local_lwt *slwt) +{ + if (!decap_and_validate(skb, IPPROTO_IPIP)) + goto drop; + + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + goto drop; + + skb->protocol = htons(ETH_P_IP); + skb_set_transport_header(skb, sizeof(struct iphdr)); + nf_reset_ct(skb); + + if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) + return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, + dev_net(skb->dev), NULL, skb, NULL, + skb_dst(skb)->dev, input_action_end_dx4_finish); + return input_action_end_dx4_finish(dev_net(skb->dev), NULL, skb); drop: kfree_skb(skb); return -EINVAL; @@ -645,6 +677,7 @@ static struct sk_buff *end_dt_vrf_core(struct sk_buff *skb, skb_dst_drop(skb); skb_set_transport_header(skb, hdrlen); + nf_reset_ct(skb); return end_dt_vrf_rcv(skb, family, vrf); @@ -1078,7 +1111,8 @@ static void seg6_local_update_counters(struct seg6_local_lwt *slwt, u64_stats_update_end(&pcounters->syncp); } -static int seg6_local_input(struct sk_buff *skb) +static int seg6_local_input_core(struct net *net, struct sock *sk, + struct sk_buff *skb) { struct dst_entry *orig_dst = skb_dst(skb); struct seg6_action_desc *desc; @@ -1086,11 +1120,6 @@ static int seg6_local_input(struct sk_buff *skb) unsigned int len = skb->len; int rc; - if (skb->protocol != htons(ETH_P_IPV6)) { - kfree_skb(skb); - return -EINVAL; - } - slwt = seg6_local_lwtunnel(orig_dst->lwtstate); desc = slwt->desc; @@ -1104,6 +1133,21 @@ static int seg6_local_input(struct sk_buff *skb) return rc; } +static int seg6_local_input(struct sk_buff *skb) +{ + if (skb->protocol != htons(ETH_P_IPV6)) { + kfree_skb(skb); + return -EINVAL; + } + + if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) + return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN, + dev_net(skb->dev), NULL, skb, skb->dev, NULL, + seg6_local_input_core); + + return seg6_local_input_core(dev_net(skb->dev), NULL, skb); +} + static const struct nla_policy seg6_local_policy[SEG6_LOCAL_MAX + 1] = { [SEG6_LOCAL_ACTION] = { .type = NLA_U32 }, [SEG6_LOCAL_SRH] = { .type = NLA_BINARY }, diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index df5bea818410..ef0c7a7c18e2 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -299,9 +299,8 @@ __ipip6_tunnel_locate_prl(struct ip_tunnel *t, __be32 addr) } -static int ipip6_tunnel_get_prl(struct net_device *dev, struct ifreq *ifr) +static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __user *a) { - struct ip_tunnel_prl __user *a = ifr->ifr_ifru.ifru_data; struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_prl kprl, *kp; struct ip_tunnel_prl_entry *prl; @@ -321,7 +320,7 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ifreq *ifr) * we try harder to allocate. */ kp = (cmax <= 1 || capable(CAP_NET_ADMIN)) ? - kcalloc(cmax, sizeof(*kp), GFP_KERNEL | __GFP_NOWARN) : + kcalloc(cmax, sizeof(*kp), GFP_KERNEL_ACCOUNT | __GFP_NOWARN) : NULL; rcu_read_lock(); @@ -334,7 +333,8 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ifreq *ifr) * For root users, retry allocating enough memory for * the answer. */ - kp = kcalloc(ca, sizeof(*kp), GFP_ATOMIC); + kp = kcalloc(ca, sizeof(*kp), GFP_ATOMIC | __GFP_ACCOUNT | + __GFP_NOWARN); if (!kp) { ret = -ENOMEM; goto out; @@ -453,8 +453,8 @@ out: return err; } -static int ipip6_tunnel_prl_ctl(struct net_device *dev, struct ifreq *ifr, - int cmd) +static int ipip6_tunnel_prl_ctl(struct net_device *dev, + struct ip_tunnel_prl __user *data, int cmd) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_prl prl; @@ -465,7 +465,7 @@ static int ipip6_tunnel_prl_ctl(struct net_device *dev, struct ifreq *ifr, if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) return -EINVAL; - if (copy_from_user(&prl, ifr->ifr_ifru.ifru_data, sizeof(prl))) + if (copy_from_user(&prl, data, sizeof(prl))) return -EFAULT; switch (cmd) { @@ -1197,14 +1197,14 @@ static int ipip6_tunnel_update_6rd(struct ip_tunnel *t, } static int -ipip6_tunnel_get6rd(struct net_device *dev, struct ifreq *ifr) +ipip6_tunnel_get6rd(struct net_device *dev, struct ip_tunnel_parm __user *data) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_6rd ip6rd; struct ip_tunnel_parm p; if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) { - if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) + if (copy_from_user(&p, data, sizeof(p))) return -EFAULT; t = ipip6_tunnel_locate(t->net, &p, 0); } @@ -1215,13 +1215,14 @@ ipip6_tunnel_get6rd(struct net_device *dev, struct ifreq *ifr) ip6rd.relay_prefix = t->ip6rd.relay_prefix; ip6rd.prefixlen = t->ip6rd.prefixlen; ip6rd.relay_prefixlen = t->ip6rd.relay_prefixlen; - if (copy_to_user(ifr->ifr_ifru.ifru_data, &ip6rd, sizeof(ip6rd))) + if (copy_to_user(data, &ip6rd, sizeof(ip6rd))) return -EFAULT; return 0; } static int -ipip6_tunnel_6rdctl(struct net_device *dev, struct ifreq *ifr, int cmd) +ipip6_tunnel_6rdctl(struct net_device *dev, struct ip_tunnel_6rd __user *data, + int cmd) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_6rd ip6rd; @@ -1229,7 +1230,7 @@ ipip6_tunnel_6rdctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (!ns_capable(t->net->user_ns, CAP_NET_ADMIN)) return -EPERM; - if (copy_from_user(&ip6rd, ifr->ifr_ifru.ifru_data, sizeof(ip6rd))) + if (copy_from_user(&ip6rd, data, sizeof(ip6rd))) return -EFAULT; if (cmd != SIOCDEL6RD) { @@ -1368,27 +1369,28 @@ ipip6_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) } static int -ipip6_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +ipip6_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr, + void __user *data, int cmd) { switch (cmd) { case SIOCGETTUNNEL: case SIOCADDTUNNEL: case SIOCCHGTUNNEL: case SIOCDELTUNNEL: - return ip_tunnel_ioctl(dev, ifr, cmd); + return ip_tunnel_siocdevprivate(dev, ifr, data, cmd); case SIOCGETPRL: - return ipip6_tunnel_get_prl(dev, ifr); + return ipip6_tunnel_get_prl(dev, data); case SIOCADDPRL: case SIOCDELPRL: case SIOCCHGPRL: - return ipip6_tunnel_prl_ctl(dev, ifr, cmd); + return ipip6_tunnel_prl_ctl(dev, data, cmd); #ifdef CONFIG_IPV6_SIT_6RD case SIOCGET6RD: - return ipip6_tunnel_get6rd(dev, ifr); + return ipip6_tunnel_get6rd(dev, data); case SIOCADD6RD: case SIOCCHG6RD: case SIOCDEL6RD: - return ipip6_tunnel_6rdctl(dev, ifr, cmd); + return ipip6_tunnel_6rdctl(dev, data, cmd); #endif default: return -EINVAL; @@ -1399,7 +1401,7 @@ static const struct net_device_ops ipip6_netdev_ops = { .ndo_init = ipip6_tunnel_init, .ndo_uninit = ipip6_tunnel_uninit, .ndo_start_xmit = sit_tunnel_xmit, - .ndo_do_ioctl = ipip6_tunnel_ioctl, + .ndo_siocdevprivate = ipip6_tunnel_siocdevprivate, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_tunnel_ctl = ipip6_tunnel_ctl, diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index d7cf26f730d7..d53dd142bf87 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -21,6 +21,7 @@ #ifdef CONFIG_NETLABEL #include <net/calipso.h> #endif +#include <linux/ioam6.h> static int two = 2; static int three = 3; @@ -28,6 +29,8 @@ static int flowlabel_reflect_max = 0x7; static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX; static u32 rt6_multipath_hash_fields_all_mask = FIB_MULTIPATH_HASH_FIELD_ALL_MASK; +static u32 ioam6_id_max = IOAM6_DEFAULT_ID; +static u64 ioam6_id_wide_max = IOAM6_DEFAULT_ID_WIDE; static int proc_rt6_multipath_hash_policy(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) @@ -196,6 +199,22 @@ static struct ctl_table ipv6_table_template[] = { .extra1 = SYSCTL_ZERO, .extra2 = &two, }, + { + .procname = "ioam6_id", + .data = &init_net.ipv6.sysctl.ioam6_id, + .maxlen = sizeof(u32), + .mode = 0644, + .proc_handler = proc_douintvec_minmax, + .extra2 = &ioam6_id_max, + }, + { + .procname = "ioam6_id_wide", + .data = &init_net.ipv6.sysctl.ioam6_id_wide, + .maxlen = sizeof(u64), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + .extra2 = &ioam6_id_wide_max, + }, { } }; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index c5e15e94bb00..ea53847b5b7e 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1475,7 +1475,7 @@ do_udp_sendmsg: fl6.saddr = np->saddr; fl6.fl6_sport = inet->inet_sport; - if (cgroup_bpf_enabled(BPF_CGROUP_UDP6_SENDMSG) && !connected) { + if (cgroup_bpf_enabled(CGROUP_UDP6_SENDMSG) && !connected) { err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, (struct sockaddr *)sin6, &fl6.saddr); if (err) diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 44453b35c7b7..18316ee3c692 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1044,7 +1044,7 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg, if (err == 0) { atomic_dec(&iucv->skbs_in_xmit); skb_unlink(skb, &iucv->send_skb_q); - kfree_skb(skb); + consume_skb(skb); } /* this error should never happen since the */ @@ -1293,7 +1293,7 @@ static int iucv_sock_recvmsg(struct socket *sock, struct msghdr *msg, } } - kfree_skb(skb); + consume_skb(skb); if (iucv->transport == AF_IUCV_TRANS_HIPER) { atomic_inc(&iucv->msg_recv); if (atomic_read(&iucv->msg_recv) > iucv->msglimit) { @@ -1756,7 +1756,7 @@ static void iucv_callback_txdone(struct iucv_path *path, spin_unlock_irqrestore(&list->lock, flags); if (this) { - kfree_skb(this); + consume_skb(this); /* wake up any process waiting for sending */ iucv_sock_wake_msglim(sk); } @@ -1903,17 +1903,17 @@ static int afiucv_hs_callback_synack(struct sock *sk, struct sk_buff *skb) { struct iucv_sock *iucv = iucv_sk(sk); - if (!iucv) - goto out; - if (sk->sk_state != IUCV_BOUND) - goto out; + if (!iucv || sk->sk_state != IUCV_BOUND) { + kfree_skb(skb); + return NET_RX_SUCCESS; + } + bh_lock_sock(sk); iucv->msglimit_peer = iucv_trans_hdr(skb)->window; sk->sk_state = IUCV_CONNECTED; sk->sk_state_change(sk); bh_unlock_sock(sk); -out: - kfree_skb(skb); + consume_skb(skb); return NET_RX_SUCCESS; } @@ -1924,16 +1924,16 @@ static int afiucv_hs_callback_synfin(struct sock *sk, struct sk_buff *skb) { struct iucv_sock *iucv = iucv_sk(sk); - if (!iucv) - goto out; - if (sk->sk_state != IUCV_BOUND) - goto out; + if (!iucv || sk->sk_state != IUCV_BOUND) { + kfree_skb(skb); + return NET_RX_SUCCESS; + } + bh_lock_sock(sk); sk->sk_state = IUCV_DISCONN; sk->sk_state_change(sk); bh_unlock_sock(sk); -out: - kfree_skb(skb); + consume_skb(skb); return NET_RX_SUCCESS; } @@ -1945,16 +1945,18 @@ static int afiucv_hs_callback_fin(struct sock *sk, struct sk_buff *skb) struct iucv_sock *iucv = iucv_sk(sk); /* other end of connection closed */ - if (!iucv) - goto out; + if (!iucv) { + kfree_skb(skb); + return NET_RX_SUCCESS; + } + bh_lock_sock(sk); if (sk->sk_state == IUCV_CONNECTED) { sk->sk_state = IUCV_DISCONN; sk->sk_state_change(sk); } bh_unlock_sock(sk); -out: - kfree_skb(skb); + consume_skb(skb); return NET_RX_SUCCESS; } @@ -2107,7 +2109,7 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, case (AF_IUCV_FLAG_WIN): err = afiucv_hs_callback_win(sk, skb); if (skb->len == sizeof(struct af_iucv_trans_hdr)) { - kfree_skb(skb); + consume_skb(skb); break; } fallthrough; /* and receive non-zero length data */ @@ -2262,21 +2264,11 @@ static struct packet_type iucv_packet_type = { .func = afiucv_hs_rcv, }; -static int afiucv_iucv_init(void) -{ - return pr_iucv->iucv_register(&af_iucv_handler, 0); -} - -static void afiucv_iucv_exit(void) -{ - pr_iucv->iucv_unregister(&af_iucv_handler, 0); -} - static int __init afiucv_init(void) { int err; - if (MACHINE_IS_VM) { + if (MACHINE_IS_VM && IS_ENABLED(CONFIG_IUCV)) { cpcmd("QUERY USERID", iucv_userid, sizeof(iucv_userid), &err); if (unlikely(err)) { WARN_ON(err); @@ -2284,11 +2276,7 @@ static int __init afiucv_init(void) goto out; } - pr_iucv = try_then_request_module(symbol_get(iucv_if), "iucv"); - if (!pr_iucv) { - printk(KERN_WARNING "iucv_if lookup failed\n"); - memset(&iucv_userid, 0, sizeof(iucv_userid)); - } + pr_iucv = &iucv_if; } else { memset(&iucv_userid, 0, sizeof(iucv_userid)); pr_iucv = NULL; @@ -2302,7 +2290,7 @@ static int __init afiucv_init(void) goto out_proto; if (pr_iucv) { - err = afiucv_iucv_init(); + err = pr_iucv->iucv_register(&af_iucv_handler, 0); if (err) goto out_sock; } @@ -2316,23 +2304,19 @@ static int __init afiucv_init(void) out_notifier: if (pr_iucv) - afiucv_iucv_exit(); + pr_iucv->iucv_unregister(&af_iucv_handler, 0); out_sock: sock_unregister(PF_IUCV); out_proto: proto_unregister(&iucv_proto); out: - if (pr_iucv) - symbol_put(iucv_if); return err; } static void __exit afiucv_exit(void) { - if (pr_iucv) { - afiucv_iucv_exit(); - symbol_put(iucv_if); - } + if (pr_iucv) + pr_iucv->iucv_unregister(&af_iucv_handler, 0); unregister_netdevice_notifier(&afiucv_netdev_notifier); dev_remove_pack(&iucv_packet_type); diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index e6795d5a546a..f3343a8541a5 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -286,19 +286,19 @@ static union iucv_param *iucv_param_irq[NR_CPUS]; */ static inline int __iucv_call_b2f0(int command, union iucv_param *parm) { - register unsigned long reg0 asm ("0"); - register unsigned long reg1 asm ("1"); - int ccode; + int cc; - reg0 = command; - reg1 = (unsigned long)parm; asm volatile( - " .long 0xb2f01000\n" - " ipm %0\n" - " srl %0,28\n" - : "=d" (ccode), "=m" (*parm), "+d" (reg0), "+a" (reg1) - : "m" (*parm) : "cc"); - return ccode; + " lgr 0,%[reg0]\n" + " lgr 1,%[reg1]\n" + " .long 0xb2f01000\n" + " ipm %[cc]\n" + " srl %[cc],28\n" + : [cc] "=&d" (cc), "+m" (*parm) + : [reg0] "d" ((unsigned long)command), + [reg1] "d" ((unsigned long)parm) + : "cc", "0", "1"); + return cc; } static inline int iucv_call_b2f0(int command, union iucv_param *parm) @@ -319,19 +319,21 @@ static inline int iucv_call_b2f0(int command, union iucv_param *parm) */ static int __iucv_query_maxconn(void *param, unsigned long *max_pathid) { - register unsigned long reg0 asm ("0"); - register unsigned long reg1 asm ("1"); - int ccode; + unsigned long reg1 = (unsigned long)param; + int cc; - reg0 = IUCV_QUERY; - reg1 = (unsigned long) param; asm volatile ( + " lghi 0,%[cmd]\n" + " lgr 1,%[reg1]\n" " .long 0xb2f01000\n" - " ipm %0\n" - " srl %0,28\n" - : "=d" (ccode), "+d" (reg0), "+d" (reg1) : : "cc"); + " ipm %[cc]\n" + " srl %[cc],28\n" + " lgr %[reg1],1\n" + : [cc] "=&d" (cc), [reg1] "+&d" (reg1) + : [cmd] "K" (IUCV_QUERY) + : "cc", "0", "1"); *max_pathid = reg1; - return ccode; + return cc; } static int iucv_query_maxconn(void) @@ -500,14 +502,14 @@ static void iucv_setmask_mp(void) { int cpu; - get_online_cpus(); + cpus_read_lock(); for_each_online_cpu(cpu) /* Enable all cpus with a declared buffer. */ if (cpumask_test_cpu(cpu, &iucv_buffer_cpumask) && !cpumask_test_cpu(cpu, &iucv_irq_cpumask)) smp_call_function_single(cpu, iucv_allow_cpu, NULL, 1); - put_online_cpus(); + cpus_read_unlock(); } /** @@ -540,7 +542,7 @@ static int iucv_enable(void) size_t alloc_size; int cpu, rc; - get_online_cpus(); + cpus_read_lock(); rc = -ENOMEM; alloc_size = iucv_max_pathid * sizeof(struct iucv_path); iucv_path_table = kzalloc(alloc_size, GFP_KERNEL); @@ -553,12 +555,12 @@ static int iucv_enable(void) if (cpumask_empty(&iucv_buffer_cpumask)) /* No cpu could declare an iucv buffer. */ goto out; - put_online_cpus(); + cpus_read_unlock(); return 0; out: kfree(iucv_path_table); iucv_path_table = NULL; - put_online_cpus(); + cpus_read_unlock(); return rc; } @@ -571,11 +573,11 @@ out: */ static void iucv_disable(void) { - get_online_cpus(); + cpus_read_lock(); on_each_cpu(iucv_retrieve_cpu, NULL, 1); kfree(iucv_path_table); iucv_path_table = NULL; - put_online_cpus(); + cpus_read_unlock(); } static int iucv_cpu_dead(unsigned int cpu) @@ -784,7 +786,7 @@ static int iucv_reboot_event(struct notifier_block *this, if (cpumask_empty(&iucv_irq_cpumask)) return NOTIFY_DONE; - get_online_cpus(); + cpus_read_lock(); on_each_cpu_mask(&iucv_irq_cpumask, iucv_block_cpu, NULL, 1); preempt_disable(); for (i = 0; i < iucv_max_pathid; i++) { @@ -792,7 +794,7 @@ static int iucv_reboot_event(struct notifier_block *this, iucv_sever_pathid(i, NULL); } preempt_enable(); - put_online_cpus(); + cpus_read_unlock(); iucv_disable(); return NOTIFY_DONE; } diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 7180979114e4..3086f4a6ae68 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -98,8 +98,16 @@ static inline u8 llc_ui_header_len(struct sock *sk, struct sockaddr_llc *addr) { u8 rc = LLC_PDU_LEN_U; - if (addr->sllc_test || addr->sllc_xid) + if (addr->sllc_test) rc = LLC_PDU_LEN_U; + else if (addr->sllc_xid) + /* We need to expand header to sizeof(struct llc_xid_info) + * since llc_pdu_init_as_xid_cmd() sets 4,5,6 bytes of LLC header + * as XID PDU. In llc_ui_sendmsg() we reserved header size and then + * filled all other space with user data. If we won't reserve this + * bytes, llc_pdu_init_as_xid_cmd() will overwrite user data + */ + rc = LLC_PDU_LEN_U_XID; else if (sk->sk_type == SOCK_STREAM) rc = LLC_PDU_LEN_I; return rc; @@ -216,8 +224,7 @@ static int llc_ui_release(struct socket *sock) } else { release_sock(sk); } - if (llc->dev) - dev_put(llc->dev); + dev_put(llc->dev); sock_put(sk); llc_sk_free(sk); out: @@ -355,8 +362,7 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) } else llc->dev = dev_getbyhwaddr_rcu(&init_net, addr->sllc_arphrd, addr->sllc_mac); - if (llc->dev) - dev_hold(llc->dev); + dev_hold(llc->dev); rcu_read_unlock(); if (!llc->dev) goto out; diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c index b554f26c68ee..79d1cef8f15a 100644 --- a/net/llc/llc_s_ac.c +++ b/net/llc/llc_s_ac.c @@ -79,7 +79,7 @@ int llc_sap_action_send_xid_c(struct llc_sap *sap, struct sk_buff *skb) struct llc_sap_state_ev *ev = llc_sap_ev(skb); int rc; - llc_pdu_header_init(skb, LLC_PDU_TYPE_U, ev->saddr.lsap, + llc_pdu_header_init(skb, LLC_PDU_TYPE_U_XID, ev->saddr.lsap, ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_xid_cmd(skb, LLC_XID_NULL_CLASS_2, 0); rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 84cc7733ea66..d69b31c20fe2 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -152,6 +152,8 @@ static int ieee80211_change_iface(struct wiphy *wiphy, struct vif_params *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = sdata->local; + struct sta_info *sta; int ret; ret = ieee80211_if_change_type(sdata, type); @@ -162,7 +164,24 @@ static int ieee80211_change_iface(struct wiphy *wiphy, RCU_INIT_POINTER(sdata->u.vlan.sta, NULL); ieee80211_check_fast_rx_iface(sdata); } else if (type == NL80211_IFTYPE_STATION && params->use_4addr >= 0) { + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + + if (params->use_4addr == ifmgd->use_4addr) + return 0; + sdata->u.mgd.use_4addr = params->use_4addr; + if (!ifmgd->associated) + return 0; + + mutex_lock(&local->sta_mtx); + sta = sta_info_get(sdata, ifmgd->bssid); + if (sta) + drv_sta_set_4addr(local, sdata, &sta->sta, + params->use_4addr); + mutex_unlock(&local->sta_mtx); + + if (params->use_4addr) + ieee80211_send_4addr_nullfunc(local, sdata); } if (sdata->vif.type == NL80211_IFTYPE_MONITOR) { @@ -809,9 +828,11 @@ static int ieee80211_set_monitor_channel(struct wiphy *wiphy, return ret; } -static int ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata, - const u8 *resp, size_t resp_len, - const struct ieee80211_csa_settings *csa) +static int +ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata, + const u8 *resp, size_t resp_len, + const struct ieee80211_csa_settings *csa, + const struct ieee80211_color_change_settings *cca) { struct probe_resp *new, *old; @@ -831,6 +852,8 @@ static int ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata, memcpy(new->cntdwn_counter_offsets, csa->counter_offsets_presp, csa->n_counter_offsets_presp * sizeof(new->cntdwn_counter_offsets[0])); + else if (cca) + new->cntdwn_counter_offsets[0] = cca->counter_offset_presp; rcu_assign_pointer(sdata->u.ap.probe_resp, new); if (old) @@ -936,7 +959,8 @@ static int ieee80211_set_ftm_responder_params( static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, struct cfg80211_beacon_data *params, - const struct ieee80211_csa_settings *csa) + const struct ieee80211_csa_settings *csa, + const struct ieee80211_color_change_settings *cca) { struct beacon_data *new, *old; int new_head_len, new_tail_len; @@ -985,6 +1009,9 @@ static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, memcpy(new->cntdwn_counter_offsets, csa->counter_offsets_beacon, csa->n_counter_offsets_beacon * sizeof(new->cntdwn_counter_offsets[0])); + } else if (cca) { + new->cntdwn_current_counter = cca->count; + new->cntdwn_counter_offsets[0] = cca->counter_offset_beacon; } /* copy in head */ @@ -1001,7 +1028,7 @@ static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, memcpy(new->tail, old->tail, new_tail_len); err = ieee80211_set_probe_resp(sdata, params->probe_resp, - params->probe_resp_len, csa); + params->probe_resp_len, csa, cca); if (err < 0) { kfree(new); return err; @@ -1156,7 +1183,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) sdata->vif.bss_conf.beacon_tx_rate = params->beacon_rate; - err = ieee80211_assign_beacon(sdata, ¶ms->beacon, NULL); + err = ieee80211_assign_beacon(sdata, ¶ms->beacon, NULL, NULL); if (err < 0) goto error; changed |= err; @@ -1211,17 +1238,17 @@ static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev, sdata = IEEE80211_DEV_TO_SUB_IF(dev); sdata_assert_lock(sdata); - /* don't allow changing the beacon while CSA is in place - offset + /* don't allow changing the beacon while a countdown is in place - offset * of channel switch counter may change */ - if (sdata->vif.csa_active) + if (sdata->vif.csa_active || sdata->vif.color_change_active) return -EBUSY; old = sdata_dereference(sdata->u.ap.beacon, sdata); if (!old) return -ENOENT; - err = ieee80211_assign_beacon(sdata, params, NULL); + err = ieee80211_assign_beacon(sdata, params, NULL, NULL); if (err < 0) return err; ieee80211_bss_info_change_notify(sdata, err); @@ -3137,7 +3164,7 @@ static int ieee80211_set_after_csa_beacon(struct ieee80211_sub_if_data *sdata, switch (sdata->vif.type) { case NL80211_IFTYPE_AP: err = ieee80211_assign_beacon(sdata, sdata->u.ap.next_beacon, - NULL); + NULL, NULL); kfree(sdata->u.ap.next_beacon); sdata->u.ap.next_beacon = NULL; @@ -3303,7 +3330,7 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata, csa.n_counter_offsets_presp = params->n_counter_offsets_presp; csa.count = params->count; - err = ieee80211_assign_beacon(sdata, ¶ms->beacon_csa, &csa); + err = ieee80211_assign_beacon(sdata, ¶ms->beacon_csa, &csa, NULL); if (err < 0) { kfree(sdata->u.ap.next_beacon); return err; @@ -3392,6 +3419,15 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata, return 0; } +static void ieee80211_color_change_abort(struct ieee80211_sub_if_data *sdata) +{ + sdata->vif.color_change_active = false; + kfree(sdata->u.ap.next_beacon); + sdata->u.ap.next_beacon = NULL; + + cfg80211_color_change_aborted_notify(sdata->dev); +} + static int __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_csa_settings *params) @@ -3460,6 +3496,10 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, goto out; } + /* if there is a color change in progress, abort it */ + if (sdata->vif.color_change_active) + ieee80211_color_change_abort(sdata); + err = ieee80211_set_csa_beacon(sdata, params, &changed); if (err) { ieee80211_vif_unreserve_chanctx(sdata); @@ -4111,6 +4151,196 @@ static int ieee80211_set_sar_specs(struct wiphy *wiphy, return local->ops->set_sar_specs(&local->hw, sar); } +static int +ieee80211_set_after_color_change_beacon(struct ieee80211_sub_if_data *sdata, + u32 *changed) +{ + switch (sdata->vif.type) { + case NL80211_IFTYPE_AP: { + int ret; + + ret = ieee80211_assign_beacon(sdata, sdata->u.ap.next_beacon, + NULL, NULL); + kfree(sdata->u.ap.next_beacon); + sdata->u.ap.next_beacon = NULL; + + if (ret < 0) + return ret; + + *changed |= ret; + break; + } + default: + WARN_ON_ONCE(1); + return -EINVAL; + } + + return 0; +} + +static int +ieee80211_set_color_change_beacon(struct ieee80211_sub_if_data *sdata, + struct cfg80211_color_change_settings *params, + u32 *changed) +{ + struct ieee80211_color_change_settings color_change = {}; + int err; + + switch (sdata->vif.type) { + case NL80211_IFTYPE_AP: + sdata->u.ap.next_beacon = + cfg80211_beacon_dup(¶ms->beacon_next); + if (!sdata->u.ap.next_beacon) + return -ENOMEM; + + if (params->count <= 1) + break; + + color_change.counter_offset_beacon = + params->counter_offset_beacon; + color_change.counter_offset_presp = + params->counter_offset_presp; + color_change.count = params->count; + + err = ieee80211_assign_beacon(sdata, ¶ms->beacon_color_change, + NULL, &color_change); + if (err < 0) { + kfree(sdata->u.ap.next_beacon); + return err; + } + *changed |= err; + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static void +ieee80211_color_change_bss_config_notify(struct ieee80211_sub_if_data *sdata, + u8 color, int enable, u32 changed) +{ + sdata->vif.bss_conf.he_bss_color.color = color; + sdata->vif.bss_conf.he_bss_color.enabled = enable; + changed |= BSS_CHANGED_HE_BSS_COLOR; + + ieee80211_bss_info_change_notify(sdata, changed); +} + +static int ieee80211_color_change_finalize(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + u32 changed = 0; + int err; + + sdata_assert_lock(sdata); + lockdep_assert_held(&local->mtx); + + sdata->vif.color_change_active = false; + + err = ieee80211_set_after_color_change_beacon(sdata, &changed); + if (err) { + cfg80211_color_change_aborted_notify(sdata->dev); + return err; + } + + ieee80211_color_change_bss_config_notify(sdata, + sdata->vif.color_change_color, + 1, changed); + cfg80211_color_change_notify(sdata->dev); + + return 0; +} + +void ieee80211_color_change_finalize_work(struct work_struct *work) +{ + struct ieee80211_sub_if_data *sdata = + container_of(work, struct ieee80211_sub_if_data, + color_change_finalize_work); + struct ieee80211_local *local = sdata->local; + + sdata_lock(sdata); + mutex_lock(&local->mtx); + + /* AP might have been stopped while waiting for the lock. */ + if (!sdata->vif.color_change_active) + goto unlock; + + if (!ieee80211_sdata_running(sdata)) + goto unlock; + + ieee80211_color_change_finalize(sdata); + +unlock: + mutex_unlock(&local->mtx); + sdata_unlock(sdata); +} + +void ieee80211_color_change_finish(struct ieee80211_vif *vif) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + + ieee80211_queue_work(&sdata->local->hw, + &sdata->color_change_finalize_work); +} +EXPORT_SYMBOL_GPL(ieee80211_color_change_finish); + +void +ieeee80211_obss_color_collision_notify(struct ieee80211_vif *vif, + u64 color_bitmap) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + + if (sdata->vif.color_change_active || sdata->vif.csa_active) + return; + + cfg80211_obss_color_collision_notify(sdata->dev, color_bitmap); +} +EXPORT_SYMBOL_GPL(ieeee80211_obss_color_collision_notify); + +static int +ieee80211_color_change(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_color_change_settings *params) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = sdata->local; + u32 changed = 0; + int err; + + sdata_assert_lock(sdata); + + mutex_lock(&local->mtx); + + /* don't allow another color change if one is already active or if csa + * is active + */ + if (sdata->vif.color_change_active || sdata->vif.csa_active) { + err = -EBUSY; + goto out; + } + + err = ieee80211_set_color_change_beacon(sdata, params, &changed); + if (err) + goto out; + + sdata->vif.color_change_active = true; + sdata->vif.color_change_color = params->color; + + cfg80211_color_change_started_notify(sdata->dev, params->count); + + if (changed) + ieee80211_color_change_bss_config_notify(sdata, 0, 0, changed); + else + /* if the beacon didn't change, we can finalize immediately */ + ieee80211_color_change_finalize(sdata); + +out: + mutex_unlock(&local->mtx); + + return err; +} + const struct cfg80211_ops mac80211_config_ops = { .add_virtual_intf = ieee80211_add_iface, .del_virtual_intf = ieee80211_del_iface, @@ -4214,4 +4444,5 @@ const struct cfg80211_ops mac80211_config_ops = { .set_tid_config = ieee80211_set_tid_config, .reset_tid_config = ieee80211_reset_tid_config, .set_sar_specs = ieee80211_set_sar_specs, + .color_change = ieee80211_color_change, }; diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index bcb7cc06db3d..cd3731cbf6c6 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1447,4 +1447,40 @@ static inline void drv_sta_set_decap_offload(struct ieee80211_local *local, trace_drv_return_void(local); } +static inline void drv_add_twt_setup(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta, + struct ieee80211_twt_setup *twt) +{ + struct ieee80211_twt_params *twt_agrt; + + might_sleep(); + + if (!check_sdata_in_driver(sdata)) + return; + + twt_agrt = (void *)twt->params; + + trace_drv_add_twt_setup(local, sta, twt, twt_agrt); + local->ops->add_twt_setup(&local->hw, sta, twt); + trace_drv_return_void(local); +} + +static inline void drv_twt_teardown_request(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta, + u8 flowid) +{ + might_sleep(); + if (!check_sdata_in_driver(sdata)) + return; + + if (!local->ops->twt_teardown_request) + return; + + trace_drv_twt_teardown_request(local, sta, flowid); + local->ops->twt_teardown_request(&local->hw, sta, flowid); + trace_drv_return_void(local); +} + #endif /* __MAC80211_DRIVER_OPS */ diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index a7ac53a2f00d..5d6ca4c3e698 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -489,7 +489,6 @@ int ieee80211_ibss_csa_beacon(struct ieee80211_sub_if_data *sdata, const struct cfg80211_bss_ies *ies; u16 capability = WLAN_CAPABILITY_IBSS; u64 tsf; - int ret = 0; sdata_assert_lock(sdata); @@ -501,10 +500,8 @@ int ieee80211_ibss_csa_beacon(struct ieee80211_sub_if_data *sdata, ifibss->ssid_len, IEEE80211_BSS_TYPE_IBSS, IEEE80211_PRIVACY(ifibss->privacy)); - if (WARN_ON(!cbss)) { - ret = -EINVAL; - goto out; - } + if (WARN_ON(!cbss)) + return -EINVAL; rcu_read_lock(); ies = rcu_dereference(cbss->ies); @@ -520,18 +517,14 @@ int ieee80211_ibss_csa_beacon(struct ieee80211_sub_if_data *sdata, sdata->vif.bss_conf.basic_rates, capability, tsf, &ifibss->chandef, NULL, csa_settings); - if (!presp) { - ret = -ENOMEM; - goto out; - } + if (!presp) + return -ENOMEM; rcu_assign_pointer(ifibss->presp, presp); if (old_presp) kfree_rcu(old_presp, rcu_head); return BSS_CHANGED_BEACON; - out: - return ret; } int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata) diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 22549b95d1aa..159af6c3ffb0 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -25,6 +25,7 @@ #include <linux/leds.h> #include <linux/idr.h> #include <linux/rhashtable.h> +#include <linux/rbtree.h> #include <net/ieee80211_radiotap.h> #include <net/cfg80211.h> #include <net/mac80211.h> @@ -244,6 +245,12 @@ struct ieee80211_csa_settings { u8 count; }; +struct ieee80211_color_change_settings { + u16 counter_offset_beacon; + u16 counter_offset_presp; + u8 count; +}; + struct beacon_data { u8 *head, *tail; int head_len, tail_len; @@ -923,6 +930,8 @@ struct ieee80211_sub_if_data { bool csa_block_tx; /* write-protected by sdata_lock and local->mtx */ struct cfg80211_chan_def csa_chandef; + struct work_struct color_change_finalize_work; + struct list_head assigned_chanctx_list; /* protected by chanctx_mtx */ struct list_head reserved_chanctx_list; /* protected by chanctx_mtx */ @@ -937,6 +946,7 @@ struct ieee80211_sub_if_data { struct work_struct work; struct sk_buff_head skb_queue; + struct sk_buff_head status_queue; u8 needed_rx_chains; enum ieee80211_smps_mode smps_mode; @@ -1524,6 +1534,7 @@ struct ieee802_11_elems { const struct ieee80211_he_spr *he_spr; const struct ieee80211_mu_edca_param_set *mu_edca_param_set; const struct ieee80211_he_6ghz_capa *he_6ghz_capa; + const struct ieee80211_tx_pwr_env *tx_pwr_env[IEEE80211_TPE_MAX_IE_COUNT]; const u8 *uora_element; const u8 *mesh_id; const u8 *peering; @@ -1574,6 +1585,8 @@ struct ieee802_11_elems { u8 perr_len; u8 country_elem_len; u8 bssid_index_len; + u8 tx_pwr_env_len[IEEE80211_TPE_MAX_IE_COUNT]; + u8 tx_pwr_env_num; /* whether a parse error occurred while retrieving these elements */ bool parse_error; @@ -1887,6 +1900,9 @@ void ieee80211_csa_finalize_work(struct work_struct *work); int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_csa_settings *params); +/* color change handling */ +void ieee80211_color_change_finalize_work(struct work_struct *work); + /* interface handling */ #define MAC80211_SUPPORTED_FEATURES_TX (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | \ NETIF_F_HW_CSUM | NETIF_F_SG | \ @@ -2068,6 +2084,11 @@ ieee80211_he_op_ie_to_bss_conf(struct ieee80211_vif *vif, /* S1G */ void ieee80211_s1g_sta_rate_init(struct sta_info *sta); +bool ieee80211_s1g_is_twt_setup(struct sk_buff *skb); +void ieee80211_s1g_rx_twt_action(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb); +void ieee80211_s1g_status_twt_action(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb); /* Spectrum management */ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, @@ -2201,6 +2222,8 @@ void ieee80211_dynamic_ps_timer(struct timer_list *t); void ieee80211_send_nullfunc(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, bool powersave); +void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata); void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata, struct ieee80211_hdr *hdr, bool ack, u16 tx_time); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 1e5e9fc45523..62c95597704b 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -462,6 +462,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do sdata_unlock(sdata); cancel_work_sync(&sdata->csa_finalize_work); + cancel_work_sync(&sdata->color_change_finalize_work); cancel_delayed_work_sync(&sdata->dfs_cac_timer_work); @@ -551,6 +552,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do */ ieee80211_free_keys(sdata, true); skb_queue_purge(&sdata->skb_queue); + skb_queue_purge(&sdata->status_queue); } spin_lock_irqsave(&local->queue_stop_reason_lock, flags); @@ -983,6 +985,7 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local) } skb_queue_head_init(&sdata->skb_queue); + skb_queue_head_init(&sdata->status_queue); INIT_WORK(&sdata->work, ieee80211_iface_work); return 0; @@ -1381,6 +1384,16 @@ static void ieee80211_iface_process_skb(struct ieee80211_local *local, WARN_ON(1); break; } + } else if (ieee80211_is_action(mgmt->frame_control) && + mgmt->u.action.category == WLAN_CATEGORY_S1G) { + switch (mgmt->u.action.u.s1g.action_code) { + case WLAN_S1G_TWT_TEARDOWN: + case WLAN_S1G_TWT_SETUP: + ieee80211_s1g_rx_twt_action(sdata, skb); + break; + default: + break; + } } else if (ieee80211_is_ext(mgmt->frame_control)) { if (sdata->vif.type == NL80211_IFTYPE_STATION) ieee80211_sta_rx_queued_ext(sdata, skb); @@ -1436,6 +1449,24 @@ static void ieee80211_iface_process_skb(struct ieee80211_local *local, } } +static void ieee80211_iface_process_status(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb) +{ + struct ieee80211_mgmt *mgmt = (void *)skb->data; + + if (ieee80211_is_action(mgmt->frame_control) && + mgmt->u.action.category == WLAN_CATEGORY_S1G) { + switch (mgmt->u.action.u.s1g.action_code) { + case WLAN_S1G_TWT_TEARDOWN: + case WLAN_S1G_TWT_SETUP: + ieee80211_s1g_status_twt_action(sdata, skb); + break; + default: + break; + } + } +} + static void ieee80211_iface_work(struct work_struct *work) { struct ieee80211_sub_if_data *sdata = @@ -1465,6 +1496,16 @@ static void ieee80211_iface_work(struct work_struct *work) kcov_remote_stop(); } + /* process status queue */ + while ((skb = skb_dequeue(&sdata->status_queue))) { + kcov_remote_start_common(skb_get_kcov_handle(skb)); + + ieee80211_iface_process_status(sdata, skb); + kfree_skb(skb); + + kcov_remote_stop(); + } + /* then other type-dependent work */ switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: @@ -1528,9 +1569,11 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, } skb_queue_head_init(&sdata->skb_queue); + skb_queue_head_init(&sdata->status_queue); INIT_WORK(&sdata->work, ieee80211_iface_work); INIT_WORK(&sdata->recalc_smps, ieee80211_recalc_smps_work); INIT_WORK(&sdata->csa_finalize_work, ieee80211_csa_finalize_work); + INIT_WORK(&sdata->color_change_finalize_work, ieee80211_color_change_finalize_work); INIT_LIST_HEAD(&sdata->assigned_chanctx_list); INIT_LIST_HEAD(&sdata->reserved_chanctx_list); @@ -2001,9 +2044,16 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, netdev_set_default_ethtool_ops(ndev, &ieee80211_ethtool_ops); - /* MTU range: 256 - 2304 */ + /* MTU range is normally 256 - 2304, where the upper limit is + * the maximum MSDU size. Monitor interfaces send and receive + * MPDU and A-MSDU frames which may be much larger so we do + * not impose an upper limit in that case. + */ ndev->min_mtu = 256; - ndev->max_mtu = local->hw.max_mtu; + if (type == NL80211_IFTYPE_MONITOR) + ndev->max_mtu = 0; + else + ndev->max_mtu = local->hw.max_mtu; ret = cfg80211_register_netdevice(ndev); if (ret) { diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 05f4c3c72619..45fb517591ee 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -260,6 +260,8 @@ static void ieee80211_restart_work(struct work_struct *work) flush_work(&local->radar_detected_work); rtnl_lock(); + /* we might do interface manipulations, so need both */ + wiphy_lock(local->hw.wiphy); WARN(test_bit(SCAN_HW_SCANNING, &local->scanning), "%s called with hardware scan in progress\n", __func__); @@ -1018,7 +1020,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) iftd = &sband->iftype_data[i]; - supp_he = supp_he || (iftd && iftd->he_cap.has_he); + supp_he = supp_he || iftd->he_cap.has_he; } /* HT, VHT, HE require QoS, thus >= 4 queues */ diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index a00f11a33699..c0ea3b1aa9e1 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1095,8 +1095,8 @@ void ieee80211_send_nullfunc(struct ieee80211_local *local, ieee80211_tx_skb(sdata, skb); } -static void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata) +void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) { struct sk_buff *skb; struct ieee80211_hdr *nullfunc; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 771921c057e8..99ed68f7dc36 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -359,7 +359,12 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, put_unaligned_le32(it_present_val, it_present); - pos = (void *)(it_present + 1); + /* This references through an offset into it_optional[] rather + * than via it_present otherwise later uses of pos will cause + * the compiler to think we have walked past the end of the + * struct member. + */ + pos = (void *)&rthdr->it_optional[it_present - rthdr->it_optional]; /* the order of the following fields is important */ @@ -372,7 +377,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, ieee80211_calculate_rx_timestamp(local, status, mpdulen, 0), pos); - rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_TSFT); + rthdr->it_present |= cpu_to_le32(BIT(IEEE80211_RADIOTAP_TSFT)); pos += 8; } @@ -396,7 +401,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, *pos = 0; } else { int shift = 0; - rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_RATE); + rthdr->it_present |= cpu_to_le32(BIT(IEEE80211_RADIOTAP_RATE)); if (status->bw == RATE_INFO_BW_10) shift = 1; else if (status->bw == RATE_INFO_BW_5) @@ -433,7 +438,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, !(status->flag & RX_FLAG_NO_SIGNAL_VAL)) { *pos = status->signal; rthdr->it_present |= - cpu_to_le32(1 << IEEE80211_RADIOTAP_DBM_ANTSIGNAL); + cpu_to_le32(BIT(IEEE80211_RADIOTAP_DBM_ANTSIGNAL)); pos++; } @@ -459,7 +464,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, if (status->encoding == RX_ENC_HT) { unsigned int stbc; - rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_MCS); + rthdr->it_present |= cpu_to_le32(BIT(IEEE80211_RADIOTAP_MCS)); *pos++ = local->hw.radiotap_mcs_details; *pos = 0; if (status->enc_flags & RX_ENC_FLAG_SHORT_GI) @@ -483,7 +488,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, while ((pos - (u8 *)rthdr) & 3) pos++; rthdr->it_present |= - cpu_to_le32(1 << IEEE80211_RADIOTAP_AMPDU_STATUS); + cpu_to_le32(BIT(IEEE80211_RADIOTAP_AMPDU_STATUS)); put_unaligned_le32(status->ampdu_reference, pos); pos += 4; if (status->flag & RX_FLAG_AMPDU_LAST_KNOWN) @@ -510,7 +515,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, if (status->encoding == RX_ENC_VHT) { u16 known = local->hw.radiotap_vht_details; - rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_VHT); + rthdr->it_present |= cpu_to_le32(BIT(IEEE80211_RADIOTAP_VHT)); put_unaligned_le16(known, pos); pos += 2; /* flags */ @@ -554,7 +559,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, u8 flags = IEEE80211_RADIOTAP_TIMESTAMP_FLAG_32BIT; rthdr->it_present |= - cpu_to_le32(1 << IEEE80211_RADIOTAP_TIMESTAMP); + cpu_to_le32(BIT(IEEE80211_RADIOTAP_TIMESTAMP)); /* ensure 8 byte alignment */ while ((pos - (u8 *)rthdr) & 7) @@ -642,7 +647,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, /* ensure 2 byte alignment */ while ((pos - (u8 *)rthdr) & 1) pos++; - rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_HE); + rthdr->it_present |= cpu_to_le32(BIT(IEEE80211_RADIOTAP_HE)); memcpy(pos, &he, sizeof(he)); pos += sizeof(he); } @@ -652,14 +657,14 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, /* ensure 2 byte alignment */ while ((pos - (u8 *)rthdr) & 1) pos++; - rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_HE_MU); + rthdr->it_present |= cpu_to_le32(BIT(IEEE80211_RADIOTAP_HE_MU)); memcpy(pos, &he_mu, sizeof(he_mu)); pos += sizeof(he_mu); } if (status->flag & RX_FLAG_NO_PSDU) { rthdr->it_present |= - cpu_to_le32(1 << IEEE80211_RADIOTAP_ZERO_LEN_PSDU); + cpu_to_le32(BIT(IEEE80211_RADIOTAP_ZERO_LEN_PSDU)); *pos++ = status->zero_length_psdu_type; } @@ -667,7 +672,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, /* ensure 2 byte alignment */ while ((pos - (u8 *)rthdr) & 1) pos++; - rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_LSIG); + rthdr->it_present |= cpu_to_le32(BIT(IEEE80211_RADIOTAP_LSIG)); memcpy(pos, &lsig, sizeof(lsig)); pos += sizeof(lsig); } @@ -730,7 +735,8 @@ ieee80211_make_monitor_skb(struct ieee80211_local *local, * Need to make a copy and possibly remove radiotap header * and FCS from the original. */ - skb = skb_copy_expand(*origskb, needed_headroom, 0, GFP_ATOMIC); + skb = skb_copy_expand(*origskb, needed_headroom + NET_SKB_PAD, + 0, GFP_ATOMIC); if (!skb) return NULL; @@ -3206,6 +3212,68 @@ ieee80211_rx_h_mgmt_check(struct ieee80211_rx_data *rx) return RX_CONTINUE; } +static bool +ieee80211_process_rx_twt_action(struct ieee80211_rx_data *rx) +{ + struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)rx->skb->data; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); + struct ieee80211_sub_if_data *sdata = rx->sdata; + const struct ieee80211_sta_he_cap *hecap; + struct ieee80211_supported_band *sband; + + /* TWT actions are only supported in AP for the moment */ + if (sdata->vif.type != NL80211_IFTYPE_AP) + return false; + + if (!rx->local->ops->add_twt_setup) + return false; + + sband = rx->local->hw.wiphy->bands[status->band]; + hecap = ieee80211_get_he_iftype_cap(sband, + ieee80211_vif_type_p2p(&sdata->vif)); + if (!hecap) + return false; + + if (!(hecap->he_cap_elem.mac_cap_info[0] & + IEEE80211_HE_MAC_CAP0_TWT_RES)) + return false; + + if (!rx->sta) + return false; + + switch (mgmt->u.action.u.s1g.action_code) { + case WLAN_S1G_TWT_SETUP: { + struct ieee80211_twt_setup *twt; + + if (rx->skb->len < IEEE80211_MIN_ACTION_SIZE + + 1 + /* action code */ + sizeof(struct ieee80211_twt_setup) + + 2 /* TWT req_type agrt */) + break; + + twt = (void *)mgmt->u.action.u.s1g.variable; + if (twt->element_id != WLAN_EID_S1G_TWT) + break; + + if (rx->skb->len < IEEE80211_MIN_ACTION_SIZE + + 4 + /* action code + token + tlv */ + twt->length) + break; + + return true; /* queue the frame */ + } + case WLAN_S1G_TWT_TEARDOWN: + if (rx->skb->len < IEEE80211_MIN_ACTION_SIZE + 2) + break; + + return true; /* queue the frame */ + default: + break; + } + + return false; +} + static ieee80211_rx_result debug_noinline ieee80211_rx_h_action(struct ieee80211_rx_data *rx) { @@ -3485,6 +3553,17 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) !mesh_path_sel_is_hwmp(sdata)) break; goto queue; + case WLAN_CATEGORY_S1G: + switch (mgmt->u.action.u.s1g.action_code) { + case WLAN_S1G_TWT_SETUP: + case WLAN_S1G_TWT_TEARDOWN: + if (ieee80211_process_rx_twt_action(rx)) + goto queue; + break; + default: + break; + } + break; } return RX_CONTINUE; diff --git a/net/mac80211/s1g.c b/net/mac80211/s1g.c index c33f332b049a..7e35ab5b6166 100644 --- a/net/mac80211/s1g.c +++ b/net/mac80211/s1g.c @@ -6,6 +6,7 @@ #include <linux/ieee80211.h> #include <net/mac80211.h> #include "ieee80211_i.h" +#include "driver-ops.h" void ieee80211_s1g_sta_rate_init(struct sta_info *sta) { @@ -14,3 +15,182 @@ void ieee80211_s1g_sta_rate_init(struct sta_info *sta) sta->rx_stats.last_rate = STA_STATS_FIELD(TYPE, STA_STATS_RATE_TYPE_S1G); } + +bool ieee80211_s1g_is_twt_setup(struct sk_buff *skb) +{ + struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)skb->data; + + if (likely(!ieee80211_is_action(mgmt->frame_control))) + return false; + + if (likely(mgmt->u.action.category != WLAN_CATEGORY_S1G)) + return false; + + return mgmt->u.action.u.s1g.action_code == WLAN_S1G_TWT_SETUP; +} + +static void +ieee80211_s1g_send_twt_setup(struct ieee80211_sub_if_data *sdata, const u8 *da, + const u8 *bssid, struct ieee80211_twt_setup *twt) +{ + int len = IEEE80211_MIN_ACTION_SIZE + 4 + twt->length; + struct ieee80211_local *local = sdata->local; + struct ieee80211_mgmt *mgmt; + struct sk_buff *skb; + + skb = dev_alloc_skb(local->hw.extra_tx_headroom + len); + if (!skb) + return; + + skb_reserve(skb, local->hw.extra_tx_headroom); + mgmt = skb_put_zero(skb, len); + mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION); + memcpy(mgmt->da, da, ETH_ALEN); + memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); + memcpy(mgmt->bssid, bssid, ETH_ALEN); + + mgmt->u.action.category = WLAN_CATEGORY_S1G; + mgmt->u.action.u.s1g.action_code = WLAN_S1G_TWT_SETUP; + memcpy(mgmt->u.action.u.s1g.variable, twt, 3 + twt->length); + + IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT | + IEEE80211_TX_INTFL_MLME_CONN_TX | + IEEE80211_TX_CTL_REQ_TX_STATUS; + ieee80211_tx_skb(sdata, skb); +} + +static void +ieee80211_s1g_send_twt_teardown(struct ieee80211_sub_if_data *sdata, + const u8 *da, const u8 *bssid, u8 flowid) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_mgmt *mgmt; + struct sk_buff *skb; + u8 *id; + + skb = dev_alloc_skb(local->hw.extra_tx_headroom + + IEEE80211_MIN_ACTION_SIZE + 2); + if (!skb) + return; + + skb_reserve(skb, local->hw.extra_tx_headroom); + mgmt = skb_put_zero(skb, IEEE80211_MIN_ACTION_SIZE + 2); + mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION); + memcpy(mgmt->da, da, ETH_ALEN); + memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); + memcpy(mgmt->bssid, bssid, ETH_ALEN); + + mgmt->u.action.category = WLAN_CATEGORY_S1G; + mgmt->u.action.u.s1g.action_code = WLAN_S1G_TWT_TEARDOWN; + id = (u8 *)mgmt->u.action.u.s1g.variable; + *id = flowid; + + IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT | + IEEE80211_TX_CTL_REQ_TX_STATUS; + ieee80211_tx_skb(sdata, skb); +} + +static void +ieee80211_s1g_rx_twt_setup(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, struct sk_buff *skb) +{ + struct ieee80211_mgmt *mgmt = (void *)skb->data; + struct ieee80211_twt_setup *twt = (void *)mgmt->u.action.u.s1g.variable; + struct ieee80211_twt_params *twt_agrt = (void *)twt->params; + + twt_agrt->req_type &= cpu_to_le16(~IEEE80211_TWT_REQTYPE_REQUEST); + + /* broadcast TWT not supported yet */ + if (twt->control & IEEE80211_TWT_CONTROL_NEG_TYPE_BROADCAST) { + le16p_replace_bits(&twt_agrt->req_type, + TWT_SETUP_CMD_REJECT, + IEEE80211_TWT_REQTYPE_SETUP_CMD); + goto out; + } + + drv_add_twt_setup(sdata->local, sdata, &sta->sta, twt); +out: + ieee80211_s1g_send_twt_setup(sdata, mgmt->sa, sdata->vif.addr, twt); +} + +static void +ieee80211_s1g_rx_twt_teardown(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, struct sk_buff *skb) +{ + struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)skb->data; + + drv_twt_teardown_request(sdata->local, sdata, &sta->sta, + mgmt->u.action.u.s1g.variable[0]); +} + +static void +ieee80211_s1g_tx_twt_setup_fail(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, struct sk_buff *skb) +{ + struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)skb->data; + struct ieee80211_twt_setup *twt = (void *)mgmt->u.action.u.s1g.variable; + struct ieee80211_twt_params *twt_agrt = (void *)twt->params; + u8 flowid = le16_get_bits(twt_agrt->req_type, + IEEE80211_TWT_REQTYPE_FLOWID); + + drv_twt_teardown_request(sdata->local, sdata, &sta->sta, flowid); + + ieee80211_s1g_send_twt_teardown(sdata, mgmt->sa, sdata->vif.addr, + flowid); +} + +void ieee80211_s1g_rx_twt_action(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb) +{ + struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)skb->data; + struct ieee80211_local *local = sdata->local; + struct sta_info *sta; + + mutex_lock(&local->sta_mtx); + + sta = sta_info_get_bss(sdata, mgmt->sa); + if (!sta) + goto out; + + switch (mgmt->u.action.u.s1g.action_code) { + case WLAN_S1G_TWT_SETUP: + ieee80211_s1g_rx_twt_setup(sdata, sta, skb); + break; + case WLAN_S1G_TWT_TEARDOWN: + ieee80211_s1g_rx_twt_teardown(sdata, sta, skb); + break; + default: + break; + } + +out: + mutex_unlock(&local->sta_mtx); +} + +void ieee80211_s1g_status_twt_action(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb) +{ + struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)skb->data; + struct ieee80211_local *local = sdata->local; + struct sta_info *sta; + + mutex_lock(&local->sta_mtx); + + sta = sta_info_get_bss(sdata, mgmt->da); + if (!sta) + goto out; + + switch (mgmt->u.action.u.s1g.action_code) { + case WLAN_S1G_TWT_SETUP: + /* process failed twt setup frames */ + ieee80211_s1g_tx_twt_setup_fail(sdata, sta, skb); + break; + default: + break; + } + +out: + mutex_unlock(&local->sta_mtx); +} diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index a5505ee51229..2b5acb37587f 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -543,7 +543,7 @@ static int sta_info_insert_check(struct sta_info *sta) return -ENETDOWN; if (WARN_ON(ether_addr_equal(sta->sta.addr, sdata->vif.addr) || - is_multicast_ether_addr(sta->sta.addr))) + !is_valid_ether_addr(sta->sta.addr))) return -EINVAL; /* The RCU read lock is required by rhashtable due to diff --git a/net/mac80211/status.c b/net/mac80211/status.c index bae321ff77f6..f6f63a0b1b72 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -305,8 +305,8 @@ ieee80211_add_tx_radiotap_header(struct ieee80211_local *local, memset(rthdr, 0, rtap_len); rthdr->it_len = cpu_to_le16(rtap_len); rthdr->it_present = - cpu_to_le32((1 << IEEE80211_RADIOTAP_TX_FLAGS) | - (1 << IEEE80211_RADIOTAP_DATA_RETRIES)); + cpu_to_le32(BIT(IEEE80211_RADIOTAP_TX_FLAGS) | + BIT(IEEE80211_RADIOTAP_DATA_RETRIES)); pos = (unsigned char *)(rthdr + 1); /* @@ -331,7 +331,7 @@ ieee80211_add_tx_radiotap_header(struct ieee80211_local *local, sband->bitrates[info->status.rates[0].idx].bitrate; if (legacy_rate) { - rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_RATE); + rthdr->it_present |= cpu_to_le32(BIT(IEEE80211_RADIOTAP_RATE)); *pos = DIV_ROUND_UP(legacy_rate, 5 * (1 << shift)); /* padding for tx flags */ pos += 2; @@ -358,7 +358,7 @@ ieee80211_add_tx_radiotap_header(struct ieee80211_local *local, if (status && status->rate && (status->rate->flags & RATE_INFO_FLAGS_MCS)) { - rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_MCS); + rthdr->it_present |= cpu_to_le32(BIT(IEEE80211_RADIOTAP_MCS)); pos[0] = IEEE80211_RADIOTAP_MCS_HAVE_MCS | IEEE80211_RADIOTAP_MCS_HAVE_GI | IEEE80211_RADIOTAP_MCS_HAVE_BW; @@ -374,7 +374,7 @@ ieee80211_add_tx_radiotap_header(struct ieee80211_local *local, (IEEE80211_RADIOTAP_VHT_KNOWN_GI | IEEE80211_RADIOTAP_VHT_KNOWN_BANDWIDTH); - rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_VHT); + rthdr->it_present |= cpu_to_le32(BIT(IEEE80211_RADIOTAP_VHT)); /* required alignment from rthdr */ pos = (u8 *)rthdr + ALIGN(pos - (u8 *)rthdr, 2); @@ -419,7 +419,7 @@ ieee80211_add_tx_radiotap_header(struct ieee80211_local *local, (status->rate->flags & RATE_INFO_FLAGS_HE_MCS)) { struct ieee80211_radiotap_he *he; - rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_HE); + rthdr->it_present |= cpu_to_le32(BIT(IEEE80211_RADIOTAP_HE)); /* required alignment from rthdr */ pos = (u8 *)rthdr + ALIGN(pos - (u8 *)rthdr, 2); @@ -495,7 +495,7 @@ ieee80211_add_tx_radiotap_header(struct ieee80211_local *local, /* IEEE80211_RADIOTAP_MCS * IEEE80211_RADIOTAP_VHT */ if (info->status.rates[0].flags & IEEE80211_TX_RC_MCS) { - rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_MCS); + rthdr->it_present |= cpu_to_le32(BIT(IEEE80211_RADIOTAP_MCS)); pos[0] = IEEE80211_RADIOTAP_MCS_HAVE_MCS | IEEE80211_RADIOTAP_MCS_HAVE_GI | IEEE80211_RADIOTAP_MCS_HAVE_BW; @@ -512,7 +512,7 @@ ieee80211_add_tx_radiotap_header(struct ieee80211_local *local, (IEEE80211_RADIOTAP_VHT_KNOWN_GI | IEEE80211_RADIOTAP_VHT_KNOWN_BANDWIDTH); - rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_VHT); + rthdr->it_present |= cpu_to_le32(BIT(IEEE80211_RADIOTAP_VHT)); /* required alignment from rthdr */ pos = (u8 *)rthdr + ALIGN(pos - (u8 *)rthdr, 2); @@ -705,13 +705,26 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local, /* Check to see if packet is a TDLS teardown packet */ if (ieee80211_is_data(hdr->frame_control) && (ieee80211_get_tdls_action(skb, hdr_size) == - WLAN_TDLS_TEARDOWN)) + WLAN_TDLS_TEARDOWN)) { ieee80211_tdls_td_tx_handle(local, sdata, skb, info->flags); - else + } else if (ieee80211_s1g_is_twt_setup(skb)) { + if (!acked) { + struct sk_buff *qskb; + + qskb = skb_clone(skb, GFP_ATOMIC); + if (qskb) { + skb_queue_tail(&sdata->status_queue, + qskb); + ieee80211_queue_work(&local->hw, + &sdata->work); + } + } + } else { ieee80211_mgd_conn_tx_status(sdata, hdr->frame_control, acked); + } } rcu_read_unlock(); diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index f6ef15366938..9e8381bef7ed 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -2825,6 +2825,73 @@ DEFINE_EVENT(sta_flag_evt, drv_sta_set_decap_offload, TP_ARGS(local, sdata, sta, enabled) ); +TRACE_EVENT(drv_add_twt_setup, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sta *sta, + struct ieee80211_twt_setup *twt, + struct ieee80211_twt_params *twt_agrt), + + TP_ARGS(local, sta, twt, twt_agrt), + + TP_STRUCT__entry( + LOCAL_ENTRY + STA_ENTRY + __field(u8, dialog_token) + __field(u8, control) + __field(__le16, req_type) + __field(__le64, twt) + __field(u8, duration) + __field(__le16, mantissa) + __field(u8, channel) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + STA_ASSIGN; + __entry->dialog_token = twt->dialog_token; + __entry->control = twt->control; + __entry->req_type = twt_agrt->req_type; + __entry->twt = twt_agrt->twt; + __entry->duration = twt_agrt->min_twt_dur; + __entry->mantissa = twt_agrt->mantissa; + __entry->channel = twt_agrt->channel; + ), + + TP_printk( + LOCAL_PR_FMT STA_PR_FMT + " token:%d control:0x%02x req_type:0x%04x" + " twt:%llu duration:%d mantissa:%d channel:%d", + LOCAL_PR_ARG, STA_PR_ARG, __entry->dialog_token, + __entry->control, le16_to_cpu(__entry->req_type), + le64_to_cpu(__entry->twt), __entry->duration, + le16_to_cpu(__entry->mantissa), __entry->channel + ) +); + +TRACE_EVENT(drv_twt_teardown_request, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sta *sta, u8 flowid), + + TP_ARGS(local, sta, flowid), + + TP_STRUCT__entry( + LOCAL_ENTRY + STA_ENTRY + __field(u8, flowid) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + STA_ASSIGN; + __entry->flowid = flowid; + ), + + TP_printk( + LOCAL_PR_FMT STA_PR_FMT " flowid:%d", + LOCAL_PR_ARG, STA_PR_ARG, __entry->flowid + ) +); + #endif /* !__MAC80211_DRIVER_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index e96981144358..2d1193ed3eb5 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1147,6 +1147,29 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx, return queued; } +static void +ieee80211_aggr_check(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, + struct sk_buff *skb) +{ + struct rate_control_ref *ref = sdata->local->rate_ctrl; + u16 tid; + + if (!ref || !(ref->ops->capa & RATE_CTRL_CAPA_AMPDU_TRIGGER)) + return; + + if (!sta || !sta->sta.ht_cap.ht_supported || + !sta->sta.wme || skb_get_queue_mapping(skb) == IEEE80211_AC_VO || + skb->protocol == sdata->control_port_protocol) + return; + + tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK; + if (likely(sta->ampdu_mlme.tid_tx[tid])) + return; + + ieee80211_start_tx_ba_session(&sta->sta, tid, 0); +} + /* * initialises @tx * pass %NULL for the station if unknown, a valid pointer if known @@ -1160,6 +1183,7 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; struct ieee80211_hdr *hdr; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + bool aggr_check = false; int tid; memset(tx, 0, sizeof(*tx)); @@ -1188,8 +1212,10 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, } else if (tx->sdata->control_port_protocol == tx->skb->protocol) { tx->sta = sta_info_get_bss(sdata, hdr->addr1); } - if (!tx->sta && !is_multicast_ether_addr(hdr->addr1)) + if (!tx->sta && !is_multicast_ether_addr(hdr->addr1)) { tx->sta = sta_info_get(sdata, hdr->addr1); + aggr_check = true; + } } if (tx->sta && ieee80211_is_data_qos(hdr->frame_control) && @@ -1199,8 +1225,12 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, struct tid_ampdu_tx *tid_tx; tid = ieee80211_get_tid(hdr); - tid_tx = rcu_dereference(tx->sta->ampdu_mlme.tid_tx[tid]); + if (!tid_tx && aggr_check) { + ieee80211_aggr_check(sdata, tx->sta, skb); + tid_tx = rcu_dereference(tx->sta->ampdu_mlme.tid_tx[tid]); + } + if (tid_tx) { bool queued; @@ -3212,7 +3242,9 @@ static bool ieee80211_amsdu_prepare_head(struct ieee80211_sub_if_data *sdata, if (info->control.flags & IEEE80211_TX_CTRL_AMSDU) return true; - if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(*amsdu_hdr))) + if (!ieee80211_amsdu_realloc_pad(local, skb, + sizeof(*amsdu_hdr) + + local->hw.extra_tx_headroom)) return false; data = skb_push(skb, sizeof(*amsdu_hdr)); @@ -4120,29 +4152,6 @@ void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac) } EXPORT_SYMBOL(ieee80211_txq_schedule_start); -static void -ieee80211_aggr_check(struct ieee80211_sub_if_data *sdata, - struct sta_info *sta, - struct sk_buff *skb) -{ - struct rate_control_ref *ref = sdata->local->rate_ctrl; - u16 tid; - - if (!ref || !