diff options
Diffstat (limited to 'net')
420 files changed, 19695 insertions, 8390 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index d4bcfd8f95bf..f292e0267bb9 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -51,12 +51,16 @@ static int vlan_group_prealloc_vid(struct vlan_group *vg, __be16 vlan_proto, u16 vlan_id) { struct net_device **array; - unsigned int pidx, vidx; + unsigned int vidx; unsigned int size; + int pidx; ASSERT_RTNL(); pidx = vlan_proto_idx(vlan_proto); + if (pidx < 0) + return -EINVAL; + vidx = vlan_id / VLAN_GROUP_ARRAY_PART_LEN; array = vg->vlan_devices_arrays[pidx][vidx]; if (array != NULL) diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index bb7ec1a3915d..953405362795 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -36,7 +36,7 @@ struct vlan_info { struct rcu_head rcu; }; -static inline unsigned int vlan_proto_idx(__be16 proto) +static inline int vlan_proto_idx(__be16 proto) { switch (proto) { case htons(ETH_P_8021Q): @@ -44,8 +44,8 @@ static inline unsigned int vlan_proto_idx(__be16 proto) case htons(ETH_P_8021AD): return VLAN_PROTO_8021AD; default: - BUG(); - return 0; + WARN(1, "invalid VLAN protocol: 0x%04x\n", ntohs(proto)); + return -EINVAL; } } @@ -64,17 +64,24 @@ static inline struct net_device *vlan_group_get_device(struct vlan_group *vg, __be16 vlan_proto, u16 vlan_id) { - return __vlan_group_get_device(vg, vlan_proto_idx(vlan_proto), vlan_id); + int pidx = vlan_proto_idx(vlan_proto); + + if (pidx < 0) + return NULL; + + return __vlan_group_get_device(vg, pidx, vlan_id); } static inline void vlan_group_set_device(struct vlan_group *vg, __be16 vlan_proto, u16 vlan_id, struct net_device *dev) { + int pidx = vlan_proto_idx(vlan_proto); struct net_device **array; - if (!vg) + + if (!vg || pidx < 0) return; - array = vg->vlan_devices_arrays[vlan_proto_idx(vlan_proto)] + array = vg->vlan_devices_arrays[pidx] [vlan_id / VLAN_GROUP_ARRAY_PART_LEN]; array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] = dev; } diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index c0762a302162..8f528e783a6c 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -1023,7 +1023,7 @@ p9_fd_create_unix(struct p9_client *client, const char *addr, char *args) csocket = NULL; - if (addr == NULL) + if (!addr || !strlen(addr)) return -EINVAL; if (strlen(addr) >= UNIX_PATH_MAX) { diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index bc8807d9281f..f4fea28e05da 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -451,13 +451,13 @@ static int xen_9pfs_front_probe(struct xenbus_device *dev, char str[16]; BUILD_BUG_ON(XEN_9PFS_NUM_RINGS > 9); - sprintf(str, "ring-ref%u", i); + sprintf(str, "ring-ref%d", i); ret = xenbus_printf(xbt, dev->nodename, str, "%d", priv->rings[i].ref); if (ret) goto error_xenbus; - sprintf(str, "event-channel-%u", i); + sprintf(str, "event-channel-%d", i); ret = xenbus_printf(xbt, dev->nodename, str, "%u", priv->rings[i].evtchn); if (ret) diff --git a/net/Kconfig b/net/Kconfig index 3831206977a1..d6567162c1cf 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -434,7 +434,6 @@ config NET_SOCK_MSG config NET_DEVLINK bool default n - imply NET_DROP_MONITOR config PAGE_POOL bool diff --git a/net/atm/lec.c b/net/atm/lec.c index b570ef919c28..7226c784dbe0 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -954,9 +954,8 @@ static void *lec_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct lec_state *state = seq->private; - v = lec_get_idx(state, 1); - *pos += !!PTR_ERR(v); - return v; + ++*pos; + return lec_get_idx(state, 1); } static int lec_seq_show(struct seq_file *seq, void *v) @@ -1070,7 +1069,7 @@ module_exit(lane_module_cleanup); /* * LANE2: 3.1.3, LE_RESOLVE.request * Non force allocates memory and fills in *tlvs, fills in *sizeoftlvs. - * If sizeoftlvs == NULL the default TLVs associated with with this + * If sizeoftlvs == NULL the default TLVs associated with this * lec will be used. * If dst_mac == NULL, targetless LE_ARP will be sent */ diff --git a/net/atm/signaling.c b/net/atm/signaling.c index fbd0c5e7b299..5de06ab8ed75 100644 --- a/net/atm/signaling.c +++ b/net/atm/signaling.c @@ -52,7 +52,7 @@ static void modify_qos(struct atm_vcc *vcc, struct atmsvc_msg *msg) msg->type = as_okay; } /* - * Should probably just turn around the old skb. But the, the buffer + * Should probably just turn around the old skb. But then, the buffer * space accounting needs to follow the change too. Maybe later. */ while (!(skb = alloc_skb(sizeof(struct atmsvc_msg), GFP_KERNEL))) diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index a4faf5f904d9..206d0b424712 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -27,6 +27,7 @@ #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/pkt_sched.h> +#include <linux/prandom.h> #include <linux/printk.h> #include <linux/random.h> #include <linux/rculist.h> diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index d35aca0e969a..79a7dfc32e76 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -20,6 +20,7 @@ #include <linux/kref.h> #include <linux/netdevice.h> #include <linux/nl80211.h> +#include <linux/prandom.h> #include <linux/random.h> #include <linux/rculist.h> #include <linux/rcupdate.h> diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 717fe657561d..8c1148fc73d7 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -20,6 +20,7 @@ #include <linux/lockdep.h> #include <linux/mutex.h> #include <linux/netdevice.h> +#include <linux/prandom.h> #include <linux/random.h> #include <linux/rculist.h> #include <linux/rcupdate.h> diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index c350ab63cd54..ba0027d1f2df 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1863,7 +1863,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb, ret = queue_work(batadv_event_workqueue, &backbone_gw->report_work); - /* backbone_gw is unreferenced in the report work function function + /* backbone_gw is unreferenced in the report work function * if queue_work() call was successful */ if (!ret) diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 9fdbe3068153..9a47ef8b95c4 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -306,7 +306,7 @@ free: * set *skb to merged packet; 2) Packet is buffered: Return true and set *skb * to NULL; 3) Error: Return false and free skb. * - * Return: true when the packet is merged or buffered, false when skb is not not + * Return: true when the packet is merged or buffered, false when skb is not * used. */ bool batadv_frag_skb_buffer(struct sk_buff **skb, diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index fa06b51c0144..dad99641df2a 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -599,7 +599,7 @@ out: /* report to the other components the maximum amount of bytes that * batman-adv can send over the wire (without considering the payload * overhead). For example, this value is used by TT to compute the - * maximum local table table size + * maximum local table size */ atomic_set(&bat_priv->packet_size_max, min_mtu); @@ -977,23 +977,6 @@ static void batadv_hardif_remove_interface(struct batadv_hard_iface *hard_iface) } /** - * batadv_hardif_remove_interfaces() - Remove all hard interfaces - */ -void batadv_hardif_remove_interfaces(void) -{ - struct batadv_hard_iface *hard_iface, *hard_iface_tmp; - - rtnl_lock(); - list_for_each_entry_safe(hard_iface, hard_iface_tmp, - &batadv_hardif_list, list) { - list_del_rcu(&hard_iface->list); - batadv_hardif_generation++; - batadv_hardif_remove_interface(hard_iface); - } - rtnl_unlock(); -} - -/** * batadv_hard_if_event_softif() - Handle events for soft interfaces * @event: NETDEV_* event to handle * @net_dev: net_device which generated an event diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index bad2e50135e8..b1855d9d0b06 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -100,7 +100,6 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, struct net *net, const char *iface_name); void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface, enum batadv_hard_if_cleanup autodel); -void batadv_hardif_remove_interfaces(void); int batadv_hardif_min_mtu(struct net_device *soft_iface); void batadv_update_min_mtu(struct net_device *soft_iface); void batadv_hardif_release(struct kref *ref); diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 519c08c2cfba..70fee9b42e25 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -137,7 +137,6 @@ static void __exit batadv_exit(void) batadv_netlink_unregister(); rtnl_link_unregister(&batadv_link_ops); unregister_netdevice_notifier(&batadv_hard_if_notifier); - batadv_hardif_remove_interfaces(); flush_workqueue(batadv_event_workqueue); destroy_workqueue(batadv_event_workqueue); diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 0393bb9ed3d0..a47dc332d796 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 "2020.3" +#define BATADV_SOURCE_VERSION "2020.4" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index ca24a2e522b7..9af99c39b9fd 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -208,7 +208,7 @@ static u8 batadv_mcast_mla_rtr_flags_bridge_get(struct batadv_priv *bat_priv, return BATADV_MCAST_WANT_NO_RTR4 | BATADV_MCAST_WANT_NO_RTR6; /* TODO: ask the bridge if a multicast router is present (the bridge - * is capable of performing proper RFC4286 multicast multicast router + * is capable of performing proper RFC4286 multicast router * discovery) instead of searching for a ff02::2 listener here */ ret = br_multicast_list_adjacent(dev, &bridge_mcast_list); @@ -221,7 +221,7 @@ static u8 batadv_mcast_mla_rtr_flags_bridge_get(struct batadv_priv *bat_priv, * address here, only IPv6 ones */ if (br_ip_entry->addr.proto == htons(ETH_P_IPV6) && - ipv6_addr_is_ll_all_routers(&br_ip_entry->addr.u.ip6)) + ipv6_addr_is_ll_all_routers(&br_ip_entry->addr.dst.ip6)) flags &= ~BATADV_MCAST_WANT_NO_RTR6; list_del(&br_ip_entry->list); @@ -562,10 +562,10 @@ out: static void batadv_mcast_mla_br_addr_cpy(char *dst, const struct br_ip *src) { if (src->proto == htons(ETH_P_IP)) - ip_eth_mc_map(src->u.ip4, dst); + ip_eth_mc_map(src->dst.ip4, dst); #if IS_ENABLED(CONFIG_IPV6) else if (src->proto == htons(ETH_P_IPV6)) - ipv6_eth_mc_map(&src->u.ip6, dst); + ipv6_eth_mc_map(&src->dst.ip6, dst); #endif else eth_zero_addr(dst); @@ -609,11 +609,11 @@ static int batadv_mcast_mla_bridge_get(struct net_device *dev, continue; if (tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES && - ipv4_is_local_multicast(br_ip_entry->addr.u.ip4)) + ipv4_is_local_multicast(br_ip_entry->addr.dst.ip4)) continue; if (!(tvlv_flags & BATADV_MCAST_WANT_NO_RTR4) && - !ipv4_is_local_multicast(br_ip_entry->addr.u.ip4)) + !ipv4_is_local_multicast(br_ip_entry->addr.dst.ip4)) continue; } @@ -623,11 +623,11 @@ static int batadv_mcast_mla_bridge_get(struct net_device *dev, continue; if (tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES && - ipv6_addr_is_ll_all_nodes(&br_ip_entry->addr.u.ip6)) + ipv6_addr_is_ll_all_nodes(&br_ip_entry->addr.dst.ip6)) continue; if (!(tvlv_flags & BATADV_MCAST_WANT_NO_RTR6) && - IPV6_ADDR_MC_SCOPE(&br_ip_entry->addr.u.ip6) > + IPV6_ADDR_MC_SCOPE(&br_ip_entry->addr.dst.ip6) > IPV6_ADDR_SCOPE_LINKLOCAL) continue; } diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index dc193618a761..c7a55647b520 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -1350,7 +1350,7 @@ static void batadv_post_doit(const struct genl_ops *ops, struct sk_buff *skb, } } -static const struct genl_ops batadv_netlink_ops[] = { +static const struct genl_small_ops batadv_netlink_ops[] = { { .cmd = BATADV_CMD_GET_MESH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, @@ -1484,8 +1484,8 @@ struct genl_family batadv_netlink_family __ro_after_init = { .pre_doit = batadv_pre_doit, .post_doit = batadv_post_doit, .module = THIS_MODULE, - .ops = batadv_netlink_ops, - .n_ops = ARRAY_SIZE(batadv_netlink_ops), + .small_ops = batadv_netlink_ops, + .n_small_ops = ARRAY_SIZE(batadv_netlink_ops), .mcgrps = batadv_netlink_mcgrps, .n_mcgrps = ARRAY_SIZE(batadv_netlink_mcgrps), }; diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 48d707850f3e..61ddd6d709a0 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -26,8 +26,8 @@ #include <linux/lockdep.h> #include <linux/net.h> #include <linux/netdevice.h> +#include <linux/prandom.h> #include <linux/printk.h> -#include <linux/random.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/seq_file.h> @@ -250,7 +250,7 @@ static void batadv_nc_path_put(struct batadv_nc_path *nc_path) /** * batadv_nc_packet_free() - frees nc packet * @nc_packet: the nc packet to free - * @dropped: whether the packet is freed because is is dropped + * @dropped: whether the packet is freed because is dropped */ static void batadv_nc_packet_free(struct batadv_nc_packet *nc_packet, bool dropped) diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index d267b94800d6..87017332b567 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -461,7 +461,7 @@ int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb, /** * batadv_forw_packet_free() - free a forwarding packet * @forw_packet: The packet to free - * @dropped: whether the packet is freed because is is dropped + * @dropped: whether the packet is freed because is dropped * * This frees a forwarding packet and releases any resources it might * have claimed. diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index cdde943c1b83..82e7ca886605 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -648,7 +648,7 @@ static void batadv_softif_destroy_vlan(struct batadv_priv *bat_priv, /** * batadv_interface_add_vid() - ndo_add_vid API implementation * @dev: the netdev of the mesh interface - * @proto: protocol of the the vlan id + * @proto: protocol of the vlan id * @vid: identifier of the new vlan * * Set up all the internal structures for handling the new vlan on top of the @@ -706,7 +706,7 @@ static int batadv_interface_add_vid(struct net_device *dev, __be16 proto, /** * batadv_interface_kill_vid() - ndo_kill_vid API implementation * @dev: the netdev of the mesh interface - * @proto: protocol of the the vlan id + * @proto: protocol of the vlan id * @vid: identifier of the deleted vlan * * Destroy all the internal structures used to handle the vlan identified by vid diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index ed519efa3c36..965336a3b89d 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1492,7 +1492,7 @@ struct batadv_tp_vars { /** @unacked_lock: protect unacked_list */ spinlock_t unacked_lock; - /** @last_recv_time: time time (jiffies) a msg was received */ + /** @last_recv_time: time (jiffies) a msg was received */ unsigned long last_recv_time; /** @refcount: number of context where the object is used */ @@ -1996,7 +1996,7 @@ struct batadv_tt_change_node { */ struct batadv_tt_req_node { /** - * @addr: mac address address of the originator this request was sent to + * @addr: mac address of the originator this request was sent to */ u8 addr[ETH_ALEN]; diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index e2497d764e97..64e669acd42f 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -64,7 +64,6 @@ source "net/bluetooth/hidp/Kconfig" config BT_HS bool "Bluetooth High Speed (HS) features" depends on BT_BREDR - default y help Bluetooth High Speed includes support for off-loading Bluetooth connections via 802.11 (wifi) physical layer diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c index 26526be579c7..da7fd7c8c2dc 100644 --- a/net/bluetooth/a2mp.c +++ b/net/bluetooth/a2mp.c @@ -226,6 +226,9 @@ static int a2mp_discover_rsp(struct amp_mgr *mgr, struct sk_buff *skb, struct a2mp_info_req req; found = true; + + memset(&req, 0, sizeof(req)); + req.id = cl->id; a2mp_send(mgr, A2MP_GETINFO_REQ, __next_ident(mgr), sizeof(req), &req); @@ -305,6 +308,8 @@ static int a2mp_getinfo_req(struct amp_mgr *mgr, struct sk_buff *skb, if (!hdev || hdev->dev_type != HCI_AMP) { struct a2mp_info_rsp rsp; + memset(&rsp, 0, sizeof(rsp)); + rsp.id = req->id; rsp.status = A2MP_STATUS_INVALID_CTRL_ID; @@ -348,6 +353,8 @@ static int a2mp_getinfo_rsp(struct amp_mgr *mgr, struct sk_buff *skb, if (!ctrl) return -ENOMEM; + memset(&req, 0, sizeof(req)); + req.id = rsp->id; a2mp_send(mgr, A2MP_GETAMPASSOC_REQ, __next_ident(mgr), sizeof(req), &req); @@ -376,6 +383,8 @@ static int a2mp_getampassoc_req(struct amp_mgr *mgr, struct sk_buff *skb, struct a2mp_amp_assoc_rsp rsp; rsp.id = req->id; + memset(&rsp, 0, sizeof(rsp)); + if (tmp) { rsp.status = A2MP_STATUS_COLLISION_OCCURED; amp_mgr_put(tmp); @@ -464,7 +473,6 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, struct a2mp_cmd *hdr) { struct a2mp_physlink_req *req = (void *) skb->data; - struct a2mp_physlink_rsp rsp; struct hci_dev *hdev; struct hci_conn *hcon; @@ -475,6 +483,8 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, BT_DBG("local_id %d, remote_id %d", req->local_id, req->remote_id); + memset(&rsp, 0, sizeof(rsp)); + rsp.local_id = req->remote_id; rsp.remote_id = req->local_id; @@ -553,6 +563,8 @@ static int a2mp_discphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, BT_DBG("local_id %d remote_id %d", req->local_id, req->remote_id); + memset(&rsp, 0, sizeof(rsp)); + rsp.local_id = req->remote_id; rsp.remote_id = req->local_id; rsp.status = A2MP_STATUS_SUCCESS; @@ -675,6 +687,8 @@ static int a2mp_chan_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) if (err) { struct a2mp_cmd_rej rej; + memset(&rej, 0, sizeof(rej)); + rej.reason = cpu_to_le16(0); hdr = (void *) skb->data; @@ -898,6 +912,8 @@ void a2mp_send_getinfo_rsp(struct hci_dev *hdev) BT_DBG("%s mgr %p", hdev->name, mgr); + memset(&rsp, 0, sizeof(rsp)); + rsp.id = hdev->id; rsp.status = A2MP_STATUS_INVALID_CTRL_ID; @@ -995,6 +1011,8 @@ void a2mp_send_create_phy_link_rsp(struct hci_dev *hdev, u8 status) if (!mgr) return; + memset(&rsp, 0, sizeof(rsp)); + hs_hcon = hci_conn_hash_lookup_state(hdev, AMP_LINK, BT_CONNECT); if (!hs_hcon) { rsp.status = A2MP_STATUS_UNABLE_START_LINK_CREATION; @@ -1027,6 +1045,8 @@ void a2mp_discover_amp(struct l2cap_chan *chan) mgr->bredr_chan = chan; + memset(&req, 0, sizeof(req)); + req.mtu = cpu_to_le16(L2CAP_A2MP_DEFAULT_MTU); req.ext_feat = 0; a2mp_send(mgr, A2MP_DISCOVER_REQ, 1, sizeof(req), &req); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 9832f8445d43..d0c1024bf600 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1388,7 +1388,7 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) return 0; } -/* Encrypt the the link */ +/* Encrypt the link */ static void hci_conn_encrypt(struct hci_conn *conn) { BT_DBG("hcon %p", conn); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 68bfe57b6625..502552d6e9af 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -808,7 +808,7 @@ static int hci_init4_req(struct hci_request *req, unsigned long opt) * Delete Stored Link Key command. They are clearly indicating its * absence in the bit mask of supported commands. * - * Check the supported commands and only if the the command is marked + * Check the supported commands and only if the command is marked * as supported send it. If not supported assume that the controller * does not have actual support for stored link keys which makes this * command redundant anyway. @@ -2963,7 +2963,7 @@ int hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags, sizeof(adv_instance->scan_rsp_data)); } else { if (hdev->adv_instance_cnt >= hdev->le_num_of_adv_sets || - instance < 1 || instance > HCI_MAX_ADV_INSTANCES) + instance < 1 || instance > hdev->le_num_of_adv_sets) return -EOVERFLOW; adv_instance = kzalloc(sizeof(*adv_instance), GFP_KERNEL); @@ -3061,6 +3061,7 @@ static int free_adv_monitor(int id, void *ptr, void *data) idr_remove(&hdev->adv_monitors_idr, monitor->handle); hci_free_adv_monitor(monitor); + hdev->adv_monitors_cnt--; return 0; } @@ -3077,6 +3078,7 @@ int hci_remove_adv_monitor(struct hci_dev *hdev, u16 handle) idr_remove(&hdev->adv_monitors_idr, monitor->handle); hci_free_adv_monitor(monitor); + hdev->adv_monitors_cnt--; } else { /* Remove all monitors if handle is 0. */ idr_for_each(&hdev->adv_monitors_idr, &free_adv_monitor, hdev); @@ -3442,6 +3444,16 @@ void hci_copy_identity_address(struct hci_dev *hdev, bdaddr_t *bdaddr, } } +static void hci_suspend_clear_tasks(struct hci_dev *hdev) +{ + int i; + + for (i = 0; i < __SUSPEND_NUM_TASKS; i++) + clear_bit(i, hdev->suspend_tasks); + + wake_up(&hdev->suspend_wait_q); +} + static int hci_suspend_wait_event(struct hci_dev *hdev) { #define WAKE_COND \ @@ -3487,12 +3499,24 @@ static int hci_change_suspend_state(struct hci_dev *hdev, return hci_suspend_wait_event(hdev); } +static void hci_clear_wake_reason(struct hci_dev *hdev) +{ + hci_dev_lock(hdev); + + hdev->wake_reason = 0; + bacpy(&hdev->wake_addr, BDADDR_ANY); + hdev->wake_addr_type = 0; + + hci_dev_unlock(hdev); +} + static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action, void *data) { struct hci_dev *hdev = container_of(nb, struct hci_dev, suspend_notifier); int ret = 0; + u8 state = BT_RUNNING; /* If powering down, wait for completion. */ if (mgmt_powering_down(hdev)) { @@ -3513,15 +3537,27 @@ static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action, * - Second, program event filter/whitelist and enable scan */ ret = hci_change_suspend_state(hdev, BT_SUSPEND_DISCONNECT); + if (!ret) + state = BT_SUSPEND_DISCONNECT; /* Only configure whitelist if disconnect succeeded and wake * isn't being prevented. */ - if (!ret && !(hdev->prevent_wake && hdev->prevent_wake(hdev))) + if (!ret && !(hdev->prevent_wake && hdev->prevent_wake(hdev))) { ret = hci_change_suspend_state(hdev, BT_SUSPEND_CONFIGURE_WAKE); + if (!ret) + state = BT_SUSPEND_CONFIGURE_WAKE; + } + + hci_clear_wake_reason(hdev); + mgmt_suspending(hdev, state); + } else if (action == PM_POST_SUSPEND) { ret = hci_change_suspend_state(hdev, BT_RUNNING); + + mgmt_resuming(hdev, hdev->wake_reason, &hdev->wake_addr, + hdev->wake_addr_type); } done: @@ -3784,6 +3820,7 @@ void hci_unregister_dev(struct hci_dev *hdev) cancel_work_sync(&hdev->power_on); + hci_suspend_clear_tasks(hdev); unregister_pm_notifier(&hdev->suspend_notifier); cancel_work_sync(&hdev->suspend_prepare); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 4b7fc430793c..f04963914366 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -2569,7 +2569,6 @@ static void hci_inquiry_result_evt(struct hci_dev *hdev, struct sk_buff *skb) static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_conn_complete *ev = (void *) skb->data; - struct inquiry_entry *ie; struct hci_conn *conn; BT_DBG("%s", hdev->name); @@ -2578,13 +2577,19 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) conn = hci_conn_hash_lookup_ba(hdev, ev->link_type, &ev->bdaddr); if (!conn) { - /* Connection may not exist if auto-connected. Check the inquiry - * cache to see if we've already discovered this bdaddr before. - * If found and link is an ACL type, create a connection class + /* Connection may not exist if auto-connected. Check the bredr + * allowlist to see if this device is allowed to auto connect. + * If link is an ACL type, create a connection class * automatically. + * + * Auto-connect will only occur if the event filter is + * programmed with a given address. Right now, event filter is + * only used during suspend. */ - ie = hci_inquiry_cache_lookup(hdev, &ev->bdaddr); - if (ie && ev->link_type == ACL_LINK) { + if (ev->link_type == ACL_LINK && + hci_bdaddr_list_lookup_with_flags(&hdev->whitelist, + &ev->bdaddr, + BDADDR_BREDR)) { conn = hci_conn_add(hdev, ev->link_type, &ev->bdaddr, HCI_ROLE_SLAVE); if (!conn) { @@ -6012,6 +6017,75 @@ static bool hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode, return true; } +static void hci_store_wake_reason(struct hci_dev *hdev, u8 event, + struct sk_buff *skb) +{ + struct hci_ev_le_advertising_info *adv; + struct hci_ev_le_direct_adv_info *direct_adv; + struct hci_ev_le_ext_adv_report *ext_adv; + const struct hci_ev_conn_complete *conn_complete = (void *)skb->data; + const struct hci_ev_conn_request *conn_request = (void *)skb->data; + + hci_dev_lock(hdev); + + /* If we are currently suspended and this is the first BT event seen, + * save the wake reason associated with the event. + */ + if (!hdev->suspended || hdev->wake_reason) + goto unlock; + + /* Default to remote wake. Values for wake_reason are documented in the + * Bluez mgmt api docs. + */ + hdev->wake_reason = MGMT_WAKE_REASON_REMOTE_WAKE; + + /* Once configured for remote wakeup, we should only wake up for + * reconnections. It's useful to see which device is waking us up so + * keep track of the bdaddr of the connection event that woke us up. + */ + if (event == HCI_EV_CONN_REQUEST) { + bacpy(&hdev->wake_addr, &conn_complete->bdaddr); + hdev->wake_addr_type = BDADDR_BREDR; + } else if (event == HCI_EV_CONN_COMPLETE) { + bacpy(&hdev->wake_addr, &conn_request->bdaddr); + hdev->wake_addr_type = BDADDR_BREDR; + } else if (event == HCI_EV_LE_META) { + struct hci_ev_le_meta *le_ev = (void *)skb->data; + u8 subevent = le_ev->subevent; + u8 *ptr = &skb->data[sizeof(*le_ev)]; + u8 num_reports = *ptr; + + if ((subevent == HCI_EV_LE_ADVERTISING_REPORT || + subevent == HCI_EV_LE_DIRECT_ADV_REPORT || + subevent == HCI_EV_LE_EXT_ADV_REPORT) && + num_reports) { + adv = (void *)(ptr + 1); + direct_adv = (void *)(ptr + 1); + ext_adv = (void *)(ptr + 1); + + switch (subevent) { + case HCI_EV_LE_ADVERTISING_REPORT: + bacpy(&hdev->wake_addr, &adv->bdaddr); + hdev->wake_addr_type = adv->bdaddr_type; + break; + case HCI_EV_LE_DIRECT_ADV_REPORT: + bacpy(&hdev->wake_addr, &direct_adv->bdaddr); + hdev->wake_addr_type = direct_adv->bdaddr_type; + break; + case HCI_EV_LE_EXT_ADV_REPORT: + bacpy(&hdev->wake_addr, &ext_adv->bdaddr); + hdev->wake_addr_type = ext_adv->bdaddr_type; + break; + } + } + } else { + hdev->wake_reason = MGMT_WAKE_REASON_UNEXPECTED; + } + +unlock: + hci_dev_unlock(hdev); +} + void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_event_hdr *hdr = (void *) skb->data; @@ -6045,6 +6119,9 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) skb_pull(skb, HCI_EVENT_HDR_SIZE); + /* Store wake reason if we're suspended */ + hci_store_wake_reason(hdev, event, skb); + switch (event) { case HCI_EV_INQUIRY_COMPLETE: hci_inquiry_complete_evt(hdev, skb); diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index e0269192f2e5..6f12bab4d2fa 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -1027,6 +1027,9 @@ void hci_req_add_le_passive_scan(struct hci_request *req) } else if (hci_is_le_conn_scanning(hdev)) { window = hdev->le_scan_window_connect; interval = hdev->le_scan_int_connect; + } else if (hci_is_adv_monitoring(hdev)) { + window = hdev->le_scan_window_adv_monitor; + interval = hdev->le_scan_int_adv_monitor; } else { window = hdev->le_scan_window; interval = hdev->le_scan_interval; @@ -1111,6 +1114,53 @@ static void hci_req_config_le_suspend_scan(struct hci_request *req) set_bit(SUSPEND_SCAN_ENABLE, req->hdev->suspend_tasks); } +static void cancel_adv_timeout(struct hci_dev *hdev) +{ + if (hdev->adv_instance_timeout) { + hdev->adv_instance_timeout = 0; + cancel_delayed_work(&hdev->adv_instance_expire); + } +} + +/* This function requires the caller holds hdev->lock */ +static void hci_suspend_adv_instances(struct hci_request *req) +{ + bt_dev_dbg(req->hdev, "Suspending advertising instances"); + + /* Call to disable any advertisements active on the controller. + * This will succeed even if no advertisements are configured. + */ + __hci_req_disable_advertising(req); + + /* If we are using software rotation, pause the loop */ + if (!ext_adv_capable(req->hdev)) + cancel_adv_timeout(req->hdev); +} + +/* This function requires the caller holds hdev->lock */ +static void hci_resume_adv_instances(struct hci_request *req) +{ + struct adv_info *adv; + + bt_dev_dbg(req->hdev, "Resuming advertising instances"); + + if (ext_adv_capable(req->hdev)) { + /* Call for each tracked instance to be re-enabled */ + list_for_each_entry(adv, &req->hdev->adv_instances, list) { + __hci_req_enable_ext_advertising(req, + adv->instance); + } + + } else { + /* Schedule for most recent instance to be restarted and begin + * the software rotation loop + */ + __hci_req_schedule_adv_instance(req, + req->hdev->cur_adv_instance, + true); + } +} + static void suspend_req_complete(struct hci_dev *hdev, u8 status, u16 opcode) { bt_dev_dbg(hdev, "Request complete opcode=0x%x, status=0x%x", opcode, @@ -1153,7 +1203,7 @@ void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next) hdev->discovery_paused = true; hdev->discovery_old_state = old_state; - /* Stop advertising */ + /* Stop directed advertising */ old_state = hci_dev_test_flag(hdev, HCI_ADVERTISING); if (old_state) { set_bit(SUSPEND_PAUSE_ADVERTISING, hdev->suspend_tasks); @@ -1162,6 +1212,10 @@ void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next) &hdev->discov_off, 0); } + /* Pause other advertisements */ + if (hdev->adv_instance_cnt) + hci_suspend_adv_instances(&req); + hdev->advertising_paused = true; hdev->advertising_old_state = old_state; /* Disable page scan */ @@ -1212,7 +1266,7 @@ void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next) /* Reset passive/background scanning to normal */ hci_req_config_le_suspend_scan(&req); - /* Unpause advertising */ + /* Unpause directed advertising */ hdev->advertising_paused = false; if (hdev->advertising_old_state) { set_bit(SUSPEND_UNPAUSE_ADVERTISING, @@ -1223,6 +1277,10 @@ void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next) hdev->advertising_old_state = 0; } + /* Resume other advertisements */ + if (hdev->adv_instance_cnt) + hci_resume_adv_instances(&req); + /* Unpause discovery */ hdev->discovery_paused = false; if (hdev->discovery_old_state != DISCOVERY_STOPPED && @@ -1533,11 +1591,14 @@ void __hci_req_update_scan_rsp_data(struct hci_request *req, u8 instance) memset(&cp, 0, sizeof(cp)); - if (instance) + /* Extended scan response data doesn't allow a response to be + * set if the instance isn't scannable. + */ + if (get_adv_instance_scan_rsp_len(hdev, instance)) len = create_instance_scan_rsp_data(hdev, instance, cp.data); else - len = create_default_scan_rsp_data(hdev, cp.data); + len = 0; if (hdev->scan_rsp_data_len == len && !memcmp(cp.data, hdev->scan_rsp_data, len)) @@ -1824,7 +1885,13 @@ int hci_get_random_address(struct hci_dev *hdev, bool require_privacy, if (use_rpa) { int to; - *own_addr_type = ADDR_LE_DEV_RANDOM; + /* If Controller supports LL Privacy use own address type is + * 0x03 + */ + if (use_ll_privacy(hdev)) + *own_addr_type = ADDR_LE_DEV_RANDOM_RESOLVED; + else + *own_addr_type = ADDR_LE_DEV_RANDOM; if (adv_instance) { if (!adv_instance->rpa_expired && @@ -2183,14 +2250,6 @@ int __hci_req_schedule_adv_instance(struct hci_request *req, u8 instance, return 0; } -static void cancel_adv_timeout(struct hci_dev *hdev) -{ - if (hdev->adv_instance_timeout) { - hdev->adv_instance_timeout = 0; - cancel_delayed_work(&hdev->adv_instance_expire); - } -} - /* For a single instance: * - force == true: The instance will be removed even when its remaining * lifetime is not zero. diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index ade83e224567..1ab27b90ddcb 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -7301,9 +7301,10 @@ static int l2cap_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb) goto drop; } - if ((chan->mode == L2CAP_MODE_ERTM || - chan->mode == L2CAP_MODE_STREAMING) && sk_filter(chan->data, skb)) - goto drop; + if (chan->ops->filter) { + if (chan->ops->filter(chan, skb)) + goto drop; + } if (!control->sframe) { int err; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index e1a3e66b1754..f1b1edd0b697 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1521,8 +1521,6 @@ static void l2cap_sock_teardown_cb(struct l2cap_chan *chan, int err) parent = bt_sk(sk)->parent; - sock_set_flag(sk, SOCK_ZAPPED); - switch (chan->state) { case BT_OPEN: case BT_BOUND: @@ -1549,8 +1547,11 @@ static void l2cap_sock_teardown_cb(struct l2cap_chan *chan, int err) break; } - release_sock(sk); + + /* Only zap after cleanup to avoid use after free race */ + sock_set_flag(sk, SOCK_ZAPPED); + } static void l2cap_sock_state_change_cb(struct l2cap_chan *chan, int state, @@ -1663,6 +1664,19 @@ static void l2cap_sock_suspend_cb(struct l2cap_chan *chan) sk->sk_state_change(sk); } +static int l2cap_sock_filter(struct l2cap_chan *chan, struct sk_buff *skb) +{ + struct sock *sk = chan->data; + + switch (chan->mode) { + case L2CAP_MODE_ERTM: + case L2CAP_MODE_STREAMING: + return sk_filter(sk, skb); + } + + return 0; +} + static const struct l2cap_ops l2cap_chan_ops = { .name = "L2CAP Socket Interface", .new_connection = l2cap_sock_new_connection_cb, @@ -1678,6 +1692,7 @@ static const struct l2cap_ops l2cap_chan_ops = { .get_sndtimeo = l2cap_sock_get_sndtimeo_cb, .get_peer_pid = l2cap_sock_get_peer_pid_cb, .alloc_skb = l2cap_sock_alloc_skb_cb, + .filter = l2cap_sock_filter, }; static void l2cap_sock_destruct(struct sock *sk) diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 5bbe71002fb9..12d7b368b428 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -163,6 +163,8 @@ static const u16 mgmt_events[] = { MGMT_EV_PHY_CONFIGURATION_CHANGED, MGMT_EV_EXP_FEATURE_CHANGED, MGMT_EV_DEVICE_FLAGS_CHANGED, + MGMT_EV_CONTROLLER_SUSPEND, + MGMT_EV_CONTROLLER_RESUME, }; static const u16 mgmt_untrusted_commands[] = { @@ -782,7 +784,8 @@ static u32 get_supported_settings(struct hci_dev *hdev) if (lmp_ssp_capable(hdev)) { settings |= MGMT_SETTING_SSP; - settings |= MGMT_SETTING_HS; + if (IS_ENABLED(CONFIG_BT_HS)) + settings |= MGMT_SETTING_HS; } if (lmp_sc_capable(hdev)) @@ -1815,6 +1818,10 @@ static int set_hs(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) bt_dev_dbg(hdev, "sock %p", sk); + if (!IS_ENABLED(CONFIG_BT_HS)) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, + MGMT_STATUS_NOT_SUPPORTED); + status = mgmt_bredr_support(hdev); if (status) return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, status); @@ -4157,7 +4164,7 @@ static int read_adv_mon_features(struct sock *sk, struct hci_dev *hdev, { struct adv_monitor *monitor = NULL; struct mgmt_rp_read_adv_monitor_features *rp = NULL; - int handle; + int handle, err; size_t rp_size = 0; __u32 supported = 0; __u16 num_handles = 0; @@ -4192,9 +4199,13 @@ static int read_adv_mon_features(struct sock *sk, struct hci_dev *hdev, if (num_handles) memcpy(&rp->handles, &handles, (num_handles * sizeof(u16))); - return mgmt_cmd_complete(sk, hdev->id, - MGMT_OP_READ_ADV_MONITOR_FEATURES, - MGMT_STATUS_SUCCESS, rp, rp_size); + err = mgmt_cmd_complete(sk, hdev->id, + MGMT_OP_READ_ADV_MONITOR_FEATURES, + MGMT_STATUS_SUCCESS, rp, rp_size); + + kfree(rp); + + return err; } static int add_adv_patterns_monitor(struct sock *sk, struct hci_dev *hdev, @@ -7202,6 +7213,8 @@ static u32 get_supported_adv_flags(struct hci_dev *hdev) if (ext_adv_capable(hdev)) { flags |= MGMT_ADV_FLAG_SEC_1M; + flags |= MGMT_ADV_FLAG_HW_OFFLOAD; + flags |= MGMT_ADV_FLAG_CAN_SET_TX_POWER; if (hdev->le_features[1] & HCI_LE_PHY_2M) flags |= MGMT_ADV_FLAG_SEC_2M; @@ -7250,7 +7263,7 @@ static int read_adv_features(struct sock *sk, struct hci_dev *hdev, rp->supported_flags = cpu_to_le32(supported_flags); rp->max_adv_data_len = HCI_MAX_AD_LENGTH; rp->max_scan_rsp_len = HCI_MAX_AD_LENGTH; - rp->max_instances = HCI_MAX_ADV_INSTANCES; + rp->max_instances = hdev->le_num_of_adv_sets; rp->num_instances = hdev->adv_instance_cnt; instance = rp->instance; @@ -7446,7 +7459,7 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev, return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING, MGMT_STATUS_NOT_SUPPORTED); - if (cp->instance < 1 || cp->instance > HCI_MAX_ADV_INSTANCES) + if (cp->instance < 1 || cp->instance > hdev->le_num_of_adv_sets) return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING, MGMT_STATUS_INVALID_PARAMS); @@ -7699,7 +7712,7 @@ static int get_adv_size_info(struct sock *sk, struct hci_dev *hdev, return mgmt_cmd_status(sk, hdev->id, MGMT_OP_GET_ADV_SIZE_INFO, MGMT_STATUS_REJECTED); - if (cp->instance < 1 || cp->instance > HCI_MAX_ADV_INSTANCES) + if (cp->instance < 1 || cp->instance > hdev->le_num_of_adv_sets) return mgmt_cmd_status(sk, hdev->id, MGMT_OP_GET_ADV_SIZE_INFO, MGMT_STATUS_INVALID_PARAMS); @@ -8262,6 +8275,10 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, ev.addr.type = link_to_bdaddr(link_type, addr_type); ev.reason = reason; + /* Report disconnects due to suspend */ + if (hdev->suspended) + ev.reason = MGMT_DEV_DISCONN_LOCAL_HOST_SUSPEND; + mgmt_event(MGMT_EV_DEVICE_DISCONNECTED, hdev, &ev, sizeof(ev), sk); if (sk) @@ -8868,6 +8885,30 @@ void mgmt_discovering(struct hci_dev *hdev, u8 discovering) mgmt_event(MGMT_EV_DISCOVERING, hdev, &ev, sizeof(ev), NULL); } +void mgmt_suspending(struct hci_dev *hdev, u8 state) +{ + struct mgmt_ev_controller_suspend ev; + + ev.suspend_state = state; + mgmt_event(MGMT_EV_CONTROLLER_SUSPEND, hdev, &ev, sizeof(ev), NULL); +} + +void mgmt_resuming(struct hci_dev *hdev, u8 reason, bdaddr_t *bdaddr, + u8 addr_type) +{ + struct mgmt_ev_controller_resume ev; + + ev.wake_reason = reason; + if (bdaddr) { + bacpy(&ev.addr.bdaddr, bdaddr); + ev.addr.type = addr_type; + } else { + memset(&ev.addr, 0, sizeof(ev.addr)); + } + + mgmt_event(MGMT_EV_CONTROLLER_RESUME, hdev, &ev, sizeof(ev), NULL); +} + static struct hci_mgmt_chan chan = { .channel = HCI_CHANNEL_CONTROL, .handler_count = ARRAY_SIZE(mgmt_handlers), diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index dcf7f96ff417..79ffcdef0b7a 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -1001,6 +1001,12 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, err = -EFAULT; break; + case BT_SNDMTU: + case BT_RCVMTU: + if (put_user(sco_pi(sk)->conn->mtu, (u32 __user *)optval)) + err = -EFAULT; + break; + default: err = -ENOPROTOOPT; break; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index a66f211726e7..c1c30a9f76f3 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -11,6 +11,7 @@ #include <net/sock.h> #include <net/tcp.h> #include <linux/error-injection.h> +#include <linux/smp.h> #define CREATE_TRACE_POINTS #include <trace/events/bpf_test_run.h> @@ -204,6 +205,9 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog, int b = 2, err = -EFAULT; u32 retval = 0; + if (kattr->test.flags || kattr->test.cpu) + return -EINVAL; + switch (prog->expected_attach_type) { case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: @@ -236,6 +240,84 @@ out: return err; } +struct bpf_raw_tp_test_run_info { + struct bpf_prog *prog; + void *ctx; + u32 retval; +}; + +static void +__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); + rcu_read_unlock(); +} + +int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + void __user *ctx_in = u64_to_user_ptr(kattr->test.ctx_in); + __u32 ctx_size_in = kattr->test.ctx_size_in; + struct bpf_raw_tp_test_run_info info; + int cpu = kattr->test.cpu, err = 0; + int current_cpu; + + /* doesn't support data_in/out, ctx_out, duration, or repeat */ + if (kattr->test.data_in || kattr->test.data_out || + kattr->test.ctx_out || kattr->test.duration || + kattr->test.repeat) + return -EINVAL; + + if (ctx_size_in < prog->aux->max_ctx_offset) + return -EINVAL; + + if ((kattr->test.flags & BPF_F_TEST_RUN_ON_CPU) == 0 && cpu != 0) + return -EINVAL; + + if (ctx_size_in) { + info.ctx = kzalloc(ctx_size_in, GFP_USER); + if (!info.ctx) + return -ENOMEM; + if (copy_from_user(info.ctx, ctx_in, ctx_size_in)) { + err = -EFAULT; + goto out; + } + } else { + info.ctx = NULL; + } + + info.prog = prog; + + current_cpu = get_cpu(); + if ((kattr->test.flags & BPF_F_TEST_RUN_ON_CPU) == 0 || + cpu == current_cpu) { + __bpf_prog_test_run_raw_tp(&info); + } else if (cpu >= nr_cpu_ids || !cpu_online(cpu)) { + /* smp_call_function_single() also checks cpu_online() + * after csd_lock(). However, since cpu is from user + * space, let's do an extra quick check to filter out + * invalid value before smp_call_function_single(). + */ + err = -ENXIO; + } else { + err = smp_call_function_single(cpu, __bpf_prog_test_run_raw_tp, + &info, 1); + } + put_cpu(); + + if (!err && + copy_to_user(&uattr->test.retval, &info.retval, sizeof(u32))) + err = -EFAULT; + +out: + kfree(info.ctx); + return err; +} + static void *bpf_ctx_init(const union bpf_attr *kattr, u32 max_size) { void __user *data_in = u64_to_user_ptr(kattr->test.ctx_in); @@ -410,6 +492,9 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, void *data; int ret; + if (kattr->test.flags || kattr->test.cpu) + return -EINVAL; + data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN, SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); if (IS_ERR(data)) @@ -607,6 +692,9 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR) return -EINVAL; + if (kattr->test.flags || kattr->test.cpu) + return -EINVAL; + if (size < ETH_HLEN) return -EINVAL; diff --git a/net/bpfilter/Kconfig b/net/bpfilter/Kconfig index 73d0b12789f1..8ad0233ce497 100644 --- a/net/bpfilter/Kconfig +++ b/net/bpfilter/Kconfig @@ -2,6 +2,7 @@ menuconfig BPFILTER bool "BPF based packet filtering framework (BPFILTER)" depends on NET && BPF && INET + select USERMODE_DRIVER help This builds experimental bpfilter framework that is aiming to provide netfilter compatible functionality via BPF diff --git a/net/bridge/br.c b/net/bridge/br.c index b6fe30e3768f..401eeb9142eb 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -183,6 +183,11 @@ static int br_switchdev_event(struct notifier_block *unused, br_fdb_offloaded_set(br, p, fdb_info->addr, fdb_info->vid, fdb_info->offloaded); break; + case SWITCHDEV_FDB_FLUSH_TO_BRIDGE: + fdb_info = ptr; + /* Don't delete static entries */ + br_fdb_delete_by_port(br, p, fdb_info->vid, 0); + break; } out: diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 9a2fb4aa1a10..6f742fee874a 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -206,27 +206,8 @@ static void br_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct net_bridge *br = netdev_priv(dev); - struct pcpu_sw_netstats tmp, sum = { 0 }; - unsigned int cpu; - - for_each_possible_cpu(cpu) { - unsigned int start; - const struct pcpu_sw_netstats *bstats - = per_cpu_ptr(br->stats, cpu); - do { - start = u64_stats_fetch_begin_irq(&bstats->syncp); - memcpy(&tmp, bstats, sizeof(tmp)); - } while (u64_stats_fetch_retry_irq(&bstats->syncp, start)); - sum.tx_bytes += tmp.tx_bytes; - sum.tx_packets += tmp.tx_packets; - sum.rx_bytes += tmp.rx_bytes; - sum.rx_packets += tmp.rx_packets; - } - stats->tx_bytes = sum.tx_bytes; - stats->tx_packets = sum.tx_packets; - stats->rx_bytes = sum.rx_bytes; - stats->rx_packets = sum.rx_packets; + dev_fetch_sw_netstats(stats, br->stats); } static int br_change_mtu(struct net_device *dev, int new_mtu) diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 7629b63f6f30..e28ffadd1371 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -274,14 +274,23 @@ void br_multicast_flood(struct net_bridge_mdb_entry *mdst, 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 = rcu_dereference(hlist_first_rcu(&br->router_list)); - p = mdst ? rcu_dereference(mdst->ports) : NULL; + if (mdst) { + p = rcu_dereference(mdst->ports); + if (br_multicast_should_handle_mode(br, mdst->addr.proto) && + br_multicast_is_star_g(&mdst->addr)) + allow_mode_include = false; + } else { + p = NULL; + } + while (p || rp) { struct net_bridge_port *port, *lport, *rport; - lport = p ? p->port : NULL; + lport = p ? p->key.port : NULL; rport = hlist_entry_safe(rp, struct net_bridge_port, rlist); if ((unsigned long)lport > (unsigned long)rport) { @@ -292,6 +301,10 @@ void br_multicast_flood(struct net_bridge_mdb_entry *mdst, local_orig); goto delivered; } + if ((!allow_mode_include && + p->filter_mode == MCAST_INCLUDE) || + (p->flags & MDB_PG_FLAGS_BLOCKED)) + goto delivered; } else { port = rport; } diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c index 5e71fc8b826f..2db800fc27ca 100644 --- a/net/bridge/br_ioctl.c +++ b/net/bridge/br_ioctl.c @@ -103,7 +103,7 @@ static int add_del_if(struct net_bridge *br, int ifindex, int isadd) /* * Legacy ioctl's through SIOCDEVPRIVATE - * This interface is deprecated because it was too difficult to + * 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) diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index da5ed4cf9233..e15bab19a012 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -62,25 +62,96 @@ static void __mdb_entry_fill_flags(struct br_mdb_entry *e, unsigned char flags) e->flags |= MDB_FLAGS_OFFLOAD; if (flags & MDB_PG_FLAGS_FAST_LEAVE) e->flags |= MDB_FLAGS_FAST_LEAVE; + if (flags & MDB_PG_FLAGS_STAR_EXCL) + e->flags |= MDB_FLAGS_STAR_EXCL; + if (flags & MDB_PG_FLAGS_BLOCKED) + e->flags |= MDB_FLAGS_BLOCKED; } -static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip) +static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip, + struct nlattr **mdb_attrs) { memset(ip, 0, sizeof(struct br_ip)); ip->vid = entry->vid; ip->proto = entry->addr.proto; - if (ip->proto == htons(ETH_P_IP)) - ip->u.ip4 = entry->addr.u.ip4; + switch (ip->proto) { + case htons(ETH_P_IP): + ip->dst.ip4 = entry->addr.u.ip4; + if (mdb_attrs && mdb_attrs[MDBE_ATTR_SOURCE]) + ip->src.ip4 = nla_get_in_addr(mdb_attrs[MDBE_ATTR_SOURCE]); + break; #if IS_ENABLED(CONFIG_IPV6) - else - ip->u.ip6 = entry->addr.u.ip6; + case htons(ETH_P_IPV6): + ip->dst.ip6 = entry->addr.u.ip6; + if (mdb_attrs && mdb_attrs[MDBE_ATTR_SOURCE]) + ip->src.ip6 = nla_get_in6_addr(mdb_attrs[MDBE_ATTR_SOURCE]); + break; +#endif + } + +} + +static int __mdb_fill_srcs(struct sk_buff *skb, + struct net_bridge_port_group *p) +{ + struct net_bridge_group_src *ent; + struct nlattr *nest, *nest_ent; + + if (hlist_empty(&p->src_list)) + return 0; + + nest = nla_nest_start(skb, MDBA_MDB_EATTR_SRC_LIST); + if (!nest) + return -EMSGSIZE; + + hlist_for_each_entry_rcu(ent, &p->src_list, node, + lockdep_is_held(&p->key.port->br->multicast_lock)) { + nest_ent = nla_nest_start(skb, MDBA_MDB_SRCLIST_ENTRY); + if (!nest_ent) + goto out_cancel_err; + switch (ent->addr.proto) { + case htons(ETH_P_IP): + if (nla_put_in_addr(skb, MDBA_MDB_SRCATTR_ADDRESS, + ent->addr.src.ip4)) { + nla_nest_cancel(skb, nest_ent); + goto out_cancel_err; + } + break; +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + if (nla_put_in6_addr(skb, MDBA_MDB_SRCATTR_ADDRESS, + &ent->addr.src.ip6)) { + nla_nest_cancel(skb, nest_ent); + goto out_cancel_err; + } + break; #endif + default: + nla_nest_cancel(skb, nest_ent); + continue; + } + if (nla_put_u32(skb, MDBA_MDB_SRCATTR_TIMER, + br_timer_value(&ent->timer))) { + nla_nest_cancel(skb, nest_ent); + goto out_cancel_err; + } + nla_nest_end(skb, nest_ent); + } + + nla_nest_end(skb, nest); + + return 0; + +out_cancel_err: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; } static int __mdb_fill_info(struct sk_buff *skb, struct net_bridge_mdb_entry *mp, struct net_bridge_port_group *p) { + bool dump_srcs_mode = false; struct timer_list *mtimer; struct nlattr *nest_ent; struct br_mdb_entry e; @@ -89,7 +160,7 @@ static int __mdb_fill_info(struct sk_buff *skb, memset(&e, 0, sizeof(e)); if (p) { - ifindex = p->port->dev->ifindex; + ifindex = p->key.port->dev->ifindex; mtimer = &p->timer; flags = p->flags; } else { @@ -101,10 +172,10 @@ static int __mdb_fill_info(struct sk_buff *skb, e.ifindex = ifindex; e.vid = mp->addr.vid; if (mp->addr.proto == htons(ETH_P_IP)) - e.addr.u.ip4 = mp->addr.u.ip4; + e.addr.u.ip4 = mp->addr.dst.ip4; #if IS_ENABLED(CONFIG_IPV6) if (mp->addr.proto == htons(ETH_P_IPV6)) - e.addr.u.ip6 = mp->addr.u.ip6; + e.addr.u.ip6 = mp->addr.dst.ip6; #endif e.addr.proto = mp->addr.proto; nest_ent = nla_nest_start_noflag(skb, @@ -115,19 +186,53 @@ static int __mdb_fill_info(struct sk_buff *skb, if (nla_put_nohdr(skb, sizeof(e), &e) || nla_put_u32(skb, MDBA_MDB_EATTR_TIMER, - br_timer_value(mtimer))) { - nla_nest_cancel(skb, nest_ent); - return -EMSGSIZE; + br_timer_value(mtimer))) + goto nest_err; + + switch (mp->addr.proto) { + case htons(ETH_P_IP): + dump_srcs_mode = !!(mp->br->multicast_igmp_version == 3); + if (mp->addr.src.ip4) { + if (nla_put_in_addr(skb, MDBA_MDB_EATTR_SOURCE, + mp->addr.src.ip4)) + goto nest_err; + break; + } + break; +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + dump_srcs_mode = !!(mp->br->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)) + goto nest_err; + break; + } + break; +#endif + } + if (p) { + if (nla_put_u8(skb, MDBA_MDB_EATTR_RTPROT, p->rt_protocol)) + goto nest_err; + if (dump_srcs_mode && + (__mdb_fill_srcs(skb, p) || + nla_put_u8(skb, MDBA_MDB_EATTR_GROUP_MODE, + p->filter_mode))) + goto nest_err; } nla_nest_end(skb, nest_ent); return 0; + +nest_err: + nla_nest_cancel(skb, nest_ent); + return -EMSGSIZE; } static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev) { - int idx = 0, s_idx = cb->args[1], err = 0; + int idx = 0, s_idx = cb->args[1], err = 0, pidx = 0, s_pidx = cb->args[2]; struct net_bridge *br = netdev_priv(dev); struct net_bridge_mdb_entry *mp; struct nlattr *nest, *nest2; @@ -152,7 +257,7 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, break; } - if (mp->host_joined) { + if (!s_pidx && mp->host_joined) { err = __mdb_fill_info(skb, mp, NULL); if (err) { nla_nest_cancel(skb, nest2); @@ -162,15 +267,21 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, for (pp = &mp->ports; (p = rcu_dereference(*pp)) != NULL; pp = &p->next) { - if (!p->port) + if (!p->key.port) continue; + if (pidx < s_pidx) + goto skip_pg; err = __mdb_fill_info(skb, mp, p); if (err) { - nla_nest_cancel(skb, nest2); + nla_nest_end(skb, nest2); goto out; } +skip_pg: + pidx++; } + pidx = 0; + s_pidx = 0; nla_nest_end(skb, nest2); skip: idx++; @@ -178,6 +289,7 @@ skip: out: cb->args[1] = idx; + cb->args[2] = pidx; nla_nest_end(skb, nest); return err; } @@ -263,14 +375,15 @@ out: static int nlmsg_populate_mdb_fill(struct sk_buff *skb, struct net_device *dev, - struct br_mdb_entry *entry, u32 pid, - u32 seq, int type, unsigned int flags) + struct net_bridge_mdb_entry *mp, + struct net_bridge_port_group *pg, + int type) { struct nlmsghdr *nlh; struct br_port_msg *bpm; struct nlattr *nest, *nest2; - nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), 0); + nlh = nlmsg_put(skb, 0, 0, type, sizeof(*bpm), 0); if (!nlh) return -EMSGSIZE; @@ -285,7 +398,7 @@ static int nlmsg_populate_mdb_fill(struct sk_buff *skb, if (nest2 == NULL) goto end; - if (nla_put(skb, MDBA_MDB_ENTRY_INFO, sizeof(*entry), entry)) + if (__mdb_fill_info(skb, mp, pg)) goto end; nla_nest_end(skb, nest2); @@ -300,10 +413,58 @@ cancel: return -EMSGSIZE; } -static inline size_t rtnl_mdb_nlmsg_size(void) +static size_t rtnl_mdb_nlmsg_size(struct net_bridge_port_group *pg) { - return NLMSG_ALIGN(sizeof(struct br_port_msg)) - + nla_total_size(sizeof(struct br_mdb_entry)); + size_t nlmsg_size = NLMSG_ALIGN(sizeof(struct br_port_msg)) + + nla_total_size(sizeof(struct br_mdb_entry)) + + nla_total_size(sizeof(u32)); + struct net_bridge_group_src *ent; + size_t addr_size = 0; + + if (!pg) + goto out; + + /* MDBA_MDB_EATTR_RTPROT */ + nlmsg_size += nla_total_size(sizeof(u8)); + + switch (pg->key.addr.proto) { + case htons(ETH_P_IP): + /* 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) + goto out; + addr_size = sizeof(__be32); + break; +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + /* 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) + goto out; + addr_size = sizeof(struct in6_addr); + break; +#endif + } + + /* MDBA_MDB_EATTR_GROUP_MODE */ + nlmsg_size += nla_total_size(sizeof(u8)); + + /* MDBA_MDB_EATTR_SRC_LIST nested attr */ + if (!hlist_empty(&pg->src_list)) + nlmsg_size += nla_total_size(0); + + hlist_for_each_entry(ent, &pg->src_list, node) { + /* MDBA_MDB_SRCLIST_ENTRY nested attr + + * MDBA_MDB_SRCATTR_ADDRESS + MDBA_MDB_SRCATTR_TIMER + */ + nlmsg_size += nla_total_size(0) + + nla_total_size(addr_size) + + nla_total_size(sizeof(u32)); + } +out: + return nlmsg_size; } struct br_mdb_complete_info { @@ -329,7 +490,7 @@ static void br_mdb_complete(struct net_device *dev, int err, void *priv) goto out; for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { - if (p->port != port) + if (p->key.port != port) continue; p->flags |= MDB_PG_FLAGS_OFFLOAD; } @@ -341,21 +502,22 @@ err: static void br_mdb_switchdev_host_port(struct net_device *dev, struct net_device *lower_dev, - struct br_mdb_entry *entry, int type) + struct net_bridge_mdb_entry *mp, + int type) { struct switchdev_obj_port_mdb mdb = { .obj = { .id = SWITCHDEV_OBJ_ID_HOST_MDB, .flags = SWITCHDEV_F_DEFER, }, - .vid = entry->vid, + .vid = mp->addr.vid, }; - if (entry->addr.proto == htons(ETH_P_IP)) - ip_eth_mc_map(entry->addr.u.ip4, mdb.addr); + if (mp->addr.proto == htons(ETH_P_IP)) + ip_eth_mc_map(mp->addr.dst.ip4, mdb.addr); #if IS_ENABLED(CONFIG_IPV6) else - ipv6_eth_mc_map(&entry->addr.u.ip6, mdb.addr); + ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb.addr); #endif mdb.obj.orig_dev = dev; @@ -370,17 +532,19 @@ static void br_mdb_switchdev_host_port(struct net_device *dev, } static void br_mdb_switchdev_host(struct net_device *dev, - struct br_mdb_entry *entry, int type) + struct net_bridge_mdb_entry *mp, int type) { struct net_device *lower_dev; struct list_head *iter; netdev_for_each_lower_dev(dev, lower_dev, iter) - br_mdb_switchdev_host_port(dev, lower_dev, entry, type); + br_mdb_switchdev_host_port(dev, lower_dev, mp, type); } -static void __br_mdb_notify(struct net_device *dev, struct net_bridge_port *p, - struct br_mdb_entry *entry, int type) +void br_mdb_notify(struct net_device *dev, + struct net_bridge_mdb_entry *mp, + struct net_bridge_port_group *pg, + int type) { struct br_mdb_complete_info *complete_info; struct switchdev_obj_port_mdb mdb = { @@ -388,44 +552,45 @@ static void __br_mdb_notify(struct net_device *dev, struct net_bridge_port *p, .id = SWITCHDEV_OBJ_ID_PORT_MDB, .flags = SWITCHDEV_F_DEFER, }, - .vid = entry->vid, + .vid = mp->addr.vid, }; - struct net_device *port_dev; struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOBUFS; - port_dev = __dev_get_by_index(net, entry->ifindex); - if (entry->addr.proto == htons(ETH_P_IP)) - ip_eth_mc_map(entry->addr.u.ip4, mdb.addr); + if (pg) { + if (mp->addr.proto == htons(ETH_P_IP)) + ip_eth_mc_map(mp->addr.dst.ip4, mdb.addr); #if IS_ENABLED(CONFIG_IPV6) - else - ipv6_eth_mc_map(&entry->addr.u.ip6, mdb.addr); + else + ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb.addr); #endif - - mdb.obj.orig_dev = port_dev; - if (p && port_dev && type == RTM_NEWMDB) { - complete_info = kmalloc(sizeof(*complete_info), GFP_ATOMIC); - if (complete_info) { - complete_info->port = p; - __mdb_entry_to_br_ip(entry, &complete_info->ip); + mdb.obj.orig_dev = pg->key.port->dev; + switch (type) { + case RTM_NEWMDB: + complete_info = kmalloc(sizeof(*complete_info), GFP_ATOMIC); + if (!complete_info) + break; + complete_info->port = pg->key.port; + complete_info->ip = mp->addr; mdb.obj.complete_priv = complete_info; mdb.obj.complete = br_mdb_complete; - if (switchdev_port_obj_add(port_dev, &mdb.obj, NULL)) + if (switchdev_port_obj_add(pg->key.port->dev, &mdb.obj, NULL)) kfree(complete_info); + break; + case RTM_DELMDB: + switchdev_port_obj_del(pg->key.port->dev, &mdb.obj); + break; } - } else if (p && port_dev && type == RTM_DELMDB) { - switchdev_port_obj_del(port_dev, &mdb.obj); + } else { + br_mdb_switchdev_host(dev, mp, type); } - if (!p) - br_mdb_switchdev_host(dev, entry, type); - - skb = nlmsg_new(rtnl_mdb_nlmsg_size(), GFP_ATOMIC); + skb = nlmsg_new(rtnl_mdb_nlmsg_size(pg), GFP_ATOMIC); if (!skb) goto errout; - err = nlmsg_populate_mdb_fill(skb, dev, entry, 0, 0, type, NTF_SELF); + err = nlmsg_populate_mdb_fill(skb, dev, mp, pg, type); if (err < 0) { kfree_skb(skb); goto errout; @@ -437,26 +602,6 @@ errout: rtnl_set_sk_err(net, RTNLGRP_MDB, err); } -void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, - struct br_ip *group, int type, u8 flags) -{ - struct br_mdb_entry entry; - - memset(&entry, 0, sizeof(entry)); - if (port) - entry.ifindex = port->dev->ifindex; - else - entry.ifindex = dev->ifindex; - entry.addr.proto = group->proto; - entry.addr.u.ip4 = group->u.ip4; -#if IS_ENABLED(CONFIG_IPV6) - entry.addr.u.ip6 = group->u.ip6; -#endif - entry.vid = group->vid; - __mdb_entry_fill_flags(&entry, flags); - __br_mdb_notify(dev, port, &entry, type); -} - static int nlmsg_populate_rtr_fill(struct sk_buff *skb, struct net_device *dev, int ifindex, u32 pid, @@ -524,33 +669,94 @@ errout: rtnl_set_sk_err(net, RTNLGRP_MDB, err); } -static bool is_valid_mdb_entry(struct br_mdb_entry *entry) +static bool is_valid_mdb_entry(struct br_mdb_entry *entry, + struct netlink_ext_ack *extack) { - if (entry->ifindex == 0) + if (entry->ifindex == 0) { + NL_SET_ERR_MSG_MOD(extack, "Zero entry ifindex is not allowed"); return false; + } if (entry->addr.proto == htons(ETH_P_IP)) { - if (!ipv4_is_multicast(entry->addr.u.ip4)) + if (!ipv4_is_multicast(entry->addr.u.ip4)) { + NL_SET_ERR_MSG_MOD(extack, "IPv4 entry group address is not multicast"); return false; - if (ipv4_is_local_multicast(entry->addr.u.ip4)) + } + if (ipv4_is_local_multicast(entry->addr.u.ip4)) { + NL_SET_ERR_MSG_MOD(extack, "IPv4 entry group address is local multicast"); return false; + } #if IS_ENABLED(CONFIG_IPV6) } else if (entry->addr.proto == htons(ETH_P_IPV6)) { - if (ipv6_addr_is_ll_all_nodes(&entry->addr.u.ip6)) + if (ipv6_addr_is_ll_all_nodes(&entry->addr.u.ip6)) { + NL_SET_ERR_MSG_MOD(extack, "IPv6 entry group address is link-local all nodes"); return false; + } #endif - } else + } else { + NL_SET_ERR_MSG_MOD(extack, "Unknown entry protocol"); + return false; + } + + if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY) { + NL_SET_ERR_MSG_MOD(extack, "Unknown entry state"); return false; - if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY) + } + if (entry->vid >= VLAN_VID_MASK) { + NL_SET_ERR_MSG_MOD(extack, "Invalid entry VLAN id"); return false; - if (entry->vid >= VLAN_VID_MASK) + } + + return true; +} + +static bool is_valid_mdb_source(struct nlattr *attr, __be16 proto, + struct netlink_ext_ack *extack) +{ + switch (proto) { + case htons(ETH_P_IP): + if (nla_len(attr) != sizeof(struct in_addr)) { + NL_SET_ERR_MSG_MOD(extack, "IPv4 invalid source address length"); + return false; + } + if (ipv4_is_multicast(nla_get_in_addr(attr))) { + NL_SET_ERR_MSG_MOD(extack, "IPv4 multicast source address is not allowed"); + return false; + } + break; +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): { + struct in6_addr src; + + if (nla_len(attr) != sizeof(struct in6_addr)) { + NL_SET_ERR_MSG_MOD(extack, "IPv6 invalid source address length"); + return false; + } + src = nla_get_in6_addr(attr); + if (ipv6_addr_is_multicast(&src)) { + NL_SET_ERR_MSG_MOD(extack, "IPv6 multicast source address is not allowed"); + return false; + } + break; + } +#endif + default: + NL_SET_ERR_MSG_MOD(extack, "Invalid protocol used with source address"); return false; + } return true; } +static const struct nla_policy br_mdbe_attrs_pol[MDBE_ATTR_MAX + 1] = { + [MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY, + sizeof(struct in_addr), + sizeof(struct in6_addr)), +}; + static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh, - struct net_device **pdev, struct br_mdb_entry **pentry) + struct net_device **pdev, struct br_mdb_entry **pentry, + struct nlattr **mdb_attrs, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct br_mdb_entry *entry; @@ -566,51 +772,86 @@ static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh, bpm = nlmsg_data(nlh); if (bpm->ifindex == 0) { - pr_info("PF_BRIDGE: br_mdb_parse() with invalid ifindex\n"); + NL_SET_ERR_MSG_MOD(extack, "Invalid bridge ifindex"); return -EINVAL; } dev = __dev_get_by_index(net, bpm->ifindex); if (dev == NULL) { - pr_info("PF_BRIDGE: br_mdb_parse() with unknown ifindex\n"); + NL_SET_ERR_MSG_MOD(extack, "Bridge device doesn't exist"); return -ENODEV; } if (!(dev->priv_flags & IFF_EBRIDGE)) { - pr_info("PF_BRIDGE: br_mdb_parse() with non-bridge\n"); + NL_SET_ERR_MSG_MOD(extack, "Device is not a bridge"); return -EOPNOTSUPP; } *pdev = dev; - if (!tb[MDBA_SET_ENTRY] || - nla_len(tb[MDBA_SET_ENTRY]) != sizeof(struct br_mdb_entry)) { - pr_info("PF_BRIDGE: br_mdb_parse() with invalid attr\n"); + if (!tb[MDBA_SET_ENTRY]) { + NL_SET_ERR_MSG_MOD(extack, "Missing MDBA_SET_ENTRY attribute"); + return -EINVAL; + } + if (nla_len(tb[MDBA_SET_ENTRY]) != sizeof(struct br_mdb_entry)) { + NL_SET_ERR_MSG_MOD(extack, "Invalid MDBA_SET_ENTRY attribute length"); return -EINVAL; } entry = nla_data(tb[MDBA_SET_ENTRY]); - if (!is_valid_mdb_entry(entry)) { - pr_info("PF_BRIDGE: br_mdb_parse() with invalid entry\n"); + if (!is_valid_mdb_entry(entry, extack)) return -EINVAL; + *pentry = entry; + + if (tb[MDBA_SET_ENTRY_ATTRS]) { + err = nla_parse_nested(mdb_attrs, MDBE_ATTR_MAX, + tb[MDBA_SET_ENTRY_ATTRS], + br_mdbe_attrs_pol, extack); + if (err) + return err; + if (mdb_attrs[MDBE_ATTR_SOURCE] && + !is_valid_mdb_source(mdb_attrs[MDBE_ATTR_SOURCE], + entry->addr.proto, extack)) + return -EINVAL; + } else { + memset(mdb_attrs, 0, + sizeof(struct nlattr *) * (MDBE_ATTR_MAX + 1)); } - *pentry = entry; return 0; } static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, - struct br_ip *group, unsigned char state) + struct br_mdb_entry *entry, + struct nlattr **mdb_attrs, + struct netlink_ext_ack *extack) { - struct net_bridge_mdb_entry *mp; + struct net_bridge_mdb_entry *mp, *star_mp; struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; + struct br_ip group, star_group; unsigned long now = jiffies; + u8 filter_mode; int err; - mp = br_mdb_ip_get(br, group); + __mdb_entry_to_br_ip(entry, &group, mdb_attrs); + + /* host join errors which can happen before creating the group */ + if (!port) { + /* don't allow any flags for host-joined groups */ + if (entry->state) { + NL_SET_ERR_MSG_MOD(extack, "Flags are not allowed for host groups"); + return -EINVAL; + } + if (!br_multicast_is_star_g(&group)) { + NL_SET_ERR_MSG_MOD(extack, "Groups with sources cannot be manually host joined"); + return -EINVAL; + } + } + + mp = br_mdb_ip_get(br, &group); if (!mp) { - mp = br_multicast_new_group(br, group); + mp = br_multicast_new_group(br, &group); err = PTR_ERR_OR_ZERO(mp); if (err) return err; @@ -618,13 +859,13 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, /* host join */ if (!port) { - /* don't allow any flags for host-joined groups */ - if (state) - return -EINVAL; - if (mp->host_joined) + if (mp->host_joined) { + NL_SET_ERR_MSG_MOD(extack, "Group is already joined by host"); return -EEXIST; + } br_multicast_host_join(mp, false); + br_mdb_notify(br->dev, mp, NULL, RTM_NEWMDB); return 0; } @@ -632,54 +873,69 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { - if (p->port == port) + if (p->key.port == port) { + NL_SET_ERR_MSG_MOD(extack, "Group is already joined by port"); return -EEXIST; - if ((unsigned long)p->port < (unsigned long)port) + } + if ((unsigned long)p->key.port < (unsigned long)port) break; } - p = br_multicast_new_port_group(port, group, *pp, state, NULL); - if (unlikely(!p)) + filter_mode = br_multicast_is_star_g(&group) ? MCAST_EXCLUDE : + MCAST_INCLUDE; + + p = br_multicast_new_port_group(port, &group, *pp, entry->state, NULL, + filter_mode, RTPROT_STATIC); + if (unlikely(!p)) { + NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new port group"); return -ENOMEM; + } rcu_assign_pointer(*pp, p); - if (state == MDB_TEMPORARY) + if (entry->state == MDB_TEMPORARY) mod_timer(&p->timer, now + br->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)) { + switch (filter_mode) { + case MCAST_EXCLUDE: + br_multicast_star_g_handle_mode(p, MCAST_EXCLUDE); + break; + case MCAST_INCLUDE: + star_group = p->key.addr; + memset(&star_group.src, 0, sizeof(star_group.src)); + star_mp = br_mdb_ip_get(br, &star_group); + if (star_mp) + br_multicast_sg_add_exclude_ports(star_mp, p); + break; + } + } return 0; } static int __br_mdb_add(struct net *net, struct net_bridge *br, - struct br_mdb_entry *entry) + struct net_bridge_port *p, + struct br_mdb_entry *entry, + struct nlattr **mdb_attrs, + struct netlink_ext_ack *extack) { - struct br_ip ip; - struct net_device *dev; - struct net_bridge_port *p = NULL; int ret; - if (!netif_running(br->dev) || !br_opt_get(br, BROPT_MULTICAST_ENABLED)) - return -EINVAL; - - if (entry->ifindex != br->dev->ifindex) { - dev = __dev_get_by_index(net, entry->ifindex); - if (!dev) - return -ENODEV; - - p = br_port_get_rtnl(dev); - if (!p || p->br != br || p->state == BR_STATE_DISABLED) - return -EINVAL; - } - - __mdb_entry_to_br_ip(entry, &ip); - spin_lock_bh(&br->multicast_lock); - ret = br_mdb_add_group(br, p, &ip, entry->state); + ret = br_mdb_add_group(br, p, entry, mdb_attrs, extack); spin_unlock_bh(&br->multicast_lock); + return ret; } static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { + struct nlattr *mdb_attrs[MDBE_ATTR_MAX + 1]; struct net *net = sock_net(skb->sk); struct net_bridge_vlan_group *vg; struct net_bridge_port *p = NULL; @@ -689,20 +945,43 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, struct net_bridge *br; int err; - err = br_mdb_parse(skb, nlh, &dev, &entry); + err = br_mdb_parse(skb, nlh, &dev, &entry, mdb_attrs, extack); if (err < 0) return err; br = netdev_priv(dev); + if (!netif_running(br->dev)) { + NL_SET_ERR_MSG_MOD(extack, "Bridge device is not running"); + return -EINVAL; + } + + if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) { + NL_SET_ERR_MSG_MOD(extack, "Bridge's multicast processing is disabled"); + return -EINVAL; + } + if (entry->ifindex != br->dev->ifindex) { pdev = __dev_get_by_index(net, entry->ifindex); - if (!pdev) + if (!pdev) { + NL_SET_ERR_MSG_MOD(extack, "Port net device doesn't exist"); return -ENODEV; + } p = br_port_get_rtnl(pdev); - if (!p || p->br != br || p->state == BR_STATE_DISABLED) + if (!p) { + NL_SET_ERR_MSG_MOD(extack, "Net device is not a bridge port"); + return -EINVAL; + } + + if (p->br != br) { + NL_SET_ERR_MSG_MOD(extack, "Port belongs to a different bridge device"); return -EINVAL; + } + if (p->state == BR_STATE_DISABLED) { + NL_SET_ERR_MSG_MOD(extack, "Port is in disabled state"); + return -EINVAL; + } vg = nbp_vlan_group(p); } else { vg = br_vlan_group(br); @@ -714,21 +993,19 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, if (br_vlan_enabled(br->dev) && vg && entry->vid == 0) { list_for_each_entry(v, &vg->vlan_list, vlist) { entry->vid = v->vid; - err = __br_mdb_add(net, br, entry); + err = __br_mdb_add(net, br, p, entry, mdb_attrs, extack); if (err) break; - __br_mdb_notify(dev, p, entry, RTM_NEWMDB); } } else { - err = __br_mdb_add(net, br, entry); - if (!err) - __br_mdb_notify(dev, p, entry, RTM_NEWMDB); + err = __br_mdb_add(net, br, p, entry, mdb_attrs, extack); } return err; } -static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) +static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry, + struct nlattr **mdb_attrs) { struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; @@ -739,7 +1016,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) if (!netif_running(br->dev) || !br_opt_get(br, BROPT_MULTICAST_ENABLED)) return -EINVAL; - __mdb_entry_to_br_ip(entry, &ip); + __mdb_entry_to_br_ip(entry, &ip, mdb_attrs); spin_lock_bh(&br->multicast_lock); mp = br_mdb_ip_get(br, &ip); @@ -750,6 +1027,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) if (entry->ifindex == mp->br->dev->ifindex && mp->host_joined) { br_multicast_host_leave(mp, false); err = 0; + br_mdb_notify(br->dev, mp, NULL, RTM_DELMDB); if (!mp->ports && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); goto unlock; @@ -758,22 +1036,14 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { - if (!p->port || p->port->dev->ifindex != entry->ifindex) + if (!p->key.port || p->key.port->dev->ifindex != entry->ifindex) continue; - if (p->port->state == BR_STATE_DISABLED) + if (p->key.port->state == BR_STATE_DISABLED) goto unlock; - __mdb_entry_fill_flags(entry, p->flags); - rcu_assign_pointer(*pp, p->next); - hlist_del_init(&p->mglist); - del_timer(&p->timer); - kfree_rcu(p, rcu); + br_multicast_del_pg(mp, p, pp); err = 0; - - if (!mp->ports && !mp->host_joined && - netif_running(br->dev)) - mod_timer(&mp->timer, jiffies); break; } @@ -785,6 +1055,7 @@ unlock: static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { + struct nlattr *mdb_attrs[MDBE_ATTR_MAX + 1]; struct net *net = sock_net(skb->sk); struct net_bridge_vlan_group *vg; struct net_bridge_port *p = NULL; @@ -794,7 +1065,7 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, struct net_bridge *br; int err; - err = br_mdb_parse(skb, nlh, &dev, &entry); + err = br_mdb_parse(skb, nlh, &dev, &entry, mdb_attrs, extack); if (err < 0) return err; @@ -819,14 +1090,10 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, if (br_vlan_enabled(br->dev) && vg && entry->vid == 0) { list_for_each_entry(v, &vg->vlan_list, vlist) { entry->vid = v->vid; - err = __br_mdb_del(br, entry); - if (!err) - __br_mdb_notify(dev, p, entry, RTM_DELMDB); + err = __br_mdb_del(br, entry, mdb_attrs); } } else { - err = __br_mdb_del(br, entry); - if (!err) - __br_mdb_notify(dev, p, entry, RTM_DELMDB); + err = __br_mdb_del(br, entry, mdb_attrs); } return err; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 4c4a93abde68..eae898c3cff7 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -41,6 +41,13 @@ static const struct rhashtable_params br_mdb_rht_params = { .automatic_shrinking = true, }; +static const struct rhashtable_params br_sg_port_rht_params = { + .head_offset = offsetof(struct net_bridge_port_group, rhnode), + .key_offset = offsetof(struct net_bridge_port_group, key), + .key_len = sizeof(struct net_bridge_port_group_sg_key), + .automatic_shrinking = true, +}; + static void br_multicast_start_querier(struct net_bridge *br, struct bridge_mcast_own_query *query); static void br_multicast_add_router(struct net_bridge *br, @@ -50,6 +57,7 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br, __be32 group, __u16 vid, const unsigned char *src); +static void br_multicast_port_group_rexmit(struct timer_list *t); static void __del_port_router(struct net_bridge_port *p); #if IS_ENABLED(CONFIG_IPV6) @@ -58,6 +66,26 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br, 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, + struct br_ip *group, + const unsigned char *src, + u8 filter_mode, + bool igmpv2_mldv1, + bool blocked); +static void br_multicast_find_del_pg(struct net_bridge *br, + struct net_bridge_port_group *pg); + +static struct net_bridge_port_group * +br_sg_port_find(struct net_bridge *br, + struct net_bridge_port_group_sg_key *sg_p) +{ + lockdep_assert_held_once(&br->multicast_lock); + + return rhashtable_lookup_fast(&br->sg_port_tbl, sg_p, + br_sg_port_rht_params); +} static struct net_bridge_mdb_entry *br_mdb_ip_get_rcu(struct net_bridge *br, struct br_ip *dst) @@ -85,7 +113,7 @@ static struct net_bridge_mdb_entry *br_mdb_ip4_get(struct net_bridge *br, struct br_ip br_dst; memset(&br_dst, 0, sizeof(br_dst)); - br_dst.u.ip4 = dst; + br_dst.dst.ip4 = dst; br_dst.proto = htons(ETH_P_IP); br_dst.vid = vid; @@ -100,7 +128,7 @@ static struct net_bridge_mdb_entry *br_mdb_ip6_get(struct net_bridge *br, struct br_ip br_dst; memset(&br_dst, 0, sizeof(br_dst)); - br_dst.u.ip6 = *dst; + br_dst.dst.ip6 = *dst; br_dst.proto = htons(ETH_P_IPV6); br_dst.vid = vid; @@ -125,11 +153,29 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, switch (skb->protocol) { case htons(ETH_P_IP): - ip.u.ip4 = ip_hdr(skb)->daddr; + ip.dst.ip4 = ip_hdr(skb)->daddr; + if (br->multicast_igmp_version == 3) { + struct net_bridge_mdb_entry *mdb; + + ip.src.ip4 = ip_hdr(skb)->saddr; + mdb = br_mdb_ip_get_rcu(br, &ip); + if (mdb) + return mdb; + ip.src.ip4 = 0; + } break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): - ip.u.ip6 = ipv6_hdr(skb)->daddr; + ip.dst.ip6 = ipv6_hdr(skb)->daddr; + if (br->multicast_mld_version == 2) { + struct net_bridge_mdb_entry *mdb; + + ip.src.ip6 = ipv6_hdr(skb)->saddr; + mdb = br_mdb_ip_get_rcu(br, &ip); + if (mdb) + return mdb; + memset(&ip.src.ip6, 0, sizeof(ip.src.ip6)); + } break; #endif default: @@ -139,38 +185,438 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, return br_mdb_ip_get_rcu(br, &ip); } +static bool br_port_group_equal(struct net_bridge_port_group *p, + struct net_bridge_port *port, + const unsigned char *src) +{ + if (p->key.port != port) + return false; + + if (!(port->flags & BR_MULTICAST_TO_UNICAST)) + return true; + + return ether_addr_equal(src, p->eth_addr); +} + +static void __fwd_add_star_excl(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; + + memset(&sg_key, 0, sizeof(sg_key)); + sg_key.port = pg->key.port; + sg_key.addr = *sg_ip; + if (br_sg_port_find(br, &sg_key)) + return; + + src_pg = __br_multicast_add_group(br, pg->key.port, sg_ip, pg->eth_addr, + MCAST_INCLUDE, false, false); + if (IS_ERR_OR_NULL(src_pg) || + src_pg->rt_protocol != RTPROT_KERNEL) + return; + + src_pg->flags |= MDB_PG_FLAGS_STAR_EXCL; +} + +static void __fwd_del_star_excl(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; + + memset(&sg_key, 0, sizeof(sg_key)); + sg_key.port = pg->key.port; + sg_key.addr = *sg_ip; + src_pg = br_sg_port_find(br, &sg_key); + if (!src_pg || !(src_pg->flags & MDB_PG_FLAGS_STAR_EXCL) || + src_pg->rt_protocol != RTPROT_KERNEL) + return; + + br_multicast_find_del_pg(br, src_pg); +} + +/* When a port group transitions to (or is added as) EXCLUDE we need to add it + * to all other ports' S,G entries which are not blocked by the current group + * for proper replication, the assumption is that any S,G blocked entries + * are already added so the S,G,port lookup should skip them. + * When a port group transitions from EXCLUDE -> INCLUDE mode or is being + * deleted we need to remove it from all ports' S,G entries where it was + * automatically installed before (i.e. where it's MDB_PG_FLAGS_STAR_EXCL). + */ +void br_multicast_star_g_handle_mode(struct net_bridge_port_group *pg, + u8 filter_mode) +{ + struct net_bridge *br = pg->key.port->br; + struct net_bridge_port_group *pg_lst; + struct net_bridge_mdb_entry *mp; + struct br_ip sg_ip; + + if (WARN_ON(!br_multicast_is_star_g(&pg->key.addr))) + return; + + mp = br_mdb_ip_get(br, &pg->key.addr); + if (!mp) + 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)) { + struct net_bridge_group_src *src_ent; + + if (pg_lst == pg) + continue; + hlist_for_each_entry(src_ent, &pg_lst->src_list, node) { + if (!(src_ent->flags & BR_SGRP_F_INSTALLED)) + continue; + sg_ip.src = src_ent->addr.src; + switch (filter_mode) { + case MCAST_INCLUDE: + __fwd_del_star_excl(pg, &sg_ip); + break; + case MCAST_EXCLUDE: + __fwd_add_star_excl(pg, &sg_ip); + break; + } + } + } +} + +/* called when adding a new S,G with host_joined == false by default */ +static void br_multicast_sg_host_state(struct net_bridge_mdb_entry *star_mp, + struct net_bridge_port_group *sg) +{ + struct net_bridge_mdb_entry *sg_mp; + + if (WARN_ON(!br_multicast_is_star_g(&star_mp->addr))) + return; + if (!star_mp->host_joined) + return; + + sg_mp = br_mdb_ip_get(star_mp->br, &sg->key.addr); + if (!sg_mp) + return; + sg_mp->host_joined = true; +} + +/* set the host_joined state of all of *,G's S,G entries */ +static void br_multicast_star_g_host_state(struct net_bridge_mdb_entry *star_mp) +{ + struct net_bridge *br = star_mp->br; + struct net_bridge_mdb_entry *sg_mp; + struct net_bridge_port_group *pg; + struct br_ip sg_ip; + + if (WARN_ON(!br_multicast_is_star_g(&star_mp->addr))) + return; + + memset(&sg_ip, 0, sizeof(sg_ip)); + sg_ip = star_mp->addr; + for (pg = mlock_dereference(star_mp->ports, br); + pg; + pg = mlock_dereference(pg->next, br)) { + struct net_bridge_group_src *src_ent; + + hlist_for_each_entry(src_ent, &pg->src_list, node) { + if (!(src_ent->flags & BR_SGRP_F_INSTALLED)) + continue; + sg_ip.src = src_ent->addr.src; + sg_mp = br_mdb_ip_get(br, &sg_ip); + if (!sg_mp) + continue; + sg_mp->host_joined = star_mp->host_joined; + } + } +} + +static void br_multicast_sg_del_exclude_ports(struct net_bridge_mdb_entry *sgmp) +{ + struct net_bridge_port_group __rcu **pp; + struct net_bridge_port_group *p; + + /* *,G exclude ports are only added to S,G entries */ + if (WARN_ON(br_multicast_is_star_g(&sgmp->addr))) + return; + + /* we need the STAR_EXCLUDE ports if there are non-STAR_EXCLUDE ports + * we should ignore perm entries since they're managed by user-space + */ + for (pp = &sgmp->ports; + (p = mlock_dereference(*pp, sgmp->br)) != NULL; + pp = &p->next) + if (!(p->flags & (MDB_PG_FLAGS_STAR_EXCL | + MDB_PG_FLAGS_PERMANENT))) + return; + + /* currently the host can only have joined the *,G which means + * we treat it as EXCLUDE {}, so for an S,G it's considered a + * STAR_EXCLUDE entry and we can safely leave it + */ + sgmp->host_joined = false; + + for (pp = &sgmp->ports; + (p = mlock_dereference(*pp, sgmp->br)) != NULL;) { + if (!(p->flags & MDB_PG_FLAGS_PERMANENT)) + br_multicast_del_pg(sgmp, p, pp); + else + pp = &p->next; + } +} + +void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp, + struct net_bridge_port_group *sg) +{ + struct net_bridge_port_group_sg_key sg_key; + struct net_bridge *br = star_mp->br; + struct net_bridge_port_group *pg; + + if (WARN_ON(br_multicast_is_star_g(&sg->key.addr))) + return; + if (WARN_ON(!br_multicast_is_star_g(&star_mp->addr))) + return; + + br_multicast_sg_host_state(star_mp, sg); + memset(&sg_key, 0, sizeof(sg_key)); + sg_key.addr = sg->key.addr; + /* we need to add all exclude ports to the S,G */ + for (pg = mlock_dereference(star_mp->ports, br); + pg; + pg = mlock_dereference(pg->next, br)) { + struct net_bridge_port_group *src_pg; + + if (pg == sg || pg->filter_mode == MCAST_INCLUDE) + continue; + + sg_key.port = pg->key.port; + if (br_sg_port_find(br, &sg_key)) + continue; + + src_pg = __br_multicast_add_group(br, pg->key.port, + &sg->key.addr, + sg->eth_addr, + MCAST_INCLUDE, false, false); + if (IS_ERR_OR_NULL(src_pg) || + src_pg->rt_protocol != RTPROT_KERNEL) + continue; + src_pg->flags |= MDB_PG_FLAGS_STAR_EXCL; + } +} + +static void br_multicast_fwd_src_add(struct net_bridge_group_src *src) +{ + struct net_bridge_mdb_entry *star_mp; + struct net_bridge_port_group *sg; + struct br_ip sg_ip; + + if (src->flags & BR_SGRP_F_INSTALLED) + return; + + memset(&sg_ip, 0, sizeof(sg_ip)); + 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, + src->pg->eth_addr, MCAST_INCLUDE, false, + !timer_pending(&src->timer)); + if (IS_ERR_OR_NULL(sg)) + return; + src->flags |= BR_SGRP_F_INSTALLED; + sg->flags &= ~MDB_PG_FLAGS_STAR_EXCL; + + /* if it was added by user-space as perm we can skip next steps */ + if (sg->rt_protocol != RTPROT_KERNEL && + (sg->flags & MDB_PG_FLAGS_PERMANENT)) + return; + + /* the kernel is now responsible for removing this S,G */ + del_timer(&sg->timer); + star_mp = br_mdb_ip_get(src->br, &src->pg->key.addr); + if (!star_mp) + return; + + br_multicast_sg_add_exclude_ports(star_mp, sg); +} + +static void br_multicast_fwd_src_remove(struct net_bridge_group_src *src) +{ + struct net_bridge_port_group *p, *pg = src->pg; + struct net_bridge_port_group __rcu **pp; + struct net_bridge_mdb_entry *mp; + struct br_ip sg_ip; + + memset(&sg_ip, 0, sizeof(sg_ip)); + sg_ip = pg->key.addr; + sg_ip.src = src->addr.src; + + mp = br_mdb_ip_get(src->br, &sg_ip); + if (!mp) + return; + + for (pp = &mp->ports; + (p = mlock_dereference(*pp, src->br)) != NULL; + pp = &p->next) { + if (!br_port_group_equal(p, pg->key.port, pg->eth_addr)) + continue; + + if (p->rt_protocol != RTPROT_KERNEL && + (p->flags & MDB_PG_FLAGS_PERMANENT)) + break; + + br_multicast_del_pg(mp, p, pp); + break; + } + src->flags &= ~BR_SGRP_F_INSTALLED; +} + +/* install S,G and based on src's timer enable or disable forwarding */ +static void br_multicast_fwd_src_handle(struct net_bridge_group_src *src) +{ + struct net_bridge_port_group_sg_key sg_key; + struct net_bridge_port_group *sg; + u8 old_flags; + + br_multicast_fwd_src_add(src); + + memset(&sg_key, 0, sizeof(sg_key)); + sg_key.addr = src->pg->key.addr; + sg_key.addr.src = src->addr.src; + sg_key.port = src->pg->key.port; + + sg = br_sg_port_find(src->br, &sg_key); + if (!sg || (sg->flags & MDB_PG_FLAGS_PERMANENT)) + return; + + old_flags = sg->flags; + if (timer_pending(&src->timer)) + sg->flags &= ~MDB_PG_FLAGS_BLOCKED; + else + sg->flags |= MDB_PG_FLAGS_BLOCKED; + + if (old_flags != sg->flags) { + struct net_bridge_mdb_entry *sg_mp; + + sg_mp = br_mdb_ip_get(src->br, &sg_key.addr); + if (!sg_mp) + return; + br_mdb_notify(src->br->dev, sg_mp, sg, RTM_NEWMDB); + } +} + +static void br_multicast_destroy_mdb_entry(struct net_bridge_mcast_gc *gc) +{ + struct net_bridge_mdb_entry *mp; + + mp = container_of(gc, struct net_bridge_mdb_entry, mcast_gc); + WARN_ON(!hlist_unhashed(&mp->mdb_node)); + WARN_ON(mp->ports); + + del_timer_sync(&mp->timer); + kfree_rcu(mp, rcu); +} + +static void br_multicast_del_mdb_entry(struct net_bridge_mdb_entry *mp) +{ + struct net_bridge *br = mp->br; + + rhashtable_remove_fast(&br->mdb_hash_tbl, &mp->rhnode, + br_mdb_rht_params); + hlist_del_init_rcu(&mp->mdb_node); + hlist_add_head(&mp->mcast_gc.gc_node, &br->mcast_gc_list); + queue_work(system_long_wq, &br->mcast_gc_work); +} + static void br_multicast_group_expired(struct timer_list *t) { struct net_bridge_mdb_entry *mp = from_timer(mp, t, timer); struct net_bridge *br = mp->br; spin_lock(&br->multicast_lock); - if (!netif_running(br->dev) || timer_pending(&mp->timer)) + if (hlist_unhashed(&mp->mdb_node) || !netif_running(br->dev) || + timer_pending(&mp->timer)) goto out; br_multicast_host_leave(mp, true); if (mp->ports) goto out; + br_multicast_del_mdb_entry(mp); +out: + spin_unlock(&br->multicast_lock); +} - rhashtable_remove_fast(&br->mdb_hash_tbl, &mp->rhnode, - br_mdb_rht_params); - hlist_del_rcu(&mp->mdb_node); +static void br_multicast_destroy_group_src(struct net_bridge_mcast_gc *gc) +{ + struct net_bridge_group_src *src; - kfree_rcu(mp, rcu); + src = container_of(gc, struct net_bridge_group_src, mcast_gc); + WARN_ON(!hlist_unhashed(&src->node)); -out: - spin_unlock(&br->multicast_lock); + del_timer_sync(&src->timer); + kfree_rcu(src, rcu); +} + +static void br_multicast_del_group_src(struct net_bridge_group_src *src) +{ + struct net_bridge *br = src->pg->key.port->br; + + br_multicast_fwd_src_remove(src); + hlist_del_init_rcu(&src->node); + src->pg->src_ents--; + hlist_add_head(&src->mcast_gc.gc_node, &br->mcast_gc_list); + queue_work(system_long_wq, &br->mcast_gc_work); +} + +static void br_multicast_destroy_port_group(struct net_bridge_mcast_gc *gc) +{ + struct net_bridge_port_group *pg; + + pg = container_of(gc, struct net_bridge_port_group, mcast_gc); + WARN_ON(!hlist_unhashed(&pg->mglist)); + WARN_ON(!hlist_empty(&pg->src_list)); + + del_timer_sync(&pg->rexmit_timer); + del_timer_sync(&pg->timer); + kfree_rcu(pg, rcu); +} + +void br_multicast_del_pg(struct net_bridge_mdb_entry *mp, + struct net_bridge_port_group *pg, + struct net_bridge_port_group __rcu **pp) +{ + struct net_bridge *br = pg->key.port->br; + struct net_bridge_group_src *ent; + struct hlist_node *tmp; + + rcu_assign_pointer(*pp, pg->next); + hlist_del_init(&pg->mglist); + hlist_for_each_entry_safe(ent, tmp, &pg->src_list, node) + br_multicast_del_group_src(ent); + br_mdb_notify(br->dev, mp, pg, RTM_DELMDB); + if (!br_multicast_is_star_g(&mp->addr)) { + rhashtable_remove_fast(&br->sg_port_tbl, &pg->rhnode, + br_sg_port_rht_params); + br_multicast_sg_del_exclude_ports(mp); + } else { + br_multicast_star_g_handle_mode(pg, MCAST_INCLUDE); + } + hlist_add_head(&pg->mcast_gc.gc_node, &br->mcast_gc_list); + queue_work(system_long_wq, &br->mcast_gc_work); + + if (!mp->ports && !mp->host_joined && netif_running(br->dev)) + mod_timer(&mp->timer, jiffies); } -static void br_multicast_del_pg(struct net_bridge *br, - struct net_bridge_port_group *pg) +static void br_multicast_find_del_pg(struct net_bridge *br, + struct net_bridge_port_group *pg) { + struct net_bridge_port_group __rcu **pp; struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; - struct net_bridge_port_group __rcu **pp; - mp = br_mdb_ip_get(br, &pg->addr); + mp = br_mdb_ip_get(br, &pg->key.addr); if (WARN_ON(!mp)) return; @@ -180,17 +626,7 @@ static void br_multicast_del_pg(struct net_bridge *br, if (p != pg) continue; - rcu_assign_pointer(*pp, p->next); - hlist_del_init(&p->mglist); - del_timer(&p->timer); - br_mdb_notify(br->dev, p->port, &pg->addr, RTM_DELMDB, - p->flags); - kfree_rcu(p, rcu); - - if (!mp->ports && !mp->host_joined && - netif_running(br->dev)) - mod_timer(&mp->timer, jiffies); - + br_multicast_del_pg(mp, pg, pp); return; } @@ -200,35 +636,98 @@ static void br_multicast_del_pg(struct net_bridge *br, static void br_multicast_port_group_expired(struct timer_list *t) { struct net_bridge_port_group *pg = from_timer(pg, t, timer); - struct net_bridge *br = pg->port->br; + struct net_bridge_group_src *src_ent; + struct net_bridge *br = pg->key.port->br; + struct hlist_node *tmp; + bool changed; spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || timer_pending(&pg->timer) || hlist_unhashed(&pg->mglist) || pg->flags & MDB_PG_FLAGS_PERMANENT) goto out; - br_multicast_del_pg(br, pg); + changed = !!(pg->filter_mode == MCAST_EXCLUDE); + pg->filter_mode = MCAST_INCLUDE; + hlist_for_each_entry_safe(src_ent, tmp, &pg->src_list, node) { + if (!timer_pending(&src_ent->timer)) { + br_multicast_del_group_src(src_ent); + changed = true; + } + } + + if (hlist_empty(&pg->src_list)) { + br_multicast_find_del_pg(br, pg); + } else if (changed) { + struct net_bridge_mdb_entry *mp = br_mdb_ip_get(br, &pg->key.addr); + if (changed && br_multicast_is_star_g(&pg->key.addr)) + br_multicast_star_g_handle_mode(pg, MCAST_INCLUDE); + + if (WARN_ON(!mp)) + goto out; + br_mdb_notify(br->dev, mp, pg, RTM_NEWMDB); + } out: spin_unlock(&br->multicast_lock); } -static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, - __be32 group, - u8 *igmp_type) +static void br_multicast_gc(struct hlist_head *head) { + struct net_bridge_mcast_gc *gcent; + struct hlist_node *tmp; + + hlist_for_each_entry_safe(gcent, tmp, head, gc_node) { + hlist_del_init(&gcent->gc_node); + gcent->destroy(gcent); + } +} + +static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, + struct net_bridge_port_group *pg, + __be32 ip_dst, __be32 group, + bool with_srcs, bool over_lmqt, + u8 sflag, u8 *igmp_type, + bool *need_rexmit) +{ + struct net_bridge_port *p = pg ? pg->key.port : NULL; + struct net_bridge_group_src *ent; + size_t pkt_size, igmp_hdr_size; + unsigned long now = jiffies; struct igmpv3_query *ihv3; - size_t igmp_hdr_size; + void *csum_start = NULL; + __sum16 *csum = NULL; struct sk_buff *skb; struct igmphdr *ih; struct ethhdr *eth; + unsigned long lmqt; struct iphdr *iph; + u16 lmqt_srcs = 0; igmp_hdr_size = sizeof(*ih); - if (br->multicast_igmp_version == 3) + if (br->multicast_igmp_version == 3) { igmp_hdr_size = sizeof(*ihv3); - skb = netdev_alloc_skb_ip_align(br->dev, sizeof(*eth) + sizeof(*iph) + - igmp_hdr_size + 4); + if (pg && with_srcs) { + lmqt = now + (br->multicast_last_member_interval * + br->multicast_last_member_count); + hlist_for_each_entry(ent, &pg->src_list, node) { + if (over_lmqt == time_after(ent->timer.expires, + lmqt) && + ent->src_query_rexmit_cnt > 0) + lmqt_srcs++; + } + + if (!lmqt_srcs) + return NULL; + igmp_hdr_size += lmqt_srcs * sizeof(__be32); + } + } + + pkt_size = sizeof(*eth) + sizeof(*iph) + 4 + igmp_hdr_size; + if ((p && pkt_size > p->dev->mtu) || + pkt_size > br->dev->mtu) + return NULL; + + skb = netdev_alloc_skb_ip_align(br->dev, pkt_size); if (!skb) goto out; @@ -238,29 +737,24 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, eth = eth_hdr(skb); ether_addr_copy(eth->h_source, br->dev->dev_addr); - eth->h_dest[0] = 1; - eth->h_dest[1] = 0; - eth->h_dest[2] = 0x5e; - eth->h_dest[3] = 0; - eth->h_dest[4] = 0; - eth->h_dest[5] = 1; + ip_eth_mc_map(ip_dst, eth->h_dest); eth->h_proto = htons(ETH_P_IP); skb_put(skb, sizeof(*eth)); skb_set_network_header(skb, skb->len); iph = ip_hdr(skb); + iph->tot_len = htons(pkt_size - sizeof(*eth)); iph->version = 4; iph->ihl = 6; iph->tos = 0xc0; - iph->tot_len = htons(sizeof(*iph) + igmp_hdr_size + 4); iph->id = 0; 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->daddr = htonl(INADDR_ALLHOSTS_GROUP); + iph->daddr = ip_dst; ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; @@ -280,7 +774,8 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, (HZ / IGMP_TIMER_SCALE); ih->group = group; ih->csum = 0; - ih->csum = ip_compute_csum((void *)ih, sizeof(*ih)); + csum = &ih->csum; + csum_start = (void *)ih; break; case 3: ihv3 = igmpv3_query_hdr(skb); @@ -290,15 +785,40 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, (HZ / IGMP_TIMER_SCALE); ihv3->group = group; ihv3->qqic = br->multicast_query_interval / HZ; - ihv3->nsrcs = 0; + ihv3->nsrcs = htons(lmqt_srcs); ihv3->resv = 0; - ihv3->suppress = 0; + ihv3->suppress = sflag; ihv3->qrv = 2; ihv3->csum = 0; - ihv3->csum = ip_compute_csum((void *)ihv3, sizeof(*ihv3)); + csum = &ihv3->csum; + csum_start = (void *)ihv3; + if (!pg || !with_srcs) + break; + + lmqt_srcs = 0; + hlist_for_each_entry(ent, &pg->src_list, node) { + if (over_lmqt == time_after(ent->timer.expires, + lmqt) && + ent->src_query_rexmit_cnt > 0) { + ihv3->srcs[lmqt_srcs++] = ent->addr.src.ip4; + ent->src_query_rexmit_cnt--; + if (need_rexmit && ent->src_query_rexmit_cnt) + *need_rexmit = true; + } + } + if (WARN_ON(lmqt_srcs != ntohs(ihv3->nsrcs))) { + kfree_skb(skb); + return NULL; + } break; } + if (WARN_ON(!csum || !csum_start)) { + kfree_skb(skb); + return NULL; + } + + *csum = ip_compute_csum(csum_start, igmp_hdr_size); skb_put(skb, igmp_hdr_size); __skb_pull(skb, sizeof(*eth)); @@ -308,23 +828,54 @@ out: #if IS_ENABLED(CONFIG_IPV6) static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, - const struct in6_addr *grp, - u8 *igmp_type) -{ + struct net_bridge_port_group *pg, + const struct in6_addr *ip6_dst, + const struct in6_addr *group, + bool with_srcs, bool over_llqt, + u8 sflag, u8 *igmp_type, + bool *need_rexmit) +{ + struct net_bridge_port *p = pg ? pg->key.port : NULL; + struct net_bridge_group_src *ent; + size_t pkt_size, mld_hdr_size; + unsigned long now = jiffies; struct mld2_query *mld2q; + void *csum_start = NULL; unsigned long interval; + __sum16 *csum = NULL; struct ipv6hdr *ip6h; struct mld_msg *mldq; - size_t mld_hdr_size; struct sk_buff *skb; + unsigned long llqt; struct ethhdr *eth; + u16 llqt_srcs = 0; u8 *hopopt; mld_hdr_size = sizeof(*mldq); - if (br->multicast_mld_version == 2) + if (br->multicast_mld_version == 2) { mld_hdr_size = sizeof(*mld2q); - skb = netdev_alloc_skb_ip_align(br->dev, sizeof(*eth) + sizeof(*ip6h) + - 8 + mld_hdr_size); + if (pg && with_srcs) { + llqt = now + (br->multicast_last_member_interval * + br->multicast_last_member_count); + hlist_for_each_entry(ent, &pg->src_list, node) { + if (over_llqt == time_after(ent->timer.expires, + llqt) && + ent->src_query_rexmit_cnt > 0) + llqt_srcs++; + } + + if (!llqt_srcs) + return NULL; + mld_hdr_size += llqt_srcs * sizeof(struct in6_addr); + } + } + + pkt_size = sizeof(*eth) + sizeof(*ip6h) + 8 + mld_hdr_size; + if ((p && pkt_size > p->dev->mtu) || + pkt_size > br->dev->mtu) + return NULL; + + skb = netdev_alloc_skb_ip_align(br->dev, pkt_size); if (!skb) goto out; @@ -346,7 +897,7 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, ip6h->payload_len = htons(8 + mld_hdr_size); ip6h->nexthdr = IPPROTO_HOPOPTS; ip6h->hop_limit = 1; - ipv6_addr_set(&ip6h->daddr, htonl(0xff020000), 0, 0, htonl(1)); + ip6h->daddr = *ip6_dst; if (ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0, &ip6h->saddr)) { kfree_skb(skb); @@ -371,7 +922,7 @@ 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(grp) ? + interval = ipv6_addr_any(group) ? br->multicast_query_response_interval : br->multicast_last_member_interval; *igmp_type = ICMPV6_MGM_QUERY; @@ -383,12 +934,9 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, mldq->mld_cksum = 0; mldq->mld_maxdelay = htons((u16)jiffies_to_msecs(interval)); mldq->mld_reserved = 0; - mldq->mld_mca = *grp; - mldq->mld_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, - sizeof(*mldq), IPPROTO_ICMPV6, - csum_partial(mldq, - sizeof(*mldq), - 0)); + mldq->mld_mca = *group; + csum = &mldq->mld_cksum; + csum_start = (void *)mldq; break; case 2: mld2q = (struct mld2_query *)icmp6_hdr(skb); @@ -398,21 +946,43 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, mld2q->mld2q_cksum = 0; mld2q->mld2q_resv1 = 0; mld2q->mld2q_resv2 = 0; - mld2q->mld2q_suppress = 0; + mld2q->mld2q_suppress = sflag; mld2q->mld2q_qrv = 2; - mld2q->mld2q_nsrcs = 0; + mld2q->mld2q_nsrcs = htons(llqt_srcs); mld2q->mld2q_qqic = br->multicast_query_interval / HZ; - mld2q->mld2q_mca = *grp; - mld2q->mld2q_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, - sizeof(*mld2q), - IPPROTO_ICMPV6, - csum_partial(mld2q, - sizeof(*mld2q), - 0)); + mld2q->mld2q_mca = *group; + csum = &mld2q->mld2q_cksum; + csum_start = (void *)mld2q; + if (!pg || !with_srcs) + break; + + llqt_srcs = 0; + hlist_for_each_entry(ent, &pg->src_list, node) { + if (over_llqt == time_after(ent->timer.expires, + llqt) && + ent->src_query_rexmit_cnt > 0) { + mld2q->mld2q_srcs[llqt_srcs++] = ent->addr.src.ip6; + ent->src_query_rexmit_cnt--; + if (need_rexmit && ent->src_query_rexmit_cnt) + *need_rexmit = true; + } + } + if (WARN_ON(llqt_srcs != ntohs(mld2q->mld2q_nsrcs))) { + kfree_skb(skb); + return NULL; + } break; } - skb_put(skb, mld_hdr_size); + if (WARN_ON(!csum || !csum_start)) { + kfree_skb(skb); + return NULL; + } + + *csum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, mld_hdr_size, + IPPROTO_ICMPV6, + csum_partial(csum_start, mld_hdr_size, 0)); + skb_put(skb, mld_hdr_size); __skb_pull(skb, sizeof(*eth)); out: @@ -421,16 +991,39 @@ out: #endif static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br, - struct br_ip *addr, - u8 *igmp_type) + struct net_bridge_port_group *pg, + struct br_ip *ip_dst, + struct br_ip *group, + bool with_srcs, bool over_lmqt, + u8 sflag, u8 *igmp_type, + bool *need_rexmit) { - switch (addr->proto) { + __be32 ip4_dst; + + switch (group->proto) { case htons(ETH_P_IP): - return br_ip4_multicast_alloc_query(br, addr->u.ip4, igmp_type); + ip4_dst = ip_dst ? ip_dst->dst.ip4 : htonl(INADDR_ALLHOSTS_GROUP); + return br_ip4_multicast_alloc_query(br, pg, + ip4_dst, group->dst.ip4, + with_srcs, over_lmqt, + sflag, igmp_type, + need_rexmit); #if IS_ENABLED(CONFIG_IPV6) - case htons(ETH_P_IPV6): - return br_ip6_multicast_alloc_query(br, &addr->u.ip6, - igmp_type); + case htons(ETH_P_IPV6): { + struct in6_addr ip6_dst; + + if (ip_dst) + ip6_dst = ip_dst->dst.ip6; + else + ipv6_addr_set(&ip6_dst, htonl(0xff020000), 0, 0, + htonl(1)); + + return br_ip6_multicast_alloc_query(br, pg, + &ip6_dst, &group->dst.ip6, + with_srcs, over_lmqt, + sflag, igmp_type, + need_rexmit); + } #endif } return NULL; @@ -457,6 +1050,7 @@ struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br, mp->br = br; mp->addr = *group; + mp->mcast_gc.destroy = br_multicast_destroy_mdb_entry; timer_setup(&mp->timer, br_multicast_group_expired, 0); err = rhashtable_lookup_insert_fast(&br->mdb_hash_tbl, &mp->rhnode, br_mdb_rht_params); @@ -470,12 +1064,101 @@ struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br, return mp; } +static void br_multicast_group_src_expired(struct timer_list *t) +{ + struct net_bridge_group_src *src = from_timer(src, t, timer); + struct net_bridge_port_group *pg; + struct net_bridge *br = src->br; + + spin_lock(&br->multicast_lock); + if (hlist_unhashed(&src->node) || !netif_running(br->dev) || + timer_pending(&src->timer)) + goto out; + + pg = src->pg; + if (pg->filter_mode == MCAST_INCLUDE) { + br_multicast_del_group_src(src); + if (!hlist_empty(&pg->src_list)) + goto out; + br_multicast_find_del_pg(br, pg); + } else { + br_multicast_fwd_src_handle(src); + } + +out: + spin_unlock(&br->multicast_lock); +} + +static struct net_bridge_group_src * +br_multicast_find_group_src(struct net_bridge_port_group *pg, struct br_ip *ip) +{ + struct net_bridge_group_src *ent; + + switch (ip->proto) { + case htons(ETH_P_IP): + hlist_for_each_entry(ent, &pg->src_list, node) + if (ip->src.ip4 == ent->addr.src.ip4) + return ent; + break; +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + hlist_for_each_entry(ent, &pg->src_list, node) + if (!ipv6_addr_cmp(&ent->addr.src.ip6, &ip->src.ip6)) + return ent; + break; +#endif + } + + return NULL; +} + +static struct net_bridge_group_src * +br_multicast_new_group_src(struct net_bridge_port_group *pg, struct br_ip *src_ip) +{ + struct net_bridge_group_src *grp_src; + + if (unlikely(pg->src_ents >= PG_SRC_ENT_LIMIT)) + return NULL; + + switch (src_ip->proto) { + case htons(ETH_P_IP): + if (ipv4_is_zeronet(src_ip->src.ip4) || + ipv4_is_multicast(src_ip->src.ip4)) + return NULL; + break; +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + if (ipv6_addr_any(&src_ip->src.ip6) || + ipv6_addr_is_multicast(&src_ip->src.ip6)) + return NULL; + break; +#endif + } + + grp_src = kzalloc(sizeof(*grp_src), GFP_ATOMIC); + if (unlikely(!grp_src)) + return NULL; + + grp_src->pg = pg; + grp_src->br = pg->key.port->br; + grp_src->addr = *src_ip; + grp_src->mcast_gc.destroy = br_multicast_destroy_group_src; + timer_setup(&grp_src->timer, br_multicast_group_src_expired, 0); + + hlist_add_head_rcu(&grp_src->node, &pg->src_list); + pg->src_ents++; + + return grp_src; +} + struct net_bridge_port_group *br_multicast_new_port_group( struct net_bridge_port *port, struct br_ip *group, struct net_bridge_port_group __rcu *next, unsigned char flags, - const unsigned char *src) + const unsigned char *src, + u8 filter_mode, + u8 rt_protocol) { struct net_bridge_port_group *p; @@ -483,12 +1166,25 @@ struct net_bridge_port_group *br_multicast_new_port_group( if (unlikely(!p)) return NULL; - p->addr = *group; - p->port = port; + p->key.addr = *group; + p->key.port = port; p->flags = flags; + p->filter_mode = filter_mode; + p->rt_protocol = rt_protocol; + p->mcast_gc.destroy = br_multicast_destroy_port_group; + INIT_HLIST_HEAD(&p->src_list); + + if (!br_multicast_is_star_g(group) && + rhashtable_lookup_insert_fast(&port->br->sg_port_tbl, &p->rhnode, + br_sg_port_rht_params)) { + kfree(p); + return NULL; + } + rcu_assign_pointer(p->next, next); - hlist_add_head(&p->mglist, &port->mglist); timer_setup(&p->timer, br_multicast_port_group_expired, 0); + timer_setup(&p->rexmit_timer, br_multicast_port_group_rexmit, 0); + hlist_add_head(&p->mglist, &port->mglist); if (src) memcpy(p->eth_addr, src, ETH_ALEN); @@ -498,26 +1194,14 @@ struct net_bridge_port_group *br_multicast_new_port_group( return p; } -static bool br_port_group_equal(struct net_bridge_port_group *p, - struct net_bridge_port *port, - const unsigned char *src) -{ - if (p->port != port) - return false; - - if (!(port->flags & BR_MULTICAST_TO_UNICAST)) - return true; - - return ether_addr_equal(src, p->eth_addr); -} - void br_multicast_host_join(struct net_bridge_mdb_entry *mp, bool notify) { if (!mp->host_joined) { mp->host_joined = true; + if (br_multicast_is_star_g(&mp->addr)) + br_multicast_star_g_host_state(mp); if (notify) - br_mdb_notify(mp->br->dev, NULL, &mp->addr, - RTM_NEWMDB, 0); + br_mdb_notify(mp->br->dev, mp, NULL, RTM_NEWMDB); } mod_timer(&mp->timer, jiffies + mp->br->multicast_membership_interval); } @@ -528,30 +1212,33 @@ void br_multicast_host_leave(struct net_bridge_mdb_entry *mp, bool notify) return; mp->host_joined = false; + if (br_multicast_is_star_g(&mp->addr)) + br_multicast_star_g_host_state(mp); if (notify) - br_mdb_notify(mp->br->dev, NULL, &mp->addr, RTM_DELMDB, 0); + br_mdb_notify(mp->br->dev, mp, NULL, RTM_DELMDB); } -static int br_multicast_add_group(struct net_bridge *br, - struct net_bridge_port *port, - struct br_ip *group, - const unsigned char *src) +static struct net_bridge_port_group * +__br_multicast_add_group(struct net_bridge *br, + struct net_bridge_port *port, + struct br_ip *group, + const unsigned char *src, + u8 filter_mode, + bool igmpv2_mldv1, + bool blocked) { struct net_bridge_port_group __rcu **pp; - struct net_bridge_port_group *p; + struct net_bridge_port_group *p = NULL; struct net_bridge_mdb_entry *mp; unsigned long now = jiffies; - int err; - spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || (port && port->state == BR_STATE_DISABLED)) goto out; mp = br_multicast_new_group(br, group); - err = PTR_ERR(mp); if (IS_ERR(mp)) - goto err; + return ERR_PTR(PTR_ERR(mp)); if (!port) { br_multicast_host_join(mp, true); @@ -563,23 +1250,46 @@ static int br_multicast_add_group(struct net_bridge *br, pp = &p->next) { if (br_port_group_equal(p, port, src)) goto found; - if ((unsigned long)p->port < (unsigned long)port) + if ((unsigned long)p->key.port < (unsigned long)port) break; } - p = br_multicast_new_port_group(port, group, *pp, 0, src); - if (unlikely(!p)) - goto err; + p = br_multicast_new_port_group(port, group, *pp, 0, src, filter_mode, + RTPROT_KERNEL); + if (unlikely(!p)) { + p = ERR_PTR(-ENOMEM); + goto out; + } rcu_assign_pointer(*pp, p); - br_mdb_notify(br->dev, port, group, RTM_NEWMDB, 0); + if (blocked) + p->flags |= MDB_PG_FLAGS_BLOCKED; + br_mdb_notify(br->dev, mp, p, RTM_NEWMDB); found: - mod_timer(&p->timer, now + br->multicast_membership_interval); + if (igmpv2_mldv1) + mod_timer(&p->timer, now + br->multicast_membership_interval); + out: - err = 0; + return p; +} + +static int br_multicast_add_group(struct net_bridge *br, + struct net_bridge_port *port, + struct br_ip *group, + const unsigned char *src, + u8 filter_mode, + bool igmpv2_mldv1) +{ + struct net_bridge_port_group *pg; + int err; -err: + spin_lock(&br->multicast_lock); + pg = __br_multicast_add_group(br, port, group, src, filter_mode, + igmpv2_mldv1, false); + /* NULL is considered valid for host joined groups */ + err = IS_ERR(pg) ? PTR_ERR(pg) : 0; spin_unlock(&br->multicast_lock); + return err; } @@ -587,19 +1297,23 @@ static int br_ip4_multicast_add_group(struct net_bridge *br, struct net_bridge_port *port, __be32 group, __u16 vid, - const unsigned char *src) + const unsigned char *src, + bool igmpv2) { struct br_ip br_group; + u8 filter_mode; if (ipv4_is_local_multicast(group)) return 0; memset(&br_group, 0, sizeof(br_group)); - br_group.u.ip4 = group; + br_group.dst.ip4 = group; br_group.proto = htons(ETH_P_IP); br_group.vid = vid; + filter_mode = igmpv2 ? MCAST_EXCLUDE : MCAST_INCLUDE; - return br_multicast_add_group(br, port, &br_group, src); + return br_multicast_add_group(br, port, &br_group, src, filter_mode, + igmpv2); } #if IS_ENABLED(CONFIG_IPV6) @@ -607,19 +1321,23 @@ static int br_ip6_multicast_add_group(struct net_bridge *br, struct net_bridge_port *port, const struct in6_addr *group, __u16 vid, - const unsigned char *src) + const unsigned char *src, + bool mldv1) { struct br_ip br_group; + u8 filter_mode; if (ipv6_addr_is_ll_all_nodes(group)) return 0; memset(&br_group, 0, sizeof(br_group)); - br_group.u.ip6 = *group; + br_group.dst.ip6 = *group; br_group.proto = htons(ETH_P_IPV6); br_group.vid = vid; + filter_mode = mldv1 ? MCAST_EXCLUDE : MCAST_INCLUDE; - return br_multicast_add_group(br, port, &br_group, src); + return br_multicast_add_group(br, port, &br_group, src, filter_mode, + mldv1); } #endif @@ -702,21 +1420,30 @@ static void br_multicast_select_own_querier(struct net_bridge *br, struct sk_buff *skb) { if (ip->proto == htons(ETH_P_IP)) - br->ip4_querier.addr.u.ip4 = ip_hdr(skb)->saddr; + br->ip4_querier.addr.src.ip4 = ip_hdr(skb)->saddr; #if IS_ENABLED(CONFIG_IPV6) else - br->ip6_querier.addr.u.ip6 = ipv6_hdr(skb)->saddr; + br->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, - struct br_ip *ip) -{ + struct net_bridge_port_group *pg, + struct br_ip *ip_dst, + struct br_ip *group, + bool with_srcs, + u8 sflag, + bool *need_rexmit) +{ + bool over_lmqt = !!sflag; struct sk_buff *skb; u8 igmp_type; - skb = br_multicast_alloc_query(br, ip, &igmp_type); +again_under_lmqt: + skb = br_multicast_alloc_query(br, pg, ip_dst, group, with_srcs, + over_lmqt, sflag, &igmp_type, + need_rexmit); if (!skb) return; @@ -727,8 +1454,13 @@ static void __br_multicast_send_query(struct net_bridge *br, NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, dev_net(port->dev), NULL, skb, NULL, skb->dev, br_dev_queue_push_xmit); + + if (over_lmqt && with_srcs && sflag) { + over_lmqt = false; + goto again_under_lmqt; + } } else { - br_multicast_select_own_querier(br, ip, skb); + br_multicast_select_own_querier(br, group, skb); br_multicast_count(br, port, skb, igmp_type, BR_MCAST_DIR_RX); netif_rx(skb); @@ -748,7 +1480,7 @@ static void br_multicast_send_query(struct net_bridge *br, !br_opt_get(br, BROPT_MULTICAST_QUERIER)) return; - memset(&br_group.u, 0, sizeof(br_group.u)); + memset(&br_group.dst, 0, sizeof(br_group.dst)); if (port ? (own_query == &port->ip4_own_query) : (own_query == &br->ip4_own_query)) { @@ -764,7 +1496,8 @@ 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, &br_group); + __br_multicast_send_query(br, port, NULL, NULL, &br_group, false, 0, + NULL); time = jiffies; time += own_query->startup_sent < br->multicast_startup_query_count ? @@ -809,6 +1542,44 @@ static void br_ip6_multicast_port_query_expired(struct timer_list *t) } #endif +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; + 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)) + goto out; + + if (pg->key.addr.proto == htons(ETH_P_IP)) + other_query = &br->ip4_other_query; +#if IS_ENABLED(CONFIG_IPV6) + else + other_query = &br->ip6_other_query; +#endif + + if (!other_query || timer_pending(&other_query->timer)) + goto out; + + if (pg->grp_query_rexmit_cnt) { + pg->grp_query_rexmit_cnt--; + __br_multicast_send_query(br, pg->key.port, pg, &pg->key.addr, + &pg->key.addr, false, 1, NULL); + } + __br_multicast_send_query(br, pg->key.port, 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); +out: + spin_unlock(&br->multicast_lock); +} + static void br_mc_disabled_update(struct net_device *dev, bool value) { struct switchdev_attr attr = { @@ -847,13 +1618,16 @@ void br_multicast_del_port(struct net_bridge_port *port) { struct net_bridge *br = port->br; struct net_bridge_port_group *pg; + HLIST_HEAD(deleted_head); struct hlist_node *n; /* Take care of the remaining groups, only perm ones should be left */ spin_lock_bh(&br->multicast_lock); hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) - br_multicast_del_pg(br, pg); + br_multicast_find_del_pg(br, pg); + hlist_move_list(&br->mcast_gc_list, &deleted_head); spin_unlock_bh(&br->multicast_lock); + br_multicast_gc(&deleted_head); del_timer_sync(&port->multicast_router_timer); free_percpu(port->mcast_stats); } @@ -901,7 +1675,7 @@ void br_multicast_disable_port(struct net_bridge_port *port) spin_lock(&br->multicast_lock); hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) if (!(pg->flags & MDB_PG_FLAGS_PERMANENT)) - br_multicast_del_pg(br, pg); + br_multicast_find_del_pg(br, pg); __del_port_router(port); @@ -913,20 +1687,574 @@ void br_multicast_disable_port(struct net_bridge_port *port) spin_unlock(&br->multicast_lock); } +static int __grp_src_delete_marked(struct net_bridge_port_group *pg) +{ + struct net_bridge_group_src *ent; + struct hlist_node *tmp; + int deleted = 0; + + hlist_for_each_entry_safe(ent, tmp, &pg->src_list, node) + if (ent->flags & BR_SGRP_F_DELETE) { + br_multicast_del_group_src(ent); + deleted++; + } + + return deleted; +} + +static void __grp_src_mod_timer(struct net_bridge_group_src *src, + unsigned long expires) +{ + mod_timer(&src->timer, expires); + br_multicast_fwd_src_handle(src); +} + +static void __grp_src_query_marked_and_rexmit(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; + unsigned long lmqt, lmi, now = jiffies; + struct net_bridge_group_src *ent; + + if (!netif_running(br->dev) || + !br_opt_get(br, BROPT_MULTICAST_ENABLED)) + return; + + if (pg->key.addr.proto == htons(ETH_P_IP)) + other_query = &br->ip4_other_query; +#if IS_ENABLED(CONFIG_IPV6) + else + other_query = &br->ip6_other_query; +#endif + + lmqt = now + br_multicast_lmqt(br); + 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) && + other_query && + !timer_pending(&other_query->timer)) + ent->src_query_rexmit_cnt = lmqc; + __grp_src_mod_timer(ent, lmqt); + } + } + } + + if (!br_opt_get(br, BROPT_MULTICAST_QUERIER) || + !other_query || timer_pending(&other_query->timer)) + return; + + __br_multicast_send_query(br, pg->key.port, pg, &pg->key.addr, + &pg->key.addr, true, 1, NULL); + + lmi = now + br->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) +{ + 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)) + return; + + if (pg->key.addr.proto == htons(ETH_P_IP)) + other_query = &br->ip4_other_query; +#if IS_ENABLED(CONFIG_IPV6) + else + other_query = &br->ip6_other_query; +#endif + + if (br_opt_get(br, BROPT_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, + &pg->key.addr, false, 0, NULL); + if (!timer_pending(&pg->rexmit_timer) || + time_after(pg->rexmit_timer.expires, lmi)) + mod_timer(&pg->rexmit_timer, lmi); + } + + 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)); +} + +/* State Msg type New state Actions + * INCLUDE (A) IS_IN (B) INCLUDE (A+B) (B)=GMI + * 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 *srcs, u32 nsrcs, size_t src_size) +{ + struct net_bridge *br = pg->key.port->br; + struct net_bridge_group_src *ent; + unsigned long now = jiffies; + bool changed = false; + struct br_ip src_ip; + u32 src_idx; + + memset(&src_ip, 0, sizeof(src_ip)); + src_ip.proto = pg->key.addr.proto; + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&src_ip.src, srcs, src_size); + ent = br_multicast_find_group_src(pg, &src_ip); + if (!ent) { + ent = br_multicast_new_group_src(pg, &src_ip); + if (ent) + changed = true; + } + + if (ent) + __grp_src_mod_timer(ent, now + br_multicast_gmi(br)); + srcs += src_size; + } + + return changed; +} + +/* State Msg type New state Actions + * INCLUDE (A) IS_EX (B) EXCLUDE (A*B,B-A) (B-A)=0 + * Delete (A-B) + * Group Timer=GMI + */ +static void __grp_src_isexc_incl(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + struct net_bridge_group_src *ent; + struct br_ip src_ip; + u32 src_idx; + + hlist_for_each_entry(ent, &pg->src_list, node) + ent->flags |= BR_SGRP_F_DELETE; + + memset(&src_ip, 0, sizeof(src_ip)); + src_ip.proto = pg->key.addr.proto; + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&src_ip.src, srcs, src_size); + ent = br_multicast_find_group_src(pg, &src_ip); + if (ent) + ent->flags &= ~BR_SGRP_F_DELETE; + else + ent = br_multicast_new_group_src(pg, &src_ip); + if (ent) + br_multicast_fwd_src_handle(ent); + srcs += src_size; + } + + __grp_src_delete_marked(pg); +} + +/* State Msg type New state Actions + * EXCLUDE (X,Y) IS_EX (A) EXCLUDE (A-Y,Y*A) (A-X-Y)=GMI + * Delete (X-A) + * Delete (Y-A) + * Group Timer=GMI + */ +static bool __grp_src_isexc_excl(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + struct net_bridge *br = pg->key.port->br; + struct net_bridge_group_src *ent; + unsigned long now = jiffies; + bool changed = false; + struct br_ip src_ip; + u32 src_idx; + + hlist_for_each_entry(ent, &pg->src_list, node) + ent->flags |= BR_SGRP_F_DELETE; + + memset(&src_ip, 0, sizeof(src_ip)); + src_ip.proto = pg->key.addr.proto; + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&src_ip.src, srcs, src_size); + ent = br_multicast_find_group_src(pg, &src_ip); + if (ent) { + ent->flags &= ~BR_SGRP_F_DELETE; + } else { + ent = br_multicast_new_group_src(pg, &src_ip); + if (ent) { + __grp_src_mod_timer(ent, + now + br_multicast_gmi(br)); + changed = true; + } + } + srcs += src_size; + } + + if (__grp_src_delete_marked(pg)) + changed = true; + + return changed; +} + +static bool br_multicast_isexc(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + struct net_bridge *br = pg->key.port->br; + bool changed = false; + + switch (pg->filter_mode) { + case MCAST_INCLUDE: + __grp_src_isexc_incl(pg, srcs, nsrcs, src_size); + br_multicast_star_g_handle_mode(pg, MCAST_EXCLUDE); + changed = true; + break; + case MCAST_EXCLUDE: + changed = __grp_src_isexc_excl(pg, srcs, nsrcs, src_size); + break; + } + + pg->filter_mode = MCAST_EXCLUDE; + mod_timer(&pg->timer, jiffies + br_multicast_gmi(br)); + + return changed; +} + +/* State Msg type New state Actions + * 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 *srcs, u32 nsrcs, size_t src_size) +{ + 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; + bool changed = false; + struct br_ip src_ip; + + hlist_for_each_entry(ent, &pg->src_list, node) + ent->flags |= BR_SGRP_F_SEND; + + memset(&src_ip, 0, sizeof(src_ip)); + src_ip.proto = pg->key.addr.proto; + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&src_ip.src, srcs, src_size); + ent = br_multicast_find_group_src(pg, &src_ip); + if (ent) { + ent->flags &= ~BR_SGRP_F_SEND; + to_send--; + } else { + ent = br_multicast_new_group_src(pg, &src_ip); + if (ent) + changed = true; + } + if (ent) + __grp_src_mod_timer(ent, now + br_multicast_gmi(br)); + srcs += src_size; + } + + if (to_send) + __grp_src_query_marked_and_rexmit(pg); + + return changed; +} + +/* State Msg type New state Actions + * EXCLUDE (X,Y) TO_IN (A) EXCLUDE (X+A,Y-A) (A)=GMI + * Send Q(G,X-A) + * Send Q(G) + */ +static bool __grp_src_toin_excl(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + 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; + bool changed = false; + struct br_ip src_ip; + + hlist_for_each_entry(ent, &pg->src_list, node) + if (timer_pending(&ent->timer)) + ent->flags |= BR_SGRP_F_SEND; + + memset(&src_ip, 0, sizeof(src_ip)); + src_ip.proto = pg->key.addr.proto; + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&src_ip.src, srcs, src_size); + ent = br_multicast_find_group_src(pg, &src_ip); + if (ent) { + if (timer_pending(&ent->timer)) { + ent->flags &= ~BR_SGRP_F_SEND; + to_send--; + } + } else { + ent = br_multicast_new_group_src(pg, &src_ip); + if (ent) + changed = true; + } + if (ent) + __grp_src_mod_timer(ent, now + br_multicast_gmi(br)); + srcs += src_size; + } + + if (to_send) + __grp_src_query_marked_and_rexmit(pg); + + __grp_send_query_and_rexmit(pg); + + return changed; +} + +static bool br_multicast_toin(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + bool changed = false; + + switch (pg->filter_mode) { + case MCAST_INCLUDE: + changed = __grp_src_toin_incl(pg, srcs, nsrcs, src_size); + break; + case MCAST_EXCLUDE: + changed = __grp_src_toin_excl(pg, srcs, nsrcs, src_size); + break; + } + + return changed; +} + +/* State Msg type New state Actions + * INCLUDE (A) TO_EX (B) EXCLUDE (A*B,B-A) (B-A)=0 + * Delete (A-B) + * Send Q(G,A*B) + * Group Timer=GMI + */ +static void __grp_src_toex_incl(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + struct net_bridge_group_src *ent; + u32 src_idx, to_send = 0; + struct br_ip src_ip; + + hlist_for_each_entry(ent, &pg->src_list, node) + ent->flags = (ent->flags & ~BR_SGRP_F_SEND) | BR_SGRP_F_DELETE; + + memset(&src_ip, 0, sizeof(src_ip)); + src_ip.proto = pg->key.addr.proto; + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&src_ip.src, srcs, src_size); + ent = br_multicast_find_group_src(pg, &src_ip); + if (ent) { + ent->flags = (ent->flags & ~BR_SGRP_F_DELETE) | + BR_SGRP_F_SEND; + to_send++; + } else { + ent = br_multicast_new_group_src(pg, &src_ip); + } + if (ent) + br_multicast_fwd_src_handle(ent); + srcs += src_size; + } + + __grp_src_delete_marked(pg); + if (to_send) + __grp_src_query_marked_and_rexmit(pg); +} + +/* State Msg type New state Actions + * EXCLUDE (X,Y) TO_EX (A) EXCLUDE (A-Y,Y*A) (A-X-Y)=Group Timer + * Delete (X-A) + * Delete (Y-A) + * Send Q(G,A-Y) + * Group Timer=GMI + */ +static bool __grp_src_toex_excl(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + struct net_bridge_group_src *ent; + u32 src_idx, to_send = 0; + bool changed = false; + struct br_ip src_ip; + + hlist_for_each_entry(ent, &pg->src_list, node) + ent->flags = (ent->flags & ~BR_SGRP_F_SEND) | BR_SGRP_F_DELETE; + + memset(&src_ip, 0, sizeof(src_ip)); + src_ip.proto = pg->key.addr.proto; + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&src_ip.src, srcs, src_size); + ent = br_multicast_find_group_src(pg, &src_ip); + if (ent) { + ent->flags &= ~BR_SGRP_F_DELETE; + } else { + ent = br_multicast_new_group_src(pg, &src_ip); + if (ent) { + __grp_src_mod_timer(ent, pg->timer.expires); + changed = true; + } + } + if (ent && timer_pending(&ent->timer)) { + ent->flags |= BR_SGRP_F_SEND; + to_send++; + } + srcs += src_size; + } + + if (__grp_src_delete_marked(pg)) + changed = true; + if (to_send) + __grp_src_query_marked_and_rexmit(pg); + + return changed; +} + +static bool br_multicast_toex(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + struct net_bridge *br = pg->key.port->br; + bool changed = false; + + switch (pg->filter_mode) { + case MCAST_INCLUDE: + __grp_src_toex_incl(pg, srcs, nsrcs, src_size); + br_multicast_star_g_handle_mode(pg, MCAST_EXCLUDE); + changed = true; + break; + case MCAST_EXCLUDE: + changed = __grp_src_toex_excl(pg, srcs, nsrcs, src_size); + break; + } + + pg->filter_mode = MCAST_EXCLUDE; + mod_timer(&pg->timer, jiffies + br_multicast_gmi(br)); + + return changed; +} + +/* State Msg type New state Actions + * INCLUDE (A) BLOCK (B) INCLUDE (A) Send Q(G,A*B) + */ +static void __grp_src_block_incl(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + struct net_bridge_group_src *ent; + u32 src_idx, to_send = 0; + struct br_ip src_ip; + + hlist_for_each_entry(ent, &pg->src_list, node) + ent->flags &= ~BR_SGRP_F_SEND; + + memset(&src_ip, 0, sizeof(src_ip)); + src_ip.proto = pg->key.addr.proto; + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&src_ip.src, srcs, src_size); + ent = br_multicast_find_group_src(pg, &src_ip); + if (ent) { + ent->flags |= BR_SGRP_F_SEND; + to_send++; + } + srcs += src_size; + } + + if (to_send) + __grp_src_query_marked_and_rexmit(pg); + + if (pg->filter_mode == MCAST_INCLUDE && hlist_empty(&pg->src_list)) + br_multicast_find_del_pg(pg->key.port->br, pg); +} + +/* State Msg type New state Actions + * 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 *srcs, u32 nsrcs, size_t src_size) +{ + struct net_bridge_group_src *ent; + u32 src_idx, to_send = 0; + bool changed = false; + struct br_ip src_ip; + + hlist_for_each_entry(ent, &pg->src_list, node) + ent->flags &= ~BR_SGRP_F_SEND; + + memset(&src_ip, 0, sizeof(src_ip)); + src_ip.proto = pg->key.addr.proto; + for (src_idx = 0; src_idx < nsrcs; src_idx++) { + memcpy(&src_ip.src, srcs, src_size); + ent = br_multicast_find_group_src(pg, &src_ip); + if (!ent) { + ent = br_multicast_new_group_src(pg, &src_ip); + if (ent) { + __grp_src_mod_timer(ent, pg->timer.expires); + changed = true; + } + } + if (ent && timer_pending(&ent->timer)) { + ent->flags |= BR_SGRP_F_SEND; + to_send++; + } + srcs += src_size; + } + + if (to_send) + __grp_src_query_marked_and_rexmit(pg); + + return changed; +} + +static bool br_multicast_block(struct net_bridge_port_group *pg, + void *srcs, u32 nsrcs, size_t src_size) +{ + bool changed = false; + + switch (pg->filter_mode) { + case MCAST_INCLUDE: + __grp_src_block_incl(pg, srcs, nsrcs, src_size); + break; + case MCAST_EXCLUDE: + changed = __grp_src_block_excl(pg, srcs, nsrcs, src_size); + break; + } + + return changed; +} + +static struct net_bridge_port_group * +br_multicast_find_port(struct net_bridge_mdb_entry *mp, + struct net_bridge_port *p, + const unsigned char *src) +{ + struct net_bridge *br __maybe_unused = mp->br; + struct net_bridge_port_group *pg; + + for (pg = mlock_dereference(mp->ports, br); + pg; + pg = mlock_dereference(pg->next, br)) + if (br_port_group_equal(pg, p, src)) + return pg; + + return NULL; +} + static int br_ip4_multicast_igmp3_report(struct net_bridge *br, struct net_bridge_port *port, struct sk_buff *skb, u16 vid) { + bool igmpv2 = br->multicast_igmp_version == 2; + struct net_bridge_mdb_entry *mdst; + struct net_bridge_port_group *pg; const unsigned char *src; struct igmpv3_report *ih; struct igmpv3_grec *grec; - int i; - int len; - int num; - int type; - int err = 0; + int i, len, num, type; + bool changed = false; __be32 group; + int err = 0; u16 nsrcs; ih = igmpv3_report_hdr(skb); @@ -947,7 +2275,6 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, if (!ip_mc_may_pull(skb, len)) return -EINVAL; - /* We treat this as an IGMPv2 report for now. */ switch (type) { case IGMPV3_MODE_IS_INCLUDE: case IGMPV3_MODE_IS_EXCLUDE: @@ -962,16 +2289,62 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, } src = eth_hdr(skb)->h_source; - if ((type == IGMPV3_CHANGE_TO_INCLUDE || - type == IGMPV3_MODE_IS_INCLUDE) && - nsrcs == 0) { - br_ip4_multicast_leave_group(br, port, group, vid, src); + 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); + continue; + } } else { err = br_ip4_multicast_add_group(br, port, group, vid, - src); + src, igmpv2); if (err) break; } + + if (!port || igmpv2) + continue; + + spin_lock_bh(&br->multicast_lock); + mdst = br_mdb_ip4_get(br, group, vid); + if (!mdst) + goto unlock_continue; + pg = br_multicast_find_port(mdst, port, src); + if (!pg || (pg->flags & MDB_PG_FLAGS_PERMANENT)) + goto unlock_continue; + /* reload grec */ + grec = (void *)(skb->data + len - sizeof(*grec) - (nsrcs * 4)); + switch (type) { + case IGMPV3_ALLOW_NEW_SOURCES: + changed = br_multicast_isinc_allow(pg, grec->grec_src, + nsrcs, sizeof(__be32)); + break; + case IGMPV3_MODE_IS_INCLUDE: + changed = br_multicast_isinc_allow(pg, grec->grec_src, nsrcs, + sizeof(__be32)); + break; + case IGMPV3_MODE_IS_EXCLUDE: + changed = br_multicast_isexc(pg, grec->grec_src, nsrcs, + sizeof(__be32)); + break; + case IGMPV3_CHANGE_TO_INCLUDE: + changed = br_multicast_toin(pg, grec->grec_src, nsrcs, + sizeof(__be32)); + break; + case IGMPV3_CHANGE_TO_EXCLUDE: + changed = br_multicast_toex(pg, grec->grec_src, nsrcs, + sizeof(__be32)); + break; + case IGMPV3_BLOCK_OLD_SOURCES: + changed = br_multicast_block(pg, grec->grec_src, nsrcs, + sizeof(__be32)); + break; + } + if (changed) + br_mdb_notify(br->dev, mdst, pg, RTM_NEWMDB); +unlock_continue: + spin_unlock_bh(&br->multicast_lock); } return err; @@ -983,14 +2356,16 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, struct sk_buff *skb, u16 vid) { + bool mldv1 = br->multicast_mld_version == 1; + struct net_bridge_mdb_entry *mdst; + struct net_bridge_port_group *pg; unsigned int nsrcs_offset; const unsigned char *src; struct icmp6hdr *icmp6h; struct mld2_grec *grec; unsigned int grec_len; - int i; - int len; - int num; + bool changed = false; + int i, len, num; int err = 0; if (!ipv6_mc_may_pull(skb, sizeof(*icmp6h))) @@ -1024,7 +2399,6 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, grec = (struct mld2_grec *)(skb->data + len); len += grec_len; - /* We treat these as MLDv1 reports for now. */ switch (grec->grec_type) { case MLD2_MODE_IS_INCLUDE: case MLD2_MODE_IS_EXCLUDE: @@ -1042,15 +2416,61 @@ 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) { - br_ip6_multicast_leave_group(br, port, &grec->grec_mca, - vid, src); + if (!port || mldv1) { + br_ip6_multicast_leave_group(br, port, + &grec->grec_mca, + vid, src); + continue; + } } else { err = br_ip6_multicast_add_group(br, port, &grec->grec_mca, vid, - src); + src, mldv1); if (err) break; } + + if (!port || mldv1) + continue; + + spin_lock_bh(&br->multicast_lock); + mdst = br_mdb_ip6_get(br, &grec->grec_mca, vid); + if (!mdst) + goto unlock_continue; + pg = br_multicast_find_port(mdst, port, src); + if (!pg || (pg->flags & MDB_PG_FLAGS_PERMANENT)) + goto unlock_continue; + switch (grec->grec_type) { + case MLD2_ALLOW_NEW_SOURCES: + changed = br_multicast_isinc_allow(pg, grec->grec_src, + nsrcs, + sizeof(struct in6_addr)); + break; + case MLD2_MODE_IS_INCLUDE: + changed = br_multicast_isinc_allow(pg, grec->grec_src, nsrcs, + sizeof(struct in6_addr)); + break; + case MLD2_MODE_IS_EXCLUDE: + changed = br_multicast_isexc(pg, grec->grec_src, nsrcs, + sizeof(struct in6_addr)); + break; + case MLD2_CHANGE_TO_INCLUDE: + changed = br_multicast_toin(pg, grec->grec_src, nsrcs, + sizeof(struct in6_addr)); + break; + case MLD2_CHANGE_TO_EXCLUDE: + changed = br_multicast_toex(pg, grec->grec_src, nsrcs, + sizeof(struct in6_addr)); + break; + case MLD2_BLOCK_OLD_SOURCES: + changed = br_multicast_block(pg, grec->grec_src, nsrcs, + sizeof(struct in6_addr)); + break; + } + if (changed) + br_mdb_notify(br->dev, mdst, pg, RTM_NEWMDB); +unlock_continue: + spin_unlock_bh(&br->multicast_lock); } return err; @@ -1065,16 +2485,16 @@ static bool br_ip4_multicast_select_querier(struct net_bridge *br, !timer_pending(&br->ip4_other_query.timer)) goto update; - if (!br->ip4_querier.addr.u.ip4) + if (!br->ip4_querier.addr.src.ip4) goto update; - if (ntohl(saddr) <= ntohl(br->ip4_querier.addr.u.ip4)) + if (ntohl(saddr) <= ntohl(br->ip4_querier.addr.src.ip4)) goto update; return false; update: - br->ip4_querier.addr.u.ip4 = saddr; + br->ip4_querier.addr.src.ip4 = saddr; /* update protected by general multicast_lock by caller */ rcu_assign_pointer(br->ip4_querier.port, port); @@ -1091,13 +2511,13 @@ static bool br_ip6_multicast_select_querier(struct net_bridge *br, !timer_pending(&br->ip6_other_query.timer)) goto update; - if (ipv6_addr_cmp(saddr, &br->ip6_querier.addr.u.ip6) <= 0) + if (ipv6_addr_cmp(saddr, &br->ip6_querier.addr.src.ip6) <= 0) goto update; return false; update: - br->ip6_querier.addr.u.ip6 = *saddr; + br->ip6_querier.addr.src.ip6 = *saddr; /* update protected by general multicast_lock by caller */ rcu_assign_pointer(br->ip6_querier.port, port); @@ -1112,10 +2532,10 @@ static bool br_multicast_select_querier(struct net_bridge *br, { switch (saddr->proto) { case htons(ETH_P_IP): - return br_ip4_multicast_select_querier(br, port, saddr->u.ip4); + return br_ip4_multicast_select_querier(br, port, saddr->src.ip4); #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): - return br_ip6_multicast_select_querier(br, port, &saddr->u.ip6); + return br_ip6_multicast_select_querier(br, port, &saddr->src.ip6); #endif } @@ -1245,7 +2665,8 @@ static void br_ip4_multicast_query(struct net_bridge *br, } } else if (transport_len >= sizeof(*ih3)) { ih3 = igmpv3_query_hdr(skb); - if (ih3->nsrcs) + if (ih3->nsrcs || + (br->multicast_igmp_version == 3 && group && ih3->suppress)) goto out; max_delay = ih3->code ? @@ -1256,7 +2677,7 @@ static void br_ip4_multicast_query(struct net_bridge *br, if (!group) { saddr.proto = htons(ETH_P_IP); - saddr.u.ip4 = iph->saddr; + saddr.src.ip4 = iph->saddr; br_multicast_query_received(br, port, &br->ip4_other_query, &saddr, max_delay); @@ -1280,7 +2701,9 @@ static void br_ip4_multicast_query(struct net_bridge *br, pp = &p->next) { if (timer_pending(&p->timer) ? time_after(p->timer.expires, now + max_delay) : - try_to_del_timer_sync(&p->timer) >= 0) + try_to_del_timer_sync(&p->timer) >= 0 && + (br->multicast_igmp_version == 2 || + p->filter_mode == MCAST_EXCLUDE)) mod_timer(&p->timer, now + max_delay); } @@ -1330,6 +2753,10 @@ 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 && + !ipv6_addr_any(&mld2q->mld2q_mca) && + mld2q->mld2q_suppress) + goto out; max_delay = max(msecs_to_jiffies(mldv2_mrc(mld2q)), 1UL); } @@ -1338,7 +2765,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, if (is_general_query) { saddr.proto = htons(ETH_P_IPV6); - saddr.u.ip6 = ipv6_hdr(skb)->saddr; + saddr.src.ip6 = ipv6_hdr(skb)->saddr; br_multicast_query_received(br, port, &br->ip6_other_query, &saddr, max_delay); @@ -1363,7 +2790,9 @@ static int br_ip6_multicast_query(struct net_bridge *br, pp = &p->next) { if (timer_pending(&p->timer) ? time_after(p->timer.expires, now + max_delay) : - try_to_del_timer_sync(&p->timer) >= 0) + try_to_del_timer_sync(&p->timer) >= 0 && + (br->multicast_mld_version == 1 || + p->filter_mode == MCAST_EXCLUDE)) mod_timer(&p->timer, now + max_delay); } @@ -1407,16 +2836,8 @@ br_multicast_leave_group(struct net_bridge *br, if (p->flags & MDB_PG_FLAGS_PERMANENT) break; - rcu_assign_pointer(*pp, p->next); - hlist_del_init(&p->mglist); - del_timer(&p->timer); - kfree_rcu(p, rcu); - br_mdb_notify(br->dev, port, group, RTM_DELMDB, - p->flags | MDB_PG_FLAGS_FAST_LEAVE); - - if (!mp->ports && !mp->host_joined && - netif_running(br->dev)) - mod_timer(&mp->timer, jiffies); + p->flags |= MDB_PG_FLAGS_FAST_LEAVE; + br_multicast_del_pg(mp, p, pp); } goto out; } @@ -1425,7 +2846,8 @@ br_multicast_leave_group(struct net_bridge *br, goto out; if (br_opt_get(br, BROPT_MULTICAST_QUERIER)) { - __br_multicast_send_query(br, port, &mp->addr); + __br_multicast_send_query(br, port, NULL, NULL, &mp->addr, + false, 0, NULL); time = jiffies + br->multicast_last_member_count * br->multicast_last_member_interval; @@ -1467,7 +2889,7 @@ br_multicast_leave_group(struct net_bridge *br, for (p = mlock_dereference(mp->ports, br); p != NULL; p = mlock_dereference(p->next, br)) { - if (p->port != port) + if (p->key.port != port) continue; if (!hlist_unhashed(&p->mglist) && @@ -1498,7 +2920,7 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br, own_query = port ? &port->ip4_own_query : &br->ip4_own_query; memset(&br_group, 0, sizeof(br_group)); - br_group.u.ip4 = group; + br_group.dst.ip4 = group; br_group.proto = htons(ETH_P_IP); br_group.vid = vid; @@ -1522,7 +2944,7 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br, own_query = port ? &port->ip6_own_query : &br->ip6_own_query; memset(&br_group, 0, sizeof(br_group)); - br_group.u.ip6 = *group; + br_group.dst.ip6 = *group; br_group.proto = htons(ETH_P_IPV6); br_group.vid = vid; @@ -1627,7 +3049,8 @@ 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); + err = br_ip4_multicast_add_group(br, port, ih->group, vid, src, + true); break; case IGMPV3_HOST_MEMBERSHIP_REPORT: err = br_ip4_multicast_igmp3_report(br, port, skb, vid); @@ -1706,7 +3129,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, 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); + src, true); break; case ICMPV6_MLD2_REPORT: err = br_ip6_multicast_mld2_report(br, port, skb, vid); @@ -1781,6 +3204,19 @@ static void br_ip6_multicast_query_expired(struct timer_list *t) } #endif +static void br_multicast_gc_work(struct work_struct *work) +{ + struct net_bridge *br = container_of(work, struct net_bridge, + mcast_gc_work); + HLIST_HEAD(deleted_head); + + spin_lock_bh(&br->multicast_lock); + hlist_move_list(&br->mcast_gc_list, &deleted_head); + spin_unlock_bh(&br->multicast_lock); + + br_multicast_gc(&deleted_head); +} + void br_multicast_init(struct net_bridge *br) { br->hash_max = BR_MULTICAST_DEFAULT_HASH_MAX; @@ -1821,6 +3257,8 @@ void br_multicast_init(struct net_bridge *br) br_ip6_multicast_query_expired, 0); #endif INIT_HLIST_HEAD(&br->mdb_list); + INIT_HLIST_HEAD(&br->mcast_gc_list); + INIT_WORK(&br->mcast_gc_work, br_multicast_gc_work); } static void br_ip4_multicast_join_snoopers(struct net_bridge *br) @@ -1924,18 +3362,18 @@ void br_multicast_stop(struct net_bridge *br) void br_multicast_dev_del(struct net_bridge *br) { struct net_bridge_mdb_entry *mp; + HLIST_HEAD(deleted_head); struct hlist_node *tmp; spin_lock_bh(&br->multicast_lock); - hlist_for_each_entry_safe(mp, tmp, &br->mdb_list, mdb_node) { - del_timer(&mp->timer); - rhashtable_remove_fast(&br->mdb_hash_tbl, &mp->rhnode, - br_mdb_rht_params); - hlist_del_rcu(&mp->mdb_node); - kfree_rcu(mp, rcu); - } + hlist_for_each_entry_safe(mp, tmp, &br->mdb_list, mdb_node) + br_multicast_del_mdb_entry(mp); + hlist_move_list(&br->mcast_gc_list, &deleted_head); spin_unlock_bh(&br->multicast_lock); + br_multicast_gc(&deleted_head); + cancel_work_sync(&br->mcast_gc_work); + rcu_barrier(); } @@ -2211,7 +3649,7 @@ int br_multicast_list_adjacent(struct net_device *dev, if (!entry) goto unlock; - entry->addr = group->addr; + entry->addr = group->key.addr; list_add(&entry->list, br_ip_list); count++; } @@ -2468,10 +3906,23 @@ void br_multicast_get_stats(const struct net_bridge *br, int br_mdb_hash_init(struct net_bridge *br) { - return rhashtable_init(&br->mdb_hash_tbl, &br_mdb_rht_params); + int err; + + err = rhashtable_init(&br->sg_port_tbl, &br_sg_port_rht_params); + if (err) + return err; + + err = rhashtable_init(&br->mdb_hash_tbl, &br_mdb_rht_params); + if (err) { + rhashtable_destroy(&br->sg_port_tbl); + return err; + } + + return 0; } void br_mdb_hash_fini(struct net_bridge *br) { + rhashtable_destroy(&br->sg_port_tbl); rhashtable_destroy(&br->mdb_hash_tbl); } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index da310f0ca725..92d64abffa87 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -1091,8 +1091,8 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_MCAST_IGMP_VERSION] = { .type = NLA_U8 }, [IFLA_BR_MCAST_MLD_VERSION] = { .type = NLA_U8 }, [IFLA_BR_VLAN_STATS_PER_PORT] = { .type = NLA_U8 }, - [IFLA_BR_MULTI_BOOLOPT] = { .type = NLA_EXACT_LEN, - .len = sizeof(struct br_boolopt_multi) }, + [IFLA_BR_MULTI_BOOLOPT] = + NLA_POLICY_EXACT_LEN(sizeof(struct br_boolopt_multi)), }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index baa1500f384f..345118e35c42 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -213,27 +213,71 @@ struct net_bridge_fdb_entry { #define MDB_PG_FLAGS_PERMANENT BIT(0) #define MDB_PG_FLAGS_OFFLOAD BIT(1) #define MDB_PG_FLAGS_FAST_LEAVE BIT(2) +#define MDB_PG_FLAGS_STAR_EXCL BIT(3) +#define MDB_PG_FLAGS_BLOCKED BIT(4) -struct net_bridge_port_group { - struct net_bridge_port *port; - struct net_bridge_port_group __rcu *next; - struct hlist_node mglist; - struct rcu_head rcu; +#define PG_SRC_ENT_LIMIT 32 + +#define BR_SGRP_F_DELETE BIT(0) +#define BR_SGRP_F_SEND BIT(1) +#define BR_SGRP_F_INSTALLED BIT(2) + +struct net_bridge_mcast_gc { + struct hlist_node gc_node; + void (*destroy)(struct net_bridge_mcast_gc *gc); +}; + +struct net_bridge_group_src { + struct hlist_node node; + + struct br_ip addr; + struct net_bridge_port_group *pg; + u8 flags; + u8 src_query_rexmit_cnt; struct timer_list timer; + + struct net_bridge *br; + struct net_bridge_mcast_gc mcast_gc; + struct rcu_head rcu; +}; + +struct net_bridge_port_group_sg_key { + struct net_bridge_port *port; struct br_ip addr; +}; + +struct net_bridge_port_group { + struct net_bridge_port_group __rcu *next; + struct net_bridge_port_group_sg_key key; unsigned char eth_addr[ETH_ALEN] __aligned(2); unsigned char flags; + unsigned char filter_mode; + unsigned char grp_query_rexmit_cnt; + unsigned char rt_protocol; + + struct hlist_head src_list; + unsigned int src_ents; + struct timer_list timer; + struct timer_list rexmit_timer; + struct hlist_node mglist; + + struct rhash_head rhnode; + struct net_bridge_mcast_gc mcast_gc; + struct rcu_head rcu; }; struct net_bridge_mdb_entry { struct rhash_head rhnode; struct net_bridge *br; struct net_bridge_port_group __rcu *ports; - struct rcu_head rcu; - struct timer_list timer; struct br_ip addr; bool host_joined; + + struct timer_list timer; struct hlist_node mdb_node; + + struct net_bridge_mcast_gc mcast_gc; + struct rcu_head rcu; }; struct net_bridge_port { @@ -405,7 +449,9 @@ struct net_bridge { unsigned long multicast_startup_query_interval; struct rhashtable mdb_hash_tbl; + struct rhashtable sg_port_tbl; + struct hlist_head mcast_gc_list; struct hlist_head mdb_list; struct hlist_head router_list; @@ -419,6 +465,7 @@ struct net_bridge { 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 struct timer_list hello_timer; @@ -766,13 +813,17 @@ br_multicast_new_group(struct net_bridge *br, struct br_ip *group); struct net_bridge_port_group * br_multicast_new_port_group(struct net_bridge_port *port, struct br_ip *group, struct net_bridge_port_group __rcu *next, - unsigned char flags, const unsigned char *src); + unsigned char flags, const unsigned char *src, + u8 filter_mode, u8 rt_protocol); 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_port *port, - struct br_ip *group, int type, u8 flags); +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, 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, const struct sk_buff *skb, u8 type, u8 dir); int br_multicast_init_stats(struct net_bridge *br); @@ -784,6 +835,10 @@ 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_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); +void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp, + struct net_bridge_port_group *sg); #define mlock_dereference(X, br) \ rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock)) @@ -832,10 +887,52 @@ static inline bool br_multicast_querier_exists(struct net_bridge *br, } } +static inline bool br_multicast_is_star_g(const struct br_ip *ip) +{ + switch (ip->proto) { + case htons(ETH_P_IP): + return ipv4_is_zeronet(ip->src.ip4); +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + return ipv6_addr_any(&ip->src.ip6); +#endif + default: + return false; + } +} + +static inline bool br_multicast_should_handle_mode(const struct net_bridge *br, + __be16 proto) +{ + switch (proto) { + case htons(ETH_P_IP): + return !!(br->multicast_igmp_version == 3); +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + return !!(br->multicast_mld_version == 2); +#endif + default: + return false; + } +} + 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) +{ + return br->multicast_last_member_interval * + br->multicast_last_member_count; +} + +static inline unsigned long br_multicast_gmi(const struct net_bridge *br) +{ + /* use the RFC default of 2 for QRV */ + return 2 * br->multicast_query_interval + + br->multicast_query_response_interval; +} #else static inline int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index ee8780080be5..3e493eb85bb2 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -140,7 +140,7 @@ static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, return err == -EOPNOTSUPP ? 0 : err; } -/* Returns a master vlan, if it didn't exist it gets created. In all cases a +/* Returns a master vlan, if it didn't exist it gets created. In all cases * a reference is taken to the master vlan before returning. */ static struct net_bridge_vlan * @@ -1897,8 +1897,8 @@ out_err: } static const struct nla_policy br_vlan_db_policy[BRIDGE_VLANDB_ENTRY_MAX + 1] = { - [BRIDGE_VLANDB_ENTRY_INFO] = { .type = NLA_EXACT_LEN, - .len = sizeof(struct bridge_vlan_info) }, + [BRIDGE_VLANDB_ENTRY_INFO] = + NLA_POLICY_EXACT_LEN(sizeof(struct bridge_vlan_info)), [BRIDGE_VLANDB_ENTRY_RANGE] = { .type = NLA_U16 }, [BRIDGE_VLANDB_ENTRY_STATE] = { .type = NLA_U8 }, [BRIDGE_VLANDB_ENTRY_TUNNEL_INFO] = { .type = NLA_NESTED }, diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c index 12a4f4d93681..3fda71a8579d 100644 --- a/net/bridge/netfilter/ebt_dnat.c +++ b/net/bridge/netfilter/ebt_dnat.c @@ -21,7 +21,7 @@ ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_nat_info *info = par->targinfo; - if (skb_ensure_writable(skb, ETH_ALEN)) + if (skb_ensure_writable(skb, 0)) return EBT_DROP; ether_addr_copy(eth_hdr(skb)->h_dest, info->mac); diff --git a/net/bridge/netfilter/ebt_redirect.c b/net/bridge/netfilter/ebt_redirect.c index 0cad62a4052b..307790562b49 100644 --- a/net/bridge/netfilter/ebt_redirect.c +++ b/net/bridge/netfilter/ebt_redirect.c @@ -21,7 +21,7 @@ ebt_redirect_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_redirect_info *info = par->targinfo; - if (skb_ensure_writable(skb, ETH_ALEN)) + if (skb_ensure_writable(skb, 0)) return EBT_DROP; if (xt_hooknum(par) != NF_BR_BROUTING) diff --git a/net/bridge/netfilter/ebt_snat.c b/net/bridge/netfilter/ebt_snat.c index 27443bf229a3..7dfbcdfc30e5 100644 --- a/net/bridge/netfilter/ebt_snat.c +++ b/net/bridge/netfilter/ebt_snat.c @@ -22,7 +22,7 @@ ebt_snat_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_nat_info *info = par->targinfo; - if (skb_ensure_writable(skb, ETH_ALEN * 2)) + if (skb_ensure_writable(skb, 0)) return EBT_DROP; ether_addr_copy(eth_hdr(skb)->h_source, info->mac); diff --git a/net/bridge/netfilter/ebt_stp.c b/net/bridge/netfilter/ebt_stp.c index 0d6d20c9105e..8f68afda5f81 100644 --- a/net/bridge/netfilter/ebt_stp.c +++ b/net/bridge/netfilter/ebt_stp.c @@ -15,7 +15,6 @@ #include <linux/netfilter_bridge/ebt_stp.h> #define BPDU_TYPE_CONFIG 0 -#define BPDU_TYPE_TCN 0x80 struct stp_header { u8 dsap; diff --git a/net/caif/cfsrvl.c b/net/caif/cfsrvl.c index d0a4d0ac7045..9cef9496a707 100644 --- a/net/caif/cfsrvl.c +++ b/net/caif/cfsrvl.c @@ -21,7 +21,6 @@ #define SRVL_FLOW_OFF 0x81 #define SRVL_FLOW_ON 0x80 #define SRVL_SET_PIN 0x82 -#define SRVL_CTRL_PKT_SIZE 1 #define container_obj(layr) container_of(layr, struct cfsrvl, layer) diff --git a/net/can/Kconfig b/net/can/Kconfig index 25436a715db3..224e5e0283a9 100644 --- a/net/can/Kconfig +++ b/net/can/Kconfig @@ -55,6 +55,20 @@ config CAN_GW source "net/can/j1939/Kconfig" +config CAN_ISOTP + tristate "ISO 15765-2:2016 CAN transport protocol" + help + CAN Transport Protocols offer support for segmented Point-to-Point + communication between CAN nodes via two defined CAN Identifiers. + As CAN frames can only transport a small amount of data bytes + (max. 8 bytes for 'classic' CAN and max. 64 bytes for CAN FD) this + segmentation is needed to transport longer PDUs as needed e.g. for + vehicle diagnosis (UDS, ISO 14229) or IP-over-CAN traffic. + This protocol driver implements data transfers according to + ISO 15765-2:2016 for 'classic' CAN and CAN FD frame types. + If you want to perform automotive vehicle diagnostic services (UDS), + say 'y'. + source "drivers/net/can/Kconfig" endif diff --git a/net/can/Makefile b/net/can/Makefile index 08bd217fc051..58f2c31c1ef3 100644 --- a/net/can/Makefile +++ b/net/can/Makefile @@ -17,3 +17,6 @@ obj-$(CONFIG_CAN_GW) += can-gw.o can-gw-y := gw.o obj-$(CONFIG_CAN_J1939) += j1939/ + +obj-$(CONFIG_CAN_ISOTP) += can-isotp.o +can-isotp-y := isotp.o diff --git a/net/can/af_can.c b/net/can/af_can.c index 5c06404bdf3e..6373ab9c5507 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -338,7 +338,7 @@ static unsigned int effhash(canid_t can_id) * can_rcv_list_find - determine optimal filterlist inside device filter struct * @can_id: pointer to CAN identifier of a given can_filter * @mask: pointer to CAN mask of a given can_filter - * @d: pointer to the device filter struct + * @dev_rcv_lists: pointer to the device filter struct * * Description: * Returns the optimal filterlist to reduce the filter handling in the @@ -358,7 +358,7 @@ static unsigned int effhash(canid_t can_id) * * Return: * Pointer to optimal filterlist for the given can_id/mask pair. - * Constistency checked mask. + * Consistency checked mask. * Reduced can_id to have a preprocessed filter compare value. */ static struct hlist_head *can_rcv_list_find(canid_t *can_id, canid_t *mask, @@ -411,7 +411,7 @@ static struct hlist_head *can_rcv_list_find(canid_t *can_id, canid_t *mask, /** * can_rx_register - subscribe CAN frames from a specific interface * @net: the applicable net namespace - * @dev: pointer to netdevice (NULL => subcribe from 'all' CAN devices list) + * @dev: pointer to netdevice (NULL => subscribe from 'all' CAN devices list) * @can_id: CAN identifier (see description) * @mask: CAN mask (see description) * @func: callback function on filter match @@ -875,7 +875,7 @@ static __init int can_init(void) offsetof(struct can_frame, data) != offsetof(struct canfd_frame, data)); - pr_info("can: controller area network core (" CAN_VERSION_STRING ")\n"); + pr_info("can: controller area network core\n"); rcv_cache = kmem_cache_create("can_receiver", sizeof(struct receiver), 0, 0, NULL); diff --git a/net/can/bcm.c b/net/can/bcm.c index d14ea12affb1..0e5c37be4a2b 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* * bcm.c - Broadcast Manager to filter/send (cyclic) CAN content * @@ -81,8 +81,6 @@ (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \ (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG)) -#define CAN_BCM_VERSION "20170425" - MODULE_DESCRIPTION("PF_CAN broadcast manager protocol"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>"); @@ -1696,7 +1694,7 @@ static int __init bcm_module_init(void) { int err; - pr_info("can: broadcast manager protocol (rev " CAN_BCM_VERSION " t)\n"); + pr_info("can: broadcast manager protocol\n"); err = can_proto_register(&bcm_can_proto); if (err < 0) { diff --git a/net/can/gw.c b/net/can/gw.c index 65d60c93af29..6b790b6ff8d2 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* gw.c - CAN frame Gateway/Router/Bridge with netlink interface * * Copyright (c) 2019 Volkswagen Group Electronic Research @@ -59,7 +59,6 @@ #include <net/net_namespace.h> #include <net/sock.h> -#define CAN_GW_VERSION "20190810" #define CAN_GW_NAME "can-gw" MODULE_DESCRIPTION("PF_CAN netlink gateway"); @@ -1194,8 +1193,7 @@ static __init int cgw_module_init(void) /* sanitize given module parameter */ max_hops = clamp_t(unsigned int, max_hops, CGW_MIN_HOPS, CGW_MAX_HOPS); - pr_info("can: netlink gateway (rev " CAN_GW_VERSION ") max_hops=%d\n", - max_hops); + pr_info("can: netlink gateway - max_hops=%d\n", max_hops); ret = register_pernet_subsys(&cangw_pernet_ops); if (ret) diff --git a/net/can/isotp.c b/net/can/isotp.c new file mode 100644 index 000000000000..4c2062875893 --- /dev/null +++ b/net/can/isotp.c @@ -0,0 +1,1424 @@ +// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) +/* isotp.c - ISO 15765-2 CAN transport protocol for protocol family CAN + * + * This implementation does not provide ISO-TP specific return values to the + * userspace. + * + * - RX path timeout of data reception leads to -ETIMEDOUT + * - RX path SN mismatch leads to -EILSEQ + * - RX path data reception with wrong padding leads to -EBADMSG + * - TX path flowcontrol reception timeout leads to -ECOMM + * - TX path flowcontrol reception overflow leads to -EMSGSIZE + * - TX path flowcontrol reception with wrong layout/padding leads to -EBADMSG + * - when a transfer (tx) is on the run the next write() blocks until it's done + * - use CAN_ISOTP_WAIT_TX_DONE flag to block the caller until the PDU is sent + * - as we have static buffers the check whether the PDU fits into the buffer + * is done at FF reception time (no support for sending 'wait frames') + * - take care of the tx-queue-len as traffic shaping is still on the TODO list + * + * Copyright (c) 2020 Volkswagen Group Electronic Research + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of Volkswagen nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * Alternatively, provided that this notice is retained in full, this + * software may be distributed under the terms of the GNU General + * Public License ("GPL") version 2, in which case the provisions of the + * GPL apply INSTEAD OF those given above. + * + * The provided data structures and external interfaces from this code + * are not restricted to be used by modules with a GPL compatible license. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH + * DAMAGE. + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/hrtimer.h> +#include <linux/wait.h> +#include <linux/uio.h> +#include <linux/net.h> +#include <linux/netdevice.h> +#include <linux/socket.h> +#include <linux/if_arp.h> +#include <linux/skbuff.h> +#include <linux/can.h> +#include <linux/can/core.h> +#include <linux/can/skb.h> +#include <linux/can/isotp.h> +#include <linux/slab.h> +#include <net/sock.h> +#include <net/net_namespace.h> + +MODULE_DESCRIPTION("PF_CAN isotp 15765-2:2016 protocol"); +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_AUTHOR("Oliver Hartkopp <socketcan@hartkopp.net>"); +MODULE_ALIAS("can-proto-6"); + +#define SINGLE_MASK(id) (((id) & CAN_EFF_FLAG) ? \ + (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \ + (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG)) + +/* ISO 15765-2:2016 supports more than 4095 byte per ISO PDU as the FF_DL can + * take full 32 bit values (4 Gbyte). We would need some good concept to handle + * this between user space and kernel space. For now increase the static buffer + * to something about 8 kbyte to be able to test this new functionality. + */ +#define MAX_MSG_LENGTH 8200 + +/* N_PCI type values in bits 7-4 of N_PCI bytes */ +#define N_PCI_SF 0x00 /* single frame */ +#define N_PCI_FF 0x10 /* first frame */ +#define N_PCI_CF 0x20 /* consecutive frame */ +#define N_PCI_FC 0x30 /* flow control */ + +#define N_PCI_SZ 1 /* size of the PCI byte #1 */ +#define SF_PCI_SZ4 1 /* size of SingleFrame PCI including 4 bit SF_DL */ +#define SF_PCI_SZ8 2 /* size of SingleFrame PCI including 8 bit SF_DL */ +#define FF_PCI_SZ12 2 /* size of FirstFrame PCI including 12 bit FF_DL */ +#define FF_PCI_SZ32 6 /* size of FirstFrame PCI including 32 bit FF_DL */ +#define FC_CONTENT_SZ 3 /* flow control content size in byte (FS/BS/STmin) */ + +#define ISOTP_CHECK_PADDING (CAN_ISOTP_CHK_PAD_LEN | CAN_ISOTP_CHK_PAD_DATA) + +/* Flow Status given in FC frame */ +#define ISOTP_FC_CTS 0 /* clear to send */ +#define ISOTP_FC_WT 1 /* wait */ +#define ISOTP_FC_OVFLW 2 /* overflow */ + +enum { + ISOTP_IDLE = 0, + ISOTP_WAIT_FIRST_FC, + ISOTP_WAIT_FC, + ISOTP_WAIT_DATA, + ISOTP_SENDING +}; + +struct tpcon { + int idx; + int len; + u8 state; + u8 bs; + u8 sn; + u8 ll_dl; + u8 buf[MAX_MSG_LENGTH + 1]; +}; + +struct isotp_sock { + struct sock sk; + int bound; + int ifindex; + canid_t txid; + canid_t rxid; + ktime_t tx_gap; + ktime_t lastrxcf_tstamp; + struct hrtimer rxtimer, txtimer; + struct can_isotp_options opt; + struct can_isotp_fc_options rxfc, txfc; + struct can_isotp_ll_options ll; + u32 force_tx_stmin; + u32 force_rx_stmin; + struct tpcon rx, tx; + struct notifier_block notifier; + wait_queue_head_t wait; +}; + +static inline struct isotp_sock *isotp_sk(const struct sock *sk) +{ + return (struct isotp_sock *)sk; +} + +static enum hrtimer_restart isotp_rx_timer_handler(struct hrtimer *hrtimer) +{ + struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, + rxtimer); + struct sock *sk = &so->sk; + + if (so->rx.state == ISOTP_WAIT_DATA) { + /* we did not get new data frames in time */ + + /* report 'connection timed out' */ + sk->sk_err = ETIMEDOUT; + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_error_report(sk); + + /* reset rx state */ + so->rx.state = ISOTP_IDLE; + } + + return HRTIMER_NORESTART; +} + +static int isotp_send_fc(struct sock *sk, int ae, u8 flowstatus) +{ + struct net_device *dev; + struct sk_buff *nskb; + struct canfd_frame *ncf; + struct isotp_sock *so = isotp_sk(sk); + int can_send_ret; + + nskb = alloc_skb(so->ll.mtu + sizeof(struct can_skb_priv), gfp_any()); + if (!nskb) + return 1; + + dev = dev_get_by_index(sock_net(sk), so->ifindex); + if (!dev) { + kfree_skb(nskb); + return 1; + } + + can_skb_reserve(nskb); + can_skb_prv(nskb)->ifindex = dev->ifindex; + can_skb_prv(nskb)->skbcnt = 0; + + nskb->dev = dev; + can_skb_set_owner(nskb, sk); + ncf = (struct canfd_frame *)nskb->data; + skb_put(nskb, so->ll.mtu); + + /* create & send flow control reply */ + ncf->can_id = so->txid; + + if (so->opt.flags & CAN_ISOTP_TX_PADDING) { + memset(ncf->data, so->opt.txpad_content, CAN_MAX_DLEN); + ncf->len = CAN_MAX_DLEN; + } else { + ncf->len = ae + FC_CONTENT_SZ; + } + + ncf->data[ae] = N_PCI_FC | flowstatus; + ncf->data[ae + 1] = so->rxfc.bs; + ncf->data[ae + 2] = so->rxfc.stmin; + + if (ae) + ncf->data[0] = so->opt.ext_address; + + if (so->ll.mtu == CANFD_MTU) + ncf->flags = so->ll.tx_flags; + + can_send_ret = can_send(nskb, 1); + if (can_send_ret) + pr_notice_once("can-isotp: %s: can_send_ret %d\n", + __func__, can_send_ret); + + dev_put(dev); + + /* reset blocksize counter */ + so->rx.bs = 0; + + /* reset last CF frame rx timestamp for rx stmin enforcement */ + so->lastrxcf_tstamp = ktime_set(0, 0); + + /* start rx timeout watchdog */ + hrtimer_start(&so->rxtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); + return 0; +} + +static void isotp_rcv_skb(struct sk_buff *skb, struct sock *sk) +{ + struct sockaddr_can *addr = (struct sockaddr_can *)skb->cb; + + BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct sockaddr_can)); + + memset(addr, 0, sizeof(*addr)); + addr->can_family = AF_CAN; + addr->can_ifindex = skb->dev->ifindex; + + if (sock_queue_rcv_skb(sk, skb) < 0) + kfree_skb(skb); +} + +static u8 padlen(u8 datalen) +{ + const u8 plen[] = {8, 8, 8, 8, 8, 8, 8, 8, 8, /* 0 - 8 */ + 12, 12, 12, 12, /* 9 - 12 */ + 16, 16, 16, 16, /* 13 - 16 */ + 20, 20, 20, 20, /* 17 - 20 */ + 24, 24, 24, 24, /* 21 - 24 */ + 32, 32, 32, 32, 32, 32, 32, 32, /* 25 - 32 */ + 48, 48, 48, 48, 48, 48, 48, 48, /* 33 - 40 */ + 48, 48, 48, 48, 48, 48, 48, 48}; /* 41 - 48 */ + + if (datalen > 48) + return 64; + + return plen[datalen]; +} + +/* check for length optimization and return 1/true when the check fails */ +static int check_optimized(struct canfd_frame *cf, int start_index) +{ + /* for CAN_DL <= 8 the start_index is equal to the CAN_DL as the + * padding would start at this point. E.g. if the padding would + * start at cf.data[7] cf->len has to be 7 to be optimal. + * Note: The data[] index starts with zero. + */ + if (cf->len <= CAN_MAX_DLEN) + return (cf->len != start_index); + + /* This relation is also valid in the non-linear DLC range, where + * we need to take care of the minimal next possible CAN_DL. + * The correct check would be (padlen(cf->len) != padlen(start_index)). + * But as cf->len can only take discrete values from 12, .., 64 at this + * point the padlen(cf->len) is always equal to cf->len. + */ + return (cf->len != padlen(start_index)); +} + +/* check padding and return 1/true when the check fails */ +static int check_pad(struct isotp_sock *so, struct canfd_frame *cf, + int start_index, u8 content) +{ + int i; + + /* no RX_PADDING value => check length of optimized frame length */ + if (!(so->opt.flags & CAN_ISOTP_RX_PADDING)) { + if (so->opt.flags & CAN_ISOTP_CHK_PAD_LEN) + return check_optimized(cf, start_index); + + /* no valid test against empty value => ignore frame */ + return 1; + } + + /* check datalength of correctly padded CAN frame */ + if ((so->opt.flags & CAN_ISOTP_CHK_PAD_LEN) && + cf->len != padlen(cf->len)) + return 1; + + /* check padding content */ + if (so->opt.flags & CAN_ISOTP_CHK_PAD_DATA) { + for (i = start_index; i < cf->len; i++) + if (cf->data[i] != content) + return 1; + } + return 0; +} + +static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) +{ + struct sock *sk = &so->sk; + + if (so->tx.state != ISOTP_WAIT_FC && + so->tx.state != ISOTP_WAIT_FIRST_FC) + return 0; + + hrtimer_cancel(&so->txtimer); + + if ((cf->len < ae + FC_CONTENT_SZ) || + ((so->opt.flags & ISOTP_CHECK_PADDING) && + check_pad(so, cf, ae + FC_CONTENT_SZ, so->opt.rxpad_content))) { + /* malformed PDU - report 'not a data message' */ + sk->sk_err = EBADMSG; + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_error_report(sk); + + so->tx.state = ISOTP_IDLE; + wake_up_interruptible(&so->wait); + return 1; + } + + /* get communication parameters only from the first FC frame */ + if (so->tx.state == ISOTP_WAIT_FIRST_FC) { + so->txfc.bs = cf->data[ae + 1]; + so->txfc.stmin = cf->data[ae + 2]; + + /* fix wrong STmin values according spec */ + if (so->txfc.stmin > 0x7F && + (so->txfc.stmin < 0xF1 || so->txfc.stmin > 0xF9)) + so->txfc.stmin = 0x7F; + + so->tx_gap = ktime_set(0, 0); + /* add transmission time for CAN frame N_As */ + so->tx_gap = ktime_add_ns(so->tx_gap, so->opt.frame_txtime); + /* add waiting time for consecutive frames N_Cs */ + if (so->opt.flags & CAN_ISOTP_FORCE_TXSTMIN) + so->tx_gap = ktime_add_ns(so->tx_gap, + so->force_tx_stmin); + else if (so->txfc.stmin < 0x80) + so->tx_gap = ktime_add_ns(so->tx_gap, + so->txfc.stmin * 1000000); + else + so->tx_gap = ktime_add_ns(so->tx_gap, + (so->txfc.stmin - 0xF0) + * 100000); + so->tx.state = ISOTP_WAIT_FC; + } + + switch (cf->data[ae] & 0x0F) { + case ISOTP_FC_CTS: + so->tx.bs = 0; + so->tx.state = ISOTP_SENDING; + /* start cyclic timer for sending CF frame */ + hrtimer_start(&so->txtimer, so->tx_gap, + HRTIMER_MODE_REL_SOFT); + break; + + case ISOTP_FC_WT: + /* start timer to wait for next FC frame */ + hrtimer_start(&so->txtimer, ktime_set(1, 0), + HRTIMER_MODE_REL_SOFT); + break; + + case ISOTP_FC_OVFLW: + /* overflow on receiver side - report 'message too long' */ + sk->sk_err = EMSGSIZE; + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_error_report(sk); + fallthrough; + + default: + /* stop this tx job */ + so->tx.state = ISOTP_IDLE; + wake_up_interruptible(&so->wait); + } + return 0; +} + +static int isotp_rcv_sf(struct sock *sk, struct canfd_frame *cf, int pcilen, + struct sk_buff *skb, int len) +{ + struct isotp_sock *so = isotp_sk(sk); + struct sk_buff *nskb; + + hrtimer_cancel(&so->rxtimer); + so->rx.state = ISOTP_IDLE; + + if (!len || len > cf->len - pcilen) + return 1; + + if ((so->opt.flags & ISOTP_CHECK_PADDING) && + check_pad(so, cf, pcilen + len, so->opt.rxpad_content)) { + /* malformed PDU - report 'not a data message' */ + sk->sk_err = EBADMSG; + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_error_report(sk); + return 1; + } + + nskb = alloc_skb(len, gfp_any()); + if (!nskb) + return 1; + + memcpy(skb_put(nskb, len), &cf->data[pcilen], len); + + nskb->tstamp = skb->tstamp; + nskb->dev = skb->dev; + isotp_rcv_skb(nskb, sk); + return 0; +} + +static int isotp_rcv_ff(struct sock *sk, struct canfd_frame *cf, int ae) +{ + struct isotp_sock *so = isotp_sk(sk); + int i; + int off; + int ff_pci_sz; + + hrtimer_cancel(&so->rxtimer); + so->rx.state = ISOTP_IDLE; + + /* get the used sender LL_DL from the (first) CAN frame data length */ + so->rx.ll_dl = padlen(cf->len); + + /* the first frame has to use the entire frame up to LL_DL length */ + if (cf->len != so->rx.ll_dl) + return 1; + + /* get the FF_DL */ + so->rx.len = (cf->data[ae] & 0x0F) << 8; + so->rx.len += cf->data[ae + 1]; + + /* Check for FF_DL escape sequence supporting 32 bit PDU length */ + if (so->rx.len) { + ff_pci_sz = FF_PCI_SZ12; + } else { + /* FF_DL = 0 => get real length from next 4 bytes */ + so->rx.len = cf->data[ae + 2] << 24; + so->rx.len += cf->data[ae + 3] << 16; + so->rx.len += cf->data[ae + 4] << 8; + so->rx.len += cf->data[ae + 5]; + ff_pci_sz = FF_PCI_SZ32; + } + + /* take care of a potential SF_DL ESC offset for TX_DL > 8 */ + off = (so->rx.ll_dl > CAN_MAX_DLEN) ? 1 : 0; + + if (so->rx.len + ae + off + ff_pci_sz < so->rx.ll_dl) + return 1; + + if (so->rx.len > MAX_MSG_LENGTH) { + /* send FC frame with overflow status */ + isotp_send_fc(sk, ae, ISOTP_FC_OVFLW); + return 1; + } + + /* copy the first received data bytes */ + so->rx.idx = 0; + for (i = ae + ff_pci_sz; i < so->rx.ll_dl; i++) + so->rx.buf[so->rx.idx++] = cf->data[i]; + + /* initial setup for this pdu reception */ + so->rx.sn = 1; + so->rx.state = ISOTP_WAIT_DATA; + + /* no creation of flow control frames */ + if (so->opt.flags & CAN_ISOTP_LISTEN_MODE) + return 0; + + /* send our first FC frame */ + isotp_send_fc(sk, ae, ISOTP_FC_CTS); + return 0; +} + +static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae, + struct sk_buff *skb) +{ + struct isotp_sock *so = isotp_sk(sk); + struct sk_buff *nskb; + int i; + + if (so->rx.state != ISOTP_WAIT_DATA) + return 0; + + /* drop if timestamp gap is less than force_rx_stmin nano secs */ + if (so->opt.flags & CAN_ISOTP_FORCE_RXSTMIN) { + if (ktime_to_ns(ktime_sub(skb->tstamp, so->lastrxcf_tstamp)) < + so->force_rx_stmin) + return 0; + + so->lastrxcf_tstamp = skb->tstamp; + } + + hrtimer_cancel(&so->rxtimer); + + /* CFs are never longer than the FF */ + if (cf->len > so->rx.ll_dl) + return 1; + + /* CFs have usually the LL_DL length */ + if (cf->len < so->rx.ll_dl) { + /* this is only allowed for the last CF */ + if (so->rx.len - so->rx.idx > so->rx.ll_dl - ae - N_PCI_SZ) + return 1; + } + + if ((cf->data[ae] & 0x0F) != so->rx.sn) { + /* wrong sn detected - report 'illegal byte sequence' */ + sk->sk_err = EILSEQ; + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_error_report(sk); + + /* reset rx state */ + so->rx.state = ISOTP_IDLE; + return 1; + } + so->rx.sn++; + so->rx.sn %= 16; + + for (i = ae + N_PCI_SZ; i < cf->len; i++) { + so->rx.buf[so->rx.idx++] = cf->data[i]; + if (so->rx.idx >= so->rx.len) + break; + } + + if (so->rx.idx >= so->rx.len) { + /* we are done */ + so->rx.state = ISOTP_IDLE; + + if ((so->opt.flags & ISOTP_CHECK_PADDING) && + check_pad(so, cf, i + 1, so->opt.rxpad_content)) { + /* malformed PDU - report 'not a data message' */ + sk->sk_err = EBADMSG; + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_error_report(sk); + return 1; + } + + nskb = alloc_skb(so->rx.len, gfp_any()); + if (!nskb) + return 1; + + memcpy(skb_put(nskb, so->rx.len), so->rx.buf, + so->rx.len); + + nskb->tstamp = skb->tstamp; + nskb->dev = skb->dev; + isotp_rcv_skb(nskb, sk); + return 0; + } + + /* no creation of flow control frames */ + if (so->opt.flags & CAN_ISOTP_LISTEN_MODE) + return 0; + + /* perform blocksize handling, if enabled */ + if (!so->rxfc.bs || ++so->rx.bs < so->rxfc.bs) { + /* start rx timeout watchdog */ + hrtimer_start(&so->rxtimer, ktime_set(1, 0), + HRTIMER_MODE_REL_SOFT); + return 0; + } + + /* we reached the specified blocksize so->rxfc.bs */ + isotp_send_fc(sk, ae, ISOTP_FC_CTS); + return 0; +} + +static void isotp_rcv(struct sk_buff *skb, void *data) +{ + struct sock *sk = (struct sock *)data; + struct isotp_sock *so = isotp_sk(sk); + struct canfd_frame *cf; + int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0; + u8 n_pci_type, sf_dl; + + /* Strictly receive only frames with the configured MTU size + * => clear separation of CAN2.0 / CAN FD transport channels + */ + if (skb->len != so->ll.mtu) + return; + + cf = (struct canfd_frame *)skb->data; + + /* if enabled: check reception of my configured extended address */ + if (ae && cf->data[0] != so->opt.rx_ext_address) + return; + + n_pci_type = cf->data[ae] & 0xF0; + + if (so->opt.flags & CAN_ISOTP_HALF_DUPLEX) { + /* check rx/tx path half duplex expectations */ + if ((so->tx.state != ISOTP_IDLE && n_pci_type != N_PCI_FC) || + (so->rx.state != ISOTP_IDLE && n_pci_type == N_PCI_FC)) + return; + } + + switch (n_pci_type) { + case N_PCI_FC: + /* tx path: flow control frame containing the FC parameters */ + isotp_rcv_fc(so, cf, ae); + break; + + case N_PCI_SF: + /* rx path: single frame + * + * As we do not have a rx.ll_dl configuration, we can only test + * if the CAN frames payload length matches the LL_DL == 8 + * requirements - no matter if it's CAN 2.0 or CAN FD + */ + + /* get the SF_DL from the N_PCI byte */ + sf_dl = cf->data[ae] & 0x0F; + + if (cf->len <= CAN_MAX_DLEN) { + isotp_rcv_sf(sk, cf, SF_PCI_SZ4 + ae, skb, sf_dl); + } else { + if (skb->len == CANFD_MTU) { + /* We have a CAN FD frame and CAN_DL is greater than 8: + * Only frames with the SF_DL == 0 ESC value are valid. + * + * If so take care of the increased SF PCI size + * (SF_PCI_SZ8) to point to the message content behind + * the extended SF PCI info and get the real SF_DL + * length value from the formerly first data byte. + */ + if (sf_dl == 0) + isotp_rcv_sf(sk, cf, SF_PCI_SZ8 + ae, skb, + cf->data[SF_PCI_SZ4 + ae]); + } + } + break; + + case N_PCI_FF: + /* rx path: first frame */ + isotp_rcv_ff(sk, cf, ae); + break; + + case N_PCI_CF: + /* rx path: consecutive frame */ + isotp_rcv_cf(sk, cf, ae, skb); + break; + } +} + +static void isotp_fill_dataframe(struct canfd_frame *cf, struct isotp_sock *so, + int ae, int off) +{ + int pcilen = N_PCI_SZ + ae + off; + int space = so->tx.ll_dl - pcilen; + int num = min_t(int, so->tx.len - so->tx.idx, space); + int i; + + cf->can_id = so->txid; + cf->len = num + pcilen; + + if (num < space) { + if (so->opt.flags & CAN_ISOTP_TX_PADDING) { + /* user requested padding */ + cf->len = padlen(cf->len); + memset(cf->data, so->opt.txpad_content, cf->len); + } else if (cf->len > CAN_MAX_DLEN) { + /* mandatory padding for CAN FD frames */ + cf->len = padlen(cf->len); + memset(cf->data, CAN_ISOTP_DEFAULT_PAD_CONTENT, + cf->len); + } + } + + for (i = 0; i < num; i++) + cf->data[pcilen + i] = so->tx.buf[so->tx.idx++]; + + if (ae) + cf->data[0] = so->opt.ext_address; +} + +static void isotp_create_fframe(struct canfd_frame *cf, struct isotp_sock *so, + int ae) +{ + int i; + int ff_pci_sz; + + cf->can_id = so->txid; + cf->len = so->tx.ll_dl; + if (ae) + cf->data[0] = so->opt.ext_address; + + /* create N_PCI bytes with 12/32 bit FF_DL data length */ + if (so->tx.len > 4095) { + /* use 32 bit FF_DL notation */ + cf->data[ae] = N_PCI_FF; + cf->data[ae + 1] = 0; + cf->data[ae + 2] = (u8)(so->tx.len >> 24) & 0xFFU; + cf->data[ae + 3] = (u8)(so->tx.len >> 16) & 0xFFU; + cf->data[ae + 4] = (u8)(so->tx.len >> 8) & 0xFFU; + cf->data[ae + 5] = (u8)so->tx.len & 0xFFU; + ff_pci_sz = FF_PCI_SZ32; + } else { + /* use 12 bit FF_DL notation */ + cf->data[ae] = (u8)(so->tx.len >> 8) | N_PCI_FF; + cf->data[ae + 1] = (u8)so->tx.len & 0xFFU; + ff_pci_sz = FF_PCI_SZ12; + } + + /* add first data bytes depending on ae */ + for (i = ae + ff_pci_sz; i < so->tx.ll_dl; i++) + cf->data[i] = so->tx.buf[so->tx.idx++]; + + so->tx.sn = 1; + so->tx.state = ISOTP_WAIT_FIRST_FC; +} + +static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) +{ + struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, + txtimer); + struct sock *sk = &so->sk; + struct sk_buff *skb; + struct net_device *dev; + struct canfd_frame *cf; + enum hrtimer_restart restart = HRTIMER_NORESTART; + int can_send_ret; + int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0; + + switch (so->tx.state) { + case ISOTP_WAIT_FC: + case ISOTP_WAIT_FIRST_FC: + + /* we did not get any flow control frame in time */ + + /* report 'communication error on send' */ + sk->sk_err = ECOMM; + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_error_report(sk); + + /* reset tx state */ + so->tx.state = ISOTP_IDLE; + wake_up_interruptible(&so->wait); + break; + + case ISOTP_SENDING: + + /* push out the next segmented pdu */ + dev = dev_get_by_index(sock_net(sk), so->ifindex); + if (!dev) + break; + +isotp_tx_burst: + skb = alloc_skb(so->ll.mtu + sizeof(struct can_skb_priv), + GFP_ATOMIC); + if (!skb) { + dev_put(dev); + break; + } + + can_skb_reserve(skb); + can_skb_prv(skb)->ifindex = dev->ifindex; + can_skb_prv(skb)->skbcnt = 0; + + cf = (struct canfd_frame *)skb->data; + skb_put(skb, so->ll.mtu); + + /* create consecutive frame */ + isotp_fill_dataframe(cf, so, ae, 0); + + /* place consecutive frame N_PCI in appropriate index */ + cf->data[ae] = N_PCI_CF | so->tx.sn++; + so->tx.sn %= 16; + so->tx.bs++; + + if (so->ll.mtu == CANFD_MTU) + cf->flags = so->ll.tx_flags; + + skb->dev = dev; + can_skb_set_owner(skb, sk); + + can_send_ret = can_send(skb, 1); + if (can_send_ret) + pr_notice_once("can-isotp: %s: can_send_ret %d\n", + __func__, can_send_ret); + + if (so->tx.idx >= so->tx.len) { + /* we are done */ + so->tx.state = ISOTP_IDLE; + dev_put(dev); + wake_up_interruptible(&so->wait); + break; + } + + if (so->txfc.bs && so->tx.bs >= so->txfc.bs) { + /* stop and wait for FC */ + so->tx.state = ISOTP_WAIT_FC; + dev_put(dev); + hrtimer_set_expires(&so->txtimer, + ktime_add(ktime_get(), + ktime_set(1, 0))); + restart = HRTIMER_RESTART; + break; + } + + /* no gap between data frames needed => use burst mode */ + if (!so->tx_gap) + goto isotp_tx_burst; + + /* start timer to send next data frame with correct delay */ + dev_put(dev); + hrtimer_set_expires(&so->txtimer, + ktime_add(ktime_get(), so->tx_gap)); + restart = HRTIMER_RESTART; + break; + + default: + WARN_ON_ONCE(1); + } + + return restart; +} + +static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) +{ + struct sock *sk = sock->sk; + struct isotp_sock *so = isotp_sk(sk); + struct sk_buff *skb; + struct net_device *dev; + struct canfd_frame *cf; + int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0; + int wait_tx_done = (so->opt.flags & CAN_ISOTP_WAIT_TX_DONE) ? 1 : 0; + int off; + int err; + + if (!so->bound) + return -EADDRNOTAVAIL; + + /* we do not support multiple buffers - for now */ + if (so->tx.state != ISOTP_IDLE || wq_has_sleeper(&so->wait)) { + if (msg->msg_flags & MSG_DONTWAIT) + return -EAGAIN; + + /* wait for complete transmission of current pdu */ + wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + } + + if (!size || size > MAX_MSG_LENGTH) + return -EINVAL; + + err = memcpy_from_msg(so->tx.buf, msg, size); + if (err < 0) + return err; + + dev = dev_get_by_index(sock_net(sk), so->ifindex); + if (!dev) + return -ENXIO; + + skb = sock_alloc_send_skb(sk, so->ll.mtu + sizeof(struct can_skb_priv), + msg->msg_flags & MSG_DONTWAIT, &err); + if (!skb) { + dev_put(dev); + return err; + } + + can_skb_reserve(skb); + can_skb_prv(skb)->ifindex = dev->ifindex; + can_skb_prv(skb)->skbcnt = 0; + + so->tx.state = ISOTP_SENDING; + so->tx.len = size; + so->tx.idx = 0; + + cf = (struct canfd_frame *)skb->data; + skb_put(skb, so->ll.mtu); + + /* take care of a potential SF_DL ESC offset for TX_DL > 8 */ + off = (so->tx.ll_dl > CAN_MAX_DLEN) ? 1 : 0; + + /* check for single frame transmission depending on TX_DL */ + if (size <= so->tx.ll_dl - SF_PCI_SZ4 - ae - off) { + /* The message size generally fits into a SingleFrame - good. + * + * SF_DL ESC offset optimization: + * + * When TX_DL is greater 8 but the message would still fit + * into a 8 byte CAN frame, we can omit the offset. + * This prevents a protocol caused length extension from + * CAN_DL = 8 to CAN_DL = 12 due to the SF_SL ESC handling. + */ + if (size <= CAN_MAX_DLEN - SF_PCI_SZ4 - ae) + off = 0; + + isotp_fill_dataframe(cf, so, ae, off); + + /* place single frame N_PCI w/o length in appropriate index */ + cf->data[ae] = N_PCI_SF; + + /* place SF_DL size value depending on the SF_DL ESC offset */ + if (off) + cf->data[SF_PCI_SZ4 + ae] = size; + else + cf->data[ae] |= size; + + so->tx.state = ISOTP_IDLE; + wake_up_interruptible(&so->wait); + + /* don't enable wait queue for a single frame transmission */ + wait_tx_done = 0; + } else { + /* send first frame and wait for FC */ + + isotp_create_fframe(cf, so, ae); + + /* start timeout for FC */ + hrtimer_start(&so->txtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); + } + + /* send the first or only CAN frame */ + if (so->ll.mtu == CANFD_MTU) + cf->flags = so->ll.tx_flags; + + skb->dev = dev; + skb->sk = sk; + err = can_send(skb, 1); + dev_put(dev); + if (err) { + pr_notice_once("can-isotp: %s: can_send_ret %d\n", + __func__, err); + return err; + } + + if (wait_tx_done) { + /* wait for complete transmission of current pdu */ + wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + } + + return size; +} + +static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int flags) +{ + struct sock *sk = sock->sk; + struct sk_buff *skb; + int err = 0; + int noblock; + + noblock = flags & MSG_DONTWAIT; + flags &= ~MSG_DONTWAIT; + + skb = skb_recv_datagram(sk, flags, noblock, &err); + if (!skb) + return err; + + if (size < skb->len) + msg->msg_flags |= MSG_TRUNC; + else + size = skb->len; + + err = memcpy_to_msg(msg, skb->data, size); + if (err < 0) { + skb_free_datagram(sk, skb); + return err; + } + + sock_recv_timestamp(msg, sk, skb); + + if (msg->msg_name) { + msg->msg_namelen = sizeof(struct sockaddr_can); + memcpy(msg->msg_name, skb->cb, msg->msg_namelen); + } + + skb_free_datagram(sk, skb); + + return size; +} + +static int isotp_release(struct socket *sock) +{ + struct sock *sk = sock->sk; + struct isotp_sock *so; + struct net *net; + + if (!sk) + return 0; + + so = isotp_sk(sk); + net = sock_net(sk); + + /* wait for complete transmission of current pdu */ + wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + + unregister_netdevice_notifier(&so->notifier); + + lock_sock(sk); + + hrtimer_cancel(&so->txtimer); + hrtimer_cancel(&so->rxtimer); + + /* remove current filters & unregister */ + if (so->bound) { + if (so->ifindex) { + struct net_device *dev; + + dev = dev_get_by_index(net, so->ifindex); + if (dev) { + can_rx_unregister(net, dev, so->rxid, + SINGLE_MASK(so->rxid), + isotp_rcv, sk); + dev_put(dev); + } + } + } + + so->ifindex = 0; + so->bound = 0; + + sock_orphan(sk); + sock->sk = NULL; + + release_sock(sk); + sock_put(sk); + + return 0; +} + +static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) +{ + struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; + struct sock *sk = sock->sk; + struct isotp_sock *so = isotp_sk(sk); + struct net *net = sock_net(sk); + int ifindex; + struct net_device *dev; + int err = 0; + int notify_enetdown = 0; + + if (len < CAN_REQUIRED_SIZE(struct sockaddr_can, can_addr.tp)) + return -EINVAL; + + if (addr->can_addr.tp.rx_id == addr->can_addr.tp.tx_id) + return -EADDRNOTAVAIL; + + if ((addr->can_addr.tp.rx_id | addr->can_addr.tp.tx_id) & + (CAN_ERR_FLAG | CAN_RTR_FLAG)) + return -EADDRNOTAVAIL; + + if (!addr->can_ifindex) + return -ENODEV; + + lock_sock(sk); + + if (so->bound && addr->can_ifindex == so->ifindex && + addr->can_addr.tp.rx_id == so->rxid && + addr->can_addr.tp.tx_id == so->txid) + goto out; + + dev = dev_get_by_index(net, addr->can_ifindex); + if (!dev) { + err = -ENODEV; + goto out; + } + if (dev->type != ARPHRD_CAN) { + dev_put(dev); + err = -ENODEV; + goto out; + } + if (dev->mtu < so->ll.mtu) { + dev_put(dev); + err = -EINVAL; + goto out; + } + if (!(dev->flags & IFF_UP)) + notify_enetdown = 1; + + ifindex = dev->ifindex; + + can_rx_register(net, dev, addr->can_addr.tp.rx_id, + SINGLE_MASK(addr->can_addr.tp.rx_id), isotp_rcv, sk, + "isotp", sk); + + dev_put(dev); + + if (so->bound) { + /* unregister old filter */ + if (so->ifindex) { + dev = dev_get_by_index(net, so->ifindex); + if (dev) { + can_rx_unregister(net, dev, so->rxid, + SINGLE_MASK(so->rxid), + isotp_rcv, sk); + dev_put(dev); + } + } + } + + /* switch to new settings */ + so->ifindex = ifindex; + so->rxid = addr->can_addr.tp.rx_id; + so->txid = addr->can_addr.tp.tx_id; + so->bound = 1; + +out: + release_sock(sk); + + if (notify_enetdown) { + sk->sk_err = ENETDOWN; + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_error_report(sk); + } + + return err; +} + +static int isotp_getname(struct socket *sock, struct sockaddr *uaddr, int peer) +{ + struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; + struct sock *sk = sock->sk; + struct isotp_sock *so = isotp_sk(sk); + + if (peer) + return -EOPNOTSUPP; + + addr->can_family = AF_CAN; + addr->can_ifindex = so->ifindex; + addr->can_addr.tp.rx_id = so->rxid; + addr->can_addr.tp.tx_id = so->txid; + + return sizeof(*addr); +} + +static int isotp_setsockopt(struct socket *sock, int level, int optname, + sockptr_t optval, unsigned int optlen) +{ + struct sock *sk = sock->sk; + struct isotp_sock *so = isotp_sk(sk); + int ret = 0; + + if (level != SOL_CAN_ISOTP) + return -EINVAL; + + switch (optname) { + case CAN_ISOTP_OPTS: + if (optlen != sizeof(struct can_isotp_options)) + return -EINVAL; + + if (copy_from_sockptr(&so->opt, optval, optlen)) + return -EFAULT; + + /* no separate rx_ext_address is given => use ext_address */ + if (!(so->opt.flags & CAN_ISOTP_RX_EXT_ADDR)) + so->opt.rx_ext_address = so->opt.ext_address; + break; + + case CAN_ISOTP_RECV_FC: + if (optlen != sizeof(struct can_isotp_fc_options)) + return -EINVAL; + + if (copy_from_sockptr(&so->rxfc, optval, optlen)) + return -EFAULT; + break; + + case CAN_ISOTP_TX_STMIN: + if (optlen != sizeof(u32)) + return -EINVAL; + + if (copy_from_sockptr(&so->force_tx_stmin, optval, optlen)) + return -EFAULT; + break; + + case CAN_ISOTP_RX_STMIN: + if (optlen != sizeof(u32)) + return -EINVAL; + + if (copy_from_sockptr(&so->force_rx_stmin, optval, optlen)) + return -EFAULT; + break; + + case CAN_ISOTP_LL_OPTS: + if (optlen == sizeof(struct can_isotp_ll_options)) { + struct can_isotp_ll_options ll; + + if (copy_from_sockptr(&ll, optval, optlen)) + return -EFAULT; + + /* check for correct ISO 11898-1 DLC data length */ + if (ll.tx_dl != padlen(ll.tx_dl)) + return -EINVAL; + + if (ll.mtu != CAN_MTU && ll.mtu != CANFD_MTU) + return -EINVAL; + + if (ll.mtu == CAN_MTU && ll.tx_dl > CAN_MAX_DLEN) + return -EINVAL; + + memcpy(&so->ll, &ll, sizeof(ll)); + + /* set ll_dl for tx path to similar place as for rx */ + so->tx.ll_dl = ll.tx_dl; + } else { + return -EINVAL; + } + break; + + default: + ret = -ENOPROTOOPT; + } + + return ret; +} + +static int isotp_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) +{ + struct sock *sk = sock->sk; + struct isotp_sock *so = isotp_sk(sk); + int len; + void *val; + + if (level != SOL_CAN_ISOTP) + return -EINVAL; + if (get_user(len, optlen)) + return -EFAULT; + if (len < 0) + return -EINVAL; + + switch (optname) { + case CAN_ISOTP_OPTS: + len = min_t(int, len, sizeof(struct can_isotp_options)); + val = &so->opt; + break; + + case CAN_ISOTP_RECV_FC: + len = min_t(int, len, sizeof(struct can_isotp_fc_options)); + val = &so->rxfc; + break; + + case CAN_ISOTP_TX_STMIN: + len = min_t(int, len, sizeof(u32)); + val = &so->force_tx_stmin; + break; + + case CAN_ISOTP_RX_STMIN: + len = min_t(int, len, sizeof(u32)); + val = &so->force_rx_stmin; + break; + + case CAN_ISOTP_LL_OPTS: + len = min_t(int, len, sizeof(struct can_isotp_ll_options)); + val = &so->ll; + break; + + default: + return -ENOPROTOOPT; + } + + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, val, len)) + return -EFAULT; + return 0; +} + +static int isotp_notifier(struct notifier_block *nb, unsigned long msg, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct isotp_sock *so = container_of(nb, struct isotp_sock, notifier); + struct sock *sk = &so->sk; + + if (!net_eq(dev_net(dev), sock_net(sk))) + return NOTIFY_DONE; + + if (dev->type != ARPHRD_CAN) + return NOTIFY_DONE; + + if (so->ifindex != dev->ifindex) + return NOTIFY_DONE; + + switch (msg) { + case NETDEV_UNREGISTER: + lock_sock(sk); + /* remove current filters & unregister */ + if (so->bound) + can_rx_unregister(dev_net(dev), dev, so->rxid, + SINGLE_MASK(so->rxid), + isotp_rcv, sk); + + so->ifindex = 0; + so->bound = 0; + release_sock(sk); + + sk->sk_err = ENODEV; + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_error_report(sk); + break; + + case NETDEV_DOWN: + sk->sk_err = ENETDOWN; + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_error_report(sk); + break; + } + + return NOTIFY_DONE; +} + +static int isotp_init(struct sock *sk) +{ + struct isotp_sock *so = isotp_sk(sk); + + so->ifindex = 0; + so->bound = 0; + + so->opt.flags = CAN_ISOTP_DEFAULT_FLAGS; + so->opt.ext_address = CAN_ISOTP_DEFAULT_EXT_ADDRESS; + so->opt.rx_ext_address = CAN_ISOTP_DEFAULT_EXT_ADDRESS; + so->opt.rxpad_content = CAN_ISOTP_DEFAULT_PAD_CONTENT; + so->opt.txpad_content = CAN_ISOTP_DEFAULT_PAD_CONTENT; + so->opt.frame_txtime = CAN_ISOTP_DEFAULT_FRAME_TXTIME; + so->rxfc.bs = CAN_ISOTP_DEFAULT_RECV_BS; + so->rxfc.stmin = CAN_ISOTP_DEFAULT_RECV_STMIN; + so->rxfc.wftmax = CAN_ISOTP_DEFAULT_RECV_WFTMAX; + so->ll.mtu = CAN_ISOTP_DEFAULT_LL_MTU; + so->ll.tx_dl = CAN_ISOTP_DEFAULT_LL_TX_DL; + so->ll.tx_flags = CAN_ISOTP_DEFAULT_LL_TX_FLAGS; + + /* set ll_dl for tx path to similar place as for rx */ + so->tx.ll_dl = so->ll.tx_dl; + + so->rx.state = ISOTP_IDLE; + so->tx.state = ISOTP_IDLE; + + hrtimer_init(&so->rxtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); + so->rxtimer.function = isotp_rx_timer_handler; + hrtimer_init(&so->txtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); + so->txtimer.function = isotp_tx_timer_handler; + + init_waitqueue_head(&so->wait); + + so->notifier.notifier_call = isotp_notifier; + register_netdevice_notifier(&so->notifier); + + return 0; +} + +static int isotp_sock_no_ioctlcmd(struct socket *sock, unsigned int cmd, + unsigned long arg) +{ + /* no ioctls for socket layer -> hand it down to NIC layer */ + return -ENOIOCTLCMD; +} + +static const struct proto_ops isotp_ops = { + .family = PF_CAN, + .release = isotp_release, + .bind = isotp_bind, + .connect = sock_no_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .getname = isotp_getname, + .poll = datagram_poll, + .ioctl = isotp_sock_no_ioctlcmd, + .gettstamp = sock_gettstamp, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .setsockopt = isotp_setsockopt, + .getsockopt = isotp_getsockopt, + .sendmsg = isotp_sendmsg, + .recvmsg = isotp_recvmsg, + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +}; + +static struct proto isotp_proto __read_mostly = { + .name = "CAN_ISOTP", + .owner = THIS_MODULE, + .obj_size = sizeof(struct isotp_sock), + .init = isotp_init, +}; + +static const struct can_proto isotp_can_proto = { + .type = SOCK_DGRAM, + .protocol = CAN_ISOTP, + .ops = &isotp_ops, + .prot = &isotp_proto, +}; + +static __init int isotp_module_init(void) +{ + int err; + + pr_info("can: isotp protocol\n"); + + err = can_proto_register(&isotp_can_proto); + if (err < 0) + pr_err("can: registration of isotp protocol failed\n"); + + return err; +} + +static __exit void isotp_module_exit(void) +{ + can_proto_unregister(&isotp_can_proto); +} + +module_init(isotp_module_init); +module_exit(isotp_module_exit); diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index 0cec4152f979..e09d087ba240 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -580,6 +580,7 @@ sk_buff *j1939_tp_tx_dat_new(struct j1939_priv *priv, skb->dev = priv->ndev; can_skb_reserve(skb); can_skb_prv(skb)->ifindex = priv->ndev->ifindex; + can_skb_prv(skb)->skbcnt = 0; /* reserve CAN header */ skb_reserve(skb, offsetof(struct can_frame, data)); @@ -1487,6 +1488,7 @@ j1939_session *j1939_session_fresh_new(struct j1939_priv *priv, skb->dev = priv->ndev; can_skb_reserve(skb); can_skb_prv(skb)->ifindex = priv->ndev->ifindex; + can_skb_prv(skb)->skbcnt = 0; skcb = j1939_skb_to_cb(skb); memcpy(skcb, rel_skcb, sizeof(*skcb)); diff --git a/net/can/proc.c b/net/can/proc.c index e6881bfc3ed1..550928b8b8a2 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* * proc.c - procfs support for Protocol family CAN core module * @@ -54,7 +54,6 @@ * proc filenames for the PF_CAN core */ -#define CAN_PROC_VERSION "version" #define CAN_PROC_STATS "stats" #define CAN_PROC_RESET_STATS "reset_stats" #define CAN_PROC_RCVLIST_ALL "rcvlist_all" @@ -293,12 +292,6 @@ static int can_reset_stats_proc_show(struct seq_file *m, void *v) return 0; } -static int can_version_proc_show(struct seq_file *m, void *v) -{ - seq_printf(m, "%s\n", CAN_VERSION_STRING); - return 0; -} - static inline void can_rcvlist_proc_show_one(struct seq_file *m, int idx, struct net_device *dev, struct can_dev_rcv_lists *dev_rcv_lists) @@ -441,8 +434,6 @@ void can_init_proc(struct net *net) } /* own procfs entries from the AF_CAN core */ - net->can.pde_version = proc_create_net_single(CAN_PROC_VERSION, 0644, - net->can.proc_dir, can_version_proc_show, NULL); net->can.pde_stats = proc_create_net_single(CAN_PROC_STATS, 0644, net->can.proc_dir, can_stats_proc_show, NULL); net->can.pde_reset_stats = proc_create_net_single(CAN_PROC_RESET_STATS, @@ -471,9 +462,6 @@ void can_init_proc(struct net *net) */ void can_remove_proc(struct net *net) { - if (net->can.pde_version) - remove_proc_entry(CAN_PROC_VERSION, net->can.proc_dir); - if (net->can.pde_stats) remove_proc_entry(CAN_PROC_STATS, net->can.proc_dir); diff --git a/net/can/raw.c b/net/can/raw.c index 94a9405658dc..6ec8aa1d0da4 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* raw.c - Raw sockets for protocol family CAN * * Copyright (c) 2002-2007 Volkswagen Group Electronic Research @@ -55,8 +55,6 @@ #include <net/sock.h> #include <net/net_namespace.h> -#define CAN_RAW_VERSION CAN_VERSION - MODULE_DESCRIPTION("PF_CAN raw protocol"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Urs Thuermann <urs.thuermann@volkswagen.de>"); @@ -154,16 +152,16 @@ static void raw_rcv(struct sk_buff *oskb, void *data) if (!skb) return; - /* Put the datagram to the queue so that raw_recvmsg() can - * get it from there. We need to pass the interface index to - * raw_recvmsg(). We pass a whole struct sockaddr_can in skb->cb - * containing the interface index. + /* Put the datagram to the queue so that raw_recvmsg() can get + * it from there. We need to pass the interface index to + * raw_recvmsg(). We pass a whole struct sockaddr_can in + * skb->cb containing the interface index. */ sock_skb_cb_check_size(sizeof(struct sockaddr_can)); addr = (struct sockaddr_can *)skb->cb; memset(addr, 0, sizeof(*addr)); - addr->can_family = AF_CAN; + addr->can_family = AF_CAN; addr->can_ifindex = skb->dev->ifindex; /* add CAN specific message flags for raw_recvmsg() */ @@ -290,8 +288,8 @@ static int raw_notifier(struct notifier_block *nb, kfree(ro->filter); ro->ifindex = 0; - ro->bound = 0; - ro->count = 0; + ro->bound = 0; + ro->count = 0; release_sock(sk); sk->sk_err = ENODEV; @@ -374,8 +372,8 @@ static int raw_release(struct socket *sock) kfree(ro->filter); ro->ifindex = 0; - ro->bound = 0; - ro->count = 0; + ro->bound = 0; + ro->count = 0; free_percpu(ro->uniq); sock_orphan(sk); @@ -773,7 +771,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) skb_setup_tx_timestamp(skb, sk->sk_tsflags); skb->dev = dev; - skb->sk = sk; + skb->sk = sk; skb->priority = sk->sk_priority; err = can_send(skb, ro->loopback); @@ -801,8 +799,12 @@ static int raw_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int err = 0; int noblock; - noblock = flags & MSG_DONTWAIT; - flags &= ~MSG_DONTWAIT; + noblock = flags & MSG_DONTWAIT; + flags &= ~MSG_DONTWAIT; + + if (flags & MSG_ERRQUEUE) + return sock_recv_errqueue(sk, msg, size, + SOL_CAN_RAW, SCM_CAN_RAW_ERRQUEUE); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) @@ -881,7 +883,7 @@ static __init int raw_module_init(void) { int err; - pr_info("can: raw protocol (rev " CAN_RAW_VERSION ")\n"); + pr_info("can: raw protocol\n"); err = can_proto_register(&raw_can_proto); if (err < 0) diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index d4d7a0e52491..af0f1fa24937 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -2016,11 +2016,11 @@ static int process_banner(struct ceph_connection *con) sizeof(con->peer_addr)) != 0 && !(addr_is_blank(&con->actual_peer_addr) && con->actual_peer_addr.nonce == con->peer_addr.nonce)) { - pr_warn("wrong peer, want %s/%d, got %s/%d\n", + pr_warn("wrong peer, want %s/%u, got %s/%u\n", ceph_pr_addr(&con->peer_addr), - (int)le32_to_cpu(con->peer_addr.nonce), + le32_to_cpu(con->peer_addr.nonce), ceph_pr_addr(&con->actual_peer_addr), - (int)le32_to_cpu(con->actual_peer_addr.nonce)); + le32_to_cpu(con->actual_peer_addr.nonce)); con->error_msg = "wrong peer at address"; return -1; } @@ -2811,13 +2811,13 @@ static int queue_con_delay(struct ceph_connection *con, unsigned long delay) return -ENOENT; } + dout("%s %p %lu\n", __func__, con, delay); if (!queue_delayed_work(ceph_msgr_wq, &con->work, delay)) { dout("%s %p - already queued\n", __func__, con); con->ops->put(con); return -EBUSY; } - dout("%s %p %lu\n", __func__, con, delay); return 0; } @@ -2998,6 +2998,11 @@ static void con_fault(struct ceph_connection *con) ceph_msg_put(con->in_msg); con->in_msg = NULL; } + if (con->out_msg) { + BUG_ON(con->out_msg->con != con); + ceph_msg_put(con->out_msg); + con->out_msg = NULL; + } /* Requeue anything that hasn't been acked */ list_splice_init(&con->out_sent, &con->out_queue); diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index d633a0aeaa55..c4cf2529d08b 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -896,8 +896,9 @@ bad: ceph_msg_dump(msg); } -int ceph_monc_blacklist_add(struct ceph_mon_client *monc, - struct ceph_entity_addr *client_addr) +static __printf(2, 0) +int do_mon_command_vargs(struct ceph_mon_client *monc, const char *fmt, + va_list ap) { struct ceph_mon_generic_request *req; struct ceph_mon_command *h; @@ -925,29 +926,65 @@ int ceph_monc_blacklist_add(struct ceph_mon_client *monc, h->monhdr.session_mon_tid = 0; h->fsid = monc->monmap->fsid; h->num_strs = cpu_to_le32(1); - len = sprintf(h->str, "{ \"prefix\": \"osd blacklist\", \ - \"blacklistop\": \"add\", \ - \"addr\": \"%pISpc/%u\" }", - &client_addr->in_addr, le32_to_cpu(client_addr->nonce)); + len = vsprintf(h->str, fmt, ap); h->str_len = cpu_to_le32(len); send_generic_request(monc, req); mutex_unlock(&monc->mutex); ret = wait_generic_request(req); - if (!ret) - /* - * Make sure we have the osdmap that includes the blacklist - * entry. This is needed to ensure that the OSDs pick up the - * new blacklist before processing any future requests from - * this client. - */ - ret = ceph_wait_for_latest_osdmap(monc->client, 0); - out: put_generic_request(req); return ret; } -EXPORT_SYMBOL(ceph_monc_blacklist_add); + +static __printf(2, 3) +int do_mon_command(struct ceph_mon_client *monc, const char *fmt, ...) +{ + va_list ap; + int ret; + + va_start(ap, fmt); + ret = do_mon_command_vargs(monc, fmt, ap); + va_end(ap); + return ret; +} + +int ceph_monc_blocklist_add(struct ceph_mon_client *monc, + struct ceph_entity_addr *client_addr) +{ + int ret; + + ret = do_mon_command(monc, + "{ \"prefix\": \"osd blocklist\", \ + \"blocklistop\": \"add\", \ + \"addr\": \"%pISpc/%u\" }", + &client_addr->in_addr, + le32_to_cpu(client_addr->nonce)); + if (ret == -EINVAL) { + /* + * The monitor returns EINVAL on an unrecognized command. + * Try the legacy command -- it is exactly the same except + * for the name. + */ + ret = do_mon_command(monc, + "{ \"prefix\": \"osd blacklist\", \ + \"blacklistop\": \"add\", \ + \"addr\": \"%pISpc/%u\" }", + &client_addr->in_addr, + le32_to_cpu(client_addr->nonce)); + } + if (ret) + return ret; + + /* + * Make sure we have the osdmap that includes the blocklist + * entry. This is needed to ensure that the OSDs pick up the + * new blocklist before processing any future requests from + * this client. + */ + return ceph_wait_for_latest_osdmap(monc->client, 0); +} +EXPORT_SYMBOL(ceph_monc_blocklist_add); /* * Resend pending generic requests. diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 96c25f5e064a..fa08c15be0c0 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -965,6 +965,143 @@ bad: } /* + * CRUSH workspaces + * + * workspace_manager framework borrowed from fs/btrfs/compression.c. + * Two simplifications: there is only one type of workspace and there + * is always at least one workspace. + */ +static struct crush_work *alloc_workspace(const struct crush_map *c) +{ + struct crush_work *work; + size_t work_size; + + WARN_ON(!c->working_size); + work_size = crush_work_size(c, CEPH_PG_MAX_SIZE); + dout("%s work_size %zu bytes\n", __func__, work_size); + + work = ceph_kvmalloc(work_size, GFP_NOIO); + if (!work) + return NULL; + + INIT_LIST_HEAD(&work->item); + crush_init_workspace(c, work); + return work; +} + +static void free_workspace(struct crush_work *work) +{ + WARN_ON(!list_empty(&work->item)); + kvfree(work); +} + +static void init_workspace_manager(struct workspace_manager *wsm) +{ + INIT_LIST_HEAD(&wsm->idle_ws); + spin_lock_init(&wsm->ws_lock); + atomic_set(&wsm->total_ws, 0); + wsm->free_ws = 0; + init_waitqueue_head(&wsm->ws_wait); +} + +static void add_initial_workspace(struct workspace_manager *wsm, + struct crush_work *work) +{ + WARN_ON(!list_empty(&wsm->idle_ws)); + + list_add(&work->item, &wsm->idle_ws); + atomic_set(&wsm->total_ws, 1); + wsm->free_ws = 1; +} + +static void cleanup_workspace_manager(struct workspace_manager *wsm) +{ + struct crush_work *work; + + while (!list_empty(&wsm->idle_ws)) { + work = list_first_entry(&wsm->idle_ws, struct crush_work, + item); + list_del_init(&work->item); + free_workspace(work); + } + atomic_set(&wsm->total_ws, 0); + wsm->free_ws = 0; +} + +/* + * Finds an available workspace or allocates a new one. If it's not + * possible to allocate a new one, waits until there is one. + */ +static struct crush_work *get_workspace(struct workspace_manager *wsm, + const struct crush_map *c) +{ + struct crush_work *work; + int cpus = num_online_cpus(); + +again: + spin_lock(&wsm->ws_lock); + if (!list_empty(&wsm->idle_ws)) { + work = list_first_entry(&wsm->idle_ws, struct crush_work, + item); + list_del_init(&work->item); + wsm->free_ws--; + spin_unlock(&wsm->ws_lock); + return work; + + } + if (atomic_read(&wsm->total_ws) > cpus) { + DEFINE_WAIT(wait); + + spin_unlock(&wsm->ws_lock); + prepare_to_wait(&wsm->ws_wait, &wait, TASK_UNINTERRUPTIBLE); + if (atomic_read(&wsm->total_ws) > cpus && !wsm->free_ws) + schedule(); + finish_wait(&wsm->ws_wait, &wait); + goto again; + } + atomic_inc(&wsm->total_ws); + spin_unlock(&wsm->ws_lock); + + work = alloc_workspace(c); + if (!work) { + atomic_dec(&wsm->total_ws); + wake_up(&wsm->ws_wait); + + /* + * Do not return the error but go back to waiting. We + * have the inital workspace and the CRUSH computation + * time is bounded so we will get it eventually. + */ + WARN_ON(atomic_read(&wsm->total_ws) < 1); + goto again; + } + return work; +} + +/* + * Puts a workspace back on the list or frees it if we have enough + * idle ones sitting around. + */ +static void put_workspace(struct workspace_manager *wsm, + struct crush_work *work) +{ + spin_lock(&wsm->ws_lock); + if (wsm->free_ws <= num_online_cpus()) { + list_add(&work->item, &wsm->idle_ws); + wsm->free_ws++; + spin_unlock(&wsm->ws_lock); + goto wake; + } + spin_unlock(&wsm->ws_lock); + + free_workspace(work); + atomic_dec(&wsm->total_ws); +wake: + if (wq_has_sleeper(&wsm->ws_wait)) + wake_up(&wsm->ws_wait); +} + +/* * osd map */ struct ceph_osdmap *ceph_osdmap_alloc(void) @@ -981,7 +1118,8 @@ struct ceph_osdmap *ceph_osdmap_alloc(void) map->primary_temp = RB_ROOT; map->pg_upmap = RB_ROOT; map->pg_upmap_items = RB_ROOT; - mutex_init(&map->crush_workspace_mutex); + + init_workspace_manager(&map->crush_wsm); return map; } @@ -989,8 +1127,11 @@ struct ceph_osdmap *ceph_osdmap_alloc(void) void ceph_osdmap_destroy(struct ceph_osdmap *map) { dout("osdmap_destroy %p\n", map); + if (map->crush) crush_destroy(map->crush); + cleanup_workspace_manager(&map->crush_wsm); + while (!RB_EMPTY_ROOT(&map->pg_temp)) { struct ceph_pg_mapping *pg = rb_entry(rb_first(&map->pg_temp), @@ -1029,7 +1170,6 @@ void ceph_osdmap_destroy(struct ceph_osdmap *map) kvfree(map->osd_weight); kvfree(map->osd_addr); kvfree(map->osd_primary_affinity); - kvfree(map->crush_workspace); kfree(map); } @@ -1104,26 +1244,22 @@ static int osdmap_set_max_osd(struct ceph_osdmap *map, u32 max) static int osdmap_set_crush(struct ceph_osdmap *map, struct crush_map *crush) { - void *workspace; - size_t work_size; + struct crush_work *work; if (IS_ERR(crush)) return PTR_ERR(crush); - work_size = crush_work_size(crush, CEPH_PG_MAX_SIZE); - dout("%s work_size %zu bytes\n", __func__, work_size); - workspace = ceph_kvmalloc(work_size, GFP_NOIO); - if (!workspace) { + work = alloc_workspace(crush); + if (!work) { crush_destroy(crush); return -ENOMEM; } - crush_init_workspace(crush, workspace); if (map->crush) crush_destroy(map->crush); - kvfree(map->crush_workspace); + cleanup_workspace_manager(&map->crush_wsm); map->crush = crush; - map->crush_workspace = workspace; + add_initial_workspace(&map->crush_wsm, work); return 0; } @@ -2322,6 +2458,7 @@ static int do_crush(struct ceph_osdmap *map, int ruleno, int x, s64 choose_args_index) { struct crush_choose_arg_map *arg_map; + struct crush_work *work; int r; BUG_ON(result_max > CEPH_PG_MAX_SIZE); @@ -2332,12 +2469,11 @@ static int do_crush(struct ceph_osdmap *map, int ruleno, int x, arg_map = lookup_choose_arg_map(&map->crush->choose_args, CEPH_DEFAULT_CHOOSE_ARGS); - mutex_lock(&map->crush_workspace_mutex); + work = get_workspace(&map->crush_wsm, map->crush); r = crush_do_rule(map->crush, ruleno, x, result, result_max, - weight, weight_max, map->crush_workspace, + weight, weight_max, work, arg_map ? arg_map->args : NULL); - mutex_unlock(&map->crush_workspace_mutex); - + put_workspace(&map->crush_wsm, work); return r; } diff --git a/net/compat.c b/net/compat.c index 95ce707a30a3..ddd15af3a283 100644 --- a/net/compat.c +++ b/net/compat.c @@ -98,8 +98,8 @@ int get_compat_msghdr(struct msghdr *kmsg, if (err) return err; - err = compat_import_iovec(save_addr ? READ : WRITE, compat_ptr(ptr), - len, UIO_FASTIOV, iov, &kmsg->msg_iter); + err = import_iovec(save_addr ? READ : WRITE, compat_ptr(ptr), len, + UIO_FASTIOV, iov, &kmsg->msg_iter); return err < 0 ? err : 0; } diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index b988f48153a4..c907f0dc7f87 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -7,97 +7,13 @@ #include <linux/spinlock.h> #include <linux/bpf.h> #include <linux/btf_ids.h> +#include <linux/bpf_local_storage.h> #include <net/bpf_sk_storage.h> #include <net/sock.h> #include <uapi/linux/sock_diag.h> #include <uapi/linux/btf.h> -#define SK_STORAGE_CREATE_FLAG_MASK \ - (BPF_F_NO_PREALLOC | BPF_F_CLONE) - -struct bucket { - struct hlist_head list; - raw_spinlock_t lock; -}; - -/* Thp map is not the primary owner of a bpf_sk_storage_elem. - * Instead, the sk->sk_bpf_storage is. - * - * The map (bpf_sk_storage_map) is for two purposes - * 1. Define the size of the "sk local storage". It is - * the map's value_size. - * - * 2. Maintain a list to keep track of all elems such - * that they can be cleaned up during the map destruction. - * - * When a bpf local storage is being looked up for a - * particular sk, the "bpf_map" pointer is actually used - * as the "key" to search in the list of elem in - * sk->sk_bpf_storage. - * - * Hence, consider sk->sk_bpf_storage is the mini-map - * with the "bpf_map" pointer as the searching key. - */ -struct bpf_sk_storage_map { - struct bpf_map map; - /* Lookup elem does not require accessing the map. - * - * Updating/Deleting requires a bucket lock to - * link/unlink the elem from the map. Having - * multiple buckets to improve contention. - */ - struct bucket *buckets; - u32 bucket_log; - u16 elem_size; - u16 cache_idx; -}; - -struct bpf_sk_storage_data { - /* smap is used as the searching key when looking up - * from sk->sk_bpf_storage. - * - * Put it in the same cacheline as the data to minimize - * the number of cachelines access during the cache hit case. - */ - struct bpf_sk_storage_map __rcu *smap; - u8 data[] __aligned(8); -}; - -/* Linked to bpf_sk_storage and bpf_sk_storage_map */ -struct bpf_sk_storage_elem { - struct hlist_node map_node; /* Linked to bpf_sk_storage_map */ - struct hlist_node snode; /* Linked to bpf_sk_storage */ - struct bpf_sk_storage __rcu *sk_storage; - struct rcu_head rcu; - /* 8 bytes hole */ - /* The data is stored in aother cacheline to minimize - * the number of cachelines access during a cache hit. - */ - struct bpf_sk_storage_data sdata ____cacheline_aligned; -}; - -#define SELEM(_SDATA) container_of((_SDATA), struct bpf_sk_storage_elem, sdata) -#define SDATA(_SELEM) (&(_SELEM)->sdata) -#define BPF_SK_STORAGE_CACHE_SIZE 16 - -static DEFINE_SPINLOCK(cache_idx_lock); -static u64 cache_idx_usage_counts[BPF_SK_STORAGE_CACHE_SIZE]; - -struct bpf_sk_storage { - struct bpf_sk_storage_data __rcu *cache[BPF_SK_STORAGE_CACHE_SIZE]; - struct hlist_head list; /* List of bpf_sk_storage_elem */ - struct sock *sk; /* The sk that owns the the above "list" of - * bpf_sk_storage_elem. - */ - struct rcu_head rcu; - raw_spinlock_t lock; /* Protect adding/removing from the "list" */ -}; - -static struct bucket *select_bucket(struct bpf_sk_storage_map *smap, - struct bpf_sk_storage_elem *selem) -{ - return &smap->buckets[hash_ptr(selem, smap->bucket_log)]; -} +DEFINE_BPF_STORAGE_CACHE(sk_cache); static int omem_charge(struct sock *sk, unsigned int size) { @@ -111,445 +27,38 @@ static int omem_charge(struct sock *sk, unsigned int size) return -ENOMEM; } -static bool selem_linked_to_sk(const struct bpf_sk_storage_elem *selem) -{ - return !hlist_unhashed(&selem->snode); -} - -static bool selem_linked_to_map(const struct bpf_sk_storage_elem *selem) -{ - return !hlist_unhashed(&selem->map_node); -} - -static struct bpf_sk_storage_elem *selem_alloc(struct bpf_sk_storage_map *smap, - struct sock *sk, void *value, - bool charge_omem) -{ - struct bpf_sk_storage_elem *selem; - - if (charge_omem && omem_charge(sk, smap->elem_size)) - return NULL; - - selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN); - if (selem) { - if (value) - memcpy(SDATA(selem)->data, value, smap->map.value_size); - return selem; - } - - if (charge_omem) - atomic_sub(smap->elem_size, &sk->sk_omem_alloc); - - return NULL; -} - -/* sk_storage->lock must be held and selem->sk_storage == sk_storage. - * The caller must ensure selem->smap is still valid to be - * dereferenced for its smap->elem_size and smap->cache_idx. - */ -static bool __selem_unlink_sk(struct bpf_sk_storage *sk_storage, - struct bpf_sk_storage_elem *selem, - bool uncharge_omem) -{ - struct bpf_sk_storage_map *smap; - bool free_sk_storage; - struct sock *sk; - - smap = rcu_dereference(SDATA(selem)->smap); - sk = sk_storage->sk; - - /* All uncharging on sk->sk_omem_alloc must be done first. - * sk may be freed once the last selem is unlinked from sk_storage. - */ - if (uncharge_omem) - atomic_sub(smap->elem_size, &sk->sk_omem_alloc); - - free_sk_storage = hlist_is_singular_node(&selem->snode, - &sk_storage->list); - if (free_sk_storage) { - atomic_sub(sizeof(struct bpf_sk_storage), &sk->sk_omem_alloc); - sk_storage->sk = NULL; - /* After this RCU_INIT, sk may be freed and cannot be used */ - RCU_INIT_POINTER(sk->sk_bpf_storage, NULL); - - /* sk_storage is not freed now. sk_storage->lock is - * still held and raw_spin_unlock_bh(&sk_storage->lock) - * will be done by the caller. - * - * Although the unlock will be done under - * rcu_read_lock(), it is more intutivie to - * read if kfree_rcu(sk_storage, rcu) is done - * after the raw_spin_unlock_bh(&sk_storage->lock). - * - * Hence, a "bool free_sk_storage" is returned - * to the caller which then calls the kfree_rcu() - * after unlock. - */ - } - hlist_del_init_rcu(&selem->snode); - if (rcu_access_pointer(sk_storage->cache[smap->cache_idx]) == - SDATA(selem)) - RCU_INIT_POINTER(sk_storage->cache[smap->cache_idx], NULL); - - kfree_rcu(selem, rcu); - - return free_sk_storage; -} - -static void selem_unlink_sk(struct bpf_sk_storage_elem *selem) -{ - struct bpf_sk_storage *sk_storage; - bool free_sk_storage = false; - - if (unlikely(!selem_linked_to_sk(selem))) - /* selem has already been unlinked from sk */ - return; - - sk_storage = rcu_dereference(selem->sk_storage); - raw_spin_lock_bh(&sk_storage->lock); - if (likely(selem_linked_to_sk(selem))) - free_sk_storage = __selem_unlink_sk(sk_storage, selem, true); - raw_spin_unlock_bh(&sk_storage->lock); - - if (free_sk_storage) - kfree_rcu(sk_storage, rcu); -} - -static void __selem_link_sk(struct bpf_sk_storage *sk_storage, - struct bpf_sk_storage_elem *selem) -{ - RCU_INIT_POINTER(selem->sk_storage, sk_storage); - hlist_add_head(&selem->snode, &sk_storage->list); -} - -static void selem_unlink_map(struct bpf_sk_storage_elem *selem) -{ - struct bpf_sk_storage_map *smap; - struct bucket *b; - - if (unlikely(!selem_linked_to_map(selem))) - /* selem has already be unlinked from smap */ - return; - - smap = rcu_dereference(SDATA(selem)->smap); - b = select_bucket(smap, selem); - raw_spin_lock_bh(&b->lock); - if (likely(selem_linked_to_map(selem))) - hlist_del_init_rcu(&selem->map_node); - raw_spin_unlock_bh(&b->lock); -} - -static void selem_link_map(struct bpf_sk_storage_map *smap, - struct bpf_sk_storage_elem *selem) -{ - struct bucket *b = select_bucket(smap, selem); - - raw_spin_lock_bh(&b->lock); - RCU_INIT_POINTER(SDATA(selem)->smap, smap); - hlist_add_head_rcu(&selem->map_node, &b->list); - raw_spin_unlock_bh(&b->lock); -} - -static void selem_unlink(struct bpf_sk_storage_elem *selem) -{ - /* Always unlink from map before unlinking from sk_storage - * because selem will be freed after successfully unlinked from - * the sk_storage. - */ - selem_unlink_map(selem); - selem_unlink_sk(selem); -} - -static struct bpf_sk_storage_data * -__sk_storage_lookup(struct bpf_sk_storage *sk_storage, - struct bpf_sk_storage_map *smap, - bool cacheit_lockit) -{ - struct bpf_sk_storage_data *sdata; - struct bpf_sk_storage_elem *selem; - - /* Fast path (cache hit) */ - sdata = rcu_dereference(sk_storage->cache[smap->cache_idx]); - if (sdata && rcu_access_pointer(sdata->smap) == smap) - return sdata; - - /* Slow path (cache miss) */ - hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) - if (rcu_access_pointer(SDATA(selem)->smap) == smap) - break; - - if (!selem) - return NULL; - - sdata = SDATA(selem); - if (cacheit_lockit) { - /* spinlock is needed to avoid racing with the - * parallel delete. Otherwise, publishing an already - * deleted sdata to the cache will become a use-after-free - * problem in the next __sk_storage_lookup(). - */ - raw_spin_lock_bh(&sk_storage->lock); - if (selem_linked_to_sk(selem)) - rcu_assign_pointer(sk_storage->cache[smap->cache_idx], - sdata); - raw_spin_unlock_bh(&sk_storage->lock); - } - - return sdata; -} - -static struct bpf_sk_storage_data * +static struct bpf_local_storage_data * sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit) { - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_map *smap; + struct bpf_local_storage *sk_storage; + struct bpf_local_storage_map *smap; sk_storage = rcu_dereference(sk->sk_bpf_storage); if (!sk_storage) return NULL; - smap = (struct bpf_sk_storage_map *)map; - return __sk_storage_lookup(sk_storage, smap, cacheit_lockit); -} - -static int check_flags(const struct bpf_sk_storage_data *old_sdata, - u64 map_flags) -{ - if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST) - /* elem already exists */ - return -EEXIST; - - if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST) - /* elem doesn't exist, cannot update it */ - return -ENOENT; - - return 0; -} - -static int sk_storage_alloc(struct sock *sk, - struct bpf_sk_storage_map *smap, - struct bpf_sk_storage_elem *first_selem) -{ - struct bpf_sk_storage *prev_sk_storage, *sk_storage; - int err; - - err = omem_charge(sk, sizeof(*sk_storage)); - if (err) - return err; - - sk_storage = kzalloc(sizeof(*sk_storage), GFP_ATOMIC | __GFP_NOWARN); - if (!sk_storage) { - err = -ENOMEM; - goto uncharge; - } - INIT_HLIST_HEAD(&sk_storage->list); - raw_spin_lock_init(&sk_storage->lock); - sk_storage->sk = sk; - - __selem_link_sk(sk_storage, first_selem); - selem_link_map(smap, first_selem); - /* Publish sk_storage to sk. sk->sk_lock cannot be acquired. - * Hence, atomic ops is used to set sk->sk_bpf_storage - * from NULL to the newly allocated sk_storage ptr. - * - * From now on, the sk->sk_bpf_storage pointer is protected - * by the sk_storage->lock. Hence, when freeing - * the sk->sk_bpf_storage, the sk_storage->lock must - * be held before setting sk->sk_bpf_storage to NULL. - */ - prev_sk_storage = cmpxchg((struct bpf_sk_storage **)&sk->sk_bpf_storage, - NULL, sk_storage); - if (unlikely(prev_sk_storage)) { - selem_unlink_map(first_selem); - err = -EAGAIN; - goto uncharge; - - /* Note that even first_selem was linked to smap's - * bucket->list, first_selem can be freed immediately - * (instead of kfree_rcu) because - * bpf_sk_storage_map_free() does a - * synchronize_rcu() before walking the bucket->list. - * Hence, no one is accessing selem from the - * bucket->list under rcu_read_lock(). - */ - } - - return 0; - -uncharge: - kfree(sk_storage); - atomic_sub(sizeof(*sk_storage), &sk->sk_omem_alloc); - return err; -} - -/* sk cannot be going away because it is linking new elem - * to sk->sk_bpf_storage. (i.e. sk->sk_refcnt cannot be 0). - * Otherwise, it will become a leak (and other memory issues - * during map destruction). - */ -static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk, - struct bpf_map *map, - void *value, - u64 map_flags) -{ - struct bpf_sk_storage_data *old_sdata = NULL; - struct bpf_sk_storage_elem *selem; - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_map *smap; - int err; - - /* BPF_EXIST and BPF_NOEXIST cannot be both set */ - if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) || - /* BPF_F_LOCK can only be used in a value with spin_lock */ - unlikely((map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map))) - return ERR_PTR(-EINVAL); - - smap = (struct bpf_sk_storage_map *)map; - sk_storage = rcu_dereference(sk->sk_bpf_storage); - if (!sk_storage || hlist_empty(&sk_storage->list)) { - /* Very first elem for this sk */ - err = check_flags(NULL, map_flags); - if (err) - return ERR_PTR(err); - - selem = selem_alloc(smap, sk, value, true); - if (!selem) - return ERR_PTR(-ENOMEM); - - err = sk_storage_alloc(sk, smap, selem); - if (err) { - kfree(selem); - atomic_sub(smap->elem_size, &sk->sk_omem_alloc); - return ERR_PTR(err); - } - - return SDATA(selem); - } - - if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) { - /* Hoping to find an old_sdata to do inline update - * such that it can avoid taking the sk_storage->lock - * and changing the lists. - */ - old_sdata = __sk_storage_lookup(sk_storage, smap, false); - err = check_flags(old_sdata, map_flags); - if (err) - return ERR_PTR(err); - if (old_sdata && selem_linked_to_sk(SELEM(old_sdata))) { - copy_map_value_locked(map, old_sdata->data, - value, false); - return old_sdata; - } - } - - raw_spin_lock_bh(&sk_storage->lock); - - /* Recheck sk_storage->list under sk_storage->lock */ - if (unlikely(hlist_empty(&sk_storage->list))) { - /* A parallel del is happening and sk_storage is going - * away. It has just been checked before, so very - * unlikely. Return instead of retry to keep things - * simple. - */ - err = -EAGAIN; - goto unlock_err; - } - - old_sdata = __sk_storage_lookup(sk_storage, smap, false); - err = check_flags(old_sdata, map_flags); - if (err) - goto unlock_err; - - if (old_sdata && (map_flags & BPF_F_LOCK)) { - copy_map_value_locked(map, old_sdata->data, value, false); - selem = SELEM(old_sdata); - goto unlock; - } - - /* sk_storage->lock is held. Hence, we are sure - * we can unlink and uncharge the old_sdata successfully - * later. Hence, instead of charging the new selem now - * and then uncharge the old selem later (which may cause - * a potential but unnecessary charge failure), avoid taking - * a charge at all here (the "!old_sdata" check) and the - * old_sdata will not be uncharged later during __selem_unlink_sk(). - */ - selem = selem_alloc(smap, sk, value, !old_sdata); - if (!selem) { - err = -ENOMEM; - goto unlock_err; - } - - /* First, link the new selem to the map */ - selem_link_map(smap, selem); - - /* Second, link (and publish) the new selem to sk_storage */ - __selem_link_sk(sk_storage, selem); - - /* Third, remove old selem, SELEM(old_sdata) */ - if (old_sdata) { - selem_unlink_map(SELEM(old_sdata)); - __selem_unlink_sk(sk_storage, SELEM(old_sdata), false); - } - -unlock: - raw_spin_unlock_bh(&sk_storage->lock); - return SDATA(selem); - -unlock_err: - raw_spin_unlock_bh(&sk_storage->lock); - return ERR_PTR(err); + smap = (struct bpf_local_storage_map *)map; + return bpf_local_storage_lookup(sk_storage, smap, cacheit_lockit); } static int sk_storage_delete(struct sock *sk, struct bpf_map *map) { - struct bpf_sk_storage_data *sdata; + struct bpf_local_storage_data *sdata; sdata = sk_storage_lookup(sk, map, false); if (!sdata) return -ENOENT; - selem_unlink(SELEM(sdata)); + bpf_selem_unlink(SELEM(sdata)); return 0; } -static u16 cache_idx_get(void) -{ - u64 min_usage = U64_MAX; - u16 i, res = 0; - - spin_lock(&cache_idx_lock); - - for (i = 0; i < BPF_SK_STORAGE_CACHE_SIZE; i++) { - if (cache_idx_usage_counts[i] < min_usage) { - min_usage = cache_idx_usage_counts[i]; - res = i; - - /* Found a free cache_idx */ - if (!min_usage) - break; - } - } - cache_idx_usage_counts[res]++; - - spin_unlock(&cache_idx_lock); - - return res; -} - -static void cache_idx_free(u16 idx) -{ - spin_lock(&cache_idx_lock); - cache_idx_usage_counts[idx]--; - spin_unlock(&cache_idx_lock); -} - /* Called by __sk_destruct() & bpf_sk_storage_clone() */ void bpf_sk_storage_free(struct sock *sk) { - struct bpf_sk_storage_elem *selem; - struct bpf_sk_storage *sk_storage; + struct bpf_local_storage_elem *selem; + struct bpf_local_storage *sk_storage; bool free_sk_storage = false; struct hlist_node *n; @@ -565,7 +74,7 @@ void bpf_sk_storage_free(struct sock *sk) * Thus, no elem can be added-to or deleted-from the * sk_storage->list by the bpf_prog or by the bpf-map's syscall. * - * It is racing with bpf_sk_storage_map_free() alone + * It is racing with bpf_local_storage_map_free() alone * when unlinking elem from the sk_storage->list and * the map's bucket->list. */ @@ -574,8 +83,9 @@ void bpf_sk_storage_free(struct sock *sk) /* Always unlink from map before unlinking from * sk_storage. */ - selem_unlink_map(selem); - free_sk_storage = __selem_unlink_sk(sk_storage, selem, true); + bpf_selem_unlink_map(selem); + free_sk_storage = bpf_selem_unlink_storage_nolock(sk_storage, + selem, true); } raw_spin_unlock_bh(&sk_storage->lock); rcu_read_unlock(); @@ -584,132 +94,24 @@ void bpf_sk_storage_free(struct sock *sk) kfree_rcu(sk_storage, rcu); } -static void bpf_sk_storage_map_free(struct bpf_map *map) -{ - struct bpf_sk_storage_elem *selem; - struct bpf_sk_storage_map *smap; - struct bucket *b; - unsigned int i; - - smap = (struct bpf_sk_storage_map *)map; - - cache_idx_free(smap->cache_idx); - - /* Note that this map might be concurrently cloned from - * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone - * RCU read section to finish before proceeding. New RCU - * read sections should be prevented via bpf_map_inc_not_zero. - */ - synchronize_rcu(); - - /* bpf prog and the userspace can no longer access this map - * now. No new selem (of this map) can be added - * to the sk->sk_bpf_storage or to the map bucket's list. - * - * The elem of this map can be cleaned up here - * or - * by bpf_sk_storage_free() during __sk_destruct(). - */ - for (i = 0; i < (1U << smap->bucket_log); i++) { - b = &smap->buckets[i]; - - rcu_read_lock(); - /* No one is adding to b->list now */ - while ((selem = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(&b->list)), - struct bpf_sk_storage_elem, - map_node))) { - selem_unlink(selem); - cond_resched_rcu(); - } - rcu_read_unlock(); - } - - /* bpf_sk_storage_free() may still need to access the map. - * e.g. bpf_sk_storage_free() has unlinked selem from the map - * which then made the above while((selem = ...)) loop - * exited immediately. - * - * However, the bpf_sk_storage_free() still needs to access - * the smap->elem_size to do the uncharging in - * __selem_unlink_sk(). - * - * Hence, wait another rcu grace period for the - * bpf_sk_storage_free() to finish. - */ - synchronize_rcu(); - - kvfree(smap->buckets); - kfree(map); -} - -/* U16_MAX is much more than enough for sk local storage - * considering a tcp_sock is ~2k. - */ -#define MAX_VALUE_SIZE \ - min_t(u32, \ - (KMALLOC_MAX_SIZE - MAX_BPF_STACK - sizeof(struct bpf_sk_storage_elem)), \ - (U16_MAX - sizeof(struct bpf_sk_storage_elem))) - -static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr) +static void sk_storage_map_free(struct bpf_map *map) { - if (attr->map_flags & ~SK_STORAGE_CREATE_FLAG_MASK || - !(attr->map_flags & BPF_F_NO_PREALLOC) || - attr->max_entries || - attr->key_size != sizeof(int) || !attr->value_size || - /* Enforce BTF for userspace sk dumping */ - !attr->btf_key_type_id || !attr->btf_value_type_id) - return -EINVAL; - - if (!bpf_capable()) - return -EPERM; - - if (attr->value_size > MAX_VALUE_SIZE) - return -E2BIG; + struct bpf_local_storage_map *smap; - return 0; + smap = (struct bpf_local_storage_map *)map; + bpf_local_storage_cache_idx_free(&sk_cache, smap->cache_idx); + bpf_local_storage_map_free(smap); } -static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) +static struct bpf_map *sk_storage_map_alloc(union bpf_attr *attr) { - struct bpf_sk_storage_map *smap; - unsigned int i; - u32 nbuckets; - u64 cost; - int ret; - - smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN); - if (!smap) - return ERR_PTR(-ENOMEM); - bpf_map_init_from_attr(&smap->map, attr); - - nbuckets = roundup_pow_of_two(num_possible_cpus()); - /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */ - nbuckets = max_t(u32, 2, nbuckets); - smap->bucket_log = ilog2(nbuckets); - cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap); - - ret = bpf_map_charge_init(&smap->map.memory, cost); - if (ret < 0) { - kfree(smap); - return ERR_PTR(ret); - } + struct bpf_local_storage_map *smap; - smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets, - GFP_USER | __GFP_NOWARN); - if (!smap->buckets) { - bpf_map_charge_finish(&smap->map.memory); - kfree(smap); - return ERR_PTR(-ENOMEM); - } - - for (i = 0; i < nbuckets; i++) { - INIT_HLIST_HEAD(&smap->buckets[i].list); - raw_spin_lock_init(&smap->buckets[i].lock); - } - - smap->elem_size = sizeof(struct bpf_sk_storage_elem) + attr->value_size; - smap->cache_idx = cache_idx_get(); + smap = bpf_local_storage_map_alloc(attr); + if (IS_ERR(smap)) + return ERR_CAST(smap); + smap->cache_idx = bpf_local_storage_cache_idx_get(&sk_cache); return &smap->map; } @@ -719,26 +121,9 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key, return -ENOTSUPP; } -static int bpf_sk_storage_map_check_btf(const struct bpf_map *map, - const struct btf *btf, - const struct btf_type *key_type, - const struct btf_type *value_type) -{ - u32 int_data; - - if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) - return -EINVAL; - - int_data = *(u32 *)(key_type + 1); - if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data)) - return -EINVAL; - - return 0; -} - static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key) { - struct bpf_sk_storage_data *sdata; + struct bpf_local_storage_data *sdata; struct socket *sock; int fd, err; @@ -756,14 +141,16 @@ static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key) static int bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { - struct bpf_sk_storage_data *sdata; + struct bpf_local_storage_data *sdata; struct socket *sock; int fd, err; fd = *(int *)key; sock = sockfd_lookup(fd, &err); if (sock) { - sdata = sk_storage_update(sock->sk, map, value, map_flags); + sdata = bpf_local_storage_update( + sock->sk, (struct bpf_local_storage_map *)map, value, + map_flags); sockfd_put(sock); return PTR_ERR_OR_ZERO(sdata); } @@ -787,14 +174,14 @@ static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key) return err; } -static struct bpf_sk_storage_elem * +static struct bpf_local_storage_elem * bpf_sk_storage_clone_elem(struct sock *newsk, - struct bpf_sk_storage_map *smap, - struct bpf_sk_storage_elem *selem) + struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem) { - struct bpf_sk_storage_elem *copy_selem; + struct bpf_local_storage_elem *copy_selem; - copy_selem = selem_alloc(smap, newsk, NULL, true); + copy_selem = bpf_selem_alloc(smap, newsk, NULL, true); if (!copy_selem) return NULL; @@ -810,9 +197,9 @@ bpf_sk_storage_clone_elem(struct sock *newsk, int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) { - struct bpf_sk_storage *new_sk_storage = NULL; - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_elem *selem; + struct bpf_local_storage *new_sk_storage = NULL; + struct bpf_local_storage *sk_storage; + struct bpf_local_storage_elem *selem; int ret = 0; RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL); @@ -824,8 +211,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) goto out; hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) { - struct bpf_sk_storage_elem *copy_selem; - struct bpf_sk_storage_map *smap; + struct bpf_local_storage_elem *copy_selem; + struct bpf_local_storage_map *smap; struct bpf_map *map; smap = rcu_dereference(SDATA(selem)->smap); @@ -833,7 +220,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) continue; /* Note that for lockless listeners adding new element - * here can race with cleanup in bpf_sk_storage_map_free. + * here can race with cleanup in bpf_local_storage_map_free. * Try to grab map refcnt to make sure that it's still * alive and prevent concurrent removal. */ @@ -849,10 +236,10 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) } if (new_sk_storage) { - selem_link_map(smap, copy_selem); - __selem_link_sk(new_sk_storage, copy_selem); + bpf_selem_link_map(smap, copy_selem); + bpf_selem_link_storage_nolock(new_sk_storage, copy_selem); } else { - ret = sk_storage_alloc(newsk, smap, copy_selem); + ret = bpf_local_storage_alloc(newsk, smap, copy_selem); if (ret) { kfree(copy_selem); atomic_sub(smap->elem_size, @@ -861,7 +248,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) goto out; } - new_sk_storage = rcu_dereference(copy_selem->sk_storage); + new_sk_storage = + rcu_dereference(copy_selem->local_storage); } bpf_map_put(map); } @@ -879,9 +267,9 @@ out: BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, void *, value, u64, flags) { - struct bpf_sk_storage_data *sdata; + struct bpf_local_storage_data *sdata; - if (flags > BPF_SK_STORAGE_GET_F_CREATE) + if (!sk || !sk_fullsock(sk) || flags > BPF_SK_STORAGE_GET_F_CREATE) return (unsigned long)NULL; sdata = sk_storage_lookup(sk, map, true); @@ -895,7 +283,9 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, * destruction). */ refcount_inc_not_zero(&sk->sk_refcnt)) { - sdata = sk_storage_update(sk, map, value, BPF_NOEXIST); + sdata = bpf_local_storage_update( + sk, (struct bpf_local_storage_map *)map, value, + BPF_NOEXIST); /* sk must be a fullsock (guaranteed by verifier), * so sock_gen_put() is unnecessary. */ @@ -909,6 +299,9 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk) { + if (!sk || !sk_fullsock(sk)) + return -EINVAL; + if (refcount_inc_not_zero(&sk->sk_refcnt)) { int err; @@ -920,18 +313,44 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk) return -ENOENT; } +static int sk_storage_charge(struct bpf_local_storage_map *smap, + void *owner, u32 size) +{ + return omem_charge(owner, size); +} + +static void sk_storage_uncharge(struct bpf_local_storage_map *smap, + void *owner, u32 size) +{ + struct sock *sk = owner; + + atomic_sub(size, &sk->sk_omem_alloc); +} + +static struct bpf_local_storage __rcu ** +sk_storage_ptr(void *owner) +{ + struct sock *sk = owner; + + return &sk->sk_bpf_storage; +} + static int sk_storage_map_btf_id; const struct bpf_map_ops sk_storage_map_ops = { - .map_alloc_check = bpf_sk_storage_map_alloc_check, - .map_alloc = bpf_sk_storage_map_alloc, - .map_free = bpf_sk_storage_map_free, + .map_meta_equal = bpf_map_meta_equal, + .map_alloc_check = bpf_local_storage_map_alloc_check, + .map_alloc = sk_storage_map_alloc, + .map_free = sk_storage_map_free, .map_get_next_key = notsupp_get_next_key, .map_lookup_elem = bpf_fd_sk_storage_lookup_elem, .map_update_elem = bpf_fd_sk_storage_update_elem, .map_delete_elem = bpf_fd_sk_storage_delete_elem, - .map_check_btf = bpf_sk_storage_map_check_btf, - .map_btf_name = "bpf_sk_storage_map", + .map_check_btf = bpf_local_storage_map_check_btf, + .map_btf_name = "bpf_local_storage_map", .map_btf_id = &sk_storage_map_btf_id, + .map_local_storage_charge = sk_storage_charge, + .map_local_storage_uncharge = sk_storage_uncharge, + .map_owner_storage_ptr = sk_storage_ptr, }; const struct bpf_func_proto bpf_sk_storage_get_proto = { @@ -939,7 +358,7 @@ const struct bpf_func_proto bpf_sk_storage_get_proto = { .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_SOCKET, + .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, }; @@ -959,7 +378,7 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_SOCKET, + .