(ref->ops->capa & RATE_CTRL_CAPA_AMPDU_TRIGGER)) - return; - - if (!sta || !sta->sta.ht_cap.ht_supported || - !sta->sta.wme || skb_get_queue_mapping(skb) == IEEE80211_AC_VO || - skb->protocol == sdata->control_port_protocol) - return; - - tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK; - if (likely(sta->ampdu_mlme.tid_tx[tid])) - return; - - ieee80211_start_tx_ba_session(&sta->sta, tid, 0); -} - void __ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev, u32 info_flags, @@ -4775,11 +4784,11 @@ static int ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata, static void ieee80211_set_beacon_cntdwn(struct ieee80211_sub_if_data *sdata, struct beacon_data *beacon) { + u8 *beacon_data, count, max_count = 1; struct probe_resp *resp; - u8 *beacon_data; size_t beacon_data_len; + u16 *bcn_offsets; int i; - u8 count = beacon->cntdwn_current_counter; switch (sdata->vif.type) { case NL80211_IFTYPE_AP: @@ -4799,21 +4808,27 @@ static void ieee80211_set_beacon_cntdwn(struct ieee80211_sub_if_data *sdata, } rcu_read_lock(); - for (i = 0; i < IEEE80211_MAX_CNTDWN_COUNTERS_NUM; ++i) { - resp = rcu_dereference(sdata->u.ap.probe_resp); + resp = rcu_dereference(sdata->u.ap.probe_resp); + + bcn_offsets = beacon->cntdwn_counter_offsets; + count = beacon->cntdwn_current_counter; + if (sdata->vif.csa_active) + max_count = IEEE80211_MAX_CNTDWN_COUNTERS_NUM; - if (beacon->cntdwn_counter_offsets[i]) { - if (WARN_ON_ONCE(beacon->cntdwn_counter_offsets[i] >= - beacon_data_len)) { + for (i = 0; i < max_count; ++i) { + if (bcn_offsets[i]) { + if (WARN_ON_ONCE(bcn_offsets[i] >= beacon_data_len)) { rcu_read_unlock(); return; } - - beacon_data[beacon->cntdwn_counter_offsets[i]] = count; + beacon_data[bcn_offsets[i]] = count; } - if (sdata->vif.type == NL80211_IFTYPE_AP && resp) - resp->data[resp->cntdwn_counter_offsets[i]] = count; + if (sdata->vif.type == NL80211_IFTYPE_AP && resp) { + u16 *resp_offsets = resp->cntdwn_counter_offsets; + + resp->data[resp_offsets[i]] = count; + } } rcu_read_unlock(); } @@ -5023,6 +5038,7 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, if (offs) { offs->tim_offset = beacon->head_len; offs->tim_length = skb->len - beacon->head_len; + offs->cntdwn_counter_offs[0] = beacon->cntdwn_counter_offsets[0]; /* for AP the csa offsets are from tail */ csa_off_base = skb->len; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 05e96212b104..49cb96d25169 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1336,6 +1336,18 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, elems->rsnx = pos; elems->rsnx_len = elen; break; + case WLAN_EID_TX_POWER_ENVELOPE: + if (elen < 1 || + elen > sizeof(struct ieee80211_tx_pwr_env)) + break; + + if (elems->tx_pwr_env_num >= ARRAY_SIZE(elems->tx_pwr_env)) + break; + + elems->tx_pwr_env[elems->tx_pwr_env_num] = (void *)pos; + elems->tx_pwr_env_len[elems->tx_pwr_env_num] = elen; + elems->tx_pwr_env_num++; + break; case WLAN_EID_EXTENSION: ieee80211_parse_extension_element(calc_crc ? &crc : NULL, diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c index 1cf5ac09edcb..323d3d2d986f 100644 --- a/net/mac802154/iface.c +++ b/net/mac802154/iface.c @@ -617,7 +617,7 @@ ieee802154_if_add(struct ieee802154_local *local, const char *name, { struct net_device *ndev = NULL; struct ieee802154_sub_if_data *sdata = NULL; - int ret = -ENOMEM; + int ret; ASSERT_RTNL(); diff --git a/net/mctp/Kconfig b/net/mctp/Kconfig new file mode 100644 index 000000000000..2cdf3d0a28c9 --- /dev/null +++ b/net/mctp/Kconfig @@ -0,0 +1,13 @@ + +menuconfig MCTP + depends on NET + tristate "MCTP core protocol support" + help + Management Component Transport Protocol (MCTP) is an in-system + protocol for communicating between management controllers and + their managed devices (peripherals, host processors, etc.). The + protocol is defined by DMTF specification DSP0236. + + This option enables core MCTP support. For communicating with other + devices, you'll want to enable a driver for a specific hardware + channel. diff --git a/net/mctp/Makefile b/net/mctp/Makefile new file mode 100644 index 000000000000..0171333384d7 --- /dev/null +++ b/net/mctp/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_MCTP) += mctp.o +mctp-objs := af_mctp.o device.o route.o neigh.o diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c new file mode 100644 index 000000000000..a9526ac29dff --- /dev/null +++ b/net/mctp/af_mctp.c @@ -0,0 +1,395 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Management Component Transport Protocol (MCTP) + * + * Copyright (c) 2021 Code Construct + * Copyright (c) 2021 Google + */ + +#include <linux/if_arp.h> +#include <linux/net.h> +#include <linux/mctp.h> +#include <linux/module.h> +#include <linux/socket.h> + +#include <net/mctp.h> +#include <net/mctpdevice.h> +#include <net/sock.h> + +/* socket implementation */ + +static int mctp_release(struct socket *sock) +{ + struct sock *sk = sock->sk; + + if (sk) { + sock->sk = NULL; + sk->sk_prot->close(sk, 0); + } + + return 0; +} + +static int mctp_bind(struct socket *sock, struct sockaddr *addr, int addrlen) +{ + struct sock *sk = sock->sk; + struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); + struct sockaddr_mctp *smctp; + int rc; + + if (addrlen < sizeof(*smctp)) + return -EINVAL; + + if (addr->sa_family != AF_MCTP) + return -EAFNOSUPPORT; + + if (!capable(CAP_NET_BIND_SERVICE)) + return -EACCES; + + /* it's a valid sockaddr for MCTP, cast and do protocol checks */ + smctp = (struct sockaddr_mctp *)addr; + + lock_sock(sk); + + /* TODO: allow rebind */ + if (sk_hashed(sk)) { + rc = -EADDRINUSE; + goto out_release; + } + msk->bind_net = smctp->smctp_network; + msk->bind_addr = smctp->smctp_addr.s_addr; + msk->bind_type = smctp->smctp_type & 0x7f; /* ignore the IC bit */ + + rc = sk->sk_prot->hash(sk); + +out_release: + release_sock(sk); + + return rc; +} + +static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) +{ + DECLARE_SOCKADDR(struct sockaddr_mctp *, addr, msg->msg_name); + const int hlen = MCTP_HEADER_MAXLEN + sizeof(struct mctp_hdr); + int rc, addrlen = msg->msg_namelen; + struct sock *sk = sock->sk; + struct mctp_skb_cb *cb; + struct mctp_route *rt; + struct sk_buff *skb; + + if (addr) { + if (addrlen < sizeof(struct sockaddr_mctp)) + return -EINVAL; + if (addr->smctp_family != AF_MCTP) + return -EINVAL; + if (addr->smctp_tag & ~(MCTP_TAG_MASK | MCTP_TAG_OWNER)) + return -EINVAL; + + } else { + /* TODO: connect()ed sockets */ + return -EDESTADDRREQ; + } + + if (!capable(CAP_NET_RAW)) + return -EACCES; + + if (addr->smctp_network == MCTP_NET_ANY) + addr->smctp_network = mctp_default_net(sock_net(sk)); + + rt = mctp_route_lookup(sock_net(sk), addr->smctp_network, + addr->smctp_addr.s_addr); + if (!rt) + return -EHOSTUNREACH; + + skb = sock_alloc_send_skb(sk, hlen + 1 + len, + msg->msg_flags & MSG_DONTWAIT, &rc); + if (!skb) + return rc; + + skb_reserve(skb, hlen); + + /* set type as fist byte in payload */ + *(u8 *)skb_put(skb, 1) = addr->smctp_type; + + rc = memcpy_from_msg((void *)skb_put(skb, len), msg, len); + if (rc < 0) { + kfree_skb(skb); + return rc; + } + + /* set up cb */ + cb = __mctp_cb(skb); + cb->net = addr->smctp_network; + + rc = mctp_local_output(sk, rt, skb, addr->smctp_addr.s_addr, + addr->smctp_tag); + + return rc ? : len; +} + +static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) +{ + DECLARE_SOCKADDR(struct sockaddr_mctp *, addr, msg->msg_name); + struct sock *sk = sock->sk; + struct sk_buff *skb; + size_t msglen; + u8 type; + int rc; + + if (flags & ~(MSG_DONTWAIT | MSG_TRUNC | MSG_PEEK)) + return -EOPNOTSUPP; + + skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &rc); + if (!skb) + return rc; + + if (!skb->len) { + rc = 0; + goto out_free; + } + + /* extract message type, remove from data */ + type = *((u8 *)skb->data); + msglen = skb->len - 1; + + if (len < msglen) + msg->msg_flags |= MSG_TRUNC; + else + len = msglen; + + rc = skb_copy_datagram_msg(skb, 1, msg, len); + if (rc < 0) + goto out_free; + + sock_recv_ts_and_drops(msg, sk, skb); + + if (addr) { + struct mctp_skb_cb *cb = mctp_cb(skb); + /* TODO: expand mctp_skb_cb for header fields? */ + struct mctp_hdr *hdr = mctp_hdr(skb); + + addr = msg->msg_name; + addr->smctp_family = AF_MCTP; + addr->smctp_network = cb->net; + addr->smctp_addr.s_addr = hdr->src; + addr->smctp_type = type; + addr->smctp_tag = hdr->flags_seq_tag & + (MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO); + msg->msg_namelen = sizeof(*addr); + } + + rc = len; + + if (flags & MSG_TRUNC) + rc = msglen; + +out_free: + skb_free_datagram(sk, skb); + return rc; +} + +static int mctp_setsockopt(struct socket *sock, int level, int optname, + sockptr_t optval, unsigned int optlen) +{ + return -EINVAL; +} + +static int mctp_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) +{ + return -EINVAL; +} + +static const struct proto_ops mctp_dgram_ops = { + .family = PF_MCTP, + .release = mctp_release, + .bind = mctp_bind, + .connect = sock_no_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .getname = sock_no_getname, + .poll = datagram_poll, + .ioctl = sock_no_ioctl, + .gettstamp = sock_gettstamp, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .setsockopt = mctp_setsockopt, + .getsockopt = mctp_getsockopt, + .sendmsg = mctp_sendmsg, + .recvmsg = mctp_recvmsg, + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +}; + +static int mctp_sk_init(struct sock *sk) +{ + struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); + + INIT_HLIST_HEAD(&msk->keys); + return 0; +} + +static void mctp_sk_close(struct sock *sk, long timeout) +{ + sk_common_release(sk); +} + +static int mctp_sk_hash(struct sock *sk) +{ + struct net *net = sock_net(sk); + + mutex_lock(&net->mctp.bind_lock); + sk_add_node_rcu(sk, &net->mctp.binds); + mutex_unlock(&net->mctp.bind_lock); + + return 0; +} + +static void mctp_sk_unhash(struct sock *sk) +{ + struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); + struct net *net = sock_net(sk); + struct mctp_sk_key *key; + struct hlist_node *tmp; + unsigned long flags; + + /* remove from any type-based binds */ + mutex_lock(&net->mctp.bind_lock); + sk_del_node_init_rcu(sk); + mutex_unlock(&net->mctp.bind_lock); + + /* remove tag allocations */ + spin_lock_irqsave(&net->mctp.keys_lock, flags); + hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) { + hlist_del_rcu(&key->sklist); + hlist_del_rcu(&key->hlist); + + spin_lock(&key->reasm_lock); + if (key->reasm_head) + kfree_skb(key->reasm_head); + key->reasm_head = NULL; + key->reasm_dead = true; + spin_unlock(&key->reasm_lock); + + kfree_rcu(key, rcu); + } + spin_unlock_irqrestore(&net->mctp.keys_lock, flags); + + synchronize_rcu(); +} + +static struct proto mctp_proto = { + .name = "MCTP", + .owner = THIS_MODULE, + .obj_size = sizeof(struct mctp_sock), + .init = mctp_sk_init, + .close = mctp_sk_close, + .hash = mctp_sk_hash, + .unhash = mctp_sk_unhash, +}; + +static int mctp_pf_create(struct net *net, struct socket *sock, + int protocol, int kern) +{ + const struct proto_ops *ops; + struct proto *proto; + struct sock *sk; + int rc; + + if (protocol) + return -EPROTONOSUPPORT; + + /* only datagram sockets are supported */ + if (sock->type != SOCK_DGRAM) + return -ESOCKTNOSUPPORT; + + proto = &mctp_proto; + ops = &mctp_dgram_ops; + + sock->state = SS_UNCONNECTED; + sock->ops = ops; + + sk = sk_alloc(net, PF_MCTP, GFP_KERNEL, proto, kern); + if (!sk) + return -ENOMEM; + + sock_init_data(sock, sk); + + rc = 0; + if (sk->sk_prot->init) + rc = sk->sk_prot->init(sk); + + if (rc) + goto err_sk_put; + + return 0; + +err_sk_put: + sock_orphan(sk); + sock_put(sk); + return rc; +} + +static struct net_proto_family mctp_pf = { + .family = PF_MCTP, + .create = mctp_pf_create, + .owner = THIS_MODULE, +}; + +static __init int mctp_init(void) +{ + int rc; + + /* ensure our uapi tag definitions match the header format */ + BUILD_BUG_ON(MCTP_TAG_OWNER != MCTP_HDR_FLAG_TO); + BUILD_BUG_ON(MCTP_TAG_MASK != MCTP_HDR_TAG_MASK); + + pr_info("mctp: management component transport protocol core\n"); + + rc = sock_register(&mctp_pf); + if (rc) + return rc; + + rc = proto_register(&mctp_proto, 0); + if (rc) + goto err_unreg_sock; + + rc = mctp_routes_init(); + if (rc) + goto err_unreg_proto; + + rc = mctp_neigh_init(); + if (rc) + goto err_unreg_proto; + + mctp_device_init(); + + return 0; + +err_unreg_proto: + proto_unregister(&mctp_proto); +err_unreg_sock: + sock_unregister(PF_MCTP); + + return rc; +} + +static __exit void mctp_exit(void) +{ + mctp_device_exit(); + mctp_neigh_exit(); + mctp_routes_exit(); + proto_unregister(&mctp_proto); + sock_unregister(PF_MCTP); +} + +module_init(mctp_init); +module_exit(mctp_exit); + +MODULE_DESCRIPTION("MCTP core"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Jeremy Kerr <jk@codeconstruct.com.au>"); + +MODULE_ALIAS_NETPROTO(PF_MCTP); diff --git a/net/mctp/device.c b/net/mctp/device.c new file mode 100644 index 000000000000..b9f38e765f61 --- /dev/null +++ b/net/mctp/device.c @@ -0,0 +1,423 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Management Component Transport Protocol (MCTP) - device implementation. + * + * Copyright (c) 2021 Code Construct + * Copyright (c) 2021 Google + */ + +#include <linux/if_link.h> +#include <linux/mctp.h> +#include <linux/netdevice.h> +#include <linux/rcupdate.h> +#include <linux/rtnetlink.h> + +#include <net/addrconf.h> +#include <net/netlink.h> +#include <net/mctp.h> +#include <net/mctpdevice.h> +#include <net/sock.h> + +struct mctp_dump_cb { + int h; + int idx; + size_t a_idx; +}; + +/* unlocked: caller must hold rcu_read_lock */ +struct mctp_dev *__mctp_dev_get(const struct net_device *dev) +{ + return rcu_dereference(dev->mctp_ptr); +} + +struct mctp_dev *mctp_dev_get_rtnl(const struct net_device *dev) +{ + return rtnl_dereference(dev->mctp_ptr); +} + +static void mctp_dev_destroy(struct mctp_dev *mdev) +{ + struct net_device *dev = mdev->dev; + + dev_put(dev); + kfree_rcu(mdev, rcu); +} + +static int mctp_fill_addrinfo(struct sk_buff *skb, struct netlink_callback *cb, + struct mctp_dev *mdev, mctp_eid_t eid) +{ + struct ifaddrmsg *hdr; + struct nlmsghdr *nlh; + + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + RTM_NEWADDR, sizeof(*hdr), NLM_F_MULTI); + if (!nlh) + return -EMSGSIZE; + + hdr = nlmsg_data(nlh); + hdr->ifa_family = AF_MCTP; + hdr->ifa_prefixlen = 0; + hdr->ifa_flags = 0; + hdr->ifa_scope = 0; + hdr->ifa_index = mdev->dev->ifindex; + + if (nla_put_u8(skb, IFA_LOCAL, eid)) + goto cancel; + + if (nla_put_u8(skb, IFA_ADDRESS, eid)) + goto cancel; + + nlmsg_end(skb, nlh); + + return 0; + +cancel: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static int mctp_dump_dev_addrinfo(struct mctp_dev *mdev, struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct mctp_dump_cb *mcb = (void *)cb->ctx; + int rc = 0; + + for (; mcb->a_idx < mdev->num_addrs; mcb->a_idx++) { + rc = mctp_fill_addrinfo(skb, cb, mdev, mdev->addrs[mcb->a_idx]); + if (rc < 0) + break; + } + + return rc; +} + +static int mctp_dump_addrinfo(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct mctp_dump_cb *mcb = (void *)cb->ctx; + struct net *net = sock_net(skb->sk); + struct hlist_head *head; + struct net_device *dev; + struct ifaddrmsg *hdr; + struct mctp_dev *mdev; + int ifindex; + int idx, rc; + + hdr = nlmsg_data(cb->nlh); + // filter by ifindex if requested + ifindex = hdr->ifa_index; + + rcu_read_lock(); + for (; mcb->h < NETDEV_HASHENTRIES; mcb->h++, mcb->idx = 0) { + idx = 0; + head = &net->dev_index_head[mcb->h]; + hlist_for_each_entry_rcu(dev, head, index_hlist) { + if (idx >= mcb->idx && + (ifindex == 0 || ifindex == dev->ifindex)) { + mdev = __mctp_dev_get(dev); + if (mdev) { + rc = mctp_dump_dev_addrinfo(mdev, + skb, cb); + // Error indicates full buffer, this + // callback will get retried. + if (rc < 0) + goto out; + } + } + idx++; + // reset for next iteration + mcb->a_idx = 0; + } + } +out: + rcu_read_unlock(); + mcb->idx = idx; + + return skb->len; +} + +static const struct nla_policy ifa_mctp_policy[IFA_MAX + 1] = { + [IFA_ADDRESS] = { .type = NLA_U8 }, + [IFA_LOCAL] = { .type = NLA_U8 }, +}; + +static int mctp_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(skb->sk); + struct nlattr *tb[IFA_MAX + 1]; + struct net_device *dev; + struct mctp_addr *addr; + struct mctp_dev *mdev; + struct ifaddrmsg *ifm; + unsigned long flags; + u8 *tmp_addrs; + int rc; + + rc = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_mctp_policy, + extack); + if (rc < 0) + return rc; + + ifm = nlmsg_data(nlh); + + if (tb[IFA_LOCAL]) + addr = nla_data(tb[IFA_LOCAL]); + else if (tb[IFA_ADDRESS]) + addr = nla_data(tb[IFA_ADDRESS]); + else + return -EINVAL; + + /* find device */ + dev = __dev_get_by_index(net, ifm->ifa_index); + if (!dev) + return -ENODEV; + + mdev = mctp_dev_get_rtnl(dev); + if (!mdev) + return -ENODEV; + + if (!mctp_address_ok(addr->s_addr)) + return -EINVAL; + + /* Prevent duplicates. Under RTNL so don't need to lock for reading */ + if (memchr(mdev->addrs, addr->s_addr, mdev->num_addrs)) + return -EEXIST; + + tmp_addrs = kmalloc(mdev->num_addrs + 1, GFP_KERNEL); + if (!tmp_addrs) + return -ENOMEM; + memcpy(tmp_addrs, mdev->addrs, mdev->num_addrs); + tmp_addrs[mdev->num_addrs] = addr->s_addr; + + /* Lock to write */ + spin_lock_irqsave(&mdev->addrs_lock, flags); + mdev->num_addrs++; + swap(mdev->addrs, tmp_addrs); + spin_unlock_irqrestore(&mdev->addrs_lock, flags); + + kfree(tmp_addrs); + + mctp_route_add_local(mdev, addr->s_addr); + + return 0; +} + +static int mctp_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(skb->sk); + struct nlattr *tb[IFA_MAX + 1]; + struct net_device *dev; + struct mctp_addr *addr; + struct mctp_dev *mdev; + struct ifaddrmsg *ifm; + unsigned long flags; + u8 *pos; + int rc; + + rc = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_mctp_policy, + extack); + if (rc < 0) + return rc; + + ifm = nlmsg_data(nlh); + + if (tb[IFA_LOCAL]) + addr = nla_data(tb[IFA_LOCAL]); + else if (tb[IFA_ADDRESS]) + addr = nla_data(tb[IFA_ADDRESS]); + else + return -EINVAL; + + /* find device */ + dev = __dev_get_by_index(net, ifm->ifa_index); + if (!dev) + return -ENODEV; + + mdev = mctp_dev_get_rtnl(dev); + if (!mdev) + return -ENODEV; + + pos = memchr(mdev->addrs, addr->s_addr, mdev->num_addrs); + if (!pos) + return -ENOENT; + + rc = mctp_route_remove_local(mdev, addr->s_addr); + // we can ignore -ENOENT in the case a route was already removed + if (rc < 0 && rc != -ENOENT) + return rc; + + spin_lock_irqsave(&mdev->addrs_lock, flags); + memmove(pos, pos + 1, mdev->num_addrs - 1 - (pos - mdev->addrs)); + mdev->num_addrs--; + spin_unlock_irqrestore(&mdev->addrs_lock, flags); + + return 0; +} + +static struct mctp_dev *mctp_add_dev(struct net_device *dev) +{ + struct mctp_dev *mdev; + + ASSERT_RTNL(); + + mdev = kzalloc(sizeof(*mdev), GFP_KERNEL); + if (!mdev) + return ERR_PTR(-ENOMEM); + + spin_lock_init(&mdev->addrs_lock); + + mdev->net = mctp_default_net(dev_net(dev)); + + /* associate to net_device */ + rcu_assign_pointer(dev->mctp_ptr, mdev); + dev_hold(dev); + mdev->dev = dev; + + return mdev; +} + +static int mctp_fill_link_af(struct sk_buff *skb, + const struct net_device *dev, u32 ext_filter_mask) +{ + struct mctp_dev *mdev; + + mdev = mctp_dev_get_rtnl(dev); + if (!mdev) + return -ENODATA; + if (nla_put_u32(skb, IFLA_MCTP_NET, mdev->net)) + return -EMSGSIZE; + return 0; +} + +static size_t mctp_get_link_af_size(const struct net_device *dev, + u32 ext_filter_mask) +{ + struct mctp_dev *mdev; + unsigned int ret; + + /* caller holds RCU */ + mdev = __mctp_dev_get(dev); + if (!mdev) + return 0; + ret = nla_total_size(4); /* IFLA_MCTP_NET */ + return ret; +} + +static const struct nla_policy ifla_af_mctp_policy[IFLA_MCTP_MAX + 1] = { + [IFLA_MCTP_NET] = { .type = NLA_U32 }, +}; + +static int mctp_set_link_af(struct net_device *dev, const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_MCTP_MAX + 1]; + struct mctp_dev *mdev; + int rc; + + rc = nla_parse_nested(tb, IFLA_MCTP_MAX, attr, ifla_af_mctp_policy, + NULL); + if (rc) + return rc; + + mdev = mctp_dev_get_rtnl(dev); + if (!mdev) + return 0; + + if (tb[IFLA_MCTP_NET]) + WRITE_ONCE(mdev->net, nla_get_u32(tb[IFLA_MCTP_NET])); + + return 0; +} + +static void mctp_unregister(struct net_device *dev) +{ + struct mctp_dev *mdev; + + mdev = mctp_dev_get_rtnl(dev); + + if (!mdev) + return; + + RCU_INIT_POINTER(mdev->dev->mctp_ptr, NULL); + + mctp_route_remove_dev(mdev); + mctp_neigh_remove_dev(mdev); + kfree(mdev->addrs); + + mctp_dev_destroy(mdev); +} + +static int mctp_register(struct net_device *dev) +{ + struct mctp_dev *mdev; + + /* Already registered? */ + if (rtnl_dereference(dev->mctp_ptr)) + return 0; + + /* only register specific types; MCTP-specific and loopback for now */ + if (dev->type != ARPHRD_MCTP && dev->type != ARPHRD_LOOPBACK) + return 0; + + mdev = mctp_add_dev(dev); + if (IS_ERR(mdev)) + return PTR_ERR(mdev); + + return 0; +} + +static int mctp_dev_notify(struct notifier_block *this, unsigned long event, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + int rc; + + switch (event) { + case NETDEV_REGISTER: + rc = mctp_register(dev); + if (rc) + return notifier_from_errno(rc); + break; + case NETDEV_UNREGISTER: + mctp_unregister(dev); + break; + } + + return NOTIFY_OK; +} + +static struct rtnl_af_ops mctp_af_ops = { + .family = AF_MCTP, + .fill_link_af = mctp_fill_link_af, + .get_link_af_size = mctp_get_link_af_size, + .set_link_af = mctp_set_link_af, +}; + +static struct notifier_block mctp_dev_nb = { + .notifier_call = mctp_dev_notify, + .priority = ADDRCONF_NOTIFY_PRIORITY, +}; + +void __init mctp_device_init(void) +{ + register_netdevice_notifier(&mctp_dev_nb); + + rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_GETADDR, + NULL, mctp_dump_addrinfo, 0); + rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_NEWADDR, + mctp_rtm_newaddr, NULL, 0); + rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_DELADDR, + mctp_rtm_deladdr, NULL, 0); + rtnl_af_register(&mctp_af_ops); +} + +void __exit mctp_device_exit(void) +{ + rtnl_af_unregister(&mctp_af_ops); + rtnl_unregister(PF_MCTP, RTM_DELADDR); + rtnl_unregister(PF_MCTP, RTM_NEWADDR); + rtnl_unregister(PF_MCTP, RTM_GETADDR); + + unregister_netdevice_notifier(&mctp_dev_nb); +} diff --git a/net/mctp/neigh.c b/net/mctp/neigh.c new file mode 100644 index 000000000000..90ed2f02d1fb --- /dev/null +++ b/net/mctp/neigh.c @@ -0,0 +1,342 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Management Component Transport Protocol (MCTP) - routing + * implementation. + * + * This is currently based on a simple routing table, with no dst cache. The + * number of routes should stay fairly small, so the lookup cost is small. + * + * Copyright (c) 2021 Code Construct + * Copyright (c) 2021 Google + */ + +#include <linux/idr.h> +#include <linux/mctp.h> +#include <linux/netdevice.h> +#include <linux/rtnetlink.h> +#include <linux/skbuff.h> + +#include <net/mctp.h> +#include <net/mctpdevice.h> +#include <net/netlink.h> +#include <net/sock.h> + +static int mctp_neigh_add(struct mctp_dev *mdev, mctp_eid_t eid, + enum mctp_neigh_source source, + size_t lladdr_len, const void *lladdr) +{ + struct net *net = dev_net(mdev->dev); + struct mctp_neigh *neigh; + int rc; + + mutex_lock(&net->mctp.neigh_lock); + if (mctp_neigh_lookup(mdev, eid, NULL) == 0) { + rc = -EEXIST; + goto out; + } + + if (lladdr_len > sizeof(neigh->ha)) { + rc = -EINVAL; + goto out; + } + + neigh = kzalloc(sizeof(*neigh), GFP_KERNEL); + if (!neigh) { + rc = -ENOMEM; + goto out; + } + INIT_LIST_HEAD(&neigh->list); + neigh->dev = mdev; + dev_hold(neigh->dev->dev); + neigh->eid = eid; + neigh->source = source; + memcpy(neigh->ha, lladdr, lladdr_len); + + list_add_rcu(&neigh->list, &net->mctp.neighbours); + rc = 0; +out: + mutex_unlock(&net->mctp.neigh_lock); + return rc; +} + +static void __mctp_neigh_free(struct rcu_head *rcu) +{ + struct mctp_neigh *neigh = container_of(rcu, struct mctp_neigh, rcu); + + dev_put(neigh->dev->dev); + kfree(neigh); +} + +/* Removes all neighbour entries referring to a device */ +void mctp_neigh_remove_dev(struct mctp_dev *mdev) +{ + struct net *net = dev_net(mdev->dev); + struct mctp_neigh *neigh, *tmp; + + mutex_lock(&net->mctp.neigh_lock); + list_for_each_entry_safe(neigh, tmp, &net->mctp.neighbours, list) { + if (neigh->dev == mdev) { + list_del_rcu(&neigh->list); + /* TODO: immediate RTM_DELNEIGH */ + call_rcu(&neigh->rcu, __mctp_neigh_free); + } + } + + mutex_unlock(&net->mctp.neigh_lock); +} + +// TODO: add a "source" flag so netlink can only delete static neighbours? +static int mctp_neigh_remove(struct mctp_dev *mdev, mctp_eid_t eid) +{ + struct net *net = dev_net(mdev->dev); + struct mctp_neigh *neigh, *tmp; + bool dropped = false; + + mutex_lock(&net->mctp.neigh_lock); + list_for_each_entry_safe(neigh, tmp, &net->mctp.neighbours, list) { + if (neigh->dev == mdev && neigh->eid == eid) { + list_del_rcu(&neigh->list); + /* TODO: immediate RTM_DELNEIGH */ + call_rcu(&neigh->rcu, __mctp_neigh_free); + dropped = true; + } + } + + mutex_unlock(&net->mctp.neigh_lock); + return dropped ? 0 : -ENOENT; +} + +static const struct nla_policy nd_mctp_policy[NDA_MAX + 1] = { + [NDA_DST] = { .type = NLA_U8 }, + [NDA_LLADDR] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN }, +}; + +static int mctp_rtm_newneigh(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(skb->sk); + struct net_device *dev; + struct mctp_dev *mdev; + struct ndmsg *ndm; + struct nlattr *tb[NDA_MAX + 1]; + int rc; + mctp_eid_t eid; + void *lladdr; + int lladdr_len; + + rc = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, nd_mctp_policy, + extack); + if (rc < 0) { + NL_SET_ERR_MSG(extack, "lladdr too large?"); + return rc; + } + + if (!tb[NDA_DST]) { + NL_SET_ERR_MSG(extack, "Neighbour EID must be specified"); + return -EINVAL; + } + + if (!tb[NDA_LLADDR]) { + NL_SET_ERR_MSG(extack, "Neighbour lladdr must be specified"); + return -EINVAL; + } + + eid = nla_get_u8(tb[NDA_DST]); + if (!mctp_address_ok(eid)) { + NL_SET_ERR_MSG(extack, "Invalid neighbour EID"); + return -EINVAL; + } + + lladdr = nla_data(tb[NDA_LLADDR]); + lladdr_len = nla_len(tb[NDA_LLADDR]); + + ndm = nlmsg_data(nlh); + + dev = __dev_get_by_index(net, ndm->ndm_ifindex); + if (!dev) + return -ENODEV; + + mdev = mctp_dev_get_rtnl(dev); + if (!mdev) + return -ENODEV; + + if (lladdr_len != dev->addr_len) { + NL_SET_ERR_MSG(extack, "Wrong lladdr length"); + return -EINVAL; + } + + return mctp_neigh_add(mdev, eid, MCTP_NEIGH_STATIC, + lladdr_len, lladdr); +} + +static int mctp_rtm_delneigh(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(skb->sk); + struct nlattr *tb[NDA_MAX + 1]; + struct net_device *dev; + struct mctp_dev *mdev; + struct ndmsg *ndm; + int rc; + mctp_eid_t eid; + + rc = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, nd_mctp_policy, + extack); + if (rc < 0) { + NL_SET_ERR_MSG(extack, "incorrect format"); + return rc; + } + + if (!tb[NDA_DST]) { + NL_SET_ERR_MSG(extack, "Neighbour EID must be specified"); + return -EINVAL; + } + eid = nla_get_u8(tb[NDA_DST]); + + ndm = nlmsg_data(nlh); + dev = __dev_get_by_index(net, ndm->ndm_ifindex); + if (!dev) + return -ENODEV; + + mdev = mctp_dev_get_rtnl(dev); + if (!mdev) + return -ENODEV; + + return mctp_neigh_remove(mdev, eid); +} + +static int mctp_fill_neigh(struct sk_buff *skb, u32 portid, u32 seq, int event, + unsigned int flags, struct mctp_neigh *neigh) +{ + struct net_device *dev = neigh->dev->dev; + struct nlmsghdr *nlh; + struct ndmsg *hdr; + + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*hdr), flags); + if (!nlh) + return -EMSGSIZE; + + hdr = nlmsg_data(nlh); + hdr->ndm_family = AF_MCTP; + hdr->ndm_ifindex = dev->ifindex; + hdr->ndm_state = 0; // TODO other state bits? + if (neigh->source == MCTP_NEIGH_STATIC) + hdr->ndm_state |= NUD_PERMANENT; + hdr->ndm_flags = 0; + hdr->ndm_type = RTN_UNICAST; // TODO: is loopback RTN_LOCAL? + + if (nla_put_u8(skb, NDA_DST, neigh->eid)) + goto cancel; + + if (nla_put(skb, NDA_LLADDR, dev->addr_len, neigh->ha)) + goto cancel; + + nlmsg_end(skb, nlh); + + return 0; +cancel: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static int mctp_rtm_getneigh(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + int rc, idx, req_ifindex; + struct mctp_neigh *neigh; + struct ndmsg *ndmsg; + struct { + int idx; + } *cbctx = (void *)cb->ctx; + + ndmsg = nlmsg_data(cb->nlh); + req_ifindex = ndmsg->ndm_ifindex; + + idx = 0; + rcu_read_lock(); + list_for_each_entry_rcu(neigh, &net->mctp.neighbours, list) { + if (idx < cbctx->idx) + goto cont; + + rc = 0; + if (req_ifindex == 0 || req_ifindex == neigh->dev->dev->ifindex) + rc = mctp_fill_neigh(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNEIGH, NLM_F_MULTI, neigh); + + if (rc) + break; +cont: + idx++; + } + rcu_read_unlock(); + + cbctx->idx = idx; + return skb->len; +} + +int mctp_neigh_lookup(struct mctp_dev *mdev, mctp_eid_t eid, void *ret_hwaddr) +{ + struct net *net = dev_net(mdev->dev); + struct mctp_neigh *neigh; + int rc = -EHOSTUNREACH; // TODO: or ENOENT? + + rcu_read_lock(); + list_for_each_entry_rcu(neigh, &net->mctp.neighbours, list) { + if (mdev == neigh->dev && eid == neigh->eid) { + if (ret_hwaddr) + memcpy(ret_hwaddr, neigh->ha, + sizeof(neigh->ha)); + rc = 0; + break; + } + } + rcu_read_unlock(); + return rc; +} + +/* namespace registration */ +static int __net_init mctp_neigh_net_init(struct net *net) +{ + struct netns_mctp *ns = &net->mctp; + + INIT_LIST_HEAD(&ns->neighbours); + mutex_init(&ns->neigh_lock); + return 0; +} + +static void __net_exit mctp_neigh_net_exit(struct net *net) +{ + struct netns_mctp *ns = &net->mctp; + struct mctp_neigh *neigh; + + list_for_each_entry(neigh, &ns->neighbours, list) + call_rcu(&neigh->rcu, __mctp_neigh_free); +} + +/* net namespace implementation */ + +static struct pernet_operations mctp_net_ops = { + .init = mctp_neigh_net_init, + .exit = mctp_neigh_net_exit, +}; + +int __init mctp_neigh_init(void) +{ + rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_NEWNEIGH, + mctp_rtm_newneigh, NULL, 0); + rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_DELNEIGH, + mctp_rtm_delneigh, NULL, 0); + rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_GETNEIGH, + NULL, mctp_rtm_getneigh, 0); + + return register_pernet_subsys(&mctp_net_ops); +} + +void __exit mctp_neigh_exit(void) +{ + unregister_pernet_subsys(&mctp_net_ops); + rtnl_unregister(PF_MCTP, RTM_GETNEIGH); + rtnl_unregister(PF_MCTP, RTM_DELNEIGH); + rtnl_unregister(PF_MCTP, RTM_NEWNEIGH); +} diff --git a/net/mctp/route.c b/net/mctp/route.c new file mode 100644 index 000000000000..5265525011ad --- /dev/null +++ b/net/mctp/route.c @@ -0,0 +1,1116 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Management Component Transport Protocol (MCTP) - routing + * implementation. + * + * This is currently based on a simple routing table, with no dst cache. The + * number of routes should stay fairly small, so the lookup cost is small. + * + * Copyright (c) 2021 Code Construct + * Copyright (c) 2021 Google + */ + +#include <linux/idr.h> +#include <linux/mctp.h> +#include <linux/netdevice.h> +#include <linux/rtnetlink.h> +#include <linux/skbuff.h> + +#include <uapi/linux/if_arp.h> + +#include <net/mctp.h> +#include <net/mctpdevice.h> +#include <net/netlink.h> +#include <net/sock.h> + +static const unsigned int mctp_message_maxlen = 64 * 1024; + +/* route output callbacks */ +static int mctp_route_discard(struct mctp_route *route, struct sk_buff *skb) +{ + kfree_skb(skb); + return 0; +} + +static struct mctp_sock *mctp_lookup_bind(struct net *net, struct sk_buff *skb) +{ + struct mctp_skb_cb *cb = mctp_cb(skb); + struct mctp_hdr *mh; + struct sock *sk; + u8 type; + + WARN_ON(!rcu_read_lock_held()); + + /* TODO: look up in skb->cb? */ + mh = mctp_hdr(skb); + + if (!skb_headlen(skb)) + return NULL; + + type = (*(u8 *)skb->data) & 0x7f; + + sk_for_each_rcu(sk, &net->mctp.binds) { + struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); + + if (msk->bind_net != MCTP_NET_ANY && msk->bind_net != cb->net) + continue; + + if (msk->bind_type != type) + continue; + + if (msk->bind_addr != MCTP_ADDR_ANY && + msk->bind_addr != mh->dest) + continue; + + return msk; + } + + return NULL; +} + +static bool mctp_key_match(struct mctp_sk_key *key, mctp_eid_t local, + mctp_eid_t peer, u8 tag) +{ + if (key->local_addr != local) + return false; + + if (key->peer_addr != peer) + return false; + + if (key->tag != tag) + return false; + + return true; +} + +static struct mctp_sk_key *mctp_lookup_key(struct net *net, struct sk_buff *skb, + mctp_eid_t peer) +{ + struct mctp_sk_key *key, *ret; + struct mctp_hdr *mh; + u8 tag; + + WARN_ON(!rcu_read_lock_held()); + + mh = mctp_hdr(skb); + tag = mh->flags_seq_tag & (MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO); + + ret = NULL; + + hlist_for_each_entry_rcu(key, &net->mctp.keys, hlist) { + if (mctp_key_match(key, mh->dest, peer, tag)) { + ret = key; + break; + } + } + + return ret; +} + +static struct mctp_sk_key *mctp_key_alloc(struct mctp_sock *msk, + mctp_eid_t local, mctp_eid_t peer, + u8 tag, gfp_t gfp) +{ + struct mctp_sk_key *key; + + key = kzalloc(sizeof(*key), gfp); + if (!key) + return NULL; + + key->peer_addr = peer; + key->local_addr = local; + key->tag = tag; + key->sk = &msk->sk; + spin_lock_init(&key->reasm_lock); + + return key; +} + +static int mctp_key_add(struct mctp_sk_key *key, struct mctp_sock *msk) +{ + struct net *net = sock_net(&msk->sk); + struct mctp_sk_key *tmp; + unsigned long flags; + int rc = 0; + + spin_lock_irqsave(&net->mctp.keys_lock, flags); + + hlist_for_each_entry(tmp, &net->mctp.keys, hlist) { + if (mctp_key_match(tmp, key->local_addr, key->peer_addr, + key->tag)) { + rc = -EEXIST; + break; + } + } + + if (!rc) { + hlist_add_head(&key->hlist, &net->mctp.keys); + hlist_add_head(&key->sklist, &msk->keys); + } + + spin_unlock_irqrestore(&net->mctp.keys_lock, flags); + + return rc; +} + +/* Must be called with key->reasm_lock, which it will release. Will schedule + * the key for an RCU free. + */ +static void __mctp_key_unlock_drop(struct mctp_sk_key *key, struct net *net, + unsigned long flags) + __releases(&key->reasm_lock) +{ + struct sk_buff *skb; + + skb = key->reasm_head; + key->reasm_head = NULL; + key->reasm_dead = true; + spin_unlock_irqrestore(&key->reasm_lock, flags); + + spin_lock_irqsave(&net->mctp.keys_lock, flags); + hlist_del_rcu(&key->hlist); + hlist_del_rcu(&key->sklist); + spin_unlock_irqrestore(&net->mctp.keys_lock, flags); + kfree_rcu(key, rcu); + + if (skb) + kfree_skb(skb); +} + +static int mctp_frag_queue(struct mctp_sk_key *key, struct sk_buff *skb) +{ + struct mctp_hdr *hdr = mctp_hdr(skb); + u8 exp_seq, this_seq; + + this_seq = (hdr->flags_seq_tag >> MCTP_HDR_SEQ_SHIFT) + & MCTP_HDR_SEQ_MASK; + + if (!key->reasm_head) { + key->reasm_head = skb; + key->reasm_tailp = &(skb_shinfo(skb)->frag_list); + key->last_seq = this_seq; + return 0; + } + + exp_seq = (key->last_seq + 1) & MCTP_HDR_SEQ_MASK; + + if (this_seq != exp_seq) + return -EINVAL; + + if (key->reasm_head->len + skb->len > mctp_message_maxlen) + return -EINVAL; + + skb->next = NULL; + skb->sk = NULL; + *key->reasm_tailp = skb; + key->reasm_tailp = &skb->next; + + key->last_seq = this_seq; + + key->reasm_head->data_len += skb->len; + key->reasm_head->len += skb->len; + key->reasm_head->truesize += skb->truesize; + + return 0; +} + +static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) +{ + struct net *net = dev_net(skb->dev); + struct mctp_sk_key *key; + struct mctp_sock *msk; + struct mctp_hdr *mh; + unsigned long f; + u8 tag, flags; + int rc; + + msk = NULL; + rc = -EINVAL; + + /* we may be receiving a locally-routed packet; drop source sk + * accounting + */ + skb_orphan(skb); + + /* ensure we have enough data for a header and a type */ + if (skb->len < sizeof(struct mctp_hdr) + 1) + goto out; + + /* grab header, advance data ptr */ + mh = mctp_hdr(skb); + skb_pull(skb, sizeof(struct mctp_hdr)); + + if (mh->ver != 1) + goto out; + + flags = mh->flags_seq_tag & (MCTP_HDR_FLAG_SOM | MCTP_HDR_FLAG_EOM); + tag = mh->flags_seq_tag & (MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO); + + rcu_read_lock(); + + /* lookup socket / reasm context, exactly matching (src,dest,tag) */ + key = mctp_lookup_key(net, skb, mh->src); + + if (flags & MCTP_HDR_FLAG_SOM) { + if (key) { + msk = container_of(key->sk, struct mctp_sock, sk); + } else { + /* first response to a broadcast? do a more general + * key lookup to find the socket, but don't use this + * key for reassembly - we'll create a more specific + * one for future packets if required (ie, !EOM). + */ + key = mctp_lookup_key(net, skb, MCTP_ADDR_ANY); + if (key) { + msk = container_of(key->sk, + struct mctp_sock, sk); + key = NULL; + } + } + + if (!key && !msk && (tag & MCTP_HDR_FLAG_TO)) + msk = mctp_lookup_bind(net, skb); + + if (!msk) { + rc = -ENOENT; + goto out_unlock; + } + + /* single-packet message? deliver to socket, clean up any + * pending key. + */ + if (flags & MCTP_HDR_FLAG_EOM) { + sock_queue_rcv_skb(&msk->sk, skb); + if (key) { + spin_lock_irqsave(&key->reasm_lock, f); + /* we've hit a pending reassembly; not much we + * can do but drop it + */ + __mctp_key_unlock_drop(key, net, f); + } + rc = 0; + goto out_unlock; + } + + /* broadcast response or a bind() - create a key for further + * packets for this message + */ + if (!key) { + key = mctp_key_alloc(msk, mh->dest, mh->src, + tag, GFP_ATOMIC); + if (!key) { + rc = -ENOMEM; + goto out_unlock; + } + + /* we can queue without the reasm lock here, as the + * key isn't observable yet + */ + mctp_frag_queue(key, skb); + + /* if the key_add fails, we've raced with another + * SOM packet with the same src, dest and tag. There's + * no way to distinguish future packets, so all we + * can do is drop; we'll free the skb on exit from + * this function. + */ + rc = mctp_key_add(key, msk); + if (rc) + kfree(key); + + } else { + /* existing key: start reassembly */ + spin_lock_irqsave(&key->reasm_lock, f); + + if (key->reasm_head || key->reasm_dead) { + /* duplicate start? drop everything */ + __mctp_key_unlock_drop(key, net, f); + rc = -EEXIST; + } else { + rc = mctp_frag_queue(key, skb); + spin_unlock_irqrestore(&key->reasm_lock, f); + } + } + + } else if (key) { + /* this packet continues a previous message; reassemble + * using the message-specific key + */ + + spin_lock_irqsave(&key->reasm_lock, f); + + /* we need to be continuing an existing reassembly... */ + if (!key->reasm_head) + rc = -EINVAL; + else + rc = mctp_frag_queue(key, skb); + + /* end of message? deliver to socket, and we're done with + * the reassembly/response key + */ + if (!rc && flags & MCTP_HDR_FLAG_EOM) { + sock_queue_rcv_skb(key->sk, key->reasm_head); + key->reasm_head = NULL; + __mctp_key_unlock_drop(key, net, f); + } else { + spin_unlock_irqrestore(&key->reasm_lock, f); + } + + } else { + /* not a start, no matching key */ + rc = -ENOENT; + } + +out_unlock: + rcu_read_unlock(); +out: + if (rc) + kfree_skb(skb); + return rc; +} + +static unsigned int mctp_route_mtu(struct mctp_route *rt) +{ + return rt->mtu ?: READ_ONCE(rt->dev->dev->mtu); +} + +static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb) +{ + struct mctp_hdr *hdr = mctp_hdr(skb); + char daddr_buf[MAX_ADDR_LEN]; + char *daddr = NULL; + unsigned int mtu; + int rc; + + skb->protocol = htons(ETH_P_MCTP); + + mtu = READ_ONCE(skb->dev->mtu); + if (skb->len > mtu) { + kfree_skb(skb); + return -EMSGSIZE; + } + + /* If lookup fails let the device handle daddr==NULL */ + if (mctp_neigh_lookup(route->dev, hdr->dest, daddr_buf) == 0) + daddr = daddr_buf; + + rc = dev_hard_header(skb, skb->dev, ntohs(skb->protocol), + daddr, skb->dev->dev_addr, skb->len); + if (rc) { + kfree_skb(skb); + return -EHOSTUNREACH; + } + + rc = dev_queue_xmit(skb); + if (rc) + rc = net_xmit_errno(rc); + + return rc; +} + +/* route alloc/release */ +static void mctp_route_release(struct mctp_route *rt) +{ + if (refcount_dec_and_test(&rt->refs)) { + dev_put(rt->dev->dev); + kfree_rcu(rt, rcu); + } +} + +/* returns a route with the refcount at 1 */ +static struct mctp_route *mctp_route_alloc(void) +{ + struct mctp_route *rt; + + rt = kzalloc(sizeof(*rt), GFP_KERNEL); + if (!rt) + return NULL; + + INIT_LIST_HEAD(&rt->list); + refcount_set(&rt->refs, 1); + rt->output = mctp_route_discard; + + return rt; +} + +unsigned int mctp_default_net(struct net *net) +{ + return READ_ONCE(net->mctp.default_net); +} + +int mctp_default_net_set(struct net *net, unsigned int index) +{ + if (index == 0) + return -EINVAL; + WRITE_ONCE(net->mctp.default_net, index); + return 0; +} + +/* tag management */ +static void mctp_reserve_tag(struct net *net, struct mctp_sk_key *key, + struct mctp_sock *msk) +{ + struct netns_mctp *mns = &net->mctp; + + lockdep_assert_held(&mns->keys_lock); + + /* we hold the net->key_lock here, allowing updates to both + * then net and sk + */ + hlist_add_head_rcu(&key->hlist, &mns->keys); + hlist_add_head_rcu(&key->sklist, &msk->keys); +} + +/* Allocate a locally-owned tag value for (saddr, daddr), and reserve + * it for the socket msk + */ +static int mctp_alloc_local_tag(struct mctp_sock *msk, + mctp_eid_t saddr, mctp_eid_t daddr, u8 *tagp) +{ + struct net *net = sock_net(&msk->sk); + struct netns_mctp *mns = &net->mctp; + struct mctp_sk_key *key, *tmp; + unsigned long flags; + int rc = -EAGAIN; + u8 tagbits; + + /* be optimistic, alloc now */ + key = mctp_key_alloc(msk, saddr, daddr, 0, GFP_KERNEL); + if (!key) + return -ENOMEM; + + /* 8 possible tag values */ + tagbits = 0xff; + + spin_lock_irqsave(&mns->keys_lock, flags); + + /* Walk through the existing keys, looking for potential conflicting + * tags. If we find a conflict, clear that bit from tagbits + */ + hlist_for_each_entry(tmp, &mns->keys, hlist) { + /* if we don't own the tag, it can't conflict */ + if (tmp->tag & MCTP_HDR_FLAG_TO) + continue; + + if ((tmp->peer_addr == daddr || + tmp->peer_addr == MCTP_ADDR_ANY) && + tmp->local_addr == saddr) + tagbits &= ~(1 << tmp->tag); + + if (!tagbits) + break; + } + + if (tagbits) { + key->tag = __ffs(tagbits); + mctp_reserve_tag(net, key, msk); + *tagp = key->tag; + rc = 0; + } + + spin_unlock_irqrestore(&mns->keys_lock, flags); + + if (!tagbits) + kfree(key); + + return rc; +} + +/* routing lookups */ +static bool mctp_rt_match_eid(struct mctp_route *rt, + unsigned int net, mctp_eid_t eid) +{ + return READ_ONCE(rt->dev->net) == net && + rt->min <= eid && rt->max >= eid; +} + +/* compares match, used for duplicate prevention */ +static bool mctp_rt_compare_exact(struct mctp_route *rt1, + struct mctp_route *rt2) +{ + ASSERT_RTNL(); + return rt1->dev->net == rt2->dev->net && + rt1->min == rt2->min && + rt1->max == rt2->max; +} + +struct mctp_route *mctp_route_lookup(struct net *net, unsigned int dnet, + mctp_eid_t daddr) +{ + struct mctp_route *tmp, *rt = NULL; + + list_for_each_entry_rcu(tmp, &net->mctp.routes, list) { + /* TODO: add metrics */ + if (mctp_rt_match_eid(tmp, dnet, daddr)) { + if (refcount_inc_not_zero(&tmp->refs)) { + rt = tmp; + break; + } + } + } + + return rt; +} + +/* sends a skb to rt and releases the route. */ +int mctp_do_route(struct mctp_route *rt, struct sk_buff *skb) +{ + int rc; + + rc = rt->output(rt, skb); + mctp_route_release(rt); + return rc; +} + +static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, + unsigned int mtu, u8 tag) +{ + const unsigned int hlen = sizeof(struct mctp_hdr); + struct mctp_hdr *hdr, *hdr2; + unsigned int pos, size; + struct sk_buff *skb2; + int rc; + u8 seq; + + hdr = mctp_hdr(skb); + seq = 0; + rc = 0; + + if (mtu < hlen + 1) { + kfree_skb(skb); + return -EMSGSIZE; + } + + /* we've got the header */ + skb_pull(skb, hlen); + + for (pos = 0; pos < skb->len;) { + /* size of message payload */ + size = min(mtu - hlen, skb->len - pos); + + skb2 = alloc_skb(MCTP_HEADER_MAXLEN + hlen + size, GFP_KERNEL); + if (!skb2) { + rc = -ENOMEM; + break; + } + + /* generic skb copy */ + skb2->protocol = skb->protocol; + skb2->priority = skb->priority; + skb2->dev = skb->dev; + memcpy(skb2->cb, skb->cb, sizeof(skb2->cb)); + + if (skb->sk) + skb_set_owner_w(skb2, skb->sk); + + /* establish packet */ + skb_reserve(skb2, MCTP_HEADER_MAXLEN); + skb_reset_network_header(skb2); + skb_put(skb2, hlen + size); + skb2->transport_header = skb2->network_header + hlen; + + /* copy header fields, calculate SOM/EOM flags & seq */ + hdr2 = mctp_hdr(skb2); + hdr2->ver = hdr->ver; + hdr2->dest = hdr->dest; + hdr2->src = hdr->src; + hdr2->flags_seq_tag = tag & + (MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO); + + if (pos == 0) + hdr2->flags_seq_tag |= MCTP_HDR_FLAG_SOM; + + if (pos + size == skb->len) + hdr2->flags_seq_tag |= MCTP_HDR_FLAG_EOM; + + hdr2->flags_seq_tag |= seq << MCTP_HDR_SEQ_SHIFT; + + /* copy message payload */ + skb_copy_bits(skb, pos, skb_transport_header(skb2), size); + + /* do route, but don't drop the rt reference */ + rc = rt->output(rt, skb2); + if (rc) + break; + + seq = (seq + 1) & MCTP_HDR_SEQ_MASK; + pos += size; + } + + mctp_route_release(rt); + consume_skb(skb); + return rc; +} + +int mctp_local_output(struct sock *sk, struct mctp_route *rt, + struct sk_buff *skb, mctp_eid_t daddr, u8 req_tag) +{ + struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); + struct mctp_skb_cb *cb = mctp_cb(skb); + struct mctp_hdr *hdr; + unsigned long flags; + unsigned int mtu; + mctp_eid_t saddr; + int rc; + u8 tag; + + if (WARN_ON(!rt->dev)) + return -EINVAL; + + spin_lock_irqsave(&rt->dev->addrs_lock, flags); + if (rt->dev->num_addrs == 0) { + rc = -EHOSTUNREACH; + } else { + /* use the outbound interface's first address as our source */ + saddr = rt->dev->addrs[0]; + rc = 0; + } + spin_unlock_irqrestore(&rt->dev->addrs_lock, flags); + + if (rc) + return rc; + + if (req_tag & MCTP_HDR_FLAG_TO) { + rc = mctp_alloc_local_tag(msk, saddr, daddr, &tag); + if (rc) + return rc; + tag |= MCTP_HDR_FLAG_TO; + } else { + tag = req_tag; + } + + + skb->protocol = htons(ETH_P_MCTP); + skb->priority = 0; + skb_reset_transport_header(skb); + skb_push(skb, sizeof(struct mctp_hdr)); + skb_reset_network_header(skb); + skb->dev = rt->dev->dev; + + /* cb->net will have been set on initial ingress */ + cb->src = saddr; + + /* set up common header fields */ + hdr = mctp_hdr(skb); + hdr->ver = 1; + hdr->dest = daddr; + hdr->src = saddr; + + mtu = mctp_route_mtu(rt); + + if (skb->len + sizeof(struct mctp_hdr) <= mtu) { + hdr->flags_seq_tag = MCTP_HDR_FLAG_SOM | MCTP_HDR_FLAG_EOM | + tag; + return mctp_do_route(rt, skb); + } else { + return mctp_do_fragment_route(rt, skb, mtu, tag); + } +} + +/* route management */ +static int mctp_route_add(struct mctp_dev *mdev, mctp_eid_t daddr_start, + unsigned int daddr_extent, unsigned int mtu, + unsigned char type) +{ + int (*rtfn)(struct mctp_route *rt, struct sk_buff *skb); + struct net *net = dev_net(mdev->dev); + struct mctp_route *rt, *ert; + + if (!mctp_address_ok(daddr_start)) + return -EINVAL; + + if (daddr_extent > 0xff || daddr_start + daddr_extent >= 255) + return -EINVAL; + + switch (type) { + case RTN_LOCAL: + rtfn = mctp_route_input; + break; + case RTN_UNICAST: + rtfn = mctp_route_output; + break; + default: + return -EINVAL; + } + + rt = mctp_route_alloc(); + if (!rt) + return -ENOMEM; + + rt->min = daddr_start; + rt->max = daddr_start + daddr_extent; + rt->mtu = mtu; + rt->dev = mdev; + dev_hold(rt->dev->dev); + rt->type = type; + rt->output = rtfn; + + ASSERT_RTNL(); + /* Prevent duplicate identical routes. */ + list_for_each_entry(ert, &net->mctp.routes, list) { + if (mctp_rt_compare_exact(rt, ert)) { + mctp_route_release(rt); + return -EEXIST; + } + } + + list_add_rcu(&rt->list, &net->mctp.routes); + + return 0; +} + +static int mctp_route_remove(struct mctp_dev *mdev, mctp_eid_t daddr_start, + unsigned int daddr_extent) +{ + struct net *net = dev_net(mdev->dev); + struct mctp_route *rt, *tmp; + mctp_eid_t daddr_end; + bool dropped; + + if (daddr_extent > 0xff || daddr_start + daddr_extent >= 255) + return -EINVAL; + + daddr_end = daddr_start + daddr_extent; + dropped = false; + + ASSERT_RTNL(); + + list_for_each_entry_safe(rt, tmp, &net->mctp.routes, list) { + if (rt->dev == mdev && + rt->min == daddr_start && rt->max == daddr_end) { + list_del_rcu(&rt->list); + /* TODO: immediate RTM_DELROUTE */ + mctp_route_release(rt); + dropped = true; + } + } + + return dropped ? 0 : -ENOENT; +} + +int mctp_route_add_local(struct mctp_dev *mdev, mctp_eid_t addr) +{ + return mctp_route_add(mdev, addr, 0, 0, RTN_LOCAL); +} + +int mctp_route_remove_local(struct mctp_dev *mdev, mctp_eid_t addr) +{ + return mctp_route_remove(mdev, addr, 0); +} + +/* removes all entries for a given device */ +void mctp_route_remove_dev(struct mctp_dev *mdev) +{ + struct net *net = dev_net(mdev->dev); + struct mctp_route *rt, *tmp; + + ASSERT_RTNL(); + list_for_each_entry_safe(rt, tmp, &net->mctp.routes, list) { + if (rt->dev == mdev) { + list_del_rcu(&rt->list); + /* TODO: immediate RTM_DELROUTE */ + mctp_route_release(rt); + } + } +} + +/* Incoming packet-handling */ + +static int mctp_pkttype_receive(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, + struct net_device *orig_dev) +{ + struct net *net = dev_net(dev); + struct mctp_skb_cb *cb; + struct mctp_route *rt; + struct mctp_hdr *mh; + + /* basic non-data sanity checks */ + if (dev->type != ARPHRD_MCTP) + goto err_drop; + + if (!pskb_may_pull(skb, sizeof(struct mctp_hdr))) + goto err_drop; + + skb_reset_transport_header(skb); + skb_reset_network_header(skb); + + /* We have enough for a header; decode and route */ + mh = mctp_hdr(skb); + if (mh->ver < MCTP_VER_MIN || mh->ver > MCTP_VER_MAX) + goto err_drop; + + cb = __mctp_cb(skb); + rcu_read_lock(); + cb->net = READ_ONCE(__mctp_dev_get(dev)->net); + rcu_read_unlock(); + + rt = mctp_route_lookup(net, cb->net, mh->dest); + if (!rt) + goto err_drop; + + mctp_do_route(rt, skb); + + return NET_RX_SUCCESS; + +err_drop: + kfree_skb(skb); + return NET_RX_DROP; +} + +static struct packet_type mctp_packet_type = { + .type = cpu_to_be16(ETH_P_MCTP), + .func = mctp_pkttype_receive, +}; + +/* netlink interface */ + +static const struct nla_policy rta_mctp_policy[RTA_MAX + 1] = { + [RTA_DST] = { .type = NLA_U8 }, + [RTA_METRICS] = { .type = NLA_NESTED }, + [RTA_OIF] = { .type = NLA_U32 }, +}; + +/* Common part for RTM_NEWROUTE and RTM_DELROUTE parsing. + * tb must hold RTA_MAX+1 elements. + */ +static int mctp_route_nlparse(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack, + struct nlattr **tb, struct rtmsg **rtm, + struct mctp_dev **mdev, mctp_eid_t *daddr_start) +{ + struct net *net = sock_net(skb->sk); + struct net_device *dev; + unsigned int ifindex; + int rc; + + rc = nlmsg_parse(nlh, sizeof(struct rtmsg), tb, RTA_MAX, + rta_mctp_policy, extack); + if (rc < 0) { + NL_SET_ERR_MSG(extack, "incorrect format"); + return rc; + } + + if (!tb[RTA_DST]) { + NL_SET_ERR_MSG(extack, "dst EID missing"); + return -EINVAL; + } + *daddr_start = nla_get_u8(tb[RTA_DST]); + + if (!tb[RTA_OIF]) { + NL_SET_ERR_MSG(extack, "ifindex missing"); + return -EINVAL; + } + ifindex = nla_get_u32(tb[RTA_OIF]); + + *rtm = nlmsg_data(nlh); + if ((*rtm)->rtm_family != AF_MCTP) { + NL_SET_ERR_MSG(extack, "route family must be AF_MCTP"); + return -EINVAL; + } + + dev = __dev_get_by_index(net, ifindex); + if (!dev) { + NL_SET_ERR_MSG(extack, "bad ifindex"); + return -ENODEV; + } + *mdev = mctp_dev_get_rtnl(dev); + if (!*mdev) + return -ENODEV; + + if (dev->flags & IFF_LOOPBACK) { + NL_SET_ERR_MSG(extack, "no routes to loopback"); + return -EINVAL; + } + + return 0; +} + +static int mctp_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[RTA_MAX + 1]; + mctp_eid_t daddr_start; + struct mctp_dev *mdev; + struct rtmsg *rtm; + unsigned int mtu; + int rc; + + rc = mctp_route_nlparse(skb, nlh, extack, tb, + &rtm, &mdev, &daddr_start); + if (rc < 0) + return rc; + + if (rtm->rtm_type != RTN_UNICAST) { + NL_SET_ERR_MSG(extack, "rtm_type must be RTN_UNICAST"); + return -EINVAL; + } + + /* TODO: parse mtu from nlparse */ + mtu = 0; + + if (rtm->rtm_type != RTN_UNICAST) + return -EINVAL; + + rc = mctp_route_add(mdev, daddr_start, rtm->rtm_dst_len, mtu, + rtm->rtm_type); + return rc; +} + +static int mctp_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[RTA_MAX + 1]; + mctp_eid_t daddr_start; + struct mctp_dev *mdev; + struct rtmsg *rtm; + int rc; + + rc = mctp_route_nlparse(skb, nlh, extack, tb, + &rtm, &mdev, &daddr_start); + if (rc < 0) + return rc; + + /* we only have unicast routes */ + if (rtm->rtm_type != RTN_UNICAST) + return -EINVAL; + + rc = mctp_route_remove(mdev, daddr_start, rtm->rtm_dst_len); + return rc; +} + +static int mctp_fill_rtinfo(struct sk_buff *skb, struct mctp_route *rt, + u32 portid, u32 seq, int event, unsigned int flags) +{ + struct nlmsghdr *nlh; + struct rtmsg *hdr; + void *metrics; + + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*hdr), flags); + if (!nlh) + return -EMSGSIZE; + + hdr = nlmsg_data(nlh); + hdr->rtm_family = AF_MCTP; + + /* we use the _len fields as a number of EIDs, rather than + * a number of bits in the address + */ + hdr->rtm_dst_len = rt->max - rt->min; + hdr->rtm_src_len = 0; + hdr->rtm_tos = 0; + hdr->rtm_table = RT_TABLE_DEFAULT; + hdr->rtm_protocol = RTPROT_STATIC; /* everything is user-defined */ + hdr->rtm_scope = RT_SCOPE_LINK; /* TODO: scope in mctp_route? */ + hdr->rtm_type = rt->type; + + if (nla_put_u8(skb, RTA_DST, rt->min)) + goto cancel; + + metrics = nla_nest_start_noflag(skb, RTA_METRICS); + if (!metrics) + goto cancel; + + if (rt->mtu) { + if (nla_put_u32(skb, RTAX_MTU, rt->mtu)) + goto cancel; + } + + nla_nest_end(skb, metrics); + + if (rt->dev) { + if (nla_put_u32(skb, RTA_OIF, rt->dev->dev->ifindex)) + goto cancel; + } + + /* TODO: conditional neighbour physaddr? */ + + nlmsg_end(skb, nlh); + + return 0; + +cancel: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static int mctp_dump_rtinfo(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct mctp_route *rt; + int s_idx, idx; + + /* TODO: allow filtering on route data, possibly under + * cb->strict_check + */ + + /* TODO: change to struct overlay */ + s_idx = cb->args[0]; + idx = 0; + + rcu_read_lock(); + list_for_each_entry_rcu(rt, &net->mctp.routes, list) { + if (idx++ < s_idx) + continue; + if (mctp_fill_rtinfo(skb, rt, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWROUTE, NLM_F_MULTI) < 0) + break; + } + + rcu_read_unlock(); + cb->args[0] = idx; + + return skb->len; +} + +/* net namespace implementation */ +static int __net_init mctp_routes_net_init(struct net *net) +{ + struct netns_mctp *ns = &net->mctp; + + INIT_LIST_HEAD(&ns->routes); + INIT_HLIST_HEAD(&ns->binds); + mutex_init(&ns->bind_lock); + INIT_HLIST_HEAD(&ns->keys); + spin_lock_init(&ns->keys_lock); + WARN_ON(mctp_default_net_set(net, MCTP_INITIAL_DEFAULT_NET)); + return 0; +} + +static void __net_exit mctp_routes_net_exit(struct net *net) +{ + struct mctp_route *rt; + + list_for_each_entry_rcu(rt, &net->mctp.routes, list) + mctp_route_release(rt); +} + +static struct pernet_operations mctp_net_ops = { + .init = mctp_routes_net_init, + .exit = mctp_routes_net_exit, +}; + +int __init mctp_routes_init(void) +{ + dev_add_pack(&mctp_packet_type); + + rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_GETROUTE, + NULL, mctp_dump_rtinfo, 0); + rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_NEWROUTE, + mctp_newroute, NULL, 0); + rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_DELROUTE, + mctp_delroute, NULL, 0); + + return register_pernet_subsys(&mctp_net_ops); +} + +void __exit mctp_routes_exit(void) +{ + unregister_pernet_subsys(&mctp_net_ops); + rtnl_unregister(PF_MCTP, RTM_DELROUTE); + rtnl_unregister(PF_MCTP, RTM_NEWROUTE); + rtnl_unregister(PF_MCTP, RTM_GETROUTE); + dev_remove_pack(&mctp_packet_type); +} diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 05a21dd072df..ffeb2df8be7a 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -407,7 +407,6 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, /* Verify ttl is valid */ if (dec.ttl <= 1) goto err; - dec.ttl -= 1; /* Find the output device */ out_dev = rcu_dereference(nh->nh_dev); @@ -431,6 +430,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, skb->dev = out_dev; skb->protocol = htons(ETH_P_MPLS_UC); + dec.ttl -= 1; if (unlikely(!new_header_size && dec.bos)) { /* Penultimate hop popping */ if (!mpls_egress(dev_net(out_dev), rt, skb, dec)) diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index 7d738bd06f2c..8b235468c88f 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -21,43 +21,50 @@ struct mptcp_pernet { struct ctl_table_header *ctl_table_hdr; #endif - u8 mptcp_enabled; unsigned int add_addr_timeout; + unsigned int stale_loss_cnt; + u8 mptcp_enabled; u8 checksum_enabled; u8 allow_join_initial_addr_port; }; -static struct mptcp_pernet *mptcp_get_pernet(struct net *net) +static struct mptcp_pernet *mptcp_get_pernet(const struct net *net) { return net_generic(net, mptcp_pernet_id); } -int mptcp_is_enabled(struct net *net) +int mptcp_is_enabled(const struct net *net) { return mptcp_get_pernet(net)->mptcp_enabled; } -unsigned int mptcp_get_add_addr_timeout(struct net *net) +unsigned int mptcp_get_add_addr_timeout(const struct net *net) { return mptcp_get_pernet(net)->add_addr_timeout; } -int mptcp_is_checksum_enabled(struct net *net) +int mptcp_is_checksum_enabled(const struct net *net) { return mptcp_get_pernet(net)->checksum_enabled; } -int mptcp_allow_join_id0(struct net *net) +int mptcp_allow_join_id0(const struct net *net) { return mptcp_get_pernet(net)->allow_join_initial_addr_port; } +unsigned int mptcp_stale_loss_cnt(const struct net *net) +{ + return mptcp_get_pernet(net)->stale_loss_cnt; +} + static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) { pernet->mptcp_enabled = 1; pernet->add_addr_timeout = TCP_RTO_MAX; pernet->checksum_enabled = 0; pernet->allow_join_initial_addr_port = 1; + pernet->stale_loss_cnt = 4; } #ifdef CONFIG_SYSCTL @@ -95,6 +102,12 @@ static struct ctl_table mptcp_sysctl_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE }, + { + .procname = "stale_loss_cnt", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_douintvec_minmax, + }, {} }; @@ -114,6 +127,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) table[1].data = &pernet->add_addr_timeout; table[2].data = &pernet->checksum_enabled; table[3].data = &pernet->allow_join_initial_addr_port; + table[4].data = &pernet->stale_loss_cnt; hdr = register_net_sysctl(net, MPTCP_SYSCTL_PATH, table); if (!hdr) diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index ff2cc0e3273d..b21ff9be04c6 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -44,7 +44,11 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW), SNMP_MIB_ITEM("MPPrioTx", MPTCP_MIB_MPPRIOTX), SNMP_MIB_ITEM("MPPrioRx", MPTCP_MIB_MPPRIORX), + SNMP_MIB_ITEM("MPFailTx", MPTCP_MIB_MPFAILTX), + SNMP_MIB_ITEM("MPFailRx", MPTCP_MIB_MPFAILRX), SNMP_MIB_ITEM("RcvPruned", MPTCP_MIB_RCVPRUNED), + SNMP_MIB_ITEM("SubflowStale", MPTCP_MIB_SUBFLOWSTALE), + SNMP_MIB_ITEM("SubflowRecover", MPTCP_MIB_SUBFLOWRECOVER), SNMP_MIB_SENTINEL }; diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index 0663cb12b448..ecd3d8b117e0 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -37,7 +37,11 @@ enum linux_mptcp_mib_field { MPTCP_MIB_RMSUBFLOW, /* Remove a subflow */ MPTCP_MIB_MPPRIOTX, /* Transmit a MP_PRIO */ MPTCP_MIB_MPPRIORX, /* Received a MP_PRIO */ + MPTCP_MIB_MPFAILTX, /* Transmit a MP_FAIL */ + MPTCP_MIB_MPFAILRX, /* Received a MP_FAIL */ MPTCP_MIB_RCVPRUNED, /* Incoming packet dropped due to memory limit */ + MPTCP_MIB_SUBFLOWSTALE, /* Subflows entered 'stale' status */ + MPTCP_MIB_SUBFLOWRECOVER, /* Subflows returned to active status after being stale */ __MPTCP_MIB_MAX }; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 4452455aef7f..c41273cefc51 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -81,12 +81,11 @@ static void mptcp_parse_option(const struct sk_buff *skb, * is if both hosts in their SYNs set A=0." */ if (flags & MPTCP_CAP_CHECKSUM_REQD) - mp_opt->csum_reqd = 1; + mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD; - if (flags & MPTCP_CAP_DENY_JOIN_ID0) - mp_opt->deny_join_id0 = 1; + mp_opt->deny_join_id0 = !!(flags & MPTCP_CAP_DENY_JOIN_ID0); - mp_opt->mp_capable = 1; + mp_opt->suboptions |= OPTIONS_MPTCP_MPC; if (opsize >= TCPOLEN_MPTCP_MPC_SYNACK) { mp_opt->sndr_key = get_unaligned_be64(ptr); ptr += 8; @@ -101,7 +100,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, * equivalent to those in a DSS option and can be used * interchangeably." */ - mp_opt->dss = 1; + mp_opt->suboptions |= OPTION_MPTCP_DSS; mp_opt->use_map = 1; mp_opt->mpc_map = 1; mp_opt->data_len = get_unaligned_be16(ptr); @@ -109,7 +108,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, } if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM) { mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr); - mp_opt->csum_reqd = 1; + mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD; ptr += 2; } pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d csum=%u", @@ -118,7 +117,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_MP_JOIN: - mp_opt->mp_join = 1; + mp_opt->suboptions |= OPTIONS_MPTCP_MPJ; if (opsize == TCPOLEN_MPTCP_MPJ_SYN) { mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP; mp_opt->join_id = *ptr++; @@ -144,7 +143,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, memcpy(mp_opt->hmac, ptr, MPTCPOPT_HMAC_LEN); pr_debug("MP_JOIN hmac"); } else { - mp_opt->mp_join = 0; + mp_opt->suboptions &= ~OPTIONS_MPTCP_MPJ; } break; @@ -192,8 +191,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, opsize != expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) break; - mp_opt->dss = 1; - + mp_opt->suboptions |= OPTION_MPTCP_DSS; if (mp_opt->use_ack) { if (mp_opt->ack64) { mp_opt->data_ack = get_unaligned_be64(ptr); @@ -222,14 +220,15 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr += 2; if (opsize == expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) { - mp_opt->csum_reqd = 1; + mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD; mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr); ptr += 2; } pr_debug("data_seq=%llu subflow_seq=%u data_len=%u csum=%d:%u", mp_opt->data_seq, mp_opt->subflow_seq, - mp_opt->data_len, mp_opt->csum_reqd, mp_opt->csum); + mp_opt->data_len, !!(mp_opt->suboptions & OPTION_MPTCP_CSUMREQD), + mp_opt->csum); } break; @@ -260,8 +259,10 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; } - mp_opt->add_addr = 1; + mp_opt->suboptions |= OPTION_MPTCP_ADD_ADDR; mp_opt->addr.id = *ptr++; + mp_opt->addr.port = 0; + mp_opt->ahmac = 0; if (mp_opt->addr.family == AF_INET) { memcpy((u8 *)&mp_opt->addr.addr.s_addr, (u8 *)ptr, 4); ptr += 4; @@ -298,7 +299,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr++; - mp_opt->rm_addr = 1; + mp_opt->suboptions |= OPTION_MPTCP_RM_ADDR; mp_opt->rm_list.nr = opsize - TCPOLEN_MPTCP_RM_ADDR_BASE; for (i = 0; i < mp_opt->rm_list.nr; i++) mp_opt->rm_list.ids[i] = *ptr++; @@ -309,7 +310,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, if (opsize != TCPOLEN_MPTCP_PRIO) break; - mp_opt->mp_prio = 1; + mp_opt->suboptions |= OPTION_MPTCP_PRIO; mp_opt->backup = *ptr++ & MPTCP_PRIO_BKUP; pr_debug("MP_PRIO: prio=%d", mp_opt->backup); break; @@ -321,7 +322,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr += 2; mp_opt->rcvr_key = get_unaligned_be64(ptr); ptr += 8; - mp_opt->fastclose = 1; + mp_opt->suboptions |= OPTION_MPTCP_FASTCLOSE; break; case MPTCPOPT_RST: @@ -330,12 +331,23 @@ static void mptcp_parse_option(const struct sk_buff *skb, if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) break; - mp_opt->reset = 1; + + mp_opt->suboptions |= OPTION_MPTCP_RST; flags = *ptr++; mp_opt->reset_transient = flags & MPTCP_RST_TRANSIENT; mp_opt->reset_reason = *ptr; break; + case MPTCPOPT_MP_FAIL: + if (opsize != TCPOLEN_MPTCP_FAIL) + break; + + ptr += 2; + mp_opt->suboptions |= OPTION_MPTCP_FAIL; + mp_opt->fail_seq = get_unaligned_be64(ptr); + pr_debug("MP_FAIL: data_seq=%llu", mp_opt->fail_seq); + break; + default: break; } @@ -345,25 +357,12 @@ void mptcp_get_options(const struct sock *sk, const struct sk_buff *skb, struct mptcp_options_received *mp_opt) { - struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - struct mptcp_sock *msk = mptcp_sk(subflow->conn); const struct tcphdr *th = tcp_hdr(skb); const unsigned char *ptr; int length; /* initialize option status */ - mp_opt->mp_capable = 0; - mp_opt->mp_join = 0; - mp_opt->add_addr = 0; - mp_opt->ahmac = 0; - mp_opt->fastclose = 0; - mp_opt->addr.port = 0; - mp_opt->rm_addr = 0; - mp_opt->dss = 0; - mp_opt->mp_prio = 0; - mp_opt->reset = 0; - mp_opt->csum_reqd = READ_ONCE(msk->csum_enabled); - mp_opt->deny_join_id0 = 0; + mp_opt->suboptions = 0; length = (th->doff * 4) - sizeof(struct tcphdr); ptr = (const unsigned char *)(th + 1); @@ -592,6 +591,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, dss_size = map_size; if (skb && snd_data_fin_enable) mptcp_write_data_fin(subflow, skb, &opts->ext_copy); + opts->suboptions = OPTION_MPTCP_DSS; ret = true; } @@ -615,6 +615,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, opts->ext_copy.ack64 = 0; } opts->ext_copy.use_ack = 1; + opts->suboptions = OPTION_MPTCP_DSS; WRITE_ONCE(msk->old_wspace, __mptcp_space((struct sock *)msk)); /* Add kind/length/subtype/flag overhead if mapping is not populated */ @@ -667,29 +668,34 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * bool port; int len; - if ((mptcp_pm_should_add_signal_ipv6(msk) || - mptcp_pm_should_add_signal_port(msk) || - mptcp_pm_should_add_signal_echo(msk)) && - skb && skb_is_tcp_pure_ack(skb)) { - pr_debug("drop other suboptions"); - opts->suboptions = 0; - opts->ext_copy.use_ack = 0; - opts->ext_copy.use_map = 0; - remaining += opt_size; - drop_other_suboptions = true; - } - + /* add addr will strip the existing options, be sure to avoid breaking + * MPC/MPJ handshakes + */ if (!mptcp_pm_should_add_signal(msk) || - !(mptcp_pm_add_addr_signal(msk, remaining, &opts->addr, &echo, &port))) + (opts->suboptions & (OPTION_MPTCP_MPJ_ACK | OPTION_MPTCP_MPC_ACK)) || + !mptcp_pm_add_addr_signal(msk, skb, opt_size, remaining, &opts->addr, + &echo, &port, &drop_other_suboptions)) return false; + if (drop_other_suboptions) + remaining += opt_size; len = mptcp_add_addr_len(opts->addr.family, echo, port); if (remaining < len) return false; *size = len; - if (drop_other_suboptions) + if (drop_other_suboptions) { + pr_debug("drop other suboptions"); + opts->suboptions = 0; + + /* note that e.g. DSS could have written into the memory + * aliased by ahmac, we must reset the field here + * to avoid appending the hmac even for ADD_ADDR echo + * options + */ + opts->ahmac = 0; *size -= opt_size; + } opts->suboptions |= OPTION_MPTCP_ADD_ADDR; if (!echo) { opts->ahmac = add_addr_generate_hmac(msk->local_key, @@ -739,7 +745,12 @@ static bool mptcp_established_options_mp_prio(struct sock *sk, { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - if (!subflow->send_mp_prio) + /* can't send MP_PRIO with MPC, as they share the same option space: + * 'backup'. Also it makes no sense at all + */ + if (!subflow->send_mp_prio || + ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK | + OPTION_MPTCP_MPC_ACK) & opts->suboptions)) return false; /* account for the trailing 'nop' option */ @@ -755,7 +766,7 @@ static bool mptcp_established_options_mp_prio(struct sock *sk, return true; } -static noinline void mptcp_established_options_rst(struct sock *sk, struct sk_buff *skb, +static noinline bool mptcp_established_options_rst(struct sock *sk, struct sk_buff *skb, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts) @@ -763,12 +774,36 @@ static noinline void mptcp_established_options_rst(struct sock *sk, struct sk_bu const struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); if (remaining < TCPOLEN_MPTCP_RST) - return; + return false; *size = TCPOLEN_MPTCP_RST; opts->suboptions |= OPTION_MPTCP_RST; opts->reset_transient = subflow->reset_transient; opts->reset_reason = subflow->reset_reason; + + return true; +} + +static bool mptcp_established_options_mp_fail(struct sock *sk, + unsigned int *size, + unsigned int remaining, + struct mptcp_out_options *opts) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + + if (likely(!subflow->send_mp_fail)) + return false; + + if (remaining < TCPOLEN_MPTCP_FAIL) + return false; + + *size = TCPOLEN_MPTCP_FAIL; + opts->suboptions |= OPTION_MPTCP_FAIL; + opts->fail_seq = subflow->map_seq; + + pr_debug("MP_FAIL fail_seq=%llu", opts->fail_seq); + + return true; } bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, @@ -787,15 +822,28 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, return false; if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) { - mptcp_established_options_rst(sk, skb, size, remaining, opts); + if (mptcp_established_options_mp_fail(sk, &opt_size, remaining, opts)) { + *size += opt_size; + remaining -= opt_size; + } + if (mptcp_established_options_rst(sk, skb, &opt_size, remaining, opts)) { + *size += opt_size; + remaining -= opt_size; + } return true; } snd_data_fin = mptcp_data_fin_enabled(msk); if (mptcp_established_options_mp(sk, skb, snd_data_fin, &opt_size, remaining, opts)) ret = true; - else if (mptcp_established_options_dss(sk, skb, snd_data_fin, &opt_size, remaining, opts)) + else if (mptcp_established_options_dss(sk, skb, snd_data_fin, &opt_size, remaining, opts)) { ret = true; + if (mptcp_established_options_mp_fail(sk, &opt_size, remaining, opts)) { + *size += opt_size; + remaining -= opt_size; + return true; + } + } /* we reserved enough space for the above options, and exceeding the * TCP option space would be fatal @@ -868,7 +916,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, */ if (TCP_SKB_CB(skb)->seq == subflow->ssn_offset + 1 && TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq && - subflow->mp_join && mp_opt->mp_join && + subflow->mp_join && (mp_opt->suboptions & OPTIONS_MPTCP_MPJ) && READ_ONCE(msk->pm.server_side)) tcp_send_ack(ssk); goto fully_established; @@ -885,25 +933,21 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, return subflow->mp_capable; } - if (mp_opt->dss && mp_opt->use_ack) { + if (((mp_opt->suboptions & OPTION_MPTCP_DSS) && mp_opt->use_ack) || + ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) && !mp_opt->echo)) { /* subflows are fully established as soon as we get any - * additional ack. + * additional ack, including ADD_ADDR. */ subflow->fully_established = 1; WRITE_ONCE(msk->fully_established, true); goto fully_established; } - if (mp_opt->add_addr) { - WRITE_ONCE(msk->fully_established, true); - return true; - } - /* If the first established packet does not contain MP_CAPABLE + data * then fallback to TCP. Fallback scenarios requires a reset for * MP_JOIN subflows. */ - if (!mp_opt->mp_capable) { + if (!(mp_opt->suboptions & OPTIONS_MPTCP_MPC)) { if (subflow->mp_join) goto reset; subflow->mp_capable = 0; @@ -975,9 +1019,11 @@ static void ack_update_msk(struct mptcp_sock *msk, old_snd_una = msk->snd_una; new_snd_una = mptcp_expand_seq(old_snd_una, mp_opt->data_ack, mp_opt->ack64); - /* ACK for data not even sent yet? Ignore. */ - if (after64(new_snd_una, snd_nxt)) - new_snd_una = old_snd_una; + /* ACK for data not even sent yet and even above recovery bound? Ignore.*/ + if (unlikely(after64(new_snd_una, snd_nxt))) { + if (!msk->recovery || after64(new_snd_una, msk->recovery_snd_nxt)) + new_snd_una = old_snd_una; + } new_wnd_end = new_snd_una + tcp_sk(ssk)->snd_wnd; @@ -1065,48 +1111,51 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) if (!check_fully_established(msk, sk, subflow, skb, &mp_opt)) return sk->sk_state != TCP_CLOSE; - if (mp_opt.fastclose && - msk->local_key == mp_opt.rcvr_key) { - WRITE_ONCE(msk->rcv_fastclose, true); - mptcp_schedule_work((struct sock *)msk); - } + if (unlikely(mp_opt.suboptions != OPTION_MPTCP_DSS)) { + if ((mp_opt.suboptions & OPTION_MPTCP_FASTCLOSE) && + msk->local_key == mp_opt.rcvr_key) { + WRITE_ONCE(msk->rcv_fastclose, true); + mptcp_schedule_work((struct sock *)msk); + } - if (mp_opt.add_addr && add_addr_hmac_valid(msk, &mp_opt)) { - if (!mp_opt.echo) { - mptcp_pm_add_addr_received(msk, &mp_opt.addr); - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDR); - } else { - mptcp_pm_add_addr_echoed(msk, &mp_opt.addr); - mptcp_pm_del_add_timer(msk, &mp_opt.addr, true); - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADD); + if ((mp_opt.suboptions & OPTION_MPTCP_ADD_ADDR) && + add_addr_hmac_valid(msk, &mp_opt)) { + if (!mp_opt.echo) { + mptcp_pm_add_addr_received(msk, &mp_opt.addr); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDR); + } else { + mptcp_pm_add_addr_echoed(msk, &mp_opt.addr); + mptcp_pm_del_add_timer(msk, &mp_opt.addr, true); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADD); + } + + if (mp_opt.addr.port) + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_PORTADD); } - if (mp_opt.addr.port) - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_PORTADD); + if (mp_opt.suboptions & OPTION_MPTCP_RM_ADDR) + mptcp_pm_rm_addr_received(msk, &mp_opt.rm_list); - mp_opt.add_addr = 0; - } + if (mp_opt.suboptions & OPTION_MPTCP_PRIO) { + mptcp_pm_mp_prio_received(sk, mp_opt.backup); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPPRIORX); + } - if (mp_opt.rm_addr) { - mptcp_pm_rm_addr_received(msk, &mp_opt.rm_list); - mp_opt.rm_addr = 0; - } + if (mp_opt.suboptions & OPTION_MPTCP_FAIL) { + mptcp_pm_mp_fail_received(sk, mp_opt.fail_seq); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILRX); + } - if (mp_opt.mp_prio) { - mptcp_pm_mp_prio_received(sk, mp_opt.backup); - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPPRIORX); - mp_opt.mp_prio = 0; - } + if (mp_opt.suboptions & OPTION_MPTCP_RST) { + subflow->reset_seen = 1; + subflow->reset_reason = mp_opt.reset_reason; + subflow->reset_transient = mp_opt.reset_transient; + } - if (mp_opt.reset) { - subflow->reset_seen = 1; - subflow->reset_reason = mp_opt.reset_reason; - subflow->reset_transient = mp_opt.reset_transient; + if (!(mp_opt.suboptions & OPTION_MPTCP_DSS)) + return true; } - if (!mp_opt.dss) - return true; - /* we can't wait for recvmsg() to update the ack_seq, otherwise * monodirectional flows will stuck */ @@ -1133,7 +1182,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) memset(mpext, 0, sizeof(*mpext)); - if (mp_opt.use_map) { + if (likely(mp_opt.use_map)) { if (mp_opt.mpc_map) { /* this is an MP_CAPABLE carrying MPTCP data * we know this map the first chunk of data @@ -1153,7 +1202,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) } mpext->data_len = mp_opt.data_len; mpext->use_map = 1; - mpext->csum_reqd = mp_opt.csum_reqd; + mpext->csum_reqd = !!(mp_opt.suboptions & OPTION_MPTCP_CSUMREQD); if (mpext->csum_reqd) mpext->csum = mp_opt.csum; @@ -1200,8 +1249,88 @@ static u16 mptcp_make_csum(const struct mptcp_ext *mpext) void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, struct mptcp_out_options *opts) { - if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK | - OPTION_MPTCP_MPC_ACK) & opts->suboptions) { + if (unlikely(OPTION_MPTCP_FAIL & opts->suboptions)) { + const struct sock *ssk = (const struct sock *)tp; + struct mptcp_subflow_context *subflow; + + subflow = mptcp_subflow_ctx(ssk); + subflow->send_mp_fail = 0; + + *ptr++ = mptcp_option(MPTCPOPT_MP_FAIL, + TCPOLEN_MPTCP_FAIL, + 0, 0); + put_unaligned_be64(opts->fail_seq, ptr); + ptr += 2; + } + + /* RST is mutually exclusive with everything else */ + if (unlikely(OPTION_MPTCP_RST & opts->suboptions)) { + *ptr++ = mptcp_option(MPTCPOPT_RST, + TCPOLEN_MPTCP_RST, + opts->reset_transient, + opts->reset_reason); + return; + } + + /* DSS, MPC, MPJ and ADD_ADDR are mutually exclusive, see + * mptcp_established_options*() + */ + if (likely(OPTION_MPTCP_DSS & opts->suboptions)) { + struct mptcp_ext *mpext = &opts->ext_copy; + u8 len = TCPOLEN_MPTCP_DSS_BASE; + u8 flags = 0; + + if (mpext->use_ack) { + flags = MPTCP_DSS_HAS_ACK; + if (mpext->ack64) { + len += TCPOLEN_MPTCP_DSS_ACK64; + flags |= MPTCP_DSS_ACK64; + } else { + len += TCPOLEN_MPTCP_DSS_ACK32; + } + } + + if (mpext->use_map) { + len += TCPOLEN_MPTCP_DSS_MAP64; + + /* Use only 64-bit mapping flags for now, add + * support for optional 32-bit mappings later. + */ + flags |= MPTCP_DSS_HAS_MAP | MPTCP_DSS_DSN64; + if (mpext->data_fin) + flags |= MPTCP_DSS_DATA_FIN; + + if (opts->csum_reqd) + len += TCPOLEN_MPTCP_DSS_CHECKSUM; + } + + *ptr++ = mptcp_option(MPTCPOPT_DSS, len, 0, flags); + + if (mpext->use_ack) { + if (mpext->ack64) { + put_unaligned_be64(mpext->data_ack, ptr); + ptr += 2; + } else { + put_unaligned_be32(mpext->data_ack32, ptr); + ptr += 1; + } + } + + if (mpext->use_map) { + put_unaligned_be64(mpext->data_seq, ptr); + ptr += 2; + put_unaligned_be32(mpext->subflow_seq, ptr); + ptr += 1; + if (opts->csum_reqd) { + put_unaligned_be32(mpext->data_len << 16 | + mptcp_make_csum(mpext), ptr); + } else { + put_unaligned_be32(mpext->data_len << 16 | + TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); + } + } + } else if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK | + OPTION_MPTCP_MPC_ACK) & opts->suboptions) { u8 len, flag = MPTCP_CAP_HMAC_SHA256; if (OPTION_MPTCP_MPC_SYN & opts->suboptions) { @@ -1248,10 +1377,31 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); } ptr += 1; - } -mp_capable_done: - if (OPTION_MPTCP_ADD_ADDR & opts->suboptions) { + /* MPC is additionally mutually exclusive with MP_PRIO */ + goto mp_capable_done; + } else if (OPTION_MPTCP_MPJ_SYN & opts->suboptions) { + *ptr++ = mptcp_option(MPTCPOPT_MP_JOIN, + TCPOLEN_MPTCP_MPJ_SYN, + opts->backup, opts->join_id); + put_unaligned_be32(opts->token, ptr); + ptr += 1; + put_unaligned_be32(opts->nonce, ptr); + ptr += 1; + } else if (OPTION_MPTCP_MPJ_SYNACK & opts->suboptions) { + *ptr++ = mptcp_option(MPTCPOPT_MP_JOIN, + TCPOLEN_MPTCP_MPJ_SYNACK, + opts->backup, opts->join_id); + put_unaligned_be64(opts->thmac, ptr); + ptr += 2; + put_unaligned_be32(opts->nonce, ptr); + ptr += 1; + } else if (OPTION_MPTCP_MPJ_ACK & opts->suboptions) { + *ptr++ = mptcp_option(MPTCPOPT_MP_JOIN, + TCPOLEN_MPTCP_MPJ_ACK, 0, 0); + memcpy(ptr, opts->hmac, MPTCPOPT_HMAC_LEN); + ptr += 5; + } else if (OPTION_MPTCP_ADD_ADDR & opts->suboptions) { u8 len = TCPOLEN_MPTCP_ADD_ADDR_BASE; u8 echo = MPTCP_ADDR_ECHO; @@ -1309,6 +1459,19 @@ mp_capable_done: } } + if (OPTION_MPTCP_PRIO & opts->suboptions) { + const struct sock *ssk = (const struct sock *)tp; + struct mptcp_subflow_context *subflow; + + subflow = mptcp_subflow_ctx(ssk); + subflow->send_mp_prio = 0; + + *ptr++ = mptcp_option(MPTCPOPT_MP_PRIO, + TCPOLEN_MPTCP_PRIO, + opts->backup, TCPOPT_NOP); + } + +mp_capable_done: if (OPTION_MPTCP_RM_ADDR & opts->suboptions) { u8 i = 1; @@ -1329,107 +1492,6 @@ mp_capable_done: } } - if (OPTION_MPTCP_PRIO & opts->suboptions) { - const struct sock *ssk = (const struct sock *)tp; - struct mptcp_subflow_context *subflow; - - subflow = mptcp_subflow_ctx(ssk); - subflow->send_mp_prio = 0; - - *ptr++ = mptcp_option(MPTCPOPT_MP_PRIO, - TCPOLEN_MPTCP_PRIO, - opts->backup, TCPOPT_NOP); - } - - if (OPTION_MPTCP_MPJ_SYN & opts->suboptions) { - *ptr++ = mptcp_option(MPTCPOPT_MP_JOIN, - TCPOLEN_MPTCP_MPJ_SYN, - opts->backup, opts->join_id); - put_unaligned_be32(opts->token, ptr); - ptr += 1; - put_unaligned_be32(opts->nonce, ptr); - ptr += 1; - } - - if (OPTION_MPTCP_MPJ_SYNACK & opts->suboptions) { - *ptr++ = mptcp_option(MPTCPOPT_MP_JOIN, - TCPOLEN_MPTCP_MPJ_SYNACK, - opts->backup, opts->join_id); - put_unaligned_be64(opts->thmac, ptr); - ptr += 2; - put_unaligned_be32(opts->nonce, ptr); - ptr += 1; - } - - if (OPTION_MPTCP_MPJ_ACK & opts->suboptions) { - *ptr++ = mptcp_option(MPTCPOPT_MP_JOIN, - TCPOLEN_MPTCP_MPJ_ACK, 0, 0); - memcpy(ptr, opts->hmac, MPTCPOPT_HMAC_LEN); - ptr += 5; - } - - if (OPTION_MPTCP_RST & opts->suboptions) - *ptr++ = mptcp_option(MPTCPOPT_RST, - TCPOLEN_MPTCP_RST, - opts->reset_transient, - opts->reset_reason); - - if (opts->ext_copy.use_ack || opts->ext_copy.use_map) { - struct mptcp_ext *mpext = &opts->ext_copy; - u8 len = TCPOLEN_MPTCP_DSS_BASE; - u8 flags = 0; - - if (mpext->use_ack) { - flags = MPTCP_DSS_HAS_ACK; - if (mpext->ack64) { - len += TCPOLEN_MPTCP_DSS_ACK64; - flags |= MPTCP_DSS_ACK64; - } else { - len += TCPOLEN_MPTCP_DSS_ACK32; - } - } - - if (mpext->use_map) { - len += TCPOLEN_MPTCP_DSS_MAP64; - - /* Use only 64-bit mapping flags for now, add - * support for optional 32-bit mappings later. - */ - flags |= MPTCP_DSS_HAS_MAP | MPTCP_DSS_DSN64; - if (mpext->data_fin) - flags |= MPTCP_DSS_DATA_FIN; - - if (opts->csum_reqd) - len += TCPOLEN_MPTCP_DSS_CHECKSUM; - } - - *ptr++ = mptcp_option(MPTCPOPT_DSS, len, 0, flags); - - if (mpext->use_ack) { - if (mpext->ack64) { - put_unaligned_be64(mpext->data_ack, ptr); - ptr += 2; - } else { - put_unaligned_be32(mpext->data_ack32, ptr); - ptr += 1; - } - } - - if (mpext->use_map) { - put_unaligned_be64(mpext->data_seq, ptr); - ptr += 2; - put_unaligned_be32(mpext->subflow_seq, ptr); - ptr += 1; - if (opts->csum_reqd) { - put_unaligned_be32(mpext->data_len << 16 | - mptcp_make_csum(mpext), ptr); - } else { - put_unaligned_be32(mpext->data_len << 16 | - TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); - } - } - } - if (tp) mptcp_set_rwin(tp); } diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 639271e09604..6ab386ff3294 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -10,6 +10,8 @@ #include <net/mptcp.h> #include "protocol.h" +#include "mib.h" + /* path manager command handlers */ int mptcp_pm_announce_addr(struct mptcp_sock *msk, @@ -18,23 +20,23 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk, { u8 add_addr = READ_ONCE(msk->pm.addr_signal); - pr_debug("msk=%p, local_id=%d", msk, addr->id); + pr_debug("msk=%p, local_id=%d, echo=%d", msk, addr->id, echo); lockdep_assert_held(&msk->pm.lock); - if (add_addr) { - pr_warn("addr_signal error, add_addr=%d", add_addr); + if (add_addr & + (echo ? BIT(MPTCP_ADD_ADDR_ECHO) : BIT(MPTCP_ADD_ADDR_SIGNAL))) { + pr_warn("addr_signal error, add_addr=%d, echo=%d", add_addr, echo); return -EINVAL; } - msk->pm.local = *addr; - add_addr |= BIT(MPTCP_ADD_ADDR_SIGNAL); - if (echo) + if (echo) { + msk->pm.remote = *addr; add_addr |= BIT(MPTCP_ADD_ADDR_ECHO); - if (addr->family == AF_INET6) - add_addr |= BIT(MPTCP_ADD_ADDR_IPV6); - if (addr->port) - add_addr |= BIT(MPTCP_ADD_ADDR_PORT); + } else { + msk->pm.local = *addr; + add_addr |= BIT(MPTCP_ADD_ADDR_SIGNAL); + } WRITE_ONCE(msk->pm.addr_signal, add_addr); return 0; } @@ -247,12 +249,21 @@ void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup) mptcp_event(MPTCP_EVENT_SUB_PRIORITY, mptcp_sk(subflow->conn), sk, GFP_ATOMIC); } +void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq) +{ + pr_debug("fail_seq=%llu", fail_seq); +} + /* path manager helpers */ -bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int remaining, - struct mptcp_addr_info *saddr, bool *echo, bool *port) +bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, struct sk_buff *skb, + unsigned int opt_size, unsigned int remaining, + struct mptcp_addr_info *addr, bool *echo, + bool *port, bool *drop_other_suboptions) { int ret = false; + u8 add_addr; + u8 family; spin_lock_bh(&msk->pm.lock); @@ -260,14 +271,30 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int remaining, if (!mptcp_pm_should_add_signal(msk)) goto out_unlock; + /* always drop every other options for pure ack ADD_ADDR; this is a + * plain dup-ack from TCP perspective. The other MPTCP-relevant info, + * if any, will be carried by the 'original' TCP ack + */ + if (skb && skb_is_tcp_pure_ack(skb)) { + remaining += opt_size; + *drop_other_suboptions = true; + } + *echo = mptcp_pm_should_add_signal_echo(msk); - *port = mptcp_pm_should_add_signal_port(msk); + *port = !!(*echo ? msk->pm.remote.port : msk->pm.local.port); - if (remaining < mptcp_add_addr_len(msk->pm.local.family, *echo, *port)) + family = *echo ? msk->pm.remote.family : msk->pm.local.family; + if (remaining < mptcp_add_addr_len(family, *echo, *port)) goto out_unlock; - *saddr = msk->pm.local; - WRITE_ONCE(msk->pm.addr_signal, 0); + if (*echo) { + *addr = msk->pm.remote; + add_addr = msk->pm.addr_signal & ~BIT(MPTCP_ADD_ADDR_ECHO); + } else { + *addr = msk->pm.local; + add_addr = msk->pm.addr_signal & ~BIT(MPTCP_ADD_ADDR_SIGNAL); + } + WRITE_ONCE(msk->pm.addr_signal, add_addr); ret = true; out_unlock: @@ -279,6 +306,7 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, struct mptcp_rm_list *rm_list) { int ret = false, len; + u8 rm_addr; spin_lock_bh(&msk->pm.lock); @@ -286,16 +314,17 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, if (!mptcp_pm_should_rm_signal(msk)) goto out_unlock; + rm_addr = msk->pm.addr_signal & ~BIT(MPTCP_RM_ADDR_SIGNAL); len = mptcp_rm_addr_len(&msk->pm.rm_list_tx); if (len < 0) { - WRITE_ONCE(msk->pm.addr_signal, 0); + WRITE_ONCE(msk->pm.addr_signal, rm_addr); goto out_unlock; } if (remaining < len) goto out_unlock; *rm_list = msk->pm.rm_list_tx; - WRITE_ONCE(msk->pm.addr_signal, 0); + WRITE_ONCE(msk->pm.addr_signal, rm_addr); ret = true; out_unlock: @@ -308,6 +337,25 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) return mptcp_pm_nl_get_local_id(msk, skc); } +void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + u32 rcv_tstamp = READ_ONCE(tcp_sk(ssk)->rcv_tstamp); + + /* keep track of rtx periods with no progress */ + if (!subflow->stale_count) { + subflow->stale_rcv_tstamp = rcv_tstamp; + subflow->stale_count++; + } else if (subflow->stale_rcv_tstamp == rcv_tstamp) { + if (subflow->stale_count < U8_MAX) + subflow->stale_count++; + mptcp_pm_nl_subflow_chk_stale(msk, ssk); + } else { + subflow->stale_count = 0; + mptcp_subflow_set_active(subflow); + } +} + void mptcp_pm_data_init(struct mptcp_sock *msk) { msk->pm.add_addr_signaled = 0; diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index d2591ebf01d9..c4f9a5ce3815 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -27,7 +27,6 @@ struct mptcp_pm_addr_entry { struct mptcp_addr_info addr; u8 flags; int ifindex; - struct rcu_head rcu; struct socket *lsk; }; @@ -47,6 +46,7 @@ struct pm_nl_pernet { spinlock_t lock; struct list_head local_addr_list; unsigned int addrs; + unsigned int stale_loss_cnt; unsigned int add_addr_signal_max; unsigned int add_addr_accept_max; unsigned int local_addr_max; @@ -317,14 +317,14 @@ static void mptcp_pm_add_timer(struct timer_list *timer) if (!entry->addr.id) return; - if (mptcp_pm_should_add_signal(msk)) { + if (mptcp_pm_should_add_signal_addr(msk)) { sk_reset_timer(sk, timer, jiffies + TCP_RTO_MAX / 8); goto out; } spin_lock_bh(&msk->pm.lock); - if (!mptcp_pm_should_add_signal(msk)) { + if (!mptcp_pm_should_add_signal_addr(msk)) { pr_debug("retransmit ADD_ADDR id=%d", entry->addr.id); mptcp_pm_announce_addr(msk, &entry->addr, false); mptcp_pm_add_addr_send_ack(msk); @@ -410,6 +410,55 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk) } } +static bool lookup_address_in_vec(struct mptcp_addr_info *addrs, unsigned int nr, + struct mptcp_addr_info *addr) +{ + int i; + + for (i = 0; i < nr; i++) { + if (addresses_equal(&addrs[i], addr, addr->port)) + return true; + } + + return false; +} + +/* Fill all the remote addresses into the array addrs[], + * and return the array size. + */ +static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, bool fullmesh, + struct mptcp_addr_info *addrs) +{ + struct sock *sk = (struct sock *)msk, *ssk; + struct mptcp_subflow_context *subflow; + struct mptcp_addr_info remote = { 0 }; + unsigned int subflows_max; + int i = 0; + + subflows_max = mptcp_pm_get_subflows_max(msk); + + /* Non-fullmesh endpoint, fill in the single entry + * corresponding to the primary MPC subflow remote address + */ + if (!fullmesh) { + remote_address((struct sock_common *)sk, &remote); + msk->pm.subflows++; + addrs[i++] = remote; + } else { + mptcp_for_each_subflow(msk, subflow) { + ssk = mptcp_subflow_tcp_sock(subflow); + remote_address((struct sock_common *)ssk, &remote); + if (!lookup_address_in_vec(addrs, i, &remote) && + msk->pm.subflows < subflows_max) { + msk->pm.subflows++; + addrs[i++] = remote; + } + } + } + + return i; +} + static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; @@ -455,15 +504,16 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) !READ_ONCE(msk->pm.remote_deny_join_id0)) { local = select_local_address(pernet, msk); if (local) { - struct mptcp_addr_info remote = { 0 }; + bool fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH); + struct mptcp_addr_info addrs[MPTCP_PM_ADDR_MAX]; + int i, nr; msk->pm.local_addr_used++; - msk->pm.subflows++; check_work_pending(msk); - remote_address((struct sock_common *)sk, &remote); + nr = fill_remote_addresses_vec(msk, fullmesh, addrs); spin_unlock_bh(&msk->pm.lock); - __mptcp_subflow_connect(sk, &local->addr, &remote, - local->flags, local->ifindex); + for (i = 0; i < nr; i++) + __mptcp_subflow_connect(sk, &local->addr, &addrs[i]); spin_lock_bh(&msk->pm.lock); return; } @@ -484,13 +534,67 @@ static void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk) mptcp_pm_create_subflow_or_signal_addr(msk); } +/* Fill all the local addresses into the array addrs[], + * and return the array size. + */ +static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, + struct mptcp_addr_info *addrs) +{ + struct sock *sk = (struct sock *)msk; + struct mptcp_pm_addr_entry *entry; + struct mptcp_addr_info local; + struct pm_nl_pernet *pernet; + unsigned int subflows_max; + int i = 0; + + pernet = net_generic(sock_net(sk), pm_nl_pernet_id); + subflows_max = mptcp_pm_get_subflows_max(msk); + + rcu_read_lock(); + __mptcp_flush_join_list(msk); + list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { + if (!(entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH)) + continue; + + if (entry->addr.family != sk->sk_family) { +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + if ((entry->addr.family == AF_INET && + !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) || + (sk->sk_family == AF_INET && + !ipv6_addr_v4mapped(&entry->addr.addr6))) +#endif + continue; + } + + if (msk->pm.subflows < subflows_max) { + msk->pm.subflows++; + addrs[i++] = entry->addr; + } + } + rcu_read_unlock(); + + /* If the array is empty, fill in the single + * 'IPADDRANY' local address + */ + if (!i) { + memset(&local, 0, sizeof(local)); + local.family = msk->pm.remote.family; + + msk->pm.subflows++; + addrs[i++] = local; + } + + return i; +} + static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) { + struct mptcp_addr_info addrs[MPTCP_PM_ADDR_MAX]; struct sock *sk = (struct sock *)msk; unsigned int add_addr_accept_max; struct mptcp_addr_info remote; - struct mptcp_addr_info local; unsigned int subflows_max; + int i, nr; add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk); subflows_max = mptcp_pm_get_subflows_max(msk); @@ -502,23 +606,22 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) if (lookup_subflow_by_daddr(&msk->conn_list, &msk->pm.remote)) goto add_addr_echo; - msk->pm.add_addr_accepted++; - msk->pm.subflows++; - if (msk->pm.add_addr_accepted >= add_addr_accept_max || - msk->pm.subflows >= subflows_max) - WRITE_ONCE(msk->pm.accept_addr, false); - /* connect to the specified remote address, using whatever * local address the routing configuration will pick. */ remote = msk->pm.remote; if (!remote.port) remote.port = sk->sk_dport; - memset(&local, 0, sizeof(local)); - local.family = remote.family; + nr = fill_local_addresses_vec(msk, addrs); + + msk->pm.add_addr_accepted++; + if (msk->pm.add_addr_accepted >= add_addr_accept_max || + msk->pm.subflows >= subflows_max) + WRITE_ONCE(msk->pm.accept_addr, false); spin_unlock_bh(&msk->pm.lock); - __mptcp_subflow_connect(sk, &local, &remote, 0, 0); + for (i = 0; i < nr; i++) + __mptcp_subflow_connect(sk, &addrs[i], &remote); spin_lock_bh(&msk->pm.lock); add_addr_echo: @@ -541,17 +644,12 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk) subflow = list_first_entry_or_null(&msk->conn_list, typeof(*subflow), node); if (subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - bool slow; spin_unlock_bh(&msk->pm.lock); - pr_debug("send ack for %s%s%s", - mptcp_pm_should_add_signal(msk) ? "add_addr" : "rm_addr", - mptcp_pm_should_add_signal_ipv6(msk) ? " [ipv6]" : "", - mptcp_pm_should_add_signal_port(msk) ? " [port]" : ""); - - slow = lock_sock_fast(ssk); - tcp_send_ack(ssk); - unlock_sock_fast(ssk, slow); + pr_debug("send ack for %s", + mptcp_pm_should_add_signal(msk) ? "add_addr" : "rm_addr"); + + mptcp_subflow_send_ack(ssk); spin_lock_bh(&msk->pm.lock); } } @@ -568,7 +666,6 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, struct sock *ssk = mptcp_subflow_tcp_sock(subflow); struct sock *sk = (struct sock *)msk; struct mptcp_addr_info local; - bool slow; local_address((struct sock_common *)ssk, &local); if (!addresses_equal(&local, addr, addr->port)) @@ -581,9 +678,7 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, spin_unlock_bh(&msk->pm.lock); pr_debug("send ack for mp_prio"); - slow = lock_sock_fast(ssk); - tcp_send_ack(ssk); - unlock_sock_fast(ssk, slow); + mptcp_subflow_send_ack(ssk); spin_lock_bh(&msk->pm.lock); return 0; @@ -900,6 +995,43 @@ static const struct nla_policy mptcp_pm_policy[MPTCP_PM_ATTR_MAX + 1] = { [MPTCP_PM_ATTR_SUBFLOWS] = { .type = NLA_U32, }, }; +void mptcp_pm_nl_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk) +{ + struct mptcp_subflow_context *iter, *subflow = mptcp_subflow_ctx(ssk); + struct sock *sk = (struct sock *)msk; + unsigned int active_max_loss_cnt; + struct net *net = sock_net(sk); + unsigned int stale_loss_cnt; + bool slow; + + stale_loss_cnt = mptcp_stale_loss_cnt(net); + if (subflow->stale || !stale_loss_cnt || subflow->stale_count <= stale_loss_cnt) + return; + + /* look for another available subflow not in loss state */ + active_max_loss_cnt = max_t(int, stale_loss_cnt - 1, 1); + mptcp_for_each_subflow(msk, iter) { + if (iter != subflow && mptcp_subflow_active(iter) && + iter->stale_count < active_max_loss_cnt) { + /* we have some alternatives, try to mark this subflow as idle ...*/ + slow = lock_sock_fast(ssk); + if (!tcp_rtx_and_write_queues_empty(ssk)) { + subflow->stale = 1; + __mptcp_retransmit_pending_data(sk); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_SUBFLOWSTALE); + } + unlock_sock_fast(ssk, slow); + + /* always try to push the pending data regarless of re-injections: + * we can possibly use backup subflows now, and subflow selection + * is cheap under the msk socket lock + */ + __mptcp_push_pending(sk, 0); + return; + } + } +} + static int mptcp_pm_family_to_addr(int family) { #if IS_ENABLED(CONFIG_MPTCP_IPV6) @@ -1068,6 +1200,27 @@ __lookup_addr_by_id(struct pm_nl_pernet *pernet, unsigned int id) return NULL; } +int mptcp_pm_get_flags_and_ifindex_by_id(struct net *net, unsigned int id, + u8 *flags, int *ifindex) +{ + struct mptcp_pm_addr_entry *entry; + + *flags = 0; + *ifindex = 0; + + if (id) { + rcu_read_lock(); + entry = __lookup_addr_by_id(net_generic(net, pm_nl_pernet_id), id); + if (entry) { + *flags = entry->flags; + *ifindex = entry->ifindex; + } + rcu_read_unlock(); + } + + return 0; +} + static bool remove_anno_list_by_saddr(struct mptcp_sock *msk, struct mptcp_addr_info *addr) { @@ -1136,36 +1289,12 @@ next: return 0; } -struct addr_entry_release_work { - struct rcu_work rwork; - struct mptcp_pm_addr_entry *entry; -}; - -static void mptcp_pm_release_addr_entry(struct work_struct *work) -{ - struct addr_entry_release_work *w; - struct mptcp_pm_addr_entry *entry; - - w = container_of(to_rcu_work(work), struct addr_entry_release_work, rwork); - entry = w->entry; - if (entry) { - if (entry->lsk) - sock_release(entry->lsk); - kfree(entry); - } - kfree(w); -} - -static void mptcp_pm_free_addr_entry(struct mptcp_pm_addr_entry *entry) +/* caller must ensure the RCU grace period is already elapsed */ +static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry) { - struct addr_entry_release_work *w; - - w = kmalloc(sizeof(*w), GFP_ATOMIC); - if (w) { - INIT_RCU_WORK(&w->rwork, mptcp_pm_release_addr_entry); - w->entry = entry; - queue_rcu_work(system_wq, &w->rwork); - } + if (entry->lsk) + sock_release(entry->lsk); + kfree(entry); } static int mptcp_nl_remove_id_zero_address(struct net *net, @@ -1245,7 +1374,8 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info) spin_unlock_bh(&pernet->lock); mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), &entry->addr); - mptcp_pm_free_addr_entry(entry); + synchronize_rcu(); + __mptcp_pm_release_addr_entry(entry); return ret; } @@ -1298,6 +1428,7 @@ static void mptcp_nl_remove_addrs_list(struct net *net, } } +/* caller must ensure the RCU grace period is already elapsed */ static void __flush_addrs(struct list_head *list) { while (!list_empty(list)) { @@ -1306,7 +1437,7 @@ static void __flush_addrs(struct list_head *list) cur = list_entry(list->next, struct mptcp_pm_addr_entry, list); list_del_rcu(&cur->list); - mptcp_pm_free_addr_entry(cur); + __mptcp_pm_release_addr_entry(cur); } } @@ -1330,6 +1461,7 @@ static int mptcp_nl_cmd_flush_addrs(struct sk_buff *skb, struct genl_info *info) bitmap_zero(pernet->id_bitmap, MAX_ADDR_ID + 1); spin_unlock_bh(&pernet->lock); mptcp_nl_remove_addrs_list(sock_net(skb->sk), &free_list); + synchronize_rcu(); __flush_addrs(&free_list); return 0; } @@ -1923,6 +2055,7 @@ static int __net_init pm_nl_init_net(struct net *net) INIT_LIST_HEAD_RCU(&pernet->local_addr_list); pernet->next_id = 1; + pernet->stale_loss_cnt = 4; spin_lock_init(&pernet->lock); /* No need to initialize other pernet fields, the struct is zeroed at @@ -1940,7 +2073,8 @@ static void __net_exit pm_nl_exit_net(struct list_head *net_list) struct pm_nl_pernet *pernet = net_generic(net, pm_nl_pernet_id); /* net is removed from namespace list, can't race with - * other modifiers + * other modifiers, also netns core already waited for a + * RCU grace period. */ __flush_addrs(&pernet->local_addr_list); } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index a88924947815..2602f1386160 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -411,35 +411,51 @@ static void mptcp_set_datafin_timeout(const struct sock *sk) TCP_RTO_MIN << icsk->icsk_retransmits); } -static void mptcp_set_timeout(const struct sock *sk, const struct sock *ssk) +static void __mptcp_set_timeout(struct sock *sk, long tout) { - long tout = ssk && inet_csk(ssk)->icsk_pending ? - inet_csk(ssk)->icsk_timeout - jiffies : 0; - - if (tout <= 0) - tout = mptcp_sk(sk)->timer_ival; mptcp_sk(sk)->timer_ival = tout > 0 ? tout : TCP_RTO_MIN; } +static long mptcp_timeout_from_subflow(const struct mptcp_subflow_context *subflow) +{ + const struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + return inet_csk(ssk)->icsk_pending && !subflow->stale_count ? + inet_csk(ssk)->icsk_timeout - jiffies : 0; +} + +static void mptcp_set_timeout(struct sock *sk) +{ + struct mptcp_subflow_context *subflow; + long tout = 0; + + mptcp_for_each_subflow(mptcp_sk(sk), subflow) + tout = max(tout, mptcp_timeout_from_subflow(subflow)); + __mptcp_set_timeout(sk, tout); +} + static bool tcp_can_send_ack(const struct sock *ssk) { return !((1 << inet_sk_state_load(ssk)) & (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE | TCPF_LISTEN)); } +void mptcp_subflow_send_ack(struct sock *ssk) +{ + bool slow; + + slow = lock_sock_fast(ssk); + if (tcp_can_send_ack(ssk)) + tcp_send_ack(ssk); + unlock_sock_fast(ssk, slow); +} + static void mptcp_send_ack(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; - mptcp_for_each_subflow(msk, subflow) { - struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - bool slow; - - slow = lock_sock_fast(ssk); - if (tcp_can_send_ack(ssk)) - tcp_send_ack(ssk); - unlock_sock_fast(ssk, slow); - } + mptcp_for_each_subflow(msk, subflow) + mptcp_subflow_send_ack(mptcp_subflow_tcp_sock(subflow)); } static void mptcp_subflow_cleanup_rbuf(struct sock *ssk) @@ -531,7 +547,6 @@ static bool mptcp_check_data_fin(struct sock *sk) } ret = true; - mptcp_set_timeout(sk, NULL); mptcp_send_ack(msk); mptcp_close_wake_up(sk); } @@ -791,10 +806,7 @@ static void mptcp_reset_timer(struct sock *sk) if (unlikely(inet_sk_state_load(sk) == TCP_CLOSE)) return; - /* should never be called with mptcp level timer cleared */ - tout = READ_ONCE(mptcp_sk(sk)->timer_ival); - if (WARN_ON_ONCE(!tout)) - tout = TCP_RTO_MIN; + tout = mptcp_sk(sk)->timer_ival; sk_reset_timer(sk, &icsk->icsk_retransmit_timer, jiffies + tout); } @@ -994,6 +1006,13 @@ static void mptcp_wmem_uncharge(struct sock *sk, int size) msk->wmem_reserved += size; } +static void __mptcp_mem_reclaim_partial(struct sock *sk) +{ + lockdep_assert_held_once(&sk->sk_lock.slock); + __mptcp_update_wmem(sk); + sk_mem_reclaim_partial(sk); +} + static void mptcp_mem_reclaim_partial(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -1046,8 +1065,14 @@ static void __mptcp_clean_una(struct sock *sk) if (after64(dfrag->data_seq + dfrag->data_len, snd_una)) break; - if (WARN_ON_ONCE(dfrag == msk->first_pending)) - break; + if (unlikely(dfrag == msk->first_pending)) { + /* in recovery mode can see ack after the current snd head */ + if (WARN_ON_ONCE(!msk->recovery)) + break; + + WRITE_ONCE(msk->first_pending, mptcp_send_next(sk)); + } + dfrag_clear(sk, dfrag); cleaned = true; } @@ -1056,8 +1081,14 @@ static void __mptcp_clean_una(struct sock *sk) if (dfrag && after64(snd_una, dfrag->data_seq)) { u64 delta = snd_una - dfrag->data_seq; - if (WARN_ON_ONCE(delta > dfrag->already_sent)) - goto out; + /* prevent wrap around in recovery mode */ + if (unlikely(delta > dfrag->already_sent)) { + if (WARN_ON_ONCE(!msk->recovery)) + goto out; + if (WARN_ON_ONCE(delta > dfrag->data_len)) + goto out; + dfrag->already_sent += delta - dfrag->already_sent; + } dfrag->data_seq += delta; dfrag->offset += delta; @@ -1068,16 +1099,16 @@ static void __mptcp_clean_una(struct sock *sk) cleaned = true; } + /* all retransmitted data acked, recovery completed */ + if (unlikely(msk->recovery) && after64(msk->snd_una, msk->recovery_snd_nxt)) + msk->recovery = false; + out: - if (cleaned) { - if (tcp_under_memory_pressure(sk)) { - __mptcp_update_wmem(sk); - sk_mem_reclaim_partial(sk); - } - } + if (cleaned && tcp_under_memory_pressure(sk)) + __mptcp_mem_reclaim_partial(sk); - if (snd_una == READ_ONCE(msk->snd_nxt)) { - if (msk->timer_ival && !mptcp_data_fin_enabled(msk)) + if (snd_una == READ_ONCE(msk->snd_nxt) && !msk->recovery) { + if (mptcp_timer_pending(sk) && !mptcp_data_fin_enabled(msk)) mptcp_stop_timer(sk); } else { mptcp_reset_timer(sk); @@ -1154,6 +1185,7 @@ struct mptcp_sendmsg_info { u16 limit; u16 sent; unsigned int flags; + bool data_lock_held; }; static int mptcp_check_allowed_size(struct mptcp_sock *msk, u64 data_seq, @@ -1225,17 +1257,17 @@ static bool __mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp) return false; } -static bool mptcp_must_reclaim_memory(struct sock *sk, struct sock *ssk) +static bool mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, bool data_lock_held) { - return !ssk->sk_tx_skb_cache && - tcp_under_memory_pressure(sk); -} + gfp_t gfp = data_lock_held ? GFP_ATOMIC : sk->sk_allocation; -static bool mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk) -{ - if (unlikely(mptcp_must_reclaim_memory(sk, ssk))) - mptcp_mem_reclaim_partial(sk); - return __mptcp_alloc_tx_skb(sk, ssk, sk->sk_allocation); + if (unlikely(tcp_under_memory_pressure(sk))) { + if (data_lock_held) + __mptcp_mem_reclaim_partial(sk); + else + mptcp_mem_reclaim_partial(sk); + } + return __mptcp_alloc_tx_skb(sk, ssk, gfp); } /* note: this always recompute the csum on the whole skb, even @@ -1259,7 +1291,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, bool zero_window_probe = false; struct mptcp_ext *mpext = NULL; struct sk_buff *skb, *tail; - bool can_collapse = false; + bool must_collapse = false; int size_bias = 0; int avail_size; size_t ret = 0; @@ -1279,16 +1311,24 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, * SSN association set here */ mpext = skb_ext_find(skb, SKB_EXT_MPTCP); - can_collapse = (info->size_goal - skb->len > 0) && - mptcp_skb_can_collapse_to(data_seq, skb, mpext); - if (!can_collapse) { + if (!mptcp_skb_can_collapse_to(data_seq, skb, mpext)) { TCP_SKB_CB(skb)->eor = 1; - } else { + goto alloc_skb; + } + + must_collapse = (info->size_goal - skb->len > 0) && + (skb_shinfo(skb)->nr_frags < sysctl_max_skb_frags); + if (must_collapse) { size_bias = skb->len; avail_size = info->size_goal - skb->len; } } +alloc_skb: + if (!must_collapse && !ssk->sk_tx_skb_cache && + !mptcp_alloc_tx_skb(sk, ssk, info->data_lock_held)) + return 0; + /* Zero window and all data acked? Probe. */ avail_size = mptcp_check_allowed_size(msk, data_seq, avail_size); if (avail_size == 0) { @@ -1318,7 +1358,6 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, if (skb == tail) { TCP_SKB_CB(tail)->tcp_flags &= ~TCPHDR_PSH; mpext->data_len += ret; - WARN_ON_ONCE(!can_collapse); WARN_ON_ONCE(zero_window_probe); goto out; } @@ -1366,16 +1405,44 @@ struct subflow_send_info { u64 ratio; }; +void mptcp_subflow_set_active(struct mptcp_subflow_context *subflow) +{ + if (!subflow->stale) + return; + + subflow->stale = 0; + MPTCP_INC_STATS(sock_net(mptcp_subflow_tcp_sock(subflow)), MPTCP_MIB_SUBFLOWRECOVER); +} + +bool mptcp_subflow_active(struct mptcp_subflow_context *subflow) +{ + if (unlikely(subflow->stale)) { + u32 rcv_tstamp = READ_ONCE(tcp_sk(mptcp_subflow_tcp_sock(subflow))->rcv_tstamp); + + if (subflow->stale_rcv_tstamp == rcv_tstamp) + return false; + + mptcp_subflow_set_active(subflow); + } + return __mptcp_subflow_active(subflow); +} + +/* implement the mptcp packet scheduler; + * returns the subflow that will transmit the next DSS + * additionally updates the rtx timeout + */ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) { struct subflow_send_info send_info[2]; struct mptcp_subflow_context *subflow; + struct sock *sk = (struct sock *)msk; int i, nr_active = 0; struct sock *ssk; + long tout = 0; u64 ratio; u32 pace; - sock_owned_by_me((struct sock *)msk); + sock_owned_by_me(sk); if (__mptcp_check_fallback(msk)) { if (!msk->first) @@ -1386,8 +1453,10 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) /* re-use last subflow, if the burst allow that */ if (msk->last_snd && msk->snd_burst > 0 && sk_stream_memory_free(msk->last_snd) && - mptcp_subflow_active(mptcp_subflow_ctx(msk->last_snd))) + mptcp_subflow_active(mptcp_subflow_ctx(msk->last_snd))) { + mptcp_set_timeout(sk); return msk->last_snd; + } /* pick the subflow with the lower wmem/wspace ratio */ for (i = 0; i < 2; ++i) { @@ -1400,6 +1469,7 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) if (!mptcp_subflow_active(subflow)) continue; + tout = max(tout, mptcp_timeout_from_subflow(subflow)); nr_active += !subflow->backup; if (!sk_stream_memory_free(subflow->tcp_sock) || !tcp_sk(ssk)->snd_wnd) continue; @@ -1415,6 +1485,7 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) send_info[subflow->backup].ratio = ratio; } } + __mptcp_set_timeout(sk, tout); /* pick the best backup if no other subflow is active */ if (!nr_active) @@ -1433,12 +1504,11 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) static void mptcp_push_release(struct sock *sk, struct sock *ssk, struct mptcp_sendmsg_info *info) { - mptcp_set_timeout(sk, ssk); tcp_push(ssk, 0, info->mss_now, tcp_sk(ssk)->nonagle, info->size_goal); release_sock(ssk); } -static void __mptcp_push_pending(struct sock *sk, unsigned int flags) +void __mptcp_push_pending(struct sock *sk, unsigned int flags) { struct sock *prev_ssk = NULL, *ssk = NULL; struct mptcp_sock *msk = mptcp_sk(sk); @@ -1459,25 +1529,20 @@ static void __mptcp_push_pending(struct sock *sk, unsigned int flags) mptcp_flush_join_list(msk); ssk = mptcp_subflow_get_send(msk); - /* try to keep the subflow socket lock across - * consecutive xmit on the same socket + /* First check. If the ssk has changed since + * the last round, release prev_ssk */ if (ssk != prev_ssk && prev_ssk) mptcp_push_release(sk, prev_ssk, &info); if (!ssk) goto out; - if (ssk != prev_ssk || !prev_ssk) - lock_sock(ssk); - - /* keep it simple and always provide a new skb for the - * subflow, even if we will not use it when collapsing - * on the pending one + /* Need to lock the new subflow only if different + * from the previous one, otherwise we are still + * helding the relevant lock */ - if (!mptcp_alloc_tx_skb(sk, ssk)) { - mptcp_push_release(sk, ssk, &info); - goto out; - } + if (ssk != prev_ssk) + lock_sock(ssk); ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info); if (ret <= 0) { @@ -1501,18 +1566,19 @@ static void __mptcp_push_pending(struct sock *sk, unsigned int flags) mptcp_push_release(sk, ssk, &info); out: - if (copied) { - /* start the timer, if it's not pending */ - if (!mptcp_timer_pending(sk)) - mptcp_reset_timer(sk); + /* ensure the rtx timer is running */ + if (!mptcp_timer_pending(sk)) + mptcp_reset_timer(sk); + if (copied) __mptcp_check_send_data_fin(sk); - } } static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk) { struct mptcp_sock *msk = mptcp_sk(sk); - struct mptcp_sendmsg_info info; + struct mptcp_sendmsg_info info = { + .data_lock_held = true, + }; struct mptcp_data_frag *dfrag; struct sock *xmit_ssk; int len, copied = 0; @@ -1538,13 +1604,6 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk) goto out; } - if (unlikely(mptcp_must_reclaim_memory(sk, ssk))) { - __mptcp_update_wmem(sk); - sk_mem_reclaim_partial(sk); - } - if (!__mptcp_alloc_tx_skb(sk, ssk, GFP_ATOMIC)) - goto out; - ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info); if (ret <= 0) goto out; @@ -1567,7 +1626,6 @@ out: */ __mptcp_update_wmem(sk); if (copied) { - mptcp_set_timeout(sk, ssk); tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle, info.size_goal); if (!mptcp_timer_pending(sk)) @@ -2083,10 +2141,11 @@ static void mptcp_timeout_timer(struct timer_list *t) * * A backup subflow is returned only if that is the only kind available. */ -static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk) +static struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk) { + struct sock *backup = NULL, *pick = NULL; struct mptcp_subflow_context *subflow; - struct sock *backup = NULL; + int min_stale_count = INT_MAX; sock_owned_by_me((const struct sock *)msk); @@ -2096,14 +2155,14 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk) mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - if (!mptcp_subflow_active(subflow)) + if (!__mptcp_subflow_active(subflow)) continue; - /* still data outstanding at TCP level? Don't retransmit. */ - if (!tcp_write_queue_empty(ssk)) { - if (inet_csk(ssk)->icsk_ca_state >= TCP_CA_Loss) - continue; - return NULL; + /* still data outstanding at TCP level? skip this */ + if (!tcp_rtx_and_write_queues_empty(ssk)) { + mptcp_pm_subflow_chk_stale(msk, ssk); + min_stale_count = min_t(int, min_stale_count, subflow->stale_count); + continue; } if (subflow->backup) { @@ -2112,10 +2171,15 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk) continue; } - return ssk; + if (!pick) + pick = ssk; } - return backup; + if (pick) + return pick; + + /* use backup only if there are no progresses anywhere */ + return min_stale_count > 1 ? backup : NULL; } static void mptcp_dispose_initial_subflow(struct mptcp_sock *msk) @@ -2126,6 +2190,50 @@ static void mptcp_dispose_initial_subflow(struct mptcp_sock *msk) } } +bool __mptcp_retransmit_pending_data(struct sock *sk) +{ + struct mptcp_data_frag *cur, *rtx_head; + struct mptcp_sock *msk = mptcp_sk(sk); + + if (__mptcp_check_fallback(mptcp_sk(sk))) + return false; + + if (tcp_rtx_and_write_queues_empty(sk)) + return false; + + /* the closing socket has some data untransmitted and/or unacked: + * some data in the mptcp rtx queue has not really xmitted yet. + * keep it simple and re-inject the whole mptcp level rtx queue + */ + mptcp_data_lock(sk); + __mptcp_clean_una_wakeup(sk); + rtx_head = mptcp_rtx_head(sk); + if (!rtx_head) { + mptcp_data_unlock(sk); + return false; + } + + /* will accept ack for reijected data before re-sending them */ + if (!msk->recovery || after64(msk->snd_nxt, msk->recovery_snd_nxt)) + msk->recovery_snd_nxt = msk->snd_nxt; + msk->recovery = true; + mptcp_data_unlock(sk); + + msk->first_pending = rtx_head; + msk->tx_pending_data += msk->snd_nxt - rtx_head->data_seq; + msk->snd_nxt = rtx_head->data_seq; + msk->snd_burst = 0; + + /* be sure to clear the "sent status" on all re-injected fragments */ + list_for_each_entry(cur, &msk->rtx_queue, list) { + if (!cur->already_sent) + break; + cur->already_sent = 0; + } + + return true; +} + /* subflow sockets can be either outgoing (connect) or incoming * (accept). * @@ -2138,6 +2246,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow) { struct mptcp_sock *msk = mptcp_sk(sk); + bool need_push; list_del(&subflow->node); @@ -2149,6 +2258,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, if (ssk->sk_socket) sock_orphan(ssk); + need_push = __mptcp_retransmit_pending_data(sk); subflow->disposable = 1; /* if ssk hit tcp_done(), tcp_cleanup_ulp() cleared the related ops @@ -2176,6 +2286,9 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, if (msk->subflow && ssk == msk->subflow->sk) mptcp_dispose_initial_subflow(msk); + + if (need_push) + __mptcp_push_pending(sk, 0); } void mptcp_close_ssk(struct sock *sk, struct sock *ssk, @@ -2296,9 +2409,6 @@ static void __mptcp_retrans(struct sock *sk) info.sent = 0; info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len : dfrag->already_sent; while (info.sent < info.limit) { - if (!mptcp_alloc_tx_skb(sk, ssk)) - break; - ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info); if (ret <= 0) break; @@ -2313,7 +2423,6 @@ static void __mptcp_retrans(struct sock *sk) info.size_goal); } - mptcp_set_timeout(sk, ssk); release_sock(ssk); reset_timer: @@ -2384,10 +2493,12 @@ static int __mptcp_init_sock(struct sock *sk) msk->wmem_reserved = 0; WRITE_ONCE(msk->rmem_released, 0); msk->tx_pending_data = 0; + msk->timer_ival = TCP_RTO_MIN; msk->first = NULL; inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); + msk->recovery = false; mptcp_pm_data_init(msk); @@ -2472,7 +2583,6 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) tcp_shutdown(ssk, how); } else { pr_debug("Sending DATA_FIN on subflow %p", ssk); - mptcp_set_timeout(sk, ssk); tcp_send_ack(ssk); if (!mptcp_timer_pending(sk)) mptcp_reset_timer(sk); @@ -2723,7 +2833,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk->token = subflow_req->token; msk->subflow = NULL; WRITE_ONCE(msk->fully_established, false); - if (mp_opt->csum_reqd) + if (mp_opt->suboptions & OPTION_MPTCP_CSUMREQD) WRITE_ONCE(msk->csum_enabled, true); msk->write_seq = subflow_req->idsn + 1; @@ -2732,7 +2842,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd; msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq; - if (mp_opt->mp_capable) { + if (mp_opt->suboptions & OPTIONS_MPTCP_MPC) { msk->can_ack = true; msk->remote_key = mp_opt->sndr_key; mptcp_crypto_key_sha(msk->remote_key, NULL, &ack_seq); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 0f0c026c5f8b..d3e6fd1615f1 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -26,6 +26,15 @@ #define OPTION_MPTCP_FASTCLOSE BIT(8) #define OPTION_MPTCP_PRIO BIT(9) #define OPTION_MPTCP_RST BIT(10) +#define OPTION_MPTCP_DSS BIT(11) +#define OPTION_MPTCP_FAIL BIT(12) + +#define OPTION_MPTCP_CSUMREQD BIT(13) + +#define OPTIONS_MPTCP_MPC (OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK | \ + OPTION_MPTCP_MPC_ACK) +#define OPTIONS_MPTCP_MPJ (OPTION_MPTCP_MPJ_SYN | OPTION_MPTCP_MPJ_SYNACK | \ + OPTION_MPTCP_MPJ_ACK) /* MPTCP option subtypes */ #define MPTCPOPT_MP_CAPABLE 0 @@ -67,6 +76,7 @@ #define TCPOLEN_MPTCP_PRIO_ALIGN 4 #define TCPOLEN_MPTCP_FASTCLOSE 12 #define TCPOLEN_MPTCP_RST 4 +#define TCPOLEN_MPTCP_FAIL 12 #define TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM (TCPOLEN_MPTCP_DSS_CHECKSUM + TCPOLEN_MPTCP_MPC_ACK_DATA) @@ -129,35 +139,28 @@ struct mptcp_options_received { u32 subflow_seq; u16 data_len; __sum16 csum; - u16 mp_capable : 1, - mp_join : 1, - fastclose : 1, - reset : 1, - dss : 1, - add_addr : 1, - rm_addr : 1, - mp_prio : 1, - echo : 1, - csum_reqd : 1, - backup : 1, - deny_join_id0 : 1; + u16 suboptions; u32 token; u32 nonce; - u64 thmac; - u8 hmac[MPTCPOPT_HMAC_LEN]; - u8 join_id; - u8 use_map:1, + u16 use_map:1, dsn64:1, data_fin:1, use_ack:1, ack64:1, mpc_map:1, + reset_reason:4, + reset_transient:1, + echo:1, + backup:1, + deny_join_id0:1, __unused:2; + u8 join_id; + u64 thmac; + u8 hmac[MPTCPOPT_HMAC_LEN]; struct mptcp_addr_info addr; struct mptcp_rm_list rm_list; u64 ahmac; - u8 reset_reason:4; - u8 reset_transient:1; + u64 fail_seq; }; static inline __be32 mptcp_option(u8 subopt, u8 len, u8 nib, u8 field) @@ -178,8 +181,6 @@ enum mptcp_pm_status { enum mptcp_addr_signal_status { MPTCP_ADD_ADDR_SIGNAL, MPTCP_ADD_ADDR_ECHO, - MPTCP_ADD_ADDR_IPV6, - MPTCP_ADD_ADDR_PORT, MPTCP_RM_ADDR_SIGNAL, }; @@ -230,12 +231,17 @@ struct mptcp_sock { struct sock *last_snd; int snd_burst; int old_wspace; + u64 recovery_snd_nxt; /* in recovery mode accept up to this seq; + * recovery related fields are under data_lock + * protection + */ u64 snd_una; u64 wnd_end; unsigned long timer_ival; u32 token; int rmem_released; unsigned long flags; + bool recovery; /* closing subflow write queue reinjected */ bool can_ack; bool fully_established; bool rcv_data_fin; @@ -425,9 +431,11 @@ struct mptcp_subflow_context { mpc_map : 1, backup : 1, send_mp_prio : 1, + send_mp_fail : 1, rx_eof : 1, can_ack : 1, /* only after processing the remote a key */ - disposable : 1; /* ctx can be free at ulp release time */ + disposable : 1, /* ctx can be free at ulp release time */ + stale : 1; /* unable to snd/rcv data, do not use for xmit */ enum mptcp_data_avail data_avail; u32 remote_nonce; u64 thmac; @@ -439,11 +447,13 @@ struct mptcp_subflow_context { u8 reset_seen:1; u8 reset_transient:1; u8 reset_reason:4; + u8 stale_count; long delegated_status; struct list_head delegated_node; /* link into delegated_action, protected by local BH */ - u32 setsockopt_seq; + u32 setsockopt_seq; + u32 stale_rcv_tstamp; struct sock *tcp_sock; /* tcp sk backpointer */ struct sock *conn; /* parent mptcp_sock */ @@ -549,31 +559,34 @@ static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *su clear_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status); } -int mptcp_is_enabled(struct net *net); -unsigned int mptcp_get_add_addr_timeout(struct net *net); -int mptcp_is_checksum_enabled(struct net *net); -int mptcp_allow_join_id0(struct net *net); +int mptcp_is_enabled(const struct net *net); +unsigned int mptcp_get_add_addr_timeout(const struct net *net); +int mptcp_is_checksum_enabled(const struct net *net); +int mptcp_allow_join_id0(const struct net *net); +unsigned int mptcp_stale_loss_cnt(const struct net *net); void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, struct mptcp_options_received *mp_opt); +bool __mptcp_retransmit_pending_data(struct sock *sk); +void __mptcp_push_pending(struct sock *sk, unsigned int flags); bool mptcp_subflow_data_available(struct sock *sk); void __init mptcp_subflow_init(void); void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how); void mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow); +void mptcp_subflow_send_ack(struct sock *ssk); void mptcp_subflow_reset(struct sock *ssk); void mptcp_sock_graft(struct sock *sk, struct socket *parent); struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk); /* called with sk socket lock held */ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, - const struct mptcp_addr_info *remote, - u8 flags, int ifindex); + const struct mptcp_addr_info *remote); int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock); void mptcp_info2sockaddr(const struct mptcp_addr_info *info, struct sockaddr_storage *addr, unsigned short family); -static inline bool mptcp_subflow_active(struct mptcp_subflow_context *subflow) +static inline bool __mptcp_subflow_active(struct mptcp_subflow_context *subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); @@ -585,6 +598,10 @@ static inline bool mptcp_subflow_active(struct mptcp_subflow_context *subflow) return ((1 << ssk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)); } +void mptcp_subflow_set_active(struct mptcp_subflow_context *subflow); + +bool mptcp_subflow_active(struct mptcp_subflow_context *subflow); + static inline void mptcp_subflow_tcp_fallback(struct sock *sk, struct mptcp_subflow_context *ctx) { @@ -596,6 +613,19 @@ static inline void mptcp_subflow_tcp_fallback(struct sock *sk, inet_csk(sk)->icsk_af_ops = ctx->icsk_af_ops; } +static inline bool mptcp_has_another_subflow(struct sock *ssk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk), *tmp; + struct mptcp_sock *msk = mptcp_sk(subflow->conn); + + mptcp_for_each_subflow(msk, tmp) { + if (tmp != subflow) + return true; + } + + return false; +} + void __init mptcp_proto_init(void); #if IS_ENABLED(CONFIG_MPTCP_IPV6) int __init mptcp_proto_v6_init(void); @@ -690,6 +720,8 @@ void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac); void __init mptcp_pm_init(void); void mptcp_pm_data_init(struct mptcp_sock *msk); +void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk); +void mptcp_pm_nl_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk); void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side); void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp); bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk); @@ -708,6 +740,7 @@ void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup); int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, struct mptcp_addr_info *addr, u8 bkup); +void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq); void mptcp_pm_free_anno_list(struct mptcp_sock *msk); bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk); struct mptcp_pm_add_entry * @@ -716,6 +749,8 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk, struct mptcp_pm_add_entry * mptcp_lookup_anno_list_by_saddr(struct mptcp_sock *msk, struct mptcp_addr_info *addr); +int mptcp_pm_get_flags_and_ifindex_by_id(struct net *net, unsigned int id, + u8 *flags, int *ifindex); int mptcp_pm_announce_addr(struct mptcp_sock *msk, const struct mptcp_addr_info *addr, @@ -730,22 +765,18 @@ void mptcp_event_addr_removed(const struct mptcp_sock *msk, u8 id); static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk) { - return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_SIGNAL); + return READ_ONCE(msk->pm.addr_signal) & + (BIT(MPTCP_ADD_ADDR_SIGNAL) | BIT(MPTCP_ADD_ADDR_ECHO)); } -static inline bool mptcp_pm_should_add_signal_echo(struct mptcp_sock *msk) -{ - return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_ECHO); -} - -static inline bool mptcp_pm_should_add_signal_ipv6(struct mptcp_sock *msk) +static inline bool mptcp_pm_should_add_signal_addr(struct mptcp_sock *msk) { - return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_IPV6); + return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_SIGNAL); } -static inline bool mptcp_pm_should_add_signal_port(struct mptcp_sock *msk) +static inline bool mptcp_pm_should_add_signal_echo(struct mptcp_sock *msk) { - return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_PORT); + return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_ECHO); } static inline bool mptcp_pm_should_rm_signal(struct mptcp_sock *msk) @@ -776,8 +807,10 @@ static inline int mptcp_rm_addr_len(const struct mptcp_rm_list *rm_list) return TCPOLEN_MPTCP_RM_ADDR_BASE + roundup(rm_list->nr - 1, 4) + 1; } -bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int remaining, - struct mptcp_addr_info *saddr, bool *echo, bool *port); +bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, struct sk_buff *skb, + unsigned int opt_size, unsigned int remaining, + struct mptcp_addr_info *addr, bool *echo, + bool *port, bool *drop_other_suboptions); bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, struct mptcp_rm_list *rm_list); int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 966f777d35ce..1de7ce883c37 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -141,6 +141,7 @@ static int subflow_check_req(struct request_sock *req, struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener); struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct mptcp_options_received mp_opt; + bool opt_mp_capable, opt_mp_join; pr_debug("subflow_req=%p, listener=%p", subflow_req, listener); @@ -154,16 +155,18 @@ static int subflow_check_req(struct request_sock *req, mptcp_get_options(sk_listener, skb, &mp_opt); - if (mp_opt.mp_capable) { + opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC); + opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ); + if (opt_mp_capable) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE); - if (mp_opt.mp_join) + if (opt_mp_join) return 0; - } else if (mp_opt.mp_join) { + } else if (opt_mp_join) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX); } - if (mp_opt.mp_capable && listener->request_mptcp) { + if (opt_mp_capable && listener->request_mptcp) { int err, retries = MPTCP_TOKEN_MAX_RETRIES; subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq; @@ -194,7 +197,7 @@ again: else SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_TOKENFALLBACKINIT); - } else if (mp_opt.mp_join && listener->request_mptcp) { + } else if (opt_mp_join && listener->request_mptcp) { subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq; subflow_req->mp_join = 1; subflow_req->backup = mp_opt.backup; @@ -243,15 +246,18 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req, struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener); struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct mptcp_options_received mp_opt; + bool opt_mp_capable, opt_mp_join; int err; subflow_init_req(req, sk_listener); mptcp_get_options(sk_listener, skb, &mp_opt); - if (mp_opt.mp_capable && mp_opt.mp_join) + opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC); + opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ); + if (opt_mp_capable && opt_mp_join) return -EINVAL; - if (mp_opt.mp_capable && listener->request_mptcp) { + if (opt_mp_capable && listener->request_mptcp) { if (mp_opt.sndr_key == 0) return -EINVAL; @@ -262,7 +268,7 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req, subflow_req->mp_capable = 1; subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq - 1; - } else if (mp_opt.mp_join && listener->request_mptcp) { + } else if (opt_mp_join && listener->request_mptcp) { if (!mptcp_token_join_cookie_init_state(subflow_req, skb)) return -EINVAL; @@ -394,7 +400,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->icsk_af_ops->sk_rx_dst_set(sk, skb); - /* be sure no special action on any packet other than syn-ack */ if (subflow->conn_finished) return; @@ -407,7 +412,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) mptcp_get_options(sk, skb, &mp_opt); if (subflow->request_mptcp) { - if (!mp_opt.mp_capable) { + if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC)) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEFALLBACK); mptcp_do_fallback(sk); @@ -415,7 +420,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) goto fallback; } - if (mp_opt.csum_reqd) + if (mp_opt.suboptions & OPTION_MPTCP_CSUMREQD) WRITE_ONCE(mptcp_sk(parent)->csum_enabled, true); if (mp_opt.deny_join_id0) WRITE_ONCE(mptcp_sk(parent)->pm.remote_deny_join_id0, true); @@ -430,15 +435,17 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) } else if (subflow->request_join) { u8 hmac[SHA256_DIGEST_SIZE]; - if (!mp_opt.mp_join) { + if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ)) { subflow->reset_reason = MPTCP_RST_EMPTCP; goto do_reset; } + subflow->backup = mp_opt.backup; subflow->thmac = mp_opt.thmac; subflow->remote_nonce = mp_opt.nonce; - pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u", subflow, - subflow->thmac, subflow->remote_nonce); + pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d", + subflow, subflow->thmac, subflow->remote_nonce, + subflow->backup); if (!subflow_thmac_valid(subflow)) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINACKMAC); @@ -634,10 +641,10 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn); - /* After child creation we must look for 'mp_capable' even when options + /* After child creation we must look for MPC even when options * are not parsed */ - mp_opt.mp_capable = 0; + mp_opt.suboptions = 0; /* hopefully temporary handling for MP_JOIN+syncookie */ subflow_req = mptcp_subflow_rsk(req); @@ -657,7 +664,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, * options. */ mptcp_get_options(sk, skb, &mp_opt); - if (!mp_opt.mp_capable) { + if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC)) { fallback = true; goto create_child; } @@ -667,7 +674,8 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, fallback = true; } else if (subflow_req->mp_join) { mptcp_get_options(sk, skb, &mp_opt); - if (!mp_opt.mp_join || !subflow_hmac_valid(req, &mp_opt) || + if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ) || + !subflow_hmac_valid(req, &mp_opt) || !mptcp_can_accept_new_subflow(subflow_req->msk)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC); fallback = true; @@ -724,7 +732,7 @@ create_child: /* with OoO packets we can reach here without ingress * mpc option */ - if (mp_opt.mp_capable) + if (mp_opt.suboptions & OPTIONS_MPTCP_MPC) mptcp_subflow_fully_established(ctx, &mp_opt); } else if (ctx->mp_join) { struct mptcp_sock *owner; @@ -908,6 +916,8 @@ static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff * csum = csum_partial(&header, sizeof(header), subflow->map_data_csum); if (unlikely(csum_fold(csum))) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR); + subflow->send_mp_fail = 1; + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPFAILTX); return subflow->mp_join ? MAPPING_INVALID : MAPPING_DUMMY; } @@ -1155,6 +1165,20 @@ no_data: fallback: /* RFC 8684 section 3.7. */ + if (subflow->send_mp_fail) { + if (mptcp_has_another_subflow(ssk)) { + while ((skb = skb_peek(&ssk->sk_receive_queue))) + sk_eat_skb(ssk, skb); + } + ssk->sk_err = EBADMSG; + tcp_set_state(ssk, TCP_CLOSE); + subflow->reset_transient = 0; + subflow->reset_reason = MPTCP_RST_EMIDDLEBOX; + tcp_send_active_reset(ssk, GFP_ATOMIC); + WRITE_ONCE(subflow->data_avail, 0); + return true; + } + if (subflow->mp_join || subflow->fully_established) { /* fatal protocol error, close the socket. * subflow_error_report() will introduce the appropriate barriers @@ -1353,8 +1377,7 @@ void mptcp_info2sockaddr(const struct mptcp_addr_info *info, } int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, - const struct mptcp_addr_info *remote, - u8 flags, int ifindex) + const struct mptcp_addr_info *remote) { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_subflow_context *subflow; @@ -1365,6 +1388,8 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, struct sock *ssk; u32 remote_token; int addrlen; + int ifindex; + u8 flags; int err; if (!mptcp_is_fully_established(sk)) @@ -1388,6 +1413,8 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, local_id = err; } + mptcp_pm_get_flags_and_ifindex_by_id(sock_net(sk), local_id, + &flags, &ifindex); subflow->remote_key = msk->remote_key; subflow->local_key = msk->local_key; subflow->token = msk->token; diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index 0b6cfd3b31e0..03757e76bb6b 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -80,6 +80,7 @@ enum { #define NCSI_OEM_MFR_BCM_ID 0x113d #define NCSI_OEM_MFR_INTEL_ID 0x157 /* Intel specific OEM command */ +#define NCSI_OEM_INTEL_CMD_GMA 0x06 /* CMD ID for Get MAC */ #define NCSI_OEM_INTEL_CMD_KEEP_PHY 0x20 /* CMD ID for Keep PHY up */ /* Broadcom specific OEM Command */ #define NCSI_OEM_BCM_CMD_GMA 0x01 /* CMD ID for Get MAC */ @@ -89,6 +90,7 @@ enum { #define NCSI_OEM_MLX_CMD_SMAF 0x01 /* CMD ID for Set MC Affinity */ #define NCSI_OEM_MLX_CMD_SMAF_PARAM 0x07 /* Parameter for SMAF */ /* OEM Command payload lengths*/ +#define NCSI_OEM_INTEL_CMD_GMA_LEN 5 #define NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN 7 #define NCSI_OEM_BCM_CMD_GMA_LEN 12 #define NCSI_OEM_MLX_CMD_GMA_LEN 8 @@ -99,6 +101,7 @@ enum { /* Mac address offset in OEM response */ #define BCM_MAC_ADDR_OFFSET 28 #define MLX_MAC_ADDR_OFFSET 8 +#define INTEL_MAC_ADDR_OFFSET 1 struct ncsi_channel_version { diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index 89c7742cd72e..7121ce2a47c0 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -795,13 +795,36 @@ static int ncsi_oem_smaf_mlx(struct ncsi_cmd_arg *nca) return ret; } +static int ncsi_oem_gma_handler_intel(struct ncsi_cmd_arg *nca) +{ + unsigned char data[NCSI_OEM_INTEL_CMD_GMA_LEN]; + int ret = 0; + + nca->payload = NCSI_OEM_INTEL_CMD_GMA_LEN; + + memset(data, 0, NCSI_OEM_INTEL_CMD_GMA_LEN); + *(unsigned int *)data = ntohl((__force __be32)NCSI_OEM_MFR_INTEL_ID); + data[4] = NCSI_OEM_INTEL_CMD_GMA; + + nca->data = data; + + ret = ncsi_xmit_cmd(nca); + if (ret) + netdev_err(nca->ndp->ndev.dev, + "NCSI: Failed to transmit cmd 0x%x during configure\n", + nca->type); + + return ret; +} + /* OEM Command handlers initialization */ static struct ncsi_oem_gma_handler { unsigned int mfr_id; int (*handler)(struct ncsi_cmd_arg *nca); } ncsi_oem_gma_handlers[] = { { NCSI_OEM_MFR_BCM_ID, ncsi_oem_gma_handler_bcm }, - { NCSI_OEM_MFR_MLX_ID, ncsi_oem_gma_handler_mlx } + { NCSI_OEM_MFR_MLX_ID, ncsi_oem_gma_handler_mlx }, + { NCSI_OEM_MFR_INTEL_ID, ncsi_oem_gma_handler_intel } }; static int ncsi_gma_handler(struct ncsi_cmd_arg *nca, unsigned int mf_id) diff --git a/net/ncsi/ncsi-pkt.h b/net/ncsi/ncsi-pkt.h index 80938b338fee..ba66c7dc3a21 100644 --- a/net/ncsi/ncsi-pkt.h +++ b/net/ncsi/ncsi-pkt.h @@ -178,6 +178,12 @@ struct ncsi_rsp_oem_bcm_pkt { unsigned char data[]; /* Cmd specific Data */ }; +/* Intel Response Data */ +struct ncsi_rsp_oem_intel_pkt { + unsigned char cmd; /* OEM Command ID */ + unsigned char data[]; /* Cmd specific Data */ +}; + /* Get Link Status */ struct ncsi_rsp_gls_pkt { struct ncsi_rsp_pkt_hdr rsp; /* Response header */ diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index d48374894817..6447a09932f5 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -699,9 +699,51 @@ static int ncsi_rsp_handler_oem_bcm(struct ncsi_request *nr) return 0; } +/* Response handler for Intel command Get Mac Address */ +static int ncsi_rsp_handler_oem_intel_gma(struct ncsi_request *nr) +{ + struct ncsi_dev_priv *ndp = nr->ndp; + struct net_device *ndev = ndp->ndev.dev; + const struct net_device_ops *ops = ndev->netdev_ops; + struct ncsi_rsp_oem_pkt *rsp; + struct sockaddr saddr; + int ret = 0; + + /* Get the response header */ + rsp = (struct ncsi_rsp_oem_pkt *)skb_network_header(nr->rsp); + + saddr.sa_family = ndev->type; + ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + memcpy(saddr.sa_data, &rsp->data[INTEL_MAC_ADDR_OFFSET], ETH_ALEN); + /* Increase mac address by 1 for BMC's address */ + eth_addr_inc((u8 *)saddr.sa_data); + if (!is_valid_ether_addr((const u8 *)saddr.sa_data)) + return -ENXIO; + + /* Set the flag for GMA command which should only be called once */ + ndp->gma_flag = 1; + + ret = ops->ndo_set_mac_address(ndev, &saddr); + if (ret < 0) + netdev_warn(ndev, + "NCSI: 'Writing mac address to device failed\n"); + + return ret; +} + /* Response handler for Intel card */ static int ncsi_rsp_handler_oem_intel(struct ncsi_request *nr) { + struct ncsi_rsp_oem_intel_pkt *intel; + struct ncsi_rsp_oem_pkt *rsp; + + /* Get the response header */ + rsp = (struct ncsi_rsp_oem_pkt *)skb_network_header(nr->rsp); + intel = (struct ncsi_rsp_oem_intel_pkt *)(rsp->data); + + if (intel->cmd == NCSI_OEM_INTEL_CMD_GMA) + return ncsi_rsp_handler_oem_intel_gma(nr); + return 0; } diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 049890e00a3d..aab20e575ecd 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -212,3 +212,6 @@ obj-$(CONFIG_IP_SET) += ipset/ # IPVS obj-$(CONFIG_IP_VS) += ipvs/ + +# lwtunnel +obj-$(CONFIG_LWTUNNEL) += nf_hooks_lwtunnel.o diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index d1bef23fd4f5..dd30c03d5a23 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -132,8 +132,11 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) return ret; - if (ip > ip_to) + if (ip > ip_to) { + if (ip_to == 0) + return -IPSET_ERR_HASH_ELEM; swap(ip, ip_to); + } } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); @@ -144,6 +147,10 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1); + /* 64bit division is not allowed on 32bit */ + if (((u64)ip_to - ip + 1) >> (32 - h->netmask) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) { ip = ntohl(h->next.ip); e.ip = htonl(ip); diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c index 18346d18aa16..153de3457423 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmark.c +++ b/net/netfilter/ipset/ip_set_hash_ipmark.c @@ -121,6 +121,8 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], e.mark = ntohl(nla_get_be32(tb[IPSET_ATTR_MARK])); e.mark &= h->markmask; + if (e.mark == 0 && e.ip == 0) + return -IPSET_ERR_HASH_ELEM; if (adt == IPSET_TEST || !