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, }; struct bpf_sk_storage_diag { @@ -1022,7 +441,7 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) u32 nr_maps = 0; int rem, err; - /* bpf_sk_storage_map is currently limited to CAP_SYS_ADMIN as + /* bpf_local_storage_map is currently limited to CAP_SYS_ADMIN as * the map_alloc_check() side also does. */ if (!bpf_capable()) @@ -1072,13 +491,13 @@ err_free: } EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_alloc); -static int diag_get(struct bpf_sk_storage_data *sdata, struct sk_buff *skb) +static int diag_get(struct bpf_local_storage_data *sdata, struct sk_buff *skb) { struct nlattr *nla_stg, *nla_value; - struct bpf_sk_storage_map *smap; + struct bpf_local_storage_map *smap; /* It cannot exceed max nlattr's payload */ - BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < MAX_VALUE_SIZE); + BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < BPF_LOCAL_STORAGE_MAX_VALUE_SIZE); nla_stg = nla_nest_start(skb, SK_DIAG_BPF_STORAGE); if (!nla_stg) @@ -1114,9 +533,9 @@ static int bpf_sk_storage_diag_put_all(struct sock *sk, struct sk_buff *skb, { /* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */ unsigned int diag_size = nla_total_size(0); - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_elem *selem; - struct bpf_sk_storage_map *smap; + struct bpf_local_storage *sk_storage; + struct bpf_local_storage_elem *selem; + struct bpf_local_storage_map *smap; struct nlattr *nla_stgs; unsigned int saved_len; int err = 0; @@ -1169,8 +588,8 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag, { /* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */ unsigned int diag_size = nla_total_size(0); - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_data *sdata; + struct bpf_local_storage *sk_storage; + struct bpf_local_storage_data *sdata; struct nlattr *nla_stgs; unsigned int saved_len; int err = 0; @@ -1197,8 +616,8 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag, saved_len = skb->len; for (i = 0; i < diag->nr_maps; i++) { - sdata = __sk_storage_lookup(sk_storage, - (struct bpf_sk_storage_map *)diag->maps[i], + sdata = bpf_local_storage_lookup(sk_storage, + (struct bpf_local_storage_map *)diag->maps[i], false); if (!sdata) @@ -1235,19 +654,20 @@ struct bpf_iter_seq_sk_storage_map_info { unsigned skip_elems; }; -static struct bpf_sk_storage_elem * +static struct bpf_local_storage_elem * bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, - struct bpf_sk_storage_elem *prev_selem) + struct bpf_local_storage_elem *prev_selem) + __acquires(RCU) __releases(RCU) { - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_elem *selem; + struct bpf_local_storage *sk_storage; + struct bpf_local_storage_elem *selem; u32 skip_elems = info->skip_elems; - struct bpf_sk_storage_map *smap; + struct bpf_local_storage_map *smap; u32 bucket_id = info->bucket_id; u32 i, count, n_buckets; - struct bucket *b; + struct bpf_local_storage_map_bucket *b; - smap = (struct bpf_sk_storage_map *)info->map; + smap = (struct bpf_local_storage_map *)info->map; n_buckets = 1U << smap->bucket_log; if (bucket_id >= n_buckets) return NULL; @@ -1256,16 +676,16 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, selem = prev_selem; count = 0; while (selem) { - selem = hlist_entry_safe(selem->map_node.next, - struct bpf_sk_storage_elem, map_node); + selem = hlist_entry_safe(rcu_dereference(hlist_next_rcu(&selem->map_node)), + struct bpf_local_storage_elem, map_node); if (!selem) { /* not found, unlock and go to the next bucket */ b = &smap->buckets[bucket_id++]; - raw_spin_unlock_bh(&b->lock); + rcu_read_unlock(); skip_elems = 0; break; } - sk_storage = rcu_dereference_raw(selem->sk_storage); + sk_storage = rcu_dereference(selem->local_storage); if (sk_storage) { info->skip_elems = skip_elems + count; return selem; @@ -1275,10 +695,10 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, for (i = bucket_id; i < (1U << smap->bucket_log); i++) { b = &smap->buckets[i]; - raw_spin_lock_bh(&b->lock); + rcu_read_lock(); count = 0; - hlist_for_each_entry(selem, &b->list, map_node) { - sk_storage = rcu_dereference_raw(selem->sk_storage); + hlist_for_each_entry_rcu(selem, &b->list, map_node) { + sk_storage = rcu_dereference(selem->local_storage); if (sk_storage && count >= skip_elems) { info->bucket_id = i; info->skip_elems = count; @@ -1286,7 +706,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, } count++; } - raw_spin_unlock_bh(&b->lock); + rcu_read_unlock(); skip_elems = 0; } @@ -1297,7 +717,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, static void *bpf_sk_storage_map_seq_start(struct seq_file *seq, loff_t *pos) { - struct bpf_sk_storage_elem *selem; + struct bpf_local_storage_elem *selem; selem = bpf_sk_storage_map_seq_find_next(seq->private, NULL); if (!selem) @@ -1330,11 +750,11 @@ DEFINE_BPF_ITER_FUNC(bpf_sk_storage_map, struct bpf_iter_meta *meta, void *value) static int __bpf_sk_storage_map_seq_show(struct seq_file *seq, - struct bpf_sk_storage_elem *selem) + struct bpf_local_storage_elem *selem) { struct bpf_iter_seq_sk_storage_map_info *info = seq->private; struct bpf_iter__bpf_sk_storage_map ctx = {}; - struct bpf_sk_storage *sk_storage; + struct bpf_local_storage *sk_storage; struct bpf_iter_meta meta; struct bpf_prog *prog; int ret = 0; @@ -1345,8 +765,8 @@ static int __bpf_sk_storage_map_seq_show(struct seq_file *seq, ctx.meta = &meta; ctx.map = info->map; if (selem) { - sk_storage = rcu_dereference_raw(selem->sk_storage); - ctx.sk = sk_storage->sk; + sk_storage = rcu_dereference(selem->local_storage); + ctx.sk = sk_storage->owner; ctx.value = SDATA(selem)->data; } ret = bpf_iter_run_prog(prog, &ctx); @@ -1361,18 +781,12 @@ static int bpf_sk_storage_map_seq_show(struct seq_file *seq, void *v) } static void bpf_sk_storage_map_seq_stop(struct seq_file *seq, void *v) + __releases(RCU) { - struct bpf_iter_seq_sk_storage_map_info *info = seq->private; - struct bpf_sk_storage_map *smap; - struct bucket *b; - - if (!v) { + if (!v) (void)__bpf_sk_storage_map_seq_show(seq, v); - } else { - smap = (struct bpf_sk_storage_map *)info->map; - b = &smap->buckets[info->bucket_id]; - raw_spin_unlock_bh(&b->lock); - } + else + rcu_read_unlock(); } static int bpf_iter_init_sk_storage_map(void *priv_data, @@ -1437,6 +851,8 @@ static struct bpf_iter_reg bpf_sk_storage_map_reg_info = { .target = "bpf_sk_storage_map", .attach_target = bpf_iter_attach_map, .detach_target = bpf_iter_detach_map, + .show_fdinfo = bpf_iter_map_show_fdinfo, + .fill_link_info = bpf_iter_map_fill_link_info, .ctx_arg_info_size = 2, .ctx_arg_info = { { offsetof(struct bpf_iter__bpf_sk_storage_map, sk), diff --git a/net/core/datagram.c b/net/core/datagram.c index 639745d4f3b9..9fcaa544f11a 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -623,10 +623,11 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, while (length && iov_iter_count(from)) { struct page *pages[MAX_SKB_FRAGS]; + struct page *last_head = NULL; size_t start; ssize_t copied; unsigned long truesize; - int n = 0; + int refs, n = 0; if (frag == MAX_SKB_FRAGS) return -EMSGSIZE; @@ -649,13 +650,37 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, } else { refcount_add(truesize, &skb->sk->sk_wmem_alloc); } - while (copied) { + for (refs = 0; copied != 0; start = 0) { int size = min_t(int, copied, PAGE_SIZE - start); - skb_fill_page_desc(skb, frag++, pages[n], start, size); - start = 0; + struct page *head = compound_head(pages[n]); + + start += (pages[n] - head) << PAGE_SHIFT; copied -= size; n++; + if (frag) { + skb_frag_t *last = &skb_shinfo(skb)->frags[frag - 1]; + + if (head == skb_frag_page(last) && + start == skb_frag_off(last) + skb_frag_size(last)) { + skb_frag_size_add(last, size); + /* We combined this page, we need to release + * a reference. Since compound pages refcount + * is shared among many pages, batch the refcount + * adjustments to limit false sharing. + */ + last_head = head; + refs++; + continue; + } + } + if (refs) { + page_ref_sub(last_head, refs); + refs = 0; + } + skb_fill_page_desc(skb, frag++, head, start, size); } + if (refs) + page_ref_sub(last_head, refs); } return 0; } diff --git a/net/core/dev.c b/net/core/dev.c index 4906b44af850..82dc6b48e45f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -98,6 +98,7 @@ #include <net/busy_poll.h> #include <linux/rtnetlink.h> #include <linux/stat.h> +#include <net/dsa.h> #include <net/dst.h> #include <net/dst_metadata.h> #include <net/pkt_sched.h> @@ -144,6 +145,7 @@ #include <linux/indirect_call_wrapper.h> #include <net/devlink.h> #include <linux/pm_runtime.h> +#include <linux/prandom.h> #include "net-sysfs.h" @@ -1130,7 +1132,7 @@ EXPORT_SYMBOL(__dev_get_by_flags); * @name: name string * * Network device names need to be valid file names to - * to allow sysfs to work. We also disallow any kind of + * allow sysfs to work. We also disallow any kind of * whitespace. */ bool dev_valid_name(const char *name) @@ -3557,6 +3559,7 @@ static int xmit_one(struct sk_buff *skb, struct net_device *dev, dev_queue_xmit_nit(skb, dev); len = skb->len; + PRANDOM_ADD_NOISE(skb, dev, txq, len + jiffies); trace_net_dev_start_xmit(skb, dev); rc = netdev_start_xmit(skb, dev, txq, more); trace_net_dev_xmit(skb, rc, dev, len); @@ -4129,6 +4132,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) if (!skb) goto out; + PRANDOM_ADD_NOISE(skb, dev, txq, jiffies); HARD_TX_LOCK(dev, txq, cpu); if (!netif_xmit_stopped(txq)) { @@ -4194,6 +4198,7 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) skb_set_queue_mapping(skb, queue_id); txq = skb_get_tx_queue(dev, skb); + PRANDOM_ADD_NOISE(skb, dev, txq, jiffies); local_bh_disable(); @@ -4840,6 +4845,21 @@ int netif_rx_ni(struct sk_buff *skb) } EXPORT_SYMBOL(netif_rx_ni); +int netif_rx_any_context(struct sk_buff *skb) +{ + /* + * If invoked from contexts which do not invoke bottom half + * processing either at return from interrupt or when softrqs are + * reenabled, use netif_rx_ni() which invokes bottomhalf processing + * directly. + */ + if (in_interrupt()) + return netif_rx(skb); + else + return netif_rx_ni(skb); +} +EXPORT_SYMBOL(netif_rx_any_context); + static __latent_entropy void net_tx_action(struct softirq_action *h) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); @@ -4914,7 +4934,7 @@ EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); static inline struct sk_buff * sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, - struct net_device *orig_dev) + struct net_device *orig_dev, bool *another) { #ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc *miniq = rcu_dereference_bh(skb->dev->miniq_ingress); @@ -4958,7 +4978,11 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, * redirecting to another netdev */ __skb_push(skb, skb->mac_len); - skb_do_redirect(skb); + if (skb_do_redirect(skb) == -EAGAIN) { + __skb_pull(skb, skb->mac_len); + *another = true; + break; + } return NULL; case TC_ACT_CONSUMED: return NULL; @@ -5147,7 +5171,12 @@ another_round: skip_taps: #ifdef CONFIG_NET_INGRESS if (static_branch_unlikely(&ingress_needed_key)) { - skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev); + bool another = false; + + skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev, + &another); + if (another) + goto another_round; if (!skb) goto out; @@ -5192,7 +5221,7 @@ skip_classify: } } - if (unlikely(skb_vlan_tag_present(skb))) { + if (unlikely(skb_vlan_tag_present(skb)) && !netdev_uses_dsa(skb->dev)) { check_vlan_id: if (skb_vlan_tag_get_id(skb)) { /* Vlan id is non 0 and vlan_do_receive() above couldn't @@ -5441,15 +5470,20 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) 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])) - return -EINVAL; - if (cpu_map_prog_allowed(new->aux->used_maps[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) { @@ -5621,17 +5655,60 @@ static void flush_backlog(struct work_struct *work) local_bh_enable(); } +static bool flush_required(int cpu) +{ +#if IS_ENABLED(CONFIG_RPS) + struct softnet_data *sd = &per_cpu(softnet_data, cpu); + bool do_flush; + + local_irq_disable(); + rps_lock(sd); + + /* as insertion into process_queue happens with the rps lock held, + * process_queue access may race only with dequeue + */ + do_flush = !skb_queue_empty(&sd->input_pkt_queue) || + !skb_queue_empty_lockless(&sd->process_queue); + rps_unlock(sd); + local_irq_enable(); + + return do_flush; +#endif + /* without RPS we can't safely check input_pkt_queue: during a + * concurrent remote skb_queue_splice() we can detect as empty both + * input_pkt_queue and process_queue even if the latter could end-up + * containing a lot of packets. + */ + return true; +} + static void flush_all_backlogs(void) { + static cpumask_t flush_cpus; unsigned int cpu; + /* since we are under rtnl lock protection we can use static data + * for the cpumask and avoid allocating on stack the possibly + * large mask + */ + ASSERT_RTNL(); + get_online_cpus(); - for_each_online_cpu(cpu) - queue_work_on(cpu, system_highpri_wq, - per_cpu_ptr(&flush_works, cpu)); + cpumask_clear(&flush_cpus); + for_each_online_cpu(cpu) { + if (flush_required(cpu)) { + queue_work_on(cpu, system_highpri_wq, + per_cpu_ptr(&flush_works, cpu)); + cpumask_set_cpu(cpu, &flush_cpus); + } + } - for_each_online_cpu(cpu) + /* we can have in flight packet[s] on the cpus we are not flushing, + * synchronize_net() in rollback_registered_many() will take care of + * them + */ + for_each_cpu(cpu, &flush_cpus) flush_work(per_cpu_ptr(&flush_works, cpu)); put_online_cpus(); @@ -6293,7 +6370,7 @@ EXPORT_SYMBOL(__napi_schedule); * @n: napi context * * Test if NAPI routine is already running, and if not mark - * it as running. This is used as a condition variable + * it as running. This is used as a condition variable to * insure only one NAPI poll instance runs. We also make * sure there is no pending NAPI disable. */ @@ -6533,8 +6610,7 @@ EXPORT_SYMBOL(napi_busy_loop); static void napi_hash_add(struct napi_struct *napi) { - if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state) || - test_and_set_bit(NAPI_STATE_HASHED, &napi->state)) + if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state)) return; spin_lock(&napi_hash_lock); @@ -6555,20 +6631,14 @@ static void napi_hash_add(struct napi_struct *napi) /* Warning : caller is responsible to make sure rcu grace period * is respected before freeing memory containing @napi */ -bool napi_hash_del(struct napi_struct *napi) +static void napi_hash_del(struct napi_struct *napi) { - bool rcu_sync_needed = false; - spin_lock(&napi_hash_lock); - if (test_and_clear_bit(NAPI_STATE_HASHED, &napi->state)) { - rcu_sync_needed = true; - hlist_del_rcu(&napi->napi_hash_node); - } + hlist_del_init_rcu(&napi->napi_hash_node); + spin_unlock(&napi_hash_lock); - return rcu_sync_needed; } -EXPORT_SYMBOL_GPL(napi_hash_del); static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) { @@ -6600,7 +6670,11 @@ static void init_gro_hash(struct napi_struct *napi) void netif_napi_add(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { + if (WARN_ON(test_and_set_bit(NAPI_STATE_LISTED, &napi->state))) + return; + INIT_LIST_HEAD(&napi->poll_list); + INIT_HLIST_NODE(&napi->napi_hash_node); hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); napi->timer.function = napi_watchdog; init_gro_hash(napi); @@ -6653,18 +6727,19 @@ static void flush_gro_hash(struct napi_struct *napi) } /* Must be called in process context */ -void netif_napi_del(struct napi_struct *napi) +void __netif_napi_del(struct napi_struct *napi) { - might_sleep(); - if (napi_hash_del(napi)) - synchronize_net(); - list_del_init(&napi->dev_list); + if (!test_and_clear_bit(NAPI_STATE_LISTED, &napi->state)) + return; + + napi_hash_del(napi); + list_del_rcu(&napi->dev_list); napi_free_frags(napi); flush_gro_hash(napi); napi->gro_bitmask = 0; } -EXPORT_SYMBOL(netif_napi_del); +EXPORT_SYMBOL(__netif_napi_del); static int napi_poll(struct napi_struct *n, struct list_head *repoll) { @@ -9533,7 +9608,7 @@ int __netdev_update_features(struct net_device *dev) /* driver might be less strict about feature dependencies */ features = netdev_fix_features(dev, features); - /* some features can't be enabled if they're off an an upper device */ + /* some features can't be enabled if they're off on an upper device */ netdev_for_each_upper_dev_rcu(dev, upper, iter) features = netdev_sync_upper_features(dev, upper, features); @@ -10037,6 +10112,8 @@ int netdev_refcnt_read(const struct net_device *dev) } EXPORT_SYMBOL(netdev_refcnt_read); +#define WAIT_REFS_MIN_MSECS 1 +#define WAIT_REFS_MAX_MSECS 250 /** * netdev_wait_allrefs - wait until all references are gone. * @dev: target net_device @@ -10052,7 +10129,7 @@ EXPORT_SYMBOL(netdev_refcnt_read); static void netdev_wait_allrefs(struct net_device *dev) { unsigned long rebroadcast_time, warning_time; - int refcnt; + int wait = 0, refcnt; linkwatch_forget_dev(dev); @@ -10086,7 +10163,13 @@ static void netdev_wait_allrefs(struct net_device *dev) rebroadcast_time = jiffies; } - msleep(250); + if (!wait) { + rcu_barrier(); + wait = WAIT_REFS_MIN_MSECS; + } else { + msleep(wait); + wait = min(wait << 1, WAIT_REFS_MAX_MSECS); + } refcnt = netdev_refcnt_read(dev); @@ -10134,7 +10217,7 @@ void netdev_run_todo(void) struct net_device *dev = list_first_entry(&unlink_list, struct net_device, unlink_list); - list_del(&dev->unlink_list); + list_del_init(&dev->unlink_list); dev->nested_level = dev->lower_level - 1; } #endif @@ -10249,6 +10332,40 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, } EXPORT_SYMBOL(dev_get_stats); +/** + * dev_fetch_sw_netstats - get per-cpu network device statistics + * @s: place to store stats + * @netstats: per-cpu network stats to read from + * + * Read per-cpu network statistics and populate the related fields in @s. + */ +void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, + const struct pcpu_sw_netstats __percpu *netstats) +{ + int cpu; + + for_each_possible_cpu(cpu) { + const struct pcpu_sw_netstats *stats; + struct pcpu_sw_netstats tmp; + unsigned int start; + + stats = per_cpu_ptr(netstats, cpu); + do { + start = u64_stats_fetch_begin_irq(&stats->syncp); + tmp.rx_packets = stats->rx_packets; + tmp.rx_bytes = stats->rx_bytes; + tmp.tx_packets = stats->tx_packets; + tmp.tx_bytes = stats->tx_bytes; + } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); + + s->rx_packets += tmp.rx_packets; + s->rx_bytes += tmp.rx_bytes; + s->tx_packets += tmp.tx_packets; + s->tx_bytes += tmp.tx_bytes; + } +} +EXPORT_SYMBOL_GPL(dev_fetch_sw_netstats); + struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) { struct netdev_queue *queue = dev_ingress_queue(dev); diff --git a/net/core/devlink.c b/net/core/devlink.c index 80ec1cd81c64..a932d95be798 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -27,7 +27,6 @@ #include <net/net_namespace.h> #include <net/sock.h> #include <net/devlink.h> -#include <net/drop_monitor.h> #define CREATE_TRACE_POINTS #include <trace/events/devlink.h> @@ -84,6 +83,7 @@ EXPORT_SYMBOL(devlink_dpipe_header_ipv6); EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg); EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr); +EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report); static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = { [DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY }, @@ -347,8 +347,12 @@ devlink_sb_tc_index_get_from_info(struct devlink_sb *devlink_sb, struct devlink_region { struct devlink *devlink; + struct devlink_port *port; struct list_head list; - const struct devlink_region_ops *ops; + union { + const struct devlink_region_ops *ops; + const struct devlink_port_region_ops *port_ops; + }; struct list_head snapshot_list; u32 max_snapshots; u32 cur_snapshots; @@ -374,6 +378,19 @@ devlink_region_get_by_name(struct devlink *devlink, const char *region_name) return NULL; } +static struct devlink_region * +devlink_port_region_get_by_name(struct devlink_port *port, + const char *region_name) +{ + struct devlink_region *region; + + list_for_each_entry(region, &port->region_list, list) + if (!strcmp(region->ops->name, region_name)) + return region; + + return NULL; +} + static struct devlink_snapshot * devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id) { @@ -462,10 +479,115 @@ static int devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink) return 0; } +struct devlink_reload_combination { + enum devlink_reload_action action; + enum devlink_reload_limit limit; +}; + +static const struct devlink_reload_combination devlink_reload_invalid_combinations[] = { + { + /* can't reinitialize driver with no down time */ + .action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT, + .limit = DEVLINK_RELOAD_LIMIT_NO_RESET, + }, +}; + +static bool +devlink_reload_combination_is_invalid(enum devlink_reload_action action, + enum devlink_reload_limit limit) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++) + if (devlink_reload_invalid_combinations[i].action == action && + devlink_reload_invalid_combinations[i].limit == limit) + return true; + return false; +} + +static bool +devlink_reload_action_is_supported(struct devlink *devlink, enum devlink_reload_action action) +{ + return test_bit(action, &devlink->ops->reload_actions); +} + +static bool +devlink_reload_limit_is_supported(struct devlink *devlink, enum devlink_reload_limit limit) +{ + return test_bit(limit, &devlink->ops->reload_limits); +} + +static int devlink_reload_stat_put(struct sk_buff *msg, enum devlink_reload_action action, + enum devlink_reload_limit limit, u32 value) +{ + struct nlattr *reload_stats_entry; + + reload_stats_entry = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS_ENTRY); + if (!reload_stats_entry) + return -EMSGSIZE; + + if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, action) || + nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) || + nla_put_u32(msg, DEVLINK_ATTR_RELOAD_STATS_VALUE, value)) + goto nla_put_failure; + nla_nest_end(msg, reload_stats_entry); + return 0; + +nla_put_failure: + nla_nest_cancel(msg, reload_stats_entry); + return -EMSGSIZE; +} + +static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink, bool is_remote) +{ + struct nlattr *reload_stats_attr; + int i, j, stat_idx; + u32 value; + + if (!is_remote) + reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS); + else + reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_REMOTE_RELOAD_STATS); + + if (!reload_stats_attr) + return -EMSGSIZE; + + for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) { + /* Remote stats are shown even if not locally supported. Stats + * of actions with unspecified limit are shown though drivers + * don't need to register unspecified limit. + */ + if (!is_remote && j != DEVLINK_RELOAD_LIMIT_UNSPEC && + !devlink_reload_limit_is_supported(devlink, j)) + continue; + for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) { + if ((!is_remote && !devlink_reload_action_is_supported(devlink, i)) || + i == DEVLINK_RELOAD_ACTION_UNSPEC || + devlink_reload_combination_is_invalid(i, j)) + continue; + + stat_idx = j * __DEVLINK_RELOAD_ACTION_MAX + i; + if (!is_remote) + value = devlink->stats.reload_stats[stat_idx]; + else + value = devlink->stats.remote_reload_stats[stat_idx]; + if (devlink_reload_stat_put(msg, i, j, value)) + goto nla_put_failure; + } + } + nla_nest_end(msg, reload_stats_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(msg, reload_stats_attr); + return -EMSGSIZE; +} + static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink, enum devlink_command cmd, u32 portid, u32 seq, int flags) { + struct nlattr *dev_stats; void *hdr; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); @@ -477,9 +599,21 @@ static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink, if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_FAILED, devlink->reload_failed)) goto nla_put_failure; + dev_stats = nla_nest_start(msg, DEVLINK_ATTR_DEV_STATS); + if (!dev_stats) + goto nla_put_failure; + + if (devlink_reload_stats_put(msg, devlink, false)) + goto dev_stats_nest_cancel; + if (devlink_reload_stats_put(msg, devlink, true)) + goto dev_stats_nest_cancel; + + nla_nest_end(msg, dev_stats); genlmsg_end(msg, hdr); return 0; +dev_stats_nest_cancel: + nla_nest_cancel(msg, dev_stats); nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; @@ -523,15 +657,20 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg, return -EMSGSIZE; switch (devlink_port->attrs.flavour) { case DEVLINK_PORT_FLAVOUR_PCI_PF: - if (nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, - attrs->pci_pf.pf)) + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, + attrs->pci_pf.controller) || + nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_pf.pf)) + return -EMSGSIZE; + if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_pf.external)) return -EMSGSIZE; break; case DEVLINK_PORT_FLAVOUR_PCI_VF: - if (nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, - attrs->pci_vf.pf) || - nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER, - attrs->pci_vf.vf)) + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, + attrs->pci_vf.controller) || + nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_vf.pf) || + nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER, attrs->pci_vf.vf)) + return -EMSGSIZE; + if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_vf.external)) return -EMSGSIZE; break; case DEVLINK_PORT_FLAVOUR_PHYSICAL: @@ -806,8 +945,6 @@ static int devlink_port_type_set(struct devlink *devlink, int err; if (devlink->ops->port_type_set) { - if (port_type == DEVLINK_PORT_TYPE_NOTSET) - return -EINVAL; if (port_type == devlink_port->type) return 0; err = devlink->ops->port_type_set(devlink_port, port_type); @@ -2943,9 +3080,9 @@ static void devlink_reload_netns_change(struct devlink *devlink, DEVLINK_CMD_PARAM_NEW); } -static bool devlink_reload_supported(const struct devlink *devlink) +static bool devlink_reload_supported(const struct devlink_ops *ops) { - return devlink->ops->reload_down && devlink->ops->reload_up; + return ops->reload_down && ops->reload_up; } static void devlink_reload_failed_set(struct devlink *devlink, @@ -2963,33 +3100,132 @@ bool devlink_is_reload_failed(const struct devlink *devlink) } EXPORT_SYMBOL_GPL(devlink_is_reload_failed); +static void +__devlink_reload_stats_update(struct devlink *devlink, u32 *reload_stats, + enum devlink_reload_limit limit, u32 actions_performed) +{ + unsigned long actions = actions_performed; + int stat_idx; + int action; + + for_each_set_bit(action, &actions, __DEVLINK_RELOAD_ACTION_MAX) { + stat_idx = limit * __DEVLINK_RELOAD_ACTION_MAX + action; + reload_stats[stat_idx]++; + } + devlink_notify(devlink, DEVLINK_CMD_NEW); +} + +static void +devlink_reload_stats_update(struct devlink *devlink, enum devlink_reload_limit limit, + u32 actions_performed) +{ + __devlink_reload_stats_update(devlink, devlink->stats.reload_stats, limit, + actions_performed); +} + +/** + * devlink_remote_reload_actions_performed - Update devlink on reload actions + * performed which are not a direct result of devlink reload call. + * + * This should be called by a driver after performing reload actions in case it was not + * a result of devlink reload call. For example fw_activate was performed as a result + * of devlink reload triggered fw_activate on another host. + * The motivation for this function is to keep data on reload actions performed on this + * function whether it was done due to direct devlink reload call or not. + * + * @devlink: devlink + * @limit: reload limit + * @actions_performed: bitmask of actions performed + */ +void devlink_remote_reload_actions_performed(struct devlink *devlink, + enum devlink_reload_limit limit, + u32 actions_performed) +{ + if (WARN_ON(!actions_performed || + actions_performed & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) || + actions_performed >= BIT(__DEVLINK_RELOAD_ACTION_MAX) || + limit > DEVLINK_RELOAD_LIMIT_MAX)) + return; + + __devlink_reload_stats_update(devlink, devlink->stats.remote_reload_stats, limit, + actions_performed); +} +EXPORT_SYMBOL_GPL(devlink_remote_reload_actions_performed); + static int devlink_reload(struct devlink *devlink, struct net *dest_net, - struct netlink_ext_ack *extack) + enum devlink_reload_action action, enum devlink_reload_limit limit, + u32 *actions_performed, struct netlink_ext_ack *extack) { + u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; int err; if (!devlink->reload_enabled) return -EOPNOTSUPP; - err = devlink->ops->reload_down(devlink, !!dest_net, extack); + memcpy(remote_reload_stats, devlink->stats.remote_reload_stats, + sizeof(remote_reload_stats)); + 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); - err = devlink->ops->reload_up(devlink, extack); + err = devlink->ops->reload_up(devlink, action, limit, actions_performed, extack); devlink_reload_failed_set(devlink, !!err); - return err; + if (err) + return err; + + 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, + sizeof(remote_reload_stats))); + devlink_reload_stats_update(devlink, limit, *actions_performed); + return 0; +} + +static int +devlink_nl_reload_actions_performed_snd(struct devlink *devlink, u32 actions_performed, + enum devlink_command cmd, struct genl_info *info) +{ + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &devlink_nl_family, 0, cmd); + if (!hdr) + goto free_msg; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + if (nla_put_bitfield32(msg, DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED, actions_performed, + actions_performed)) + goto nla_put_failure; + genlmsg_end(msg, hdr); + + return genlmsg_reply(msg, info); + +nla_put_failure: + genlmsg_cancel(msg, hdr); +free_msg: + nlmsg_free(msg); + return -EMSGSIZE; } static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; + enum devlink_reload_action action; + enum devlink_reload_limit limit; struct net *dest_net = NULL; + u32 actions_performed; int err; - if (!devlink_reload_supported(devlink)) + if (!devlink_reload_supported(devlink->ops)) return -EOPNOTSUPP; err = devlink_resources_validate(devlink, NULL, info); @@ -3006,20 +3242,67 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) return PTR_ERR(dest_net); } - err = devlink_reload(devlink, dest_net, info->extack); + if (info->attrs[DEVLINK_ATTR_RELOAD_ACTION]) + action = nla_get_u8(info->attrs[DEVLINK_ATTR_RELOAD_ACTION]); + else + action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT; + + if (!devlink_reload_action_is_supported(devlink, action)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Requested reload action is not supported by the driver"); + return -EOPNOTSUPP; + } + + limit = DEVLINK_RELOAD_LIMIT_UNSPEC; + if (info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) { + struct nla_bitfield32 limits; + u32 limits_selected; + + limits = nla_get_bitfield32(info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]); + limits_selected = limits.value & limits.selector; + if (!limits_selected) { + NL_SET_ERR_MSG_MOD(info->extack, "Invalid limit selected"); + return -EINVAL; + } + for (limit = 0 ; limit <= DEVLINK_RELOAD_LIMIT_MAX ; limit++) + if (limits_selected & BIT(limit)) + break; + /* UAPI enables multiselection, but currently it is not used */ + if (limits_selected != BIT(limit)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Multiselection of limit is not supported"); + return -EOPNOTSUPP; + } + if (!devlink_reload_limit_is_supported(devlink, limit)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Requested limit is not supported by the driver"); + return -EOPNOTSUPP; + } + if (devlink_reload_combination_is_invalid(action, limit)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Requested limit is invalid for this action"); + return -EINVAL; + } + } + err = devlink_reload(devlink, dest_net, action, limit, &actions_performed, info->extack); if (dest_net) put_net(dest_net); - return err; + if (err) + return err; + /* For backward compatibility generate reply only if attributes used by user */ + if (!info->attrs[DEVLINK_ATTR_RELOAD_ACTION] && !info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) + return 0; + + return devlink_nl_reload_actions_performed_snd(devlink, actions_performed, + DEVLINK_CMD_RELOAD, info); } static int devlink_nl_flash_update_fill(struct sk_buff *msg, struct devlink *devlink, enum devlink_command cmd, - const char *status_msg, - const char *component, - unsigned long done, unsigned long total) + struct devlink_flash_notify *params) { void *hdr; @@ -3033,19 +3316,22 @@ static int devlink_nl_flash_update_fill(struct sk_buff *msg, if (cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS) goto out; - if (status_msg && + if (params->status_msg && nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_MSG, - status_msg)) + params->status_msg)) goto nla_put_failure; - if (component && + if (params->component && nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_COMPONENT, - component)) + params->component)) goto nla_put_failure; if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_DONE, - done, DEVLINK_ATTR_PAD)) + params->done, DEVLINK_ATTR_PAD)) goto nla_put_failure; if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TOTAL, - total, DEVLINK_ATTR_PAD)) + params->total, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT, + params->timeout, DEVLINK_ATTR_PAD)) goto nla_put_failure; out: @@ -3059,10 +3345,7 @@ nla_put_failure: static void __devlink_flash_update_notify(struct devlink *devlink, enum devlink_command cmd, - const char *status_msg, - const char *component, - unsigned long done, - unsigned long total) + struct devlink_flash_notify *params) { struct sk_buff *msg; int err; @@ -3075,8 +3358,7 @@ static void __devlink_flash_update_notify(struct devlink *devlink, if (!msg) return; - err = devlink_nl_flash_update_fill(msg, devlink, cmd, status_msg, - component, done, total); + err = devlink_nl_flash_update_fill(msg, devlink, cmd, params); if (err) goto out_free_msg; @@ -3090,17 +3372,21 @@ out_free_msg: void devlink_flash_update_begin_notify(struct devlink *devlink) { + struct devlink_flash_notify params = { 0 }; + __devlink_flash_update_notify(devlink, DEVLINK_CMD_FLASH_UPDATE, - NULL, NULL, 0, 0); + ¶ms); } EXPORT_SYMBOL_GPL(devlink_flash_update_begin_notify); void devlink_flash_update_end_notify(struct devlink *devlink) { + struct devlink_flash_notify params = { 0 }; + __devlink_flash_update_notify(devlink, DEVLINK_CMD_FLASH_UPDATE_END, - NULL, NULL, 0, 0); + ¶ms); } EXPORT_SYMBOL_GPL(devlink_flash_update_end_notify); @@ -3110,31 +3396,78 @@ void devlink_flash_update_status_notify(struct devlink *devlink, unsigned long done, unsigned long total) { + struct devlink_flash_notify params = { + .status_msg = status_msg, + .component = component, + .done = done, + .total = total, + }; + __devlink_flash_update_notify(devlink, DEVLINK_CMD_FLASH_UPDATE_STATUS, - status_msg, component, done, total); + ¶ms); } EXPORT_SYMBOL_GPL(devlink_flash_update_status_notify); +void devlink_flash_update_timeout_notify(struct devlink *devlink, + const char *status_msg, + const char *component, + unsigned long timeout) +{ + struct devlink_flash_notify params = { + .status_msg = status_msg, + .component = component, + .timeout = timeout, + }; + + __devlink_flash_update_notify(devlink, + DEVLINK_CMD_FLASH_UPDATE_STATUS, + ¶ms); +} +EXPORT_SYMBOL_GPL(devlink_flash_update_timeout_notify); + static int devlink_nl_cmd_flash_update(struct sk_buff *skb, struct genl_info *info) { + struct nlattr *nla_component, *nla_overwrite_mask; + struct devlink_flash_update_params params = {}; struct devlink *devlink = info->user_ptr[0]; - const char *file_name, *component; - struct nlattr *nla_component; + u32 supported_params; if (!devlink->ops->flash_update) return -EOPNOTSUPP; if (!info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]) return -EINVAL; - file_name = nla_data(info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]); + + supported_params = devlink->ops->supported_flash_update_params; + + params.file_name = nla_data(info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]); nla_component = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT]; - component = nla_component ? nla_data(nla_component) : NULL; + if (nla_component) { + if (!(supported_params & DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT)) { + NL_SET_ERR_MSG_ATTR(info->extack, nla_component, + "component update is not supported by this device"); + return -EOPNOTSUPP; + } + params.component = nla_data(nla_component); + } + + nla_overwrite_mask = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK]; + if (nla_overwrite_mask) { + struct nla_bitfield32 sections; + + if (!(supported_params & DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK)) { + NL_SET_ERR_MSG_ATTR(info->extack, nla_overwrite_mask, + "overwrite settings are not supported by this device"); + return -EOPNOTSUPP; + } + sections = nla_get_bitfield32(nla_overwrite_mask); + params.overwrite_mask = sections.value & sections.selector; + } - return devlink->ops->flash_update(devlink, file_name, component, - info->extack); + return devlink->ops->flash_update(devlink, ¶ms, info->extack); } static const struct devlink_param devlink_param_generic[] = { @@ -3188,6 +3521,11 @@ static const struct devlink_param devlink_param_generic[] = { .name = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_NAME, .type = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_TYPE, }, + { + .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_REMOTE_DEV_RESET, + .name = DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_NAME, + .type = DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_TYPE, + }, }; static int devlink_param_generic_verify(const struct devlink_param *param) @@ -3875,6 +4213,13 @@ static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink, if (err) goto nla_put_failure; + if (region->port) { + err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, + region->port->index); + if (err) + goto nla_put_failure; + } + err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->ops->name); if (err) goto nla_put_failure; @@ -3922,6 +4267,13 @@ devlink_nl_region_notify_build(struct devlink_region *region, if (err) goto out_cancel_msg; + if (region->port) { + err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, + region->port->index); + if (err) + goto out_cancel_msg; + } + err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->ops->name); if (err) @@ -4168,16 +4520,30 @@ static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; + struct devlink_port *port = NULL; struct devlink_region *region; const char *region_name; struct sk_buff *msg; + unsigned int index; int err; if (!info->attrs[DEVLINK_ATTR_REGION_NAME]) return -EINVAL; + if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { + index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + + port = devlink_port_get_by_index(devlink, index); + if (!port) + return -ENODEV; + } + region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); - region = devlink_region_get_by_name(devlink, region_name); + if (port) + region = devlink_port_region_get_by_name(port, region_name); + else + region = devlink_region_get_by_name(devlink, region_name); + if (!region) return -EINVAL; @@ -4196,10 +4562,75 @@ static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb, return genlmsg_reply(msg, info); } +static int devlink_nl_cmd_region_get_port_dumpit(struct sk_buff *msg, + struct netlink_callback *cb, + struct devlink_port *port, + int *idx, + int start) +{ + struct devlink_region *region; + int err = 0; + + list_for_each_entry(region, &port->region_list, list) { + if (*idx < start) { + (*idx)++; + continue; + } + err = devlink_nl_region_fill(msg, port->devlink, + DEVLINK_CMD_REGION_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, region); + if (err) + goto out; + (*idx)++; + } + +out: + return err; +} + +static int devlink_nl_cmd_region_get_devlink_dumpit(struct sk_buff *msg, + struct netlink_callback *cb, + struct devlink *devlink, + int *idx, + int start) +{ + struct devlink_region *region; + struct devlink_port *port; + int err = 0; + + mutex_lock(&devlink->lock); + list_for_each_entry(region, &devlink->region_list, list) { + if (*idx < start) { + (*idx)++; + continue; + } + err = devlink_nl_region_fill(msg, devlink, + DEVLINK_CMD_REGION_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, region); + if (err) + goto out; + (*idx)++; + } + + list_for_each_entry(port, &devlink->port_list, list) { + err = devlink_nl_cmd_region_get_port_dumpit(msg, cb, port, idx, + start); + if (err) + goto out; + } + +out: + mutex_unlock(&devlink->lock); + return err; +} + static int devlink_nl_cmd_region_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) { - struct devlink_region *region; struct devlink *devlink; int start = cb->args[0]; int idx = 0; @@ -4209,25 +4640,10 @@ static int devlink_nl_cmd_region_get_dumpit(struct sk_buff *msg, list_for_each_entry(devlink, &devlink_list, list) { if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) continue; - - mutex_lock(&devlink->lock); - list_for_each_entry(region, &devlink->region_list, list) { - if (idx < start) { - idx++; - continue; - } - err = devlink_nl_region_fill(msg, devlink, - DEVLINK_CMD_REGION_GET, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI, region); - if (err) { - mutex_unlock(&devlink->lock); - goto out; - } - idx++; - } - mutex_unlock(&devlink->lock); + err = devlink_nl_cmd_region_get_devlink_dumpit(msg, cb, devlink, + &idx, start); + if (err) + goto out; } out: mutex_unlock(&devlink_mutex); @@ -4240,8 +4656,10 @@ static int devlink_nl_cmd_region_del(struct sk_buff *skb, { struct devlink *devlink = info->user_ptr[0]; struct devlink_snapshot *snapshot; + struct devlink_port *port = NULL; struct devlink_region *region; const char *region_name; + unsigned int index; u32 snapshot_id; if (!info->attrs[DEVLINK_ATTR_REGION_NAME] || @@ -4251,7 +4669,19 @@ static int devlink_nl_cmd_region_del(struct sk_buff *skb, region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); snapshot_id = nla_get_u32(info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]); - region = devlink_region_get_by_name(devlink, region_name); + if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { + index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + + port = devlink_port_get_by_index(devlink, index); + if (!port) + return -ENODEV; + } + + if (port) + region = devlink_port_region_get_by_name(port, region_name); + else + region = devlink_region_get_by_name(devlink, region_name); + if (!region) return -EINVAL; @@ -4268,9 +4698,11 @@ devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_snapshot *snapshot; + struct devlink_port *port = NULL; struct nlattr *snapshot_id_attr; struct devlink_region *region; const char *region_name; + unsigned int index; u32 snapshot_id; u8 *data; int err; @@ -4281,7 +4713,20 @@ devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info) } region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); - region = devlink_region_get_by_name(devlink, region_name); + + if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { + index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + + port = devlink_port_get_by_index(devlink, index); + if (!port) + return -ENODEV; + } + + if (port) + region = devlink_port_region_get_by_name(port, region_name); + else + region = devlink_region_get_by_name(devlink, region_name); + if (!region) { NL_SET_ERR_MSG_MOD(info->extack, "The requested region does not exist"); return -EINVAL; @@ -4317,7 +4762,12 @@ devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info) } } - err = region->ops->snapshot(devlink, info->extack, &data); + if (port) + err = region->port_ops->snapshot(port, region->port_ops, + info->extack, &data); + else + err = region->ops->snapshot(devlink, region->ops, + info->extack, &data); if (err) goto err_snapshot_capture; @@ -4439,10 +4889,12 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, const struct genl_dumpit_info *info = genl_dumpit_info(cb); u64 ret_offset, start_offset, end_offset = U64_MAX; struct nlattr **attrs = info->attrs; + struct devlink_port *port = NULL; struct devlink_region *region; struct nlattr *chunks_attr; const char *region_name; struct devlink *devlink; + unsigned int index; void *hdr; int err; @@ -4463,8 +4915,23 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, goto out_unlock; } + if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { + index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + + port = devlink_port_get_by_index(devlink, index); + if (!port) { + err = -ENODEV; + goto out_unlock; + } + } + region_name = nla_data(attrs[DEVLINK_ATTR_REGION_NAME]); - region = devlink_region_get_by_name(devlink, region_name); + + if (port) + region = devlink_port_region_get_by_name(port, region_name); + else + region = devlink_region_get_by_name(devlink, region_name); + if (!region) { err = -EINVAL; goto out_unlock; @@ -4501,6 +4968,13 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, if (err) goto nla_put_failure; + if (region->port) { + err = nla_put_u32(skb, DEVLINK_ATTR_PORT_INDEX, + region->port->index); + if (err) + goto nla_put_failure; + } + err = nla_put_string(skb, DEVLINK_ATTR_REGION_NAME, region_name); if (err) goto nla_put_failure; @@ -5895,6 +6369,7 @@ devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg, list_for_each_entry(devlink, &devlink_list, list) { if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) continue; + mutex_lock(&devlink->lock); list_for_each_entry(port, &devlink->port_list, list) { mutex_lock(&port->reporters_lock); list_for_each_entry(reporter, &port->reporter_list, list) { @@ -5909,12 +6384,14 @@ devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg, NLM_F_MULTI); if (err) { mutex_unlock(&port->reporters_lock); + mutex_unlock(&devlink->lock); goto out; } idx++; } mutex_unlock(&port->reporters_lock); } + mutex_unlock(&devlink->lock); } out: mutex_unlock(&devlink_mutex); @@ -6088,6 +6565,28 @@ devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb, return 0; } +static int devlink_nl_cmd_health_reporter_test_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + int err; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + if (!reporter->ops->test) { + devlink_health_reporter_put(reporter); + return -EOPNOTSUPP; + } + + err = reporter->ops->test(reporter, info->extack); + + devlink_health_reporter_put(reporter); + return err; +} + struct devlink_stats { u64 rx_bytes; u64 rx_packets; @@ -6644,6 +7143,24 @@ __devlink_trap_group_action_set(struct devlink *devlink, struct devlink_trap_item *trap_item; int err; + if (devlink->ops->trap_group_action_set) { + err = devlink->ops->trap_group_action_set(devlink, group_item->group, + trap_action, extack); + if (err) + return err; + + list_for_each_entry(trap_item, &devlink->trap_list, list) { + if (strcmp(trap_item->group_item->group->name, group_name)) + continue; + if (trap_item->action != trap_action && + trap_item->trap->type != DEVLINK_TRAP_TYPE_DROP) + continue; + trap_item->action = trap_action; + } + + return 0; + } + list_for_each_entry(trap_item, &devlink->trap_list, list) { if (strcmp(trap_item->group_item->group->name, group_name)) continue; @@ -7000,7 +7517,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32 }, - [DEVLINK_ATTR_PORT_TYPE] = { .type = NLA_U16 }, + [DEVLINK_ATTR_PORT_TYPE] = NLA_POLICY_RANGE(NLA_U16, DEVLINK_PORT_TYPE_AUTO, + DEVLINK_PORT_TYPE_IB), [DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .type = NLA_U32 }, [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32 }, [DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16 }, @@ -7009,7 +7527,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = { .type = NLA_U8 }, [DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32 }, [DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 }, - [DEVLINK_ATTR_ESWITCH_MODE] = { .type = NLA_U16 }, + [DEVLINK_ATTR_ESWITCH_MODE] = NLA_POLICY_RANGE(NLA_U16, DEVLINK_ESWITCH_MODE_LEGACY, + DEVLINK_ESWITCH_MODE_SWITCHDEV), [DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .type = NLA_U8 }, [DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = { .type = NLA_U8 }, [DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING }, @@ -7028,6 +7547,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 }, [DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_FLASH_UPDATE_COMPONENT] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK] = + NLA_POLICY_BITFIELD32(DEVLINK_SUPPORTED_FLASH_OVERWRITE_SECTIONS), [DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_TRAP_ACTION] = { .type = NLA_U8 }, [DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING }, @@ -7039,9 +7560,12 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_TRAP_POLICER_RATE] = { .type = NLA_U64 }, [DEVLINK_ATTR_TRAP_POLICER_BURST] = { .type = NLA_U64 }, [DEVLINK_ATTR_PORT_FUNCTION] = { .type = NLA_NESTED }, + [DEVLINK_ATTR_RELOAD_ACTION] = NLA_POLICY_RANGE(NLA_U8, DEVLINK_RELOAD_ACTION_DRIVER_REINIT, + DEVLINK_RELOAD_ACTION_MAX), + [DEVLINK_ATTR_RELOAD_LIMITS] = NLA_POLICY_BITFIELD32(DEVLINK_RELOAD_LIMITS_VALID_MASK), }; -static const struct genl_ops devlink_nl_ops[] = { +static const struct genl_small_ops devlink_nl_ops[] = { { .cmd = DEVLINK_CMD_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, @@ -7309,6 +7833,14 @@ static const struct genl_ops devlink_nl_ops[] = { DEVLINK_NL_FLAG_NO_LOCK, }, { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_TEST, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_health_reporter_test_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT | + DEVLINK_NL_FLAG_NO_LOCK, + }, + { .cmd = DEVLINK_CMD_FLASH_UPDATE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_flash_update, @@ -7358,12 +7890,41 @@ static struct genl_family devlink_nl_family __ro_after_init = { .pre_doit = devlink_nl_pre_doit, .post_doit = devlink_nl_post_doit, .module = THIS_MODULE, - .ops = devlink_nl_ops, - .n_ops = ARRAY_SIZE(devlink_nl_ops), + .small_ops = devlink_nl_ops, + .n_small_ops = ARRAY_SIZE(devlink_nl_ops), .mcgrps = devlink_nl_mcgrps, .n_mcgrps = ARRAY_SIZE(devlink_nl_mcgrps), }; +static bool devlink_reload_actions_valid(const struct devlink_ops *ops) +{ + const struct devlink_reload_combination *comb; + int i; + + if (!devlink_reload_supported(ops)) { + if (WARN_ON(ops->reload_actions)) + return false; + return true; + } + + if (WARN_ON(!ops->reload_actions || + ops->reload_actions & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) || + ops->reload_actions >= BIT(__DEVLINK_RELOAD_ACTION_MAX))) + return false; + + if (WARN_ON(ops->reload_limits & BIT(DEVLINK_RELOAD_LIMIT_UNSPEC) || + ops->reload_limits >= BIT(__DEVLINK_RELOAD_LIMIT_MAX))) + return false; + + for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++) { + comb = &devlink_reload_invalid_combinations[i]; + if (ops->reload_actions == BIT(comb->action) && + ops->reload_limits == BIT(comb->limit)) + return false; + } + return true; +} + /** * devlink_alloc - Allocate new devlink instance resources * @@ -7380,6 +7941,9 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) if (WARN_ON(!ops)) return NULL; + if (!devlink_reload_actions_valid(ops)) + return NULL; + devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL); if (!devlink) return NULL; @@ -7428,7 +7992,7 @@ EXPORT_SYMBOL_GPL(devlink_register); void devlink_unregister(struct devlink *devlink) { mutex_lock(&devlink_mutex); - WARN_ON(devlink_reload_supported(devlink) && + WARN_ON(devlink_reload_supported(devlink->ops) && devlink->reload_enabled); devlink_notify(devlink, DEVLINK_CMD_DEL); list_del(&devlink->list); @@ -7506,7 +8070,8 @@ static bool devlink_port_type_should_warn(struct devlink_port *devlink_port) { /* Ignore CPU and DSA flavours. */ return devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_CPU && - devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_DSA; + devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_DSA && + devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_UNUSED; } #define DEVLINK_PORT_TYPE_WARN_TIMEOUT (HZ * 3600) @@ -7555,11 +8120,12 @@ int devlink_port_register(struct 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); list_add_tail(&devlink_port->list, &devlink->port_list); INIT_LIST_HEAD(&devlink_port->param_list); + INIT_LIST_HEAD(&devlink_port->region_list); mutex_unlock(&devlink->lock); - INIT_LIST_HEAD(&devlink_port->reporter_list); - mutex_init(&devlink_port->reporters_lock); INIT_DELAYED_WORK(&devlink_port->type_warn_dw, &devlink_port_type_warn); devlink_port_type_warn_schedule(devlink_port); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); @@ -7576,13 +8142,14 @@ void devlink_port_unregister(struct devlink_port *devlink_port) { struct devlink *devlink = devlink_port->devlink; - WARN_ON(!list_empty(&devlink_port->reporter_list)); - mutex_destroy(&devlink_port->reporters_lock); devlink_port_type_warn_cancel(devlink_port); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); mutex_lock(&devlink->lock); list_del(&devlink_port->list); mutex_unlock(&devlink->lock); + WARN_ON(!list_empty(&devlink_port->reporter_list)); + WARN_ON(!list_empty(&devlink_port->region_list)); + mutex_destroy(&devlink_port->reporters_lock); } EXPORT_SYMBOL_GPL(devlink_port_unregister); @@ -7600,14 +8167,8 @@ static void __devlink_port_type_set(struct devlink_port *devlink_port, devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); } -/** - * devlink_port_type_eth_set - Set port type to Ethernet - * - * @devlink_port: devlink port - * @netdev: related netdevice - */ -void devlink_port_type_eth_set(struct devlink_port *devlink_port, - struct net_device *netdev) +static void devlink_port_type_netdev_checks(struct devlink_port *devlink_port, + struct net_device *netdev) { const struct net_device_ops *ops = netdev->netdev_ops; @@ -7641,6 +8202,24 @@ void devlink_port_type_eth_set(struct devlink_port *devlink_port, err = ops->ndo_get_port_parent_id(netdev, &ppid); WARN_ON(err != -EOPNOTSUPP); } +} + +/** + * devlink_port_type_eth_set - Set port type to Ethernet + * + * @devlink_port: devlink port + * @netdev: related netdevice + */ +void devlink_port_type_eth_set(struct devlink_port *devlink_port, + struct net_device *netdev) +{ + if (netdev) + devlink_port_type_netdev_checks(devlink_port, netdev); + else + dev_warn(devlink_port->devlink->dev, + "devlink port type for port %d set to Ethernet without a software interface reference, device type not supported by the kernel?\n", + devlink_port->index); + __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, netdev); } EXPORT_SYMBOL_GPL(devlink_port_type_eth_set); @@ -7712,9 +8291,12 @@ EXPORT_SYMBOL_GPL(devlink_port_attrs_set); * devlink_port_attrs_pci_pf_set - Set PCI PF port attributes * * @devlink_port: devlink port + * @controller: associated controller number for the devlink port instance * @pf: associated PF for the devlink port instance + * @external: indicates if the port is for an external controller */ -void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf) +void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 controller, + u16 pf, bool external) { struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; @@ -7723,8 +8305,9 @@ void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf) DEVLINK_PORT_FLAVOUR_PCI_PF); if (ret) return; - + attrs->pci_pf.controller = controller; attrs->pci_pf.pf = pf; + attrs->pci_pf.external = external; } EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_pf_set); @@ -7732,11 +8315,13 @@ EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_pf_set); * devlink_port_attrs_pci_vf_set - Set PCI VF port attributes * * @devlink_port: devlink port + * @controller: associated controller number for the devlink port instance * @pf: associated PF for the devlink port instance * @vf: associated VF of a PF for the devlink port instance + * @external: indicates if the port is for an external controller */ -void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, - u16 pf, u16 vf) +void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller, + u16 pf, u16 vf, bool external) { struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; @@ -7745,8 +8330,10 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, DEVLINK_PORT_FLAVOUR_PCI_VF); if (ret) return; + attrs->pci_vf.controller = controller; attrs->pci_vf.pf = pf; attrs->pci_vf.vf = vf; + attrs->pci_vf.external = external; } EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_vf_set); @@ -7771,15 +8358,30 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, break; case DEVLINK_PORT_FLAVOUR_CPU: case DEVLINK_PORT_FLAVOUR_DSA: + case DEVLINK_PORT_FLAVOUR_UNUSED: /* As CPU and DSA ports do not have a netdevice associated * case should not ever happen. */ WARN_ON(1); return -EINVAL; case DEVLINK_PORT_FLAVOUR_PCI_PF: + if (attrs->pci_pf.external) { + n = snprintf(name, len, "c%u", attrs->pci_pf.controller); + if (n >= len) + return -EINVAL; + len -= n; + name += n; + } n = snprintf(name, len, "pf%u", attrs->pci_pf.pf); break; case DEVLINK_PORT_FLAVOUR_PCI_VF: + if (attrs->pci_vf.external) { + n = snprintf(name, len, "c%u", attrs->pci_vf.controller); + if (n >= len) + return -EINVAL; + len -= n; + name += n; + } n = snprintf(name, len, "pf%uvf%u", attrs->pci_vf.pf, attrs->pci_vf.vf); break; @@ -8431,7 +9033,7 @@ __devlink_param_driverinit_value_set(struct devlink *devlink, int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, union devlink_param_value *init_val) { - if (!devlink_reload_supported(devlink)) + if (!devlink_reload_supported(devlink->ops)) return -EOPNOTSUPP; return __devlink_param_driverinit_value_get(&devlink->param_list, @@ -8478,7 +9080,7 @@ int devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, { struct devlink *devlink = devlink_port->devlink; - if (!devlink_reload_supported(devlink)) + if (!devlink_reload_supported(devlink->ops)) return -EOPNOTSUPP; return __devlink_param_driverinit_value_get(&devlink_port->param_list, @@ -8627,6 +9229,57 @@ unlock: EXPORT_SYMBOL_GPL(devlink_region_create); /** + * devlink_port_region_create - create a new address region for a port + * + * @port: devlink port + * @ops: region operations and name + * @region_max_snapshots: Maximum supported number of snapshots for region + * @region_size: size of region + */ +struct devlink_region * +devlink_port_region_create(struct devlink_port *port, + const struct devlink_port_region_ops *ops, + u32 region_max_snapshots, u64 region_size) +{ + struct devlink *devlink = port->devlink; + struct devlink_region *region; + int err = 0; + + if (WARN_ON(!ops) || WARN_ON(!ops->destructor)) + return ERR_PTR(-EINVAL); + + mutex_lock(&devlink->lock); + + if (devlink_port_region_get_by_name(port, ops->name)) { + err = -EEXIST; + goto unlock; + } + + region = kzalloc(sizeof(*region), GFP_KERNEL); + if (!region) { + err = -ENOMEM; + goto unlock; + } + + region->devlink = devlink; + region->port = port; + region->max_snapshots = region_max_snapshots; + region->port_ops = ops; + region->size = region_size; + INIT_LIST_HEAD(®ion->snapshot_list); + list_add_tail(®ion->list, &port->region_list); + devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); + + mutex_unlock(&devlink->lock); + return region; + +unlock: + mutex_unlock(&devlink->lock); + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(devlink_port_region_create); + +/** * devlink_region_destroy - destroy address region * * @region: devlink region to destroy @@ -8803,6 +9456,22 @@ static const struct devlink_trap devlink_trap_generic[] = { DEVLINK_TRAP(FLOW_ACTION_SAMPLE, CONTROL), DEVLINK_TRAP(FLOW_ACTION_TRAP, CONTROL), DEVLINK_TRAP(EARLY_DROP, DROP), + DEVLINK_TRAP(VXLAN_PARSING, DROP), + DEVLINK_TRAP(LLC_SNAP_PARSING, DROP), + DEVLINK_TRAP(VLAN_PARSING, DROP), + DEVLINK_TRAP(PPPOE_PPP_PARSING, DROP), + DEVLINK_TRAP(MPLS_PARSING, DROP), + DEVLINK_TRAP(ARP_PARSING, DROP), + DEVLINK_TRAP(IP_1_PARSING, DROP), + DEVLINK_TRAP(IP_N_PARSING, DROP), + DEVLINK_TRAP(GRE_PARSING, DROP), + DEVLINK_TRAP(UDP_PARSING, DROP), + DEVLINK_TRAP(TCP_PARSING, DROP), + DEVLINK_TRAP(IPSEC_PARSING, DROP), + DEVLINK_TRAP(SCTP_PARSING, DROP), + DEVLINK_TRAP(DCCP_PARSING, DROP), + DEVLINK_TRAP(GTP_PARSING, DROP), + DEVLINK_TRAP(ESP_PARSING, DROP), }; #define DEVLINK_TRAP_GROUP(_id) \ @@ -8837,6 +9506,7 @@ static const struct devlink_trap_group devlink_trap_group_generic[] = { DEVLINK_TRAP_GROUP(PTP_GENERAL), DEVLINK_TRAP_GROUP(ACL_SAMPLE), DEVLINK_TRAP_GROUP(ACL_TRAP), + DEVLINK_TRAP_GROUP(PARSER_ERROR_DROPS), }; static int devlink_trap_generic_verify(const struct devlink_trap *trap) @@ -9139,20 +9809,19 @@ devlink_trap_stats_update(struct devlink_stats __percpu *trap_stats, } static void -devlink_trap_report_metadata_fill(struct net_dm_hw_metadata *hw_metadata, - const struct devlink_trap_item *trap_item, - struct devlink_port *in_devlink_port, - const struct flow_action_cookie *fa_cookie) +devlink_trap_report_metadata_set(struct devlink_trap_metadata *metadata, + const struct devlink_trap_item *trap_item, + struct devlink_port *in_devlink_port, + const struct flow_action_cookie *fa_cookie) { - struct devlink_trap_group_item *group_item = trap_item->group_item; - - hw_metadata->trap_group_name = group_item->group->name; - hw_metadata->trap_name = trap_item->trap->name; - hw_metadata->fa_cookie = fa_cookie; + metadata->trap_name = trap_item->trap->name; + metadata->trap_group_name = trap_item->group_item->group->name; + metadata->fa_cookie = fa_cookie; + metadata->trap_type = trap_item->trap->type; spin_lock(&in_devlink_port->type_lock); if (in_devlink_port->type == DEVLINK_PORT_TYPE_ETH) - hw_metadata->input_dev = in_devlink_port->type_dev; + metadata->input_dev = in_devlink_port->type_dev; spin_unlock(&in_devlink_port->type_lock); } @@ -9170,21 +9839,17 @@ void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb, { struct devlink_trap_item *trap_item = trap_ctx; - struct net_dm_hw_metadata hw_metadata = {}; devlink_trap_stats_update(trap_item->stats, skb->len); devlink_trap_stats_update(trap_item->group_item->stats, skb->len); - /* Control packets were not dropped by the device or encountered an - * exception during forwarding and therefore should not be reported to - * the kernel's drop monitor. - */ - if (trap_item->trap->type == DEVLINK_TRAP_TYPE_CONTROL) - return; + if (trace_devlink_trap_report_enabled()) { + struct devlink_trap_metadata metadata = {}; - devlink_trap_report_metadata_fill(&hw_metadata, trap_item, - in_devlink_port, fa_cookie); - net_dm_hw_report(skb, &hw_metadata); + devlink_trap_report_metadata_set(&metadata, trap_item, + in_devlink_port, fa_cookie); + trace_devlink_trap_report(devlink, skb, &metadata); + } } EXPORT_SYMBOL_GPL(devlink_trap_report); @@ -9543,6 +10208,7 @@ out: int devlink_compat_flash_update(struct net_device *dev, const char *file_name) { + struct devlink_flash_update_params params = {}; struct devlink *devlink; int ret; @@ -9555,8 +10221,10 @@ int devlink_compat_flash_update(struct net_device *dev, const char *file_name) goto out; } + params.file_name = file_name; + mutex_lock(&devlink->lock); - ret = devlink->ops->flash_update(devlink, file_name, NULL, NULL); + ret = devlink->ops->flash_update(devlink, ¶ms, NULL); mutex_unlock(&devlink->lock); out: @@ -9605,6 +10273,7 @@ int devlink_compat_switch_id_get(struct net_device *dev, static void __net_exit devlink_pernet_pre_exit(struct net *net) { struct devlink *devlink; + u32 actions_performed; int err; /* In case network namespace is getting destroyed, reload @@ -9613,9 +10282,12 @@ static void __net_exit devlink_pernet_pre_exit(struct net *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))) + if (WARN_ON(!devlink_reload_supported(devlink->ops))) continue; - err = devlink_reload(devlink, &init_net, NULL); + 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"); } diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 9704522b0872..571f191c06d9 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -26,13 +26,14 @@ #include <linux/bitops.h> #include <linux/slab.h> #include <linux/module.h> -#include <net/drop_monitor.h> #include <net/genetlink.h> #include <net/netevent.h> #include <net/flow_offload.h> +#include <net/devlink.h> #include <trace/events/skb.h> #include <trace/events/napi.h> +#include <trace/events/devlink.h> #include <asm/unaligned.h> @@ -114,13 +115,14 @@ struct net_dm_alert_ops { int work, int budget); void (*work_item_func)(struct work_struct *work); void (*hw_work_item_func)(struct work_struct *work); - void (*hw_probe)(struct sk_buff *skb, - const struct net_dm_hw_metadata *hw_metadata); + void (*hw_trap_probe)(void *ignore, const struct devlink *devlink, + struct sk_buff *skb, + const struct devlink_trap_metadata *metadata); }; struct net_dm_skb_cb { union { - struct net_dm_hw_metadata *hw_metadata; + struct devlink_trap_metadata *hw_metadata; void *pc; }; }; @@ -432,8 +434,9 @@ out: } static void -net_dm_hw_summary_probe(struct sk_buff *skb, - const struct net_dm_hw_metadata *hw_metadata) +net_dm_hw_trap_summary_probe(void *ignore, const struct devlink *devlink, + struct sk_buff *skb, + const struct devlink_trap_metadata *metadata) { struct net_dm_hw_entries *hw_entries; struct net_dm_hw_entry *hw_entry; @@ -441,6 +444,9 @@ net_dm_hw_summary_probe(struct sk_buff *skb, unsigned long flags; int i; + if (metadata->trap_type == DEVLINK_TRAP_TYPE_CONTROL) + return; + hw_data = this_cpu_ptr(&dm_hw_cpu_data); spin_lock_irqsave(&hw_data->lock, flags); hw_entries = hw_data->hw_entries; @@ -450,7 +456,7 @@ net_dm_hw_summary_probe(struct sk_buff *skb, for (i = 0; i < hw_entries->num_entries; i++) { hw_entry = &hw_entries->entries[i]; - if (!strncmp(hw_entry->trap_name, hw_metadata->trap_name, + if (!strncmp(hw_entry->trap_name, metadata->trap_name, NET_DM_MAX_HW_TRAP_NAME_LEN - 1)) { hw_entry->count++; goto out; @@ -460,7 +466,7 @@ net_dm_hw_summary_probe(struct sk_buff *skb, goto out; hw_entry = &hw_entries->entries[hw_entries->num_entries]; - strlcpy(hw_entry->trap_name, hw_metadata->trap_name, + strlcpy(hw_entry->trap_name, metadata->trap_name, NET_DM_MAX_HW_TRAP_NAME_LEN - 1); hw_entry->count = 1; hw_entries->num_entries++; @@ -479,7 +485,7 @@ static const struct net_dm_alert_ops net_dm_alert_summary_ops = { .napi_poll_probe = trace_napi_poll_hit, .work_item_func = send_dm_alert, .hw_work_item_func = net_dm_hw_summary_work, - .hw_probe = net_dm_hw_summary_probe, + .hw_trap_probe = net_dm_hw_trap_summary_probe, }; static void net_dm_packet_trace_kfree_skb_hit(void *ignore, @@ -705,7 +711,7 @@ static void net_dm_packet_work(struct work_struct *work) } static size_t -net_dm_flow_action_cookie_size(const struct net_dm_hw_metadata *hw_metadata) +net_dm_flow_action_cookie_size(const struct devlink_trap_metadata *hw_metadata) { return hw_metadata->fa_cookie ? nla_total_size(hw_metadata->fa_cookie->cookie_len) : 0; @@ -713,7 +719,7 @@ net_dm_flow_action_cookie_size(const struct net_dm_hw_metadata *hw_metadata) static size_t net_dm_hw_packet_report_size(size_t payload_len, - const struct net_dm_hw_metadata *hw_metadata) + const struct devlink_trap_metadata *hw_metadata) { size_t size; @@ -743,7 +749,7 @@ net_dm_hw_packet_report_size(size_t payload_len, static int net_dm_hw_packet_report_fill(struct sk_buff *msg, struct sk_buff *skb, size_t payload_len) { - struct net_dm_hw_metadata *hw_metadata; + struct devlink_trap_metadata *hw_metadata; struct nlattr *attr; void *hdr; @@ -810,56 +816,56 @@ nla_put_failure: return -EMSGSIZE; } -static struct net_dm_hw_metadata * -net_dm_hw_metadata_clone(const struct net_dm_hw_metadata *hw_metadata) +static struct devlink_trap_metadata * +net_dm_hw_metadata_copy(const struct devlink_trap_metadata *metadata) { const struct flow_action_cookie *fa_cookie; - struct net_dm_hw_metadata *n_hw_metadata; + struct devlink_trap_metadata *hw_metadata; const char *trap_group_name; const char *trap_name; - n_hw_metadata = kzalloc(sizeof(*hw_metadata), GFP_ATOMIC); - if (!n_hw_metadata) + hw_metadata = kzalloc(sizeof(*hw_metadata), GFP_ATOMIC); + if (!hw_metadata) return NULL; - trap_group_name = kstrdup(hw_metadata->trap_group_name, GFP_ATOMIC); + trap_group_name = kstrdup(metadata->trap_group_name, GFP_ATOMIC); if (!trap_group_name) goto free_hw_metadata; - n_hw_metadata->trap_group_name = trap_group_name; + hw_metadata->trap_group_name = trap_group_name; - trap_name = kstrdup(hw_metadata->trap_name, GFP_ATOMIC); + trap_name = kstrdup(metadata->trap_name, GFP_ATOMIC); if (!trap_name) goto free_trap_group; - n_hw_metadata->trap_name = trap_name; + hw_metadata->trap_name = trap_name; - if (hw_metadata->fa_cookie) { + if (metadata->fa_cookie) { size_t cookie_size = sizeof(*fa_cookie) + - hw_metadata->fa_cookie->cookie_len; + metadata->fa_cookie->cookie_len; - fa_cookie = kmemdup(hw_metadata->fa_cookie, cookie_size, + fa_cookie = kmemdup(metadata->fa_cookie, cookie_size, GFP_ATOMIC); if (!fa_cookie) goto free_trap_name; - n_hw_metadata->fa_cookie = fa_cookie; + hw_metadata->fa_cookie = fa_cookie; } - n_hw_metadata->input_dev = hw_metadata->input_dev; - if (n_hw_metadata->input_dev) - dev_hold(n_hw_metadata->input_dev); + hw_metadata->input_dev = metadata->input_dev; + if (hw_metadata->input_dev) + dev_hold(hw_metadata->input_dev); - return n_hw_metadata; + return hw_metadata; free_trap_name: kfree(trap_name); free_trap_group: kfree(trap_group_name); free_hw_metadata: - kfree(n_hw_metadata); + kfree(hw_metadata); return NULL; } static void -net_dm_hw_metadata_free(const struct net_dm_hw_metadata *hw_metadata) +net_dm_hw_metadata_free(const struct devlink_trap_metadata *hw_metadata) { if (hw_metadata->input_dev) dev_put(hw_metadata->input_dev); @@ -871,7 +877,7 @@ net_dm_hw_metadata_free(const struct net_dm_hw_metadata *hw_metadata) static void net_dm_hw_packet_report(struct sk_buff *skb) { - struct net_dm_hw_metadata *hw_metadata; + struct devlink_trap_metadata *hw_metadata; struct sk_buff *msg; size_t payload_len; int rc; @@ -924,15 +930,19 @@ static void net_dm_hw_packet_work(struct work_struct *work) } static void -net_dm_hw_packet_probe(struct sk_buff *skb, - const struct net_dm_hw_metadata *hw_metadata) +net_dm_hw_trap_packet_probe(void *ignore, const struct devlink *devlink, + struct sk_buff *skb, + const struct devlink_trap_metadata *metadata) { - struct net_dm_hw_metadata *n_hw_metadata; + struct devlink_trap_metadata *n_hw_metadata; ktime_t tstamp = ktime_get_real(); struct per_cpu_dm_data *hw_data; struct sk_buff *nskb; unsigned long flags; + if (metadata->trap_type == DEVLINK_TRAP_TYPE_CONTROL) + return; + if (!skb_mac_header_was_set(skb)) return; @@ -940,7 +950,7 @@ net_dm_hw_packet_probe(struct sk_buff *skb, if (!nskb) return; - n_hw_metadata = net_dm_hw_metadata_clone(hw_metadata); + n_hw_metadata = net_dm_hw_metadata_copy(metadata); if (!n_hw_metadata) goto free; @@ -975,7 +985,7 @@ static const struct net_dm_alert_ops net_dm_alert_packet_ops = { .napi_poll_probe = net_dm_packet_trace_napi_poll_hit, .work_item_func = net_dm_packet_work, .hw_work_item_func = net_dm_hw_packet_work, - .hw_probe = net_dm_hw_packet_probe, + .hw_trap_probe = net_dm_hw_trap_packet_probe, }; static const struct net_dm_alert_ops *net_dm_alert_ops_arr[] = { @@ -983,25 +993,32 @@ static const struct net_dm_alert_ops *net_dm_alert_ops_arr[] = { [NET_DM_ALERT_MODE_PACKET] = &net_dm_alert_packet_ops, }; -void net_dm_hw_report(struct sk_buff *skb, - const struct net_dm_hw_metadata *hw_metadata) +#if IS_ENABLED(CONFIG_NET_DEVLINK) +static int net_dm_hw_probe_register(const struct net_dm_alert_ops *ops) { - rcu_read_lock(); - - if (!monitor_hw) - goto out; + return register_trace_devlink_trap_report(ops->hw_trap_probe, NULL); +} - net_dm_alert_ops_arr[net_dm_alert_mode]->hw_probe(skb, hw_metadata); +static void net_dm_hw_probe_unregister(const struct net_dm_alert_ops *ops) +{ + unregister_trace_devlink_trap_report(ops->hw_trap_probe, NULL); + tracepoint_synchronize_unregister(); +} +#else +static int net_dm_hw_probe_register(const struct net_dm_alert_ops *ops) +{ + return -EOPNOTSUPP; +} -out: - rcu_read_unlock(); +static void net_dm_hw_probe_unregister(const struct net_dm_alert_ops *ops) +{ } -EXPORT_SYMBOL_GPL(net_dm_hw_report); +#endif static int net_dm_hw_monitor_start(struct netlink_ext_ack *extack) { const struct net_dm_alert_ops *ops; - int cpu; + int cpu, rc; if (monitor_hw) { NL_SET_ERR_MSG_MOD(extack, "Hardware monitoring already enabled"); @@ -1025,13 +1042,24 @@ static int net_dm_hw_monitor_start(struct netlink_ext_ack *extack) kfree(hw_entries); } + rc = net_dm_hw_probe_register(ops); + if (rc) { + NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to devlink_trap_probe() tracepoint"); + goto err_module_put; + } + monitor_hw = true; return 0; + +err_module_put: + module_put(THIS_MODULE); + return rc; } static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack) { + const struct net_dm_alert_ops *ops; int cpu; if (!monitor_hw) { @@ -1039,12 +1067,11 @@ static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack) return; } + ops = net_dm_alert_ops_arr[net_dm_alert_mode]; + monitor_hw = false; - /* After this call returns we are guaranteed that no CPU is processing - * any hardware drops. - */ - synchronize_rcu(); + net_dm_hw_probe_unregister(ops); for_each_possible_cpu(cpu) { struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); @@ -1053,7 +1080,7 @@ static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack) del_timer_sync(&hw_data->send_timer); cancel_work_sync(&hw_data->dm_alert_work); while ((skb = __skb_dequeue(&hw_data->drop_queue))) { - struct net_dm_hw_metadata *hw_metadata; + struct devlink_trap_metadata *hw_metadata; hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; net_dm_hw_metadata_free(hw_metadata); @@ -1548,7 +1575,7 @@ static const struct nla_policy net_dm_nl_policy[NET_DM_ATTR_MAX + 1] = { [NET_DM_ATTR_HW_DROPS] = {. type = NLA_FLAG }, }; -static const struct genl_ops dropmon_ops[] = { +static const struct genl_small_ops dropmon_ops[] = { { .cmd = NET_DM_CMD_CONFIG, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, @@ -1598,8 +1625,8 @@ static struct genl_family net_drop_monitor_family __ro_after_init = { .pre_doit = net_dm_nl_pre_doit, .post_doit = net_dm_nl_post_doit, .module = THIS_MODULE, - .ops = dropmon_ops, - .n_ops = ARRAY_SIZE(dropmon_ops), + .small_ops = dropmon_ops, + .n_small_ops = ARRAY_SIZE(dropmon_ops), .mcgrps = dropmon_mcgrps, .n_mcgrps = ARRAY_SIZE(dropmon_mcgrps), }; diff --git a/net/core/filter.c b/net/core/filter.c index b5f3faac5e3b..2ca5eecebacf 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -76,6 +76,10 @@ #include <net/bpf_sk_storage.h> #include <net/transp_v6.h> #include <linux/btf_ids.h> +#include <net/tls.h> + +static const struct bpf_func_proto * +bpf_sk_base_func_proto(enum bpf_func_id func_id); int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len) { @@ -2160,13 +2164,266 @@ static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev, return __bpf_redirect_no_mac(skb, dev, flags); } +#if IS_ENABLED(CONFIG_IPV6) +static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb, + struct net_device *dev, struct bpf_nh_params *nh) +{ + u32 hh_len = LL_RESERVED_SPACE(dev); + const struct in6_addr *nexthop; + struct dst_entry *dst = NULL; + struct neighbour *neigh; + + if (dev_xmit_recursion()) { + net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); + goto out_drop; + } + + skb->dev = dev; + 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); + return -ENOMEM; + } + if (skb->sk) + skb_set_owner_w(skb2, skb->sk); + consume_skb(skb); + skb = skb2; + } + + rcu_read_lock_bh(); + if (!nh) { + dst = skb_dst(skb); + nexthop = rt6_nexthop(container_of(dst, struct rt6_info, dst), + &ipv6_hdr(skb)->daddr); + } else { + nexthop = &nh->ipv6_nh; + } + neigh = ip_neigh_gw6(dev, nexthop); + if (likely(!IS_ERR(neigh))) { + int ret; + + sock_confirm_neigh(skb, neigh); + dev_xmit_recursion_inc(); + ret = neigh_output(neigh, skb, false); + dev_xmit_recursion_dec(); + rcu_read_unlock_bh(); + return ret; + } + rcu_read_unlock_bh(); + if (dst) + IP6_INC_STATS(dev_net(dst->dev), + ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); +out_drop: + kfree_skb(skb); + return -ENETDOWN; +} + +static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev, + struct bpf_nh_params *nh) +{ + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + struct net *net = dev_net(dev); + int err, ret = NET_XMIT_DROP; + + if (!nh) { + struct dst_entry *dst; + struct flowi6 fl6 = { + .flowi6_flags = FLOWI_FLAG_ANYSRC, + .flowi6_mark = skb->mark, + .flowlabel = ip6_flowinfo(ip6h), + .flowi6_oif = dev->ifindex, + .flowi6_proto = ip6h->nexthdr, + .daddr = ip6h->daddr, + .saddr = ip6h->saddr, + }; + + dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL); + if (IS_ERR(dst)) + goto out_drop; + + skb_dst_set(skb, dst); + } else if (nh->nh_family != AF_INET6) { + goto out_drop; + } + + err = bpf_out_neigh_v6(net, skb, dev, nh); + if (unlikely(net_xmit_eval(err))) + dev->stats.tx_errors++; + else + ret = NET_XMIT_SUCCESS; + goto out_xmit; +out_drop: + dev->stats.tx_errors++; + kfree_skb(skb); +out_xmit: + return ret; +} +#else +static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev, + struct bpf_nh_params *nh) +{ + kfree_skb(skb); + return NET_XMIT_DROP; +} +#endif /* CONFIG_IPV6 */ + +#if IS_ENABLED(CONFIG_INET) +static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb, + struct net_device *dev, struct bpf_nh_params *nh) +{ + u32 hh_len = LL_RESERVED_SPACE(dev); + struct neighbour *neigh; + bool is_v6gw = false; + + if (dev_xmit_recursion()) { + net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); + goto out_drop; + } + + skb->dev = dev; + 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); + return -ENOMEM; + } + if (skb->sk) + skb_set_owner_w(skb2, skb->sk); + consume_skb(skb); + skb = skb2; + } + + rcu_read_lock_bh(); + if (!nh) { + struct dst_entry *dst = skb_dst(skb); + struct rtable *rt = container_of(dst, struct rtable, dst); + + neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); + } else if (nh->nh_family == AF_INET6) { + neigh = ip_neigh_gw6(dev, &nh->ipv6_nh); + is_v6gw = true; + } else if (nh->nh_family == AF_INET) { + neigh = ip_neigh_gw4(dev, nh->ipv4_nh); + } else { + rcu_read_unlock_bh(); + goto out_drop; + } + + if (likely(!IS_ERR(neigh))) { + int ret; + + sock_confirm_neigh(skb, neigh); + dev_xmit_recursion_inc(); + ret = neigh_output(neigh, skb, is_v6gw); + dev_xmit_recursion_dec(); + rcu_read_unlock_bh(); + return ret; + } + rcu_read_unlock_bh(); +out_drop: + kfree_skb(skb); + return -ENETDOWN; +} + +static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev, + struct bpf_nh_params *nh) +{ + const struct iphdr *ip4h = ip_hdr(skb); + struct net *net = dev_net(dev); + int err, ret = NET_XMIT_DROP; + + if (!nh) { + struct flowi4 fl4 = { + .flowi4_flags = FLOWI_FLAG_ANYSRC, + .flowi4_mark = skb->mark, + .flowi4_tos = RT_TOS(ip4h->tos), + .flowi4_oif = dev->ifindex, + .flowi4_proto = ip4h->protocol, + .daddr = ip4h->daddr, + .saddr = ip4h->saddr, + }; + struct rtable *rt; + + rt = ip_route_output_flow(net, &fl4, NULL); + if (IS_ERR(rt)) + goto out_drop; + if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) { + ip_rt_put(rt); + goto out_drop; + } + + skb_dst_set(skb, &rt->dst); + } + + err = bpf_out_neigh_v4(net, skb, dev, nh); + if (unlikely(net_xmit_eval(err))) + dev->stats.tx_errors++; + else + ret = NET_XMIT_SUCCESS; + goto out_xmit; +out_drop: + dev->stats.tx_errors++; + kfree_skb(skb); +out_xmit: + return ret; +} +#else +static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev, + struct bpf_nh_params *nh) +{ + kfree_skb(skb); + return NET_XMIT_DROP; +} +#endif /* CONFIG_INET */ + +static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev, + struct bpf_nh_params *nh) +{ + struct ethhdr *ethh = eth_hdr(skb); + + if (unlikely(skb->mac_header >= skb->network_header)) + goto out; + bpf_push_mac_rcsum(skb); + if (is_multicast_ether_addr(ethh->h_dest)) + goto out; + + skb_pull(skb, sizeof(*ethh)); + skb_unset_mac_header(skb); + skb_reset_network_header(skb); + + if (skb->protocol == htons(ETH_P_IP)) + return __bpf_redirect_neigh_v4(skb, dev, nh); + else if (skb->protocol == htons(ETH_P_IPV6)) + return __bpf_redirect_neigh_v6(skb, dev, nh); +out: + kfree_skb(skb); + return -ENOTSUPP; +} + +/* Internal, non-exposed redirect flags. */ +enum { + BPF_F_NEIGH = (1ULL << 1), + BPF_F_PEER = (1ULL << 2), + BPF_F_NEXTHOP = (1ULL << 3), +#define BPF_F_REDIRECT_INTERNAL (BPF_F_NEIGH | BPF_F_PEER | BPF_F_NEXTHOP) +}; + BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) { struct net_device *dev; struct sk_buff *clone; int ret; - if (unlikely(flags & ~(BPF_F_INGRESS))) + if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) return -EINVAL; dev = dev_get_by_index_rcu(dev_net(skb->dev), ifindex); @@ -2203,11 +2460,46 @@ static const struct bpf_func_proto bpf_clone_redirect_proto = { DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info); +int skb_do_redirect(struct sk_buff *skb) +{ + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct net *net = dev_net(skb->dev); + struct net_device *dev; + u32 flags = ri->flags; + + dev = dev_get_by_index_rcu(net, ri->tgt_index); + ri->tgt_index = 0; + ri->flags = 0; + if (unlikely(!dev)) + goto out_drop; + if (flags & BPF_F_PEER) { + const struct net_device_ops *ops = dev->netdev_ops; + + if (unlikely(!ops->ndo_get_peer_dev || + !skb_at_tc_ingress(skb))) + goto out_drop; + dev = ops->ndo_get_peer_dev(dev); + if (unlikely(!dev || + !is_skb_forwardable(dev, skb) || + net_eq(net, dev_net(dev)))) + goto out_drop; + skb->dev = dev; + return -EAGAIN; + } + return flags & BPF_F_NEIGH ? + __bpf_redirect_neigh(skb, dev, flags & BPF_F_NEXTHOP ? + &ri->nh : NULL) : + __bpf_redirect(skb, dev, flags); +out_drop: + kfree_skb(skb); + return -EINVAL; +} + BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); - if (unlikely(flags & ~(BPF_F_INGRESS))) + if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) return TC_ACT_SHOT; ri->flags = flags; @@ -2216,29 +2508,63 @@ BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) return TC_ACT_REDIRECT; } -int skb_do_redirect(struct sk_buff *skb) +static const struct bpf_func_proto bpf_redirect_proto = { + .func = bpf_redirect, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_ANYTHING, +}; + +BPF_CALL_2(bpf_redirect_peer, u32, ifindex, u64, flags) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); - struct net_device *dev; - dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->tgt_index); - ri->tgt_index = 0; - if (unlikely(!dev)) { - kfree_skb(skb); - return -EINVAL; - } + if (unlikely(flags)) + return TC_ACT_SHOT; + + ri->flags = BPF_F_PEER; + ri->tgt_index = ifindex; - return __bpf_redirect(skb, dev, ri->flags); + return TC_ACT_REDIRECT; } -static const struct bpf_func_proto bpf_redirect_proto = { - .func = bpf_redirect, +static const struct bpf_func_proto bpf_redirect_peer_proto = { + .func = bpf_redirect_peer, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_redirect_neigh, u32, ifindex, struct bpf_redir_neigh *, params, + int, plen, u64, flags) +{ + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + + if (unlikely((plen && plen < sizeof(*params)) || flags)) + return TC_ACT_SHOT; + + ri->flags = BPF_F_NEIGH | (plen ? BPF_F_NEXTHOP : 0); + ri->tgt_index = ifindex; + + BUILD_BUG_ON(sizeof(struct bpf_redir_neigh) != sizeof(struct bpf_nh_params)); + if (plen) + memcpy(&ri->nh, params, sizeof(ri->nh)); + + return TC_ACT_REDIRECT; +} + +static const struct bpf_func_proto bpf_redirect_neigh_proto = { + .func = bpf_redirect_neigh, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_PTR_TO_MEM_OR_NULL, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .arg4_type = ARG_ANYTHING, +}; + BPF_CALL_2(bpf_msg_apply_bytes, struct sk_msg *, msg, u32, bytes) { msg->apply_bytes = bytes; @@ -2704,6 +3030,23 @@ static const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto = { .gpl_only = false, .ret_type = RET_INTEGER, }; + +BPF_CALL_1(bpf_skb_cgroup_classid, const struct sk_buff *, skb) +{ + struct sock *sk = skb_to_full_sk(skb); + + if (!sk || !sk_fullsock(sk)) + return 0; + + return sock_cgroup_classid(&sk->sk_cgrp_data); +} + +static const struct bpf_func_proto bpf_skb_cgroup_classid_proto = { + .func = bpf_skb_cgroup_classid, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; #endif BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb) @@ -3215,6 +3558,48 @@ static u32 __bpf_skb_max_len(const struct sk_buff *skb) SKB_MAX_ALLOC; } +BPF_CALL_4(sk_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, + u32, mode, u64, flags) +{ + u32 len_diff_abs = abs(len_diff); + bool shrink = len_diff < 0; + int ret = 0; + + if (unlikely(flags || mode)) + return -EINVAL; + if (unlikely(len_diff_abs > 0xfffU)) + return -EFAULT; + + if (!shrink) { + ret = skb_cow(skb, len_diff); + if (unlikely(ret < 0)) + return ret; + __skb_push(skb, len_diff_abs); + memset(skb->data, 0, len_diff_abs); + } else { + if (unlikely(!pskb_may_pull(skb, len_diff_abs))) + return -ENOMEM; + __skb_pull(skb, len_diff_abs); + } + bpf_compute_data_end_sk_skb(skb); + if (tls_sw_has_ctx_rx(skb->sk)) { + struct strp_msg *rxm = strp_msg(skb); + + rxm->full_len += len_diff; + } + return ret; +} + +static const struct bpf_func_proto sk_skb_adjust_room_proto = { + .func = sk_skb_adjust_room, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_ANYTHING, +}; + BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, u32, mode, u64, flags) { @@ -3803,19 +4188,18 @@ static const struct bpf_func_proto bpf_skb_event_output_proto = { .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; -BTF_ID_LIST(bpf_skb_output_btf_ids) -BTF_ID(struct, sk_buff) +BTF_ID_LIST_SINGLE(bpf_skb_output_btf_ids, struct, sk_buff) const struct bpf_func_proto bpf_skb_output_proto = { .func = bpf_skb_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_skb_output_btf_ids[0], .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM, .arg5_type = ARG_CONST_SIZE_OR_ZERO, - .btf_id = bpf_skb_output_btf_ids, }; static unsigned short bpf_tunnel_key_af(u64 flags) @@ -4086,18 +4470,17 @@ static inline u64 __bpf_sk_cgroup_id(struct sock *sk) { struct cgroup *cgrp; + sk = sk_to_full_sk(sk); + if (!sk || !sk_fullsock(sk)) + return 0; + cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); return cgroup_id(cgrp); } BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb) { - struct sock *sk = skb_to_full_sk(skb); - - if (!sk || !sk_fullsock(sk)) - return 0; - - return __bpf_sk_cgroup_id(sk); + return __bpf_sk_cgroup_id(skb->sk); } static const struct bpf_func_proto bpf_skb_cgroup_id_proto = { @@ -4113,6 +4496,10 @@ static inline u64 __bpf_sk_ancestor_cgroup_id(struct sock *sk, struct cgroup *ancestor; struct cgroup *cgrp; + sk = sk_to_full_sk(sk); + if (!sk || !sk_fullsock(sk)) + return 0; + cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); ancestor = cgroup_ancestor(cgrp, ancestor_level); if (!ancestor) @@ -4124,12 +4511,7 @@ static inline u64 __bpf_sk_ancestor_cgroup_id(struct sock *sk, BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int, ancestor_level) { - struct sock *sk = skb_to_full_sk(skb); - - if (!sk || !sk_fullsock(sk)) - return 0; - - return __bpf_sk_ancestor_cgroup_id(sk, ancestor_level); + return __bpf_sk_ancestor_cgroup_id(skb->sk, ancestor_level); } static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = { @@ -4149,7 +4531,7 @@ static const struct bpf_func_proto bpf_sk_cgroup_id_proto = { .func = bpf_sk_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_SOCKET, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, }; BPF_CALL_2(bpf_sk_ancestor_cgroup_id, struct sock *, sk, int, ancestor_level) @@ -4161,7 +4543,7 @@ static const struct bpf_func_proto bpf_sk_ancestor_cgroup_id_proto = { .func = bpf_sk_ancestor_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_SOCKET, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, }; #endif @@ -4199,24 +4581,23 @@ static const struct bpf_func_proto bpf_xdp_event_output_proto = { .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; -BTF_ID_LIST(bpf_xdp_output_btf_ids) -BTF_ID(struct, xdp_buff) +BTF_ID_LIST_SINGLE(bpf_xdp_output_btf_ids, struct, xdp_buff) const struct bpf_func_proto bpf_xdp_output_proto = { .func = bpf_xdp_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_xdp_output_btf_ids[0], .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM, .arg5_type = ARG_CONST_SIZE_OR_ZERO, - .btf_id = bpf_xdp_output_btf_ids, }; BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb) { - return skb->sk ? sock_gen_cookie(skb->sk) : 0; + return skb->sk ? __sock_gen_cookie(skb->sk) : 0; } static const struct bpf_func_proto bpf_get_socket_cookie_proto = { @@ -4228,7 +4609,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_proto = { BPF_CALL_1(bpf_get_socket_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx) { - return sock_gen_cookie(ctx->sk); + return __sock_gen_cookie(ctx->sk); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = { @@ -4240,7 +4621,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = { BPF_CALL_1(bpf_get_socket_cookie_sock, struct sock *, ctx) { - return sock_gen_cookie(ctx); + return __sock_gen_cookie(ctx); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = { @@ -4252,7 +4633,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = { BPF_CALL_1(bpf_get_socket_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx) { - return sock_gen_cookie(ctx->sk); + return __sock_gen_cookie(ctx->sk); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = { @@ -4265,7 +4646,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = { static u64 __bpf_get_netns_cookie(struct sock *sk) { #ifdef CONFIG_NET_NS - return net_gen_cookie(sk ? sk->sk_net.net : &init_net); + return __net_gen_cookie(sk ? sk->sk_net.net : &init_net); #else return 0; #endif @@ -4313,10 +4694,8 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = { .arg1_type = ARG_PTR_TO_CTX, }; -#define SOCKOPT_CC_REINIT (1 << 0) - static int _bpf_setsockopt(struct sock *sk, int level, int optname, - char *optval, int optlen, u32 flags) + char *optval, int optlen) { char devname[IFNAMSIZ]; int val, valbool; @@ -4354,7 +4733,8 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); - sk->sk_max_pacing_rate = (val == ~0U) ? ~0UL : val; + sk->sk_max_pacing_rate = (val == ~0U) ? + ~0UL : (unsigned int)val; sk->sk_pacing_rate = min(sk->sk_pacing_rate, sk->sk_max_pacing_rate); break; @@ -4449,16 +4829,15 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, sk->sk_prot->setsockopt == tcp_setsockopt) { if (optname == TCP_CONGESTION) { char name[TCP_CA_NAME_MAX]; - bool reinit = flags & SOCKOPT_CC_REINIT; strncpy(name, optval, min_t(long, optlen, TCP_CA_NAME_MAX-1)); name[TCP_CA_NAME_MAX-1] = 0; - ret = tcp_set_congestion_control(sk, name, false, - reinit, true); + ret = tcp_set_congestion_control(sk, name, false, true); } else { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); + unsigned long timeout; if (optlen != sizeof(int)) return -EINVAL; @@ -4480,6 +4859,20 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, tp->snd_ssthresh = val; } break; + case TCP_BPF_DELACK_MAX: + timeout = usecs_to_jiffies(val); + if (timeout > TCP_DELACK_MAX || + timeout < TCP_TIMEOUT_MIN) + return -EINVAL; + inet_csk(sk)->icsk_delack_max = timeout; + break; + case TCP_BPF_RTO_MIN: + timeout = usecs_to_jiffies(val); + if (timeout > TCP_RTO_MIN || + timeout < TCP_TIMEOUT_MIN) + return -EINVAL; + inet_csk(sk)->icsk_rto_min = timeout; + break; case TCP_SAVE_SYN: if (val < 0 || val > 1) ret = -EINVAL; @@ -4513,6 +4906,10 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, else icsk->icsk_user_timeout = val; break; + case TCP_NOTSENT_LOWAT: + tp->notsent_lowat = val; + sk->sk_write_space(sk); + break; default: ret = -EINVAL; } @@ -4550,9 +4947,9 @@ static int _bpf_getsockopt(struct sock *sk, int level, int optname, tp = tcp_sk(sk); if (optlen <= 0 || !tp->saved_syn || - optlen > tp->saved_syn[0]) + optlen > tcp_saved_syn_len(tp->saved_syn)) goto err_clear; - memcpy(optval, tp->saved_syn + 1, optlen); + memcpy(optval, tp->saved_syn->data, optlen); break; default: goto err_clear; @@ -4600,9 +4997,7 @@ err_clear: BPF_CALL_5(bpf_sock_addr_setsockopt, struct bpf_sock_addr_kern *, ctx, int, level, int, optname, char *, optval, int, optlen) { - u32 flags = 0; - return _bpf_setsockopt(ctx->sk, level, optname, optval, optlen, - flags); + return _bpf_setsockopt(ctx->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_addr_setsockopt_proto = { @@ -4636,11 +5031,7 @@ static const struct bpf_func_proto bpf_sock_addr_getsockopt_proto = { BPF_CALL_5(bpf_sock_ops_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { - u32 flags = 0; - if (bpf_sock->op > BPF_SOCK_OPS_NEEDS_ECN) - flags |= SOCKOPT_CC_REINIT; - return _bpf_setsockopt(bpf_sock->sk, level, optname, optval, optlen, - flags); + return _bpf_setsockopt(bpf_sock->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_ops_setsockopt_proto = { @@ -4654,9 +5045,99 @@ static const struct bpf_func_proto bpf_sock_ops_setsockopt_proto = { .arg5_type = ARG_CONST_SIZE, }; +static int bpf_sock_ops_get_syn(struct bpf_sock_ops_kern *bpf_sock, + int optname, const u8 **start) +{ + struct sk_buff *syn_skb = bpf_sock->syn_skb; + const u8 *hdr_start; + int ret; + + if (syn_skb) { + /* sk is a request_sock here */ + + if (optname == TCP_BPF_SYN) { + hdr_start = syn_skb->data; + ret = tcp_hdrlen(syn_skb); + } else if (optname == TCP_BPF_SYN_IP) { + hdr_start = skb_network_header(syn_skb); + ret = skb_network_header_len(syn_skb) + + tcp_hdrlen(syn_skb); + } else { + /* optname == TCP_BPF_SYN_MAC */ + hdr_start = skb_mac_header(syn_skb); + ret = skb_mac_header_len(syn_skb) + + skb_network_header_len(syn_skb) + + tcp_hdrlen(syn_skb); + } + } else { + struct sock *sk = bpf_sock->sk; + struct saved_syn *saved_syn; + + if (sk->sk_state == TCP_NEW_SYN_RECV) + /* synack retransmit. bpf_sock->syn_skb will + * not be available. It has to resort to + * saved_syn (if it is saved). + */ + saved_syn = inet_reqsk(sk)->saved_syn; + else + saved_syn = tcp_sk(sk)->saved_syn; + + if (!saved_syn) + return -ENOENT; + + if (optname == TCP_BPF_SYN) { + hdr_start = saved_syn->data + + saved_syn->mac_hdrlen + + saved_syn->network_hdrlen; + ret = saved_syn->tcp_hdrlen; + } else if (optname == TCP_BPF_SYN_IP) { + hdr_start = saved_syn->data + + saved_syn->mac_hdrlen; + ret = saved_syn->network_hdrlen + + saved_syn->tcp_hdrlen; + } else { + /* optname == TCP_BPF_SYN_MAC */ + + /* TCP_SAVE_SYN may not have saved the mac hdr */ + if (!saved_syn->mac_hdrlen) + return -ENOENT; + + hdr_start = saved_syn->data; + ret = saved_syn->mac_hdrlen + + saved_syn->network_hdrlen + + saved_syn->tcp_hdrlen; + } + } + + *start = hdr_start; + return ret; +} + BPF_CALL_5(bpf_sock_ops_getsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { + if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP && + optname >= TCP_BPF_SYN && optname <= TCP_BPF_SYN_MAC) { + int ret, copy_len = 0; + const u8 *start; + + ret = bpf_sock_ops_get_syn(bpf_sock, optname, &start); + if (ret > 0) { + copy_len = ret; + if (optlen < copy_len) { + copy_len = optlen; + ret = -ENOSPC; + } + + memcpy(optval, start, copy_len); + } + + /* Zero out unused buffer at the end */ + memset(optval + copy_len, 0, optlen - copy_len); + + return ret; + } + return _bpf_getsockopt(bpf_sock->sk, level, optname, optval, optlen); } @@ -4794,7 +5275,6 @@ static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, memcpy(params->smac, dev->dev_addr, ETH_ALEN); params->h_vlan_TCI = 0; params->h_vlan_proto = 0; - params->ifindex = dev->ifindex; return 0; } @@ -4891,6 +5371,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, dev = nhc->nhc_dev; params->rt_metric = res.fi->fib_priority; + params->ifindex = dev->ifindex; /* xdp and cls_bpf programs are run in RCU-bh so * rcu_read_lock_bh is not needed here @@ -5016,6 +5497,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, dev = res.nh->fib_nh_dev; params->rt_metric = res.f6i->fib6_metric; + params->ifindex = dev->ifindex; /* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is * not needed here. @@ -5601,7 +6083,7 @@ static const struct bpf_func_proto bpf_sk_lookup_udp_proto = { BPF_CALL_1(bpf_sk_release, struct sock *, sk) { - if (sk_is_refcounted(sk)) + if (sk && sk_is_refcounted(sk)) sock_gen_put(sk); return 0; } @@ -5610,7 +6092,7 @@ static const struct bpf_func_proto bpf_sk_release_proto = { .func = bpf_sk_release, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_SOCK_COMMON, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, }; BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx, @@ -5992,7 +6474,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len u32 cookie; int ret; - if (unlikely(th_len < sizeof(*th))) + if (unlikely(!sk || th_len < sizeof(*th))) return -EINVAL; /* sk_listener() allows TCP_NEW_SYN_RECV, which makes no sense here. */ @@ -6045,7 +6527,7 @@ static const struct bpf_func_proto bpf_tcp_check_syncookie_proto = { .gpl_only = true, .pkt_access = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_SOCK_COMMON, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_PTR_TO_MEM, @@ -6059,7 +6541,7 @@ BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len, u32 cookie; u16 mss; - if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4)) + if (unlikely(!sk || th_len < sizeof(*th) || th_len != th->doff * 4)) return -EINVAL; if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) @@ -6114,7 +6596,7 @@ static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = { .gpl_only = true, /* __cookie_v*_init_sequence() is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_SOCK_COMMON, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_PTR_TO_MEM, @@ -6123,7 +6605,7 @@ static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = { BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags) { - if (flags != 0) + if (!sk || flags != 0) return -EINVAL; if (!skb_at_tc_ingress(skb)) return -EOPNOTSUPP; @@ -6147,7 +6629,233 @@ static const struct bpf_func_proto bpf_sk_assign_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_SOCK_COMMON, + .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, + .arg3_type = ARG_ANYTHING, +}; + +static const u8 *bpf_search_tcp_opt(const u8 *op, const u8 *opend, + u8 search_kind, const u8 *magic, + u8 magic_len, bool *eol) +{ + u8 kind, kind_len; + + *eol = false; + + while (op < opend) { + kind = op[0]; + + if (kind == TCPOPT_EOL) { + *eol = true; + return ERR_PTR(-ENOMSG); + } else if (kind == TCPOPT_NOP) { + op++; + continue; + } + + if (opend - op < 2 || opend - op < op[1] || op[1] < 2) + /* Something is wrong in the received header. + * Follow the TCP stack's tcp_parse_options() + * and just bail here. + */ + return ERR_PTR(-EFAULT); + + kind_len = op[1]; + if (search_kind == kind) { + if (!magic_len) + return op; + + if (magic_len > kind_len - 2) + return ERR_PTR(-ENOMSG); + + if (!memcmp(&op[2], magic, magic_len)) + return op; + } + + op += kind_len; + } + + return ERR_PTR(-ENOMSG); +} + +BPF_CALL_4(bpf_sock_ops_load_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, + void *, search_res, u32, len, u64, flags) +{ + bool eol, load_syn = flags & BPF_LOAD_HDR_OPT_TCP_SYN; + const u8 *op, *opend, *magic, *search = search_res; + u8 search_kind, search_len, copy_len, magic_len; + int ret; + + /* 2 byte is the minimal option len except TCPOPT_NOP and + * TCPOPT_EOL which are useless for the bpf prog to learn + * and this helper disallow loading them also. + */ + if (len < 2 || flags & ~BPF_LOAD_HDR_OPT_TCP_SYN) + return -EINVAL; + + search_kind = search[0]; + search_len = search[1]; + + if (search_len > len || search_kind == TCPOPT_NOP || + search_kind == TCPOPT_EOL) + return -EINVAL; + + if (search_kind == TCPOPT_EXP || search_kind == 253) { + /* 16 or 32 bit magic. +2 for kind and kind length */ + if (search_len != 4 && search_len != 6) + return -EINVAL; + magic = &search[2]; + magic_len = search_len - 2; + } else { + if (search_len) + return -EINVAL; + magic = NULL; + magic_len = 0; + } + + if (load_syn) { + ret = bpf_sock_ops_get_syn(bpf_sock, TCP_BPF_SYN, &op); + if (ret < 0) + return ret; + + opend = op + ret; + op += sizeof(struct tcphdr); + } else { + if (!bpf_sock->skb || + bpf_sock->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB) + /* This bpf_sock->op cannot call this helper */ + return -EPERM; + + opend = bpf_sock->skb_data_end; + op = bpf_sock->skb->data + sizeof(struct tcphdr); + } + + op = bpf_search_tcp_opt(op, opend, search_kind, magic, magic_len, + &eol); + if (IS_ERR(op)) + return PTR_ERR(op); + + copy_len = op[1]; + ret = copy_len; + if (copy_len > len) { + ret = -ENOSPC; + copy_len = len; + } + + memcpy(search_res, op, copy_len); + return ret; +} + +static const struct bpf_func_proto bpf_sock_ops_load_hdr_opt_proto = { + .func = bpf_sock_ops_load_hdr_opt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, +}; + +BPF_CALL_4(bpf_sock_ops_store_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, + const void *, from, u32, len, u64, flags) +{ + u8 new_kind, new_kind_len, magic_len = 0, *opend; + const u8 *op, *new_op, *magic = NULL; + struct sk_buff *skb; + bool eol; + + if (bpf_sock->op != BPF_SOCK_OPS_WRITE_HDR_OPT_CB) + return -EPERM; + + if (len < 2 || flags) + return -EINVAL; + + new_op = from; + new_kind = new_op[0]; + new_kind_len = new_op[1]; + + if (new_kind_len > len || new_kind == TCPOPT_NOP || + new_kind == TCPOPT_EOL) + return -EINVAL; + + if (new_kind_len > bpf_sock->remaining_opt_len) + return -ENOSPC; + + /* 253 is another experimental kind */ + if (new_kind == TCPOPT_EXP || new_kind == 253) { + if (new_kind_len < 4) + return -EINVAL; + /* Match for the 2 byte magic also. + * RFC 6994: the magic could be 2 or 4 bytes. + * Hence, matching by 2 byte only is on the + * conservative side but it is the right + * thing to do for the 'search-for-duplication' + * purpose. + */ + magic = &new_op[2]; + magic_len = 2; + } + + /* Check for duplication */ + skb = bpf_sock->skb; + op = skb->data + sizeof(struct tcphdr); + opend = bpf_sock->skb_data_end; + + op = bpf_search_tcp_opt(op, opend, new_kind, magic, magic_len, + &eol); + if (!IS_ERR(op)) + return -EEXIST; + + if (PTR_ERR(op) != -ENOMSG) + return PTR_ERR(op); + + if (eol) + /* The option has been ended. Treat it as no more + * header option can be written. + */ + return -ENOSPC; + + /* No duplication found. Store the header option. */ + memcpy(opend, from, new_kind_len); + + bpf_sock->remaining_opt_len -= new_kind_len; + bpf_sock->skb_data_end += new_kind_len; + + return 0; +} + +static const struct bpf_func_proto bpf_sock_ops_store_hdr_opt_proto = { + .func = bpf_sock_ops_store_hdr_opt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, +}; + +BPF_CALL_3(bpf_sock_ops_reserve_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, + u32, len, u64, flags) +{ + if (bpf_sock->op != BPF_SOCK_OPS_HDR_OPT_LEN_CB) + return -EPERM; + + if (flags || len < 2) + return -EINVAL; + + if (len > bpf_sock->remaining_opt_len) + return -ENOSPC; + + bpf_sock->remaining_opt_len -= len; + + return 0; +} + +static const struct bpf_func_proto bpf_sock_ops_reserve_hdr_opt_proto = { + .func = bpf_sock_ops_reserve_hdr_opt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; @@ -6164,6 +6872,7 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_skb_change_tail || func == sk_skb_change_tail || func == bpf_skb_adjust_room || + func == sk_skb_adjust_room || func == bpf_skb_pull_data || func == sk_skb_pull_data || func == bpf_clone_redirect || @@ -6180,6 +6889,9 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_lwt_seg6_adjust_srh || func == bpf_lwt_seg6_action || #endif +#ifdef CONFIG_INET + func == bpf_sock_ops_store_hdr_opt || +#endif func == bpf_lwt_in_push_encap || func == bpf_lwt_xmit_push_encap) return true; @@ -6298,7 +7010,7 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return NULL; } default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6317,7 +7029,7 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6419,6 +7131,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_redirect: return &bpf_redirect_proto; + case BPF_FUNC_redirect_neigh: + return &bpf_redirect_neigh_proto; + case BPF_FUNC_redirect_peer: + return &bpf_redirect_peer_proto; case BPF_FUNC_get_route_realm: return &bpf_get_route_realm_proto; case BPF_FUNC_get_hash_recalc: @@ -6449,6 +7165,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_get_xfrm_state: return &bpf_skb_get_xfrm_state_proto; #endif +#ifdef CONFIG_CGROUP_NET_CLASSID + case BPF_FUNC_skb_cgroup_classid: + return &bpf_skb_cgroup_classid_proto; +#endif #ifdef CONFIG_SOCK_CGROUP_DATA case BPF_FUNC_skb_cgroup_id: return &bpf_skb_cgroup_id_proto; @@ -6478,7 +7198,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sk_assign_proto; #endif default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6519,7 +7239,7 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_tcp_gen_syncookie_proto; #endif default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6551,11 +7271,17 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; #ifdef CONFIG_INET + case BPF_FUNC_load_hdr_opt: + return &bpf_sock_ops_load_hdr_opt_proto; + case BPF_FUNC_store_hdr_opt: + return &bpf_sock_ops_store_hdr_opt_proto; + case BPF_FUNC_reserve_hdr_opt: + return &bpf_sock_ops_reserve_hdr_opt_proto; case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; #endif /* CONFIG_INET */ default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6601,7 +7327,7 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_cgroup_classid_curr_proto; #endif default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6622,6 +7348,8 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &sk_skb_change_tail_proto; case BPF_FUNC_skb_change_head: return &sk_skb_change_head_proto; + case BPF_FUNC_skb_adjust_room: + return &sk_skb_adjust_room_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_socket_uid: @@ -6643,7 +7371,7 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skc_lookup_tcp_proto; #endif default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6654,7 +7382,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_load_bytes: return &bpf_flow_dissector_load_bytes_proto; default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6681,7 +7409,7 @@ lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_under_cgroup: return &bpf_skb_under_cgroup_proto; default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -7350,6 +8078,20 @@ static bool sock_ops_is_valid_access(int off, int size, return false; info->reg_type = PTR_TO_SOCKET_OR_NULL; break; + case offsetof(struct bpf_sock_ops, skb_data): + if (size != sizeof(__u64)) + return false; + info->reg_type = PTR_TO_PACKET; + break; + case offsetof(struct bpf_sock_ops, skb_data_end): + if (size != sizeof(__u64)) + return false; + info->reg_type = PTR_TO_PACKET_END; + break; + case offsetof(struct bpf_sock_ops, skb_tcp_flags): + bpf_ctx_record_field_size(info, size_default); + return bpf_ctx_narrow_access_ok(off, size, + size_default); default: if (size != size_default) return false; @@ -8451,17 +9193,22 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; switch (si->off) { - case offsetof(struct bpf_sock_ops, op) ... + case offsetof(struct bpf_sock_ops, op): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, + op), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, op)); + break; + + case offsetof(struct bpf_sock_ops, replylong[0]) ... offsetof(struct bpf_sock_ops, replylong[3]): - BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, op) != - sizeof_field(struct bpf_sock_ops_kern, op)); BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, reply) != sizeof_field(struct bpf_sock_ops_kern, reply)); BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, replylong) != sizeof_field(struct bpf_sock_ops_kern, replylong)); off = si->off; - off -= offsetof(struct bpf_sock_ops, op); - off += offsetof(struct bpf_sock_ops_kern, op); + off -= offsetof(struct bpf_sock_ops, replylong[0]); + off += offsetof(struct bpf_sock_ops_kern, replylong[0]); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, off); @@ -8682,6 +9429,49 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, case offsetof(struct bpf_sock_ops, sk): SOCK_OPS_GET_SK(); break; + case offsetof(struct bpf_sock_ops, skb_data_end): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, + skb_data_end), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, + skb_data_end)); + break; + case offsetof(struct bpf_sock_ops, skb_data): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, + skb), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, + skb)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), + si->dst_reg, si->dst_reg, + offsetof(struct sk_buff, data)); + break; + case offsetof(struct bpf_sock_ops, skb_len): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, + skb), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, + skb)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len), + si->dst_reg, si->dst_reg, + offsetof(struct sk_buff, len)); + break; + case offsetof(struct bpf_sock_ops, skb_tcp_flags): + off = offsetof(struct sk_buff, cb); + off += offsetof(struct tcp_skb_cb, tcp_flags); + *target_size = sizeof_field(struct tcp_skb_cb, tcp_flags); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, + skb), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, + skb)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_skb_cb, + tcp_flags), + si->dst_reg, si->dst_reg, off); + break; } return insn - insn_buf; } @@ -9356,7 +10146,7 @@ sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_sk_release: return &bpf_sk_release_proto; default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -9506,17 +10296,6 @@ BTF_SOCK_TYPE_xxx u32 btf_sock_ids[MAX_BTF_SOCK_TYPE]; #endif -static bool check_arg_btf_id(u32 btf_id, u32 arg) -{ - int i; - - /* only one argument, no need to check arg */ - for (i = 0; i < MAX_BTF_SOCK_TYPE; i++) - if (btf_sock_ids[i] == btf_id) - return true; - return false; -} - BPF_CALL_1(bpf_skc_to_tcp6_sock, struct sock *, sk) { /* tcp6_sock type is not generated in dwarf and hence btf, @@ -9534,8 +10313,7 @@ const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto = { .func = bpf_skc_to_tcp6_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, - .arg1_type = ARG_PTR_TO_BTF_ID, - .check_btf_id = check_arg_btf_id, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP6], }; @@ -9551,8 +10329,7 @@ const struct bpf_func_proto bpf_skc_to_tcp_sock_proto = { .func = bpf_skc_to_tcp_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, - .arg1_type = ARG_PTR_TO_BTF_ID, - .check_btf_id = check_arg_btf_id, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP], }; @@ -9581,8 +10358,7 @@ const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto = { .func = bpf_skc_to_tcp_timewait_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, - .arg1_type = ARG_PTR_TO_BTF_ID, - .check_btf_id = check_arg_btf_id, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP_TW], }; @@ -9605,8 +10381,7 @@ const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto = { .func = bpf_skc_to_tcp_request_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, - .arg1_type = ARG_PTR_TO_BTF_ID, - .check_btf_id = check_arg_btf_id, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP_REQ], }; @@ -9627,7 +10402,37 @@ const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = { .func = bpf_skc_to_udp6_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, - .arg1_type = ARG_PTR_TO_BTF_ID, - .check_btf_id = check_arg_btf_id, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UDP6], }; + +static const struct bpf_func_proto * +bpf_sk_base_func_proto(enum bpf_func_id func_id) +{ + const struct bpf_func_proto *func; + + switch (func_id) { + case BPF_FUNC_skc_to_tcp6_sock: + func = &bpf_skc_to_tcp6_sock_proto; + break; + case BPF_FUNC_skc_to_tcp_sock: + func = &bpf_skc_to_tcp_sock_proto; + break; + case BPF_FUNC_skc_to_tcp_timewait_sock: + func = &bpf_skc_to_tcp_timewait_sock_proto; + break; + case BPF_FUNC_skc_to_tcp_request_sock: + func = &bpf_skc_to_tcp_request_sock_proto; + break; + case BPF_FUNC_skc_to_udp6_sock: + func = &bpf_skc_to_udp6_sock_proto; + break; + default: + return bpf_base_func_proto(func_id); + } + + if (!perfmon_capable()) + return NULL; + + return func; +} diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 29806eb765cf..e21950a2c897 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -932,8 +932,14 @@ bool __skb_flow_dissect(const struct net *net, int offset = 0; ops = skb->dev->dsa_ptr->tag_ops; - if (ops->flow_dissect && - !ops->flow_dissect(skb, &proto, &offset)) { + /* Tail taggers don't break flow dissection */ + if (!ops->tail_tag) { + if (ops->flow_dissect) + ops->flow_dissect(skb, &proto, &offset); + else + dsa_tag_generic_flow_dissect(skb, + &proto, + &offset); hlen -= offset; nhoff += offset; } diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index 6bbd06f7dc7d..c714e6a9dad4 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -116,6 +116,12 @@ static int dev_seq_show(struct seq_file *seq, void *v) return 0; } +static u32 softnet_backlog_len(struct softnet_data *sd) +{ + return skb_queue_len_lockless(&sd->input_pkt_queue) + + skb_queue_len_lockless(&sd->process_queue); +} + static struct softnet_data *softnet_get_online(loff_t *pos) { struct softnet_data *sd = NULL; @@ -159,12 +165,17 @@ static int softnet_seq_show(struct seq_file *seq, void *v) rcu_read_unlock(); #endif + /* the index is the CPU id owing this sd. Since offline CPUs are not + * displayed, it would be othrwise not trivial for the user-space + * mapping the data a specific CPU + */ seq_printf(seq, - "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n", + "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n", sd->processed, sd->dropped, sd->time_squeeze, 0, 0, 0, 0, 0, /* was fastroute */ 0, /* was cpu_collision */ - sd->received_rps, flow_limit_count); + sd->received_rps, flow_limit_count, + softnet_backlog_len(sd), (int)seq->index); return 0; } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index efec66fa78b7..94fff0700bdd 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1158,8 +1158,8 @@ static ssize_t traffic_class_show(struct netdev_queue *queue, * belongs to the root device it will be reported with just the * traffic class, so just "0" for TC 0 for example. */ - return dev->num_tc < 0 ? sprintf(buf, "%u%d\n", tc, dev->num_tc) : - sprintf(buf, "%u\n", tc); + return dev->num_tc < 0 ? sprintf(buf, "%d%d\n", tc, dev->num_tc) : + sprintf(buf, "%d\n", tc); } #ifdef CONFIG_XPS diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 944ab214e5ae..dbc66b896287 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -19,6 +19,7 @@ #include <linux/net_namespace.h> #include <linux/sched/task.h> #include <linux/uidgid.h> +#include <linux/cookie.h> #include <net/sock.h> #include <net/netlink.h> @@ -69,16 +70,16 @@ EXPORT_SYMBOL_GPL(pernet_ops_rwsem); static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS; -static atomic64_t cookie_gen; +DEFINE_COOKIE(net_cookie); -u64 net_gen_cookie(struct net *net) +u64 __net_gen_cookie(struct net *net) { while (1) { u64 res = atomic64_read(&net->net_cookie); if (res) return res; - res = atomic64_inc_return(&cookie_gen); + res = gen_cookie_next(&net_cookie); atomic64_cmpxchg(&net->net_cookie, 0, res); } } @@ -1101,7 +1102,10 @@ static int __init net_ns_init(void) panic("Could not allocate generic netns"); rcu_assign_pointer(init_net.gen, ng); - net_gen_cookie(&init_net); + + preempt_disable(); + __net_gen_cookie(&init_net); + preempt_enable(); down_write(&pernet_ops_rwsem); if (setup_net(&init_net, &init_user_ns)) diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 2338753e936b..c310c7c1cef7 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -297,7 +297,7 @@ static int netpoll_owner_active(struct net_device *dev) { struct napi_struct *napi; - list_for_each_entry(napi, &dev->napi_list, dev_list) { + list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) { if (napi->poll_owner == smp_processor_id()) return 1; } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 44fdbb9c6e53..105978604ffd 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -922,7 +922,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->min_pkt_size = value; pkt_dev->cur_pkt_size = value; } - sprintf(pg_result, "OK: min_pkt_size=%u", + sprintf(pg_result, "OK: min_pkt_size=%d", pkt_dev->min_pkt_size); return count; } @@ -939,7 +939,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->max_pkt_size = value; pkt_dev->cur_pkt_size = value; } - sprintf(pg_result, "OK: max_pkt_size=%u", + sprintf(pg_result, "OK: max_pkt_size=%d", pkt_dev->max_pkt_size); return count; } @@ -959,7 +959,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->max_pkt_size = value; pkt_dev->cur_pkt_size = value; } - sprintf(pg_result, "OK: pkt_size=%u", pkt_dev->min_pkt_size); + sprintf(pg_result, "OK: pkt_size=%d", pkt_dev->min_pkt_size); return count; } @@ -981,7 +981,7 @@ static ssize_t pktgen_if_write(struct file *file, i += len; pkt_dev->nfrags = value; - sprintf(pg_result, "OK: frags=%u", pkt_dev->nfrags); + sprintf(pg_result, "OK: frags=%d", pkt_dev->nfrags); return count; } if (!strcmp(name, "delay")) { @@ -1146,7 +1146,7 @@ static ssize_t pktgen_if_write(struct file *file, (!(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING))))) return -ENOTSUPP; pkt_dev->burst = value < 1 ? 1 : value; - sprintf(pg_result, "OK: burst=%d", pkt_dev->burst); + sprintf(pg_result, "OK: burst=%u", pkt_dev->burst); return count; } if (!strcmp(name, "node")) { diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c index d964a5147f22..e33fde06d528 100644 --- a/net/core/ptp_classifier.c +++ b/net/core/ptp_classifier.c @@ -107,6 +107,36 @@ unsigned int ptp_classify_raw(const struct sk_buff *skb) } EXPORT_SYMBOL_GPL(ptp_classify_raw); +struct ptp_header *ptp_parse_header(struct sk_buff *skb, unsigned int type) +{ + u8 *ptr = skb_mac_header(skb); + + if (type & PTP_CLASS_VLAN) + ptr += VLAN_HLEN; + + switch (type & PTP_CLASS_PMASK) { + case PTP_CLASS_IPV4: + ptr += IPV4_HLEN(ptr) + UDP_HLEN; + break; + case PTP_CLASS_IPV6: + ptr += IP6_HLEN + UDP_HLEN; + break; + case PTP_CLASS_L2: + break; + default: + return NULL; + } + + ptr += ETH_HLEN; + + /* Ensure that the entire header is present in this packet. */ + if (ptr + sizeof(struct ptp_header) > skb->data + skb->len) + return NULL; + + return (struct ptp_header *)ptr; +} +EXPORT_SYMBOL_GPL(ptp_parse_header); + void __init ptp_classifier_init(void) { static struct sock_filter ptp_filter[] __initdata = { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 68e0682450c6..7d7223691783 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3709,13 +3709,13 @@ static int rtnl_dellinkprop(struct sk_buff *skb, struct nlmsghdr *nlh, return rtnl_linkprop(RTM_DELLINKPROP, skb, nlh, extack); } -static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh) +static u32 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); - struct net_device *dev; + size_t min_ifinfo_dump_size = 0; struct nlattr *tb[IFLA_MAX+1]; u32 ext_filter_mask = 0; - u16 min_ifinfo_dump_size = 0; + struct net_device *dev; int hdrlen; /* Same kernel<->userspace interface hack as in rtnl_dump_ifinfo. */ @@ -3735,9 +3735,8 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh) */ rcu_read_lock(); for_each_netdev_rcu(net, dev) { - min_ifinfo_dump_size = max_t(u16, min_ifinfo_dump_size, - if_nlmsg_size(dev, - ext_filter_mask)); + min_ifinfo_dump_size = max(min_ifinfo_dump_size, + if_nlmsg_size(dev, ext_filter_mask)); } rcu_read_unlock(); @@ -5494,7 +5493,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) { struct sock *rtnl; rtnl_dumpit_func dumpit; - u16 min_dump_alloc = 0; + u32 min_dump_alloc = 0; link = rtnl_get_link(family, type); if (!link || !link->dumpit) { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2b48cb0cc684..1ba8f0163744 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -712,11 +712,10 @@ EXPORT_SYMBOL(kfree_skb_list); * * Must only be called from net_ratelimit()-ed paths. * - * Dumps up to can_dump_full whole packets if full_pkt, headers otherwise. + * Dumps whole packets if full_pkt, only headers otherwise. */ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) { - static atomic_t can_dump_full = ATOMIC_INIT(5); struct skb_shared_info *sh = skb_shinfo(skb); struct net_device *dev = skb->dev; struct sock *sk = skb->sk; @@ -726,9 +725,6 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) int i, len, seg_len; if (full_pkt) - full_pkt = atomic_dec_if_positive(&can_dump_full) >= 0; - - if (full_pkt) len = skb->len; else len = min_t(int, skb->len, MAX_HEADER + 128); @@ -895,9 +891,6 @@ void __kfree_skb_defer(struct sk_buff *skb) void napi_consume_skb(struct sk_buff *skb, int budget) { - if (unlikely(!skb)) - return; - /* Zero budget indicate non-NAPI context called us, like netpoll */ if (unlikely(!budget)) { dev_consume_skb_any(skb); @@ -2725,19 +2718,20 @@ EXPORT_SYMBOL(skb_checksum); /* Both of above in one bottle. */ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, - u8 *to, int len, __wsum csum) + u8 *to, int len) { int start = skb_headlen(skb); int i, copy = start - offset; struct sk_buff *frag_iter; int pos = 0; + __wsum csum = 0; /* Copy header. */ if (copy > 0) { if (copy > len) copy = len; csum = csum_partial_copy_nocheck(skb->data + offset, to, - copy, csum); + copy); if ((len -= copy) == 0) return csum; offset += copy; @@ -2767,7 +2761,7 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, vaddr = kmap_atomic(p); csum2 = csum_partial_copy_nocheck(vaddr + p_off, to + copied, - p_len, 0); + p_len); kunmap_atomic(vaddr); csum = csum_block_add(csum, csum2, pos); pos += p_len; @@ -2793,7 +2787,7 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, copy = len; csum2 = skb_copy_and_csum_bits(frag_iter, offset - start, - to, copy, 0); + to, copy); csum = csum_block_add(csum, csum2, pos); if ((len -= copy) == 0) return csum; @@ -3013,7 +3007,7 @@ void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to) csum = 0; if (csstart != skb->len) csum = skb_copy_and_csum_bits(skb, csstart, to + csstart, - skb->len - csstart, 0); + skb->len - csstart); if (skb->ip_summed == CHECKSUM_PARTIAL) { long csstuff = csstart + skb->csum_offset; @@ -3934,7 +3928,7 @@ normal: skb_copy_and_csum_bits(head_skb, offset, skb_put(nskb, len), - len, 0); + len); SKB_GSO_CB(nskb)->csum_start = skb_headroom(nskb) + doffset; } else { @@ -5561,6 +5555,73 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) } EXPORT_SYMBOL(skb_vlan_push); +/** + * skb_eth_pop() - Drop the Ethernet header at the head of a packet + * + * @skb: Socket buffer to modify + * + * Drop the Ethernet header of @skb. + * + * Expects that skb->data points to the mac header and that no VLAN tags are + * present. + * + * Returns 0 on success, -errno otherwise. + */ +int skb_eth_pop(struct sk_buff *skb) +{ + if (!pskb_may_pull(skb, ETH_HLEN) || skb_vlan_tagged(skb) || + skb_network_offset(skb) < ETH_HLEN) + return -EPROTO; + + skb_pull_rcsum(skb, ETH_HLEN); + skb_reset_mac_header(skb); + skb_reset_mac_len(skb); + + return 0; +} +EXPORT_SYMBOL(skb_eth_pop); + +/** + * skb_eth_push() - Add a new Ethernet header at the head of a packet + * + * @skb: Socket buffer to modify + * @dst: Destination MAC address of the new header + * @src: Source MAC address of the new header + * + * Prepend @skb with a new Ethernet header. + * + * Expects that skb->data points to the mac header, which must be empty. + * + * Returns 0 on success, -errno otherwise. + */ +int skb_eth_push(struct sk_buff *skb, const unsigned char *dst, + const unsigned char *src) +{ + struct ethhdr *eth; + int err; + + if (skb_network_offset(skb) || skb_vlan_tag_present(skb)) + return -EPROTO; + + err = skb_cow_head(skb, sizeof(*eth)); + if (err < 0) + return err; + + skb_push(skb, sizeof(*eth)); + skb_reset_mac_header(skb); + skb_reset_mac_len(skb); + + eth = eth_hdr(skb); + ether_addr_copy(eth->h_dest, dst); + ether_addr_copy(eth->h_source, src); + eth->h_proto = skb->protocol; + + skb_postpush_rcsum(skb, eth, sizeof(*eth)); + + return 0; +} +EXPORT_SYMBOL(skb_eth_push); + /* Update the ethertype of hdr and the skb csum value if required. */ static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr, __be16 ethertype) @@ -5955,8 +6016,7 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, size = SKB_WITH_OVERHEAD(ksize(data)); memcpy((struct skb_shared_info *)(data + size), - skb_shinfo(skb), offsetof(struct skb_shared_info, - frags[skb_shinfo(skb)->nr_frags])); + skb_shinfo(skb), offsetof(struct skb_shared_info, frags[0])); if (skb_orphan_frags(skb, gfp_mask)) { kfree(data); return -ENOMEM; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 649583158983..654182ecf87b 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -433,10 +433,12 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, u32 off, u32 len, bool ingress) { - if (ingress) - return sk_psock_skb_ingress(psock, skb); - else + if (!ingress) { + if (!sock_writeable(psock->sk)) + return -EAGAIN; return skb_send_sock_locked(psock->sk, skb, off, len); + } + return sk_psock_skb_ingress(psock, skb); } static void sk_psock_backlog(struct work_struct *work) @@ -494,14 +496,34 @@ end: struct sk_psock *sk_psock_init(struct sock *sk, int node) { - struct sk_psock *psock = kzalloc_node(sizeof(*psock), - GFP_ATOMIC | __GFP_NOWARN, - node); - if (!psock) - return NULL; + struct sk_psock *psock; + struct proto *prot; + + write_lock_bh(&sk->sk_callback_lock); + + if (inet_csk_has_ulp(sk)) { + psock = ERR_PTR(-EINVAL); + goto out; + } + + if (sk->sk_user_data) { + psock = ERR_PTR(-EBUSY); + goto out; + } + + psock = kzalloc_node(sizeof(*psock), GFP_ATOMIC | __GFP_NOWARN, node); + if (!psock) { + psock = ERR_PTR(-ENOMEM); + goto out; + } + prot = READ_ONCE(sk->sk_prot); psock->sk = sk; - psock->eval = __SK_NONE; + psock->eval = __SK_NONE; + psock->sk_proto = prot; + psock->saved_unhash = prot->unhash; + psock->saved_close = prot->close; + psock->saved_write_space = sk->sk_write_space; INIT_LIST_HEAD(&psock->link); spin_lock_init(&psock->link_lock); @@ -516,6 +538,8 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node) rcu_assign_sk_user_data_nocopy(sk, psock); sock_hold(sk); +out: + write_unlock_bh(&sk->sk_callback_lock); return psock; } EXPORT_SYMBOL_GPL(sk_psock_init); @@ -603,6 +627,8 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock) rcu_assign_sk_user_data(sk, NULL); if (psock->progs.skb_parser) sk_psock_stop_strp(sk, psock); + else if (psock->progs.skb_verdict) + sk_psock_stop_verdict(sk, psock); write_unlock_bh(&sk->sk_callback_lock); sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); @@ -660,19 +686,8 @@ EXPORT_SYMBOL_GPL(sk_psock_msg_verdict); static int sk_psock_bpf_run(struct sk_psock *psock, struct bpf_prog *prog, struct sk_buff *skb) { - int ret; - - skb->sk = psock->sk; bpf_compute_data_end_sk_skb(skb); - ret = bpf_prog_run_pin_on_cpu(prog, skb); - /* strparser clones the skb before handing it to a upper layer, - * meaning skb_orphan has been called. We NULL sk on the way out - * to ensure we don't trigger a BUG_ON() in skb/sk operations - * later and because we are not charging the memory of this skb - * to any socket yet. - */ - skb->sk = NULL; - return ret; + return bpf_prog_run_pin_on_cpu(prog, skb); } static struct sk_psock *sk_psock_from_strp(struct strparser *strp) @@ -687,38 +702,35 @@ static void sk_psock_skb_redirect(struct sk_buff *skb) { struct sk_psock *psock_other; struct sock *sk_other; - bool ingress; sk_other = tcp_skb_bpf_redirect_fetch(skb); + /* This error is a buggy BPF program, it returned a redirect + * return code, but then didn't set a redirect interface. + */ if (unlikely(!sk_other)) { kfree_skb(skb); return; } psock_other = sk_psock(sk_other); + /* This error indicates the socket is being torn down or had another + * error that caused the pipe to break. We can't send a packet on + * a socket that is in this state so we drop the skb. + */ if (!psock_other || sock_flag(sk_other, SOCK_DEAD) || !sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED)) { kfree_skb(skb); return; } - ingress = tcp_skb_bpf_ingress(skb); - if ((!ingress && sock_writeable(sk_other)) || - (ingress && - atomic_read(&sk_other->sk_rmem_alloc) <= - sk_other->sk_rcvbuf)) { - if (!ingress) - skb_set_owner_w(skb, sk_other); - skb_queue_tail(&psock_other->ingress_skb, skb); - schedule_work(&psock_other->work); - } else { - kfree_skb(skb); - } + skb_queue_tail(&psock_other->ingress_skb, skb); + schedule_work(&psock_other->work); } -static void sk_psock_tls_verdict_apply(struct sk_buff *skb, int verdict) +static void sk_psock_tls_verdict_apply(struct sk_buff *skb, struct sock *sk, int verdict) { switch (verdict) { case __SK_REDIRECT: + skb_set_owner_r(skb, sk); sk_psock_skb_redirect(skb); break; case __SK_PASS: @@ -736,11 +748,17 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb) rcu_read_lock(); prog = READ_ONCE(psock->progs.skb_verdict); if (likely(prog)) { + /* We skip full set_owner_r here because if we do a SK_PASS + * or SK_DROP we can skip skb memory accounting and use the + * TLS context. + */ + skb->sk = psock->sk; tcp_skb_bpf_redirect_clear(skb); ret = sk_psock_bpf_run(psock, prog, skb); ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); + skb->sk = NULL; } - sk_psock_tls_verdict_apply(skb, ret); + sk_psock_tls_verdict_apply(skb, psock->sk, ret); rcu_read_unlock(); return ret; } @@ -749,7 +767,9 @@ EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read); static void sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, int verdict) { + struct tcp_skb_cb *tcp; struct sock *sk_other; + int err = -EIO; switch (verdict) { case __SK_PASS: @@ -758,16 +778,24 @@ static void sk_psock_verdict_apply(struct sk_psock *psock, !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { goto out_free; } - if (atomic_read(&sk_other->sk_rmem_alloc) <= - sk_other->sk_rcvbuf) { - struct tcp_skb_cb *tcp = TCP_SKB_CB(skb); - tcp->bpf.flags |= BPF_F_INGRESS; + tcp = TCP_SKB_CB(skb); + tcp->bpf.flags |= BPF_F_INGRESS; + + /* If the queue is empty then we can submit directly + * into the msg queue. If its not empty we have to + * queue work otherwise we may get OOO data. Otherwise, + * if sk_psock_skb_ingress errors will be handled by + * retrying later from workqueue. + */ + if (skb_queue_empty(&psock->ingress_skb)) { + err = sk_psock_skb_ingress(psock, skb); + } + if (err < 0) { skb_queue_tail(&psock->ingress_skb, skb); schedule_work(&psock->work); - break; } - goto out_free; + break; case __SK_REDIRECT: sk_psock_skb_redirect(skb); break; @@ -792,9 +820,9 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) kfree_skb(skb); goto out; } + skb_set_owner_r(skb, sk); prog = READ_ONCE(psock->progs.skb_verdict); if (likely(prog)) { - skb_orphan(skb); tcp_skb_bpf_redirect_clear(skb); ret = sk_psock_bpf_run(psock, prog, skb); ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); @@ -817,8 +845,11 @@ static int sk_psock_strp_parse(struct strparser *strp, struct sk_buff *skb) rcu_read_lock(); prog = READ_ONCE(psock->progs.skb_parser); - if (likely(prog)) + if (likely(prog)) { + skb->sk = psock->sk; ret = sk_psock_bpf_run(psock, prog, skb); + skb->sk = NULL; + } rcu_read_unlock(); return ret; } @@ -842,6 +873,57 @@ static void sk_psock_strp_data_ready(struct sock *sk) rcu_read_unlock(); } +static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb, + unsigned int offset, size_t orig_len) +{ + struct sock *sk = (struct sock *)desc->arg.data; + struct sk_psock *psock; + struct bpf_prog *prog; + int ret = __SK_DROP; + int len = skb->len; + + /* clone here so sk_eat_skb() in tcp_read_sock does not drop our data */ + skb = skb_clone(skb, GFP_ATOMIC); + if (!skb) { + desc->error = -ENOMEM; + return 0; + } + + rcu_read_lock(); + psock = sk_psock(sk); + if (unlikely(!psock)) { + len = 0; + kfree_skb(skb); + goto out; + } + skb_set_owner_r(skb, sk); + prog = READ_ONCE(psock->progs.skb_verdict); + if (likely(prog)) { + tcp_skb_bpf_redirect_clear(skb); + ret = sk_psock_bpf_run(psock, prog, skb); + ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); + } + sk_psock_verdict_apply(psock, skb, ret); +out: + rcu_read_unlock(); + return len; +} + +static void sk_psock_verdict_data_ready(struct sock *sk) +{ + struct socket *sock = sk->sk_socket; + read_descriptor_t desc; + + if (unlikely(!sock || !sock->ops || !sock->ops->read_sock)) + return; + + desc.arg.data = sk; + desc.error = 0; + desc.count = 1; + + sock->ops->read_sock(sk, &desc, sk_psock_verdict_recv); +} + static void sk_psock_write_space(struct sock *sk) { struct sk_psock *psock; @@ -871,6 +953,19 @@ int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) return strp_init(&psock->parser.strp, sk, &cb); } +void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock) +{ + struct sk_psock_parser *parser = &psock->parser; + + if (parser->enabled) + return; + + parser->saved_data_ready = sk->sk_data_ready; + sk->sk_data_ready = sk_psock_verdict_data_ready; + sk->sk_write_space = sk_psock_write_space; + parser->enabled = true; +} + void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) { struct sk_psock_parser *parser = &psock->parser; @@ -896,3 +991,15 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) strp_stop(&parser->strp); parser->enabled = false; } + +void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock) +{ + struct sk_psock_parser *parser = &psock->parser; + + if (!parser->enabled) + return; + + sk->sk_data_ready = parser->saved_data_ready; + parser->saved_data_ready = NULL; + parser->enabled = false; +} diff --git a/net/core/sock.c b/net/core/sock.c index 6c5c6b18eff4..727ea1cc633c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -413,18 +413,6 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, return 0; } -static void sock_warn_obsolete_bsdism(const char *name) -{ - static int warned; - static char warncomm[TASK_COMM_LEN]; - if (strcmp(warncomm, current->comm) && warned < 5) { - strcpy(warncomm, current->comm); - pr_warn("process `%s' is using obsolete %s SO_BSDCOMPAT\n", - warncomm, name); - warned++; - } -} - static bool sock_needs_netstamp(const struct sock *sk) { switch (sk->sk_family) { @@ -769,7 +757,6 @@ static void __sock_set_timestamps(struct sock *sk, bool val, bool new, bool ns) } else { sock_reset_flag(sk, SOCK_RCVTSTAMP); sock_reset_flag(sk, SOCK_RCVTSTAMPNS); - sock_reset_flag(sk, SOCK_TSTAMP_NEW); } } @@ -984,7 +971,6 @@ set_sndbuf: break; case SO_BSDCOMPAT: - sock_warn_obsolete_bsdism("setsockopt"); break; case SO_PASSCRED: @@ -1007,8 +993,6 @@ set_sndbuf: __sock_set_timestamps(sk, valbool, true, true); break; case SO_TIMESTAMPING_NEW: - sock_set_flag(sk, SOCK_TSTAMP_NEW); - fallthrough; case SO_TIMESTAMPING_OLD: if (val & ~SOF_TIMESTAMPING_MASK) { ret = -EINVAL; @@ -1037,16 +1021,14 @@ set_sndbuf: } sk->sk_tsflags = val; + sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW); + if (val & SOF_TIMESTAMPING_RX_SOFTWARE) sock_enable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE); - else { - if (optname == SO_TIMESTAMPING_NEW) - sock_reset_flag(sk, SOCK_TSTAMP_NEW); - + else sock_disable_timestamp(sk, (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)); - } break; case SO_RCVLOWAT: @@ -1181,7 +1163,7 @@ set_sndbuf: case SO_MAX_PACING_RATE: { - unsigned long ulval = (val == ~0U) ? ~0UL : val; + unsigned long ulval = (val == ~0U) ? ~0UL : (unsigned int)val; if (sizeof(ulval) != sizeof(val) && optlen >= sizeof(ulval) && @@ -1387,7 +1369,6 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_BSDCOMPAT: - sock_warn_obsolete_bsdism("getsockopt"); break; case SO_TIMESTAMP_OLD: @@ -2961,6 +2942,13 @@ void sk_stop_timer(struct sock *sk, struct timer_list* timer) } EXPORT_SYMBOL(sk_stop_timer); +void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer) +{ + if (del_timer_sync(timer)) + __sock_put(sk); +} +EXPORT_SYMBOL(sk_stop_timer_sync); + void sock_init_data(struct socket *sock, struct sock *sk) { sk_init_common(sk); diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index c13ffbd33d8d..c9c45b935f99 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -11,7 +11,7 @@ #include <linux/tcp.h> #include <linux/workqueue.h> #include <linux/nospec.h> - +#include <linux/cookie.h> #include <linux/inet_diag.h> #include <linux/sock_diag.h> @@ -19,16 +19,17 @@ static const struct sock_diag_handler *sock_diag_handlers[AF_MAX]; static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh); static DEFINE_MUTEX(sock_diag_table_mutex); static struct workqueue_struct *broadcast_wq; -static atomic64_t cookie_gen; -u64 sock_gen_cookie(struct sock *sk) +DEFINE_COOKIE(sock_cookie); + +u64 __sock_gen_cookie(struct sock *sk) { while (1) { u64 res = atomic64_read(&sk->sk_cookie); if (res) return res; - res = atomic64_inc_return(&cookie_gen); + res = gen_cookie_next(&sock_cookie); atomic64_cmpxchg(&sk->sk_cookie, 0, res); } } diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 119f52a99dc1..ddc899e83313 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -2,6 +2,7 @@ /* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */ #include <linux/bpf.h> +#include <linux/btf_ids.h> #include <linux/filter.h> #include <linux/errno.h> #include <linux/file.h> @@ -147,8 +148,8 @@ static void sock_map_add_link(struct sk_psock *psock, static void sock_map_del_link(struct sock *sk, struct sk_psock *psock, void *link_raw) { + bool strp_stop = false, verdict_stop = false; struct sk_psock_link *link, *tmp; - bool strp_stop = false; spin_lock_bh(&psock->link_lock); list_for_each_entry_safe(link, tmp, &psock->link, list) { @@ -158,14 +159,19 @@ static void sock_map_del_link(struct sock *sk, map); if (psock->parser.enabled && stab->progs.skb_parser) strp_stop = true; + if (psock->parser.enabled && stab->progs.skb_verdict) + verdict_stop = true; list_del(&link->list); sk_psock_free_link(link); } } spin_unlock_bh(&psock->link_lock); - if (strp_stop) { + if (strp_stop || verdict_stop) { write_lock_bh(&sk->sk_callback_lock); - sk_psock_stop_strp(sk, psock); + if (strp_stop) + sk_psock_stop_strp(sk, psock); + else + sk_psock_stop_verdict(sk, psock); write_unlock_bh(&sk->sk_callback_lock); } } @@ -184,8 +190,6 @@ static int sock_map_init_proto(struct sock *sk, struct sk_psock *psock) { struct proto *prot; - sock_owned_by_me(sk); - switch (sk->sk_type) { case SOCK_STREAM: prot = tcp_bpf_get_proto(sk, psock); @@ -231,20 +235,21 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs, { struct bpf_prog *msg_parser, *skb_parser, *skb_verdict; struct sk_psock *psock; - bool skb_progs; int ret; skb_verdict = READ_ONCE(progs->skb_verdict); - skb_parser = READ_ONCE(progs->skb_parser); - skb_progs = skb_parser && skb_verdict; - if (skb_progs) { + if (skb_verdict) { skb_verdict = bpf_prog_inc_not_zero(skb_verdict); if (IS_ERR(skb_verdict)) return PTR_ERR(skb_verdict); + } + + skb_parser = READ_ONCE(progs->skb_parser); + if (skb_parser) { skb_parser = bpf_prog_inc_not_zero(skb_parser); if (IS_ERR(skb_parser)) { - bpf_prog_put(skb_verdict); - return PTR_ERR(skb_parser); + ret = PTR_ERR(skb_parser); + goto out_put_skb_verdict; } } @@ -253,7 +258,7 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs, msg_parser = bpf_prog_inc_not_zero(msg_parser); if (IS_ERR(msg_parser)) { ret = PTR_ERR(msg_parser); - goto out; + goto out_put_skb_parser; } } @@ -265,15 +270,16 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs, if (psock) { if ((msg_parser && READ_ONCE(psock->progs.msg_parser)) || - (skb_progs && READ_ONCE(psock->progs.skb_parser))) { + (skb_parser && READ_ONCE(psock->progs.skb_parser)) || + (skb_verdict && READ_ONCE(psock->progs.skb_verdict))) { sk_psock_put(sk, psock); ret = -EBUSY; goto out_progs; } } else { psock = sk_psock_init(sk, map->numa_node); - if (!psock) { - ret = -ENOMEM; + if (IS_ERR(psock)) { + ret = PTR_ERR(psock); goto out_progs; } } @@ -286,28 +292,32 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs, goto out_drop; write_lock_bh(&sk->sk_callback_lock); - if (skb_progs && !psock->parser.enabled) { + if (skb_parser && skb_verdict && !psock->parser.enabled) { ret = sk_psock_init_strp(sk, psock); - if (ret) { - write_unlock_bh(&sk->sk_callback_lock); - goto out_drop; - } + if (ret) + goto out_unlock_drop; psock_set_prog(&psock->progs.skb_verdict, skb_verdict); psock_set_prog(&psock->progs.skb_parser, skb_parser); sk_psock_start_strp(sk, psock); + } else if (!skb_parser && skb_verdict && !psock->parser.enabled) { + psock_set_prog(&psock->progs.skb_verdict, skb_verdict); + sk_psock_start_verdict(sk,psock); } write_unlock_bh(&sk->sk_callback_lock); return 0; +out_unlock_drop: + write_unlock_bh(&sk->sk_callback_lock); out_drop: sk_psock_put(sk, psock); out_progs: if (msg_parser) bpf_prog_put(msg_parser); -out: - if (skb_progs) { - bpf_prog_put(skb_verdict); +out_put_skb_parser: + if (skb_parser) bpf_prog_put(skb_parser); - } +out_put_skb_verdict: + if (skb_verdict) + bpf_prog_put(skb_verdict); return ret; } @@ -322,8 +332,8 @@ static int sock_map_link_no_progs(struct bpf_map *map, struct sock *sk) if (!psock) { psock = sk_psock_init(sk, map->numa_node); - if (!psock) - return -ENOMEM; + if (IS_ERR(psock)) + return PTR_ERR(psock); } ret = sock_map_init_proto(sk, psock); @@ -384,7 +394,7 @@ static void *sock_map_lookup(struct bpf_map *map, void *key) struct sock *sk; sk = __sock_map_lookup_elem(map, *(u32 *)key); - if (!sk || !sk_fullsock(sk)) + if (!sk) return NULL; if (sk_is_refcounted(sk) && !refcount_inc_not_zero(&sk->sk_refcnt)) return NULL; @@ -402,7 +412,7 @@ static void *sock_map_lookup_sys(struct bpf_map *map, void *key) if (!sk) return ERR_PTR(-ENOENT); - sock_gen_cookie(sk); + __sock_gen_cookie(sk); return &sk->sk_cookie; } @@ -478,8 +488,6 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx, return -EINVAL; if (unlikely(idx >= map->max_entries)) return -E2BIG; - if (inet_csk_has_ulp(sk)) - return -EINVAL; link = sk_psock_init_link(); if (!link) @@ -563,10 +571,12 @@ static bool sock_map_sk_state_allowed(const struct sock *sk) return false; } -static int sock_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 flags) +static int sock_hash_update_common(struct bpf_map *map, void *key, + struct sock *sk, u64 flags); + +int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, + u64 flags) { - u32 idx = *(u32 *)key; struct socket *sock; struct sock *sk; int ret; @@ -595,14 +605,41 @@ static int sock_map_update_elem(struct bpf_map *map, void *key, sock_map_sk_acquire(sk); if (!sock_map_sk_state_allowed(sk)) ret = -EOPNOTSUPP; + else if (map->map_type == BPF_MAP_TYPE_SOCKMAP) + ret = sock_map_update_common(map, *(u32 *)key, sk, flags); else - ret = sock_map_update_common(map, idx, sk, flags); + ret = sock_hash_update_common(map, key, sk, flags); sock_map_sk_release(sk); out: fput(sock->file); return ret; } +static int sock_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + struct sock *sk = (struct sock *)value; + int ret; + + if (unlikely(!sk || !sk_fullsock(sk))) + return -EINVAL; + + if (!sock_map_sk_is_suitable(sk)) + return -EOPNOTSUPP; + + local_bh_disable(); + bh_lock_sock(sk); + if (!sock_map_sk_state_allowed(sk)) + ret = -EOPNOTSUPP; + else if (map->map_type == BPF_MAP_TYPE_SOCKMAP) + ret = sock_map_update_common(map, *(u32 *)key, sk, flags); + else + ret = sock_hash_update_common(map, key, sk, flags); + bh_unlock_sock(sk); + local_bh_enable(); + return ret; +} + BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, sops, struct bpf_map *, map, void *, key, u64, flags) { @@ -681,8 +718,116 @@ const struct bpf_func_proto bpf_msg_redirect_map_proto = { .arg4_type = ARG_ANYTHING, }; +struct sock_map_seq_info { + struct bpf_map *map; + struct sock *sk; + u32 index; +}; + +struct bpf_iter__sockmap { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct bpf_map *, map); + __bpf_md_ptr(void *, key); + __bpf_md_ptr(struct sock *, sk); +}; + +DEFINE_BPF_ITER_FUNC(sockmap, struct bpf_iter_meta *meta, + struct bpf_map *map, void *key, + struct sock *sk) + +static void *sock_map_seq_lookup_elem(struct sock_map_seq_info *info) +{ + if (unlikely(info->index >= info->map->max_entries)) + return NULL; + + info->sk = __sock_map_lookup_elem(info->map, info->index); + + /* can't return sk directly, since that might be NULL */ + return info; +} + +static void *sock_map_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(rcu) +{ + struct sock_map_seq_info *info = seq->private; + + if (*pos == 0) + ++*pos; + + /* pairs with sock_map_seq_stop */ + rcu_read_lock(); + return sock_map_seq_lookup_elem(info); +} + +static void *sock_map_seq_next(struct seq_file *seq, void *v, loff_t *pos) + __must_hold(rcu) +{ + struct sock_map_seq_info *info = seq->private; + + ++*pos; + ++info->index; + + return sock_map_seq_lookup_elem(info); +} + +static int sock_map_seq_show(struct seq_file *seq, void *v) + __must_hold(rcu) +{ + struct sock_map_seq_info *info = seq->private; + struct bpf_iter__sockmap ctx = {}; + struct bpf_iter_meta meta; + struct bpf_prog *prog; + + meta.seq = seq; + prog = bpf_iter_get_info(&meta, !v); + if (!prog) + return 0; + + ctx.meta = &meta; + ctx.map = info->map; + if (v) { + ctx.key = &info->index; + ctx.sk = info->sk; + } + + return bpf_iter_run_prog(prog, &ctx); +} + +static void sock_map_seq_stop(struct seq_file *seq, void *v) + __releases(rcu) +{ + if (!v) + (void)sock_map_seq_show(seq, NULL); + + /* pairs with sock_map_seq_start */ + rcu_read_unlock(); +} + +static const struct seq_operations sock_map_seq_ops = { + .start = sock_map_seq_start, + .next = sock_map_seq_next, + .stop = sock_map_seq_stop, + .show = sock_map_seq_show, +}; + +static int sock_map_init_seq_private(void *priv_data, + struct bpf_iter_aux_info *aux) +{ + struct sock_map_seq_info *info = priv_data; + + info->map = aux->map; + return 0; +} + +static const struct bpf_iter_seq_info sock_map_iter_seq_info = { + .seq_ops = &sock_map_seq_ops, + .init_seq_private = sock_map_init_seq_private, + .seq_priv_size = sizeof(struct sock_map_seq_info), +}; + static int sock_map_btf_id; const struct bpf_map_ops sock_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc = sock_map_alloc, .map_free = sock_map_free, .map_get_next_key = sock_map_get_next_key, @@ -694,6 +839,7 @@ const struct bpf_map_ops sock_map_ops = { .map_check_btf = map_check_no_btf, .map_btf_name = "bpf_stab", .map_btf_id = &sock_map_btf_id, + .iter_seq_info = &sock_map_iter_seq_info, }; struct bpf_shtab_elem { @@ -855,8 +1001,6 @@ static int sock_hash_update_common(struct bpf_map *map, void *key, WARN_ON_ONCE(!rcu_read_lock_held()); if (unlikely(flags > BPF_EXIST)) return -EINVAL; - if (inet_csk_has_ulp(sk)) - return -EINVAL; link = sk_psock_init_link(); if (!link) @@ -915,45 +1059,6 @@ out_free: return ret; } -static int sock_hash_update_elem(struct bpf_map *map, void *key, - void *value, u64 flags) -{ - struct socket *sock; - struct sock *sk; - int ret; - u64 ufd; - - if (map->value_size == sizeof(u64)) - ufd = *(u64 *)value; - else - ufd = *(u32 *)value; - if (ufd > S32_MAX) - return -EINVAL; - - sock = sockfd_lookup(ufd, &ret); - if (!sock) - return ret; - sk = sock->sk; - if (!sk) { - ret = -EINVAL; - goto out; - } - if (!sock_map_sk_is_suitable(sk)) { - ret = -EOPNOTSUPP; - goto out; - } - - sock_map_sk_acquire(sk); - if (!sock_map_sk_state_allowed(sk)) - ret = -EOPNOTSUPP; - else - ret = sock_hash_update_common(map, key, sk, flags); - sock_map_sk_release(sk); -out: - fput(sock->file); - return ret; -} - static int sock_hash_get_next_key(struct bpf_map *map, void *key, void *key_next) { @@ -971,7 +1076,7 @@ static int sock_hash_get_next_key(struct bpf_map *map, void *key, if (!elem) goto find_first_elem; - elem_next = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&elem->node)), + elem_next = hlist_entry_safe(rcu_dereference(hlist_next_rcu(&elem->node)), struct bpf_shtab_elem, node); if (elem_next) { memcpy(key_next, elem_next->key, key_size); @@ -983,7 +1088,7 @@ static int sock_hash_get_next_key(struct bpf_map *map, void *key, find_first_elem: for (; i < htab->buckets_num; i++) { head = &sock_hash_select_bucket(htab, i)->head; - elem_next = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)), + elem_next = hlist_entry_safe(rcu_dereference(hlist_first_rcu(head)), struct bpf_shtab_elem, node); if (elem_next) { memcpy(key_next, elem_next->key, key_size); @@ -1119,7 +1224,7 @@ static void *sock_hash_lookup_sys(struct bpf_map *map, void *key) if (!sk) return ERR_PTR(-ENOENT); - sock_gen_cookie(sk); + __sock_gen_cookie(sk); return &sk->sk_cookie; } @@ -1128,7 +1233,7 @@ static void *sock_hash_lookup(struct bpf_map *map, void *key) struct sock *sk; sk = __sock_hash_lookup_elem(map, key); - if (!sk || !sk_fullsock(sk)) + if (!sk) return NULL; if (sk_is_refcounted(sk) && !refcount_inc_not_zero(&sk->sk_refcnt)) return NULL; @@ -1217,12 +1322,128 @@ const struct bpf_func_proto bpf_msg_redirect_hash_proto = { .arg4_type = ARG_ANYTHING, }; +struct sock_hash_seq_info { + struct bpf_map *map; + struct bpf_shtab *htab; + u32 bucket_id; +}; + +static void *sock_hash_seq_find_next(struct sock_hash_seq_info *info, + struct bpf_shtab_elem *prev_elem) +{ + const struct bpf_shtab *htab = info->htab; + struct bpf_shtab_bucket *bucket; + struct bpf_shtab_elem *elem; + struct hlist_node *node; + + /* try to find next elem in the same bucket */ + if (prev_elem) { + node = rcu_dereference(hlist_next_rcu(&prev_elem->node)); + elem = hlist_entry_safe(node, struct bpf_shtab_elem, node); + if (elem) + return elem; + + /* no more elements, continue in the next bucket */ + info->bucket_id++; + } + + for (; info->bucket_id < htab->buckets_num; info->bucket_id++) { + bucket = &htab->buckets[info->bucket_id]; + node = rcu_dereference(hlist_first_rcu(&bucket->head)); + elem = hlist_entry_safe(node, struct bpf_shtab_elem, node); + if (elem) + return elem; + } + + return NULL; +} + +static void *sock_hash_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(rcu) +{ + struct sock_hash_seq_info *info = seq->private; + + if (*pos == 0) + ++*pos; + + /* pairs with sock_hash_seq_stop */ + rcu_read_lock(); + return sock_hash_seq_find_next(info, NULL); +} + +static void *sock_hash_seq_next(struct seq_file *seq, void *v, loff_t *pos) + __must_hold(rcu) +{ + struct sock_hash_seq_info *info = seq->private; + + ++*pos; + return sock_hash_seq_find_next(info, v); +} + +static int sock_hash_seq_show(struct seq_file *seq, void *v) + __must_hold(rcu) +{ + struct sock_hash_seq_info *info = seq->private; + struct bpf_iter__sockmap ctx = {}; + struct bpf_shtab_elem *elem = v; + struct bpf_iter_meta meta; + struct bpf_prog *prog; + + meta.seq = seq; + prog = bpf_iter_get_info(&meta, !elem); + if (!prog) + return 0; + + ctx.meta = &meta; + ctx.map = info->map; + if (elem) { + ctx.key = elem->key; + ctx.sk = elem->sk; + } + + return bpf_iter_run_prog(prog, &ctx); +} + +static void sock_hash_seq_stop(struct seq_file *seq, void *v) + __releases(rcu) +{ + if (!v) + (void)sock_hash_seq_show(seq, NULL); + + /* pairs with sock_hash_seq_start */ + rcu_read_unlock(); +} + +static const struct seq_operations sock_hash_seq_ops = { + .start = sock_hash_seq_start, + .next = sock_hash_seq_next, + .stop = sock_hash_seq_stop, + .show = sock_hash_seq_show, +}; + +static int sock_hash_init_seq_private(void *priv_data, + struct bpf_iter_aux_info *aux) +{ + struct sock_hash_seq_info *info = priv_data; + + info->map = aux->map; + info->htab = container_of(aux->map, struct bpf_shtab, map); + return 0; +} + +static const struct bpf_iter_seq_info sock_hash_iter_seq_info = { + .seq_ops = &sock_hash_seq_ops, + .init_seq_private = sock_hash_init_seq_private, + .seq_priv_size = sizeof(struct sock_hash_seq_info), +}; + static int sock_hash_map_btf_id; const struct bpf_map_ops sock_hash_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc = sock_hash_alloc, .map_free = sock_hash_free, .map_get_next_key = sock_hash_get_next_key, - .map_update_elem = sock_hash_update_elem, + .map_update_elem = sock_map_update_elem, .map_delete_elem = sock_hash_delete_elem, .map_lookup_elem = sock_hash_lookup, .map_lookup_elem_sys_only = sock_hash_lookup_sys, @@ -1230,6 +1451,7 @@ const struct bpf_map_ops sock_hash_ops = { .map_check_btf = map_check_no_btf, .map_btf_name = "bpf_shtab", .map_btf_id = &sock_hash_map_btf_id, + .iter_seq_info = &sock_hash_iter_seq_info, }; static struct sk_psock_progs *sock_map_progs(struct bpf_map *map) @@ -1340,3 +1562,62 @@ void sock_map_close(struct sock *sk, long timeout) release_sock(sk); saved_close(sk, timeout); } + +static int sock_map_iter_attach_target(struct bpf_prog *prog, + union bpf_iter_link_info *linfo, + struct bpf_iter_aux_info *aux) +{ + struct bpf_map *map; + int err = -EINVAL; + + if (!linfo->map.map_fd) + return -EBADF; + + map = bpf_map_get_with_uref(linfo->map.map_fd); + if (IS_ERR(map)) + return PTR_ERR(map); + + if (map->map_type != BPF_MAP_TYPE_SOCKMAP && + map->map_type != BPF_MAP_TYPE_SOCKHASH) + goto put_map; + + if (prog->aux->max_rdonly_access > map->key_size) { + err = -EACCES; + goto put_map; + } + + aux->map = map; + return 0; + +put_map: + bpf_map_put_with_uref(map); + return err; +} + +static void sock_map_iter_detach_target(struct bpf_iter_aux_info *aux) +{ + bpf_map_put_with_uref(aux->map); +} + +static struct bpf_iter_reg sock_map_iter_reg = { + .target = "sockmap", + .attach_target = sock_map_iter_attach_target, + .detach_target = sock_map_iter_detach_target, + .show_fdinfo = bpf_iter_map_show_fdinfo, + .fill_link_info = bpf_iter_map_fill_link_info, + .ctx_arg_info_size = 2, + .ctx_arg_info = { + { offsetof(struct bpf_iter__sockmap, key), + PTR_TO_RDONLY_BUF_OR_NULL }, + { offsetof(struct bpf_iter__sockmap, sk), + PTR_TO_BTF_ID_OR_NULL }, + }, +}; + +static int __init bpf_sockmap_iter_init(void) +{ + sock_map_iter_reg.ctx_arg_info[1].btf_id = + btf_sock_ids[BTF_SOCK_TYPE_SOCK]; + return bpf_iter_reg_target(&sock_map_iter_reg); +} +late_initcall(bpf_sockmap_iter_init); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 6ada114bbcca..d86d8d11cfe4 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -22,7 +22,7 @@ #include <net/busy_poll.h> #include <net/pkt_sched.h> -static int two __maybe_unused = 2; +static int two = 2; static int three = 3; static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; @@ -546,7 +546,7 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, + .extra2 = &two, }, { .procname = "devconf_inherit_init_net", @@ -587,6 +587,19 @@ static struct ctl_table netns_core_table[] = { { } }; +static int __init fb_tunnels_only_for_init_net_sysctl_setup(char *str) +{ + /* fallback tunnels for initns only */ + if (!strncmp(str, "initns", 6)) + sysctl_fb_tunnels_only_for_init_net = 1; + /* no fallback tunnels anywhere */ + else if (!strncmp(str, "none", 4)) + sysctl_fb_tunnels_only_for_init_net = 2; + + return 1; +} +__setup("fb_tunnels=", fb_tunnels_only_for_init_net_sysctl_setup); + static __net_init int sysctl_core_net_init(struct net *net) { struct ctl_table *tbl; diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index 0a72510d5de1..8f3dd3b1d2d0 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -274,7 +274,7 @@ void dccp_ackvec_input(struct dccp_ackvec *av, struct sk_buff *skb) /** * dccp_ackvec_clear_state - Perform house-keeping / garbage-collection * This routine is called when the peer acknowledges the receipt of Ack Vectors - * up to and including @ackno. While based on on section A.3 of RFC 4340, here + * up to and including @ackno. While based on section A.3 of RFC 4340, here * are additional precautions to prevent corrupted buffer state. In particular, * we use tail_ackno to identify outdated records; it always marks the earliest * packet of group (2) in 11.4.2. diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 9c28c8251125..bb3d70664dde 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -495,7 +495,8 @@ static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req rcu_read_lock(); err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, - rcu_dereference(ireq->ireq_opt)); + rcu_dereference(ireq->ireq_opt), + inet_sk(sk)->tos); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -537,7 +538,8 @@ static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) local_bh_disable(); bh_lock_sock(ctl_sk); err = ip_build_and_send_pkt(skb, ctl_sk, - rxiph->daddr, rxiph->saddr, NULL); + rxiph->daddr, rxiph->saddr, NULL, + inet_sk(ctl_sk)->tos); bh_unlock_sock(ctl_sk); if (net_xmit_eval(err) == 0) { @@ -731,7 +733,7 @@ int dccp_invalid_packet(struct sk_buff *skb) return 1; } /* - * If P.Data Offset is too too large for packet, drop packet and return + * If P.Data Offset is too large for packet, drop packet and return */ if (!pskb_may_pull(skb, dccph_doff * sizeof(u32))) { DCCP_WARN("P.Data Offset(%u) too large\n", dccph_doff); diff --git a/net/dccp/timer.c b/net/dccp/timer.c index 0e06dfc32273..a934d2932373 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -85,7 +85,7 @@ static void dccp_retransmit_timer(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); /* - * More than than 4MSL (8 minutes) has passed, a RESET(aborted) was + * More than 4MSL (8 minutes) has passed, a RESET(aborted) was * sent, no need to retransmit, this sock is dead. */ if (dccp_write_timeout(sk)) @@ -176,7 +176,6 @@ static void dccp_delack_timer(struct timer_list *t) bh_lock_sock(sk); if (sock_owned_by_user(sk)) { /* Try again later. */ - icsk->icsk_ack.blocked = 1; __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED); sk_reset_timer(sk, &icsk->icsk_delack_timer, jiffies + TCP_DELACK_MIN); diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 1ce9ba8cf545..2131bf2b3a67 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -225,6 +225,15 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, skb->dev); + if (unlikely(cpu_dp->ds->untag_bridge_pvid)) { + nskb = dsa_untag_bridge_pvid(skb); + if (!nskb) { + kfree_skb(skb); + return 0; + } + skb = nskb; + } + s = this_cpu_ptr(p->stats64); u64_stats_update_begin(&s->syncp); s->rx_packets++; @@ -330,11 +339,7 @@ EXPORT_SYMBOL_GPL(call_dsa_notifiers); int dsa_devlink_param_get(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx) { - struct dsa_devlink_priv *dl_priv; - struct dsa_switch *ds; - - dl_priv = devlink_priv(dl); - ds = dl_priv->ds; + struct dsa_switch *ds = dsa_devlink_to_ds(dl); if (!ds->ops->devlink_param_get) return -EOPNOTSUPP; @@ -346,11 +351,7 @@ EXPORT_SYMBOL_GPL(dsa_devlink_param_get); int dsa_devlink_param_set(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx) { - struct dsa_devlink_priv *dl_priv; - struct dsa_switch *ds; - - dl_priv = devlink_priv(dl); - ds = dl_priv->ds; + struct dsa_switch *ds = dsa_devlink_to_ds(dl); if (!ds->ops->devlink_param_set) return -EOPNOTSUPP; @@ -412,6 +413,36 @@ void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds, } EXPORT_SYMBOL_GPL(dsa_devlink_resource_occ_get_unregister); +struct devlink_region * +dsa_devlink_region_create(struct dsa_switch *ds, + const struct devlink_region_ops *ops, + u32 region_max_snapshots, u64 region_size) +{ + return devlink_region_create(ds->devlink, ops, region_max_snapshots, + region_size); +} +EXPORT_SYMBOL_GPL(dsa_devlink_region_create); + +struct devlink_region * +dsa_devlink_port_region_create(struct dsa_switch *ds, + int port, + const struct devlink_port_region_ops *ops, + u32 region_max_snapshots, u64 region_size) +{ + struct dsa_port *dp = dsa_to_port(ds, port); + + return devlink_port_region_create(&dp->devlink_port, ops, + region_max_snapshots, + region_size); +} +EXPORT_SYMBOL_GPL(dsa_devlink_port_region_create); + +void dsa_devlink_region_destroy(struct devlink_region *region) +{ + devlink_region_destroy(region); +} +EXPORT_SYMBOL_GPL(dsa_devlink_region_destroy); + struct dsa_port *dsa_port_from_netdev(struct net_device *netdev) { if (!netdev || !dsa_slave_dev_check(netdev)) diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index c0ffc7a2b65f..183003e45762 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -21,9 +21,6 @@ static DEFINE_MUTEX(dsa2_mutex); LIST_HEAD(dsa_tree_list); -static const struct devlink_ops dsa_devlink_ops = { -}; - struct dsa_switch *dsa_switch_find(int tree_index, int sw_index) { struct dsa_switch_tree *dst; @@ -254,22 +251,11 @@ static void dsa_tree_teardown_default_cpu(struct dsa_switch_tree *dst) static int dsa_port_setup(struct dsa_port *dp) { - struct dsa_switch *ds = dp->ds; - struct dsa_switch_tree *dst = ds->dst; - const unsigned char *id = (const unsigned char *)&dst->index; - const unsigned char len = sizeof(dst->index); struct devlink_port *dlp = &dp->devlink_port; bool dsa_port_link_registered = false; - bool devlink_port_registered = false; - struct devlink_port_attrs attrs = {}; - struct devlink *dl = ds->devlink; bool dsa_port_enabled = false; int err = 0; - attrs.phys.port_number = dp->index; - memcpy(attrs.switch_id.id, id, len); - attrs.switch_id.id_len = len; - if (dp->setup) return 0; @@ -278,14 +264,6 @@ static int dsa_port_setup(struct dsa_port *dp) dsa_port_disable(dp); break; case DSA_PORT_TYPE_CPU: - memset(dlp, 0, sizeof(*dlp)); - attrs.flavour = DEVLINK_PORT_FLAVOUR_CPU; - devlink_port_attrs_set(dlp, &attrs); - err = devlink_port_register(dl, dlp, dp->index); - if (err) - break; - devlink_port_registered = true; - err = dsa_port_link_register_of(dp); if (err) break; @@ -298,14 +276,6 @@ static int dsa_port_setup(struct dsa_port *dp) break; case DSA_PORT_TYPE_DSA: - memset(dlp, 0, sizeof(*dlp)); - attrs.flavour = DEVLINK_PORT_FLAVOUR_DSA; - devlink_port_attrs_set(dlp, &attrs); - err = devlink_port_register(dl, dlp, dp->index); - if (err) - break; - devlink_port_registered = true; - err = dsa_port_link_register_of(dp); if (err) break; @@ -318,14 +288,6 @@ static int dsa_port_setup(struct dsa_port *dp) break; case DSA_PORT_TYPE_USER: - memset(dlp, 0, sizeof(*dlp)); - attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; - devlink_port_attrs_set(dlp, &attrs); - err = devlink_port_register(dl, dlp, dp->index); - if (err) - break; - devlink_port_registered = true; - dp->mac = of_get_mac_address(dp->dn); err = dsa_slave_create(dp); if (err) @@ -339,8 +301,6 @@ static int dsa_port_setup(struct dsa_port *dp) dsa_port_disable(dp); if (err && dsa_port_link_registered) dsa_port_link_unregister_of(dp); - if (err && devlink_port_registered) - devlink_port_unregister(dlp); if (err) return err; @@ -349,10 +309,50 @@ static int dsa_port_setup(struct dsa_port *dp) return 0; } -static void dsa_port_teardown(struct dsa_port *dp) +static int dsa_port_devlink_setup(struct dsa_port *dp) { struct devlink_port *dlp = &dp->devlink_port; + struct dsa_switch_tree *dst = dp->ds->dst; + struct devlink_port_attrs attrs = {}; + struct devlink *dl = dp->ds->devlink; + const unsigned char *id; + unsigned char len; + int err; + + id = (const unsigned char *)&dst->index; + len = sizeof(dst->index); + attrs.phys.port_number = dp->index; + memcpy(attrs.switch_id.id, id, len); + attrs.switch_id.id_len = len; + memset(dlp, 0, sizeof(*dlp)); + + switch (dp->type) { + case DSA_PORT_TYPE_UNUSED: + attrs.flavour = DEVLINK_PORT_FLAVOUR_UNUSED; + break; + case DSA_PORT_TYPE_CPU: + attrs.flavour = DEVLINK_PORT_FLAVOUR_CPU; + break; + case DSA_PORT_TYPE_DSA: + attrs.flavour = DEVLINK_PORT_FLAVOUR_DSA; + break; + case DSA_PORT_TYPE_USER: + attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; + break; + } + + devlink_port_attrs_set(dlp, &attrs); + err = devlink_port_register(dl, dlp, dp->index); + + if (!err) + dp->devlink_port_setup = true; + + return err; +} + +static void dsa_port_teardown(struct dsa_port *dp) +{ if (!dp->setup) return; @@ -362,16 +362,13 @@ static void dsa_port_teardown(struct dsa_port *dp) case DSA_PORT_TYPE_CPU: dsa_port_disable(dp); dsa_tag_driver_put(dp->tag_ops); - devlink_port_unregister(dlp); dsa_port_link_unregister_of(dp); break; case DSA_PORT_TYPE_DSA: dsa_port_disable(dp); - devlink_port_unregister(dlp); dsa_port_link_unregister_of(dp); break; case DSA_PORT_TYPE_USER: - devlink_port_unregister(dlp); if (dp->slave) { dsa_slave_destroy(dp->slave); dp->slave = NULL; @@ -382,9 +379,35 @@ static void dsa_port_teardown(struct dsa_port *dp) dp->setup = false; } +static void dsa_port_devlink_teardown(struct dsa_port *dp) +{ + struct devlink_port *dlp = &dp->devlink_port; + + if (dp->devlink_port_setup) + devlink_port_unregister(dlp); + dp->devlink_port_setup = false; +} + +static int dsa_devlink_info_get(struct devlink *dl, + struct devlink_info_req *req, + struct netlink_ext_ack *extack) +{ + struct dsa_switch *ds = dsa_devlink_to_ds(dl); + + if (ds->ops->devlink_info_get) + return ds->ops->devlink_info_get(ds, req, extack); + + return -EOPNOTSUPP; +} + +static const struct devlink_ops dsa_devlink_ops = { + .info_get = dsa_devlink_info_get, +}; + static int dsa_switch_setup(struct dsa_switch *ds) { struct dsa_devlink_priv *dl_priv; + struct dsa_port *dp; int err; if (ds->setup) @@ -410,9 +433,20 @@ static int dsa_switch_setup(struct dsa_switch *ds) if (err) goto free_devlink; + /* Setup devlink port instances now, so that the switch + * setup() can register regions etc, against the ports + */ + list_for_each_entry(dp, &ds->dst->ports, list) { + if (dp->ds == ds) { + err = dsa_port_devlink_setup(dp); + if (err) + goto unregister_devlink_ports; + } + } + err = dsa_switch_register_notifier(ds); if (err) - goto unregister_devlink; + goto unregister_devlink_ports; err = ds->ops->setup(ds); if (err < 0) @@ -440,7 +474,10 @@ static int dsa_switch_setup(struct dsa_switch *ds) unregister_notifier: dsa_switch_unregister_notifier(ds); -unregister_devlink: +unregister_devlink_ports: + list_for_each_entry(dp, &ds->dst->ports, list) + if (dp->ds == ds) + dsa_port_devlink_teardown(dp); devlink_unregister(ds->devlink); free_devlink: devlink_free(ds->devlink); @@ -451,6 +488,8 @@ free_devlink: static void dsa_switch_teardown(struct dsa_switch *ds) { + struct dsa_port *dp; + if (!ds->setup) return; @@ -463,6 +502,9 @@ static void dsa_switch_teardown(struct dsa_switch *ds) ds->ops->teardown(ds); if (ds->devlink) { + list_for_each_entry(dp, &ds->dst->ports, list) + if (dp->ds == ds) + dsa_port_devlink_teardown(dp); devlink_unregister(ds->devlink); devlink_free(ds->devlink); ds->devlink = NULL; diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 1653e3377cb3..12998bf04e55 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -7,6 +7,7 @@ #ifndef __DSA_PRIV_H #define __DSA_PRIV_H +#include <linux/if_bridge.h> #include <linux/phy.h> #include <linux/netdevice.h> #include <linux/netpoll.h> @@ -164,8 +165,6 @@ int dsa_port_vlan_add(struct dsa_port *dp, struct switchdev_trans *trans); int dsa_port_vlan_del(struct dsa_port *dp, const struct switchdev_obj_port_vlan *vlan); -int dsa_port_vid_add(struct dsa_port *dp, u16 vid, u16 flags); -int dsa_port_vid_del(struct dsa_port *dp, u16 vid); int dsa_port_link_register_of(struct dsa_port *dp); void dsa_port_link_unregister_of(struct dsa_port *dp); extern const struct phylink_mac_ops dsa_port_phylink_mac_ops; @@ -196,6 +195,65 @@ dsa_slave_to_master(const struct net_device *dev) return dp->cpu_dp->master; } +/* If under a bridge with vlan_filtering=0, make sure to send pvid-tagged + * frames as untagged, since the bridge will not untag them. + */ +static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb) +{ + struct dsa_port *dp = dsa_slave_to_port(skb->dev); + struct net_device *br = dp->bridge_dev; + struct net_device *dev = skb->dev; + struct net_device *upper_dev; + u16 vid, pvid, proto; + int err; + + if (!br || br_vlan_enabled(br)) + return skb; + + err = br_vlan_get_proto(br, &proto); + if (err) + return skb; + + /* Move VLAN tag from data to hwaccel */ + if (!skb_vlan_tag_present(skb) && skb->protocol == htons(proto)) { + skb = skb_vlan_untag(skb); + if (!skb) + return NULL; + } + + if (!skb_vlan_tag_present(skb)) + return skb; + + vid = skb_vlan_tag_get_id(skb); + + /* We already run under an RCU read-side critical section since + * we are called from netif_receive_skb_list_internal(). + */ + err = br_vlan_get_pvid_rcu(dev, &pvid); + if (err) + return skb; + + if (vid != pvid) + return skb; + + /* The sad part about attempting to untag from DSA is that we + * don't know, unless we check, if the skb will end up in + * the bridge's data path - br_allowed_ingress() - or not. + * For example, there might be an 8021q upper for the + * default_pvid of the bridge, which will steal VLAN-tagged traffic + * from the bridge's data path. This is a configuration that DSA + * supports because vlan_filtering is 0. In that case, we should + * definitely keep the tag, to make sure it keeps working. + */ + upper_dev = __vlan_find_dev_deep_rcu(br, htons(proto), vid); + if (upper_dev) + return skb; + + __vlan_hwaccel_clear_tag(skb); + + return skb; +} + /* switch.c */ int dsa_switch_register_notifier(struct dsa_switch *ds); void dsa_switch_unregister_notifier(struct dsa_switch *ds); diff --git a/net/dsa/master.c b/net/dsa/master.c index 61615ebc70e9..c91de041a91d 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -259,6 +259,18 @@ static void dsa_netdev_ops_set(struct net_device *dev, dev->dsa_ptr->netdev_ops = ops; } +static void dsa_master_set_promiscuity(struct net_device *dev, int inc) +{ + const struct dsa_device_ops *ops = dev->dsa_ptr->tag_ops; + + if (!ops->promisc_on_master) + return; + + rtnl_lock(); + dev_set_promiscuity(dev, inc); + rtnl_unlock(); +} + static ssize_t tagging_show(struct device *d, struct device_attribute *attr, char *buf) { @@ -314,9 +326,12 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) dev->dsa_ptr = cpu_dp; lockdep_set_class(&dev->addr_list_lock, &dsa_master_addr_list_lock_key); + + dsa_master_set_promiscuity(dev, 1); + ret = dsa_master_ethtool_setup(dev); if (ret) - return ret; + goto out_err_reset_promisc; dsa_netdev_ops_set(dev, &dsa_netdev_ops); @@ -329,6 +344,8 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) out_err_ndo_teardown: dsa_netdev_ops_set(dev, NULL); dsa_master_ethtool_teardown(dev); +out_err_reset_promisc: + dsa_master_set_promiscuity(dev, -1); return ret; } @@ -338,6 +355,7 @@ void dsa_master_teardown(struct net_device *dev) dsa_netdev_ops_set(dev, NULL); dsa_master_ethtool_teardown(dev); dsa_master_reset_mtu(dev); + dsa_master_set_promiscuity(dev, -1); dev->dsa_ptr = NULL; diff --git a/net/dsa/port.c b/net/dsa/port.c index e23ece229c7e..73569c9af3cc 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -193,11 +193,44 @@ void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br) dsa_port_set_state_now(dp, BR_STATE_FORWARDING); } +/* Must be called under rcu_read_lock() */ static bool dsa_port_can_apply_vlan_filtering(struct dsa_port *dp, bool vlan_filtering) { struct dsa_switch *ds = dp->ds; - int i; + int err, i; + + /* VLAN awareness was off, so the question is "can we turn it on". + * We may have had 8021q uppers, those need to go. Make sure we don't + * enter an inconsistent state: deny changing the VLAN awareness state + * as long as we have 8021q uppers. + */ + if (vlan_filtering && dsa_is_user_port(ds, dp->index)) { + struct net_device *upper_dev, *slave = dp->slave; + struct net_device *br = dp->bridge_dev; + struct list_head *iter; + + netdev_for_each_upper_dev_rcu(slave, upper_dev, iter) { + struct bridge_vlan_info br_info; + u16 vid; + + if (!is_vlan_dev(upper_dev)) + continue; + + vid = vlan_dev_vlan_id(upper_dev); + + /* br_vlan_get_info() returns -EINVAL or -ENOENT if the + * device, respectively the VID is not found, returning + * 0 means success, which is a failure for us here. + */ + err = br_vlan_get_info(br, vid, &br_info); + if (err == 0) { + dev_err(ds->dev, "Must remove upper %s first\n", + upper_dev->name); + return false; + } + } + } if (!ds->vlan_filtering_is_global) return true; @@ -232,28 +265,38 @@ int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, struct dsa_switch *ds = dp->ds; int err; - /* bridge skips -EOPNOTSUPP, so skip the prepare phase */ - if (switchdev_trans_ph_prepare(trans)) - return 0; + if (switchdev_trans_ph_prepare(trans)) { + bool apply; - if (!ds->ops->port_vlan_filtering) - return 0; + if (!ds->ops->port_vlan_filtering) + return -EOPNOTSUPP; - if (!dsa_port_can_apply_vlan_filtering(dp, vlan_filtering)) - return -EINVAL; + /* We are called from dsa_slave_switchdev_blocking_event(), + * which is not under rcu_read_lock(), unlike + * dsa_slave_switchdev_event(). + */ + rcu_read_lock(); + apply = dsa_port_can_apply_vlan_filtering(dp, vlan_filtering); + rcu_read_unlock(); + if (!apply) + return -EINVAL; + } if (dsa_port_is_vlan_filtering(dp) == vlan_filtering) return 0; - err = ds->ops->port_vlan_filtering(ds, dp->index, - vlan_filtering); + err = ds->ops->port_vlan_filtering(ds, dp->index, vlan_filtering, + trans); if (err) return err; - if (ds->vlan_filtering_is_global) - ds->vlan_filtering = vlan_filtering; - else - dp->vlan_filtering = vlan_filtering; + if (switchdev_trans_ph_commit(trans)) { + if (ds->vlan_filtering_is_global) + ds->vlan_filtering = vlan_filtering; + else + dp->vlan_filtering = vlan_filtering; + } + return 0; } @@ -433,39 +476,6 @@ int dsa_port_vlan_del(struct dsa_port *dp, return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_DEL, &info); } -int dsa_port_vid_add(struct dsa_port *dp, u16 vid, u16 flags) -{ - struct switchdev_obj_port_vlan vlan = { - .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, - .flags = flags, - .vid_begin = vid, - .vid_end = vid, - }; - struct switchdev_trans trans; - int err; - - trans.ph_prepare = true; - err = dsa_port_vlan_add(dp, &vlan, &trans); - if (err) - return err; - - trans.ph_prepare = false; - return dsa_port_vlan_add(dp, &vlan, &trans); -} -EXPORT_SYMBOL(dsa_port_vid_add); - -int dsa_port_vid_del(struct dsa_port *dp, u16 vid) -{ - struct switchdev_obj_port_vlan vlan = { - .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, - .vid_begin = vid, - .vid_end = vid, - }; - - return dsa_port_vlan_del(dp, &vlan); -} -EXPORT_SYMBOL(dsa_port_vid_del); - static struct phy_device *dsa_port_get_phy_device(struct dsa_port *dp) { struct device_node *phy_dn; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 16e5f98d4882..3bc5ca40c9fb 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -303,13 +303,36 @@ static int dsa_slave_port_attr_set(struct net_device *dev, return ret; } +/* Must be called under rcu_read_lock() */ +static int +dsa_slave_vlan_check_for_8021q_uppers(struct net_device *slave, + const struct switchdev_obj_port_vlan *vlan) +{ + struct net_device *upper_dev; + struct list_head *iter; + + netdev_for_each_upper_dev_rcu(slave, upper_dev, iter) { + u16 vid; + + if (!is_vlan_dev(upper_dev)) + continue; + + vid = vlan_dev_vlan_id(upper_dev); + if (vid >= vlan->vid_begin && vid <= vlan->vid_end) + return -EBUSY; + } + + return 0; +} + static int dsa_slave_vlan_add(struct net_device *dev, const struct switchdev_obj *obj, struct switchdev_trans *trans) { + struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); struct switchdev_obj_port_vlan vlan; - int err; + int vid, err; if (obj->orig_dev != dev) return -EOPNOTSUPP; @@ -319,6 +342,17 @@ static int dsa_slave_vlan_add(struct net_device *dev, vlan = *SWITCHDEV_OBJ_PORT_VLAN(obj); + /* Deny adding a bridge VLAN when there is already an 802.1Q upper with + * the same VID. + */ + if (trans->ph_prepare && br_vlan_enabled(dp->bridge_dev)) { + rcu_read_lock(); + err = dsa_slave_vlan_check_for_8021q_uppers(dev, &vlan); + rcu_read_unlock(); + if (err) + return err; + } + err = dsa_port_vlan_add(dp, &vlan, trans); if (err) return err; @@ -333,6 +367,12 @@ static int dsa_slave_vlan_add(struct net_device *dev, if (err) return err; + for (vid = vlan.vid_begin; vid <= vlan.vid_end; vid++) { + err = vlan_vid_add(master, htons(ETH_P_8021Q), vid); + if (err) + return err; + } + return 0; } @@ -376,7 +416,10 @@ static int dsa_slave_port_obj_add(struct net_device *dev, static int dsa_slave_vlan_del(struct net_device *dev, const struct switchdev_obj *obj) { + struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); + struct switchdev_obj_port_vlan *vlan; + int vid, err; if (obj->orig_dev != dev) return -EOPNOTSUPP; @@ -384,10 +427,19 @@ static int dsa_slave_vlan_del(struct net_device *dev, if (dsa_port_skip_vlan_configuration(dp)) return 0; + vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); + /* Do not deprogram the CPU port as it may be shared with other user * ports which can be members of this VLAN as well. */ - return dsa_port_vlan_del(dp, SWITCHDEV_OBJ_PORT_VLAN(obj)); + err = dsa_port_vlan_del(dp, vlan); + if (err) + return err; + + for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) + vlan_vid_del(master, htons(ETH_P_8021Q), vid); + + return 0; } static int dsa_slave_port_obj_del(struct net_device *dev, @@ -1169,28 +1221,9 @@ static void dsa_slave_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct dsa_slave_priv *p = netdev_priv(dev); - struct pcpu_sw_netstats *s; - unsigned int start; - int i; netdev_stats_to_stats64(stats, &dev->stats); - for_each_possible_cpu(i) { - u64 tx_packets, tx_bytes, rx_packets, rx_bytes; - - s = per_cpu_ptr(p->stats64, i); - do { - start = u64_stats_fetch_begin_irq(&s->syncp); - tx_packets = s->tx_packets; - tx_bytes = s->tx_bytes; - rx_packets = s->rx_packets; - rx_bytes = s->rx_bytes; - } while (u64_stats_fetch_retry_irq(&s->syncp, start)); - - stats->tx_packets += tx_packets; - stats->tx_bytes += tx_bytes; - stats->rx_packets += rx_packets; - stats->rx_bytes += rx_bytes; - } + dev_fetch_sw_netstats(stats, p->stats64); } static int dsa_slave_get_rxnfc(struct net_device *dev, @@ -1232,64 +1265,66 @@ static int dsa_slave_get_ts_info(struct net_device *dev, static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { + struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); - struct bridge_vlan_info info; + struct switchdev_obj_port_vlan vlan = { + .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, + .vid_begin = vid, + .vid_end = vid, + /* This API only allows programming tagged, non-PVID VIDs */ + .flags = 0, + }; + struct switchdev_trans trans; int ret; - /* Check for a possible bridge VLAN entry now since there is no - * need to emulate the switchdev prepare + commit phase. - */ - if (dp->bridge_dev) { - if (dsa_port_skip_vlan_configuration(dp)) - return 0; + /* User port... */ + trans.ph_prepare = true; + ret = dsa_port_vlan_add(dp, &vlan, &trans); + if (ret) + return ret; - /* br_vlan_get_info() returns -EINVAL or -ENOENT if the - * device, respectively the VID is not found, returning - * 0 means success, which is a failure for us here. - */ - ret = br_vlan_get_info(dp->bridge_dev, vid, &info); - if (ret == 0) - return -EBUSY; - } + trans.ph_prepare = false; + ret = dsa_port_vlan_add(dp, &vlan, &trans); + if (ret) + return ret; - ret = dsa_port_vid_add(dp, vid, 0); + /* And CPU port... */ + trans.ph_prepare = true; + ret = dsa_port_vlan_add(dp->cpu_dp, &vlan, &trans); if (ret) return ret; - ret = dsa_port_vid_add(dp->cpu_dp, vid, 0); + trans.ph_prepare = false; + ret = dsa_port_vlan_add(dp->cpu_dp, &vlan, &trans); if (ret) return ret; - return 0; + return vlan_vid_add(master, proto, vid); } static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { + struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); - struct bridge_vlan_info info; - int ret; - - /* Check for a possible bridge VLAN entry now since there is no - * need to emulate the switchdev prepare + commit phase. - */ - if (dp->bridge_dev) { - if (dsa_port_skip_vlan_configuration(dp)) - return 0; - - /* br_vlan_get_info() returns -EINVAL or -ENOENT if the - * device, respectively the VID is not found, returning - * 0 means success, which is a failure for us here. - */ - ret = br_vlan_get_info(dp->bridge_dev, vid, &info); - if (ret == 0) - return -EBUSY; - } + struct switchdev_obj_port_vlan vlan = { + .vid_begin = vid, + .vid_end = vid, + /* This API only allows programming tagged, non-PVID VIDs */ + .flags = 0, + }; + int err; /* Do not deprogram the CPU port as it may be shared with other user * ports which can be members of this VLAN as well. */ - return dsa_port_vid_del(dp, vid); + err = dsa_port_vlan_del(dp, &vlan); + if (err) + return err; + + vlan_vid_del(master, proto, vid); + + return 0; } struct dsa_hw_port { @@ -1784,7 +1819,7 @@ int dsa_slave_create(struct dsa_port *port) rtnl_lock(); ret = dsa_slave_change_mtu(slave_dev, ETH_DATA_LEN); rtnl_unlock(); - if (ret) + if (ret && ret != -EOPNOTSUPP) dev_warn(ds->dev, "nonfatal error %d setting MTU on port %d\n", ret, port->index); @@ -1792,8 +1827,9 @@ int dsa_slave_create(struct dsa_port *port) ret = dsa_slave_phy_setup(slave_dev); if (ret) { - netdev_err(master, "error %d setting up slave PHY for %s\n", - ret, slave_dev->name); + netdev_err(slave_dev, + "error %d setting up PHY for tree %d, switch %d, port %d\n", + ret, ds->dst->index, ds->index, port->index); goto out_gcells; } @@ -1880,9 +1916,9 @@ static int dsa_slave_changeupper(struct net_device *dev, return err; } -static int dsa_slave_upper_vlan_check(struct net_device *dev, - struct netdev_notifier_changeupper_info * - info) +static int +dsa_prevent_bridging_8021q_upper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *ext_ack; struct net_device *slave; @@ -1912,14 +1948,56 @@ static int dsa_slave_upper_vlan_check(struct net_device *dev, return NOTIFY_DONE; } +static int +dsa_slave_check_8021q_upper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct net_device *br = dp->bridge_dev; + struct bridge_vlan_info br_info; + struct netlink_ext_ack *extack; + int err = NOTIFY_DONE; + u16 vid; + + if (!br || !br_vlan_enabled(br)) + return NOTIFY_DONE; + + extack = netdev_notifier_info_to_extack(&info->info); + vid = vlan_dev_vlan_id(info->upper_dev); + + /* br_vlan_get_info() returns -EINVAL or -ENOENT if the + * device, respectively the VID is not found, returning + * 0 means success, which is a failure for us here. + */ + err = br_vlan_get_info(br, vid, &br_info); + if (err == 0) { + NL_SET_ERR_MSG_MOD(extack, + "This VLAN is already configured by the bridge"); + return notifier_from_errno(-EBUSY); + } + + return NOTIFY_DONE; +} + static int dsa_slave_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); - if (event == NETDEV_CHANGEUPPER) { + switch (event) { + case NETDEV_PRECHANGEUPPER: { + struct netdev_notifier_changeupper_info *info = ptr; + + if (!dsa_slave_dev_check(dev)) + return dsa_prevent_bridging_8021q_upper(dev, ptr); + + if (is_vlan_dev(info->upper_dev)) + return dsa_slave_check_8021q_upper(dev, ptr); + break; + } + case NETDEV_CHANGEUPPER: if (!dsa_slave_dev_check(dev)) - return dsa_slave_upper_vlan_check(dev, ptr); + return NOTIFY_DONE; return dsa_slave_changeupper(dev, ptr); } diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 86c8dc5c32a0..3fb362b6874e 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -139,8 +139,15 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, } } if (unset_vlan_filtering) { - struct switchdev_trans trans = {0}; + struct switchdev_trans trans; + trans.ph_prepare = true; + err = dsa_port_vlan_filtering(dsa_to_port(ds, info->port), + false, &trans); + if (err && err != EOPNOTSUPP) + return err; + + trans.ph_prepare = false; err = dsa_port_vlan_filtering(dsa_to_port(ds, info->port), false, &trans); if (err && err != EOPNOTSUPP) @@ -232,43 +239,6 @@ static int dsa_switch_mdb_del(struct dsa_switch *ds, return 0; } -static int dsa_port_vlan_device_check(struct net_device *vlan_dev, - int vlan_dev_vid, - void *arg) -{ - struct switchdev_obj_port_vlan *vlan = arg; - u16 vid; - - for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) { - if (vid == vlan_dev_vid) - return -EBUSY; - } - - return 0; -} - -static int dsa_port_vlan_check(struct dsa_switch *ds, int port, - const struct switchdev_obj_port_vlan *vlan) -{ - const struct dsa_port *dp = dsa_to_port(ds, port); - int err = 0; - - /* Device is not bridged, let it proceed with the VLAN device - * creation. - */ - if (!dp->bridge_dev) - return err; - - /* dsa_slave_vlan_rx_{add,kill}_vid() cannot use the prepare phase and - * already checks whether there is an overlapping bridge VLAN entry - * with the same VID, so here we only need to check that if we are - * adding a bridge VLAN entry there is not an overlapping VLAN device - * claiming that VID. - */ - return vlan_for_each(dp->slave, dsa_port_vlan_device_check, - (void *)vlan); -} - static bool dsa_switch_vlan_match(struct dsa_switch *ds, int port, struct dsa_notifier_vlan_info *info) { @@ -291,10 +261,6 @@ static int dsa_switch_vlan_prepare(struct dsa_switch *ds, for (port = 0; port < ds->num_ports; port++) { if (dsa_switch_vlan_match(ds, port, info)) { - err = dsa_port_vlan_check(ds, port, info->vlan); - if (err) - return err; - err = ds->ops->port_vlan_prepare(ds, port, info->vlan); if (err) return err; diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 780b2a15ac9b..8e3e8a5b8559 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -146,15 +146,15 @@ EXPORT_SYMBOL_GPL(vid_is_dsa_8021q); * 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_switch *ds, int port, u16 vid, +static int dsa_8021q_vid_apply(struct dsa_8021q_context *ctx, int port, u16 vid, u16 flags, bool enabled) { - struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_port *dp = dsa_to_port(ctx->ds, port); if (enabled) - return dsa_port_vid_add(dp, vid, flags); + return ctx->ops->vlan_add(ctx->ds, dp->index, vid, flags); - return dsa_port_vid_del(dp, vid); + return ctx->ops->vlan_del(ctx->ds, dp->index, vid); } /* RX VLAN tagging (left) and TX VLAN tagging (right) setup shown for a single @@ -209,25 +209,29 @@ static int dsa_8021q_vid_apply(struct dsa_switch *ds, int port, u16 vid, * +-+-----+-+-----+-+-----+-+-----+-+ +-+-----+-+-----+-+-----+-+-----+-+ * swp0 swp1 swp2 swp3 swp0 swp1 swp2 swp3 */ -int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int port, bool enabled) +static int dsa_8021q_setup_port(struct dsa_8021q_context *ctx, int port, + bool enabled) { - int upstream = dsa_upstream_port(ds, port); - u16 rx_vid = dsa_8021q_rx_vid(ds, port); - u16 tx_vid = dsa_8021q_tx_vid(ds, port); - int i, err; + 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 net_device *master; + int i, err, subvlan; /* The CPU port is implicitly configured by * configuring the front-panel ports */ - if (!dsa_is_user_port(ds, port)) + if (!dsa_is_user_port(ctx->ds, port)) return 0; + master = dsa_to_port(ctx->ds, port)->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 < ds->num_ports; i++) { + for (i = 0; i < ctx->ds->num_ports; i++) { u16 flags; if (i == upstream) @@ -240,9 +244,10 @@ int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int port, bool enabled) /* The RX VID is a regular VLAN on all others */ flags = BRIDGE_VLAN_INFO_UNTAGGED; - err = dsa_8021q_vid_apply(ds, i, rx_vid, flags, enabled); + err = dsa_8021q_vid_apply(ctx, i, rx_vid, flags, enabled); if (err) { - dev_err(ds->dev, "Failed to apply RX VID %d to port %d: %d\n", + dev_err(ctx->ds->dev, + "Failed to apply RX VID %d to port %d: %d\n", rx_vid, port, err); return err; } @@ -251,80 +256,115 @@ int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int port, bool enabled) /* CPU port needs to see this port's RX VID * as tagged egress. */ - err = dsa_8021q_vid_apply(ds, upstream, rx_vid, 0, enabled); + err = dsa_8021q_vid_apply(ctx, upstream, rx_vid, 0, enabled); if (err) { - dev_err(ds->dev, "Failed to apply RX VID %d to port %d: %d\n", + dev_err(ctx->ds->dev, + "Failed to apply RX VID %d to port %d: %d\n", rx_vid, port, 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); + } + /* Finally apply the TX VID on this port and on the CPU port */ - err = dsa_8021q_vid_apply(ds, port, tx_vid, BRIDGE_VLAN_INFO_UNTAGGED, + err = dsa_8021q_vid_apply(ctx, port, tx_vid, BRIDGE_VLAN_INFO_UNTAGGED, enabled); if (err) { - dev_err(ds->dev, "Failed to apply TX VID %d on port %d: %d\n", + 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(ds, upstream, tx_vid, 0, enabled); + err = dsa_8021q_vid_apply(ctx, upstream, tx_vid, 0, enabled); if (err) { - dev_err(ds->dev, "Failed to apply TX VID %d on port %d: %d\n", + dev_err(ctx->ds->dev, + "Failed to apply TX VID %d on port %d: %d\n", tx_vid, upstream, err); return err; } return err; } -EXPORT_SYMBOL_GPL(dsa_port_setup_8021q_tagging); -static int dsa_8021q_crosschip_link_apply(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, +int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled) +{ + int rc, port; + + ASSERT_RTNL(); + + 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; + } + } + + return 0; +} +EXPORT_SYMBOL_GPL(dsa_8021q_setup); + +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(ds, port); + u16 rx_vid = dsa_8021q_rx_vid(ctx->ds, port); /* @rx_vid of local @ds port @port goes to @other_port of * @other_ds */ - return dsa_8021q_vid_apply(other_ds, other_port, rx_vid, + return dsa_8021q_vid_apply(other_ctx, other_port, rx_vid, BRIDGE_VLAN_INFO_UNTAGGED, enabled); } -static int dsa_8021q_crosschip_link_add(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port, - struct list_head *crosschip_links) +static int dsa_8021q_crosschip_link_add(struct dsa_8021q_context *ctx, int port, + struct dsa_8021q_context *other_ctx, + int other_port) { struct dsa_8021q_crosschip_link *c; - list_for_each_entry(c, crosschip_links, list) { - if (c->port == port && c->other_ds == other_ds && + 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; } } - dev_dbg(ds->dev, "adding crosschip link from port %d to %s port %d\n", - port, dev_name(other_ds->dev), other_port); + 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_ds = other_ds; + c->other_ctx = other_ctx; c->other_port = other_port; refcount_set(&c->refcount, 1); - list_add(&c->list, crosschip_links); + list_add(&c->list, &ctx->crosschip_links); return 0; } -static void dsa_8021q_crosschip_link_del(struct dsa_switch *ds, +static void dsa_8021q_crosschip_link_del(struct dsa_8021q_context *ctx, struct dsa_8021q_crosschip_link *c, - struct list_head *crosschip_links, bool *keep) { *keep = !refcount_dec_and_test(&c->refcount); @@ -332,9 +372,9 @@ static void dsa_8021q_crosschip_link_del(struct dsa_switch *ds, if (*keep) return; - dev_dbg(ds->dev, + dev_dbg(ctx->ds->dev, "deleting crosschip link from port %d to %s port %d\n", - c->port, dev_name(c->other_ds->dev), c->other_port); + c->port, dev_name(c->other_ctx->ds->dev), c->other_port); list_del(&c->list); kfree(c); @@ -347,64 +387,58 @@ static void dsa_8021q_crosschip_link_del(struct dsa_switch *ds, * 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_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port, - struct list_head *crosschip_links) +int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, + struct dsa_8021q_context *other_ctx, + int other_port) { /* @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_ds, other_port); + int other_upstream = dsa_upstream_port(other_ctx->ds, other_port); int rc; - rc = dsa_8021q_crosschip_link_add(ds, port, other_ds, - other_port, crosschip_links); + rc = dsa_8021q_crosschip_link_add(ctx, port, other_ctx, other_port); if (rc) return rc; - rc = dsa_8021q_crosschip_link_apply(ds, port, other_ds, + rc = dsa_8021q_crosschip_link_apply(ctx, port, other_ctx, other_port, true); if (rc) return rc; - rc = dsa_8021q_crosschip_link_add(ds, port, other_ds, - other_upstream, - crosschip_links); + rc = dsa_8021q_crosschip_link_add(ctx, port, other_ctx, other_upstream); if (rc) return rc; - return dsa_8021q_crosschip_link_apply(ds, port, other_ds, + return dsa_8021q_crosschip_link_apply(ctx, port, other_ctx, other_upstream, true); } EXPORT_SYMBOL_GPL(dsa_8021q_crosschip_bridge_join); -int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port, - struct list_head *crosschip_links) +int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, + struct dsa_8021q_context *other_ctx, + int other_port) { - int other_upstream = dsa_upstream_port(other_ds, other_port); + 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, crosschip_links, list) { - if (c->port == port && c->other_ds == other_ds && + 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_switch *other_ds = c->other_ds; + struct dsa_8021q_context *other_ctx = c->other_ctx; int other_port = c->other_port; bool keep; int rc; - dsa_8021q_crosschip_link_del(ds, c, crosschip_links, - &keep); + dsa_8021q_crosschip_link_del(ctx, c, &keep); if (keep) continue; - rc = dsa_8021q_crosschip_link_apply(ds, port, - other_ds, + rc = dsa_8021q_crosschip_link_apply(ctx, port, + other_ctx, other_port, false); if (rc) diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index cc8512b5f9e2..ad72dff8d524 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -107,6 +107,18 @@ static struct sk_buff *brcm_tag_xmit_ll(struct sk_buff *skb, return skb; } +/* Frames with this tag have one of these two layouts: + * ----------------------------------- + * | MAC DA | MAC SA | 4b tag | Type | DSA_TAG_PROTO_BRCM + * ----------------------------------- + * ----------------------------------- + * | 4b tag | MAC DA | MAC SA | Type | DSA_TAG_PROTO_BRCM_PREPEND + * ----------------------------------- + * In both cases, at receive time, skb->data points 2 bytes before the actual + * Ethernet type field and we have an offset of 4bytes between where skb->data + * and where the payload starts. So the same low-level receive function can be + * used. + */ static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, @@ -144,27 +156,6 @@ static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb, return skb; } - -static int brcm_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto, - int *offset) -{ - /* We have been called on the DSA master network device after - * eth_type_trans() which pulled the Ethernet header already. - * Frames have one of these two layouts: - * ----------------------------------- - * | MAC DA | MAC SA | 4b tag | Type | DSA_TAG_PROTO_BRCM - * ----------------------------------- - * ----------------------------------- - * | 4b tag | MAC DA | MAC SA | Type | DSA_TAG_PROTO_BRCM_PREPEND - * ----------------------------------- - * skb->data points 2 bytes before the actual Ethernet type field and - * we have an offset of 4bytes between where skb->data and where the - * payload starts. - */ - *offset = BRCM_TAG_LEN; - *proto = ((__be16 *)skb->data)[1]; - return 0; -} #endif #if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM) @@ -200,7 +191,6 @@ static const struct dsa_device_ops brcm_netdev_ops = { .xmit = brcm_tag_xmit, .rcv = brcm_tag_rcv, .overhead = BRCM_TAG_LEN, - .flow_dissect = brcm_tag_flow_dissect, }; DSA_TAG_DRIVER(brcm_netdev_ops); @@ -229,7 +219,6 @@ static const struct dsa_device_ops brcm_prepend_netdev_ops = { .xmit = brcm_tag_xmit_prepend, .rcv = brcm_tag_rcv_prepend, .overhead = BRCM_TAG_LEN, - .flow_dissect = brcm_tag_flow_dissect, }; DSA_TAG_DRIVER(brcm_prepend_netdev_ops); diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index 7ddec9794477..0b756fae68a5 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -142,20 +142,11 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev, return skb; } -static int dsa_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto, - int *offset) -{ - *offset = 4; - *proto = ((__be16 *)skb->data)[1]; - return 0; -} - static const struct dsa_device_ops dsa_netdev_ops = { .name = "dsa", .proto = DSA_TAG_PROTO_DSA, .xmit = dsa_xmit, .rcv = dsa_rcv, - .flow_dissect = dsa_tag_flow_dissect, .overhead = DSA_HLEN, }; diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c index d6200ff98200..120614240319 100644 --- a/net/dsa/tag_edsa.c +++ b/net/dsa/tag_edsa.c @@ -192,20 +192,11 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, return skb; } -static int edsa_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto, - int *offset) -{ - *offset = 8; - *proto = ((__be16 *)skb->data)[3]; - return 0; -} - static const struct dsa_device_ops edsa_netdev_ops = { .name = "edsa", .proto = DSA_TAG_PROTO_EDSA, .xmit = edsa_xmit, .rcv = edsa_rcv, - .flow_dissect = edsa_tag_flow_dissect, .overhead = EDSA_HLEN, }; diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index bd1a3158d79a..0a5aa982c60d 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -123,6 +123,7 @@ static const struct dsa_device_ops ksz8795_netdev_ops = { .xmit = ksz8795_xmit, .rcv = ksz8795_rcv, .overhead = KSZ_INGRESS_TAG_LEN, + .tail_tag = true, }; DSA_TAG_DRIVER(ksz8795_netdev_ops); @@ -199,6 +200,7 @@ static const struct dsa_device_ops ksz9477_netdev_ops = { .xmit = ksz9477_xmit, .rcv = ksz9477_rcv, .overhead = KSZ9477_INGRESS_TAG_LEN, + .tail_tag = true, }; DSA_TAG_DRIVER(ksz9477_netdev_ops); @@ -237,6 +239,7 @@ static const struct dsa_device_ops ksz9893_netdev_ops = { .xmit = ksz9893_xmit, .rcv = ksz9477_rcv, .overhead = KSZ_INGRESS_TAG_LEN, + .tail_tag = true, }; DSA_TAG_DRIVER(ksz9893_netdev_ops); diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index f602fc758d68..4cdd9cf428fb 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -105,21 +105,11 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, return skb; } -static int mtk_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto, - int *offset) -{ - *offset = 4; - *proto = ((__be16 *)skb->data)[1]; - - return 0; -} - static const struct dsa_device_ops mtk_netdev_ops = { .name = "mtk", .proto = DSA_TAG_PROTO_MTK, .xmit = mtk_tag_xmit, .rcv = mtk_tag_rcv, - .flow_dissect = mtk_tag_flow_dissect, .overhead = MTK_HDR_LEN, }; diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index b4fc05cafaa6..3b468aca5c53 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -137,13 +137,16 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb, struct net_device *netdev) { struct dsa_port *dp = dsa_slave_to_port(netdev); + struct sk_buff *clone = DSA_SKB_CB(skb)->clone; struct dsa_switch *ds = dp->ds; struct ocelot *ocelot = ds->priv; struct ocelot_port *ocelot_port; + u8 *prefix, *injection; u64 qos_class, rew_op; - u8 *injection; + int err; - if (unlikely(skb_cow_head(skb, OCELOT_TAG_LEN) < 0)) { + err = skb_cow_head(skb, OCELOT_TOTAL_TAG_LEN); + if (unlikely(err < 0)) { netdev_err(netdev, "Cannot make room for tag.\n"); return NULL; } @@ -152,16 +155,18 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb, injection = skb_push(skb, OCELOT_TAG_LEN); - memcpy(injection, ocelot_port->xmit_template, OCELOT_TAG_LEN); + prefix = skb_push(skb, OCELOT_SHORT_PREFIX_LEN); + + memcpy(prefix, ocelot_port->xmit_template, OCELOT_TOTAL_TAG_LEN); + /* Fix up the fields which are not statically determined * in the template */ qos_class = skb->priority; packing(injection, &qos_class, 19, 17, OCELOT_TAG_LEN, PACK, 0); - if (ocelot->ptp && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { - struct sk_buff *clone = DSA_SKB_CB(skb)->clone; - + /* TX timestamping was requested */ + if (clone) { rew_op = ocelot_port->ptp_cmd; /* Retrieve timestamp ID populated inside skb->cb[0] of the * clone by ocelot_port_add_txtstamp_skb @@ -179,19 +184,24 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, struct net_device *netdev, struct packet_type *pt) { + struct dsa_port *cpu_dp = netdev->dsa_ptr; + struct dsa_switch *ds = cpu_dp->ds; + struct ocelot *ocelot = ds->priv; u64 src_port, qos_class; + u64 vlan_tci, tag_type; u8 *start = skb->data; u8 *extraction; + u16 vlan_tpid; /* Revert skb->data by the amount consumed by the DSA master, * so it points to the beginning of the frame. */ skb_push(skb, ETH_HLEN); - /* We don't care about the long prefix, it is just for easy entrance + /* We don't care about the short prefix, it is just for easy entrance * into the DSA master's RX filter. Discard it now by moving it into * the headroom. */ - skb_pull(skb, OCELOT_LONG_PREFIX_LEN); + skb_pull(skb, OCELOT_SHORT_PREFIX_LEN); /* And skb->data now points to the extraction frame header. * Keep a pointer to it. */ @@ -205,10 +215,12 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, skb_pull(skb, ETH_HLEN); /* Remove from inet csum the extraction header */ - skb_postpull_rcsum(skb, start, OCELOT_LONG_PREFIX_LEN + OCELOT_TAG_LEN); + skb_postpull_rcsum(skb, start, OCELOT_TOTAL_TAG_LEN); packing(extraction, &src_port, 46, 43, OCELOT_TAG_LEN, UNPACK, 0); packing(extraction, &qos_class, 19, 17, OCELOT_TAG_LEN, UNPACK, 0); + packing(extraction, &tag_type, 16, 16, OCELOT_TAG_LEN, UNPACK, 0); + packing(extraction, &vlan_tci, 15, 0, OCELOT_TAG_LEN, UNPACK, 0); skb->dev = dsa_master_find_slave(netdev, 0, src_port); if (!skb->dev) @@ -223,6 +235,33 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, skb->offload_fwd_mark = 1; skb->priority = qos_class; + /* Ocelot switches copy frames unmodified to the CPU. However, it is + * possible for the user to request a VLAN modification through + * VCAP_IS1_ACT_VID_REPLACE_ENA. In this case, what will happen is that + * the VLAN ID field from the Extraction Header gets updated, but the + * 802.1Q header does not (the classified VLAN only becomes visible on + * egress through the "port tag" of front-panel ports). + * So, for traffic extracted by the CPU, we want to pick up the + * classified VLAN and manually replace the existing 802.1Q header from + * the packet with it, so that the operating system is always up to + * date with the result of tc-vlan actions. + * NOTE: In VLAN-unaware mode, we don't want to do that, we want the + * frame to remain unmodified, because the classified VLAN is always + * equal to the pvid of the ingress port and should not be used for + * processing. + */ + vlan_tpid = tag_type ? ETH_P_8021AD : ETH_P_8021Q; + + if (ocelot->ports[src_port]->vlan_aware && + eth_hdr(skb)->h_proto == htons(vlan_tpid)) { + u16 dummy_vlan_tci; + + skb_push_rcsum(skb, ETH_HLEN); + __skb_vlan_pop(skb, &dummy_vlan_tci); + skb_pull_rcsum(skb, ETH_HLEN); + __vlan_hwaccel_put_tag(skb, htons(vlan_tpid), vlan_tci); + } + return skb; } @@ -231,7 +270,8 @@ static const struct dsa_device_ops ocelot_netdev_ops = { .proto = DSA_TAG_PROTO_OCELOT, .xmit = ocelot_xmit, .rcv = ocelot_rcv, - .overhead = OCELOT_TAG_LEN + OCELOT_LONG_PREFIX_LEN, + .overhead = OCELOT_TOTAL_TAG_LEN, + .promisc_on_master = true, }; MODULE_LICENSE("GPL v2"); diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index 7066f5e697d7..1b9e8507112b 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -89,21 +89,11 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, return skb; } -static int qca_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto, - int *offset) -{ - *offset = QCA_HDR_LEN; - *proto = ((__be16 *)skb->data)[0]; - - return 0; -} - static const struct dsa_device_ops qca_netdev_ops = { .name = "qca", .proto = DSA_TAG_PROTO_QCA, .xmit = qca_tag_xmit, .rcv = qca_tag_rcv, - .flow_dissect = qca_tag_flow_dissect, .overhead = QCA_HDR_LEN, }; diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c index 7b63010fa87b..2646abe5a69e 100644 --- a/net/dsa/tag_rtl4_a.c +++ b/net/dsa/tag_rtl4_a.c @@ -106,22 +106,11 @@ static struct sk_buff *rtl4a_tag_rcv(struct sk_buff *skb, return skb; } -static int rtl4a_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto, - int *offset) -{ - *offset = RTL4_A_HDR_LEN; - /* Skip past the tag and fetch the encapsulated Ethertype */ - *proto = ((__be16 *)skb->data)[1]; - - return 0; -} - static const struct dsa_device_ops rtl4a_netdev_ops = { .name = "rtl4a", .proto = DSA_TAG_PROTO_RTL4_A, .xmit = rtl4a_tag_xmit, .rcv = rtl4a_tag_rcv, - .flow_dissect = rtl4a_tag_flow_dissect, .overhead = RTL4_A_HDR_LEN, }; module_dsa_tag_driver(rtl4a_netdev_ops); diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 9b4a4d719291..50496013cdb7 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -72,14 +72,21 @@ static inline bool sja1105_is_meta_frame(const struct sk_buff *skb) static bool sja1105_can_use_vlan_as_tags(const 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; - if (hdr->h_vlan_proto != htons(ETH_P_8021Q)) + if (hdr->h_vlan_proto != htons(ETH_P_8021Q) && + !skb_vlan_tag_present(skb)) return false; - return vid_is_dsa_8021q(ntohs(hdr->h_vlan_TCI) & VLAN_VID_MASK); + if (skb_vlan_tag_present(skb)) + vlan_tci = skb_vlan_tag_get(skb); + else + vlan_tci = ntohs(hdr->h_vlan_TCI); + + return vid_is_dsa_8021q(vlan_tci & VLAN_VID_MASK); } /* This is the first time the tagger sees the frame on RX. @@ -283,7 +290,8 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, hdr = eth_hdr(skb); tpid = ntohs(hdr->h_proto); - is_tagged = (tpid == ETH_P_SJA1105 || tpid == ETH_P_8021Q); + is_tagged = (tpid == ETH_P_SJA1105 || tpid == ETH_P_8021Q || + skb_vlan_tag_present(skb)); is_link_local = sja1105_is_link_local(skb); is_meta = sja1105_is_meta_frame(skb); @@ -292,7 +300,12 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, if (is_tagged) { /* Normal traffic path. */ skb_push_rcsum(skb, ETH_HLEN); - __skb_vlan_pop(skb, &tci); + if (skb_vlan_tag_present(skb)) { + tci = skb_vlan_tag_get(skb); + __vlan_hwaccel_clear_tag(skb); + } else { + __skb_vlan_pop(skb, &tci); + } skb_pull_rcsum(skb, ETH_HLEN); skb_reset_network_header(skb); skb_reset_transport_header(skb); @@ -333,6 +346,16 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, is_meta); } +static void sja1105_flow_dissect(const struct sk_buff *skb, __be16 *proto, + int *offset) +{ + /* No tag added for management frames, all ok */ + if (unlikely(sja1105_is_link_local(skb))) + return; + + dsa_tag_generic_flow_dissect(skb, proto, offset); +} + static const struct dsa_device_ops sja1105_netdev_ops = { .name = "sja1105", .proto = DSA_TAG_PROTO_SJA1105, @@ -340,6 +363,8 @@ static const struct dsa_device_ops sja1105_netdev_ops = { .rcv = sja1105_rcv, .filter = sja1105_filter, .overhead = VLAN_HLEN, + .flow_dissect = sja1105_flow_dissect, + .promisc_on_master = true, }; MODULE_LICENSE("GPL v2"); diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index 4f8ab62f0208..3a1cc24a4f0a 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -83,6 +83,7 @@ static const struct dsa_device_ops trailer_netdev_ops = { .xmit = trailer_xmit, .rcv = trailer_rcv, .overhead = 4, + .tail_tag = true, }; MODULE_LICENSE("GPL"); diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c index dae7402eaca3..1fb3603d92ad 100644 --- a/net/ethtool/bitset.c +++ b/net/ethtool/bitset.c @@ -302,8 +302,7 @@ nla_put_failure: return -EMSGSIZE; } -static const struct nla_policy bitset_policy[ETHTOOL_A_BITSET_MAX + 1] = { - [ETHTOOL_A_BITSET_UNSPEC] = { .type = NLA_REJECT }, +static const struct nla_policy bitset_policy[] = { [ETHTOOL_A_BITSET_NOMASK] = { .type = NLA_FLAG }, [ETHTOOL_A_BITSET_SIZE] = NLA_POLICY_MAX(NLA_U32, ETHNL_MAX_BITSET_SIZE), @@ -312,8 +311,7 @@ static const struct nla_policy bitset_policy[ETHTOOL_A_BITSET_MAX + 1] = { [ETHTOOL_A_BITSET_MASK] = { .type = NLA_BINARY }, }; -static const struct nla_policy bit_policy[ETHTOOL_A_BITSET_BIT_MAX + 1] = { - [ETHTOOL_A_BITSET_BIT_UNSPEC] = { .type = NLA_REJECT }, +static const struct nla_policy bit_policy[] = { [ETHTOOL_A_BITSET_BIT_INDEX] = { .type = NLA_U32 }, [ETHTOOL_A_BITSET_BIT_NAME] = { .type = NLA_NUL_STRING }, [ETHTOOL_A_BITSET_BIT_VALUE] = { .type = NLA_FLAG }, @@ -329,10 +327,10 @@ static const struct nla_policy bit_policy[ETHTOOL_A_BITSET_BIT_MAX + 1] = { */ int ethnl_bitset_is_compact(const struct nlattr *bitset, bool *compact) { - struct nlattr *tb[ETHTOOL_A_BITSET_MAX + 1]; + struct nlattr *tb[ARRAY_SIZE(bitset_policy)]; int ret; - ret = nla_parse_nested(tb, ETHTOOL_A_BITSET_MAX, bitset, + ret = nla_parse_nested(tb, ARRAY_SIZE(bitset_policy) - 1, bitset, bitset_policy, NULL); if (ret < 0) return ret; @@ -381,10 +379,10 @@ static int ethnl_parse_bit(unsigned int *index, bool *val, unsigned int nbits, ethnl_string_array_t names, struct netlink_ext_ack *extack) { - struct nlattr *tb[ETHTOOL_A_BITSET_BIT_MAX + 1]; + struct nlattr *tb[ARRAY_SIZE(bit_policy)]; int ret, idx; - ret = nla_parse_nested(tb, ETHTOOL_A_BITSET_BIT_MAX, bit_attr, + ret = nla_parse_nested(tb, ARRAY_SIZE(bit_policy) - 1, bit_attr, bit_policy, extack); if (ret < 0) return ret; @@ -555,15 +553,15 @@ int ethnl_update_bitset32(u32 *bitmap, unsigned int nbits, const struct nlattr *attr, ethnl_string_array_t names, struct netlink_ext_ack *extack, bool *mod) { - struct nlattr *tb[ETHTOOL_A_BITSET_MAX + 1]; + struct nlattr *tb[ARRAY_SIZE(bitset_policy)]; unsigned int change_bits; bool no_mask; int ret; if (!attr) return 0; - ret = nla_parse_nested(tb, ETHTOOL_A_BITSET_MAX, attr, bitset_policy, - extack); + ret = nla_parse_nested(tb, ARRAY_SIZE(bitset_policy) - 1, attr, + bitset_policy, extack); if (ret < 0) return ret; @@ -608,7 +606,7 @@ int ethnl_parse_bitset(unsigned long *val, unsigned long *mask, ethnl_string_array_t names, struct netlink_ext_ack *extack) { - struct nlattr *tb[ETHTOOL_A_BITSET_MAX + 1]; + struct nlattr *tb[ARRAY_SIZE(bitset_policy)]; const struct nlattr *bit_attr; bool no_mask; int rem; @@ -616,8 +614,8 @@ int ethnl_parse_bitset(unsigned long *val, unsigned long *mask, if (!attr) return 0; - ret = nla_parse_nested(tb, ETHTOOL_A_BITSET_MAX, attr, bitset_policy, - extack); + ret = nla_parse_nested(tb, ARRAY_SIZE(bitset_policy) - 1, attr, + bitset_policy, extack); if (ret < 0) return ret; no_mask = tb[ETHTOOL_A_BITSET_NOMASK]; diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c index 888f6e101f34..63560bbb7d1f 100644 --- a/net/ethtool/cabletest.c +++ b/net/ethtool/cabletest.c @@ -11,10 +11,9 @@ */ #define MAX_CABLE_LENGTH_CM (150 * 100) -static const struct nla_policy -cable_test_act_policy[ETHTOOL_A_CABLE_TEST_MAX + 1] = { - [ETHTOOL_A_CABLE_TEST_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_CABLE_TEST_HEADER] = { .type = NLA_NESTED }, +const struct nla_policy ethnl_cable_test_act_policy[] = { + [ETHTOOL_A_CABLE_TEST_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), }; static int ethnl_cable_test_started(struct phy_device *phydev, u8 cmd) @@ -56,18 +55,12 @@ out: int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *tb[ETHTOOL_A_CABLE_TEST_MAX + 1]; struct ethnl_req_info req_info = {}; const struct ethtool_phy_ops *ops; + struct nlattr **tb = info->attrs; struct net_device *dev; int ret; - ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, - ETHTOOL_A_CABLE_TEST_MAX, - cable_test_act_policy, info->extack); - if (ret < 0) - return ret; - ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_CABLE_TEST_HEADER], genl_info_net(info), info->extack, @@ -218,18 +211,16 @@ struct cable_test_tdr_req_info { struct ethnl_req_info base; }; -static const struct nla_policy -cable_test_tdr_act_cfg_policy[ETHTOOL_A_CABLE_TEST_TDR_CFG_MAX + 1] = { +static const struct nla_policy cable_test_tdr_act_cfg_policy[] = { [ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST] = { .type = NLA_U32 }, [ETHTOOL_A_CABLE_TEST_TDR_CFG_LAST] = { .type = NLA_U32 }, [ETHTOOL_A_CABLE_TEST_TDR_CFG_STEP] = { .type = NLA_U32 }, [ETHTOOL_A_CABLE_TEST_TDR_CFG_PAIR] = { .type = NLA_U8 }, }; -static const struct nla_policy -cable_test_tdr_act_policy[ETHTOOL_A_CABLE_TEST_TDR_MAX + 1] = { - [ETHTOOL_A_CABLE_TEST_TDR_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_CABLE_TEST_TDR_HEADER] = { .type = NLA_NESTED }, +const struct nla_policy ethnl_cable_test_tdr_act_policy[] = { + [ETHTOOL_A_CABLE_TEST_TDR_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_CABLE_TEST_TDR_CFG] = { .type = NLA_NESTED }, }; @@ -238,7 +229,7 @@ static int ethnl_act_cable_test_tdr_cfg(const struct nlattr *nest, struct genl_info *info, struct phy_tdr_config *cfg) { - struct nlattr *tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_MAX + 1]; + struct nlattr *tb[ARRAY_SIZE(cable_test_tdr_act_cfg_policy)]; int ret; cfg->first = 100; @@ -249,8 +240,10 @@ static int ethnl_act_cable_test_tdr_cfg(const struct nlattr *nest, if (!nest) return 0; - ret = nla_parse_nested(tb, ETHTOOL_A_CABLE_TEST_TDR_CFG_MAX, nest, - cable_test_tdr_act_cfg_policy, info->extack); + ret = nla_parse_nested(tb, + ARRAY_SIZE(cable_test_tdr_act_cfg_policy) - 1, + nest, cable_test_tdr_act_cfg_policy, + info->extack); if (ret < 0) return ret; @@ -313,19 +306,13 @@ static int ethnl_act_cable_test_tdr_cfg(const struct nlattr *nest, int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *tb[ETHTOOL_A_CABLE_TEST_TDR_MAX + 1]; struct ethnl_req_info req_info = {}; const struct ethtool_phy_ops *ops; + struct nlattr **tb = info->attrs; struct phy_tdr_config cfg; struct net_device *dev; int ret; - ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, - ETHTOOL_A_CABLE_TEST_TDR_MAX, - cable_test_tdr_act_policy, info->extack); - if (ret < 0) - return ret; - ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_CABLE_TEST_TDR_HEADER], genl_info_net(info), info->extack, diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c index 9ef54cdcf662..5635604cb9ba 100644 --- a/net/ethtool/channels.c +++ b/net/ethtool/channels.c @@ -17,18 +17,9 @@ struct channels_reply_data { #define CHANNELS_REPDATA(__reply_base) \ container_of(__reply_base, struct channels_reply_data, base) -static const struct nla_policy -channels_get_policy[ETHTOOL_A_CHANNELS_MAX + 1] = { - [ETHTOOL_A_CHANNELS_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_CHANNELS_HEADER] = { .type = NLA_NESTED }, - [ETHTOOL_A_CHANNELS_RX_MAX] = { .type = NLA_REJECT }, - [ETHTOOL_A_CHANNELS_TX_MAX] = { .type = NLA_REJECT }, - [ETHTOOL_A_CHANNELS_OTHER_MAX] = { .type = NLA_REJECT }, - [ETHTOOL_A_CHANNELS_COMBINED_MAX] = { .type = NLA_REJECT }, - [ETHTOOL_A_CHANNELS_RX_COUNT] = { .type = NLA_REJECT }, - [ETHTOOL_A_CHANNELS_TX_COUNT] = { .type = NLA_REJECT }, - [ETHTOOL_A_CHANNELS_OTHER_COUNT] = { .type = NLA_REJECT }, - [ETHTOOL_A_CHANNELS_COMBINED_COUNT] = { .type = NLA_REJECT }, +const struct nla_policy ethnl_channels_get_policy[] = { + [ETHTOOL_A_CHANNELS_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), }; static int channels_prepare_data(const struct ethnl_req_info *req_base, @@ -99,10 +90,8 @@ const struct ethnl_request_ops ethnl_channels_request_ops = { .request_cmd = ETHTOOL_MSG_CHANNELS_GET, .reply_cmd = ETHTOOL_MSG_CHANNELS_GET_REPLY, .hdr_attr = ETHTOOL_A_CHANNELS_HEADER, - .max_attr = ETHTOOL_A_CHANNELS_MAX, .req_info_size = sizeof(struct channels_req_info), .reply_data_size = sizeof(struct channels_reply_data), - .request_policy = channels_get_policy, .prepare_data = channels_prepare_data, .reply_size = channels_reply_size, @@ -111,14 +100,9 @@ const struct ethnl_request_ops ethnl_channels_request_ops = { /* CHANNELS_SET */ -static const struct nla_policy -channels_set_policy[ETHTOOL_A_CHANNELS_MAX + 1] = { - [ETHTOOL_A_CHANNELS_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_CHANNELS_HEADER] = { .type = NLA_NESTED }, - [ETHTOOL_A_CHANNELS_RX_MAX] = { .type = NLA_REJECT }, - [ETHTOOL_A_CHANNELS_TX_MAX] = { .type = NLA_REJECT }, - [ETHTOOL_A_CHANNELS_OTHER_MAX] = { .type = NLA_REJECT }, - [ETHTOOL_A_CHANNELS_COMBINED_MAX] = { .type = NLA_REJECT }, +const struct nla_policy ethnl_channels_set_policy[] = { + [ETHTOOL_A_CHANNELS_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_CHANNELS_RX_COUNT] = { .type = NLA_U32 }, [ETHTOOL_A_CHANNELS_TX_COUNT] = { .type = NLA_U32 }, [ETHTOOL_A_CHANNELS_OTHER_COUNT] = { .type = NLA_U32 }, @@ -127,22 +111,17 @@ channels_set_policy[ETHTOOL_A_CHANNELS_MAX + 1] = { int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *tb[ETHTOOL_A_CHANNELS_MAX + 1]; unsigned int from_channel, old_total, i; bool mod = false, mod_combined = false; struct ethtool_channels channels = {}; struct ethnl_req_info req_info = {}; + struct nlattr **tb = info->attrs; const struct nlattr *err_attr; const struct ethtool_ops *ops; struct net_device *dev; u32 max_rx_in_use = 0; int ret; - ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, - ETHTOOL_A_CHANNELS_MAX, channels_set_policy, - info->extack); - if (ret < 0) - return ret; ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_CHANNELS_HEADER], genl_info_net(info), info->extack, @@ -223,7 +202,7 @@ int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info) from_channel = channels.combined_count + min(channels.rx_count, channels.tx_count); for (i = from_channel; i < old_total; i++) - if (xdp_get_umem_from_qid(dev, i)) { + if (xsk_get_pool_from_qid(dev, i)) { GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing zerocopy AF_XDP sockets"); return -EINVAL; } diff --git a/net/ethtool/coalesce.c b/net/ethtool/coalesce.c index 6afd99042d67..1d6bc132aa4d 100644 --- a/net/ethtool/coalesce.c +++ b/net/ethtool/coalesce.c @@ -51,32 +51,9 @@ __CHECK_SUPPORTED_OFFSET(COALESCE_TX_USECS_HIGH); __CHECK_SUPPORTED_OFFSET(COALESCE_TX_MAX_FRAMES_HIGH); __CHECK_SUPPORTED_OFFSET(COALESCE_RATE_SAMPLE_INTERVAL); -static const struct nla_policy -coalesce_get_policy[ETHTOOL_A_COALESCE_MAX + 1] = { - [ETHTOOL_A_COALESCE_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_HEADER] = { .type = NLA_NESTED }, - [ETHTOOL_A_COALESCE_RX_USECS] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_RX_MAX_FRAMES] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_RX_USECS_IRQ] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_TX_USECS] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_TX_MAX_FRAMES] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_TX_USECS_IRQ] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_STATS_BLOCK_USECS] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_PKT_RATE_LOW] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_RX_USECS_LOW] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_TX_USECS_LOW] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_PKT_RATE_HIGH] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_RX_USECS_HIGH] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_TX_USECS_HIGH] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL] = { .type = NLA_REJECT }, +const struct nla_policy ethnl_coalesce_get_policy[] = { + [ETHTOOL_A_COALESCE_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), }; static int coalesce_prepare_data(const struct ethnl_req_info *req_base, @@ -203,10 +180,8 @@ const struct ethnl_request_ops ethnl_coalesce_request_ops = { .request_cmd = ETHTOOL_MSG_COALESCE_GET, .reply_cmd = ETHTOOL_MSG_COALESCE_GET_REPLY, .hdr_attr = ETHTOOL_A_COALESCE_HEADER, - .max_attr = ETHTOOL_A_COALESCE_MAX, .req_info_size = sizeof(struct coalesce_req_info), .reply_data_size = sizeof(struct coalesce_reply_data), - .request_policy = coalesce_get_policy, .prepare_data = coalesce_prepare_data, .reply_size = coalesce_reply_size, @@ -215,10 +190,9 @@ const struct ethnl_request_ops ethnl_coalesce_request_ops = { /* COALESCE_SET */ -static const struct nla_policy -coalesce_set_policy[ETHTOOL_A_COALESCE_MAX + 1] = { - [ETHTOOL_A_COALESCE_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_COALESCE_HEADER] = { .type = NLA_NESTED }, +const struct nla_policy ethnl_coalesce_set_policy[] = { + [ETHTOOL_A_COALESCE_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_COALESCE_RX_USECS] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_RX_MAX_FRAMES] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_RX_USECS_IRQ] = { .type = NLA_U32 }, @@ -245,9 +219,9 @@ coalesce_set_policy[ETHTOOL_A_COALESCE_MAX + 1] = { int ethnl_set_coalesce(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *tb[ETHTOOL_A_COALESCE_MAX + 1]; struct ethtool_coalesce coalesce = {}; struct ethnl_req_info req_info = {}; + struct nlattr **tb = info->attrs; const struct ethtool_ops *ops; struct net_device *dev; u32 supported_params; @@ -255,11 +229,6 @@ int ethnl_set_coalesce(struct sk_buff *skb, struct genl_info *info) int ret; u16 a; - ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, - ETHTOOL_A_COALESCE_MAX, coalesce_set_policy, - info->extack); - if (ret < 0) - return ret; ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_COALESCE_HEADER], genl_info_net(info), info->extack, diff --git a/net/ethtool/common.c b/net/ethtool/common.c index ed19573fccd7..24036e3055a1 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -192,6 +192,8 @@ const char link_mode_names[][ETH_GSTRING_LEN] = { __DEFINE_LINK_MODE_NAME(400000, LR4_ER4_FR4, Full), __DEFINE_LINK_MODE_NAME(400000, DR4, Full), __DEFINE_LINK_MODE_NAME(400000, CR4, Full), + __DEFINE_LINK_MODE_NAME(100, FX, Half), + __DEFINE_LINK_MODE_NAME(100, FX, Full), }; static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); diff --git a/net/ethtool/debug.c b/net/ethtool/debug.c index 1bd026a29f3f..f99912d7957e 100644 --- a/net/ethtool/debug.c +++ b/net/ethtool/debug.c @@ -16,11 +16,9 @@ struct debug_reply_data { #define DEBUG_REPDATA(__reply_base) \ container_of(__reply_base, struct debug_reply_data, base) -static const struct nla_policy -debug_get_policy[ETHTOOL_A_DEBUG_MAX + 1] = { - [ETHTOOL_A_DEBUG_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_DEBUG_HEADER] = { .type = NLA_NESTED }, - [ETHTOOL_A_DEBUG_MSGMASK] = { .type = NLA_REJECT }, +const struct nla_policy ethnl_debug_get_policy[] = { + [ETHTOOL_A_DEBUG_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), }; static int debug_prepare_data(const struct ethnl_req_info *req_base, @@ -69,10 +67,8 @@ const struct ethnl_request_ops ethnl_debug_request_ops = { .request_cmd = ETHTOOL_MSG_DEBUG_GET, .reply_cmd = ETHTOOL_MSG_DEBUG_GET_REPLY, .hdr_attr = ETHTOOL_A_DEBUG_HEADER, - .max_attr = ETHTOOL_A_DEBUG_MAX, .req_info_size = sizeof(struct debug_req_info), .reply_data_size = sizeof(struct debug_reply_data), - .request_policy = debug_get_policy, .prepare_data = debug_prepare_data, .reply_size = debug_reply_size, @@ -81,27 +77,21 @@ const struct ethnl_request_ops ethnl_debug_request_ops = { /* DEBUG_SET */ -static const struct nla_policy -debug_set_policy[ETHTOOL_A_DEBUG_MAX + 1] = { - [ETHTOOL_A_DEBUG_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_DEBUG_HEADER] = { .type = NLA_NESTED }, +const struct nla_policy ethnl_debug_set_policy[] = { + [ETHTOOL_A_DEBUG_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_DEBUG_MSGMASK] = { .type = NLA_NESTED }, }; int ethnl_set_debug(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *tb[ETHTOOL_A_DEBUG_MAX + 1]; struct ethnl_req_info req_info = {}; + struct nlattr **tb = info->attrs; struct net_device *dev; bool mod = false; u32 msg_mask; int ret; - ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, - ETHTOOL_A_DEBUG_MAX, debug_set_policy, - info->extack); - if (ret < 0) - return ret; ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_DEBUG_HEADER], genl_info_net(info), info->extack, diff --git a/net/ethtool/eee.c b/net/ethtool/eee.c index 94aa19cff22f..901b7de941ab 100644 --- a/net/ethtool/eee.c +++ b/net/ethtool/eee.c @@ -19,16 +19,9 @@ struct eee_reply_data { #define EEE_REPDATA(__reply_base) \ container_of(__reply_base, struct eee_reply_data, base) -static const struct nla_policy -eee_get_policy[ETHTOOL_A_EEE_MAX + 1] = { - [ETHTOOL_A_EEE_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_EEE_HEADER] = { .type = NLA_NESTED }, - [ETHTOOL_A_EEE_MODES_OURS] = { .type = NLA_REJECT }, - [ETHTOOL_A_EEE_MODES_PEER] = { .type = NLA_REJECT }, - [ETHTOOL_A_EEE_ACTIVE] = { .type = NLA_REJECT }, - [ETHTOOL_A_EEE_ENABLED] = { .type = NLA_REJECT }, - [ETHTOOL_A_EEE_TX_LPI_ENABLED] = { .type = NLA_REJECT }, - [ETHTOOL_A_EEE_TX_LPI_TIMER] = { .type = NLA_REJECT }, +const struct nla_policy ethnl_eee_get_policy[] = { + [ETHTOOL_A_EEE_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), }; static int eee_prepare_data(const struct ethnl_req_info *req_base, @@ -119,10 +112,8 @@ const struct ethnl_request_ops ethnl_eee_request_ops = { .request_cmd = ETHTOOL_MSG_EEE_GET, .reply_cmd = ETHTOOL_MSG_EEE_GET_REPLY, .hdr_attr = ETHTOOL_A_EEE_HEADER, - .max_attr = ETHTOOL_A_EEE_MAX, .req_info_size = sizeof(struct eee_req_info), .reply_data_size = sizeof(struct eee_reply_data), - .request_policy = eee_get_policy, .prepare_data = eee_prepare_data, .reply_size = eee_reply_size, @@ -131,13 +122,10 @@ const struct ethnl_request_ops ethnl_eee_request_ops = { /* EEE_SET */ -static const struct nla_policy -eee_set_policy[ETHTOOL_A_EEE_MAX + 1] = { - [ETHTOOL_A_EEE_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_EEE_HEADER] = { .type = NLA_NESTED }, +const struct nla_policy ethnl_eee_set_policy[] = { + [ETHTOOL_A_EEE_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_EEE_MODES_OURS] = { .type = NLA_NESTED }, - [ETHTOOL_A_EEE_MODES_PEER] = { .type = NLA_REJECT }, - [ETHTOOL_A_EEE_ACTIVE] = { .type = NLA_REJECT }, [ETHTOOL_A_EEE_ENABLED] = { .type = NLA_U8 }, [ETHTOOL_A_EEE_TX_LPI_ENABLED] = { .type = NLA_U8 }, [ETHTOOL_A_EEE_TX_LPI_TIMER] = { .type = NLA_U32 }, @@ -145,18 +133,14 @@ eee_set_policy[ETHTOOL_A_EEE_MAX + 1] = { int ethnl_set_eee(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *tb[ETHTOOL_A_EEE_MAX + 1]; - struct ethtool_eee eee = {}; struct ethnl_req_info req_info = {}; + struct nlattr **tb = info->attrs; const struct ethtool_ops *ops; + struct ethtool_eee eee = {}; struct net_device *dev; bool mod = false; int ret; - ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, ETHTOOL_A_EEE_MAX, - eee_set_policy, info->extack); - if (ret < 0) - return ret; ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_EEE_HEADER], genl_info_net(info), info->extack, diff --git a/net/ethtool/features.c b/net/ethtool/features.c index 495635f152ba..8ee4cdbd6b82 100644 --- a/net/ethtool/features.c +++ b/net/ethtool/features.c @@ -20,14 +20,9 @@ struct features_reply_data { #define FEATURES_REPDATA(__reply_base) \ container_of(__reply_base, struct features_reply_data, base) -static const struct nla_policy -features_get_policy[ETHTOOL_A_FEATURES_MAX + 1] = { - [ETHTOOL_A_FEATURES_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_FEATURES_HEADER] = { .type = NLA_NESTED }, - [ETHTOOL_A_FEATURES_HW] = { .type = NLA_REJECT }, - [ETHTOOL_A_FEATURES_WANTED] = { .type = NLA_REJECT }, - [ETHTOOL_A_FEATURES_ACTIVE] = { .type = NLA_REJECT }, - [ETHTOOL_A_FEATURES_NOCHANGE] = { .type = NLA_REJECT }, +const struct nla_policy ethnl_features_get_policy[] = { + [ETHTOOL_A_FEATURES_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), }; static void ethnl_features_to_bitmap32(u32 *dest, netdev_features_t src) @@ -120,10 +115,8 @@ const struct ethnl_request_ops ethnl_features_request_ops = { .request_cmd = ETHTOOL_MSG_FEATURES_GET, .reply_cmd = ETHTOOL_MSG_FEATURES_GET_REPLY, .hdr_attr = ETHTOOL_A_FEATURES_HEADER, - .max_attr = ETHTOOL_A_FEATURES_MAX, .req_info_size = sizeof(struct features_req_info), .reply_data_size = sizeof(struct features_reply_data), - .request_policy = features_get_policy, .prepare_data = features_prepare_data, .reply_size = features_reply_size, @@ -132,14 +125,10 @@ const struct ethnl_request_ops ethnl_features_request_ops = { /* FEATURES_SET */ -static const struct nla_policy -features_set_policy[ETHTOOL_A_FEATURES_MAX + 1] = { - [ETHTOOL_A_FEATURES_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_FEATURES_HEADER] = { .type = NLA_NESTED }, - [ETHTOOL_A_FEATURES_HW] = { .type = NLA_REJECT }, +const struct nla_policy ethnl_features_set_policy[] = { + [ETHTOOL_A_FEATURES_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_FEATURES_WANTED] = { .type = NLA_NESTED }, - [ETHTOOL_A_FEATURES_ACTIVE] = { .type = NLA_REJECT }, - [ETHTOOL_A_FEATURES_NOCHANGE] = { .type = NLA_REJECT }, }; static void ethnl_features_to_bitmap(unsigned long *dest, netdev_features_t val) @@ -229,17 +218,12 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info) DECLARE_BITMAP(new_wanted, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(req_wanted, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(req_mask, NETDEV_FEATURE_COUNT); - struct nlattr *tb[ETHTOOL_A_FEATURES_MAX + 1]; struct ethnl_req_info req_info = {}; + struct nlattr **tb = info->attrs; struct net_device *dev; bool mod; int ret; - ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, - ETHTOOL_A_FEATURES_MAX, features_set_policy, - info->extack); - if (ret < 0) - return ret; if (!tb[ETHTOOL_A_FEATURES_WANTED]) return -EINVAL; ret = ethnl_parse_header_dev_get(&req_info, diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 441794e0034f..ec2cd7aab5ad 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1706,7 +1706,7 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev, min(channels.rx_count, channels.tx_count); to_channel = curr.combined_count + max(curr.rx_count, curr.tx_count); for (i = from_channel; i < to_channel; i++) - if (xdp_get_umem_from_qid(dev, i)) + if (xsk_get_pool_from_qid(dev, i)) return -EINVAL; ret = dev->ethtool_ops->set_channels(dev, &channels); @@ -1861,23 +1861,18 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) id.data ? (id.data * HZ) : MAX_SCHEDULE_TIMEOUT); } else { /* Driver expects to be called at twice the frequency in rc */ - int n = rc * 2, i, interval = HZ / n; + int n = rc * 2, interval = HZ / n; + u64 count = n * id.data, i = 0; - /* Count down seconds */ do { - /* Count down iterations per second */ - i = n; - do { - rtnl_lock(); - rc = ops->set_phys_id(dev, - (i & 1) ? ETHTOOL_ID_OFF : ETHTOOL_ID_ON); - rtnl_unlock(); - if (rc) - break; - schedule_timeout_interruptible(interval); - } while (!signal_pending(current) && --i != 0); - } while (!signal_pending(current) && - (id.data == 0 || --id.data != 0)); + rtnl_lock(); + rc = ops->set_phys_id(dev, + (i++ & 1) ? ETHTOOL_ID_OFF : ETHTOOL_ID_ON); + rtnl_unlock(); + if (rc) + break; + schedule_timeout_interruptible(interval); + } while (!signal_pending(current) && (!id.data || i < count)); } rtnl_lock(); @@ -2464,14 +2459,15 @@ static int ethtool_phy_tunable_valid(const struct ethtool_tunable *tuna) static int get_phy_tunable(struct net_device *dev, void __user *useraddr) { - int ret; - struct ethtool_tunable tuna; struct phy_device *phydev = dev->phydev; + struct ethtool_tunable tuna; + bool phy_drv_tunable; void *data; + int ret; - if (!(phydev && phydev->drv && phydev->drv->get_tunable)) + phy_drv_tunable = phydev && phydev->drv && phydev->drv->get_tunable; + if (!phy_drv_tunable && !dev->ethtool_ops->get_phy_tunable) return -EOPNOTSUPP; - if (copy_from_user(&tuna, useraddr, sizeof(tuna))) return -EFAULT; ret = ethtool_phy_tunable_valid(&tuna); @@ -2480,9 +2476,13 @@ static int get_phy_tunable(struct net_device *dev, void __user *useraddr) data = kmalloc(tuna.len, GFP_USER); if (!data) return -ENOMEM; - mutex_lock(&phydev->lock); - ret = phydev->drv->get_tunable(phydev, &tuna, data); - mutex_unlock(&phydev->lock); + if (phy_drv_tunable) { + mutex_lock(&phydev->lock); + ret = phydev->drv->get_tunable(phydev, &tuna, data); + mutex_unlock(&phydev->lock); + } else { + ret = dev->ethtool_ops->get_phy_tunable(dev, &tuna, data); + } if (ret) goto out; useraddr += sizeof(tuna); @@ -2498,12 +2498,14 @@ out: static int set_phy_tunable(struct net_device *dev, void __user *useraddr) { - int ret; - struct ethtool_tunable tuna; struct phy_device *phydev = dev->phydev; + struct ethtool_tunable tuna; + bool phy_drv_tunable; void *data; + int ret; - if (!(phydev && phydev->drv && phydev->drv->set_tunable)) + phy_drv_tunable = phydev && phydev->drv && phydev->drv->get_tunable; + if (!phy_drv_tunable && !dev->ethtool_ops->set_phy_tunable) return -EOPNOTSUPP; if (copy_from_user(&tuna, useraddr, sizeof(tuna))) return -EFAULT; @@ -2514,9 +2516,13 @@ static int set_phy_tunable(struct net_device *dev, void __user *useraddr) data = memdup_user(useraddr, tuna.len); if (IS_ERR(data)) return PTR_ERR(data); - mutex_lock(&phydev->lock); - ret = phydev->drv->set_tunable(phydev, &tuna, data); - mutex_unlock(&phydev->lock); + if (phy_drv_tunable) { + mutex_lock(&phydev->lock); + ret = phydev->drv->set_tunable(phydev, &tuna, data); + mutex_unlock(&phydev->lock); + } else { + ret = dev->ethtool_ops->set_phy_tunable(dev, &tuna, data); + } kfree(data); return ret; @@ -3025,13 +3031,14 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input) case TCP_V4_FLOW: case TCP_V6_FLOW: match->key.basic.ip_proto = IPPROTO_TCP; + match->mask.basic.ip_proto = 0xff; break; case UDP_V4_FLOW: case UDP_V6_FLOW: match->key.basic.ip_proto = IPPROTO_UDP; + match->mask.basic.ip_proto = 0xff; break; } - match->mask.basic.ip_proto = 0xff; match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_BASIC); match->dissector.offset[FLOW_DISSECTOR_KEY_BASIC] = diff --git a/net/ethtool/linkinfo.c b/net/ethtool/linkinfo.c index 5eaf173eaaca..b91839870efc 100644 --- a/net/ethtool/linkinfo.c +++ b/net/ethtool/linkinfo.c @@ -16,15 +16,9 @@ struct linkinfo_reply_data { #define LINKINFO_REPDATA(__reply_base) \ container_of(__reply_base, struct linkinfo_reply_data, base) -static const struct nla_policy -linkinfo_get_policy[ETHTOOL_A_LINKINFO_MAX + 1] = { - [ETHTOOL_A_LINKINFO_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_LINKINFO_HEADER] = { .type = NLA_NESTED }, - [ETHTOOL_A_LINKINFO_PORT] = { .type = NLA_REJECT }, - [ETHTOOL_A_LINKINFO_PHYADDR] = { .type = NLA_REJECT }, - [ETHTOOL_A_LINKINFO_TP_MDIX] = { .type = NLA_REJECT }, - [ETHTOOL_A_LINKINFO_TP_MDIX_CTRL] = { .type = NLA_REJECT }, - [ETHTOOL_A_LINKINFO_TRANSCEIVER] = { .type = NLA_REJECT }, +const struct nla_policy ethnl_linkinfo_get_policy[] = { + [ETHTOOL_A_LINKINFO_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), }; static int linkinfo_prepare_data(const struct ethnl_req_info *req_base, @@ -83,10 +77,8 @@ const struct ethnl_request_ops ethnl_linkinfo_request_ops = { .request_cmd = ETHTOOL_MSG_LINKINFO_GET, .reply_cmd = ETHTOOL_MSG_LINKINFO_GET_REPLY, .hdr_attr = ETHTOOL_A_LINKINFO_HEADER, - .max_attr = ETHTOOL_A_LINKINFO_MAX, .req_info_size = sizeof(struct linkinfo_req_info), .reply_data_size = sizeof(struct linkinfo_reply_data), - .request_policy = linkinfo_get_policy, .prepare_data = linkinfo_prepare_data, .reply_size = linkinfo_reply_size, @@ -95,32 +87,24 @@ const struct ethnl_request_ops ethnl_linkinfo_request_ops = { /* LINKINFO_SET */ -static const struct nla_policy -linkinfo_set_policy[ETHTOOL_A_LINKINFO_MAX + 1] = { - [ETHTOOL_A_LINKINFO_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_LINKINFO_HEADER] = { .type = NLA_NESTED }, +const struct nla_policy ethnl_linkinfo_set_policy[] = { + [ETHTOOL_A_LINKINFO_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_LINKINFO_PORT] = { .type = NLA_U8 }, [ETHTOOL_A_LINKINFO_PHYADDR] = { .type = NLA_U8 }, - [ETHTOOL_A_LINKINFO_TP_MDIX] = { .type = NLA_REJECT }, [ETHTOOL_A_LINKINFO_TP_MDIX_CTRL] = { .type = NLA_U8 }, - [ETHTOOL_A_LINKINFO_TRANSCEIVER] = { .type = NLA_REJECT }, }; int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *tb[ETHTOOL_A_LINKINFO_MAX + 1]; struct ethtool_link_ksettings ksettings = {}; struct ethtool_link_settings *lsettings; struct ethnl_req_info req_info = {}; + struct nlattr **tb = info->attrs; struct net_device *dev; bool mod = false; int ret; - ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, - ETHTOOL_A_LINKINFO_MAX, linkinfo_set_policy, - info->extack); - if (ret < 0) - return ret; ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_LINKINFO_HEADER], genl_info_net(info), info->extack, diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c index 7044a2853886..c5bcb9abc8b9 100644 --- a/net/ethtool/linkmodes.c +++ b/net/ethtool/linkmodes.c @@ -18,17 +18,9 @@ struct linkmodes_reply_data { #define LINKMODES_REPDATA(__reply_base) \ container_of(__reply_base, struct linkmodes_reply_data, base) -static const struct nla_policy -linkmodes_get_policy[ETHTOOL_A_LINKMODES_MAX + 1] = { - [ETHTOOL_A_LINKMODES_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_LINKMODES_HEADER] = { .type = NLA_NESTED }, - [ETHTOOL_A_LINKMODES_AUTONEG] = { .type = NLA_REJECT }, - [ETHTOOL_A_LINKMODES_OURS] = { .type = NLA_REJECT }, - [ETHTOOL_A_LINKMODES_PEER] = { .type = NLA_REJECT }, - [ETHTOOL_A_LINKMODES_SPEED] = { .type = NLA_REJECT }, - [ETHTOOL_A_LINKMODES_DUPLEX] = { .type = NLA_REJECT }, - [ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG] = { .type = NLA_REJECT }, - [ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE] = { .type = NLA_REJECT }, +const struct nla_policy ethnl_linkmodes_get_policy[] = { + [ETHTOOL_A_LINKMODES_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), }; static int linkmodes_prepare_data(const struct ethnl_req_info *req_base, @@ -148,10 +140,8 @@ const struct ethnl_request_ops ethnl_linkmodes_request_ops = { .request_cmd = ETHTOOL_MSG_LINKMODES_GET, .reply_cmd = ETHTOOL_MSG_LINKMODES_GET_REPLY, .hdr_attr = ETHTOOL_A_LINKMODES_HEADER, - .max_attr = ETHTOOL_A_LINKMODES_MAX, .req_info_size = sizeof(struct linkmodes_req_info), .reply_data_size = sizeof(struct linkmodes_reply_data), - .request_policy = linkmodes_get_policy, .prepare_data = linkmodes_prepare_data, .reply_size = linkmodes_reply_size, @@ -272,19 +262,18 @@ static const struct link_mode_info link_mode_params[] = { __DEFINE_LINK_MODE_PARAMS(400000, LR4_ER4_FR4, Full), __DEFINE_LINK_MODE_PARAMS(400000, DR4, Full), __DEFINE_LINK_MODE_PARAMS(400000, CR4, Full), + __DEFINE_LINK_MODE_PARAMS(100, FX, Half), + __DEFINE_LINK_MODE_PARAMS(100, FX, Full), }; -static const struct nla_policy -linkmodes_set_policy[ETHTOOL_A_LINKMODES_MAX + 1] = { - [ETHTOOL_A_LINKMODES_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_LINKMODES_HEADER] = { .type = NLA_NESTED }, +const struct nla_policy ethnl_linkmodes_set_policy[] = { + [ETHTOOL_A_LINKMODES_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_LINKMODES_AUTONEG] = { .type = NLA_U8 }, [ETHTOOL_A_LINKMODES_OURS] = { .type = NLA_NESTED }, - [ETHTOOL_A_LINKMODES_PEER] = { .type = NLA_REJECT }, [ETHTOOL_A_LINKMODES_SPEED] = { .type = NLA_U32 }, [ETHTOOL_A_LINKMODES_DUPLEX] = { .type = NLA_U8 }, [ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG] = { .type = NLA_U8 }, - [ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE] = { .type = NLA_REJECT }, }; /* Set advertised link modes to all supported modes matching requested speed @@ -390,18 +379,13 @@ static int ethnl_update_linkmodes(struct genl_info *info, struct nlattr **tb, int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *tb[ETHTOOL_A_LINKMODES_MAX + 1]; struct ethtool_link_ksettings ksettings = {}; struct ethnl_req_info req_info = {}; + struct nlattr **tb = info->attrs; struct net_device *dev; bool mod = false; int ret; - ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, - ETHTOOL_A_LINKMODES_MAX, linkmodes_set_policy, - info->extack); - if (ret < 0) - return ret; ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_LINKMODES_HEADER], genl_info_net(info), info->extack, diff --git a/net/ethtool/linkstate.c b/net/ethtool/linkstate.c index 4834091ec24c..fb676f349455 100644 --- a/net/ethtool/linkstate.c +++ b/net/ethtool/linkstate.c @@ -20,15 +20,9 @@ struct linkstate_reply_data { #define LINKSTATE_REPDATA(__reply_base) \ container_of(__reply_base, struct linkstate_reply_data, base) -static const struct nla_policy -linkstate_get_policy[ETHTOOL_A_LINKSTATE_MAX + 1] = { - [ETHTOOL_A_LINKSTATE_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_LINKSTATE_HEADER] = { .type = NLA_NESTED }, - [ETHTOOL_A_LINKSTATE_LINK] = { .type = NLA_REJECT }, - [ETHTOOL_A_LINKSTATE_SQI] = { .type = NLA_REJECT }, - [ETHTOOL_A_LINKSTATE_SQI_MAX] = { .type = NLA_REJECT }, - [ETHTOOL_A_LINKSTATE_EXT_STATE] = { .type = NLA_REJECT }, - [ETHTOOL_A_LINKSTATE_EXT_SUBSTATE] = { .type = NLA_REJECT }, +const struct nla_policy ethnl_linkstate_get_policy[] = { + [ETHTOOL_A_LINKSTATE_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), }; static int linkstate_get_sqi(struct net_device *dev) @@ -179,10 +173,8 @@ const struct ethnl_request_ops ethnl_linkstate_request_ops = { .request_cmd = ETHTOOL_MSG_LINKSTATE_GET, .reply_cmd = ETHTOOL_MSG_LINKSTATE_GET_REPLY, .hdr_attr = ETHTOOL_A_LINKSTATE_HEADER, - .max_attr = ETHTOOL_A_LINKSTATE_MAX, .req_info_size = sizeof(struct linkstate_req_info), .reply_data_size = sizeof(struct linkstate_reply_data), - .request_policy = linkstate_get_policy, .prepare_data = linkstate_prepare_data, .reply_size = linkstate_reply_size, diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 0c3f54baec4e..50d3c8896f91 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -9,12 +9,24 @@ static struct genl_family ethtool_genl_family; static bool ethnl_ok __read_mostly; static u32 ethnl_bcast_seq; -static const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_MAX + 1] = { - [ETHTOOL_A_HEADER_UNSPEC] = { .type = NLA_REJECT }, +#define ETHTOOL_FLAGS_BASIC (ETHTOOL_FLAG_COMPACT_BITSETS | \ + ETHTOOL_FLAG_OMIT_REPLY) +#define ETHTOOL_FLAGS_STATS (ETHTOOL_FLAGS_BASIC | ETHTOOL_FLAG_STATS) + +const struct nla_policy ethnl_header_policy[] = { [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, .len = ALTIFNAMSIZ - 1 }, - [ETHTOOL_A_HEADER_FLAGS] = { .type = NLA_U32 }, + [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, + ETHTOOL_FLAGS_BASIC), +}; + +const struct nla_policy ethnl_header_policy_stats[] = { + [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, + [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, + .len = ALTIFNAMSIZ - 1 }, + [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, + ETHTOOL_FLAGS_STATS), }; /** @@ -37,7 +49,7 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, const struct nlattr *header, struct net *net, struct netlink_ext_ack *extack, bool require_dev) { - struct nlattr *tb[ETHTOOL_A_HEADER_MAX + 1]; + struct nlattr *tb[ARRAY_SIZE(ethnl_header_policy)]; const struct nlattr *devname_attr; struct net_device *dev = NULL; u32 flags = 0; @@ -47,19 +59,15 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, NL_SET_ERR_MSG(extack, "request header missing"); return -EINVAL; } - ret = nla_parse_nested(tb, ETHTOOL_A_HEADER_MAX, header, - ethnl_header_policy, extack); + /* No validation here, command policy should have a nested policy set + * for the header, therefore validation should have already been done. + */ + ret = nla_parse_nested(tb, ARRAY_SIZE(ethnl_header_policy) - 1, header, + NULL, extack); if (ret < 0) return ret; - if (tb[ETHTOOL_A_HEADER_FLAGS]) { + if (tb[ETHTOOL_A_HEADER_FLAGS]) flags = nla_get_u32(tb[ETHTOOL_A_HEADER_FLAGS]); - if (flags & ~ETHTOOL_FLAG_ALL) { - NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_HEADER_FLAGS], - "unrecognized request flags"); - nl_set_extack_cookie_u32(extack, ETHTOOL_FLAG_ALL); - return -EOPNOTSUPP; - } - } devname_attr = tb[ETHTOOL_A_HEADER_DEV_NAME]; if (tb[ETHTOOL_A_HEADER_DEV_INDEX]) { @@ -247,7 +255,7 @@ static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) /** * ethnl_default_parse() - Parse request message * @req_info: pointer to structure to put data into - * @nlhdr: pointer to request message header + * @tb: parsed attributes * @net: request netns * @request_ops: struct request_ops for request type * @extack: netlink extack for error reporting @@ -259,37 +267,24 @@ static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) * Return: 0 on success or negative error code */ static int ethnl_default_parse(struct ethnl_req_info *req_info, - const struct nlmsghdr *nlhdr, struct net *net, + struct nlattr **tb, struct net *net, const struct ethnl_request_ops *request_ops, struct netlink_ext_ack *extack, bool require_dev) { - struct nlattr **tb; int ret; - tb = kmalloc_array(request_ops->max_attr + 1, sizeof(tb[0]), - GFP_KERNEL); - if (!tb) - return -ENOMEM; - - ret = nlmsg_parse(nlhdr, GENL_HDRLEN, tb, request_ops->max_attr, - request_ops->request_policy, extack); - if (ret < 0) - goto out; ret = ethnl_parse_header_dev_get(req_info, tb[request_ops->hdr_attr], net, extack, require_dev); if (ret < 0) - goto out; + return ret; if (request_ops->parse_request) { ret = request_ops->parse_request(req_info, tb, extack); if (ret < 0) - goto out; + return ret; } - ret = 0; -out: - kfree(tb); - return ret; + return 0; } /** @@ -334,8 +329,8 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info) return -ENOMEM; } - ret = ethnl_default_parse(req_info, info->nlhdr, genl_info_net(info), ops, - info->extack, !ops->allow_nodev_do); + ret = ethnl_default_parse(req_info, info->attrs, genl_info_net(info), + ops, info->extack, !ops->allow_nodev_do); if (ret < 0) goto err_dev; ethnl_init_reply_data(reply_data, ops, req_info->dev); @@ -480,6 +475,7 @@ out: /* generic ->start() handler for GET requests */ static int ethnl_default_start(struct netlink_callback *cb) { + const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct ethnl_dump_ctx *ctx = ethnl_dump_context(cb); struct ethnl_reply_data *reply_data; const struct ethnl_request_ops *ops; @@ -502,8 +498,8 @@ static int ethnl_default_start(struct netlink_callback *cb) goto free_req_info; } - ret = ethnl_default_parse(req_info, cb->nlh, sock_net(cb->skb->sk), ops, - cb->extack, false); + ret = ethnl_default_parse(req_info, info->attrs, sock_net(cb->skb->sk), + ops, cb->extack, false); if (req_info->dev) { /* We ignore device specification in dump requests but as the * same parser as for non-dump (doit) requests is used, it @@ -696,6 +692,8 @@ static const struct genl_ops ethtool_genl_ops[] = { .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, + .policy = ethnl_strset_get_policy, + .maxattr = ARRAY_SIZE(ethnl_strset_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_LINKINFO_GET, @@ -703,11 +701,15 @@ static const struct genl_ops ethtool_genl_ops[] = { .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, + .policy = ethnl_linkinfo_get_policy, + .maxattr = ARRAY_SIZE(ethnl_linkinfo_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_LINKINFO_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_linkinfo, + .policy = ethnl_linkinfo_set_policy, + .maxattr = ARRAY_SIZE(ethnl_linkinfo_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_LINKMODES_GET, @@ -715,11 +717,15 @@ static const struct genl_ops ethtool_genl_ops[] = { .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, + .policy = ethnl_linkmodes_get_policy, + .maxattr = ARRAY_SIZE(ethnl_linkmodes_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_LINKMODES_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_linkmodes, + .policy = ethnl_linkmodes_set_policy, + .maxattr = ARRAY_SIZE(ethnl_linkmodes_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_LINKSTATE_GET, @@ -727,6 +733,8 @@ static const struct genl_ops ethtool_genl_ops[] = { .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, + .policy = ethnl_linkstate_get_policy, + .maxattr = ARRAY_SIZE(ethnl_linkstate_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_DEBUG_GET, @@ -734,11 +742,15 @@ static const struct genl_ops ethtool_genl_ops[] = { .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, + .policy = ethnl_debug_get_policy, + .maxattr = ARRAY_SIZE(ethnl_debug_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_DEBUG_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_debug, + .policy = ethnl_debug_set_policy, + .maxattr = ARRAY_SIZE(ethnl_debug_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_WOL_GET, @@ -747,11 +759,15 @@ static const struct genl_ops ethtool_genl_ops[] = { .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, + .policy = ethnl_wol_get_policy, + .maxattr = ARRAY_SIZE(ethnl_wol_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_WOL_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_wol, + .policy = ethnl_wol_set_policy, + .maxattr = ARRAY_SIZE(ethnl_wol_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_FEATURES_GET, @@ -759,11 +775,15 @@ static const struct genl_ops ethtool_genl_ops[] = { .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, + .policy = ethnl_features_get_policy, + .maxattr = ARRAY_SIZE(ethnl_features_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_FEATURES_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_features, + .policy = ethnl_features_set_policy, + .maxattr = ARRAY_SIZE(ethnl_features_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_PRIVFLAGS_GET, @@ -771,11 +791,15 @@ static const struct genl_ops ethtool_genl_ops[] = { .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, + .policy = ethnl_privflags_get_policy, + .maxattr = ARRAY_SIZE(ethnl_privflags_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_PRIVFLAGS_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_privflags, + .policy = ethnl_privflags_set_policy, + .maxattr = ARRAY_SIZE(ethnl_privflags_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_RINGS_GET, @@ -783,11 +807,15 @@ static const struct genl_ops ethtool_genl_ops[] = { .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, + .policy = ethnl_rings_get_policy, + .maxattr = ARRAY_SIZE(ethnl_rings_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_RINGS_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_rings, + .policy = ethnl_rings_set_policy, + .maxattr = ARRAY_SIZE(ethnl_rings_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_CHANNELS_GET, @@ -795,11 +823,15 @@ static const struct genl_ops ethtool_genl_ops[] = { .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, + .policy = ethnl_channels_get_policy, + .maxattr = ARRAY_SIZE(ethnl_channels_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_CHANNELS_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_channels, + .policy = ethnl_channels_set_policy, + .maxattr = ARRAY_SIZE(ethnl_channels_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_COALESCE_GET, @@ -807,11 +839,15 @@ static const struct genl_ops ethtool_genl_ops[] = { .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, + .policy = ethnl_coalesce_get_policy, + .maxattr = ARRAY_SIZE(ethnl_coalesce_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_COALESCE_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_coalesce, + .policy = ethnl_coalesce_set_policy, + .maxattr = ARRAY_SIZE(ethnl_coalesce_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_PAUSE_GET, @@ -819,11 +855,15 @@ static const struct genl_ops ethtool_genl_ops[] = { .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, + .policy = ethnl_pause_get_policy, + .maxattr = ARRAY_SIZE(ethnl_pause_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_PAUSE_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_pause, + .policy = ethnl_pause_set_policy, + .maxattr = ARRAY_SIZE(ethnl_pause_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_EEE_GET, @@ -831,11 +871,15 @@ static const struct genl_ops ethtool_genl_ops[] = { .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, + .policy = ethnl_eee_get_policy, + .maxattr = ARRAY_SIZE(ethnl_eee_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_EEE_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_eee, + .policy = ethnl_eee_set_policy, + .maxattr = ARRAY_SIZE(ethnl_eee_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_TSINFO_GET, @@ -843,22 +887,30 @@ static const struct genl_ops ethtool_genl_ops[] = { .