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR])) { @@ -133,8 +135,11 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) return ret; - if (ip > ip_to) + if (ip > ip_to) { + if (e.mark == 0 && ip_to == 0) + return -IPSET_ERR_HASH_ELEM; swap(ip, ip_to); + } } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); @@ -143,6 +148,9 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], ip_set_mask_from_to(ip, ip_to, cidr); } + if (((u64)ip_to - ip + 1) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index e1ca11196515..7303138e46be 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -173,6 +173,9 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } + if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index ab179e064597..334fb1ad0e86 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -180,6 +180,9 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } + if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 8f075b44cf64..7df94f437f60 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -253,6 +253,9 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } + if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; + ip2_to = ip2_from; if (tb[IPSET_ATTR_IP2_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2_TO], &ip2_to); diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index c1a11f041ac6..1422739d9aa2 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -140,7 +140,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_net4_elem e = { .cidr = HOST_MASK }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip = 0, ip_to = 0; + u32 ip = 0, ip_to = 0, ipn, n = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -188,6 +188,15 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], if (ip + UINT_MAX == ip_to) return -IPSET_ERR_HASH_RANGE; } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr); + n++; + } while (ipn++ < ip_to); + + if (n > IPSET_MAX_RANGE) + return -ERANGE; + if (retried) ip = ntohl(h->next.ip); do { diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index ddd51c2e1cb3..9810f5bf63f5 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -202,7 +202,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netiface4_elem e = { .cidr = HOST_MASK, .elem = 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 ip = 0, ip_to = 0; + u32 ip = 0, ip_to = 0, ipn, n = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -256,6 +256,14 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip, ip_to, e.cidr); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr); + n++; + } while (ipn++ < ip_to); + + if (n > IPSET_MAX_RANGE) + return -ERANGE; if (retried) ip = ntohl(h->next.ip); diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index 6532f0505e66..3d09eefe998a 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -168,7 +168,8 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_netnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0; - u32 ip2 = 0, ip2_from = 0, ip2_to = 0; + u32 ip2 = 0, ip2_from = 0, ip2_to = 0, ipn; + u64 n = 0, m = 0; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -244,6 +245,19 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]); + n++; + } while (ipn++ < ip_to); + ipn = ip2_from; + do { + ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]); + m++; + } while (ipn++ < ip2_to); + + if (n*m > IPSET_MAX_RANGE) + return -ERANGE; if (retried) { ip = ntohl(h->next.ip[0]); diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index ec1564a1cb5a..09cf72eb37f8 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -158,7 +158,8 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport4_elem e = { .cidr = HOST_MASK - 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); - u32 port, port_to, p = 0, ip = 0, ip_to = 0; + u32 port, port_to, p = 0, ip = 0, ip_to = 0, ipn; + u64 n = 0; bool with_ports = false; u8 cidr; int ret; @@ -235,6 +236,14 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip, ip_to, e.cidr + 1); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &cidr); + n++; + } while (ipn++ < ip_to); + + if (n*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; if (retried) { ip = ntohl(h->next.ip); diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index 0e91d1e82f1c..19bcdb3141f6 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -182,7 +182,8 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_netportnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0, p = 0, port, port_to; - u32 ip2_from = 0, ip2_to = 0, ip2; + u32 ip2_from = 0, ip2_to = 0, ip2, ipn; + u64 n = 0, m = 0; bool with_ports = false; int ret; @@ -284,6 +285,19 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], } else { ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]); } + ipn = ip; + do { + ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]); + n++; + } while (ipn++ < ip_to); + ipn = ip2_from; + do { + ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]); + m++; + } while (ipn++ < ip2_to); + + if (n*m*(port_to - port + 1) > IPSET_MAX_RANGE) + return -ERANGE; if (retried) { ip = ntohl(h->next.ip[0]); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 83c52df85870..94e18fb9690d 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -21,7 +21,6 @@ #include <linux/stddef.h> #include <linux/slab.h> #include <linux/random.h> -#include <linux/jhash.h> #include <linux/siphash.h> #include <linux/err.h> #include <linux/percpu.h> @@ -66,22 +65,19 @@ EXPORT_SYMBOL_GPL(nf_conntrack_hash); struct conntrack_gc_work { struct delayed_work dwork; - u32 last_bucket; + u32 next_bucket; bool exiting; bool early_drop; - long next_gc_run; }; static __read_mostly struct kmem_cache *nf_conntrack_cachep; static DEFINE_SPINLOCK(nf_conntrack_locks_all_lock); static __read_mostly bool nf_conntrack_locks_all; -/* every gc cycle scans at most 1/GC_MAX_BUCKETS_DIV part of table */ -#define GC_MAX_BUCKETS_DIV 128u -/* upper bound of full table scan */ -#define GC_MAX_SCAN_JIFFIES (16u * HZ) -/* desired ratio of entries found to be expired */ -#define GC_EVICT_RATIO 50u +#define GC_SCAN_INTERVAL (120u * HZ) +#define GC_SCAN_MAX_DURATION msecs_to_jiffies(10) + +#define MAX_CHAINLEN 64u static struct conntrack_gc_work conntrack_gc_work; @@ -189,25 +185,31 @@ EXPORT_SYMBOL_GPL(nf_conntrack_htable_size); unsigned int nf_conntrack_max __read_mostly; EXPORT_SYMBOL_GPL(nf_conntrack_max); seqcount_spinlock_t nf_conntrack_generation __read_mostly; -static unsigned int nf_conntrack_hash_rnd __read_mostly; +static siphash_key_t nf_conntrack_hash_rnd __read_mostly; static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, const struct net *net) { - unsigned int n; - u32 seed; + struct { + struct nf_conntrack_man src; + union nf_inet_addr dst_addr; + u32 net_mix; + u16 dport; + u16 proto; + } __aligned(SIPHASH_ALIGNMENT) combined; get_random_once(&nf_conntrack_hash_rnd, sizeof(nf_conntrack_hash_rnd)); - /* The direction must be ignored, so we hash everything up to the - * destination ports (which is a multiple of 4) and treat the last - * three bytes manually. - */ - seed = nf_conntrack_hash_rnd ^ net_hash_mix(net); - n = (sizeof(tuple->src) + sizeof(tuple->dst.u3)) / sizeof(u32); - return jhash2((u32 *)tuple, n, seed ^ - (((__force __u16)tuple->dst.u.all << 16) | - tuple->dst.protonum)); + memset(&combined, 0, sizeof(combined)); + + /* The direction must be ignored, so handle usable members manually. */ + combined.src = tuple->src; + combined.dst_addr = tuple->dst.u3; + combined.net_mix = net_hash_mix(net); + combined.dport = (__force __u16)tuple->dst.u.all; + combined.proto = tuple->dst.protonum; + + return (u32)siphash(&combined, sizeof(combined), &nf_conntrack_hash_rnd); } static u32 scale_hash(u32 hash) @@ -670,8 +672,13 @@ bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report) return false; tstamp = nf_conn_tstamp_find(ct); - if (tstamp && tstamp->stop == 0) + if (tstamp) { + s32 timeout = ct->timeout - nfct_time_stamp; + tstamp->stop = ktime_get_real_ns(); + if (timeout < 0) + tstamp->stop -= jiffies_to_nsecs(-timeout); + } if (nf_conntrack_event_report(IPCT_DESTROY, ct, portid, report) < 0) { @@ -835,7 +842,9 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) unsigned int hash, reply_hash; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; + unsigned int chainlen = 0; unsigned int sequence; + int err = -EEXIST; zone = nf_ct_zone(ct); @@ -849,15 +858,24 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); /* See if there's one in the list already, including reverse */ - hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode) + hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode) { if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, zone, net)) goto out; - hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode) + if (chainlen++ > MAX_CHAINLEN) + goto chaintoolong; + } + + chainlen = 0; + + hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode) { if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, zone, net)) goto out; + if (chainlen++ > MAX_CHAINLEN) + goto chaintoolong; + } smp_wmb(); /* The caller holds a reference to this object */ @@ -867,11 +885,13 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) NF_CT_STAT_INC(net, insert); local_bh_enable(); return 0; - +chaintoolong: + NF_CT_STAT_INC(net, chaintoolong); + err = -ENOSPC; out: nf_conntrack_double_unlock(hash, reply_hash); local_bh_enable(); - return -EEXIST; + return err; } EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert); @@ -1084,6 +1104,7 @@ int __nf_conntrack_confirm(struct sk_buff *skb) { const struct nf_conntrack_zone *zone; + unsigned int chainlen = 0, sequence; unsigned int hash, reply_hash; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; @@ -1091,7 +1112,6 @@ __nf_conntrack_confirm(struct sk_buff *skb) struct hlist_nulls_node *n; enum ip_conntrack_info ctinfo; struct net *net; - unsigned int sequence; int ret = NF_DROP; ct = nf_ct_get(skb, &ctinfo); @@ -1151,15 +1171,28 @@ __nf_conntrack_confirm(struct sk_buff *skb) /* See if there's one in the list already, including reverse: NAT could have grabbed it without realizing, since we're not in the hash. If there is, we lost race. */ - hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode) + hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode) { if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, zone, net)) goto out; + if (chainlen++ > MAX_CHAINLEN) + goto chaintoolong; + } - hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode) + chainlen = 0; + hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode) { if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, zone, net)) goto out; + if (chainlen++ > MAX_CHAINLEN) { +chaintoolong: + nf_ct_add_to_dying_list(ct); + NF_CT_STAT_INC(net, chaintoolong); + NF_CT_STAT_INC(net, insert_failed); + ret = NF_DROP; + goto dying; + } + } /* Timer relative to confirmation time, not original setting time, otherwise we'd get timer wrap in @@ -1358,17 +1391,13 @@ static bool gc_worker_can_early_drop(const struct nf_conn *ct) static void gc_worker(struct work_struct *work) { - unsigned int min_interval = max(HZ / GC_MAX_BUCKETS_DIV, 1u); - unsigned int i, goal, buckets = 0, expired_count = 0; - unsigned int nf_conntrack_max95 = 0; + unsigned long end_time = jiffies + GC_SCAN_MAX_DURATION; + unsigned int i, hashsz, nf_conntrack_max95 = 0; + unsigned long next_run = GC_SCAN_INTERVAL; struct conntrack_gc_work *gc_work; - unsigned int ratio, scanned = 0; - unsigned long next_run; - gc_work = container_of(work, struct conntrack_gc_work, dwork.work); - goal = nf_conntrack_htable_size / GC_MAX_BUCKETS_DIV; - i = gc_work->last_bucket; + i = gc_work->next_bucket; if (gc_work->early_drop) nf_conntrack_max95 = nf_conntrack_max / 100u * 95u; @@ -1376,15 +1405,15 @@ static void gc_worker(struct work_struct *work) struct nf_conntrack_tuple_hash *h; struct hlist_nulls_head *ct_hash; struct hlist_nulls_node *n; - unsigned int hashsz; struct nf_conn *tmp; - i++; rcu_read_lock(); nf_conntrack_get_ht(&ct_hash, &hashsz); - if (i >= hashsz) - i = 0; + if (i >= hashsz) { + rcu_read_unlock(); + break; + } hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[i], hnnode) { struct nf_conntrack_net *cnet; @@ -1392,7 +1421,6 @@ static void gc_worker(struct work_struct *work) tmp = nf_ct_tuplehash_to_ctrack(h); - scanned++; if (test_bit(IPS_OFFLOAD_BIT, &tmp->status)) { nf_ct_offload_timeout(tmp); continue; @@ -1400,7 +1428,6 @@ static void gc_worker(struct work_struct *work) if (nf_ct_is_expired(tmp)) { nf_ct_gc_expired(tmp); - expired_count++; continue; } @@ -1433,7 +1460,14 @@ static void gc_worker(struct work_struct *work) */ rcu_read_unlock(); cond_resched(); - } while (++buckets < goal); + i++; + + if (time_after(jiffies, end_time) && i < hashsz) { + gc_work->next_bucket = i; + next_run = 0; + break; + } + } while (i < hashsz); if (gc_work->exiting) return; @@ -1444,40 +1478,17 @@ static void gc_worker(struct work_struct *work) * * This worker is only here to reap expired entries when system went * idle after a busy period. - * - * The heuristics below are supposed to balance conflicting goals: - * - * 1. Minimize time until we notice a stale entry - * 2. Maximize scan intervals to not waste cycles - * - * Normally, expire ratio will be close to 0. - * - * As soon as a sizeable fraction of the entries have expired - * increase scan frequency. */ - ratio = scanned ? expired_count * 100 / scanned : 0; - if (ratio > GC_EVICT_RATIO) { - gc_work->next_gc_run = min_interval; - } else { - unsigned int max = GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV; - - BUILD_BUG_ON((GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV) == 0); - - gc_work->next_gc_run += min_interval; - if (gc_work->next_gc_run > max) - gc_work->next_gc_run = max; + if (next_run) { + gc_work->early_drop = false; + gc_work->next_bucket = 0; } - - next_run = gc_work->next_gc_run; - gc_work->last_bucket = i; - gc_work->early_drop = false; queue_delayed_work(system_power_efficient_wq, &gc_work->dwork, next_run); } static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work) { INIT_DEFERRABLE_WORK(&gc_work->dwork, gc_worker); - gc_work->next_gc_run = HZ; gc_work->exiting = false; } @@ -2616,26 +2627,24 @@ int nf_conntrack_init_start(void) spin_lock_init(&nf_conntrack_locks[i]); if (!nf_conntrack_htable_size) { - /* Idea from tcp.c: use 1/16384 of memory. - * On i386: 32MB machine has 512 buckets. - * >= 1GB machines have 16384 buckets. - * >= 4GB machines have 65536 buckets. - */ nf_conntrack_htable_size = (((nr_pages << PAGE_SHIFT) / 16384) / sizeof(struct hlist_head)); - if (nr_pages > (4 * (1024 * 1024 * 1024 / PAGE_SIZE))) - nf_conntrack_htable_size = 65536; + if (BITS_PER_LONG >= 64 && + nr_pages > (4 * (1024 * 1024 * 1024 / PAGE_SIZE))) + nf_conntrack_htable_size = 262144; else if (nr_pages > (1024 * 1024 * 1024 / PAGE_SIZE)) - nf_conntrack_htable_size = 16384; - if (nf_conntrack_htable_size < 32) - nf_conntrack_htable_size = 32; - - /* Use a max. factor of four by default to get the same max as - * with the old struct list_heads. When a table size is given - * we use the old value of 8 to avoid reducing the max. - * entries. */ - max_factor = 4; + nf_conntrack_htable_size = 65536; + + if (nf_conntrack_htable_size < 1024) + nf_conntrack_htable_size = 1024; + /* Use a max. factor of one by default to keep the average + * hash chain length at 2 entries. Each entry has to be added + * twice (once for original direction, once for reply). + * When a table size is given we use the old value of 8 to + * avoid implicit reduction of the max entries setting. + */ + max_factor = 1; } nf_conntrack_hash = nf_ct_alloc_hashtable(&nf_conntrack_htable_size, 1); diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 296e4a171bd1..41768ff19464 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -130,58 +130,77 @@ static void ecache_work(struct work_struct *work) schedule_delayed_work(&cnet->ecache_dwork, delay); } -int nf_conntrack_eventmask_report(unsigned int eventmask, struct nf_conn *ct, - u32 portid, int report) +static int __nf_conntrack_eventmask_report(struct nf_conntrack_ecache *e, + const unsigned int events, + const unsigned long missed, + const struct nf_ct_event *item) { - int ret = 0; - struct net *net = nf_ct_net(ct); + struct nf_conn *ct = item->ct; + struct net *net = nf_ct_net(item->ct); struct nf_ct_event_notifier *notify; - struct nf_conntrack_ecache *e; + int ret; + + if (!((events | missed) & e->ctmask)) + return 0; rcu_read_lock(); + notify = rcu_dereference(net->ct.nf_conntrack_event_cb); - if (!notify) - goto out_unlock; + if (!notify) { + rcu_read_unlock(); + return 0; + } + + ret = notify->ct_event(events | missed, item); + rcu_read_unlock(); + + if (likely(ret >= 0 && missed == 0)) + return 0; + + spin_lock_bh(&ct->lock); + if (ret < 0) + e->missed |= events; + else + e->missed &= ~missed; + spin_unlock_bh(&ct->lock); + + return ret; +} + +int nf_conntrack_eventmask_report(unsigned int events, struct nf_conn *ct, + u32 portid, int report) +{ + struct nf_conntrack_ecache *e; + struct nf_ct_event item; + unsigned long missed; + int ret; + + if (!nf_ct_is_confirmed(ct)) + return 0; e = nf_ct_ecache_find(ct); if (!e) - goto out_unlock; + return 0; - if (nf_ct_is_confirmed(ct)) { - struct nf_ct_event item = { - .ct = ct, - .portid = e->portid ? e->portid : portid, - .report = report - }; - /* This is a resent of a destroy event? If so, skip missed */ - unsigned long missed = e->portid ? 0 : e->missed; - - if (!((eventmask | missed) & e->ctmask)) - goto out_unlock; - - ret = notify->fcn(eventmask | missed, &item); - if (unlikely(ret < 0 || missed)) { - spin_lock_bh(&ct->lock); - if (ret < 0) { - /* This is a destroy event that has been - * triggered by a process, we store the PORTID - * to include it in the retransmission. - */ - if (eventmask & (1 << IPCT_DESTROY)) { - if (e->portid == 0 && portid != 0) - e->portid = portid; - e->state = NFCT_ECACHE_DESTROY_FAIL; - } else { - e->missed |= eventmask; - } - } else { - e->missed &= ~missed; - } - spin_unlock_bh(&ct->lock); - } + memset(&item, 0, sizeof(item)); + + item.ct = ct; + item.portid = e->portid ? e->portid : portid; + item.report = report; + + /* This is a resent of a destroy event? If so, skip missed */ + missed = e->portid ? 0 : e->missed; + + ret = __nf_conntrack_eventmask_report(e, events, missed, &item); + if (unlikely(ret < 0 && (events & (1 << IPCT_DESTROY)))) { + /* This is a destroy event that has been triggered by a process, + * we store the PORTID to include it in the retransmission. + */ + if (e->portid == 0 && portid != 0) + e->portid = portid; + e->state = NFCT_ECACHE_DESTROY_FAIL; } -out_unlock: - rcu_read_unlock(); + return ret; } EXPORT_SYMBOL_GPL(nf_conntrack_eventmask_report); @@ -190,53 +209,28 @@ EXPORT_SYMBOL_GPL(nf_conntrack_eventmask_report); * disabled softirqs */ void nf_ct_deliver_cached_events(struct nf_conn *ct) { - struct net *net = nf_ct_net(ct); - unsigned long events, missed; - struct nf_ct_event_notifier *notify; struct nf_conntrack_ecache *e; struct nf_ct_event item; - int ret; - - rcu_read_lock(); - notify = rcu_dereference(net->ct.nf_conntrack_event_cb); - if (notify == NULL) - goto out_unlock; + unsigned long events; if (!nf_ct_is_confirmed(ct) || nf_ct_is_dying(ct)) - goto out_unlock; + return; e = nf_ct_ecache_find(ct); if (e == NULL) - goto out_unlock; + return; events = xchg(&e->cache, 0); - /* We make a copy of the missed event cache without taking - * the lock, thus we may send missed events twice. However, - * this does not harm and it happens very rarely. */ - missed = e->missed; - - if (!((events | missed) & e->ctmask)) - goto out_unlock; - item.ct = ct; item.portid = 0; item.report = 0; - ret = notify->fcn(events | missed, &item); - - if (likely(ret == 0 && !missed)) - goto out_unlock; - - spin_lock_bh(&ct->lock); - if (ret < 0) - e->missed |= events; - else - e->missed &= ~missed; - spin_unlock_bh(&ct->lock); - -out_unlock: - rcu_read_unlock(); + /* We make a copy of the missed event cache without taking + * the lock, thus we may send missed events twice. However, + * this does not harm and it happens very rarely. + */ + __nf_conntrack_eventmask_report(e, events, e->missed, &item); } EXPORT_SYMBOL_GPL(nf_ct_deliver_cached_events); @@ -246,11 +240,11 @@ void nf_ct_expect_event_report(enum ip_conntrack_expect_events event, { struct net *net = nf_ct_exp_net(exp); - struct nf_exp_event_notifier *notify; + struct nf_ct_event_notifier *notify; struct nf_conntrack_ecache *e; rcu_read_lock(); - notify = rcu_dereference(net->ct.nf_expect_event_cb); + notify = rcu_dereference(net->ct.nf_conntrack_event_cb); if (!notify) goto out_unlock; @@ -264,86 +258,35 @@ void nf_ct_expect_event_report(enum ip_conntrack_expect_events event, .portid = portid, .report = report }; - notify->fcn(1 << event, &item); + notify->exp_event(1 << event, &item); } out_unlock: rcu_read_unlock(); } -int nf_conntrack_register_notifier(struct net *net, - struct nf_ct_event_notifier *new) +void nf_conntrack_register_notifier(struct net *net, + const struct nf_ct_event_notifier *new) { - int ret; struct nf_ct_event_notifier *notify; mutex_lock(&nf_ct_ecache_mutex); notify = rcu_dereference_protected(net->ct.nf_conntrack_event_cb, lockdep_is_held(&nf_ct_ecache_mutex)); - if (notify != NULL) { - ret = -EBUSY; - goto out_unlock; - } + WARN_ON_ONCE(notify); rcu_assign_pointer(net->ct.nf_conntrack_event_cb, new); - ret = 0; - -out_unlock: mutex_unlock(&nf_ct_ecache_mutex); - return ret; } EXPORT_SYMBOL_GPL(nf_conntrack_register_notifier); -void nf_conntrack_unregister_notifier(struct net *net, - struct nf_ct_event_notifier *new) +void nf_conntrack_unregister_notifier(struct net *net) { - struct nf_ct_event_notifier *notify; - mutex_lock(&nf_ct_ecache_mutex); - notify = rcu_dereference_protected(net->ct.nf_conntrack_event_cb, - lockdep_is_held(&nf_ct_ecache_mutex)); - BUG_ON(notify != new); RCU_INIT_POINTER(net->ct.nf_conntrack_event_cb, NULL); mutex_unlock(&nf_ct_ecache_mutex); - /* synchronize_rcu() is called from ctnetlink_exit. */ + /* synchronize_rcu() is called after netns pre_exit */ } EXPORT_SYMBOL_GPL(nf_conntrack_unregister_notifier); -int nf_ct_expect_register_notifier(struct net *net, - struct nf_exp_event_notifier *new) -{ - int ret; - struct nf_exp_event_notifier *notify; - - mutex_lock(&nf_ct_ecache_mutex); - notify = rcu_dereference_protected(net->ct.nf_expect_event_cb, - lockdep_is_held(&nf_ct_ecache_mutex)); - if (notify != NULL) { - ret = -EBUSY; - goto out_unlock; - } - rcu_assign_pointer(net->ct.nf_expect_event_cb, new); - ret = 0; - -out_unlock: - mutex_unlock(&nf_ct_ecache_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(nf_ct_expect_register_notifier); - -void nf_ct_expect_unregister_notifier(struct net *net, - struct nf_exp_event_notifier *new) -{ - struct nf_exp_event_notifier *notify; - - mutex_lock(&nf_ct_ecache_mutex); - notify = rcu_dereference_protected(net->ct.nf_expect_event_cb, - lockdep_is_held(&nf_ct_ecache_mutex)); - BUG_ON(notify != new); - RCU_INIT_POINTER(net->ct.nf_expect_event_cb, NULL); - mutex_unlock(&nf_ct_ecache_mutex); - /* synchronize_rcu() is called from ctnetlink_exit. */ -} -EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier); - void nf_conntrack_ecache_work(struct net *net, enum nf_ct_ecache_state state) { struct nf_conntrack_net *cnet = nf_ct_pernet(net); diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 1e851bc2e61a..f562eeef4234 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -17,7 +17,7 @@ #include <linux/err.h> #include <linux/percpu.h> #include <linux/kernel.h> -#include <linux/jhash.h> +#include <linux/siphash.h> #include <linux/moduleparam.h> #include <linux/export.h> #include <net/net_namespace.h> @@ -41,7 +41,7 @@ EXPORT_SYMBOL_GPL(nf_ct_expect_hash); unsigned int nf_ct_expect_max __read_mostly; static struct kmem_cache *nf_ct_expect_cachep __read_mostly; -static unsigned int nf_ct_expect_hashrnd __read_mostly; +static siphash_key_t nf_ct_expect_hashrnd __read_mostly; /* nf_conntrack_expect helper functions */ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp, @@ -81,15 +81,26 @@ static void nf_ct_expectation_timed_out(struct timer_list *t) static unsigned int nf_ct_expect_dst_hash(const struct net *n, const struct nf_conntrack_tuple *tuple) { - unsigned int hash, seed; + struct { + union nf_inet_addr dst_addr; + u32 net_mix; + u16 dport; + u8 l3num; + u8 protonum; + } __aligned(SIPHASH_ALIGNMENT) combined; + u32 hash; get_random_once(&nf_ct_expect_hashrnd, sizeof(nf_ct_expect_hashrnd)); - seed = nf_ct_expect_hashrnd ^ net_hash_mix(n); + memset(&combined, 0, sizeof(combined)); - hash = jhash2(tuple->dst.u3.all, ARRAY_SIZE(tuple->dst.u3.all), - (((tuple->dst.protonum ^ tuple->src.l3num) << 16) | - (__force __u16)tuple->dst.u.all) ^ seed); + combined.dst_addr = tuple->dst.u3; + combined.net_mix = net_hash_mix(n); + combined.dport = (__force __u16)tuple->dst.u.all; + combined.l3num = tuple->src.l3num; + combined.protonum = tuple->dst.protonum; + + hash = siphash(&combined, sizeof(combined), &nf_ct_expect_hashrnd); return reciprocal_scale(hash, nf_ct_expect_hsize); } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index e81af33b233b..f1e5443fe7c7 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -706,7 +706,7 @@ static size_t ctnetlink_nlmsg_size(const struct nf_conn *ct) } static int -ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) +ctnetlink_conntrack_event(unsigned int events, const struct nf_ct_event *item) { const struct nf_conntrack_zone *zone; struct net *net; @@ -852,6 +852,11 @@ static int ctnetlink_done(struct netlink_callback *cb) return 0; } +struct ctnetlink_filter_u32 { + u32 val; + u32 mask; +}; + struct ctnetlink_filter { u8 family; @@ -862,10 +867,8 @@ struct ctnetlink_filter { struct nf_conntrack_tuple reply; struct nf_conntrack_zone zone; - struct { - u_int32_t val; - u_int32_t mask; - } mark; + struct ctnetlink_filter_u32 mark; + struct ctnetlink_filter_u32 status; }; static const struct nla_policy cta_filter_nla_policy[CTA_FILTER_MAX + 1] = { @@ -907,6 +910,46 @@ static int ctnetlink_parse_tuple_filter(const struct nlattr * const cda[], struct nf_conntrack_zone *zone, u_int32_t flags); +static int ctnetlink_filter_parse_mark(struct ctnetlink_filter_u32 *mark, + const struct nlattr * const cda[]) +{ +#ifdef CONFIG_NF_CONNTRACK_MARK + if (cda[CTA_MARK]) { + mark->val = ntohl(nla_get_be32(cda[CTA_MARK])); + + if (cda[CTA_MARK_MASK]) + mark->mask = ntohl(nla_get_be32(cda[CTA_MARK_MASK])); + else + mark->mask = 0xffffffff; + } else if (cda[CTA_MARK_MASK]) { + return -EINVAL; + } +#endif + return 0; +} + +static int ctnetlink_filter_parse_status(struct ctnetlink_filter_u32 *status, + const struct nlattr * const cda[]) +{ + if (cda[CTA_STATUS]) { + status->val = ntohl(nla_get_be32(cda[CTA_STATUS])); + if (cda[CTA_STATUS_MASK]) + status->mask = ntohl(nla_get_be32(cda[CTA_STATUS_MASK])); + else + status->mask = status->val; + + /* status->val == 0? always true, else always false. */ + if (status->mask == 0) + return -EINVAL; + } else if (cda[CTA_STATUS_MASK]) { + return -EINVAL; + } + + /* CTA_STATUS is NLA_U32, if this fires UAPI needs to be extended */ + BUILD_BUG_ON(__IPS_MAX_BIT >= 32); + return 0; +} + static struct ctnetlink_filter * ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) { @@ -924,18 +967,14 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) filter->family = family; -#ifdef CONFIG_NF_CONNTRACK_MARK - if (cda[CTA_MARK]) { - filter->mark.val = ntohl(nla_get_be32(cda[CTA_MARK])); - if (cda[CTA_MARK_MASK]) - filter->mark.mask = ntohl(nla_get_be32(cda[CTA_MARK_MASK])); - else - filter->mark.mask = 0xffffffff; - } else if (cda[CTA_MARK_MASK]) { - err = -EINVAL; + err = ctnetlink_filter_parse_mark(&filter->mark, cda); + if (err) goto err_filter; - } -#endif + + err = ctnetlink_filter_parse_status(&filter->status, cda); + if (err) + goto err_filter; + if (!cda[CTA_FILTER]) return filter; @@ -989,7 +1028,7 @@ err_filter: static bool ctnetlink_needs_filter(u8 family, const struct nlattr * const *cda) { - return family || cda[CTA_MARK] || cda[CTA_FILTER]; + return family || cda[CTA_MARK] || cda[CTA_FILTER] || cda[CTA_STATUS]; } static int ctnetlink_start(struct netlink_callback *cb) @@ -1082,6 +1121,7 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data) { struct ctnetlink_filter *filter = data; struct nf_conntrack_tuple *tuple; + u32 status; if (filter == NULL) goto out; @@ -1113,6 +1153,9 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data) if ((ct->mark & filter->mark.mask) != filter->mark.val) goto ignore_entry; #endif + status = (u32)READ_ONCE(ct->status); + if ((status & filter->status.mask) != filter->status.val) + goto ignore_entry; out: return 1; @@ -1495,6 +1538,7 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { [CTA_LABELS_MASK] = { .type = NLA_BINARY, .len = NF_CT_LABELS_MAX_SIZE }, [CTA_FILTER] = { .type = NLA_NESTED }, + [CTA_STATUS_MASK] = { .type = NLA_U32 }, }; static int ctnetlink_flush_iterate(struct nf_conn *ct, void *data) @@ -2484,7 +2528,9 @@ ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq, nla_put_be32(skb, CTA_STATS_SEARCH_RESTART, htonl(st->search_restart)) || nla_put_be32(skb, CTA_STATS_CLASH_RESOLVE, - htonl(st->clash_resolve))) + htonl(st->clash_resolve)) || + nla_put_be32(skb, CTA_STATS_CHAIN_TOOLONG, + htonl(st->chaintoolong))) goto nla_put_failure; nlmsg_end(skb, nlh); @@ -2625,6 +2671,8 @@ ctnetlink_glue_build_size(const struct nf_conn *ct) + nla_total_size(0) /* CTA_HELP */ + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */ + ctnetlink_secctx_size(ct) + + ctnetlink_acct_size(ct) + + ctnetlink_timestamp_size(ct) #if IS_ENABLED(CONFIG_NF_NAT) + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */ + 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */ @@ -2682,6 +2730,10 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) if (ctnetlink_dump_protoinfo(skb, ct, false) < 0) goto nla_put_failure; + if (ctnetlink_dump_acct(skb, ct, IPCTNL_MSG_CT_GET) < 0 || + ctnetlink_dump_timestamp(skb, ct) < 0) + goto nla_put_failure; + if (ctnetlink_dump_helpinfo(skb, ct) < 0) goto nla_put_failure; @@ -3060,7 +3112,7 @@ nla_put_failure: #ifdef CONFIG_NF_CONNTRACK_EVENTS static int -ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item) +ctnetlink_expect_event(unsigned int events, const struct nf_exp_event *item) { struct nf_conntrack_expect *exp = item->exp; struct net *net = nf_ct_exp_net(exp); @@ -3711,11 +3763,8 @@ static int ctnetlink_stat_exp_cpu(struct sk_buff *skb, #ifdef CONFIG_NF_CONNTRACK_EVENTS static struct nf_ct_event_notifier ctnl_notifier = { - .fcn = ctnetlink_conntrack_event, -}; - -static struct nf_exp_event_notifier ctnl_notifier_exp = { - .fcn = ctnetlink_expect_event, + .ct_event = ctnetlink_conntrack_event, + .exp_event = ctnetlink_expect_event, }; #endif @@ -3808,52 +3857,21 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_EXP); static int __net_init ctnetlink_net_init(struct net *net) { #ifdef CONFIG_NF_CONNTRACK_EVENTS - int ret; - - ret = nf_conntrack_register_notifier(net, &ctnl_notifier); - if (ret < 0) { - pr_err("ctnetlink_init: cannot register notifier.\n"); - goto err_out; - } - - ret = nf_ct_expect_register_notifier(net, &ctnl_notifier_exp); - if (ret < 0) { - pr_err("ctnetlink_init: cannot expect register notifier.\n"); - goto err_unreg_notifier; - } + nf_conntrack_register_notifier(net, &ctnl_notifier); #endif return 0; - -#ifdef CONFIG_NF_CONNTRACK_EVENTS -err_unreg_notifier: - nf_conntrack_unregister_notifier(net, &ctnl_notifier); -err_out: - return ret; -#endif } -static void ctnetlink_net_exit(struct net *net) +static void ctnetlink_net_pre_exit(struct net *net) { #ifdef CONFIG_NF_CONNTRACK_EVENTS - nf_ct_expect_unregister_notifier(net, &ctnl_notifier_exp); - nf_conntrack_unregister_notifier(net, &ctnl_notifier); + nf_conntrack_unregister_notifier(net); #endif } -static void __net_exit ctnetlink_net_exit_batch(struct list_head *net_exit_list) -{ - struct net *net; - - list_for_each_entry(net, net_exit_list, exit_list) - ctnetlink_net_exit(net); - - /* wait for other cpus until they are done with ctnl_notifiers */ - synchronize_rcu(); -} - static struct pernet_operations ctnetlink_net_ops = { .init = ctnetlink_net_init, - .exit_batch = ctnetlink_net_exit_batch, + .pre_exit = ctnetlink_net_pre_exit, }; static int __init ctnetlink_init(void) diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 3259416f2ea4..af5115e127cf 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1478,7 +1478,6 @@ void nf_conntrack_tcp_init_net(struct net *net) #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) tn->offload_timeout = 30 * HZ; - tn->offload_pickup = 120 * HZ; #endif } diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 698fee49e732..f8e3c0d2602f 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -271,7 +271,6 @@ void nf_conntrack_udp_init_net(struct net *net) #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) un->offload_timeout = 30 * HZ; - un->offload_pickup = 30 * HZ; #endif } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 214d9f9e499b..80f675d884b2 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -22,6 +22,9 @@ #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_timestamp.h> +#ifdef CONFIG_LWTUNNEL +#include <net/netfilter/nf_hooks_lwtunnel.h> +#endif #include <linux/rculist_nulls.h> static bool enable_hooks __read_mostly; @@ -429,7 +432,7 @@ static int ct_cpu_seq_show(struct seq_file *seq, void *v) unsigned int nr_conntracks; if (v == SEQ_START_TOKEN) { - seq_puts(seq, "entries clashres found new invalid ignore delete delete_list insert insert_failed drop early_drop icmp_error expect_new expect_create expect_delete search_restart\n"); + seq_puts(seq, "entries clashres found new invalid ignore delete chainlength insert insert_failed drop early_drop icmp_error expect_new expect_create expect_delete search_restart\n"); return 0; } @@ -444,7 +447,7 @@ static int ct_cpu_seq_show(struct seq_file *seq, void *v) st->invalid, 0, 0, - 0, + st->chaintoolong, st->insert, st->insert_failed, st->drop, @@ -575,7 +578,6 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_UNACK, #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD, - NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP, #endif NF_SYSCTL_CT_PROTO_TCP_LOOSE, NF_SYSCTL_CT_PROTO_TCP_LIBERAL, @@ -585,7 +587,6 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM, #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD, - NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP, #endif NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP, NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6, @@ -614,6 +615,9 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_GRE, NF_SYSCTL_CT_PROTO_TIMEOUT_GRE_STREAM, #endif +#ifdef CONFIG_LWTUNNEL + NF_SYSCTL_CT_LWTUNNEL, +#endif __NF_SYSCTL_CT_LAST_SYSCTL, }; @@ -776,12 +780,6 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP] = { - .procname = "nf_flowtable_tcp_pickup", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, #endif [NF_SYSCTL_CT_PROTO_TCP_LOOSE] = { .procname = "nf_conntrack_tcp_loose", @@ -832,12 +830,6 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - [NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP] = { - .procname = "nf_flowtable_udp_pickup", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, #endif [NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP] = { .procname = "nf_conntrack_icmp_timeout", @@ -973,6 +965,15 @@ static struct ctl_table nf_ct_sysctl_table[] = { .proc_handler = proc_dointvec_jiffies, }, #endif +#ifdef CONFIG_LWTUNNEL + [NF_SYSCTL_CT_LWTUNNEL] = { + .procname = "nf_hooks_lwtunnel", + .data = NULL, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = nf_hooks_lwtunnel_sysctl_handler, + }, +#endif {} }; @@ -1018,7 +1019,6 @@ static void nf_conntrack_standalone_init_tcp_sysctl(struct net *net, #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD].data = &tn->offload_timeout; - table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP].data = &tn->offload_pickup; #endif } @@ -1111,7 +1111,6 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM].data = &un->timeouts[UDP_CT_REPLIED]; #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD].data = &un->offload_timeout; - table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP].data = &un->offload_pickup; #endif nf_conntrack_standalone_init_tcp_sysctl(net, table); diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 1e50908b1b7e..87a7388b6c89 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -99,7 +99,7 @@ static int flow_offload_fill_route(struct flow_offload *flow, flow_tuple->mtu = ip_dst_mtu_maybe_forward(dst, true); break; case NFPROTO_IPV6: - flow_tuple->mtu = ip6_dst_mtu_forward(dst); + flow_tuple->mtu = ip6_dst_mtu_maybe_forward(dst, true); break; } @@ -180,27 +180,27 @@ static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp) static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) { - const struct nf_conntrack_l4proto *l4proto; struct net *net = nf_ct_net(ct); int l4num = nf_ct_protonum(ct); - unsigned int timeout; - - l4proto = nf_ct_l4proto_find(l4num); - if (!l4proto) - return; + s32 timeout; if (l4num == IPPROTO_TCP) { struct nf_tcp_net *tn = nf_tcp_pernet(net); - timeout = tn->offload_pickup; + timeout = tn->timeouts[TCP_CONNTRACK_ESTABLISHED]; + timeout -= tn->offload_timeout; } else if (l4num == IPPROTO_UDP) { struct nf_udp_net *tn = nf_udp_pernet(net); - timeout = tn->offload_pickup; + timeout = tn->timeouts[UDP_CT_REPLIED]; + timeout -= tn->offload_timeout; } else { return; } + if (timeout < 0) + timeout = 0; + if (nf_flow_timeout_delta(ct->timeout) > (__s32)timeout) ct->timeout = nfct_time_stamp + timeout; } @@ -273,15 +273,10 @@ static const struct rhashtable_params nf_flow_offload_rhash_params = { unsigned long flow_offload_get_timeout(struct flow_offload *flow) { - const struct nf_conntrack_l4proto *l4proto; unsigned long timeout = NF_FLOW_TIMEOUT; struct net *net = nf_ct_net(flow->ct); int l4num = nf_ct_protonum(flow->ct); - l4proto = nf_ct_l4proto_find(l4num); - if (!l4proto) - return timeout; - if (l4num == IPPROTO_TCP) { struct nf_tcp_net *tn = nf_tcp_pernet(net); @@ -331,7 +326,11 @@ EXPORT_SYMBOL_GPL(flow_offload_add); void flow_offload_refresh(struct nf_flowtable *flow_table, struct flow_offload *flow) { - flow->timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); + u32 timeout; + + timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); + if (READ_ONCE(flow->timeout) != timeout) + WRITE_ONCE(flow->timeout, timeout); if (likely(!nf_flowtable_hw_offload(flow_table))) return; diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index f92006cec94c..d6bf1b2cd541 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -251,8 +251,7 @@ static int flow_offload_eth_src(struct net *net, flow_offload_mangle(entry1, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 8, &val, &mask); - if (dev) - dev_put(dev); + dev_put(dev); return 0; } @@ -1097,6 +1096,7 @@ static void nf_flow_table_block_offload_init(struct flow_block_offload *bo, bo->command = cmd; bo->binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; bo->extack = extack; + bo->cb_list_head = &flowtable->flow_block.cb_list; INIT_LIST_HEAD(&bo->cb_list); } diff --git a/net/netfilter/nf_hooks_lwtunnel.c b/net/netfilter/nf_hooks_lwtunnel.c new file mode 100644 index 000000000000..00e89ffd78f6 --- /dev/null +++ b/net/netfilter/nf_hooks_lwtunnel.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/sysctl.h> +#include <net/lwtunnel.h> +#include <net/netfilter/nf_hooks_lwtunnel.h> + +static inline int nf_hooks_lwtunnel_get(void) +{ + if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) + return 1; + else + return 0; +} + +static inline int nf_hooks_lwtunnel_set(int enable) +{ + if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) { + if (!enable) + return -EBUSY; + } else if (enable) { + static_branch_enable(&nf_hooks_lwtunnel_enabled); + } + + return 0; +} + +#ifdef CONFIG_SYSCTL +int nf_hooks_lwtunnel_sysctl_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int proc_nf_hooks_lwtunnel_enabled = 0; + struct ctl_table tmp = { + .procname = table->procname, + .data = &proc_nf_hooks_lwtunnel_enabled, + .maxlen = sizeof(int), + .mode = table->mode, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }; + int ret; + + if (!write) + proc_nf_hooks_lwtunnel_enabled = nf_hooks_lwtunnel_get(); + + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + + if (write && ret == 0) + ret = nf_hooks_lwtunnel_set(proc_nf_hooks_lwtunnel_enabled); + + return ret; +} +EXPORT_SYMBOL_GPL(nf_hooks_lwtunnel_sysctl_handler); +#endif /* CONFIG_SYSCTL */ diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 7de595ead06a..7008961f5cb0 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -13,7 +13,7 @@ #include <linux/skbuff.h> #include <linux/gfp.h> #include <net/xfrm.h> -#include <linux/jhash.h> +#include <linux/siphash.h> #include <linux/rtnetlink.h> #include <net/netfilter/nf_conntrack.h> @@ -34,7 +34,7 @@ static unsigned int nat_net_id __read_mostly; static struct hlist_head *nf_nat_bysource __read_mostly; static unsigned int nf_nat_htable_size __read_mostly; -static unsigned int nf_nat_hash_rnd __read_mostly; +static siphash_key_t nf_nat_hash_rnd __read_mostly; struct nf_nat_lookup_hook_priv { struct nf_hook_entries __rcu *entries; @@ -153,12 +153,22 @@ static unsigned int hash_by_src(const struct net *n, const struct nf_conntrack_tuple *tuple) { unsigned int hash; + struct { + struct nf_conntrack_man src; + u32 net_mix; + u32 protonum; + } __aligned(SIPHASH_ALIGNMENT) combined; get_random_once(&nf_nat_hash_rnd, sizeof(nf_nat_hash_rnd)); + memset(&combined, 0, sizeof(combined)); + /* Original src, to ensure we map it consistently if poss. */ - hash = jhash2((u32 *)&tuple->src, sizeof(tuple->src) / sizeof(u32), - tuple->dst.protonum ^ nf_nat_hash_rnd ^ net_hash_mix(n)); + combined.src = tuple->src; + combined.net_mix = net_hash_mix(n); + combined.protonum = tuple->dst.protonum; + + hash = siphash(&combined, sizeof(combined), &nf_nat_hash_rnd); return reciprocal_scale(hash, nf_nat_htable_size); } diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index bbd1209694b8..6d12afabfe8a 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -21,6 +21,8 @@ #include "nf_internals.h" +static const struct nf_queue_handler __rcu *nf_queue_handler; + /* * Hook for nfnetlink_queue to register its queue handler. * We do this so that most of the NFQUEUE code can be modular. @@ -29,20 +31,18 @@ * receives, no matter what. */ -/* return EBUSY when somebody else is registered, return EEXIST if the - * same handler is registered, return 0 in case of success. */ -void nf_register_queue_handler(struct net *net, const struct nf_queue_handler *qh) +void nf_register_queue_handler(const struct nf_queue_handler *qh) { /* should never happen, we only have one queueing backend in kernel */ - WARN_ON(rcu_access_pointer(net->nf.queue_handler)); - rcu_assign_pointer(net->nf.queue_handler, qh); + WARN_ON(rcu_access_pointer(nf_queue_handler)); + rcu_assign_pointer(nf_queue_handler, qh); } EXPORT_SYMBOL(nf_register_queue_handler); /* The caller must flush their queue before this */ -void nf_unregister_queue_handler(struct net *net) +void nf_unregister_queue_handler(void) { - RCU_INIT_POINTER(net->nf.queue_handler, NULL); + RCU_INIT_POINTER(nf_queue_handler, NULL); } EXPORT_SYMBOL(nf_unregister_queue_handler); @@ -51,18 +51,14 @@ static void nf_queue_entry_release_refs(struct nf_queue_entry *entry) struct nf_hook_state *state = &entry->state; /* Release those devices we held, or Alexey will kill me. */ - if (state->in) - dev_put(state->in); - if (state->out) - dev_put(state->out); + dev_put(state->in); + dev_put(state->out); if (state->sk) sock_put(state->sk); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - if (entry->physin) - dev_put(entry->physin); - if (entry->physout) - dev_put(entry->physout); + dev_put(entry->physin); + dev_put(entry->physout); #endif } @@ -95,18 +91,14 @@ void nf_queue_entry_get_refs(struct nf_queue_entry *entry) { struct nf_hook_state *state = &entry->state; - if (state->in) - dev_hold(state->in); - if (state->out) - dev_hold(state->out); + dev_hold(state->in); + dev_hold(state->out); if (state->sk) sock_hold(state->sk); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - if (entry->physin) - dev_hold(entry->physin); - if (entry->physout) - dev_hold(entry->physout); + dev_hold(entry->physin); + dev_hold(entry->physout); #endif } EXPORT_SYMBOL_GPL(nf_queue_entry_get_refs); @@ -116,7 +108,7 @@ void nf_queue_nf_hook_drop(struct net *net) const struct nf_queue_handler *qh; rcu_read_lock(); - qh = rcu_dereference(net->nf.queue_handler); + qh = rcu_dereference(nf_queue_handler); if (qh) qh->nf_hook_drop(net); rcu_read_unlock(); @@ -157,12 +149,11 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state, { struct nf_queue_entry *entry = NULL; const struct nf_queue_handler *qh; - struct net *net = state->net; unsigned int route_key_size; int status; /* QUEUE == DROP if no one is waiting, to be safe. */ - qh = rcu_dereference(net->nf.queue_handler); + qh = rcu_dereference(nf_queue_handler); if (!qh) return -ESRCH; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index de182d1f7c4e..081437dd75b7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8445,6 +8445,16 @@ static int nf_tables_commit_audit_alloc(struct list_head *adl, return 0; } +static void nf_tables_commit_audit_free(struct list_head *adl) +{ + struct nft_audit_data *adp, *adn; + + list_for_each_entry_safe(adp, adn, adl, list) { + list_del(&adp->list); + kfree(adp); + } +} + static void nf_tables_commit_audit_collect(struct list_head *adl, struct nft_table *table, u32 op) { @@ -8509,6 +8519,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) ret = nf_tables_commit_audit_alloc(&adl, trans->ctx.table); if (ret) { nf_tables_commit_chain_prepare_cancel(net); + nf_tables_commit_audit_free(&adl); return ret; } if (trans->msg_type == NFT_MSG_NEWRULE || @@ -8518,6 +8529,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) ret = nf_tables_commit_chain_prepare(net, chain); if (ret < 0) { nf_tables_commit_chain_prepare_cancel(net); + nf_tables_commit_audit_free(&adl); return ret; } } diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index b58d73a96523..9656c1646222 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -353,6 +353,7 @@ static void nft_flow_block_offload_init(struct flow_block_offload *bo, bo->command = cmd; bo->binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; bo->extack = extack; + bo->cb_list_head = &basechain->flow_block.cb_list; INIT_LIST_HEAD(&bo->cb_list); } diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c index 50b4e3c9347a..f554e2ea32ee 100644 --- a/net/netfilter/nfnetlink_hook.c +++ b/net/netfilter/nfnetlink_hook.c @@ -89,11 +89,15 @@ static int nfnl_hook_put_nft_chain_info(struct sk_buff *nlskb, if (!nest2) goto cancel_nest; - ret = nla_put_string(nlskb, NFTA_CHAIN_TABLE, chain->table->name); + ret = nla_put_string(nlskb, NFNLA_CHAIN_TABLE, chain->table->name); if (ret) goto cancel_nest; - ret = nla_put_string(nlskb, NFTA_CHAIN_NAME, chain->name); + ret = nla_put_string(nlskb, NFNLA_CHAIN_NAME, chain->name); + if (ret) + goto cancel_nest; + + ret = nla_put_u8(nlskb, NFNLA_CHAIN_FAMILY, chain->table->family); if (ret) goto cancel_nest; @@ -109,18 +113,19 @@ cancel_nest: static int nfnl_hook_dump_one(struct sk_buff *nlskb, const struct nfnl_dump_hook_data *ctx, const struct nf_hook_ops *ops, - unsigned int seq) + int family, unsigned int seq) { u16 event = nfnl_msg_type(NFNL_SUBSYS_HOOK, NFNL_MSG_HOOK_GET); unsigned int portid = NETLINK_CB(nlskb).portid; struct nlmsghdr *nlh; int ret = -EMSGSIZE; + u32 hooknum; #ifdef CONFIG_KALLSYMS char sym[KSYM_SYMBOL_LEN]; char *module_name; #endif nlh = nfnl_msg_put(nlskb, portid, seq, event, - NLM_F_MULTI, ops->pf, NFNETLINK_V0, 0); + NLM_F_MULTI, family, NFNETLINK_V0, 0); if (!nlh) goto nla_put_failure; @@ -135,6 +140,7 @@ static int nfnl_hook_dump_one(struct sk_buff *nlskb, if (module_name) { char *end; + *module_name = '\0'; module_name += 2; end = strchr(module_name, ']'); if (end) { @@ -151,7 +157,12 @@ static int nfnl_hook_dump_one(struct sk_buff *nlskb, goto nla_put_failure; #endif - ret = nla_put_be32(nlskb, NFNLA_HOOK_HOOKNUM, htonl(ops->hooknum)); + if (ops->pf == NFPROTO_INET && ops->hooknum == NF_INET_INGRESS) + hooknum = NF_NETDEV_INGRESS; + else + hooknum = ops->hooknum; + + ret = nla_put_be32(nlskb, NFNLA_HOOK_HOOKNUM, htonl(hooknum)); if (ret) goto nla_put_failure; @@ -174,7 +185,9 @@ static const struct nf_hook_entries * nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *dev) { const struct nf_hook_entries *hook_head = NULL; +#ifdef CONFIG_NETFILTER_INGRESS struct net_device *netdev; +#endif switch (pf) { case NFPROTO_IPV4: @@ -257,7 +270,8 @@ static int nfnl_hook_dump(struct sk_buff *nlskb, ops = nf_hook_entries_get_hook_ops(e); for (; i < e->num_hook_entries; i++) { - err = nfnl_hook_dump_one(nlskb, ctx, ops[i], cb->seq); + err = nfnl_hook_dump_one(nlskb, ctx, ops[i], family, + cb->nlh->nlmsg_seq); if (err) break; } diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index f774de0fc24f..4c3fbaaeb103 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -951,6 +951,16 @@ static void nfqnl_nf_hook_drop(struct net *net) struct nfnl_queue_net *q = nfnl_queue_pernet(net); int i; + /* This function is also called on net namespace error unwind, + * when pernet_ops->init() failed and ->exit() functions of the + * previous pernet_ops gets called. + * + * This may result in a call to nfqnl_nf_hook_drop() before + * struct nfnl_queue_net was allocated. + */ + if (!q) + return; + for (i = 0; i < INSTANCE_BUCKETS; i++) { struct nfqnl_instance *inst; struct hlist_head *head = &q->instance_table[i]; @@ -1502,7 +1512,6 @@ static int __net_init nfnl_queue_net_init(struct net *net) &nfqnl_seq_ops, sizeof(struct iter_state))) return -ENOMEM; #endif - nf_register_queue_handler(net, &nfqh); return 0; } @@ -1511,7 +1520,6 @@ static void __net_exit nfnl_queue_net_exit(struct net *net) struct nfnl_queue_net *q = nfnl_queue_pernet(net); unsigned int i; - nf_unregister_queue_handler(net); #ifdef CONFIG_PROC_FS remove_proc_entry("nfnetlink_queue", net->nf.proc_netfilter); #endif @@ -1555,6 +1563,8 @@ static int __init nfnetlink_queue_init(void) goto cleanup_netlink_subsys; } + nf_register_queue_handler(&nfqh); + return status; cleanup_netlink_subsys: @@ -1568,6 +1578,7 @@ out: static void __exit nfnetlink_queue_fini(void) { + nf_unregister_queue_handler(); unregister_netdevice_notifier(&nfqnl_dev_notifier); nfnetlink_subsys_unregister(&nfqnl_subsys); netlink_unregister_notifier(&nfqnl_rtnl_notifier); diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 639c337c885b..272bcdb1392d 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -683,14 +683,12 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb, goto out_put; } - ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (ret > 0) - ret = 0; + ret = nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); out_put: rcu_read_lock(); module_put(THIS_MODULE); - return ret == -EAGAIN ? -ENOBUFS : ret; + + return ret; } static const struct nla_policy nfnl_compat_policy_get[NFTA_COMPAT_MAX+1] = { diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 337e22d8b40b..99b1de14ff7e 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -41,6 +41,7 @@ struct nft_ct_helper_obj { #ifdef CONFIG_NF_CONNTRACK_ZONES static DEFINE_PER_CPU(struct nf_conn *, nft_ct_pcpu_template); static unsigned int nft_ct_pcpu_template_refcnt __read_mostly; +static DEFINE_MUTEX(nft_ct_pcpu_mutex); #endif static u64 nft_ct_get_eval_counter(const struct nf_conn_counter *c, @@ -525,8 +526,10 @@ static void __nft_ct_set_destroy(const struct nft_ctx *ctx, struct nft_ct *priv) #endif #ifdef CONFIG_NF_CONNTRACK_ZONES case NFT_CT_ZONE: + mutex_lock(&nft_ct_pcpu_mutex); if (--nft_ct_pcpu_template_refcnt == 0) nft_ct_tmpl_put_pcpu(); + mutex_unlock(&nft_ct_pcpu_mutex); break; #endif default: @@ -564,9 +567,13 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, #endif #ifdef CONFIG_NF_CONNTRACK_ZONES case NFT_CT_ZONE: - if (!nft_ct_tmpl_alloc_pcpu()) + mutex_lock(&nft_ct_pcpu_mutex); + if (!nft_ct_tmpl_alloc_pcpu()) { + mutex_unlock(&nft_ct_pcpu_mutex); return -ENOMEM; + } nft_ct_pcpu_template_refcnt++; + mutex_unlock(&nft_ct_pcpu_mutex); len = sizeof(u16); break; #endif diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c index 8088b99f2ee3..304e33cbed9b 100644 --- a/net/netfilter/nft_last.c +++ b/net/netfilter/nft_last.c @@ -48,24 +48,30 @@ static void nft_last_eval(const struct nft_expr *expr, { struct nft_last_priv *priv = nft_expr_priv(expr); - priv->last_jiffies = jiffies; - priv->last_set = 1; + if (READ_ONCE(priv->last_jiffies) != jiffies) + WRITE_ONCE(priv->last_jiffies, jiffies); + if (READ_ONCE(priv->last_set) == 0) + WRITE_ONCE(priv->last_set, 1); } static int nft_last_dump(struct sk_buff *skb, const struct nft_expr *expr) { struct nft_last_priv *priv = nft_expr_priv(expr); + unsigned long last_jiffies = READ_ONCE(priv->last_jiffies); + u32 last_set = READ_ONCE(priv->last_set); __be64 msecs; - if (time_before(jiffies, priv->last_jiffies)) - priv->last_set = 0; + if (time_before(jiffies, last_jiffies)) { + WRITE_ONCE(priv->last_set, 0); + last_set = 0; + } - if (priv->last_set) - msecs = nf_jiffies64_to_msecs(jiffies - priv->last_jiffies); + if (last_set) + msecs = nf_jiffies64_to_msecs(jiffies - last_jiffies); else msecs = 0; - if (nla_put_be32(skb, NFTA_LAST_SET, htonl(priv->last_set)) || + if (nla_put_be32(skb, NFTA_LAST_SET, htonl(last_set)) || nla_put_be64(skb, NFTA_LAST_MSECS, msecs, NFTA_LAST_PAD)) goto nla_put_failure; diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 0840c635b752..be1595d6979d 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -201,7 +201,9 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, alen = sizeof_field(struct nf_nat_range, min_addr.ip6); break; default: - return -EAFNOSUPPORT; + if (tb[NFTA_NAT_REG_ADDR_MIN]) + return -EAFNOSUPPORT; + break; } priv->family = family; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 84e58ee501a4..25524e393349 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -39,6 +39,20 @@ MODULE_DESCRIPTION("{ip,ip6,arp,eb}_tables backend module"); #define XT_PCPU_BLOCK_SIZE 4096 #define XT_MAX_TABLE_SIZE (512 * 1024 * 1024) +struct xt_template { + struct list_head list; + + /* called when table is needed in the given netns */ + int (*table_init)(struct net *net); + + struct module *me; + + /* A unique name... */ + char name[XT_TABLE_MAXNAMELEN]; +}; + +static struct list_head xt_templates[NFPROTO_NUMPROTO]; + struct xt_pernet { struct list_head tables[NFPROTO_NUMPROTO]; }; @@ -1221,48 +1235,43 @@ struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af, const char *name) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); - struct xt_table *t, *found = NULL; + struct module *owner = NULL; + struct xt_template *tmpl; + struct xt_table *t; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt_net->tables[af], list) if (strcmp(t->name, name) == 0 && try_module_get(t->me)) return t; - if (net == &init_net) - goto out; - - /* Table doesn't exist in this netns, re-try init */ - xt_net = net_generic(&init_net, xt_pernet_id); - list_for_each_entry(t, &xt_net->tables[af], list) { + /* Table doesn't exist in this netns, check larval list */ + list_for_each_entry(tmpl, &xt_templates[af], list) { int err; - if (strcmp(t->name, name)) + if (strcmp(tmpl->name, name)) continue; - if (!try_module_get(t->me)) + if (!try_module_get(tmpl->me)) goto out; + + owner = tmpl->me; + mutex_unlock(&xt[af].mutex); - err = t->table_init(net); + err = tmpl->table_init(net); if (err < 0) { - module_put(t->me); + module_put(owner); return ERR_PTR(err); } - found = t; - mutex_lock(&xt[af].mutex); break; } - if (!found) - goto out; - - xt_net = net_generic(net, xt_pernet_id); /* and once again: */ list_for_each_entry(t, &xt_net->tables[af], list) if (strcmp(t->name, name) == 0) return t; - module_put(found->me); + module_put(owner); out: mutex_unlock(&xt[af].mutex); return ERR_PTR(-ENOENT); @@ -1749,6 +1758,58 @@ xt_hook_ops_alloc(const struct xt_table *table, nf_hookfn *fn) } EXPORT_SYMBOL_GPL(xt_hook_ops_alloc); +int xt_register_template(const struct xt_table *table, + int (*table_init)(struct net *net)) +{ + int ret = -EEXIST, af = table->af; + struct xt_template *t; + + mutex_lock(&xt[af].mutex); + + list_for_each_entry(t, &xt_templates[af], list) { + if (WARN_ON_ONCE(strcmp(table->name, t->name) == 0)) + goto out_unlock; + } + + ret = -ENOMEM; + t = kzalloc(sizeof(*t), GFP_KERNEL); + if (!t) + goto out_unlock; + + BUILD_BUG_ON(sizeof(t->name) != sizeof(table->name)); + + strscpy(t->name, table->name, sizeof(t->name)); + t->table_init = table_init; + t->me = table->me; + list_add(&t->list, &xt_templates[af]); + ret = 0; +out_unlock: + mutex_unlock(&xt[af].mutex); + return ret; +} +EXPORT_SYMBOL_GPL(xt_register_template); + +void xt_unregister_template(const struct xt_table *table) +{ + struct xt_template *t; + int af = table->af; + + mutex_lock(&xt[af].mutex); + list_for_each_entry(t, &xt_templates[af], list) { + if (strcmp(table->name, t->name)) + continue; + + list_del(&t->list); + mutex_unlock(&xt[af].mutex); + kfree(t); + return; + } + + mutex_unlock(&xt[af].mutex); + WARN_ON_ONCE(1); +} +EXPORT_SYMBOL_GPL(xt_unregister_template); + int xt_proto_init(struct net *net, u_int8_t af) { #ifdef CONFIG_PROC_FS @@ -1937,6 +1998,7 @@ static int __init xt_init(void) #endif INIT_LIST_HEAD(&xt[i].target); INIT_LIST_HEAD(&xt[i].match); + INIT_LIST_HEAD(&xt_templates[i]); } rv = register_pernet_subsys(&xt_net_ops); if (rv < 0) diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 12404d221026..0a913ce07425 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -351,21 +351,10 @@ notrack_tg(struct sk_buff *skb, const struct xt_action_param *par) return XT_CONTINUE; } -static int notrack_chk(const struct xt_tgchk_param *par) -{ - if (!par->net->xt.notrack_deprecated_warning) { - pr_info("netfilter: NOTRACK target is deprecated, " - "use CT instead or upgrade iptables\n"); - par->net->xt.notrack_deprecated_warning = true; - } - return 0; -} - static struct xt_target notrack_tg_reg __read_mostly = { .name = "NOTRACK", .revision = 0, .family = NFPROTO_UNSPEC, - .checkentry = notrack_chk, .target = notrack_tg, .table = "raw", .me = THIS_MODULE, diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c index 13cf3f9b5938..849ac552a154 100644 --- a/net/netfilter/xt_bpf.c +++ b/net/netfilter/xt_bpf.c @@ -90,7 +90,7 @@ static bool bpf_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_bpf_info *info = par->matchinfo; - return BPF_PROG_RUN(info->filter, skb); + return bpf_prog_run(info->filter, skb); } static bool bpf_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index baf235721c43..894e6b8f1a86 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -144,8 +144,8 @@ static int netlbl_cipsov4_add_std(struct genl_info *info, return -ENOMEM; doi_def->map.std = kzalloc(sizeof(*doi_def->map.std), GFP_KERNEL); if (doi_def->map.std == NULL) { - ret_val = -ENOMEM; - goto add_std_failure; + kfree(doi_def); + return -ENOMEM; } doi_def->type = CIPSO_V4_MAP_TRANS; @@ -187,14 +187,14 @@ static int netlbl_cipsov4_add_std(struct genl_info *info, } doi_def->map.std->lvl.local = kcalloc(doi_def->map.std->lvl.local_size, sizeof(u32), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (doi_def->map.std->lvl.local == NULL) { ret_val = -ENOMEM; goto add_std_failure; } doi_def->map.std->lvl.cipso = kcalloc(doi_def->map.std->lvl.cipso_size, sizeof(u32), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (doi_def->map.std->lvl.cipso == NULL) { ret_val = -ENOMEM; goto add_std_failure; @@ -263,7 +263,7 @@ static int netlbl_cipsov4_add_std(struct genl_info *info, doi_def->map.std->cat.local = kcalloc( doi_def->map.std->cat.local_size, sizeof(u32), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (doi_def->map.std->cat.local == NULL) { ret_val = -ENOMEM; goto add_std_failure; @@ -271,7 +271,7 @@ static int netlbl_cipsov4_add_std(struct genl_info *info, doi_def->map.std->cat.cipso = kcalloc( doi_def->map.std->cat.cipso_size, sizeof(u32), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (doi_def->map.std->cat.cipso == NULL) { ret_val = -ENOMEM; goto add_std_failure; diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 2483df0bbd7c..566ba4397ee4 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -492,8 +492,7 @@ static int netlbl_unlhsh_remove_addr4(struct net *net, netlbl_af4list_audit_addr(audit_buf, 1, (dev != NULL ? dev->name : NULL), addr->s_addr, mask->s_addr); - if (dev != NULL) - dev_put(dev); + dev_put(dev); if (entry != NULL && security_secid_to_secctx(entry->secid, &secctx, &secctx_len) == 0) { @@ -553,8 +552,7 @@ static int netlbl_unlhsh_remove_addr6(struct net *net, netlbl_af6list_audit_addr(audit_buf, 1, (dev != NULL ? dev->name : NULL), addr, mask); - if (dev != NULL) - dev_put(dev); + dev_put(dev); if (entry != NULL && security_secid_to_secctx(entry->secid, &secctx, &secctx_len) == 0) { diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 380f95aacdec..24b7cf447bc5 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2545,13 +2545,15 @@ int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid, /* errors reported via destination sk->sk_err, but propagate * delivery errors if NETLINK_BROADCAST_ERROR flag is set */ err = nlmsg_multicast(sk, skb, exclude_portid, group, flags); + if (err == -ESRCH) + err = 0; } if (report) { int err2; err2 = nlmsg_unicast(sk, skb, portid); - if (!err || err == -ESRCH) + if (!err) err = err2; } diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 2d6fdf40df66..1afca2a6c2ac 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -40,14 +40,6 @@ void genl_unlock(void) } EXPORT_SYMBOL(genl_unlock); -#ifdef CONFIG_LOCKDEP -bool lockdep_genl_is_held(void) -{ - return lockdep_is_held(&genl_mutex); -} -EXPORT_SYMBOL(lockdep_genl_is_held); -#endif - static void genl_lock_all(void) { down_write(&cb_lock); @@ -1485,6 +1477,7 @@ int genlmsg_multicast_allns(const struct genl_family *family, { if (WARN_ON_ONCE(group >= family->n_mcgrps)) return -EINVAL; + group = family->mcgrp_offset + group; return genlmsg_mcast(skb, portid, group, flags); } @@ -1495,14 +1488,12 @@ void genl_notify(const struct genl_family *family, struct sk_buff *skb, { struct net *net = genl_info_net(info); struct sock *sk = net->genl_sock; - int report = 0; - - if (info->nlhdr) - report = nlmsg_report(info->nlhdr); if (WARN_ON_ONCE(group >= family->n_mcgrps)) return; + group = family->mcgrp_offset + group; - nlmsg_notify(sk, skb, info->snd_portid, group, report, flags); + nlmsg_notify(sk, skb, info->snd_portid, group, + nlmsg_report(info->nlhdr), flags); } EXPORT_SYMBOL(genl_notify); diff --git a/net/netrom/nr_loopback.c b/net/netrom/nr_loopback.c index a880dd33e901..511819fbfa67 100644 --- a/net/netrom/nr_loopback.c +++ b/net/netrom/nr_loopback.c @@ -59,8 +59,7 @@ static void nr_loopback_timer(struct timer_list *unused) if (dev == NULL || nr_rx_frame(skb, dev) == 0) kfree_skb(skb); - if (dev != NULL) - dev_put(dev); + dev_put(dev); if (!skb_queue_empty(&loopback_queue) && !nr_loopback_running()) mod_timer(&loopback_timer, jiffies + 10); diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index de0456073dc0..ddd5cbd455e3 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -582,8 +582,7 @@ struct net_device *nr_dev_first(void) if (first == NULL || strncmp(dev->name, first->name, 3) < 0) first = dev; } - if (first) - dev_hold(first); + dev_hold(first); rcu_read_unlock(); return first; diff --git a/net/nfc/af_nfc.c b/net/nfc/af_nfc.c index 4a9e72073564..6024fad905ff 100644 --- a/net/nfc/af_nfc.c +++ b/net/nfc/af_nfc.c @@ -79,7 +79,7 @@ int __init af_nfc_init(void) return sock_register(&nfc_sock_family_ops); } -void af_nfc_exit(void) +void __exit af_nfc_exit(void) { sock_unregister(PF_NFC); } diff --git a/net/nfc/core.c b/net/nfc/core.c index 573c80c6ff7a..3c645c1d99c9 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -636,7 +636,7 @@ error: return rc; } -int nfc_set_remote_general_bytes(struct nfc_dev *dev, u8 *gb, u8 gb_len) +int nfc_set_remote_general_bytes(struct nfc_dev *dev, const u8 *gb, u8 gb_len) { pr_debug("dev_name=%s gb_len=%d\n", dev_name(&dev->dev), gb_len); @@ -665,7 +665,7 @@ int nfc_tm_data_received(struct nfc_dev *dev, struct sk_buff *skb) EXPORT_SYMBOL(nfc_tm_data_received); int nfc_tm_activated(struct nfc_dev *dev, u32 protocol, u8 comm_mode, - u8 *gb, size_t gb_len) + const u8 *gb, size_t gb_len) { int rc; @@ -824,7 +824,7 @@ EXPORT_SYMBOL(nfc_targets_found); */ int nfc_target_lost(struct nfc_dev *dev, u32 target_idx) { - struct nfc_target *tg; + const struct nfc_target *tg; int i; pr_debug("dev_name %s n_target %d\n", dev_name(&dev->dev), target_idx); @@ -1048,7 +1048,7 @@ struct nfc_dev *nfc_get_device(unsigned int idx) * @tx_headroom: reserved space at beginning of skb * @tx_tailroom: reserved space at end of skb */ -struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, +struct nfc_dev *nfc_allocate_device(const struct nfc_ops *ops, u32 supported_protocols, int tx_headroom, int tx_tailroom) { diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c index 5044c7db577e..fefc03674f4f 100644 --- a/net/nfc/digital_core.c +++ b/net/nfc/digital_core.c @@ -732,7 +732,7 @@ exit: return rc; } -static struct nfc_ops digital_nfc_ops = { +static const struct nfc_ops digital_nfc_ops = { .dev_up = digital_dev_up, .dev_down = digital_dev_down, .start_poll = digital_start_poll, @@ -745,7 +745,7 @@ static struct nfc_ops digital_nfc_ops = { .im_transceive = digital_in_send, }; -struct nfc_digital_dev *nfc_digital_allocate_device(struct nfc_digital_ops *ops, +struct nfc_digital_dev *nfc_digital_allocate_device(const struct nfc_digital_ops *ops, __u32 supported_protocols, __u32 driver_capabilities, int tx_headroom, int tx_tailroom) diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c index 3481941be70b..ceb87db57cdb 100644 --- a/net/nfc/hci/core.c +++ b/net/nfc/hci/core.c @@ -128,7 +128,7 @@ static void nfc_hci_msg_rx_work(struct work_struct *work) struct nfc_hci_dev *hdev = container_of(work, struct nfc_hci_dev, msg_rx_work); struct sk_buff *skb; - struct hcp_message *message; + const struct hcp_message *message; u8 pipe; u8 type; u8 instruction; @@ -182,9 +182,9 @@ void nfc_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd, struct sk_buff *skb) { u8 status = NFC_HCI_ANY_OK; - struct hci_create_pipe_resp *create_info; - struct hci_delete_pipe_noti *delete_info; - struct hci_all_pipe_cleared_noti *cleared_info; + const struct hci_create_pipe_resp *create_info; + const struct hci_delete_pipe_noti *delete_info; + const struct hci_all_pipe_cleared_noti *cleared_info; u8 gate; pr_debug("from pipe %x cmd %x\n", pipe, cmd); @@ -447,7 +447,7 @@ static void nfc_hci_cmd_timeout(struct timer_list *t) } static int hci_dev_connect_gates(struct nfc_hci_dev *hdev, u8 gate_count, - struct nfc_hci_gate *gates) + const struct nfc_hci_gate *gates) { int r; while (gate_count--) { @@ -928,7 +928,7 @@ static int hci_fw_download(struct nfc_dev *nfc_dev, const char *firmware_name) return hdev->ops->fw_download(hdev, firmware_name); } -static struct nfc_ops hci_nfc_ops = { +static const struct nfc_ops hci_nfc_ops = { .dev_up = hci_dev_up, .dev_down = hci_dev_down, .start_poll = hci_start_poll, @@ -947,7 +947,7 @@ static struct nfc_ops hci_nfc_ops = { .se_io = hci_se_io, }; -struct nfc_hci_dev *nfc_hci_allocate_device(struct nfc_hci_ops *ops, +struct nfc_hci_dev *nfc_hci_allocate_device(const struct nfc_hci_ops *ops, struct nfc_hci_init_data *init_data, unsigned long quirks, u32 protocols, diff --git a/net/nfc/hci/llc.c b/net/nfc/hci/llc.c index 6ab40ea17662..2140f6724644 100644 --- a/net/nfc/hci/llc.c +++ b/net/nfc/hci/llc.c @@ -11,7 +11,7 @@ static LIST_HEAD(llc_engines); -int nfc_llc_init(void) +int __init nfc_llc_init(void) { int r; @@ -41,7 +41,7 @@ void nfc_llc_exit(void) } } -int nfc_llc_register(const char *name, struct nfc_llc_ops *ops) +int nfc_llc_register(const char *name, const struct nfc_llc_ops *ops) { struct nfc_llc_engine *llc_engine; diff --git a/net/nfc/hci/llc.h b/net/nfc/hci/llc.h index 823ddb621e5d..d66271d211a5 100644 --- a/net/nfc/hci/llc.h +++ b/net/nfc/hci/llc.h @@ -26,20 +26,20 @@ struct nfc_llc_ops { struct nfc_llc_engine { const char *name; - struct nfc_llc_ops *ops; + const struct nfc_llc_ops *ops; struct list_head entry; }; struct nfc_llc { void *data; - struct nfc_llc_ops *ops; + const struct nfc_llc_ops *ops; int rx_headroom; int rx_tailroom; }; void *nfc_llc_get_data(struct nfc_llc *llc); -int nfc_llc_register(const char *name, struct nfc_llc_ops *ops); +int nfc_llc_register(const char *name, const struct nfc_llc_ops *ops); void nfc_llc_unregister(const char *name); int nfc_llc_nop_register(void); diff --git a/net/nfc/hci/llc_nop.c b/net/nfc/hci/llc_nop.c index a42852f36f2e..a58716f16954 100644 --- a/net/nfc/hci/llc_nop.c +++ b/net/nfc/hci/llc_nop.c @@ -71,7 +71,7 @@ static int llc_nop_xmit_from_hci(struct nfc_llc *llc, struct sk_buff *skb) return llc_nop->xmit_to_drv(llc_nop->hdev, skb); } -static struct nfc_llc_ops llc_nop_ops = { +static const struct nfc_llc_ops llc_nop_ops = { .init = llc_nop_init, .deinit = llc_nop_deinit, .start = llc_nop_start, diff --git a/net/nfc/hci/llc_shdlc.c b/net/nfc/hci/llc_shdlc.c index 1e3a90049da9..aef750d7787c 100644 --- a/net/nfc/hci/llc_shdlc.c +++ b/net/nfc/hci/llc_shdlc.c @@ -123,7 +123,7 @@ static bool llc_shdlc_x_lteq_y_lt_z(int x, int y, int z) return ((y >= x) || (y < z)) ? true : false; } -static struct sk_buff *llc_shdlc_alloc_skb(struct llc_shdlc *shdlc, +static struct sk_buff *llc_shdlc_alloc_skb(const struct llc_shdlc *shdlc, int payload_len) { struct sk_buff *skb; @@ -137,7 +137,7 @@ static struct sk_buff *llc_shdlc_alloc_skb(struct llc_shdlc *shdlc, } /* immediately sends an S frame. */ -static int llc_shdlc_send_s_frame(struct llc_shdlc *shdlc, +static int llc_shdlc_send_s_frame(const struct llc_shdlc *shdlc, enum sframe_type sframe_type, int nr) { int r; @@ -159,7 +159,7 @@ static int llc_shdlc_send_s_frame(struct llc_shdlc *shdlc, } /* immediately sends an U frame. skb may contain optional payload */ -static int llc_shdlc_send_u_frame(struct llc_shdlc *shdlc, +static int llc_shdlc_send_u_frame(const struct llc_shdlc *shdlc, struct sk_buff *skb, enum uframe_modifier uframe_modifier) { @@ -361,7 +361,7 @@ static void llc_shdlc_connect_complete(struct llc_shdlc *shdlc, int r) wake_up(shdlc->connect_wq); } -static int llc_shdlc_connect_initiate(struct llc_shdlc *shdlc) +static int llc_shdlc_connect_initiate(const struct llc_shdlc *shdlc) { struct sk_buff *skb; @@ -377,7 +377,7 @@ static int llc_shdlc_connect_initiate(struct llc_shdlc *shdlc) return llc_shdlc_send_u_frame(shdlc, skb, U_FRAME_RSET); } -static int llc_shdlc_connect_send_ua(struct llc_shdlc *shdlc) +static int llc_shdlc_connect_send_ua(const struct llc_shdlc *shdlc) { struct sk_buff *skb; @@ -820,7 +820,7 @@ static int llc_shdlc_xmit_from_hci(struct nfc_llc *llc, struct sk_buff *skb) return 0; } -static struct nfc_llc_ops llc_shdlc_ops = { +static const struct nfc_llc_ops llc_shdlc_ops = { .init = llc_shdlc_init, .deinit = llc_shdlc_deinit, .start = llc_shdlc_start, diff --git a/net/nfc/llcp.h b/net/nfc/llcp.h index 97853c9cefc7..d49d4bf2e37c 100644 --- a/net/nfc/llcp.h +++ b/net/nfc/llcp.h @@ -221,15 +221,15 @@ struct sock *nfc_llcp_accept_dequeue(struct sock *sk, struct socket *newsock); /* TLV API */ int nfc_llcp_parse_gb_tlv(struct nfc_llcp_local *local, - u8 *tlv_array, u16 tlv_array_len); + const u8 *tlv_array, u16 tlv_array_len); int nfc_llcp_parse_connection_tlv(struct nfc_llcp_sock *sock, - u8 *tlv_array, u16 tlv_array_len); + const u8 *tlv_array, u16 tlv_array_len); /* Commands API */ void nfc_llcp_recv(void *data, struct sk_buff *skb, int err); -u8 *nfc_llcp_build_tlv(u8 type, u8 *value, u8 value_length, u8 *tlv_length); +u8 *nfc_llcp_build_tlv(u8 type, const u8 *value, u8 value_length, u8 *tlv_length); struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdres_tlv(u8 tid, u8 sap); -struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdreq_tlv(u8 tid, char *uri, +struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdreq_tlv(u8 