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, + .policy = ethnl_tsinfo_get_policy, + .maxattr = ARRAY_SIZE(ethnl_tsinfo_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_CABLE_TEST_ACT, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_act_cable_test, + .policy = ethnl_cable_test_act_policy, + .maxattr = ARRAY_SIZE(ethnl_cable_test_act_policy) - 1, }, { .cmd = ETHTOOL_MSG_CABLE_TEST_TDR_ACT, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_act_cable_test_tdr, + .policy = ethnl_cable_test_tdr_act_policy, + .maxattr = ARRAY_SIZE(ethnl_cable_test_tdr_act_policy) - 1, }, { .cmd = ETHTOOL_MSG_TUNNEL_INFO_GET, .doit = ethnl_tunnel_info_doit, .start = ethnl_tunnel_info_start, .dumpit = ethnl_tunnel_info_dumpit, + .policy = ethnl_tunnel_info_get_policy, + .maxattr = ARRAY_SIZE(ethnl_tunnel_info_get_policy) - 1, }, }; diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index e2085005caac..d8efec516d86 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -266,10 +266,8 @@ static inline void ethnl_ops_complete(struct net_device *dev) * @request_cmd: command id for request (GET) * @reply_cmd: command id for reply (GET_REPLY) * @hdr_attr: attribute type for request header - * @max_attr: maximum (top level) attribute type * @req_info_size: size of request info * @reply_data_size: size of reply data - * @request_policy: netlink policy for message contents * @allow_nodev_do: allow non-dump request with no device identification * @parse_request: * Parse request except common header (struct ethnl_req_info). Common @@ -312,10 +310,8 @@ struct ethnl_request_ops { u8 request_cmd; u8 reply_cmd; u16 hdr_attr; - unsigned int max_attr; unsigned int req_info_size; unsigned int reply_data_size; - const struct nla_policy *request_policy; bool allow_nodev_do; int (*parse_request)(struct ethnl_req_info *req_info, @@ -349,6 +345,37 @@ extern const struct ethnl_request_ops ethnl_pause_request_ops; extern const struct ethnl_request_ops ethnl_eee_request_ops; extern const struct ethnl_request_ops ethnl_tsinfo_request_ops; +extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; +extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; +extern const struct nla_policy ethnl_strset_get_policy[ETHTOOL_A_STRSET_COUNTS_ONLY + 1]; +extern const struct nla_policy ethnl_linkinfo_get_policy[ETHTOOL_A_LINKINFO_HEADER + 1]; +extern const struct nla_policy ethnl_linkinfo_set_policy[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL + 1]; +extern const struct nla_policy ethnl_linkmodes_get_policy[ETHTOOL_A_LINKMODES_HEADER + 1]; +extern const struct nla_policy ethnl_linkmodes_set_policy[ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG + 1]; +extern const struct nla_policy ethnl_linkstate_get_policy[ETHTOOL_A_LINKSTATE_HEADER + 1]; +extern const struct nla_policy ethnl_debug_get_policy[ETHTOOL_A_DEBUG_HEADER + 1]; +extern const struct nla_policy ethnl_debug_set_policy[ETHTOOL_A_DEBUG_MSGMASK + 1]; +extern const struct nla_policy ethnl_wol_get_policy[ETHTOOL_A_WOL_HEADER + 1]; +extern const struct nla_policy ethnl_wol_set_policy[ETHTOOL_A_WOL_SOPASS + 1]; +extern const struct nla_policy ethnl_features_get_policy[ETHTOOL_A_FEATURES_HEADER + 1]; +extern const struct nla_policy ethnl_features_set_policy[ETHTOOL_A_FEATURES_WANTED + 1]; +extern const struct nla_policy ethnl_privflags_get_policy[ETHTOOL_A_PRIVFLAGS_HEADER + 1]; +extern const struct nla_policy ethnl_privflags_set_policy[ETHTOOL_A_PRIVFLAGS_FLAGS + 1]; +extern const struct nla_policy ethnl_rings_get_policy[ETHTOOL_A_RINGS_HEADER + 1]; +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_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]; +extern const struct nla_policy ethnl_eee_set_policy[ETHTOOL_A_EEE_TX_LPI_TIMER + 1]; +extern const struct nla_policy ethnl_tsinfo_get_policy[ETHTOOL_A_TSINFO_HEADER + 1]; +extern const struct nla_policy ethnl_cable_test_act_policy[ETHTOOL_A_CABLE_TEST_HEADER + 1]; +extern const struct nla_policy ethnl_cable_test_tdr_act_policy[ETHTOOL_A_CABLE_TEST_TDR_CFG + 1]; +extern const struct nla_policy ethnl_tunnel_info_get_policy[ETHTOOL_A_TUNNEL_INFO_HEADER + 1]; + int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info); int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info); int ethnl_set_debug(struct sk_buff *skb, struct genl_info *info); diff --git a/net/ethtool/pause.c b/net/ethtool/pause.c index 7aea35d1e8a5..09998dc5c185 100644 --- a/net/ethtool/pause.c +++ b/net/ethtool/pause.c @@ -10,20 +10,23 @@ struct pause_req_info { struct pause_reply_data { struct ethnl_reply_data base; struct ethtool_pauseparam pauseparam; + struct ethtool_pause_stats pausestat; }; #define PAUSE_REPDATA(__reply_base) \ container_of(__reply_base, struct pause_reply_data, base) -static const struct nla_policy -pause_get_policy[ETHTOOL_A_PAUSE_MAX + 1] = { - [ETHTOOL_A_PAUSE_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_PAUSE_HEADER] = { .type = NLA_NESTED }, - [ETHTOOL_A_PAUSE_AUTONEG] = { .type = NLA_REJECT }, - [ETHTOOL_A_PAUSE_RX] = { .type = NLA_REJECT }, - [ETHTOOL_A_PAUSE_TX] = { .type = NLA_REJECT }, +const struct nla_policy ethnl_pause_get_policy[] = { + [ETHTOOL_A_PAUSE_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy_stats), }; +static void ethtool_stats_init(u64 *stats, unsigned int n) +{ + while (n--) + stats[n] = ETHTOOL_STAT_NOT_SET; +} + static int pause_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, struct genl_info *info) @@ -34,10 +37,17 @@ static int pause_prepare_data(const struct ethnl_req_info *req_base, if (!dev->ethtool_ops->get_pauseparam) return -EOPNOTSUPP; + ret = ethnl_ops_begin(dev); if (ret < 0) return ret; dev->ethtool_ops->get_pauseparam(dev, &data->pauseparam); + if (req_base->flags & ETHTOOL_FLAG_STATS && + dev->ethtool_ops->get_pause_stats) { + ethtool_stats_init((u64 *)&data->pausestat, + sizeof(data->pausestat) / 8); + dev->ethtool_ops->get_pause_stats(dev, &data->pausestat); + } ethnl_ops_complete(dev); return 0; @@ -46,9 +56,50 @@ static int pause_prepare_data(const struct ethnl_req_info *req_base, static int pause_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { - return nla_total_size(sizeof(u8)) + /* _PAUSE_AUTONEG */ + int n = nla_total_size(sizeof(u8)) + /* _PAUSE_AUTONEG */ nla_total_size(sizeof(u8)) + /* _PAUSE_RX */ nla_total_size(sizeof(u8)); /* _PAUSE_TX */ + + if (req_base->flags & ETHTOOL_FLAG_STATS) + n += nla_total_size(0) + /* _PAUSE_STATS */ + nla_total_size_64bit(sizeof(u64)) * + (ETHTOOL_A_PAUSE_STAT_MAX - 2); + return n; +} + +static int ethtool_put_stat(struct sk_buff *skb, u64 val, u16 attrtype, + u16 padtype) +{ + if (val == ETHTOOL_STAT_NOT_SET) + return 0; + if (nla_put_u64_64bit(skb, attrtype, val, padtype)) + return -EMSGSIZE; + + return 0; +} + +static int pause_put_stats(struct sk_buff *skb, + const struct ethtool_pause_stats *pause_stats) +{ + const u16 pad = ETHTOOL_A_PAUSE_STAT_PAD; + struct nlattr *nest; + + nest = nla_nest_start(skb, ETHTOOL_A_PAUSE_STATS); + if (!nest) + return -EMSGSIZE; + + if (ethtool_put_stat(skb, pause_stats->tx_pause_frames, + ETHTOOL_A_PAUSE_STAT_TX_FRAMES, pad) || + ethtool_put_stat(skb, pause_stats->rx_pause_frames, + ETHTOOL_A_PAUSE_STAT_RX_FRAMES, pad)) + goto err_cancel; + + nla_nest_end(skb, nest); + return 0; + +err_cancel: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; } static int pause_fill_reply(struct sk_buff *skb, @@ -63,6 +114,10 @@ static int pause_fill_reply(struct sk_buff *skb, nla_put_u8(skb, ETHTOOL_A_PAUSE_TX, !!pauseparam->tx_pause)) return -EMSGSIZE; + if (req_base->flags & ETHTOOL_FLAG_STATS && + pause_put_stats(skb, &data->pausestat)) + return -EMSGSIZE; + return 0; } @@ -70,10 +125,8 @@ const struct ethnl_request_ops ethnl_pause_request_ops = { .request_cmd = ETHTOOL_MSG_PAUSE_GET, .reply_cmd = ETHTOOL_MSG_PAUSE_GET_REPLY, .hdr_attr = ETHTOOL_A_PAUSE_HEADER, - .max_attr = ETHTOOL_A_PAUSE_MAX, .req_info_size = sizeof(struct pause_req_info), .reply_data_size = sizeof(struct pause_reply_data), - .request_policy = pause_get_policy, .prepare_data = pause_prepare_data, .reply_size = pause_reply_size, @@ -82,10 +135,9 @@ const struct ethnl_request_ops ethnl_pause_request_ops = { /* PAUSE_SET */ -static const struct nla_policy -pause_set_policy[ETHTOOL_A_PAUSE_MAX + 1] = { - [ETHTOOL_A_PAUSE_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_PAUSE_HEADER] = { .type = NLA_NESTED }, +const struct nla_policy ethnl_pause_set_policy[] = { + [ETHTOOL_A_PAUSE_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_PAUSE_AUTONEG] = { .type = NLA_U8 }, [ETHTOOL_A_PAUSE_RX] = { .type = NLA_U8 }, [ETHTOOL_A_PAUSE_TX] = { .type = NLA_U8 }, @@ -93,18 +145,14 @@ pause_set_policy[ETHTOOL_A_PAUSE_MAX + 1] = { int ethnl_set_pause(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *tb[ETHTOOL_A_PAUSE_MAX + 1]; struct ethtool_pauseparam params = {}; struct ethnl_req_info req_info = {}; + struct nlattr **tb = info->attrs; const struct ethtool_ops *ops; struct net_device *dev; bool mod = false; int ret; - ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, ETHTOOL_A_PAUSE_MAX, - pause_set_policy, info->extack); - if (ret < 0) - return ret; ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_PAUSE_HEADER], genl_info_net(info), info->extack, diff --git a/net/ethtool/privflags.c b/net/ethtool/privflags.c index 77447dceb109..fc9f3be23a19 100644 --- a/net/ethtool/privflags.c +++ b/net/ethtool/privflags.c @@ -18,11 +18,9 @@ struct privflags_reply_data { #define PRIVFLAGS_REPDATA(__reply_base) \ container_of(__reply_base, struct privflags_reply_data, base) -static const struct nla_policy -privflags_get_policy[ETHTOOL_A_PRIVFLAGS_MAX + 1] = { - [ETHTOOL_A_PRIVFLAGS_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_PRIVFLAGS_HEADER] = { .type = NLA_NESTED }, - [ETHTOOL_A_PRIVFLAGS_FLAGS] = { .type = NLA_REJECT }, +const struct nla_policy ethnl_privflags_get_policy[] = { + [ETHTOOL_A_PRIVFLAGS_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), }; static int ethnl_get_priv_flags_info(struct net_device *dev, @@ -124,10 +122,8 @@ const struct ethnl_request_ops ethnl_privflags_request_ops = { .request_cmd = ETHTOOL_MSG_PRIVFLAGS_GET, .reply_cmd = ETHTOOL_MSG_PRIVFLAGS_GET_REPLY, .hdr_attr = ETHTOOL_A_PRIVFLAGS_HEADER, - .max_attr = ETHTOOL_A_PRIVFLAGS_MAX, .req_info_size = sizeof(struct privflags_req_info), .reply_data_size = sizeof(struct privflags_reply_data), - .request_policy = privflags_get_policy, .prepare_data = privflags_prepare_data, .reply_size = privflags_reply_size, @@ -137,18 +133,17 @@ const struct ethnl_request_ops ethnl_privflags_request_ops = { /* PRIVFLAGS_SET */ -static const struct nla_policy -privflags_set_policy[ETHTOOL_A_PRIVFLAGS_MAX + 1] = { - [ETHTOOL_A_PRIVFLAGS_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_PRIVFLAGS_HEADER] = { .type = NLA_NESTED }, +const struct nla_policy ethnl_privflags_set_policy[] = { + [ETHTOOL_A_PRIVFLAGS_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_PRIVFLAGS_FLAGS] = { .type = NLA_NESTED }, }; int ethnl_set_privflags(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *tb[ETHTOOL_A_PRIVFLAGS_MAX + 1]; const char (*names)[ETH_GSTRING_LEN] = NULL; struct ethnl_req_info req_info = {}; + struct nlattr **tb = info->attrs; const struct ethtool_ops *ops; struct net_device *dev; unsigned int nflags; @@ -157,11 +152,6 @@ int ethnl_set_privflags(struct sk_buff *skb, struct genl_info *info) u32 flags; int ret; - ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, - ETHTOOL_A_PRIVFLAGS_MAX, privflags_set_policy, - info->extack); - if (ret < 0) - return ret; if (!tb[ETHTOOL_A_PRIVFLAGS_FLAGS]) return -EINVAL; ret = ethnl_bitset_is_compact(tb[ETHTOOL_A_PRIVFLAGS_FLAGS], &compact); diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c index 5422526f4eef..4e097812a967 100644 --- a/net/ethtool/rings.c +++ b/net/ethtool/rings.c @@ -15,18 +15,9 @@ struct rings_reply_data { #define RINGS_REPDATA(__reply_base) \ container_of(__reply_base, struct rings_reply_data, base) -static const struct nla_policy -rings_get_policy[ETHTOOL_A_RINGS_MAX + 1] = { - [ETHTOOL_A_RINGS_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_RINGS_HEADER] = { .type = NLA_NESTED }, - [ETHTOOL_A_RINGS_RX_MAX] = { .type = NLA_REJECT }, - [ETHTOOL_A_RINGS_RX_MINI_MAX] = { .type = NLA_REJECT }, - [ETHTOOL_A_RINGS_RX_JUMBO_MAX] = { .type = NLA_REJECT }, - [ETHTOOL_A_RINGS_TX_MAX] = { .type = NLA_REJECT }, - [ETHTOOL_A_RINGS_RX] = { .type = NLA_REJECT }, - [ETHTOOL_A_RINGS_RX_MINI] = { .type = NLA_REJECT }, - [ETHTOOL_A_RINGS_RX_JUMBO] = { .type = NLA_REJECT }, - [ETHTOOL_A_RINGS_TX] = { .type = NLA_REJECT }, +const struct nla_policy ethnl_rings_get_policy[] = { + [ETHTOOL_A_RINGS_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), }; static int rings_prepare_data(const struct ethnl_req_info *req_base, @@ -97,10 +88,8 @@ const struct ethnl_request_ops ethnl_rings_request_ops = { .request_cmd = ETHTOOL_MSG_RINGS_GET, .reply_cmd = ETHTOOL_MSG_RINGS_GET_REPLY, .hdr_attr = ETHTOOL_A_RINGS_HEADER, - .max_attr = ETHTOOL_A_RINGS_MAX, .req_info_size = sizeof(struct rings_req_info), .reply_data_size = sizeof(struct rings_reply_data), - .request_policy = rings_get_policy, .prepare_data = rings_prepare_data, .reply_size = rings_reply_size, @@ -109,14 +98,9 @@ const struct ethnl_request_ops ethnl_rings_request_ops = { /* RINGS_SET */ -static const struct nla_policy -rings_set_policy[ETHTOOL_A_RINGS_MAX + 1] = { - [ETHTOOL_A_RINGS_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_RINGS_HEADER] = { .type = NLA_NESTED }, - [ETHTOOL_A_RINGS_RX_MAX] = { .type = NLA_REJECT }, - [ETHTOOL_A_RINGS_RX_MINI_MAX] = { .type = NLA_REJECT }, - [ETHTOOL_A_RINGS_RX_JUMBO_MAX] = { .type = NLA_REJECT }, - [ETHTOOL_A_RINGS_TX_MAX] = { .type = NLA_REJECT }, +const struct nla_policy ethnl_rings_set_policy[] = { + [ETHTOOL_A_RINGS_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_RINGS_RX] = { .type = NLA_U32 }, [ETHTOOL_A_RINGS_RX_MINI] = { .type = NLA_U32 }, [ETHTOOL_A_RINGS_RX_JUMBO] = { .type = NLA_U32 }, @@ -125,20 +109,15 @@ rings_set_policy[ETHTOOL_A_RINGS_MAX + 1] = { int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *tb[ETHTOOL_A_RINGS_MAX + 1]; struct ethtool_ringparam ringparam = {}; struct ethnl_req_info req_info = {}; + struct nlattr **tb = info->attrs; const struct nlattr *err_attr; const struct ethtool_ops *ops; struct net_device *dev; bool mod = false; int ret; - ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, - ETHTOOL_A_RINGS_MAX, rings_set_policy, - info->extack); - if (ret < 0) - return ret; ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_RINGS_HEADER], genl_info_net(info), info->extack, diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c index 82707b662fe4..0baad0ce1832 100644 --- a/net/ethtool/strset.c +++ b/net/ethtool/strset.c @@ -99,18 +99,15 @@ struct strset_reply_data { #define STRSET_REPDATA(__reply_base) \ container_of(__reply_base, struct strset_reply_data, base) -static const struct nla_policy strset_get_policy[ETHTOOL_A_STRSET_MAX + 1] = { - [ETHTOOL_A_STRSET_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_STRSET_HEADER] = { .type = NLA_NESTED }, +const struct nla_policy ethnl_strset_get_policy[] = { + [ETHTOOL_A_STRSET_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_STRSET_STRINGSETS] = { .type = NLA_NESTED }, + [ETHTOOL_A_STRSET_COUNTS_ONLY] = { .type = NLA_FLAG }, }; -static const struct nla_policy -get_stringset_policy[ETHTOOL_A_STRINGSET_MAX + 1] = { - [ETHTOOL_A_STRINGSET_UNSPEC] = { .type = NLA_REJECT }, +static const struct nla_policy get_stringset_policy[] = { [ETHTOOL_A_STRINGSET_ID] = { .type = NLA_U32 }, - [ETHTOOL_A_STRINGSET_COUNT] = { .type = NLA_REJECT }, - [ETHTOOL_A_STRINGSET_STRINGS] = { .type = NLA_REJECT }, }; /** @@ -138,10 +135,10 @@ static bool strset_include(const struct strset_req_info *info, static int strset_get_id(const struct nlattr *nest, u32 *val, struct netlink_ext_ack *extack) { - struct nlattr *tb[ETHTOOL_A_STRINGSET_MAX + 1]; + struct nlattr *tb[ARRAY_SIZE(get_stringset_policy)]; int ret; - ret = nla_parse_nested(tb, ETHTOOL_A_STRINGSET_MAX, nest, + ret = nla_parse_nested(tb, ARRAY_SIZE(get_stringset_policy) - 1, nest, get_stringset_policy, extack); if (ret < 0) return ret; @@ -152,9 +149,7 @@ static int strset_get_id(const struct nlattr *nest, u32 *val, return 0; } -static const struct nla_policy -strset_stringsets_policy[ETHTOOL_A_STRINGSETS_MAX + 1] = { - [ETHTOOL_A_STRINGSETS_UNSPEC] = { .type = NLA_REJECT }, +static const struct nla_policy strset_stringsets_policy[] = { [ETHTOOL_A_STRINGSETS_STRINGSET] = { .type = NLA_NESTED }, }; @@ -169,7 +164,8 @@ static int strset_parse_request(struct ethnl_req_info *req_base, if (!nest) return 0; - ret = nla_validate_nested(nest, ETHTOOL_A_STRINGSETS_MAX, + ret = nla_validate_nested(nest, + ARRAY_SIZE(strset_stringsets_policy) - 1, strset_stringsets_policy, extack); if (ret < 0) return ret; @@ -445,10 +441,8 @@ const struct ethnl_request_ops ethnl_strset_request_ops = { .request_cmd = ETHTOOL_MSG_STRSET_GET, .reply_cmd = ETHTOOL_MSG_STRSET_GET_REPLY, .hdr_attr = ETHTOOL_A_STRSET_HEADER, - .max_attr = ETHTOOL_A_STRSET_MAX, .req_info_size = sizeof(struct strset_req_info), .reply_data_size = sizeof(struct strset_reply_data), - .request_policy = strset_get_policy, .allow_nodev_do = true, .parse_request = strset_parse_request, diff --git a/net/ethtool/tsinfo.c b/net/ethtool/tsinfo.c index 7cb5b512b77c..63b5814bd460 100644 --- a/net/ethtool/tsinfo.c +++ b/net/ethtool/tsinfo.c @@ -18,14 +18,9 @@ struct tsinfo_reply_data { #define TSINFO_REPDATA(__reply_base) \ container_of(__reply_base, struct tsinfo_reply_data, base) -static const struct nla_policy -tsinfo_get_policy[ETHTOOL_A_TSINFO_MAX + 1] = { - [ETHTOOL_A_TSINFO_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_TSINFO_HEADER] = { .type = NLA_NESTED }, - [ETHTOOL_A_TSINFO_TIMESTAMPING] = { .type = NLA_REJECT }, - [ETHTOOL_A_TSINFO_TX_TYPES] = { .type = NLA_REJECT }, - [ETHTOOL_A_TSINFO_RX_FILTERS] = { .type = NLA_REJECT }, - [ETHTOOL_A_TSINFO_PHC_INDEX] = { .type = NLA_REJECT }, +const struct nla_policy ethnl_tsinfo_get_policy[] = { + [ETHTOOL_A_TSINFO_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), }; static int tsinfo_prepare_data(const struct ethnl_req_info *req_base, @@ -132,10 +127,8 @@ const struct ethnl_request_ops ethnl_tsinfo_request_ops = { .request_cmd = ETHTOOL_MSG_TSINFO_GET, .reply_cmd = ETHTOOL_MSG_TSINFO_GET_REPLY, .hdr_attr = ETHTOOL_A_TSINFO_HEADER, - .max_attr = ETHTOOL_A_TSINFO_MAX, .req_info_size = sizeof(struct tsinfo_req_info), .reply_data_size = sizeof(struct tsinfo_reply_data), - .request_policy = tsinfo_get_policy, .prepare_data = tsinfo_prepare_data, .reply_size = tsinfo_reply_size, diff --git a/net/ethtool/tunnels.c b/net/ethtool/tunnels.c index d93bf2da0f34..e7f2ee0d2471 100644 --- a/net/ethtool/tunnels.c +++ b/net/ethtool/tunnels.c @@ -8,10 +8,9 @@ #include "common.h" #include "netlink.h" -static const struct nla_policy -ethtool_tunnel_info_policy[ETHTOOL_A_TUNNEL_INFO_MAX + 1] = { - [ETHTOOL_A_TUNNEL_INFO_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_TUNNEL_INFO_HEADER] = { .type = NLA_NESTED }, +const struct nla_policy ethnl_tunnel_info_get_policy[] = { + [ETHTOOL_A_TUNNEL_INFO_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), }; static_assert(ETHTOOL_UDP_TUNNEL_TYPE_VXLAN == ilog2(UDP_TUNNEL_TYPE_VXLAN)); @@ -161,35 +160,19 @@ err_cancel_ports: return -EMSGSIZE; } -static int -ethnl_tunnel_info_req_parse(struct ethnl_req_info *req_info, - const struct nlmsghdr *nlhdr, struct net *net, - struct netlink_ext_ack *extack, bool require_dev) -{ - struct nlattr *tb[ETHTOOL_A_TUNNEL_INFO_MAX + 1]; - int ret; - - ret = nlmsg_parse(nlhdr, GENL_HDRLEN, tb, ETHTOOL_A_TUNNEL_INFO_MAX, - ethtool_tunnel_info_policy, extack); - if (ret < 0) - return ret; - - return ethnl_parse_header_dev_get(req_info, - tb[ETHTOOL_A_TUNNEL_INFO_HEADER], - net, extack, require_dev); -} - int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info) { struct ethnl_req_info req_info = {}; + struct nlattr **tb = info->attrs; struct sk_buff *rskb; void *reply_payload; int reply_len; int ret; - ret = ethnl_tunnel_info_req_parse(&req_info, info->nlhdr, - genl_info_net(info), info->extack, - true); + ret = ethnl_parse_header_dev_get(&req_info, + tb[ETHTOOL_A_TUNNEL_INFO_HEADER], + genl_info_net(info), info->extack, + true); if (ret < 0) return ret; @@ -233,16 +216,19 @@ struct ethnl_tunnel_info_dump_ctx { int ethnl_tunnel_info_start(struct netlink_callback *cb) { + const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct ethnl_tunnel_info_dump_ctx *ctx = (void *)cb->ctx; + struct nlattr **tb = info->attrs; int ret; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); memset(ctx, 0, sizeof(*ctx)); - ret = ethnl_tunnel_info_req_parse(&ctx->req_info, cb->nlh, - sock_net(cb->skb->sk), cb->extack, - false); + ret = ethnl_parse_header_dev_get(&ctx->req_info, + tb[ETHTOOL_A_TUNNEL_INFO_HEADER], + sock_net(cb->skb->sk), cb->extack, + false); if (ctx->req_info.dev) { dev_put(ctx->req_info.dev); ctx->req_info.dev = NULL; diff --git a/net/ethtool/wol.c b/net/ethtool/wol.c index 1798421e9f1c..ada7df2331d2 100644 --- a/net/ethtool/wol.c +++ b/net/ethtool/wol.c @@ -17,12 +17,9 @@ struct wol_reply_data { #define WOL_REPDATA(__reply_base) \ container_of(__reply_base, struct wol_reply_data, base) -static const struct nla_policy -wol_get_policy[ETHTOOL_A_WOL_MAX + 1] = { - [ETHTOOL_A_WOL_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_WOL_HEADER] = { .type = NLA_NESTED }, - [ETHTOOL_A_WOL_MODES] = { .type = NLA_REJECT }, - [ETHTOOL_A_WOL_SOPASS] = { .type = NLA_REJECT }, +const struct nla_policy ethnl_wol_get_policy[] = { + [ETHTOOL_A_WOL_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), }; static int wol_prepare_data(const struct ethnl_req_info *req_base, @@ -89,10 +86,8 @@ const struct ethnl_request_ops ethnl_wol_request_ops = { .request_cmd = ETHTOOL_MSG_WOL_GET, .reply_cmd = ETHTOOL_MSG_WOL_GET_REPLY, .hdr_attr = ETHTOOL_A_WOL_HEADER, - .max_attr = ETHTOOL_A_WOL_MAX, .req_info_size = sizeof(struct wol_req_info), .reply_data_size = sizeof(struct wol_reply_data), - .request_policy = wol_get_policy, .prepare_data = wol_prepare_data, .reply_size = wol_reply_size, @@ -101,10 +96,9 @@ const struct ethnl_request_ops ethnl_wol_request_ops = { /* WOL_SET */ -static const struct nla_policy -wol_set_policy[ETHTOOL_A_WOL_MAX + 1] = { - [ETHTOOL_A_WOL_UNSPEC] = { .type = NLA_REJECT }, - [ETHTOOL_A_WOL_HEADER] = { .type = NLA_NESTED }, +const struct nla_policy ethnl_wol_set_policy[] = { + [ETHTOOL_A_WOL_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_WOL_MODES] = { .type = NLA_NESTED }, [ETHTOOL_A_WOL_SOPASS] = { .type = NLA_BINARY, .len = SOPASS_MAX }, @@ -113,16 +107,12 @@ wol_set_policy[ETHTOOL_A_WOL_MAX + 1] = { int ethnl_set_wol(struct sk_buff *skb, struct genl_info *info) { struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; - struct nlattr *tb[ETHTOOL_A_WOL_MAX + 1]; struct ethnl_req_info req_info = {}; + struct nlattr **tb = info->attrs; struct net_device *dev; bool mod = false; int ret; - ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, ETHTOOL_A_WOL_MAX, - wol_set_policy, info->extack); - if (ret < 0) - return ret; ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_WOL_HEADER], genl_info_net(info), info->extack, true); diff --git a/net/hsr/hsr_debugfs.c b/net/hsr/hsr_debugfs.c index 7e11a6c35bc3..4cfd9e829c7b 100644 --- a/net/hsr/hsr_debugfs.c +++ b/net/hsr/hsr_debugfs.c @@ -60,17 +60,7 @@ hsr_node_table_show(struct seq_file *sfp, void *data) return 0; } -/* hsr_node_table_open - Open the node_table file - * - * Description: - * This routine opens a debugfs file node_table of specific hsr - * or prp device - */ -static int -hsr_node_table_open(struct inode *inode, struct file *filp) -{ - return single_open(filp, hsr_node_table_show, inode->i_private); -} +DEFINE_SHOW_ATTRIBUTE(hsr_node_table); void hsr_debugfs_rename(struct net_device *dev) { @@ -85,13 +75,6 @@ void hsr_debugfs_rename(struct net_device *dev) priv->node_tbl_root = d; } -static const struct file_operations hsr_fops = { - .open = hsr_node_table_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - /* hsr_debugfs_init - create hsr node_table file for dumping * the node table * @@ -113,7 +96,7 @@ void hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev) de = debugfs_create_file("node_table", S_IFREG | 0444, priv->node_tbl_root, priv, - &hsr_fops); + &hsr_node_table_fops); if (IS_ERR(de)) { pr_err("Cannot create hsr node_table file\n"); debugfs_remove(priv->node_tbl_root); diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 0e4681cf71db..f3c8f91dbe2c 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -493,7 +493,7 @@ fail: return res; } -static const struct genl_ops hsr_ops[] = { +static const struct genl_small_ops hsr_ops[] = { { .cmd = HSR_C_GET_NODE_STATUS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, @@ -518,8 +518,8 @@ static struct genl_family hsr_genl_family __ro_after_init = { .policy = hsr_genl_policy, .netnsok = true, .module = THIS_MODULE, - .ops = hsr_ops, - .n_ops = ARRAY_SIZE(hsr_ops), + .small_ops = hsr_ops, + .n_small_ops = ARRAY_SIZE(hsr_ops), .mcgrps = hsr_mcgrps, .n_mcgrps = ARRAY_SIZE(hsr_mcgrps), }; diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c index 7fe3b6b6c495..b07abc38b4b3 100644 --- a/net/ieee802154/netlink.c +++ b/net/ieee802154/netlink.c @@ -81,7 +81,7 @@ int ieee802154_nl_reply(struct sk_buff *msg, struct genl_info *info) return genlmsg_reply(msg, info); } -static const struct genl_ops ieee802154_ops[] = { +static const struct genl_small_ops ieee802154_ops[] = { /* see nl-phy.c */ IEEE802154_DUMP(IEEE802154_LIST_PHY, ieee802154_list_phy, ieee802154_dump_phy), @@ -130,8 +130,8 @@ struct genl_family nl802154_family __ro_after_init = { .maxattr = IEEE802154_ATTR_MAX, .policy = ieee802154_policy, .module = THIS_MODULE, - .ops = ieee802154_ops, - .n_ops = ARRAY_SIZE(ieee802154_ops), + .small_ops = ieee802154_ops, + .n_small_ops = ARRAY_SIZE(ieee802154_ops), .mcgrps = ieee802154_mcgrps, .n_mcgrps = ARRAY_SIZE(ieee802154_mcgrps), }; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 4307503a6f0b..b7260c8cef2e 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1017,6 +1017,7 @@ static int inet_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lon const struct proto_ops inet_stream_ops = { .family = PF_INET, + .flags = PROTO_CMSG_DATA_ONLY, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index e3939f76b024..618954f82764 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -28,27 +28,6 @@ static u32 unsupported_ops[] = { static const struct btf_type *tcp_sock_type; static u32 tcp_sock_id, sock_id; -static int btf_sk_storage_get_ids[5]; -static struct bpf_func_proto btf_sk_storage_get_proto __read_mostly; - -static int btf_sk_storage_delete_ids[5]; -static struct bpf_func_proto btf_sk_storage_delete_proto __read_mostly; - -static void convert_sk_func_proto(struct bpf_func_proto *to, int *to_btf_ids, - const struct bpf_func_proto *from) -{ - int i; - - *to = *from; - to->btf_id = to_btf_ids; - for (i = 0; i < ARRAY_SIZE(to->arg_type); i++) { - if (to->arg_type[i] == ARG_PTR_TO_SOCKET) { - to->arg_type[i] = ARG_PTR_TO_BTF_ID; - to->btf_id[i] = tcp_sock_id; - } - } -} - static int bpf_tcp_ca_init(struct btf *btf) { s32 type_id; @@ -64,13 +43,6 @@ static int bpf_tcp_ca_init(struct btf *btf) tcp_sock_id = type_id; tcp_sock_type = btf_type_by_id(btf, tcp_sock_id); - convert_sk_func_proto(&btf_sk_storage_get_proto, - btf_sk_storage_get_ids, - &bpf_sk_storage_get_proto); - convert_sk_func_proto(&btf_sk_storage_delete_proto, - btf_sk_storage_delete_ids, - &bpf_sk_storage_delete_proto); - return 0; } @@ -185,8 +157,8 @@ static const struct bpf_func_proto bpf_tcp_send_ack_proto = { /* In case we want to report error later */ .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &tcp_sock_id, .arg2_type = ARG_ANYTHING, - .btf_id = &tcp_sock_id, }; static const struct bpf_func_proto * @@ -197,9 +169,9 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, case BPF_FUNC_tcp_send_ack: return &bpf_tcp_send_ack_proto; case BPF_FUNC_sk_storage_get: - return &btf_sk_storage_get_proto; + return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: - return &btf_sk_storage_delete_proto; + return &bpf_sk_storage_delete_proto; default: return bpf_base_func_proto(func_id); } diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 2eb71579f4d2..471d33a0d095 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -498,7 +498,7 @@ static void cipso_v4_doi_free_rcu(struct rcu_head *entry) /** * cipso_v4_doi_remove - Remove an existing DOI from the CIPSO protocol engine * @doi: the DOI value - * @audit_secid: the LSM secid to use in the audit message + * @audit_info: NetLabel audit information * * Description: * Removes a DOI definition from the CIPSO engine. The NetLabel routines will diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index abd083415f89..e5f69b0bf3df 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -237,7 +237,7 @@ static struct sk_buff *fou_gro_receive(struct sock *sk, /* We can clear the encap_mark for FOU as we are essentially doing * one of two possible things. We are either adding an L4 tunnel - * header to the outer L3 tunnel header, or we are are simply + * header to the outer L3 tunnel header, or we are simply * treating the GRE tunnel header as though it is a UDP protocol * specific header such as VXLAN or GENEVE. */ @@ -429,7 +429,7 @@ next_proto: /* We can clear the encap_mark for GUE as we are essentially doing * one of two possible things. We are either adding an L4 tunnel - * header to the outer L3 tunnel header, or we are are simply + * header to the outer L3 tunnel header, or we are simply * treating the GRE tunnel header as though it is a UDP protocol * specific header such as VXLAN or GENEVE. */ @@ -911,7 +911,7 @@ static int fou_nl_dump(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } -static const struct genl_ops fou_nl_ops[] = { +static const struct genl_small_ops fou_nl_ops[] = { { .cmd = FOU_CMD_ADD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, @@ -940,8 +940,8 @@ static struct genl_family fou_nl_family __ro_after_init = { .policy = fou_nl_policy, .netnsok = true, .module = THIS_MODULE, - .ops = fou_nl_ops, - .n_ops = ARRAY_SIZE(fou_nl_ops), + .small_ops = fou_nl_ops, + .n_small_ops = ARRAY_SIZE(fou_nl_ops), }; size_t fou_encap_hlen(struct ip_tunnel_encap *e) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index cf36f955bfe6..005faea415a4 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -239,7 +239,7 @@ static struct { /** * icmp_global_allow - Are we allowed to send one more ICMP message ? * - * Uses a token bucket to limit our ICMP messages to sysctl_icmp_msgs_per_sec. + * Uses a token bucket to limit our ICMP messages to ~sysctl_icmp_msgs_per_sec. * Returns false if we reached the limit and can not send another packet. * Note: called with BH disabled */ @@ -267,7 +267,10 @@ bool icmp_global_allow(void) } credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst); if (credit) { - credit--; + /* We want to use a credit of one in average, but need to randomize + * it for security reasons. + */ + credit = max_t(int, credit - prandom_u32_max(3), 0); rc = true; } WRITE_ONCE(icmp_global.credit, credit); @@ -352,7 +355,7 @@ static int icmp_glue_bits(void *from, char *to, int offset, int len, int odd, csum = skb_copy_and_csum_bits(icmp_param->skb, icmp_param->offset + offset, - to, len, 0); + to, len); skb->csum = csum_block_add(skb->csum, csum, odd); if (icmp_pointers[icmp_param->data.icmph.type].error) @@ -376,15 +379,15 @@ static void icmp_push_reply(struct icmp_bxm *icmp_param, ip_flush_pending_frames(sk); } else if ((skb = skb_peek(&sk->sk_write_queue)) != NULL) { struct icmphdr *icmph = icmp_hdr(skb); - __wsum csum = 0; + __wsum csum; struct sk_buff *skb1; + csum = csum_partial_copy_nocheck((void *)&icmp_param->data, + (char *)icmph, + icmp_param->head_len); skb_queue_walk(&sk->sk_write_queue, skb1) { csum = csum_add(csum, skb1->csum); } - csum = csum_partial_copy_nocheck((void *)&icmp_param->data, - (char *)icmph, - icmp_param->head_len, csum); icmph->checksum = csum_fold(csum); skb->ip_summed = CHECKSUM_NONE; ip_push_pending_frames(sk, fl4); @@ -457,6 +460,23 @@ out_bh_enable: local_bh_enable(); } +/* + * The device used for looking up which routing table to use for sending an ICMP + * error is preferably the source whenever it is set, which should ensure the + * icmp error can be sent to the source host, else lookup using the routing + * table of the destination device, else use the main routing table (index 0). + */ +static struct net_device *icmp_get_route_lookup_dev(struct sk_buff *skb) +{ + struct net_device *route_lookup_dev = NULL; + + if (skb->dev) + route_lookup_dev = skb->dev; + else if (skb_dst(skb)) + route_lookup_dev = skb_dst(skb)->dev; + return route_lookup_dev; +} + static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4, struct sk_buff *skb_in, @@ -465,6 +485,7 @@ static struct rtable *icmp_route_lookup(struct net *net, int type, int code, struct icmp_bxm *param) { + struct net_device *route_lookup_dev; struct rtable *rt, *rt2; struct flowi4 fl4_dec; int err; @@ -479,7 +500,8 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->flowi4_proto = IPPROTO_ICMP; fl4->fl4_icmp_type = type; fl4->fl4_icmp_code = code; - fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev); + route_lookup_dev = icmp_get_route_lookup_dev(skb_in); + fl4->flowi4_oif = l3mdev_master_ifindex(route_lookup_dev); security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4)); rt = ip_route_output_key_hash(net, fl4, skb_in); @@ -503,7 +525,7 @@ static struct rtable *icmp_route_lookup(struct net *net, if (err) goto relookup_failed; - if (inet_addr_type_dev_table(net, skb_dst(skb_in)->dev, + if (inet_addr_type_dev_table(net, route_lookup_dev, fl4_dec.saddr) == RTN_LOCAL) { rt2 = __ip_route_output_key(net, &fl4_dec); if (IS_ERR(rt2)) @@ -690,9 +712,9 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, rcu_read_unlock(); } - tos = icmp_pointers[type].error ? ((iph->tos & IPTOS_TOS_MASK) | + tos = icmp_pointers[type].error ? (RT_TOS(iph->tos) | IPTOS_PREC_INTERNETCONTROL) : - iph->tos; + iph->tos; mark = IP4_REPLY_MARK(net, skb_in->mark); if (__ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in, opt)) @@ -784,7 +806,7 @@ EXPORT_SYMBOL(icmp_ndo_send); static void icmp_socket_deliver(struct sk_buff *skb, u32 info) { - const struct iphdr *iph = (const struct iphdr *) skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; const struct net_protocol *ipprot; int protocol = iph->protocol; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index b457dd2d6c75..4148f5f78f31 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -564,7 +564,7 @@ void inet_csk_clear_xmit_timers(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); - icsk->icsk_pending = icsk->icsk_ack.pending = icsk->icsk_ack.blocked = 0; + icsk->icsk_pending = icsk->icsk_ack.pending = 0; sk_stop_timer(sk, &icsk->icsk_retransmit_timer); sk_stop_timer(sk, &icsk->icsk_delack_timer); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index f1bd95f243b3..366a4507b5a3 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -125,6 +125,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, bool net_admin) { const struct inet_sock *inet = inet_sk(sk); + struct inet_diag_sockopt inet_sockopt; if (nla_put_u8(skb, INET_DIAG_SHUTDOWN, sk->sk_shutdown)) goto errout; @@ -180,6 +181,22 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk)); r->idiag_inode = sock_i_ino(sk); + memset(&inet_sockopt, 0, sizeof(inet_sockopt)); + inet_sockopt.recverr = inet->recverr; + inet_sockopt.is_icsk = inet->is_icsk; + inet_sockopt.freebind = inet->freebind; + inet_sockopt.hdrincl = inet->hdrincl; + inet_sockopt.mc_loop = inet->mc_loop; + inet_sockopt.transparent = inet->transparent; + inet_sockopt.mc_all = inet->mc_all; + inet_sockopt.nodefrag = inet->nodefrag; + inet_sockopt.bind_address_no_port = inet->bind_address_no_port; + inet_sockopt.recverr_rfc4884 = inet->recverr_rfc4884; + inet_sockopt.defer_connect = inet->defer_connect; + if (nla_put(skb, INET_DIAG_SOCKOPT, sizeof(inet_sockopt), + &inet_sockopt)) + goto errout; + return 0; errout: return 1; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 239e54474b65..8cbe74313f38 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -228,7 +228,7 @@ static void inet_unhash2(struct inet_hashinfo *h, struct sock *sk) static inline int compute_score(struct sock *sk, struct net *net, const unsigned short hnum, const __be32 daddr, - const int dif, const int sdif, bool exact_dif) + const int dif, const int sdif) { int score = -1; @@ -277,15 +277,13 @@ static struct sock *inet_lhash2_lookup(struct net *net, const __be32 daddr, const unsigned short hnum, const int dif, const int sdif) { - bool exact_dif = inet_exact_dif_match(net, skb); struct inet_connection_sock *icsk; struct sock *sk, *result = NULL; int score, hiscore = 0; inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) { sk = (struct sock *)icsk; - score = compute_score(sk, net, hnum, daddr, - dif, sdif, exact_dif); + score = compute_score(sk, net, hnum, daddr, dif, sdif); if (score > hiscore) { result = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 4e31f23e4117..e70291748889 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -625,9 +625,7 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, } if (dev->header_ops) { - /* Need space for new headers */ - if (skb_cow_head(skb, dev->needed_headroom - - (tunnel->hlen + sizeof(struct iphdr)))) + if (skb_cow_head(skb, 0)) goto free_skb; tnl_params = (const struct iphdr *)skb->data; @@ -748,7 +746,11 @@ static void ipgre_link_update(struct net_device *dev, bool set_mtu) len = tunnel->tun_hlen - len; tunnel->hlen = tunnel->hlen + len; - dev->needed_headroom = dev->needed_headroom + len; + if (dev->header_ops) + dev->hard_header_len += len; + else + dev->needed_headroom += len; + if (set_mtu) dev->mtu = max_t(int, dev->mtu - len, 68); @@ -944,6 +946,7 @@ static void __gre_tunnel_init(struct net_device *dev) tunnel->parms.iph.protocol = IPPROTO_GRE; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; + dev->needed_headroom = tunnel->hlen + sizeof(tunnel->parms.iph); dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; @@ -987,10 +990,14 @@ static int ipgre_tunnel_init(struct net_device *dev) return -EINVAL; dev->flags = IFF_BROADCAST; dev->header_ops = &ipgre_header_ops; + dev->hard_header_len = tunnel->hlen + sizeof(*iph); + dev->needed_headroom = 0; } #endif } else if (!tunnel->collect_md) { dev->header_ops = &ipgre_header_ops; + dev->hard_header_len = tunnel->hlen + sizeof(*iph); + dev->needed_headroom = 0; } return ip_tunnel_init(dev); diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 948747aac4e2..da1b5038bdfd 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -47,32 +47,32 @@ void ip_options_build(struct sk_buff *skb, struct ip_options *opt, unsigned char *iph = skb_network_header(skb); memcpy(&(IPCB(skb)->opt), opt, sizeof(struct ip_options)); - memcpy(iph+sizeof(struct iphdr), opt->__data, opt->optlen); + memcpy(iph + sizeof(struct iphdr), opt->__data, opt->optlen); opt = &(IPCB(skb)->opt); if (opt->srr) - memcpy(iph+opt->srr+iph[opt->srr+1]-4, &daddr, 4); + memcpy(iph + opt->srr + iph[opt->srr + 1] - 4, &daddr, 4); if (!is_frag) { if (opt->rr_needaddr) - ip_rt_get_source(iph+opt->rr+iph[opt->rr+2]-5, skb, rt); + ip_rt_get_source(iph + opt->rr + iph[opt->rr + 2] - 5, skb, rt); if (opt->ts_needaddr) - ip_rt_get_source(iph+opt->ts+iph[opt->ts+2]-9, skb, rt); + ip_rt_get_source(iph + opt->ts + iph[opt->ts + 2] - 9, skb, rt); if (opt->ts_needtime) { __be32 midtime; midtime = inet_current_timestamp(); - memcpy(iph+opt->ts+iph[opt->ts+2]-5, &midtime, 4); + memcpy(iph + opt->ts + iph[opt->ts + 2] - 5, &midtime, 4); } return; } if (opt->rr) { - memset(iph+opt->rr, IPOPT_NOP, iph[opt->rr+1]); + memset(iph + opt->rr, IPOPT_NOP, iph[opt->rr + 1]); opt->rr = 0; opt->rr_needaddr = 0; } if (opt->ts) { - memset(iph+opt->ts, IPOPT_NOP, iph[opt->ts+1]); + memset(iph + opt->ts, IPOPT_NOP, iph[opt->ts + 1]); opt->ts = 0; opt->ts_needaddr = opt->ts_needtime = 0; } @@ -495,26 +495,29 @@ EXPORT_SYMBOL(ip_options_compile); void ip_options_undo(struct ip_options *opt) { if (opt->srr) { - unsigned char *optptr = opt->__data+opt->srr-sizeof(struct iphdr); - memmove(optptr+7, optptr+3, optptr[1]-7); - memcpy(optptr+3, &opt->faddr, 4); + unsigned char *optptr = opt->__data + opt->srr - sizeof(struct iphdr); + + memmove(optptr + 7, optptr + 3, optptr[1] - 7); + memcpy(optptr + 3, &opt->faddr, 4); } if (opt->rr_needaddr) { - unsigned char *optptr = opt->__data+opt->rr-sizeof(struct iphdr); + unsigned char *optptr = opt->__data + opt->rr - sizeof(struct iphdr); + optptr[2] -= 4; - memset(&optptr[optptr[2]-1], 0, 4); + memset(&optptr[optptr[2] - 1], 0, 4); } if (opt->ts) { - unsigned char *optptr = opt->__data+opt->ts-sizeof(struct iphdr); + unsigned char *optptr = opt->__data + opt->ts - sizeof(struct iphdr); + if (opt->ts_needtime) { optptr[2] -= 4; - memset(&optptr[optptr[2]-1], 0, 4); - if ((optptr[3]&0xF) == IPOPT_TS_PRESPEC) + memset(&optptr[optptr[2] - 1], 0, 4); + if ((optptr[3] & 0xF) == IPOPT_TS_PRESPEC) optptr[2] -= 4; } if (opt->ts_needaddr) { optptr[2] -= 4; - memset(&optptr[optptr[2]-1], 0, 4); + memset(&optptr[optptr[2] - 1], 0, 4); } } } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index e6f2ada9e7d5..879b76ae4435 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -143,7 +143,8 @@ static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst) * */ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, - __be32 saddr, __be32 daddr, struct ip_options_rcu *opt) + __be32 saddr, __be32 daddr, struct ip_options_rcu *opt, + u8 tos) { struct inet_sock *inet = inet_sk(sk); struct rtable *rt = skb_rtable(skb); @@ -156,7 +157,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, iph = ip_hdr(skb); iph->version = 4; iph->ihl = 5; - iph->tos = inet->tos; + iph->tos = tos; iph->ttl = ip_select_ttl(inet, &rt->dst); iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; @@ -997,7 +998,7 @@ static int __ip_append_data(struct sock *sk, fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; - maxnonfragsize = ip_sk_ignore_df(sk) ? 0xFFFF : mtu; + maxnonfragsize = ip_sk_ignore_df(sk) ? IP_MAX_MTU : mtu; if (cork->length + length > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, @@ -1127,7 +1128,7 @@ alloc_new_skb: if (fraggap) { skb->csum = skb_copy_and_csum_bits( skb_prev, maxfraglen, - data + transhdrlen, fraggap, 0); + data + transhdrlen, fraggap); skb_prev->csum = csum_sub(skb_prev->csum, skb->csum); data += fraggap; @@ -1352,7 +1353,7 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, if (cork->flags & IPCORK_OPT) opt = cork->opt; - if (!(rt->dst.dev->features&NETIF_F_SG)) + if (!(rt->dst.dev->features & NETIF_F_SG)) return -EOPNOTSUPP; hh_len = LL_RESERVED_SPACE(rt->dst.dev); @@ -1412,7 +1413,7 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, skb->csum = skb_copy_and_csum_bits(skb_prev, maxfraglen, skb_transport_header(skb), - fraggap, 0); + fraggap); skb_prev->csum = csum_sub(skb_prev->csum, skb->csum); pskb_trim_unique(skb_prev, maxfraglen); @@ -1537,7 +1538,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, ip_select_ident(net, skb, sk); if (opt) { - iph->ihl += opt->optlen>>2; + iph->ihl += opt->optlen >> 2; ip_options_build(skb, opt, cork->addr, rt, 0); } @@ -1649,7 +1650,7 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset, { __wsum csum; - csum = csum_partial_copy_nocheck(dptr+offset, to, len, 0); + csum = csum_partial_copy_nocheck(dptr+offset, to, len); skb->csum = csum_block_add(skb->csum, csum, odd); return 0; } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index d2c223554ff7..ec6036713e2c 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1124,8 +1124,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname, dev_put(dev); err = -EINVAL; - if (sk->sk_bound_dev_if && - (!midx || midx != sk->sk_bound_dev_if)) + if (sk->sk_bound_dev_if && midx != sk->sk_bound_dev_if) break; inet->uc_index = ifindex; @@ -1189,7 +1188,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname, err = -EINVAL; if (sk->sk_bound_dev_if && mreq.imr_ifindex != sk->sk_bound_dev_if && - (!midx || midx != sk->sk_bound_dev_if)) + midx != sk->sk_bound_dev_if) break; inet->mc_index = mreq.imr_ifindex; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 0c1f36404471..ee65c9225178 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -360,7 +360,6 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, bool log_ecn_error) { - struct pcpu_sw_netstats *tstats; const struct iphdr *iph = ip_hdr(skb); int err; @@ -402,12 +401,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, } } - tstats = this_cpu_ptr(tunnel->dev->tstats); - u64_stats_update_begin(&tstats->syncp); - tstats->rx_packets++; - tstats->rx_bytes += skb->len; - u64_stats_update_end(&tstats->syncp); - + dev_sw_netstats_rx_add(tunnel->dev, skb->len); skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev))); if (tunnel->dev->type == ARPHRD_ETHER) { @@ -614,9 +608,6 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, ttl = ip4_dst_hoplimit(&rt->dst); } - if (!df && skb->protocol == htons(ETH_P_IP)) - df = inner_iph->frag_off & htons(IP_DF); - headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; if (headroom > dev->needed_headroom) dev->needed_headroom = headroom; diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index b2ea1a8c5fd6..25f1caf5abf9 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -433,29 +433,8 @@ EXPORT_SYMBOL(skb_tunnel_check_pmtu); void ip_tunnel_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *tot) { - int i; - netdev_stats_to_stats64(tot, &dev->stats); - - for_each_possible_cpu(i) { - const struct pcpu_sw_netstats *tstats = - per_cpu_ptr(dev->tstats, i); - u64 rx_packets, rx_bytes, tx_packets, tx_bytes; - unsigned int start; - - do { - start = u64_stats_fetch_begin_irq(&tstats->syncp); - rx_packets = tstats->rx_packets; - tx_packets = tstats->tx_packets; - rx_bytes = tstats->rx_bytes; - tx_bytes = tstats->tx_bytes; - } while (u64_stats_fetch_retry_irq(&tstats->syncp, start)); - - tot->rx_packets += rx_packets; - tot->tx_packets += tx_packets; - tot->rx_bytes += rx_bytes; - tot->tx_bytes += tx_bytes; - } + dev_fetch_sw_netstats(tot, dev->tstats); } EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index f687abb069fa..b957cbee2cf7 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -95,7 +95,6 @@ static int vti_rcv_cb(struct sk_buff *skb, int err) { unsigned short family; struct net_device *dev; - struct pcpu_sw_netstats *tstats; struct xfrm_state *x; const struct xfrm_mode *inner_mode; struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4; @@ -138,13 +137,7 @@ static int vti_rcv_cb(struct sk_buff *skb, int err) skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev))); skb->dev = dev; - - tstats = this_cpu_ptr(dev->tstats); - - u64_stats_update_begin(&tstats->syncp); - tstats->rx_packets++; - tstats->rx_bytes += skb->len; - u64_stats_update_end(&tstats->syncp); + dev_sw_netstats_rx_add(dev, skb->len); return 0; } diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 876fd6ff1ff9..939792a38814 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1038,10 +1038,13 @@ static int ipmr_cache_report(struct mr_table *mrt, memcpy(msg, skb_network_header(pkt), sizeof(struct iphdr)); msg->im_msgtype = assert; msg->im_mbz = 0; - if (assert == IGMPMSG_WRVIFWHOLE) + if (assert == IGMPMSG_WRVIFWHOLE) { msg->im_vif = vifi; - else + msg->im_vif_hi = vifi >> 8; + } else { msg->im_vif = mrt->mroute_reg_vif_num; + msg->im_vif_hi = mrt->mroute_reg_vif_num >> 8; + } ip_hdr(skb)->ihl = sizeof(struct iphdr) >> 2; ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(pkt)->tot_len) + sizeof(struct iphdr)); @@ -1054,6 +1057,7 @@ static int ipmr_cache_report(struct mr_table *mrt, ip_hdr(skb)->protocol = 0; msg = (struct igmpmsg *)skb_network_header(skb); msg->im_vif = vifi; + msg->im_vif_hi = vifi >> 8; skb_dst_set(skb, dst_clone(skb_dst(pkt))); /* Add our header */ igmp = skb_put(skb, sizeof(struct igmphdr)); @@ -2396,6 +2400,7 @@ static size_t igmpmsg_netlink_msgsize(size_t payloadlen) + nla_total_size(4) /* IPMRA_CREPORT_VIF_ID */ + nla_total_size(4) /* IPMRA_CREPORT_SRC_ADDR */ + nla_total_size(4) /* IPMRA_CREPORT_DST_ADDR */ + + nla_total_size(4) /* IPMRA_CREPORT_TABLE */ /* IPMRA_CREPORT_PKT */ + nla_total_size(payloadlen) ; @@ -2427,11 +2432,12 @@ static void igmpmsg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt) rtgenm = nlmsg_data(nlh); rtgenm->rtgen_family = RTNL_FAMILY_IPMR; if (nla_put_u8(skb, IPMRA_CREPORT_MSGTYPE, msg->im_msgtype) || - nla_put_u32(skb, IPMRA_CREPORT_VIF_ID, msg->im_vif) || + nla_put_u32(skb, IPMRA_CREPORT_VIF_ID, msg->im_vif | (msg->im_vif_hi << 8)) || nla_put_in_addr(skb, IPMRA_CREPORT_SRC_ADDR, msg->im_src.s_addr) || nla_put_in_addr(skb, IPMRA_CREPORT_DST_ADDR, - msg->im_dst.s_addr)) + msg->im_dst.s_addr) || + nla_put_u32(skb, IPMRA_CREPORT_TABLE, mrt->id)) goto nla_put_failure; nla = nla_reserve(skb, IPMRA_CREPORT_PKT, payloadlen); diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index a058213b77a7..7c841037c533 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -17,17 +17,19 @@ #include <net/netfilter/nf_queue.h> /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */ -int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_type) +int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int addr_type) { const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; struct flowi4 fl4 = {}; __be32 saddr = iph->saddr; - const struct sock *sk = skb_to_full_sk(skb); - __u8 flags = sk ? inet_sk_flowi_flags(sk) : 0; + __u8 flags; struct net_device *dev = skb_dst(skb)->dev; unsigned int hh_len; + sk = sk_to_full_sk(sk); + flags = sk ? inet_sk_flowi_flags(sk) : 0; + if (addr_type == RTN_UNSPEC) addr_type = inet_addr_type_dev_table(net, dev, saddr); if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST) diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index f703a717ab1d..833079589273 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -62,7 +62,7 @@ ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) iph->daddr != daddr || skb->mark != mark || iph->tos != tos) { - err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); + err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/ipv4/netfilter/nf_log_arp.c b/net/ipv4/netfilter/nf_log_arp.c index 7a83f881efa9..136030ad2e54 100644 --- a/net/ipv4/netfilter/nf_log_arp.c +++ b/net/ipv4/netfilter/nf_log_arp.c @@ -43,16 +43,31 @@ static void dump_arp_packet(struct nf_log_buf *m, const struct nf_loginfo *info, const struct sk_buff *skb, unsigned int nhoff) { - const struct arphdr *ah; - struct arphdr _arph; const struct arppayload *ap; struct arppayload _arpp; + const struct arphdr *ah; + unsigned int logflags; + struct arphdr _arph; ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph); if (ah == NULL) { nf_log_buf_add(m, "TRUNCATED"); return; } + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + else + logflags = NF_LOG_DEFAULT_MASK; + + if (logflags & NF_LOG_MACDECODE) { + nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest); + nf_log_dump_vlan(m, skb); + nf_log_buf_add(m, "MACPROTO=%04x ", + ntohs(eth_hdr(skb)->h_proto)); + } + nf_log_buf_add(m, "ARP HTYPE=%d PTYPE=0x%04x OPCODE=%d", ntohs(ah->ar_hrd), ntohs(ah->ar_pro), ntohs(ah->ar_op)); diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c index 0c72156130b6..d07583fac8f8 100644 --- a/net/ipv4/netfilter/nf_log_ipv4.c +++ b/net/ipv4/netfilter/nf_log_ipv4.c @@ -284,8 +284,10 @@ static void dump_ipv4_mac_header(struct nf_log_buf *m, switch (dev->type) { case ARPHRD_ETHER: - nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", - eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, + nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest); + nf_log_dump_vlan(m, skb); + nf_log_buf_add(m, "MACPROTO=%04x ", ntohs(eth_hdr(skb)->h_proto)); return; default: diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 9dcfa4e461b6..93b07739807b 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -145,7 +145,7 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook) ip4_dst_hoplimit(skb_dst(nskb))); nf_reject_ip_tcphdr_put(nskb, oldskb, oth); - if (ip_route_me_harder(net, nskb, RTN_UNSPEC)) + if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC)) goto free_nskb; niph = ip_hdr(nskb); diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 134e92382275..0dc43ad28eb9 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -42,8 +42,8 @@ static int call_nexthop_notifiers(struct net *net, { int err; - err = atomic_notifier_call_chain(&net->nexthop.notifier_chain, - event_type, nh); + err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, + event_type, nh); return notifier_to_errno(err); } @@ -133,12 +133,9 @@ static struct nexthop *nexthop_alloc(void) static struct nh_group *nexthop_grp_alloc(u16 num_nh) { - size_t sz = offsetof(struct nexthop, nh_grp) - + sizeof(struct nh_group) - + sizeof(struct nh_grp_entry) * num_nh; struct nh_group *nhg; - nhg = kzalloc(sz, GFP_KERNEL); + nhg = kzalloc(struct_size(nhg, nh_entries, num_nh), GFP_KERNEL); if (nhg) nhg->num_nh = num_nh; @@ -279,7 +276,7 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, case AF_INET: fib_nh = &nhi->fib_nh; if (fib_nh->fib_nh_gw_family && - nla_put_u32(skb, NHA_GATEWAY, fib_nh->fib_nh_gw4)) + nla_put_be32(skb, NHA_GATEWAY, fib_nh->fib_nh_gw4)) goto nla_put_failure; break; @@ -800,7 +797,7 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, return; } - newg->has_v4 = nhg->has_v4; + newg->has_v4 = false; newg->mpath = nhg->mpath; newg->fdb_nh = nhg->fdb_nh; newg->num_nh = nhg->num_nh; @@ -809,12 +806,18 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, nhges = nhg->nh_entries; new_nhges = newg->nh_entries; for (i = 0, j = 0; i < nhg->num_nh; ++i) { + struct nh_info *nhi; + /* current nexthop getting removed */ if (nhg->nh_entries[i].nh == nh) { newg->num_nh--; continue; } + nhi = rtnl_dereference(nhges[i].nh->nh_info); + if (nhi->family == AF_INET) + newg->has_v4 = true; + list_del(&nhges[i].nh_list); new_nhges[j].nh_parent = nhges[i].nh_parent; new_nhges[j].nh = nhges[i].nh; @@ -842,7 +845,7 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh, remove_nh_grp_entry(net, nhge, nlinfo); /* make sure all see the newly published array before releasing rtnl */ - synchronize_rcu(); + synchronize_net(); } static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo) @@ -867,8 +870,6 @@ static void __remove_nexthop_fib(struct net *net, struct nexthop *nh) bool do_flush = false; struct fib_info *fi; - call_nexthop_notifiers(net, NEXTHOP_EVENT_DEL, nh); - list_for_each_entry(fi, &nh->fi_list, nh_list) { fi->fib_flags |= RTNH_F_DEAD; do_flush = true; @@ -906,6 +907,8 @@ static void __remove_nexthop(struct net *net, struct nexthop *nh, static void remove_nexthop(struct net *net, struct nexthop *nh, struct nl_info *nlinfo) { + call_nexthop_notifiers(net, NEXTHOP_EVENT_DEL, nh); + /* remove from the tree */ rb_erase(&nh->rb_node, &net->nexthop.rb_root); @@ -961,6 +964,23 @@ static int replace_nexthop_grp(struct net *net, struct nexthop *old, return 0; } +static void nh_group_v4_update(struct nh_group *nhg) +{ + struct nh_grp_entry *nhges; + bool has_v4 = false; + int i; + + nhges = nhg->nh_entries; + for (i = 0; i < nhg->num_nh; i++) { + struct nh_info *nhi; + + nhi = rtnl_dereference(nhges[i].nh->nh_info); + if (nhi->family == AF_INET) + has_v4 = true; + } + nhg->has_v4 = has_v4; +} + static int replace_nexthop_single(struct net *net, struct nexthop *old, struct nexthop *new, struct netlink_ext_ack *extack) @@ -984,6 +1004,21 @@ static int replace_nexthop_single(struct net *net, struct nexthop *old, rcu_assign_pointer(old->nh_info, newi); rcu_assign_pointer(new->nh_info, oldi); + /* When replacing an IPv4 nexthop with an IPv6 nexthop, potentially + * update IPv4 indication in all the groups using the nexthop. + */ + if (oldi->family == AF_INET && newi->family == AF_INET6) { + struct nh_grp_entry *nhge; + + list_for_each_entry(nhge, &old->grp_list, nh_list) { + struct nexthop *nhp = nhge->nh_parent; + struct nh_group *nhg; + + nhg = rtnl_dereference(nhp->nh_grp); + nh_group_v4_update(nhg); + } + } + return 0; } @@ -1101,7 +1136,7 @@ static int insert_nexthop(struct net *net, struct nexthop *new_nh, while (1) { struct nexthop *nh; - next = rtnl_dereference(*pp); + next = *pp; if (!next) break; @@ -1924,14 +1959,15 @@ static struct notifier_block nh_netdev_notifier = { int register_nexthop_notifier(struct net *net, struct notifier_block *nb) { - return atomic_notifier_chain_register(&net->nexthop.notifier_chain, nb); + return blocking_notifier_chain_register(&net->nexthop.notifier_chain, + nb); } EXPORT_SYMBOL(register_nexthop_notifier); int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb) { - return atomic_notifier_chain_unregister(&net->nexthop.notifier_chain, - nb); + return blocking_notifier_chain_unregister(&net->nexthop.notifier_chain, + nb); } EXPORT_SYMBOL(unregister_nexthop_notifier); @@ -1951,7 +1987,7 @@ static int __net_init nexthop_net_init(struct net *net) net->nexthop.devhash = kzalloc(sz, GFP_KERNEL); if (!net->nexthop.devhash) return -ENOMEM; - ATOMIC_INIT_NOTIFIER_HEAD(&net->nexthop.notifier_chain); + BLOCKING_INIT_NOTIFIER_HEAD(&net->nexthop.notifier_chain); return 0; } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index df6fbefe44d4..248856b301c4 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -293,7 +293,8 @@ EXPORT_SYMBOL_GPL(ping_close); /* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, - struct sockaddr *uaddr, int addr_len) { + struct sockaddr *uaddr, int addr_len) +{ struct net *net = sock_net(sk); if (sk->sk_family == AF_INET) { struct sockaddr_in *addr = (struct sockaddr_in *) uaddr; @@ -310,10 +311,10 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n", sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port)); - chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr); - if (addr->sin_addr.s_addr == htonl(INADDR_ANY)) chk_addr_ret = RTN_LOCAL; + else + chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr); if ((!inet_can_nonlocal_bind(net, isk) && chk_addr_ret != RTN_LOCAL) || @@ -383,20 +384,6 @@ static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr) } } -static void ping_clear_saddr(struct sock *sk, int dif) -{ - sk->sk_bound_dev_if = dif; - if (sk->sk_family == AF_INET) { - struct inet_sock *isk = inet_sk(sk); - isk->inet_rcv_saddr = isk->inet_saddr = 0; -#if IS_ENABLED(CONFIG_IPV6) - } else if (sk->sk_family == AF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); - memset(&sk->sk_v6_rcv_saddr, 0, sizeof(sk->sk_v6_rcv_saddr)); - memset(&np->saddr, 0, sizeof(np->saddr)); -#endif - } -} /* * We need our own bind because there are no privileged id's == local ports. * Moreover, we don't allow binding to multi- and broadcast addresses. @@ -420,12 +407,13 @@ int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) goto out; err = -EADDRINUSE; - ping_set_saddr(sk, uaddr); snum = ntohs(((struct sockaddr_in *)uaddr)->sin_port); if (ping_get_port(sk, snum) != 0) { - ping_clear_saddr(sk, dif); + /* Restore possibly modified sk->sk_bound_dev_if by ping_check_bind_addr(). */ + sk->sk_bound_dev_if = dif; goto out; } + ping_set_saddr(sk, uaddr); pr_debug("after bind(): num = %hu, dif = %d\n", isk->inet_num, @@ -647,7 +635,8 @@ static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh, } int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, - void *user_icmph, size_t icmph_len) { + void *user_icmph, size_t icmph_len) +{ u8 type, code; if (len > 0xFFFF) diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 407956be7deb..7d26e0f8bdae 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -260,11 +260,12 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) err = EHOSTUNREACH; if (code > NR_ICMP_UNREACH) break; - err = icmp_err_convert[code].errno; - harderr = icmp_err_convert[code].fatal; if (code == ICMP_FRAG_NEEDED) { harderr = inet->pmtudisc != IP_PMTUDISC_DONT; err = EMSGSIZE; + } else { + err = icmp_err_convert[code].errno; + harderr = icmp_err_convert[code].fatal; } } @@ -478,7 +479,7 @@ static int raw_getfrag(void *from, char *to, int offset, int len, int odd, skb->csum = csum_block_add( skb->csum, csum_partial_copy_nocheck(rfv->hdr.c + offset, - to, copy, 0), + to, copy), odd); odd = 0; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 58642b29a499..dc2a399cd9f4 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -623,7 +623,7 @@ static inline u32 fnhe_hashfun(__be32 daddr) u32 hval; net_get_random_once(&fnhe_hashrnd, sizeof(fnhe_hashrnd)); - hval = jhash_1word((__force u32) daddr, fnhe_hashrnd); + hval = jhash_1word((__force u32)daddr, fnhe_hashrnd); return hash_32(hval, FNHE_HASH_SHIFT); } @@ -1016,13 +1016,14 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; struct net *net = dev_net(dst->dev); - u32 old_mtu = ipv4_mtu(dst); struct fib_result res; bool lock = false; + u32 old_mtu; if (ip_mtu_locked(dst)) return; + old_mtu = ipv4_mtu(dst); if (old_mtu < mtu) return; @@ -1066,7 +1067,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif, u8 protocol) { - const struct iphdr *iph = (const struct iphdr *) skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; u32 mark = IP4_REPLY_MARK(net, skb->mark); @@ -1083,7 +1084,7 @@ EXPORT_SYMBOL_GPL(ipv4_update_pmtu); static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) { - const struct iphdr *iph = (const struct iphdr *) skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; @@ -1101,7 +1102,7 @@ static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) { - const struct iphdr *iph = (const struct iphdr *) skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; struct dst_entry *odst = NULL; @@ -1131,7 +1132,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) new = true; } - __ip_rt_update_pmtu((struct rtable *) xfrm_dst_path(&rt->dst), &fl4, mtu); + __ip_rt_update_pmtu((struct rtable *)xfrm_dst_path(&rt->dst), &fl4, mtu); if (!dst_check(&rt->dst, 0)) { if (new) @@ -1156,7 +1157,7 @@ EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu); void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u8 protocol) { - const struct iphdr *iph = (const struct iphdr *) skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; @@ -1172,7 +1173,7 @@ EXPORT_SYMBOL_GPL(ipv4_redirect); void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk) { - const struct iphdr *iph = (const struct iphdr *) skb->data; + const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; struct net *net = sock_net(sk); @@ -1312,7 +1313,7 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst) static unsigned int ipv4_mtu(const struct dst_entry *dst) { - const struct rtable *rt = (const struct rtable *) dst; + const struct rtable *rt = (const struct rtable *)dst; unsigned int mtu = rt->rt_pmtu; if (!mtu || time_after_eq(jiffies, rt->dst.expires)) @@ -2769,10 +2770,12 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, if (IS_ERR(rt)) return rt; - if (flp4->flowi4_proto) + if (flp4->flowi4_proto) { + flp4->flowi4_oif = rt->dst.dev->ifindex; rt = (struct rtable *)xfrm_lookup_route(net, &rt->dst, flowi4_to_flowi(flp4), sk, 0); + } return rt; } diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index e03756631541..6ac473b47f30 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -286,11 +286,10 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk, struct sk_buff *skb) { + struct tcp_request_sock *treq; struct request_sock *req; #ifdef CONFIG_MPTCP - struct tcp_request_sock *treq; - if (sk_is_mptcp(sk)) ops = &mptcp_subflow_request_sock_ops; #endif @@ -299,8 +298,9 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, if (!req) return NULL; -#if IS_ENABLED(CONFIG_MPTCP) treq = tcp_rsk(req); + treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield; +#if IS_ENABLED(CONFIG_MPTCP) treq->is_mptcp = sk_is_mptcp(sk); if (treq->is_mptcp) { int err = mptcp_subflow_init_cookie_req(req, sk, skb); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 54023a46db04..3e5f4f2e705e 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -1330,6 +1330,15 @@ static struct ctl_table ipv4_net_table[] = { .extra2 = &comp_sack_nr_max, }, { + .procname = "tcp_reflect_tos", + .data = &init_net.ipv4.sysctl_tcp_reflect_tos, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { .procname = "udp_rmem_min", .data = &init_net.ipv4.sysctl_udp_rmem_min, .maxlen = sizeof(init_net.ipv4.sysctl_udp_rmem_min), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2135ee7c806d..b2bc3d7fe9e8 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -418,6 +418,8 @@ void tcp_init_sock(struct sock *sk) INIT_LIST_HEAD(&tp->tsorted_sent_queue); icsk->icsk_rto = TCP_TIMEOUT_INIT; + icsk->icsk_rto_min = TCP_RTO_MIN; + icsk->icsk_delack_max = TCP_DELACK_MAX; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U); @@ -483,6 +485,8 @@ static inline bool tcp_stream_is_readable(const struct tcp_sock *tp, return true; if (tcp_rmem_pressure(sk)) return true; + if (tcp_receive_window(tp) <= inet_csk(sk)->icsk_ack.rcv_mss) + return true; } if (sk->sk_prot->stream_memory_read) return sk->sk_prot->stream_memory_read(sk); @@ -562,7 +566,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) mask |= EPOLLIN | EPOLLRDNORM; if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { - if (sk_stream_is_writeable(sk)) { + if (__sk_stream_is_writeable(sk, 1)) { mask |= EPOLLOUT | EPOLLWRNORM; } else { /* send SIGIO later */ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); @@ -574,7 +578,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) * pairs with the input side. */ smp_mb__after_atomic(); - if (sk_stream_is_writeable(sk)) + if (__sk_stream_is_writeable(sk, 1)) mask |= EPOLLOUT | EPOLLWRNORM; } } else @@ -1003,12 +1007,12 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, !tcp_skb_can_collapse_to(skb)) { new_segment: if (!sk_stream_memory_free(sk)) - goto wait_for_sndbuf; + goto wait_for_space; skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation, tcp_rtx_and_write_queues_empty(sk)); if (!skb) - goto wait_for_memory; + goto wait_for_space; #ifdef CONFIG_TLS_DEVICE skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED); @@ -1027,7 +1031,7 @@ new_segment: goto new_segment; } if (!sk_wmem_schedule(sk, copy)) - goto wait_for_memory; + goto wait_for_space; if (can_coalesce) { skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); @@ -1068,9 +1072,8 @@ new_segment: tcp_push_one(sk, mss_now); continue; -wait_for_sndbuf: +wait_for_space: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); -wait_for_memory: tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH, size_goal); @@ -1281,7 +1284,7 @@ restart: new_segment: if (!sk_stream_memory_free(sk)) - goto wait_for_sndbuf; + goto wait_for_space; if (unlikely(process_backlog >= 16)) { process_backlog = 0; @@ -1292,7 +1295,7 @@ new_segment: skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation, first_skb); if (!skb) - goto wait_for_memory; + goto wait_for_space; process_backlog++; skb->ip_summed = CHECKSUM_PARTIAL; @@ -1325,7 +1328,7 @@ new_segment: struct page_frag *pfrag = sk_page_frag(sk); if (!sk_page_frag_refill(sk, pfrag)) - goto wait_for_memory; + goto wait_for_space; if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { @@ -1339,7 +1342,7 @@ new_segment: copy = min_t(int, copy, pfrag->size - pfrag->offset); if (!sk_wmem_schedule(sk, copy)) - goto wait_for_memory; + goto wait_for_space; err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb, pfrag->page, @@ -1392,9 +1395,8 @@ new_segment: tcp_push_one(sk, mss_now); continue; -wait_for_sndbuf: +wait_for_space: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); -wait_for_memory: if (copied) tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH, size_goal); @@ -1526,7 +1528,7 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len) * calculation of whether or not we must ACK for the sake of * a window update. */ -static void tcp_cleanup_rbuf(struct sock *sk, int copied) +void tcp_cleanup_rbuf(struct sock *sk, int copied) { struct tcp_sock *tp = tcp_sk(sk); bool time_to_ack = false; @@ -1539,10 +1541,8 @@ static void tcp_cleanup_rbuf(struct sock *sk, int copied) if (inet_csk_ack_scheduled(sk)) { const struct inet_connection_sock *icsk = inet_csk(sk); - /* Delayed ACKs frequently hit locked sockets during bulk - * receive. */ - if (icsk->icsk_ack.blocked || - /* Once-per-two-segments ACK was not sent by tcp_input.c */ + + if (/* Once-per-two-segments ACK was not sent by tcp_input.c */ tp->rcv_nxt - tp->rcv_wup > icsk->icsk_ack.rcv_mss || /* * If this read emptied read buffer, we send ACK, if @@ -2686,6 +2686,8 @@ int tcp_disconnect(struct sock *sk, int flags) icsk->icsk_backoff = 0; icsk->icsk_probes_out = 0; icsk->icsk_rto = TCP_TIMEOUT_INIT; + icsk->icsk_rto_min = TCP_RTO_MIN; + icsk->icsk_delack_max = TCP_DELACK_MAX; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd = TCP_INIT_CWND; tp->snd_cwnd_cnt = 0; @@ -2695,6 +2697,7 @@ int tcp_disconnect(struct sock *sk, int flags) if (icsk->icsk_ca_ops->release) icsk->icsk_ca_ops->release(sk); memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); + icsk->icsk_ca_initialized = 0; tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; tcp_clear_retrans(tp); @@ -3046,7 +3049,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname, name[val] = 0; lock_sock(sk); - err = tcp_set_congestion_control(sk, name, true, true, + err = tcp_set_congestion_control(sk, name, true, ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)); release_sock(sk); @@ -3208,7 +3211,8 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname, break; case TCP_SAVE_SYN: - if (val < 0 || val > 1) + /* 0: disable, 1: enable, 2: start from ether_header */ + if (val < 0 || val > 2) err = -EINVAL; else tp->save_syn = val; @@ -3789,20 +3793,21 @@ static int do_tcp_getsockopt(struct sock *sk, int level, lock_sock(sk); if (tp->saved_syn) { - if (len < tp->saved_syn[0]) { - if (put_user(tp->saved_syn[0], optlen)) { + if (len < tcp_saved_syn_len(tp->saved_syn)) { + if (put_user(tcp_saved_syn_len(tp->saved_syn), + optlen)) { release_sock(sk); return -EFAULT; } release_sock(sk); return -EINVAL; } - len = tp->saved_syn[0]; + len = tcp_saved_syn_len(tp->saved_syn); if (put_user(len, optlen)) { release_sock(sk); return -EFAULT; } - if (copy_to_user(optval, tp->saved_syn + 1, len)) { + if (copy_to_user(optval, tp->saved_syn->data, len)) { release_sock(sk); return -EFAULT; } diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 7aa68f4aae6c..37f4cb2bba5c 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -567,10 +567,9 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS], prot[TCP_BPF_TX].sendpage = tcp_bpf_sendpage; } -static void tcp_bpf_check_v6_needs_rebuild(struct sock *sk, struct proto *ops) +static void tcp_bpf_check_v6_needs_rebuild(struct proto *ops) { - if (sk->sk_family == AF_INET6 && - unlikely(ops != smp_load_acquire(&tcpv6_prot_saved))) { + if (unlikely(ops != smp_load_acquire(&tcpv6_prot_saved))) { spin_lock_bh(&tcpv6_prot_lock); if (likely(ops != tcpv6_prot_saved)) { tcp_bpf_rebuild_protos(tcp_bpf_prots[TCP_BPF_IPV6], ops); @@ -603,13 +602,11 @@ struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock) int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4; int config = psock->progs.msg_parser ? TCP_BPF_TX : TCP_BPF_BASE; - if (!psock->sk_proto) { - struct proto *ops = READ_ONCE(sk->sk_prot); - - if (tcp_bpf_assert_proto_ops(ops)) + if (sk->sk_family == AF_INET6) { + if (tcp_bpf_assert_proto_ops(psock->sk_proto)) return ERR_PTR(-EINVAL); - tcp_bpf_check_v6_needs_rebuild(sk, ops); + tcp_bpf_check_v6_needs_rebuild(psock->sk_proto); } return &tcp_bpf_prots[family][config]; diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 62878cf26d9c..db47ac24d057 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -176,7 +176,7 @@ void tcp_assign_congestion_control(struct sock *sk) void tcp_init_congestion_control(struct sock *sk) { - const struct inet_connection_sock *icsk = inet_csk(sk); + struct inet_connection_sock *icsk = inet_csk(sk); tcp_sk(sk)->prior_ssthresh = 0; if (icsk->icsk_ca_ops->init) @@ -185,6 +185,7 @@ void tcp_init_congestion_control(struct sock *sk) INET_ECN_xmit(sk); else INET_ECN_dontxmit(sk); + icsk->icsk_ca_initialized = 1; } static void tcp_reinit_congestion_control(struct sock *sk, @@ -340,7 +341,7 @@ out: * already initialized. */ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, - bool reinit, bool cap_net_admin) + bool cap_net_admin) { struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_congestion_ops *ca; @@ -361,28 +362,14 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, goto out; } - if (!ca) { + if (!ca) err = -ENOENT; - } else if (!load) { - const struct tcp_congestion_ops *old_ca = icsk->icsk_ca_ops; - - if (bpf_try_module_get(ca, ca->owner)) { - if (reinit) { - tcp_reinit_congestion_control(sk, ca); - } else { - icsk->icsk_ca_ops = ca; - bpf_module_put(old_ca, old_ca->owner); - } - } else { - err = -EBUSY; - } - } else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin)) { + else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin)) err = -EPERM; - } else if (!bpf_try_module_get(ca, ca->owner)) { + else if (!bpf_try_module_get(ca, ca->owner)) err = -EBUSY; - } else { + else tcp_reinit_congestion_control(sk, ca); - } out: rcu_read_unlock(); return err; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 09b62de04eea..af2814c9342a 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -295,7 +295,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, refcount_set(&req->rsk_refcnt, 2); /* Now finish processing the fastopen child socket. */ - tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); + tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, skb); tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b1ce2054291d..389d1b340248 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -138,6 +138,69 @@ void clean_acked_data_flush(void) EXPORT_SYMBOL_GPL(clean_acked_data_flush); #endif +#ifdef CONFIG_CGROUP_BPF +static void bpf_skops_parse_hdr(struct sock *sk, struct sk_buff *skb) +{ + bool unknown_opt = tcp_sk(sk)->rx_opt.saw_unknown && + BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), + BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG); + bool parse_all_opt = BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), + BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG); + struct bpf_sock_ops_kern sock_ops; + + if (likely(!unknown_opt && !parse_all_opt)) + return; + + /* The skb will be handled in the + * bpf_skops_established() or + * bpf_skops_write_hdr_opt(). + */ + switch (sk->sk_state) { + case TCP_SYN_RECV: + case TCP_SYN_SENT: + case TCP_LISTEN: + return; + } + + sock_owned_by_me(sk); + + memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); + sock_ops.op = BPF_SOCK_OPS_PARSE_HDR_OPT_CB; + sock_ops.is_fullsock = 1; + sock_ops.sk = sk; + bpf_skops_init_skb(&sock_ops, skb, tcp_hdrlen(skb)); + + BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops); +} + +static void bpf_skops_established(struct sock *sk, int bpf_op, + struct sk_buff *skb) +{ + struct bpf_sock_ops_kern sock_ops; + + sock_owned_by_me(sk); + + memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); + sock_ops.op = bpf_op; + sock_ops.is_fullsock = 1; + sock_ops.sk = sk; + /* sk with TCP_REPAIR_ON does not have skb in tcp_finish_connect */ + if (skb) + bpf_skops_init_skb(&sock_ops, skb, tcp_hdrlen(skb)); + + BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops); +} +#else +static void bpf_skops_parse_hdr(struct sock *sk, struct sk_buff *skb) +{ +} + +static void bpf_skops_established(struct sock *sk, int bpf_op, + struct sk_buff *skb) +{ +} +#endif + static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb, unsigned int len) { @@ -956,7 +1019,11 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq, ts ? LINUX_MIB_TCPTSREORDER : LINUX_MIB_TCPSACKREORDER); } -/* This must be called before lost_out is incremented */ + /* This must be called before lost_out or retrans_out are updated + * on a new loss, because we want to know if all skbs previously + * known to be lost have already been retransmitted, indicating + * that this newly lost skb is our next skb to retransmit. + */ static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb) { if ((!tp->retransmit_skb_hint && tp->retrans_out >= tp->lost_out) || @@ -966,41 +1033,36 @@ static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb) tp->retransmit_skb_hint = skb; } -/* Sum the number of packets on the wire we have marked as lost. - * There are two cases we care about here: - * a) Packet hasn't been marked lost (nor retransmitted), - * and this is the first loss. - * b) Packet has been marked both lost and retransmitted, - * and this means we think it was lost again. +/* Sum the number of packets on the wire we have marked as lost, and + * notify the congestion control module that the given skb was marked lost. */ -static void tcp_sum_lost(struct tcp_sock *tp, struct sk_buff *skb) +static void tcp_notify_skb_loss_event(struct tcp_sock *tp, const struct sk_buff *skb) { - __u8 sacked = TCP_SKB_CB(skb)->sacked; - - if (!(sacked & TCPCB_LOST) || - ((sacked & TCPCB_LOST) && (sacked & TCPCB_SACKED_RETRANS))) - tp->lost += tcp_skb_pcount(skb); + tp->lost += tcp_skb_pcount(skb); } -static void tcp_skb_mark_lost(struct tcp_sock *tp, struct sk_buff *skb) +void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb) { - if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) { - tcp_verify_retransmit_hint(tp, skb); + __u8 sacked = TCP_SKB_CB(skb)->sacked; + struct tcp_sock *tp = tcp_sk(sk); - tp->lost_out += tcp_skb_pcount(skb); - tcp_sum_lost(tp, skb); - TCP_SKB_CB(skb)->sacked |= TCPCB_LOST; - } -} + if (sacked & TCPCB_SACKED_ACKED) + return; -void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb) -{ tcp_verify_retransmit_hint(tp, skb); - - tcp_sum_lost(tp, skb); - if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) { + if (sacked & TCPCB_LOST) { + if (sacked & TCPCB_SACKED_RETRANS) { + /* Account for retransmits that are lost again */ + TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS; + tp->retrans_out -= tcp_skb_pcount(skb); + NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT, + tcp_skb_pcount(skb)); + tcp_notify_skb_loss_event(tp, skb); + } + } else { tp->lost_out += tcp_skb_pcount(skb); TCP_SKB_CB(skb)->sacked |= TCPCB_LOST; + tcp_notify_skb_loss_event(tp, skb); } } @@ -2263,7 +2325,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) if (cnt > packets) break; - tcp_skb_mark_lost(tp, skb); + if (!(TCP_SKB_CB(skb)->sacked & TCPCB_LOST)) + tcp_mark_skb_lost(sk, skb); if (mark_head) break; @@ -2629,14 +2692,8 @@ void tcp_simple_retransmit(struct sock *sk) unsigned int mss = tcp_current_mss(sk); skb_rbtree_walk(skb, &sk->tcp_rtx_queue) { - if (tcp_skb_seglen(skb) > mss && - !(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) { - if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { - TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS; - tp->retrans_out -= tcp_skb_pcount(skb); - } - tcp_skb_mark_lost_uncond_verify(tp, skb); - } + if (tcp_skb_seglen(skb) > mss) + tcp_mark_skb_lost(sk, skb); } tcp_clear_retrans_hints_partial(tp); @@ -3819,7 +3876,7 @@ static void tcp_parse_fastopen_option(int len, const unsigned char *cookie, foc->exp = exp_opt; } -static void smc_parse_options(const struct tcphdr *th, +static bool smc_parse_options(const struct tcphdr *th, struct tcp_options_received *opt_rx, const unsigned char *ptr, int opsize) @@ -3828,10 +3885,13 @@ static void smc_parse_options(const struct tcphdr *th, if (static_branch_unlikely(&tcp_have_smc)) { if (th->syn && !(opsize & 1) && opsize >= TCPOLEN_EXP_SMC_BASE && - get_unaligned_be32(ptr) == TCPOPT_SMC_MAGIC) + get_unaligned_be32(ptr) == TCPOPT_SMC_MAGIC) { opt_rx->smc_ok = 1; + return true; + } } #endif + return false; } /* Try to parse the MSS option from the TCP header. Return 0 on failure, clamped @@ -3892,6 +3952,7 @@ void tcp_parse_options(const struct net *net, ptr = (const unsigned char *)(th + 1); opt_rx->saw_tstamp = 0; + opt_rx->saw_unknown = 0; while (length > 0) { int opcode = *ptr++; @@ -3982,15 +4043,21 @@ void tcp_parse_options(const struct net *net, */ if (opsize >= TCPOLEN_EXP_FASTOPEN_BASE && get_unaligned_be16(ptr) == - TCPOPT_FASTOPEN_MAGIC) + TCPOPT_FASTOPEN_MAGIC) { tcp_parse_fastopen_option(opsize - TCPOLEN_EXP_FASTOPEN_BASE, ptr + 2, th->syn, foc, true); - else - smc_parse_options(th, opt_rx, ptr, - opsize); + break; + } + + if (smc_parse_options(th, opt_rx, ptr, opsize)) + break; + + opt_rx->saw_unknown = 1; break; + default: + opt_rx->saw_unknown = 1; } ptr += opsize-2; length -= opsize; @@ -4363,7 +4430,8 @@ static void tcp_sack_maybe_coalesce(struct tcp_sock *tp) sp[i] = sp[i + 1]; continue; } - this_sack++, swalk++; + this_sack++; + swalk++; } } @@ -4840,7 +4908,8 @@ void tcp_data_ready(struct sock *sk) int avail = tp->rcv_nxt - tp->copied_seq; if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) && - !sock_flag(sk, SOCK_DONE)) + !sock_flag(sk, SOCK_DONE) && + tcp_receive_window(tp) > inet_csk(sk)->icsk_ack.rcv_mss) return; sk->sk_data_ready(sk); @@ -4853,7 +4922,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) int eaten; if (sk_is_mptcp(sk)) - mptcp_incoming_options(sk, skb, &tp->rx_opt); + mptcp_incoming_options(sk, skb); if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { __kfree_skb(skb); @@ -5277,12 +5346,6 @@ static bool tcp_should_expand_sndbuf(const struct sock *sk) return true; } -/* When incoming ACK allowed to free some skb from write_queue, - * we remember this event in flag SOCK_QUEUE_SHRUNK and wake up socket - * on the exit from tcp input handler. - * - * PROBLEM: sndbuf expansion does not work well with largesend. - */ static void tcp_new_space(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); @@ -5297,16 +5360,13 @@ static void tcp_new_space(struct sock *sk) static void tcp_check_space(struct sock *sk) { - if (sock_flag(sk, SOCK_QUEUE_SHRUNK)) { - sock_reset_flag(sk, SOCK_QUEUE_SHRUNK); - /* pairs with tcp_poll() */ - smp_mb(); - if (sk->sk_socket && - test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { - tcp_new_space(sk); - if (!test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) - tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); - } + /* pairs with tcp_poll() */ + smp_mb(); + if (sk->sk_socket && + test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { + tcp_new_space(sk); + if (!test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) + tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } } @@ -5608,6 +5668,8 @@ syn_challenge: goto discard; } + bpf_skops_parse_hdr(sk, skb); + return true; discard: @@ -5766,6 +5828,8 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) tcp_data_snd_check(sk); if (!inet_csk_ack_scheduled(sk)) goto no_ack; + } else { + tcp_update_wl(tp, TCP_SKB_CB(skb)->seq); } __tcp_ack_snd_check(sk, 0); @@ -5816,7 +5880,7 @@ discard: } EXPORT_SYMBOL(tcp_rcv_established); -void tcp_init_transfer(struct sock *sk, int bpf_op) +void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -5837,8 +5901,10 @@ void tcp_init_transfer(struct sock *sk, int bpf_op) tp->snd_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk)); tp->snd_cwnd_stamp = tcp_jiffies32; - tcp_call_bpf(sk, bpf_op, 0, NULL); - tcp_init_congestion_control(sk); + icsk->icsk_ca_initialized = 0; + bpf_skops_established(sk, bpf_op, skb); + if (!icsk->icsk_ca_initialized) + tcp_init_congestion_control(sk); tcp_init_buffer_space(sk); } @@ -5856,7 +5922,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) sk_mark_napi_id(sk, skb); } - tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB); + tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB, skb); /* Prevent spurious tcp_cwnd_restart() on first data * packet. @@ -6328,7 +6394,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) } else { tcp_try_undo_spurious_syn(sk); tp->retrans_stamp = 0; - tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); + tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, + skb); WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); } smp_mb(); @@ -6438,7 +6505,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) case TCP_LAST_ACK: if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) { if (sk_is_mptcp(sk)) - mptcp_incoming_options(sk, skb, &tp->rx_opt); + mptcp_incoming_options(sk, skb); break; } fallthrough; @@ -6617,13 +6684,27 @@ static void tcp_reqsk_record_syn(const struct sock *sk, { if (tcp_sk(sk)->save_syn) { u32 len = skb_network_header_len(skb) + tcp_hdrlen(skb); - u32 *copy; + struct saved_syn *saved_syn; + u32 mac_hdrlen; + void *base; + + if (tcp_sk(sk)->save_syn == 2) { /* Save full header. */ + base = skb_mac_header(skb); + mac_hdrlen = skb_mac_header_len(skb); + len += mac_hdrlen; + } else { + base = skb_network_header(skb); + mac_hdrlen = 0; + } - copy = kmalloc(len + sizeof(u32), GFP_ATOMIC); - if (copy) { - copy[0] = len; - memcpy(©[1], skb_network_header(skb), len); - req->saved_syn = copy; + saved_syn = kmalloc(struct_size(saved_syn, data, len), + GFP_ATOMIC); + if (saved_syn) { + saved_syn->mac_hdrlen = mac_hdrlen; + saved_syn->network_hdrlen = skb_network_header_len(skb); + saved_syn->tcp_hdrlen = tcp_hdrlen(skb); + memcpy(saved_syn->data, base, len); + req->saved_syn = saved_syn; } } } @@ -6762,6 +6843,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_rsk(req)->snt_isn = isn; tcp_rsk(req)->txhash = net_tx_rndhash(); + tcp_rsk(req)->syn_tos = TCP_SKB_CB(skb)->ip_dsfield; tcp_openreq_init_rwin(req, sk, dst); sk_rx_queue_set(req_to_sk(req), skb); if (!want_cookie) { @@ -6770,7 +6852,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, } if (fastopen_sk) { af_ops->send_synack(fastopen_sk, dst, &fl, req, - &foc, TCP_SYNACK_FASTOPEN); + &foc, TCP_SYNACK_FASTOPEN, skb); /* Add the child socket directly into the accept queue */ if (!inet_csk_reqsk_queue_add(sk, req, fastopen_sk)) { reqsk_fastopen_remove(fastopen_sk, req, false); @@ -6788,7 +6870,8 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_timeout_init((struct sock *)req)); af_ops->send_synack(sk, dst, &fl, req, &foc, !want_cookie ? TCP_SYNACK_NORMAL : - TCP_SYNACK_COOKIE); + TCP_SYNACK_COOKIE, + skb); if (want_cookie) { reqsk_free(req); return 0; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 592c73962723..7352c097ae48 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -575,7 +575,7 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) case TCP_SYN_SENT: case TCP_SYN_RECV: /* Only in fast or simultaneous open. If a fast open socket is - * is already accepted it is treated as a connected one below. + * already accepted it is treated as a connected one below. */ if (fastopen && !fastopen->sk) break; @@ -965,18 +965,23 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, - enum tcp_synack_type synack_type) + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb) { const struct inet_request_sock *ireq = inet_rsk(req); struct flowi4 fl4; int err = -1; struct sk_buff *skb; + u8 tos; /* First, grab a route. */ if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL) return -1; - skb = tcp_make_synack(sk, dst, req, foc, synack_type); + skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb); + + tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? + tcp_rsk(req)->syn_tos : inet_sk(sk)->tos; if (skb) { __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); @@ -984,7 +989,8 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, rcu_read_lock(); err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, - rcu_dereference(ireq->ireq_opt)); + rcu_dereference(ireq->ireq_opt), + tos & ~INET_ECN_MASK); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -1529,6 +1535,10 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; newinet->inet_id = prandom_u32(); + /* Set ToS of the new socket based upon the value of incoming SYN. */ + if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) + newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; + if (!dst) { dst = inet_csk_route_child_sock(sk, newsk, req); if (!dst) diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 279db8822439..6b27c481fe18 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -943,7 +943,7 @@ static int tcp_metrics_nl_cmd_del(struct sk_buff *skb, struct genl_info *info) return 0; } -static const struct genl_ops tcp_metrics_nl_ops[] = { +static const struct genl_small_ops tcp_metrics_nl_ops[] = { { .cmd = TCP_METRICS_CMD_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, @@ -966,8 +966,8 @@ static struct genl_family tcp_metrics_nl_family __ro_after_init = { .policy = tcp_metrics_nl_policy, .netnsok = true, .module = THIS_MODULE, - .ops = tcp_metrics_nl_ops, - .n_ops = ARRAY_SIZE(tcp_metrics_nl_ops), + .small_ops = tcp_metrics_nl_ops, + .n_small_ops = ARRAY_SIZE(tcp_metrics_nl_ops), }; static unsigned int tcpmhash_entries; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 85ff417bda7f..bf48cd73e967 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -438,6 +438,7 @@ struct tcp_out_options { u8 ws; /* window scale, 0 to disable */ u8 num_sack_blocks; /* number of SACK blocks to include */ u8 hash_size; /* bytes in hash_location */ + u8 bpf_opt_len; /* length of BPF hdr option */ __u8 *hash_location; /* temporary pointer, overloaded */ __u32 tsval, tsecr; /* need to include OPTION_TS */ struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */ @@ -452,6 +453,145 @@ static void mptcp_options_write(__be32 *ptr, struct tcp_out_options *opts) #endif } +#ifdef CONFIG_CGROUP_BPF +static int bpf_skops_write_hdr_opt_arg0(struct sk_buff *skb, + enum tcp_synack_type synack_type) +{ + if (unlikely(!skb)) + return BPF_WRITE_HDR_TCP_CURRENT_MSS; + + if (unlikely(synack_type == TCP_SYNACK_COOKIE)) + return BPF_WRITE_HDR_TCP_SYNACK_COOKIE; + + return 0; +} + +/* req, syn_skb and synack_type are used when writing synack */ +static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct sk_buff *syn_skb, + enum tcp_synack_type synack_type, + struct tcp_out_options *opts, + unsigned int *remaining) +{ + struct bpf_sock_ops_kern sock_ops; + int err; + + if (likely(!BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), + BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG)) || + !*remaining) + return; + + /* *remaining has already been aligned to 4 bytes, so *remaining >= 4 */ + + /* init sock_ops */ + memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); + + sock_ops.op = BPF_SOCK_OPS_HDR_OPT_LEN_CB; + + if (req) { + /* The listen "sk" cannot be passed here because + * it is not locked. It would not make too much + * sense to do bpf_setsockopt(listen_sk) based + * on individual connection request also. + * + * Thus, "req" is passed here and the cgroup-bpf-progs + * of the listen "sk" will be run. + * + * "req" is also used here for fastopen even the "sk" here is + * a fullsock "child" sk. It is to keep the behavior + * consistent between fastopen and non-fastopen on + * the bpf programming side. + */ + sock_ops.sk = (struct sock *)req; + sock_ops.syn_skb = syn_skb; + } else { + sock_owned_by_me(sk); + + sock_ops.is_fullsock = 1; + sock_ops.sk = sk; + } + + sock_ops.args[0] = bpf_skops_write_hdr_opt_arg0(skb, synack_type); + sock_ops.remaining_opt_len = *remaining; + /* tcp_current_mss() does not pass a skb */ + if (skb) + bpf_skops_init_skb(&sock_ops, skb, 0); + + err = BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk); + + if (err || sock_ops.remaining_opt_len == *remaining) + return; + + opts->bpf_opt_len = *remaining - sock_ops.remaining_opt_len; + /* round up to 4 bytes */ + opts->bpf_opt_len = (opts->bpf_opt_len + 3) & ~3; + + *remaining -= opts->bpf_opt_len; +} + +static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct sk_buff *syn_skb, + enum tcp_synack_type synack_type, + struct tcp_out_options *opts) +{ + u8 first_opt_off, nr_written, max_opt_len = opts->bpf_opt_len; + struct bpf_sock_ops_kern sock_ops; + int err; + + if (likely(!max_opt_len)) + return; + + memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); + + sock_ops.op = BPF_SOCK_OPS_WRITE_HDR_OPT_CB; + + if (req) { + sock_ops.sk = (struct sock *)req; + sock_ops.syn_skb = syn_skb; + } else { + sock_owned_by_me(sk); + + sock_ops.is_fullsock = 1; + sock_ops.sk = sk; + } + + sock_ops.args[0] = bpf_skops_write_hdr_opt_arg0(skb, synack_type); + sock_ops.remaining_opt_len = max_opt_len; + first_opt_off = tcp_hdrlen(skb) - max_opt_len; + bpf_skops_init_skb(&sock_ops, skb, first_opt_off); + + err = BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk); + + if (err) + nr_written = 0; + else + nr_written = max_opt_len - sock_ops.remaining_opt_len; + + if (nr_written < max_opt_len) + memset(skb->data + first_opt_off + nr_written, TCPOPT_NOP, + max_opt_len - nr_written); +} +#else +static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct sk_buff *syn_skb, + enum tcp_synack_type synack_type, + struct tcp_out_options *opts, + unsigned int *remaining) +{ +} + +static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct sk_buff *syn_skb, + enum tcp_synack_type synack_type, + struct tcp_out_options *opts) +{ +} +#endif + /* Write previously computed TCP options to the packet. * * Beware: Something in the Internet is very sensitive to the ordering of @@ -691,6 +831,8 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, } } + bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining); + return MAX_TCP_OPTION_SPACE - remaining; } @@ -701,7 +843,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, struct tcp_out_options *opts, const struct tcp_md5sig_key *md5, struct tcp_fastopen_cookie *foc, - enum tcp_synack_type synack_type) + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE; @@ -758,6 +901,9 @@ static unsigned int tcp_synack_options(const struct sock *sk, smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining); + bpf_skops_hdr_opt_len((struct sock *)sk, skb, req, syn_skb, + synack_type, opts, &remaining); + return MAX_TCP_OPTION_SPACE - remaining; } @@ -826,6 +972,15 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; } + if (unlikely(BPF_SOCK_OPS_TEST_FLAG(tp, + BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG))) { + unsigned int remaining = MAX_TCP_OPTION_SPACE - size; + + bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining); + + size = MAX_TCP_OPTION_SPACE - remaining; + } + return size; } @@ -1213,6 +1368,9 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, } #endif + /* BPF prog is the last one writing header option */ + bpf_skops_write_hdr_opt(sk, skb, NULL, NULL, 0, &opts); + INDIRECT_CALL_INET(icsk->icsk_af_ops->send_check, tcp_v6_send_check, tcp_v4_send_check, sk, skb); @@ -1524,7 +1682,6 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) skb->truesize -= delta_truesize; sk_wmem_queued_add(sk, -delta_truesize); sk_mem_uncharge(sk, delta_truesize); - sock_set_flag(sk, SOCK_QUEUE_SHRUNK); } /* Any change of skb->len requires recalculation of tso factor. */ @@ -3336,20 +3493,20 @@ int tcp_send_synack(struct sock *sk) } /** - * tcp_make_synack - Prepare a SYN-ACK. - * sk: listener socket - * dst: dst entry attached to the SYNACK - * req: request_sock pointer - * foc: cookie for tcp fast open - * synack_type: Type of synback to prepare - * - * Allocate one skb and build a SYNACK packet. - * @dst is consumed : Caller should not use it again. + * tcp_make_synack - Allocate one skb and build a SYNACK packet. + * @sk: listener socket + * @dst: dst entry attached to the SYNACK. It is consumed and caller + * should not use it again. + * @req: request_sock pointer + * @foc: cookie for tcp fast open + * @synack_type: Type of synack to prepare + * @syn_skb: SYN packet just received. It could be NULL for rtx case. */ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc, - enum tcp_synack_type synack_type) + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); const struct tcp_sock *tp = tcp_sk(sk); @@ -3408,8 +3565,11 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req)); #endif skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4); + /* bpf program will be interested in the tcp_flags */ + TCP_SKB_CB(skb)->tcp_flags = TCPHDR_SYN | TCPHDR_ACK; tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, - foc, synack_type) + sizeof(*th); + foc, synack_type, + syn_skb) + sizeof(*th); skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); @@ -3441,6 +3601,9 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, rcu_read_unlock(); #endif + bpf_skops_write_hdr_opt((struct sock *)sk, skb, req, syn_skb, + synack_type, &opts); + skb->skb_mstamp_ns = now; tcp_add_tx_delay(skb, tp); @@ -3741,16 +3904,15 @@ void tcp_send_delayed_ack(struct sock *sk) ato = min(ato, max_ato); } + ato = min_t(u32, ato, inet_csk(sk)->icsk_delack_max); + /* Stay within the limit we were given */ timeout = jiffies + ato; /* Use new timeout only if there wasn't a older one earlier. */ if (icsk->icsk_ack.pending & ICSK_ACK_TIMER) { - /* If delack timer was blocked or is about to expire, - * send ACK now. - */ - if (icsk->icsk_ack.blocked || - time_before_eq(icsk->icsk_ack.timeout, jiffies + (ato >> 2))) { + /* If delack timer is about to expire, send ACK now. */ + if (time_before_eq(icsk->icsk_ack.timeout, jiffies + (ato >> 2))) { tcp_send_ack(sk); return; } @@ -3779,10 +3941,15 @@ void __tcp_send_ack(struct sock *sk, u32 rcv_nxt) buff = alloc_skb(MAX_TCP_HEADER, sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN)); if (unlikely(!buff)) { + struct inet_connection_sock *icsk = inet_csk(sk); + unsigned long delay; + + delay = TCP_DELACK_MAX << icsk->icsk_ack.retry; + if (delay < TCP_RTO_MAX) + icsk->icsk_ack.retry++; inet_csk_schedule_ack(sk); - inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN; - inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, - TCP_DELACK_MAX, TCP_RTO_MAX); + icsk->icsk_ack.ato = TCP_ATO_MIN; + inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, delay, TCP_RTO_MAX); return; } @@ -3934,7 +4101,8 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) int res; tcp_rsk(req)->txhash = net_tx_rndhash(); - res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL); + res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL, + NULL); if (!res) { __TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index fdb715bdd2d1..f65a3ddd0d58 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -2,20 +2,6 @@ #include <linux/tcp.h> #include <net/tcp.h> -void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb) -{ - struct tcp_sock *tp = tcp_sk(sk); - - tcp_skb_mark_lost_uncond_verify(tp, skb); - if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { - /* Account for retransmits that are lost again */ - TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS; - tp->retrans_out -= tcp_skb_pcount(skb); - NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT, - tcp_skb_pcount(skb)); - } -} - static bool tcp_rack_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) { return t1 > t2 || (t1 == t2 && after(seq1, seq2)); @@ -246,6 +232,6 @@ void tcp_newreno_mark_lost(struct sock *sk, bool snd_una_advanced) tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, mss, mss, GFP_ATOMIC); - tcp_skb_mark_lost_uncond_verify(tp, skb); + tcp_mark_skb_lost(sk, skb); } } diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c index 6cebf412d590..5842081bc8a2 100644 --- a/net/ipv4/tcp_scalable.c +++ b/net/ipv4/tcp_scalable.c @@ -10,7 +10,7 @@ #include <net/tcp.h> /* These factors derived from the recommended values in the aer: - * .01 and and 7/8. + * .01 and 7/8. */ #define TCP_SCALABLE_AI_CNT 100U #define TCP_SCALABLE_MD_SCALE 3 diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 0c08c420fbc2..6c62b9ea1320 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -331,7 +331,6 @@ static void tcp_delack_timer(struct timer_list *t) if (!sock_owned_by_user(sk)) { tcp_delack_timer_handler(sk); } else { - icsk->icsk_ack.blocked = 1; __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED); /* deleguate our work to tcp_release_cb() */ if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &sk->sk_tsq_flags)) diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index 3f51e781562a..c8003c8aad2c 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -293,10 +293,10 @@ size_t tcp_vegas_get_info(struct sock *sk, u32 ext, int *attr, const struct vegas *ca = inet_csk_ca(sk); if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) { - info->vegas.tcpv_enabled = ca->doing_vegas_now, - info->vegas.tcpv_rttcnt = ca->cntRTT, - info->vegas.tcpv_rtt = ca->baseRTT, - info->vegas.tcpv_minrtt = ca->minRTT, + info->vegas.tcpv_enabled = ca->doing_vegas_now; + info->vegas.tcpv_rttcnt = ca->cntRTT; + info->vegas.tcpv_rtt = ca->baseRTT; + info->vegas.tcpv_minrtt = ca->minRTT; *attr = INET_DIAG_VEGASINFO; return sizeof(struct tcpvegas_info); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index e88efba07551..09f0a23d1a01 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1170,7 +1170,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc.oif = inet->uc_index; } else if (ipv4_is_lbcast(daddr) && inet->uc_index) { /* oif is set, packet is to local broadcast and - * and uc_index is set. oif is most likely set + * uc_index is set. oif is most likely set * by sk_bound_dev_if. If uc_index != oif check if the * oif is an L3 master and uc_index is an L3 slave. * If so, we want to allow the send using the uc_index. diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c index eddd973e6575..7a94791efc1a 100644 --- a/net/ipv4/udp_bpf.c +++ b/net/ipv4/udp_bpf.c @@ -22,10 +22,9 @@ static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base) prot->close = sock_map_close; } -static void udp_bpf_check_v6_needs_rebuild(struct sock *sk, struct proto *ops) +static void udp_bpf_check_v6_needs_rebuild(struct proto *ops) { - if (sk->sk_family == AF_INET6 && - unlikely(ops != smp_load_acquire(&udpv6_prot_saved))) { + if (unlikely(ops != smp_load_acquire(&udpv6_prot_saved))) { spin_lock_bh(&udpv6_prot_lock); if (likely(ops != udpv6_prot_saved)) { udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV6], ops); @@ -46,8 +45,8 @@ struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock) { int family = sk->sk_family == AF_INET ? UDP_BPF_IPV4 : UDP_BPF_IPV6; - if (!psock->sk_proto) - udp_bpf_check_v6_needs_rebuild(sk, READ_ONCE(sk->sk_prot)); + if (sk->sk_family == AF_INET6) + udp_bpf_check_v6_needs_rebuild(psock->sk_proto); return &udp_bpf_prots[family]; } diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c index 69962165c0e8..0d122edc368d 100644 --- a/net/ipv4/udp_tunnel_nic.c +++ b/net/ipv4/udp_tunnel_nic.c @@ -19,8 +19,9 @@ enum udp_tunnel_nic_table_entry_flags { struct udp_tunnel_nic_table_entry { __be16 port; u8 type; - u8 use_cnt; u8 flags; + u16 use_cnt; +#define UDP_TUNNEL_NIC_USE_CNT_MAX U16_MAX u8 hw_priv; }; @@ -370,6 +371,8 @@ udp_tunnel_nic_entry_adj(struct udp_tunnel_nic *utn, bool dodgy = entry->flags & UDP_TUNNEL_NIC_ENTRY_OP_FAIL; unsigned int from, to; + WARN_ON(entry->use_cnt + (u32)use_cnt_adj > U16_MAX); + /* If not going from used to unused or vice versa - all done. * For dodgy entries make sure we try to sync again (queue the entry). */ @@ -675,6 +678,7 @@ static void udp_tunnel_nic_replay(struct net_device *dev, struct udp_tunnel_nic *utn) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; + struct udp_tunnel_nic_shared_node *node; unsigned int i, j; /* Freeze all the ports we are already tracking so that the replay @@ -686,7 +690,12 @@ udp_tunnel_nic_replay(struct net_device *dev, struct udp_tunnel_nic *utn) utn->missed = 0; utn->need_replay = 0; - udp_tunnel_get_rx_info(dev); + if (!info->shared) { + udp_tunnel_get_rx_info(dev); + } else { + list_for_each_entry(node, &info->shared->devices, list) + udp_tunnel_get_rx_info(node->dev); + } for (i = 0; i < utn->n_tables; i++) for (j = 0; j < info->tables[i].n_entries; j++) @@ -742,20 +751,39 @@ err_free_utn: return NULL; } +static void udp_tunnel_nic_free(struct udp_tunnel_nic *utn) +{ + unsigned int i; + + for (i = 0; i < utn->n_tables; i++) + kfree(utn->entries[i]); + kfree(utn->entries); + kfree(utn); +} + static int udp_tunnel_nic_register(struct net_device *dev) { const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; + struct udp_tunnel_nic_shared_node *node = NULL; struct udp_tunnel_nic *utn; unsigned int n_tables, i; BUILD_BUG_ON(sizeof(utn->missed) * BITS_PER_BYTE < UDP_TUNNEL_NIC_MAX_TABLES); + /* Expect use count of at most 2 (IPv4, IPv6) per device */ + BUILD_BUG_ON(UDP_TUNNEL_NIC_USE_CNT_MAX < + UDP_TUNNEL_NIC_MAX_SHARING_DEVICES * 2); + /* Check that the driver info is sane */ if (WARN_ON(!info->set_port != !info->unset_port) || WARN_ON(!info->set_port == !info->sync_table) || WARN_ON(!info->tables[0].n_entries)) return -EINVAL; + if (WARN_ON(info->shared && + info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY)) + return -EINVAL; + n_tables = 1; for (i = 1; i < UDP_TUNNEL_NIC_MAX_TABLES; i++) { if (!info->tables[i].n_entries) @@ -766,9 +794,33 @@ static int udp_tunnel_nic_register(struct net_device *dev) return -EINVAL; } - utn = udp_tunnel_nic_alloc(info, n_tables); - if (!utn) - return -ENOMEM; + /* Create UDP tunnel state structures */ + if (info->shared) { + node = kzalloc(sizeof(*node), GFP_KERNEL); + if (!node) + return -ENOMEM; + + node->dev = dev; + } + + if (info->shared && info->shared->udp_tunnel_nic_info) { + utn = info->shared->udp_tunnel_nic_info; + } else { + utn = udp_tunnel_nic_alloc(info, n_tables); + if (!utn) { + kfree(node); + return -ENOMEM; + } + } + + if (info->shared) { + if (!info->shared->udp_tunnel_nic_info) { + INIT_LIST_HEAD(&info->shared->devices); + info->shared->udp_tunnel_nic_info = utn; + } + + list_add_tail(&node->list, &info->shared->devices); + } utn->dev = dev; dev_hold(dev); @@ -783,7 +835,33 @@ static int udp_tunnel_nic_register(struct net_device *dev) static void udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn) { - unsigned int i; + const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info; + + /* For a shared table remove this dev from the list of sharing devices + * and if there are other devices just detach. + */ + if (info->shared) { + struct udp_tunnel_nic_shared_node *node, *first; + + list_for_each_entry(node, &info->shared->devices, list) + if (node->dev == dev) + break; + if (node->dev != dev) + return; + + list_del(&node->list); + kfree(node); + + first = list_first_entry_or_null(&info->shared->devices, + typeof(*first), list); + if (first) { + udp_tunnel_drop_rx_info(dev); + utn->dev = first->dev; + goto release_dev; + } + + info->shared->udp_tunnel_nic_info = NULL; + } /* Flush before we check work, so we don't waste time adding entries * from the work which we will boot immediately. @@ -796,10 +874,8 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn) if (utn->work_pending) return; - for (i = 0; i < utn->n_tables; i++) - kfree(utn->entries[i]); - kfree(utn->entries); - kfree(utn); + udp_tunnel_nic_free(utn); +release_dev: dev->udp_tunnel_nic = NULL; dev_put(dev); } diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 9ebf3fe0d2b1..c70c192bc91b 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -191,6 +191,13 @@ static int eafnosupport_ip6_del_rt(struct net *net, struct fib6_info *rt, return -EAFNOSUPPORT; } +static int eafnosupport_ipv6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct net *, struct sock *, struct sk_buff *)) +{ + kfree_skb(skb); + return -EAFNOSUPPORT; +} + const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { .ipv6_dst_lookup_flow = eafnosupport_ipv6_dst_lookup_flow, .ipv6_route_input = eafnosupport_ipv6_route_input, @@ -201,6 +208,7 @@ const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { .ip6_mtu_from_fib6 = eafnosupport_ip6_mtu_from_fib6, .fib6_nh_init = eafnosupport_fib6_nh_init, .ip6_del_rt = eafnosupport_ip6_del_rt, + .ipv6_fragment = eafnosupport_ipv6_fragment, }; EXPORT_SYMBOL_GPL(ipv6_stub); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 0306509ab063..e648fbebb167 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -661,6 +661,7 @@ int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, const struct proto_ops inet6_stream_ops = { .family = PF_INET6, + .flags = PROTO_CMSG_DATA_ONLY, .owner = THIS_MODULE, .release = inet6_release, .bind = inet6_bind, @@ -1026,6 +1027,7 @@ static const struct ipv6_stub ipv6_stub_impl = { .xfrm6_rcv_encap = xfrm6_rcv_encap, #endif .nd_tbl = &nd_tbl, + .ipv6_fragment = ip6_fragment, }; static const struct ipv6_bpf_stub ipv6_bpf_stub_impl = { diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index 8d3f66c310db..78f766019b7e 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -761,7 +761,7 @@ static int calipso_genopt(unsigned char *buf, u32 start, u32 buf_len, calipso[1] = len - 2; *(__be32 *)(calipso + 2) = htonl(doi_def->doi); calipso[6] = (len - CALIPSO_HDR_LEN) / 4; - calipso[7] = secattr->attr.mls.lvl, + calipso[7] = secattr->attr.mls.lvl; crc = ~crc_ccitt(0xffff, calipso, len); calipso[8] = crc & 0xff; calipso[9] = (crc >> 8) & 0xff; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index a4e4912ad607..8956144ea65e 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -158,7 +158,13 @@ static bool is_ineligible(const struct sk_buff *skb) tp = skb_header_pointer(skb, ptr+offsetof(struct icmp6hdr, icmp6_type), sizeof(_type), &_type); - if (!tp || !(*tp & ICMPV6_INFOMSG_MASK)) + + /* Based on RFC 8200, Section 4.5 Fragment Header, return + * false if this is a fragment packet with no icmp header info. + */ + if (!tp && frag_off != 0) + return false; + else if (!tp || !(*tp & ICMPV6_INFOMSG_MASK)) return true; } return false; @@ -314,10 +320,10 @@ static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, st { struct icmpv6_msg *msg = (struct icmpv6_msg *) from; struct sk_buff *org_skb = msg->skb; - __wsum csum = 0; + __wsum csum; csum = skb_copy_and_csum_bits(org_skb, msg->offset + offset, - to, len, csum); + to, len); skb->csum = csum_block_add(skb->csum, csum, odd); if (!(msg->type & ICMPV6_INFOMSG_MASK)) nf_ct_attach(skb, org_skb); @@ -501,8 +507,11 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, if (__ipv6_addr_needs_scope_id(addr_type)) { iif = icmp6_iif(skb); } else { - dst = skb_dst(skb); - iif = l3mdev_master_ifindex(dst ? dst->dev : skb->dev); + /* + * The source device is used for looking up which routing table + * to use for sending an ICMP error. + */ + iif = l3mdev_master_ifindex(skb->dev); } /* diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 2d3add9e6116..55c290d55605 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -94,7 +94,7 @@ EXPORT_SYMBOL(__inet6_lookup_established); static inline int compute_score(struct sock *sk, struct net *net, const unsigned short hnum, const struct in6_addr *daddr, - const int dif, const int sdif, bool exact_dif) + const int dif, const int sdif) { int score = -1; @@ -138,15 +138,13 @@ static struct sock *inet6_lhash2_lookup(struct net *net, const __be16 sport, const struct in6_addr *daddr, const unsigned short hnum, const int dif, const int sdif) { - bool exact_dif = inet6_exact_dif_match(net, skb); struct inet_connection_sock *icsk; struct sock *sk, *result = NULL; int score, hiscore = 0; inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) { sk = (struct sock *)icsk; - score = compute_score(sk, net, hnum, daddr, dif, sdif, - exact_dif); + score = compute_score(sk, net, hnum, daddr, dif, sdif); if (score > hiscore) { result = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 4a664ad4f4d4..605cdd38a919 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1812,10 +1812,14 @@ static struct fib6_node *fib6_repair_tree(struct net *net, children = 0; child = NULL; - if (fn_r) - child = fn_r, children |= 1; - if (fn_l) - child = fn_l, children |= 2; + if (fn_r) { + child = fn_r; + children |= 1; + } + if (fn_l) { + child = fn_l; + children |= 2; + } if (children == 3 || FIB6_SUBTREE(fn) #ifdef CONFIG_IPV6_SUBTREES @@ -2618,8 +2622,10 @@ static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) iter->skip = *pos; if (iter->tbl) { + loff_t p = 0; + ipv6_route_seq_setup_walk(iter, net); - return ipv6_route_seq_next(seq, NULL, pos); + return ipv6_route_seq_next(seq, NULL, &p); } else { return NULL; } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 3a57fb9ce049..931b186d2e48 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -707,6 +707,17 @@ static int prepare_ip6gre_xmit_ipv6(struct sk_buff *skb, return 0; } +static struct ip_tunnel_info *skb_tunnel_info_txcheck(struct sk_buff *skb) +{ + struct ip_tunnel_info *tun_info; + + tun_info = skb_tunnel_info(skb); + if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX))) + return ERR_PTR(-EINVAL); + + return tun_info; +} + static netdev_tx_t __gre6_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, struct flowi6 *fl6, int encap_limit, @@ -734,10 +745,9 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, const struct ip_tunnel_key *key; __be16 flags; - tun_info = skb_tunnel_info(skb); - if (unlikely(!tun_info || - !(tun_info->mode & IP_TUNNEL_INFO_TX) || - ip_tunnel_info_af(tun_info) != AF_INET6)) + tun_info = skb_tunnel_info_txcheck(skb); + if (IS_ERR(tun_info) || + unlikely(ip_tunnel_info_af(tun_info) != AF_INET6)) return -EINVAL; key = &tun_info->key; @@ -908,7 +918,8 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, return NETDEV_TX_OK; tx_err: - stats->tx_errors++; + if (!t->parms.collect_md || !IS_ERR(skb_tunnel_info_txcheck(skb))) + stats->tx_errors++; stats->tx_dropped++; kfree_skb(skb); return NETDEV_TX_OK; @@ -917,6 +928,7 @@ tx_err: static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { + struct ip_tunnel_info *tun_info = NULL; struct ip6_tnl *t = netdev_priv(dev); struct dst_entry *dst = skb_dst(skb); struct net_device_stats *stats; @@ -964,15 +976,13 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, * for native mode, call prepare_ip6gre_xmit_{ipv4,ipv6}. */ if (t->parms.collect_md) { - struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; struct erspan_metadata *md; __be32 tun_id; - tun_info = skb_tunnel_info(skb); - if (unlikely(!tun_info || - !(tun_info->mode & IP_TUNNEL_INFO_TX) || - ip_tunnel_info_af(tun_info) != AF_INET6)) + tun_info = skb_tunnel_info_txcheck(skb); + if (IS_ERR(tun_info) || + unlikely(ip_tunnel_info_af(tun_info) != AF_INET6)) goto tx_err; key = &tun_info->key; @@ -1065,7 +1075,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, tx_err: stats = &t->dev->stats; - stats->tx_errors++; + if (!IS_ERR(tun_info)) + stats->tx_errors++; stats->tx_dropped++; kfree_skb(skb); return NETDEV_TX_OK; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index c78e67d7747f..749ad72386b2 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -468,8 +468,6 @@ int ip6_forward(struct sk_buff *skb) * check and decrement ttl */ if (hdr->hop_limit <= 1) { - /* Force OUTPUT device used as source address */ - skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); @@ -1492,7 +1490,7 @@ emsgsize: * Otherwise, we need to reserve fragment header and * fragment alignment (= 8-15 octects, in total). * - * Note that we may need to "move" the data from the tail of + * Note that we may need to "move" the data from the tail * of the buffer to the new fragment when we split * the message. * @@ -1615,7 +1613,7 @@ alloc_new_skb: if (fraggap) { skb->csum = skb_copy_and_csum_bits( skb_prev, maxfraglen, - data + transhdrlen, fraggap, 0); + data + transhdrlen, fraggap); skb_prev->csum = csum_sub(skb_prev->csum, skb->csum); data += fraggap; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index a0217e5bf3bc..648db3fe508f 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1271,6 +1271,8 @@ route_lookup: if (max_headroom > dev->needed_headroom) dev->needed_headroom = max_headroom; + skb_set_inner_ipproto(skb, proto); + err = ip6_tnl_encap(skb, t, &proto, fl6); if (err) return err; @@ -1280,8 +1282,6 @@ route_lookup: ipv6_push_frag_opts(skb, &opt.ops, &proto); } - skb_set_inner_ipproto(skb, proto); - skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); ipv6h = ipv6_hdr(skb); diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index fac01b80a104..5f9c4fdc120d 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -347,7 +347,6 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err) { unsigned short family; struct net_device *dev; - struct pcpu_sw_netstats *tstats; struct xfrm_state *x; const struct xfrm_mode *inner_mode; struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6; @@ -390,12 +389,7 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err) skb_scrub_packet(skb, !net_eq(t->net, dev_net(skb->dev))); skb->dev = dev; - - tstats = this_cpu_ptr(dev->tstats); - u64_stats_update_begin(&tstats->syncp); - tstats->rx_packets++; - tstats->rx_bytes += skb->len; - u64_stats_update_end(&tstats->syncp); + dev_sw_netstats_rx_add(dev, skb->len); return 0; } diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 6d0e942d082d..ab9a279dd6d4 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -20,10 +20,10 @@ #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #include "../bridge/br_private.h" -int ip6_route_me_harder(struct net *net, struct sk_buff *skb) +int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff *skb) { const struct ipv6hdr *iph = ipv6_hdr(skb); - struct sock *sk = sk_to_full_sk(skb->sk); + struct sock *sk = sk_to_full_sk(sk_partial); unsigned int hh_len; struct dst_entry *dst; int strict = (ipv6_addr_type(&iph->daddr) & @@ -84,7 +84,7 @@ static int nf_ip6_reroute(struct sk_buff *skb, if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) || !ipv6_addr_equal(&iph->saddr, &rt_info->saddr) || skb->mark != rt_info->mark) - return ip6_route_me_harder(entry->state.net, skb); + return ip6_route_me_harder(entry->state.net, entry->state.sk, skb); } return 0; } diff --git a/net/ipv6/netfilter/ip6t_NPT.c b/net/ipv6/netfilter/ip6t_NPT.c index 9ee077bf4f49..787c74aa85e3 100644 --- a/net/ipv6/netfilter/ip6t_NPT.c +++ b/net/ipv6/netfilter/ip6t_NPT.c @@ -77,16 +77,43 @@ static bool ip6t_npt_map_pfx(const struct ip6t_npt_tginfo *npt, return true; } +static struct ipv6hdr *icmpv6_bounced_ipv6hdr(struct sk_buff *skb, + struct ipv6hdr *_bounced_hdr) +{ + if (ipv6_hdr(skb)->nexthdr != IPPROTO_ICMPV6) + return NULL; + + if (!icmpv6_is_err(icmp6_hdr(skb)->icmp6_type)) + return NULL; + + return skb_header_pointer(skb, + skb_transport_offset(skb) + sizeof(struct icmp6hdr), + sizeof(struct ipv6hdr), + _bounced_hdr); +} + static unsigned int ip6t_snpt_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ip6t_npt_tginfo *npt = par->targinfo; + struct ipv6hdr _bounced_hdr; + struct ipv6hdr *bounced_hdr; + struct in6_addr bounced_pfx; if (!ip6t_npt_map_pfx(npt, &ipv6_hdr(skb)->saddr)) { icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD, offsetof(struct ipv6hdr, saddr)); return NF_DROP; } + + /* rewrite dst addr of bounced packet which was sent to dst range */ + bounced_hdr = icmpv6_bounced_ipv6hdr(skb, &_bounced_hdr); + if (bounced_hdr) { + ipv6_addr_prefix(&bounced_pfx, &bounced_hdr->daddr, npt->src_pfx_len); + if (ipv6_addr_cmp(&bounced_pfx, &npt->src_pfx.in6) == 0) + ip6t_npt_map_pfx(npt, &bounced_hdr->daddr); + } + return XT_CONTINUE; } @@ -94,12 +121,24 @@ static unsigned int ip6t_dnpt_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ip6t_npt_tginfo *npt = par->targinfo; + struct ipv6hdr _bounced_hdr; + struct ipv6hdr *bounced_hdr; + struct in6_addr bounced_pfx; if (!ip6t_npt_map_pfx(npt, &ipv6_hdr(skb)->daddr)) { icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD, offsetof(struct ipv6hdr, daddr)); return NF_DROP; } + + /* rewrite src addr of bounced packet which was sent from dst range */ + bounced_hdr = icmpv6_bounced_ipv6hdr(skb, &_bounced_hdr); + if (bounced_hdr) { + ipv6_addr_prefix(&bounced_pfx, &bounced_hdr->saddr, npt->src_pfx_len); + if (ipv6_addr_cmp(&bounced_pfx, &npt->src_pfx.in6) == 0) + ip6t_npt_map_pfx(npt, &bounced_hdr->saddr); + } + return XT_CONTINUE; } diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 1a2748611e00..cee74803d7a1 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -57,7 +57,7 @@ ip6t_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) skb->mark != mark || ipv6_hdr(skb)->hop_limit != hop_limit || flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) { - err = ip6_route_me_harder(state->net, skb); + err = ip6_route_me_harder(state->net, state->sk, skb); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index fed9666a2f7d..054d287eb13d 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -355,6 +355,7 @@ static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, ipv6_hdr(skb)->payload_len = htons(payload_len); ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn); IP6CB(skb)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size; + IP6CB(skb)->flags |= IP6SKB_FRAGMENTED; /* Yes, and fold redundant checksum back. 8) */ if (skb->ip_summed == CHECKSUM_COMPLETE) diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c index da64550a5707..8210ff34ed9b 100644 --- a/net/ipv6/netfilter/nf_log_ipv6.c +++ b/net/ipv6/netfilter/nf_log_ipv6.c @@ -297,9 +297,11 @@ static void dump_ipv6_mac_header(struct nf_log_buf *m, switch (dev->type) { case ARPHRD_ETHER: - nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", - eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, - ntohs(eth_hdr(skb)->h_proto)); + nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest); + nf_log_dump_vlan(m, skb); + nf_log_buf_add(m, "MACPROTO=%04x ", + ntohs(eth_hdr(skb)->h_proto)); return; default: break; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 874f01cd7aec..6e4ab80a3b94 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -746,7 +746,7 @@ static int raw6_getfrag(void *from, char *to, int offset, int len, int odd, skb->csum = csum_block_add( skb->csum, csum_partial_copy_nocheck(rfv->c + offset, - to, copy, 0), + to, copy), odd); odd = 0; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 1f5d4d196dcc..c8cf1bbad74a 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -42,6 +42,8 @@ #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/tcp.h> +#include <linux/udp.h> #include <net/sock.h> #include <net/snmp.h> @@ -322,7 +324,9 @@ static int ipv6_frag_rcv(struct sk_buff *skb) struct frag_queue *fq; const struct ipv6hdr *hdr = ipv6_hdr(skb); struct net *net = dev_net(skb_dst(skb)->dev); - int iif; + __be16 frag_off; + int iif, offset; + u8 nexthdr; if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED) goto fail_hdr; @@ -351,6 +355,33 @@ static int ipv6_frag_rcv(struct sk_buff *skb) return 1; } + /* RFC 8200, Section 4.5 Fragment Header: + * If the first fragment does not include all headers through an + * Upper-Layer header, then that fragment should be discarded and + * an ICMP Parameter Problem, Code 3, message should be sent to + * the source of the fragment, with the Pointer field set to zero. + */ + nexthdr = hdr->nexthdr; + offset = ipv6_skip_exthdr(skb, skb_transport_offset(skb), &nexthdr, &frag_off); + if (offset >= 0) { + /* Check some common protocols' header */ + if (nexthdr == IPPROTO_TCP) + offset += sizeof(struct tcphdr); + else if (nexthdr == IPPROTO_UDP) + offset += sizeof(struct udphdr); + else if (nexthdr == IPPROTO_ICMPV6) + offset += sizeof(struct icmp6hdr); + else + offset += 1; + + if (!