tid, const char *uri, size_t uri_len); void nfc_llcp_free_sdp_tlv(struct nfc_llcp_sdp_tlv *sdp); void nfc_llcp_free_sdp_tlv_list(struct hlist_head *sdp_head); diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index 475061c79c44..3c4172a5aeb5 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -15,7 +15,7 @@ #include "nfc.h" #include "llcp.h" -static u8 llcp_tlv_length[LLCP_TLV_MAX] = { +static const u8 llcp_tlv_length[LLCP_TLV_MAX] = { 0, 1, /* VERSION */ 2, /* MIUX */ @@ -29,7 +29,7 @@ static u8 llcp_tlv_length[LLCP_TLV_MAX] = { }; -static u8 llcp_tlv8(u8 *tlv, u8 type) +static u8 llcp_tlv8(const u8 *tlv, u8 type) { if (tlv[0] != type || tlv[1] != llcp_tlv_length[tlv[0]]) return 0; @@ -37,7 +37,7 @@ static u8 llcp_tlv8(u8 *tlv, u8 type) return tlv[2]; } -static u16 llcp_tlv16(u8 *tlv, u8 type) +static u16 llcp_tlv16(const u8 *tlv, u8 type) { if (tlv[0] != type || tlv[1] != llcp_tlv_length[tlv[0]]) return 0; @@ -46,37 +46,37 @@ static u16 llcp_tlv16(u8 *tlv, u8 type) } -static u8 llcp_tlv_version(u8 *tlv) +static u8 llcp_tlv_version(const u8 *tlv) { return llcp_tlv8(tlv, LLCP_TLV_VERSION); } -static u16 llcp_tlv_miux(u8 *tlv) +static u16 llcp_tlv_miux(const u8 *tlv) { return llcp_tlv16(tlv, LLCP_TLV_MIUX) & 0x7ff; } -static u16 llcp_tlv_wks(u8 *tlv) +static u16 llcp_tlv_wks(const u8 *tlv) { return llcp_tlv16(tlv, LLCP_TLV_WKS); } -static u16 llcp_tlv_lto(u8 *tlv) +static u16 llcp_tlv_lto(const u8 *tlv) { return llcp_tlv8(tlv, LLCP_TLV_LTO); } -static u8 llcp_tlv_opt(u8 *tlv) +static u8 llcp_tlv_opt(const u8 *tlv) { return llcp_tlv8(tlv, LLCP_TLV_OPT); } -static u8 llcp_tlv_rw(u8 *tlv) +static u8 llcp_tlv_rw(const u8 *tlv) { return llcp_tlv8(tlv, LLCP_TLV_RW) & 0xf; } -u8 *nfc_llcp_build_tlv(u8 type, u8 *value, u8 value_length, u8 *tlv_length) +u8 *nfc_llcp_build_tlv(u8 type, const u8 *value, u8 value_length, u8 *tlv_length) { u8 *tlv, length; @@ -130,7 +130,7 @@ struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdres_tlv(u8 tid, u8 sap) return sdres; } -struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdreq_tlv(u8 tid, char *uri, +struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdreq_tlv(u8 tid, const char *uri, size_t uri_len) { struct nfc_llcp_sdp_tlv *sdreq; @@ -190,9 +190,10 @@ void nfc_llcp_free_sdp_tlv_list(struct hlist_head *head) } int nfc_llcp_parse_gb_tlv(struct nfc_llcp_local *local, - u8 *tlv_array, u16 tlv_array_len) + const u8 *tlv_array, u16 tlv_array_len) { - u8 *tlv = tlv_array, type, length, offset = 0; + const u8 *tlv = tlv_array; + u8 type, length, offset = 0; pr_debug("TLV array length %d\n", tlv_array_len); @@ -239,9 +240,10 @@ int nfc_llcp_parse_gb_tlv(struct nfc_llcp_local *local, } int nfc_llcp_parse_connection_tlv(struct nfc_llcp_sock *sock, - u8 *tlv_array, u16 tlv_array_len) + const u8 *tlv_array, u16 tlv_array_len) { - u8 *tlv = tlv_array, type, length, offset = 0; + const u8 *tlv = tlv_array; + u8 type, length, offset = 0; pr_debug("TLV array length %d\n", tlv_array_len); @@ -295,7 +297,7 @@ static struct sk_buff *llcp_add_header(struct sk_buff *pdu, return pdu; } -static struct sk_buff *llcp_add_tlv(struct sk_buff *pdu, u8 *tlv, +static struct sk_buff *llcp_add_tlv(struct sk_buff *pdu, const u8 *tlv, u8 tlv_length) { /* XXX Add an skb length check */ @@ -389,9 +391,10 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) { struct nfc_llcp_local *local; struct sk_buff *skb; - u8 *service_name_tlv = NULL, service_name_tlv_length; - u8 *miux_tlv = NULL, miux_tlv_length; - u8 *rw_tlv = NULL, rw_tlv_length, rw; + const u8 *service_name_tlv = NULL; + const u8 *miux_tlv = NULL; + const u8 *rw_tlv = NULL; + u8 service_name_tlv_length, miux_tlv_length, rw_tlv_length, rw; int err; u16 size = 0; __be16 miux; @@ -465,8 +468,9 @@ int nfc_llcp_send_cc(struct nfc_llcp_sock *sock) { struct nfc_llcp_local *local; struct sk_buff *skb; - u8 *miux_tlv = NULL, miux_tlv_length; - u8 *rw_tlv = NULL, rw_tlv_length, rw; + const u8 *miux_tlv = NULL; + const u8 *rw_tlv = NULL; + u8 miux_tlv_length, rw_tlv_length, rw; int err; u16 size = 0; __be16 miux; diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index cc997518f79d..eaeb2b1cfa6a 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -301,7 +301,7 @@ static char *wks[] = { "urn:nfc:sn:snep", }; -static int nfc_llcp_wks_sap(char *service_name, size_t service_name_len) +static int nfc_llcp_wks_sap(const char *service_name, size_t service_name_len) { int sap, num_wks; @@ -325,7 +325,7 @@ static int nfc_llcp_wks_sap(char *service_name, size_t service_name_len) static struct nfc_llcp_sock *nfc_llcp_sock_from_sn(struct nfc_llcp_local *local, - u8 *sn, size_t sn_len) + const u8 *sn, size_t sn_len) { struct sock *sk; struct nfc_llcp_sock *llcp_sock, *tmp_sock; @@ -522,7 +522,7 @@ static int nfc_llcp_build_gb(struct nfc_llcp_local *local) { u8 *gb_cur, version, version_length; u8 lto_length, wks_length, miux_length; - u8 *version_tlv = NULL, *lto_tlv = NULL, + const u8 *version_tlv = NULL, *lto_tlv = NULL, *wks_tlv = NULL, *miux_tlv = NULL; __be16 wks = cpu_to_be16(local->local_wks); u8 gb_len = 0; @@ -612,7 +612,7 @@ u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len) return local->gb; } -int nfc_llcp_set_remote_gb(struct nfc_dev *dev, u8 *gb, u8 gb_len) +int nfc_llcp_set_remote_gb(struct nfc_dev *dev, const u8 *gb, u8 gb_len) { struct nfc_llcp_local *local; @@ -639,27 +639,27 @@ int nfc_llcp_set_remote_gb(struct nfc_dev *dev, u8 *gb, u8 gb_len) local->remote_gb_len - 3); } -static u8 nfc_llcp_dsap(struct sk_buff *pdu) +static u8 nfc_llcp_dsap(const struct sk_buff *pdu) { return (pdu->data[0] & 0xfc) >> 2; } -static u8 nfc_llcp_ptype(struct sk_buff *pdu) +static u8 nfc_llcp_ptype(const struct sk_buff *pdu) { return ((pdu->data[0] & 0x03) << 2) | ((pdu->data[1] & 0xc0) >> 6); } -static u8 nfc_llcp_ssap(struct sk_buff *pdu) +static u8 nfc_llcp_ssap(const struct sk_buff *pdu) { return pdu->data[1] & 0x3f; } -static u8 nfc_llcp_ns(struct sk_buff *pdu) +static u8 nfc_llcp_ns(const struct sk_buff *pdu) { return pdu->data[2] >> 4; } -static u8 nfc_llcp_nr(struct sk_buff *pdu) +static u8 nfc_llcp_nr(const struct sk_buff *pdu) { return pdu->data[2] & 0xf; } @@ -801,7 +801,7 @@ out: } static struct nfc_llcp_sock *nfc_llcp_sock_get_sn(struct nfc_llcp_local *local, - u8 *sn, size_t sn_len) + const u8 *sn, size_t sn_len) { struct nfc_llcp_sock *llcp_sock; @@ -815,9 +815,10 @@ static struct nfc_llcp_sock *nfc_llcp_sock_get_sn(struct nfc_llcp_local *local, return llcp_sock; } -static u8 *nfc_llcp_connect_sn(struct sk_buff *skb, size_t *sn_len) +static const u8 *nfc_llcp_connect_sn(const struct sk_buff *skb, size_t *sn_len) { - u8 *tlv = &skb->data[2], type, length; + u8 type, length; + const u8 *tlv = &skb->data[2]; size_t tlv_array_len = skb->len - LLCP_HEADER_SIZE, offset = 0; while (offset < tlv_array_len) { @@ -875,7 +876,7 @@ static void nfc_llcp_recv_ui(struct nfc_llcp_local *local, } static void nfc_llcp_recv_connect(struct nfc_llcp_local *local, - struct sk_buff *skb) + const struct sk_buff *skb) { struct sock *new_sk, *parent; struct nfc_llcp_sock *sock, *new_sock; @@ -893,7 +894,7 @@ static void nfc_llcp_recv_connect(struct nfc_llcp_local *local, goto fail; } } else { - u8 *sn; + const u8 *sn; size_t sn_len; sn = nfc_llcp_connect_sn(skb, &sn_len); @@ -1112,7 +1113,7 @@ static void nfc_llcp_recv_hdlc(struct nfc_llcp_local *local, } static void nfc_llcp_recv_disc(struct nfc_llcp_local *local, - struct sk_buff *skb) + const struct sk_buff *skb) { struct nfc_llcp_sock *llcp_sock; struct sock *sk; @@ -1155,7 +1156,8 @@ static void nfc_llcp_recv_disc(struct nfc_llcp_local *local, nfc_llcp_sock_put(llcp_sock); } -static void nfc_llcp_recv_cc(struct nfc_llcp_local *local, struct sk_buff *skb) +static void nfc_llcp_recv_cc(struct nfc_llcp_local *local, + const struct sk_buff *skb) { struct nfc_llcp_sock *llcp_sock; struct sock *sk; @@ -1188,7 +1190,8 @@ static void nfc_llcp_recv_cc(struct nfc_llcp_local *local, struct sk_buff *skb) nfc_llcp_sock_put(llcp_sock); } -static void nfc_llcp_recv_dm(struct nfc_llcp_local *local, struct sk_buff *skb) +static void nfc_llcp_recv_dm(struct nfc_llcp_local *local, + const struct sk_buff *skb) { struct nfc_llcp_sock *llcp_sock; struct sock *sk; @@ -1226,12 +1229,13 @@ static void nfc_llcp_recv_dm(struct nfc_llcp_local *local, struct sk_buff *skb) } static void nfc_llcp_recv_snl(struct nfc_llcp_local *local, - struct sk_buff *skb) + const struct sk_buff *skb) { struct nfc_llcp_sock *llcp_sock; - u8 dsap, ssap, *tlv, type, length, tid, sap; + u8 dsap, ssap, type, length, tid, sap; + const u8 *tlv; u16 tlv_len, offset; - char *service_name; + const char *service_name; size_t service_name_len; struct nfc_llcp_sdp_tlv *sdp; HLIST_HEAD(llc_sdres_list); diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index da7fe9db1b00..82ab39d80726 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -53,9 +53,9 @@ struct nci_conn_info *nci_get_conn_info_by_conn_id(struct nci_dev *ndev, } int nci_get_conn_info_by_dest_type_params(struct nci_dev *ndev, u8 dest_type, - struct dest_spec_params *params) + const struct dest_spec_params *params) { - struct nci_conn_info *conn_info; + const struct nci_conn_info *conn_info; list_for_each_entry(conn_info, &ndev->conn_info_list, list) { if (conn_info->dest_type == dest_type) { @@ -95,8 +95,8 @@ static void nci_req_cancel(struct nci_dev *ndev, int err) /* Execute request and wait for completion. */ static int __nci_request(struct nci_dev *ndev, - void (*req)(struct nci_dev *ndev, unsigned long opt), - unsigned long opt, __u32 timeout) + void (*req)(struct nci_dev *ndev, const void *opt), + const void *opt, __u32 timeout) { int rc = 0; long completion_rc; @@ -139,8 +139,8 @@ static int __nci_request(struct nci_dev *ndev, inline int nci_request(struct nci_dev *ndev, void (*req)(struct nci_dev *ndev, - unsigned long opt), - unsigned long opt, __u32 timeout) + const void *opt), + const void *opt, __u32 timeout) { int rc; @@ -155,7 +155,7 @@ inline int nci_request(struct nci_dev *ndev, return rc; } -static void nci_reset_req(struct nci_dev *ndev, unsigned long opt) +static void nci_reset_req(struct nci_dev *ndev, const void *opt) { struct nci_core_reset_cmd cmd; @@ -163,17 +163,17 @@ static void nci_reset_req(struct nci_dev *ndev, unsigned long opt) nci_send_cmd(ndev, NCI_OP_CORE_RESET_CMD, 1, &cmd); } -static void nci_init_req(struct nci_dev *ndev, unsigned long opt) +static void nci_init_req(struct nci_dev *ndev, const void *opt) { u8 plen = 0; if (opt) plen = sizeof(struct nci_core_init_v2_cmd); - nci_send_cmd(ndev, NCI_OP_CORE_INIT_CMD, plen, (void *)opt); + nci_send_cmd(ndev, NCI_OP_CORE_INIT_CMD, plen, opt); } -static void nci_init_complete_req(struct nci_dev *ndev, unsigned long opt) +static void nci_init_complete_req(struct nci_dev *ndev, const void *opt) { struct nci_rf_disc_map_cmd cmd; struct disc_map_config *cfg = cmd.mapping_configs; @@ -210,14 +210,14 @@ static void nci_init_complete_req(struct nci_dev *ndev, unsigned long opt) } struct nci_set_config_param { - __u8 id; - size_t len; - __u8 *val; + __u8 id; + size_t len; + const __u8 *val; }; -static void nci_set_config_req(struct nci_dev *ndev, unsigned long opt) +static void nci_set_config_req(struct nci_dev *ndev, const void *opt) { - struct nci_set_config_param *param = (struct nci_set_config_param *)opt; + const struct nci_set_config_param *param = opt; struct nci_core_set_config_cmd cmd; BUG_ON(param->len > NCI_MAX_PARAM_LEN); @@ -235,10 +235,9 @@ struct nci_rf_discover_param { __u32 tm_protocols; }; -static void nci_rf_discover_req(struct nci_dev *ndev, unsigned long opt) +static void nci_rf_discover_req(struct nci_dev *ndev, const void *opt) { - struct nci_rf_discover_param *param = - (struct nci_rf_discover_param *)opt; + const struct nci_rf_discover_param *param = opt; struct nci_rf_disc_cmd cmd; cmd.num_disc_configs = 0; @@ -301,10 +300,9 @@ struct nci_rf_discover_select_param { __u8 rf_protocol; }; -static void nci_rf_discover_select_req(struct nci_dev *ndev, unsigned long opt) +static void nci_rf_discover_select_req(struct nci_dev *ndev, const void *opt) { - struct nci_rf_discover_select_param *param = - (struct nci_rf_discover_select_param *)opt; + const struct nci_rf_discover_select_param *param = opt; struct nci_rf_discover_select_cmd cmd; cmd.rf_discovery_id = param->rf_discovery_id; @@ -328,11 +326,11 @@ static void nci_rf_discover_select_req(struct nci_dev *ndev, unsigned long opt) sizeof(struct nci_rf_discover_select_cmd), &cmd); } -static void nci_rf_deactivate_req(struct nci_dev *ndev, unsigned long opt) +static void nci_rf_deactivate_req(struct nci_dev *ndev, const void *opt) { struct nci_rf_deactivate_cmd cmd; - cmd.type = opt; + cmd.type = (unsigned long)opt; nci_send_cmd(ndev, NCI_OP_RF_DEACTIVATE_CMD, sizeof(struct nci_rf_deactivate_cmd), &cmd); @@ -341,18 +339,17 @@ static void nci_rf_deactivate_req(struct nci_dev *ndev, unsigned long opt) struct nci_cmd_param { __u16 opcode; size_t len; - __u8 *payload; + const __u8 *payload; }; -static void nci_generic_req(struct nci_dev *ndev, unsigned long opt) +static void nci_generic_req(struct nci_dev *ndev, const void *opt) { - struct nci_cmd_param *param = - (struct nci_cmd_param *)opt; + const struct nci_cmd_param *param = opt; nci_send_cmd(ndev, param->opcode, param->len, param->payload); } -int nci_prop_cmd(struct nci_dev *ndev, __u8 oid, size_t len, __u8 *payload) +int nci_prop_cmd(struct nci_dev *ndev, __u8 oid, size_t len, const __u8 *payload) { struct nci_cmd_param param; @@ -360,12 +357,13 @@ int nci_prop_cmd(struct nci_dev *ndev, __u8 oid, size_t len, __u8 *payload) param.len = len; param.payload = payload; - return __nci_request(ndev, nci_generic_req, (unsigned long)¶m, + return __nci_request(ndev, nci_generic_req, ¶m, msecs_to_jiffies(NCI_CMD_TIMEOUT)); } EXPORT_SYMBOL(nci_prop_cmd); -int nci_core_cmd(struct nci_dev *ndev, __u16 opcode, size_t len, __u8 *payload) +int nci_core_cmd(struct nci_dev *ndev, __u16 opcode, size_t len, + const __u8 *payload) { struct nci_cmd_param param; @@ -373,21 +371,21 @@ int nci_core_cmd(struct nci_dev *ndev, __u16 opcode, size_t len, __u8 *payload) param.len = len; param.payload = payload; - return __nci_request(ndev, nci_generic_req, (unsigned long)¶m, + return __nci_request(ndev, nci_generic_req, ¶m, msecs_to_jiffies(NCI_CMD_TIMEOUT)); } EXPORT_SYMBOL(nci_core_cmd); int nci_core_reset(struct nci_dev *ndev) { - return __nci_request(ndev, nci_reset_req, 0, + return __nci_request(ndev, nci_reset_req, (void *)0, msecs_to_jiffies(NCI_RESET_TIMEOUT)); } EXPORT_SYMBOL(nci_core_reset); int nci_core_init(struct nci_dev *ndev) { - return __nci_request(ndev, nci_init_req, 0, + return __nci_request(ndev, nci_init_req, (void *)0, msecs_to_jiffies(NCI_INIT_TIMEOUT)); } EXPORT_SYMBOL(nci_core_init); @@ -397,9 +395,9 @@ struct nci_loopback_data { struct sk_buff *data; }; -static void nci_send_data_req(struct nci_dev *ndev, unsigned long opt) +static void nci_send_data_req(struct nci_dev *ndev, const void *opt) { - struct nci_loopback_data *data = (struct nci_loopback_data *)opt; + const struct nci_loopback_data *data = opt; nci_send_data(ndev, data->conn_id, data->data); } @@ -407,7 +405,7 @@ static void nci_send_data_req(struct nci_dev *ndev, unsigned long opt) static void nci_nfcc_loopback_cb(void *context, struct sk_buff *skb, int err) { struct nci_dev *ndev = (struct nci_dev *)context; - struct nci_conn_info *conn_info; + struct nci_conn_info *conn_info; conn_info = nci_get_conn_info_by_conn_id(ndev, ndev->cur_conn_id); if (!conn_info) { @@ -420,7 +418,7 @@ static void nci_nfcc_loopback_cb(void *context, struct sk_buff *skb, int err) nci_req_complete(ndev, NCI_STATUS_OK); } -int nci_nfcc_loopback(struct nci_dev *ndev, void *data, size_t data_len, +int nci_nfcc_loopback(struct nci_dev *ndev, const void *data, size_t data_len, struct sk_buff **resp) { int r; @@ -460,7 +458,7 @@ int nci_nfcc_loopback(struct nci_dev *ndev, void *data, size_t data_len, loopback_data.data = skb; ndev->cur_conn_id = conn_id; - r = nci_request(ndev, nci_send_data_req, (unsigned long)&loopback_data, + r = nci_request(ndev, nci_send_data_req, &loopback_data, msecs_to_jiffies(NCI_DATA_TIMEOUT)); if (r == NCI_STATUS_OK && resp) *resp = conn_info->rx_skb; @@ -493,7 +491,7 @@ static int nci_open_device(struct nci_dev *ndev) rc = ndev->ops->init(ndev); if (!rc) { - rc = __nci_request(ndev, nci_reset_req, 0, + rc = __nci_request(ndev, nci_reset_req, (void *)0, msecs_to_jiffies(NCI_RESET_TIMEOUT)); } @@ -506,10 +504,10 @@ static int nci_open_device(struct nci_dev *ndev) .feature1 = NCI_FEATURE_DISABLE, .feature2 = NCI_FEATURE_DISABLE }; - unsigned long opt = 0; + const void *opt = NULL; if (ndev->nci_ver & NCI_VER_2_MASK) - opt = (unsigned long)&nci_init_v2_cmd; + opt = &nci_init_v2_cmd; rc = __nci_request(ndev, nci_init_req, opt, msecs_to_jiffies(NCI_INIT_TIMEOUT)); @@ -519,7 +517,7 @@ static int nci_open_device(struct nci_dev *ndev) rc = ndev->ops->post_setup(ndev); if (!rc) { - rc = __nci_request(ndev, nci_init_complete_req, 0, + rc = __nci_request(ndev, nci_init_complete_req, (void *)0, msecs_to_jiffies(NCI_INIT_TIMEOUT)); } @@ -569,7 +567,7 @@ static int nci_close_device(struct nci_dev *ndev) atomic_set(&ndev->cmd_cnt, 1); set_bit(NCI_INIT, &ndev->flags); - __nci_request(ndev, nci_reset_req, 0, + __nci_request(ndev, nci_reset_req, (void *)0, msecs_to_jiffies(NCI_RESET_TIMEOUT)); /* After this point our queues are empty @@ -624,7 +622,7 @@ static int nci_dev_down(struct nfc_dev *nfc_dev) return nci_close_device(ndev); } -int nci_set_config(struct nci_dev *ndev, __u8 id, size_t len, __u8 *val) +int nci_set_config(struct nci_dev *ndev, __u8 id, size_t len, const __u8 *val) { struct nci_set_config_param param; @@ -635,15 +633,15 @@ int nci_set_config(struct nci_dev *ndev, __u8 id, size_t len, __u8 *val) param.len = len; param.val = val; - return __nci_request(ndev, nci_set_config_req, (unsigned long)¶m, + return __nci_request(ndev, nci_set_config_req, ¶m, msecs_to_jiffies(NCI_SET_CONFIG_TIMEOUT)); } EXPORT_SYMBOL(nci_set_config); -static void nci_nfcee_discover_req(struct nci_dev *ndev, unsigned long opt) +static void nci_nfcee_discover_req(struct nci_dev *ndev, const void *opt) { struct nci_nfcee_discover_cmd cmd; - __u8 action = opt; + __u8 action = (unsigned long)opt; cmd.discovery_action = action; @@ -652,15 +650,16 @@ static void nci_nfcee_discover_req(struct nci_dev *ndev, unsigned long opt) int nci_nfcee_discover(struct nci_dev *ndev, u8 action) { - return __nci_request(ndev, nci_nfcee_discover_req, action, + unsigned long opt = action; + + return __nci_request(ndev, nci_nfcee_discover_req, (void *)opt, msecs_to_jiffies(NCI_CMD_TIMEOUT)); } EXPORT_SYMBOL(nci_nfcee_discover); -static void nci_nfcee_mode_set_req(struct nci_dev *ndev, unsigned long opt) +static void nci_nfcee_mode_set_req(struct nci_dev *ndev, const void *opt) { - struct nci_nfcee_mode_set_cmd *cmd = - (struct nci_nfcee_mode_set_cmd *)opt; + const struct nci_nfcee_mode_set_cmd *cmd = opt; nci_send_cmd(ndev, NCI_OP_NFCEE_MODE_SET_CMD, sizeof(struct nci_nfcee_mode_set_cmd), cmd); @@ -673,16 +672,14 @@ int nci_nfcee_mode_set(struct nci_dev *ndev, u8 nfcee_id, u8 nfcee_mode) cmd.nfcee_id = nfcee_id; cmd.nfcee_mode = nfcee_mode; - return __nci_request(ndev, nci_nfcee_mode_set_req, - (unsigned long)&cmd, + return __nci_request(ndev, nci_nfcee_mode_set_req, &cmd, msecs_to_jiffies(NCI_CMD_TIMEOUT)); } EXPORT_SYMBOL(nci_nfcee_mode_set); -static void nci_core_conn_create_req(struct nci_dev *ndev, unsigned long opt) +static void nci_core_conn_create_req(struct nci_dev *ndev, const void *opt) { - struct core_conn_create_data *data = - (struct core_conn_create_data *)opt; + const struct core_conn_create_data *data = opt; nci_send_cmd(ndev, NCI_OP_CORE_CONN_CREATE_CMD, data->length, data->cmd); } @@ -690,7 +687,7 @@ static void nci_core_conn_create_req(struct nci_dev *ndev, unsigned long opt) int nci_core_conn_create(struct nci_dev *ndev, u8 destination_type, u8 number_destination_params, size_t params_len, - struct core_conn_create_dest_spec_params *params) + const struct core_conn_create_dest_spec_params *params) { int r; struct nci_core_conn_create_cmd *cmd; @@ -719,24 +716,26 @@ int nci_core_conn_create(struct nci_dev *ndev, u8 destination_type, } ndev->cur_dest_type = destination_type; - r = __nci_request(ndev, nci_core_conn_create_req, (unsigned long)&data, + r = __nci_request(ndev, nci_core_conn_create_req, &data, msecs_to_jiffies(NCI_CMD_TIMEOUT)); kfree(cmd); return r; } EXPORT_SYMBOL(nci_core_conn_create); -static void nci_core_conn_close_req(struct nci_dev *ndev, unsigned long opt) +static void nci_core_conn_close_req(struct nci_dev *ndev, const void *opt) { - __u8 conn_id = opt; + __u8 conn_id = (unsigned long)opt; nci_send_cmd(ndev, NCI_OP_CORE_CONN_CLOSE_CMD, 1, &conn_id); } int nci_core_conn_close(struct nci_dev *ndev, u8 conn_id) { + unsigned long opt = conn_id; + ndev->cur_conn_id = conn_id; - return __nci_request(ndev, nci_core_conn_close_req, conn_id, + return __nci_request(ndev, nci_core_conn_close_req, (void *)opt, msecs_to_jiffies(NCI_CMD_TIMEOUT)); } EXPORT_SYMBOL(nci_core_conn_close); @@ -756,14 +755,14 @@ static int nci_set_local_general_bytes(struct nfc_dev *nfc_dev) param.id = NCI_PN_ATR_REQ_GEN_BYTES; - rc = nci_request(ndev, nci_set_config_req, (unsigned long)¶m, + rc = nci_request(ndev, nci_set_config_req, ¶m, msecs_to_jiffies(NCI_SET_CONFIG_TIMEOUT)); if (rc) return rc; param.id = NCI_LN_ATR_RES_GEN_BYTES; - return nci_request(ndev, nci_set_config_req, (unsigned long)¶m, + return nci_request(ndev, nci_set_config_req, ¶m, msecs_to_jiffies(NCI_SET_CONFIG_TIMEOUT)); } @@ -813,7 +812,7 @@ static int nci_start_poll(struct nfc_dev *nfc_dev, pr_debug("target active or w4 select, implicitly deactivate\n"); rc = nci_request(ndev, nci_rf_deactivate_req, - NCI_DEACTIVATE_TYPE_IDLE_MODE, + (void *)NCI_DEACTIVATE_TYPE_IDLE_MODE, msecs_to_jiffies(NCI_RF_DEACTIVATE_TIMEOUT)); if (rc) return -EBUSY; @@ -835,7 +834,7 @@ static int nci_start_poll(struct nfc_dev *nfc_dev, param.im_protocols = im_protocols; param.tm_protocols = tm_protocols; - rc = nci_request(ndev, nci_rf_discover_req, (unsigned long)¶m, + rc = nci_request(ndev, nci_rf_discover_req, ¶m, msecs_to_jiffies(NCI_RF_DISC_TIMEOUT)); if (!rc) @@ -854,7 +853,8 @@ static void nci_stop_poll(struct nfc_dev *nfc_dev) return; } - nci_request(ndev, nci_rf_deactivate_req, NCI_DEACTIVATE_TYPE_IDLE_MODE, + nci_request(ndev, nci_rf_deactivate_req, + (void *)NCI_DEACTIVATE_TYPE_IDLE_MODE, msecs_to_jiffies(NCI_RF_DEACTIVATE_TIMEOUT)); } @@ -863,7 +863,7 @@ static int nci_activate_target(struct nfc_dev *nfc_dev, { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); struct nci_rf_discover_select_param param; - struct nfc_target *nci_target = NULL; + const struct nfc_target *nci_target = NULL; int i; int rc = 0; @@ -913,8 +913,7 @@ static int nci_activate_target(struct nfc_dev *nfc_dev, else param.rf_protocol = NCI_RF_PROTOCOL_NFC_DEP; - rc = nci_request(ndev, nci_rf_discover_select_req, - (unsigned long)¶m, + rc = nci_request(ndev, nci_rf_discover_select_req, ¶m, msecs_to_jiffies(NCI_RF_DISC_SELECT_TIMEOUT)); } @@ -929,7 +928,7 @@ static void nci_deactivate_target(struct nfc_dev *nfc_dev, __u8 mode) { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); - u8 nci_mode = NCI_DEACTIVATE_TYPE_IDLE_MODE; + unsigned long nci_mode = NCI_DEACTIVATE_TYPE_IDLE_MODE; pr_debug("entry\n"); @@ -947,7 +946,7 @@ static void nci_deactivate_target(struct nfc_dev *nfc_dev, } if (atomic_read(&ndev->state) == NCI_POLL_ACTIVE) { - nci_request(ndev, nci_rf_deactivate_req, nci_mode, + nci_request(ndev, nci_rf_deactivate_req, (void *)nci_mode, msecs_to_jiffies(NCI_RF_DEACTIVATE_TIMEOUT)); } } @@ -985,8 +984,8 @@ static int nci_dep_link_down(struct nfc_dev *nfc_dev) } else { if (atomic_read(&ndev->state) == NCI_LISTEN_ACTIVE || atomic_read(&ndev->state) == NCI_DISCOVERY) { - nci_request(ndev, nci_rf_deactivate_req, 0, - msecs_to_jiffies(NCI_RF_DEACTIVATE_TIMEOUT)); + nci_request(ndev, nci_rf_deactivate_req, (void *)0, + msecs_to_jiffies(NCI_RF_DEACTIVATE_TIMEOUT)); } rc = nfc_tm_deactivated(nfc_dev); @@ -1004,7 +1003,7 @@ static int nci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target, { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); int rc; - struct nci_conn_info *conn_info; + struct nci_conn_info *conn_info; conn_info = ndev->rf_conn_info; if (!conn_info) @@ -1102,7 +1101,7 @@ static int nci_fw_download(struct nfc_dev *nfc_dev, const char *firmware_name) return ndev->ops->fw_download(ndev, firmware_name); } -static struct nfc_ops nci_nfc_ops = { +static const struct nfc_ops nci_nfc_ops = { .dev_up = nci_dev_up, .dev_down = nci_dev_down, .start_poll = nci_start_poll, @@ -1129,7 +1128,7 @@ static struct nfc_ops nci_nfc_ops = { * @tx_headroom: Reserved space at beginning of skb * @tx_tailroom: Reserved space at end of skb */ -struct nci_dev *nci_allocate_device(struct nci_ops *ops, +struct nci_dev *nci_allocate_device(const struct nci_ops *ops, __u32 supported_protocols, int tx_headroom, int tx_tailroom) { @@ -1152,8 +1151,7 @@ struct nci_dev *nci_allocate_device(struct nci_ops *ops, if (ops->n_prop_ops > NCI_MAX_PROPRIETARY_CMD) { pr_err("Too many proprietary commands: %zd\n", ops->n_prop_ops); - ops->prop_ops = NULL; - ops->n_prop_ops = 0; + goto free_nci; } ndev->tx_headroom = tx_headroom; @@ -1270,7 +1268,7 @@ EXPORT_SYMBOL(nci_register_device); */ void nci_unregister_device(struct nci_dev *ndev) { - struct nci_conn_info *conn_info, *n; + struct nci_conn_info *conn_info, *n; nci_close_device(ndev); @@ -1332,7 +1330,7 @@ int nci_send_frame(struct nci_dev *ndev, struct sk_buff *skb) EXPORT_SYMBOL(nci_send_frame); /* Send NCI command */ -int nci_send_cmd(struct nci_dev *ndev, __u16 opcode, __u8 plen, void *payload) +int nci_send_cmd(struct nci_dev *ndev, __u16 opcode, __u8 plen, const void *payload) { struct nci_ctrl_hdr *hdr; struct sk_buff *skb; @@ -1364,12 +1362,12 @@ int nci_send_cmd(struct nci_dev *ndev, __u16 opcode, __u8 plen, void *payload) EXPORT_SYMBOL(nci_send_cmd); /* Proprietary commands API */ -static struct nci_driver_ops *ops_cmd_lookup(struct nci_driver_ops *ops, - size_t n_ops, - __u16 opcode) +static const struct nci_driver_ops *ops_cmd_lookup(const struct nci_driver_ops *ops, + size_t n_ops, + __u16 opcode) { size_t i; - struct nci_driver_ops *op; + const struct nci_driver_ops *op; if (!ops || !n_ops) return NULL; @@ -1384,10 +1382,10 @@ static struct nci_driver_ops *ops_cmd_lookup(struct nci_driver_ops *ops, } static int nci_op_rsp_packet(struct nci_dev *ndev, __u16 rsp_opcode, - struct sk_buff *skb, struct nci_driver_ops *ops, + struct sk_buff *skb, const struct nci_driver_ops *ops, size_t n_ops) { - struct nci_driver_ops *op; + const struct nci_driver_ops *op; op = ops_cmd_lookup(ops, n_ops, rsp_opcode); if (!op || !op->rsp) @@ -1397,10 +1395,10 @@ static int nci_op_rsp_packet(struct nci_dev *ndev, __u16 rsp_opcode, } static int nci_op_ntf_packet(struct nci_dev *ndev, __u16 ntf_opcode, - struct sk_buff *skb, struct nci_driver_ops *ops, + struct sk_buff *skb, const struct nci_driver_ops *ops, size_t n_ops) { - struct nci_driver_ops *op; + const struct nci_driver_ops *op; op = ops_cmd_lookup(ops, n_ops, ntf_opcode); if (!op || !op->ntf) @@ -1442,7 +1440,7 @@ int nci_core_ntf_packet(struct nci_dev *ndev, __u16 opcode, static void nci_tx_work(struct work_struct *work) { struct nci_dev *ndev = container_of(work, struct nci_dev, tx_work); - struct nci_conn_info *conn_info; + struct nci_conn_info *conn_info; struct sk_buff *skb; conn_info = nci_get_conn_info_by_conn_id(ndev, ndev->cur_conn_id); diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c index ce3382be937f..6055dc9a82aa 100644 --- a/net/nfc/nci/data.c +++ b/net/nfc/nci/data.c @@ -26,7 +26,7 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb, __u8 conn_id, int err) { - struct nci_conn_info *conn_info; + const struct nci_conn_info *conn_info; data_exchange_cb_t cb; void *cb_context; @@ -80,7 +80,7 @@ static inline void nci_push_data_hdr(struct nci_dev *ndev, int nci_conn_max_data_pkt_payload_size(struct nci_dev *ndev, __u8 conn_id) { - struct nci_conn_info *conn_info; + const struct nci_conn_info *conn_info; conn_info = nci_get_conn_info_by_conn_id(ndev, conn_id); if (!conn_info) @@ -93,9 +93,9 @@ EXPORT_SYMBOL(nci_conn_max_data_pkt_payload_size); static int nci_queue_tx_data_frags(struct nci_dev *ndev, __u8 conn_id, struct sk_buff *skb) { - struct nci_conn_info *conn_info; + const struct nci_conn_info *conn_info; int total_len = skb->len; - unsigned char *data = skb->data; + const unsigned char *data = skb->data; unsigned long flags; struct sk_buff_head frags_q; struct sk_buff *skb_frag; @@ -166,7 +166,7 @@ exit: /* Send NCI data */ int nci_send_data(struct nci_dev *ndev, __u8 conn_id, struct sk_buff *skb) { - struct nci_conn_info *conn_info; + const struct nci_conn_info *conn_info; int rc = 0; pr_debug("conn_id 0x%x, plen %d\n", conn_id, skb->len); @@ -269,7 +269,7 @@ void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb) __u8 pbf = nci_pbf(skb->data); __u8 status = 0; __u8 conn_id = nci_conn_id(skb->data); - struct nci_conn_info *conn_info; + const struct nci_conn_info *conn_info; pr_debug("len %d\n", skb->len); diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c index d6732e5e8958..e199912ee1e5 100644 --- a/net/nfc/nci/hci.c +++ b/net/nfc/nci/hci.c @@ -16,11 +16,11 @@ #include <linux/nfc.h> struct nci_data { - u8 conn_id; - u8 pipe; - u8 cmd; - const u8 *data; - u32 data_len; + u8 conn_id; + u8 pipe; + u8 cmd; + const u8 *data; + u32 data_len; } __packed; struct nci_hci_create_pipe_params { @@ -142,7 +142,7 @@ static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe, const u8 data_type, const u8 *data, size_t data_len) { - struct nci_conn_info *conn_info; + const struct nci_conn_info *conn_info; struct sk_buff *skb; int len, i, r; u8 cb = pipe; @@ -195,9 +195,9 @@ static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe, return i; } -static void nci_hci_send_data_req(struct nci_dev *ndev, unsigned long opt) +static void nci_hci_send_data_req(struct nci_dev *ndev, const void *opt) { - struct nci_data *data = (struct nci_data *)opt; + const struct nci_data *data = opt; nci_hci_send_data(ndev, data->pipe, data->cmd, data->data, data->data_len); @@ -221,8 +221,8 @@ int nci_hci_send_cmd(struct nci_dev *ndev, u8 gate, u8 cmd, const u8 *param, size_t param_len, struct sk_buff **skb) { - struct nci_hcp_message *message; - struct nci_conn_info *conn_info; + const struct nci_hcp_message *message; + const struct nci_conn_info *conn_info; struct nci_data data; int r; u8 pipe = ndev->hci_dev->gate2pipe[gate]; @@ -240,7 +240,7 @@ int nci_hci_send_cmd(struct nci_dev *ndev, u8 gate, u8 cmd, data.data = param; data.data_len = param_len; - r = nci_request(ndev, nci_hci_send_data_req, (unsigned long)&data, + r = nci_request(ndev, nci_hci_send_data_req, &data, msecs_to_jiffies(NCI_DATA_TIMEOUT)); if (r == NCI_STATUS_OK) { message = (struct nci_hcp_message *)conn_info->rx_skb->data; @@ -363,7 +363,7 @@ exit: static void nci_hci_resp_received(struct nci_dev *ndev, u8 pipe, struct sk_buff *skb) { - struct nci_conn_info *conn_info; + struct nci_conn_info *conn_info; conn_info = ndev->hci_dev->conn_info; if (!conn_info) @@ -406,7 +406,7 @@ static void nci_hci_msg_rx_work(struct work_struct *work) struct nci_hci_dev *hdev = container_of(work, struct nci_hci_dev, msg_rx_work); struct sk_buff *skb; - struct nci_hcp_message *message; + const struct nci_hcp_message *message; u8 pipe, type, instruction; while ((skb = skb_dequeue(&hdev->msg_rx_queue)) != NULL) { @@ -498,7 +498,7 @@ void nci_hci_data_received_cb(void *context, int nci_hci_open_pipe(struct nci_dev *ndev, u8 pipe) { struct nci_data data; - struct nci_conn_info *conn_info; + const struct nci_conn_info *conn_info; conn_info = ndev->hci_dev->conn_info; if (!conn_info) @@ -511,9 +511,8 @@ int nci_hci_open_pipe(struct nci_dev *ndev, u8 pipe) data.data = NULL; data.data_len = 0; - return nci_request(ndev, nci_hci_send_data_req, - (unsigned long)&data, - msecs_to_jiffies(NCI_DATA_TIMEOUT)); + return nci_request(ndev, nci_hci_send_data_req, &data, + msecs_to_jiffies(NCI_DATA_TIMEOUT)); } EXPORT_SYMBOL(nci_hci_open_pipe); @@ -523,7 +522,7 @@ static u8 nci_hci_create_pipe(struct nci_dev *ndev, u8 dest_host, u8 pipe; struct sk_buff *skb; struct nci_hci_create_pipe_params params; - struct nci_hci_create_pipe_resp *resp; + const struct nci_hci_create_pipe_resp *resp; pr_debug("gate=%d\n", dest_gate); @@ -557,8 +556,8 @@ static int nci_hci_delete_pipe(struct nci_dev *ndev, u8 pipe) int nci_hci_set_param(struct nci_dev *ndev, u8 gate, u8 idx, const u8 *param, size_t param_len) { - struct nci_hcp_message *message; - struct nci_conn_info *conn_info; + const struct nci_hcp_message *message; + const struct nci_conn_info *conn_info; struct nci_data data; int r; u8 *tmp; @@ -587,8 +586,7 @@ int nci_hci_set_param(struct nci_dev *ndev, u8 gate, u8 idx, data.data = tmp; data.data_len = param_len + 1; - r = nci_request(ndev, nci_hci_send_data_req, - (unsigned long)&data, + r = nci_request(ndev, nci_hci_send_data_req, &data, msecs_to_jiffies(NCI_DATA_TIMEOUT)); if (r == NCI_STATUS_OK) { message = (struct nci_hcp_message *)conn_info->rx_skb->data; @@ -605,8 +603,8 @@ EXPORT_SYMBOL(nci_hci_set_param); int nci_hci_get_param(struct nci_dev *ndev, u8 gate, u8 idx, struct sk_buff **skb) { - struct nci_hcp_message *message; - struct nci_conn_info *conn_info; + const struct nci_hcp_message *message; + const struct nci_conn_info *conn_info; struct nci_data data; int r; u8 pipe = ndev->hci_dev->gate2pipe[gate]; @@ -627,7 +625,7 @@ int nci_hci_get_param(struct nci_dev *ndev, u8 gate, u8 idx, data.data = &idx; data.data_len = 1; - r = nci_request(ndev, nci_hci_send_data_req, (unsigned long)&data, + r = nci_request(ndev, nci_hci_send_data_req, &data, msecs_to_jiffies(NCI_DATA_TIMEOUT)); if (r == NCI_STATUS_OK) { @@ -697,7 +695,7 @@ EXPORT_SYMBOL(nci_hci_connect_gate); static int nci_hci_dev_connect_gates(struct nci_dev *ndev, u8 gate_count, - struct nci_hci_gate *gates) + const struct nci_hci_gate *gates) { int r; @@ -714,7 +712,7 @@ static int nci_hci_dev_connect_gates(struct nci_dev *ndev, int nci_hci_dev_session_init(struct nci_dev *ndev) { - struct nci_conn_info *conn_info; + struct nci_conn_info *conn_info; struct sk_buff *skb; int r; diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c index 98af04c86b2c..c5eacaac41ae 100644 --- a/net/nfc/nci/ntf.c +++ b/net/nfc/nci/ntf.c @@ -28,10 +28,10 @@ /* Handle NCI Notification packets */ static void nci_core_reset_ntf_packet(struct nci_dev *ndev, - struct sk_buff *skb) + const struct sk_buff *skb) { /* Handle NCI 2.x core reset notification */ - struct nci_core_reset_ntf *ntf = (void *)skb->data; + const struct nci_core_reset_ntf *ntf = (void *)skb->data; ndev->nci_ver = ntf->nci_ver; pr_debug("nci_ver 0x%x, config_status 0x%x\n", @@ -48,7 +48,7 @@ static void nci_core_conn_credits_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb) { struct nci_core_conn_credit_ntf *ntf = (void *) skb->data; - struct nci_conn_info *conn_info; + struct nci_conn_info *conn_info; int i; pr_debug("num_entries %d\n", ntf->num_entries); @@ -80,7 +80,7 @@ static void nci_core_conn_credits_ntf_packet(struct nci_dev *ndev, } static void nci_core_generic_error_ntf_packet(struct nci_dev *ndev, - struct sk_buff *skb) + const struct sk_buff *skb) { __u8 status = skb->data[0]; @@ -107,9 +107,10 @@ static void nci_core_conn_intf_error_ntf_packet(struct nci_dev *ndev, nci_data_exchange_complete(ndev, NULL, ntf->conn_id, -EIO); } -static __u8 *nci_extract_rf_params_nfca_passive_poll(struct nci_dev *ndev, - struct rf_tech_specific_params_nfca_poll *nfca_poll, - __u8 *data) +static const __u8 * +nci_extract_rf_params_nfca_passive_poll(struct nci_dev *ndev, + struct rf_tech_specific_params_nfca_poll *nfca_poll, + const __u8 *data) { nfca_poll->sens_res = __le16_to_cpu(*((__le16 *)data)); data += 2; @@ -134,9 +135,10 @@ static __u8 *nci_extract_rf_params_nfca_passive_poll(struct nci_dev *ndev, return data; } -static __u8 *nci_extract_rf_params_nfcb_passive_poll(struct nci_dev *ndev, - struct rf_tech_specific_params_nfcb_poll *nfcb_poll, - __u8 *data) +static const __u8 * +nci_extract_rf_params_nfcb_passive_poll(struct nci_dev *ndev, + struct rf_tech_specific_params_nfcb_poll *nfcb_poll, + const __u8 *data) { nfcb_poll->sensb_res_len = min_t(__u8, *data++, NFC_SENSB_RES_MAXSIZE); @@ -148,9 +150,10 @@ static __u8 *nci_extract_rf_params_nfcb_passive_poll(struct nci_dev *ndev, return data; } -static __u8 *nci_extract_rf_params_nfcf_passive_poll(struct nci_dev *ndev, - struct rf_tech_specific_params_nfcf_poll *nfcf_poll, - __u8 *data) +static const __u8 * +nci_extract_rf_params_nfcf_passive_poll(struct nci_dev *ndev, + struct rf_tech_specific_params_nfcf_poll *nfcf_poll, + const __u8 *data) { nfcf_poll->bit_rate = *data++; nfcf_poll->sensf_res_len = min_t(__u8, *data++, NFC_SENSF_RES_MAXSIZE); @@ -164,9 +167,10 @@ static __u8 *nci_extract_rf_params_nfcf_passive_poll(struct nci_dev *ndev, return data; } -static __u8 *nci_extract_rf_params_nfcv_passive_poll(struct nci_dev *ndev, - struct rf_tech_specific_params_nfcv_poll *nfcv_poll, - __u8 *data) +static const __u8 * +nci_extract_rf_params_nfcv_passive_poll(struct nci_dev *ndev, + struct rf_tech_specific_params_nfcv_poll *nfcv_poll, + const __u8 *data) { ++data; nfcv_poll->dsfid = *data++; @@ -175,9 +179,10 @@ static __u8 *nci_extract_rf_params_nfcv_passive_poll(struct nci_dev *ndev, return data; } -static __u8 *nci_extract_rf_params_nfcf_passive_listen(struct nci_dev *ndev, - struct rf_tech_specific_params_nfcf_listen *nfcf_listen, - __u8 *data) +static const __u8 * +nci_extract_rf_params_nfcf_passive_listen(struct nci_dev *ndev, + struct rf_tech_specific_params_nfcf_listen *nfcf_listen, + const __u8 *data) { nfcf_listen->local_nfcid2_len = min_t(__u8, *data++, NFC_NFCID2_MAXSIZE); @@ -198,12 +203,12 @@ static int nci_add_new_protocol(struct nci_dev *ndev, struct nfc_target *target, __u8 rf_protocol, __u8 rf_tech_and_mode, - void *params) + const void *params) { - struct rf_tech_specific_params_nfca_poll *nfca_poll; - struct rf_tech_specific_params_nfcb_poll *nfcb_poll; - struct rf_tech_specific_params_nfcf_poll *nfcf_poll; - struct rf_tech_specific_params_nfcv_poll *nfcv_poll; + const struct rf_tech_specific_params_nfca_poll *nfca_poll; + const struct rf_tech_specific_params_nfcb_poll *nfcb_poll; + const struct rf_tech_specific_params_nfcf_poll *nfcf_poll; + const struct rf_tech_specific_params_nfcv_poll *nfcv_poll; __u32 protocol; if (rf_protocol == NCI_RF_PROTOCOL_T1T) @@ -274,7 +279,7 @@ static int nci_add_new_protocol(struct nci_dev *ndev, } static void nci_add_new_target(struct nci_dev *ndev, - struct nci_rf_discover_ntf *ntf) + const struct nci_rf_discover_ntf *ntf) { struct nfc_target *target; int i, rc; @@ -319,10 +324,10 @@ void nci_clear_target_list(struct nci_dev *ndev) } static void nci_rf_discover_ntf_packet(struct nci_dev *ndev, - struct sk_buff *skb) + const struct sk_buff *skb) { struct nci_rf_discover_ntf ntf; - __u8 *data = skb->data; + const __u8 *data = skb->data; bool add_target = true; ntf.rf_discovery_id = *data++; @@ -382,7 +387,8 @@ static void nci_rf_discover_ntf_packet(struct nci_dev *ndev, } static int nci_extract_activation_params_iso_dep(struct nci_dev *ndev, - struct nci_rf_intf_activated_ntf *ntf, __u8 *data) + struct nci_rf_intf_activated_ntf *ntf, + const __u8 *data) { struct activation_params_nfca_poll_iso_dep *nfca_poll; struct activation_params_nfcb_poll_iso_dep *nfcb_poll; @@ -418,7 +424,8 @@ static int nci_extract_activation_params_iso_dep(struct nci_dev *ndev, } static int nci_extract_activation_params_nfc_dep(struct nci_dev *ndev, - struct nci_rf_intf_activated_ntf *ntf, __u8 *data) + struct nci_rf_intf_activated_ntf *ntf, + const __u8 *data) { struct activation_params_poll_nfc_dep *poll; struct activation_params_listen_nfc_dep *listen; @@ -454,7 +461,7 @@ static int nci_extract_activation_params_nfc_dep(struct nci_dev *ndev, } static void nci_target_auto_activated(struct nci_dev *ndev, - struct nci_rf_intf_activated_ntf *ntf) + const struct nci_rf_intf_activated_ntf *ntf) { struct nfc_target *target; int rc; @@ -477,7 +484,7 @@ static void nci_target_auto_activated(struct nci_dev *ndev, } static int nci_store_general_bytes_nfc_dep(struct nci_dev *ndev, - struct nci_rf_intf_activated_ntf *ntf) + const struct nci_rf_intf_activated_ntf *ntf) { ndev->remote_gb_len = 0; @@ -519,11 +526,11 @@ static int nci_store_general_bytes_nfc_dep(struct nci_dev *ndev, } static void nci_rf_intf_activated_ntf_packet(struct nci_dev *ndev, - struct sk_buff *skb) + const struct sk_buff *skb) { - struct nci_conn_info *conn_info; + struct nci_conn_info *conn_info; struct nci_rf_intf_activated_ntf ntf; - __u8 *data = skb->data; + const __u8 *data = skb->data; int err = NCI_STATUS_OK; ntf.rf_discovery_id = *data++; @@ -681,10 +688,10 @@ listen: } static void nci_rf_deactivate_ntf_packet(struct nci_dev *ndev, - struct sk_buff *skb) + const struct sk_buff *skb) { - struct nci_conn_info *conn_info; - struct nci_rf_deactivate_ntf *ntf = (void *) skb->data; + const struct nci_conn_info *conn_info; + const struct nci_rf_deactivate_ntf *ntf = (void *)skb->data; pr_debug("entry, type 0x%x, reason 0x%x\n", ntf->type, ntf->reason); @@ -725,10 +732,10 @@ static void nci_rf_deactivate_ntf_packet(struct nci_dev *ndev, } static void nci_nfcee_discover_ntf_packet(struct nci_dev *ndev, - struct sk_buff *skb) + const struct sk_buff *skb) { u8 status = NCI_STATUS_OK; - struct nci_nfcee_discover_ntf *nfcee_ntf = + const struct nci_nfcee_discover_ntf *nfcee_ntf = (struct nci_nfcee_discover_ntf *)skb->data; pr_debug("\n"); @@ -745,7 +752,7 @@ static void nci_nfcee_discover_ntf_packet(struct nci_dev *ndev, } static void nci_nfcee_action_ntf_packet(struct nci_dev *ndev, - struct sk_buff *skb) + const struct sk_buff *skb) { pr_debug("\n"); } diff --git a/net/nfc/nci/rsp.c b/net/nfc/nci/rsp.c index e9605922a322..a2e72c003805 100644 --- a/net/nfc/nci/rsp.c +++ b/net/nfc/nci/rsp.c @@ -25,9 +25,10 @@ /* Handle NCI Response packets */ -static void nci_core_reset_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb) +static void nci_core_reset_rsp_packet(struct nci_dev *ndev, + const struct sk_buff *skb) { - struct nci_core_reset_rsp *rsp = (void *) skb->data; + const struct nci_core_reset_rsp *rsp = (void *)skb->data; pr_debug("status 0x%x\n", rsp->status); @@ -43,10 +44,11 @@ static void nci_core_reset_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb) } } -static u8 nci_core_init_rsp_packet_v1(struct nci_dev *ndev, struct sk_buff *skb) +static u8 nci_core_init_rsp_packet_v1(struct nci_dev *ndev, + const struct sk_buff *skb) { - struct nci_core_init_rsp_1 *rsp_1 = (void *) skb->data; - struct nci_core_init_rsp_2 *rsp_2; + const struct nci_core_init_rsp_1 *rsp_1 = (void *)skb->data; + const struct nci_core_init_rsp_2 *rsp_2; pr_debug("status 0x%x\n", rsp_1->status); @@ -81,10 +83,11 @@ static u8 nci_core_init_rsp_packet_v1(struct nci_dev *ndev, struct sk_buff *skb) return NCI_STATUS_OK; } -static u8 nci_core_init_rsp_packet_v2(struct nci_dev *ndev, struct sk_buff *skb) +static u8 nci_core_init_rsp_packet_v2(struct nci_dev *ndev, + const struct sk_buff *skb) { - struct nci_core_init_rsp_nci_ver2 *rsp = (void *)skb->data; - u8 *supported_rf_interface = rsp->supported_rf_interfaces; + const struct nci_core_init_rsp_nci_ver2 *rsp = (void *)skb->data; + const u8 *supported_rf_interface = rsp->supported_rf_interfaces; u8 rf_interface_idx = 0; u8 rf_extension_cnt = 0; @@ -118,7 +121,7 @@ static u8 nci_core_init_rsp_packet_v2(struct nci_dev *ndev, struct sk_buff *skb) return NCI_STATUS_OK; } -static void nci_core_init_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb) +static void nci_core_init_rsp_packet(struct nci_dev *ndev, const struct sk_buff *skb) { u8 status = 0; @@ -160,9 +163,9 @@ exit: } static void nci_core_set_config_rsp_packet(struct nci_dev *ndev, - struct sk_buff *skb) + const struct sk_buff *skb) { - struct nci_core_set_config_rsp *rsp = (void *) skb->data; + const struct nci_core_set_config_rsp *rsp = (void *)skb->data; pr_debug("status 0x%x\n", rsp->status); @@ -170,7 +173,7 @@ static void nci_core_set_config_rsp_packet(struct nci_dev *ndev, } static void nci_rf_disc_map_rsp_packet(struct nci_dev *ndev, - struct sk_buff *skb) + const struct sk_buff *skb) { __u8 status = skb->data[0]; @@ -179,9 +182,10 @@ static void nci_rf_disc_map_rsp_packet(struct nci_dev *ndev, nci_req_complete(ndev, status); } -static void nci_rf_disc_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb) +static void nci_rf_disc_rsp_packet(struct nci_dev *ndev, + const struct sk_buff *skb) { - struct nci_conn_info *conn_info; + struct nci_conn_info *conn_info; __u8 status = skb->data[0]; pr_debug("status 0x%x\n", status); @@ -210,7 +214,7 @@ exit: } static void nci_rf_disc_select_rsp_packet(struct nci_dev *ndev, - struct sk_buff *skb) + const struct sk_buff *skb) { __u8 status = skb->data[0]; @@ -222,7 +226,7 @@ static void nci_rf_disc_select_rsp_packet(struct nci_dev *ndev, } static void nci_rf_deactivate_rsp_packet(struct nci_dev *ndev, - struct sk_buff *skb) + const struct sk_buff *skb) { __u8 status = skb->data[0]; @@ -238,9 +242,9 @@ static void nci_rf_deactivate_rsp_packet(struct nci_dev *ndev, } static void nci_nfcee_discover_rsp_packet(struct nci_dev *ndev, - struct sk_buff *skb) + const struct sk_buff *skb) { - struct nci_nfcee_discover_rsp *discover_rsp; + const struct nci_nfcee_discover_rsp *discover_rsp; if (skb->len != 2) { nci_req_complete(ndev, NCI_STATUS_NFCEE_PROTOCOL_ERROR); @@ -255,7 +259,7 @@ static void nci_nfcee_discover_rsp_packet(struct nci_dev *ndev, } static void nci_nfcee_mode_set_rsp_packet(struct nci_dev *ndev, - struct sk_buff *skb) + const struct sk_buff *skb) { __u8 status = skb->data[0]; @@ -264,11 +268,11 @@ static void nci_nfcee_mode_set_rsp_packet(struct nci_dev *ndev, } static void nci_core_conn_create_rsp_packet(struct nci_dev *ndev, - struct sk_buff *skb) + const struct sk_buff *skb) { __u8 status = skb->data[0]; struct nci_conn_info *conn_info = NULL; - struct nci_core_conn_create_rsp *rsp; + const struct nci_core_conn_create_rsp *rsp; pr_debug("status 0x%x\n", status); @@ -319,7 +323,7 @@ exit: } static void nci_core_conn_close_rsp_packet(struct nci_dev *ndev, - struct sk_buff *skb) + const struct sk_buff *skb) { struct nci_conn_info *conn_info; __u8 status = skb->data[0]; diff --git a/net/nfc/nci/spi.c b/net/nfc/nci/spi.c index 7d8e10e27c20..0935527d1d12 100644 --- a/net/nfc/nci/spi.c +++ b/net/nfc/nci/spi.c @@ -27,7 +27,7 @@ #define CRC_INIT 0xFFFF -static int __nci_spi_send(struct nci_spi *nspi, struct sk_buff *skb, +static int __nci_spi_send(struct nci_spi *nspi, const struct sk_buff *skb, int cs_change) { struct spi_message m; diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 722f7ef891e1..49089c50872e 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -530,7 +530,7 @@ free_msg: int nfc_genl_se_connectivity(struct nfc_dev *dev, u8 se_idx) { - struct nfc_se *se; + const struct nfc_se *se; struct sk_buff *msg; void *hdr; @@ -1531,7 +1531,7 @@ static int nfc_genl_vendor_cmd(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; - struct nfc_vendor_cmd *cmd; + const struct nfc_vendor_cmd *cmd; u32 dev_idx, vid, subcmd; u8 *data; size_t data_len; diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h index 889fefd64e56..de2ec66d7e83 100644 --- a/net/nfc/nfc.h +++ b/net/nfc/nfc.h @@ -48,7 +48,7 @@ void nfc_llcp_mac_is_up(struct nfc_dev *dev, u32 target_idx, u8 comm_mode, u8 rf_mode); int nfc_llcp_register_device(struct nfc_dev *dev); void nfc_llcp_unregister_device(struct nfc_dev *dev); -int nfc_llcp_set_remote_gb(struct nfc_dev *dev, u8 *gb, u8 gb_len); +int nfc_llcp_set_remote_gb(struct nfc_dev *dev, const u8 *gb, u8 gb_len); u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len); int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb); struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev); diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index 5e39640becdb..0ca214ab5aef 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -140,7 +140,7 @@ static void rawsock_data_exchange_complete(void *context, struct sk_buff *skb, { struct sock *sk = (struct sock *) context; - BUG_ON(in_irq()); + BUG_ON(in_hardirq()); pr_debug("sk=%p err=%d\n", sk, err); diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index ef15d9eb4774..076774034bb9 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -924,7 +924,13 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, break; case OVS_USERSPACE_ATTR_PID: - upcall.portid = nla_get_u32(a); + if (dp->user_features & + OVS_DP_F_DISPATCH_UPCALL_PER_CPU) + upcall.portid = + ovs_dp_get_upcall_portid(dp, + smp_processor_id()); + else + upcall.portid = nla_get_u32(a); break; case OVS_USERSPACE_ATTR_EGRESS_TUN_PORT: { diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index bc164b35e67d..67ad08320886 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -133,6 +133,8 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *, static void ovs_dp_masks_rebalance(struct work_struct *work); +static int ovs_dp_set_upcall_portids(struct datapath *, const struct nlattr *); + /* Must be called with rcu_read_lock or ovs_mutex. */ const char *ovs_dp_name(const struct datapath *dp) { @@ -166,6 +168,7 @@ static void destroy_dp_rcu(struct rcu_head *rcu) free_percpu(dp->stats_percpu); kfree(dp->ports); ovs_meters_exit(dp); + kfree(rcu_dereference_raw(dp->upcall_portids)); kfree(dp); } @@ -239,7 +242,13 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) memset(&upcall, 0, sizeof(upcall)); upcall.cmd = OVS_PACKET_CMD_MISS; - upcall.portid = ovs_vport_find_upcall_portid(p, skb); + + if (dp->user_features & OVS_DP_F_DISPATCH_UPCALL_PER_CPU) + upcall.portid = + ovs_dp_get_upcall_portid(dp, smp_processor_id()); + else + upcall.portid = ovs_vport_find_upcall_portid(p, skb); + upcall.mru = OVS_CB(skb)->mru; error = ovs_dp_upcall(dp, skb, key, &upcall, 0); if (unlikely(error)) @@ -1594,16 +1603,70 @@ static void ovs_dp_reset_user_features(struct sk_buff *skb, DEFINE_STATIC_KEY_FALSE(tc_recirc_sharing_support); +static int ovs_dp_set_upcall_portids(struct datapath *dp, + const struct nlattr *ids) +{ + struct dp_nlsk_pids *old, *dp_nlsk_pids; + + if (!nla_len(ids) || nla_len(ids) % sizeof(u32)) + return -EINVAL; + + old = ovsl_dereference(dp->upcall_portids); + + dp_nlsk_pids = kmalloc(sizeof(*dp_nlsk_pids) + nla_len(ids), + GFP_KERNEL); + if (!dp_nlsk_pids) + return -ENOMEM; + + dp_nlsk_pids->n_pids = nla_len(ids) / sizeof(u32); + nla_memcpy(dp_nlsk_pids->pids, ids, nla_len(ids)); + + rcu_assign_pointer(dp->upcall_portids, dp_nlsk_pids); + + kfree_rcu(old, rcu); + + return 0; +} + +u32 ovs_dp_get_upcall_portid(const struct datapath *dp, uint32_t cpu_id) +{ + struct dp_nlsk_pids *dp_nlsk_pids; + + dp_nlsk_pids = rcu_dereference(dp->upcall_portids); + + if (dp_nlsk_pids) { + if (cpu_id < dp_nlsk_pids->n_pids) { + return dp_nlsk_pids->pids[cpu_id]; + } else if (dp_nlsk_pids->n_pids > 0 && + cpu_id >= dp_nlsk_pids->n_pids) { + /* If the number of netlink PIDs is mismatched with + * the number of CPUs as seen by the kernel, log this + * and send the upcall to an arbitrary socket (0) in + * order to not drop packets + */ + pr_info_ratelimited("cpu_id mismatch with handler threads"); + return dp_nlsk_pids->pids[cpu_id % + dp_nlsk_pids->n_pids]; + } else { + return 0; + } + } else { + return 0; + } +} + static int ovs_dp_change(struct datapath *dp, struct nlattr *a[]) { u32 user_features = 0; + int err; if (a[OVS_DP_ATTR_USER_FEATURES]) { user_features = nla_get_u32(a[OVS_DP_ATTR_USER_FEATURES]); if (user_features & ~(OVS_DP_F_VPORT_PIDS | OVS_DP_F_UNALIGNED | - OVS_DP_F_TC_RECIRC_SHARING)) + OVS_DP_F_TC_RECIRC_SHARING | + OVS_DP_F_DISPATCH_UPCALL_PER_CPU)) return -EOPNOTSUPP; #if !IS_ENABLED(CONFIG_NET_TC_SKB_EXT) @@ -1624,6 +1687,15 @@ static int ovs_dp_change(struct datapath *dp, struct nlattr *a[]) dp->user_features = user_features; + if (dp->user_features & OVS_DP_F_DISPATCH_UPCALL_PER_CPU && + a[OVS_DP_ATTR_PER_CPU_PIDS]) { + /* Upcall Netlink Port IDs have been updated */ + err = ovs_dp_set_upcall_portids(dp, + a[OVS_DP_ATTR_PER_CPU_PIDS]); + if (err) + return err; + } + if (dp->user_features & OVS_DP_F_TC_RECIRC_SHARING) static_branch_enable(&tc_recirc_sharing_support); else diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 38f7d3e66ca6..fcfe6cb46441 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -51,6 +51,21 @@ struct dp_stats_percpu { }; /** + * struct dp_nlsk_pids - array of netlink portids of for a datapath. + * This is used when OVS_DP_F_DISPATCH_UPCALL_PER_CPU + * is enabled and must be protected by rcu. + * @rcu: RCU callback head for deferred destruction. + * @n_pids: Size of @pids array. + * @pids: Array storing the Netlink socket PIDs indexed by CPU ID for packets + * that miss the flow table. + */ +struct dp_nlsk_pids { + struct rcu_head rcu; + u32 n_pids; + u32 pids[]; +}; + +/** * struct datapath - datapath for flow-based packet switching * @rcu: RCU callback head for deferred destruction. * @list_node: Element in global 'dps' list. @@ -61,6 +76,7 @@ struct dp_stats_percpu { * @net: Reference to net namespace. * @max_headroom: the maximum headroom of all vports in this datapath; it will * be used by all the internal vports in this dp. + * @upcall_portids: RCU protected 'struct dp_nlsk_pids'. * * Context: See the comment on locking at the top of datapath.c for additional * locking information. @@ -87,6 +103,8 @@ struct datapath { /* Switch meters. */ struct dp_meter_table meter_tbl; + + struct dp_nlsk_pids __rcu *upcall_portids; }; /** @@ -243,6 +261,8 @@ int ovs_dp_upcall(struct datapath *, struct sk_buff *, const struct sw_flow_key *, const struct dp_upcall_info *, uint32_t cutlen); +u32 ovs_dp_get_upcall_portid(const struct datapath *dp, uint32_t cpu_id); + const char *ovs_dp_name(const struct datapath *dp); struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, struct net *net, u32 portid, u32 seq, u8 cmd); diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index e586424d8b04..9713035b89e3 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -293,14 +293,14 @@ static bool icmp6hdr_ok(struct sk_buff *skb) } /** - * Parse vlan tag from vlan header. + * parse_vlan_tag - Parse vlan tag from vlan header. * @skb: skb containing frame to parse * @key_vh: pointer to parsed vlan tag * @untag_vlan: should the vlan header be removed from the frame * - * Returns ERROR on memory error. - * Returns 0 if it encounters a non-vlan or incomplete packet. - * Returns 1 after successfully parsing vlan tag. + * Return: ERROR on memory error. + * %0 if it encounters a non-vlan or incomplete packet. + * %1 after successfully parsing vlan tag. */ static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh, bool untag_vlan) @@ -532,6 +532,7 @@ static int parse_nsh(struct sk_buff *skb, struct sw_flow_key *key) * L3 header * @key: output flow key * + * Return: %0 if successful, otherwise a negative errno value. */ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) { @@ -748,8 +749,6 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) * * The caller must ensure that skb->len >= ETH_HLEN. * - * Returns 0 if successful, otherwise a negative errno value. - * * Initializes @skb header fields as follows: * * - skb->mac_header: the L2 header. @@ -764,6 +763,8 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) * * - skb->protocol: the type of the data starting at skb->network_header. * Equals to key->eth.type. + * + * Return: %0 if successful, otherwise a negative errno value. */ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) { diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 88deb5b41429..cf2ce5812489 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -507,6 +507,7 @@ void ovs_vport_send(struct vport *vport, struct sk_buff *skb, u8 mac_proto) } skb->dev = vport->dev; + skb->tstamp = 0; vport->ops->send(skb); return; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 57a1971f29e5..543365f58e97 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -250,8 +250,7 @@ static struct net_device *packet_cached_dev_get(struct packet_sock *po) rcu_read_lock(); dev = rcu_dereference(po->cached_dev); - if (likely(dev)) - dev_hold(dev); + dev_hold(dev); rcu_read_unlock(); return dev; @@ -3024,8 +3023,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) out_free: kfree_skb(skb); out_unlock: - if (dev) - dev_put(dev); + dev_put(dev); out: return err; } @@ -3158,8 +3156,7 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, } } - if (dev) - dev_hold(dev); + dev_hold(dev); proto_curr = po->prot_hook.type; dev_curr = po->prot_hook.dev; @@ -3196,8 +3193,7 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, packet_cached_dev_assign(po, dev); } } - if (dev_curr) - dev_put(dev_curr); + dev_put(dev_curr); if (proto == 0 || !need_rehook) goto out_unlock; @@ -4109,8 +4105,7 @@ static int packet_notifier(struct notifier_block *this, if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); WRITE_ONCE(po->ifindex, -1); - if (po->prot_hook.dev) - dev_put(po->prot_hook.dev); + dev_put(po->prot_hook.dev); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index ca6ae4c59433..65218b7ce9f9 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -275,8 +275,7 @@ int pn_skb_send(struct sock *sk, struct sk_buff *skb, drop: kfree_skb(skb); - if (dev) - dev_put(dev); + dev_put(dev); return err; } EXPORT_SYMBOL(pn_skb_send); diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index ac0fae06cc15..cde671d29d5d 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -122,8 +122,7 @@ struct net_device *phonet_device_get(struct net *net) break; dev = NULL; } - if (dev) - dev_hold(dev); + dev_hold(dev); rcu_read_unlock(); return dev; } @@ -233,11 +232,11 @@ static int phonet_device_autoconf(struct net_device *dev) struct if_phonet_req req; int ret; - if (!dev->netdev_ops->ndo_do_ioctl) + if (!dev->netdev_ops->ndo_siocdevprivate) return -EOPNOTSUPP; - ret = dev->netdev_ops->ndo_do_ioctl(dev, (struct ifreq *)&req, - SIOCPNGAUTOCONF); + ret = dev->netdev_ops->ndo_siocdevprivate(dev, (struct ifreq *)&req, + NULL, SIOCPNGAUTOCONF); if (ret < 0) return ret; @@ -411,8 +410,7 @@ struct net_device *phonet_route_output(struct net *net, u8 daddr) daddr >>= 2; rcu_read_lock(); dev = rcu_dereference(routes->table[daddr]); - if (dev) - dev_hold(dev); + dev_hold(dev); rcu_read_unlock(); if (!dev) diff --git a/net/phonet/socket.c b/net/phonet/socket.c index 2599235d592e..71e2caf6ab85 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -379,8 +379,7 @@ static int pn_socket_ioctl(struct socket *sock, unsigned int cmd, saddr = PN_NO_ADDR; release_sock(sk); - if (dev) - dev_put(dev); + dev_put(dev); if (saddr == PN_NO_ADDR) return -EHOSTUNREACH; diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index e6f4a6202f82..ec2322529727 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -493,7 +493,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) goto err; } - if (len != ALIGN(size, 4) + hdrlen) + if (!size || len != ALIGN(size, 4) + hdrlen) goto err; if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA && @@ -506,8 +506,12 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) if (cb->type == QRTR_TYPE_NEW_SERVER) { /* Remote node endpoint can bridge other distant nodes */ - const struct qrtr_ctrl_pkt *pkt = data + hdrlen; + const struct qrtr_ctrl_pkt *pkt; + if (size < sizeof(*pkt)) + goto err; + + pkt = data + hdrlen; qrtr_node_assign(node, le32_to_cpu(pkt->server.node)); } @@ -518,8 +522,10 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) if (!ipc) goto err; - if (sock_queue_rcv_skb(&ipc->sk, skb)) + if (sock_queue_rcv_skb(&ipc->sk, skb)) { + qrtr_port_put(ipc); goto err; + } qrtr_port_put(ipc); } @@ -839,6 +845,8 @@ static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb, ipc = qrtr_port_lookup(to->sq_port); if (!ipc || &ipc->sk == skb->sk) { /* do not send to self */ + if (ipc) + qrtr_port_put(ipc); kfree_skb(skb); return -ENODEV; } @@ -1153,14 +1161,14 @@ static int qrtr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) rc = put_user(len, (int __user *)argp); break; case SIOCGIFADDR: - if (copy_from_user(&ifr, argp, sizeof(ifr))) { + if (get_user_ifreq(&ifr, NULL, argp)) { rc = -EFAULT; break; } sq = (struct sockaddr_qrtr *)&ifr.ifr_addr; *sq = ipc->us; - if (copy_to_user(argp, &ifr, sizeof(ifr))) { + if (put_user_ifreq(&ifr, argp)) { rc = -EFAULT; break; } diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c index 9b6ffff72f2d..28c1b0022178 100644 --- a/net/rds/ib_frmr.c +++ b/net/rds/ib_frmr.c @@ -131,9 +131,9 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr) cpu_relax(); } - ret = ib_map_mr_sg_zbva(frmr->mr, ibmr->sg, ibmr->sg_len, + ret = ib_map_mr_sg_zbva(frmr->mr, ibmr->sg, ibmr->sg_dma_len, &off, PAGE_SIZE); - if (unlikely(ret != ibmr->sg_len)) + if (unlikely(ret != ibmr->sg_dma_len)) return ret < 0 ? ret : -EINVAL; if (cmpxchg(&frmr->fr_state, diff --git a/net/rxrpc/Kconfig b/net/rxrpc/Kconfig index 0885b22e5c0e..accd35c05577 100644 --- a/net/rxrpc/Kconfig +++ b/net/rxrpc/Kconfig @@ -21,6 +21,8 @@ config AF_RXRPC See Documentation/networking/rxrpc.rst. +if AF_RXRPC + config AF_RXRPC_IPV6 bool "IPv6 support for RxRPC" depends on (IPV6 = m && AF_RXRPC = m) || (IPV6 = y && AF_RXRPC) @@ -30,7 +32,6 @@ config AF_RXRPC_IPV6 config AF_RXRPC_INJECT_LOSS bool "Inject packet loss into RxRPC packet stream" - depends on AF_RXRPC help Say Y here to inject packet loss by discarding some received and some transmitted packets. @@ -38,7 +39,6 @@ config AF_RXRPC_INJECT_LOSS config AF_RXRPC_DEBUG bool "RxRPC dynamic debugging" - depends on AF_RXRPC help Say Y here to make runtime controllable debugging messages appear. @@ -47,7 +47,6 @@ config AF_RXRPC_DEBUG config RXKAD bool "RxRPC Kerberos security" - depends on AF_RXRPC select CRYPTO select CRYPTO_MANAGER select CRYPTO_SKCIPHER @@ -58,3 +57,5 @@ config RXKAD through the use of the key retention service. See Documentation/networking/rxrpc.rst. + +endif diff --git a/net/sched/act_api.c b/net/sched/act_api.c index d17a66aab8ee..7dd3a2dc5fa4 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -495,7 +495,7 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, p->tcfa_tm.install = jiffies; p->tcfa_tm.lastuse = jiffies; p->tcfa_tm.firstuse = 0; - p->tcfa_flags = flags; + p->tcfa_flags = flags & TCA_ACT_FLAGS_USER_MASK; if (est) { err = gen_new_estimator(&p->tcfa_bstats, p->cpu_bstats, &p->tcfa_rate_est, @@ -941,7 +941,7 @@ void tcf_idr_insert_many(struct tc_action *actions[]) } } -struct tc_action_ops *tc_action_load_ops(char *name, struct nlattr *nla, +struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, bool police, bool rtnl_held, struct netlink_ext_ack *extack) { @@ -951,7 +951,7 @@ struct tc_action_ops *tc_action_load_ops(char *name, struct nlattr *nla, struct nlattr *kind; int err; - if (name == NULL) { + if (!police) { err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, tcf_action_policy, extack); if (err < 0) @@ -967,7 +967,7 @@ struct tc_action_ops *tc_action_load_ops(char *name, struct nlattr *nla, return ERR_PTR(err); } } else { - if (strlcpy(act_name, name, IFNAMSIZ) >= IFNAMSIZ) { + if (strlcpy(act_name, "police", IFNAMSIZ) >= IFNAMSIZ) { NL_SET_ERR_MSG(extack, "TC action name too long"); return ERR_PTR(-EINVAL); } @@ -1004,12 +1004,11 @@ struct tc_action_ops *tc_action_load_ops(char *name, struct nlattr *nla, struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, - char *name, int ovr, int bind, struct tc_action_ops *a_o, int *init_res, - bool rtnl_held, - struct netlink_ext_ack *extack) + u32 flags, struct netlink_ext_ack *extack) { - struct nla_bitfield32 flags = { 0, 0 }; + bool police = flags & TCA_ACT_FLAGS_POLICE; + struct nla_bitfield32 userflags = { 0, 0 }; u8 hw_stats = TCA_ACT_HW_STATS_ANY; struct nlattr *tb[TCA_ACT_MAX + 1]; struct tc_cookie *cookie = NULL; @@ -1017,7 +1016,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, int err; /* backward compatibility for policer */ - if (name == NULL) { + if (!police) { err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, tcf_action_policy, extack); if (err < 0) @@ -1032,22 +1031,22 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, } hw_stats = tcf_action_hw_stats_get(tb[TCA_ACT_HW_STATS]); if (tb[TCA_ACT_FLAGS]) - flags = nla_get_bitfield32(tb[TCA_ACT_FLAGS]); + userflags = nla_get_bitfield32(tb[TCA_ACT_FLAGS]); - err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, ovr, bind, - rtnl_held, tp, flags.value, extack); + err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, tp, + userflags.value | flags, extack); } else { - err = a_o->init(net, nla, est, &a, ovr, bind, rtnl_held, - tp, flags.value, extack); + err = a_o->init(net, nla, est, &a, tp, userflags.value | flags, + extack); } if (err < 0) goto err_out; *init_res = err; - if (!name && tb[TCA_ACT_COOKIE]) + if (!police && tb[TCA_ACT_COOKIE]) tcf_set_action_cookie(&a->act_cookie, cookie); - if (!name) + if (!police) a->hw_stats = hw_stats; return a; @@ -1063,9 +1062,9 @@ err_out: /* Returns numbers of initialized actions or negative error. */ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, - struct nlattr *est, char *name, int ovr, int bind, - struct tc_action *actions[], int init_res[], size_t *attr_size, - bool rtnl_held, struct netlink_ext_ack *extack) + struct nlattr *est, struct tc_action *actions[], + int init_res[], size_t *attr_size, u32 flags, + struct netlink_ext_ack *extack) { struct tc_action_ops *ops[TCA_ACT_MAX_PRIO] = {}; struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; @@ -1082,7 +1081,9 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { struct tc_action_ops *a_o; - a_o = tc_action_load_ops(name, tb[i], rtnl_held, extack); + a_o = tc_action_load_ops(tb[i], flags & TCA_ACT_FLAGS_POLICE, + !(flags & TCA_ACT_FLAGS_NO_RTNL), + extack); if (IS_ERR(a_o)) { err = PTR_ERR(a_o); goto err_mod; @@ -1091,9 +1092,8 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, } for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { - act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind, - ops[i - 1], &init_res[i - 1], rtnl_held, - extack); + act = tcf_action_init_1(net, tp, tb[i], est, ops[i - 1], + &init_res[i - 1], flags, extack); if (IS_ERR(act)) { err = PTR_ERR(act); goto err; @@ -1113,7 +1113,7 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, goto err_mod; err: - tcf_action_destroy(actions, bind); + tcf_action_destroy(actions, flags & TCA_ACT_FLAGS_BIND); err_mod: for (i = 0; i < TCA_ACT_MAX_PRIO; i++) { if (ops[i]) @@ -1351,8 +1351,6 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, module_put(ops->owner); err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); - if (err > 0) - return 0; if (err < 0) NL_SET_ERR_MSG(extack, "Failed to send TC action flush notification"); @@ -1423,8 +1421,6 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], ret = rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); - if (ret > 0) - return 0; return ret; } @@ -1481,7 +1477,6 @@ tcf_add_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], u32 portid, size_t attr_size, struct netlink_ext_ack *extack) { struct sk_buff *skb; - int err = 0; skb = alloc_skb(attr_size <= NLMSG_GOODSIZE ? NLMSG_GOODSIZE : attr_size, GFP_KERNEL); @@ -1495,15 +1490,12 @@ tcf_add_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], return -EINVAL; } - err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, - n->nlmsg_flags & NLM_F_ECHO); - if (err > 0) - err = 0; - return err; + return rtnetlink_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); } static int tcf_action_add(struct net *net, struct nlattr *nla, - struct nlmsghdr *n, u32 portid, int ovr, + struct nlmsghdr *n, u32 portid, u32 flags, struct netlink_ext_ack *extack) { size_t attr_size = 0; @@ -1512,8 +1504,8 @@ static int tcf_action_add(struct net *net, struct nlattr *nla, int init_res[TCA_ACT_MAX_PRIO] = {}; for (loop = 0; loop < 10; loop++) { - ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, - actions, init_res, &attr_size, true, extack); + ret = tcf_action_init(net, NULL, nla, NULL, actions, init_res, + &attr_size, flags, extack); if (ret != -EAGAIN) break; } @@ -1543,7 +1535,8 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_ROOT_MAX + 1]; u32 portid = NETLINK_CB(skb).portid; - int ret = 0, ovr = 0; + u32 flags = 0; + int ret = 0; if ((n->nlmsg_type != RTM_GETACTION) && !netlink_capable(skb, CAP_NET_ADMIN)) @@ -1569,8 +1562,8 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, * is zero) then just set this */ if (n->nlmsg_flags & NLM_F_REPLACE) - ovr = 1; - ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr, + flags = TCA_ACT_FLAGS_REPLACE; + ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, flags, extack); break; case RTM_DELACTION: diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index e409a0005717..5c36013339e1 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -47,11 +47,11 @@ static int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act, if (at_ingress) { __skb_push(skb, skb->mac_len); bpf_compute_data_pointers(skb); - filter_res = BPF_PROG_RUN(filter, skb); + filter_res = bpf_prog_run(filter, skb); __skb_pull(skb, skb->mac_len); } else { bpf_compute_data_pointers(skb); - filter_res = BPF_PROG_RUN(filter, skb); + filter_res = bpf_prog_run(filter, skb); } if (skb_sk_is_prefetched(skb) && filter_res != TC_ACT_OK) skb_orphan(skb); @@ -275,11 +275,11 @@ static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog, static int tcf_bpf_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **act, - int replace, int bind, bool rtnl_held, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, bpf_net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tcf_bpf_cfg cfg, old; @@ -317,7 +317,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, if (bind) return 0; - if (!replace) { + if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*act, bind); return -EEXIST; } diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index e19885d7fe2c..94e78ac7a748 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -96,12 +96,12 @@ static const struct nla_policy connmark_policy[TCA_CONNMARK_MAX + 1] = { static int tcf_connmark_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, bool rtnl_held, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, connmark_net_id); struct nlattr *tb[TCA_CONNMARK_MAX + 1]; + bool bind = flags & TCA_ACT_FLAGS_BIND; struct tcf_chain *goto_ch = NULL; struct tcf_connmark_info *ci; struct tc_connmark *parm; @@ -144,7 +144,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, ci = to_connmark(*a); if (bind) return 0; - if (!ovr) { + if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 4fa4fcb842ba..a15ec95e69c3 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -41,11 +41,12 @@ static unsigned int csum_net_id; static struct tc_action_ops act_csum_ops; static int tcf_csum_init(struct net *net, struct nlattr *nla, - struct nlattr *est, struct tc_action **a, int ovr, - int bind, bool rtnl_held, struct tcf_proto *tp, + struct nlattr *est, struct tc_action **a, + struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, csum_net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; struct tcf_csum_params *params_new; struct nlattr *tb[TCA_CSUM_MAX + 1]; struct tcf_chain *goto_ch = NULL; @@ -78,7 +79,7 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, } else if (err > 0) { if (bind)/* dont override defaults */ return 0; - if (!ovr) { + if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 1b4b3514c94f..ad9df0cb4b98 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1235,11 +1235,11 @@ static int tcf_ct_fill_params(struct net *net, static int tcf_ct_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int replace, int bind, bool rtnl_held, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, ct_net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; struct tcf_ct_params *params = NULL; struct nlattr *tb[TCA_CT_MAX + 1]; struct tcf_chain *goto_ch = NULL; @@ -1279,7 +1279,7 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, if (bind) return 0; - if (!replace) { + if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index b20c8ce59905..549374a2d008 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -154,11 +154,11 @@ static const struct nla_policy ctinfo_policy[TCA_CTINFO_MAX + 1] = { static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, bool rtnl_held, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, ctinfo_net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; u32 dscpmask = 0, dscpstatemask, index; struct nlattr *tb[TCA_CTINFO_MAX + 1]; struct tcf_ctinfo_params *cp_new; @@ -221,7 +221,7 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, } else if (err > 0) { if (bind) /* don't override defaults */ return 0; - if (!ovr) { + if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 73c3926358a0..d8dce173df37 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -52,11 +52,11 @@ static const struct nla_policy gact_policy[TCA_GACT_MAX + 1] = { static int tcf_gact_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, bool rtnl_held, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, gact_net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_GACT_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tc_gact *parm; @@ -109,7 +109,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, } else if (err > 0) { if (bind)/* dont override defaults */ return 0; - if (!ovr) { + if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c index a78cb7965718..7df72a4197a3 100644 --- a/net/sched/act_gate.c +++ b/net/sched/act_gate.c @@ -295,12 +295,12 @@ static void gate_setup_timer(struct tcf_gate *gact, u64 basetime, static int tcf_gate_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, bool rtnl_held, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, gate_net_id); enum tk_offsets tk_offset = TK_OFFS_TAI; + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_GATE_MAX + 1]; struct tcf_chain *goto_ch = NULL; u64 cycletime = 0, basetime = 0; @@ -364,7 +364,7 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, } ret = ACT_P_CREATED; - } else if (!ovr) { + } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index a2ddea04183a..7064a365a1a9 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -479,11 +479,11 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, static int tcf_ife_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, bool rtnl_held, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, ife_net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_IFE_MAX + 1]; struct nlattr *tb2[IFE_META_MAX + 1]; struct tcf_chain *goto_ch = NULL; @@ -532,7 +532,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, kfree(p); return err; } - err = load_metalist(tb2, rtnl_held); + err = load_metalist(tb2, !(flags & TCA_ACT_FLAGS_NO_RTNL)); if (err) { kfree(p); return err; @@ -560,7 +560,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, return ret; } ret = ACT_P_CREATED; - } else if (!ovr) { + } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); kfree(p); return -EEXIST; @@ -600,7 +600,8 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, } if (tb[TCA_IFE_METALST]) { - err = populate_metalist(ife, tb2, exists, rtnl_held); + err = populate_metalist(ife, tb2, exists, + !(flags & TCA_ACT_FLAGS_NO_RTNL)); if (err) goto metadata_parse_err; } else { diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index ac7297f42355..265b1443e252 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -94,10 +94,11 @@ static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = { static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - const struct tc_action_ops *ops, int ovr, int bind, + const struct tc_action_ops *ops, struct tcf_proto *tp, u32 flags) { struct tc_action_net *tn = net_generic(net, id); + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_IPT_MAX + 1]; struct tcf_ipt *ipt; struct xt_entry_target *td, *t; @@ -154,7 +155,7 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla, if (bind)/* dont override defaults */ return 0; - if (!ovr) { + if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } @@ -201,21 +202,21 @@ err1: } static int tcf_ipt_init(struct net *net, struct nlattr *nla, - struct nlattr *est, struct tc_action **a, int ovr, - int bind, bool rtnl_held, struct tcf_proto *tp, + struct nlattr *est, struct tc_action **a, + struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { - return __tcf_ipt_init(net, ipt_net_id, nla, est, a, &act_ipt_ops, ovr, - bind, tp, flags); + return __tcf_ipt_init(net, ipt_net_id, nla, est, a, &act_ipt_ops, + tp, flags); } static int tcf_xt_init(struct net *net, struct nlattr *nla, - struct nlattr *est, struct tc_action **a, int ovr, - int bind, bool unlocked, struct tcf_proto *tp, + struct nlattr *est, struct tc_action **a, + struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { - return __tcf_ipt_init(net, xt_net_id, nla, est, a, &act_xt_ops, ovr, - bind, tp, flags); + return __tcf_ipt_init(net, xt_net_id, nla, est, a, &act_xt_ops, + tp, flags); } static int tcf_ipt_act(struct sk_buff *skb, const struct tc_action *a, diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 7153c67f641e..d64b0eeccbe4 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -78,8 +78,7 @@ static void tcf_mirred_release(struct tc_action *a) /* last reference to action, no need to lock */ dev = rcu_dereference_protected(m->tcfm_dev, 1); - if (dev) - dev_put(dev); + dev_put(dev); } static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = { @@ -91,11 +90,11 @@ static struct tc_action_ops act_mirred_ops; static int tcf_mirred_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, bool rtnl_held, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, mirred_net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_MIRRED_MAX + 1]; struct tcf_chain *goto_ch = NULL; bool mac_header_xmit = false; @@ -155,7 +154,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, return ret; } ret = ACT_P_CREATED; - } else if (!ovr) { + } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } @@ -180,8 +179,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, mac_header_xmit = dev_is_mac_header_xmit(dev); dev = rcu_replace_pointer(m->tcfm_dev, dev, lockdep_is_held(&m->tcf_lock)); - if (dev) - dev_put(dev); + dev_put(dev); m->tcfm_mac_header_xmit = mac_header_xmit; } goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); @@ -273,6 +271,9 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, goto out; } + /* All mirred/redirected skbs should clear previous ct info */ + nf_reset_ct(skb2); + want_ingress = tcf_mirred_act_wants_ingress(m_eaction); expects_nh = want_ingress || !m_mac_header_xmit; diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index d1486ea496a2..e4529b428cf4 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -152,11 +152,11 @@ static const struct nla_policy mpls_policy[TCA_MPLS_MAX + 1] = { static int tcf_mpls_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, bool rtnl_held, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, mpls_net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_MPLS_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tcf_mpls_params *p; @@ -255,7 +255,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, } ret = ACT_P_CREATED; - } else if (!ovr) { + } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 1ebd2a86d980..7dd6b586ba7f 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -34,11 +34,11 @@ static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = { }; static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, - struct tc_action **a, int ovr, int bind, - bool rtnl_held, struct tcf_proto *tp, + struct tc_action **a, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, nat_net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_NAT_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tc_nat *parm; @@ -70,7 +70,7 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, } else if (err > 0) { if (bind) return 0; - if (!ovr) { + if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index b45304446e13..c6c862c459cc 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -136,11 +136,11 @@ nla_failure: static int tcf_pedit_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, bool rtnl_held, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, pedit_net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_PEDIT_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tc_pedit_key *keys = NULL; @@ -198,7 +198,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, } else if (err > 0) { if (bind) goto out_free; - if (!ovr) { + if (!(flags & TCA_ACT_FLAGS_REPLACE)) { ret = -EEXIST; goto out_release; } diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 0fab8de176d2..832157a840fc 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -48,11 +48,11 @@ static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { static int tcf_police_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, bool rtnl_held, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { int ret = 0, tcfp_result = TC_ACT_OK, err, size; + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_POLICE_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tc_police *parm; @@ -97,7 +97,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, } ret = ACT_P_CREATED; spin_lock_init(&(to_police(*a)->tcfp_lock)); - } else if (!ovr) { + } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 6a0c16e4351d..230501eb9e06 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -34,11 +34,12 @@ static const struct nla_policy sample_policy[TCA_SAMPLE_MAX + 1] = { }; static int tcf_sample_init(struct net *net, struct nlattr *nla, - struct nlattr *est, struct tc_action **a, int ovr, - int bind, bool rtnl_held, struct tcf_proto *tp, + struct nlattr *est, struct tc_action **a, + struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, sample_net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_SAMPLE_MAX + 1]; struct psample_group *psample_group; u32 psample_group_num, rate, index; @@ -75,7 +76,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, return ret; } ret = ACT_P_CREATED; - } else if (!ovr) { + } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 726cc956d06f..cbbe1861d3a2 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -85,11 +85,11 @@ static const struct nla_policy simple_policy[TCA_DEF_MAX + 1] = { static int tcf_simp_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, bool rtnl_held, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, simp_net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_DEF_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tc_defact *parm; @@ -147,7 +147,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, tcf_action_set_ctrlact(*a, parm->action, goto_ch); ret = ACT_P_CREATED; } else { - if (!ovr) { + if (!(flags & TCA_ACT_FLAGS_REPLACE)) { err = -EEXIST; goto release_idr; } diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index e5f3fb8b00e3..605418538347 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -96,11 +96,11 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = { static int tcf_skbedit_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, bool rtnl_held, struct tcf_proto *tp, u32 act_flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbedit_net_id); + bool bind = act_flags & TCA_ACT_FLAGS_BIND; struct tcf_skbedit_params *params_new; struct nlattr *tb[TCA_SKBEDIT_MAX + 1]; struct tcf_chain *goto_ch = NULL; @@ -186,7 +186,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, ret = ACT_P_CREATED; } else { d = to_skbedit(*a); - if (!ovr) { + if (!(act_flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 8d17a543cc9f..ecb9ee666095 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -11,6 +11,7 @@ #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> +#include <net/inet_ecn.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> @@ -21,15 +22,13 @@ static unsigned int skbmod_net_id; static struct tc_action_ops act_skbmod_ops; -#define MAX_EDIT_LEN ETH_HLEN static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_skbmod *d = to_skbmod(a); - int action; + int action, max_edit_len, err; struct tcf_skbmod_params *p; u64 flags; - int err; tcf_lastuse_update(&d->tcf_tm); bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb); @@ -38,19 +37,34 @@ static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a, if (unlikely(action == TC_ACT_SHOT)) goto drop; - if (!skb->dev || skb->dev->type != ARPHRD_ETHER) - return action; + max_edit_len = skb_mac_header_len(skb); + p = rcu_dereference_bh(d->skbmod_p); + flags = p->flags; + + /* tcf_skbmod_init() guarantees "flags" to be one of the following: + * 1. a combination of SKBMOD_F_{DMAC,SMAC,ETYPE} + * 2. SKBMOD_F_SWAPMAC + * 3. SKBMOD_F_ECN + * SKBMOD_F_ECN only works with IP packets; all other flags only work with Ethernet + * packets. + */ + if (flags == SKBMOD_F_ECN) { + switch (skb_protocol(skb, true)) { + case cpu_to_be16(ETH_P_IP): + case cpu_to_be16(ETH_P_IPV6): + max_edit_len += skb_network_header_len(skb); + break; + default: + goto out; + } + } else if (!skb->dev || skb->dev->type != ARPHRD_ETHER) { + goto out; + } - /* XXX: if you are going to edit more fields beyond ethernet header - * (example when you add IP header replacement or vlan swap) - * then MAX_EDIT_LEN needs to change appropriately - */ - err = skb_ensure_writable(skb, MAX_EDIT_LEN); + err = skb_ensure_writable(skb, max_edit_len); if (unlikely(err)) /* best policy is to drop on the floor */ goto drop; - p = rcu_dereference_bh(d->skbmod_p); - flags = p->flags; if (flags & SKBMOD_F_DMAC) ether_addr_copy(eth_hdr(skb)->h_dest, p->eth_dst); if (flags & SKBMOD_F_SMAC) @@ -66,6 +80,10 @@ static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a, ether_addr_copy(eth_hdr(skb)->h_source, (u8 *)tmpaddr); } + if (flags & SKBMOD_F_ECN) + INET_ECN_set_ce(skb); + +out: return action; drop: @@ -82,11 +100,12 @@ static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = { static int tcf_skbmod_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, bool rtnl_held, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbmod_net_id); + bool ovr = flags & TCA_ACT_FLAGS_REPLACE; + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_SKBMOD_MAX + 1]; struct tcf_skbmod_params *p, *p_old; struct tcf_chain *goto_ch = NULL; @@ -129,6 +148,8 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, index = parm->index; if (parm->flags & SKBMOD_F_SWAPMAC) lflags = SKBMOD_F_SWAPMAC; + if (parm->flags & SKBMOD_F_ECN) + lflags = SKBMOD_F_ECN; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 85c0d0d5b9da..d9cd174eecb7 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -355,11 +355,11 @@ static void tunnel_key_release_params(struct tcf_tunnel_key_params *p) static int tunnel_key_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, bool rtnl_held, struct tcf_proto *tp, u32 act_flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); + bool bind = act_flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_TUNNEL_KEY_MAX + 1]; struct tcf_tunnel_key_params *params_new; struct metadata_dst *metadata = NULL; @@ -504,7 +504,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, } ret = ACT_P_CREATED; - } else if (!ovr) { + } else if (!(act_flags & TCA_ACT_FLAGS_REPLACE)) { NL_SET_ERR_MSG(extack, "TC IDR already exists"); ret = -EEXIST; goto release_tun_meta; diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 71f2015c70ca..e4dc5a555bd8 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -114,11 +114,11 @@ static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = { static int tcf_vlan_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - int ovr, int bind, bool rtnl_held, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, vlan_net_id); + bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_VLAN_MAX + 1]; struct tcf_chain *goto_ch = NULL; bool push_prio_exists = false; @@ -223,7 +223,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, } ret = ACT_P_CREATED; - } else if (!ovr) { + } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index e3e79e9bd706..2ef8f5a6205a 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -634,6 +634,7 @@ static void tcf_block_offload_init(struct flow_block_offload *bo, bo->block_shared = shared; bo->extack = extack; bo->sch = sch; + bo->cb_list_head = &flow_block->cb_list; INIT_LIST_HEAD(&bo->cb_list); } @@ -1577,21 +1578,11 @@ reset: #endif } -int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, +int tcf_classify(struct sk_buff *skb, + const struct tcf_block *block, + const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode) { - u32 last_executed_chain = 0; - - return __tcf_classify(skb, tp, tp, res, compat_mode, - &last_executed_chain); -} -EXPORT_SYMBOL(tcf_classify); - -int tcf_classify_ingress(struct sk_buff *skb, - const struct tcf_block *ingress_block, - const struct tcf_proto *tp, - struct tcf_result *res, bool compat_mode) -{ #if !IS_ENABLED(CONFIG_NET_TC_SKB_EXT) u32 last_executed_chain = 0; @@ -1603,20 +1594,22 @@ int tcf_classify_ingress(struct sk_buff *skb, struct tc_skb_ext *ext; int ret; - ext = skb_ext_find(skb, TC_SKB_EXT); + if (block) { + ext = skb_ext_find(skb, TC_SKB_EXT); - if (ext && ext->chain) { - struct tcf_chain *fchain; + if (ext && ext->chain) { + struct tcf_chain *fchain; - fchain = tcf_chain_lookup_rcu(ingress_block, ext->chain); - if (!fchain) - return TC_ACT_SHOT; + fchain = tcf_chain_lookup_rcu(block, ext->chain); + if (!fchain) + return TC_ACT_SHOT; - /* Consume, so cloned/redirect skbs won't inherit ext */ - skb_ext_del(skb, TC_SKB_EXT); + /* Consume, so cloned/redirect skbs won't inherit ext */ + skb_ext_del(skb, TC_SKB_EXT); - tp = rcu_dereference_bh(fchain->filter_chain); - last_executed_chain = fchain->index; + tp = rcu_dereference_bh(fchain->filter_chain); + last_executed_chain = fchain->index; + } } ret = __tcf_classify(skb, tp, orig_tp, res, compat_mode, @@ -1635,7 +1628,7 @@ int tcf_classify_ingress(struct sk_buff *skb, return ret; #endif } -EXPORT_SYMBOL(tcf_classify_ingress); +EXPORT_SYMBOL(tcf_classify); struct tcf_chain_info { struct tcf_proto __rcu **pprev; @@ -1870,13 +1863,10 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, } if (unicast) - err = netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT); + err = rtnl_unicast(skb, net, portid); else err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); - - if (err > 0) - err = 0; return err; } @@ -1909,15 +1899,13 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, } if (unicast) - err = netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT); + err = rtnl_unicast(skb, net, portid); else err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); if (err < 0) NL_SET_ERR_MSG(extack, "Failed to send filter delete notification"); - if (err > 0) - err = 0; return err; } @@ -1962,6 +1950,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, int err; int tp_created; bool rtnl_held = false; + u32 flags; if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) return -EPERM; @@ -1982,6 +1971,7 @@ replay: tp = NULL; cl = 0; block = NULL; + flags = 0; if (prio == 0) { /* If no priority is provided by the user, @@ -2125,9 +2115,12 @@ replay: goto errout; } + if (!(n->nlmsg_flags & NLM_F_CREATE)) + flags |= TCA_ACT_FLAGS_REPLACE; + if (!rtnl_held) + flags |= TCA_ACT_FLAGS_NO_RTNL; err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh, - n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE, - rtnl_held, extack); + flags, extack); if (err == 0) { tfilter_notify(net, skb, n, tp, block, q, parent, fh, RTM_NEWTFILTER, false, rtnl_held); @@ -2711,13 +2704,11 @@ static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, } if (unicast) - err = netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT); + err = rtnl_unicast(skb, net, portid); else err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO); - if (err > 0) - err = 0; return err; } @@ -2741,7 +2732,7 @@ static int tc_chain_notify_delete(const struct tcf_proto_ops *tmplt_ops, } if (unicast) - return netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT); + return rtnl_unicast(skb, net, portid); return rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO); } @@ -3035,8 +3026,8 @@ void tcf_exts_destroy(struct tcf_exts *exts) EXPORT_SYMBOL(tcf_exts_destroy); int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, - struct nlattr *rate_tlv, struct tcf_exts *exts, bool ovr, - bool rtnl_held, struct netlink_ext_ack *extack) + struct nlattr *rate_tlv, struct tcf_exts *exts, + u32 flags, struct netlink_ext_ack *extack) { #ifdef CONFIG_NET_CLS_ACT { @@ -3047,13 +3038,15 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, if (exts->police && tb[exts->police]) { struct tc_action_ops *a_o; - a_o = tc_action_load_ops("police", tb[exts->police], rtnl_held, extack); + a_o = tc_action_load_ops(tb[exts->police], true, + !(flags & TCA_ACT_FLAGS_NO_RTNL), + extack); if (IS_ERR(a_o)) return PTR_ERR(a_o); + flags |= TCA_ACT_FLAGS_POLICE | TCA_ACT_FLAGS_BIND; act = tcf_action_init_1(net, tp, tb[exts->police], - rate_tlv, "police", ovr, - TCA_ACT_BIND, a_o, init_res, - rtnl_held, extack); + rate_tlv, a_o, init_res, flags, + extack); module_put(a_o->owner); if (IS_ERR(act)) return PTR_ERR(act); @@ -3065,10 +3058,10 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, } else if (exts->action && tb[exts->action]) { int err; + flags |= TCA_ACT_FLAGS_BIND; err = tcf_action_init(net, tp, tb[exts->action], - rate_tlv, NULL, ovr, TCA_ACT_BIND, - exts->actions, init_res, - &attr_size, rtnl_held, extack); + rate_tlv, exts->actions, init_res, + &attr_size, flags, extack); if (err < 0) return err; exts->nr_actions = err; @@ -3832,7 +3825,7 @@ struct sk_buff *tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, stru fl = rcu_dereference_bh(qe->filter_chain); - switch (tcf_classify(skb, fl, &cl_res, false)) { + switch (tcf_classify(skb, NULL, fl, &cl_res, false)) { case TC_ACT_SHOT: qdisc_qstats_drop(sch); __qdisc_drop(skb, to_free); diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index f256a7c69093..8158fc9ee1ab 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -145,12 +145,12 @@ static const struct nla_policy basic_policy[TCA_BASIC_MAX + 1] = { static int basic_set_parms(struct net *net, struct tcf_proto *tp, struct basic_filter *f, unsigned long base, struct nlattr **tb, - struct nlattr *est, bool ovr, + struct nlattr *est, u32 flags, struct netlink_ext_ack *extack) { int err; - err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, true, extack); + err = tcf_exts_validate(net, tp, tb, est, &f->exts, flags, extack); if (err < 0) return err; @@ -169,8 +169,8 @@ static int basic_set_parms(struct net *net, struct tcf_proto *tp, static int basic_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, void **arg, bool ovr, - bool rtnl_held, struct netlink_ext_ack *extack) + struct nlattr **tca, void **arg, + u32 flags, struct netlink_ext_ack *extack) { int err; struct basic_head *head = rtnl_dereference(tp->root); @@ -216,7 +216,7 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, goto errout; } - err = basic_set_parms(net, tp, fnew, base, tb, tca[TCA_RATE], ovr, + err = basic_set_parms(net, tp, fnew, base, tb, tca[TCA_RATE], flags, extack); if (err < 0) { if (!fold) diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index fa739efa59f4..df19a847829e 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -96,11 +96,11 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, /* It is safe to push/pull even if skb_shared() */ __skb_push(skb, skb->mac_len); bpf_compute_data_pointers(skb); - filter_res = BPF_PROG_RUN(prog->filter, skb); + filter_res = bpf_prog_run(prog->filter, skb); __skb_pull(skb, skb->mac_len); } else { bpf_compute_data_pointers(skb); - filter_res = BPF_PROG_RUN(prog->filter, skb); + filter_res = bpf_prog_run(prog->filter, skb); } if (prog->exts_integrated) { @@ -404,7 +404,7 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog, static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp, struct cls_bpf_prog *prog, unsigned long base, - struct nlattr **tb, struct nlattr *est, bool ovr, + struct nlattr **tb, struct nlattr *est, u32 flags, struct netlink_ext_ack *extack) { bool is_bpf, is_ebpf, have_exts = false; @@ -416,7 +416,7 @@ static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp, if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) return -EINVAL; - ret = tcf_exts_validate(net, tp, tb, est, &prog->exts, ovr, true, + ret = tcf_exts_validate(net, tp, tb, est, &prog->exts, flags, extack); if (ret < 0) return ret; @@ -455,7 +455,7 @@ static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp, 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, - void **arg, bool ovr, bool rtnl_held, + void **arg, u32 flags, struct netlink_ext_ack *extack) { struct cls_bpf_head *head = rtnl_dereference(tp->root); @@ -500,7 +500,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, goto errout; prog->handle = handle; - ret = cls_bpf_set_parms(net, tp, prog, base, tb, tca[TCA_RATE], ovr, + ret = cls_bpf_set_parms(net, tp, prog, base, tb, tca[TCA_RATE], flags, extack); if (ret < 0) goto errout_idr; diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index fb881144fa01..ed00001b528a 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -76,7 +76,7 @@ static void cls_cgroup_destroy_work(struct work_struct *work) static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr, bool rtnl_held, + void **arg, u32 flags, struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_CGROUP_MAX + 1]; @@ -108,8 +108,8 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, if (err < 0) goto errout; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &new->exts, ovr, - true, extack); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &new->exts, flags, + extack); if (err < 0) goto errout; diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 87398af2715a..972303aa8edd 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -387,7 +387,7 @@ static void flow_destroy_filter_work(struct work_struct *work) static int flow_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr, bool rtnl_held, + void **arg, u32 flags, struct netlink_ext_ack *extack) { struct flow_head *head = rtnl_dereference(tp->root); @@ -442,8 +442,8 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, if (err < 0) goto err2; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &fnew->exts, ovr, - true, extack); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &fnew->exts, flags, + extack); if (err < 0) goto err2; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index d7869a984881..23b21253b3c3 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1915,23 +1915,22 @@ errout_cleanup: static int fl_set_parms(struct net *net, struct tcf_proto *tp, struct cls_fl_filter *f, struct fl_flow_mask *mask, unsigned long base, struct nlattr **tb, - struct nlattr *est, bool ovr, - struct fl_flow_tmplt *tmplt, bool rtnl_held, + struct nlattr *est, + struct fl_flow_tmplt *tmplt, u32 flags, struct netlink_ext_ack *extack) { int err; - err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, rtnl_held, - extack); + err = tcf_exts_validate(net, tp, tb, est, &f->exts, flags, extack); if (err < 0) return err; if (tb[TCA_FLOWER_CLASSID]) { f->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]); - if (!rtnl_held) + if (flags & TCA_ACT_FLAGS_NO_RTNL) rtnl_lock(); tcf_bind_filter(tp, &f->res, base); - if (!rtnl_held) + if (flags & TCA_ACT_FLAGS_NO_RTNL) rtnl_unlock(); } @@ -1975,10 +1974,11 @@ static int fl_ht_insert_unique(struct cls_fl_filter *fnew, static int fl_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr, bool rtnl_held, + void **arg, u32 flags, struct netlink_ext_ack *extack) { struct cls_fl_head *head = fl_head_dereference(tp); + bool rtnl_held = !(flags & TCA_ACT_FLAGS_NO_RTNL); struct cls_fl_filter *fold = *arg; struct cls_fl_filter *fnew; struct fl_flow_mask *mask; @@ -2034,8 +2034,8 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, } } - err = fl_set_parms(net, tp, fnew, mask, base, tb, tca[TCA_RATE], ovr, - tp->chain->tmplt_priv, rtnl_held, extack); + err = fl_set_parms(net, tp, fnew, mask, base, tb, tca[TCA_RATE], + tp->chain->tmplt_priv, flags, extack); if (err) goto errout; diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index ec945294626a..8654b0ce997c 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -198,15 +198,15 @@ static const struct nla_policy fw_policy[TCA_FW_MAX + 1] = { static int fw_set_parms(struct net *net, struct tcf_proto *tp, struct fw_filter *f, struct nlattr **tb, - struct nlattr **tca, unsigned long base, bool ovr, + struct nlattr **tca, unsigned long base, u32 flags, struct netlink_ext_ack *extack) { struct fw_head *head = rtnl_dereference(tp->root); u32 mask; int err; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &f->exts, ovr, - true, extack); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &f->exts, flags, + extack); if (err < 0) return err; @@ -237,8 +237,7 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp, static int fw_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, void **arg, - bool ovr, bool rtnl_held, - struct netlink_ext_ack *extack) + u32 flags, struct netlink_ext_ack *extack) { struct fw_head *head = rtnl_dereference(tp->root); struct fw_filter *f = *arg; @@ -277,7 +276,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, return err; } - err = fw_set_parms(net, tp, fnew, tb, tca, base, ovr, extack); + err = fw_set_parms(net, tp, fnew, tb, tca, base, flags, extack); if (err < 0) { tcf_exts_destroy(&fnew->exts); kfree(fnew); @@ -326,7 +325,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, f->id = handle; f->tp = tp; - err = fw_set_parms(net, tp, f, tb, tca, base, ovr, extack); + err = fw_set_parms(net, tp, f, tb, tca, base, flags, extack); if (err < 0) goto errout; diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index cafb84480bab..24f0046ce0b3 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -163,13 +163,12 @@ static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = { static int mall_set_parms(struct net *net, struct tcf_proto *tp, struct cls_mall_head *head, unsigned long base, struct nlattr **tb, - struct nlattr *est, bool ovr, + struct nlattr *est, u32 flags, struct netlink_ext_ack *extack) { int err; - err = tcf_exts_validate(net, tp, tb, est, &head->exts, ovr, true, - extack); + err = tcf_exts_validate(net, tp, tb, est, &head->exts, flags, extack); if (err < 0) return err; @@ -183,13 +182,13 @@ static int mall_set_parms(struct net *net, struct tcf_proto *tp, static int mall_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr, bool rtnl_held, + void **arg, u32 flags, struct netlink_ext_ack *extack) { struct cls_mall_head *head = rtnl_dereference(tp->root); struct nlattr *tb[TCA_MATCHALL_MAX + 1]; struct cls_mall_head *new; - u32 flags = 0; + u32 userflags = 0; int err; if (!tca[TCA_OPTIONS]) @@ -204,8 +203,8 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, return err; if (tb[TCA_MATCHALL_FLAGS]) { - flags = nla_get_u32(tb[TCA_MATCHALL_FLAGS]); - if (!tc_flags_valid(flags)) + userflags = nla_get_u32(tb[TCA_MATCHALL_FLAGS]); + if (!tc_flags_valid(userflags)) return -EINVAL; } @@ -220,14 +219,14 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, if (!handle) handle = 1; new->handle = handle; - new->flags = flags; + new->flags = userflags; new->pf = alloc_percpu(struct tc_matchall_pcnt); if (!new->pf) { err = -ENOMEM; goto err_alloc_percpu; } - err = mall_set_parms(net, tp, new, base, tb, tca[TCA_RATE], ovr, + err = mall_set_parms(net, tp, new, base, tb, tca[TCA_RATE], flags, extack); if (err) goto err_set_parms; diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 5efa3e7ace15..a35ab8c27866 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -382,7 +382,7 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, struct route4_filter *f, u32 handle, struct route4_head *head, struct nlattr **tb, struct nlattr *est, int new, - bool ovr, struct netlink_ext_ack *extack) + u32 flags, struct netlink_ext_ack *extack) { u32 id = 0, to = 0, nhandle = 0x8000; struct route4_filter *fp; @@ -390,7 +390,7 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, struct route4_bucket *b; int err; - err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, true, extack); + err = tcf_exts_validate(net, tp, tb, est, &f->exts, flags, extack); if (err < 0) return err; @@ -464,8 +464,8 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, static int route4_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, void **arg, bool ovr, - bool rtnl_held, struct netlink_ext_ack *extack) + struct nlattr **tca, void **arg, u32 flags, + struct netlink_ext_ack *extack) { struct route4_head *head = rtnl_dereference(tp->root); struct route4_filter __rcu **fp; @@ -510,7 +510,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, } err = route4_set_parms(net, tp, base, f, handle, head, tb, - tca[TCA_RATE], new, ovr, extack); + tca[TCA_RATE], new, flags, extack); if (err < 0) goto errout; diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 27a4b6dbcf57..5cd9d6b143c4 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -470,9 +470,8 @@ static const struct nla_policy rsvp_policy[TCA_RSVP_MAX + 1] = { static int rsvp_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, - u32 handle, - struct nlattr **tca, - void **arg, bool ovr, bool rtnl_held, + u32 handle, struct nlattr **tca, + void **arg, u32 flags, struct netlink_ext_ack *extack) { struct rsvp_head *data = rtnl_dereference(tp->root); @@ -499,7 +498,7 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb, err = tcf_exts_init(&e, net, TCA_RSVP_ACT, TCA_RSVP_POLICE); if (err < 0) return err; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr, true, + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, flags, extack); if (err < 0) goto errout2; diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index e9a8a2c86bbd..742c7d49a958 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -330,7 +330,7 @@ static int tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, u32 handle, struct tcindex_data *p, struct tcindex_filter_result *r, struct nlattr **tb, - struct nlattr *est, bool ovr, struct netlink_ext_ack *extack) + struct nlattr *est, u32 flags, struct netlink_ext_ack *extack) { struct tcindex_filter_result new_filter_result, *old_r = r; struct tcindex_data *cp = NULL, *oldp; @@ -342,7 +342,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, err = tcf_exts_init(&e, net, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); if (err < 0) return err; - err = tcf_exts_validate(net, tp, tb, est, &e, ovr, true, extack); + err = tcf_exts_validate(net, tp, tb, est, &e, flags, extack); if (err < 0) goto errout; @@ -529,8 +529,8 @@ errout: static int tcindex_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, void **arg, bool ovr, - bool rtnl_held, struct netlink_ext_ack *extack) + struct nlattr **tca, void **arg, u32 flags, + struct netlink_ext_ack *extack) { struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_TCINDEX_MAX + 1]; @@ -551,7 +551,7 @@ tcindex_change(struct net *net, struct sk_buff *in_skb, return err; return tcindex_set_parms(net, tp, base, handle, p, r, tb, - tca[TCA_RATE], ovr, extack); + tca[TCA_RATE], flags, extack); } static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker, diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 6e1abe805448..4272814487f0 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -709,12 +709,12 @@ static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { static int u32_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, struct tc_u_knode *n, struct nlattr **tb, - struct nlattr *est, bool ovr, + struct nlattr *est, u32 flags, struct netlink_ext_ack *extack) { int err; - err = tcf_exts_validate(net, tp, tb, est, &n->exts, ovr, true, extack); + err = tcf_exts_validate(net, tp, tb, est, &n->exts, flags, extack); if (err < 0) return err; @@ -840,7 +840,7 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, static int u32_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, void **arg, bool ovr, bool rtnl_held, + struct nlattr **tca, void **arg, u32 flags, struct netlink_ext_ack *extack) { struct tc_u_common *tp_c = tp->data; @@ -849,7 +849,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, struct tc_u32_sel *s; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_U32_MAX + 1]; - u32 htid, flags = 0; + u32 htid, userflags = 0; size_t sel_size; int err; @@ -868,8 +868,8 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return err; if (tb[TCA_U32_FLAGS]) { - flags = nla_get_u32(tb[TCA_U32_FLAGS]); - if (!tc_flags_valid(flags)) { + userflags = nla_get_u32(tb[TCA_U32_FLAGS]); + if (!tc_flags_valid(userflags)) { NL_SET_ERR_MSG_MOD(extack, "Invalid filter flags"); return -EINVAL; } @@ -884,7 +884,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return -EINVAL; } - if ((n->flags ^ flags) & + if ((n->flags ^ userflags) & ~(TCA_CLS_FLAGS_IN_HW | TCA_CLS_FLAGS_NOT_IN_HW)) { NL_SET_ERR_MSG_MOD(extack, "Key node flags do not match passed flags"); return -EINVAL; @@ -895,7 +895,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return -ENOMEM; err = u32_set_parms(net, tp, base, new, tb, - tca[TCA_RATE], ovr, extack); + tca[TCA_RATE], flags, extack); if (err) { u32_destroy_key(new, false); @@ -955,9 +955,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, ht->handle = handle; ht->prio = tp->prio; idr_init(&ht->handle_idr); - ht->flags = flags; + ht->flags = userflags; - err = u32_replace_hw_hnode(tp, ht, flags, extack); + err = u32_replace_hw_hnode(tp, ht, userflags, extack); if (err) { idr_remove(&tp_c->handle_idr, handle); kfree(ht); @@ -1038,7 +1038,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, RCU_INIT_POINTER(n->ht_up, ht); n->handle = handle; n->fshift = s->hmask ? ffs(ntohl(s->hmask)) - 1 : 0; - n->flags = flags; + n->flags = userflags; err = tcf_exts_init(&n->exts, net, TCA_U32_ACT, TCA_U32_POLICE); if (err < 0) @@ -1060,7 +1060,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, } #endif - err = u32_set_parms(net, tp, base, n, tb, tca[TCA_RATE], ovr, + err = u32_set_parms(net, tp, base, n, tb, tca[TCA_RATE], flags, extack); if (err == 0) { struct tc_u_knode __rcu **ins; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index f87d07736a14..5e90e9b160e3 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1845,7 +1845,6 @@ static int tclass_notify(struct net *net, struct sk_buff *oskb, { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; - int err = 0; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) @@ -1856,11 +1855,8 @@ static int tclass_notify(struct net *net, struct sk_buff *oskb, return -EINVAL; } - err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, - n->nlmsg_flags & NLM_F_ECHO); - if (err > 0) - err = 0; - return err; + return rtnetlink_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); } static int tclass_del_notify(struct net *net, @@ -1894,8 +1890,6 @@ static int tclass_del_notify(struct net *net, err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); - if (err > 0) - err = 0; return err; } diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index d0c9a57398fc..7d8518176b45 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -394,7 +394,7 @@ static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch, list_for_each_entry(flow, &p->flows, list) { fl = rcu_dereference_bh(flow->filter_list); if (fl) { - result = tcf_classify(skb, fl, &res, true); + result = tcf_classify(skb, NULL, fl, &res, true); if (result < 0) continue; flow = (struct atm_flow_data *)res.class; diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 951542843cab..3c2300d14468 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -720,7 +720,7 @@ static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb, skip_hash: if (flow_override) flow_hash = flow_override - 1; - else if (use_skbhash) + else if (use_skbhash && (flow_mode & CAKE_FLOW_FLOWS)) flow_hash = skb->hash; if (host_override) { dsthost_hash = host_override - 1; @@ -1665,7 +1665,7 @@ static u32 cake_classify(struct Qdisc *sch, struct cake_tin_data **t, goto hash; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - result = tcf_classify(skb, filter, &res, false); + result = tcf_classify(skb, NULL, filter, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index b79a7e27bb31..e0da15530f0e 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -228,7 +228,7 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) /* * Step 2+n. Apply classifier. */ - result = tcf_classify(skb, fl, &res, true); + result = tcf_classify(skb, NULL, fl, &res, true); if (!fl || result < 0) goto fallback; @@ -1614,7 +1614,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack); if (err) { kfree(cl); - return err; + goto failure; } if (tca[TCA_RATE]) { diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index fc1e47069593..642cd179b7a7 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -317,7 +317,7 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch, *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; fl = rcu_dereference_bh(q->filter_list); - result = tcf_classify(skb, fl, &res, false); + result = tcf_classify(skb, NULL, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index d320bcfb2da2..4c100d105269 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -242,7 +242,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, else { struct tcf_result res; struct tcf_proto *fl = rcu_dereference_bh(p->filter_list); - int result = tcf_classify(skb, fl, &res, false); + int result = tcf_classify(skb, NULL, fl, &res, false); pr_debug("result %d class 0x%04x\n", result, res.classid); diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index c1e84d1eeaba..1f857ffd1ac2 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -390,7 +390,7 @@ static struct ets_class *ets_classify(struct sk_buff *skb, struct Qdisc *sch, *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; if (TC_H_MAJ(skb->priority) != sch->handle) { fl = rcu_dereference_bh(q->filter_list); - err = tcf_classify(skb, fl, &res, false); + err = tcf_classify(skb, NULL, fl, &res, false); #ifdef CONFIG_NET_CLS_ACT switch (err) { case TC_ACT_STOLEN: @@ -660,6 +660,13 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, sch_tree_lock(sch); q->nbands = nbands; + for (i = nstrict; i < q->nstrict; i++) { + INIT_LIST_HEAD(&q->classes[i].alist); + if (q->classes[i].qdisc->q.qlen) { + list_add_tail(&q->classes[i].alist, &q->active); + q->classes[i].deficit = quanta[i]; + } + } q->nstrict = nstrict; memcpy(q->prio2band, priomap, sizeof(priomap)); diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index bbd5f8753600..bb0cd6d3d2c2 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -91,7 +91,7 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch, return fq_codel_hash(q, skb) + 1; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - result = tcf_classify(skb, filter, &res, false); + result = tcf_classify(skb, NULL, filter, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { @@ -369,6 +369,7 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, { struct fq_codel_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_FQ_CODEL_MAX + 1]; + u32 quantum = 0; int err; if (!opt) @@ -386,6 +387,13 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, q->flows_cnt > 65536) return -EINVAL; } + if (tb[TCA_FQ_CODEL_QUANTUM]) { + quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM])); + if (quantum > FQ_CODEL_QUANTUM_MAX) { + NL_SET_ERR_MSG(extack, "Invalid quantum"); + return -EINVAL; + } + } sch_tree_lock(sch); if (tb[TCA_FQ_CODEL_TARGET]) { @@ -412,8 +420,8 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, if (tb[TCA_FQ_CODEL_ECN]) q->cparams.ecn = !!nla_get_u32(tb[TCA_FQ_CODEL_ECN]); - if (tb[TCA_FQ_CODEL_QUANTUM]) - q->quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM])); + if (quantum) + q->quantum = quantum; if (tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]) q->drop_batch_size = max(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])); diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index cac684952edc..830f3559f727 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -94,7 +94,7 @@ static unsigned int fq_pie_classify(struct sk_buff *skb, struct Qdisc *sch, return fq_pie_hash(q, skb) + 1; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - result = tcf_classify(skb, filter, &res, false); + result = tcf_classify(skb, NULL, filter, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index d9ac60ffe927..a8dd06c74e31 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -913,7 +913,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, /* seqlock has the same scope of busylock, for NOLOCK qdisc */ spin_lock_init(&sch->seqlock); - lockdep_set_class(&sch->busylock, + lockdep_set_class(&sch->seqlock, dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); seqcount_init(&sch->running); diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index bf0034c66e35..b7ac30cca035 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1130,7 +1130,7 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; head = &q->root; tcf = rcu_dereference_bh(q->root.filter_list); - while (tcf && (result = tcf_classify(skb, tcf, &res, false)) >= 0) { + while (tcf && (result = tcf_classify(skb, NULL, tcf, &res, false)) >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 5f7ac27a5264..5067a6e5d4fd 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -125,6 +125,7 @@ struct htb_class { struct htb_class_leaf { int deficit[TC_HTB_MAXDEPTH]; struct Qdisc *q; + struct netdev_queue *offload_queue; } leaf; struct htb_class_inner { struct htb_prio clprio[TC_HTB_NUMPRIO]; @@ -238,7 +239,7 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, } *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - while (tcf && (result = tcf_classify(skb, tcf, &res, false)) >= 0) { + while (tcf && (result = tcf_classify(skb, NULL, tcf, &res, false)) >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: @@ -1411,24 +1412,47 @@ htb_graft_helper(struct netdev_queue *dev_queue, struct Qdisc *new_q) return old_q; } -static void htb_offload_move_qdisc(struct Qdisc *sch, u16 qid_old, u16 qid_new) +static struct netdev_queue *htb_offload_get_queue(struct htb_class *cl) +{ + struct netdev_queue *queue; + + queue = cl->leaf.offload_queue; + if (!(cl->leaf.q->flags & TCQ_F_BUILTIN)) + WARN_ON(cl->leaf.q->dev_queue != queue); + + return queue; +} + +static void htb_offload_move_qdisc(struct Qdisc *sch, struct htb_class *cl_old, + struct htb_class *cl_new, bool destroying) { struct netdev_queue *queue_old, *queue_new; struct net_device *dev = qdisc_dev(sch); - struct Qdisc *qdisc; - queue_old = netdev_get_tx_queue(dev, qid_old); - queue_new = netdev_get_tx_queue(dev, qid_new); + queue_old = htb_offload_get_queue(cl_old); + queue_new = htb_offload_get_queue(cl_new); - if (dev->flags & IFF_UP) - dev_deactivate(dev); - qdisc = dev_graft_qdisc(queue_old, NULL); - qdisc->dev_queue = queue_new; - qdisc = dev_graft_qdisc(queue_new, qdisc); - if (dev->flags & IFF_UP) - dev_activate(dev); + if (!destroying) { + struct Qdisc *qdisc; - WARN_ON(!(qdisc->flags & TCQ_F_BUILTIN)); + if (dev->flags & IFF_UP) + dev_deactivate(dev); + qdisc = dev_graft_qdisc(queue_old, NULL); + WARN_ON(qdisc != cl_old->leaf.q); + } + + if (!(cl_old->leaf.q->flags & TCQ_F_BUILTIN)) + cl_old->leaf.q->dev_queue = queue_new; + cl_old->leaf.offload_queue = queue_new; + + if (!destroying) { + struct Qdisc *qdisc; + + qdisc = dev_graft_qdisc(queue_new, cl_old->leaf.q); + if (dev->flags & IFF_UP) + dev_activate(dev); + WARN_ON(!(qdisc->flags & TCQ_F_BUILTIN)); + } } static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, @@ -1442,10 +1466,8 @@ static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, if (cl->level) return -EINVAL; - if (q->offload) { - dev_queue = new->dev_queue; - WARN_ON(dev_queue != cl->leaf.q->dev_queue); - } + if (q->offload) + dev_queue = htb_offload_get_queue(cl); if (!new) { new = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops, @@ -1514,6 +1536,8 @@ static void htb_parent_to_leaf(struct Qdisc *sch, struct htb_class *cl, parent->ctokens = parent->cbuffer; parent->t_c = ktime_get_ns(); parent->cmode = HTB_CAN_SEND; + if (q->offload) + parent->leaf.offload_queue = cl->leaf.offload_queue; } static void htb_parent_to_leaf_offload(struct Qdisc *sch, @@ -1534,6 +1558,7 @@ static int htb_destroy_class_offload(struct Qdisc *sch, struct htb_class *cl, struct netlink_ext_ack *extack) { struct tc_htb_qopt_offload offload_opt; + struct netdev_queue *dev_queue; struct Qdisc *q = cl->leaf.q; struct Qdisc *old = NULL; int err; @@ -1542,16 +1567,15 @@ static int htb_destroy_class_offload(struct Qdisc *sch, struct htb_class *cl, return -EINVAL; WARN_ON(!q); - if (!destroying) { - /* On destroy of HTB, two cases are possible: - * 1. q is a normal qdisc, but q->dev_queue has noop qdisc. - * 2. q is a noop qdisc (for nodes that were inner), - * q->dev_queue is noop_netdev_queue. + dev_queue = htb_offload_get_queue(cl); + old = htb_graft_helper(dev_queue, NULL); + if (destroying) + /* Before HTB is destroyed, the kernel grafts noop_qdisc to + * all queues. */ - old = htb_graft_helper(q->dev_queue, NULL); - WARN_ON(!old); + WARN_ON(!(old->flags & TCQ_F_BUILTIN)); + else WARN_ON(old != q); - } if (cl->parent) { cl->parent->bstats_bias.bytes += q->bstats.bytes; @@ -1570,18 +1594,17 @@ static int htb_destroy_class_offload(struct Qdisc *sch, struct htb_class *cl, if (!err || destroying) qdisc_put(old); else - htb_graft_helper(q->dev_queue, old); + htb_graft_helper(dev_queue, old); if (last_child) return err; - if (!err && offload_opt.moved_qid != 0) { - if (destroying) - q->dev_queue = netdev_get_tx_queue(qdisc_dev(sch), - offload_opt.qid); - else - htb_offload_move_qdisc(sch, offload_opt.moved_qid, - offload_opt.qid); + if (!err && offload_opt.classid != TC_H_MIN(cl->common.classid)) { + u32 classid = TC_H_MAJ(sch->handle) | + TC_H_MIN(offload_opt.classid); + struct htb_class *moved_cl = htb_find(classid, sch); + + htb_offload_move_qdisc(sch, moved_cl, cl, destroying); } return err; @@ -1704,9 +1727,11 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg, } if (last_child) { - struct netdev_queue *dev_queue; + struct netdev_queue *dev_queue = sch->dev_queue; + + if (q->offload) + dev_queue = htb_offload_get_queue(cl); - dev_queue = q->offload ? cl->leaf.q->dev_queue : sch->dev_queue; new_q = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops, cl->parent->common.classid, NULL); @@ -1878,7 +1903,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, } dev_queue = netdev_get_tx_queue(dev, offload_opt.qid); } else { /* First child. */ - dev_queue = parent->leaf.q->dev_queue; + dev_queue = htb_offload_get_queue(parent); old_q = htb_graft_helper(dev_queue, NULL); WARN_ON(old_q != parent->leaf.q); offload_opt = (struct tc_htb_qopt_offload) { @@ -1935,6 +1960,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, /* leaf (we) needs elementary qdisc */ cl->leaf.q = new_q ? new_q : &noop_qdisc; + if (q->offload) + cl->leaf.offload_queue = dev_queue; cl->parent = parent; diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 5c27b4270b90..e282e7382117 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -36,7 +36,7 @@ multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) int err; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - err = tcf_classify(skb, fl, &res, false); + err = tcf_classify(skb, NULL, fl, &res, false); #ifdef CONFIG_NET_CLS_ACT switch (err) { case TC_ACT_STOLEN: diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 3eabb871a1d5..03fdf31ccb6a 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -39,7 +39,7 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; if (TC_H_MAJ(skb->priority) != sch->handle) { fl = rcu_dereference_bh(q->filter_list); - err = tcf_classify(skb, fl, &res, false); + err = tcf_classify(skb, NULL, fl, &res, false); #ifdef CONFIG_NET_CLS_ACT switch (err) { case TC_ACT_STOLEN: diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index b692a0de1ad5..58a9d42b52b8 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -690,7 +690,7 @@ static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch, *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; fl = rcu_dereference_bh(q->filter_list); - result = tcf_classify(skb, fl, &res, false); + result = tcf_classify(skb, NULL, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index dde829d4b9f8..3d061a13d7ed 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -257,7 +257,7 @@ static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl, struct tcf_result res; int result; - result = tcf_classify(skb, fl, &res, false); + result = tcf_classify(skb, NULL, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 066754a18569..f8e569f79f13 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -178,7 +178,7 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, return sfq_hash(q, skb) + 1; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - result = tcf_classify(skb, fl, &res, false); + result = tcf_classify(skb, NULL, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 07b30d0601d7..1ab2fc933a21 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1513,7 +1513,9 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, taprio_set_picos_per_byte(dev, q); if (mqprio) { - netdev_set_num_tc(dev, mqprio->num_tc); + err = netdev_set_num_tc(dev, mqprio->num_tc); + if (err) + goto free_sched; for (i = 0; i < mqprio->num_tc; i++) netdev_set_tc_queue(dev, i, mqprio->count[i], @@ -1739,8 +1741,6 @@ static void taprio_attach(struct Qdisc *sch) if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; old = dev_graft_qdisc(qdisc->dev_queue, qdisc); - if (ntx < dev->real_num_tx_queues) - qdisc_hash_add(qdisc, false); } else { old = dev_graft_qdisc(qdisc->dev_queue, sch); qdisc_refcount_inc(sch); diff --git a/net/sctp/auth.c b/net/sctp/auth.c index fe74c5f95630..db6b7373d16c 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -857,14 +857,18 @@ int sctp_auth_set_key(struct sctp_endpoint *ep, memcpy(key->data, &auth_key->sca_key[0], auth_key->sca_keylength); cur_key->key = key; - if (replace) { - list_del_init(&shkey->key_list); - sctp_auth_shkey_release(shkey); - if (asoc && asoc->active_key_id == auth_key->sca_keynumber) - sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL); + if (!replace) { + list_add(&cur_key->key_list, sh_keys); + return 0; } + + list_del_init(&shkey->key_list); + sctp_auth_shkey_release(shkey); list_add(&cur_key->key_list, sh_keys); + if (asoc && asoc->active_key_id == auth_key->sca_keynumber) + sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL); + return 0; } diff --git a/net/sctp/input.c b/net/sctp/input.c index eb3c2a34a31c..5ef86fdb1176 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -1203,7 +1203,7 @@ static struct sctp_association *__sctp_rcv_asconf_lookup( if (unlikely(!af)) return NULL; - if (af->from_addr_param(&paddr, param, peer_port, 0)) + if (!af->from_addr_param(&paddr, param, peer_port, 0)) return NULL; return __sctp_lookup_association(net, laddr, &paddr, transportp); diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index e48dd909dee5..470dbdc27d58 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -100,8 +100,9 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, list_for_each_entry_safe(addr, temp, &net->sctp.local_addr_list, list) { if (addr->a.sa.sa_family == AF_INET6 && - ipv6_addr_equal(&addr->a.v6.sin6_addr, - &ifa->addr)) { + ipv6_addr_equal(&addr->a.v6.sin6_addr, + &ifa->addr) && + addr->a.v6.sin6_scope_id == ifa->idev->dev->ifindex) { sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL); found = 1; addr->valid = 0; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 09a8f23ec709..32df65f68c12 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -1109,12 +1109,12 @@ enum sctp_disposition sctp_sf_send_probe(struct net *net, if (!sctp_transport_pl_enabled(transport)) return SCTP_DISPOSITION_CONSUME; - sctp_transport_pl_send(transport); - - reply = sctp_make_heartbeat(asoc, transport, transport->pl.probe_size); - if (!reply) - return SCTP_DISPOSITION_NOMEM; - sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply)); + if (sctp_transport_pl_send(transport)) { + reply = sctp_make_heartbeat(asoc, transport, transport->pl.probe_size); + if (!reply) + return SCTP_DISPOSITION_NOMEM; + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply)); + } sctp_add_cmd_sf(commands, SCTP_CMD_PROBE_TIMER_UPDATE, SCTP_TRANSPORT(transport)); @@ -1274,8 +1274,7 @@ enum sctp_disposition sctp_sf_backbeat_8_3(struct net *net, !sctp_transport_pl_enabled(link)) return SCTP_DISPOSITION_DISCARD; - sctp_transport_pl_recv(link); - if (link->pl.state == SCTP_PL_COMPLETE) + if (sctp_transport_pl_recv(link)) return SCTP_DISPOSITION_CONSUME; return sctp_sf_send_probe(net, ep, asoc, type, link, commands); diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 397a6244dd97..a3d3ca6dd63d 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -258,16 +258,13 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) sctp_transport_pl_update(transport); } -void sctp_transport_pl_send(struct sctp_transport *t) +bool sctp_transport_pl_send(struct sctp_transport *t) { - pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n", - __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high); - - if (t->pl.probe_count < SCTP_MAX_PROBES) { - t->pl.probe_count++; - return; - } + if (t->pl.probe_count < SCTP_MAX_PROBES) + goto out; + t->pl.last_rtx_chunks = t->asoc->rtx_data_chunks; + t->pl.probe_count = 0; if (t->pl.state == SCTP_PL_BASE) { if (t->pl.probe_size == SCTP_BASE_PLPMTU) { /* BASE_PLPMTU Confirmation Failed */ t->pl.state = SCTP_PL_ERROR; /* Base -> Error */ @@ -299,14 +296,27 @@ void sctp_transport_pl_send(struct sctp_transport *t) sctp_assoc_sync_pmtu(t->asoc); } } - t->pl.probe_count = 1; + +out: + if (t->pl.state == SCTP_PL_COMPLETE && t->pl.raise_count < 30 && + !t->pl.probe_count && t->pl.last_rtx_chunks == t->asoc->rtx_data_chunks) { + t->pl.raise_count++; + return false; + } + + pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n", + __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high); + + t->pl.probe_count++; + return true; } -void sctp_transport_pl_recv(struct sctp_transport *t) +bool sctp_transport_pl_recv(struct sctp_transport *t) { pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n", __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high); + t->pl.last_rtx_chunks = t->asoc->rtx_data_chunks; t->pl.pmtu = t->pl.probe_size; t->pl.probe_count = 0; if (t->pl.state == SCTP_PL_BASE) { @@ -323,7 +333,7 @@ void sctp_transport_pl_recv(struct sctp_transport *t) if (!t->pl.probe_high) { t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_BIG_STEP, SCTP_MAX_PLPMTU); - return; + return false; } t->pl.probe_size += SCTP_PL_MIN_STEP; if (t->pl.probe_size >= t->pl.probe_high) { @@ -335,14 +345,13 @@ void sctp_transport_pl_recv(struct sctp_transport *t) t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); sctp_assoc_sync_pmtu(t->asoc); } - } else if (t->pl.state == SCTP_PL_COMPLETE) { - t->pl.raise_count++; - if (t->pl.raise_count == 30) { - /* Raise probe_size again after 30 * interval in Search Complete */ - t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */ - t->pl.probe_size += SCTP_PL_MIN_STEP; - } + } else if (t->pl.state == SCTP_PL_COMPLETE && t->pl.raise_count == 30) { + /* Raise probe_size again after 30 * interval in Search Complete */ + t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */ + t->pl.probe_size += SCTP_PL_MIN_STEP; } + + return t->pl.state == SCTP_PL_COMPLETE; } static bool sctp_transport_pl_toobig(struct sctp_transport *t, u32 pmtu) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 898389611ae8..c038efc23ce3 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -795,7 +795,7 @@ static int smc_connect_rdma(struct smc_sock *smc, reason_code = SMC_CLC_DECL_NOSRVLINK; goto connect_abort; } - smc->conn.lnk = link; + smc_switch_link_and_count(&smc->conn, link); } /* create send buffer and rmb */ diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index cd0d7c908b2a..af227b65669e 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -917,8 +917,8 @@ static int smc_switch_cursor(struct smc_sock *smc, struct smc_cdc_tx_pend *pend, return rc; } -static void smc_switch_link_and_count(struct smc_connection *conn, - struct smc_link *to_lnk) +void smc_switch_link_and_count(struct smc_connection *conn, + struct smc_link *to_lnk) { atomic_dec(&conn->lnk->conn_cnt); conn->lnk = to_lnk; @@ -1752,21 +1752,30 @@ out: return rc; } -/* convert the RMB size into the compressed notation - minimum 16K. +#define SMCD_DMBE_SIZES 6 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */ +#define SMCR_RMBE_SIZES 5 /* 0 -> 16KB, 1 -> 32KB, .. 