(frag_off & htons(IP6_OFFSET)) && offset > skb->len) { + __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev), + IPSTATS_MIB_INHDRERRORS); + icmpv6_param_prob(skb, ICMPV6_HDR_INCOMP, 0); + return -1; + } + } + iif = skb->dev ? skb->dev->ifindex : 0; fq = fq_find(net, fhdr->identification, hdr, iif); if (fq) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index fb075d9545b9..7e0ce7af8234 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2745,7 +2745,8 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, if (confirm_neigh) dst_confirm_neigh(dst, daddr); - mtu = max_t(u32, mtu, IPV6_MIN_MTU); + if (mtu < IPV6_MIN_MTU) + return; if (mtu >= dst_mtu(dst)) return; @@ -5284,9 +5285,10 @@ static int ip6_route_multipath_del(struct fib6_config *cfg, { struct fib6_config r_cfg; struct rtnexthop *rtnh; + int last_err = 0; int remaining; int attrlen; - int err = 1, last_err = 0; + int err; remaining = cfg->fc_mp_len; rtnh = (struct rtnexthop *)cfg->fc_mp; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 305870a72352..8db59f4e5f13 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -458,7 +458,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, case TCP_SYN_SENT: case TCP_SYN_RECV: /* Only in fast or simultaneous open. If a fast open socket is - * is already accepted it is treated as a connected one below. + * already accepted it is treated as a connected one below. */ if (fastopen && !fastopen->sk) break; @@ -501,7 +501,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, - enum tcp_synack_type synack_type) + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); struct ipv6_pinfo *np = tcp_inet6_sk(sk); @@ -509,13 +510,14 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi6 *fl6 = &fl->u.ip6; struct sk_buff *skb; int err = -ENOMEM; + u8 tclass; /* First, grab a route. */ if (!dst && (dst = inet6_csk_route_req(sk, fl6, req, IPPROTO_TCP)) == NULL) goto done; - skb = tcp_make_synack(sk, dst, req, foc, synack_type); + skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb); if (skb) { __tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr, @@ -527,9 +529,12 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, rcu_read_lock(); opt = ireq->ipv6_opt; + tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? + tcp_rsk(req)->syn_tos : np->tclass; if (!opt) opt = rcu_dereference(np->opt); - err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, np->tclass, + err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, + tclass & ~INET_ECN_MASK, sk->sk_priority); rcu_read_unlock(); err = net_xmit_eval(err); @@ -958,8 +963,8 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(buff, dst); - ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass, - priority); + ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, + tclass & ~INET_ECN_MASK, priority); TCP_INC_STATS(net, TCP_MIB_OUTSEGS); if (rst) TCP_INC_STATS(net, TCP_MIB_OUTRSTS); @@ -1067,8 +1072,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) label = ip6_flowlabel(ipv6h); } - tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, - label, priority); + tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, + ipv6_get_dsfield(ipv6h), label, priority); #ifdef CONFIG_TCP_MD5SIG out: @@ -1121,7 +1126,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, req->ts_recent, sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index), - 0, 0, sk->sk_priority); + ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority); } @@ -1309,6 +1314,10 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * if (np->repflow) newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb)); + /* Set ToS of the new socket based upon the value of incoming SYN. */ + if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) + newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; + /* Clone native IPv6 options from listening socket (if any) Yes, keeping reference count would be much more clever, diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index a95af62acb52..d80572074667 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -588,11 +588,11 @@ static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { struct sockaddr_iucv *sa = (struct sockaddr_iucv *) addr; + char uid[sizeof(sa->siucv_user_id)]; struct sock *sk = sock->sk; struct iucv_sock *iucv; int err = 0; struct net_device *dev; - char uid[9]; /* Verify the input sockaddr */ if (addr_len < sizeof(struct sockaddr_iucv) || diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index cd2e468852e7..349c6ac3313f 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -1116,10 +1116,9 @@ int __iucv_message_receive(struct iucv_path *path, struct iucv_message *msg, if (msg->flags & IUCV_IPRMDATA) return iucv_message_receive_iprmdata(path, msg, flags, buffer, size, residual); - if (cpumask_empty(&iucv_buffer_cpumask)) { - rc = -EIO; - goto out; - } + if (cpumask_empty(&iucv_buffer_cpumask)) + return -EIO; + parm = iucv_param[smp_processor_id()]; memset(parm, 0, sizeof(union iucv_param)); parm->db.ipbfadr1 = (u32)(addr_t) buffer; @@ -1135,7 +1134,6 @@ int __iucv_message_receive(struct iucv_path *path, struct iucv_message *msg, if (residual) *residual = parm->db.ipbfln1f; } -out: return rc; } EXPORT_SYMBOL(__iucv_message_receive); diff --git a/net/l2tp/Makefile b/net/l2tp/Makefile index 399a7e5db2f4..cf8f27071d3f 100644 --- a/net/l2tp/Makefile +++ b/net/l2tp/Makefile @@ -5,6 +5,8 @@ obj-$(CONFIG_L2TP) += l2tp_core.o +CFLAGS_l2tp_core.o += -I$(src) + # Build l2tp as modules if L2TP is M obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_PPPOL2TP)) += l2tp_ppp.o obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_L2TP_IP)) += l2tp_ip.o diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 701fc72ad9f4..7be5103ff2a8 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -61,6 +61,10 @@ #include <linux/atomic.h> #include "l2tp_core.h" +#include "trace.h" + +#define CREATE_TRACE_POINTS +#include "trace.h" #define L2TP_DRV_VERSION "V2.0" @@ -116,11 +120,6 @@ static bool l2tp_sk_is_v6(struct sock *sk) } #endif -static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk) -{ - return sk->sk_user_data; -} - static inline struct l2tp_net *l2tp_pernet(const struct net *net) { return net_generic(net, l2tp_net_id); @@ -151,23 +150,30 @@ l2tp_session_id_hash(struct l2tp_tunnel *tunnel, u32 session_id) static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) { + trace_free_tunnel(tunnel); sock_put(tunnel->sock); /* the tunnel is freed in the socket destructor */ } static void l2tp_session_free(struct l2tp_session *session) { - struct l2tp_tunnel *tunnel = session->tunnel; + trace_free_session(session); + if (session->tunnel) + l2tp_tunnel_dec_refcount(session->tunnel); + kfree(session); +} - if (tunnel) { +struct l2tp_tunnel *l2tp_sk_to_tunnel(struct sock *sk) +{ + struct l2tp_tunnel *tunnel = sk->sk_user_data; + + if (tunnel) if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC)) - goto out; - l2tp_tunnel_dec_refcount(tunnel); - } + return NULL; -out: - kfree(session); + return tunnel; } +EXPORT_SYMBOL_GPL(l2tp_sk_to_tunnel); void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel) { @@ -381,6 +387,8 @@ int l2tp_session_register(struct l2tp_session *session, hlist_add_head(&session->hlist, head); write_unlock_bh(&tunnel->hlist_lock); + trace_register_session(session); + return 0; err_tlock_pnlock: @@ -409,10 +417,6 @@ static void l2tp_recv_queue_skb(struct l2tp_session *session, struct sk_buff *sk skb_queue_walk_safe(&session->reorder_q, skbp, tmp) { if (L2TP_SKB_CB(skbp)->ns > ns) { __skb_queue_before(&session->reorder_q, skbp, skb); - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: pkt %hu, inserted before %hu, reorder_q len=%d\n", - session->name, ns, L2TP_SKB_CB(skbp)->ns, - skb_queue_len(&session->reorder_q)); atomic_long_inc(&session->stats.rx_oos_packets); goto out; } @@ -445,9 +449,7 @@ static void l2tp_recv_dequeue_skb(struct l2tp_session *session, struct sk_buff * /* Bump our Nr */ session->nr++; session->nr &= session->nr_max; - - l2tp_dbg(session, L2TP_MSG_SEQ, "%s: updated nr to %hu\n", - session->name, session->nr); + trace_session_seqnum_update(session); } /* call private receive handler */ @@ -472,37 +474,27 @@ static void l2tp_recv_dequeue(struct l2tp_session *session) start: spin_lock_bh(&session->reorder_q.lock); skb_queue_walk_safe(&session->reorder_q, skb, tmp) { - if (time_after(jiffies, L2TP_SKB_CB(skb)->expires)) { + struct l2tp_skb_cb *cb = L2TP_SKB_CB(skb); + + /* If the packet has been pending on the queue for too long, discard it */ + if (time_after(jiffies, cb->expires)) { atomic_long_inc(&session->stats.rx_seq_discards); atomic_long_inc(&session->stats.rx_errors); - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: oos pkt %u len %d discarded (too old), waiting for %u, reorder_q_len=%d\n", - session->name, L2TP_SKB_CB(skb)->ns, - L2TP_SKB_CB(skb)->length, session->nr, - skb_queue_len(&session->reorder_q)); + trace_session_pkt_expired(session, cb->ns); session->reorder_skip = 1; __skb_unlink(skb, &session->reorder_q); kfree_skb(skb); continue; } - if (L2TP_SKB_CB(skb)->has_seq) { + if (cb->has_seq) { if (session->reorder_skip) { - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: advancing nr to next pkt: %u -> %u", - session->name, session->nr, - L2TP_SKB_CB(skb)->ns); session->reorder_skip = 0; - session->nr = L2TP_SKB_CB(skb)->ns; + session->nr = cb->ns; + trace_session_seqnum_reset(session); } - if (L2TP_SKB_CB(skb)->ns != session->nr) { - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: holding oos pkt %u len %d, waiting for %u, reorder_q_len=%d\n", - session->name, L2TP_SKB_CB(skb)->ns, - L2TP_SKB_CB(skb)->length, session->nr, - skb_queue_len(&session->reorder_q)); + if (cb->ns != session->nr) goto out; - } } __skb_unlink(skb, &session->reorder_q); @@ -535,14 +527,13 @@ static int l2tp_seq_check_rx_window(struct l2tp_session *session, u32 nr) */ static int l2tp_recv_data_seq(struct l2tp_session *session, struct sk_buff *skb) { - if (!l2tp_seq_check_rx_window(session, L2TP_SKB_CB(skb)->ns)) { + struct l2tp_skb_cb *cb = L2TP_SKB_CB(skb); + + if (!l2tp_seq_check_rx_window(session, cb->ns)) { /* Packet sequence number is outside allowed window. * Discard it. */ - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: pkt %u len %d discarded, outside window, nr=%u\n", - session->name, L2TP_SKB_CB(skb)->ns, - L2TP_SKB_CB(skb)->length, session->nr); + trace_session_pkt_outside_rx_window(session, cb->ns); goto discard; } @@ -559,10 +550,10 @@ static int l2tp_recv_data_seq(struct l2tp_session *session, struct sk_buff *skb) * is seen. After nr_oos_count_max in-sequence packets, reset the * sequence number to re-enable packet reception. */ - if (L2TP_SKB_CB(skb)->ns == session->nr) { + if (cb->ns == session->nr) { skb_queue_tail(&session->reorder_q, skb); } else { - u32 nr_oos = L2TP_SKB_CB(skb)->ns; + u32 nr_oos = cb->ns; u32 nr_next = (session->nr_oos + 1) & session->nr_max; if (nr_oos == nr_next) @@ -573,17 +564,10 @@ static int l2tp_recv_data_seq(struct l2tp_session *session, struct sk_buff *skb) session->nr_oos = nr_oos; if (session->nr_oos_count > session->nr_oos_count_max) { session->reorder_skip = 1; - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: %d oos packets received. Resetting sequence numbers\n", - session->name, session->nr_oos_count); } if (!session->reorder_skip) { atomic_long_inc(&session->stats.rx_seq_discards); - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: oos pkt %u len %d discarded, waiting for %u, reorder_q_len=%d\n", - session->name, L2TP_SKB_CB(skb)->ns, - L2TP_SKB_CB(skb)->length, session->nr, - skb_queue_len(&session->reorder_q)); + trace_session_pkt_oos(session, cb->ns); goto discard; } skb_queue_tail(&session->reorder_q, skb); @@ -660,16 +644,14 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, int length) { struct l2tp_tunnel *tunnel = session->tunnel; - u32 ns = 0, nr = 0; int offset; /* Parse and check optional cookie */ if (session->peer_cookie_len > 0) { if (memcmp(ptr, &session->peer_cookie[0], session->peer_cookie_len)) { - l2tp_info(tunnel, L2TP_MSG_DATA, - "%s: cookie mismatch (%u/%u). Discarding.\n", - tunnel->name, tunnel->tunnel_id, - session->session_id); + pr_warn_ratelimited("%s: cookie mismatch (%u/%u). Discarding.\n", + tunnel->name, tunnel->tunnel_id, + session->session_id); atomic_long_inc(&session->stats.rx_cookie_discards); goto discard; } @@ -686,32 +668,21 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, L2TP_SKB_CB(skb)->has_seq = 0; if (tunnel->version == L2TP_HDR_VER_2) { if (hdrflags & L2TP_HDRFLAG_S) { - ns = ntohs(*(__be16 *)ptr); - ptr += 2; - nr = ntohs(*(__be16 *)ptr); - ptr += 2; - /* Store L2TP info in the skb */ - L2TP_SKB_CB(skb)->ns = ns; + L2TP_SKB_CB(skb)->ns = ntohs(*(__be16 *)ptr); L2TP_SKB_CB(skb)->has_seq = 1; + ptr += 2; + /* Skip past nr in the header */ + ptr += 2; - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: recv data ns=%u, nr=%u, session nr=%u\n", - session->name, ns, nr, session->nr); } } else if (session->l2specific_type == L2TP_L2SPECTYPE_DEFAULT) { u32 l2h = ntohl(*(__be32 *)ptr); if (l2h & 0x40000000) { - ns = l2h & 0x00ffffff; - /* Store L2TP info in the skb */ - L2TP_SKB_CB(skb)->ns = ns; + L2TP_SKB_CB(skb)->ns = l2h & 0x00ffffff; L2TP_SKB_CB(skb)->has_seq = 1; - - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: recv data ns=%u, session nr=%u\n", - session->name, ns, session->nr); } ptr += 4; } @@ -722,9 +693,7 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, * configure it so. */ if (!session->lns_mode && !session->send_seq) { - l2tp_info(session, L2TP_MSG_SEQ, - "%s: requested to enable seq numbers by LNS\n", - session->name); + trace_session_seqnum_lns_enable(session); session->send_seq = 1; l2tp_session_set_header_len(session, tunnel->version); } @@ -733,9 +702,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, * If user has configured mandatory sequence numbers, discard. */ if (session->recv_seq) { - l2tp_warn(session, L2TP_MSG_SEQ, - "%s: recv data has no seq numbers when required. Discarding.\n", - session->name); + pr_warn_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", + session->name); atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } @@ -746,15 +714,12 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, * LAC is broken. Discard the frame. */ if (!session->lns_mode && session->send_seq) { - l2tp_info(session, L2TP_MSG_SEQ, - "%s: requested to disable seq numbers by LNS\n", - session->name); + trace_session_seqnum_lns_disable(session); session->send_seq = 0; l2tp_session_set_header_len(session, tunnel->version); } else if (session->send_seq) { - l2tp_warn(session, L2TP_MSG_SEQ, - "%s: recv data has no seq numbers when required. Discarding.\n", - session->name); + pr_warn_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", + session->name); atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } @@ -816,9 +781,6 @@ static void l2tp_session_queue_purge(struct l2tp_session *session) { struct sk_buff *skb = NULL; - if (WARN_ON(session->magic != L2TP_SESSION_MAGIC)) - return; - while ((skb = skb_dequeue(&session->reorder_q))) { atomic_long_inc(&session->stats.rx_errors); kfree_skb(skb); @@ -847,22 +809,11 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) /* Short packet? */ if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) { - l2tp_info(tunnel, L2TP_MSG_DATA, - "%s: recv short packet (len=%d)\n", - tunnel->name, skb->len); + pr_warn_ratelimited("%s: recv short packet (len=%d)\n", + tunnel->name, skb->len); goto error; } - /* Trace packet contents, if enabled */ - if (tunnel->debug & L2TP_MSG_DATA) { - length = min(32u, skb->len); - if (!pskb_may_pull(skb, length)) - goto error; - - pr_debug("%s: recv\n", tunnel->name); - print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, skb->data, length); - } - /* Point to L2TP header */ optr = skb->data; ptr = skb->data; @@ -873,9 +824,8 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) /* Check protocol version */ version = hdrflags & L2TP_HDR_VER_MASK; if (version != tunnel->version) { - l2tp_info(tunnel, L2TP_MSG_DATA, - "%s: recv protocol version mismatch: got %d expected %d\n", - tunnel->name, version, tunnel->version); + pr_warn_ratelimited("%s: recv protocol version mismatch: got %d expected %d\n", + tunnel->name, version, tunnel->version); goto error; } @@ -883,12 +833,8 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) length = skb->len; /* If type is control packet, it is handled by userspace. */ - if (hdrflags & L2TP_HDRFLAG_T) { - l2tp_dbg(tunnel, L2TP_MSG_DATA, - "%s: recv control packet, len=%d\n", - tunnel->name, length); + if (hdrflags & L2TP_HDRFLAG_T) goto error; - } /* Skip flags */ ptr += 2; @@ -917,9 +863,8 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) l2tp_session_dec_refcount(session); /* Not found? Pass to userspace to deal with */ - l2tp_info(tunnel, L2TP_MSG_DATA, - "%s: no session found (%u/%u). Passing up.\n", - tunnel->name, tunnel_id, session_id); + pr_warn_ratelimited("%s: no session found (%u/%u). Passing up.\n", + tunnel->name, tunnel_id, session_id); goto error; } @@ -949,12 +894,17 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct l2tp_tunnel *tunnel; + /* Note that this is called from the encap_rcv hook inside an + * RCU-protected region, but without the socket being locked. + * Hence we use rcu_dereference_sk_user_data to access the + * tunnel data structure rather the usual l2tp_sk_to_tunnel + * accessor function. + */ tunnel = rcu_dereference_sk_user_data(sk); if (!tunnel) goto pass_up; - - l2tp_dbg(tunnel, L2TP_MSG_DATA, "%s: received %d bytes\n", - tunnel->name, skb->len); + if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC)) + goto pass_up; if (l2tp_udp_recv_core(tunnel, skb)) goto pass_up; @@ -993,8 +943,7 @@ static int l2tp_build_l2tpv2_header(struct l2tp_session *session, void *buf) *bufp++ = 0; session->ns++; session->ns &= 0xffff; - l2tp_dbg(session, L2TP_MSG_SEQ, "%s: updated ns to %u\n", - session->name, session->ns); + trace_session_seqnum_update(session); } return bufp - optr; @@ -1030,9 +979,7 @@ static int l2tp_build_l2tpv3_header(struct l2tp_session *session, void *buf) l2h = 0x40000000 | session->ns; session->ns++; session->ns &= 0xffffff; - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: updated ns to %u\n", - session->name, session->ns); + trace_session_seqnum_update(session); } *((__be32 *)bufp) = htonl(l2h); @@ -1042,74 +989,39 @@ static int l2tp_build_l2tpv3_header(struct l2tp_session *session, void *buf) return bufp - optr; } -static void l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, - struct flowi *fl, size_t data_len) +/* Queue the packet to IP for output: tunnel socket lock must be held */ +static int l2tp_xmit_queue(struct l2tp_tunnel *tunnel, struct sk_buff *skb, struct flowi *fl) { - struct l2tp_tunnel *tunnel = session->tunnel; - unsigned int len = skb->len; - int error; - - /* Debug */ - if (session->send_seq) - l2tp_dbg(session, L2TP_MSG_DATA, "%s: send %zd bytes, ns=%u\n", - session->name, data_len, session->ns - 1); - else - l2tp_dbg(session, L2TP_MSG_DATA, "%s: send %zd bytes\n", - session->name, data_len); - - if (session->debug & L2TP_MSG_DATA) { - int uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0; - unsigned char *datap = skb->data + uhlen; - - pr_debug("%s: xmit\n", session->name); - print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, - datap, min_t(size_t, 32, len - uhlen)); - } + int err; - /* Queue the packet to IP for output */ skb->ignore_df = 1; skb_dst_drop(skb); #if IS_ENABLED(CONFIG_IPV6) if (l2tp_sk_is_v6(tunnel->sock)) - error = inet6_csk_xmit(tunnel->sock, skb, NULL); + err = inet6_csk_xmit(tunnel->sock, skb, NULL); else #endif - error = ip_queue_xmit(tunnel->sock, skb, fl); + err = ip_queue_xmit(tunnel->sock, skb, fl); - /* Update stats */ - if (error >= 0) { - atomic_long_inc(&tunnel->stats.tx_packets); - atomic_long_add(len, &tunnel->stats.tx_bytes); - atomic_long_inc(&session->stats.tx_packets); - atomic_long_add(len, &session->stats.tx_bytes); - } else { - atomic_long_inc(&tunnel->stats.tx_errors); - atomic_long_inc(&session->stats.tx_errors); - } + return err >= 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; } -/* If caller requires the skb to have a ppp header, the header must be - * inserted in the skb data before calling this function. - */ -int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len) +static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, unsigned int *len) { - int data_len = skb->len; struct l2tp_tunnel *tunnel = session->tunnel; + unsigned int data_len = skb->len; struct sock *sk = tunnel->sock; - struct flowi *fl; - struct udphdr *uh; - struct inet_sock *inet; - int headroom; - int uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0; - int udp_len; + int headroom, uhlen, udp_len; int ret = NET_XMIT_SUCCESS; + struct inet_sock *inet; + struct udphdr *uh; /* Check that there's enough headroom in the skb to insert IP, * UDP and L2TP headers. If not enough, expand it to * make room. Adjust truesize. */ - headroom = NET_SKB_PAD + sizeof(struct iphdr) + - uhlen + hdr_len; + uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(*uh) : 0; + headroom = NET_SKB_PAD + sizeof(struct iphdr) + uhlen + session->hdr_len; if (skb_cow_head(skb, headroom)) { kfree_skb(skb); return NET_XMIT_DROP; @@ -1117,14 +1029,13 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len /* Setup L2TP header */ if (tunnel->version == L2TP_HDR_VER_2) - l2tp_build_l2tpv2_header(session, __skb_push(skb, hdr_len)); + l2tp_build_l2tpv2_header(session, __skb_push(skb, session->hdr_len)); else - l2tp_build_l2tpv3_header(session, __skb_push(skb, hdr_len)); + l2tp_build_l2tpv3_header(session, __skb_push(skb, session->hdr_len)); /* Reset skb netfilter state */ memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | - IPSKB_REROUTED); + IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); nf_reset_ct(skb); bh_lock_sock(sk); @@ -1143,8 +1054,12 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len goto out_unlock; } + /* Report transmitted length before we add encap header, which keeps + * statistics consistent for both UDP and IP encap tx/rx paths. + */ + *len = skb->len; + inet = inet_sk(sk); - fl = &inet->cork.fl; switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: /* Setup UDP header */ @@ -1153,7 +1068,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len uh = udp_hdr(skb); uh->source = inet->inet_sport; uh->dest = inet->inet_dport; - udp_len = uhlen + hdr_len + data_len; + udp_len = uhlen + session->hdr_len + data_len; uh->len = htons(udp_len); /* Calculate UDP checksum if configured to do so */ @@ -1172,12 +1087,34 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len break; } - l2tp_xmit_core(session, skb, fl, data_len); + ret = l2tp_xmit_queue(tunnel, skb, &inet->cork.fl); + out_unlock: bh_unlock_sock(sk); return ret; } + +/* If caller requires the skb to have a ppp header, the header must be + * inserted in the skb data before calling this function. + */ +int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb) +{ + unsigned int len = 0; + int ret; + + ret = l2tp_xmit_core(session, skb, &len); + if (ret == NET_XMIT_SUCCESS) { + atomic_long_inc(&session->tunnel->stats.tx_packets); + atomic_long_add(len, &session->tunnel->stats.tx_bytes); + atomic_long_inc(&session->stats.tx_packets); + atomic_long_add(len, &session->stats.tx_bytes); + } else { + atomic_long_inc(&session->tunnel->stats.tx_errors); + atomic_long_inc(&session->stats.tx_errors); + } + return ret; +} EXPORT_SYMBOL_GPL(l2tp_xmit_skb); /***************************************************************************** @@ -1190,13 +1127,11 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb); */ static void l2tp_tunnel_destruct(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_tunnel(sk); + struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); if (!tunnel) goto end; - l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: closing...\n", tunnel->name); - /* Disable udp encapsulation */ switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: @@ -1255,34 +1190,16 @@ static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel) struct hlist_node *tmp; struct l2tp_session *session; - l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: closing all sessions...\n", - tunnel->name); - write_lock_bh(&tunnel->hlist_lock); tunnel->acpt_newsess = false; for (hash = 0; hash < L2TP_HASH_SIZE; hash++) { again: hlist_for_each_safe(walk, tmp, &tunnel->session_hlist[hash]) { session = hlist_entry(walk, struct l2tp_session, hlist); - - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: closing session\n", session->name); - hlist_del_init(&session->hlist); - if (test_and_set_bit(0, &session->dead)) - goto again; - write_unlock_bh(&tunnel->hlist_lock); - - l2tp_session_unhash(session); - l2tp_session_queue_purge(session); - - if (session->session_close) - (*session->session_close)(session); - - l2tp_session_dec_refcount(session); - + l2tp_session_delete(session); write_lock_bh(&tunnel->hlist_lock); /* Now restart from the beginning of this hash @@ -1299,7 +1216,7 @@ again: /* Tunnel socket destroy hook for UDP encapsulation */ static void l2tp_udp_encap_destroy(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_tunnel(sk); + struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); if (tunnel) l2tp_tunnel_delete(tunnel); @@ -1464,7 +1381,7 @@ out: static struct lock_class_key l2tp_socket_class; -int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, +int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp) { struct l2tp_tunnel *tunnel = NULL; @@ -1483,16 +1400,12 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 tunnel->version = version; tunnel->tunnel_id = tunnel_id; tunnel->peer_tunnel_id = peer_tunnel_id; - tunnel->debug = L2TP_DEFAULT_DEBUG_FLAGS; tunnel->magic = L2TP_TUNNEL_MAGIC; sprintf(&tunnel->name[0], "tunl %u", tunnel_id); rwlock_init(&tunnel->hlist_lock); tunnel->acpt_newsess = true; - if (cfg) - tunnel->debug = cfg->debug; - tunnel->encap = encap; refcount_set(&tunnel->ref_count, 1); @@ -1597,6 +1510,8 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, "l2tp_sock"); sk->sk_allocation = GFP_ATOMIC; + trace_register_tunnel(tunnel); + if (tunnel->fd >= 0) sockfd_put(sock); @@ -1617,6 +1532,7 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_register); void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel) { if (!test_and_set_bit(0, &tunnel->dead)) { + trace_delete_tunnel(tunnel); l2tp_tunnel_inc_refcount(tunnel); queue_work(l2tp_wq, &tunnel->del_work); } @@ -1628,6 +1544,7 @@ void l2tp_session_delete(struct l2tp_session *session) if (test_and_set_bit(0, &session->dead)) return; + trace_delete_session(session); l2tp_session_unhash(session); l2tp_session_queue_purge(session); if (session->session_close) @@ -1686,12 +1603,8 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn INIT_HLIST_NODE(&session->hlist); INIT_HLIST_NODE(&session->global_hlist); - /* Inherit debug options from tunnel */ - session->debug = tunnel->debug; - if (cfg) { session->pwtype = cfg->pw_type; - session->debug = cfg->debug; session->send_seq = cfg->send_seq; session->recv_seq = cfg->recv_seq; session->lns_mode = cfg->lns_mode; diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 3468d6b177a0..cb21d906343e 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -51,7 +51,6 @@ struct l2tp_session_cfg { unsigned int lns_mode:1; /* behave as LNS? * LAC enables sequence numbers under LNS control. */ - int debug; /* bitmask of debug message categories */ u16 l2specific_type; /* Layer 2 specific type */ u8 cookie[8]; /* optional cookie */ int cookie_len; /* 0, 4 or 8 bytes */ @@ -66,6 +65,7 @@ struct l2tp_session_cfg { * Is linked into a per-tunnel session hashlist; and in the case of an L2TPv3 session into * an additional per-net ("global") hashlist. */ +#define L2TP_SESSION_NAME_MAX 32 struct l2tp_session { int magic; /* should be L2TP_SESSION_MAGIC */ long dead; @@ -90,14 +90,13 @@ struct l2tp_session { struct hlist_node hlist; /* hash list node */ refcount_t ref_count; - char name[32]; /* for logging */ + char name[L2TP_SESSION_NAME_MAX]; /* for logging */ char ifname[IFNAMSIZ]; unsigned int recv_seq:1; /* expect receive packets with sequence numbers? */ unsigned int send_seq:1; /* send packets with sequence numbers? */ unsigned int lns_mode:1; /* behave as LNS? * LAC enables sequence numbers under LNS control. */ - int debug; /* bitmask of debug message categories */ int reorder_timeout; /* configured reorder timeout (in jiffies) */ int reorder_skip; /* set if skip to next nr */ enum l2tp_pwtype pwtype; @@ -131,7 +130,6 @@ struct l2tp_session { /* L2TP tunnel configuration */ struct l2tp_tunnel_cfg { - int debug; /* bitmask of debug message categories */ enum l2tp_encap_type encap; /* Used only for kernel-created sockets */ @@ -154,6 +152,7 @@ struct l2tp_tunnel_cfg { * Maintains a hashlist of sessions belonging to the tunnel instance. * Is linked into a per-net list of tunnels. */ +#define L2TP_TUNNEL_NAME_MAX 20 struct l2tp_tunnel { int magic; /* Should be L2TP_TUNNEL_MAGIC */ @@ -170,8 +169,7 @@ struct l2tp_tunnel { u32 peer_tunnel_id; int version; /* 2=>L2TPv2, 3=>L2TPv3 */ - char name[20]; /* for logging */ - int debug; /* bitmask of debug message categories */ + char name[L2TP_TUNNEL_NAME_MAX]; /* for logging */ enum l2tp_encap_type encap; struct l2tp_stats stats; @@ -237,7 +235,7 @@ struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, * Creation of a new instance is a two-step process: create, then register. * Destruction is triggered using the *_delete functions, and completes asynchronously. */ -int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, +int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp); int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, @@ -263,8 +261,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb); /* Transmit path helpers for sending packets over the tunnel socket. */ void l2tp_session_set_header_len(struct l2tp_session *session, int version); -int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, - int hdr_len); +int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb); /* Pseudowire management. * Pseudowires should register with l2tp core on module init, and unregister @@ -276,6 +273,11 @@ void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type); /* IOCTL helper for IP encap modules. */ int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg); +/* Extract the tunnel structure from a socket's sk_user_data pointer, + * validating the tunnel magic feather. + */ +struct l2tp_tunnel *l2tp_sk_to_tunnel(struct sock *sk); + static inline int l2tp_get_l2specific_len(struct l2tp_session *session) { switch (session->l2specific_type) { @@ -337,19 +339,6 @@ static inline int l2tp_v3_ensure_opt_in_linear(struct l2tp_session *session, str return 0; } -#define l2tp_printk(ptr, type, func, fmt, ...) \ -do { \ - if (((ptr)->debug) & (type)) \ - func(fmt, ##__VA_ARGS__); \ -} while (0) - -#define l2tp_warn(ptr, type, fmt, ...) \ - l2tp_printk(ptr, type, pr_warn, fmt, ##__VA_ARGS__) -#define l2tp_info(ptr, type, fmt, ...) \ - l2tp_printk(ptr, type, pr_info, fmt, ##__VA_ARGS__) -#define l2tp_dbg(ptr, type, fmt, ...) \ - l2tp_printk(ptr, type, pr_debug, fmt, ##__VA_ARGS__) - #define MODULE_ALIAS_L2TP_PWTYPE(type) \ MODULE_ALIAS("net-l2tp-type-" __stringify(type)) diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index 96cb9601c21b..bca75bef8282 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -167,7 +167,7 @@ static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v) tunnel->sock ? refcount_read(&tunnel->sock->sk_refcnt) : 0, refcount_read(&tunnel->ref_count)); seq_printf(m, " %08x rx %ld/%ld/%ld rx %ld/%ld/%ld\n", - tunnel->debug, + 0, atomic_long_read(&tunnel->stats.tx_packets), atomic_long_read(&tunnel->stats.tx_bytes), atomic_long_read(&tunnel->stats.tx_errors), @@ -192,7 +192,7 @@ static void l2tp_dfs_seq_session_show(struct seq_file *m, void *v) session->recv_seq ? 'R' : '-', session->send_seq ? 'S' : '-', session->lns_mode ? "LNS" : "LAC", - session->debug, + 0, jiffies_to_msecs(session->reorder_timeout)); seq_printf(m, " offset 0 l2specific %hu/%hu\n", session->l2specific_type, l2tp_get_l2specific_len(session)); diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 7ed2b4eced94..6cd97c75445c 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -76,7 +76,7 @@ static netdev_tx_t l2tp_eth_dev_xmit(struct sk_buff *skb, struct net_device *dev struct l2tp_eth *priv = netdev_priv(dev); struct l2tp_session *session = priv->session; unsigned int len = skb->len; - int ret = l2tp_xmit_skb(session, skb, session->hdr_len); + int ret = l2tp_xmit_skb(session, skb); if (likely(ret == NET_XMIT_SUCCESS)) { atomic_long_add(len, &priv->tx_bytes); @@ -128,17 +128,6 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, struct net_device *dev; struct l2tp_eth *priv; - if (session->debug & L2TP_MSG_DATA) { - unsigned int length; - - length = min(32u, skb->len); - if (!pskb_may_pull(skb, length)) - goto error; - - pr_debug("%s: eth recv\n", session->name); - print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, skb->data, length); - } - if (!pskb_may_pull(skb, ETH_HLEN)) goto error; diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index df2a35b5714a..97ae1255fcb6 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -118,7 +118,6 @@ static int l2tp_ip_recv(struct sk_buff *skb) struct l2tp_session *session; struct l2tp_tunnel *tunnel = NULL; struct iphdr *iph; - int length; if (!pskb_may_pull(skb, 4)) goto discard; @@ -147,20 +146,6 @@ static int l2tp_ip_recv(struct sk_buff *skb) if (!tunnel) goto discard_sess; - /* Trace packet contents, if enabled */ - if (tunnel->debug & L2TP_MSG_DATA) { - length = min(32u, skb->len); - if (!pskb_may_pull(skb, length)) - goto discard_sess; - - /* Point to L2TP header */ - optr = skb->data; - ptr = skb->data; - ptr += 4; - pr_debug("%s: ip recv\n", tunnel->name); - print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); - } - if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) goto discard_sess; @@ -248,8 +233,8 @@ static void l2tp_ip_close(struct sock *sk, long timeout) static void l2tp_ip_destroy_sock(struct sock *sk) { + struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); struct sk_buff *skb; - struct l2tp_tunnel *tunnel = sk->sk_user_data; while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) kfree_skb(skb); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index bc757bc7e264..e5e5036257b0 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -131,7 +131,6 @@ static int l2tp_ip6_recv(struct sk_buff *skb) struct l2tp_session *session; struct l2tp_tunnel *tunnel = NULL; struct ipv6hdr *iph; - int length; if (!pskb_may_pull(skb, 4)) goto discard; @@ -160,20 +159,6 @@ static int l2tp_ip6_recv(struct sk_buff *skb) if (!tunnel) goto discard_sess; - /* Trace packet contents, if enabled */ - if (tunnel->debug & L2TP_MSG_DATA) { - length = min(32u, skb->len); - if (!pskb_may_pull(skb, length)) - goto discard_sess; - - /* Point to L2TP header */ - optr = skb->data; - ptr = skb->data; - ptr += 4; - pr_debug("%s: ip recv\n", tunnel->name); - print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); - } - if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) goto discard_sess; @@ -262,7 +247,7 @@ static void l2tp_ip6_close(struct sock *sk, long timeout) static void l2tp_ip6_destroy_sock(struct sock *sk) { - struct l2tp_tunnel *tunnel = sk->sk_user_data; + struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); lock_sock(sk); ip6_flush_pending_frames(sk); diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index def78eebca4c..83956c9ee1fc 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -229,14 +229,11 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info goto out; } - if (attrs[L2TP_ATTR_DEBUG]) - cfg.debug = nla_get_u32(attrs[L2TP_ATTR_DEBUG]); - ret = -EINVAL; switch (cfg.encap) { case L2TP_ENCAPTYPE_UDP: case L2TP_ENCAPTYPE_IP: - ret = l2tp_tunnel_create(net, fd, proto_version, tunnel_id, + ret = l2tp_tunnel_create(fd, proto_version, tunnel_id, peer_tunnel_id, &cfg, &tunnel); break; } @@ -307,9 +304,6 @@ static int l2tp_nl_cmd_tunnel_modify(struct sk_buff *skb, struct genl_info *info goto out; } - if (info->attrs[L2TP_ATTR_DEBUG]) - tunnel->debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]); - ret = l2tp_tunnel_notify(&l2tp_nl_family, info, tunnel, L2TP_CMD_TUNNEL_MODIFY); @@ -400,7 +394,7 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla if (nla_put_u8(skb, L2TP_ATTR_PROTO_VERSION, tunnel->version) || nla_put_u32(skb, L2TP_ATTR_CONN_ID, tunnel->tunnel_id) || nla_put_u32(skb, L2TP_ATTR_PEER_CONN_ID, tunnel->peer_tunnel_id) || - nla_put_u32(skb, L2TP_ATTR_DEBUG, tunnel->debug) || + nla_put_u32(skb, L2TP_ATTR_DEBUG, 0) || nla_put_u16(skb, L2TP_ATTR_ENCAP_TYPE, tunnel->encap)) goto nla_put_failure; @@ -426,6 +420,9 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla nla_put_u64_64bit(skb, L2TP_ATTR_RX_SEQ_DISCARDS, atomic_long_read(&tunnel->stats.rx_seq_discards), L2TP_ATTR_STATS_PAD) || + nla_put_u64_64bit(skb, L2TP_ATTR_RX_COOKIE_DISCARDS, + atomic_long_read(&tunnel->stats.rx_cookie_discards), + L2TP_ATTR_STATS_PAD) || nla_put_u64_64bit(skb, L2TP_ATTR_RX_OOS_PACKETS, atomic_long_read(&tunnel->stats.rx_oos_packets), L2TP_ATTR_STATS_PAD) || @@ -605,9 +602,6 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf cfg.ifname = nla_data(info->attrs[L2TP_ATTR_IFNAME]); } - if (info->attrs[L2TP_ATTR_DEBUG]) - cfg.debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]); - if (info->attrs[L2TP_ATTR_RECV_SEQ]) cfg.recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]); @@ -689,9 +683,6 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf goto out; } - if (info->attrs[L2TP_ATTR_DEBUG]) - session->debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]); - if (info->attrs[L2TP_ATTR_RECV_SEQ]) session->recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]); @@ -730,7 +721,7 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl nla_put_u32(skb, L2TP_ATTR_SESSION_ID, session->session_id) || nla_put_u32(skb, L2TP_ATTR_PEER_CONN_ID, tunnel->peer_tunnel_id) || nla_put_u32(skb, L2TP_ATTR_PEER_SESSION_ID, session->peer_session_id) || - nla_put_u32(skb, L2TP_ATTR_DEBUG, session->debug) || + nla_put_u32(skb, L2TP_ATTR_DEBUG, 0) || nla_put_u16(skb, L2TP_ATTR_PW_TYPE, session->pwtype)) goto nla_put_failure; @@ -772,6 +763,9 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl nla_put_u64_64bit(skb, L2TP_ATTR_RX_SEQ_DISCARDS, atomic_long_read(&session->stats.rx_seq_discards), L2TP_ATTR_STATS_PAD) || + nla_put_u64_64bit(skb, L2TP_ATTR_RX_COOKIE_DISCARDS, + atomic_long_read(&session->stats.rx_cookie_discards), + L2TP_ATTR_STATS_PAD) || nla_put_u64_64bit(skb, L2TP_ATTR_RX_OOS_PACKETS, atomic_long_read(&session->stats.rx_oos_packets), L2TP_ATTR_STATS_PAD) || @@ -920,7 +914,7 @@ static const struct nla_policy l2tp_nl_policy[L2TP_ATTR_MAX + 1] = { }, }; -static const struct genl_ops l2tp_nl_ops[] = { +static const struct genl_small_ops l2tp_nl_ops[] = { { .cmd = L2TP_CMD_NOOP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, @@ -987,8 +981,8 @@ static struct genl_family l2tp_nl_family __ro_after_init = { .policy = l2tp_nl_policy, .netnsok = true, .module = THIS_MODULE, - .ops = l2tp_nl_ops, - .n_ops = ARRAY_SIZE(l2tp_nl_ops), + .small_ops = l2tp_nl_ops, + .n_small_ops = ARRAY_SIZE(l2tp_nl_ops), .mcgrps = l2tp_multicast_group, .n_mcgrps = ARRAY_SIZE(l2tp_multicast_group), }; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 13c3153b40d6..aea85f91f059 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -237,17 +237,9 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int if (sk->sk_state & PPPOX_BOUND) { struct pppox_sock *po; - l2tp_dbg(session, L2TP_MSG_DATA, - "%s: recv %d byte data frame, passing to ppp\n", - session->name, data_len); - po = pppox_sk(sk); ppp_input(&po->chan, skb); } else { - l2tp_dbg(session, L2TP_MSG_DATA, - "%s: recv %d byte data frame, passing to L2TP socket\n", - session->name, data_len); - if (sock_queue_rcv_skb(sk, skb) < 0) { atomic_long_inc(&session->stats.rx_errors); kfree_skb(skb); @@ -259,7 +251,7 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int no_sock: rcu_read_unlock(); - l2tp_info(session, L2TP_MSG_DATA, "%s: no socket\n", session->name); + pr_warn_ratelimited("%s: no socket in recv\n", session->name); kfree_skb(skb); } @@ -324,7 +316,7 @@ static int pppol2tp_sendmsg(struct socket *sock, struct msghdr *m, } local_bh_disable(); - l2tp_xmit_skb(session, skb, session->hdr_len); + l2tp_xmit_skb(session, skb); local_bh_enable(); sock_put(sk); @@ -383,7 +375,7 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) skb->data[1] = PPP_UI; local_bh_disable(); - l2tp_xmit_skb(session, skb, session->hdr_len); + l2tp_xmit_skb(session, skb); local_bh_enable(); sock_put(sk); @@ -710,7 +702,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, if (!tunnel) { struct l2tp_tunnel_cfg tcfg = { .encap = L2TP_ENCAPTYPE_UDP, - .debug = 0, }; /* Prevent l2tp_tunnel_register() from trying to set up @@ -721,7 +712,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, goto end; } - error = l2tp_tunnel_create(sock_net(sk), info.fd, + error = l2tp_tunnel_create(info.fd, info.version, info.tunnel_id, info.peer_tunnel_id, &tcfg, @@ -840,8 +831,6 @@ out_no_ppp: drop_refcnt = false; sk->sk_state = PPPOX_CONNECTED; - l2tp_info(session, L2TP_MSG_CONTROL, "%s: created\n", - session->name); end: if (error) { @@ -1076,6 +1065,9 @@ static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd, if (!session) return -ENOTCONN; + if (WARN_ON(session->magic != L2TP_SESSION_MAGIC)) + return -EBADF; + /* Not defined for tunnels */ if (!session->session_id && !session->peer_session_id) return -ENOSYS; @@ -1090,6 +1082,9 @@ static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd, if (!session) return -ENOTCONN; + if (WARN_ON(session->magic != L2TP_SESSION_MAGIC)) + return -EBADF; + /* Not defined for tunnels */ if (!session->session_id && !session->peer_session_id) return -ENOSYS; @@ -1103,6 +1098,9 @@ static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd, if (!session) return -ENOTCONN; + if (WARN_ON(session->magic != L2TP_SESSION_MAGIC)) + return -EBADF; + /* Session 0 represents the parent tunnel */ if (!session->session_id && !session->peer_session_id) { u32 session_id; @@ -1157,9 +1155,7 @@ static int pppol2tp_tunnel_setsockopt(struct sock *sk, switch (optname) { case PPPOL2TP_SO_DEBUG: - tunnel->debug = val; - l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: set debug=%x\n", - tunnel->name, tunnel->debug); + /* Tunnel debug flags option is deprecated */ break; default: @@ -1185,9 +1181,6 @@ static int pppol2tp_session_setsockopt(struct sock *sk, break; } session->recv_seq = !!val; - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: set recv_seq=%d\n", - session->name, session->recv_seq); break; case PPPOL2TP_SO_SENDSEQ: @@ -1203,9 +1196,6 @@ static int pppol2tp_session_setsockopt(struct sock *sk, PPPOL2TP_L2TP_HDR_SIZE_NOSEQ; } l2tp_session_set_header_len(session, session->tunnel->version); - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: set send_seq=%d\n", - session->name, session->send_seq); break; case PPPOL2TP_SO_LNSMODE: @@ -1214,22 +1204,14 @@ static int pppol2tp_session_setsockopt(struct sock *sk, break; } session->lns_mode = !!val; - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: set lns_mode=%d\n", - session->name, session->lns_mode); break; case PPPOL2TP_SO_DEBUG: - session->debug = val; - l2tp_info(session, L2TP_MSG_CONTROL, "%s: set debug=%x\n", - session->name, session->debug); + /* Session debug flags option is deprecated */ break; case PPPOL2TP_SO_REORDERTO: session->reorder_timeout = msecs_to_jiffies(val); - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: set reorder_timeout=%d\n", - session->name, session->reorder_timeout); break; default: @@ -1297,9 +1279,8 @@ static int pppol2tp_tunnel_getsockopt(struct sock *sk, switch (optname) { case PPPOL2TP_SO_DEBUG: - *val = tunnel->debug; - l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: get debug=%x\n", - tunnel->name, tunnel->debug); + /* Tunnel debug flags option is deprecated */ + *val = 0; break; default: @@ -1321,32 +1302,23 @@ static int pppol2tp_session_getsockopt(struct sock *sk, switch (optname) { case PPPOL2TP_SO_RECVSEQ: *val = session->recv_seq; - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: get recv_seq=%d\n", session->name, *val); break; case PPPOL2TP_SO_SENDSEQ: *val = session->send_seq; - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: get send_seq=%d\n", session->name, *val); break; case PPPOL2TP_SO_LNSMODE: *val = session->lns_mode; - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: get lns_mode=%d\n", session->name, *val); break; case PPPOL2TP_SO_DEBUG: - *val = session->debug; - l2tp_info(session, L2TP_MSG_CONTROL, "%s: get debug=%d\n", - session->name, *val); + /* Session debug flags option is deprecated */ + *val = 0; break; case PPPOL2TP_SO_REORDERTO: *val = (int)jiffies_to_msecs(session->reorder_timeout); - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: get reorder_timeout=%d\n", session->name, *val); break; default: @@ -1534,7 +1506,7 @@ static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v) (tunnel == tunnel->sock->sk_user_data) ? 'Y' : 'N', refcount_read(&tunnel->ref_count) - 1); seq_printf(m, " %08x %ld/%ld/%ld %ld/%ld/%ld\n", - tunnel->debug, + 0, atomic_long_read(&tunnel->stats.tx_packets), atomic_long_read(&tunnel->stats.tx_bytes), atomic_long_read(&tunnel->stats.tx_errors), @@ -1580,7 +1552,7 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v) session->recv_seq ? 'R' : '-', session->send_seq ? 'S' : '-', session->lns_mode ? "LNS" : "LAC", - session->debug, + 0, jiffies_to_msecs(session->reorder_timeout)); seq_printf(m, " %hu/%hu %ld/%ld/%ld %ld/%ld/%ld\n", session->nr, session->ns, diff --git a/net/l2tp/trace.h b/net/l2tp/trace.h new file mode 100644 index 000000000000..8596eaa12a2e --- /dev/null +++ b/net/l2tp/trace.h @@ -0,0 +1,211 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM l2tp + +#if !defined(_TRACE_L2TP_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_L2TP_H + +#include <linux/tracepoint.h> +#include <linux/l2tp.h> +#include "l2tp_core.h" + +#define encap_type_name(e) { L2TP_ENCAPTYPE_##e, #e } +#define show_encap_type_name(val) \ + __print_symbolic(val, \ + encap_type_name(UDP), \ + encap_type_name(IP)) + +#define pw_type_name(p) { L2TP_PWTYPE_##p, #p } +#define show_pw_type_name(val) \ + __print_symbolic(val, \ + pw_type_name(ETH_VLAN), \ + pw_type_name(ETH), \ + pw_type_name(PPP), \ + pw_type_name(PPP_AC), \ + pw_type_name(IP)) + +DECLARE_EVENT_CLASS(tunnel_only_evt, + TP_PROTO(struct l2tp_tunnel *tunnel), + TP_ARGS(tunnel), + TP_STRUCT__entry( + __array(char, name, L2TP_TUNNEL_NAME_MAX) + ), + TP_fast_assign( + memcpy(__entry->name, tunnel->name, L2TP_TUNNEL_NAME_MAX); + ), + TP_printk("%s", __entry->name) +); + +DECLARE_EVENT_CLASS(session_only_evt, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session), + TP_STRUCT__entry( + __array(char, name, L2TP_SESSION_NAME_MAX) + ), + TP_fast_assign( + memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX); + ), + TP_printk("%s", __entry->name) +); + +TRACE_EVENT(register_tunnel, + TP_PROTO(struct l2tp_tunnel *tunnel), + TP_ARGS(tunnel), + TP_STRUCT__entry( + __array(char, name, L2TP_TUNNEL_NAME_MAX) + __field(int, fd) + __field(u32, tid) + __field(u32, ptid) + __field(int, version) + __field(enum l2tp_encap_type, encap) + ), + TP_fast_assign( + memcpy(__entry->name, tunnel->name, L2TP_TUNNEL_NAME_MAX); + __entry->fd = tunnel->fd; + __entry->tid = tunnel->tunnel_id; + __entry->ptid = tunnel->peer_tunnel_id; + __entry->version = tunnel->version; + __entry->encap = tunnel->encap; + ), + TP_printk("%s: type=%s encap=%s version=L2TPv%d tid=%u ptid=%u fd=%d", + __entry->name, + __entry->fd > 0 ? "managed" : "unmanaged", + show_encap_type_name(__entry->encap), + __entry->version, + __entry->tid, + __entry->ptid, + __entry->fd) +); + +DEFINE_EVENT(tunnel_only_evt, delete_tunnel, + TP_PROTO(struct l2tp_tunnel *tunnel), + TP_ARGS(tunnel) +); + +DEFINE_EVENT(tunnel_only_evt, free_tunnel, + TP_PROTO(struct l2tp_tunnel *tunnel), + TP_ARGS(tunnel) +); + +TRACE_EVENT(register_session, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session), + TP_STRUCT__entry( + __array(char, name, L2TP_SESSION_NAME_MAX) + __field(u32, tid) + __field(u32, ptid) + __field(u32, sid) + __field(u32, psid) + __field(enum l2tp_pwtype, pwtype) + ), + TP_fast_assign( + memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX); + __entry->tid = session->tunnel ? session->tunnel->tunnel_id : 0; + __entry->ptid = session->tunnel ? session->tunnel->peer_tunnel_id : 0; + __entry->sid = session->session_id; + __entry->psid = session->peer_session_id; + __entry->pwtype = session->pwtype; + ), + TP_printk("%s: pseudowire=%s sid=%u psid=%u tid=%u ptid=%u", + __entry->name, + show_pw_type_name(__entry->pwtype), + __entry->sid, + __entry->psid, + __entry->sid, + __entry->psid) +); + +DEFINE_EVENT(session_only_evt, delete_session, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session) +); + +DEFINE_EVENT(session_only_evt, free_session, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session) +); + +DEFINE_EVENT(session_only_evt, session_seqnum_lns_enable, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session) +); + +DEFINE_EVENT(session_only_evt, session_seqnum_lns_disable, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session) +); + +DECLARE_EVENT_CLASS(session_seqnum_evt, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session), + TP_STRUCT__entry( + __array(char, name, L2TP_SESSION_NAME_MAX) + __field(u32, ns) + __field(u32, nr) + ), + TP_fast_assign( + memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX); + __entry->ns = session->ns; + __entry->nr = session->nr; + ), + TP_printk("%s: ns=%u nr=%u", + __entry->name, + __entry->ns, + __entry->nr) +); + +DEFINE_EVENT(session_seqnum_evt, session_seqnum_update, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session) +); + +DEFINE_EVENT(session_seqnum_evt, session_seqnum_reset, + TP_PROTO(struct l2tp_session *session), + TP_ARGS(session) +); + +DECLARE_EVENT_CLASS(session_pkt_discard_evt, + TP_PROTO(struct l2tp_session *session, u32 pkt_ns), + TP_ARGS(session, pkt_ns), + TP_STRUCT__entry( + __array(char, name, L2TP_SESSION_NAME_MAX) + __field(u32, pkt_ns) + __field(u32, my_nr) + __field(u32, reorder_q_len) + ), + TP_fast_assign( + memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX); + __entry->pkt_ns = pkt_ns, + __entry->my_nr = session->nr; + __entry->reorder_q_len = skb_queue_len(&session->reorder_q); + ), + TP_printk("%s: pkt_ns=%u my_nr=%u reorder_q_len=%u", + __entry->name, + __entry->pkt_ns, + __entry->my_nr, + __entry->reorder_q_len) +); + +DEFINE_EVENT(session_pkt_discard_evt, session_pkt_expired, + TP_PROTO(struct l2tp_session *session, u32 pkt_ns), + TP_ARGS(session, pkt_ns) +); + +DEFINE_EVENT(session_pkt_discard_evt, session_pkt_outside_rx_window, + TP_PROTO(struct l2tp_session *session, u32 pkt_ns), + TP_ARGS(session, pkt_ns) +); + +DEFINE_EVENT(session_pkt_discard_evt, session_pkt_oos, + TP_PROTO(struct l2tp_session *session, u32 pkt_ns), + TP_ARGS(session, pkt_ns) +); + +#endif /* _TRACE_L2TP_H */ + +/* This part must be outside protection */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace +#include <trace/define_trace.h> diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile index 6cbb1286d6c0..ad04c361cba5 100644 --- a/net/mac80211/Makefile +++ b/net/mac80211/Makefile @@ -13,6 +13,7 @@ mac80211-y := \ ht.o agg-tx.o agg-rx.o \ vht.o \ he.o \ + s1g.o \ ibss.o \ iface.o \ rate.o \ diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 313ba97acae3..cd4cf84a7f99 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -350,7 +350,7 @@ void ___ieee80211_start_rx_ba_session(struct sta_info *sta, sta->sta.addr, tid); /* We have no API to update the timeout value in the * driver so reject the timeout update if the timeout - * changed. If if did not change, i.e., no real update, + * changed. If it did not change, i.e., no real update, * just reply with success. */ rcu_read_lock(); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 87fddd84c621..7276e66ae435 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -709,7 +709,8 @@ void sta_set_rate_info_tx(struct sta_info *sta, u16 brate; sband = ieee80211_get_sband(sta->sdata); - if (sband) { + WARN_ON_ONCE(sband && !sband->bitrates); + if (sband && sband->bitrates) { brate = sband->bitrates[rate->idx].bitrate; rinfo->legacy = DIV_ROUND_UP(brate, 1 << shift); } @@ -826,9 +827,9 @@ static int ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata, memcpy(new->data, resp, resp_len); if (csa) - memcpy(new->csa_counter_offsets, csa->counter_offsets_presp, + memcpy(new->cntdwn_counter_offsets, csa->counter_offsets_presp, csa->n_counter_offsets_presp * - sizeof(new->csa_counter_offsets[0])); + sizeof(new->cntdwn_counter_offsets[0])); rcu_assign_pointer(sdata->u.ap.probe_resp, new); if (old) @@ -837,6 +838,59 @@ static int ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata, return 0; } +static int ieee80211_set_fils_discovery(struct ieee80211_sub_if_data *sdata, + struct cfg80211_fils_discovery *params) +{ + struct fils_discovery_data *new, *old = NULL; + struct ieee80211_fils_discovery *fd; + + if (!params->tmpl || !params->tmpl_len) + return -EINVAL; + + fd = &sdata->vif.bss_conf.fils_discovery; + fd->min_interval = params->min_interval; + fd->max_interval = params->max_interval; + + old = sdata_dereference(sdata->u.ap.fils_discovery, sdata); + new = kzalloc(sizeof(*new) + params->tmpl_len, GFP_KERNEL); + if (!new) + return -ENOMEM; + new->len = params->tmpl_len; + memcpy(new->data, params->tmpl, params->tmpl_len); + rcu_assign_pointer(sdata->u.ap.fils_discovery, new); + + if (old) + kfree_rcu(old, rcu_head); + + return 0; +} + +static int +ieee80211_set_unsol_bcast_probe_resp(struct ieee80211_sub_if_data *sdata, + struct cfg80211_unsol_bcast_probe_resp *params) +{ + struct unsol_bcast_probe_resp_data *new, *old = NULL; + + if (!params->tmpl || !params->tmpl_len) + return -EINVAL; + + old = sdata_dereference(sdata->u.ap.unsol_bcast_probe_resp, sdata); + new = kzalloc(sizeof(*new) + params->tmpl_len, GFP_KERNEL); + if (!new) + return -ENOMEM; + new->len = params->tmpl_len; + memcpy(new->data, params->tmpl, params->tmpl_len); + rcu_assign_pointer(sdata->u.ap.unsol_bcast_probe_resp, new); + + if (old) + kfree_rcu(old, rcu_head); + + sdata->vif.bss_conf.unsol_bcast_probe_resp_interval = + params->interval; + + return 0; +} + static int ieee80211_set_ftm_responder_params( struct ieee80211_sub_if_data *sdata, const u8 *lci, size_t lci_len, @@ -926,10 +980,10 @@ static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, new->tail_len = new_tail_len; if (csa) { - new->csa_current_counter = csa->count; - memcpy(new->csa_counter_offsets, csa->counter_offsets_beacon, + new->cntdwn_current_counter = csa->count; + memcpy(new->cntdwn_counter_offsets, csa->counter_offsets_beacon, csa->n_counter_offsets_beacon * - sizeof(new->csa_counter_offsets[0])); + sizeof(new->cntdwn_counter_offsets[0])); } /* copy in head */ @@ -1071,6 +1125,8 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, sizeof(struct ieee80211_he_obss_pd)); memcpy(&sdata->vif.bss_conf.he_bss_color, ¶ms->he_bss_color, sizeof(struct ieee80211_he_bss_color)); + sdata->vif.bss_conf.s1g = params->chandef.chan->band == + NL80211_BAND_S1GHZ; sdata->vif.bss_conf.ssid_len = params->ssid_len; if (params->ssid_len) @@ -1098,13 +1154,30 @@ 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); - if (err < 0) { - ieee80211_vif_release_channel(sdata); - return err; - } + if (err < 0) + goto error; changed |= err; + if (params->fils_discovery.max_interval) { + err = ieee80211_set_fils_discovery(sdata, + ¶ms->fils_discovery); + if (err < 0) + goto error; + changed |= BSS_CHANGED_FILS_DISCOVERY; + } + + if (params->unsol_bcast_probe_resp.interval) { + err = ieee80211_set_unsol_bcast_probe_resp(sdata, + ¶ms->unsol_bcast_probe_resp); + if (err < 0) + goto error; + changed |= BSS_CHANGED_UNSOL_BCAST_PROBE_RESP; + } + err = drv_start_ap(sdata->local, sdata); if (err) { old = sdata_dereference(sdata->u.ap.beacon, sdata); @@ -1112,8 +1185,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, if (old) kfree_rcu(old, rcu_head); RCU_INIT_POINTER(sdata->u.ap.beacon, NULL); - ieee80211_vif_release_channel(sdata); - return err; + goto error; } ieee80211_recalc_dtim(local, sdata); @@ -1124,6 +1196,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, netif_carrier_on(vlan->dev); return 0; + +error: + ieee80211_vif_release_channel(sdata); + return err; } static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev, @@ -1160,6 +1236,8 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) struct ieee80211_local *local = sdata->local; struct beacon_data *old_beacon; struct probe_resp *old_probe_resp; + struct fils_discovery_data *old_fils_discovery; + struct unsol_bcast_probe_resp_data *old_unsol_bcast_probe_resp; struct cfg80211_chan_def chandef; sdata_assert_lock(sdata); @@ -1168,6 +1246,11 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) if (!old_beacon) return -ENOENT; old_probe_resp = sdata_dereference(sdata->u.ap.probe_resp, sdata); + old_fils_discovery = sdata_dereference(sdata->u.ap.fils_discovery, + sdata); + old_unsol_bcast_probe_resp = + sdata_dereference(sdata->u.ap.unsol_bcast_probe_resp, + sdata); /* abort any running channel switch */ mutex_lock(&local->mtx); @@ -1191,9 +1274,15 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) /* remove beacon and probe response */ RCU_INIT_POINTER(sdata->u.ap.beacon, NULL); RCU_INIT_POINTER(sdata->u.ap.probe_resp, NULL); + RCU_INIT_POINTER(sdata->u.ap.fils_discovery, NULL); + RCU_INIT_POINTER(sdata->u.ap.unsol_bcast_probe_resp, NULL); kfree_rcu(old_beacon, rcu_head); if (old_probe_resp) kfree_rcu(old_probe_resp, rcu_head); + if (old_fils_discovery) + kfree_rcu(old_fils_discovery, rcu_head); + if (old_unsol_bcast_probe_resp) + kfree_rcu(old_unsol_bcast_probe_resp, rcu_head); kfree(sdata->vif.bss_conf.ftmr_params); sdata->vif.bss_conf.ftmr_params = NULL; @@ -1696,6 +1785,7 @@ static int ieee80211_change_station(struct wiphy *wiphy, rcu_assign_pointer(vlansdata->u.vlan.sta, sta); __ieee80211_check_fast_rx_iface(vlansdata); + drv_sta_set_4addr(local, sta->sdata, &sta->sta, true); } if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN && @@ -3186,9 +3276,9 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata, break; if ((params->n_counter_offsets_beacon > - IEEE80211_MAX_CSA_COUNTERS_NUM) || + IEEE80211_MAX_CNTDWN_COUNTERS_NUM) || (params->n_counter_offsets_presp > - IEEE80211_MAX_CSA_COUNTERS_NUM)) + IEEE80211_MAX_CNTDWN_COUNTERS_NUM)) return -EINVAL; csa.counter_offsets_beacon = params->counter_offsets_beacon; diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index bdc0f29dc6cd..8f48aff74c7b 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -536,7 +536,14 @@ static void ieee80211_del_chanctx(struct ieee80211_local *local, if (!local->use_chanctx) { struct cfg80211_chan_def *chandef = &local->_oper_chandef; - chandef->width = NL80211_CHAN_WIDTH_20_NOHT; + /* S1G doesn't have 20MHz, so get the correct width for the + * current channel. + */ + if (chandef->chan->band == NL80211_BAND_S1GHZ) + chandef->width = + ieee80211_s1g_channel_width(chandef->chan); + else + chandef->width = NL80211_CHAN_WIDTH_20_NOHT; chandef->center_freq1 = chandef->chan->center_freq; chandef->freq1_offset = chandef->chan->freq_offset; chandef->center_freq2 = 0; diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 54080290d6e2..90470392fdaa 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -408,6 +408,7 @@ static const char *hw_flag_names[] = { FLAG(SUPPORTS_MULTI_BSSID), FLAG(SUPPORTS_ONLY_HE_MULTI_BSSID), FLAG(AMPDU_KEYBORDER_SUPPORT), + FLAG(SUPPORTS_TX_ENCAP_OFFLOAD), #undef FLAG }; diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 41d495d73d3a..bcdfd19a596b 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1384,4 +1384,33 @@ static inline int drv_reset_tid_config(struct ieee80211_local *local, return ret; } + +static inline void drv_update_vif_offload(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) +{ + might_sleep(); + check_sdata_in_driver(sdata); + + if (!local->ops->update_vif_offload) + return; + + trace_drv_update_vif_offload(local, sdata); + local->ops->update_vif_offload(&local->hw, &sdata->vif); + trace_drv_return_void(local); +} + +static inline void drv_sta_set_4addr(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta, bool enabled) +{ + sdata = get_bss_sdata(sdata); + if (!check_sdata_in_driver(sdata)) + return; + + trace_drv_sta_set_4addr(local, sdata, sta, enabled); + if (local->ops->sta_set_4addr) + local->ops->sta_set_4addr(&local->hw, &sdata->vif, sta, enabled); + trace_drv_return_void(local); +} + #endif /* __MAC80211_DRIVER_OPS */ diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 53632c2f5217..1f552f374e97 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -145,9 +145,9 @@ ieee80211_ibss_build_presp(struct ieee80211_sub_if_data *sdata, *pos++ = csa_settings->block_tx ? 1 : 0; *pos++ = ieee80211_frequency_to_channel( csa_settings->chandef.chan->center_freq); - presp->csa_counter_offsets[0] = (pos - presp->head); + presp->cntdwn_counter_offsets[0] = (pos - presp->head); *pos++ = csa_settings->count; - presp->csa_current_counter = csa_settings->count; + presp->cntdwn_current_counter = csa_settings->count; } /* put the remaining rates in WLAN_EID_EXT_SUPP_RATES */ @@ -1037,7 +1037,8 @@ static void ieee80211_update_sta_info(struct ieee80211_sub_if_data *sdata, } if (sta && !sta->sta.wme && - elems->wmm_info && local->hw.queues >= IEEE80211_NUM_ACS) { + (elems->wmm_info || elems->s1g_capab) && + local->hw.queues >= IEEE80211_NUM_ACS) { sta->sta.wme = true; ieee80211_check_fast_xmit(sta); } diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 0b1eaec6649f..2a21226fb518 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -259,15 +259,27 @@ struct beacon_data { u8 *head, *tail; int head_len, tail_len; struct ieee80211_meshconf_ie *meshconf; - u16 csa_counter_offsets[IEEE80211_MAX_CSA_COUNTERS_NUM]; - u8 csa_current_counter; + u16 cntdwn_counter_offsets[IEEE80211_MAX_CNTDWN_COUNTERS_NUM]; + u8 cntdwn_current_counter; struct rcu_head rcu_head; }; struct probe_resp { struct rcu_head rcu_head; int len; - u16 csa_counter_offsets[IEEE80211_MAX_CSA_COUNTERS_NUM]; + u16 cntdwn_counter_offsets[IEEE80211_MAX_CNTDWN_COUNTERS_NUM]; + u8 data[]; +}; + +struct fils_discovery_data { + struct rcu_head rcu_head; + int len; + u8 data[]; +}; + +struct unsol_bcast_probe_resp_data { + struct rcu_head rcu_head; + int len; u8 data[]; }; @@ -286,6 +298,8 @@ struct ps_data { struct ieee80211_if_ap { struct beacon_data __rcu *beacon; struct probe_resp __rcu *probe_resp; + struct fils_discovery_data __rcu *fils_discovery; + struct unsol_bcast_probe_resp_data __rcu *unsol_bcast_probe_resp; /* to be used after channel switch. */ struct cfg80211_beacon_data *next_beacon; @@ -530,6 +544,8 @@ struct ieee80211_if_managed { struct ieee80211_ht_cap ht_capa_mask; /* Valid parts of ht_capa */ struct ieee80211_vht_cap vht_capa; /* configured VHT overrides */ struct ieee80211_vht_cap vht_capa_mask; /* Valid parts of vht_capa */ + struct ieee80211_s1g_cap s1g_capa; /* configured S1G overrides */ + struct ieee80211_s1g_cap s1g_capa_mask; /* valid s1g_capa bits */ /* TDLS support */ u8 tdls_peer[ETH_ALEN] __aligned(2); @@ -989,8 +1005,6 @@ struct ieee80211_sub_if_data { } debugfs; #endif - bool hw_80211_encap; - /* must be last, dynamically sized area in this! */ struct ieee80211_vif vif; }; @@ -1364,7 +1378,6 @@ struct ieee80211_local { */ bool pspolling; - bool offchannel_ps_enabled; /* * PS can only be enabled when we have exactly one managed * interface (and monitors) in PS, this then points there. @@ -1522,6 +1535,10 @@ struct ieee802_11_elems { u8 dtim_count; u8 dtim_period; const struct ieee80211_addba_ext_ie *addba_ext_ie; + const struct ieee80211_s1g_cap *s1g_capab; + const struct ieee80211_s1g_oper_ie *s1g_oper; + const struct ieee80211_s1g_bcn_compat_ie *s1g_bcn_compat; + const struct ieee80211_aid_response_ie *aid_resp; /* length of them, respectively */ u8 ext_capab_len; @@ -1640,6 +1657,8 @@ int ieee80211_set_arp_filter(struct ieee80211_sub_if_data *sdata); void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata); void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); +void ieee80211_sta_rx_queued_ext(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb); void ieee80211_sta_reset_beacon_monitor(struct ieee80211_sub_if_data *sdata); void ieee80211_sta_reset_conn_monitor(struct ieee80211_sub_if_data *sdata); void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata); @@ -1767,6 +1786,7 @@ void ieee80211_del_virtual_monitor(struct ieee80211_local *local); bool __ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata); void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata, bool update_bss); +void ieee80211_recalc_offload(struct ieee80211_local *local); static inline bool ieee80211_sdata_running(struct ieee80211_sub_if_data *sdata) { @@ -1908,6 +1928,9 @@ void ieee80211_he_op_ie_to_bss_conf(struct ieee80211_vif *vif, const struct ieee80211_he_operation *he_op_ie_elem); +/* S1G */ +void ieee80211_s1g_sta_rate_init(struct sta_info *sta); + /* Spectrum management */ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, @@ -2040,8 +2063,6 @@ 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_sta_rx_notify(struct ieee80211_sub_if_data *sdata, - struct ieee80211_hdr *hdr); void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata, struct ieee80211_hdr *hdr, bool ack, u16 tx_time); @@ -2193,6 +2214,11 @@ int ieee80211_add_ext_srates_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, bool need_basic, enum nl80211_band band); u8 *ieee80211_add_wmm_info_ie(u8 *buf, u8 qosinfo); +void ieee80211_add_s1g_capab_ie(struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta_s1g_cap *caps, + struct sk_buff *skb); +void ieee80211_add_aid_request_ie(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb); /* channel management */ bool ieee80211_chandef_ht_oper(const struct ieee80211_ht_operation *ht_oper, @@ -2204,6 +2230,8 @@ bool ieee80211_chandef_vht_oper(struct ieee80211_hw *hw, u32 vht_cap_info, bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata, const struct ieee80211_he_operation *he_oper, struct cfg80211_chan_def *chandef); +bool ieee80211_chandef_s1g_oper(const struct ieee80211_s1g_oper_ie *oper, + struct cfg80211_chan_def *chandef); u32 ieee80211_chandef_downgrade(struct cfg80211_chan_def *c); int __must_check @@ -2282,6 +2310,9 @@ void ieee80211_tdls_chsw_work(struct work_struct *wk); void ieee80211_tdls_handle_disconnect(struct ieee80211_sub_if_data *sdata, const u8 *peer, u16 reason); const char *ieee80211_get_reason_code_string(u16 reason_code); +u16 ieee80211_encode_usf(int val); +u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len, + enum nl80211_iftype type); extern const struct ethtool_ops ieee80211_ethtool_ops; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 9740ae8fa697..1be775979132 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -348,439 +348,6 @@ static int ieee80211_check_queues(struct ieee80211_sub_if_data *sdata, return 0; } -void ieee80211_adjust_monitor_flags(struct ieee80211_sub_if_data *sdata, - const int offset) -{ - struct ieee80211_local *local = sdata->local; - u32 flags = sdata->u.mntr.flags; - -#define ADJUST(_f, _s) do { \ - if (flags & MONITOR_FLAG_##_f) \ - local->fif_##_s += offset; \ - } while (0) - - ADJUST(FCSFAIL, fcsfail); - ADJUST(PLCPFAIL, plcpfail); - ADJUST(CONTROL, control); - ADJUST(CONTROL, pspoll); - ADJUST(OTHER_BSS, other_bss); - -#undef ADJUST -} - -static void ieee80211_set_default_queues(struct ieee80211_sub_if_data *sdata) -{ - struct ieee80211_local *local = sdata->local; - int i; - - for (i = 0; i < IEEE80211_NUM_ACS; i++) { - if (ieee80211_hw_check(&local->hw, QUEUE_CONTROL)) - sdata->vif.hw_queue[i] = IEEE80211_INVAL_HW_QUEUE; - else if (local->hw.queues >= IEEE80211_NUM_ACS) - sdata->vif.hw_queue[i] = i; - else - sdata->vif.hw_queue[i] = 0; - } - sdata->vif.cab_queue = IEEE80211_INVAL_HW_QUEUE; -} - -int ieee80211_add_virtual_monitor(struct ieee80211_local *local) -{ - struct ieee80211_sub_if_data *sdata; - int ret; - - if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) - return 0; - - ASSERT_RTNL(); - - if (local->monitor_sdata) - return 0; - - sdata = kzalloc(sizeof(*sdata) + local->hw.vif_data_size, GFP_KERNEL); - if (!sdata) - return -ENOMEM; - - /* set up data */ - sdata->local = local; - sdata->vif.type = NL80211_IFTYPE_MONITOR; - snprintf(sdata->name, IFNAMSIZ, "%s-monitor", - wiphy_name(local->hw.wiphy)); - sdata->wdev.iftype = NL80211_IFTYPE_MONITOR; - - sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM; - - ieee80211_set_default_queues(sdata); - - ret = drv_add_interface(local, sdata); - if (WARN_ON(ret)) { - /* ok .. stupid driver, it asked for this! */ - kfree(sdata); - return ret; - } - - ret = ieee80211_check_queues(sdata, NL80211_IFTYPE_MONITOR); - if (ret) { - kfree(sdata); - return ret; - } - - mutex_lock(&local->iflist_mtx); - rcu_assign_pointer(local->monitor_sdata, sdata); - mutex_unlock(&local->iflist_mtx); - - mutex_lock(&local->mtx); - ret = ieee80211_vif_use_channel(sdata, &local->monitor_chandef, - IEEE80211_CHANCTX_EXCLUSIVE); - mutex_unlock(&local->mtx); - if (ret) { - mutex_lock(&local->iflist_mtx); - RCU_INIT_POINTER(local->monitor_sdata, NULL); - mutex_unlock(&local->iflist_mtx); - synchronize_net(); - drv_remove_interface(local, sdata); - kfree(sdata); - return ret; - } - - skb_queue_head_init(&sdata->skb_queue); - INIT_WORK(&sdata->work, ieee80211_iface_work); - - return 0; -} - -void ieee80211_del_virtual_monitor(struct ieee80211_local *local) -{ - struct ieee80211_sub_if_data *sdata; - - if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) - return; - - ASSERT_RTNL(); - - mutex_lock(&local->iflist_mtx); - - sdata = rcu_dereference_protected(local->monitor_sdata, - lockdep_is_held(&local->iflist_mtx)); - if (!sdata) { - mutex_unlock(&local->iflist_mtx); - return; - } - - RCU_INIT_POINTER(local->monitor_sdata, NULL); - mutex_unlock(&local->iflist_mtx); - - synchronize_net(); - - mutex_lock(&local->mtx); - ieee80211_vif_release_channel(sdata); - mutex_unlock(&local->mtx); - - drv_remove_interface(local, sdata); - - kfree(sdata); -} - -/* - * NOTE: Be very careful when changing this function, it must NOT return - * an error on interface type changes that have been pre-checked, so most - * checks should be in ieee80211_check_concurrent_iface. - */ -int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) -{ - struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); - struct net_device *dev = wdev->netdev; - struct ieee80211_local *local = sdata->local; - struct sta_info *sta; - u32 changed = 0; - int res; - u32 hw_reconf_flags = 0; - - switch (sdata->vif.type) { - case NL80211_IFTYPE_WDS: - if (!is_valid_ether_addr(sdata->u.wds.remote_addr)) - return -ENOLINK; - break; - case NL80211_IFTYPE_AP_VLAN: { - struct ieee80211_sub_if_data *master; - - if (!sdata->bss) - return -ENOLINK; - - mutex_lock(&local->mtx); - list_add(&sdata->u.vlan.list, &sdata->bss->vlans); - mutex_unlock(&local->mtx); - - master = container_of(sdata->bss, - struct ieee80211_sub_if_data, u.ap); - sdata->control_port_protocol = - master->control_port_protocol; - sdata->control_port_no_encrypt = - master->control_port_no_encrypt; - sdata->control_port_over_nl80211 = - master->control_port_over_nl80211; - sdata->control_port_no_preauth = - master->control_port_no_preauth; - sdata->vif.cab_queue = master->vif.cab_queue; - memcpy(sdata->vif.hw_queue, master->vif.hw_queue, - sizeof(sdata->vif.hw_queue)); - sdata->vif.bss_conf.chandef = master->vif.bss_conf.chandef; - - mutex_lock(&local->key_mtx); - sdata->crypto_tx_tailroom_needed_cnt += - master->crypto_tx_tailroom_needed_cnt; - mutex_unlock(&local->key_mtx); - - break; - } - case NL80211_IFTYPE_AP: - sdata->bss = &sdata->u.ap; - break; - case NL80211_IFTYPE_MESH_POINT: - case NL80211_IFTYPE_STATION: - case NL80211_IFTYPE_MONITOR: - case NL80211_IFTYPE_ADHOC: - case NL80211_IFTYPE_P2P_DEVICE: - case NL80211_IFTYPE_OCB: - case NL80211_IFTYPE_NAN: - /* no special treatment */ - break; - case NL80211_IFTYPE_UNSPECIFIED: - case NUM_NL80211_IFTYPES: - case NL80211_IFTYPE_P2P_CLIENT: - case NL80211_IFTYPE_P2P_GO: - /* cannot happen */ - WARN_ON(1); - break; - } - - if (local->open_count == 0) { - res = drv_start(local); - if (res) - goto err_del_bss; - /* we're brought up, everything changes */ - hw_reconf_flags = ~0; - ieee80211_led_radio(local, true); - ieee80211_mod_tpt_led_trig(local, - IEEE80211_TPT_LEDTRIG_FL_RADIO, 0); - } - - /* - * Copy the hopefully now-present MAC address to - * this interface, if it has the special null one. - */ - if (dev && is_zero_ether_addr(dev->dev_addr)) { - memcpy(dev->dev_addr, - local->hw.wiphy->perm_addr, - ETH_ALEN); - memcpy(dev->perm_addr, dev->dev_addr, ETH_ALEN); - - if (!is_valid_ether_addr(dev->dev_addr)) { - res = -EADDRNOTAVAIL; - goto err_stop; - } - } - - switch (sdata->vif.type) { - case NL80211_IFTYPE_AP_VLAN: - /* no need to tell driver, but set carrier and chanctx */ - if (rtnl_dereference(sdata->bss->beacon)) { - ieee80211_vif_vlan_copy_chanctx(sdata); - netif_carrier_on(dev); - } else { - netif_carrier_off(dev); - } - break; - case NL80211_IFTYPE_MONITOR: - if (sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES) { - local->cooked_mntrs++; - break; - } - - if (sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE) { - res = drv_add_interface(local, sdata); - if (res) - goto err_stop; - } else if (local->monitors == 0 && local->open_count == 0) { - res = ieee80211_add_virtual_monitor(local); - if (res) - goto err_stop; - } - - /* must be before the call to ieee80211_configure_filter */ - local->monitors++; - if (local->monitors == 1) { - local->hw.conf.flags |= IEEE80211_CONF_MONITOR; - hw_reconf_flags |= IEEE80211_CONF_CHANGE_MONITOR; - } - - ieee80211_adjust_monitor_flags(sdata, 1); - ieee80211_configure_filter(local); - mutex_lock(&local->mtx); - ieee80211_recalc_idle(local); - mutex_unlock(&local->mtx); - - netif_carrier_on(dev); - break; - default: - if (coming_up) { - ieee80211_del_virtual_monitor(local); - - res = drv_add_interface(local, sdata); - if (res) - goto err_stop; - res = ieee80211_check_queues(sdata, - ieee80211_vif_type_p2p(&sdata->vif)); - if (res) - goto err_del_interface; - } - - if (sdata->vif.type == NL80211_IFTYPE_AP) { - local->fif_pspoll++; - local->fif_probe_req++; - - ieee80211_configure_filter(local); - } else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { - local->fif_probe_req++; - } - - if (sdata->vif.probe_req_reg) - drv_config_iface_filter(local, sdata, - FIF_PROBE_REQ, - FIF_PROBE_REQ); - - if (sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE && - sdata->vif.type != NL80211_IFTYPE_NAN) - changed |= ieee80211_reset_erp_info(sdata); - ieee80211_bss_info_change_notify(sdata, changed); - - switch (sdata->vif.type) { - case NL80211_IFTYPE_STATION: - case NL80211_IFTYPE_ADHOC: - case NL80211_IFTYPE_AP: - case NL80211_IFTYPE_MESH_POINT: - case NL80211_IFTYPE_OCB: - netif_carrier_off(dev); - break; - case NL80211_IFTYPE_WDS: - case NL80211_IFTYPE_P2P_DEVICE: - case NL80211_IFTYPE_NAN: - break; - default: - /* not reached */ - WARN_ON(1); - } - - /* - * Set default queue parameters so drivers don't - * need to initialise the hardware if the hardware - * doesn't start up with sane defaults. - * Enable QoS for anything but station interfaces. - */ - ieee80211_set_wmm_default(sdata, true, - sdata->vif.type != NL80211_IFTYPE_STATION); - } - - set_bit(SDATA_STATE_RUNNING, &sdata->state); - - switch (sdata->vif.type) { - case NL80211_IFTYPE_WDS: - /* Create STA entry for the WDS peer */ - sta = sta_info_alloc(sdata, sdata->u.wds.remote_addr, - GFP_KERNEL); - if (!sta) { - res = -ENOMEM; - goto err_del_interface; - } - - sta_info_pre_move_state(sta, IEEE80211_STA_AUTH); - sta_info_pre_move_state(sta, IEEE80211_STA_ASSOC); - sta_info_pre_move_state(sta, IEEE80211_STA_AUTHORIZED); - - res = sta_info_insert(sta); - if (res) { - /* STA has been freed */ - goto err_del_interface; - } - - rate_control_rate_init(sta); - netif_carrier_on(dev); - break; - case NL80211_IFTYPE_P2P_DEVICE: - rcu_assign_pointer(local->p2p_sdata, sdata); - break; - case NL80211_IFTYPE_MONITOR: - if (sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES) - break; - list_add_tail_rcu(&sdata->u.mntr.list, &local->mon_list); - break; - default: - break; - } - - /* - * set_multicast_list will be invoked by the networking core - * which will check whether any increments here were done in - * error and sync them down to the hardware as filter flags. - */ - if (sdata->flags & IEEE80211_SDATA_ALLMULTI) - atomic_inc(&local->iff_allmultis); - - if (coming_up) - local->open_count++; - - if (hw_reconf_flags) - ieee80211_hw_config(local, hw_reconf_flags); - - ieee80211_recalc_ps(local); - - if (sdata->vif.type == NL80211_IFTYPE_MONITOR || - sdata->vif.type == NL80211_IFTYPE_AP_VLAN || - local->ops->wake_tx_queue) { - /* XXX: for AP_VLAN, actually track AP queues */ - if (dev) - netif_tx_start_all_queues(dev); - } else if (dev) { - unsigned long flags; - int n_acs = IEEE80211_NUM_ACS; - int ac; - - if (local->hw.queues < IEEE80211_NUM_ACS) - n_acs = 1; - - spin_lock_irqsave(&local->queue_stop_reason_lock, flags); - if (sdata->vif.cab_queue == IEEE80211_INVAL_HW_QUEUE || - (local->queue_stop_reasons[sdata->vif.cab_queue] == 0 && - skb_queue_empty(&local->pending[sdata->vif.cab_queue]))) { - for (ac = 0; ac < n_acs; ac++) { - int ac_queue = sdata->vif.hw_queue[ac]; - - if (local->queue_stop_reasons[ac_queue] == 0 && - skb_queue_empty(&local->pending[ac_queue])) - netif_start_subqueue(dev, ac); - } - } - spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); - } - - return 0; - err_del_interface: - drv_remove_interface(local, sdata); - err_stop: - if (!local->open_count) - drv_stop(local); - err_del_bss: - sdata->bss = NULL; - if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { - mutex_lock(&local->mtx); - list_del(&sdata->u.vlan.list); - mutex_unlock(&local->mtx); - } - /* might already be clear but that doesn't matter */ - clear_bit(SDATA_STATE_RUNNING, &sdata->state); - return res; -} - static int ieee80211_open(struct net_device *dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); @@ -1142,28 +709,7 @@ static u16 ieee80211_netdev_select_queue(struct net_device *dev, static void ieee80211_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { - int i; - - for_each_possible_cpu(i) { - const struct pcpu_sw_netstats *tstats; - u64 rx_packets, rx_bytes, tx_packets, tx_bytes; - unsigned int start; - - tstats = per_cpu_ptr(dev->tstats, i); - - do { - start = u64_stats_fetch_begin_irq(&tstats->syncp); - rx_packets = tstats->rx_packets; - tx_packets = tstats->tx_packets; - rx_bytes = tstats->rx_bytes; - tx_bytes = tstats->tx_bytes; - } while (u64_stats_fetch_retry_irq(&tstats->syncp, start)); - - stats->rx_packets += rx_packets; - stats->tx_packets += tx_packets; - stats->rx_bytes += rx_bytes; - stats->tx_bytes += tx_bytes; - } + dev_fetch_sw_netstats(stats, dev->tstats); } static const struct net_device_ops ieee80211_dataif_ops = { @@ -1227,60 +773,547 @@ static const struct net_device_ops ieee80211_dataif_8023_ops = { .ndo_get_stats64 = ieee80211_get_stats64, }; -static void __ieee80211_set_hw_80211_encap(struct ieee80211_sub_if_data *sdata, - bool enable) +static bool ieee80211_iftype_supports_encap_offload(enum nl80211_iftype iftype) { - sdata->dev->netdev_ops = enable ? &ieee80211_dataif_8023_ops : - &ieee80211_dataif_ops; - sdata->hw_80211_encap = enable; + switch (iftype) { + /* P2P GO and client are mapped to AP/STATION types */ + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_STATION: + return true; + default: + return false; + } } -bool ieee80211_set_hw_80211_encap(struct ieee80211_vif *vif, bool enable) +static bool ieee80211_set_sdata_offload_flags(struct ieee80211_sub_if_data *sdata) { - struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; - struct ieee80211_sub_if_data *iter; - struct ieee80211_key *key; + u32 flags; + + flags = sdata->vif.offload_flags; + + if (ieee80211_hw_check(&local->hw, SUPPORTS_TX_ENCAP_OFFLOAD) && + ieee80211_iftype_supports_encap_offload(sdata->vif.type)) { + flags |= IEEE80211_OFFLOAD_ENCAP_ENABLED; + + if (!ieee80211_hw_check(&local->hw, SUPPORTS_TX_FRAG) && + local->hw.wiphy->frag_threshold != (u32)-1) + flags &= ~IEEE80211_OFFLOAD_ENCAP_ENABLED; + + if (local->monitors) + flags &= ~IEEE80211_OFFLOAD_ENCAP_ENABLED; + } else { + flags &= ~IEEE80211_OFFLOAD_ENCAP_ENABLED; + } + + if (sdata->vif.offload_flags == flags) + return false; + + sdata->vif.offload_flags = flags; + return true; +} + +static void ieee80211_set_vif_encap_ops(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_sub_if_data *bss = sdata; + bool enabled; + + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { + if (!sdata->bss) + return; + + bss = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap); + } + + if (!ieee80211_hw_check(&local->hw, SUPPORTS_TX_ENCAP_OFFLOAD) || + !ieee80211_iftype_supports_encap_offload(bss->vif.type)) + return; + + enabled = bss->vif.offload_flags & IEEE80211_OFFLOAD_ENCAP_ENABLED; + if (sdata->wdev.use_4addr && + !(bss->vif.offload_flags & IEEE80211_OFFLOAD_ENCAP_4ADDR)) + enabled = false; + + sdata->dev->netdev_ops = enabled ? &ieee80211_dataif_8023_ops : + &ieee80211_dataif_ops; +} + +static void ieee80211_recalc_sdata_offload(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_sub_if_data *vsdata; + + if (ieee80211_set_sdata_offload_flags(sdata)) { + drv_update_vif_offload(local, sdata); + ieee80211_set_vif_encap_ops(sdata); + } + + list_for_each_entry(vsdata, &local->interfaces, list) { + if (vsdata->vif.type != NL80211_IFTYPE_AP_VLAN || + vsdata->bss != &sdata->u.ap) + continue; + + ieee80211_set_vif_encap_ops(vsdata); + } +} + +void ieee80211_recalc_offload(struct ieee80211_local *local) +{ + struct ieee80211_sub_if_data *sdata; + + if (!ieee80211_hw_check(&local->hw, SUPPORTS_TX_ENCAP_OFFLOAD)) + return; mutex_lock(&local->iflist_mtx); - list_for_each_entry(iter, &local->interfaces, list) { - struct ieee80211_sub_if_data *disable = NULL; - - if (vif->type == NL80211_IFTYPE_MONITOR) { - disable = iter; - __ieee80211_set_hw_80211_encap(iter, false); - } else if (iter->vif.type == NL80211_IFTYPE_MONITOR) { - disable = sdata; - enable = false; - } - if (disable) - sdata_dbg(disable, - "disable hw 80211 encap due to mon co-exist\n"); + + list_for_each_entry(sdata, &local->interfaces, list) { + if (!ieee80211_sdata_running(sdata)) + continue; + + ieee80211_recalc_sdata_offload(sdata); } + mutex_unlock(&local->iflist_mtx); +} - if (enable == sdata->hw_80211_encap) - return enable; +void ieee80211_adjust_monitor_flags(struct ieee80211_sub_if_data *sdata, + const int offset) +{ + struct ieee80211_local *local = sdata->local; + u32 flags = sdata->u.mntr.flags; - if (!sdata->dev) - return false; +#define ADJUST(_f, _s) do { \ + if (flags & MONITOR_FLAG_##_f) \ + local->fif_##_s += offset; \ + } while (0) + + ADJUST(FCSFAIL, fcsfail); + ADJUST(PLCPFAIL, plcpfail); + ADJUST(CONTROL, control); + ADJUST(CONTROL, pspoll); + ADJUST(OTHER_BSS, other_bss); + +#undef ADJUST +} + +static void ieee80211_set_default_queues(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + int i; + + for (i = 0; i < IEEE80211_NUM_ACS; i++) { + if (ieee80211_hw_check(&local->hw, QUEUE_CONTROL)) + sdata->vif.hw_queue[i] = IEEE80211_INVAL_HW_QUEUE; + else if (local->hw.queues >= IEEE80211_NUM_ACS) + sdata->vif.hw_queue[i] = i; + else + sdata->vif.hw_queue[i] = 0; + } + sdata->vif.cab_queue = IEEE80211_INVAL_HW_QUEUE; +} + +int ieee80211_add_virtual_monitor(struct ieee80211_local *local) +{ + struct ieee80211_sub_if_data *sdata; + int ret; + + if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) + return 0; + + ASSERT_RTNL(); + + if (local->monitor_sdata) + return 0; + + sdata = kzalloc(sizeof(*sdata) + local->hw.vif_data_size, GFP_KERNEL); + if (!sdata) + return -ENOMEM; + + /* set up data */ + sdata->local = local; + sdata->vif.type = NL80211_IFTYPE_MONITOR; + snprintf(sdata->name, IFNAMSIZ, "%s-monitor", + wiphy_name(local->hw.wiphy)); + sdata->wdev.iftype = NL80211_IFTYPE_MONITOR; + + sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM; + + ieee80211_set_default_queues(sdata); + + ret = drv_add_interface(local, sdata); + if (WARN_ON(ret)) { + /* ok .. stupid driver, it asked for this! */ + kfree(sdata); + return ret; + } + + ret = ieee80211_check_queues(sdata, NL80211_IFTYPE_MONITOR); + if (ret) { + kfree(sdata); + return ret; + } + + mutex_lock(&local->iflist_mtx); + rcu_assign_pointer(local->monitor_sdata, sdata); + mutex_unlock(&local->iflist_mtx); + + mutex_lock(&local->mtx); + ret = ieee80211_vif_use_channel(sdata, &local->monitor_chandef, + IEEE80211_CHANCTX_EXCLUSIVE); + mutex_unlock(&local->mtx); + if (ret) { + mutex_lock(&local->iflist_mtx); + RCU_INIT_POINTER(local->monitor_sdata, NULL); + mutex_unlock(&local->iflist_mtx); + synchronize_net(); + drv_remove_interface(local, sdata); + kfree(sdata); + return ret; + } - if (!ieee80211_hw_check(&local->hw, SUPPORTS_TX_FRAG) && - (local->hw.wiphy->frag_threshold != (u32)-1)) - enable = false; + skb_queue_head_init(&sdata->skb_queue); + INIT_WORK(&sdata->work, ieee80211_iface_work); + + return 0; +} - mutex_lock(&sdata->local->key_mtx); - list_for_each_entry(key, &sdata->key_list, list) { - if (key->conf.cipher == WLAN_CIPHER_SUITE_TKIP) - enable = false; +void ieee80211_del_virtual_monitor(struct ieee80211_local *local) +{ + struct ieee80211_sub_if_data *sdata; + + if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) + return; + + ASSERT_RTNL(); + + mutex_lock(&local->iflist_mtx); + + sdata = rcu_dereference_protected(local->monitor_sdata, + lockdep_is_held(&local->iflist_mtx)); + if (!sdata) { + mutex_unlock(&local->iflist_mtx); + return; } - mutex_unlock(&sdata->local->key_mtx); - __ieee80211_set_hw_80211_encap(sdata, enable); + RCU_INIT_POINTER(local->monitor_sdata, NULL); + mutex_unlock(&local->iflist_mtx); + + synchronize_net(); - return enable; + mutex_lock(&local->mtx); + ieee80211_vif_release_channel(sdata); + mutex_unlock(&local->mtx); + + drv_remove_interface(local, sdata); + + kfree(sdata); +} + +/* + * NOTE: Be very careful when changing this function, it must NOT return + * an error on interface type changes that have been pre-checked, so most + * checks should be in ieee80211_check_concurrent_iface. + */ +int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); + struct net_device *dev = wdev->netdev; + struct ieee80211_local *local = sdata->local; + struct sta_info *sta; + u32 changed = 0; + int res; + u32 hw_reconf_flags = 0; + + switch (sdata->vif.type) { + case NL80211_IFTYPE_WDS: + if (!is_valid_ether_addr(sdata->u.wds.remote_addr)) + return -ENOLINK; + break; + case NL80211_IFTYPE_AP_VLAN: { + struct ieee80211_sub_if_data *master; + + if (!sdata->bss) + return -ENOLINK; + + mutex_lock(&local->mtx); + list_add(&sdata->u.vlan.list, &sdata->bss->vlans); + mutex_unlock(&local->mtx); + + master = container_of(sdata->bss, + struct ieee80211_sub_if_data, u.ap); + sdata->control_port_protocol = + master->control_port_protocol; + sdata->control_port_no_encrypt = + master->control_port_no_encrypt; + sdata->control_port_over_nl80211 = + master->control_port_over_nl80211; + sdata->control_port_no_preauth = + master->control_port_no_preauth; + sdata->vif.cab_queue = master->vif.cab_queue; + memcpy(sdata->vif.hw_queue, master->vif.hw_queue, + sizeof(sdata->vif.hw_queue)); + sdata->vif.bss_conf.chandef = master->vif.bss_conf.chandef; + + mutex_lock(&local->key_mtx); + sdata->crypto_tx_tailroom_needed_cnt += + master->crypto_tx_tailroom_needed_cnt; + mutex_unlock(&local->key_mtx); + + break; + } + case NL80211_IFTYPE_AP: + sdata->bss = &sdata->u.ap; + break; + case NL80211_IFTYPE_MESH_POINT: + case NL80211_IFTYPE_STATION: + case NL80211_IFTYPE_MONITOR: + case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_P2P_DEVICE: + case NL80211_IFTYPE_OCB: + case NL80211_IFTYPE_NAN: + /* no special treatment */ + break; + case NL80211_IFTYPE_UNSPECIFIED: + case NUM_NL80211_IFTYPES: + case NL80211_IFTYPE_P2P_CLIENT: + case NL80211_IFTYPE_P2P_GO: + /* cannot happen */ + WARN_ON(1); + break; + } + + if (local->open_count == 0) { + res = drv_start(local); + if (res) + goto err_del_bss; + /* we're brought up, everything changes */ + hw_reconf_flags = ~0; + ieee80211_led_radio(local, true); + ieee80211_mod_tpt_led_trig(local, + IEEE80211_TPT_LEDTRIG_FL_RADIO, 0); + } + + /* + * Copy the hopefully now-present MAC address to + * this interface, if it has the special null one. + */ + if (dev && is_zero_ether_addr(dev->dev_addr)) { + memcpy(dev->dev_addr, + local->hw.wiphy->perm_addr, + ETH_ALEN); + memcpy(dev->perm_addr, dev->dev_addr, ETH_ALEN); + + if (!is_valid_ether_addr(dev->dev_addr)) { + res = -EADDRNOTAVAIL; + goto err_stop; + } + } + + switch (sdata->vif.type) { + case NL80211_IFTYPE_AP_VLAN: + /* no need to tell driver, but set carrier and chanctx */ + if (rtnl_dereference(sdata->bss->beacon)) { + ieee80211_vif_vlan_copy_chanctx(sdata); + netif_carrier_on(dev); + ieee80211_set_vif_encap_ops(sdata); + } else { + netif_carrier_off(dev); + } + break; + case NL80211_IFTYPE_MONITOR: + if (sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES) { + local->cooked_mntrs++; + break; + } + + if (sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE) { + res = drv_add_interface(local, sdata); + if (res) + goto err_stop; + } else if (local->monitors == 0 && local->open_count == 0) { + res = ieee80211_add_virtual_monitor(local); + if (res) + goto err_stop; + } + + /* must be before the call to ieee80211_configure_filter */ + local->monitors++; + if (local->monitors == 1) { + local->hw.conf.flags |= IEEE80211_CONF_MONITOR; + hw_reconf_flags |= IEEE80211_CONF_CHANGE_MONITOR; + } + + ieee80211_adjust_monitor_flags(sdata, 1); + ieee80211_configure_filter(local); + ieee80211_recalc_offload(local); + mutex_lock(&local->mtx); + ieee80211_recalc_idle(local); + mutex_unlock(&local->mtx); + + netif_carrier_on(dev); + break; + default: + if (coming_up) { + ieee80211_del_virtual_monitor(local); + ieee80211_set_sdata_offload_flags(sdata); + + res = drv_add_interface(local, sdata); + if (res) + goto err_stop; + + ieee80211_set_vif_encap_ops(sdata); + res = ieee80211_check_queues(sdata, + ieee80211_vif_type_p2p(&sdata->vif)); + if (res) + goto err_del_interface; + } + + if (sdata->vif.type == NL80211_IFTYPE_AP) { + local->fif_pspoll++; + local->fif_probe_req++; + + ieee80211_configure_filter(local); + } else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { + local->fif_probe_req++; + } + + if (sdata->vif.probe_req_reg) + drv_config_iface_filter(local, sdata, + FIF_PROBE_REQ, + FIF_PROBE_REQ); + + if (sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE && + sdata->vif.type != NL80211_IFTYPE_NAN) + changed |= ieee80211_reset_erp_info(sdata); + ieee80211_bss_info_change_notify(sdata, changed); + + switch (sdata->vif.type) { + case NL80211_IFTYPE_STATION: + case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_MESH_POINT: + case NL80211_IFTYPE_OCB: + netif_carrier_off(dev); + break; + case NL80211_IFTYPE_WDS: + case NL80211_IFTYPE_P2P_DEVICE: + case NL80211_IFTYPE_NAN: + break; + default: + /* not reached */ + WARN_ON(1); + } + + /* + * Set default queue parameters so drivers don't + * need to initialise the hardware if the hardware + * doesn't start up with sane defaults. + * Enable QoS for anything but station interfaces. + */ + ieee80211_set_wmm_default(sdata, true, + sdata->vif.type != NL80211_IFTYPE_STATION); + } + + set_bit(SDATA_STATE_RUNNING, &sdata->state); + + switch (sdata->vif.type) { + case NL80211_IFTYPE_WDS: + /* Create STA entry for the WDS peer */ + sta = sta_info_alloc(sdata, sdata->u.wds.remote_addr, + GFP_KERNEL); + if (!sta) { + res = -ENOMEM; + goto err_del_interface; + } + + sta_info_pre_move_state(sta, IEEE80211_STA_AUTH); + sta_info_pre_move_state(sta, IEEE80211_STA_ASSOC); + sta_info_pre_move_state(sta, IEEE80211_STA_AUTHORIZED); + + res = sta_info_insert(sta); + if (res) { + /* STA has been freed */ + goto err_del_interface; + } + + rate_control_rate_init(sta); + netif_carrier_on(dev); + break; + case NL80211_IFTYPE_P2P_DEVICE: + rcu_assign_pointer(local->p2p_sdata, sdata); + break; + case NL80211_IFTYPE_MONITOR: + if (sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES) + break; + list_add_tail_rcu(&sdata->u.mntr.list, &local->mon_list); + break; + default: + break; + } + + /* + * set_multicast_list will be invoked by the networking core + * which will check whether any increments here were done in + * error and sync them down to the hardware as filter flags. + */ + if (sdata->flags & IEEE80211_SDATA_ALLMULTI) + atomic_inc(&local->iff_allmultis); + + if (coming_up) + local->open_count++; + + if (hw_reconf_flags) + ieee80211_hw_config(local, hw_reconf_flags); + + ieee80211_recalc_ps(local); + + if (sdata->vif.type == NL80211_IFTYPE_MONITOR || + sdata->vif.type == NL80211_IFTYPE_AP_VLAN || + local->ops->wake_tx_queue) { + /* XXX: for AP_VLAN, actually track AP queues */ + if (dev) + netif_tx_start_all_queues(dev); + } else if (dev) { + unsigned long flags; + int n_acs = IEEE80211_NUM_ACS; + int ac; + + if (local->hw.queues < IEEE80211_NUM_ACS) + n_acs = 1; + + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); + if (sdata->vif.cab_queue == IEEE80211_INVAL_HW_QUEUE || + (local->queue_stop_reasons[sdata->vif.cab_queue] == 0 && + skb_queue_empty(&local->pending[sdata->vif.cab_queue]))) { + for (ac = 0; ac < n_acs; ac++) { + int ac_queue = sdata->vif.hw_queue[ac]; + + if (local->queue_stop_reasons[ac_queue] == 0 && + skb_queue_empty(&local->pending[ac_queue])) + netif_start_subqueue(dev, ac); + } + } + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + } + + return 0; + err_del_interface: + drv_remove_interface(local, sdata); + err_stop: + if (!local->open_count) + drv_stop(local); + err_del_bss: + sdata->bss = NULL; + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { + mutex_lock(&local->mtx); + list_del(&sdata->u.vlan.list); + mutex_unlock(&local->mtx); + } + /* might already be clear but that doesn't matter */ + clear_bit(SDATA_STATE_RUNNING, &sdata->state); + return res; } -EXPORT_SYMBOL(ieee80211_set_hw_80211_encap); static void ieee80211_if_free(struct net_device *dev) { @@ -1379,6 +1412,11 @@ static void ieee80211_iface_work(struct work_struct *work) WARN_ON(1); break; } + } else if (ieee80211_is_ext(mgmt->frame_control)) { + if (sdata->vif.type == NL80211_IFTYPE_STATION) + ieee80211_sta_rx_queued_ext(sdata, skb); + else + WARN_ON(1); } else if (ieee80211_is_data_qos(mgmt->frame_control)) { struct ieee80211_hdr *hdr = (void *)mgmt; /* @@ -1484,7 +1522,6 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, sdata->vif.bss_conf.txpower = INT_MIN; /* unset */ sdata->noack_map = 0; - sdata->hw_80211_encap = false; /* only monitor/p2p-device differ */ if (sdata->dev) { @@ -1619,6 +1656,7 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata, ieee80211_teardown_sdata(sdata); + ieee80211_set_sdata_offload_flags(sdata); ret = drv_change_interface(local, sdata, internal_type, p2p); if (ret) type = ieee80211_vif_type_p2p(&sdata->vif); @@ -1631,6 +1669,7 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata, ieee80211_check_queues(sdata, type); ieee80211_setup_sdata(sdata, type); + ieee80211_set_vif_encap_ops(sdata); err = ieee80211_do_open(&sdata->wdev, false); WARN(err, "type change: do_open returned %d", err); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 2df636c32432..8c5f829ff6d7 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -177,13 +177,6 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) } } - /* TKIP countermeasures don't work in encap offload mode */ - if (key->conf.cipher == WLAN_CIPHER_SUITE_TKIP && - sdata->hw_80211_encap) { - sdata_dbg(sdata, "TKIP is not allowed in hw 80211 encap mode\n"); - return -EINVAL; - } - ret = drv_set_key(key->local, SET_KEY, sdata, sta ? &sta->sta : NULL, &key->conf); @@ -219,14 +212,6 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) case WLAN_CIPHER_SUITE_CCMP_256: case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: - /* We cannot do software crypto of data frames with - * encapsulation offload enabled. However for 802.11w to - * function properly we need cmac/gmac keys. - */ - if (sdata->hw_80211_encap) - return -EINVAL; - fallthrough; - case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: case WLAN_CIPHER_SUITE_BIP_GMAC_128: diff --git a/net/mac80211/main.c b/net/mac80211/main.c index b4a2efe8e83a..523380aed92e 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1168,7 +1168,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT; } - local->hw.wiphy->max_num_csa_counters = IEEE80211_MAX_CSA_COUNTERS_NUM; + local->hw.wiphy->max_num_csa_counters = IEEE80211_MAX_CNTDWN_COUNTERS_NUM; /* * We use the number of queues for feature tests (QoS, HT) internally diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 7ecd801a943b..ce5825d6f1d1 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -672,7 +672,7 @@ void ieee80211_mesh_root_setup(struct ieee80211_if_mesh *ifmsh) * @hdr: 802.11 frame header * @fc: frame control field * @meshda: destination address in the mesh - * @meshsa: source address address in the mesh. Same as TA, as frame is + * @meshsa: source address in the mesh. Same as TA, as frame is * locally originated. * * Return the length of the 802.11 (does not include a mesh control header) @@ -864,8 +864,8 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) *pos++ = 0x0; *pos++ = ieee80211_frequency_to_channel( csa->settings.chandef.chan->center_freq); - bcn->csa_current_counter = csa->settings.count; - bcn->csa_counter_offsets[0] = hdr_len + 6; + bcn->cntdwn_current_counter = csa->settings.count; + bcn->cntdwn_counter_offsets[0] = hdr_len + 6; *pos++ = csa->settings.count; *pos++ = WLAN_EID_CHAN_SWITCH_PARAM; *pos++ = 6; diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index bec23d2eee7a..313eee12410e 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -212,7 +212,7 @@ static void prepare_frame_for_deferred_tx(struct ieee80211_sub_if_data *sdata, skb->priority = 7; info->control.vif = &sdata->vif; - info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; + info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING; ieee80211_set_qos_hdr(sdata, skb); ieee80211_mps_set_frame_flags(sdata, NULL, hdr); } @@ -1163,7 +1163,7 @@ int mesh_nexthop_resolve(struct ieee80211_sub_if_data *sdata, if (skb_queue_len(&mpath->frame_queue) >= MESH_FRAME_QUEUE_LEN) skb_to_free = skb_dequeue(&mpath->frame_queue); - info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; + info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING; ieee80211_set_qos_hdr(sdata, skb); skb_queue_tail(&mpath->frame_queue, skb); if (skb_to_free) diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index 15f2fc658f70..aca26df7587d 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -144,6 +144,7 @@ out: /** * mesh_set_ht_prot_mode - set correct HT protection mode + * @sdata: the (mesh) interface to handle * * Section 9.23.3.5 of IEEE 80211-2012 describes the protection rules for HT * mesh STA in a MBSS. Three HT protection modes are supported for now, non-HT diff --git a/net/mac80211/mesh_ps.c b/net/mac80211/mesh_ps.c index 031e905f684a..204830a55240 100644 --- a/net/mac80211/mesh_ps.c +++ b/net/mac80211/mesh_ps.c @@ -12,6 +12,7 @@ /** * mps_qos_null_get - create pre-addressed QoS Null frame for mesh powersave + * @sta: the station to get the frame for */ static struct sk_buff *mps_qos_null_get(struct sta_info *sta) { @@ -44,6 +45,7 @@ static struct sk_buff *mps_qos_null_get(struct sta_info *sta) /** * mps_qos_null_tx - send a QoS Null to indicate link-specific power mode + * @sta: the station to send to */ static void mps_qos_null_tx(struct sta_info *sta) { @@ -400,6 +402,8 @@ static void mpsp_trigger_send(struct sta_info *sta, bool rspi, bool eosp) /** * mpsp_qos_null_append - append QoS Null frame to MPSP skb queue if needed + * @sta: the station to handle + * @frames: the frame list to append to * * To properly end a mesh MPSP the last transmitted frame has to set the EOSP * flag in the QoS Control field. In case the current tailing frame is not a @@ -432,7 +436,7 @@ static void mpsp_qos_null_append(struct sta_info *sta, info = IEEE80211_SKB_CB(new_skb); info->control.vif = &sdata->vif; - info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; + info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING; __skb_queue_tail(frames, new_skb); } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 2e400b0ff696..6adfcb9c06dc 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -149,6 +149,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, const struct ieee80211_ht_operation *ht_oper, const struct ieee80211_vht_operation *vht_oper, const struct ieee80211_he_operation *he_oper, + const struct ieee80211_s1g_oper_ie *s1g_oper, struct cfg80211_chan_def *chandef, bool tracking) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; @@ -171,6 +172,18 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, ret = 0; vht_chandef = *chandef; goto out; + } else if (sband->band == NL80211_BAND_S1GHZ) { + if (!ieee80211_chandef_s1g_oper(s1g_oper, chandef)) { + sdata_info(sdata, + "Missing S1G Operation Element? Trying operating == primary\n"); + chandef->width = ieee80211_s1g_channel_width(channel); + } + + ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_40MHZ | + IEEE80211_STA_DISABLE_VHT | + IEEE80211_STA_DISABLE_80P80MHZ | + IEEE80211_STA_DISABLE_160MHZ; + goto out; } memcpy(&sta_ht_cap, &sband->ht_cap, sizeof(sta_ht_cap)); @@ -347,6 +360,7 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, const struct ieee80211_ht_operation *ht_oper, const struct ieee80211_vht_operation *vht_oper, const struct ieee80211_he_operation *he_oper, + const struct ieee80211_s1g_oper_ie *s1g_oper, const u8 *bssid, u32 *changed) { struct ieee80211_local *local = sdata->local; @@ -393,7 +407,7 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, /* calculate new channel (type) based on HT/VHT/HE operation IEs */ flags = ieee80211_determine_chantype(sdata, sband, chan, vht_cap_info, ht_oper, vht_oper, he_oper, - &chandef, true); + s1g_oper, &chandef, true); /* * Downgrade the new channel if we associated with restricted @@ -696,6 +710,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) struct ieee80211_chanctx_conf *chanctx_conf; struct ieee80211_channel *chan; u32 rates = 0; + __le16 listen_int; struct element *ext_capa = NULL; /* we know it's writable, cast away the const */ @@ -784,13 +799,15 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); memcpy(mgmt->bssid, assoc_data->bss->bssid, ETH_ALEN); + listen_int = cpu_to_le16(sband->band == NL80211_BAND_S1GHZ ? + ieee80211_encode_usf(local->hw.conf.listen_interval) : + local->hw.conf.listen_interval); if (!is_zero_ether_addr(assoc_data->prev_bssid)) { skb_put(skb, 10); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_REASSOC_REQ); mgmt->u.reassoc_req.capab_info = cpu_to_le16(capab); - mgmt->u.reassoc_req.listen_interval = - cpu_to_le16(local->hw.conf.listen_interval); + mgmt->u.reassoc_req.listen_interval = listen_int; memcpy(mgmt->u.reassoc_req.current_ap, assoc_data->prev_bssid, ETH_ALEN); } else { @@ -798,8 +815,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ASSOC_REQ); mgmt->u.assoc_req.capab_info = cpu_to_le16(capab); - mgmt->u.assoc_req.listen_interval = - cpu_to_le16(local->hw.conf.listen_interval); + mgmt->u.assoc_req.listen_interval = listen_int; } /* SSID */ @@ -809,6 +825,9 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) *pos++ = assoc_data->ssid_len; memcpy(pos, assoc_data->ssid, assoc_data->ssid_len); + if (sband->band == NL80211_BAND_S1GHZ) + goto skip_rates; + /* add all rates which were marked to be used above */ supp_rates_len = rates_len; if (supp_rates_len > 8) @@ -844,6 +863,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) } } +skip_rates: if (capab & WLAN_CAPABILITY_SPECTRUM_MGMT || capab & WLAN_CAPABILITY_RADIO_MEASURE) { pos = skb_put(skb, 4); @@ -1018,6 +1038,11 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) pos = ieee80211_add_wmm_info_ie(skb_put(skb, 9), qos_info); } + if (sband->band == NL80211_BAND_S1GHZ) { + ieee80211_add_aid_request_ie(sdata, skb); + ieee80211_add_s1g_capab_ie(sdata, &sband->s1g_cap, skb); + } + /* add any remaining custom (i.e. vendor specific here) IEs */ if (assoc_data->ie_len) { noffset = assoc_data->ie_len; @@ -1597,6 +1622,9 @@ static u32 ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata, int new_ap_level; __le16 capab = mgmt->u.probe_resp.capab_info; + if (ieee80211_is_s1g_beacon(mgmt->frame_control)) + return 0; /* TODO */ + if (country_ie && (capab & cpu_to_le16(WLAN_CAPABILITY_SPECTRUM_MGMT) || capab & cpu_to_le16(WLAN_CAPABILITY_RADIO_MEASURE))) { @@ -2432,23 +2460,6 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM; } -void ieee80211_sta_rx_notify(struct ieee80211_sub_if_data *sdata, - struct ieee80211_hdr *hdr) -{ - /* - * We can postpone the mgd.timer whenever receiving unicast frames - * from AP because we know that the connection is working both ways - * at that time. But multicast frames (and hence also beacons) must - * be ignored here, because we need to trigger the timer during - * data idle periods for sending the periodic probe request to the - * AP we're connected to. - */ - if (is_multicast_ether_addr(hdr->addr1)) - return; - - ieee80211_sta_reset_conn_monitor(sdata); -} - static void ieee80211_reset_ap_probe(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; @@ -2521,21 +2532,15 @@ void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata, { ieee80211_sta_tx_wmm_ac_notify(sdata, hdr, tx_time); - if (!ieee80211_is_data(hdr->frame_control)) - return; - - if (ieee80211_is_any_nullfunc(hdr->frame_control) && - sdata->u.mgd.probe_send_count > 0) { - if (ack) - ieee80211_sta_reset_conn_monitor(sdata); - else - sdata->u.mgd.nullfunc_failed = true; - ieee80211_queue_work(&sdata->local->hw, &sdata->work); + if (!ieee80211_is_any_nullfunc(hdr->frame_control) || + !sdata->u.mgd.probe_send_count) return; - } if (ack) - ieee80211_sta_reset_conn_monitor(sdata); + sdata->u.mgd.probe_send_count = 0; + else + sdata->u.mgd.nullfunc_failed = true; + ieee80211_queue_work(&sdata->local->hw, &sdata->work); } static void ieee80211_mlme_send_probe_req(struct ieee80211_sub_if_data *sdata, @@ -3267,14 +3272,26 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, const struct cfg80211_bss_ies *bss_ies = NULL; struct ieee80211_mgd_assoc_data *assoc_data = ifmgd->assoc_data; bool is_6ghz = cbss->channel->band == NL80211_BAND_6GHZ; + bool is_s1g = cbss->channel->band == NL80211_BAND_S1GHZ; u32 changed = 0; + u8 *pos; int err; bool ret; /* AssocResp and ReassocResp have identical structure */ + pos = mgmt->u.assoc_resp.variable; aid = le16_to_cpu(mgmt->u.assoc_resp.aid); + if (is_s1g) { + pos = (u8 *) mgmt->u.s1g_assoc_resp.variable; + aid = 0; /* TODO */ + } capab_info = le16_to_cpu(mgmt->u.assoc_resp.capab_info); + ieee802_11_parse_elems(pos, len - (pos - (u8 *)mgmt), false, elems, + mgmt->bssid, assoc_data->bss->bssid); + + if (elems->aid_resp) + aid = le16_to_cpu(elems->aid_resp->aid); /* * The 5 MSB of the AID field are reserved @@ -3291,7 +3308,7 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, ifmgd->broken_ap = true; } - if (!elems->supp_rates) { + if (!is_s1g && !elems->supp_rates) { sdata_info(sdata, "no SuppRates element in AssocResp\n"); return false; } @@ -3533,7 +3550,8 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, sta->sta.mfp = false; } - sta->sta.wme = elems->wmm_param && local->hw.queues >= IEEE80211_NUM_ACS; + sta->sta.wme = (elems->wmm_param || elems->s1g_capab) && + local->hw.queues >= IEEE80211_NUM_ACS; err = sta_info_move_state(sta, IEEE80211_STA_ASSOC); if (!err && !(ifmgd->flags & IEEE80211_STA_CONTROL_PORT)) @@ -3548,6 +3566,9 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, goto out; } + if (sdata->wdev.use_4addr) + drv_sta_set_4addr(local, sdata, &sta->sta, true); + mutex_unlock(&sdata->local->sta_mtx); /* @@ -3605,8 +3626,8 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, * Start timer to probe the connection to the AP now. * Also start the timer that will detect beacon loss. */ - ieee80211_sta_rx_notify(sdata, (struct ieee80211_hdr *)mgmt); ieee80211_sta_reset_beacon_monitor(sdata); + ieee80211_sta_reset_conn_monitor(sdata); ret = true; out: @@ -3625,7 +3646,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, int ac, uapsd_queues = -1; u8 *pos; bool reassoc; - struct cfg80211_bss *bss; + struct cfg80211_bss *cbss; struct ieee80211_event event = { .type = MLME_EVENT, .u.mlme.data = ASSOC_EVENT, @@ -3635,9 +3656,12 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, if (!assoc_data) return; + if (!ether_addr_equal(assoc_data->bss->bssid, mgmt->bssid)) return; + cbss = assoc_data->bss; + /* * AssocResp and ReassocResp have identical structure, so process both * of them in this function. @@ -3649,7 +3673,12 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, reassoc = ieee80211_is_reassoc_resp(mgmt->frame_control); capab_info = le16_to_cpu(mgmt->u.assoc_resp.capab_info); status_code = le16_to_cpu(mgmt->u.assoc_resp.status_code); + pos = mgmt->u.assoc_resp.variable; aid = le16_to_cpu(mgmt->u.assoc_resp.aid); + if (cbss->channel->band == NL80211_BAND_S1GHZ) { + pos = (u8 *) mgmt->u.s1g_assoc_resp.variable; + aid = 0; /* TODO */ + } sdata_info(sdata, "RX %sssocResp from %pM (capab=0x%x status=%d aid=%d)\n", @@ -3660,7 +3689,6 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, fils_decrypt_assoc_resp(sdata, (u8 *)mgmt, &len, assoc_data) < 0) return; - pos = mgmt->u.assoc_resp.variable; ieee802_11_parse_elems(pos, len - (pos - (u8 *)mgmt), false, &elems, mgmt->bssid, assoc_data->bss->bssid); @@ -3680,8 +3708,6 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, return; } - bss = assoc_data->bss; - if (status_code != WLAN_STATUS_SUCCESS) { sdata_info(sdata, "%pM denied association (code=%d)\n", mgmt->sa, status_code); @@ -3690,10 +3716,10 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, event.u.mlme.reason = status_code; drv_event_callback(sdata->local, sdata, &event); } else { - if (!ieee80211_assoc_success(sdata, bss, mgmt, len, &elems)) { + if (!ieee80211_assoc_success(sdata, cbss, mgmt, len, &elems)) { /* oops -- internal error -- send timeout for now */ ieee80211_destroy_assoc_data(sdata, false, false); - cfg80211_assoc_timeout(sdata->dev, bss); + cfg80211_assoc_timeout(sdata->dev, cbss); return; } event.u.mlme.status = MLME_SUCCESS; @@ -3714,7 +3740,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, uapsd_queues |= ieee80211_ac_to_qos_mask[ac]; } - cfg80211_rx_assoc_resp(sdata->dev, bss, (u8 *)mgmt, len, uapsd_queues, + cfg80211_rx_assoc_resp(sdata->dev, cbss, (u8 *)mgmt, len, uapsd_queues, ifmgd->assoc_req_ies, ifmgd->assoc_req_ies_len); } @@ -3913,11 +3939,12 @@ static bool ieee80211_rx_our_beacon(const u8 *tx_bssid, } static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, - struct ieee80211_mgmt *mgmt, size_t len, + struct ieee80211_hdr *hdr, size_t len, struct ieee80211_rx_status *rx_status) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf; + struct ieee80211_mgmt *mgmt = (void *) hdr; size_t baselen; struct ieee802_11_elems elems; struct ieee80211_local *local = sdata->local; @@ -3927,14 +3954,24 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, u32 changed = 0; bool erp_valid; u8 erp_value = 0; - u32 ncrc; - u8 *bssid; + u32 ncrc = 0; + u8 *bssid, *variable = mgmt->u.beacon.variable; u8 deauth_buf[IEEE80211_DEAUTH_FRAME_LEN]; sdata_assert_lock(sdata); /* Process beacon from the current BSS */ - baselen = (u8 *) mgmt->u.beacon.variable - (u8 *) mgmt; + bssid = ieee80211_get_bssid(hdr, len, sdata->vif.type); + if (ieee80211_is_s1g_beacon(mgmt->frame_control)) { + struct ieee80211_ext *ext = (void *) mgmt; + + if (ieee80211_is_s1g_short_beacon(ext->frame_control)) + variable = ext->u.s1g_short_beacon.variable; + else + variable = ext->u.s1g_beacon.variable; + } + + baselen = (u8 *) variable - (u8 *) mgmt; if (baselen > len) return; @@ -3954,10 +3991,10 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, rcu_read_unlock(); if (ifmgd->assoc_data && ifmgd->assoc_data->need_beacon && - ieee80211_rx_our_beacon(mgmt->bssid, ifmgd->assoc_data->bss)) { - ieee802_11_parse_elems(mgmt->u.beacon.variable, + ieee80211_rx_our_beacon(bssid, ifmgd->assoc_data->bss)) { + ieee802_11_parse_elems(variable, len - baselen, false, &elems, - mgmt->bssid, + bssid, ifmgd->assoc_data->bss->bssid); ieee80211_rx_bss_info(sdata, mgmt, len, rx_status); @@ -3990,7 +4027,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, } if (!ifmgd->associated || - !ieee80211_rx_our_beacon(mgmt->bssid, ifmgd->associated)) + !ieee80211_rx_our_beacon(bssid, ifmgd->associated)) return; bssid = ifmgd->associated->bssid; @@ -4010,8 +4047,14 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, */ ieee80211_sta_reset_beacon_monitor(sdata); - ncrc = crc32_be(0, (void *)&mgmt->u.beacon.beacon_int, 4); - ncrc = ieee802_11_parse_elems_crc(mgmt->u.beacon.variable, + /* TODO: CRC urrently not calculated on S1G Beacon Compatibility + * element (which carries the beacon interval). Don't forget to add a + * bit to care_about_ies[] above if mac80211 is interested in a + * changing S1G element. + */ + if (!ieee80211_is_s1g_beacon(hdr->frame_control)) + ncrc = crc32_be(0, (void *)&mgmt->u.beacon.beacon_int, 4); + ncrc = ieee802_11_parse_elems_crc(variable, len - baselen, false, &elems, care_about_ies, ncrc, mgmt->bssid, bssid); @@ -4045,7 +4088,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, struct ieee80211_p2p_noa_attr noa = {}; int ret; - ret = cfg80211_get_p2p_attr(mgmt->u.beacon.variable, + ret = cfg80211_get_p2p_attr(variable, len - baselen, IEEE80211_P2P_ATTR_ABSENCE_NOTICE, (u8 *) &noa, sizeof(noa)); @@ -4081,7 +4124,8 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, * the driver will use them. The synchronized view is currently * guaranteed only in certain callbacks. */ - if (ieee80211_hw_check(&local->hw, TIMING_BEACON_ONLY)) { + if (ieee80211_hw_check(&local->hw, TIMING_BEACON_ONLY) && + !ieee80211_is_s1g_beacon(hdr->frame_control)) { sdata->vif.bss_conf.sync_tsf = le64_to_cpu(mgmt->u.beacon.timestamp); sdata->vif.bss_conf.sync_device_ts = @@ -4089,7 +4133,8 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, sdata->vif.bss_conf.sync_dtim_count = elems.dtim_count; } - if (ncrc == ifmgd->beacon_crc && ifmgd->beacon_crc_valid) + if ((ncrc == ifmgd->beacon_crc && ifmgd->beacon_crc_valid) || + ieee80211_is_s1g_short_beacon(mgmt->frame_control)) return; ifmgd->beacon_crc = ncrc; ifmgd->beacon_crc_valid = true; @@ -4130,9 +4175,11 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, } else { erp_valid = false; } - changed |= ieee80211_handle_bss_capability(sdata, - le16_to_cpu(mgmt->u.beacon.capab_info), - erp_valid, erp_value); + + if (!ieee80211_is_s1g_beacon(hdr->frame_control)) + changed |= ieee80211_handle_bss_capability(sdata, + le16_to_cpu(mgmt->u.beacon.capab_info), + erp_valid, erp_value); mutex_lock(&local->sta_mtx); sta = sta_info_get(sdata, bssid); @@ -4142,7 +4189,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, if (ieee80211_config_bw(sdata, sta, elems.ht_cap_elem, elems.vht_cap_elem, elems.ht_operation, elems.vht_operation, elems.he_operation, - bssid, &changed)) { + elems.s1g_oper, bssid, &changed)) { mutex_unlock(&local->sta_mtx); sdata_info(sdata, "failed to follow AP %pM bandwidth change, disconnect\n", @@ -4170,6 +4217,26 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, ieee80211_bss_info_change_notify(sdata, changed); } +void ieee80211_sta_rx_queued_ext(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb) +{ + struct ieee80211_rx_status *rx_status; + struct ieee80211_hdr *hdr; + u16 fc; + + rx_status = (struct ieee80211_rx_status *) skb->cb; + hdr = (struct ieee80211_hdr *) skb->data; + fc = le16_to_cpu(hdr->frame_control); + + sdata_lock(sdata); + switch (fc & IEEE80211_FCTL_STYPE) { + case IEEE80211_STYPE_S1G_BEACON: + ieee80211_rx_mgmt_beacon(sdata, hdr, skb->len, rx_status); + break; + } + sdata_unlock(sdata); +} + void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { @@ -4187,7 +4254,8 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, switch (fc & IEEE80211_FCTL_STYPE) { case IEEE80211_STYPE_BEACON: - ieee80211_rx_mgmt_beacon(sdata, mgmt, skb->len, rx_status); + ieee80211_rx_mgmt_beacon(sdata, (void *)mgmt, + skb->len, rx_status); break; case IEEE80211_STYPE_PROBE_RESP: ieee80211_rx_mgmt_probe_resp(sdata, skb); @@ -4577,10 +4645,26 @@ static void ieee80211_sta_conn_mon_timer(struct timer_list *t) from_timer(sdata, t, u.mgd.conn_mon_timer); struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; + struct sta_info *sta; + unsigned long timeout; if (sdata->vif.csa_active && !ifmgd->csa_waiting_bcn) return; + sta = sta_info_get(sdata, ifmgd->bssid); + if (!sta) + return; + + timeout = sta->status_stats.last_ack; + if (time_before(sta->status_stats.last_ack, sta->rx_stats.last_rx)) + timeout = sta->rx_stats.last_rx; + timeout += IEEE80211_CONNECTION_IDLE_TIME; + + if (time_is_before_jiffies(timeout)) { + mod_timer(&ifmgd->conn_mon_timer, round_jiffies_up(timeout)); + return; + } + ieee80211_queue_work(&local->hw, &ifmgd->monitor_work); } @@ -4858,6 +4942,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, const struct ieee80211_ht_operation *ht_oper = NULL; const struct ieee80211_vht_operation *vht_oper = NULL; const struct ieee80211_he_operation *he_oper = NULL; + const struct ieee80211_s1g_oper_ie *s1g_oper = NULL; struct ieee80211_supported_band *sband; struct cfg80211_chan_def chandef; bool is_6ghz = cbss->channel->band == NL80211_BAND_6GHZ; @@ -4961,10 +5046,23 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, if (!have_80mhz) ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; + if (sband->band == NL80211_BAND_S1GHZ) { + const u8 *s1g_oper_ie; + + s1g_oper_ie = ieee80211_bss_get_ie(cbss, + WLAN_EID_S1G_OPERATION); + if (s1g_oper_ie && s1g_oper_ie[1] >= sizeof(*s1g_oper)) + s1g_oper = (void *)(s1g_oper_ie + 2); + else + sdata_info(sdata, + "AP missing S1G operation element?