5 -> 512KB */ + +/* convert the RMB size into the compressed notation (minimum 16K, see + * SMCD/R_DMBE_SIZES. * In contrast to plain ilog2, this rounds towards the next power of 2, * so the socket application gets at least its desired sndbuf / rcvbuf size. */ -static u8 smc_compress_bufsize(int size) +static u8 smc_compress_bufsize(int size, bool is_smcd, bool is_rmb) { + const unsigned int max_scat = SG_MAX_SINGLE_ALLOC * PAGE_SIZE; u8 compressed; if (size <= SMC_BUF_MIN_SIZE) return 0; - size = (size - 1) >> 14; - compressed = ilog2(size) + 1; - if (compressed >= SMC_RMBE_SIZES) - compressed = SMC_RMBE_SIZES - 1; + size = (size - 1) >> 14; /* convert to 16K multiple */ + compressed = min_t(u8, ilog2(size) + 1, + is_smcd ? SMCD_DMBE_SIZES : SMCR_RMBE_SIZES); + + if (!is_smcd && is_rmb) + /* RMBs are backed by & limited to max size of scatterlists */ + compressed = min_t(u8, compressed, ilog2(max_scat >> 14)); + return compressed; } @@ -1982,17 +1991,12 @@ out: return rc; } -#define SMCD_DMBE_SIZES 6 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */ - static struct smc_buf_desc *smcd_new_buf_create(struct smc_link_group *lgr, bool is_dmb, int bufsize) { struct smc_buf_desc *buf_desc; int rc; - if (smc_compress_bufsize(bufsize) > SMCD_DMBE_SIZES) - return ERR_PTR(-EAGAIN); - /* try to alloc a new DMB */ buf_desc = kzalloc(sizeof(*buf_desc), GFP_KERNEL); if (!buf_desc) @@ -2041,9 +2045,8 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) /* use socket send buffer size (w/o overhead) as start value */ sk_buf_size = smc->sk.sk_sndbuf / 2; - for (bufsize_short = smc_compress_bufsize(sk_buf_size); + for (bufsize_short = smc_compress_bufsize(sk_buf_size, is_smcd, is_rmb); bufsize_short >= 0; bufsize_short--) { - if (is_rmb) { lock = &lgr->rmbs_lock; buf_list = &lgr->rmbs[bufsize_short]; @@ -2052,8 +2055,6 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) buf_list = &lgr->sndbufs[bufsize_short]; } bufsize = smc_uncompress_bufsize(bufsize_short); - if ((1 << get_order(bufsize)) > SG_MAX_SINGLE_ALLOC) - continue; /* check for reusable slot in the link group */ buf_desc = smc_buf_get_slot(bufsize_short, lock, buf_list); diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 6d6fd1397c87..c043ecdca5c4 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -97,6 +97,7 @@ struct smc_link { unsigned long *wr_tx_mask; /* bit mask of used indexes */ u32 wr_tx_cnt; /* number of WR send buffers */ wait_queue_head_t wr_tx_wait; /* wait for free WR send buf */ + atomic_t wr_tx_refcnt; /* tx refs to link */ struct smc_wr_buf *wr_rx_bufs; /* WR recv payload buffers */ struct ib_recv_wr *wr_rx_ibs; /* WR recv meta data */ @@ -109,6 +110,7 @@ struct smc_link { struct ib_reg_wr wr_reg; /* WR register memory region */ wait_queue_head_t wr_reg_wait; /* wait for wr_reg result */ + atomic_t wr_reg_refcnt; /* reg refs to link */ enum smc_wr_reg_state wr_reg_state; /* state of wr_reg request */ u8 gid[SMC_GID_SIZE];/* gid matching used vlan id*/ @@ -444,6 +446,8 @@ void smc_core_exit(void); int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, u8 link_idx, struct smc_init_info *ini); void smcr_link_clear(struct smc_link *lnk, bool log); +void smc_switch_link_and_count(struct smc_connection *conn, + struct smc_link *to_lnk); int smcr_buf_map_lgr(struct smc_link *lnk); int smcr_buf_reg_lgr(struct smc_link *lnk); void smcr_lgr_set_type(struct smc_link_group *lgr, enum smc_lgr_type new_type); diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 7d7ba0320d5a..a8845343d183 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -753,8 +753,7 @@ void smc_ib_ndev_change(struct net_device *ndev, unsigned long event) if (!libdev->ops.get_netdev) continue; lndev = libdev->ops.get_netdev(libdev, i + 1); - if (lndev) - dev_put(lndev); + dev_put(lndev); if (lndev != ndev) continue; if (event == NETDEV_REGISTER) diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 273eaf1bfe49..2e7560eba981 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -888,6 +888,7 @@ int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry) if (!rc) goto out; out_clear_lnk: + lnk_new->state = SMC_LNK_INACTIVE; smcr_link_clear(lnk_new, false); out_reject: smc_llc_cli_add_link_reject(qentry); @@ -1184,6 +1185,7 @@ int smc_llc_srv_add_link(struct smc_link *link) goto out_err; return 0; out_err: + link_new->state = SMC_LNK_INACTIVE; smcr_link_clear(link_new, false); return rc; } @@ -1286,10 +1288,8 @@ static void smc_llc_process_cli_delete_link(struct smc_link_group *lgr) del_llc->reason = 0; smc_llc_send_message(lnk, &qentry->msg); /* response */ - if (smc_link_downing(&lnk_del->state)) { - if (smc_switch_conns(lgr, lnk_del, false)) - smc_wr_tx_wait_no_pending_sends(lnk_del); - } + if (smc_link_downing(&lnk_del->state)) + smc_switch_conns(lgr, lnk_del, false); smcr_link_clear(lnk_del, true); active_links = smc_llc_active_link_count(lgr); @@ -1805,8 +1805,6 @@ void smc_llc_link_clear(struct smc_link *link, bool log) link->smcibdev->ibdev->name, link->ibport); complete(&link->llc_testlink_resp); cancel_delayed_work_sync(&link->llc_testlink_wrk); - smc_wr_wakeup_reg_wait(link); - smc_wr_wakeup_tx_wait(link); } /* register a new rtoken at the remote peer (for all links) */ diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 6f6d33edb135..4a964e9190b0 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -394,8 +394,7 @@ static int smc_pnet_add_eth(struct smc_pnettable *pnettable, struct net *net, return 0; out_put: - if (ndev) - dev_put(ndev); + dev_put(ndev); return rc; } diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index 289025cd545a..c79361dfcdfb 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -496,7 +496,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn, /* Wakeup sndbuf consumers from any context (IRQ or process) * since there is more data to transmit; usable snd_wnd as max transmit */ -static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) +static int _smcr_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags; struct smc_link *link = conn->lnk; @@ -550,6 +550,22 @@ out_unlock: return rc; } +static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) +{ + struct smc_link *link = conn->lnk; + int rc = -ENOLINK; + + if (!link) + return rc; + + atomic_inc(&link->wr_tx_refcnt); + if (smc_link_usable(link)) + rc = _smcr_tx_sndbuf_nonempty(conn); + if (atomic_dec_and_test(&link->wr_tx_refcnt)) + wake_up_all(&link->wr_tx_wait); + return rc; +} + static int smcd_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags; diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index cbc73a7e4d59..a419e9af36b9 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -322,9 +322,12 @@ int smc_wr_reg_send(struct smc_link *link, struct ib_mr *mr) if (rc) return rc; + atomic_inc(&link->wr_reg_refcnt); rc = wait_event_interruptible_timeout(link->wr_reg_wait, (link->wr_reg_state != POSTED), SMC_WR_REG_MR_WAIT_TIME); + if (atomic_dec_and_test(&link->wr_reg_refcnt)) + wake_up_all(&link->wr_reg_wait); if (!rc) { /* timeout - terminate link */ smcr_link_down_cond_sched(link); @@ -566,10 +569,15 @@ void smc_wr_free_link(struct smc_link *lnk) return; ibdev = lnk->smcibdev->ibdev; + smc_wr_wakeup_reg_wait(lnk); + smc_wr_wakeup_tx_wait(lnk); + if (smc_wr_tx_wait_no_pending_sends(lnk)) memset(lnk->wr_tx_mask, 0, BITS_TO_LONGS(SMC_WR_BUF_CNT) * sizeof(*lnk->wr_tx_mask)); + wait_event(lnk->wr_reg_wait, (!atomic_read(&lnk->wr_reg_refcnt))); + wait_event(lnk->wr_tx_wait, (!atomic_read(&lnk->wr_tx_refcnt))); if (lnk->wr_rx_dma_addr) { ib_dma_unmap_single(ibdev, lnk->wr_rx_dma_addr, @@ -728,7 +736,9 @@ int smc_wr_create_link(struct smc_link *lnk) memset(lnk->wr_tx_mask, 0, BITS_TO_LONGS(SMC_WR_BUF_CNT) * sizeof(*lnk->wr_tx_mask)); init_waitqueue_head(&lnk->wr_tx_wait); + atomic_set(&lnk->wr_tx_refcnt, 0); init_waitqueue_head(&lnk->wr_reg_wait); + atomic_set(&lnk->wr_reg_refcnt, 0); return rc; dma_unmap: diff --git a/net/socket.c b/net/socket.c index 0b2dad3bdf7f..7f64a6eccf63 100644 --- a/net/socket.c +++ b/net/socket.c @@ -212,6 +212,7 @@ static const char * const pf_family_names[] = { [PF_QIPCRTR] = "PF_QIPCRTR", [PF_SMC] = "PF_SMC", [PF_XDP] = "PF_XDP", + [PF_MCTP] = "PF_MCTP", }; /* @@ -1064,9 +1065,13 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) */ static DEFINE_MUTEX(br_ioctl_mutex); -static int (*br_ioctl_hook) (struct net *, unsigned int cmd, void __user *arg); +static int (*br_ioctl_hook)(struct net *net, struct net_bridge *br, + unsigned int cmd, struct ifreq *ifr, + void __user *uarg); -void brioctl_set(int (*hook) (struct net *, unsigned int, void __user *)) +void brioctl_set(int (*hook)(struct net *net, struct net_bridge *br, + unsigned int cmd, struct ifreq *ifr, + void __user *uarg)) { mutex_lock(&br_ioctl_mutex); br_ioctl_hook = hook; @@ -1074,6 +1079,22 @@ void brioctl_set(int (*hook) (struct net *, unsigned int, void __user *)) } EXPORT_SYMBOL(brioctl_set); +int br_ioctl_call(struct net *net, struct net_bridge *br, unsigned int cmd, + struct ifreq *ifr, void __user *uarg) +{ + int err = -ENOPKG; + + if (!br_ioctl_hook) + request_module("bridge"); + + mutex_lock(&br_ioctl_mutex); + if (br_ioctl_hook) + err = br_ioctl_hook(net, br, cmd, ifr, uarg); + mutex_unlock(&br_ioctl_mutex); + + return err; +} + static DEFINE_MUTEX(vlan_ioctl_mutex); static int (*vlan_ioctl_hook) (struct net *, void __user *arg); @@ -1088,8 +1109,11 @@ EXPORT_SYMBOL(vlan_ioctl_set); static long sock_do_ioctl(struct net *net, struct socket *sock, unsigned int cmd, unsigned long arg) { + struct ifreq ifr; + bool need_copyout; int err; void __user *argp = (void __user *)arg; + void __user *data; err = sock->ops->ioctl(sock, cmd, arg); @@ -1100,25 +1124,16 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, if (err != -ENOIOCTLCMD) return err; - if (cmd == SIOCGIFCONF) { - struct ifconf ifc; - if (copy_from_user(&ifc, argp, sizeof(struct ifconf))) - return -EFAULT; - rtnl_lock(); - err = dev_ifconf(net, &ifc, sizeof(struct ifreq)); - rtnl_unlock(); - if (!err && copy_to_user(argp, &ifc, sizeof(struct ifconf))) - err = -EFAULT; - } else { - struct ifreq ifr; - bool need_copyout; - if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) + if (!is_socket_ioctl_cmd(cmd)) + return -ENOTTY; + + if (get_user_ifreq(&ifr, &data, argp)) + return -EFAULT; + err = dev_ioctl(net, cmd, &ifr, data, &need_copyout); + if (!err && need_copyout) + if (put_user_ifreq(&ifr, argp)) return -EFAULT; - err = dev_ioctl(net, cmd, &ifr, &need_copyout); - if (!err && need_copyout) - if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) - return -EFAULT; - } + return err; } @@ -1140,12 +1155,13 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) net = sock_net(sk); if (unlikely(cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15))) { struct ifreq ifr; + void __user *data; bool need_copyout; - if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) + if (get_user_ifreq(&ifr, &data, argp)) return -EFAULT; - err = dev_ioctl(net, cmd, &ifr, &need_copyout); + err = dev_ioctl(net, cmd, &ifr, data, &need_copyout); if (!err && need_copyout) - if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) + if (put_user_ifreq(&ifr, argp)) return -EFAULT; } else #ifdef CONFIG_WEXT_CORE @@ -1170,14 +1186,7 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) case SIOCSIFBR: case SIOCBRADDBR: case SIOCBRDELBR: - err = -ENOPKG; - if (!br_ioctl_hook) - request_module("bridge"); - - mutex_lock(&br_ioctl_mutex); - if (br_ioctl_hook) - err = br_ioctl_hook(net, cmd, argp); - mutex_unlock(&br_ioctl_mutex); + err = br_ioctl_call(net, NULL, cmd, NULL, argp); break; case SIOCGIFVLAN: case SIOCSIFVLAN: @@ -1217,6 +1226,11 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) cmd == SIOCGSTAMP_NEW, false); break; + + case SIOCGIFCONF: + err = dev_ifconf(net, argp); + break; + default: err = sock_do_ioctl(net, sock, cmd, arg); break; @@ -1722,32 +1736,22 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog) return __sys_listen(fd, backlog); } -int __sys_accept4_file(struct file *file, unsigned file_flags, +struct file *do_accept(struct file *file, unsigned file_flags, struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen, int flags, - unsigned long nofile) + int __user *upeer_addrlen, int flags) { struct socket *sock, *newsock; struct file *newfile; - int err, len, newfd; + int err, len; struct sockaddr_storage address; - if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) - return -EINVAL; - - if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) - flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; - sock = sock_from_file(file); - if (!sock) { - err = -ENOTSOCK; - goto out; - } + if (!sock) + return ERR_PTR(-ENOTSOCK); - err = -ENFILE; newsock = sock_alloc(); if (!newsock) - goto out; + return ERR_PTR(-ENFILE); newsock->type = sock->type; newsock->ops = sock->ops; @@ -1758,18 +1762,9 @@ int __sys_accept4_file(struct file *file, unsigned file_flags, */ __module_get(newsock->ops->owner); - newfd = __get_unused_fd_flags(flags, nofile); - if (unlikely(newfd < 0)) { - err = newfd; - sock_release(newsock); - goto out; - } newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name); - if (IS_ERR(newfile)) { - err = PTR_ERR(newfile); - put_unused_fd(newfd); - goto out; - } + if (IS_ERR(newfile)) + return newfile; err = security_socket_accept(sock, newsock); if (err) @@ -1794,16 +1789,38 @@ int __sys_accept4_file(struct file *file, unsigned file_flags, } /* File flags are not inherited via accept() unlike another OSes. */ - - fd_install(newfd, newfile); - err = newfd; -out: - return err; + return newfile; out_fd: fput(newfile); - put_unused_fd(newfd); - goto out; + return ERR_PTR(err); +} + +int __sys_accept4_file(struct file *file, unsigned file_flags, + struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags, + unsigned long nofile) +{ + struct file *newfile; + int newfd; + + if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return -EINVAL; + if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) + flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; + + newfd = __get_unused_fd_flags(flags, nofile); + if (unlikely(newfd < 0)) + return newfd; + + newfile = do_accept(file, file_flags, upeer_sockaddr, upeer_addrlen, + flags); + if (IS_ERR(newfile)) { + put_unused_fd(newfd); + return PTR_ERR(newfile); + } + fd_install(newfd, newfile); + return newfd; } /* @@ -3126,154 +3143,55 @@ void socket_seq_show(struct seq_file *seq) } #endif /* CONFIG_PROC_FS */ -#ifdef CONFIG_COMPAT -static int compat_dev_ifconf(struct net *net, struct compat_ifconf __user *uifc32) +/* Handle the fact that while struct ifreq has the same *layout* on + * 32/64 for everything but ifreq::ifru_ifmap and ifreq::ifru_data, + * which are handled elsewhere, it still has different *size* due to + * ifreq::ifru_ifmap (which is 16 bytes on 32 bit, 24 bytes on 64-bit, + * resulting in struct ifreq being 32 and 40 bytes respectively). + * As a result, if the struct happens to be at the end of a page and + * the next page isn't readable/writable, we get a fault. To prevent + * that, copy back and forth to the full size. + */ +int get_user_ifreq(struct ifreq *ifr, void __user **ifrdata, void __user *arg) { - struct compat_ifconf ifc32; - struct ifconf ifc; - int err; + if (in_compat_syscall()) { + struct compat_ifreq *ifr32 = (struct compat_ifreq *)ifr; - if (copy_from_user(&ifc32, uifc32, sizeof(struct compat_ifconf))) - return -EFAULT; + memset(ifr, 0, sizeof(*ifr)); + if (copy_from_user(ifr32, arg, sizeof(*ifr32))) + return -EFAULT; - ifc.ifc_len = ifc32.ifc_len; - ifc.ifc_req = compat_ptr(ifc32.ifcbuf); + if (ifrdata) + *ifrdata = compat_ptr(ifr32->ifr_data); - rtnl_lock(); - err = dev_ifconf(net, &ifc, sizeof(struct compat_ifreq)); - rtnl_unlock(); - if (err) - return err; + return 0; + } - ifc32.ifc_len = ifc.ifc_len; - if (copy_to_user(uifc32, &ifc32, sizeof(struct compat_ifconf))) + if (copy_from_user(ifr, arg, sizeof(*ifr))) return -EFAULT; + if (ifrdata) + *ifrdata = ifr->ifr_data; + return 0; } +EXPORT_SYMBOL(get_user_ifreq); -static int ethtool_ioctl(struct net *net, struct compat_ifreq __user *ifr32) +int put_user_ifreq(struct ifreq *ifr, void __user *arg) { - struct compat_ethtool_rxnfc __user *compat_rxnfc; - bool convert_in = false, convert_out = false; - size_t buf_size = 0; - struct ethtool_rxnfc __user *rxnfc = NULL; - struct ifreq ifr; - u32 rule_cnt = 0, actual_rule_cnt; - u32 ethcmd; - u32 data; - int ret; + size_t size = sizeof(*ifr); - if (get_user(data, &ifr32->ifr_ifru.ifru_data)) - return -EFAULT; + if (in_compat_syscall()) + size = sizeof(struct compat_ifreq); - compat_rxnfc = compat_ptr(data); - - if (get_user(ethcmd, &compat_rxnfc->cmd)) + if (copy_to_user(arg, ifr, size)) return -EFAULT; - /* Most ethtool structures are defined without padding. - * Unfortunately struct ethtool_rxnfc is an exception. - */ - switch (ethcmd) { - default: - break; - case ETHTOOL_GRXCLSRLALL: - /* Buffer size is variable */ - if (get_user(rule_cnt, &compat_rxnfc->rule_cnt)) - return -EFAULT; - if (rule_cnt > KMALLOC_MAX_SIZE / sizeof(u32)) - return -ENOMEM; - buf_size += rule_cnt * sizeof(u32); - fallthrough; - case ETHTOOL_GRXRINGS: - case ETHTOOL_GRXCLSRLCNT: - case ETHTOOL_GRXCLSRULE: - case ETHTOOL_SRXCLSRLINS: - convert_out = true; - fallthrough; - case ETHTOOL_SRXCLSRLDEL: - buf_size += sizeof(struct ethtool_rxnfc); - convert_in = true; - rxnfc = compat_alloc_user_space(buf_size); - break; - } - - if (copy_from_user(&ifr.ifr_name, &ifr32->ifr_name, IFNAMSIZ)) - return -EFAULT; - - ifr.ifr_data = convert_in ? rxnfc : (void __user *)compat_rxnfc; - - if (convert_in) { - /* We expect there to be holes between fs.m_ext and - * fs.ring_cookie and at the end of fs, but nowhere else. - */ - BUILD_BUG_ON(offsetof(struct compat_ethtool_rxnfc, fs.m_ext) + - sizeof(compat_rxnfc->fs.m_ext) != - offsetof(struct ethtool_rxnfc, fs.m_ext) + - sizeof(rxnfc->fs.m_ext)); - BUILD_BUG_ON( - offsetof(struct compat_ethtool_rxnfc, fs.location) - - offsetof(struct compat_ethtool_rxnfc, fs.ring_cookie) != - offsetof(struct ethtool_rxnfc, fs.location) - - offsetof(struct ethtool_rxnfc, fs.ring_cookie)); - - if (copy_in_user(rxnfc, compat_rxnfc, - (void __user *)(&rxnfc->fs.m_ext + 1) - - (void __user *)rxnfc) || - copy_in_user(&rxnfc->fs.ring_cookie, - &compat_rxnfc->fs.ring_cookie, - (void __user *)(&rxnfc->fs.location + 1) - - (void __user *)&rxnfc->fs.ring_cookie)) - return -EFAULT; - if (ethcmd == ETHTOOL_GRXCLSRLALL) { - if (put_user(rule_cnt, &rxnfc->rule_cnt)) - return -EFAULT; - } else if (copy_in_user(&rxnfc->rule_cnt, - &compat_rxnfc->rule_cnt, - sizeof(rxnfc->rule_cnt))) - return -EFAULT; - } - - ret = dev_ioctl(net, SIOCETHTOOL, &ifr, NULL); - if (ret) - return ret; - - if (convert_out) { - if (copy_in_user(compat_rxnfc, rxnfc, - (const void __user *)(&rxnfc->fs.m_ext + 1) - - (const void __user *)rxnfc) || - copy_in_user(&compat_rxnfc->fs.ring_cookie, - &rxnfc->fs.ring_cookie, - (const void __user *)(&rxnfc->fs.location + 1) - - (const void __user *)&rxnfc->fs.ring_cookie) || - copy_in_user(&compat_rxnfc->rule_cnt, &rxnfc->rule_cnt, - sizeof(rxnfc->rule_cnt))) - return -EFAULT; - - if (ethcmd == ETHTOOL_GRXCLSRLALL) { - /* As an optimisation, we only copy the actual - * number of rules that the underlying - * function returned. Since Mallory might - * change the rule count in user memory, we - * check that it is less than the rule count - * originally given (as the user buffer size), - * which has been range-checked. - */ - if (get_user(actual_rule_cnt, &rxnfc->rule_cnt)) - return -EFAULT; - if (actual_rule_cnt < rule_cnt) - rule_cnt = actual_rule_cnt; - if (copy_in_user(&compat_rxnfc->rule_locs[0], - &rxnfc->rule_locs[0], - rule_cnt * sizeof(u32))) - return -EFAULT; - } - } - return 0; } +EXPORT_SYMBOL(put_user_ifreq); +#ifdef CONFIG_COMPAT static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32) { compat_uptr_t uptr32; @@ -3281,7 +3199,7 @@ static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32 void __user *saved; int err; - if (copy_from_user(&ifr, uifr32, sizeof(struct compat_ifreq))) + if (get_user_ifreq(&ifr, NULL, uifr32)) return -EFAULT; if (get_user(uptr32, &uifr32->ifr_settings.ifs_ifsu)) @@ -3290,10 +3208,10 @@ static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32 saved = ifr.ifr_settings.ifs_ifsu.raw_hdlc; ifr.ifr_settings.ifs_ifsu.raw_hdlc = compat_ptr(uptr32); - err = dev_ioctl(net, SIOCWANDEV, &ifr, NULL); + err = dev_ioctl(net, SIOCWANDEV, &ifr, NULL, NULL); if (!err) { ifr.ifr_settings.ifs_ifsu.raw_hdlc = saved; - if (copy_to_user(uifr32, &ifr, sizeof(struct compat_ifreq))) + if (put_user_ifreq(&ifr, uifr32)) err = -EFAULT; } return err; @@ -3304,97 +3222,15 @@ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd, struct compat_ifreq __user *u_ifreq32) { struct ifreq ifreq; - u32 data32; + void __user *data; - if (copy_from_user(ifreq.ifr_name, u_ifreq32->ifr_name, IFNAMSIZ)) - return -EFAULT; - if (get_user(data32, &u_ifreq32->ifr_data)) + if (!is_socket_ioctl_cmd(cmd)) + return -ENOTTY; + if (get_user_ifreq(&ifreq, &data, u_ifreq32)) return -EFAULT; - ifreq.ifr_data = compat_ptr(data32); + ifreq.ifr_data = data; - return dev_ioctl(net, cmd, &ifreq, NULL); -} - -static int compat_ifreq_ioctl(struct net *net, struct socket *sock, - unsigned int cmd, - struct compat_ifreq __user *uifr32) -{ - struct ifreq __user *uifr; - int err; - - /* Handle the fact that while struct ifreq has the same *layout* on - * 32/64 for everything but ifreq::ifru_ifmap and ifreq::ifru_data, - * which are handled elsewhere, it still has different *size* due to - * ifreq::ifru_ifmap (which is 16 bytes on 32 bit, 24 bytes on 64-bit, - * resulting in struct ifreq being 32 and 40 bytes respectively). - * As a result, if the struct happens to be at the end of a page and - * the next page isn't readable/writable, we get a fault. To prevent - * that, copy back and forth to the full size. - */ - - uifr = compat_alloc_user_space(sizeof(*uifr)); - if (copy_in_user(uifr, uifr32, sizeof(*uifr32))) - return -EFAULT; - - err = sock_do_ioctl(net, sock, cmd, (unsigned long)uifr); - - if (!err) { - switch (cmd) { - case SIOCGIFFLAGS: - case SIOCGIFMETRIC: - case SIOCGIFMTU: - case SIOCGIFMEM: - case SIOCGIFHWADDR: - case SIOCGIFINDEX: - case SIOCGIFADDR: - case SIOCGIFBRDADDR: - case SIOCGIFDSTADDR: - case SIOCGIFNETMASK: - case SIOCGIFPFLAGS: - case SIOCGIFTXQLEN: - case SIOCGMIIPHY: - case SIOCGMIIREG: - case SIOCGIFNAME: - if (copy_in_user(uifr32, uifr, sizeof(*uifr32))) - err = -EFAULT; - break; - } - } - return err; -} - -static int compat_sioc_ifmap(struct net *net, unsigned int cmd, - struct compat_ifreq __user *uifr32) -{ - struct ifreq ifr; - struct compat_ifmap __user *uifmap32; - int err; - - uifmap32 = &uifr32->ifr_ifru.ifru_map; - err = copy_from_user(&ifr, uifr32, sizeof(ifr.ifr_name)); - err |= get_user(ifr.ifr_map.mem_start, &uifmap32->mem_start); - err |= get_user(ifr.ifr_map.mem_end, &uifmap32->mem_end); - err |= get_user(ifr.ifr_map.base_addr, &uifmap32->base_addr); - err |= get_user(ifr.ifr_map.irq, &uifmap32->irq); - err |= get_user(ifr.ifr_map.dma, &uifmap32->dma); - err |= get_user(ifr.ifr_map.port, &uifmap32->port); - if (err) - return -EFAULT; - - err = dev_ioctl(net, cmd, &ifr, NULL); - - if (cmd == SIOCGIFMAP && !err) { - err = copy_to_user(uifr32, &ifr, sizeof(ifr.ifr_name)); - err |= put_user(ifr.ifr_map.mem_start, &uifmap32->mem_start); - err |= put_user(ifr.ifr_map.mem_end, &uifmap32->mem_end); - err |= put_user(ifr.ifr_map.base_addr, &uifmap32->base_addr); - err |= put_user(ifr.ifr_map.irq, &uifmap32->irq); - err |= put_user(ifr.ifr_map.dma, &uifmap32->dma); - err |= put_user(ifr.ifr_map.port, &uifmap32->port); - if (err) - err = -EFAULT; - } - return err; + return dev_ioctl(net, cmd, &ifreq, data, NULL); } /* Since old style bridge ioctl's endup using SIOCDEVPRIVATE @@ -3420,21 +3256,14 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, struct net *net = sock_net(sk); if (cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) - return compat_ifr_data_ioctl(net, cmd, argp); + return sock_ioctl(file, cmd, (unsigned long)argp); switch (cmd) { case SIOCSIFBR: case SIOCGIFBR: return old_bridge_ioctl(argp); - case SIOCGIFCONF: - return compat_dev_ifconf(net, argp); - case SIOCETHTOOL: - return ethtool_ioctl(net, argp); case SIOCWANDEV: return compat_siocwandev(net, argp); - case SIOCGIFMAP: - case SIOCSIFMAP: - return compat_sioc_ifmap(net, cmd, argp); case SIOCGSTAMP_OLD: case SIOCGSTAMPNS_OLD: if (!sock->ops->gettstamp) @@ -3442,6 +3271,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, return sock->ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_OLD, !COMPAT_USE_64BIT_TIME); + case SIOCETHTOOL: case SIOCBONDSLAVEINFOQUERY: case SIOCBONDINFOQUERY: case SIOCSHWTSTAMP: @@ -3459,10 +3289,13 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCGSKNS: case SIOCGSTAMP_NEW: case SIOCGSTAMPNS_NEW: + case SIOCGIFCONF: return sock_ioctl(file, cmd, arg); case SIOCGIFFLAGS: case SIOCSIFFLAGS: + case SIOCGIFMAP: + case SIOCSIFMAP: case SIOCGIFMETRIC: case SIOCSIFMETRIC: case SIOCGIFMTU: @@ -3499,8 +3332,6 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCBONDRELEASE: case SIOCBONDSETHWADDR: case SIOCBONDCHANGEACTIVE: - return compat_ifreq_ioctl(net, sock, cmd, argp); - case SIOCSARP: case SIOCGARP: case SIOCDARP: diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index d1c003a25b0f..61c276bddaf2 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -160,7 +160,7 @@ static struct rpc_clnt *get_gssp_clnt(struct sunrpc_net *sn) mutex_lock(&sn->gssp_lock); clnt = sn->gssp_clnt; if (clnt) - atomic_inc(&clnt->cl_count); + refcount_inc(&clnt->cl_count); mutex_unlock(&sn->gssp_lock); return clnt; } diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index a81be45f40d9..9de41e7f2d07 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -707,11 +707,11 @@ svc_safe_putnetobj(struct kvec *resv, struct xdr_netobj *o) /* * Verify the checksum on the header and return SVC_OK on success. * Otherwise, return SVC_DROP (in the case of a bad sequence number) - * or return SVC_DENIED and indicate error in authp. + * or return SVC_DENIED and indicate error in rqstp->rq_auth_stat. */ static int gss_verify_header(struct svc_rqst *rqstp, struct rsc *rsci, - __be32 *rpcstart, struct rpc_gss_wire_cred *gc, __be32 *authp) + __be32 *rpcstart, struct rpc_gss_wire_cred *gc) { struct gss_ctx *ctx_id = rsci->mechctx; struct xdr_buf rpchdr; @@ -725,7 +725,7 @@ gss_verify_header(struct svc_rqst *rqstp, struct rsc *rsci, iov.iov_len = (u8 *)argv->iov_base - (u8 *)rpcstart; xdr_buf_from_iov(&iov, &rpchdr); - *authp = rpc_autherr_badverf; + rqstp->rq_auth_stat = rpc_autherr_badverf; if (argv->iov_len < 4) return SVC_DENIED; flavor = svc_getnl(argv); @@ -737,13 +737,13 @@ gss_verify_header(struct svc_rqst *rqstp, struct rsc *rsci, if (rqstp->rq_deferred) /* skip verification of revisited request */ return SVC_OK; if (gss_verify_mic(ctx_id, &rpchdr, &checksum) != GSS_S_COMPLETE) { - *authp = rpcsec_gsserr_credproblem; + rqstp->rq_auth_stat = rpcsec_gsserr_credproblem; return SVC_DENIED; } if (gc->gc_seq > MAXSEQ) { trace_rpcgss_svc_seqno_large(rqstp, gc->gc_seq); - *authp = rpcsec_gsserr_ctxproblem; + rqstp->rq_auth_stat = rpcsec_gsserr_ctxproblem; return SVC_DENIED; } if (!gss_check_seq_num(rqstp, rsci, gc->gc_seq)) @@ -1038,6 +1038,8 @@ svcauth_gss_set_client(struct svc_rqst *rqstp) struct rpc_gss_wire_cred *gc = &svcdata->clcred; int stat; + rqstp->rq_auth_stat = rpc_autherr_badcred; + /* * A gss export can be specified either by: * export *(sec=krb5,rw) @@ -1053,6 +1055,8 @@ svcauth_gss_set_client(struct svc_rqst *rqstp) stat = svcauth_unix_set_client(rqstp); if (stat == SVC_DROP || stat == SVC_CLOSE) return stat; + + rqstp->rq_auth_stat = rpc_auth_ok; return SVC_OK; } @@ -1142,7 +1146,7 @@ static void gss_free_in_token_pages(struct gssp_in_token *in_token) } static int gss_read_proxy_verf(struct svc_rqst *rqstp, - struct rpc_gss_wire_cred *gc, __be32 *authp, + struct rpc_gss_wire_cred *gc, struct xdr_netobj *in_handle, struct gssp_in_token *in_token) { @@ -1151,7 +1155,7 @@ static int gss_read_proxy_verf(struct svc_rqst *rqstp, int pages, i, res, pgto, pgfrom; size_t inlen, to_offs, from_offs; - res = gss_read_common_verf(gc, argv, authp, in_handle); + res = gss_read_common_verf(gc, argv, &rqstp->rq_auth_stat, in_handle); if (res) return res; @@ -1227,7 +1231,7 @@ gss_write_resv(struct kvec *resv, size_t size_limit, * Otherwise, drop the request pending an answer to the upcall. */ static int svcauth_gss_legacy_init(struct svc_rqst *rqstp, - struct rpc_gss_wire_cred *gc, __be32 *authp) + struct rpc_gss_wire_cred *gc) { struct kvec *argv = &rqstp->rq_arg.head[0]; struct kvec *resv = &rqstp->rq_res.head[0]; @@ -1236,7 +1240,7 @@ static int svcauth_gss_legacy_init(struct svc_rqst *rqstp, struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id); memset(&rsikey, 0, sizeof(rsikey)); - ret = gss_read_verf(gc, argv, authp, + ret = gss_read_verf(gc, argv, &rqstp->rq_auth_stat, &rsikey.in_handle, &rsikey.in_token); if (ret) return ret; @@ -1339,7 +1343,7 @@ out: } static int svcauth_gss_proxy_init(struct svc_rqst *rqstp, - struct rpc_gss_wire_cred *gc, __be32 *authp) + struct rpc_gss_wire_cred *gc) { struct kvec *resv = &rqstp->rq_res.head[0]; struct xdr_netobj cli_handle; @@ -1351,8 +1355,7 @@ static int svcauth_gss_proxy_init(struct svc_rqst *rqstp, struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); memset(&ud, 0, sizeof(ud)); - ret = gss_read_proxy_verf(rqstp, gc, authp, - &ud.in_handle, &ud.in_token); + ret = gss_read_proxy_verf(rqstp, gc, &ud.in_handle, &ud.in_token); if (ret) return ret; @@ -1525,7 +1528,7 @@ static void destroy_use_gss_proxy_proc_entry(struct net *net) {} * response here and return SVC_COMPLETE. */ static int -svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp) +svcauth_gss_accept(struct svc_rqst *rqstp) { struct kvec *argv = &rqstp->rq_arg.head[0]; struct kvec *resv = &rqstp->rq_res.head[0]; @@ -1538,7 +1541,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp) int ret; struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id); - *authp = rpc_autherr_badcred; + rqstp->rq_auth_stat = rpc_autherr_badcred; if (!svcdata) svcdata = kmalloc(sizeof(*svcdata), GFP_KERNEL); if (!svcdata) @@ -1575,22 +1578,22 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp) if ((gc->gc_proc != RPC_GSS_PROC_DATA) && (rqstp->rq_proc != 0)) goto auth_err; - *authp = rpc_autherr_badverf; + rqstp->rq_auth_stat = rpc_autherr_badverf; switch (gc->gc_proc) { case RPC_GSS_PROC_INIT: case RPC_GSS_PROC_CONTINUE_INIT: if (use_gss_proxy(SVC_NET(rqstp))) - return svcauth_gss_proxy_init(rqstp, gc, authp); + return svcauth_gss_proxy_init(rqstp, gc); else - return svcauth_gss_legacy_init(rqstp, gc, authp); + return svcauth_gss_legacy_init(rqstp, gc); case RPC_GSS_PROC_DATA: case RPC_GSS_PROC_DESTROY: /* Look up the context, and check the verifier: */ - *authp = rpcsec_gsserr_credproblem; + rqstp->rq_auth_stat = rpcsec_gsserr_credproblem; rsci = gss_svc_searchbyctx(sn->rsc_cache, &gc->gc_ctx); if (!rsci) goto auth_err; - switch (gss_verify_header(rqstp, rsci, rpcstart, gc, authp)) { + switch (gss_verify_header(rqstp, rsci, rpcstart, gc)) { case SVC_OK: break; case SVC_DENIED: @@ -1600,7 +1603,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp) } break; default: - *authp = rpc_autherr_rejectedcred; + rqstp->rq_auth_stat = rpc_autherr_rejectedcred; goto auth_err; } @@ -1616,13 +1619,13 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp) svc_putnl(resv, RPC_SUCCESS); goto complete; case RPC_GSS_PROC_DATA: - *authp = rpcsec_gsserr_ctxproblem; + rqstp->rq_auth_stat = rpcsec_gsserr_ctxproblem; svcdata->verf_start = resv->iov_base + resv->iov_len; if (gss_write_verf(rqstp, rsci->mechctx, gc->gc_seq)) goto auth_err; rqstp->rq_cred = rsci->cred; get_group_info(rsci->cred.cr_group_info); - *authp = rpc_autherr_badcred; + rqstp->rq_auth_stat = rpc_autherr_badcred; switch (gc->gc_svc) { case RPC_GSS_SVC_NONE: break; @@ -1980,7 +1983,7 @@ gss_svc_init_net(struct net *net) goto out2; return 0; out2: - destroy_use_gss_proxy_proc_entry(net); + rsi_cache_destroy_net(net); out1: rsc_cache_destroy_net(net); return rv; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 8b4de70e8ead..f056ff931444 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -167,7 +167,7 @@ static int rpc_clnt_skip_event(struct rpc_clnt *clnt, unsigned long event) case RPC_PIPEFS_MOUNT: if (clnt->cl_pipedir_objects.pdh_dentry != NULL) return 1; - if (atomic_read(&clnt->cl_count) == 0) + if (refcount_read(&clnt->cl_count) == 0) return 1; break; case RPC_PIPEFS_UMOUNT: @@ -419,7 +419,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, clnt->cl_rtt = &clnt->cl_rtt_default; rpc_init_rtt(&clnt->cl_rtt_default, clnt->cl_timeout->to_initval); - atomic_set(&clnt->cl_count, 1); + refcount_set(&clnt->cl_count, 1); if (nodename == NULL) nodename = utsname()->nodename; @@ -431,7 +431,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, if (err) goto out_no_path; if (parent) - atomic_inc(&parent->cl_count); + refcount_inc(&parent->cl_count); trace_rpc_clnt_new(clnt, xprt, program->name, args->servername); return clnt; @@ -918,18 +918,16 @@ rpc_free_client(struct rpc_clnt *clnt) static struct rpc_clnt * rpc_free_auth(struct rpc_clnt *clnt) { - if (clnt->cl_auth == NULL) - return rpc_free_client(clnt); - /* * Note: RPCSEC_GSS may need to send NULL RPC calls in order to * release remaining GSS contexts. This mechanism ensures * that it can do so safely. */ - atomic_inc(&clnt->cl_count); - rpcauth_release(clnt->cl_auth); - clnt->cl_auth = NULL; - if (atomic_dec_and_test(&clnt->cl_count)) + if (clnt->cl_auth != NULL) { + rpcauth_release(clnt->cl_auth); + clnt->cl_auth = NULL; + } + if (refcount_dec_and_test(&clnt->cl_count)) return rpc_free_client(clnt); return NULL; } @@ -943,7 +941,7 @@ rpc_release_client(struct rpc_clnt *clnt) do { if (list_empty(&clnt->cl_tasks)) wake_up(&destroy_wait); - if (!atomic_dec_and_test(&clnt->cl_count)) + if (refcount_dec_not_one(&clnt->cl_count)) break; clnt = rpc_free_auth(clnt); } while (clnt != NULL); @@ -1082,7 +1080,7 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt) if (clnt != NULL) { rpc_task_set_transport(task, clnt); task->tk_client = clnt; - atomic_inc(&clnt->cl_count); + refcount_inc(&clnt->cl_count); if (clnt->cl_softrtry) task->tk_flags |= RPC_TASK_SOFT; if (clnt->cl_softerr) @@ -2694,17 +2692,18 @@ static const struct rpc_procinfo rpcproc_null = { .p_decode = rpcproc_decode_null, }; -static int rpc_ping(struct rpc_clnt *clnt) +static void +rpc_null_call_prepare(struct rpc_task *task, void *data) { - struct rpc_message msg = { - .rpc_proc = &rpcproc_null, - }; - int err; - err = rpc_call_sync(clnt, &msg, RPC_TASK_SOFT | RPC_TASK_SOFTCONN | - RPC_TASK_NULLCREDS); - return err; + task->tk_flags &= ~RPC_TASK_NO_RETRANS_TIMEOUT; + rpc_call_start(task); } +static const struct rpc_call_ops rpc_null_ops = { + .rpc_call_prepare = rpc_null_call_prepare, + .rpc_call_done = rpc_default_callback, +}; + static struct rpc_task *rpc_call_null_helper(struct rpc_clnt *clnt, struct rpc_xprt *xprt, struct rpc_cred *cred, int flags, @@ -2718,7 +2717,7 @@ struct rpc_task *rpc_call_null_helper(struct rpc_clnt *clnt, .rpc_xprt = xprt, .rpc_message = &msg, .rpc_op_cred = cred, - .callback_ops = (ops != NULL) ? ops : &rpc_default_ops, + .callback_ops = ops ?: &rpc_null_ops, .callback_data = data, .flags = flags | RPC_TASK_SOFT | RPC_TASK_SOFTCONN | RPC_TASK_NULLCREDS, @@ -2733,6 +2732,19 @@ struct rpc_task *rpc_call_null(struct rpc_clnt *clnt, struct rpc_cred *cred, int } EXPORT_SYMBOL_GPL(rpc_call_null); +static int rpc_ping(struct rpc_clnt *clnt) +{ + struct rpc_task *task; + int status; + + task = rpc_call_null_helper(clnt, NULL, NULL, 0, NULL, NULL); + if (IS_ERR(task)) + return PTR_ERR(task); + status = task->tk_status; + rpc_put_task(task); + return status; +} + struct rpc_cb_add_xprt_calldata { struct rpc_xprt_switch *xps; struct rpc_xprt *xprt; @@ -2756,6 +2768,7 @@ static void rpc_cb_add_xprt_release(void *calldata) } static const struct rpc_call_ops rpc_cb_add_xprt_call_ops = { + .rpc_call_prepare = rpc_null_call_prepare, .rpc_call_done = rpc_cb_add_xprt_done, .rpc_release = rpc_cb_add_xprt_release, }; @@ -2774,6 +2787,15 @@ int rpc_clnt_test_and_add_xprt(struct rpc_clnt *clnt, struct rpc_cb_add_xprt_calldata *data; struct rpc_task *task; + if (xps->xps_nunique_destaddr_xprts + 1 > clnt->cl_max_connect) { + rcu_read_lock(); + pr_warn("SUNRPC: reached max allowed number (%d) did not add " + "transport to server: %s\n", clnt->cl_max_connect, + rpc_peeraddr2str(clnt, RPC_DISPLAY_ADDR)); + rcu_read_unlock(); + return -EINVAL; + } + data = kmalloc(sizeof(*data), GFP_NOFS); if (!data) return -ENOMEM; @@ -2786,7 +2808,7 @@ int rpc_clnt_test_and_add_xprt(struct rpc_clnt *clnt, task = rpc_call_null_helper(clnt, xprt, NULL, RPC_TASK_ASYNC, &rpc_cb_add_xprt_call_ops, data); - + data->xps->xps_nunique_destaddr_xprts++; rpc_put_task(task); success: return 1; diff --git a/net/sunrpc/debugfs.c b/net/sunrpc/debugfs.c index 56029e3af6ff..7dc9cc929bfd 100644 --- a/net/sunrpc/debugfs.c +++ b/net/sunrpc/debugfs.c @@ -8,14 +8,14 @@ #include <linux/debugfs.h> #include <linux/sunrpc/sched.h> #include <linux/sunrpc/clnt.h> + #include "netns.h" +#include "fail.h" static struct dentry *topdir; static struct dentry *rpc_clnt_dir; static struct dentry *rpc_xprt_dir; -unsigned int rpc_inject_disconnect; - static int tasks_show(struct seq_file *f, void *v) { @@ -90,7 +90,7 @@ static int tasks_open(struct inode *inode, struct file *filp) struct seq_file *seq = filp->private_data; struct rpc_clnt *clnt = seq->private = inode->i_private; - if (!atomic_inc_not_zero(&clnt->cl_count)) { + if (!refcount_inc_not_zero(&clnt->cl_count)) { seq_release(inode, filp); ret = -EINVAL; } @@ -235,8 +235,6 @@ rpc_xprt_debugfs_register(struct rpc_xprt *xprt) /* make tasks file */ debugfs_create_file("info", S_IFREG | 0400, xprt->debugfs, xprt, &xprt_info_fops); - - atomic_set(&xprt->inject_disconnect, rpc_inject_disconnect); } void @@ -246,56 +244,30 @@ rpc_xprt_debugfs_unregister(struct rpc_xprt *xprt) xprt->debugfs = NULL; } -static int -fault_open(struct inode *inode, struct file *filp) -{ - filp->private_data = kmalloc(128, GFP_KERNEL); - if (!filp->private_data) - return -ENOMEM; - return 0; -} +#if IS_ENABLED(CONFIG_FAIL_SUNRPC) +struct fail_sunrpc_attr fail_sunrpc = { + .attr = FAULT_ATTR_INITIALIZER, +}; +EXPORT_SYMBOL_GPL(fail_sunrpc); -static int -fault_release(struct inode *inode, struct file *filp) +static void fail_sunrpc_init(void) { - kfree(filp->private_data); - return 0; -} + struct dentry *dir; -static ssize_t -fault_disconnect_read(struct file *filp, char __user *user_buf, - size_t len, loff_t *offset) -{ - char *buffer = (char *)filp->private_data; - size_t size; + dir = fault_create_debugfs_attr("fail_sunrpc", NULL, + &fail_sunrpc.attr); - size = sprintf(buffer, "%u\n", rpc_inject_disconnect); - return simple_read_from_buffer(user_buf, len, offset, buffer, size); -} + debugfs_create_bool("ignore-client-disconnect", S_IFREG | 0600, dir, + &fail_sunrpc.ignore_client_disconnect); -static ssize_t -fault_disconnect_write(struct file *filp, const char __user *user_buf, - size_t len, loff_t *offset) + debugfs_create_bool("ignore-server-disconnect", S_IFREG | 0600, dir, + &fail_sunrpc.ignore_server_disconnect); +} +#else +static void fail_sunrpc_init(void) { - char buffer[16]; - - if (len >= sizeof(buffer)) - len = sizeof(buffer) - 1; - if (copy_from_user(buffer, user_buf, len)) - return -EFAULT; - buffer[len] = '\0'; - if (kstrtouint(buffer, 10, &rpc_inject_disconnect)) - return -EINVAL; - return len; } - -static const struct file_operations fault_disconnect_fops = { - .owner = THIS_MODULE, - .open = fault_open, - .read = fault_disconnect_read, - .write = fault_disconnect_write, - .release = fault_release, -}; +#endif void __exit sunrpc_debugfs_exit(void) @@ -309,16 +281,11 @@ sunrpc_debugfs_exit(void) void __init sunrpc_debugfs_init(void) { - struct dentry *rpc_fault_dir; - topdir = debugfs_create_dir("sunrpc", NULL); rpc_clnt_dir = debugfs_create_dir("rpc_clnt", topdir); rpc_xprt_dir = debugfs_create_dir("rpc_xprt", topdir); - rpc_fault_dir = debugfs_create_dir("inject_fault", topdir); - - debugfs_create_file("disconnect", S_IFREG | 0400, rpc_fault_dir, NULL, - &fault_disconnect_fops); + fail_sunrpc_init(); } diff --git a/net/sunrpc/fail.h b/net/sunrpc/fail.h new file mode 100644 index 000000000000..69dc30cc44b8 --- /dev/null +++ b/net/sunrpc/fail.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2021, Oracle. All rights reserved. + */ + +#ifndef _NET_SUNRPC_FAIL_H_ +#define _NET_SUNRPC_FAIL_H_ + +#include <linux/fault-inject.h> + +#if IS_ENABLED(CONFIG_FAULT_INJECTION) + +struct fail_sunrpc_attr { + struct fault_attr attr; + + bool ignore_client_disconnect; + + bool ignore_server_disconnect; +}; + +extern struct fail_sunrpc_attr fail_sunrpc; + +#endif /* CONFIG_FAULT_INJECTION */ + +#endif /* _NET_SUNRPC_FAIL_H_ */ diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 09c000d490a1..ee5336d73fdd 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -423,7 +423,7 @@ rpc_info_open(struct inode *inode, struct file *file) spin_lock(&file->f_path.dentry->d_lock); if (!d_unhashed(file->f_path.dentry)) clnt = RPC_I(inode)->private; - if (clnt != NULL && atomic_inc_not_zero(&clnt->cl_count)) { + if (clnt != NULL && refcount_inc_not_zero(&clnt->cl_count)) { spin_unlock(&file->f_path.dentry->d_lock); m->private = clnt; } else { diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 0de918cb3d90..a3bbe5ce4570 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -31,6 +31,8 @@ #include <trace/events/sunrpc.h> +#include "fail.h" + #define RPCDBG_FACILITY RPCDBG_SVCDSP static void svc_unregister(const struct svc_serv *serv, struct net *net); @@ -838,6 +840,27 @@ svc_set_num_threads_sync(struct svc_serv *serv, struct svc_pool *pool, int nrser } EXPORT_SYMBOL_GPL(svc_set_num_threads_sync); +/** + * svc_rqst_replace_page - Replace one page in rq_pages[] + * @rqstp: svc_rqst with pages to replace + * @page: replacement page + * + * When replacing a page in rq_pages, batch the release of the + * replaced pages to avoid hammering the page allocator. + */ +void svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page) +{ + if (*rqstp->rq_next_page) { + if (!pagevec_space(&rqstp->rq_pvec)) + __pagevec_release(&rqstp->rq_pvec); + pagevec_add(&rqstp->rq_pvec, *rqstp->rq_next_page); + } + + get_page(page); + *(rqstp->rq_next_page++) = page; +} +EXPORT_SYMBOL_GPL(svc_rqst_replace_page); + /* * Called from a server thread as it's exiting. Caller must hold the "service * mutex" for the service. @@ -1163,22 +1186,6 @@ void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) static __printf(2,3) void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) {} #endif -__be32 -svc_return_autherr(struct svc_rqst *rqstp, __be32 auth_err) -{ - set_bit(RQ_AUTHERR, &rqstp->rq_flags); - return auth_err; -} -EXPORT_SYMBOL_GPL(svc_return_autherr); - -static __be32 -svc_get_autherr(struct svc_rqst *rqstp, __be32 *statp) -{ - if (test_and_clear_bit(RQ_AUTHERR, &rqstp->rq_flags)) - return *statp; - return rpc_auth_ok; -} - static int svc_generic_dispatch(struct svc_rqst *rqstp, __be32 *statp) { @@ -1202,7 +1209,7 @@ svc_generic_dispatch(struct svc_rqst *rqstp, __be32 *statp) test_bit(RQ_DROPME, &rqstp->rq_flags)) return 0; - if (test_bit(RQ_AUTHERR, &rqstp->rq_flags)) + if (rqstp->rq_auth_stat != rpc_auth_ok) return 1; if (*statp != rpc_success) @@ -1283,7 +1290,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) struct svc_process_info process; __be32 *statp; u32 prog, vers; - __be32 auth_stat, rpc_stat; + __be32 rpc_stat; int auth_res; __be32 *reply_statp; @@ -1326,14 +1333,12 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) * We do this before anything else in order to get a decent * auth verifier. */ - auth_res = svc_authenticate(rqstp, &auth_stat); + auth_res = svc_authenticate(rqstp); /* Also give the program a chance to reject this call: */ - if (auth_res == SVC_OK && progp) { - auth_stat = rpc_autherr_badcred; + if (auth_res == SVC_OK && progp) auth_res = progp->pg_authenticate(rqstp); - } if (auth_res != SVC_OK) - trace_svc_authenticate(rqstp, auth_res, auth_stat); + trace_svc_authenticate(rqstp, auth_res); switch (auth_res) { case SVC_OK: break; @@ -1392,15 +1397,15 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) goto release_dropit; if (*statp == rpc_garbage_args) goto err_garbage; - auth_stat = svc_get_autherr(rqstp, statp); - if (auth_stat != rpc_auth_ok) - goto err_release_bad_auth; } else { dprintk("svc: calling dispatcher\n"); if (!process.dispatch(rqstp, statp)) goto release_dropit; /* Release reply info */ } + if (rqstp->rq_auth_stat != rpc_auth_ok) + goto err_release_bad_auth; + /* Check RPC status result */ if (*statp != rpc_success) resv->iov_len = ((void*)statp) - resv->iov_base + 4; @@ -1450,13 +1455,14 @@ err_release_bad_auth: if (procp->pc_release) procp->pc_release(rqstp); err_bad_auth: - dprintk("svc: authentication failed (%d)\n", ntohl(auth_stat)); + dprintk("svc: authentication failed (%d)\n", + be32_to_cpu(rqstp->rq_auth_stat)); serv->sv_stats->rpcbadauth++; /* Restore write pointer to location of accept status: */ xdr_ressize_check(rqstp, reply_statp); svc_putnl(resv, 1); /* REJECT */ svc_putnl(resv, 1); /* AUTH_ERROR */ - svc_putnl(resv, ntohl(auth_stat)); /* status */ + svc_putu32(resv, rqstp->rq_auth_stat); /* status */ goto sendit; err_bad_prog: @@ -1503,6 +1509,12 @@ svc_process(struct svc_rqst *rqstp) struct svc_serv *serv = rqstp->rq_server; u32 dir; +#if IS_ENABLED(CONFIG_FAIL_SUNRPC) + if (!fail_sunrpc.ignore_server_disconnect && + should_fail(&fail_sunrpc.attr, 1)) + svc_xprt_deferred_close(rqstp->rq_xprt); +#endif + /* * Setup response xdr_buf. * Initially it has just one page @@ -1630,6 +1642,21 @@ u32 svc_max_payload(const struct svc_rqst *rqstp) EXPORT_SYMBOL_GPL(svc_max_payload); /** + * svc_proc_name - Return RPC procedure name in string form + * @rqstp: svc_rqst to operate on + * + * Return value: + * Pointer to a NUL-terminated string + */ +const char *svc_proc_name(const struct svc_rqst *rqstp) +{ + if (rqstp && rqstp->rq_procinfo) + return rqstp->rq_procinfo->pc_name; + return "unknown"; +} + + +/** * svc_encode_result_payload - mark a range of bytes as a result payload * @rqstp: svc_rqst to operate on * @offset: payload's byte offset in rqstp->rq_res diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index d66a8e44a1ae..e1153cba9cc6 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -539,6 +539,7 @@ static void svc_xprt_release(struct svc_rqst *rqstp) kfree(rqstp->rq_deferred); rqstp->rq_deferred = NULL; + pagevec_release(&rqstp->rq_pvec); svc_free_res_pages(rqstp); rqstp->rq_res.page_len = 0; rqstp->rq_res.page_base = 0; @@ -664,6 +665,8 @@ static int svc_alloc_arg(struct svc_rqst *rqstp) struct xdr_buf *arg = &rqstp->rq_arg; unsigned long pages, filled; + pagevec_init(&rqstp->rq_pvec); + pages = (serv->sv_max_mesg + 2 * PAGE_SIZE) >> PAGE_SHIFT; if (pages > RPCSVC_MAXPAGES) { pr_warn_once("svc: warning: pages=%lu > RPCSVC_MAXPAGES=%lu\n", @@ -835,7 +838,8 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt) rqstp->rq_stime = ktime_get(); rqstp->rq_reserved = serv->sv_max_mesg; atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved); - } + } else + svc_xprt_received(xprt); out: trace_svc_handle_xprt(xprt, len); return len; diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index 998b196b6176..5a8b8e03fdd4 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -59,12 +59,12 @@ svc_put_auth_ops(struct auth_ops *aops) } int -svc_authenticate(struct svc_rqst *rqstp, __be32 *authp) +svc_authenticate(struct svc_rqst *rqstp) { rpc_authflavor_t flavor; struct auth_ops *aops; - *authp = rpc_auth_ok; + rqstp->rq_auth_stat = rpc_auth_ok; flavor = svc_getnl(&rqstp->rq_arg.head[0]); @@ -72,7 +72,7 @@ svc_authenticate(struct svc_rqst *rqstp, __be32 *authp) aops = svc_get_auth_ops(flavor); if (aops == NULL) { - *authp = rpc_autherr_badcred; + rqstp->rq_auth_stat = rpc_autherr_badcred; return SVC_DENIED; } @@ -80,7 +80,7 @@ svc_authenticate(struct svc_rqst *rqstp, __be32 *authp) init_svc_cred(&rqstp->rq_cred); rqstp->rq_authop = aops; - return aops->accept(rqstp, authp); + return aops->accept(rqstp); } EXPORT_SYMBOL_GPL(svc_authenticate); diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 35b7966ac3b3..d7ed7d49115a 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -681,8 +681,9 @@ svcauth_unix_set_client(struct svc_rqst *rqstp) rqstp->rq_client = NULL; if (rqstp->rq_proc == 0) - return SVC_OK; + goto out; + rqstp->rq_auth_stat = rpc_autherr_badcred; ipm = ip_map_cached_get(xprt); if (ipm == NULL) ipm = __ip_map_lookup(sn->ip_map_cache, rqstp->rq_server->sv_program->pg_class, @@ -719,13 +720,16 @@ svcauth_unix_set_client(struct svc_rqst *rqstp) put_group_info(cred->cr_group_info); cred->cr_group_info = gi; } + +out: + rqstp->rq_auth_stat = rpc_auth_ok; return SVC_OK; } EXPORT_SYMBOL_GPL(svcauth_unix_set_client); static int -svcauth_null_accept(struct svc_rqst *rqstp, __be32 *authp) +svcauth_null_accept(struct svc_rqst *rqstp) { struct kvec *argv = &rqstp->rq_arg.head[0]; struct kvec *resv = &rqstp->rq_res.head[0]; @@ -736,12 +740,12 @@ svcauth_null_accept(struct svc_rqst *rqstp, __be32 *authp) if (svc_getu32(argv) != 0) { dprintk("svc: bad null cred\n"); - *authp = rpc_autherr_badcred; + rqstp->rq_auth_stat = rpc_autherr_badcred; return SVC_DENIED; } if (svc_getu32(argv) != htonl(RPC_AUTH_NULL) || svc_getu32(argv) != 0) { dprintk("svc: bad null verf\n"); - *authp = rpc_autherr_badverf; + rqstp->rq_auth_stat = rpc_autherr_badverf; return SVC_DENIED; } @@ -785,7 +789,7 @@ struct auth_ops svcauth_null = { static int -svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp) +svcauth_unix_accept(struct svc_rqst *rqstp) { struct kvec *argv = &rqstp->rq_arg.head[0]; struct kvec *resv = &rqstp->rq_res.head[0]; @@ -827,7 +831,7 @@ svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp) } groups_sort(cred->cr_group_info); if (svc_getu32(argv) != htonl(RPC_AUTH_NULL) || svc_getu32(argv) != 0) { - *authp = rpc_autherr_badverf; + rqstp->rq_auth_stat = rpc_autherr_badverf; return SVC_DENIED; } @@ -839,7 +843,7 @@ svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp) return SVC_OK; badcred: - *authp = rpc_autherr_badcred; + rqstp->rq_auth_stat = rpc_autherr_badcred; return SVC_DENIED; } diff --git a/net/sunrpc/sysfs.c b/net/sunrpc/sysfs.c index 64da3bfd28e6..9a6f17e18f73 100644 --- a/net/sunrpc/sysfs.c +++ b/net/sunrpc/sysfs.c @@ -100,6 +100,28 @@ static ssize_t rpc_sysfs_xprt_dstaddr_show(struct kobject *kobj, return ret + 1; } +static ssize_t rpc_sysfs_xprt_srcaddr_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + struct rpc_xprt *xprt = rpc_sysfs_xprt_kobj_get_xprt(kobj); + struct sockaddr_storage saddr; + struct sock_xprt *sock; + ssize_t ret = -1; + + if (!xprt) + return 0; + + sock = container_of(xprt, struct sock_xprt, xprt); + if (kernel_getsockname(sock->sock, (struct sockaddr *)&saddr) < 0) + goto out; + + ret = sprintf(buf, "%pISc\n", &saddr); +out: + xprt_put(xprt); + return ret + 1; +} + static ssize_t rpc_sysfs_xprt_info_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) @@ -114,14 +136,16 @@ static ssize_t rpc_sysfs_xprt_info_show(struct kobject *kobj, "max_num_slots=%u\nmin_num_slots=%u\nnum_reqs=%u\n" "binding_q_len=%u\nsending_q_len=%u\npending_q_len=%u\n" "backlog_q_len=%u\nmain_xprt=%d\nsrc_port=%u\n" - "tasks_queuelen=%ld\n", + "tasks_queuelen=%ld\ndst_port=%s\n", xprt->last_used, xprt->cong, xprt->cwnd, xprt->max_reqs, xprt->min_reqs, xprt->num_reqs, xprt->binding.qlen, xprt->sending.qlen, xprt->pending.qlen, xprt->backlog.qlen, xprt->main, (xprt->xprt_class->ident == XPRT_TRANSPORT_TCP) ? get_srcport(xprt) : 0, - atomic_long_read(&xprt->queuelen)); + atomic_long_read(&xprt->queuelen), + (xprt->xprt_class->ident == XPRT_TRANSPORT_TCP) ? + xprt->address_strings[RPC_DISPLAY_PORT] : "0"); xprt_put(xprt); return ret + 1; } @@ -183,8 +207,10 @@ static ssize_t rpc_sysfs_xprt_switch_info_show(struct kobject *kobj, if (!xprt_switch) return 0; - ret = sprintf(buf, "num_xprts=%u\nnum_active=%u\nqueue_len=%ld\n", + ret = sprintf(buf, "num_xprts=%u\nnum_active=%u\n" + "num_unique_destaddr=%u\nqueue_len=%ld\n", xprt_switch->xps_nxprts, xprt_switch->xps_nactive, + xprt_switch->xps_nunique_destaddr_xprts, atomic_long_read(&xprt_switch->xps_queuelen)); xprt_switch_put(xprt_switch); return ret + 1; @@ -376,6 +402,9 @@ static const void *rpc_sysfs_xprt_namespace(struct kobject *kobj) static struct kobj_attribute rpc_sysfs_xprt_dstaddr = __ATTR(dstaddr, 0644, rpc_sysfs_xprt_dstaddr_show, rpc_sysfs_xprt_dstaddr_store); +static struct kobj_attribute rpc_sysfs_xprt_srcaddr = __ATTR(srcaddr, + 0644, rpc_sysfs_xprt_srcaddr_show, NULL); + static struct kobj_attribute rpc_sysfs_xprt_info = __ATTR(xprt_info, 0444, rpc_sysfs_xprt_info_show, NULL); @@ -384,6 +413,7 @@ static struct kobj_attribute rpc_sysfs_xprt_change_state = __ATTR(xprt_state, static struct attribute *rpc_sysfs_xprt_attrs[] = { &rpc_sysfs_xprt_dstaddr.attr, + &rpc_sysfs_xprt_srcaddr.attr, &rpc_sysfs_xprt_info.attr, &rpc_sysfs_xprt_change_state.attr, NULL, diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index fb6db09725c7..cfd681700d1a 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -56,6 +56,7 @@ #include "sunrpc.h" #include "sysfs.h" +#include "fail.h" /* * Local variables @@ -761,6 +762,20 @@ void xprt_disconnect_done(struct rpc_xprt *xprt) EXPORT_SYMBOL_GPL(xprt_disconnect_done); /** + * xprt_schedule_autoclose_locked - Try to schedule an autoclose RPC call + * @xprt: transport to disconnect + */ +static void xprt_schedule_autoclose_locked(struct rpc_xprt *xprt) +{ + set_bit(XPRT_CLOSE_WAIT, &xprt->state); + if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0) + queue_work(xprtiod_workqueue, &xprt->task_cleanup); + else if (xprt->snd_task && !test_bit(XPRT_SND_IS_COOKIE, &xprt->state)) + rpc_wake_up_queued_task_set_status(&xprt->pending, + xprt->snd_task, -ENOTCONN); +} + +/** * xprt_force_disconnect - force a transport to disconnect * @xprt: transport to disconnect * @@ -771,13 +786,7 @@ void xprt_force_disconnect(struct rpc_xprt *xprt) /* Don't race with the test_bit() in xprt_clear_locked() */ spin_lock(&xprt->transport_lock); - set_bit(XPRT_CLOSE_WAIT, &xprt->state); - /* Try to schedule an autoclose RPC call */ - if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0) - queue_work(xprtiod_workqueue, &xprt->task_cleanup); - else if (xprt->snd_task) - rpc_wake_up_queued_task_set_status(&xprt->pending, - xprt->snd_task, -ENOTCONN); + xprt_schedule_autoclose_locked(xprt); spin_unlock(&xprt->transport_lock); } EXPORT_SYMBOL_GPL(xprt_force_disconnect); @@ -817,11 +826,7 @@ void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie) goto out; if (test_bit(XPRT_CLOSING, &xprt->state)) goto out; - set_bit(XPRT_CLOSE_WAIT, &xprt->state); - /* Try to schedule an autoclose RPC call */ - if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0) - queue_work(xprtiod_workqueue, &xprt->task_cleanup); - xprt_wake_pending_tasks(xprt, -EAGAIN); + xprt_schedule_autoclose_locked(xprt); out: spin_unlock(&xprt->transport_lock); } @@ -855,6 +860,19 @@ xprt_init_autodisconnect(struct timer_list *t) queue_work(xprtiod_workqueue, &xprt->task_cleanup); } +#if IS_ENABLED(CONFIG_FAIL_SUNRPC) +static void xprt_inject_disconnect(struct rpc_xprt *xprt) +{ + if (!fail_sunrpc.ignore_client_disconnect && + should_fail(&fail_sunrpc.attr, 1)) + xprt->ops->inject_disconnect(xprt); +} +#else +static inline void xprt_inject_disconnect(struct rpc_xprt *xprt) +{ +} +#endif + bool xprt_lock_connect(struct rpc_xprt *xprt, struct rpc_task *task, void *cookie) @@ -866,12 +884,14 @@ bool xprt_lock_connect(struct rpc_xprt *xprt, goto out; if (xprt->snd_task != task) goto out; + set_bit(XPRT_SND_IS_COOKIE, &xprt->state); xprt->snd_task = cookie; ret = true; out: spin_unlock(&xprt->transport_lock); return ret; } +EXPORT_SYMBOL_GPL(xprt_lock_connect); void xprt_unlock_connect(struct rpc_xprt *xprt, void *cookie) { @@ -881,12 +901,14 @@ void xprt_unlock_connect(struct rpc_xprt *xprt, void *cookie) if (!test_bit(XPRT_LOCKED, &xprt->state)) goto out; xprt->snd_task =NULL; + clear_bit(XPRT_SND_IS_COOKIE, &xprt->state); xprt->ops->release_xprt(xprt, NULL); xprt_schedule_autodisconnect(xprt); out: spin_unlock(&xprt->transport_lock); wake_up_bit(&xprt->state, XPRT_LOCKED); } +EXPORT_SYMBOL_GPL(xprt_unlock_connect); /** * xprt_connect - schedule a transport connect operation diff --git a/net/sunrpc/xprtmultipath.c b/net/sunrpc/xprtmultipath.c index c60820e45082..1693f81aae37 100644 --- a/net/sunrpc/xprtmultipath.c +++ b/net/sunrpc/xprtmultipath.c @@ -139,6 +139,7 @@ struct rpc_xprt_switch *xprt_switch_alloc(struct rpc_xprt *xprt, xps->xps_iter_ops = &rpc_xprt_iter_singular; rpc_sysfs_xprt_switch_setup(xps, xprt, gfp_flags); xprt_switch_add_xprt_locked(xps, xprt); + xps->xps_nunique_destaddr_xprts = 1; rpc_sysfs_xprt_setup(xps, xprt, gfp_flags); } diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index 1151efd09b27..17f174d6ea3b 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -115,7 +115,7 @@ int xprt_rdma_bc_send_reply(struct rpc_rqst *rqst) if (rc < 0) goto failed_marshal; - if (rpcrdma_post_sends(r_xprt, req)) + if (frwr_send(r_xprt, req)) goto drop_connection; return 0; diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 229fcc9a9064..f700b34a5bfd 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -394,6 +394,7 @@ int frwr_send(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) struct rpcrdma_ep *ep = r_xprt->rx_ep; struct rpcrdma_mr *mr; unsigned int num_wrs; + int ret; num_wrs = 1; post_wr = send_wr; @@ -420,7 +421,10 @@ int frwr_send(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) } trace_xprtrdma_post_send(req); - return ib_post_send(ep->re_id->qp, post_wr, NULL); + ret = ib_post_send(ep->re_id->qp, post_wr, NULL); + if (ret) + trace_xprtrdma_post_send_err(r_xprt, req, ret); + return ret; } /** @@ -557,6 +561,10 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) /* On error, the MRs get destroyed once the QP has drained. */ trace_xprtrdma_post_linv_err(req, rc); + + /* Force a connection loss to ensure complete recovery. + */ + rpcrdma_force_disconnect(ep); } /** @@ -653,4 +661,8 @@ void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) * retransmission. */ rpcrdma_unpin_rqst(req->rl_reply); + + /* Force a connection loss to ensure complete recovery. + */ + rpcrdma_force_disconnect(ep); } diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index 1e651447dc4e..e27433f08ca7 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -35,6 +35,7 @@ static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc); * controlling svcxprt_rdma is destroyed. */ struct svc_rdma_rw_ctxt { + struct llist_node rw_node; struct list_head rw_list; struct rdma_rw_ctx rw_ctx; unsigned int rw_nents; @@ -53,19 +54,19 @@ static struct svc_rdma_rw_ctxt * svc_rdma_get_rw_ctxt(struct svcxprt_rdma *rdma, unsigned int sges) { struct svc_rdma_rw_ctxt *ctxt; + struct llist_node *node; spin_lock(&rdma->sc_rw_ctxt_lock); - - ctxt = svc_rdma_next_ctxt(&rdma->sc_rw_ctxts); - if (ctxt) { - list_del(&ctxt->rw_list); - spin_unlock(&rdma->sc_rw_ctxt_lock); + node = llist_del_first(&rdma->sc_rw_ctxts); + spin_unlock(&rdma->sc_rw_ctxt_lock); + if (node) { + ctxt = llist_entry(node, struct svc_rdma_rw_ctxt, rw_node); } else { - spin_unlock(&rdma->sc_rw_ctxt_lock); ctxt = kmalloc(struct_size(ctxt, rw_first_sgl, SG_CHUNK_SIZE), GFP_KERNEL); if (!ctxt) goto out_noctx; + INIT_LIST_HEAD(&ctxt->rw_list); } @@ -83,14 +84,18 @@ out_noctx: return NULL; } -static void svc_rdma_put_rw_ctxt(struct svcxprt_rdma *rdma, - struct svc_rdma_rw_ctxt *ctxt) +static void __svc_rdma_put_rw_ctxt(struct svcxprt_rdma *rdma, + struct svc_rdma_rw_ctxt *ctxt, + struct llist_head *list) { sg_free_table_chained(&ctxt->rw_sg_table, SG_CHUNK_SIZE); + llist_add(&ctxt->rw_node, list); +} - spin_lock(&rdma->sc_rw_ctxt_lock); - list_add(&ctxt->rw_list, &rdma->sc_rw_ctxts); - spin_unlock(&rdma->sc_rw_ctxt_lock); +static void svc_rdma_put_rw_ctxt(struct svcxprt_rdma *rdma, + struct svc_rdma_rw_ctxt *ctxt) +{ + __svc_rdma_put_rw_ctxt(rdma, ctxt, &rdma->sc_rw_ctxts); } /** @@ -101,9 +106,10 @@ static void svc_rdma_put_rw_ctxt(struct svcxprt_rdma *rdma, void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma) { struct svc_rdma_rw_ctxt *ctxt; + struct llist_node *node; - while ((ctxt = svc_rdma_next_ctxt(&rdma->sc_rw_ctxts)) != NULL) { - list_del(&ctxt->rw_list); + while ((node = llist_del_first(&rdma->sc_rw_ctxts)) != NULL) { + ctxt = llist_entry(node, struct svc_rdma_rw_ctxt, rw_node); kfree(ctxt); } } @@ -171,20 +177,35 @@ static void svc_rdma_cc_init(struct svcxprt_rdma *rdma, cc->cc_sqecount = 0; } +/* + * The consumed rw_ctx's are cleaned and placed on a local llist so + * that only one atomic llist operation is needed to put them all + * back on the free list. + */ static void svc_rdma_cc_release(struct svc_rdma_chunk_ctxt *cc, enum dma_data_direction dir) { struct svcxprt_rdma *rdma = cc->cc_rdma; + struct llist_node *first, *last; struct svc_rdma_rw_ctxt *ctxt; + LLIST_HEAD(free); + first = last = NULL; while ((ctxt = svc_rdma_next_ctxt(&cc->cc_rwctxts)) != NULL) { list_del(&ctxt->rw_list); rdma_rw_ctx_destroy(&ctxt->rw_ctx, rdma->sc_qp, rdma->sc_port_num, ctxt->rw_sg_table.sgl, ctxt->rw_nents, dir); - svc_rdma_put_rw_ctxt(rdma, ctxt); + __svc_rdma_put_rw_ctxt(rdma, ctxt, &free); + + ctxt->rw_node.next = first; + first = &ctxt->rw_node; + if (!last) + last = first; } + if (first) + llist_add_batch(first, last, &rdma->sc_rw_ctxts); } /* State for sending a Write or Reply chunk. @@ -248,8 +269,7 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc) trace_svcrdma_wc_write(wc, &cc->cc_cid); - atomic_add(cc->cc_sqecount, &rdma->sc_sq_avail); - wake_up(&rdma->sc_send_wait); + svc_rdma_wake_send_waiters(rdma, cc->cc_sqecount); if (unlikely(wc->status != IB_WC_SUCCESS)) svc_xprt_deferred_close(&rdma->sc_xprt); @@ -304,9 +324,7 @@ static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc) trace_svcrdma_wc_read(wc, &cc->cc_cid); - atomic_add(cc->cc_sqecount, &rdma->sc_sq_avail); - wake_up(&rdma->sc_send_wait); - + svc_rdma_wake_send_waiters(rdma, cc->cc_sqecount); cc->cc_status = wc->status; complete(&cc->cc_done); return; diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index d6bbafb773e1..599021b2391d 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -113,13 +113,6 @@ static void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc); -static inline struct svc_rdma_send_ctxt * -svc_rdma_next_send_ctxt(struct list_head *list) -{ - return list_first_entry_or_null(list, struct svc_rdma_send_ctxt, - sc_list); -} - static void svc_rdma_send_cid_init(struct svcxprt_rdma *rdma, struct rpc_rdma_cid *cid) { @@ -182,9 +175,10 @@ fail0: void svc_rdma_send_ctxts_destroy(struct svcxprt_rdma *rdma) { struct svc_rdma_send_ctxt *ctxt; + struct llist_node *node; - while ((ctxt = svc_rdma_next_send_ctxt(&rdma->sc_send_ctxts))) { - list_del(&ctxt->sc_list); + while ((node = llist_del_first(&rdma->sc_send_ctxts)) != NULL) { + ctxt = llist_entry(node, struct svc_rdma_send_ctxt, sc_node); ib_dma_unmap_single(rdma->sc_pd->device, ctxt->sc_sges[0].addr, rdma->sc_max_req_size, @@ -204,12 +198,13 @@ void svc_rdma_send_ctxts_destroy(struct svcxprt_rdma *rdma) struct svc_rdma_send_ctxt *svc_rdma_send_ctxt_get(struct svcxprt_rdma *rdma) { struct svc_rdma_send_ctxt *ctxt; + struct llist_node *node; spin_lock(&rdma->sc_send_lock); - ctxt = svc_rdma_next_send_ctxt(&rdma->sc_send_ctxts); - if (!ctxt) + node = llist_del_first(&rdma->sc_send_ctxts); + if (!node) goto out_empty; - list_del(&ctxt->sc_list); + ctxt = llist_entry(node, struct svc_rdma_send_ctxt, sc_node); spin_unlock(&rdma->sc_send_lock); out: @@ -253,9 +248,21 @@ void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma, ctxt->sc_sges[i].length); } - spin_lock(&rdma->sc_send_lock); - list_add(&ctxt->sc_list, &rdma->sc_send_ctxts); - spin_unlock(&rdma->sc_send_lock); + llist_add(&ctxt->sc_node, &rdma->sc_send_ctxts); +} + +/** + * svc_rdma_wake_send_waiters - manage Send Queue accounting + * @rdma: controlling transport + * @avail: Number of additional SQEs that are now available + * + */ +void svc_rdma_wake_send_waiters(struct svcxprt_rdma *rdma, int avail) +{ + atomic_add(avail, &rdma->sc_sq_avail); + smp_mb__after_atomic(); + if (unlikely(waitqueue_active(&rdma->sc_send_wait))) + wake_up(&rdma->sc_send_wait); } /** @@ -275,11 +282,9 @@ static void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc) trace_svcrdma_wc_send(wc, &ctxt->sc_cid); + svc_rdma_wake_send_waiters(rdma, 1); complete(&ctxt->sc_done); - atomic_inc(&rdma->sc_sq_avail); - wake_up(&rdma->sc_send_wait); - if (unlikely(wc->status != IB_WC_SUCCESS)) svc_xprt_deferred_close(&rdma->sc_xprt); } diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index d94b7759ada1..94b20fb47135 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -136,9 +136,9 @@ static struct svcxprt_rdma *svc_rdma_create_xprt(struct svc_serv *serv, svc_xprt_init(net, &svc_rdma_class, &cma_xprt->sc_xprt, serv); INIT_LIST_HEAD(&cma_xprt->sc_accept_q); INIT_LIST_HEAD(&cma_xprt->sc_rq_dto_q); - INIT_LIST_HEAD(&cma_xprt->sc_send_ctxts); + init_llist_head(&cma_xprt->sc_send_ctxts); init_llist_head(&cma_xprt->sc_recv_ctxts); - INIT_LIST_HEAD(&cma_xprt->sc_rw_ctxts); + init_llist_head(&cma_xprt->sc_rw_ctxts); init_waitqueue_head(&cma_xprt->sc_send_wait); spin_lock_init(&cma_xprt->sc_lock); @@ -545,7 +545,6 @@ static void __svc_rdma_free(struct work_struct *work) { struct svcxprt_rdma *rdma = container_of(work, struct svcxprt_rdma, sc_work); - struct svc_xprt *xprt = &rdma->sc_xprt; /* This blocks until the Completion Queues are empty */ if (rdma->sc_qp && !IS_ERR(rdma->sc_qp)) @@ -553,12 +552,6 @@ static void __svc_rdma_free(struct work_struct *work) svc_rdma_flush_recv_queues(rdma); - /* Final put of backchannel client transport */ - if (xprt->xpt_bc_xprt) { - xprt_put(xprt->xpt_bc_xprt); - xprt->xpt_bc_xprt = NULL; - } - svc_rdma_destroy_rw_ctxts(rdma); svc_rdma_send_ctxts_destroy(rdma); svc_rdma_recv_ctxts_destroy(rdma); diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 9c2ffc67c0fd..16e5696314a4 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -250,12 +250,9 @@ xprt_rdma_connect_worker(struct work_struct *work) xprt->stat.connect_start; xprt_set_connected(xprt); rc = -EAGAIN; - } else { - /* Force a call to xprt_rdma_close to clean up */ - spin_lock(&xprt->transport_lock); - set_bit(XPRT_CLOSE_WAIT, &xprt->state); - spin_unlock(&xprt->transport_lock); - } + } else + rpcrdma_xprt_disconnect(r_xprt); + xprt_unlock_connect(xprt, r_xprt); xprt_wake_pending_tasks(xprt, rc); } @@ -489,6 +486,8 @@ xprt_rdma_connect(struct rpc_xprt *xprt, struct rpc_task *task) struct rpcrdma_ep *ep = r_xprt->rx_ep; unsigned long delay; + WARN_ON_ONCE(!xprt_lock_connect(xprt, task, r_xprt)); + delay = 0; if (ep && ep->re_connect_status != 0) { delay = xprt_reconnect_delay(xprt); @@ -661,7 +660,7 @@ xprt_rdma_send_request(struct rpc_rqst *rqst) goto drop_connection; rqst->rq_xtime = ktime_get(); - if (rpcrdma_post_sends(r_xprt, req)) + if (frwr_send(r_xprt, req)) goto drop_connection; rqst->rq_xmit_bytes_sent += rqst->rq_snd_buf.len; diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 649c23518ec0..aaec3c9be8db 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -124,7 +124,7 @@ static void rpcrdma_xprt_drain(struct rpcrdma_xprt *r_xprt) * connection is closed or lost. (The important thing is it needs * to be invoked "at least" once). */ -static void rpcrdma_force_disconnect(struct rpcrdma_ep *ep) +void rpcrdma_force_disconnect(struct rpcrdma_ep *ep) { if (atomic_add_unless(&ep->re_force_disconnect, 1, 1)) xprt_force_disconnect(ep->re_xprt); @@ -1350,21 +1350,6 @@ static