\n"); + } + ifmgd->flags |= ieee80211_determine_chantype(sdata, sband, cbss->channel, bss->vht_cap_info, ht_oper, vht_oper, he_oper, + s1g_oper, &chandef, false); sdata->needed_rx_chains = min(ieee80211_ht_vht_rx_chains(sdata, cbss), @@ -5091,6 +5189,12 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, const struct cfg80211_bss_ies *ies; int shift = ieee80211_vif_get_shift(&sdata->vif); + /* TODO: S1G Basic Rate Set is expressed elsewhere */ + if (cbss->channel->band == NL80211_BAND_S1GHZ) { + ieee80211_s1g_sta_rate_init(new_sta); + goto skip_rates; + } + ieee80211_get_rates(sband, bss->supp_rates, bss->supp_rates_len, &rates, &basic_rates, @@ -5135,6 +5239,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, else sdata->flags &= ~IEEE80211_SDATA_OPERATING_GMODE; +skip_rates: memcpy(ifmgd->bssid, cbss->bssid, ETH_ALEN); /* set timing information */ @@ -5359,6 +5464,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, struct cfg80211_assoc_request *req) { bool is_6ghz = req->bss->channel->band == NL80211_BAND_6GHZ; + bool is_5ghz = req->bss->channel->band == NL80211_BAND_5GHZ; struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_bss *bss = (void *)req->bss->priv; @@ -5462,6 +5568,10 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, memcpy(&ifmgd->vht_capa_mask, &req->vht_capa_mask, sizeof(ifmgd->vht_capa_mask)); + memcpy(&ifmgd->s1g_capa, &req->s1g_capa, sizeof(ifmgd->s1g_capa)); + memcpy(&ifmgd->s1g_capa_mask, &req->s1g_capa_mask, + sizeof(ifmgd->s1g_capa_mask)); + if (req->ie && req->ie_len) { memcpy(assoc_data->ie, req->ie, req->ie_len); assoc_data->ie_len = req->ie_len; @@ -5507,7 +5617,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, if (vht_ie && vht_ie[1] >= sizeof(struct ieee80211_vht_cap)) memcpy(&assoc_data->ap_vht_cap, vht_ie + 2, sizeof(struct ieee80211_vht_cap)); - else if (!is_6ghz) + else if (is_5ghz) ifmgd->flags |= IEEE80211_STA_DISABLE_VHT | IEEE80211_STA_DISABLE_HE; rcu_read_unlock(); diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index f470d1a7ce9b..853c9a369d72 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -26,8 +26,7 @@ static void ieee80211_offchannel_ps_enable(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - - local->offchannel_ps_enabled = false; + bool offchannel_ps_enabled = false; /* FIXME: what to do when local->pspolling is true? */ @@ -38,12 +37,12 @@ static void ieee80211_offchannel_ps_enable(struct ieee80211_sub_if_data *sdata) cancel_work_sync(&local->dynamic_ps_enable_work); if (local->hw.conf.flags & IEEE80211_CONF_PS) { - local->offchannel_ps_enabled = true; + offchannel_ps_enabled = true; local->hw.conf.flags &= ~IEEE80211_CONF_PS; ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS); } - if (!local->offchannel_ps_enabled || + if (!offchannel_ps_enabled || !ieee80211_hw_check(&local->hw, PS_NULLFUNC_STACK)) /* * If power save was enabled, no need to send a nullfunc @@ -58,38 +57,19 @@ static void ieee80211_offchannel_ps_enable(struct ieee80211_sub_if_data *sdata) ieee80211_send_nullfunc(local, sdata, true); } -/* inform AP that we are awake again, unless power save is enabled */ +/* inform AP that we are awake again */ static void ieee80211_offchannel_ps_disable(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; if (!local->ps_sdata) ieee80211_send_nullfunc(local, sdata, false); - else if (local->offchannel_ps_enabled) { - /* - * In !IEEE80211_HW_PS_NULLFUNC_STACK case the hardware - * will send a nullfunc frame with the powersave bit set - * even though the AP already knows that we are sleeping. - * This could be avoided by sending a null frame with power - * save bit disabled before enabling the power save, but - * this doesn't gain anything. - * - * When IEEE80211_HW_PS_NULLFUNC_STACK is enabled, no need - * to send a nullfunc frame because AP already knows that - * we are sleeping, let's just enable power save mode in - * hardware. - */ - /* TODO: Only set hardware if CONF_PS changed? - * TODO: Should we set offchannel_ps_enabled to false? - */ - local->hw.conf.flags |= IEEE80211_CONF_PS; - ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS); - } else if (local->hw.conf.dynamic_ps_timeout > 0) { + else if (local->hw.conf.dynamic_ps_timeout > 0) { /* - * If IEEE80211_CONF_PS was not set and the dynamic_ps_timer - * had been running before leaving the operating channel, - * restart the timer now and send a nullfunc frame to inform - * the AP that we are awake. + * the dynamic_ps_timer had been running before leaving the + * operating channel, restart the timer now and send a nullfunc + * frame to inform the AP that we are awake so that AP sends + * the buffered packets (if any). */ ieee80211_send_nullfunc(local, sdata, false); mod_timer(&local->dynamic_ps_timer, jiffies + @@ -916,7 +896,7 @@ int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, if (beacon) for (i = 0; i < params->n_csa_offsets; i++) data[params->csa_offsets[i]] = - beacon->csa_current_counter; + beacon->cntdwn_current_counter; rcu_read_unlock(); } diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index b051f125d3af..45927202c71c 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -51,6 +51,13 @@ void rate_control_rate_init(struct sta_info *sta) sband = local->hw.wiphy->bands[chanctx_conf->def.chan->band]; + /* TODO: check for minstrel_s1g ? */ + if (sband->band == NL80211_BAND_S1GHZ) { + ieee80211_s1g_sta_rate_init(sta); + rcu_read_unlock(); + return; + } + spin_lock_bh(&sta->rate_ctrl_lock); ref->ops->rate_init(ref->priv, sband, &chanctx_conf->def, ista, priv_sta); @@ -266,10 +273,15 @@ void ieee80211_check_rate_mask(struct ieee80211_sub_if_data *sdata) if (WARN_ON(!sdata->vif.bss_conf.chandef.chan)) return; + band = sdata->vif.bss_conf.chandef.chan->band; + if (band == NL80211_BAND_S1GHZ) { + /* TODO */ + return; + } + if (WARN_ON_ONCE(!basic_rates)) return; - band = sdata->vif.bss_conf.chandef.chan->band; user_mask = sdata->rc_rateidx_mask[band]; sband = local->hw.wiphy->bands[band]; @@ -296,21 +308,29 @@ static bool rc_no_data_or_no_ack_use_min(struct ieee80211_tx_rate_control *txrc) !ieee80211_is_data(fc); } -static void rc_send_low_basicrate(s8 *idx, u32 basic_rates, +static void rc_send_low_basicrate(struct ieee80211_tx_rate *rate, + u32 basic_rates, struct ieee80211_supported_band *sband) { u8 i; + if (sband->band == NL80211_BAND_S1GHZ) { + /* TODO */ + rate->flags |= IEEE80211_TX_RC_S1G_MCS; + rate->idx = 0; + return; + } + if (basic_rates == 0) return; /* assume basic rates unknown and accept rate */ - if (*idx < 0) + if (rate->idx < 0) return; - if (basic_rates & (1 << *idx)) + if (basic_rates & (1 << rate->idx)) return; /* selected rate is a basic rate */ - for (i = *idx + 1; i <= sband->n_bitrates; i++) { + for (i = rate->idx + 1; i <= sband->n_bitrates; i++) { if (basic_rates & (1 << i)) { - *idx = i; + rate->idx = i; return; } } @@ -328,6 +348,12 @@ static void __rate_control_send_low(struct ieee80211_hw *hw, u32 rate_flags = ieee80211_chandef_rate_flags(&hw->conf.chandef); + if (sband->band == NL80211_BAND_S1GHZ) { + info->control.rates[0].flags |= IEEE80211_TX_RC_S1G_MCS; + info->control.rates[0].idx = 0; + return; + } + if ((sband->band == NL80211_BAND_2GHZ) && (info->flags & IEEE80211_TX_CTL_NO_CCK_RATE)) rate_flags |= IEEE80211_RATE_ERP_G; @@ -388,7 +414,7 @@ static bool rate_control_send_low(struct ieee80211_sta *pubsta, } if (use_basicrate) - rc_send_low_basicrate(&info->control.rates[0].idx, + rc_send_low_basicrate(&info->control.rates[0], txrc->bss_conf->basic_rates, sband); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index a959ebf56852..1e2e5a406d58 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -42,51 +42,6 @@ static inline void ieee80211_rx_stats(struct net_device *dev, u32 len) u64_stats_update_end(&tstats->syncp); } -static u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len, - enum nl80211_iftype type) -{ - __le16 fc = hdr->frame_control; - - if (ieee80211_is_data(fc)) { - if (len < 24) /* drop incorrect hdr len (data) */ - return NULL; - - if (ieee80211_has_a4(fc)) - return NULL; - if (ieee80211_has_tods(fc)) - return hdr->addr1; - if (ieee80211_has_fromds(fc)) - return hdr->addr2; - - return hdr->addr3; - } - - if (ieee80211_is_mgmt(fc)) { - if (len < 24) /* drop incorrect hdr len (mgmt) */ - return NULL; - return hdr->addr3; - } - - if (ieee80211_is_ctl(fc)) { - if (ieee80211_is_pspoll(fc)) - return hdr->addr1; - - if (ieee80211_is_back_req(fc)) { - switch (type) { - case NL80211_IFTYPE_STATION: - return hdr->addr2; - case NL80211_IFTYPE_AP: - case NL80211_IFTYPE_AP_VLAN: - return hdr->addr1; - default: - break; /* fall through to the return */ - } - } - } - - return NULL; -} - /* * monitor mode reception * @@ -1802,7 +1757,8 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) } } else if (rx->sdata->vif.type == NL80211_IFTYPE_OCB) { sta->rx_stats.last_rx = jiffies; - } else if (!is_multicast_ether_addr(hdr->addr1)) { + } else if (!ieee80211_is_s1g_beacon(hdr->frame_control) && + is_multicast_ether_addr(hdr->addr1)) { /* * Mesh beacons will update last_rx when if they are found to * match the current local configuration when processed. @@ -1812,9 +1768,6 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) sta->rx_stats.last_rate = sta_stats_encode_rate(status); } - if (rx->sdata->vif.type == NL80211_IFTYPE_STATION) - ieee80211_sta_rx_notify(rx->sdata, hdr); - sta->rx_stats.fragments++; u64_stats_update_begin(&rx->sta->rx_stats.syncp); @@ -1840,6 +1793,9 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) } } + if (ieee80211_is_s1g_beacon(hdr->frame_control)) + return RX_CONTINUE; + /* * Change STA power saving mode only at the end of a frame * exchange sequence, and only for a data or management @@ -1950,6 +1906,9 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) __le16 fc; const struct ieee80211_cipher_scheme *cs = NULL; + if (ieee80211_is_ext(hdr->frame_control)) + return RX_CONTINUE; + /* * Key selection 101 * @@ -2258,7 +2217,7 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) hdr = (struct ieee80211_hdr *)rx->skb->data; fc = hdr->frame_control; - if (ieee80211_is_ctl(fc)) + if (ieee80211_is_ctl(fc) || ieee80211_is_ext(fc)) return RX_CONTINUE; sc = le16_to_cpu(hdr->seq_ctrl); @@ -2900,7 +2859,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) fwd_hdr->frame_control &= ~cpu_to_le16(IEEE80211_FCTL_RETRY); info = IEEE80211_SKB_CB(fwd_skb); memset(info, 0, sizeof(*info)); - info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; + info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING; info->control.vif = &rx->sdata->vif; info->control.jiffies = jiffies; if (is_multicast_ether_addr(fwd_hdr->addr1)) { @@ -3132,6 +3091,9 @@ ieee80211_rx_h_mgmt_check(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); + if (ieee80211_is_s1g_beacon(mgmt->frame_control)) + return RX_CONTINUE; + /* * From here on, look only at management frames. * Data and control frames are already handled, @@ -3599,6 +3561,27 @@ ieee80211_rx_h_action_return(struct ieee80211_rx_data *rx) } static ieee80211_rx_result debug_noinline +ieee80211_rx_h_ext(struct ieee80211_rx_data *rx) +{ + struct ieee80211_sub_if_data *sdata = rx->sdata; + struct ieee80211_hdr *hdr = (void *)rx->skb->data; + + if (!ieee80211_is_ext(hdr->frame_control)) + return RX_CONTINUE; + + if (sdata->vif.type != NL80211_IFTYPE_STATION) + return RX_DROP_MONITOR; + + /* for now only beacons are ext, so queue them */ + skb_queue_tail(&sdata->skb_queue, rx->skb); + ieee80211_queue_work(&rx->local->hw, &sdata->work); + if (rx->sta) + rx->sta->rx_stats.packets++; + + return RX_QUEUED; +} + +static ieee80211_rx_result debug_noinline ieee80211_rx_h_mgmt(struct ieee80211_rx_data *rx) { struct ieee80211_sub_if_data *sdata = rx->sdata; @@ -3817,6 +3800,7 @@ static void ieee80211_rx_handlers(struct ieee80211_rx_data *rx, CALL_RXH(ieee80211_rx_h_userspace_mgmt); CALL_RXH(ieee80211_rx_h_action_post_userspace); CALL_RXH(ieee80211_rx_h_action_return); + CALL_RXH(ieee80211_rx_h_ext); CALL_RXH(ieee80211_rx_h_mgmt); rxh_next: @@ -3983,7 +3967,8 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) struct ieee80211_hdr *hdr = (void *)skb->data; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); u8 *bssid = ieee80211_get_bssid(hdr, skb->len, sdata->vif.type); - bool multicast = is_multicast_ether_addr(hdr->addr1); + bool multicast = is_multicast_ether_addr(hdr->addr1) || + ieee80211_is_s1g_beacon(hdr->frame_control); switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: @@ -4149,7 +4134,6 @@ void ieee80211_check_fast_rx(struct sta_info *sta) fastrx.sa_offs = offsetof(struct ieee80211_hdr, addr2); fastrx.expected_ds_bits = 0; } else { - fastrx.sta_notify = sdata->u.mgd.probe_send_count > 0; fastrx.da_offs = offsetof(struct ieee80211_hdr, addr1); fastrx.sa_offs = offsetof(struct ieee80211_hdr, addr3); fastrx.expected_ds_bits = @@ -4379,11 +4363,6 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, pskb_trim(skb, skb->len - fast_rx->icv_len)) goto drop; - if (unlikely(fast_rx->sta_notify)) { - ieee80211_sta_rx_notify(rx->sdata, hdr); - fast_rx->sta_notify = false; - } - /* statistics part of ieee80211_rx_h_sta_process() */ if (!(status->flag & RX_FLAG_NO_SIGNAL_VAL)) { stats->last_signal = status->signal; @@ -4587,7 +4566,8 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, ieee80211_verify_alignment(&rx); if (unlikely(ieee80211_is_probe_resp(hdr->frame_control) || - ieee80211_is_beacon(hdr->frame_control))) + ieee80211_is_beacon(hdr->frame_control) || + ieee80211_is_s1g_beacon(hdr->frame_control))) ieee80211_scan_rx(local, skb); if (ieee80211_is_data(fc)) { diff --git a/net/mac80211/s1g.c b/net/mac80211/s1g.c new file mode 100644 index 000000000000..c33f332b049a --- /dev/null +++ b/net/mac80211/s1g.c @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * S1G handling + * Copyright(c) 2020 Adapt-IP + */ +#include <linux/ieee80211.h> +#include <net/mac80211.h> +#include "ieee80211_i.h" + +void ieee80211_s1g_sta_rate_init(struct sta_info *sta) +{ + /* avoid indicating legacy bitrates for S1G STAs */ + sta->tx_stats.last_rate.flags |= IEEE80211_TX_RC_S1G_MCS; + sta->rx_stats.last_rate = + STA_STATS_FIELD(TYPE, STA_STATS_RATE_TYPE_S1G); +} diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 5ac2785cdc7b..d4cc9ac2d703 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -9,7 +9,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2013-2015 Intel Mobile Communications GmbH * Copyright 2016-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2019 Intel Corporation + * Copyright (C) 2018-2020 Intel Corporation */ #include <linux/if_arp.h> @@ -146,7 +146,8 @@ ieee80211_bss_info_update(struct ieee80211_local *local, struct ieee80211_mgmt *mgmt, size_t len, struct ieee80211_channel *channel) { - bool beacon = ieee80211_is_beacon(mgmt->frame_control); + bool beacon = ieee80211_is_beacon(mgmt->frame_control) || + ieee80211_is_s1g_beacon(mgmt->frame_control); struct cfg80211_bss *cbss, *non_tx_cbss; struct ieee80211_bss *bss, *non_tx_bss; struct cfg80211_inform_bss bss_meta = { @@ -195,6 +196,11 @@ ieee80211_bss_info_update(struct ieee80211_local *local, elements = mgmt->u.probe_resp.variable; baselen = offsetof(struct ieee80211_mgmt, u.probe_resp.variable); + } else if (ieee80211_is_s1g_beacon(mgmt->frame_control)) { + struct ieee80211_ext *ext = (void *) mgmt; + + baselen = offsetof(struct ieee80211_ext, u.s1g_beacon.variable); + elements = ext->u.s1g_beacon.variable; } else { baselen = offsetof(struct ieee80211_mgmt, u.beacon.variable); elements = mgmt->u.beacon.variable; @@ -246,9 +252,12 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) struct ieee80211_bss *bss; struct ieee80211_channel *channel; - if (skb->len < 24 || - (!ieee80211_is_probe_resp(mgmt->frame_control) && - !ieee80211_is_beacon(mgmt->frame_control))) + if (ieee80211_is_s1g_beacon(mgmt->frame_control)) { + if (skb->len < 15) + return; + } else if (skb->len < 24 || + (!ieee80211_is_probe_resp(mgmt->frame_control) && + !ieee80211_is_beacon(mgmt->frame_control))) return; sdata1 = rcu_dereference(local->scan_sdata); @@ -712,6 +721,10 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, req->duration_mandatory; local->hw_scan_band = 0; + local->hw_scan_req->req.n_6ghz_params = req->n_6ghz_params; + local->hw_scan_req->req.scan_6ghz_params = + req->scan_6ghz_params; + local->hw_scan_req->req.scan_6ghz = req->scan_6ghz; /* * After allocating local->hw_scan_req, we must @@ -905,6 +918,17 @@ static void ieee80211_scan_state_set_channel(struct ieee80211_local *local, local->scan_chandef.center_freq1 = chan->center_freq; local->scan_chandef.freq1_offset = chan->freq_offset; local->scan_chandef.center_freq2 = 0; + + /* For scanning on the S1G band, ignore scan_width (which is constant + * across all channels) for now since channel width is specific to each + * channel. Detect the required channel width here and likely revisit + * later. Maybe scan_width could be used to build the channel scan list? + */ + if (chan->band == NL80211_BAND_S1GHZ) { + local->scan_chandef.width = ieee80211_s1g_channel_width(chan); + goto set_channel; + } + switch (scan_req->scan_width) { case NL80211_BSS_CHAN_WIDTH_5: local->scan_chandef.width = NL80211_CHAN_WIDTH_5; @@ -925,8 +949,14 @@ static void ieee80211_scan_state_set_channel(struct ieee80211_local *local, else local->scan_chandef.width = NL80211_CHAN_WIDTH_20_NOHT; break; + case NL80211_BSS_CHAN_WIDTH_1: + case NL80211_BSS_CHAN_WIDTH_2: + /* shouldn't get here, S1G handled above */ + WARN_ON(1); + break; } +set_channel: if (ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL)) skip = 1; @@ -1124,7 +1154,8 @@ int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata, int max_n; for (band = 0; band < NUM_NL80211_BANDS; band++) { - if (!local->hw.wiphy->bands[band]) + if (!local->hw.wiphy->bands[band] || + band == NL80211_BAND_6GHZ) continue; max_n = local->hw.wiphy->bands[band]->n_channels; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index f2840d1d95cf..4fe284ff1ea3 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -258,6 +258,24 @@ struct sta_info *sta_info_get_by_idx(struct ieee80211_sub_if_data *sdata, */ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta) { + /* + * If we had used sta_info_pre_move_state() then we might not + * have gone through the state transitions down again, so do + * it here now (and warn if it's inserted). + * + * This will clear state such as fast TX/RX that may have been + * allocated during state transitions. + */ + while (sta->sta_state > IEEE80211_STA_NONE) { + int ret; + + WARN_ON_ONCE(test_sta_flag(sta, WLAN_STA_INSERTED)); + + ret = sta_info_move_state(sta, sta->sta_state - 1); + if (WARN_ONCE(ret, "sta_info_move_state() returned %d\n", ret)) + break; + } + if (sta->rate_ctrl) rate_control_free_sta(sta); @@ -2122,6 +2140,10 @@ static void sta_stats_decode_rate(struct ieee80211_local *local, u32 rate, int rate_idx = STA_STATS_GET(LEGACY_IDX, rate); sband = local->hw.wiphy->bands[band]; + + if (WARN_ON_ONCE(!sband->bitrates)) + break; + brate = sband->bitrates[rate_idx].bitrate; if (rinfo->bw == RATE_INFO_BW_5) shift = 2; diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index d5010116cf4d..7afd07636b81 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -336,7 +336,6 @@ struct ieee80211_fast_tx { * @expected_ds_bits: from/to DS bits expected * @icv_len: length of the MIC if present * @key: bool indicating encryption is expected (key is set) - * @sta_notify: notify the MLME code (once) * @internal_forward: forward froms internally on AP/VLAN type interfaces * @uses_rss: copy of USES_RSS hw flag * @da_offs: offset of the DA in the header (for header conversion) @@ -352,7 +351,6 @@ struct ieee80211_fast_rx { __le16 expected_ds_bits; u8 icv_len; u8 key:1, - sta_notify:1, internal_forward:1, uses_rss:1; u8 da_offs, sa_offs; @@ -787,7 +785,7 @@ int sta_info_init(struct ieee80211_local *local); void sta_info_stop(struct ieee80211_local *local); /** - * sta_info_flush - flush matching STA entries from the STA table + * __sta_info_flush - flush matching STA entries from the STA table * * Returns the number of removed STA entries. * @@ -796,6 +794,13 @@ void sta_info_stop(struct ieee80211_local *local); */ int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans); +/** + * sta_info_flush - flush matching STA entries from the STA table + * + * Returns the number of removed STA entries. + * + * @sdata: sdata to remove all stations from + */ static inline int sta_info_flush(struct ieee80211_sub_if_data *sdata) { return __sta_info_flush(sdata, false); @@ -825,6 +830,7 @@ enum sta_stats_type { STA_STATS_RATE_TYPE_HT, STA_STATS_RATE_TYPE_VHT, STA_STATS_RATE_TYPE_HE, + STA_STATS_RATE_TYPE_S1G, }; #define STA_STATS_FIELD_HT_MCS GENMASK( 7, 0) diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 0794396a7988..6feb45135020 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -66,8 +66,8 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, info->control.jiffies = jiffies; info->control.vif = &sta->sdata->vif; - info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING | - IEEE80211_TX_INTFL_RETRANSMISSION; + info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING; + info->flags |= IEEE80211_TX_INTFL_RETRANSMISSION; info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS; sta->status_stats.filtered++; @@ -184,18 +184,6 @@ static void ieee80211_frame_acked(struct sta_info *sta, struct sk_buff *skb) struct ieee80211_mgmt *mgmt = (void *) skb->data; struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; - struct ieee80211_tx_info *txinfo = IEEE80211_SKB_CB(skb); - - if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) { - sta->status_stats.last_ack = jiffies; - if (txinfo->status.is_valid_ack_signal) { - sta->status_stats.last_ack_signal = - (s8)txinfo->status.ack_signal; - sta->status_stats.ack_signal_filled = true; - ewma_avg_signal_add(&sta->status_stats.avg_ack_signal, - -txinfo->status.ack_signal); - } - } if (ieee80211_is_data_qos(mgmt->frame_control)) { struct ieee80211_hdr *hdr = (void *) skb->data; @@ -890,7 +878,8 @@ void ieee80211_tx_monitor(struct ieee80211_local *local, struct sk_buff *skb, } static void __ieee80211_tx_status(struct ieee80211_hw *hw, - struct ieee80211_tx_status *status) + struct ieee80211_tx_status *status, + int rates_idx, int retry_count) { struct sk_buff *skb = status->skb; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; @@ -899,17 +888,12 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, struct sta_info *sta; __le16 fc; struct ieee80211_supported_band *sband; - int retry_count; - int rates_idx; bool send_to_cooked; bool acked; bool noack_success; struct ieee80211_bar *bar; int shift = 0; int tid = IEEE80211_NUM_TIDS; - u16 tx_time_est; - - rates_idx = ieee80211_tx_get_rates(hw, info, &retry_count); sband = local->hw.wiphy->bands[info->band]; fc = hdr->frame_control; @@ -987,62 +971,17 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, if (info->flags & IEEE80211_TX_STAT_TX_FILTERED) { ieee80211_handle_filtered_frame(local, sta, skb); return; - } else { + } else if (ieee80211_is_data_present(fc)) { if (!acked && !noack_success) - sta->status_stats.retry_failed++; - sta->status_stats.retry_count += retry_count; + sta->status_stats.msdu_failed[tid]++; - if (ieee80211_is_data_present(fc)) { - if (!acked && !noack_success) - sta->status_stats.msdu_failed[tid]++; - - sta->status_stats.msdu_retries[tid] += - retry_count; - } + sta->status_stats.msdu_retries[tid] += + retry_count; } - rate_control_tx_status(local, sband, status); - if (ieee80211_vif_is_mesh(&sta->sdata->vif)) - ieee80211s_update_metric(local, sta, status); - if (!(info->flags & IEEE80211_TX_CTL_INJECTED) && acked) ieee80211_frame_acked(sta, skb); - if ((sta->sdata->vif.type == NL80211_IFTYPE_STATION) && - ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) - ieee80211_sta_tx_notify(sta->sdata, (void *) skb->data, - acked, info->status.tx_time); - - if (info->status.tx_time && - wiphy_ext_feature_isset(local->hw.wiphy, - NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) - ieee80211_sta_register_airtime(&sta->sta, tid, - info->status.tx_time, 0); - - if ((tx_time_est = ieee80211_info_get_tx_time_est(info)) > 0) { - /* Do this here to avoid the expensive lookup of the sta - * in ieee80211_report_used_skb(). - */ - ieee80211_sta_update_pending_airtime(local, sta, - skb_get_queue_mapping(skb), - tx_time_est, - true); - ieee80211_info_set_tx_time_est(info, 0); - } - - if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) { - if (acked) { - if (sta->status_stats.lost_packets) - sta->status_stats.lost_packets = 0; - - /* Track when last TDLS packet was ACKed */ - sta->status_stats.last_pkt_time = jiffies; - } else if (noack_success) { - /* nothing to do here, do not account as lost */ - } else { - ieee80211_lost_packet(sta, info); - } - } } /* SNMP counters @@ -1101,7 +1040,10 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, * with this test... */ if (!local->monitors && (!send_to_cooked || !local->cooked_mntrs)) { - dev_kfree_skb(skb); + if (status->free_list) + list_add_tail(&skb->list, status->free_list); + else + dev_kfree_skb(skb); return; } @@ -1126,7 +1068,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) if (sta) status.sta = &sta->sta; - __ieee80211_tx_status(hw, &status); + ieee80211_tx_status_ext(hw, &status); rcu_read_unlock(); } EXPORT_SYMBOL(ieee80211_tx_status); @@ -1137,10 +1079,12 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_tx_info *info = status->info; struct ieee80211_sta *pubsta = status->sta; + struct sk_buff *skb = status->skb; struct ieee80211_supported_band *sband; - struct sta_info *sta; - int retry_count; + struct sta_info *sta = NULL; + int rates_idx, retry_count; bool acked, noack_success; + u16 tx_time_est; if (pubsta) { sta = container_of(pubsta, struct sta_info, sta); @@ -1149,13 +1093,22 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, sta->tx_stats.last_rate_info = *status->rate; } - if (status->skb) - return __ieee80211_tx_status(hw, status); + if (skb && (tx_time_est = + ieee80211_info_get_tx_time_est(IEEE80211_SKB_CB(skb))) > 0) { + /* Do this here to avoid the expensive lookup of the sta + * in ieee80211_report_used_skb(). + */ + ieee80211_sta_update_pending_airtime(local, sta, + skb_get_queue_mapping(skb), + tx_time_est, + true); + ieee80211_info_set_tx_time_est(IEEE80211_SKB_CB(skb), 0); + } - if (!status->sta) - return; + if (!status->info) + goto free; - ieee80211_tx_get_rates(hw, info, &retry_count); + rates_idx = ieee80211_tx_get_rates(hw, info, &retry_count); sband = hw->wiphy->bands[info->band]; @@ -1163,24 +1116,46 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, noack_success = !!(info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED); if (pubsta) { + struct ieee80211_sub_if_data *sdata = sta->sdata; + if (!acked && !noack_success) sta->status_stats.retry_failed++; sta->status_stats.retry_count += retry_count; - if (acked) { - sta->status_stats.last_ack = jiffies; + if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) { + if (sdata->vif.type == NL80211_IFTYPE_STATION && + skb && !(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP)) + ieee80211_sta_tx_notify(sdata, (void *) skb->data, + acked, info->status.tx_time); - if (sta->status_stats.lost_packets) - sta->status_stats.lost_packets = 0; + if (acked) { + sta->status_stats.last_ack = jiffies; - /* Track when last packet was ACKed */ - sta->status_stats.last_pkt_time = jiffies; - } else if (test_sta_flag(sta, WLAN_STA_PS_STA)) { - return; - } else if (noack_success) { - /* nothing to do here, do not account as lost */ - } else { - ieee80211_lost_packet(sta, info); + if (sta->status_stats.lost_packets) + sta->status_stats.lost_packets = 0; + + /* Track when last packet was ACKed */ + sta->status_stats.last_pkt_time = jiffies; + + /* Reset connection monitor */ + if (sdata->vif.type == NL80211_IFTYPE_STATION && + unlikely(sdata->u.mgd.probe_send_count > 0)) + sdata->u.mgd.probe_send_count = 0; + + if (info->status.is_valid_ack_signal) { + sta->status_stats.last_ack_signal = + (s8)info->status.ack_signal; + sta->status_stats.ack_signal_filled = true; + ewma_avg_signal_add(&sta->status_stats.avg_ack_signal, + -info->status.ack_signal); + } + } else if (test_sta_flag(sta, WLAN_STA_PS_STA)) { + return; + } else if (noack_success) { + /* nothing to do here, do not account as lost */ + } else { + ieee80211_lost_packet(sta, info); + } } rate_control_tx_status(local, sband, status); @@ -1188,6 +1163,10 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, ieee80211s_update_metric(local, sta, status); } + if (skb && !(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP)) + return __ieee80211_tx_status(hw, status, rates_idx, + retry_count); + if (acked || noack_success) { I802_DEBUG_INC(local->dot11TransmittedFrameCount); if (!pubsta) @@ -1199,6 +1178,16 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, } else { I802_DEBUG_INC(local->dot11FailedCount); } + +free: + if (!skb) + return; + + ieee80211_report_used_skb(local, skb, false); + if (status->free_list) + list_add_tail(&skb->list, status->free_list); + else + dev_kfree_skb(skb); } EXPORT_SYMBOL(ieee80211_tx_status_ext); @@ -1225,69 +1214,23 @@ void ieee80211_tx_status_8023(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct sk_buff *skb) { - struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_sub_if_data *sdata; - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_tx_status status = { + .skb = skb, + .info = IEEE80211_SKB_CB(skb), + }; struct sta_info *sta; - int retry_count; - int rates_idx; - bool acked; sdata = vif_to_sdata(vif); - acked = info->flags & IEEE80211_TX_STAT_ACK; - rates_idx = ieee80211_tx_get_rates(hw, info, &retry_count); - rcu_read_lock(); - if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) - goto counters_update; - - if (IS_ERR(sta)) - goto counters_update; - - if (!acked) - sta->status_stats.retry_failed++; - - if (rates_idx != -1) - sta->tx_stats.last_rate = info->status.rates[rates_idx]; - - sta->status_stats.retry_count += retry_count; - - if (ieee80211_hw_check(hw, REPORTS_TX_ACK_STATUS)) { - if (acked && vif->type == NL80211_IFTYPE_STATION) - ieee80211_sta_reset_conn_monitor(sdata); - - sta->status_stats.last_ack = jiffies; - if (info->flags & IEEE80211_TX_STAT_ACK) { - if (sta->status_stats.lost_packets) - sta->status_stats.lost_packets = 0; + if (!ieee80211_lookup_ra_sta(sdata, skb, &sta) && !IS_ERR(sta)) + status.sta = &sta->sta; - sta->status_stats.last_pkt_time = jiffies; - } else { - ieee80211_lost_packet(sta, info); - } - } + ieee80211_tx_status_ext(hw, &status); -counters_update: rcu_read_unlock(); - ieee80211_led_tx(local); - - if (!(info->flags & IEEE80211_TX_STAT_ACK) && - !(info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED)) - goto skip_stats_update; - - I802_DEBUG_INC(local->dot11TransmittedFrameCount); - if (is_multicast_ether_addr(skb->data)) - I802_DEBUG_INC(local->dot11MulticastTransmittedFrameCount); - if (retry_count > 0) - I802_DEBUG_INC(local->dot11RetryCount); - if (retry_count > 1) - I802_DEBUG_INC(local->dot11MultipleRetryCount); - -skip_stats_update: - ieee80211_report_used_skb(local, skb, false); - dev_kfree_skb(skb); } EXPORT_SYMBOL(ieee80211_tx_status_8023); diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 50ab5b9d8eab..89723907a094 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -2734,6 +2734,39 @@ TRACE_EVENT(drv_get_ftm_responder_stats, ) ); +DEFINE_EVENT(local_sdata_addr_evt, drv_update_vif_offload, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata), + TP_ARGS(local, sdata) +); + +TRACE_EVENT(drv_sta_set_4addr, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta, bool enabled), + + TP_ARGS(local, sdata, sta, enabled), + + TP_STRUCT__entry( + LOCAL_ENTRY + VIF_ENTRY + STA_ENTRY + __field(bool, enabled) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + VIF_ASSIGN; + STA_ASSIGN; + __entry->enabled = enabled; + ), + + TP_printk( + LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT " enabled:%d", + LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->enabled + ) +); + #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 dca01d7e6e3e..56a4d0d20a26 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -82,6 +82,10 @@ static __le16 ieee80211_duration(struct ieee80211_tx_data *tx, erp = txrate->flags & IEEE80211_RATE_ERP_G; + /* device is expected to do this */ + if (sband->band == NL80211_BAND_S1GHZ) + return 0; + /* * data and mgmt (except PS Poll): * - during CFP: 32768 @@ -531,7 +535,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) info->control.jiffies = jiffies; info->control.vif = &tx->sdata->vif; - info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; + info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING; info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS; skb_queue_tail(&sta->ps_tx_buf[ac], tx->skb); spin_unlock(&sta->ps_lock); @@ -1134,7 +1138,7 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx, tx->sta->sta.addr, tx->sta->sta.aid); } info->control.vif = &tx->sdata->vif; - info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; + info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING; info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS; __skb_queue_tail(&tid_tx->pending, skb); if (skb_queue_len(&tid_tx->pending) > STA_MAX_TX_BUFFER) @@ -1179,7 +1183,7 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, * we are doing the needed processing, so remove the flag * now. */ - info->flags &= ~IEEE80211_TX_INTFL_NEED_TXPROCESSING; + info->control.flags &= ~IEEE80211_TX_INTCFL_NEED_TXPROCESSING; hdr = (struct ieee80211_hdr *) skb->data; @@ -1258,7 +1262,7 @@ static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local, (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE)) return NULL; - if (!(info->control.flags & IEEE80211_TX_CTRL_HW_80211_ENCAP) && + if (!(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) && unlikely(!ieee80211_is_data_present(hdr->frame_control))) { if ((!ieee80211_is_mgmt(hdr->frame_control) || ieee80211_is_bufferable_mmpdu(hdr->frame_control) || @@ -1938,19 +1942,24 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata, /* device xmit handlers */ +enum ieee80211_encrypt { + ENCRYPT_NO, + ENCRYPT_MGMT, + ENCRYPT_DATA, +}; + static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, - int head_need, bool may_encrypt) + int head_need, + enum ieee80211_encrypt encrypt) { struct ieee80211_local *local = sdata->local; - struct ieee80211_hdr *hdr; bool enc_tailroom; int tail_need = 0; - hdr = (struct ieee80211_hdr *) skb->data; - enc_tailroom = may_encrypt && - (sdata->crypto_tx_tailroom_needed_cnt || - ieee80211_is_mgmt(hdr->frame_control)); + enc_tailroom = encrypt == ENCRYPT_MGMT || + (encrypt == ENCRYPT_DATA && + sdata->crypto_tx_tailroom_needed_cnt); if (enc_tailroom) { tail_need = IEEE80211_ENCRYPT_TAILROOM; @@ -1981,23 +1990,29 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, { struct ieee80211_local *local = sdata->local; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - struct ieee80211_hdr *hdr; + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; int headroom; - bool may_encrypt; + enum ieee80211_encrypt encrypt; - may_encrypt = !(info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT); + if (info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT) + encrypt = ENCRYPT_NO; + else if (ieee80211_is_mgmt(hdr->frame_control)) + encrypt = ENCRYPT_MGMT; + else + encrypt = ENCRYPT_DATA; headroom = local->tx_headroom; - if (may_encrypt) + if (encrypt != ENCRYPT_NO) headroom += sdata->encrypt_headroom; headroom -= skb_headroom(skb); headroom = max_t(int, 0, headroom); - if (ieee80211_skb_resize(sdata, skb, headroom, may_encrypt)) { + if (ieee80211_skb_resize(sdata, skb, headroom, encrypt)) { ieee80211_free_txskb(&local->hw, skb); return; } + /* reload after potential resize */ hdr = (struct ieee80211_hdr *) skb->data; info->control.vif = &sdata->vif; @@ -2473,7 +2488,9 @@ static u16 ieee80211_store_ack_skb(struct ieee80211_local *local, * @sdata: virtual interface to build the header for * @skb: the skb to build the header in * @info_flags: skb flags to set + * @sta: the station pointer * @ctrl_flags: info control flags to set + * @cookie: cookie pointer to fill (if not %NULL) * * This function takes the skb with 802.3 header and reformats the header to * the appropriate IEEE 802.11 header based on which interface the packet is @@ -2822,7 +2839,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, head_need += sdata->encrypt_headroom; head_need += local->tx_headroom; head_need = max_t(int, 0, head_need); - if (ieee80211_skb_resize(sdata, skb, head_need, true)) { + if (ieee80211_skb_resize(sdata, skb, head_need, ENCRYPT_DATA)) { ieee80211_free_txskb(&local->hw, skb); skb = NULL; return ERR_PTR(-ENOMEM); @@ -3496,7 +3513,7 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, if (unlikely(ieee80211_skb_resize(sdata, skb, max_t(int, extra_head + hw_headroom - skb_headroom(skb), 0), - false))) { + ENCRYPT_NO))) { kfree_skb(skb); return true; } @@ -3613,13 +3630,14 @@ begin: tx.skb = skb; tx.sdata = vif_to_sdata(info->control.vif); - if (txq->sta && !(info->flags & IEEE80211_TX_CTL_INJECTED)) { + if (txq->sta) { tx.sta = container_of(txq->sta, struct sta_info, sta); /* * Drop unicast frames to unauthorised stations unless they are - * EAPOL frames from the local station. + * injected frames or EAPOL frames from the local station. */ - if (unlikely(ieee80211_is_data(hdr->frame_control) && + if (unlikely(!(info->flags & IEEE80211_TX_CTL_INJECTED) && + ieee80211_is_data(hdr->frame_control) && !ieee80211_vif_is_mesh(&tx.sdata->vif) && tx.sdata->vif.type != NL80211_IFTYPE_OCB && !is_multicast_ether_addr(hdr->addr1) && @@ -3649,7 +3667,7 @@ begin: else info->flags &= ~IEEE80211_TX_CTL_AMPDU; - if (info->control.flags & IEEE80211_TX_CTRL_HW_80211_ENCAP) + if (info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) goto encap_out; if (info->control.flags & IEEE80211_TX_CTRL_FAST_XMIT) { @@ -4190,38 +4208,18 @@ static bool ieee80211_tx_8023(struct ieee80211_sub_if_data *sdata, static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, struct net_device *dev, struct sta_info *sta, - struct sk_buff *skb) + struct ieee80211_key *key, struct sk_buff *skb) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - struct ethhdr *ehdr = (struct ethhdr *)skb->data; struct ieee80211_local *local = sdata->local; - bool authorized = false; - bool multicast; - unsigned char *ra = ehdr->h_dest; - - if (IS_ERR(sta) || (sta && !sta->uploaded)) - sta = NULL; + struct tid_ampdu_tx *tid_tx; + u8 tid; - if (sdata->vif.type == NL80211_IFTYPE_STATION && - (!sta || !test_sta_flag(sta, WLAN_STA_TDLS_PEER))) - ra = sdata->u.mgd.bssid; - - if (is_zero_ether_addr(ra)) - goto out_free; - - multicast = is_multicast_ether_addr(ra); - - if (sta) - authorized = test_sta_flag(sta, WLAN_STA_AUTHORIZED); - - if (!multicast && !authorized && - (ehdr->h_proto != sdata->control_port_protocol || - !ether_addr_equal(sdata->vif.addr, ehdr->h_source))) - goto out_free; - - if (multicast && sdata->vif.type == NL80211_IFTYPE_AP && - !atomic_read(&sdata->u.ap.num_mcast_sta)) - goto out_free; + if (local->ops->wake_tx_queue) { + u16 queue = __ieee80211_select_queue(sdata, sta, skb); + skb_set_queue_mapping(skb, queue); + skb_get_hash(skb); + } if (unlikely(test_bit(SCAN_SW_SCANNING, &local->scanning)) && test_bit(SDATA_STATE_OFFCHANNEL, &sdata->state)) @@ -4229,36 +4227,42 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, memset(info, 0, sizeof(*info)); - if (unlikely(!multicast && skb->sk && - skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS)) - info->ack_frame_id = ieee80211_store_ack_skb(local, skb, - &info->flags, NULL); + tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK; + tid_tx = rcu_dereference(sta->ampdu_mlme.tid_tx[tid]); + if (tid_tx) { + if (!test_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state)) { + /* fall back to non-offload slow path */ + __ieee80211_subif_start_xmit(skb, dev, 0, 0, NULL); + return; + } - if (unlikely(sdata->control_port_protocol == ehdr->h_proto)) { - if (sdata->control_port_no_encrypt) - info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; - info->control.flags |= IEEE80211_TX_CTRL_PORT_CTRL_PROTO; + info->flags |= IEEE80211_TX_CTL_AMPDU; + if (tid_tx->timeout) + tid_tx->last_tx = jiffies; } - if (multicast) - info->flags |= IEEE80211_TX_CTL_NO_ACK; + if (unlikely(skb->sk && + skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS)) + info->ack_frame_id = ieee80211_store_ack_skb(local, skb, + &info->flags, NULL); info->hw_queue = sdata->vif.hw_queue[skb_get_queue_mapping(skb)]; ieee80211_tx_stats(dev, skb->len); - if (sta) { - sta->tx_stats.bytes[skb_get_queue_mapping(skb)] += skb->len; - sta->tx_stats.packets[skb_get_queue_mapping(skb)]++; - } + sta->tx_stats.bytes[skb_get_queue_mapping(skb)] += skb->len; + sta->tx_stats.packets[skb_get_queue_mapping(skb)]++; if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) sdata = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap); - info->control.flags |= IEEE80211_TX_CTRL_HW_80211_ENCAP; + info->flags |= IEEE80211_TX_CTL_HW_80211_ENCAP; info->control.vif = &sdata->vif; + if (key) + info->control.hw_key = &key->conf; + ieee80211_tx_8023(sdata, skb, skb->len, sta, false); return; @@ -4271,12 +4275,10 @@ netdev_tx_t ieee80211_subif_start_xmit_8023(struct sk_buff *skb, struct net_device *dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ethhdr *ehdr = (struct ethhdr *)skb->data; + struct ieee80211_key *key; struct sta_info *sta; - - if (WARN_ON(!sdata->hw_80211_encap)) { - kfree_skb(skb); - return NETDEV_TX_OK; - } + bool offload = true; if (unlikely(skb->len < ETH_HLEN)) { kfree_skb(skb); @@ -4285,11 +4287,26 @@ netdev_tx_t ieee80211_subif_start_xmit_8023(struct sk_buff *skb, rcu_read_lock(); - if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) + if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) { kfree_skb(skb); + goto out; + } + + if (unlikely(IS_ERR_OR_NULL(sta) || !sta->uploaded || + !test_sta_flag(sta, WLAN_STA_AUTHORIZED) || + sdata->control_port_protocol == ehdr->h_proto)) + offload = false; + else if ((key = rcu_dereference(sta->ptk[sta->ptk_idx])) && + (!(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE) || + key->conf.cipher == WLAN_CIPHER_SUITE_TKIP)) + offload = false; + + if (offload) + ieee80211_8023_xmit(sdata, dev, sta, key, skb); else - ieee80211_8023_xmit(sdata, dev, sta, skb); + ieee80211_subif_start_xmit(skb, dev); +out: rcu_read_unlock(); return NETDEV_TX_OK; @@ -4365,7 +4382,7 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local, sdata = vif_to_sdata(info->control.vif); - if (info->flags & IEEE80211_TX_INTFL_NEED_TXPROCESSING) { + if (info->control.flags & IEEE80211_TX_INTCFL_NEED_TXPROCESSING) { chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); if (unlikely(!chanctx_conf)) { dev_kfree_skb(skb); @@ -4373,7 +4390,7 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local, } info->band = chanctx_conf->def.chan->band; result = ieee80211_tx(sdata, NULL, skb, true); - } else if (info->control.flags & IEEE80211_TX_CTRL_HW_80211_ENCAP) { + } else if (info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) { if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) { dev_kfree_skb(skb); return true; @@ -4538,14 +4555,14 @@ static int ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata, return 0; } -static void ieee80211_set_csa(struct ieee80211_sub_if_data *sdata, - struct beacon_data *beacon) +static void ieee80211_set_beacon_cntdwn(struct ieee80211_sub_if_data *sdata, + struct beacon_data *beacon) { struct probe_resp *resp; u8 *beacon_data; size_t beacon_data_len; int i; - u8 count = beacon->csa_current_counter; + u8 count = beacon->cntdwn_current_counter; switch (sdata->vif.type) { case NL80211_IFTYPE_AP: @@ -4565,36 +4582,36 @@ static void ieee80211_set_csa(struct ieee80211_sub_if_data *sdata, } rcu_read_lock(); - for (i = 0; i < IEEE80211_MAX_CSA_COUNTERS_NUM; ++i) { + for (i = 0; i < IEEE80211_MAX_CNTDWN_COUNTERS_NUM; ++i) { resp = rcu_dereference(sdata->u.ap.probe_resp); - if (beacon->csa_counter_offsets[i]) { - if (WARN_ON_ONCE(beacon->csa_counter_offsets[i] >= + if (beacon->cntdwn_counter_offsets[i]) { + if (WARN_ON_ONCE(beacon->cntdwn_counter_offsets[i] >= beacon_data_len)) { rcu_read_unlock(); return; } - beacon_data[beacon->csa_counter_offsets[i]] = count; + beacon_data[beacon->cntdwn_counter_offsets[i]] = count; } if (sdata->vif.type == NL80211_IFTYPE_AP && resp) - resp->data[resp->csa_counter_offsets[i]] = count; + resp->data[resp->cntdwn_counter_offsets[i]] = count; } rcu_read_unlock(); } -static u8 __ieee80211_csa_update_counter(struct beacon_data *beacon) +static u8 __ieee80211_beacon_update_cntdwn(struct beacon_data *beacon) { - beacon->csa_current_counter--; + beacon->cntdwn_current_counter--; /* the counter should never reach 0 */ - WARN_ON_ONCE(!beacon->csa_current_counter); + WARN_ON_ONCE(!beacon->cntdwn_current_counter); - return beacon->csa_current_counter; + return beacon->cntdwn_current_counter; } -u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif) +u8 ieee80211_beacon_update_cntdwn(struct ieee80211_vif *vif) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct beacon_data *beacon = NULL; @@ -4612,15 +4629,15 @@ u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif) if (!beacon) goto unlock; - count = __ieee80211_csa_update_counter(beacon); + count = __ieee80211_beacon_update_cntdwn(beacon); unlock: rcu_read_unlock(); return count; } -EXPORT_SYMBOL(ieee80211_csa_update_counter); +EXPORT_SYMBOL(ieee80211_beacon_update_cntdwn); -void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter) +void ieee80211_beacon_set_cntdwn(struct ieee80211_vif *vif, u8 counter) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct beacon_data *beacon = NULL; @@ -4637,15 +4654,15 @@ void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter) if (!beacon) goto unlock; - if (counter < beacon->csa_current_counter) - beacon->csa_current_counter = counter; + if (counter < beacon->cntdwn_current_counter) + beacon->cntdwn_current_counter = counter; unlock: rcu_read_unlock(); } -EXPORT_SYMBOL(ieee80211_csa_set_counter); +EXPORT_SYMBOL(ieee80211_beacon_set_cntdwn); -bool ieee80211_csa_is_complete(struct ieee80211_vif *vif) +bool ieee80211_beacon_cntdwn_is_complete(struct ieee80211_vif *vif) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct beacon_data *beacon = NULL; @@ -4688,20 +4705,21 @@ bool ieee80211_csa_is_complete(struct ieee80211_vif *vif) goto out; } - if (!beacon->csa_counter_offsets[0]) + if (!beacon->cntdwn_counter_offsets[0]) goto out; - if (WARN_ON_ONCE(beacon->csa_counter_offsets[0] > beacon_data_len)) + if (WARN_ON_ONCE(beacon->cntdwn_counter_offsets[0] > beacon_data_len)) goto out; - if (beacon_data[beacon->csa_counter_offsets[0]] == 1) + if (beacon_data[beacon->cntdwn_counter_offsets[0]] == 1) ret = true; + out: rcu_read_unlock(); return ret; } -EXPORT_SYMBOL(ieee80211_csa_is_complete); +EXPORT_SYMBOL(ieee80211_beacon_cntdwn_is_complete); static int ieee80211_beacon_protect(struct sk_buff *skb, struct ieee80211_local *local, @@ -4761,11 +4779,11 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, beacon = rcu_dereference(ap->beacon); if (beacon) { - if (beacon->csa_counter_offsets[0]) { + if (beacon->cntdwn_counter_offsets[0]) { if (!is_template) - __ieee80211_csa_update_counter(beacon); + ieee80211_beacon_update_cntdwn(vif); - ieee80211_set_csa(sdata, beacon); + ieee80211_set_beacon_cntdwn(sdata, beacon); } /* @@ -4809,11 +4827,11 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, if (!beacon) goto out; - if (beacon->csa_counter_offsets[0]) { + if (beacon->cntdwn_counter_offsets[0]) { if (!is_template) - __ieee80211_csa_update_counter(beacon); + __ieee80211_beacon_update_cntdwn(beacon); - ieee80211_set_csa(sdata, beacon); + ieee80211_set_beacon_cntdwn(sdata, beacon); } skb = dev_alloc_skb(local->tx_headroom + beacon->head_len + @@ -4833,16 +4851,16 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, if (!beacon) goto out; - if (beacon->csa_counter_offsets[0]) { + if (beacon->cntdwn_counter_offsets[0]) { if (!is_template) /* TODO: For mesh csa_counter is in TU, so * decrementing it by one isn't correct, but * for now we leave it consistent with overall * mac80211's behavior. */ - __ieee80211_csa_update_counter(beacon); + __ieee80211_beacon_update_cntdwn(beacon); - ieee80211_set_csa(sdata, beacon); + ieee80211_set_beacon_cntdwn(sdata, beacon); } if (ifmsh->sync_ops) @@ -4874,13 +4892,13 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, if (offs && beacon) { int i; - for (i = 0; i < IEEE80211_MAX_CSA_COUNTERS_NUM; i++) { - u16 csa_off = beacon->csa_counter_offsets[i]; + for (i = 0; i < IEEE80211_MAX_CNTDWN_COUNTERS_NUM; i++) { + u16 csa_off = beacon->cntdwn_counter_offsets[i]; if (!csa_off) continue; - offs->csa_counter_offs[i] = csa_off_base + csa_off; + offs->cntdwn_counter_offs[i] = csa_off_base + csa_off; } } @@ -4999,6 +5017,63 @@ out: } EXPORT_SYMBOL(ieee80211_proberesp_get); +struct sk_buff *ieee80211_get_fils_discovery_tmpl(struct ieee80211_hw *hw, + struct ieee80211_vif *vif) +{ + struct sk_buff *skb = NULL; + struct fils_discovery_data *tmpl = NULL; + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + + if (sdata->vif.type != NL80211_IFTYPE_AP) + return NULL; + + rcu_read_lock(); + tmpl = rcu_dereference(sdata->u.ap.fils_discovery); + if (!tmpl) { + rcu_read_unlock(); + return NULL; + } + + skb = dev_alloc_skb(sdata->local->hw.extra_tx_headroom + tmpl->len); + if (skb) { + skb_reserve(skb, sdata->local->hw.extra_tx_headroom); + skb_put_data(skb, tmpl->data, tmpl->len); + } + + rcu_read_unlock(); + return skb; +} +EXPORT_SYMBOL(ieee80211_get_fils_discovery_tmpl); + +struct sk_buff * +ieee80211_get_unsol_bcast_probe_resp_tmpl(struct ieee80211_hw *hw, + struct ieee80211_vif *vif) +{ + struct sk_buff *skb = NULL; + struct unsol_bcast_probe_resp_data *tmpl = NULL; + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + + if (sdata->vif.type != NL80211_IFTYPE_AP) + return NULL; + + rcu_read_lock(); + tmpl = rcu_dereference(sdata->u.ap.unsol_bcast_probe_resp); + if (!tmpl) { + rcu_read_unlock(); + return NULL; + } + + skb = dev_alloc_skb(sdata->local->hw.extra_tx_headroom + tmpl->len); + if (skb) { + skb_reserve(skb, sdata->local->hw.extra_tx_headroom); + skb_put_data(skb, tmpl->data, tmpl->len); + } + + rcu_read_unlock(); + return skb; +} +EXPORT_SYMBOL(ieee80211_get_unsol_bcast_probe_resp_tmpl); + struct sk_buff *ieee80211_pspoll_get(struct ieee80211_hw *hw, struct ieee80211_vif *vif) { diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 8d3bfc0fe176..49342060490f 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -45,6 +45,58 @@ struct ieee80211_hw *wiphy_to_ieee80211_hw(struct wiphy *wiphy) } EXPORT_SYMBOL(wiphy_to_ieee80211_hw); +u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len, + enum nl80211_iftype type) +{ + __le16 fc = hdr->frame_control; + + if (ieee80211_is_data(fc)) { + if (len < 24) /* drop incorrect hdr len (data) */ + return NULL; + + if (ieee80211_has_a4(fc)) + return NULL; + if (ieee80211_has_tods(fc)) + return hdr->addr1; + if (ieee80211_has_fromds(fc)) + return hdr->addr2; + + return hdr->addr3; + } + + if (ieee80211_is_s1g_beacon(fc)) { + struct ieee80211_ext *ext = (void *) hdr; + + return ext->u.s1g_beacon.sa; + } + + if (ieee80211_is_mgmt(fc)) { + if (len < 24) /* drop incorrect hdr len (mgmt) */ + return NULL; + return hdr->addr3; + } + + if (ieee80211_is_ctl(fc)) { + if (ieee80211_is_pspoll(fc)) + return hdr->addr1; + + if (ieee80211_is_back_req(fc)) { + switch (type) { + case NL80211_IFTYPE_STATION: + return hdr->addr2; + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_AP_VLAN: + return hdr->addr1; + default: + break; /* fall through to the return */ + } + } + } + + return NULL; +} +EXPORT_SYMBOL(ieee80211_get_bssid); + void ieee80211_tx_set_protected(struct ieee80211_tx_data *tx) { struct sk_buff *skb; @@ -733,6 +785,9 @@ static void __iterate_interfaces(struct ieee80211_local *local, if (!(iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL) && active_only && !(sdata->flags & IEEE80211_SDATA_IN_DRIVER)) continue; + if ((iter_flags & IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER) && + !(sdata->flags & IEEE80211_SDATA_IN_DRIVER)) + continue; if (ieee80211_sdata_running(sdata) || !active_only) iterator(data, sdata->vif.addr, &sdata->vif); @@ -1003,6 +1058,11 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, case WLAN_EID_LINK_ID: case WLAN_EID_BSS_MAX_IDLE_PERIOD: case WLAN_EID_RSNX: + case WLAN_EID_S1G_BCN_COMPAT: + case WLAN_EID_S1G_CAPABILITIES: + case WLAN_EID_S1G_OPERATION: + case WLAN_EID_AID_RESPONSE: + case WLAN_EID_S1G_SHORT_BCN_INTERVAL: /* * not listing WLAN_EID_CHANNEL_SWITCH_WRAPPER -- it seems possible * that if the content gets bigger it might be needed more than once @@ -1288,6 +1348,30 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, &crc : NULL, elem, elems); break; + case WLAN_EID_S1G_CAPABILITIES: + if (elen == sizeof(*elems->s1g_capab)) + elems->s1g_capab = (void *)pos; + else + elem_parse_failed = true; + break; + case WLAN_EID_S1G_OPERATION: + if (elen == sizeof(*elems->s1g_oper)) + elems->s1g_oper = (void *)pos; + else + elem_parse_failed = true; + break; + case WLAN_EID_S1G_BCN_COMPAT: + if (elen == sizeof(*elems->s1g_bcn_compat)) + elems->s1g_bcn_compat = (void *)pos; + else + elem_parse_failed = true; + break; + case WLAN_EID_AID_RESPONSE: + if (elen == sizeof(struct ieee80211_aid_response_ie)) + elems->aid_resp = (void *)pos; + else + elem_parse_failed = true; + break; default: break; } @@ -3371,6 +3455,42 @@ bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata, *chandef = he_chandef; + return false; +} + +bool ieee80211_chandef_s1g_oper(const struct ieee80211_s1g_oper_ie *oper, + struct cfg80211_chan_def *chandef) +{ + u32 oper_freq; + + if (!oper) + return false; + + switch (FIELD_GET(S1G_OPER_CH_WIDTH_OPER, oper->ch_width)) { + case IEEE80211_S1G_CHANWIDTH_1MHZ: + chandef->width = NL80211_CHAN_WIDTH_1; + break; + case IEEE80211_S1G_CHANWIDTH_2MHZ: + chandef->width = NL80211_CHAN_WIDTH_2; + break; + case IEEE80211_S1G_CHANWIDTH_4MHZ: + chandef->width = NL80211_CHAN_WIDTH_4; + break; + case IEEE80211_S1G_CHANWIDTH_8MHZ: + chandef->width = NL80211_CHAN_WIDTH_8; + break; + case IEEE80211_S1G_CHANWIDTH_16MHZ: + chandef->width = NL80211_CHAN_WIDTH_16; + break; + default: + return false; + } + + oper_freq = ieee80211_channel_to_freq_khz(oper->oper_ch, + NL80211_BAND_S1GHZ); + chandef->center_freq1 = KHZ_TO_MHZ(oper_freq); + chandef->freq1_offset = oper_freq % 1000; + return true; } @@ -4277,6 +4397,58 @@ int ieee80211_max_num_channels(struct ieee80211_local *local) return max_num_different_channels; } +void ieee80211_add_s1g_capab_ie(struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta_s1g_cap *caps, + struct sk_buff *skb) +{ + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + struct ieee80211_s1g_cap s1g_capab; + u8 *pos; + int i; + + if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_STATION)) + return; + + if (!caps->s1g) + return; + + memcpy(s1g_capab.capab_info, caps->cap, sizeof(caps->cap)); + memcpy(s1g_capab.supp_mcs_nss, caps->nss_mcs, sizeof(caps->nss_mcs)); + + /* override the capability info */ + for (i = 0; i < sizeof(ifmgd->s1g_capa.capab_info); i++) { + u8 mask = ifmgd->s1g_capa_mask.capab_info[i]; + + s1g_capab.capab_info[i] &= ~mask; + s1g_capab.capab_info[i] |= ifmgd->s1g_capa.capab_info[i] & mask; + } + + /* then MCS and NSS set */ + for (i = 0; i < sizeof(ifmgd->s1g_capa.supp_mcs_nss); i++) { + u8 mask = ifmgd->s1g_capa_mask.supp_mcs_nss[i]; + + s1g_capab.supp_mcs_nss[i] &= ~mask; + s1g_capab.supp_mcs_nss[i] |= + ifmgd->s1g_capa.supp_mcs_nss[i] & mask; + } + + pos = skb_put(skb, 2 + sizeof(s1g_capab)); + *pos++ = WLAN_EID_S1G_CAPABILITIES; + *pos++ = sizeof(s1g_capab); + + memcpy(pos, &s1g_capab, sizeof(s1g_capab)); +} + +void ieee80211_add_aid_request_ie(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb) +{ + u8 *pos = skb_put(skb, 3); + + *pos++ = WLAN_EID_AID_REQUEST; + *pos++ = 1; + *pos++ = 0; +} + u8 *ieee80211_add_wmm_info_ie(u8 *buf, u8 qosinfo) { *buf++ = WLAN_EID_VENDOR_SPECIFIC; @@ -4319,3 +4491,24 @@ const u8 ieee80211_ac_to_qos_mask[IEEE80211_NUM_ACS] = { IEEE80211_WMM_IE_STA_QOSINFO_AC_BE, IEEE80211_WMM_IE_STA_QOSINFO_AC_BK }; + +u16 ieee80211_encode_usf(int listen_interval) +{ + static const int listen_int_usf[] = { 1, 10, 1000, 10000 }; + u16 ui, usf = 0; + + /* find greatest USF */ + while (usf < IEEE80211_MAX_USF) { + if (listen_interval % listen_int_usf[usf + 1]) + break; + usf += 1; + } + ui = listen_interval / listen_int_usf[usf]; + + /* error if there is a remainder. Should've been checked by user */ + WARN_ON_ONCE(ui > IEEE80211_MAX_UI); + listen_interval = FIELD_PREP(LISTEN_INT_USF, usf) | + FIELD_PREP(LISTEN_INT_UI, ui); + + return (u16) listen_interval; +} diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index d1b64d0751f2..fb0e3a657d2d 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -315,10 +315,6 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, sta->sta.bandwidth = ieee80211_sta_cur_vht_bw(sta); - /* If HT IE reported 3839 bytes only, stay with that size. */ - if (sta->sta.max_amsdu_len == IEEE80211_MAX_MPDU_LEN_HT_3839) - return; - switch (vht_cap->cap & IEEE80211_VHT_CAP_MAX_MPDU_MASK) { case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454: sta->sta.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_VHT_11454; diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index 2def85718d94..ef59e25dc482 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -300,5 +300,6 @@ static void __exit mpls_iptunnel_exit(void) module_exit(mpls_iptunnel_exit); MODULE_ALIAS_RTNL_LWT(MPLS); +MODULE_SOFTDEP("post: mpls_gso"); MODULE_DESCRIPTION("MultiProtocol Label Switching IP Tunnels"); MODULE_LICENSE("GPL v2"); diff --git a/net/mptcp/Kconfig b/net/mptcp/Kconfig index 698bc3525160..a014149aa323 100644 --- a/net/mptcp/Kconfig +++ b/net/mptcp/Kconfig @@ -19,14 +19,11 @@ config INET_MPTCP_DIAG config MPTCP_IPV6 bool "MPTCP: IPv6 support for Multipath TCP" - select IPV6 + depends on IPV6=y default y -endif - config MPTCP_KUNIT_TESTS tristate "This builds the MPTCP KUnit tests" if !KUNIT_ALL_TESTS - select MPTCP depends on KUNIT default KUNIT_ALL_TESTS help @@ -39,3 +36,4 @@ config MPTCP_KUNIT_TESTS If unsure, say N. +endif diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index 0a6a15f3456d..84d119436b22 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -22,6 +22,15 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC), SNMP_MIB_ITEM("DSSNotMatching", MPTCP_MIB_DSSNOMATCH), SNMP_MIB_ITEM("InfiniteMapRx", MPTCP_MIB_INFINITEMAPRX), + SNMP_MIB_ITEM("OFOQueueTail", MPTCP_MIB_OFOQUEUETAIL), + SNMP_MIB_ITEM("OFOQueue", MPTCP_MIB_OFOQUEUE), + SNMP_MIB_ITEM("OFOMerge", MPTCP_MIB_OFOMERGE), + SNMP_MIB_ITEM("NoDSSInWindow", MPTCP_MIB_NODSSWINDOW), + SNMP_MIB_ITEM("DuplicateData", MPTCP_MIB_DUPDATA), + SNMP_MIB_ITEM("AddAddr", MPTCP_MIB_ADDADDR), + SNMP_MIB_ITEM("EchoAdd", MPTCP_MIB_ECHOADD), + SNMP_MIB_ITEM("RmAddr", MPTCP_MIB_RMADDR), + SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW), SNMP_MIB_SENTINEL }; diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index d7de340fc997..47bcecce1106 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -15,6 +15,15 @@ enum linux_mptcp_mib_field { MPTCP_MIB_JOINACKMAC, /* HMAC was wrong on ACK + MP_JOIN */ MPTCP_MIB_DSSNOMATCH, /* Received a new mapping that did not match the previous one */ MPTCP_MIB_INFINITEMAPRX, /* Received an infinite mapping */ + MPTCP_MIB_OFOQUEUETAIL, /* Segments inserted into OoO queue tail */ + MPTCP_MIB_OFOQUEUE, /* Segments inserted into OoO queue */ + MPTCP_MIB_OFOMERGE, /* Segments merged in OoO queue */ + MPTCP_MIB_NODSSWINDOW, /* Segments not in MPTCP windows */ + MPTCP_MIB_DUPDATA, /* Segments discarded due to duplicate DSS */ + MPTCP_MIB_ADDADDR, /* Received ADD_ADDR with echo-flag=0 */ + MPTCP_MIB_ECHOADD, /* Received ADD_ADDR with echo-flag=1 */ + MPTCP_MIB_RMADDR, /* Received RM_ADDR */ + MPTCP_MIB_RMSUBFLOW, /* Remove a subflow */ __MPTCP_MIB_MAX }; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 888bbbbb3e8a..a044dd43411d 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -11,6 +11,7 @@ #include <net/tcp.h> #include <net/mptcp.h> #include "protocol.h" +#include "mib.h" static bool mptcp_cap_flag_sha256(u8 flags) { @@ -240,9 +241,8 @@ static void mptcp_parse_option(const struct sk_buff *skb, } mp_opt->add_addr = 1; - mp_opt->port = 0; mp_opt->addr_id = *ptr++; - pr_debug("ADD_ADDR: id=%d", mp_opt->addr_id); + pr_debug("ADD_ADDR: id=%d, echo=%d", mp_opt->addr_id, mp_opt->echo); if (mp_opt->family == MPTCP_ADDR_IPVERSION_4) { memcpy((u8 *)&mp_opt->addr.s_addr, (u8 *)ptr, 4); ptr += 4; @@ -296,6 +296,8 @@ void mptcp_get_options(const struct sk_buff *skb, mp_opt->mp_capable = 0; mp_opt->mp_join = 0; mp_opt->add_addr = 0; + mp_opt->ahmac = 0; + mp_opt->port = 0; mp_opt->rm_addr = 0; mp_opt->dss = 0; @@ -516,7 +518,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, return ret; } - if (subflow->use_64bit_ack) { + if (READ_ONCE(msk->use_64bit_ack)) { ack_size = TCPOLEN_MPTCP_DSS_ACK64; opts->ext_copy.data_ack = READ_ONCE(msk->ack_seq); opts->ext_copy.ack64 = 1; @@ -571,21 +573,22 @@ static u64 add_addr6_generate_hmac(u64 key1, u64 key2, u8 addr_id, } #endif -static bool mptcp_established_options_addr(struct sock *sk, - unsigned int *size, - unsigned int remaining, - struct mptcp_out_options *opts) +static bool mptcp_established_options_add_addr(struct sock *sk, + unsigned int *size, + unsigned int remaining, + struct mptcp_out_options *opts) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); struct mptcp_addr_info saddr; + bool echo; int len; - if (!mptcp_pm_should_signal(msk) || - !(mptcp_pm_addr_signal(msk, remaining, &saddr))) + if (!mptcp_pm_should_add_signal(msk) || + !(mptcp_pm_add_addr_signal(msk, remaining, &saddr, &echo))) return false; - len = mptcp_add_addr_len(saddr.family); + len = mptcp_add_addr_len(saddr.family, echo); if (remaining < len) return false; @@ -594,22 +597,51 @@ static bool mptcp_established_options_addr(struct sock *sk, if (saddr.family == AF_INET) { opts->suboptions |= OPTION_MPTCP_ADD_ADDR; opts->addr = saddr.addr; - opts->ahmac = add_addr_generate_hmac(msk->local_key, - msk->remote_key, - opts->addr_id, - &opts->addr); + if (!echo) { + opts->ahmac = add_addr_generate_hmac(msk->local_key, + msk->remote_key, + opts->addr_id, + &opts->addr); + } } #if IS_ENABLED(CONFIG_MPTCP_IPV6) else if (saddr.family == AF_INET6) { opts->suboptions |= OPTION_MPTCP_ADD_ADDR6; opts->addr6 = saddr.addr6; - opts->ahmac = add_addr6_generate_hmac(msk->local_key, - msk->remote_key, - opts->addr_id, - &opts->addr6); + if (!echo) { + opts->ahmac = add_addr6_generate_hmac(msk->local_key, + msk->remote_key, + opts->addr_id, + &opts->addr6); + } } #endif - pr_debug("addr_id=%d, ahmac=%llu", opts->addr_id, opts->ahmac); + pr_debug("addr_id=%d, ahmac=%llu, echo=%d", opts->addr_id, opts->ahmac, echo); + + return true; +} + +static bool mptcp_established_options_rm_addr(struct sock *sk, + unsigned int *size, + unsigned int remaining, + struct mptcp_out_options *opts) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_sock *msk = mptcp_sk(subflow->conn); + u8 rm_id; + + if (!mptcp_pm_should_rm_signal(msk) || + !(mptcp_pm_rm_addr_signal(msk, remaining, &rm_id))) + return false; + + if (remaining < TCPOLEN_MPTCP_RM_ADDR_BASE) + return false; + + *size = TCPOLEN_MPTCP_RM_ADDR_BASE; + opts->suboptions |= OPTION_MPTCP_RM_ADDR; + opts->rm_id = rm_id; + + pr_debug("rm_id=%d", opts->rm_id); return true; } @@ -626,6 +658,12 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, if (unlikely(mptcp_check_fallback(sk))) return false; + /* prevent adding of any MPTCP related options on reset packet + * until we support MP_TCPRST/MP_FASTCLOSE + */ + if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) + return false; + if (mptcp_established_options_mp(sk, skb, &opt_size, remaining, opts)) ret = true; else if (mptcp_established_options_dss(sk, skb, &opt_size, remaining, @@ -640,7 +678,11 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, *size += opt_size; remaining -= opt_size; - if (mptcp_established_options_addr(sk, &opt_size, remaining, opts)) { + if (mptcp_established_options_add_addr(sk, &opt_size, remaining, opts)) { + *size += opt_size; + remaining -= opt_size; + ret = true; + } else if (mptcp_established_options_rm_addr(sk, &opt_size, remaining, opts)) { *size += opt_size; remaining -= opt_size; ret = true; @@ -676,7 +718,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, return false; } -static bool check_fully_established(struct mptcp_sock *msk, struct sock *sk, +static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, struct mptcp_subflow_context *subflow, struct sk_buff *skb, struct mptcp_options_received *mp_opt) @@ -693,15 +735,20 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *sk, TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq && subflow->mp_join && mp_opt->mp_join && READ_ONCE(msk->pm.server_side)) - tcp_send_ack(sk); + tcp_send_ack(ssk); goto fully_established; } - /* we should process OoO packets before the first subflow is fully - * established, but not expected for MP_JOIN subflows + /* we must process OoO packets before the first subflow is fully + * established. OoO packets are instead a protocol violation + * for MP_JOIN subflows as the peer must not send any data + * before receiving the forth ack - cfr. RFC 8684 section 3.2. */ - if (TCP_SKB_CB(skb)->seq != subflow->ssn_offset + 1) + if (TCP_SKB_CB(skb)->seq != subflow->ssn_offset + 1) { + if (subflow->mp_join) + goto reset; return subflow->mp_capable; + } if (mp_opt->dss && mp_opt->use_ack) { /* subflows are fully established as soon as we get any @@ -713,9 +760,12 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *sk, } /* If the first established packet does not contain MP_CAPABLE + data - * then fallback to TCP + * then fallback to TCP. Fallback scenarios requires a reset for + * MP_JOIN subflows. */ if (!mp_opt->mp_capable) { + if (subflow->mp_join) + goto reset; subflow->mp_capable = 0; pr_fallback(msk); __mptcp_do_fallback(msk); @@ -732,12 +782,16 @@ fully_established: subflow->pm_notified = 1; if (subflow->mp_join) { - clear_3rdack_retransmission(sk); + clear_3rdack_retransmission(ssk); mptcp_pm_subflow_established(msk, subflow); } else { mptcp_pm_fully_established(msk); } return true; + +reset: + mptcp_subflow_reset(ssk); + return false; } static u64 expand_ack(u64 old_ack, u64 cur_ack, bool use_64bit) @@ -825,8 +879,7 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk, return hmac == mp_opt->ahmac; } -void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb, - struct tcp_options_received *opt_rx) +void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); @@ -855,11 +908,21 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb, addr.addr6 = mp_opt.addr6; } #endif - if (!mp_opt.echo) + if (!mp_opt.echo) { mptcp_pm_add_addr_received(msk, &addr); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDR); + } else { + mptcp_pm_del_add_timer(msk, &addr); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADD); + } mp_opt.add_addr = 0; } + if (mp_opt.rm_addr) { + mptcp_pm_rm_addr_received(msk, mp_opt.rm_id); + mp_opt.rm_addr = 0; + } + if (!mp_opt.dss) return; diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index a8ad20559aaa..e19e1525ecbb 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -13,23 +13,34 @@ /* path manager command handlers */ int mptcp_pm_announce_addr(struct mptcp_sock *msk, - const struct mptcp_addr_info *addr) + const struct mptcp_addr_info *addr, + bool echo) { pr_debug("msk=%p, local_id=%d", msk, addr->id); msk->pm.local = *addr; - WRITE_ONCE(msk->pm.addr_signal, true); + WRITE_ONCE(msk->pm.add_addr_echo, echo); + WRITE_ONCE(msk->pm.add_addr_signal, true); return 0; } int mptcp_pm_remove_addr(struct mptcp_sock *msk, u8 local_id) { - return -ENOTSUPP; + pr_debug("msk=%p, local_id=%d", msk, local_id); + + msk->pm.rm_id = local_id; + WRITE_ONCE(msk->pm.rm_addr_signal, true); + return 0; } -int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 remote_id) +int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 local_id) { - return -ENOTSUPP; + pr_debug("msk=%p, local_id=%d", msk, local_id); + + spin_lock_bh(&msk->pm.lock); + mptcp_pm_nl_rm_subflow_received(msk, local_id); + spin_unlock_bh(&msk->pm.lock); + return 0; } /* path manager event handlers */ @@ -46,7 +57,7 @@ void mptcp_pm_new_connection(struct mptcp_sock *msk, int server_side) bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk) { struct mptcp_pm_data *pm = &msk->pm; - int ret; + int ret = 0; pr_debug("msk=%p subflows=%d max=%d allow=%d", msk, pm->subflows, pm->subflows_max, READ_ONCE(pm->accept_subflow)); @@ -56,9 +67,11 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk) return false; spin_lock_bh(&pm->lock); - ret = pm->subflows < pm->subflows_max; - if (ret && ++pm->subflows == pm->subflows_max) - WRITE_ONCE(pm->accept_subflow, false); + if (READ_ONCE(pm->accept_subflow)) { + ret = pm->subflows < pm->subflows_max; + if (ret && ++pm->subflows == pm->subflows_max) + WRITE_ONCE(pm->accept_subflow, false); + } spin_unlock_bh(&pm->lock); return ret; @@ -135,38 +148,71 @@ void mptcp_pm_add_addr_received(struct mptcp_sock *msk, pr_debug("msk=%p remote_id=%d accept=%d", msk, addr->id, READ_ONCE(pm->accept_addr)); - /* avoid acquiring the lock if there is no room for fouther addresses */ - if (!READ_ONCE(pm->accept_addr)) - return; - spin_lock_bh(&pm->lock); - /* be sure there is something to signal re-checking under PM lock */ - if (READ_ONCE(pm->accept_addr) && - mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED)) + if (!READ_ONCE(pm->accept_addr)) + mptcp_pm_announce_addr(msk, addr, true); + else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED)) pm->remote = *addr; spin_unlock_bh(&pm->lock); } +void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, u8 rm_id) +{ + struct mptcp_pm_data *pm = &msk->pm; + + pr_debug("msk=%p remote_id=%d", msk, rm_id); + + spin_lock_bh(&pm->lock); + mptcp_pm_schedule_work(msk, MPTCP_PM_RM_ADDR_RECEIVED); + pm->rm_id = rm_id; + spin_unlock_bh(&pm->lock); +} + /* path manager helpers */ -bool mptcp_pm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, - struct mptcp_addr_info *saddr) +bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int remaining, + struct mptcp_addr_info *saddr, bool *echo) { int ret = false; spin_lock_bh(&msk->pm.lock); /* double check after the lock is acquired */ - if (!mptcp_pm_should_signal(msk)) + if (!mptcp_pm_should_add_signal(msk)) goto out_unlock; - if (remaining < mptcp_add_addr_len(msk->pm.local.family)) + *echo = READ_ONCE(msk->pm.add_addr_echo); + + if (remaining < mptcp_add_addr_len(msk->pm.local.family, *echo)) goto out_unlock; *saddr = msk->pm.local; - WRITE_ONCE(msk->pm.addr_signal, false); + WRITE_ONCE(msk->pm.add_addr_signal, false); + ret = true; + +out_unlock: + spin_unlock_bh(&msk->pm.lock); + return ret; +} + +bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, + u8 *rm_id) +{ + int ret = false; + + spin_lock_bh(&msk->pm.lock); + + /* double check after the lock is acquired */ + if (!mptcp_pm_should_rm_signal(msk)) + goto out_unlock; + + if (remaining < TCPOLEN_MPTCP_RM_ADDR_BASE) + goto out_unlock; + + *rm_id = msk->pm.rm_id; + WRITE_ONCE(msk->pm.rm_addr_signal, false); ret = true; out_unlock: @@ -185,13 +231,17 @@ void mptcp_pm_data_init(struct mptcp_sock *msk) msk->pm.add_addr_accepted = 0; msk->pm.local_addr_used = 0; msk->pm.subflows = 0; + msk->pm.rm_id = 0; WRITE_ONCE(msk->pm.work_pending, false); - WRITE_ONCE(msk->pm.addr_signal, false); + WRITE_ONCE(msk->pm.add_addr_signal, false); + WRITE_ONCE(msk->pm.rm_addr_signal, false); WRITE_ONCE(msk->pm.accept_addr, false); WRITE_ONCE(msk->pm.accept_subflow, false); + WRITE_ONCE(msk->pm.add_addr_echo, false); msk->pm.status = 0; spin_lock_init(&msk->pm.lock); + INIT_LIST_HEAD(&msk->pm.anno_list); mptcp_pm_nl_data_init(msk); } diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 770da3627848..0d6f3d912891 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -15,6 +15,7 @@ #include <uapi/linux/mptcp.h> #include "protocol.h" +#include "mib.h" /* forward declaration */ static struct genl_family mptcp_genl_family; @@ -23,12 +24,18 @@ static int pm_nl_pernet_id; struct mptcp_pm_addr_entry { struct list_head list; - unsigned int flags; - int ifindex; struct mptcp_addr_info addr; struct rcu_head rcu; }; +struct mptcp_pm_add_entry { + struct list_head list; + struct mptcp_addr_info addr; + struct timer_list add_timer; + struct mptcp_sock *sock; + u8 retrans_times; +}; + struct pm_nl_pernet { /* protects pernet updates */ spinlock_t lock; @@ -42,6 +49,7 @@ struct pm_nl_pernet { }; #define MPTCP_PM_ADDR_MAX 8 +#define ADD_ADDR_RETRANS_MAX 3 static bool addresses_equal(const struct mptcp_addr_info *a, struct mptcp_addr_info *b, bool use_port) @@ -129,7 +137,7 @@ select_local_address(const struct pm_nl_pernet *pernet, rcu_read_lock(); spin_lock_bh(&msk->join_list_lock); list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { - if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)) + if (!(entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)) continue; /* avoid any address already in use by subflows and @@ -160,7 +168,7 @@ select_signal_address(struct pm_nl_pernet *pernet, unsigned int pos) * can lead to additional addresses not being announced. */ list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { - if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) + if (!(entry->addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) continue; if (i++ == pos) { ret = entry; @@ -179,6 +187,121 @@ static void check_work_pending(struct mptcp_sock *msk) WRITE_ONCE(msk->pm.work_pending, false); } +static struct mptcp_pm_add_entry * +lookup_anno_list_by_saddr(struct mptcp_sock *msk, + struct mptcp_addr_info *addr) +{ + struct mptcp_pm_add_entry *entry; + + list_for_each_entry(entry, &msk->pm.anno_list, list) { + if (addresses_equal(&entry->addr, addr, false)) + return entry; + } + + return NULL; +} + +static void mptcp_pm_add_timer(struct timer_list *timer) +{ + struct mptcp_pm_add_entry *entry = from_timer(entry, timer, add_timer); + struct mptcp_sock *msk = entry->sock; + struct sock *sk = (struct sock *)msk; + + pr_debug("msk=%p", msk); + + if (!msk) + return; + + if (inet_sk_state_load(sk) == TCP_CLOSE) + return; + + if (!entry->addr.id) + return; + + if (mptcp_pm_should_add_signal(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)) { + pr_debug("retransmit ADD_ADDR id=%d", entry->addr.id); + mptcp_pm_announce_addr(msk, &entry->addr, false); + entry->retrans_times++; + } + + if (entry->retrans_times < ADD_ADDR_RETRANS_MAX) + sk_reset_timer(sk, timer, jiffies + TCP_RTO_MAX); + + spin_unlock_bh(&msk->pm.lock); + +out: + __sock_put(sk); +} + +struct mptcp_pm_add_entry * +mptcp_pm_del_add_timer(struct mptcp_sock *msk, + struct mptcp_addr_info *addr) +{ + struct mptcp_pm_add_entry *entry; + struct sock *sk = (struct sock *)msk; + + spin_lock_bh(&msk->pm.lock); + entry = lookup_anno_list_by_saddr(msk, addr); + if (entry) + entry->retrans_times = ADD_ADDR_RETRANS_MAX; + spin_unlock_bh(&msk->pm.lock); + + if (entry) + sk_stop_timer_sync(sk, &entry->add_timer); + + return entry; +} + +static bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, + struct mptcp_pm_addr_entry *entry) +{ + struct mptcp_pm_add_entry *add_entry = NULL; + struct sock *sk = (struct sock *)msk; + + if (lookup_anno_list_by_saddr(msk, &entry->addr)) + return false; + + add_entry = kmalloc(sizeof(*add_entry), GFP_ATOMIC); + if (!add_entry) + return false; + + list_add(&add_entry->list, &msk->pm.anno_list); + + add_entry->addr = entry->addr; + add_entry->sock = msk; + add_entry->retrans_times = 0; + + timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0); + sk_reset_timer(sk, &add_entry->add_timer, jiffies + TCP_RTO_MAX); + + return true; +} + +void mptcp_pm_free_anno_list(struct mptcp_sock *msk) +{ + struct mptcp_pm_add_entry *entry, *tmp; + struct sock *sk = (struct sock *)msk; + LIST_HEAD(free_list); + + pr_debug("msk=%p", msk); + + spin_lock_bh(&msk->pm.lock); + list_splice_init(&msk->pm.anno_list, &free_list); + spin_unlock_bh(&msk->pm.lock); + + list_for_each_entry_safe(entry, tmp, &free_list, list) { + sk_stop_timer_sync(sk, &entry->add_timer); + kfree(entry); + } +} + static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) { struct mptcp_addr_info remote = { 0 }; @@ -199,8 +322,10 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) msk->pm.add_addr_signaled); if (local) { - msk->pm.add_addr_signaled++; - mptcp_pm_announce_addr(msk, &local->addr); + if (mptcp_pm_alloc_anno_list(msk, local)) { + msk->pm.add_addr_signaled++; + mptcp_pm_announce_addr(msk, &local->addr, false); + } } else { /* pick failed, avoid fourther attempts later */ msk->pm.local_addr_used = msk->pm.add_addr_signal_max; @@ -220,8 +345,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) msk->pm.subflows++; check_work_pending(msk); spin_unlock_bh(&msk->pm.lock); - __mptcp_subflow_connect(sk, local->ifindex, - &local->addr, &remote); + __mptcp_subflow_connect(sk, &local->addr, &remote); spin_lock_bh(&msk->pm.lock); return; } @@ -267,13 +391,86 @@ void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) local.family = remote.family; spin_unlock_bh(&msk->pm.lock); - __mptcp_subflow_connect((struct sock *)msk, 0, &local, &remote); + __mptcp_subflow_connect((struct sock *)msk, &local, &remote); spin_lock_bh(&msk->pm.lock); + + mptcp_pm_announce_addr(msk, &remote, true); +} + +void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk) +{ + struct mptcp_subflow_context *subflow, *tmp; + struct sock *sk = (struct sock *)msk; + + pr_debug("address rm_id %d", msk->pm.rm_id); + + if (!msk->pm.rm_id) + return; + + if (list_empty(&msk->conn_list)) + return; + + list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + int how = RCV_SHUTDOWN | SEND_SHUTDOWN; + long timeout = 0; + + if (msk->pm.rm_id != subflow->remote_id) + continue; + + spin_unlock_bh(&msk->pm.lock); + mptcp_subflow_shutdown(sk, ssk, how); + __mptcp_close_ssk(sk, ssk, subflow, timeout); + spin_lock_bh(&msk->pm.lock); + + msk->pm.add_addr_accepted--; + msk->pm.subflows--; + WRITE_ONCE(msk->pm.accept_addr, true); + + __MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMADDR); + + break; + } +} + +void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id) +{ + struct mptcp_subflow_context *subflow, *tmp; + struct sock *sk = (struct sock *)msk; + + pr_debug("subflow rm_id %d", rm_id); + + if (!rm_id) + return; + + if (list_empty(&msk->conn_list)) + return; + + list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + int how = RCV_SHUTDOWN | SEND_SHUTDOWN; + long timeout = 0; + + if (rm_id != subflow->local_id) + continue; + + spin_unlock_bh(&msk->pm.lock); + mptcp_subflow_shutdown(sk, ssk, how); + __mptcp_close_ssk(sk, ssk, subflow, timeout); + spin_lock_bh(&msk->pm.lock); + + msk->pm.local_addr_used--; + msk->pm.subflows--; + + __MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMSUBFLOW); + + break; + } } static bool address_use_port(struct mptcp_pm_addr_entry *entry) { - return (entry->flags & + return (entry->addr.flags & (MPTCP_PM_ADDR_FLAG_SIGNAL | MPTCP_PM_ADDR_FLAG_SUBFLOW)) == MPTCP_PM_ADDR_FLAG_SIGNAL; } @@ -303,9 +500,9 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, goto out; } - if (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL) + if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL) pernet->add_addr_signal_max++; - if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) + if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) pernet->local_addr_max++; entry->addr.id = pernet->next_id++; @@ -358,8 +555,9 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) if (!entry) return -ENOMEM; - entry->flags = 0; entry->addr = skc_local; + entry->addr.ifindex = 0; + entry->addr.flags = 0; ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); if (ret < 0) kfree(entry); @@ -397,8 +595,8 @@ mptcp_pm_addr_policy[MPTCP_PM_ADDR_ATTR_MAX + 1] = { [MPTCP_PM_ADDR_ATTR_FAMILY] = { .type = NLA_U16, }, [MPTCP_PM_ADDR_ATTR_ID] = { .type = NLA_U8, }, [MPTCP_PM_ADDR_ATTR_ADDR4] = { .type = NLA_U32, }, - [MPTCP_PM_ADDR_ATTR_ADDR6] = { .type = NLA_EXACT_LEN, - .len = sizeof(struct in6_addr), }, + [MPTCP_PM_ADDR_ATTR_ADDR6] = + NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [MPTCP_PM_ADDR_ATTR_PORT] = { .type = NLA_U16 }, [MPTCP_PM_ADDR_ATTR_FLAGS] = { .type = NLA_U32 }, [MPTCP_PM_ADDR_ATTR_IF_IDX] = { .type = NLA_S32 }, @@ -473,14 +671,17 @@ static int mptcp_pm_parse_addr(struct nlattr *attr, struct genl_info *info, entry->addr.addr.s_addr = nla_get_in_addr(tb[addr_addr]); skip_family: - if (tb[MPTCP_PM_ADDR_ATTR_IF_IDX]) - entry->ifindex = nla_get_s32(tb[MPTCP_PM_ADDR_ATTR_IF_IDX]); + if (tb[MPTCP_PM_ADDR_ATTR_IF_IDX]) { + u32 val = nla_get_s32(tb[MPTCP_PM_ADDR_ATTR_IF_IDX]); + + entry->addr.ifindex = val; + } if (tb[MPTCP_PM_ADDR_ATTR_ID]) entry->addr.id = nla_get_u8(tb[MPTCP_PM_ADDR_ATTR_ID]); if (tb[MPTCP_PM_ADDR_ATTR_FLAGS]) - entry->flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]); + entry->addr.flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]); return 0; } @@ -530,6 +731,68 @@ __lookup_addr_by_id(struct pm_nl_pernet *pernet, unsigned int id) return NULL; } +static bool remove_anno_list_by_saddr(struct mptcp_sock *msk, + struct mptcp_addr_info *addr) +{ + struct mptcp_pm_add_entry *entry; + + entry = mptcp_pm_del_add_timer(msk, addr); + if (entry) { + list_del(&entry->list); + kfree(entry); + return true; + } + + return false; +} + +static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, + struct mptcp_addr_info *addr, + bool force) +{ + bool ret; + + ret = remove_anno_list_by_saddr(msk, addr); + if (ret || force) { + spin_lock_bh(&msk->pm.lock); + mptcp_pm_remove_addr(msk, addr->id); + spin_unlock_bh(&msk->pm.lock); + } + return ret; +} + +static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, + struct mptcp_addr_info *addr) +{ + struct mptcp_sock *msk; + long s_slot = 0, s_num = 0; + + pr_debug("remove_id=%d", addr->id); + + while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { + struct sock *sk = (struct sock *)msk; + bool remove_subflow; + + if (list_empty(&msk->conn_list)) { + mptcp_pm_remove_anno_addr(msk, addr, false); + goto next; + } + + lock_sock(sk); + remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr); + mptcp_pm_remove_anno_addr(msk, addr, remove_subflow); + if (remove_subflow) + mptcp_pm_remove_subflow(msk, addr->id); + release_sock(sk); + +next: + sock_put(sk); + cond_resched(); + } + + return 0; +} + static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; @@ -545,19 +808,21 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info) entry = __lookup_addr_by_id(pernet, addr.addr.id); if (!entry) { GENL_SET_ERR_MSG(info, "address not found"); - ret = -EINVAL; - goto out; + spin_unlock_bh(&pernet->lock); + return -EINVAL; } - if (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL) + if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL) pernet->add_addr_signal_max--; - if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) + if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) pernet->local_addr_max--; pernet->addrs--; list_del_rcu(&entry->list); - kfree_rcu(entry, rcu); -out: spin_unlock_bh(&pernet->lock); + + mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), &entry->addr); + kfree_rcu(entry, rcu); + return ret; } @@ -606,10 +871,10 @@ static int mptcp_nl_fill_addr(struct sk_buff *skb, goto nla_put_failure; if (nla_put_u8(skb, MPTCP_PM_ADDR_ATTR_ID, addr->id)) goto nla_put_failure; - if (nla_put_u32(skb, MPTCP_PM_ADDR_ATTR_FLAGS, entry->flags)) + if (nla_put_u32(skb, MPTCP_PM_ADDR_ATTR_FLAGS, entry->addr.flags)) goto nla_put_failure; - if (entry->ifindex && - nla_put_s32(skb, MPTCP_PM_ADDR_ATTR_IF_IDX, entry->ifindex)) + if (entry->addr.ifindex && + nla_put_s32(skb, MPTCP_PM_ADDR_ATTR_IF_IDX, entry->addr.ifindex)) goto nla_put_failure; if (addr->family == AF_INET && @@ -789,7 +1054,7 @@ fail: return -EMSGSIZE; } -static struct genl_ops mptcp_pm_ops[] = { +static const struct genl_small_ops mptcp_pm_ops[] = { { .cmd = MPTCP_PM_CMD_ADD_ADDR, .doit = mptcp_nl_cmd_add_addr, @@ -828,8 +1093,8 @@ static struct genl_family mptcp_genl_family __ro_after_init = { .policy = mptcp_pm_policy, .netnsok = true, .module = THIS_MODULE, - .ops = mptcp_pm_ops, - .n_ops = ARRAY_SIZE(mptcp_pm_ops), + .small_ops = mptcp_pm_ops, + .n_small_ops = ARRAY_SIZE(mptcp_pm_ops), .mcgrps = mptcp_pm_mcgrps, .n_mcgrps = ARRAY_SIZE(mptcp_pm_mcgrps), }; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 5d747c6a610e..e7419fd15d84 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -24,8 +24,6 @@ #include "protocol.h" #include "mib.h" -#define MPTCP_SAME_STATE TCP_MAX_STATES - #if IS_ENABLED(CONFIG_MPTCP_IPV6) struct mptcp6_sock { struct mptcp_sock msk; @@ -34,6 +32,8 @@ struct mptcp6_sock { #endif struct mptcp_skb_cb { + u64 map_seq; + u64 end_seq; u32 offset; }; @@ -112,64 +112,215 @@ static int __mptcp_socket_create(struct mptcp_sock *msk) return 0; } -static void __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, - struct sk_buff *skb, - unsigned int offset, size_t copy_len) +static void mptcp_drop(struct sock *sk, struct sk_buff *skb) +{ + sk_drops_add(sk, skb); + __kfree_skb(skb); +} + +static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, + struct sk_buff *from) +{ + bool fragstolen; + int delta; + + if (MPTCP_SKB_CB(from)->offset || + !skb_try_coalesce(to, from, &fragstolen, &delta)) + return false; + + pr_debug("colesced seq %llx into %llx new len %d new end seq %llx", + MPTCP_SKB_CB(from)->map_seq, MPTCP_SKB_CB(to)->map_seq, + to->len, MPTCP_SKB_CB(from)->end_seq); + MPTCP_SKB_CB(to)->end_seq = MPTCP_SKB_CB(from)->end_seq; + kfree_skb_partial(from, fragstolen); + atomic_add(delta, &sk->sk_rmem_alloc); + sk_mem_charge(sk, delta); + return true; +} + +static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to, + struct sk_buff *from) +{ + if (MPTCP_SKB_CB(from)->map_seq != MPTCP_SKB_CB(to)->end_seq) + return false; + + return mptcp_try_coalesce((struct sock *)msk, to, from); +} + +/* "inspired" by tcp_data_queue_ofo(), main differences: + * - use mptcp seqs + * - don't cope with sacks + */ +static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb) { struct sock *sk = (struct sock *)msk; - struct sk_buff *tail; + struct rb_node **p, *parent; + u64 seq, end_seq, max_seq; + struct sk_buff *skb1; + int space; + + seq = MPTCP_SKB_CB(skb)->map_seq; + end_seq = MPTCP_SKB_CB(skb)->end_seq; + space = tcp_space(sk); + max_seq = space > 0 ? space + msk->ack_seq : msk->ack_seq; + + pr_debug("msk=%p seq=%llx limit=%llx empty=%d", msk, seq, max_seq, + RB_EMPTY_ROOT(&msk->out_of_order_queue)); + if (after64(seq, max_seq)) { + /* out of window */ + mptcp_drop(sk, skb); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_NODSSWINDOW); + return; + } - __skb_unlink(skb, &ssk->sk_receive_queue); + p = &msk->out_of_order_queue.rb_node; + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUE); + if (RB_EMPTY_ROOT(&msk->out_of_order_queue)) { + rb_link_node(&skb->rbnode, NULL, p); + rb_insert_color(&skb->rbnode, &msk->out_of_order_queue); + msk->ooo_last_skb = skb; + goto end; + } - skb_ext_reset(skb); - skb_orphan(skb); - WRITE_ONCE(msk->ack_seq, msk->ack_seq + copy_len); + /* with 2 subflows, adding at end of ooo queue is quite likely + * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup. + */ + if (mptcp_ooo_try_coalesce(msk, msk->ooo_last_skb, skb)) { + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOMERGE); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUETAIL); + return; + } - tail = skb_peek_tail(&sk->sk_receive_queue); - if (offset == 0 && tail) { - bool fragstolen; - int delta; + /* Can avoid an rbtree lookup if we are adding skb after ooo_last_skb */ + if (!before64(seq, MPTCP_SKB_CB(msk->ooo_last_skb)->end_seq)) { + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUETAIL); + parent = &msk->ooo_last_skb->rbnode; + p = &parent->rb_right; + goto insert; + } - if (skb_try_coalesce(tail, skb, &fragstolen, &delta)) { - kfree_skb_partial(skb, fragstolen); - atomic_add(delta, &sk->sk_rmem_alloc); - sk_mem_charge(sk, delta); + /* Find place to insert this segment. Handle overlaps on the way. */ + parent = NULL; + while (*p) { + parent = *p; + skb1 = rb_to_skb(parent); + if (before64(seq, MPTCP_SKB_CB(skb1)->map_seq)) { + p = &parent->rb_left; + continue; + } + if (before64(seq, MPTCP_SKB_CB(skb1)->end_seq)) { + if (!after64(end_seq, MPTCP_SKB_CB(skb1)->end_seq)) { + /* All the bits are present. Drop. */ + mptcp_drop(sk, skb); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); + return; + } + if (after64(seq, MPTCP_SKB_CB(skb1)->map_seq)) { + /* partial overlap: + * | skb | + * | skb1 | + * continue traversing + */ + } else { + /* skb's seq == skb1's seq and skb covers skb1. + * Replace skb1 with skb. + */ + rb_replace_node(&skb1->rbnode, &skb->rbnode, + &msk->out_of_order_queue); + mptcp_drop(sk, skb1); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); + goto merge_right; + } + } else if (mptcp_ooo_try_coalesce(msk, skb1, skb)) { + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOMERGE); return; } + p = &parent->rb_right; } - skb_set_owner_r(skb, sk); - __skb_queue_tail(&sk->sk_receive_queue, skb); - MPTCP_SKB_CB(skb)->offset = offset; -} +insert: + /* Insert segment into RB tree. */ + rb_link_node(&skb->rbnode, parent, p); + rb_insert_color(&skb->rbnode, &msk->out_of_order_queue); -static void mptcp_stop_timer(struct sock *sk) -{ - struct inet_connection_sock *icsk = inet_csk(sk); +merge_right: + /* Remove other segments covered by skb. */ + while ((skb1 = skb_rb_next(skb)) != NULL) { + if (before64(end_seq, MPTCP_SKB_CB(skb1)->end_seq)) + break; + rb_erase(&skb1->rbnode, &msk->out_of_order_queue); + mptcp_drop(sk, skb1); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); + } + /* If there is no skb after us, we are the last_skb ! */ + if (!skb1) + msk->ooo_last_skb = skb; - sk_stop_timer(sk, &icsk->icsk_retransmit_timer); - mptcp_sk(sk)->timer_ival = 0; +end: + skb_condense(skb); + skb_set_owner_r(skb, sk); } -/* both sockets must be locked */ -static bool mptcp_subflow_dsn_valid(const struct mptcp_sock *msk, - struct sock *ssk) +static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, + struct sk_buff *skb, unsigned int offset, + size_t copy_len) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); - u64 dsn = mptcp_subflow_get_mapped_dsn(subflow); + struct sock *sk = (struct sock *)msk; + struct sk_buff *tail; - /* revalidate data sequence number. - * - * mptcp_subflow_data_available() is usually called - * without msk lock. Its unlikely (but possible) - * that msk->ack_seq has been advanced since the last - * call found in-sequence data. + __skb_unlink(skb, &ssk->sk_receive_queue); + + skb_ext_reset(skb); + skb_orphan(skb); + + /* try to fetch required memory from subflow */ + if (!sk_rmem_schedule(sk, skb, skb->truesize)) { + if (ssk->sk_forward_alloc < skb->truesize) + goto drop; + __sk_mem_reclaim(ssk, skb->truesize); + if (!sk_rmem_schedule(sk, skb, skb->truesize)) + goto drop; + } + + /* the skb map_seq accounts for the skb offset: + * mptcp_subflow_get_mapped_dsn() is based on the current tp->copied_seq + * value */ - if (likely(dsn == msk->ack_seq)) + MPTCP_SKB_CB(skb)->map_seq = mptcp_subflow_get_mapped_dsn(subflow); + MPTCP_SKB_CB(skb)->end_seq = MPTCP_SKB_CB(skb)->map_seq + copy_len; + MPTCP_SKB_CB(skb)->offset = offset; + + if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) { + /* in sequence */ + WRITE_ONCE(msk->ack_seq, msk->ack_seq + copy_len); + tail = skb_peek_tail(&sk->sk_receive_queue); + if (tail && mptcp_try_coalesce(sk, tail, skb)) + return true; + + skb_set_owner_r(skb, sk); + __skb_queue_tail(&sk->sk_receive_queue, skb); return true; + } else if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq)) { + mptcp_data_queue_ofo(msk, skb); + return false; + } - subflow->data_avail = 0; - return mptcp_subflow_data_available(ssk); + /* old data, keep it simple and drop the whole pkt, sender + * will retransmit as needed, if needed. + */ + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); +drop: + mptcp_drop(sk, skb); + return false; +} + +static void mptcp_stop_timer(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + sk_stop_timer(sk, &icsk->icsk_retransmit_timer); + mptcp_sk(sk)->timer_ival = 0; } static void mptcp_check_data_fin_ack(struct sock *sk) @@ -313,14 +464,12 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, unsigned int moved = 0; bool more_data_avail; struct tcp_sock *tp; + u32 old_copied_seq; bool done = false; - if (!mptcp_subflow_dsn_valid(msk, ssk)) { - *bytes = 0; - return false; - } - + pr_debug("msk=%p ssk=%p", msk, ssk); tp = tcp_sk(ssk); + old_copied_seq = tp->copied_seq; do { u32 map_remaining, offset; u32 seq = tp->copied_seq; @@ -332,8 +481,15 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, mptcp_subflow_get_map_offset(subflow); skb = skb_peek(&ssk->sk_receive_queue); - if (!skb) + if (!skb) { + /* if no data is found, a racing workqueue/recvmsg + * already processed the new data, stop here or we + * can enter an infinite loop + */ + if (!moved) + done = true; break; + } if (__mptcp_check_fallback(msk)) { /* if we are running under the workqueue, TCP could have @@ -357,9 +513,9 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, if (tp->urg_data) done = true; - __mptcp_move_skb(msk, ssk, skb, offset, len); + if (__mptcp_move_skb(msk, ssk, skb, offset, len)) + moved += len; seq += len; - moved += len; if (WARN_ON_ONCE(map_remaining < len)) break; @@ -378,20 +534,56 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, } } while (more_data_avail); - *bytes = moved; - - /* If the moves have caught up with the DATA_FIN sequence number - * it's time to ack the DATA_FIN and change socket state, but - * this is not a good place to change state. Let the workqueue - * do it. - */ - if (mptcp_pending_data_fin(sk, NULL) && - schedule_work(&msk->work)) - sock_hold(sk); + *bytes += moved; + if (tp->copied_seq != old_copied_seq) + tcp_cleanup_rbuf(ssk, 1); return done; } +static bool mptcp_ofo_queue(struct mptcp_sock *msk) +{ + struct sock *sk = (struct sock *)msk; + struct sk_buff *skb, *tail; + bool moved = false; + struct rb_node *p; + u64 end_seq; + + p = rb_first(&msk->out_of_order_queue); + pr_debug("msk=%p empty=%d", msk, RB_EMPTY_ROOT(&msk->out_of_order_queue)); + while (p) { + skb = rb_to_skb(p); + if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq)) + break; + + p = rb_next(p); + rb_erase(&skb->rbnode, &msk->out_of_order_queue); + + if (unlikely(!after64(MPTCP_SKB_CB(skb)->end_seq, + msk->ack_seq))) { + mptcp_drop(sk, skb); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); + continue; + } + + end_seq = MPTCP_SKB_CB(skb)->end_seq; + tail = skb_peek_tail(&sk->sk_receive_queue); + if (!tail || !mptcp_ooo_try_coalesce(msk, tail, skb)) { + int delta = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq; + + /* skip overlapping data, if any */ + pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d", + MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq, + delta); + MPTCP_SKB_CB(skb)->offset += delta; + __skb_queue_tail(&sk->sk_receive_queue, skb); + } + msk->ack_seq = end_seq; + moved = true; + } + return moved; +} + /* In most cases we will be able to lock the mptcp socket. If its already * owned, we need to defer to the work queue to avoid ABBA deadlock. */ @@ -407,8 +599,19 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) return false; /* must re-check after taking the lock */ - if (!READ_ONCE(sk->sk_lock.owned)) + if (!READ_ONCE(sk->sk_lock.owned)) { __mptcp_move_skbs_from_subflow(msk, ssk, &moved); + mptcp_ofo_queue(msk); + + /* If the moves have caught up with the DATA_FIN sequence number + * it's time to ack the DATA_FIN and change socket state, but + * this is not a good place to change state. Let the workqueue + * do it. + */ + if (mptcp_pending_data_fin(sk, NULL) && + schedule_work(&msk->work)) + sock_hold(sk); + } spin_unlock_bh(&sk->sk_lock.slock); @@ -417,9 +620,17 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) void mptcp_data_ready(struct sock *sk, struct sock *ssk) { + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct mptcp_sock *msk = mptcp_sk(sk); + bool wake; - set_bit(MPTCP_DATA_READY, &msk->flags); + /* move_skbs_to_msk below can legitly clear the data_avail flag, + * but we will need later to properly woke the reader, cache its + * value + */ + wake = subflow->data_avail == MPTCP_SUBFLOW_DATA_AVAIL; + if (wake) + set_bit(MPTCP_DATA_READY, &msk->flags); if (atomic_read(&sk->sk_rmem_alloc) < READ_ONCE(sk->sk_rcvbuf) && move_skbs_to_msk(msk, ssk)) @@ -440,7 +651,8 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) move_skbs_to_msk(msk, ssk); } wake: - sk->sk_data_ready(sk); + if (wake) + sk->sk_data_ready(sk); } static void __mptcp_flush_join_list(struct mptcp_sock *msk) @@ -474,7 +686,7 @@ void mptcp_data_acked(struct sock *sk) { mptcp_reset_timer(sk); - if ((!sk_stream_is_writeable(sk) || + if ((!test_bit(MPTCP_SEND_SPACE, &mptcp_sk(sk)->flags) || (inet_sk_state_load(sk) != TCP_ESTABLISHED)) && schedule_work(&mptcp_sk(sk)->work)) sock_hold(sk); @@ -569,6 +781,20 @@ static void dfrag_clear(struct sock *sk, struct mptcp_data_frag *dfrag) put_page(dfrag->page); } +static bool mptcp_is_writeable(struct mptcp_sock *msk) +{ + struct mptcp_subflow_context *subflow; + + if (!sk_stream_is_writeable((struct sock *)msk)) + return false; + + mptcp_for_each_subflow(msk, subflow) { + if (sk_stream_is_writeable(subflow->tcp_sock)) + return true; + } + return false; +} + static void mptcp_clean_una(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -611,8 +837,15 @@ out: sk_mem_reclaim_partial(sk); /* Only wake up writers if a subflow is ready */ - if (test_bit(MPTCP_SEND_SPACE, &msk->flags)) + if (mptcp_is_writeable(msk)) { + set_bit(MPTCP_SEND_SPACE, &mptcp_sk(sk)->flags); + smp_mb__after_atomic(); + + /* set SEND_SPACE before sk_stream_write_space clears + * NOSPACE + */ sk_stream_write_space(sk); + } } } @@ -803,60 +1036,128 @@ out: return ret; } -static void mptcp_nospace(struct mptcp_sock *msk, struct socket *sock) +static void mptcp_nospace(struct mptcp_sock *msk) { + struct mptcp_subflow_context *subflow; + clear_bit(MPTCP_SEND_SPACE, &msk->flags); smp_mb__after_atomic(); /* msk->flags is changed by write_space cb */ - /* enables sk->write_space() callbacks */ - set_bit(SOCK_NOSPACE, &sock->flags); + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + struct socket *sock = READ_ONCE(ssk->sk_socket); + + /* enables ssk->write_space() callbacks */ + if (sock) + set_bit(SOCK_NOSPACE, &sock->flags); + } } -static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) +static bool mptcp_subflow_active(struct mptcp_subflow_context *subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + /* can't send if JOIN hasn't completed yet (i.e. is usable for mptcp) */ + if (subflow->request_join && !subflow->fully_established) + return false; + + /* only send if our side has not closed yet */ + return ((1 << ssk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)); +} + +#define MPTCP_SEND_BURST_SIZE ((1 << 16) - \ + sizeof(struct tcphdr) - \ + MAX_TCP_OPTION_SPACE - \ + sizeof(struct ipv6hdr) - \ + sizeof(struct frag_hdr)) + +struct subflow_send_info { + struct sock *ssk; + u64 ratio; +}; + +static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk, + u32 *sndbuf) +{ + struct subflow_send_info send_info[2]; struct mptcp_subflow_context *subflow; - struct sock *backup = NULL; + int i, nr_active = 0; + struct sock *ssk; + u64 ratio; + u32 pace; - sock_owned_by_me((const struct sock *)msk); + sock_owned_by_me((struct sock *)msk); + *sndbuf = 0; if (!mptcp_ext_cache_refill(msk)) return NULL; + if (__mptcp_check_fallback(msk)) { + if (!msk->first) + return NULL; + *sndbuf = msk->first->sk_sndbuf; + return sk_stream_memory_free(msk->first) ? msk->first : NULL; + } + + /* 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_for_each_subflow(msk, subflow) { + ssk = mptcp_subflow_tcp_sock(subflow); + *sndbuf = max(tcp_sk(ssk)->snd_wnd, *sndbuf); + } + return msk->last_snd; + } + + /* pick the subflow with the lower wmem/wspace ratio */ + for (i = 0; i < 2; ++i) { + send_info[i].ssk = NULL; + send_info[i].ratio = -1; + } mptcp_for_each_subflow(msk, subflow) { - struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + ssk = mptcp_subflow_tcp_sock(subflow); + if (!mptcp_subflow_active(subflow)) + continue; - if (!sk_stream_memory_free(ssk)) { - struct socket *sock = ssk->sk_socket; + nr_active += !subflow->backup; + *sndbuf = max(tcp_sk(ssk)->snd_wnd, *sndbuf); + if (!sk_stream_memory_free(subflow->tcp_sock)) + continue; - if (sock) - mptcp_nospace(msk, sock); + pace = READ_ONCE(ssk->sk_pacing_rate); + if (!pace) + continue; - return NULL; + ratio = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32, + pace); + if (ratio < send_info[subflow->backup].ratio) { + send_info[subflow->backup].ssk = ssk; + send_info[subflow->backup].ratio = ratio; } + } - if (subflow->backup) { - if (!backup) - backup = ssk; + pr_debug("msk=%p nr_active=%d ssk=%p:%lld backup=%p:%lld", + msk, nr_active, send_info[0].ssk, send_info[0].ratio, + send_info[1].ssk, send_info[1].ratio); - continue; - } + /* pick the best backup if no other subflow is active */ + if (!nr_active) + send_info[0].ssk = send_info[1].ssk; - return ssk; + if (send_info[0].ssk) { + msk->last_snd = send_info[0].ssk; + msk->snd_burst = min_t(int, MPTCP_SEND_BURST_SIZE, + sk_stream_wspace(msk->last_snd)); + return msk->last_snd; } - - return backup; + return NULL; } -static void ssk_check_wmem(struct mptcp_sock *msk, struct sock *ssk) +static void ssk_check_wmem(struct mptcp_sock *msk) { - struct socket *sock; - - if (likely(sk_stream_is_writeable(ssk))) - return; - - sock = READ_ONCE(ssk->sk_socket); - if (sock) - mptcp_nospace(msk, sock); + if (unlikely(!mptcp_is_writeable(msk))) + mptcp_nospace(msk); } static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) @@ -866,6 +1167,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct page_frag *pfrag; size_t copied = 0; struct sock *ssk; + u32 sndbuf; bool tx_ok; long timeo; @@ -892,7 +1194,7 @@ restart: } __mptcp_flush_join_list(msk); - ssk = mptcp_subflow_get_send(msk); + ssk = mptcp_subflow_get_send(msk, &sndbuf); while (!sk_stream_memory_free(sk) || !ssk || !mptcp_page_frag_refill(ssk, pfrag)) { @@ -909,19 +1211,25 @@ restart: mptcp_reset_timer(sk); } + mptcp_nospace(msk); ret = sk_stream_wait_memory(sk, &timeo); if (ret) goto out; mptcp_clean_una(sk); - ssk = mptcp_subflow_get_send(msk); + ssk = mptcp_subflow_get_send(msk, &sndbuf); if (list_empty(&msk->conn_list)) { ret = -ENOTCONN; goto out; } } + /* do auto tuning */ + if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK) && + sndbuf > READ_ONCE(sk->sk_sndbuf)) + WRITE_ONCE(sk->sk_sndbuf, sndbuf); + pr_debug("conn_list->subflow=%p", ssk); lock_sock(ssk); @@ -938,6 +1246,10 @@ restart: break; } + /* burst can be negative, we will try move to the next subflow + * at selection time, if possible. + */ + msk->snd_burst -= ret; copied += ret; tx_ok = msg_data_left(msg); @@ -947,7 +1259,6 @@ restart: if (!sk_stream_memory_free(ssk) || !mptcp_page_frag_refill(ssk, pfrag) || !mptcp_ext_cache_refill(msk)) { - set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); tcp_push(ssk, msg->msg_flags, mss_now, tcp_sk(ssk)->nonagle, size_goal); mptcp_set_timeout(sk, ssk); @@ -995,9 +1306,9 @@ restart: mptcp_reset_timer(sk); } - ssk_check_wmem(msk, ssk); release_sock(ssk); out: + ssk_check_wmem(msk); release_sock(sk); return copied ? : ret; } @@ -1135,10 +1446,14 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) */ mptcp_for_each_subflow(msk, subflow) { struct sock *ssk; + bool slow; ssk = mptcp_subflow_tcp_sock(subflow); + slow = lock_sock_fast(ssk); WRITE_ONCE(ssk->sk_rcvbuf, rcvbuf); tcp_sk(ssk)->window_clamp = window_clamp; + tcp_cleanup_rbuf(ssk, 1); + unlock_sock_fast(ssk, slow); } } } @@ -1154,6 +1469,11 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk) unsigned int moved = 0; bool done; + /* avoid looping forever below on racing close */ + if (((struct sock *)msk)->sk_state == TCP_CLOSE) + return false; + + __mptcp_flush_join_list(msk); do { struct sock *ssk = mptcp_subflow_recv_lookup(msk); @@ -1165,7 +1485,11 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk) release_sock(ssk); } while (!done); - return moved > 0; + if (mptcp_ofo_queue(msk) || moved > 0) { + mptcp_check_data_fin((struct sock *)msk); + return true; + } + return false; } static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, @@ -1261,6 +1585,9 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, set_bit(MPTCP_DATA_READY, &msk->flags); } out_err: + pr_debug("msk=%p data_ready=%d rx queue empty=%d copied=%d", + msk, test_bit(MPTCP_DATA_READY, &msk->flags), + skb_queue_empty(&sk->sk_receive_queue), copied); mptcp_rcv_space_adjust(msk, copied); release_sock(sk); @@ -1311,9 +1638,15 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk) sock_owned_by_me((const struct sock *)msk); + if (__mptcp_check_fallback(msk)) + return msk->first; + mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + if (!mptcp_subflow_active(subflow)) + continue; + /* still data outstanding at TCP level? Don't retransmit. */ if (!tcp_write_queue_empty(ssk)) return NULL; @@ -1338,9 +1671,9 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk) * so we need to use tcp_close() after detaching them from the mptcp * parent socket. */ -static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, - struct mptcp_subflow_context *subflow, - long timeout) +void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, + struct mptcp_subflow_context *subflow, + long timeout) { struct socket *sock = READ_ONCE(ssk->sk_socket); @@ -1371,6 +1704,10 @@ static void pm_work(struct mptcp_sock *msk) pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED); mptcp_pm_nl_add_addr_received(msk); } + if (pm->status & BIT(MPTCP_PM_RM_ADDR_RECEIVED)) { + pm->status &= ~BIT(MPTCP_PM_RM_ADDR_RECEIVED); + mptcp_pm_nl_rm_addr_received(msk); + } if (pm->status & BIT(MPTCP_PM_ESTABLISHED)) { pm->status &= ~BIT(MPTCP_PM_ESTABLISHED); mptcp_pm_nl_fully_established(msk); @@ -1383,6 +1720,20 @@ static void pm_work(struct mptcp_sock *msk) spin_unlock_bh(&msk->pm.lock); } +static void __mptcp_close_subflow(struct mptcp_sock *msk) +{ + struct mptcp_subflow_context *subflow, *tmp; + + list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + if (inet_sk_state_load(ssk) != TCP_CLOSE) + continue; + + __mptcp_close_ssk((struct sock *)msk, ssk, subflow, 0); + } +} + static void mptcp_worker(struct work_struct *work) { struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work); @@ -1400,6 +1751,9 @@ static void mptcp_worker(struct work_struct *work) mptcp_clean_una(sk); mptcp_check_data_fin_ack(sk); __mptcp_flush_join_list(msk); + if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) + __mptcp_close_subflow(msk); + __mptcp_move_skbs(msk); if (msk->pm.status) @@ -1474,6 +1828,7 @@ static int __mptcp_init_sock(struct sock *sk) INIT_LIST_HEAD(&msk->rtx_queue); __set_bit(MPTCP_SEND_SPACE, &msk->flags); INIT_WORK(&msk->work, mptcp_worker); + msk->out_of_order_queue = RB_ROOT; msk->first = NULL; inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; @@ -1491,23 +1846,23 @@ static int mptcp_init_sock(struct sock *sk) struct net *net = sock_net(sk); int ret; + ret = __mptcp_init_sock(sk); + if (ret) + return ret; + if (!mptcp_is_enabled(net)) return -ENOPROTOOPT; if (unlikely(!net->mib.mptcp_statistics) && !mptcp_mib_alloc(net)) return -ENOMEM; - ret = __mptcp_init_sock(sk); - if (ret) - return ret; - ret = __mptcp_socket_create(mptcp_sk(sk)); if (ret) return ret; sk_sockets_allocated_inc(sk); sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1]; - sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[2]; + sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1]; return 0; } @@ -1531,7 +1886,7 @@ static void mptcp_cancel_work(struct sock *sk) sock_put(sk); } -static void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) +void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) { lock_sock(ssk); @@ -1809,14 +2164,21 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, return newsk; } +void mptcp_destroy_common(struct mptcp_sock *msk) +{ + skb_rbtree_purge(&msk->out_of_order_queue); + mptcp_token_destroy(msk); + mptcp_pm_free_anno_list(msk); +} + static void mptcp_destroy(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); - mptcp_token_destroy(msk); if (msk->cached_ext) __skb_ext_put(msk->cached_ext); + mptcp_destroy_common(msk); sk_sockets_allocated_dec(sk); } @@ -2288,13 +2650,13 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, sock_poll_wait(file, sock, wait); state = inet_sk_state_load(sk); + pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags); if (state == TCP_LISTEN) return mptcp_check_readable(msk); if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) { mask |= mptcp_check_readable(msk); - if (sk_stream_is_writeable(sk) && - test_bit(MPTCP_SEND_SPACE, &msk->flags)) + if (test_bit(MPTCP_SEND_SPACE, &msk->flags)) mask |= EPOLLOUT | EPOLLWRNORM; } if (sk->sk_shutdown & RCV_SHUTDOWN) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 20f04ac85409..13ab89dc1914 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -90,6 +90,7 @@ #define MPTCP_WORK_RTX 2 #define MPTCP_WORK_EOF 3 #define MPTCP_FALLBACK_DONE 4 +#define MPTCP_WORK_CLOSE_SUBFLOW 5 struct mptcp_options_received { u64 sndr_key; @@ -140,6 +141,8 @@ struct mptcp_addr_info { sa_family_t family; __be16 port; u8 id; + u8 flags; + int ifindex; union { struct in_addr addr; #if IS_ENABLED(CONFIG_MPTCP_IPV6) @@ -150,6 +153,7 @@ struct mptcp_addr_info { enum mptcp_pm_status { MPTCP_PM_ADD_ADDR_RECEIVED, + MPTCP_PM_RM_ADDR_RECEIVED, MPTCP_PM_ESTABLISHED, MPTCP_PM_SUBFLOW_ESTABLISHED, }; @@ -157,14 +161,17 @@ enum mptcp_pm_status { struct mptcp_pm_data { struct mptcp_addr_info local; struct mptcp_addr_info remote; + struct list_head anno_list; spinlock_t lock; /*protects the whole PM data */ - bool addr_signal; + bool add_addr_signal; + bool rm_addr_signal; bool server_side; bool work_pending; bool accept_addr; bool accept_subflow; + bool add_addr_echo; u8 add_addr_signaled; u8 add_addr_accepted; u8 local_addr_used; @@ -174,6 +181,7 @@ struct mptcp_pm_data { u8 local_addr_max; u8 subflows_max; u8 status; + u8 rm_id; }; struct mptcp_data_frag { @@ -194,6 +202,8 @@ struct mptcp_sock { u64 write_seq; u64 ack_seq; u64 rcv_data_fin_seq; + struct sock *last_snd; + int snd_burst; atomic64_t snd_una; unsigned long timer_ival; u32 token; @@ -202,8 +212,11 @@ struct mptcp_sock { bool fully_established; bool rcv_data_fin; bool snd_data_fin_enable; + bool use_64bit_ack; /* Set when we received a 64-bit DSN */ spinlock_t join_list_lock; struct work_struct work; + struct sk_buff *ooo_last_skb; + struct rb_root out_of_order_queue; struct list_head conn_list; struct list_head rtx_queue; struct list_head join_list; @@ -268,6 +281,12 @@ mptcp_subflow_rsk(const struct request_sock *rsk) return (struct mptcp_subflow_request_sock *)rsk; } +enum mptcp_data_avail { + MPTCP_SUBFLOW_NODATA, + MPTCP_SUBFLOW_DATA_AVAIL, + MPTCP_SUBFLOW_OOO_DATA +}; + /* MPTCP subflow context */ struct mptcp_subflow_context { struct list_head node;/* conn_list of subflows */ @@ -292,10 +311,9 @@ struct mptcp_subflow_context { map_valid : 1, mpc_map : 1, backup : 1, - data_avail : 1, rx_eof : 1, - use_64bit_ack : 1, /* Set when we received a 64-bit DSN */ can_ack : 1; /* only after processing the remote a key */ + enum mptcp_data_avail data_avail; u32 remote_nonce; u64 thmac; u32 local_nonce; @@ -348,10 +366,14 @@ void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, struct mptcp_options_received *mp_opt); 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, + long timeout); +void mptcp_subflow_reset(struct sock *ssk); /* called with sk socket lock held */ -int __mptcp_subflow_connect(struct sock *sk, int ifindex, - const struct mptcp_addr_info *loc, +int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, const struct mptcp_addr_info *remote); int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock); @@ -388,6 +410,7 @@ bool mptcp_finish_join(struct sock *sk); void mptcp_data_acked(struct sock *sk); void mptcp_subflow_eof(struct sock *sk); bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit); +void mptcp_destroy_common(struct mptcp_sock *msk); void __init mptcp_token_init(void); static inline void mptcp_token_init_request(struct request_sock *req) @@ -421,26 +444,40 @@ void mptcp_pm_subflow_established(struct mptcp_sock *msk, void mptcp_pm_subflow_closed(struct mptcp_sock *msk, u8 id); void mptcp_pm_add_addr_received(struct mptcp_sock *msk, const struct mptcp_addr_info *addr); +void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, u8 rm_id); +void mptcp_pm_free_anno_list(struct mptcp_sock *msk); +struct mptcp_pm_add_entry * +mptcp_pm_del_add_timer(struct mptcp_sock *msk, + struct mptcp_addr_info *addr); int mptcp_pm_announce_addr(struct mptcp_sock *msk, - const struct mptcp_addr_info *addr); + const struct mptcp_addr_info *addr, + bool echo); int mptcp_pm_remove_addr(struct mptcp_sock *msk, u8 local_id); -int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 remote_id); +int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 local_id); + +static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk) +{ + return READ_ONCE(msk->pm.add_addr_signal); +} -static inline bool mptcp_pm_should_signal(struct mptcp_sock *msk) +static inline bool mptcp_pm_should_rm_signal(struct mptcp_sock *msk) { - return READ_ONCE(msk->pm.addr_signal); + return READ_ONCE(msk->pm.rm_addr_signal); } -static inline unsigned int mptcp_add_addr_len(int family) +static inline unsigned int mptcp_add_addr_len(int family, bool echo) { if (family == AF_INET) - return TCPOLEN_MPTCP_ADD_ADDR; - return TCPOLEN_MPTCP_ADD_ADDR6; + return echo ? TCPOLEN_MPTCP_ADD_ADDR_BASE + : TCPOLEN_MPTCP_ADD_ADDR; + return echo ? TCPOLEN_MPTCP_ADD_ADDR6_BASE : TCPOLEN_MPTCP_ADD_ADDR6; } -bool mptcp_pm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, - struct mptcp_addr_info *saddr); +bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int remaining, + struct mptcp_addr_info *saddr, bool *echo); +bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, + u8 *rm_id); int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); void __init mptcp_pm_nl_init(void); @@ -448,6 +485,8 @@ void mptcp_pm_nl_data_init(struct mptcp_sock *msk); void mptcp_pm_nl_fully_established(struct mptcp_sock *msk); void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk); void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk); +void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk); +void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id); int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); static inline struct mptcp_ext *mptcp_get_ext(struct sk_buff *skb) @@ -464,12 +503,12 @@ static inline bool before64(__u64 seq1, __u64 seq2) void mptcp_diag_subflow_init(struct tcp_ulp_ops *ops); -static inline bool __mptcp_check_fallback(struct mptcp_sock *msk) +static inline bool __mptcp_check_fallback(const struct mptcp_sock *msk) { return test_bit(MPTCP_FALLBACK_DONE, &msk->flags); } -static inline bool mptcp_check_fallback(struct sock *sk) +static inline bool mptcp_check_fallback(const struct sock *sk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 6f035af1c9d2..ac4a1fe3550b 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -20,6 +20,7 @@ #include <net/ip6_route.h> #endif #include <net/mptcp.h> +#include <uapi/linux/mptcp.h> #include "protocol.h" #include "mib.h" @@ -270,6 +271,19 @@ static bool subflow_thmac_valid(struct mptcp_subflow_context *subflow) return thmac == subflow->thmac; } +void mptcp_subflow_reset(struct sock *ssk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + struct sock *sk = subflow->conn; + + tcp_set_state(ssk, TCP_CLOSE); + tcp_send_active_reset(ssk, GFP_ATOMIC); + tcp_done(ssk); + if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags) && + schedule_work(&mptcp_sk(sk)->work)) + sock_hold(sk); +} + static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); @@ -342,8 +356,7 @@ fallback: return; do_reset: - tcp_send_active_reset(sk, GFP_ATOMIC); - tcp_done(sk); + mptcp_subflow_reset(sk); } struct request_sock_ops mptcp_subflow_request_sock_ops; @@ -434,7 +447,7 @@ static void mptcp_sock_destruct(struct sock *sk) sock_orphan(sk); } - mptcp_token_destroy(mptcp_sk(sk)); + mptcp_destroy_common(mptcp_sk(sk)); inet_sock_destruct(sk); } @@ -769,12 +782,11 @@ static enum mapping_status get_mapping_status(struct sock *ssk, if (!mpext->dsn64) { map_seq = expand_seq(subflow->map_seq, subflow->map_data_len, mpext->data_seq); - subflow->use_64bit_ack = 0; pr_debug("expanded seq=%llu", subflow->map_seq); } else { map_seq = mpext->data_seq; - subflow->use_64bit_ack = 1; } + WRITE_ONCE(mptcp_sk(subflow->conn)->use_64bit_ack, !!mpext->dsn64); if (subflow->map_valid) { /* Allow replacing only with an identical map */ @@ -817,16 +829,25 @@ validate_seq: return MAPPING_OK; } -static int subflow_read_actor(read_descriptor_t *desc, - struct sk_buff *skb, - unsigned int offset, size_t len) +static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb, + u64 limit) { - size_t copy_len = min(desc->count, len); - - desc->count -= copy_len; - - pr_debug("flushed %zu bytes, %zu left", copy_len, desc->count); - return copy_len; + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + bool fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; + u32 incr; + + incr = limit >= skb->len ? skb->len + fin : limit; + + pr_debug("discarding=%d len=%d seq=%d", incr, skb->len, + subflow->map_subflow_seq); + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA); + tcp_sk(ssk)->copied_seq += incr; + if (!before(tcp_sk(ssk)->copied_seq, TCP_SKB_CB(skb)->end_seq)) + sk_eat_skb(ssk, skb); + if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) + subflow->map_valid = 0; + if (incr) + tcp_cleanup_rbuf(ssk, incr); } static bool subflow_check_data_avail(struct sock *ssk) @@ -838,13 +859,13 @@ static bool subflow_check_data_avail(struct sock *ssk) pr_debug("msk=%p ssk=%p data_avail=%d skb=%p", subflow->conn, ssk, subflow->data_avail, skb_peek(&ssk->sk_receive_queue)); + if (!skb_peek(&ssk->sk_receive_queue)) + subflow->data_avail = 0; if (subflow->data_avail) return true; msk = mptcp_sk(subflow->conn); for (;;) { - u32 map_remaining; - size_t delta; u64 ack_seq; u64 old_ack; @@ -862,6 +883,7 @@ static bool subflow_check_data_avail(struct sock *ssk) subflow->map_data_len = skb->len; subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq - subflow->ssn_offset; + subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL; return true; } @@ -889,42 +911,18 @@ static bool subflow_check_data_avail(struct sock *ssk) ack_seq = mptcp_subflow_get_mapped_dsn(subflow); pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack, ack_seq); - if (ack_seq == old_ack) + if (ack_seq == old_ack) { + subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL; break; + } else if (after64(ack_seq, old_ack)) { + subflow->data_avail = MPTCP_SUBFLOW_OOO_DATA; + break; + } /* only accept in-sequence mapping. Old values are spurious - * retransmission; we can hit "future" values on active backup - * subflow switch, we relay on retransmissions to get - * in-sequence data. - * Cuncurrent subflows support will require subflow data - * reordering + * retransmission */ - map_remaining = subflow->map_data_len - - mptcp_subflow_get_map_offset(subflow); - if (before64(ack_seq, old_ack)) - delta = min_t(size_t, old_ack - ack_seq, map_remaining); - else - delta = min_t(size_t, ack_seq - old_ack, map_remaining); - - /* discard mapped data */ - pr_debug("discarding %zu bytes, current map len=%d", delta, - map_remaining); - if (delta) { - read_descriptor_t desc = { - .count = delta, - }; - int ret; - - ret = tcp_read_sock(ssk, &desc, subflow_read_actor); - if (ret < 0) { - ssk->sk_err = -ret; - goto fatal; - } - if (ret < delta) - return false; - if (delta == map_remaining) - subflow->map_valid = 0; - } + mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq); } return true; @@ -935,13 +933,13 @@ fatal: ssk->sk_error_report(ssk); tcp_set_state(ssk, TCP_CLOSE); tcp_send_active_reset(ssk, GFP_ATOMIC); + subflow->data_avail = 0; return false; } bool mptcp_subflow_data_available(struct sock *sk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - struct sk_buff *skb; /* check if current mapping is still valid */ if (subflow->map_valid && @@ -954,15 +952,7 @@ bool mptcp_subflow_data_available(struct sock *sk) subflow->map_data_len); } - if (!subflow_check_data_avail(sk)) { - subflow->data_avail = 0; - return false; - } - - skb = skb_peek(&sk->sk_receive_queue); - subflow->data_avail = skb && - before(tcp_sk(sk)->copied_seq, TCP_SKB_CB(skb)->end_seq); - return subflow->data_avail; + return subflow_check_data_avail(sk); } /* If ssk has an mptcp parent socket, use the mptcp rcvbuf occupancy, @@ -1009,8 +999,10 @@ static void subflow_write_space(struct sock *sk) struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct sock *parent = subflow->conn; - sk_stream_write_space(sk); - if (sk_stream_is_writeable(sk)) { + if (!sk_stream_is_writeable(sk)) + return; + + if (sk_stream_is_writeable(parent)) { set_bit(MPTCP_SEND_SPACE, &mptcp_sk(parent)->flags); smp_mb__after_atomic(); /* set SEND_SPACE before sk_stream_write_space clears NOSPACE */ @@ -1069,8 +1061,7 @@ static void mptcp_info2sockaddr(const struct mptcp_addr_info *info, #endif } -int __mptcp_subflow_connect(struct sock *sk, int ifindex, - const struct mptcp_addr_info *loc, +int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, const struct mptcp_addr_info *remote) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -1115,7 +1106,7 @@ int __mptcp_subflow_connect(struct sock *sk, int ifindex, if (loc->family == AF_INET6) addrlen = sizeof(struct sockaddr_in6); #endif - ssk->sk_bound_dev_if = ifindex; + ssk->sk_bound_dev_if = loc->ifindex; err = kernel_bind(sf, (struct sockaddr *)&addr, addrlen); if (err) goto failed; @@ -1127,7 +1118,7 @@ int __mptcp_subflow_connect(struct sock *sk, int ifindex, subflow->local_id = local_id; subflow->remote_id = remote_id; subflow->request_join = 1; - subflow->request_bkup = 1; + subflow->request_bkup = !!