void rpcrdma_regbuf_free(struct rpcrdma_regbuf *rb) } /** - * rpcrdma_post_sends - Post WRs to a transport's Send Queue - * @r_xprt: controlling transport instance - * @req: rpcrdma_req containing the Send WR to post - * - * Returns 0 if the post was successful, otherwise -ENOTCONN - * is returned. - */ -int rpcrdma_post_sends(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) -{ - if (frwr_send(r_xprt, req)) - return -ENOTCONN; - return 0; -} - -/** * rpcrdma_post_recvs - Refill the Receive Queue * @r_xprt: controlling transport instance * @needed: current credit grant @@ -1416,12 +1401,8 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed, bool temp) rc = ib_post_recv(ep->re_id->qp, wr, (const struct ib_recv_wr **)&bad_wr); - if (atomic_dec_return(&ep->re_receiving) > 0) - complete(&ep->re_done); - -out: - trace_xprtrdma_post_recvs(r_xprt, count, rc); if (rc) { + trace_xprtrdma_post_recvs_err(r_xprt, rc); for (wr = bad_wr; wr;) { struct rpcrdma_rep *rep; @@ -1431,6 +1412,11 @@ out: --count; } } + if (atomic_dec_return(&ep->re_receiving) > 0) + complete(&ep->re_done); + +out: + trace_xprtrdma_post_recvs(r_xprt, count); ep->re_receive_count += count; return; } diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 5d231d94e944..d91f54eae00b 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -454,11 +454,11 @@ extern unsigned int xprt_rdma_memreg_strategy; /* * Endpoint calls - xprtrdma/verbs.c */ +void rpcrdma_force_disconnect(struct rpcrdma_ep *ep); void rpcrdma_flush_disconnect(struct rpcrdma_xprt *r_xprt, struct ib_wc *wc); int rpcrdma_xprt_connect(struct rpcrdma_xprt *r_xprt); void rpcrdma_xprt_disconnect(struct rpcrdma_xprt *r_xprt); -int rpcrdma_post_sends(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req); void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed, bool temp); /* diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index e573dcecdd66..04f1b78bcbca 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1656,7 +1656,7 @@ static int xs_get_srcport(struct sock_xprt *transport) unsigned short get_srcport(struct rpc_xprt *xprt) { struct sock_xprt *sock = container_of(xprt, struct sock_xprt, xprt); - return sock->srcport; + return xs_sock_getport(sock->sock); } EXPORT_SYMBOL(get_srcport); @@ -2099,13 +2099,20 @@ static void xs_tcp_shutdown(struct rpc_xprt *xprt) if (sock == NULL) return; + if (!xprt->reuseport) { + xs_close(xprt); + return; + } switch (skst) { - default: + case TCP_FIN_WAIT1: + case TCP_FIN_WAIT2: + break; + case TCP_ESTABLISHED: + case TCP_CLOSE_WAIT: kernel_sock_shutdown(sock, SHUT_RDWR); trace_rpc_socket_shutdown(xprt, sock); break; - case TCP_CLOSE: - case TCP_TIME_WAIT: + default: xs_reset_transport(transport); } } @@ -3149,24 +3156,6 @@ void cleanup_socket_xprt(void) xprt_unregister_transport(&xs_bc_tcp_transport); } -static int param_set_uint_minmax(const char *val, - const struct kernel_param *kp, - unsigned int min, unsigned int max) -{ - unsigned int num; - int ret; - - if (!val) - return -EINVAL; - ret = kstrtouint(val, 0, &num); - if (ret) - return ret; - if (num < min || num > max) - return -EINVAL; - *((unsigned int *)kp->arg) = num; - return 0; -} - static int param_set_portnr(const char *val, const struct kernel_param *kp) { return param_set_uint_minmax(val, kp, diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 070698dd19bc..0b2c18efc079 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -378,6 +378,266 @@ int call_switchdev_blocking_notifiers(unsigned long val, struct net_device *dev, } EXPORT_SYMBOL_GPL(call_switchdev_blocking_notifiers); +struct switchdev_nested_priv { + bool (*check_cb)(const struct net_device *dev); + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev); + const struct net_device *dev; + struct net_device *lower_dev; +}; + +static int switchdev_lower_dev_walk(struct net_device *lower_dev, + struct netdev_nested_priv *priv) +{ + struct switchdev_nested_priv *switchdev_priv = priv->data; + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev); + bool (*check_cb)(const struct net_device *dev); + const struct net_device *dev; + + check_cb = switchdev_priv->check_cb; + foreign_dev_check_cb = switchdev_priv->foreign_dev_check_cb; + dev = switchdev_priv->dev; + + if (check_cb(lower_dev) && !foreign_dev_check_cb(lower_dev, dev)) { + switchdev_priv->lower_dev = lower_dev; + return 1; + } + + return 0; +} + +static struct net_device * +switchdev_lower_dev_find(struct net_device *dev, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev)) +{ + struct switchdev_nested_priv switchdev_priv = { + .check_cb = check_cb, + .foreign_dev_check_cb = foreign_dev_check_cb, + .dev = dev, + .lower_dev = NULL, + }; + struct netdev_nested_priv priv = { + .data = &switchdev_priv, + }; + + netdev_walk_all_lower_dev_rcu(dev, switchdev_lower_dev_walk, &priv); + + return switchdev_priv.lower_dev; +} + +static int __switchdev_handle_fdb_add_to_device(struct net_device *dev, + const struct net_device *orig_dev, + const struct switchdev_notifier_fdb_info *fdb_info, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), + int (*add_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info), + int (*lag_add_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info)) +{ + const struct switchdev_notifier_info *info = &fdb_info->info; + struct net_device *br, *lower_dev; + struct list_head *iter; + int err = -EOPNOTSUPP; + + if (check_cb(dev)) + return add_cb(dev, orig_dev, info->ctx, fdb_info); + + if (netif_is_lag_master(dev)) { + if (!switchdev_lower_dev_find(dev, check_cb, foreign_dev_check_cb)) + goto maybe_bridged_with_us; + + /* This is a LAG interface that we offload */ + if (!lag_add_cb) + return -EOPNOTSUPP; + + return lag_add_cb(dev, orig_dev, info->ctx, fdb_info); + } + + /* Recurse through lower interfaces in case the FDB entry is pointing + * towards a bridge device. + */ + if (netif_is_bridge_master(dev)) { + if (!switchdev_lower_dev_find(dev, check_cb, foreign_dev_check_cb)) + return 0; + + /* This is a bridge interface that we offload */ + netdev_for_each_lower_dev(dev, lower_dev, iter) { + /* Do not propagate FDB entries across bridges */ + if (netif_is_bridge_master(lower_dev)) + continue; + + /* Bridge ports might be either us, or LAG interfaces + * that we offload. + */ + if (!check_cb(lower_dev) && + !switchdev_lower_dev_find(lower_dev, check_cb, + foreign_dev_check_cb)) + continue; + + err = __switchdev_handle_fdb_add_to_device(lower_dev, orig_dev, + fdb_info, check_cb, + foreign_dev_check_cb, + add_cb, lag_add_cb); + if (err && err != -EOPNOTSUPP) + return err; + } + + return 0; + } + +maybe_bridged_with_us: + /* Event is neither on a bridge nor a LAG. Check whether it is on an + * interface that is in a bridge with us. + */ + br = netdev_master_upper_dev_get_rcu(dev); + if (!br || !netif_is_bridge_master(br)) + return 0; + + if (!switchdev_lower_dev_find(br, check_cb, foreign_dev_check_cb)) + return 0; + + return __switchdev_handle_fdb_add_to_device(br, orig_dev, fdb_info, + check_cb, foreign_dev_check_cb, + add_cb, lag_add_cb); +} + +int switchdev_handle_fdb_add_to_device(struct net_device *dev, + const struct switchdev_notifier_fdb_info *fdb_info, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), + int (*add_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info), + int (*lag_add_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info)) +{ + int err; + + err = __switchdev_handle_fdb_add_to_device(dev, dev, fdb_info, + check_cb, + foreign_dev_check_cb, + add_cb, lag_add_cb); + if (err == -EOPNOTSUPP) + err = 0; + + return err; +} +EXPORT_SYMBOL_GPL(switchdev_handle_fdb_add_to_device); + +static int __switchdev_handle_fdb_del_to_device(struct net_device *dev, + const struct net_device *orig_dev, + const struct switchdev_notifier_fdb_info *fdb_info, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), + int (*del_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info), + int (*lag_del_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info)) +{ + const struct switchdev_notifier_info *info = &fdb_info->info; + struct net_device *br, *lower_dev; + struct list_head *iter; + int err = -EOPNOTSUPP; + + if (check_cb(dev)) + return del_cb(dev, orig_dev, info->ctx, fdb_info); + + if (netif_is_lag_master(dev)) { + if (!switchdev_lower_dev_find(dev, check_cb, foreign_dev_check_cb)) + goto maybe_bridged_with_us; + + /* This is a LAG interface that we offload */ + if (!lag_del_cb) + return -EOPNOTSUPP; + + return lag_del_cb(dev, orig_dev, info->ctx, fdb_info); + } + + /* Recurse through lower interfaces in case the FDB entry is pointing + * towards a bridge device. + */ + if (netif_is_bridge_master(dev)) { + if (!switchdev_lower_dev_find(dev, check_cb, foreign_dev_check_cb)) + return 0; + + /* This is a bridge interface that we offload */ + netdev_for_each_lower_dev(dev, lower_dev, iter) { + /* Do not propagate FDB entries across bridges */ + if (netif_is_bridge_master(lower_dev)) + continue; + + /* Bridge ports might be either us, or LAG interfaces + * that we offload. + */ + if (!check_cb(lower_dev) && + !switchdev_lower_dev_find(lower_dev, check_cb, + foreign_dev_check_cb)) + continue; + + err = __switchdev_handle_fdb_del_to_device(lower_dev, orig_dev, + fdb_info, check_cb, + foreign_dev_check_cb, + del_cb, lag_del_cb); + if (err && err != -EOPNOTSUPP) + return err; + } + + return 0; + } + +maybe_bridged_with_us: + /* Event is neither on a bridge nor a LAG. Check whether it is on an + * interface that is in a bridge with us. + */ + br = netdev_master_upper_dev_get_rcu(dev); + if (!br || !netif_is_bridge_master(br)) + return 0; + + if (!switchdev_lower_dev_find(br, check_cb, foreign_dev_check_cb)) + return 0; + + return __switchdev_handle_fdb_del_to_device(br, orig_dev, fdb_info, + check_cb, foreign_dev_check_cb, + del_cb, lag_del_cb); +} + +int switchdev_handle_fdb_del_to_device(struct net_device *dev, + const struct switchdev_notifier_fdb_info *fdb_info, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), + int (*del_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info), + int (*lag_del_cb)(struct net_device *dev, + const struct net_device *orig_dev, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info)) +{ + int err; + + err = __switchdev_handle_fdb_del_to_device(dev, dev, fdb_info, + check_cb, + foreign_dev_check_cb, + del_cb, lag_del_cb); + if (err == -EOPNOTSUPP) + err = 0; + + return err; +} +EXPORT_SYMBOL_GPL(switchdev_handle_fdb_del_to_device); + static int __switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), @@ -549,3 +809,51 @@ int switchdev_handle_port_attr_set(struct net_device *dev, return err; } EXPORT_SYMBOL_GPL(switchdev_handle_port_attr_set); + +int switchdev_bridge_port_offload(struct net_device *brport_dev, + struct net_device *dev, const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb, + bool tx_fwd_offload, + struct netlink_ext_ack *extack) +{ + struct switchdev_notifier_brport_info brport_info = { + .brport = { + .dev = dev, + .ctx = ctx, + .atomic_nb = atomic_nb, + .blocking_nb = blocking_nb, + .tx_fwd_offload = tx_fwd_offload, + }, + }; + int err; + + ASSERT_RTNL(); + + err = call_switchdev_blocking_notifiers(SWITCHDEV_BRPORT_OFFLOADED, + brport_dev, &brport_info.info, + extack); + return notifier_to_errno(err); +} +EXPORT_SYMBOL_GPL(switchdev_bridge_port_offload); + +void switchdev_bridge_port_unoffload(struct net_device *brport_dev, + const void *ctx, + struct notifier_block *atomic_nb, + struct notifier_block *blocking_nb) +{ + struct switchdev_notifier_brport_info brport_info = { + .brport = { + .ctx = ctx, + .atomic_nb = atomic_nb, + .blocking_nb = blocking_nb, + }, + }; + + ASSERT_RTNL(); + + call_switchdev_blocking_notifiers(SWITCHDEV_BRPORT_UNOFFLOADED, + brport_dev, &brport_info.info, + NULL); +} +EXPORT_SYMBOL_GPL(switchdev_bridge_port_unoffload); diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index e5c43d4d5a75..c9391d38de85 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -898,16 +898,10 @@ static int tipc_aead_decrypt(struct net *net, struct tipc_aead *aead, if (unlikely(!aead)) return -ENOKEY; - /* Cow skb data if needed */ - if (likely(!skb_cloned(skb) && - (!skb_is_nonlinear(skb) || !skb_has_frag_list(skb)))) { - nsg = 1 + skb_shinfo(skb)->nr_frags; - } else { - nsg = skb_cow_data(skb, 0, &unused); - if (unlikely(nsg < 0)) { - pr_err("RX: skb_cow_data() returned %d\n", nsg); - return nsg; - } + nsg = skb_cow_data(skb, 0, &unused); + if (unlikely(nsg < 0)) { + pr_err("RX: skb_cow_data() returned %d\n", nsg); + return nsg; } /* Allocate memory for the AEAD operation */ diff --git a/net/tipc/link.c b/net/tipc/link.c index cf586840caeb..1b7a487c8841 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -913,7 +913,7 @@ static int link_schedule_user(struct tipc_link *l, struct tipc_msg *hdr) skb = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0, dnode, l->addr, dport, 0, 0); if (!skb) - return -ENOMEM; + return -ENOBUFS; msg_set_dest_droppable(buf_msg(skb), true); TIPC_SKB_CB(skb)->chain_imp = msg_importance(hdr); skb_queue_tail(&l->wakeupq, skb); @@ -1031,7 +1031,7 @@ void tipc_link_reset(struct tipc_link *l) * * Consumes the buffer chain. * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted - * Return: 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS or -ENOMEM + * Return: 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS */ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, struct sk_buff_head *xmitq) @@ -1089,7 +1089,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, if (!_skb) { kfree_skb(skb); __skb_queue_purge(list); - return -ENOMEM; + return -ENOBUFS; } __skb_queue_tail(transmq, skb); tipc_link_set_skb_retransmit_time(skb, l); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 34a97ea36cc8..a0a27d87f631 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -158,6 +158,7 @@ static void tipc_sk_remove(struct tipc_sock *tsk); static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dsz); static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz); static void tipc_sk_push_backlog(struct tipc_sock *tsk, bool nagle_ack); +static int tipc_wait_for_connect(struct socket *sock, long *timeo_p); static const struct proto_ops packet_ops; static const struct proto_ops stream_ops; @@ -1425,7 +1426,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) if (ua) { if (!tipc_uaddr_valid(ua, m->msg_namelen)) return -EINVAL; - atype = ua->addrtype; + atype = ua->addrtype; } /* If socket belongs to a communication group follow other paths */ @@ -1515,8 +1516,13 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) rc = 0; } - if (unlikely(syn && !rc)) + if (unlikely(syn && !rc)) { tipc_set_sk_state(sk, TIPC_CONNECTING); + if (dlen && timeout) { + timeout = msecs_to_jiffies(timeout); + tipc_wait_for_connect(sock, &timeout); + } + } return rc ? rc : dlen; } @@ -1564,7 +1570,7 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen) return -EMSGSIZE; /* Handle implicit connection setup */ - if (unlikely(dest)) { + if (unlikely(dest && sk->sk_state == TIPC_OPEN)) { rc = __tipc_sendmsg(sock, m, dlen); if (dlen && dlen == rc) { tsk->peer_caps = tipc_node_get_capabilities(net, dnode); @@ -1880,6 +1886,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, bool connected = !tipc_sk_type_connectionless(sk); struct tipc_sock *tsk = tipc_sk(sk); int rc, err, hlen, dlen, copy; + struct tipc_skb_cb *skb_cb; struct sk_buff_head xmitq; struct tipc_msg *hdr; struct sk_buff *skb; @@ -1903,6 +1910,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, if (unlikely(rc)) goto exit; skb = skb_peek(&sk->sk_receive_queue); + skb_cb = TIPC_SKB_CB(skb); hdr = buf_msg(skb); dlen = msg_data_sz(hdr); hlen = msg_hdr_sz(hdr); @@ -1922,18 +1930,33 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, /* Capture data if non-error msg, otherwise just set return value */ if (likely(!err)) { - copy = min_t(int, dlen, buflen); - if (unlikely(copy != dlen)) - m->msg_flags |= MSG_TRUNC; - rc = skb_copy_datagram_msg(skb, hlen, m, copy); + int offset = skb_cb->bytes_read; + + copy = min_t(int, dlen - offset, buflen); + rc = skb_copy_datagram_msg(skb, hlen + offset, m, copy); + if (unlikely(rc)) + goto exit; + if (unlikely(offset + copy < dlen)) { + if (flags & MSG_EOR) { + if (!(flags & MSG_PEEK)) + skb_cb->bytes_read = offset + copy; + } else { + m->msg_flags |= MSG_TRUNC; + skb_cb->bytes_read = 0; + } + } else { + if (flags & MSG_EOR) + m->msg_flags |= MSG_EOR; + skb_cb->bytes_read = 0; + } } else { copy = 0; rc = 0; - if (err != TIPC_CONN_SHUTDOWN && connected && !m->msg_control) + if (err != TIPC_CONN_SHUTDOWN && connected && !m->msg_control) { rc = -ECONNRESET; + goto exit; + } } - if (unlikely(rc)) - goto exit; /* Mark message as group event if applicable */ if (unlikely(grp_evt)) { @@ -1956,6 +1979,9 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, tipc_node_distr_xmit(sock_net(sk), &xmitq); } + if (skb_cb->bytes_read) + goto exit; + tsk_advance_rx_queue(sk); if (likely(!connected)) @@ -2646,7 +2672,7 @@ static int tipc_listen(struct socket *sock, int len) static int tipc_wait_for_accept(struct socket *sock, long timeo) { struct sock *sk = sock->sk; - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); int err; /* True wake-one mechanism for incoming connections: only @@ -2655,12 +2681,12 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) * anymore, the common case will execute the loop only once. */ for (;;) { - prepare_to_wait_exclusive(sk_sleep(sk), &wait, - TASK_INTERRUPTIBLE); if (timeo && skb_queue_empty(&sk->sk_receive_queue)) { + add_wait_queue(sk_sleep(sk), &wait); release_sock(sk); - timeo = schedule_timeout(timeo); + timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); lock_sock(sk); + remove_wait_queue(sk_sleep(sk), &wait); } err = 0; if (!skb_queue_empty(&sk->sk_receive_queue)) @@ -2672,7 +2698,6 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) if (signal_pending(current)) break; } - finish_wait(sk_sleep(sk), &wait); return err; } @@ -2689,9 +2714,10 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, bool kern) { struct sock *new_sk, *sk = sock->sk; - struct sk_buff *buf; struct tipc_sock *new_tsock; + struct msghdr m = {NULL,}; struct tipc_msg *msg; + struct sk_buff *buf; long timeo; int res; @@ -2737,19 +2763,17 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, } /* - * Respond to 'SYN-' by discarding it & returning 'ACK'-. - * Respond to 'SYN+' by queuing it on new socket. + * Respond to 'SYN-' by discarding it & returning 'ACK'. + * Respond to 'SYN+' by queuing it on new socket & returning 'ACK'. */ if (!msg_data_sz(msg)) { - struct msghdr m = {NULL,}; - tsk_advance_rx_queue(sk); - __tipc_sendstream(new_sock, &m, 0); } else { __skb_dequeue(&sk->sk_receive_queue); __skb_queue_head(&new_sk->sk_receive_queue, buf); skb_set_owner_r(buf, new_sk); } + __tipc_sendstream(new_sock, &m, 0); release_sock(new_sk); exit: release_sock(sk); diff --git a/net/unix/Kconfig b/net/unix/Kconfig index b6c4282899ec..b7f811216820 100644 --- a/net/unix/Kconfig +++ b/net/unix/Kconfig @@ -25,6 +25,11 @@ config UNIX_SCM depends on UNIX default y +config AF_UNIX_OOB + bool + depends on UNIX + default y + config UNIX_DIAG tristate "UNIX: socket monitoring interface" depends on UNIX diff --git a/net/unix/Makefile b/net/unix/Makefile index 54e58cc4f945..20491825b4d0 100644 --- a/net/unix/Makefile +++ b/net/unix/Makefile @@ -7,6 +7,7 @@ obj-$(CONFIG_UNIX) += unix.o unix-y := af_unix.o garbage.o unix-$(CONFIG_SYSCTL) += sysctl_net_unix.o +unix-$(CONFIG_BPF_SYSCALL) += unix_bpf.o obj-$(CONFIG_UNIX_DIAG) += unix_diag.o unix_diag-y := diag.o diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 23c92ad15c61..eb47b9de2380 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -113,6 +113,7 @@ #include <linux/security.h> #include <linux/freezer.h> #include <linux/file.h> +#include <linux/btf_ids.h> #include "scm.h" @@ -494,6 +495,7 @@ static void unix_dgram_disconnected(struct sock *sk, struct sock *other) sk_error_report(other); } } + other->sk_state = TCP_CLOSE; } static void unix_sock_destructor(struct sock *sk) @@ -502,6 +504,12 @@ static void unix_sock_destructor(struct sock *sk) skb_queue_purge(&sk->sk_receive_queue); +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + if (u->oob_skb) { + kfree_skb(u->oob_skb); + u->oob_skb = NULL; + } +#endif WARN_ON(refcount_read(&sk->sk_wmem_alloc)); WARN_ON(!sk_unhashed(sk)); WARN_ON(sk->sk_socket); @@ -669,6 +677,10 @@ static ssize_t unix_stream_splice_read(struct socket *, loff_t *ppos, unsigned int flags); static int unix_dgram_sendmsg(struct socket *, struct msghdr *, size_t); static int unix_dgram_recvmsg(struct socket *, struct msghdr *, size_t, int); +static int unix_read_sock(struct sock *sk, read_descriptor_t *desc, + sk_read_actor_t recv_actor); +static int unix_stream_read_sock(struct sock *sk, read_descriptor_t *desc, + sk_read_actor_t recv_actor); static int unix_dgram_connect(struct socket *, struct sockaddr *, int, int); static int unix_seqpacket_sendmsg(struct socket *, struct msghdr *, size_t); @@ -722,6 +734,7 @@ static const struct proto_ops unix_stream_ops = { .shutdown = unix_shutdown, .sendmsg = unix_stream_sendmsg, .recvmsg = unix_stream_recvmsg, + .read_sock = unix_stream_read_sock, .mmap = sock_no_mmap, .sendpage = unix_stream_sendpage, .splice_read = unix_stream_splice_read, @@ -746,6 +759,7 @@ static const struct proto_ops unix_dgram_ops = { .listen = sock_no_listen, .shutdown = unix_shutdown, .sendmsg = unix_dgram_sendmsg, + .read_sock = unix_read_sock, .recvmsg = unix_dgram_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, @@ -777,13 +791,42 @@ static const struct proto_ops unix_seqpacket_ops = { .show_fdinfo = unix_show_fdinfo, }; -static struct proto unix_proto = { - .name = "UNIX", +static void unix_close(struct sock *sk, long timeout) +{ + /* Nothing to do here, unix socket does not need a ->close(). + * This is merely for sockmap. + */ +} + +static void unix_unhash(struct sock *sk) +{ + /* Nothing to do here, unix socket does not need a ->unhash(). + * This is merely for sockmap. + */ +} + +struct proto unix_dgram_proto = { + .name = "UNIX-DGRAM", .owner = THIS_MODULE, .obj_size = sizeof(struct unix_sock), + .close = unix_close, +#ifdef CONFIG_BPF_SYSCALL + .psock_update_sk_prot = unix_dgram_bpf_update_proto, +#endif }; -static struct sock *unix_create1(struct net *net, struct socket *sock, int kern) +struct proto unix_stream_proto = { + .name = "UNIX-STREAM", + .owner = THIS_MODULE, + .obj_size = sizeof(struct unix_sock), + .close = unix_close, + .unhash = unix_unhash, +#ifdef CONFIG_BPF_SYSCALL + .psock_update_sk_prot = unix_stream_bpf_update_proto, +#endif +}; + +static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, int type) { struct sock *sk = NULL; struct unix_sock *u; @@ -792,7 +835,11 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern) if (atomic_long_read(&unix_nr_socks) > 2 * get_max_files()) goto out; - sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_proto, kern); + if (type == SOCK_STREAM) + sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_stream_proto, kern); + else /*dgram and seqpacket */ + sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_dgram_proto, kern); + if (!sk) goto out; @@ -854,7 +901,7 @@ static int unix_create(struct net *net, struct socket *sock, int protocol, return -ESOCKTNOSUPPORT; } - return unix_create1(net, sock, kern) ? 0 : -ENOMEM; + return unix_create1(net, sock, kern, sock->type) ? 0 : -ENOMEM; } static int unix_release(struct socket *sock) @@ -864,6 +911,7 @@ static int unix_release(struct socket *sock) if (!sk) return 0; + sk->sk_prot->close(sk, 0); unix_release_sock(sk, 0); sock->sk = NULL; @@ -1174,6 +1222,7 @@ restart: if (err) goto out_unlock; + sk->sk_state = other->sk_state = TCP_ESTABLISHED; } else { /* * 1003.1g breaking connected state with AF_UNSPEC @@ -1187,7 +1236,10 @@ restart: */ if (unix_peer(sk)) { struct sock *old_peer = unix_peer(sk); + unix_peer(sk) = other; + if (!other) + sk->sk_state = TCP_CLOSE; unix_dgram_peer_wake_disconnect_wakeup(sk, old_peer); unix_state_double_unlock(sk, other); @@ -1199,6 +1251,7 @@ restart: unix_peer(sk) = other; unix_state_double_unlock(sk, other); } + return 0; out_unlock: @@ -1264,7 +1317,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, err = -ENOMEM; /* create new sock for complete connection */ - newsk = unix_create1(sock_net(sk), NULL, 0); + newsk = unix_create1(sock_net(sk), NULL, 0, sock->type); if (newsk == NULL) goto out; @@ -1431,12 +1484,10 @@ static int unix_socketpair(struct socket *socka, struct socket *sockb) init_peercred(ska); init_peercred(skb); - if (ska->sk_type != SOCK_DGRAM) { - ska->sk_state = TCP_ESTABLISHED; - skb->sk_state = TCP_ESTABLISHED; - socka->state = SS_CONNECTED; - sockb->state = SS_CONNECTED; - } + ska->sk_state = TCP_ESTABLISHED; + skb->sk_state = TCP_ESTABLISHED; + socka->state = SS_CONNECTED; + sockb->state = SS_CONNECTED; return 0; } @@ -1526,6 +1577,53 @@ out: return err; } +static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + scm->fp = scm_fp_dup(UNIXCB(skb).fp); + + /* + * Garbage collection of unix sockets starts by selecting a set of + * candidate sockets which have reference only from being in flight + * (total_refs == inflight_refs). This condition is checked once during + * the candidate collection phase, and candidates are marked as such, so + * that non-candidates can later be ignored. While inflight_refs is + * protected by unix_gc_lock, total_refs (file count) is not, hence this + * is an instantaneous decision. + * + * Once a candidate, however, the socket must not be reinstalled into a + * file descriptor while the garbage collection is in progress. + * + * If the above conditions are met, then the directed graph of + * candidates (*) does not change while unix_gc_lock is held. + * + * Any operations that changes the file count through file descriptors + * (dup, close, sendmsg) does not change the graph since candidates are + * not installed in fds. + * + * Dequeing a candidate via recvmsg would install it into an fd, but + * that takes unix_gc_lock to decrement the inflight count, so it's + * serialized with garbage collection. + * + * MSG_PEEK is special in that it does not change the inflight count, + * yet does install the socket into an fd. The following lock/unlock + * pair is to ensure serialization with garbage collection. It must be + * done between incrementing the file count and installing the file into + * an fd. + * + * If garbage collection starts after the barrier provided by the + * lock/unlock, then it will see the elevated refcount and not mark this + * as a candidate. If a garbage collection is already in progress + * before the file count was incremented, then the lock/unlock pair will + * ensure that garbage collection is finished before progressing to + * installing the fd. + * + * (*) A -> B where B is on the queue of A or B is on the queue of C + * which is on the queue of listening socket A. + */ + spin_lock(&unix_gc_lock); + spin_unlock(&unix_gc_lock); +} + static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds) { int err = 0; @@ -1735,6 +1833,7 @@ restart_locked: unix_state_unlock(sk); + sk->sk_state = TCP_CLOSE; unix_dgram_disconnected(sk, other); sock_put(other); err = -ECONNREFUSED; @@ -1825,6 +1924,53 @@ out: */ #define UNIX_SKB_FRAGS_SZ (PAGE_SIZE << get_order(32768)) +#if (IS_ENABLED(CONFIG_AF_UNIX_OOB)) +static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other) +{ + struct unix_sock *ousk = unix_sk(other); + struct sk_buff *skb; + int err = 0; + + skb = sock_alloc_send_skb(sock->sk, 1, msg->msg_flags & MSG_DONTWAIT, &err); + + if (!skb) + return err; + + skb_put(skb, 1); + err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, 1); + + if (err) { + kfree_skb(skb); + return err; + } + + unix_state_lock(other); + + if (sock_flag(other, SOCK_DEAD) || + (other->sk_shutdown & RCV_SHUTDOWN)) { + unix_state_unlock(other); + kfree_skb(skb); + return -EPIPE; + } + + maybe_add_creds(skb, sock, other); + skb_get(skb); + + if (ousk->oob_skb) + consume_skb(ousk->oob_skb); + + ousk->oob_skb = skb; + + scm_stat_add(other, skb); + skb_queue_tail(&other->sk_receive_queue, skb); + sk_send_sigurg(other); + unix_state_unlock(other); + other->sk_data_ready(other); + + return err; +} +#endif + static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { @@ -1843,8 +1989,14 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, return err; err = -EOPNOTSUPP; - if (msg->msg_flags&MSG_OOB) - goto out_err; + if (msg->msg_flags & MSG_OOB) { +#if (IS_ENABLED(CONFIG_AF_UNIX_OOB)) + if (len) + len--; + else +#endif + goto out_err; + } if (msg->msg_namelen) { err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP; @@ -1909,6 +2061,15 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, sent += size; } +#if (IS_ENABLED(CONFIG_AF_UNIX_OOB)) + if (msg->msg_flags & MSG_OOB) { + err = queue_oob(sock, msg, other); + if (err) + goto out_err; + sent++; + } +#endif + scm_destroy(&scm); return sent; @@ -2081,11 +2242,11 @@ static void unix_copy_addr(struct msghdr *msg, struct sock *sk) } } -static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, - size_t size, int flags) +int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size, + int flags) { struct scm_cookie scm; - struct sock *sk = sock->sk; + struct socket *sock = sk->sk_socket; struct unix_sock *u = unix_sk(sk); struct sk_buff *skb, *last; long timeo; @@ -2175,7 +2336,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, sk_peek_offset_fwd(sk, size); if (UNIXCB(skb).fp) - scm.fp = scm_fp_dup(UNIXCB(skb).fp); + unix_peek_fds(&scm, skb); } err = (flags & MSG_TRUNC) ? skb->len - skip : size; @@ -2188,6 +2349,55 @@ out: return err; } +static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int flags) +{ + struct sock *sk = sock->sk; + +#ifdef CONFIG_BPF_SYSCALL + const struct proto *prot = READ_ONCE(sk->sk_prot); + + if (prot != &unix_dgram_proto) + return prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT, + flags & ~MSG_DONTWAIT, NULL); +#endif + return __unix_dgram_recvmsg(sk, msg, size, flags); +} + +static int unix_read_sock(struct sock *sk, read_descriptor_t *desc, + sk_read_actor_t recv_actor) +{ + int copied = 0; + + while (1) { + struct unix_sock *u = unix_sk(sk); + struct sk_buff *skb; + int used, err; + + mutex_lock(&u->iolock); + skb = skb_recv_datagram(sk, 0, 1, &err); + mutex_unlock(&u->iolock); + if (!skb) + return err; + + used = recv_actor(desc, skb, 0, skb->len); + if (used <= 0) { + if (!copied) + copied = used; + kfree_skb(skb); + break; + } else if (used <= skb->len) { + copied += used; + } + + kfree_skb(skb); + if (!desc->count) + break; + } + + return copied; +} + /* * Sleep until more data has arrived. But check for races.. */ @@ -2247,6 +2457,86 @@ struct unix_stream_read_state { unsigned int splice_flags; }; +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) +static int unix_stream_recv_urg(struct unix_stream_read_state *state) +{ + struct socket *sock = state->socket; + struct sock *sk = sock->sk; + struct unix_sock *u = unix_sk(sk); + int chunk = 1; + struct sk_buff *oob_skb; + + mutex_lock(&u->iolock); + unix_state_lock(sk); + + if (sock_flag(sk, SOCK_URGINLINE) || !u->oob_skb) { + unix_state_unlock(sk); + mutex_unlock(&u->iolock); + return -EINVAL; + } + + oob_skb = u->oob_skb; + + if (!(state->flags & MSG_PEEK)) { + u->oob_skb = NULL; + } + + unix_state_unlock(sk); + + chunk = state->recv_actor(oob_skb, 0, chunk, state); + + if (!(state->flags & MSG_PEEK)) { + UNIXCB(oob_skb).consumed += 1; + kfree_skb(oob_skb); + } + + mutex_unlock(&u->iolock); + + if (chunk < 0) + return -EFAULT; + + state->msg->msg_flags |= MSG_OOB; + return 1; +} + +static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, + int flags, int copied) +{ + struct unix_sock *u = unix_sk(sk); + + if (!unix_skb_len(skb) && !(flags & MSG_PEEK)) { + skb_unlink(skb, &sk->sk_receive_queue); + consume_skb(skb); + skb = NULL; + } else { + if (skb == u->oob_skb) { + if (copied) { + skb = NULL; + } else if (sock_flag(sk, SOCK_URGINLINE)) { + if (!(flags & MSG_PEEK)) { + u->oob_skb = NULL; + consume_skb(skb); + } + } else if (!(flags & MSG_PEEK)) { + skb_unlink(skb, &sk->sk_receive_queue); + consume_skb(skb); + skb = skb_peek(&sk->sk_receive_queue); + } + } + } + return skb; +} +#endif + +static int unix_stream_read_sock(struct sock *sk, read_descriptor_t *desc, + sk_read_actor_t recv_actor) +{ + if (unlikely(sk->sk_state != TCP_ESTABLISHED)) + return -ENOTCONN; + + return unix_read_sock(sk, desc, recv_actor); +} + static int unix_stream_read_generic(struct unix_stream_read_state *state, bool freezable) { @@ -2272,6 +2562,9 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, if (unlikely(flags & MSG_OOB)) { err = -EOPNOTSUPP; +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + err = unix_stream_recv_urg(state); +#endif goto out; } @@ -2300,6 +2593,18 @@ redo: } last = skb = skb_peek(&sk->sk_receive_queue); last_len = last ? last->len : 0; + +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + if (skb) { + skb = manage_oob(skb, sk, flags, copied); + if (!skb) { + unix_state_unlock(sk); + if (copied) + break; + goto redo; + } + } +#endif again: if (skb == NULL) { if (copied >= target) @@ -2418,7 +2723,7 @@ unlock: /* It is questionable, see note in unix_dgram_recvmsg. */ if (UNIXCB(skb).fp) - scm.fp = scm_fp_dup(UNIXCB(skb).fp); + unix_peek_fds(&scm, skb); sk_peek_offset_fwd(sk, chunk); @@ -2457,6 +2762,20 @@ static int unix_stream_read_actor(struct sk_buff *skb, return ret ?: chunk; } +int __unix_stream_recvmsg(struct sock *sk, struct msghdr *msg, + size_t size, int flags) +{ + struct unix_stream_read_state state = { + .recv_actor = unix_stream_read_actor, + .socket = sk->sk_socket, + .msg = msg, + .size = size, + .flags = flags + }; + + return unix_stream_read_generic(&state, true); +} + static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { @@ -2468,6 +2787,14 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg, .flags = flags }; +#ifdef CONFIG_BPF_SYSCALL + struct sock *sk = sock->sk; + const struct proto *prot = READ_ONCE(sk->sk_prot); + + if (prot != &unix_stream_proto) + return prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT, + flags & ~MSG_DONTWAIT, NULL); +#endif return unix_stream_read_generic(&state, true); } @@ -2528,7 +2855,10 @@ static int unix_shutdown(struct socket *sock, int mode) (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)) { int peer_mode = 0; + const struct proto *prot = READ_ONCE(other->sk_prot); + if (prot->unhash) + prot->unhash(other); if (mode&RCV_SHUTDOWN) peer_mode |= SEND_SHUTDOWN; if (mode&SEND_SHUTDOWN) @@ -2537,10 +2867,12 @@ static int unix_shutdown(struct socket *sock, int mode) other->sk_shutdown |= peer_mode; unix_state_unlock(other); other->sk_state_change(other); - if (peer_mode == SHUTDOWN_MASK) + if (peer_mode == SHUTDOWN_MASK) { sk_wake_async(other, SOCK_WAKE_WAITD, POLL_HUP); - else if (peer_mode & RCV_SHUTDOWN) + other->sk_state = TCP_CLOSE; + } else if (peer_mode & RCV_SHUTDOWN) { sk_wake_async(other, SOCK_WAKE_WAITD, POLL_IN); + } } if (other) sock_put(other); @@ -2635,6 +2967,20 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) case SIOCUNIXFILE: err = unix_open_file(sk); break; +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + case SIOCATMARK: + { + struct sk_buff *skb; + struct unix_sock *u = unix_sk(sk); + int answ = 0; + + skb = skb_peek(&sk->sk_receive_queue); + if (skb && skb == u->oob_skb) + answ = 1; + err = put_user(answ, (int __user *)arg); + } + break; +#endif default: err = -ENOIOCTLCMD; break; @@ -2871,6 +3217,64 @@ static const struct seq_operations unix_seq_ops = { .stop = unix_seq_stop, .show = unix_seq_show, }; + +#if IS_BUILTIN(CONFIG_UNIX) && defined(CONFIG_BPF_SYSCALL) +struct bpf_iter__unix { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct unix_sock *, unix_sk); + uid_t uid __aligned(8); +}; + +static int unix_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, + struct unix_sock *unix_sk, uid_t uid) +{ + struct bpf_iter__unix ctx; + + meta->seq_num--; /* skip SEQ_START_TOKEN */ + ctx.meta = meta; + ctx.unix_sk = unix_sk; + ctx.uid = uid; + return bpf_iter_run_prog(prog, &ctx); +} + +static int bpf_iter_unix_seq_show(struct seq_file *seq, void *v) +{ + struct bpf_iter_meta meta; + struct bpf_prog *prog; + struct sock *sk = v; + uid_t uid; + + if (v == SEQ_START_TOKEN) + return 0; + + uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)); + meta.seq = seq; + prog = bpf_iter_get_info(&meta, false); + return unix_prog_seq_show(prog, &meta, v, uid); +} + +static void bpf_iter_unix_seq_stop(struct seq_file *seq, void *v) +{ + struct bpf_iter_meta meta; + struct bpf_prog *prog; + + if (!v) { + meta.seq = seq; + prog = bpf_iter_get_info(&meta, true); + if (prog) + (void)unix_prog_seq_show(prog, &meta, v, 0); + } + + unix_seq_stop(seq, v); +} + +static const struct seq_operations bpf_iter_unix_seq_ops = { + .start = unix_seq_start, + .next = unix_seq_next, + .stop = bpf_iter_unix_seq_stop, + .show = bpf_iter_unix_seq_show, +}; +#endif #endif static const struct net_proto_family unix_family_ops = { @@ -2911,13 +3315,48 @@ static struct pernet_operations unix_net_ops = { .exit = unix_net_exit, }; +#if IS_BUILTIN(CONFIG_UNIX) && defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) +DEFINE_BPF_ITER_FUNC(unix, struct bpf_iter_meta *meta, + struct unix_sock *unix_sk, uid_t uid) + +static const struct bpf_iter_seq_info unix_seq_info = { + .seq_ops = &bpf_iter_unix_seq_ops, + .init_seq_private = bpf_iter_init_seq_net, + .fini_seq_private = bpf_iter_fini_seq_net, + .seq_priv_size = sizeof(struct seq_net_private), +}; + +static struct bpf_iter_reg unix_reg_info = { + .target = "unix", + .ctx_arg_info_size = 1, + .ctx_arg_info = { + { offsetof(struct bpf_iter__unix, unix_sk), + PTR_TO_BTF_ID_OR_NULL }, + }, + .seq_info = &unix_seq_info, +}; + +static void __init bpf_iter_register(void) +{ + unix_reg_info.ctx_arg_info[0].btf_id = btf_sock_ids[BTF_SOCK_TYPE_UNIX]; + if (bpf_iter_reg_target(&unix_reg_info)) + pr_warn("Warning: could not register bpf iterator unix\n"); +} +#endif + static int __init af_unix_init(void) { int rc = -1; BUILD_BUG_ON(sizeof(struct unix_skb_parms) > sizeof_field(struct sk_buff, cb)); - rc = proto_register(&unix_proto, 1); + rc = proto_register(&unix_dgram_proto, 1); + if (rc != 0) { + pr_crit("%s: Cannot create unix_sock SLAB cache!\n", __func__); + goto out; + } + + rc = proto_register(&unix_stream_proto, 1); if (rc != 0) { pr_crit("%s: Cannot create unix_sock SLAB cache!\n", __func__); goto out; @@ -2925,6 +3364,12 @@ static int __init af_unix_init(void) sock_register(&unix_family_ops); register_pernet_subsys(&unix_net_ops); + unix_bpf_build_proto(); + +#if IS_BUILTIN(CONFIG_UNIX) && defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) + bpf_iter_register(); +#endif + out: return rc; } @@ -2932,7 +3377,8 @@ out: static void __exit af_unix_exit(void) { sock_unregister(PF_UNIX); - proto_unregister(&unix_proto); + proto_unregister(&unix_dgram_proto); + proto_unregister(&unix_stream_proto); unregister_pernet_subsys(&unix_net_ops); } diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c new file mode 100644 index 000000000000..b927e2baae50 --- /dev/null +++ b/net/unix/unix_bpf.c @@ -0,0 +1,174 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Cong Wang <cong.wang@bytedance.com> */ + +#include <linux/skmsg.h> +#include <linux/bpf.h> +#include <net/sock.h> +#include <net/af_unix.h> + +#define unix_sk_has_data(__sk, __psock) \ + ({ !skb_queue_empty(&__sk->sk_receive_queue) || \ + !skb_queue_empty(&__psock->ingress_skb) || \ + !list_empty(&__psock->ingress_msg); \ + }) + +static int unix_msg_wait_data(struct sock *sk, struct sk_psock *psock, + long timeo) +{ + DEFINE_WAIT_FUNC(wait, woken_wake_function); + struct unix_sock *u = unix_sk(sk); + int ret = 0; + + if (sk->sk_shutdown & RCV_SHUTDOWN) + return 1; + + if (!timeo) + return ret; + + add_wait_queue(sk_sleep(sk), &wait); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); + if (!unix_sk_has_data(sk, psock)) { + mutex_unlock(&u->iolock); + wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); + mutex_lock(&u->iolock); + ret = unix_sk_has_data(sk, psock); + } + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); + remove_wait_queue(sk_sleep(sk), &wait); + return ret; +} + +static int __unix_recvmsg(struct sock *sk, struct msghdr *msg, + size_t len, int flags) +{ + if (sk->sk_type == SOCK_DGRAM) + return __unix_dgram_recvmsg(sk, msg, len, flags); + else + return __unix_stream_recvmsg(sk, msg, len, flags); +} + +static int unix_bpf_recvmsg(struct sock *sk, struct msghdr *msg, + size_t len, int nonblock, int flags, + int *addr_len) +{ + struct unix_sock *u = unix_sk(sk); + struct sk_psock *psock; + int copied; + + psock = sk_psock_get(sk); + if (unlikely(!psock)) + return __unix_recvmsg(sk, msg, len, flags); + + mutex_lock(&u->iolock); + if (!skb_queue_empty(&sk->sk_receive_queue) && + sk_psock_queue_empty(psock)) { + mutex_unlock(&u->iolock); + sk_psock_put(sk, psock); + return __unix_recvmsg(sk, msg, len, flags); + } + +msg_bytes_ready: + copied = sk_msg_recvmsg(sk, psock, msg, len, flags); + if (!copied) { + long timeo; + int data; + + timeo = sock_rcvtimeo(sk, nonblock); + data = unix_msg_wait_data(sk, psock, timeo); + if (data) { + if (!sk_psock_queue_empty(psock)) + goto msg_bytes_ready; + mutex_unlock(&u->iolock); + sk_psock_put(sk, psock); + return __unix_recvmsg(sk, msg, len, flags); + } + copied = -EAGAIN; + } + mutex_unlock(&u->iolock); + sk_psock_put(sk, psock); + return copied; +} + +static struct proto *unix_dgram_prot_saved __read_mostly; +static DEFINE_SPINLOCK(unix_dgram_prot_lock); +static struct proto unix_dgram_bpf_prot; + +static struct proto *unix_stream_prot_saved __read_mostly; +static DEFINE_SPINLOCK(unix_stream_prot_lock); +static struct proto unix_stream_bpf_prot; + +static void unix_dgram_bpf_rebuild_protos(struct proto *prot, const struct proto *base) +{ + *prot = *base; + prot->close = sock_map_close; + prot->recvmsg = unix_bpf_recvmsg; +} + +static void unix_stream_bpf_rebuild_protos(struct proto *prot, + const struct proto *base) +{ + *prot = *base; + prot->close = sock_map_close; + prot->recvmsg = unix_bpf_recvmsg; + prot->unhash = sock_map_unhash; +} + +static void unix_dgram_bpf_check_needs_rebuild(struct proto *ops) +{ + if (unlikely(ops != smp_load_acquire(&unix_dgram_prot_saved))) { + spin_lock_bh(&unix_dgram_prot_lock); + if (likely(ops != unix_dgram_prot_saved)) { + unix_dgram_bpf_rebuild_protos(&unix_dgram_bpf_prot, ops); + smp_store_release(&unix_dgram_prot_saved, ops); + } + spin_unlock_bh(&unix_dgram_prot_lock); + } +} + +static void unix_stream_bpf_check_needs_rebuild(struct proto *ops) +{ + if (unlikely(ops != smp_load_acquire(&unix_stream_prot_saved))) { + spin_lock_bh(&unix_stream_prot_lock); + if (likely(ops != unix_stream_prot_saved)) { + unix_stream_bpf_rebuild_protos(&unix_stream_bpf_prot, ops); + smp_store_release(&unix_stream_prot_saved, ops); + } + spin_unlock_bh(&unix_stream_prot_lock); + } +} + +int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) +{ + if (sk->sk_type != SOCK_DGRAM) + return -EOPNOTSUPP; + + if (restore) { + sk->sk_write_space = psock->saved_write_space; + WRITE_ONCE(sk->sk_prot, psock->sk_proto); + return 0; + } + + unix_dgram_bpf_check_needs_rebuild(psock->sk_proto); + WRITE_ONCE(sk->sk_prot, &unix_dgram_bpf_prot); + return 0; +} + +int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) +{ + if (restore) { + sk->sk_write_space = psock->saved_write_space; + WRITE_ONCE(sk->sk_prot, psock->sk_proto); + return 0; + } + + unix_stream_bpf_check_needs_rebuild(psock->sk_proto); + WRITE_ONCE(sk->sk_prot, &unix_stream_bpf_prot); + return 0; +} + +void __init unix_bpf_build_proto(void) +{ + unix_dgram_bpf_rebuild_protos(&unix_dgram_bpf_prot, &unix_dgram_proto); + unix_stream_bpf_rebuild_protos(&unix_stream_bpf_prot, &unix_stream_proto); + +} diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index e0c2c992ad9c..4f7c99dfd16c 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -357,11 +357,14 @@ static void virtio_vsock_event_fill(struct virtio_vsock *vsock) static void virtio_vsock_reset_sock(struct sock *sk) { - lock_sock(sk); + /* vmci_transport.c doesn't take sk_lock here either. At least we're + * under vsock_table_lock so the sock cannot disappear while we're + * executing. + */ + sk->sk_state = TCP_CLOSE; sk->sk_err = ECONNRESET; sk_error_report(sk); - release_sock(sk); } static void virtio_vsock_update_guest_cid(struct virtio_vsock *vsock) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 169ba8b72a63..081e7ae93cb1 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1079,6 +1079,9 @@ virtio_transport_recv_connected(struct sock *sk, virtio_transport_recv_enqueue(vsk, pkt); sk->sk_data_ready(sk); return err; + case VIRTIO_VSOCK_OP_CREDIT_REQUEST: + virtio_transport_send_credit_update(vsk); + break; case VIRTIO_VSOCK_OP_CREDIT_UPDATE: sk->sk_write_space(sk); break; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 50eb405b0690..bf7cd4752547 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -759,6 +759,10 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_RECONNECT_REQUESTED] = { .type = NLA_REJECT }, [NL80211_ATTR_SAR_SPEC] = NLA_POLICY_NESTED(sar_policy), [NL80211_ATTR_DISABLE_HE] = { .type = NLA_FLAG }, + [NL80211_ATTR_OBSS_COLOR_BITMAP] = { .type = NLA_U64 }, + [NL80211_ATTR_COLOR_CHANGE_COUNT] = { .type = NLA_U8 }, + [NL80211_ATTR_COLOR_CHANGE_COLOR] = { .type = NLA_U8 }, + [NL80211_ATTR_COLOR_CHANGE_ELEMS] = NLA_POLICY_NESTED(nl80211_policy), }; /* policy for the key attributes */ @@ -2351,7 +2355,10 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, goto nla_put_failure; for (band = state->band_start; - band < NUM_NL80211_BANDS; band++) { + band < (state->split ? + NUM_NL80211_BANDS : + NL80211_BAND_60GHZ + 1); + band++) { struct ieee80211_supported_band *sband; /* omit higher bands for ancient software */ @@ -6524,8 +6531,7 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) err = rdev_change_station(rdev, dev, mac_addr, ¶ms); out_put_vlan: - if (params.vlan) - dev_put(params.vlan); + dev_put(params.vlan); return err; } @@ -6760,8 +6766,7 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) err = rdev_add_station(rdev, dev, mac_addr, ¶ms); - if (params.vlan) - dev_put(params.vlan); + dev_put(params.vlan); return err; } @@ -8486,8 +8491,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) goto out_free; nl80211_send_scan_start(rdev, wdev); - if (wdev->netdev) - dev_hold(wdev->netdev); + dev_hold(wdev->netdev); return 0; @@ -14800,6 +14804,106 @@ bad_tid_conf: return ret; } +static int nl80211_color_change(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct cfg80211_color_change_settings params = {}; + struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct nlattr **tb; + u16 offset; + int err; + + if (!rdev->ops->color_change) + return -EOPNOTSUPP; + + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_BSS_COLOR)) + return -EOPNOTSUPP; + + if (wdev->iftype != NL80211_IFTYPE_AP) + return -EOPNOTSUPP; + + if (!info->attrs[NL80211_ATTR_COLOR_CHANGE_COUNT] || + !info->attrs[NL80211_ATTR_COLOR_CHANGE_COLOR] || + !info->attrs[NL80211_ATTR_COLOR_CHANGE_ELEMS]) + return -EINVAL; + + params.count = nla_get_u8(info->attrs[NL80211_ATTR_COLOR_CHANGE_COUNT]); + params.color = nla_get_u8(info->attrs[NL80211_ATTR_COLOR_CHANGE_COLOR]); + + err = nl80211_parse_beacon(rdev, info->attrs, ¶ms.beacon_next); + if (err) + return err; + + tb = kcalloc(NL80211_ATTR_MAX + 1, sizeof(*tb), GFP_KERNEL); + if (!tb) + return -ENOMEM; + + err = nla_parse_nested(tb, NL80211_ATTR_MAX, + info->attrs[NL80211_ATTR_COLOR_CHANGE_ELEMS], + nl80211_policy, info->extack); + if (err) + goto out; + + err = nl80211_parse_beacon(rdev, tb, ¶ms.beacon_color_change); + if (err) + goto out; + + if (!tb[NL80211_ATTR_CNTDWN_OFFS_BEACON]) { + err = -EINVAL; + goto out; + } + + if (nla_len(tb[NL80211_ATTR_CNTDWN_OFFS_BEACON]) != sizeof(u16)) { + err = -EINVAL; + goto out; + } + + offset = nla_get_u16(tb[NL80211_ATTR_CNTDWN_OFFS_BEACON]); + if (offset >= params.beacon_color_change.tail_len) { + err = -EINVAL; + goto out; + } + + if (params.beacon_color_change.tail[offset] != params.count) { + err = -EINVAL; + goto out; + } + + params.counter_offset_beacon = offset; + + if (tb[NL80211_ATTR_CNTDWN_OFFS_PRESP]) { + if (nla_len(tb[NL80211_ATTR_CNTDWN_OFFS_PRESP]) != + sizeof(u16)) { + err = -EINVAL; + goto out; + } + + offset = nla_get_u16(tb[NL80211_ATTR_CNTDWN_OFFS_PRESP]); + if (offset >= params.beacon_color_change.probe_resp_len) { + err = -EINVAL; + goto out; + } + + if (params.beacon_color_change.probe_resp[offset] != + params.count) { + err = -EINVAL; + goto out; + } + + params.counter_offset_presp = offset; + } + + wdev_lock(wdev); + err = rdev_color_change(rdev, dev, ¶ms); + wdev_unlock(wdev); + +out: + kfree(tb); + return err; +} + #define NL80211_FLAG_NEED_WIPHY 0x01 #define NL80211_FLAG_NEED_NETDEV 0x02 #define NL80211_FLAG_NEED_RTNL 0x04 @@ -14857,9 +14961,7 @@ static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, return -ENETDOWN; } - if (dev) - dev_hold(dev); - + dev_hold(dev); info->user_ptr[0] = rdev; } @@ -14881,8 +14983,7 @@ static void nl80211_post_doit(const struct genl_ops *ops, struct sk_buff *skb, if (ops->internal_flags & NL80211_FLAG_NEED_WDEV) { struct wireless_dev *wdev = info->user_ptr[1]; - if (wdev->netdev) - dev_put(wdev->netdev); + dev_put(wdev->netdev); } else { dev_put(info->user_ptr[1]); } @@ -15798,6 +15899,14 @@ static const struct genl_small_ops nl80211_small_ops[] = { .internal_flags = NL80211_FLAG_NEED_WIPHY | NL80211_FLAG_NEED_RTNL, }, + { + .cmd = NL80211_CMD_COLOR_CHANGE_REQUEST, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = nl80211_color_change, + .flags = GENL_UNS_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, + }, }; static struct genl_family nl80211_fam __ro_after_init = { @@ -17427,6 +17536,51 @@ void cfg80211_ch_switch_started_notify(struct net_device *dev, } EXPORT_SYMBOL(cfg80211_ch_switch_started_notify); +int cfg80211_bss_color_notify(struct net_device *dev, gfp_t gfp, + enum nl80211_commands cmd, u8 count, + u64 color_bitmap) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); + struct sk_buff *msg; + void *hdr; + + ASSERT_WDEV_LOCK(wdev); + + trace_cfg80211_bss_color_notify(dev, cmd, count, color_bitmap); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); + if (!msg) + return -ENOMEM; + + hdr = nl80211hdr_put(msg, 0, 0, 0, cmd); + if (!hdr) + goto nla_put_failure; + + if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex)) + goto nla_put_failure; + + if (cmd == NL80211_CMD_COLOR_CHANGE_STARTED && + nla_put_u32(msg, NL80211_ATTR_COLOR_CHANGE_COUNT, count)) + goto nla_put_failure; + + if (cmd == NL80211_CMD_OBSS_COLOR_COLLISION && + nla_put_u64_64bit(msg, NL80211_ATTR_OBSS_COLOR_BITMAP, + color_bitmap, NL80211_ATTR_PAD)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + return genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), + msg, 0, NL80211_MCGRP_MLME, gfp); + +nla_put_failure: + nlmsg_free(msg); + return -EINVAL; +} +EXPORT_SYMBOL(cfg80211_bss_color_notify); + void nl80211_radar_notify(struct cfg80211_registered_device *rdev, const struct cfg80211_chan_def *chandef, diff --git a/net/wireless/radiotap.c b/net/wireless/radiotap.c index 36f1b59a78bf..ae2e1a896461 100644 --- a/net/wireless/radiotap.c +++ b/net/wireless/radiotap.c @@ -115,23 +115,22 @@ int ieee80211_radiotap_iterator_init( iterator->_max_length = get_unaligned_le16(&radiotap_header->it_len); iterator->_arg_index = 0; iterator->_bitmap_shifter = get_unaligned_le32(&radiotap_header->it_present); - iterator->_arg = (uint8_t *)radiotap_header + sizeof(*radiotap_header); + iterator->_arg = (uint8_t *)radiotap_header->it_optional; iterator->_reset_on_ext = 0; - iterator->_next_bitmap = &radiotap_header->it_present; - iterator->_next_bitmap++; + iterator->_next_bitmap = radiotap_header->it_optional; iterator->_vns = vns; iterator->current_namespace = &radiotap_ns; iterator->is_radiotap_ns = 1; /* find payload start allowing for extended bitmap(s) */ - if (iterator->_bitmap_shifter & (1<<IEEE80211_RADIOTAP_EXT)) { + if (iterator->_bitmap_shifter & (BIT(IEEE80211_RADIOTAP_EXT))) { if ((unsigned long)iterator->_arg - (unsigned long)iterator->_rtheader + sizeof(uint32_t) > (unsigned long)iterator->_max_length) return -EINVAL; while (get_unaligned_le32(iterator->_arg) & - (1 << IEEE80211_RADIOTAP_EXT)) { + (BIT(IEEE80211_RADIOTAP_EXT))) { iterator->_arg += sizeof(uint32_t); /* diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index b1d37f582dc6..ce6bf218a1a3 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -1368,4 +1368,17 @@ static inline int rdev_set_sar_specs(struct cfg80211_registered_device *rdev, return ret; } +static inline int rdev_color_change(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_color_change_settings *params) +{ + int ret; + + trace_rdev_color_change(&rdev->wiphy, dev, params); + ret = rdev->ops->color_change(&rdev->wiphy, dev, params); + trace_rdev_return_int(&rdev->wiphy, ret); + + return ret; +} + #endif /* __CFG80211_RDEV_OPS */ diff --git a/net/wireless/reg.c b/net/wireless/reg.c index c2d0ff7f089f..df87c7f3a049 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -171,9 +171,11 @@ enum nl80211_dfs_regions reg_get_dfs_region(struct wiphy *wiphy) { const struct ieee80211_regdomain *regd = NULL; const struct ieee80211_regdomain *wiphy_regd = NULL; + enum nl80211_dfs_regions dfs_region; rcu_read_lock(); regd = get_cfg80211_regdom(); + dfs_region = regd->dfs_region; if (!wiphy) goto out; @@ -182,6 +184,11 @@ enum nl80211_dfs_regions reg_get_dfs_region(struct wiphy *wiphy) if (!wiphy_regd) goto out; + if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) { + dfs_region = wiphy_regd->dfs_region; + goto out; + } + if (wiphy_regd->dfs_region == regd->dfs_region) goto out; @@ -193,7 +200,7 @@ enum nl80211_dfs_regions reg_get_dfs_region(struct wiphy *wiphy) out: rcu_read_unlock(); - return regd->dfs_region; + return dfs_region; } static void rcu_free_regdom(const struct ieee80211_regdomain *r) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index f03c7ac8e184..11c68b159324 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -975,8 +975,7 @@ void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, } #endif - if (wdev->netdev) - dev_put(wdev->netdev); + dev_put(wdev->netdev); kfree(rdev->int_scan_req); rdev->int_scan_req = NULL; @@ -1754,16 +1753,14 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, * be grouped with this beacon for updates ... */ if (!cfg80211_combine_bsses(rdev, new)) { - kfree(new); + bss_ref_put(rdev, new); goto drop; } } if (rdev->bss_entries >= bss_entries_limit && !cfg80211_bss_expire_oldest(rdev)) { - if (!list_empty(&new->hidden_list)) - list_del(&new->hidden_list); - kfree(new); + bss_ref_put(rdev, new); goto drop; } diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 440bce5f0274..19b78d472283 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -3597,6 +3597,52 @@ TRACE_EVENT(rdev_set_sar_specs, WIPHY_PR_ARG, __entry->type, __entry->num) ); +TRACE_EVENT(rdev_color_change, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_color_change_settings *params), + TP_ARGS(wiphy, netdev, params), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(u8, count) + __field(u16, bcn_ofs) + __field(u16, pres_ofs) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + __entry->count = params->count; + __entry->bcn_ofs = params->counter_offset_beacon; + __entry->pres_ofs = params->counter_offset_presp; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT + ", count: %u", + WIPHY_PR_ARG, NETDEV_PR_ARG, + __entry->count) +); + +TRACE_EVENT(cfg80211_bss_color_notify, + TP_PROTO(struct net_device *netdev, + enum nl80211_commands cmd, + u8 count, u64 color_bitmap), + TP_ARGS(netdev, cmd, count, color_bitmap), + TP_STRUCT__entry( + NETDEV_ENTRY + __field(u32, cmd) + __field(u8, count) + __field(u64, color_bitmap) + ), + TP_fast_assign( + NETDEV_ASSIGN; + __entry->cmd = cmd; + __entry->count = count; + __entry->color_bitmap = color_bitmap; + ), + TP_printk(NETDEV_PR_FMT ", cmd: %x, count: %u, bitmap: %llx", + NETDEV_PR_ARG, __entry->cmd, __entry->count, + __entry->color_bitmap) +); + #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index a20aec9d7393..2bf269390163 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -298,8 +298,16 @@ static int xfrm_xlate64(struct sk_buff *dst, const struct nlmsghdr *nlh_src) len = nlmsg_attrlen(nlh_src, xfrm_msg_min[type]); nla_for_each_attr(nla, attrs, len, remaining) { - int err = xfrm_xlate64_attr(dst, nla); + int err; + switch (type) { + case XFRM_MSG_NEWSPDINFO: + err = xfrm_nla_cpy(dst, nla, nla_len(nla)); + break; + default: + err = xfrm_xlate64_attr(dst, nla); + break; + } if (err) return err; } @@ -341,7 +349,8 @@ static int xfrm_alloc_compat(struct sk_buff *skb, const struct nlmsghdr *nlh_src /* Calculates len of translated 64-bit message. */ static size_t xfrm_user_rcv_calculate_len64(const struct nlmsghdr *src, - struct nlattr *attrs[XFRMA_MAX+1]) + struct nlattr *attrs[XFRMA_MAX + 1], + int maxtype) { size_t len = nlmsg_len(src); @@ -358,10 +367,20 @@ static size_t xfrm_user_rcv_calculate_len64(const struct nlmsghdr *src, case XFRM_MSG_POLEXPIRE: len += 8; break; + case XFRM_MSG_NEWSPDINFO: + /* attirbutes are xfrm_spdattr_type_t, not xfrm_attr_type_t */ + return len; default: break; } + /* Unexpected for anything, but XFRM_MSG_NEWSPDINFO, please + * correct both 64=>32-bit and 32=>64-bit translators to copy + * new attributes. + */ + if (WARN_ON_ONCE(maxtype)) + return len; + if (attrs[XFRMA_SA]) len += 4; if (attrs[XFRMA_POLICY]) @@ -440,7 +459,8 @@ static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla, static int xfrm_xlate32(struct nlmsghdr *dst, const struct nlmsghdr *src, struct nlattr *attrs[XFRMA_MAX+1], - size_t size, u8 type, struct netlink_ext_ack *extack) + size_t size, u8 type, int maxtype, + struct netlink_ext_ack *extack) { size_t pos; int i; @@ -520,6 +540,25 @@ static int xfrm_xlate32(struct nlmsghdr *dst, const struct nlmsghdr *src, } pos = dst->nlmsg_len; + if (maxtype) { + /* attirbutes are xfrm_spdattr_type_t, not xfrm_attr_type_t */ + WARN_ON_ONCE(src->nlmsg_type != XFRM_MSG_NEWSPDINFO); + + for (i = 1; i <= maxtype; i++) { + int err; + + if (!attrs[i]) + continue; + + /* just copy - no need for translation */ + err = xfrm_attr_cpy32(dst, &pos, attrs[i], size, + nla_len(attrs[i]), nla_len(attrs[i])); + if (err) + return err; + } + return 0; + } + for (i = 1; i < XFRMA_MAX + 1; i++) { int err; @@ -564,7 +603,7 @@ static struct nlmsghdr *xfrm_user_rcv_msg_compat(const struct nlmsghdr *h32, if (err < 0) return ERR_PTR(err); - len = xfrm_user_rcv_calculate_len64(h32, attrs); + len = xfrm_user_rcv_calculate_len64(h32, attrs, maxtype); /* The message doesn't need translation */ if (len == nlmsg_len(h32)) return NULL; @@ -574,7 +613,7 @@ static struct nlmsghdr *xfrm_user_rcv_msg_compat(const struct nlmsghdr *h32, if (!h64) return ERR_PTR(-ENOMEM); - err = xfrm_xlate32(h64, h32, attrs, len, type, extack); + err = xfrm_xlate32(h64, h32, attrs, len, type, maxtype, extack); if (err < 0) { kvfree(h64); return ERR_PTR(err); diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c index 2e8afe078d61..cb40ff0ff28d 100644 --- a/net/xfrm/xfrm_ipcomp.c +++ b/net/xfrm/xfrm_ipcomp.c @@ -241,7 +241,7 @@ static void ipcomp_free_tfms(struct crypto_comp * __percpu *tfms) break; } - WARN_ON(!pos); + WARN_ON(list_entry_is_head(pos, &ipcomp_tfms_list, list)); if (--pos->users) return; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 827d84255021..37d17a79617c 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -155,7 +155,6 @@ static struct xfrm_policy_afinfo const __rcu *xfrm_policy_afinfo[AF_INET6 + 1] __read_mostly; static struct kmem_cache *xfrm_dst_cache __ro_after_init; -static __read_mostly seqcount_mutex_t xfrm_policy_hash_generation; static struct rhashtable xfrm_policy_inexact_table; static const struct rhashtable_params xfrm_pol_inexact_params; @@ -585,7 +584,7 @@ static void xfrm_bydst_resize(struct net *net, int dir) return; spin_lock_bh(&net->xfrm.xfrm_policy_lock); - write_seqcount_begin(&xfrm_policy_hash_generation); + write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table, lockdep_is_held(&net->xfrm.xfrm_policy_lock)); @@ -596,7 +595,7 @@ static void xfrm_bydst_resize(struct net *net, int dir) rcu_assign_pointer(net->xfrm.policy_bydst[dir].table, ndst); net->xfrm.policy_bydst[dir].hmask = nhashmask; - write_seqcount_end(&xfrm_policy_hash_generation); + write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); synchronize_rcu(); @@ -1245,7 +1244,7 @@ static void xfrm_hash_rebuild(struct work_struct *work) } while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq)); spin_lock_bh(&net->xfrm.xfrm_policy_lock); - write_seqcount_begin(&xfrm_policy_hash_generation); + write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); /* make sure that we can insert the indirect policies again before * we start with destructive action. @@ -1354,7 +1353,7 @@ static void xfrm_hash_rebuild(struct work_struct *work) out_unlock: __xfrm_policy_inexact_flush(net); - write_seqcount_end(&xfrm_policy_hash_generation); + write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); mutex_unlock(&hash_resize_mutex); @@ -2091,15 +2090,12 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, if (unlikely(!daddr || !saddr)) return NULL; - retry: - sequence = read_seqcount_begin(&xfrm_policy_hash_generation); rcu_read_lock(); - - chain = policy_hash_direct(net, daddr, saddr, family, dir); - if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) { - rcu_read_unlock(); - goto retry; - } + retry: + do { + sequence = read_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); + chain = policy_hash_direct(net, daddr, saddr, family, dir); + } while (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence)); ret = NULL; hlist_for_each_entry_rcu(pol, chain, bydst) { @@ -2130,15 +2126,11 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, } skip_inexact: - if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) { - rcu_read_unlock(); + if (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence)) goto retry; - } - if (ret && !xfrm_pol_hold_rcu(ret)) { - rcu_read_unlock(); + if (ret && !xfrm_pol_hold_rcu(ret)) goto retry; - } fail: rcu_read_unlock(); @@ -3165,6 +3157,11 @@ ok: return dst; nopol: + if (!(dst_orig->dev->flags & IFF_LOOPBACK) && + !xfrm_default_allow(net, dir)) { + err = -EPERM; + goto error; + } if (!(flags & XFRM_LOOKUP_ICMP)) { dst = dst_orig; goto ok; @@ -3553,6 +3550,11 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, } if (!pol) { + if (!xfrm_default_allow(net, dir)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS); + return 0; + } + if (sp && secpath_has_nontransport(sp, 0, &xerr_idx)) { xfrm_secpath_reject(xerr_idx, skb, &fl); XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS); @@ -3607,6 +3609,12 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, tpp[ti++] = &pols[pi]->xfrm_vec[i]; } xfrm_nr = ti; + + if (!xfrm_default_allow(net, dir) && !xfrm_nr) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES); + goto reject; + } + if (npols > 1) { xfrm_tmpl_sort(stp, tpp, xfrm_nr, family); tpp = stp; @@ -4089,6 +4097,7 @@ static int __net_init xfrm_net_init(struct net *net) /* Initialize the per-net locks here */ spin_lock_init(&net->xfrm.xfrm_state_lock); spin_lock_init(&net->xfrm.xfrm_policy_lock); + seqcount_spinlock_init(&net->xfrm.xfrm_policy_hash_generation, &net->xfrm.xfrm_policy_lock); mutex_init(&net->xfrm.xfrm_cfg_mutex); rv = xfrm_statistics_init(net); @@ -4133,7 +4142,6 @@ void __init xfrm_init(void) { register_pernet_subsys(&xfrm_net_ops); xfrm_dev_init(); - seqcount_mutex_init(&xfrm_policy_hash_generation, &hash_resize_mutex); xfrm_input_init(); #ifdef CONFIG_XFRM_ESPINTCP diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index b47d613409b7..03b66d154b2b 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1961,6 +1961,59 @@ static struct sk_buff *xfrm_policy_netlink(struct sk_buff *in_skb, return skb; } +static int xfrm_set_default(struct sk_buff *skb, struct nlmsghdr *nlh, + struct nlattr **attrs) +{ + struct net *net = sock_net(skb->sk); + struct xfrm_userpolicy_default *up = nlmsg_data(nlh); + u8 dirmask; + u8 old_default = net->xfrm.policy_default; + + if (up->dirmask >= XFRM_USERPOLICY_DIRMASK_MAX) + return -EINVAL; + + dirmask = (1 << up->dirmask) & XFRM_POL_DEFAULT_MASK; + + net->xfrm.policy_default = (old_default & (0xff ^ dirmask)) + | (up->action << up->dirmask); + + rt_genid_bump_all(net); + + return 0; +} + +static int xfrm_get_default(struct sk_buff *skb, struct nlmsghdr *nlh, + struct nlattr **attrs) +{ + struct sk_buff *r_skb; + struct nlmsghdr *r_nlh; + struct net *net = sock_net(skb->sk); + struct xfrm_userpolicy_default *r_up, *up; + int len = NLMSG_ALIGN(sizeof(struct xfrm_userpolicy_default)); + u32 portid = NETLINK_CB(skb).portid; + u32 seq = nlh->nlmsg_seq; + + up = nlmsg_data(nlh); + + r_skb = nlmsg_new(len, GFP_ATOMIC); + if (!r_skb) + return -ENOMEM; + + r_nlh = nlmsg_put(r_skb, portid, seq, XFRM_MSG_GETDEFAULT, sizeof(*r_up), 0); + if (!r_nlh) { + kfree_skb(r_skb); + return -EMSGSIZE; + } + + r_up = nlmsg_data(r_nlh); + + r_up->action = ((net->xfrm.policy_default & (1 << up->dirmask)) >> up->dirmask); + r_up->dirmask = up->dirmask; + nlmsg_end(r_skb, r_nlh); + + return nlmsg_unicast(net->xfrm.nlsk, r_skb, portid); +} + static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { @@ -2664,6 +2717,8 @@ const int xfrm_msg_min[XFRM_NR_MSGTYPES] = { [XFRM_MSG_GETSADINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_NEWSPDINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_GETSPDINFO - XFRM_MSG_BASE] = sizeof(u32), + [XFRM_MSG_SETDEFAULT - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_default), + [XFRM_MSG_GETDEFAULT - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_default), }; EXPORT_SYMBOL_GPL(xfrm_msg_min); @@ -2743,6 +2798,8 @@ static const struct xfrm_link { .nla_pol = xfrma_spd_policy, .nla_max = XFRMA_SPD_MAX }, [XFRM_MSG_GETSPDINFO - XFRM_MSG_BASE] = { .doit = xfrm_get_spdinfo }, + [XFRM_MSG_SETDEFAULT - XFRM_MSG_BASE] = { .doit = xfrm_set_default }, + [XFRM_MSG_GETDEFAULT - XFRM_MSG_BASE] = { .doit = xfrm_get_default }, }; static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -2811,6 +2868,16 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, err = link->doit(skb, nlh, attrs); + /* We need to free skb allocated in xfrm_alloc_compat() before + * returning from this function, because consume_skb() won't take + * care of frag_list since netlink destructor sets + * sbk->head to NULL. (see netlink_skb_destructor()) + */ + if (skb_has_frag_list(skb)) { + kfree_skb(skb_shinfo(skb)->frag_list); + skb_shinfo(skb)->frag_list = NULL; + } + err: kvfree(nlh64); return err; |