(loc->flags & MPTCP_PM_ADDR_FLAG_BACKUP); mptcp_info2sockaddr(remote, &addr); err = kernel_connect(sf, (struct sockaddr *)&addr, addrlen, O_NONBLOCK); diff --git a/net/mptcp/token.c b/net/mptcp/token.c index 8b47c4bb1c6b..feb4b9ffd462 100644 --- a/net/mptcp/token.c +++ b/net/mptcp/token.c @@ -291,7 +291,7 @@ struct mptcp_sock *mptcp_token_iter_next(const struct net *net, long *s_slot, { struct mptcp_sock *ret = NULL; struct hlist_nulls_node *pos; - int slot, num; + int slot, num = 0; for (slot = *s_slot; slot <= token_mask; *s_num = 0, slot++) { struct token_bucket *bucket = &token_hash[slot]; diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index 8b386d766e7d..adddc7707aa4 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -716,7 +716,7 @@ static int ncsi_set_channel_mask_nl(struct sk_buff *msg, return 0; } -static const struct genl_ops ncsi_ops[] = { +static const struct genl_small_ops ncsi_ops[] = { { .cmd = NCSI_CMD_PKG_INFO, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, @@ -762,8 +762,8 @@ static struct genl_family ncsi_genl_family __ro_after_init = { .maxattr = NCSI_ATTR_MAX, .policy = ncsi_genl_policy, .module = THIS_MODULE, - .ops = ncsi_ops, - .n_ops = ARRAY_SIZE(ncsi_ops), + .small_ops = ncsi_ops, + .n_small_ops = ARRAY_SIZE(ncsi_ops), }; int ncsi_init_netlink(struct net_device *dev) diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 25313c29d799..52370211e46b 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -441,6 +441,7 @@ endif # NF_CONNTRACK config NF_TABLES select NETFILTER_NETLINK + select LIBCRC32C tristate "Netfilter nf_tables support" help nftables is the new packet classification framework that intends to diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 3ac7c8c1548d..63d032191e62 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -282,6 +282,16 @@ nf_hook_entry_head(struct net *net, int pf, unsigned int hooknum, return NULL; return net->nf.hooks_bridge + hooknum; #endif +#ifdef CONFIG_NETFILTER_INGRESS + case NFPROTO_INET: + if (WARN_ON_ONCE(hooknum != NF_INET_INGRESS)) + return NULL; + if (!dev || dev_net(dev) != net) { + WARN_ON_ONCE(1); + return NULL; + } + return &dev->nf_hooks_ingress; +#endif case NFPROTO_IPV4: if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_ipv4) <= hooknum)) return NULL; @@ -311,20 +321,80 @@ nf_hook_entry_head(struct net *net, int pf, unsigned int hooknum, return NULL; } +static int nf_ingress_check(struct net *net, const struct nf_hook_ops *reg, + int hooknum) +{ +#ifndef CONFIG_NETFILTER_INGRESS + if (reg->hooknum == hooknum) + return -EOPNOTSUPP; +#endif + if (reg->hooknum != hooknum || + !reg->dev || dev_net(reg->dev) != net) + return -EINVAL; + + return 0; +} + +static inline bool nf_ingress_hook(const struct nf_hook_ops *reg, int pf) +{ + if ((pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) || + (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS)) + return true; + + return false; +} + +static void nf_static_key_inc(const struct nf_hook_ops *reg, int pf) +{ +#ifdef CONFIG_JUMP_LABEL + int hooknum; + + if (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS) { + pf = NFPROTO_NETDEV; + hooknum = NF_NETDEV_INGRESS; + } else { + hooknum = reg->hooknum; + } + static_key_slow_inc(&nf_hooks_needed[pf][hooknum]); +#endif +} + +static void nf_static_key_dec(const struct nf_hook_ops *reg, int pf) +{ +#ifdef CONFIG_JUMP_LABEL + int hooknum; + + if (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS) { + pf = NFPROTO_NETDEV; + hooknum = NF_NETDEV_INGRESS; + } else { + hooknum = reg->hooknum; + } + static_key_slow_dec(&nf_hooks_needed[pf][hooknum]); +#endif +} + static int __nf_register_net_hook(struct net *net, int pf, const struct nf_hook_ops *reg) { struct nf_hook_entries *p, *new_hooks; struct nf_hook_entries __rcu **pp; + int err; - if (pf == NFPROTO_NETDEV) { -#ifndef CONFIG_NETFILTER_INGRESS - if (reg->hooknum == NF_NETDEV_INGRESS) - return -EOPNOTSUPP; -#endif - if (reg->hooknum != NF_NETDEV_INGRESS || - !reg->dev || dev_net(reg->dev) != net) - return -EINVAL; + switch (pf) { + case NFPROTO_NETDEV: + err = nf_ingress_check(net, reg, NF_NETDEV_INGRESS); + if (err < 0) + return err; + break; + case NFPROTO_INET: + if (reg->hooknum != NF_INET_INGRESS) + break; + + err = nf_ingress_check(net, reg, NF_INET_INGRESS); + if (err < 0) + return err; + break; } pp = nf_hook_entry_head(net, pf, reg->hooknum, reg->dev); @@ -345,12 +415,11 @@ static int __nf_register_net_hook(struct net *net, int pf, hooks_validate(new_hooks); #ifdef CONFIG_NETFILTER_INGRESS - if (pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) + if (nf_ingress_hook(reg, pf)) net_inc_ingress_queue(); #endif -#ifdef CONFIG_JUMP_LABEL - static_key_slow_inc(&nf_hooks_needed[pf][reg->hooknum]); -#endif + nf_static_key_inc(reg, pf); + BUG_ON(p == new_hooks); nf_hook_entries_free(p); return 0; @@ -403,12 +472,10 @@ static void __nf_unregister_net_hook(struct net *net, int pf, if (nf_remove_net_hook(p, reg)) { #ifdef CONFIG_NETFILTER_INGRESS - if (pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) + if (nf_ingress_hook(reg, pf)) net_dec_ingress_queue(); #endif -#ifdef CONFIG_JUMP_LABEL - static_key_slow_dec(&nf_hooks_needed[pf][reg->hooknum]); -#endif + nf_static_key_dec(reg, pf); } else { WARN_ONCE(1, "hook not found, pf %d num %d", pf, reg->hooknum); } @@ -425,8 +492,12 @@ static void __nf_unregister_net_hook(struct net *net, int pf, void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg) { if (reg->pf == NFPROTO_INET) { - __nf_unregister_net_hook(net, NFPROTO_IPV4, reg); - __nf_unregister_net_hook(net, NFPROTO_IPV6, reg); + if (reg->hooknum == NF_INET_INGRESS) { + __nf_unregister_net_hook(net, NFPROTO_INET, reg); + } else { + __nf_unregister_net_hook(net, NFPROTO_IPV4, reg); + __nf_unregister_net_hook(net, NFPROTO_IPV6, reg); + } } else { __nf_unregister_net_hook(net, reg->pf, reg); } @@ -451,14 +522,20 @@ int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg) int err; if (reg->pf == NFPROTO_INET) { - err = __nf_register_net_hook(net, NFPROTO_IPV4, reg); - if (err < 0) - return err; - - err = __nf_register_net_hook(net, NFPROTO_IPV6, reg); - if (err < 0) { - __nf_unregister_net_hook(net, NFPROTO_IPV4, reg); - return err; + if (reg->hooknum == NF_INET_INGRESS) { + err = __nf_register_net_hook(net, NFPROTO_INET, reg); + if (err < 0) + return err; + } else { + err = __nf_register_net_hook(net, NFPROTO_IPV4, reg); + if (err < 0) + return err; + + err = __nf_register_net_hook(net, NFPROTO_IPV6, reg); + if (err < 0) { + __nf_unregister_net_hook(net, NFPROTO_IPV4, reg); + return err; + } } } else { err = __nf_register_net_hook(net, reg->pf, reg); diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 920b7c4331f0..7cff6e5e7445 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -250,22 +250,7 @@ EXPORT_SYMBOL_GPL(ip_set_type_unregister); void * ip_set_alloc(size_t size) { - void *members = NULL; - - if (size < KMALLOC_MAX_SIZE) - members = kzalloc(size, GFP_KERNEL | __GFP_NOWARN); - - if (members) { - pr_debug("%p: allocated with kmalloc\n", members); - return members; - } - - members = vzalloc(size); - if (!members) - return NULL; - pr_debug("%p: allocated with vmalloc\n", members); - - return members; + return kvzalloc(size, GFP_KERNEL_ACCOUNT); } EXPORT_SYMBOL_GPL(ip_set_alloc); @@ -652,13 +637,14 @@ ip_set_match_extensions(struct ip_set *set, const struct ip_set_ext *ext, if (SET_WITH_COUNTER(set)) { struct ip_set_counter *counter = ext_counter(data, set); + ip_set_update_counter(counter, ext, flags); + if (flags & IPSET_FLAG_MATCH_COUNTERS && !(ip_set_match_counter(ip_set_get_packets(counter), mext->packets, mext->packets_op) && ip_set_match_counter(ip_set_get_bytes(counter), mext->bytes, mext->bytes_op))) return false; - ip_set_update_counter(counter, ext, flags); } if (SET_WITH_SKBINFO(set)) ip_set_get_skbinfo(ext_skbinfo(data, set), diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index 2c1593089ede..eb0e329f9b8d 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -29,7 +29,6 @@ if IP_VS config IP_VS_IPV6 bool "IPv6 support for IPVS" depends on IPV6 = y || IP_VS = IPV6 - select IP6_NF_IPTABLES select NF_DEFRAG_IPV6 help Add IPv6 support to IPVS. diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index a90b8eac16ac..c100c6b112c8 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -402,6 +402,8 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p) { unsigned int hash; struct ip_vs_conn *cp, *ret=NULL; + const union nf_inet_addr *saddr; + __be16 sport; /* * Check for "full" addressed entries @@ -411,10 +413,20 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p) rcu_read_lock(); hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) { - if (p->vport == cp->cport && p->cport == cp->dport && - cp->af == p->af && + if (p->vport != cp->cport) + continue; + + if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) { + sport = cp->vport; + saddr = &cp->vaddr; + } else { + sport = cp->dport; + saddr = &cp->daddr; + } + + if (p->cport == sport && cp->af == p->af && ip_vs_addr_equal(p->af, p->vaddr, &cp->caddr) && - ip_vs_addr_equal(p->af, p->caddr, &cp->daddr) && + ip_vs_addr_equal(p->af, p->caddr, saddr) && p->protocol == cp->protocol && cp->ipvs == p->ipvs) { if (!__ip_vs_conn_get(cp)) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index e3668a6e54e4..c0b8215ab3d4 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -742,12 +742,12 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af, struct dst_entry *dst = skb_dst(skb); if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) && - ip6_route_me_harder(ipvs->net, skb) != 0) + ip6_route_me_harder(ipvs->net, skb->sk, skb) != 0) return 1; } else #endif if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) && - ip_route_me_harder(ipvs->net, skb, RTN_LOCAL) != 0) + ip_route_me_harder(ipvs->net, skb->sk, skb, RTN_LOCAL) != 0) return 1; return 0; @@ -875,7 +875,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb, unsigned int verdict = NF_DROP; if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) - goto ignore_cp; + goto after_nat; /* Ensure the checksum is correct */ if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) { @@ -901,6 +901,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb, if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto out; +after_nat: /* do the statistics and put it back */ ip_vs_out_stats(cp, skb); @@ -909,8 +910,6 @@ static int handle_response_icmp(int af, struct sk_buff *skb, ip_vs_notrack(skb); else ip_vs_update_conntrack(skb, cp, 0); - -ignore_cp: verdict = NF_ACCEPT; out: @@ -1276,6 +1275,9 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, { struct ip_vs_protocol *pp = pd->pp; + if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) + goto after_nat; + IP_VS_DBG_PKT(11, af, pp, skb, iph->off, "Outgoing packet"); if (skb_ensure_writable(skb, iph->len)) @@ -1316,6 +1318,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, IP_VS_DBG_PKT(10, af, pp, skb, iph->off, "After SNAT"); +after_nat: ip_vs_out_stats(cp, skb); ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd); skb->ipvs_property = 1; @@ -1412,11 +1415,8 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, af, skb, &iph); - if (likely(cp)) { - if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) - goto ignore_cp; + if (likely(cp)) return handle_response(af, skb, pd, cp, &iph, hooknum); - } /* Check for real-server-started requests */ if (atomic_read(&ipvs->conn_out_counter)) { @@ -1475,14 +1475,9 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in } } -out: IP_VS_DBG_PKT(12, af, pp, skb, iph.off, "ip_vs_out: packet continues traversal as normal"); return NF_ACCEPT; - -ignore_cp: - __ip_vs_conn_put(cp); - goto out; } /* diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 678c5b14841c..e279ded4e306 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2508,6 +2508,10 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, sockptr_t ptr, unsigned int len) /* Set timeout values for (tcp tcpfin udp) */ ret = ip_vs_set_timeout(ipvs, (struct ip_vs_timeout_user *)arg); goto out_unlock; + } else if (!len) { + /* No more commands with len == 0 below */ + ret = -EINVAL; + goto out_unlock; } usvc_compat = (struct ip_vs_service_user *)arg; @@ -2584,9 +2588,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, sockptr_t ptr, unsigned int len) break; case IP_VS_SO_SET_DELDEST: ret = ip_vs_del_dest(svc, &udest); - break; - default: - ret = -EINVAL; } out_unlock: @@ -3892,7 +3893,7 @@ out: } -static const struct genl_ops ip_vs_genl_ops[] = { +static const struct genl_small_ops ip_vs_genl_ops[] = { { .cmd = IPVS_CMD_NEW_SERVICE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, @@ -4000,8 +4001,8 @@ static struct genl_family ip_vs_genl_family __ro_after_init = { .policy = ip_vs_cmd_policy, .netnsok = true, /* Make ipvsadm to work on netns */ .module = THIS_MODULE, - .ops = ip_vs_genl_ops, - .n_ops = ARRAY_SIZE(ip_vs_genl_ops), + .small_ops = ip_vs_genl_ops, + .n_small_ops = ARRAY_SIZE(ip_vs_genl_ops), }; static int __init ip_vs_genl_register(void) diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index dc2e7da2742a..7da51390cea6 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -539,8 +539,8 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, if (new_state != cp->state) { struct ip_vs_dest *dest = cp->dest; - IP_VS_DBG_BUF(8, "%s %s [%c%c%c%c] %s:%d->" - "%s:%d state: %s->%s conn->refcnt:%d\n", + IP_VS_DBG_BUF(8, "%s %s [%c%c%c%c] c:%s:%d v:%s:%d " + "d:%s:%d state: %s->%s conn->refcnt:%d\n", pd->pp->name, ((state_off == TCP_DIR_OUTPUT) ? "output " : "input "), @@ -548,10 +548,12 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, th->fin ? 'F' : '.', th->ack ? 'A' : '.', th->rst ? 'R' : '.', - IP_VS_DBG_ADDR(cp->daf, &cp->daddr), - ntohs(cp->dport), IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), + IP_VS_DBG_ADDR(cp->af, &cp->vaddr), + ntohs(cp->vport), + IP_VS_DBG_ADDR(cp->daf, &cp->daddr), + ntohs(cp->dport), tcp_state_name(cp->state), tcp_state_name(new_state), refcount_read(&cp->refcnt)); diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 2b8abbfe018c..16b48064f715 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -242,9 +242,6 @@ struct ip_vs_sync_thread_data { | IPVS Sync Connection (1) | */ -#define SYNC_MESG_HEADER_LEN 4 -#define MAX_CONNS_PER_SYNCBUFF 255 /* nr_conns in ip_vs_sync_mesg is 8 bit */ - /* Version 0 header */ struct ip_vs_sync_mesg_v0 { __u8 nr_conns; diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index b00866d777fe..d2e5a8f644b8 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -609,6 +609,8 @@ static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *skb, if (ret == NF_ACCEPT) { nf_reset_ct(skb); skb_forward_csum(skb); + if (skb->dev) + skb->tstamp = 0; } return ret; } @@ -649,6 +651,8 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb, if (!local) { skb_forward_csum(skb); + if (skb->dev) + skb->tstamp = 0; NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb, NULL, skb_dst(skb)->dev, dst_output); } else @@ -669,6 +673,8 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb, if (!local) { ip_vs_drop_early_demux_sk(skb); skb_forward_csum(skb); + if (skb->dev) + skb->tstamp = 0; NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb, NULL, skb_dst(skb)->dev, dst_output); } else diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 5b97d233f89b..234b7cab37c3 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -859,7 +859,6 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) out: nf_conntrack_double_unlock(hash, reply_hash); - NF_CT_STAT_INC(net, insert_failed); local_bh_enable(); return -EEXIST; } @@ -909,6 +908,7 @@ static void __nf_conntrack_insert_prepare(struct nf_conn *ct) tstamp->start = ktime_get_real_ns(); } +/* caller must hold locks to prevent concurrent changes */ static int __nf_ct_resolve_clash(struct sk_buff *skb, struct nf_conntrack_tuple_hash *h) { @@ -922,23 +922,21 @@ static int __nf_ct_resolve_clash(struct sk_buff *skb, if (nf_ct_is_dying(ct)) return NF_DROP; - if (!atomic_inc_not_zero(&ct->ct_general.use)) - return NF_DROP; - if (((ct->status & IPS_NAT_DONE_MASK) == 0) || nf_ct_match(ct, loser_ct)) { struct net *net = nf_ct_net(ct); + nf_conntrack_get(&ct->ct_general); + nf_ct_acct_merge(ct, ctinfo, loser_ct); nf_ct_add_to_dying_list(loser_ct); nf_conntrack_put(&loser_ct->ct_general); nf_ct_set(skb, ct, ctinfo); - NF_CT_STAT_INC(net, insert_failed); + NF_CT_STAT_INC(net, clash_resolve); return NF_ACCEPT; } - nf_ct_put(ct); return NF_DROP; } @@ -998,6 +996,8 @@ static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx) hlist_nulls_add_head_rcu(&loser_ct->tuplehash[IP_CT_DIR_REPLY].hnnode, &nf_conntrack_hash[repl_idx]); + + NF_CT_STAT_INC(net, clash_resolve); return NF_ACCEPT; } @@ -1027,10 +1027,10 @@ static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx) * * Failing that, the new, unconfirmed conntrack is still added to the table * provided that the collision only occurs in the ORIGINAL direction. - * The new entry will be added after the existing one in the hash list, + * The new entry will be added only in the non-clashing REPLY direction, * so packets in the ORIGINAL direction will continue to match the existing * entry. The new entry will also have a fixed timeout so it expires -- - * due to the collision, it will not see bidirectional traffic. + * due to the collision, it will only see reply traffic. * * Returns NF_DROP if the clash could not be resolved. */ @@ -1725,10 +1725,8 @@ nf_conntrack_handle_icmp(struct nf_conn *tmpl, else return NF_ACCEPT; - if (ret <= 0) { + if (ret <= 0) NF_CT_STAT_INC_ATOMIC(state->net, error); - NF_CT_STAT_INC_ATOMIC(state->net, invalid); - } return ret; } @@ -1802,10 +1800,8 @@ nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state) if (tmpl || ctinfo == IP_CT_UNTRACKED) { /* Previously seen (loopback or untracked)? Ignore. */ if ((tmpl && !nf_ct_is_template(tmpl)) || - ctinfo == IP_CT_UNTRACKED) { - NF_CT_STAT_INC_ATOMIC(state->net, ignore); + ctinfo == IP_CT_UNTRACKED) return NF_ACCEPT; - } skb->_nfct = 0; } @@ -1813,7 +1809,6 @@ nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state) dataoff = get_l4proto(skb, skb_network_offset(skb), state->pf, &protonum); if (dataoff <= 0) { pr_debug("not prepared to track yet or error occurred\n"); - NF_CT_STAT_INC_ATOMIC(state->net, error); NF_CT_STAT_INC_ATOMIC(state->net, invalid); ret = NF_ACCEPT; goto out; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index c3a4214dc958..3d0fd33be018 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2497,7 +2497,6 @@ ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq, if (nla_put_be32(skb, CTA_STATS_FOUND, htonl(st->found)) || nla_put_be32(skb, CTA_STATS_INVALID, htonl(st->invalid)) || - nla_put_be32(skb, CTA_STATS_IGNORE, htonl(st->ignore)) || nla_put_be32(skb, CTA_STATS_INSERT, htonl(st->insert)) || nla_put_be32(skb, CTA_STATS_INSERT_FAILED, htonl(st->insert_failed)) || @@ -2505,7 +2504,9 @@ ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq, nla_put_be32(skb, CTA_STATS_EARLY_DROP, htonl(st->early_drop)) || nla_put_be32(skb, CTA_STATS_ERROR, htonl(st->error)) || nla_put_be32(skb, CTA_STATS_SEARCH_RESTART, - htonl(st->search_restart))) + htonl(st->search_restart)) || + nla_put_be32(skb, CTA_STATS_CLASH_RESOLVE, + htonl(st->clash_resolve))) goto nla_put_failure; nlmsg_end(skb, nlh); diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index e8c86ee4c1c4..c8fb2187ad4b 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -541,13 +541,20 @@ static bool tcp_in_window(const struct nf_conn *ct, swin = win << sender->td_scale; sender->td_maxwin = (swin == 0 ? 1 : swin); sender->td_maxend = end + sender->td_maxwin; - /* - * We haven't seen traffic in the other direction yet - * but we have to tweak window tracking to pass III - * and IV until that happens. - */ - if (receiver->td_maxwin == 0) + if (receiver->td_maxwin == 0) { + /* We haven't seen traffic in the other + * direction yet but we have to tweak window + * tracking to pass III and IV until that + * happens. + */ receiver->td_end = receiver->td_maxend = sack; + } else if (sack == receiver->td_end + 1) { + /* Likely a reply to a keepalive. + * Needed for III. + */ + receiver->td_end++; + } + } } else if (((state->state == TCP_CONNTRACK_SYN_SENT && dir == IP_CT_DIR_ORIGINAL) diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index a604f43e3e6b..46c5557c1fec 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -428,18 +428,18 @@ static int ct_cpu_seq_show(struct seq_file *seq, void *v) const struct ip_conntrack_stat *st = v; if (v == SEQ_START_TOKEN) { - seq_puts(seq, "entries searched 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 delete_list insert insert_failed drop early_drop icmp_error expect_new expect_create expect_delete search_restart\n"); return 0; } seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x " "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n", nr_conntracks, - 0, + st->clash_resolve, st->found, 0, st->invalid, - st->ignore, + 0, 0, 0, st->insert, diff --git a/net/netfilter/nf_dup_netdev.c b/net/netfilter/nf_dup_netdev.c index 2b01a151eaa8..a579e59ee5c5 100644 --- a/net/netfilter/nf_dup_netdev.c +++ b/net/netfilter/nf_dup_netdev.c @@ -19,6 +19,7 @@ static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev) skb_push(skb, skb->mac_len); skb->dev = dev; + skb->tstamp = 0; dev_queue_xmit(skb); } diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 4f7a567c536e..513f78db3cb2 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -395,8 +395,7 @@ static int nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff, { struct tcphdr *tcph; - if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) || - skb_try_make_writable(skb, thoff + sizeof(*tcph))) + if (skb_try_make_writable(skb, thoff + sizeof(*tcph))) return -1; tcph = (void *)(skb_network_header(skb) + thoff); @@ -410,8 +409,7 @@ static int nf_flow_nat_port_udp(struct sk_buff *skb, unsigned int thoff, { struct udphdr *udph; - if (!pskb_may_pull(skb, thoff + sizeof(*udph)) || - skb_try_make_writable(skb, thoff + sizeof(*udph))) + if (skb_try_make_writable(skb, thoff + sizeof(*udph))) return -1; udph = (void *)(skb_network_header(skb) + thoff); @@ -449,8 +447,7 @@ int nf_flow_snat_port(const struct flow_offload *flow, struct flow_ports *hdr; __be16 port, new_port; - if (!pskb_may_pull(skb, thoff + sizeof(*hdr)) || - skb_try_make_writable(skb, thoff + sizeof(*hdr))) + if (skb_try_make_writable(skb, thoff + sizeof(*hdr))) return -1; hdr = (void *)(skb_network_header(skb) + thoff); @@ -481,8 +478,7 @@ int nf_flow_dnat_port(const struct flow_offload *flow, struct flow_ports *hdr; __be16 port, new_port; - if (!pskb_may_pull(skb, thoff + sizeof(*hdr)) || - skb_try_make_writable(skb, thoff + sizeof(*hdr))) + if (skb_try_make_writable(skb, thoff + sizeof(*hdr))) return -1; hdr = (void *)(skb_network_header(skb) + thoff); diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index a3bca758b849..a698dbe28ef5 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -25,9 +25,6 @@ static int nf_flow_state_check(struct flow_offload *flow, int proto, if (proto != IPPROTO_TCP) return 0; - if (!pskb_may_pull(skb, thoff + sizeof(*tcph))) - return -1; - tcph = (void *)(skb_network_header(skb) + thoff); if (unlikely(tcph->fin || tcph->rst)) { flow_offload_teardown(flow); @@ -42,8 +39,7 @@ static int nf_flow_nat_ip_tcp(struct sk_buff *skb, unsigned int thoff, { struct tcphdr *tcph; - if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) || - skb_try_make_writable(skb, thoff + sizeof(*tcph))) + if (skb_try_make_writable(skb, thoff + sizeof(*tcph))) return -1; tcph = (void *)(skb_network_header(skb) + thoff); @@ -57,8 +53,7 @@ static int nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff, { struct udphdr *udph; - if (!pskb_may_pull(skb, thoff + sizeof(*udph)) || - skb_try_make_writable(skb, thoff + sizeof(*udph))) + if (skb_try_make_writable(skb, thoff + sizeof(*udph))) return -1; udph = (void *)(skb_network_header(skb) + thoff); @@ -167,8 +162,8 @@ static bool ip_has_options(unsigned int thoff) static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev, struct flow_offload_tuple *tuple) { + unsigned int thoff, hdrsize; struct flow_ports *ports; - unsigned int thoff; struct iphdr *iph; if (!pskb_may_pull(skb, sizeof(*iph))) @@ -181,15 +176,22 @@ static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev, unlikely(ip_has_options(thoff))) return -1; - if (iph->protocol != IPPROTO_TCP && - iph->protocol != IPPROTO_UDP) + switch (iph->protocol) { + case IPPROTO_TCP: + hdrsize = sizeof(struct tcphdr); + break; + case IPPROTO_UDP: + hdrsize = sizeof(struct udphdr); + break; + default: return -1; + } if (iph->ttl <= 1) return -1; thoff = iph->ihl * 4; - if (!pskb_may_pull(skb, thoff + sizeof(*ports))) + if (!pskb_may_pull(skb, thoff + hdrsize)) return -1; iph = ip_hdr(skb); @@ -315,8 +317,7 @@ static int nf_flow_nat_ipv6_tcp(struct sk_buff *skb, unsigned int thoff, { struct tcphdr *tcph; - if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) || - skb_try_make_writable(skb, thoff + sizeof(*tcph))) + if (skb_try_make_writable(skb, thoff + sizeof(*tcph))) return -1; tcph = (void *)(skb_network_header(skb) + thoff); @@ -332,8 +333,7 @@ static int nf_flow_nat_ipv6_udp(struct sk_buff *skb, unsigned int thoff, { struct udphdr *udph; - if (!pskb_may_pull(skb, thoff + sizeof(*udph)) || - skb_try_make_writable(skb, thoff + sizeof(*udph))) + if (skb_try_make_writable(skb, thoff + sizeof(*udph))) return -1; udph = (void *)(skb_network_header(skb) + thoff); @@ -439,24 +439,31 @@ static int nf_flow_nat_ipv6(const struct flow_offload *flow, static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev, struct flow_offload_tuple *tuple) { + unsigned int thoff, hdrsize; struct flow_ports *ports; struct ipv6hdr *ip6h; - unsigned int thoff; if (!pskb_may_pull(skb, sizeof(*ip6h))) return -1; ip6h = ipv6_hdr(skb); - if (ip6h->nexthdr != IPPROTO_TCP && - ip6h->nexthdr != IPPROTO_UDP) + switch (ip6h->nexthdr) { + case IPPROTO_TCP: + hdrsize = sizeof(struct tcphdr); + break; + case IPPROTO_UDP: + hdrsize = sizeof(struct udphdr); + break; + default: return -1; + } if (ip6h->hop_limit <= 1) return -1; thoff = sizeof(*ip6h); - if (!pskb_may_pull(skb, thoff + sizeof(*ports))) + if (!pskb_may_pull(skb, thoff + hdrsize)) return -1; ip6h = ipv6_hdr(skb); diff --git a/net/netfilter/nf_log_common.c b/net/netfilter/nf_log_common.c index ae5628ddbe6d..fd7c5f0f5c25 100644 --- a/net/netfilter/nf_log_common.c +++ b/net/netfilter/nf_log_common.c @@ -171,6 +171,18 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf, } EXPORT_SYMBOL_GPL(nf_log_dump_packet_common); +void nf_log_dump_vlan(struct nf_log_buf *m, const struct sk_buff *skb) +{ + u16 vid; + + if (!skb_vlan_tag_present(skb)) + return; + + vid = skb_vlan_tag_get(skb); + nf_log_buf_add(m, "VPROTO=%04x VID=%u ", ntohs(skb->vlan_proto), vid); +} +EXPORT_SYMBOL_GPL(nf_log_dump_vlan); + /* bridge and netdev logging families share this code. */ void nf_log_l2packet(struct net *net, u_int8_t pf, __be16 protocol, diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c index 59151dc07fdc..e87b6bd6b3cd 100644 --- a/net/netfilter/nf_nat_proto.c +++ b/net/netfilter/nf_nat_proto.c @@ -715,7 +715,7 @@ nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, if (ct->tuplehash[dir].tuple.dst.u3.ip != ct->tuplehash[!dir].tuple.src.u3.ip) { - err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); + err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } @@ -953,7 +953,7 @@ nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, &ct->tuplehash[!dir].tuple.src.u3)) { - err = nf_ip6_route_me_harder(state->net, skb); + err = nf_ip6_route_me_harder(state->net, state->sk, skb); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 9cca35d22927..d7d34a62d3bf 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -446,7 +446,7 @@ synproxy_send_tcp(struct net *net, skb_dst_set_noref(nskb, skb_dst(skb)); nskb->protocol = htons(ETH_P_IP); - if (ip_route_me_harder(net, nskb, RTN_UNSPEC)) + if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC)) goto free_nskb; if (nfct) { diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 4603b667973a..0f58e98542be 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -206,7 +206,7 @@ static int nf_tables_register_hook(struct net *net, if (basechain->type->ops_register) return basechain->type->ops_register(net, ops); - if (table->family == NFPROTO_NETDEV) + if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) return nft_netdev_register_hooks(net, &basechain->hook_list); return nf_register_net_hook(net, &basechain->ops); @@ -228,7 +228,7 @@ static void nf_tables_unregister_hook(struct net *net, if (basechain->type->ops_unregister) return basechain->type->ops_unregister(net, ops); - if (table->family == NFPROTO_NETDEV) + if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) nft_netdev_unregister_hooks(net, &basechain->hook_list); else nf_unregister_net_hook(net, &basechain->ops); @@ -302,7 +302,7 @@ static void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_expr *expr; expr = nft_expr_first(rule); - while (expr != nft_expr_last(rule) && expr->ops) { + while (nft_expr_more(rule, expr)) { if (expr->ops->activate) expr->ops->activate(ctx, expr); @@ -317,7 +317,7 @@ static void nft_rule_expr_deactivate(const struct nft_ctx *ctx, struct nft_expr *expr; expr = nft_expr_first(rule); - while (expr != nft_expr_last(rule) && expr->ops) { + while (nft_expr_more(rule, expr)) { if (expr->ops->deactivate) expr->ops->deactivate(ctx, expr, phase); @@ -650,6 +650,8 @@ static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = { .len = NFT_TABLE_MAXNAMELEN - 1 }, [NFTA_TABLE_FLAGS] = { .type = NLA_U32 }, [NFTA_TABLE_HANDLE] = { .type = NLA_U64 }, + [NFTA_TABLE_USERDATA] = { .type = NLA_BINARY, + .len = NFT_USERDATA_MAXLEN } }; static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, @@ -676,6 +678,11 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, NFTA_TABLE_PAD)) goto nla_put_failure; + if (table->udata) { + if (nla_put(skb, NFTA_TABLE_USERDATA, table->udlen, table->udata)) + goto nla_put_failure; + } + nlmsg_end(skb, nlh); return 0; @@ -988,8 +995,8 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, int family = nfmsg->nfgen_family; const struct nlattr *attr; struct nft_table *table; - u32 flags = 0; struct nft_ctx ctx; + u32 flags = 0; int err; lockdep_assert_held(&net->nft.commit_mutex); @@ -1025,6 +1032,14 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, if (table->name == NULL) goto err_strdup; + if (nla[NFTA_TABLE_USERDATA]) { + table->udata = nla_memdup(nla[NFTA_TABLE_USERDATA], GFP_KERNEL); + if (table->udata == NULL) + goto err_table_udata; + + table->udlen = nla_len(nla[NFTA_TABLE_USERDATA]); + } + err = rhltable_init(&table->chains_ht, &nft_chain_ht_params); if (err) goto err_chain_ht; @@ -1047,6 +1062,8 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, err_trans: rhltable_destroy(&table->chains_ht); err_chain_ht: + kfree(table->udata); +err_table_udata: kfree(table->name); err_strdup: kfree(table); @@ -1202,6 +1219,7 @@ static void nf_tables_table_destroy(struct nft_ctx *ctx) rhltable_destroy(&ctx->table->chains_ht); kfree(ctx->table->name); + kfree(ctx->table->udata); kfree(ctx->table); } @@ -1297,6 +1315,8 @@ static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = { [NFTA_CHAIN_COUNTERS] = { .type = NLA_NESTED }, [NFTA_CHAIN_FLAGS] = { .type = NLA_U32 }, [NFTA_CHAIN_ID] = { .type = NLA_U32 }, + [NFTA_CHAIN_USERDATA] = { .type = NLA_BINARY, + .len = NFT_USERDATA_MAXLEN }, }; static const struct nla_policy nft_hook_policy[NFTA_HOOK_MAX + 1] = { @@ -1361,7 +1381,7 @@ static int nft_dump_basechain_hook(struct sk_buff *skb, int family, if (nla_put_be32(skb, NFTA_HOOK_PRIORITY, htonl(ops->priority))) goto nla_put_failure; - if (family == NFPROTO_NETDEV) { + if (nft_base_chain_netdev(family, ops->hooknum)) { nest_devs = nla_nest_start_noflag(skb, NFTA_HOOK_DEVS); list_for_each_entry(hook, &basechain->hook_list, list) { if (!first) @@ -1438,6 +1458,10 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, if (nla_put_be32(skb, NFTA_CHAIN_USE, htonl(chain->use))) goto nla_put_failure; + if (chain->udata && + nla_put(skb, NFTA_CHAIN_USERDATA, chain->udlen, chain->udata)) + goto nla_put_failure; + nlmsg_end(skb, nlh); return 0; @@ -1661,7 +1685,7 @@ void nf_tables_chain_destroy(struct nft_ctx *ctx) if (nft_is_base_chain(chain)) { struct nft_base_chain *basechain = nft_base_chain(chain); - if (ctx->family == NFPROTO_NETDEV) { + if (nft_base_chain_netdev(ctx->family, basechain->ops.hooknum)) { list_for_each_entry_safe(hook, next, &basechain->hook_list, list) { list_del_rcu(&hook->list); @@ -1674,9 +1698,11 @@ void nf_tables_chain_destroy(struct nft_ctx *ctx) free_percpu(rcu_dereference_raw(basechain->stats)); } kfree(chain->name); + kfree(chain->udata); kfree(basechain); } else { kfree(chain->name); + kfree(chain->udata); kfree(chain); } } @@ -1838,7 +1864,7 @@ static int nft_chain_parse_hook(struct net *net, if (IS_ERR(type)) return PTR_ERR(type); } - if (hook->num > NF_MAX_HOOKS || !(type->hook_mask & (1 << hook->num))) + if (hook->num >= NFT_MAX_HOOKS || !(type->hook_mask & (1 << hook->num))) return -EOPNOTSUPP; if (type->type == NFT_CHAIN_T_NAT && @@ -1851,7 +1877,7 @@ static int nft_chain_parse_hook(struct net *net, hook->type = type; INIT_LIST_HEAD(&hook->list); - if (family == NFPROTO_NETDEV) { + if (nft_base_chain_netdev(family, hook->num)) { err = nft_chain_parse_netdev(net, ha, &hook->list); if (err < 0) { module_put(type->owner); @@ -1918,7 +1944,7 @@ static int nft_basechain_init(struct nft_base_chain *basechain, u8 family, INIT_LIST_HEAD(&basechain->hook_list); chain = &basechain->chain; - if (family == NFPROTO_NETDEV) { + if (nft_base_chain_netdev(family, hook->num)) { list_splice_init(&hook->list, &basechain->hook_list); list_for_each_entry(h, &basechain->hook_list, list) nft_basechain_hook_init(&h->ops, family, hook, chain); @@ -2030,7 +2056,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, } else { if (!(flags & NFT_CHAIN_BINDING)) { err = -EINVAL; - goto err1; + goto err_destroy_chain; } snprintf(name, sizeof(name), "__chain%llu", ++chain_id); @@ -2039,13 +2065,22 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, if (!chain->name) { err = -ENOMEM; - goto err1; + goto err_destroy_chain; + } + + if (nla[NFTA_CHAIN_USERDATA]) { + chain->udata = nla_memdup(nla[NFTA_CHAIN_USERDATA], GFP_KERNEL); + if (chain->udata == NULL) { + err = -ENOMEM; + goto err_destroy_chain; + } + chain->udlen = nla_len(nla[NFTA_CHAIN_USERDATA]); } rules = nf_tables_chain_alloc_rules(chain, 0); if (!rules) { err = -ENOMEM; - goto err1; + goto err_destroy_chain; } *rules = NULL; @@ -2054,12 +2089,12 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, err = nf_tables_register_hook(net, table, chain); if (err < 0) - goto err1; + goto err_destroy_chain; trans = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN); if (IS_ERR(trans)) { err = PTR_ERR(trans); - goto err2; + goto err_unregister_hook; } nft_trans_chain_policy(trans) = NFT_CHAIN_POLICY_UNSET; @@ -2069,15 +2104,15 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, err = nft_chain_add(table, chain); if (err < 0) { nft_trans_destroy(trans); - goto err2; + goto err_unregister_hook; } table->use++; return 0; -err2: +err_unregister_hook: nf_tables_unregister_hook(net, table, chain); -err1: +err_destroy_chain: nf_tables_chain_destroy(ctx); return err; @@ -2103,7 +2138,8 @@ static bool nft_hook_list_equal(struct list_head *hook_list1, } static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, - u32 flags) + u32 flags, const struct nlattr *attr, + struct netlink_ext_ack *extack) { const struct nlattr * const *nla = ctx->nla; struct nft_table *table = ctx->table; @@ -2119,9 +2155,10 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, return -EOPNOTSUPP; if (nla[NFTA_CHAIN_HOOK]) { - if (!nft_is_base_chain(chain)) + if (!nft_is_base_chain(chain)) { + NL_SET_BAD_ATTR(extack, attr); return -EEXIST; - + } err = nft_chain_parse_hook(ctx->net, nla, &hook, ctx->family, false); if (err < 0) @@ -2130,13 +2167,15 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, basechain = nft_base_chain(chain); if (basechain->type != hook.type) { nft_chain_release_hook(&hook); + NL_SET_BAD_ATTR(extack, attr); return -EEXIST; } - if (ctx->family == NFPROTO_NETDEV) { + if (nft_base_chain_netdev(ctx->family, hook.num)) { if (!nft_hook_list_equal(&basechain->hook_list, &hook.list)) { nft_chain_release_hook(&hook); + NL_SET_BAD_ATTR(extack, attr); return -EEXIST; } } else { @@ -2144,6 +2183,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, if (ops->hooknum != hook.num || ops->priority != hook.priority) { nft_chain_release_hook(&hook); + NL_SET_BAD_ATTR(extack, attr); return -EEXIST; } } @@ -2156,8 +2196,10 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, chain2 = nft_chain_lookup(ctx->net, table, nla[NFTA_CHAIN_NAME], genmask); - if (!IS_ERR(chain2)) + if (!IS_ERR(chain2)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]); return -EEXIST; + } } if (nla[NFTA_CHAIN_COUNTERS]) { @@ -2200,6 +2242,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, nft_trans_chain_update(tmp) && nft_trans_chain_name(tmp) && strcmp(name, nft_trans_chain_name(tmp)) == 0) { + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]); kfree(name); goto err; } @@ -2322,7 +2365,8 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, return -EOPNOTSUPP; flags |= chain->flags & NFT_CHAIN_BASE; - return nf_tables_updchain(&ctx, genmask, policy, flags); + return nf_tables_updchain(&ctx, genmask, policy, flags, attr, + extack); } return nf_tables_addchain(&ctx, family, genmask, policy, flags); @@ -3036,7 +3080,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, * is called on error from nf_tables_newrule(). */ expr = nft_expr_first(rule); - while (expr != nft_expr_last(rule) && expr->ops) { + while (nft_expr_more(rule, expr)) { next = nft_expr_next(expr); nf_tables_expr_destroy(ctx, expr); expr = next; @@ -5737,6 +5781,8 @@ static const struct nla_policy nft_obj_policy[NFTA_OBJ_MAX + 1] = { [NFTA_OBJ_TYPE] = { .type = NLA_U32 }, [NFTA_OBJ_DATA] = { .type = NLA_NESTED }, [NFTA_OBJ_HANDLE] = { .type = NLA_U64}, + [NFTA_OBJ_USERDATA] = { .type = NLA_BINARY, + .len = NFT_USERDATA_MAXLEN }, }; static struct nft_object *nft_obj_init(const struct nft_ctx *ctx, @@ -5928,7 +5974,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, obj = nft_obj_init(&ctx, type, nla[NFTA_OBJ_DATA]); if (IS_ERR(obj)) { err = PTR_ERR(obj); - goto err1; + goto err_init; } obj->key.table = table; obj->handle = nf_tables_alloc_handle(table); @@ -5936,32 +5982,42 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, obj->key.name = nla_strdup(nla[NFTA_OBJ_NAME], GFP_KERNEL); if (!obj->key.name) { err = -ENOMEM; - goto err2; + goto err_strdup; + } + + if (nla[NFTA_OBJ_USERDATA]) { + obj->udata = nla_memdup(nla[NFTA_OBJ_USERDATA], GFP_KERNEL); + if (obj->udata == NULL) + goto err_userdata; + + obj->udlen = nla_len(nla[NFTA_OBJ_USERDATA]); } err = nft_trans_obj_add(&ctx, NFT_MSG_NEWOBJ, obj); if (err < 0) - goto err3; + goto err_trans; err = rhltable_insert(&nft_objname_ht, &obj->rhlhead, nft_objname_ht_params); if (err < 0) - goto err4; + goto err_obj_ht; list_add_tail_rcu(&obj->list, &table->objects); table->use++; return 0; -err4: +err_obj_ht: /* queued in transaction log */ INIT_LIST_HEAD(&obj->list); return err; -err3: +err_trans: kfree(obj->key.name); -err2: +err_userdata: + kfree(obj->udata); +err_strdup: if (obj->ops->destroy) obj->ops->destroy(&ctx, obj); kfree(obj); -err1: +err_init: module_put(type->owner); return err; } @@ -5993,6 +6049,10 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net, NFTA_OBJ_PAD)) goto nla_put_failure; + if (obj->udata && + nla_put(skb, NFTA_OBJ_USERDATA, obj->udlen, obj->udata)) + goto nla_put_failure; + nlmsg_end(skb, nlh); return 0; @@ -6199,6 +6259,7 @@ static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) module_put(obj->ops->type->owner); kfree(obj->key.name); + kfree(obj->udata); kfree(obj); } @@ -7076,7 +7137,7 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx, GFP_KERNEL); kfree(buf); - if (ctx->report && + if (!ctx->report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES)) return; @@ -7198,7 +7259,7 @@ static void nf_tables_gen_notify(struct net *net, struct sk_buff *skb, audit_log_nfcfg("?:0;?:0", 0, net->nft.base_seq, AUDIT_NFT_OP_GEN_REGISTER, GFP_KERNEL); - if (nlmsg_report(nlh) && + if (!nlmsg_report(nlh) && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) return; @@ -7992,12 +8053,16 @@ static void nf_tables_abort_release(struct nft_trans *trans) kfree(trans); } -static int __nf_tables_abort(struct net *net, bool autoload) +static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) { struct nft_trans *trans, *next; struct nft_trans_elem *te; struct nft_hook *hook; + if (action == NFNL_ABORT_VALIDATE && + nf_tables_validate(net) < 0) + return -EAGAIN; + list_for_each_entry_safe_reverse(trans, next, &net->nft.commit_list, list) { switch (trans->msg_type) { @@ -8129,7 +8194,7 @@ static int __nf_tables_abort(struct net *net, bool autoload) nf_tables_abort_release(trans); } - if (autoload) + if (action == NFNL_ABORT_AUTOLOAD) nf_tables_module_autoload(net); else nf_tables_module_autoload_cleanup(net); @@ -8142,9 +8207,10 @@ static void nf_tables_cleanup(struct net *net) nft_validate_state_update(net, NFT_VALIDATE_SKIP); } -static int nf_tables_abort(struct net *net, struct sk_buff *skb, bool autoload) +static int nf_tables_abort(struct net *net, struct sk_buff *skb, + enum nfnl_abort_action action) { - int ret = __nf_tables_abort(net, autoload); + int ret = __nf_tables_abort(net, action); mutex_unlock(&net->nft.commit_mutex); @@ -8775,7 +8841,7 @@ static void __net_exit nf_tables_exit_net(struct net *net) { mutex_lock(&net->nft.commit_mutex); if (!list_empty(&net->nft.commit_list)) - __nf_tables_abort(net, false); + __nf_tables_abort(net, NFNL_ABORT_NONE); __nft_release_tables(net); mutex_unlock(&net->nft.commit_mutex); WARN_ON_ONCE(!list_empty(&net->nft.tables)); diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 587897a2498b..dbc2e945c98e 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -47,13 +47,22 @@ static inline void nft_trace_packet(struct nft_traceinfo *info, } } +static void nft_bitwise_fast_eval(const struct nft_expr *expr, + struct nft_regs *regs) +{ + const struct nft_bitwise_fast_expr *priv = nft_expr_priv(expr); + u32 *src = ®s->data[priv->sreg]; + u32 *dst = ®s->data[priv->dreg]; + + *dst = (*src & priv->mask) ^ priv->xor; +} + static void nft_cmp_fast_eval(const struct nft_expr *expr, struct nft_regs *regs) { const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr); - u32 mask = nft_cmp_fast_mask(priv->len); - if ((regs->data[priv->sreg] & mask) == priv->data) + if (((regs->data[priv->sreg] & priv->mask) == priv->data) ^ priv->inv) return; regs->verdict.code = NFT_BREAK; } @@ -176,6 +185,8 @@ next_rule: nft_rule_for_each_expr(expr, last, rule) { if (expr->ops == &nft_cmp_fast_ops) nft_cmp_fast_eval(expr, ®s); + else if (expr->ops == &nft_bitwise_fast_ops) + nft_bitwise_fast_eval(expr, ®s); else if (expr->ops != &nft_payload_fast_ops || !nft_payload_fast_eval(expr, ®s, pkt)) expr_call_ops_eval(expr, ®s, pkt); diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 9ef37c1b7b3b..9f625724a20f 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -37,7 +37,7 @@ struct nft_flow_rule *nft_flow_rule_create(struct net *net, struct nft_expr *expr; expr = nft_expr_first(rule); - while (expr->ops && expr != nft_expr_last(rule)) { + while (nft_expr_more(rule, expr)) { if (expr->ops->offload_flags & NFT_OFFLOAD_F_ACTION) num_actions++; @@ -61,7 +61,7 @@ struct nft_flow_rule *nft_flow_rule_create(struct net *net, ctx->net = net; ctx->dep.type = NFT_OFFLOAD_DEP_UNSPEC; - while (expr->ops && expr != nft_expr_last(rule)) { + while (nft_expr_more(rule, expr)) { if (!expr->ops->offload) { err = -EOPNOTSUPP; goto err_out; @@ -323,8 +323,6 @@ static int nft_indr_block_offload_cmd(struct nft_base_chain *basechain, return nft_block_setup(basechain, &bo, cmd); } -#define FLOW_SETUP_BLOCK TC_SETUP_BLOCK - static int nft_chain_offload_cmd(struct nft_base_chain *basechain, struct net_device *dev, enum flow_block_command cmd) diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 3a2e64e13b22..d3df66a39b5e 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -46,6 +46,23 @@ static struct { const struct nfnetlink_subsystem __rcu *subsys; } table[NFNL_SUBSYS_COUNT]; +static struct lock_class_key nfnl_lockdep_keys[NFNL_SUBSYS_COUNT]; + +static const char *const nfnl_lockdep_names[NFNL_SUBSYS_COUNT] = { + [NFNL_SUBSYS_NONE] = "nfnl_subsys_none", + [NFNL_SUBSYS_CTNETLINK] = "nfnl_subsys_ctnetlink", + [NFNL_SUBSYS_CTNETLINK_EXP] = "nfnl_subsys_ctnetlink_exp", + [NFNL_SUBSYS_QUEUE] = "nfnl_subsys_queue", + [NFNL_SUBSYS_ULOG] = "nfnl_subsys_ulog", + [NFNL_SUBSYS_OSF] = "nfnl_subsys_osf", + [NFNL_SUBSYS_IPSET] = "nfnl_subsys_ipset", + [NFNL_SUBSYS_ACCT] = "nfnl_subsys_acct", + [NFNL_SUBSYS_CTNETLINK_TIMEOUT] = "nfnl_subsys_cttimeout", + [NFNL_SUBSYS_CTHELPER] = "nfnl_subsys_cthelper", + [NFNL_SUBSYS_NFTABLES] = "nfnl_subsys_nftables", + [NFNL_SUBSYS_NFT_COMPAT] = "nfnl_subsys_nftcompat", +}; + static const int nfnl_group2type[NFNLGRP_MAX+1] = { [NFNLGRP_CONNTRACK_NEW] = NFNL_SUBSYS_CTNETLINK, [NFNLGRP_CONNTRACK_UPDATE] = NFNL_SUBSYS_CTNETLINK, @@ -316,7 +333,7 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, return netlink_ack(skb, nlh, -EINVAL, NULL); replay: status = 0; - +replay_abort: skb = netlink_skb_clone(oskb, GFP_KERNEL); if (!skb) return netlink_ack(oskb, nlh, -ENOMEM, NULL); @@ -482,7 +499,7 @@ ack: } done: if (status & NFNL_BATCH_REPLAY) { - ss->abort(net, oskb, true); + ss->abort(net, oskb, NFNL_ABORT_AUTOLOAD); nfnl_err_reset(&err_list); kfree_skb(skb); module_put(ss->owner); @@ -493,11 +510,25 @@ done: status |= NFNL_BATCH_REPLAY; goto done; } else if (err) { - ss->abort(net, oskb, false); + ss->abort(net, oskb, NFNL_ABORT_NONE); netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL); } } else { - ss->abort(net, oskb, false); + enum nfnl_abort_action abort_action; + + if (status & NFNL_BATCH_FAILURE) + abort_action = NFNL_ABORT_NONE; + else + abort_action = NFNL_ABORT_VALIDATE; + + err = ss->abort(net, oskb, abort_action); + if (err == -EAGAIN) { + nfnl_err_reset(&err_list); + kfree_skb(skb); + module_put(ss->owner); + status |= NFNL_BATCH_FAILURE; + goto replay_abort; + } } if (ss->cleanup) ss->cleanup(net); @@ -632,7 +663,7 @@ static int __init nfnetlink_init(void) BUG_ON(nfnl_group2type[i] == NFNL_SUBSYS_NONE); for (i=0; i<NFNL_SUBSYS_COUNT; i++) - mutex_init(&table[i].mutex); + __mutex_init(&table[i].mutex, nfnl_lockdep_names[i], &nfnl_lockdep_keys[i]); return register_pernet_subsys(&nfnetlink_net_ops); } diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index bc37d6c59db4..bbd773d74377 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -163,11 +163,6 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, u32 len; int err; - if (!tb[NFTA_BITWISE_SREG] || - !tb[NFTA_BITWISE_DREG] || - !tb[NFTA_BITWISE_LEN]) - return -EINVAL; - err = nft_parse_u32_check(tb[NFTA_BITWISE_LEN], U8_MAX, &len); if (err < 0) return err; @@ -292,9 +287,143 @@ static const struct nft_expr_ops nft_bitwise_ops = { .offload = nft_bitwise_offload, }; +static int +nft_bitwise_extract_u32_data(const struct nlattr * const tb, u32 *out) +{ + struct nft_data_desc desc; + struct nft_data data; + int err = 0; + + err = nft_data_init(NULL, &data, sizeof(data), &desc, tb); + if (err < 0) + return err; + + if (desc.type != NFT_DATA_VALUE || desc.len != sizeof(u32)) { + err = -EINVAL; + goto err; + } + *out = data.data[0]; +err: + nft_data_release(&data, desc.type); + return err; +} + +static int nft_bitwise_fast_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_bitwise_fast_expr *priv = nft_expr_priv(expr); + int err; + + priv->sreg = nft_parse_register(tb[NFTA_BITWISE_SREG]); + err = nft_validate_register_load(priv->sreg, sizeof(u32)); + if (err < 0) + return err; + + priv->dreg = nft_parse_register(tb[NFTA_BITWISE_DREG]); + err = nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, sizeof(u32)); + if (err < 0) + return err; + + if (tb[NFTA_BITWISE_DATA]) + return -EINVAL; + + if (!tb[NFTA_BITWISE_MASK] || + !tb[NFTA_BITWISE_XOR]) + return -EINVAL; + + err = nft_bitwise_extract_u32_data(tb[NFTA_BITWISE_MASK], &priv->mask); + if (err < 0) + return err; + + err = nft_bitwise_extract_u32_data(tb[NFTA_BITWISE_XOR], &priv->xor); + if (err < 0) + return err; + + return 0; +} + +static int +nft_bitwise_fast_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_bitwise_fast_expr *priv = nft_expr_priv(expr); + struct nft_data data; + + if (nft_dump_register(skb, NFTA_BITWISE_SREG, priv->sreg)) + return -1; + if (nft_dump_register(skb, NFTA_BITWISE_DREG, priv->dreg)) + return -1; + if (nla_put_be32(skb, NFTA_BITWISE_LEN, htonl(sizeof(u32)))) + return -1; + if (nla_put_be32(skb, NFTA_BITWISE_OP, htonl(NFT_BITWISE_BOOL))) + return -1; + + data.data[0] = priv->mask; + if (nft_data_dump(skb, NFTA_BITWISE_MASK, &data, + NFT_DATA_VALUE, sizeof(u32)) < 0) + return -1; + + data.data[0] = priv->xor; + if (nft_data_dump(skb, NFTA_BITWISE_XOR, &data, + NFT_DATA_VALUE, sizeof(u32)) < 0) + return -1; + + return 0; +} + +static int nft_bitwise_fast_offload(struct nft_offload_ctx *ctx, + struct nft_flow_rule *flow, + const struct nft_expr *expr) +{ + const struct nft_bitwise_fast_expr *priv = nft_expr_priv(expr); + struct nft_offload_reg *reg = &ctx->regs[priv->dreg]; + + if (priv->xor || priv->sreg != priv->dreg || reg->len != sizeof(u32)) + return -EOPNOTSUPP; + + reg->mask.data[0] = priv->mask; + return 0; +} + +const struct nft_expr_ops nft_bitwise_fast_ops = { + .type = &nft_bitwise_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_bitwise_fast_expr)), + .eval = NULL, /* inlined */ + .init = nft_bitwise_fast_init, + .dump = nft_bitwise_fast_dump, + .offload = nft_bitwise_fast_offload, +}; + +static const struct nft_expr_ops * +nft_bitwise_select_ops(const struct nft_ctx *ctx, + const struct nlattr * const tb[]) +{ + int err; + u32 len; + + if (!tb[NFTA_BITWISE_LEN] || + !tb[NFTA_BITWISE_SREG] || + !tb[NFTA_BITWISE_DREG]) + return ERR_PTR(-EINVAL); + + err = nft_parse_u32_check(tb[NFTA_BITWISE_LEN], U8_MAX, &len); + if (err < 0) + return ERR_PTR(err); + + if (len != sizeof(u32)) + return &nft_bitwise_ops; + + if (tb[NFTA_BITWISE_OP] && + ntohl(nla_get_be32(tb[NFTA_BITWISE_OP])) != NFT_BITWISE_BOOL) + return &nft_bitwise_ops; + + return &nft_bitwise_fast_ops; +} + struct nft_expr_type nft_bitwise_type __read_mostly = { .name = "bitwise", - .ops = &nft_bitwise_ops, + .select_ops = nft_bitwise_select_ops, .policy = nft_bitwise_policy, .maxattr = NFTA_BITWISE_MAX, .owner = THIS_MODULE, diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index c78d01bc02e9..ff8528ad3dc6 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -161,16 +161,49 @@ static unsigned int nft_do_chain_inet(void *priv, struct sk_buff *skb, return nft_do_chain(&pkt, priv); } +static unsigned int nft_do_chain_inet_ingress(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct nf_hook_state ingress_state = *state; + struct nft_pktinfo pkt; + + switch (skb->protocol) { + case htons(ETH_P_IP): + /* Original hook is NFPROTO_NETDEV and NF_NETDEV_INGRESS. */ + ingress_state.pf = NFPROTO_IPV4; + ingress_state.hook = NF_INET_INGRESS; + nft_set_pktinfo(&pkt, skb, &ingress_state); + + if (nft_set_pktinfo_ipv4_ingress(&pkt, skb) < 0) + return NF_DROP; + break; + case htons(ETH_P_IPV6): + ingress_state.pf = NFPROTO_IPV6; + ingress_state.hook = NF_INET_INGRESS; + nft_set_pktinfo(&pkt, skb, &ingress_state); + + if (nft_set_pktinfo_ipv6_ingress(&pkt, skb) < 0) + return NF_DROP; + break; + default: + return NF_ACCEPT; + } + + return nft_do_chain(&pkt, priv); +} + static const struct nft_chain_type nft_chain_filter_inet = { .name = "filter", .type = NFT_CHAIN_T_DEFAULT, .family = NFPROTO_INET, - .hook_mask = (1 << NF_INET_LOCAL_IN) | + .hook_mask = (1 << NF_INET_INGRESS) | + (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD) | (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING), .hooks = { + [NF_INET_INGRESS] = nft_do_chain_inet_ingress, [NF_INET_LOCAL_IN] = nft_do_chain_inet, [NF_INET_LOCAL_OUT] = nft_do_chain_inet, [NF_INET_FORWARD] = nft_do_chain_inet, diff --git a/net/netfilter/nft_chain_route.c b/net/netfilter/nft_chain_route.c index 8826bbe71136..edd02cda57fc 100644 --- a/net/netfilter/nft_chain_route.c +++ b/net/netfilter/nft_chain_route.c @@ -42,7 +42,7 @@ static unsigned int nf_route_table_hook4(void *priv, iph->daddr != daddr || skb->mark != mark || iph->tos != tos) { - err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); + err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } @@ -92,7 +92,7 @@ static unsigned int nf_route_table_hook6(void *priv, skb->mark != mark || ipv6_hdr(skb)->hop_limit != hop_limit || flowlabel != *((u32 *)ipv6_hdr(skb)))) { - err = nf_ip6_route_me_harder(state->net, skb); + err = nf_ip6_route_me_harder(state->net, state->sk, skb); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index 16f4d84599ac..bc079d68a536 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -167,7 +167,6 @@ static int nft_cmp_fast_init(const struct nft_ctx *ctx, struct nft_cmp_fast_expr *priv = nft_expr_priv(expr); struct nft_data_desc desc; struct nft_data data; - u32 mask; int err; err = nft_data_init(NULL, &data, sizeof(data), &desc, @@ -181,10 +180,11 @@ static int nft_cmp_fast_init(const struct nft_ctx *ctx, return err; desc.len *= BITS_PER_BYTE; - mask = nft_cmp_fast_mask(desc.len); - priv->data = data.data[0] & mask; + priv->mask = nft_cmp_fast_mask(desc.len); + priv->data = data.data[0] & priv->mask; priv->len = desc.len; + priv->inv = ntohl(nla_get_be32(tb[NFTA_CMP_OP])) != NFT_CMP_EQ; return 0; } @@ -201,7 +201,7 @@ static int nft_cmp_fast_offload(struct nft_offload_ctx *ctx, }, .sreg = priv->sreg, .len = priv->len / BITS_PER_BYTE, - .op = NFT_CMP_EQ, + .op = priv->inv ? NFT_CMP_NEQ : NFT_CMP_EQ, }; return __nft_cmp_offload(ctx, flow, &cmp); @@ -210,11 +210,12 @@ static int nft_cmp_fast_offload(struct nft_offload_ctx *ctx, static int nft_cmp_fast_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr); + enum nft_cmp_ops op = priv->inv ? NFT_CMP_NEQ : NFT_CMP_EQ; struct nft_data data; if (nft_dump_register(skb, NFTA_CMP_SREG, priv->sreg)) goto nla_put_failure; - if (nla_put_be32(skb, NFTA_CMP_OP, htonl(NFT_CMP_EQ))) + if (nla_put_be32(skb, NFTA_CMP_OP, htonl(op))) goto nla_put_failure; data.data[0] = priv->data; @@ -272,7 +273,7 @@ nft_cmp_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) goto err1; } - if (desc.len <= sizeof(u32) && op == NFT_CMP_EQ) + if (desc.len <= sizeof(u32) && (op == NFT_CMP_EQ || op == NFT_CMP_NEQ)) return &nft_cmp_fast_ops; return &nft_cmp_ops; diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c index 3087e23297db..b77985986b24 100644 --- a/net/netfilter/nft_fwd_netdev.c +++ b/net/netfilter/nft_fwd_netdev.c @@ -138,6 +138,7 @@ static void nft_fwd_neigh_eval(const struct nft_expr *expr, return; skb->dev = dev; + skb->tstamp = 0; neigh_xmit(neigh_table, dev, addr, skb); out: regs->verdict.code = verdict; diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 7a2e59638499..dcd3c7b8a367 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -22,6 +22,7 @@ #include <linux/icmpv6.h> #include <linux/ip.h> #include <linux/ipv6.h> +#include <net/sctp/checksum.h> static bool nft_payload_rebuild_vlan_hdr(const struct sk_buff *skb, int mac_off, struct vlan_ethhdr *veth) @@ -484,6 +485,19 @@ static int nft_payload_l4csum_offset(const struct nft_pktinfo *pkt, return 0; } +static int nft_payload_csum_sctp(struct sk_buff *skb, int offset) +{ + struct sctphdr *sh; + + if (skb_ensure_writable(skb, offset + sizeof(*sh))) + return -1; + + sh = (struct sctphdr *)(skb->data + offset); + sh->checksum = sctp_compute_cksum(skb, offset); + skb->ip_summed = CHECKSUM_UNNECESSARY; + return 0; +} + static int nft_payload_l4csum_update(const struct nft_pktinfo *pkt, struct sk_buff *skb, __wsum fsum, __wsum tsum) @@ -587,6 +601,13 @@ static void nft_payload_set_eval(const struct nft_expr *expr, skb_store_bits(skb, offset, src, priv->len) < 0) goto err; + if (priv->csum_type == NFT_PAYLOAD_CSUM_SCTP && + pkt->tprot == IPPROTO_SCTP && + skb->ip_summed != CHECKSUM_PARTIAL) { + if (nft_payload_csum_sctp(skb, pkt->xt.thoff)) + goto err; + } + return; err: regs->verdict.code = NFT_BREAK; @@ -623,6 +644,13 @@ static int nft_payload_set_init(const struct nft_ctx *ctx, case NFT_PAYLOAD_CSUM_NONE: case NFT_PAYLOAD_CSUM_INET: break; + case NFT_PAYLOAD_CSUM_SCTP: + if (priv->base != NFT_PAYLOAD_TRANSPORT_HEADER) + return -EINVAL; + + if (priv->csum_offset != offsetof(struct sctphdr, checksum)) + return -EINVAL; + break; default: return -EOPNOTSUPP; } diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 637ce3e8c575..a28aca5124ce 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -14,6 +14,25 @@ struct nft_socket { }; }; +static void nft_socket_wildcard(const struct nft_pktinfo *pkt, + struct nft_regs *regs, struct sock *sk, + u32 *dest) +{ + switch (nft_pf(pkt)) { + case NFPROTO_IPV4: + nft_reg_store8(dest, inet_sk(sk)->inet_rcv_saddr == 0); + break; +#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) + case NFPROTO_IPV6: + nft_reg_store8(dest, ipv6_addr_any(&sk->sk_v6_rcv_saddr)); + break; +#endif + default: + regs->verdict.code = NFT_BREAK; + return; + } +} + static void nft_socket_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -59,6 +78,13 @@ static void nft_socket_eval(const struct nft_expr *expr, return; } break; + case NFT_SOCKET_WILDCARD: + if (!sk_fullsock(sk)) { + regs->verdict.code = NFT_BREAK; + return; + } + nft_socket_wildcard(pkt, regs, sk, dest); + break; default: WARN_ON(1); regs->verdict.code = NFT_BREAK; @@ -97,6 +123,7 @@ static int nft_socket_init(const struct nft_ctx *ctx, priv->key = ntohl(nla_get_u32(tb[NFTA_SOCKET_KEY])); switch(priv->key) { case NFT_SOCKET_TRANSPARENT: + case NFT_SOCKET_WILDCARD: len = sizeof(u8); break; case NFT_SOCKET_MARK: diff --git a/net/netfilter/utils.c b/net/netfilter/utils.c index cedf47ab3c6f..2182d361e273 100644 --- a/net/netfilter/utils.c +++ b/net/netfilter/utils.c @@ -191,8 +191,8 @@ static int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry skb->mark == rt_info->mark && iph->daddr == rt_info->daddr && iph->saddr == rt_info->saddr)) - return ip_route_me_harder(entry->state.net, skb, - RTN_UNSPEC); + return ip_route_me_harder(entry->state.net, entry->state.sk, + skb, RTN_UNSPEC); } #endif return 0; diff --git a/net/netfilter/xt_HMARK.c b/net/netfilter/xt_HMARK.c index 713fb38541df..8928ec56c388 100644 --- a/net/netfilter/xt_HMARK.c +++ b/net/netfilter/xt_HMARK.c @@ -276,7 +276,7 @@ hmark_pkt_set_htuple_ipv4(const struct sk_buff *skb, struct hmark_tuple *t, return 0; /* follow-up fragments don't contain ports, skip all fragments */ - if (ip->frag_off & htons(IP_MF | IP_OFFSET)) + if (ip_is_fragment(ip)) return 0; hmark_set_tuple_ports(skb, (ip->ihl * 4) + nhoff, t, info); diff --git a/net/netlabel/netlabel_calipso.c b/net/netlabel/netlabel_calipso.c index 249da67d50a2..4e62f2ad3575 100644 --- a/net/netlabel/netlabel_calipso.c +++ b/net/netlabel/netlabel_calipso.c @@ -304,7 +304,7 @@ static int netlbl_calipso_remove(struct sk_buff *skb, struct genl_info *info) /* NetLabel Generic NETLINK Command Definitions */ -static const struct genl_ops netlbl_calipso_ops[] = { +static const struct genl_small_ops netlbl_calipso_ops[] = { { .cmd = NLBL_CALIPSO_C_ADD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, @@ -342,8 +342,8 @@ static struct genl_family netlbl_calipso_gnl_family __ro_after_init = { .maxattr = NLBL_CALIPSO_A_MAX, .policy = calipso_genl_policy, .module = THIS_MODULE, - .ops = netlbl_calipso_ops, - .n_ops = ARRAY_SIZE(netlbl_calipso_ops), + .small_ops = netlbl_calipso_ops, + .n_small_ops = ARRAY_SIZE(netlbl_calipso_ops), }; /* NetLabel Generic NETLINK Protocol Functions @@ -426,7 +426,7 @@ void calipso_doi_free(struct calipso_doi *doi_def) /** * calipso_doi_remove - Remove an existing DOI from the CALIPSO protocol engine * @doi: the DOI value - * @audit_secid: the LSM secid to use in the audit message + * @audit_info: NetLabel audit information * * Description: * Removes a DOI definition from the CALIPSO engine. The NetLabel routines will @@ -595,7 +595,7 @@ int calipso_req_setattr(struct request_sock *req, /** * calipso_req_delattr - Delete the CALIPSO option from a request socket - * @reg: the request socket + * @req: the request socket * * Description: * Removes the CALIPSO option from a request socket, if present. diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index 0f16080b87cb..726dda95934c 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -724,7 +724,7 @@ static int netlbl_cipsov4_remove(struct sk_buff *skb, struct genl_info *info) * NetLabel Generic NETLINK Command Definitions */ -static const struct genl_ops netlbl_cipsov4_ops[] = { +static const struct genl_small_ops netlbl_cipsov4_ops[] = { { .cmd = NLBL_CIPSOV4_C_ADD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, @@ -762,8 +762,8 @@ static struct genl_family netlbl_cipsov4_gnl_family __ro_after_init = { .maxattr = NLBL_CIPSOV4_A_MAX, .policy = netlbl_cipsov4_genl_policy, .module = THIS_MODULE, - .ops = netlbl_cipsov4_ops, - .n_ops = ARRAY_SIZE(netlbl_cipsov4_ops), + .small_ops = netlbl_cipsov4_ops, + .n_small_ops = ARRAY_SIZE(netlbl_cipsov4_ops), }; /* diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index f73a8382c275..dc8c39f51f7d 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -612,9 +612,8 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry, audit_buf = netlbl_audit_start_common(AUDIT_MAC_MAP_DEL, audit_info); if (audit_buf != NULL) { audit_log_format(audit_buf, - " nlbl_domain=%s res=%u", - entry->domain ? entry->domain : "(default)", - ret_val == 0 ? 1 : 0); + " nlbl_domain=%s res=1", + entry->domain ? entry->domain : "(default)"); audit_log_end(audit_buf); } diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index e7a25fbfaf8b..eb1d66d20afb 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -757,7 +757,7 @@ version_failure: * NetLabel Generic NETLINK Command Definitions */ -static const struct genl_ops netlbl_mgmt_genl_ops[] = { +static const struct genl_small_ops netlbl_mgmt_genl_ops[] = { { .cmd = NLBL_MGMT_C_ADD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, @@ -823,8 +823,8 @@ static struct genl_family netlbl_mgmt_gnl_family __ro_after_init = { .maxattr = NLBL_MGMT_A_MAX, .policy = netlbl_mgmt_genl_policy, .module = THIS_MODULE, - .ops = netlbl_mgmt_genl_ops, - .n_ops = ARRAY_SIZE(netlbl_mgmt_genl_ops), + .small_ops = netlbl_mgmt_genl_ops, + .n_small_ops = ARRAY_SIZE(netlbl_mgmt_genl_ops), }; /* diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 77bb1bb22c3b..2e8e3f7b2111 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -1301,7 +1301,7 @@ unlabel_staticlistdef_return: * NetLabel Generic NETLINK Command Definitions */ -static const struct genl_ops netlbl_unlabel_genl_ops[] = { +static const struct genl_small_ops netlbl_unlabel_genl_ops[] = { { .cmd = NLBL_UNLABEL_C_STATICADD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, @@ -1367,8 +1367,8 @@ static struct genl_family netlbl_unlabel_gnl_family __ro_after_init = { .maxattr = NLBL_UNLABEL_A_MAX, .policy = netlbl_unlabel_genl_policy, .module = THIS_MODULE, - .ops = netlbl_unlabel_genl_ops, - .n_ops = ARRAY_SIZE(netlbl_unlabel_genl_ops), + .small_ops = netlbl_unlabel_genl_ops, + .n_small_ops = ARRAY_SIZE(netlbl_unlabel_genl_ops), }; /* diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index d2d1448274f5..daca50d6bb12 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -848,7 +848,7 @@ retry: * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the - * message has has the capability @cap in the user namespace @user_ns. + * message has the capability @cap in the user namespace @user_ns. */ bool __netlink_ns_capable(const struct netlink_skb_parms *nsp, struct user_namespace *user_ns, int cap) @@ -867,7 +867,7 @@ EXPORT_SYMBOL(__netlink_ns_capable); * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the - * message has has the capability @cap in the user namespace @user_ns. + * message has the capability @cap in the user namespace @user_ns. */ bool netlink_ns_capable(const struct sk_buff *skb, struct user_namespace *user_ns, int cap) @@ -883,7 +883,7 @@ EXPORT_SYMBOL(netlink_ns_capable); * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the - * message has has the capability @cap in all user namespaces. + * message has the capability @cap in all user namespaces. */ bool netlink_capable(const struct sk_buff *skb, int cap) { @@ -898,7 +898,7 @@ EXPORT_SYMBOL(netlink_capable); * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the - * message has has the capability @cap over the network namespace of + * message has the capability @cap over the network namespace of * the socket we received the message from. */ bool netlink_net_capable(const struct sk_buff *skb, int cap) @@ -1853,7 +1853,7 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) struct scm_cookie scm; u32 netlink_skb_flags = 0; - if (msg->msg_flags&MSG_OOB) + if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; err = scm_send(sock, msg, &scm, true); @@ -1916,7 +1916,7 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) refcount_inc(&skb->users); netlink_broadcast(sk, skb, dst_portid, dst_group, GFP_KERNEL); } - err = netlink_unicast(sk, skb, dst_portid, msg->msg_flags&MSG_DONTWAIT); + err = netlink_unicast(sk, skb, dst_portid, msg->msg_flags & MSG_DONTWAIT); out: scm_destroy(&scm); @@ -1929,12 +1929,12 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, struct scm_cookie scm; struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); - int noblock = flags&MSG_DONTWAIT; + int noblock = flags & MSG_DONTWAIT; size_t copied; struct sk_buff *skb, *data_skb; int err, ret; - if (flags&MSG_OOB) + if (flags & MSG_OOB) return -EOPNOTSUPP; copied = 0; @@ -2186,13 +2186,35 @@ EXPORT_SYMBOL(__nlmsg_put); * It would be better to create kernel thread. */ +static int netlink_dump_done(struct netlink_sock *nlk, struct sk_buff *skb, + struct netlink_callback *cb, + struct netlink_ext_ack *extack) +{ + struct nlmsghdr *nlh; + + nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(nlk->dump_done_errno), + NLM_F_MULTI | cb->answer_flags); + if (WARN_ON(!nlh)) + return -ENOBUFS; + + nl_dump_check_consistent(cb, nlh); + memcpy(nlmsg_data(nlh), &nlk->dump_done_errno, sizeof(nlk->dump_done_errno)); + + if (extack->_msg && nlk->flags & NETLINK_F_EXT_ACK) { + nlh->nlmsg_flags |= NLM_F_ACK_TLVS; + if (!nla_put_string(skb, NLMSGERR_ATTR_MSG, extack->_msg)) + nlmsg_end(skb, nlh); + } + + return 0; +} + static int netlink_dump(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); struct netlink_ext_ack extack = {}; struct netlink_callback *cb; struct sk_buff *skb = NULL; - struct nlmsghdr *nlh; struct module *module; int err = -ENOBUFS; int alloc_min_size; @@ -2258,22 +2280,19 @@ static int netlink_dump(struct sock *sk) return 0; } - nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, - sizeof(nlk->dump_done_errno), - NLM_F_MULTI | cb->answer_flags); - if (WARN_ON(!nlh)) + if (netlink_dump_done(nlk, skb, cb, &extack)) goto errout_skb; - nl_dump_check_consistent(cb, nlh); - - memcpy(nlmsg_data(nlh), &nlk->dump_done_errno, - sizeof(nlk->dump_done_errno)); - - if (extack._msg && nlk->flags & NETLINK_F_EXT_ACK) { - nlh->nlmsg_flags |= NLM_F_ACK_TLVS; - if (!nla_put_string(skb, NLMSGERR_ATTR_MSG, extack._msg)) - nlmsg_end(skb, nlh); +#ifdef CONFIG_COMPAT_NETLINK_MESSAGES + /* frag_list skb's data is used for compat tasks + * and the regular skb's data for normal (non-compat) tasks. + * See netlink_recvmsg(). + */ + if (unlikely(skb_shinfo(skb)->frag_list)) { + if (netlink_dump_done(nlk, skb_shinfo(skb)->frag_list, cb, &extack)) + goto errout_skb; } +#endif if (sk_filter(sk, skb)) kfree_skb(skb); @@ -2401,6 +2420,8 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, tlvlen += nla_total_size(sizeof(u32)); if (nlk_has_extack && extack && extack->cookie_len) tlvlen += nla_total_size(extack->cookie_len); + if (err && nlk_has_extack && extack && extack->policy) + tlvlen += netlink_policy_dump_attr_size_estimate(extack->policy); if (tlvlen) flags |= NLM_F_ACK_TLVS; @@ -2433,6 +2454,9 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, if (extack->cookie_len) WARN_ON(nla_put(skb, NLMSGERR_ATTR_COOKIE, extack->cookie_len, extack->cookie)); + if (extack->policy) + netlink_policy_dump_write_attr(skb, extack->policy, + NLMSGERR_ATTR_POLICY); } nlmsg_end(skb, rep); diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index c4b4d3376227..c992424e4d63 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -107,16 +107,83 @@ static const struct genl_family *genl_family_find_byname(char *name) return NULL; } -static const struct genl_ops *genl_get_cmd(u8 cmd, - const struct genl_family *family) +static int genl_get_cmd_cnt(const struct genl_family *family) +{ + return family->n_ops + family->n_small_ops; +} + +static void genl_op_from_full(const struct genl_family *family, + unsigned int i, struct genl_ops *op) +{ + *op = family->ops[i]; + + if (!op->maxattr) + op->maxattr = family->maxattr; + if (!op->policy) + op->policy = family->policy; +} + +static int genl_get_cmd_full(u32 cmd, const struct genl_family *family, + struct genl_ops *op) { int i; for (i = 0; i < family->n_ops; i++) - if (family->ops[i].cmd == cmd) - return &family->ops[i]; + if (family->ops[i].cmd == cmd) { + genl_op_from_full(family, i, op); + return 0; + } - return NULL; + return -ENOENT; +} + +static void genl_op_from_small(const struct genl_family *family, + unsigned int i, struct genl_ops *op) +{ + memset(op, 0, sizeof(*op)); + op->doit = family->small_ops[i].doit; + op->dumpit = family->small_ops[i].dumpit; + op->cmd = family->small_ops[i].cmd; + op->internal_flags = family->small_ops[i].internal_flags; + op->flags = family->small_ops[i].flags; + op->validate = family->small_ops[i].validate; + + op->maxattr = family->maxattr; + op->policy = family->policy; +} + +static int genl_get_cmd_small(u32 cmd, const struct genl_family *family, + struct genl_ops *op) +{ + int i; + + for (i = 0; i < family->n_small_ops; i++) + if (family->small_ops[i].cmd == cmd) { + genl_op_from_small(family, i, op); + return 0; + } + + return -ENOENT; +} + +static int genl_get_cmd(u32 cmd, const struct genl_family *family, + struct genl_ops *op) +{ + if (!genl_get_cmd_full(cmd, family, op)) + return 0; + return genl_get_cmd_small(cmd, family, op); +} + +static void genl_get_cmd_by_index(unsigned int i, + const struct genl_family *family, + struct genl_ops *op) +{ + if (i < family->n_ops) + genl_op_from_full(family, i, op); + else if (i < family->n_ops + family->n_small_ops) + genl_op_from_small(family, i - family->n_ops, op); + else + WARN_ON_ONCE(1); } static int genl_allocate_reserve_groups(int n_groups, int *first_id) @@ -222,7 +289,7 @@ static int genl_validate_assign_mc_groups(struct genl_family *family) family->mcgrp_offset = first_id; - /* if still initializing, can't and don't need to to realloc bitmaps */ + /* if still initializing, can't and don't need to realloc bitmaps */ if (!init_net.genl_sock) return 0; @@ -286,22 +353,25 @@ static void genl_unregister_mc_groups(const struct genl_family *family) static int genl_validate_ops(const struct genl_family *family) { - const struct genl_ops *ops = family->ops; - unsigned int n_ops = family->n_ops; int i, j; - if (WARN_ON(n_ops && !ops)) + if (WARN_ON(family->n_ops && !family->ops) || + WARN_ON(family->n_small_ops && !family->small_ops)) return -EINVAL; - if (!n_ops) - return 0; + for (i = 0; i < genl_get_cmd_cnt(family); i++) { + struct genl_ops op; - for (i = 0; i < n_ops; i++) { - if (ops[i].dumpit == NULL && ops[i].doit == NULL) + genl_get_cmd_by_index(i, family, &op); + if (op.dumpit == NULL && op.doit == NULL) return -EINVAL; - for (j = i + 1; j < n_ops; j++) - if (ops[i].cmd == ops[j].cmd) + for (j = i + 1; j < genl_get_cmd_cnt(family); j++) { + struct genl_ops op2; + + genl_get_cmd_by_index(j, family, &op2); + if (op.cmd == op2.cmd) return -EINVAL; + } } return 0; @@ -467,16 +537,16 @@ genl_family_rcv_msg_attrs_parse(const struct genl_family *family, struct nlattr **attrbuf; int err; - if (!family->maxattr) + if (!ops->maxattr) return NULL; - attrbuf = kmalloc_array(family->maxattr + 1, + attrbuf = kmalloc_array(ops->maxattr + 1, sizeof(struct nlattr *), GFP_KERNEL); if (!attrbuf) return ERR_PTR(-ENOMEM); - err = __nlmsg_parse(nlh, hdrlen, attrbuf, family->maxattr, - family->policy, validate, extack); + err = __nlmsg_parse(nlh, hdrlen, attrbuf, ops->maxattr, ops->policy, + validate, extack); if (err) { kfree(attrbuf); return ERR_PTR(err); @@ -524,7 +594,7 @@ no_attrs: return -ENOMEM; } info->family = ctx->family; - info->ops = ops; + info->op = *ops; info->attrs = attrs; cb->data = info; @@ -546,7 +616,7 @@ no_attrs: static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { - const struct genl_ops *ops = genl_dumpit_info(cb)->ops; + const struct genl_ops *ops = &genl_dumpit_info(cb)->op; int rc; genl_lock(); @@ -558,7 +628,7 @@ static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb) static int genl_lock_done(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); - const struct genl_ops *ops = info->ops; + const struct genl_ops *ops = &info->op; int rc = 0; if (ops->done) { @@ -574,7 +644,7 @@ static int genl_lock_done(struct netlink_callback *cb) static int genl_parallel_done(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); - const struct genl_ops *ops = info->ops; + const struct genl_ops *ops = &info->op; int rc = 0; if (ops->done) @@ -682,9 +752,9 @@ static int genl_family_rcv_msg(const struct genl_family *family, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { - const struct genl_ops *ops; struct net *net = sock_net(skb->sk); struct genlmsghdr *hdr = nlmsg_data(nlh); + struct genl_ops op; int hdrlen; /* this family doesn't exist in this netns */ @@ -695,24 +765,23 @@ static int genl_family_rcv_msg(const struct genl_family *family, if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) return -EINVAL; - ops = genl_get_cmd(hdr->cmd, family); - if (ops == NULL) + if (genl_get_cmd(hdr->cmd, family, &op)) return -EOPNOTSUPP; - if ((ops->flags & GENL_ADMIN_PERM) && + if ((op.flags & GENL_ADMIN_PERM) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; - if ((ops->flags & GENL_UNS_ADMIN_PERM) && + if ((op.flags & GENL_UNS_ADMIN_PERM) && !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) return -EPERM; if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP) return genl_family_rcv_msg_dumpit(family, skb, nlh, extack, - ops, hdrlen, net); + &op, hdrlen, net); else return genl_family_rcv_msg_doit(family, skb, nlh, extack, - ops, hdrlen, net); + &op, hdrlen, net); } static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -765,7 +834,7 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq, nla_put_u32(skb, CTRL_ATTR_MAXATTR, family->maxattr)) goto nla_put_failure; - if (family->n_ops) { + if (genl_get_cmd_cnt(family)) { struct nlattr *nla_ops; int i; @@ -773,23 +842,25 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq, if (nla_ops == NULL) goto nla_put_failure; - for (i = 0; i < family->n_ops; i++) { + for (i = 0; i < genl_get_cmd_cnt(family); i++) { struct nlattr *nest; - const struct genl_ops *ops = &family->ops[i]; - u32 op_flags = ops->flags; + struct genl_ops op; + u32 op_flags; - if (ops->dumpit) + genl_get_cmd_by_index(i, family, &op); + op_flags = op.flags; + if (op.dumpit) op_flags |= GENL_CMD_CAP_DUMP; - if (ops->doit) + if (op.doit) op_flags |= GENL_CMD_CAP_DO; - if (family->policy) + if (op.policy) op_flags |= GENL_CMD_CAP_HASPOL; nest = nla_nest_start_noflag(skb, i + 1); if (nest == NULL) goto nla_put_failure; - if (nla_put_u32(skb, CTRL_ATTR_OP_ID, ops->cmd) || + if (nla_put_u32(skb, CTRL_ATTR_OP_ID, op.cmd) || nla_put_u32(skb, CTRL_ATTR_OP_FLAGS, op_flags)) goto nla_put_failure; @@ -945,7 +1016,7 @@ ctrl_build_mcgrp_msg(const struct genl_family *family, return skb; } -static const struct nla_policy ctrl_policy[CTRL_ATTR_MAX+1] = { +static const struct nla_policy ctrl_policy_family[] = { [CTRL_ATTR_FAMILY_ID] = { .type = NLA_U16 }, [CTRL_ATTR_FAMILY_NAME] = { .type = NLA_NUL_STRING, .len = GENL_NAMSIZ - 1 }, @@ -1039,83 +1110,218 @@ static int genl_ctrl_event(int event, const struct genl_family *family, return 0; } -static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb) -{ +struct ctrl_dump_policy_ctx { + struct netlink_policy_dump_state *state; const struct genl_family *rt; - unsigned int fam_id = cb->args[0]; - int err; + unsigned int opidx; + u32 op; + u16 fam_id; + u8 policies:1, + single_op:1; +}; - if (!fam_id) { - struct nlattr *tb[CTRL_ATTR_MAX + 1]; +static const struct nla_policy ctrl_policy_policy[] = { + [CTRL_ATTR_FAMILY_ID] = { .type = NLA_U16 }, + [CTRL_ATTR_FAMILY_NAME] = { .type = NLA_NUL_STRING, + .len = GENL_NAMSIZ - 1 }, + [CTRL_ATTR_OP] = { .type = NLA_U32 }, +}; - err = genlmsg_parse(cb->nlh, &genl_ctrl, tb, - genl_ctrl.maxattr, - genl_ctrl.policy, cb->extack); - if (err) - return err; +static int ctrl_dumppolicy_start(struct netlink_callback *cb) +{ + const struct genl_dumpit_info *info = genl_dumpit_info(cb); + struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; + struct nlattr **tb = info->attrs; + const struct genl_family *rt; + struct genl_ops op; + int err, i; - if (!tb[CTRL_ATTR_FAMILY_ID] && !tb[CTRL_ATTR_FAMILY_NAME]) - return -EINVAL; + BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); - if (tb[CTRL_ATTR_FAMILY_ID]) { - fam_id = nla_get_u16(tb[CTRL_ATTR_FAMILY_ID]); - } else { - rt = genl_family_find_byname( - nla_data(tb[CTRL_ATTR_FAMILY_NAME])); - if (!rt) - return -ENOENT; - fam_id = rt->id; - } + if (!tb[CTRL_ATTR_FAMILY_ID] && !tb[CTRL_ATTR_FAMILY_NAME]) + return -EINVAL; + + if (tb[CTRL_ATTR_FAMILY_ID]) { + ctx->fam_id = nla_get_u16(tb[CTRL_ATTR_FAMILY_ID]); + } else { + rt = genl_family_find_byname( + nla_data(tb[CTRL_ATTR_FAMILY_NAME])); + if (!rt) + return -ENOENT; + ctx->fam_id = rt->id; } - rt = genl_family_find_byid(fam_id); + rt = genl_family_find_byid(ctx->fam_id); if (!rt) return -ENOENT; - if (!rt->policy) + ctx->rt = rt; + + if (tb[CTRL_ATTR_OP]) { + ctx->single_op = true; + ctx->op = nla_get_u32(tb[CTRL_ATTR_OP]); + + err = genl_get_cmd(ctx->op, rt, &op); + if (err) { + NL_SET_BAD_ATTR(cb->extack, tb[CTRL_ATTR_OP]); + return err; + } + + if (!op.policy) + return -ENODATA; + + return netlink_policy_dump_add_policy(&ctx->state, op.policy, + op.maxattr); + } + + for (i = 0; i < genl_get_cmd_cnt(rt); i++) { + genl_get_cmd_by_index(i, rt, &op); + + if (op.policy) { + err = netlink_policy_dump_add_policy(&ctx->state, + op.policy, + op.maxattr); + if (err) + return err; + } + } + + if (!ctx->state) return -ENODATA; + return 0; +} - err = netlink_policy_dump_start(rt->policy, rt->maxattr, &cb->args[1]); - if (err) - return err; +static void *ctrl_dumppolicy_prep(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; + void *hdr; + + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, &genl_ctrl, + NLM_F_MULTI, CTRL_CMD_GETPOLICY); + if (!hdr) + return NULL; + + if (nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, ctx->fam_id)) + return NULL; + + return hdr; +} + +static int ctrl_dumppolicy_put_op(struct sk_buff *skb, + struct netlink_callback *cb, + struct genl_ops *op) +{ + struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; + struct nlattr *nest_pol, *nest_op; + void *hdr; + int idx; + + /* skip if we have nothing to show */ + if (!op->policy) + return 0; + if (!op->doit && + (!op->dumpit || op->validate & GENL_DONT_VALIDATE_DUMP)) + return 0; + + hdr = ctrl_dumppolicy_prep(skb, cb); + if (!hdr) + return -ENOBUFS; + + nest_pol = nla_nest_start(skb, CTRL_ATTR_OP_POLICY); + if (!nest_pol) + goto err; + + nest_op = nla_nest_start(skb, op->cmd); + if (!nest_op) + goto err; + + /* for now both do/dump are always the same */ + idx = netlink_policy_dump_get_policy_idx(ctx->state, + op->policy, + op->maxattr); + + if (op->doit && nla_put_u32(skb, CTRL_ATTR_POLICY_DO, idx)) + goto err; + + if (op->dumpit && !(op->validate & GENL_DONT_VALIDATE_DUMP) && + nla_put_u32(skb, CTRL_ATTR_POLICY_DUMP, idx)) + goto err; + + nla_nest_end(skb, nest_op); + nla_nest_end(skb, nest_pol); + genlmsg_end(skb, hdr); - while (netlink_policy_dump_loop(cb->args[1])) { - void *hdr; + return 0; +err: + genlmsg_cancel(skb, hdr); + return -ENOBUFS; +} + +static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; + void *hdr; + + if (!ctx->policies) { + while (ctx->opidx < genl_get_cmd_cnt(ctx->rt)) { + struct genl_ops op; + + if (ctx->single_op) { + int err; + + err = genl_get_cmd(ctx->op, ctx->rt, &op); + if (WARN_ON(err)) + return skb->len; + + /* break out of the loop after this one */ + ctx->opidx = genl_get_cmd_cnt(ctx->rt); + } else { + genl_get_cmd_by_index(ctx->opidx, ctx->rt, &op); + } + + if (ctrl_dumppolicy_put_op(skb, cb, &op)) + return skb->len; + + ctx->opidx++; + } + + /* completed with the per-op policy index list */ + ctx->policies = true; + } + + while (netlink_policy_dump_loop(ctx->state)) { struct nlattr *nest; - hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, &genl_ctrl, - NLM_F_MULTI, CTRL_CMD_GETPOLICY); + hdr = ctrl_dumppolicy_prep(skb, cb); if (!hdr) goto nla_put_failure; - if (nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, rt->id)) - goto nla_put_failure; - nest = nla_nest_start(skb, CTRL_ATTR_POLICY); if (!nest) goto nla_put_failure; - if (netlink_policy_dump_write(skb, cb->args[1])) + if (netlink_policy_dump_write(skb, ctx->state)) goto nla_put_failure; nla_nest_end(skb, nest); genlmsg_end(skb, hdr); - continue; - -nla_put_failure: - genlmsg_cancel(skb, hdr); - break; } - cb->args[0] = fam_id; + return skb->len; + +nla_put_failure: + genlmsg_cancel(skb, hdr); return skb->len; } static int ctrl_dumppolicy_done(struct netlink_callback *cb) { - netlink_policy_dump_free(cb->args[1]); + struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; + + netlink_policy_dump_free(ctx->state); return 0; } @@ -1123,11 +1329,16 @@ static const struct genl_ops genl_ctrl_ops[] = { { .cmd = CTRL_CMD_GETFAMILY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .policy = ctrl_policy_family, + .maxattr = ARRAY_SIZE(ctrl_policy_family) - 1, .doit = ctrl_getfamily, .dumpit = ctrl_dumpfamily, }, { .cmd = CTRL_CMD_GETPOLICY, + .policy = ctrl_policy_policy, + .maxattr = ARRAY_SIZE(ctrl_policy_policy) - 1, + .start = ctrl_dumppolicy_start, .dumpit = ctrl_dumppolicy, .done = ctrl_dumppolicy_done, }, @@ -1146,8 +1357,6 @@ static struct genl_family genl_ctrl __ro_after_init = { .id = GENL_ID_CTRL, .name = "nlctrl", .version = 0x2, - .maxattr = CTRL_ATTR_MAX, - .policy = ctrl_policy, .netnsok = true, }; diff --git a/net/netlink/policy.c b/net/netlink/policy.c index 0176b59ce530..8d7c900e27f4 100644 --- a/net/netlink/policy.c +++ b/net/netlink/policy.c @@ -14,7 +14,7 @@ #define INITIAL_POLICIES_ALLOC 10 -struct nl_policy_dump { +struct netlink_policy_dump_state { unsigned int policy_idx; unsigned int attr_idx; unsigned int n_alloc; @@ -24,18 +24,19 @@ struct nl_policy_dump { } policies[]; }; -static int add_policy(struct nl_policy_dump **statep, +static int add_policy(struct netlink_policy_dump_state **statep, const struct nla_policy *policy, unsigned int maxtype) { - struct nl_policy_dump *state = *statep; + struct netlink_policy_dump_state *state = *statep; unsigned int n_alloc, i; if (!policy || !maxtype) return 0; for (i = 0; i < state->n_alloc; i++) { - if (state->policies[i].policy == policy) + if (state->policies[i].policy == policy && + state->policies[i].maxtype == maxtype) return 0; if (!state->policies[i].policy) { @@ -62,42 +63,85 @@ static int add_policy(struct nl_policy_dump **statep, return 0; } -static unsigned int get_policy_idx(struct nl_policy_dump *state, - const struct nla_policy *policy) +/** + * netlink_policy_dump_get_policy_idx - retrieve policy index + * @state: the policy dump state + * @policy: the policy to find + * @maxtype: the policy's maxattr + * + * Returns: the index of the given policy in the dump state + * + * Call this to find a policy index when you've added multiple and e.g. + * need to tell userspace which command has which policy (by index). + * + * Note: this will WARN and return 0 if the policy isn't found, which + * means it wasn't added in the first place, which would be an + * internal consistency bug. + */ +int netlink_policy_dump_get_policy_idx(struct netlink_policy_dump_state *state, + const struct nla_policy *policy, + unsigned int maxtype) { unsigned int i; + if (WARN_ON(!policy || !maxtype)) + return 0; + for (i = 0; i < state->n_alloc; i++) { - if (state->policies[i].policy == policy) + if (state->policies[i].policy == policy && + state->policies[i].maxtype == maxtype) return i; } - WARN_ON_ONCE(1); - return -1; + WARN_ON(1); + return 0; +} + +static struct netlink_policy_dump_state *alloc_state(void) +{ + struct netlink_policy_dump_state *state; + + state = kzalloc(struct_size(state, policies, INITIAL_POLICIES_ALLOC), + GFP_KERNEL); + if (!state) + return ERR_PTR(-ENOMEM); + state->n_alloc = INITIAL_POLICIES_ALLOC; + + return state; } -int netlink_policy_dump_start(const struct nla_policy *policy, - unsigned int maxtype, - unsigned long *_state) +/** + * netlink_policy_dump_add_policy - add a policy to the dump + * @pstate: state to add to, may be reallocated, must be %NULL the first time + * @policy: the new policy to add to the dump + * @maxtype: the new policy's max attr type + * + * Returns: 0 on success, a negative error code otherwise. + * + * Call this to allocate a policy dump state, and to add policies to it. This + * should be called from the dump start() callback. + * + * Note: on failures, any previously allocated state is freed. + */ +int netlink_policy_dump_add_policy(struct netlink_policy_dump_state **pstate, + const struct nla_policy *policy, + unsigned int maxtype) { - struct nl_policy_dump *state; + struct netlink_policy_dump_state *state = *pstate; unsigned int policy_idx; int err; - if (*_state) - return 0; + if (!state) { + state = alloc_state(); + if (IS_ERR(state)) + return PTR_ERR(state); + } /* * walk the policies and nested ones first, and build * a linear list of them. */ - state = kzalloc(struct_size(state, policies, INITIAL_POLICIES_ALLOC), - GFP_KERNEL); - if (!state) - return -ENOMEM; - state->n_alloc = INITIAL_POLICIES_ALLOC; - err = add_policy(&state, policy, maxtype); if (err) return err; @@ -128,62 +172,103 @@ int netlink_policy_dump_start(const struct nla_policy *policy, } } - *_state = (unsigned long)state; - + *pstate = state; return 0; } -static bool netlink_policy_dump_finished(struct nl_policy_dump *state) +static bool +netlink_policy_dump_finished(struct netlink_policy_dump_state *state) { return state->policy_idx >= state->n_alloc || !state->policies[state->policy_idx].policy; } -bool netlink_policy_dump_loop(unsigned long _state) +/** + * netlink_policy_dump_loop - dumping loop indicator + * @state: the policy dump state + * + * Returns: %true if the dump continues, %false otherwise + * + * Note: this frees the dump state when finishing + */ +bool netlink_policy_dump_loop(struct netlink_policy_dump_state *state) { - struct nl_policy_dump *state = (void *)_state; - return !netlink_policy_dump_finished(state); } -int netlink_policy_dump_write(struct sk_buff *skb, unsigned long _state) +int netlink_policy_dump_attr_size_estimate(const struct nla_policy *pt) { - struct nl_policy_dump *state = (void *)_state; - const struct nla_policy *pt; - struct nlattr *policy, *attr; - enum netlink_attribute_type type; - bool again; + /* nested + type */ + int common = 2 * nla_attr_size(sizeof(u32)); -send_attribute: - again = false; + switch (pt->type) { + case NLA_UNSPEC: + case NLA_REJECT: + /* these actually don't need any space */ + return 0; + case NLA_NESTED: + case NLA_NESTED_ARRAY: + /* common, policy idx, policy maxattr */ + return common + 2 * nla_attr_size(sizeof(u32)); + case NLA_U8: + case NLA_U16: + case NLA_U32: + case NLA_U64: + case NLA_MSECS: + case NLA_S8: + case NLA_S16: + case NLA_S32: + case NLA_S64: + /* maximum is common, u64 min/max with padding */ + return common + + 2 * (nla_attr_size(0) + nla_attr_size(sizeof(u64))); + case NLA_BITFIELD32: + return common + nla_attr_size(sizeof(u32)); + case NLA_STRING: + case NLA_NUL_STRING: + case NLA_BINARY: + /* maximum is common, u32 min-length/max-length */ + return common + 2 * nla_attr_size(sizeof(u32)); + case NLA_FLAG: + return common; + } - pt = &state->policies[state->policy_idx].policy[state->attr_idx]; + /* this should then cause a warning later */ + return 0; +} - policy = nla_nest_start(skb, state->policy_idx); - if (!policy) - return -ENOBUFS; +static int +__netlink_policy_dump_write_attr(struct netlink_policy_dump_state *state, + struct sk_buff *skb, + const struct nla_policy *pt, + int nestattr) +{ + int estimate = netlink_policy_dump_attr_size_estimate(pt); + enum netlink_attribute_type type; + struct nlattr *attr; - attr = nla_nest_start(skb, state->attr_idx); + attr = nla_nest_start(skb, nestattr); if (!attr) - goto nla_put_failure; + return -ENOBUFS; switch (pt->type) { default: case NLA_UNSPEC: case NLA_REJECT: /* skip - use NLA_MIN_LEN to advertise such */ - nla_nest_cancel(skb, policy); - again = true; - goto next; + nla_nest_cancel(skb, attr); + return -ENODATA; case NLA_NESTED: type = NL_ATTR_TYPE_NESTED; fallthrough; case NLA_NESTED_ARRAY: if (pt->type == NLA_NESTED_ARRAY) type = NL_ATTR_TYPE_NESTED_ARRAY; - if (pt->nested_policy && pt->len && + if (state && pt->nested_policy && pt->len && (nla_put_u32(skb, NL_POLICY_TYPE_ATTR_POLICY_IDX, - get_policy_idx(state, pt->nested_policy)) || + netlink_policy_dump_get_policy_idx(state, + pt->nested_policy, + pt->len)) || nla_put_u32(skb, NL_POLICY_TYPE_ATTR_POLICY_MAXTYPE, pt->len))) goto nla_put_failure; @@ -204,6 +289,14 @@ send_attribute: else type = NL_ATTR_TYPE_U64; + if (pt->validation_type == NLA_VALIDATE_MASK) { + if (nla_put_u64_64bit(skb, NL_POLICY_TYPE_ATTR_MASK, + pt->mask, + NL_POLICY_TYPE_ATTR_PAD)) + goto nla_put_failure; + break; + } + nla_get_range_unsigned(pt, &range); if (nla_put_u64_64bit(skb, NL_POLICY_TYPE_ATTR_MIN_VALUE_U, @@ -243,12 +336,6 @@ send_attribute: pt->bitfield32_valid)) goto nla_put_failure; break; - case NLA_EXACT_LEN: - type = NL_ATTR_TYPE_BINARY; - if (nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MIN_LENGTH, pt->len) || - nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MAX_LENGTH, pt->len)) - goto nla_put_failure; - break; case NLA_STRING: case NLA_NUL_STRING: case NLA_BINARY: @@ -258,14 +345,27 @@ send_attribute: type = NL_ATTR_TYPE_NUL_STRING; else type = NL_ATTR_TYPE_BINARY; - if (pt->len && nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MAX_LENGTH, - pt->len)) - goto nla_put_failure; - break; - case NLA_MIN_LEN: - type = NL_ATTR_TYPE_BINARY; - if (nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MIN_LENGTH, pt->len)) + + if (pt->validation_type == NLA_VALIDATE_RANGE || + pt->validation_type == NLA_VALIDATE_RANGE_WARN_TOO_LONG) { + struct netlink_range_validation range; + + nla_get_range_unsigned(pt, &range); + + if (range.min && + nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MIN_LENGTH, + range.min)) + goto nla_put_failure; + + if (range.max < U16_MAX && + nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MAX_LENGTH, + range.max)) + goto nla_put_failure; + } else if (pt->len && + nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MAX_LENGTH, + pt->len)) { goto nla_put_failure; + } break; case NLA_FLAG: type = NL_ATTR_TYPE_FLAG; @@ -275,8 +375,66 @@ send_attribute: if (nla_put_u32(skb, NL_POLICY_TYPE_ATTR_TYPE, type)) goto nla_put_failure; - /* finish and move state to next attribute */ nla_nest_end(skb, attr); + WARN_ON(attr->nla_len > estimate); + + return 0; +nla_put_failure: + nla_nest_cancel(skb, attr); + return -ENOBUFS; +} + +/** + * netlink_policy_dump_write_attr - write a given attribute policy + * @skb: the message skb to write to + * @pt: the attribute's policy + * @nestattr: the nested attribute ID to use + * + * Returns: 0 on success, an error code otherwise; -%ENODATA is + * special, indicating that there's no policy data and + * the attribute is generally rejected. + */ +int netlink_policy_dump_write_attr(struct sk_buff *skb, + const struct nla_policy *pt, + int nestattr) +{ + return __netlink_policy_dump_write_attr(NULL, skb, pt, nestattr); +} + +/** + * netlink_policy_dump_write - write current policy dump attributes + * @skb: the message skb to write to + * @state: the policy dump state + * + * Returns: 0 on success, an error code otherwise + */ +int netlink_policy_dump_write(struct sk_buff *skb, + struct netlink_policy_dump_state *state) +{ + const struct nla_policy *pt; + struct nlattr *policy; + bool again; + int err; + +send_attribute: + again = false; + + pt = &state->policies[state->policy_idx].policy[state->attr_idx]; + + policy = nla_nest_start(skb, state->policy_idx); + if (!policy) + return -ENOBUFS; + + err = __netlink_policy_dump_write_attr(state, skb, pt, state->attr_idx); + if (err == -ENODATA) { + nla_nest_cancel(skb, policy); + again = true; + goto next; + } else if (err) { + goto nla_put_failure; + } + + /* finish and move state to next attribute */ nla_nest_end(skb, policy); next: @@ -299,9 +457,13 @@ nla_put_failure: return -ENOBUFS; } -void netlink_policy_dump_free(unsigned long _state) +/** + * netlink_policy_dump_free - free policy dump state + * @state: the policy dump state to free + * + * Call this from the done() method to ensure dump state is freed. + */ +void netlink_policy_dump_free(struct netlink_policy_dump_state *state) { - struct nl_policy_dump *state = (void *)_state; - kfree(state); } diff --git a/net/nfc/digital_dep.c b/net/nfc/digital_dep.c index 304b1a9bb18a..5971fb6f51cc 100644 --- a/net/nfc/digital_dep.c +++ b/net/nfc/digital_dep.c @@ -38,9 +38,6 @@ #define DIGITAL_GB_BIT 0x02 -#define DIGITAL_NFC_DEP_REQ_RES_HEADROOM 2 /* SoD: [SB (NFC-A)] + LEN */ -#define DIGITAL_NFC_DEP_REQ_RES_TAILROOM 2 /* EoD: 2-byte CRC */ - #define DIGITAL_NFC_DEP_PFB_TYPE(pfb) ((pfb) & 0xE0) #define DIGITAL_NFC_DEP_PFB_TIMEOUT_BIT 0x10 diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index e894254c17d4..8709f3d4e7c4 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1217,7 +1217,7 @@ static int nfc_genl_fw_download(struct sk_buff *skb, struct genl_info *info) u32 idx; char firmware_name[NFC_FIRMWARE_NAME_MAXSIZE + 1]; - if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) + if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_FIRMWARE_NAME]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 2611657f40ca..b87bfc82f44f 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -9,7 +9,6 @@ #include <linux/in.h> #include <linux/ip.h> #include <linux/openvswitch.h> -#include <linux/netfilter_ipv6.h> #include <linux/sctp.h> #include <linux/tcp.h> #include <linux/udp.h> @@ -278,9 +277,11 @@ static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key, */ static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key) { - skb_pull_rcsum(skb, ETH_HLEN); - skb_reset_mac_header(skb); - skb_reset_mac_len(skb); + int err; + + err = skb_eth_pop(skb); + if (err) + return err; /* safe right before invalidate_flow_key */ key->mac_proto = MAC_PROTO_NONE; @@ -291,22 +292,12 @@ static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key) static int push_eth(struct sk_buff *skb, struct sw_flow_key *key, const struct ovs_action_push_eth *ethh) { - struct ethhdr *hdr; - - /* Add the new Ethernet header */ - if (skb_cow_head(skb, ETH_HLEN) < 0) - return -ENOMEM; - - skb_push(skb, ETH_HLEN); - skb_reset_mac_header(skb); - skb_reset_mac_len(skb); - - hdr = eth_hdr(skb); - ether_addr_copy(hdr->h_source, ethh->addresses.eth_src); - ether_addr_copy(hdr->h_dest, ethh->addresses.eth_dst); - hdr->h_proto = skb->protocol; + int err; - skb_postpush_rcsum(skb, hdr, ETH_HLEN); + err = skb_eth_push(skb, ethh->addresses.eth_dst, + ethh->addresses.eth_src); + if (err) + return err; /* safe right before invalidate_flow_key */ key->mac_proto = MAC_PROTO_ETHERNET; @@ -742,7 +733,8 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key, return 0; } -static int ovs_vport_output(struct net *net, struct sock *sk, struct sk_buff *skb) +static int ovs_vport_output(struct net *net, struct sock *sk, + struct sk_buff *skb) { struct ovs_frag_data *data = this_cpu_ptr(&ovs_frag_data_storage); struct vport *vport = data->vport; @@ -848,13 +840,9 @@ static void ovs_fragment(struct net *net, struct vport *vport, ip_do_fragment(net, skb->sk, skb, ovs_vport_output); refdst_drop(orig_dst); } else if (key->eth.type == htons(ETH_P_IPV6)) { - const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); unsigned long orig_dst; struct rt6_info ovs_rt; - if (!v6ops) - goto err; - prepare_frag(vport, skb, orig_network_offset, ovs_key_mac_proto(key)); memset(&ovs_rt, 0, sizeof(ovs_rt)); @@ -866,7 +854,7 @@ static void ovs_fragment(struct net *net, struct vport *vport, skb_dst_set_noref(skb, &ovs_rt.dst); IP6CB(skb)->frag_max_size = mru; - v6ops->fragment(net, skb->sk, skb, ovs_vport_output); + ipv6_stub->ipv6_fragment(net, skb->sk, skb, ovs_vport_output); refdst_drop(orig_dst); } else { WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.", @@ -925,7 +913,7 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, upcall.mru = OVS_CB(skb)->mru; for (a = nla_data(attr), rem = nla_len(attr); rem > 0; - a = nla_next(a, &rem)) { + a = nla_next(a, &rem)) { switch (nla_type(a)) { case OVS_USERSPACE_ATTR_USERDATA: upcall.userdata = a; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 12d42ab0193b..4beb96139d77 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1905,8 +1905,8 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net) lockdep_ovsl_is_held()) kfree_rcu(ct_limit, rcu); } - kfree(ovs_net->ct_limit_info->limits); - kfree(ovs_net->ct_limit_info); + kfree(info->limits); + kfree(info); } static struct sk_buff * @@ -2235,7 +2235,7 @@ exit_err: return err; } -static struct genl_ops ct_limit_genl_ops[] = { +static const struct genl_small_ops ct_limit_genl_ops[] = { { .cmd = OVS_CT_LIMIT_CMD_SET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN @@ -2267,8 +2267,8 @@ struct genl_family dp_ct_limit_genl_family __ro_after_init = { .policy = ct_limit_policy, .netnsok = true, .parallel_ops = true, - .ops = ct_limit_genl_ops, - .n_ops = ARRAY_SIZE(ct_limit_genl_ops), + .small_ops = ct_limit_genl_ops, + .n_small_ops = ARRAY_SIZE(ct_limit_genl_ops), .mcgrps = &ovs_ct_limit_multicast_group, .n_mcgrps = 1, .module = THIS_MODULE, diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 6e47ef7ef036..9d6ef6cb9b26 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -182,7 +182,7 @@ struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no) head = vport_hash_bucket(dp, port_no); hlist_for_each_entry_rcu(vport, head, dp_hash_node, - lockdep_ovsl_is_held()) { + lockdep_ovsl_is_held()) { if (vport->port_no == port_no) return vport; } @@ -254,7 +254,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) error = ovs_execute_actions(dp, skb, sf_acts, key); if (unlikely(error)) net_dbg_ratelimited("ovs: action execution error on datapath %s: %d\n", - ovs_dp_name(dp), error); + ovs_dp_name(dp), error); stats_counter = &stats->n_hit; @@ -302,7 +302,7 @@ err: static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb, const struct sw_flow_key *key, const struct dp_upcall_info *upcall_info, - uint32_t cutlen) + uint32_t cutlen) { unsigned int gso_type = skb_shinfo(skb)->gso_type; struct sw_flow_key later_key; @@ -652,7 +652,7 @@ static const struct nla_policy packet_policy[OVS_PACKET_ATTR_MAX + 1] = { [OVS_PACKET_ATTR_HASH] = { .type = NLA_U64 }, }; -static const struct genl_ops dp_packet_genl_ops[] = { +static const struct genl_small_ops dp_packet_genl_ops[] = { { .cmd = OVS_PACKET_CMD_EXECUTE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ @@ -668,8 +668,8 @@ static struct genl_family dp_packet_genl_family __ro_after_init = { .policy = packet_policy, .netnsok = true, .parallel_ops = true, - .ops = dp_packet_genl_ops, - .n_ops = ARRAY_SIZE(dp_packet_genl_ops), + .small_ops = dp_packet_genl_ops, + .n_small_ops = ARRAY_SIZE(dp_packet_genl_ops), .module = THIS_MODULE, }; @@ -1080,11 +1080,12 @@ error: } /* Factor out action copy to avoid "Wframe-larger-than=1024" warning. */ -static noinline_for_stack struct sw_flow_actions *get_flow_actions(struct net *net, - const struct nlattr *a, - const struct sw_flow_key *key, - const struct sw_flow_mask *mask, - bool log) +static noinline_for_stack +struct sw_flow_actions *get_flow_actions(struct net *net, + const struct nlattr *a, + const struct sw_flow_key *key, + const struct sw_flow_mask *mask, + bool log) { struct sw_flow_actions *acts; struct sw_flow_key masked_key; @@ -1383,7 +1384,8 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) ovs_notify(&dp_flow_genl_family, reply, info); } else { - netlink_set_err(sock_net(skb->sk)->genl_sock, 0, 0, PTR_ERR(reply)); + netlink_set_err(sock_net(skb->sk)->genl_sock, 0, 0, + PTR_ERR(reply)); } } @@ -1451,7 +1453,7 @@ static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = { [OVS_FLOW_ATTR_UFID_FLAGS] = { .type = NLA_U32 }, }; -static const struct genl_ops dp_flow_genl_ops[] = { +static const struct genl_small_ops dp_flow_genl_ops[] = { { .cmd = OVS_FLOW_CMD_NEW, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ @@ -1483,8 +1485,8 @@ static struct genl_family dp_flow_genl_family __ro_after_init = { .policy = flow_policy, .netnsok = true, .parallel_ops = true, - .ops = dp_flow_genl_ops, - .n_ops = ARRAY_SIZE(dp_flow_genl_ops), + .small_ops = dp_flow_genl_ops, + .n_small_ops = ARRAY_SIZE(dp_flow_genl_ops), .mcgrps = &ovs_dp_flow_multicast_group, .n_mcgrps = 1, .module = THIS_MODULE, @@ -1513,7 +1515,7 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb, int err; ovs_header = genlmsg_put(skb, portid, seq, &dp_datapath_genl_family, - flags, cmd); + flags, cmd); if (!ovs_header) goto error; @@ -1572,11 +1574,13 @@ static struct datapath *lookup_datapath(struct net *net, return dp ? dp : ERR_PTR(-ENODEV); } -static void ovs_dp_reset_user_features(struct sk_buff *skb, struct genl_info *info) +static void ovs_dp_reset_user_features(struct sk_buff *skb, + struct genl_info *info) { struct datapath *dp; - dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); + dp = lookup_datapath(sock_net(skb->sk), info->userhdr, + info->attrs); if (IS_ERR(dp)) return; @@ -1699,13 +1703,13 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) parms.port_no = OVSP_LOCAL; parms.upcall_portids = a[OVS_DP_ATTR_UPCALL_PID]; - err = ovs_dp_change(dp, a); - if (err) - goto err_destroy_meters; - /* So far only local changes have been made, now need the lock. */ ovs_lock(); + err = ovs_dp_change(dp, a); + if (err) + goto err_unlock_and_destroy_meters; + vport = new_vport(&parms); if (IS_ERR(vport)) { err = PTR_ERR(vport); @@ -1721,8 +1725,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) ovs_dp_reset_user_features(skb, info); } - ovs_unlock(); - goto err_destroy_meters; + goto err_unlock_and_destroy_meters; } err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid, @@ -1737,7 +1740,8 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) ovs_notify(&dp_datapath_genl_family, reply, info); return 0; -err_destroy_meters: +err_unlock_and_destroy_meters: + ovs_unlock(); ovs_meters_exit(dp); err_destroy_ports: kfree(dp->ports); @@ -1914,7 +1918,7 @@ static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = { PCPU_MIN_UNIT_SIZE / sizeof(struct mask_cache_entry)), }; -static const struct genl_ops dp_datapath_genl_ops[] = { +static const struct genl_small_ops dp_datapath_genl_ops[] = { { .cmd = OVS_DP_CMD_NEW, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ @@ -1946,8 +1950,8 @@ static struct genl_family dp_datapath_genl_family __ro_after_init = { .policy = datapath_policy, .netnsok = true, .parallel_ops = true, - .ops = dp_datapath_genl_ops, - .n_ops = ARRAY_SIZE(dp_datapath_genl_ops), + .small_ops = dp_datapath_genl_ops, + .n_small_ops = ARRAY_SIZE(dp_datapath_genl_ops), .mcgrps = &ovs_dp_datapath_multicast_group, .n_mcgrps = 1, .module = THIS_MODULE, @@ -2075,7 +2079,7 @@ static unsigned int ovs_get_max_headroom(struct datapath *dp) for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node, - lockdep_ovsl_is_held()) { + lockdep_ovsl_is_held()) { dev = vport->dev; dev_headroom = netdev_get_fwd_headroom(dev); if (dev_headroom > max_headroom) @@ -2093,10 +2097,11 @@ static void ovs_update_headroom(struct datapath *dp, unsigned int new_headroom) int i; dp->max_headroom = new_headroom; - for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) + for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node, - lockdep_ovsl_is_held()) + lockdep_ovsl_is_held()) netdev_set_rx_headroom(vport->dev, new_headroom); + } } static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) @@ -2396,7 +2401,7 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = { [OVS_VPORT_ATTR_NETNSID] = { .type = NLA_S32 }, }; -static const struct genl_ops dp_vport_genl_ops[] = { +static const struct genl_small_ops dp_vport_genl_ops[] = { { .cmd = OVS_VPORT_CMD_NEW, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ @@ -2428,8 +2433,8 @@ struct genl_family dp_vport_genl_family __ro_after_init = { .policy = vport_policy, .netnsok = true, .parallel_ops = true, - .ops = dp_vport_genl_ops, - .n_ops = ARRAY_SIZE(dp_vport_genl_ops), + .small_ops = dp_vport_genl_ops, + .n_small_ops = ARRAY_SIZE(dp_vport_genl_ops), .mcgrps = &ovs_dp_vport_multicast_group, .n_mcgrps = 1, .module = THIS_MODULE, @@ -2476,13 +2481,19 @@ error: static int __net_init ovs_init_net(struct net *net) { struct ovs_net *ovs_net = net_generic(net, ovs_net_id); + int err; INIT_LIST_HEAD(&ovs_net->dps); INIT_WORK(&ovs_net->dp_notify_work, ovs_dp_notify_wq); INIT_DELAYED_WORK(&ovs_net->masks_rebalance, ovs_dp_masks_rebalance); + + err = ovs_ct_init(net); + if (err) + return err; + schedule_delayed_work(&ovs_net->masks_rebalance, msecs_to_jiffies(DP_MASKS_REBALANCE_INTERVAL)); - return ovs_ct_init(net); + return 0; } static void __net_exit list_vports_from_net(struct net *net, struct net *dnet, @@ -2551,7 +2562,8 @@ static int __init dp_init(void) { int err; - BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > sizeof_field(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > + sizeof_field(struct sk_buff, cb)); pr_info("Open vSwitch switching datapath\n"); diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index e2235849a57e..c89c8da99f1a 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -111,12 +111,16 @@ static void flow_free(struct sw_flow *flow) if (ovs_identifier_is_key(&flow->id)) kfree(flow->id.unmasked_key); if (flow->sf_acts) - ovs_nla_free_flow_actions((struct sw_flow_actions __force *)flow->sf_acts); + ovs_nla_free_flow_actions((struct sw_flow_actions __force *) + flow->sf_acts); /* We open code this to make sure cpu 0 is always considered */ - for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) + for (cpu = 0; cpu < nr_cpu_ids; + cpu = cpumask_next(cpu, &flow->cpu_used_mask)) { if (flow->stats[cpu]) kmem_cache_free(flow_stats_cache, (struct sw_flow_stats __force *)flow->stats[cpu]); + } + kmem_cache_free(flow_cache, flow); } @@ -164,7 +168,6 @@ static struct table_instance *table_instance_alloc(int new_size) ti->n_buckets = new_size; ti->node_ver = 0; - ti->keep_flows = false; get_random_bytes(&ti->hash_seed, sizeof(u32)); return ti; @@ -172,7 +175,7 @@ static struct table_instance *table_instance_alloc(int new_size) static void __mask_array_destroy(struct mask_array *ma) { - free_percpu(ma->masks_usage_cntr); + free_percpu(ma->masks_usage_stats); kfree(ma); } @@ -192,19 +195,19 @@ static void tbl_mask_array_reset_counters(struct mask_array *ma) * zero based counter we store the value at reset, and subtract it * later when processing. */ - for (i = 0; i < ma->max; i++) { + for (i = 0; i < ma->max; i++) { ma->masks_usage_zero_cntr[i] = 0; for_each_possible_cpu(cpu) { - u64 *usage_counters = per_cpu_ptr(ma->masks_usage_cntr, - cpu); + struct mask_array_stats *stats; unsigned int start; u64 counter; + stats = per_cpu_ptr(ma->masks_usage_stats, cpu); do { - start = u64_stats_fetch_begin_irq(&ma->syncp); - counter = usage_counters[i]; - } while (u64_stats_fetch_retry_irq(&ma->syncp, start)); + start = u64_stats_fetch_begin_irq(&stats->syncp); + counter = stats->usage_cntrs[i]; + } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); ma->masks_usage_zero_cntr[i] += counter; } @@ -227,9 +230,10 @@ static struct mask_array *tbl_mask_array_alloc(int size) sizeof(struct sw_flow_mask *) * size); - new->masks_usage_cntr = __alloc_percpu(sizeof(u64) * size, - __alignof__(u64)); - if (!new->masks_usage_cntr) { + new->masks_usage_stats = __alloc_percpu(sizeof(struct mask_array_stats) + + sizeof(u64) * size, + __alignof__(u64)); + if (!new->masks_usage_stats) { kfree(new); return NULL; } @@ -273,7 +277,7 @@ static int tbl_mask_array_add_mask(struct flow_table *tbl, if (ma_count >= ma->max) { err = tbl_mask_array_realloc(tbl, ma->max + - MASK_ARRAY_SIZE_MIN); + MASK_ARRAY_SIZE_MIN); if (err) return err; @@ -288,7 +292,7 @@ static int tbl_mask_array_add_mask(struct flow_table *tbl, BUG_ON(ovsl_dereference(ma->masks[ma_count])); rcu_assign_pointer(ma->masks[ma_count], new); - WRITE_ONCE(ma->count, ma_count +1); + WRITE_ONCE(ma->count, ma_count + 1); return 0; } @@ -309,10 +313,10 @@ static void tbl_mask_array_del_mask(struct flow_table *tbl, return; found: - WRITE_ONCE(ma->count, ma_count -1); + WRITE_ONCE(ma->count, ma_count - 1); - rcu_assign_pointer(ma->masks[i], ma->masks[ma_count -1]); - RCU_INIT_POINTER(ma->masks[ma_count -1], NULL); + rcu_assign_pointer(ma->masks[i], ma->masks[ma_count - 1]); + RCU_INIT_POINTER(ma->masks[ma_count - 1], NULL); kfree_rcu(mask, rcu); @@ -386,7 +390,7 @@ static struct mask_cache *tbl_mask_cache_alloc(u32 size) } int ovs_flow_tbl_masks_cache_resize(struct flow_table *table, u32 size) { - struct mask_cache *mc = rcu_dereference(table->mask_cache); + struct mask_cache *mc = rcu_dereference_ovsl(table->mask_cache); struct mask_cache *new; if (size == mc->cache_size) @@ -448,26 +452,23 @@ free_mask_cache: static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu) { - struct table_instance *ti = container_of(rcu, struct table_instance, rcu); + struct table_instance *ti; + ti = container_of(rcu, struct table_instance, rcu); __table_instance_destroy(ti); } static void table_instance_flow_free(struct flow_table *table, - struct table_instance *ti, - struct table_instance *ufid_ti, - struct sw_flow *flow, - bool count) + struct table_instance *ti, + struct table_instance *ufid_ti, + struct sw_flow *flow) { hlist_del_rcu(&flow->flow_table.node[ti->node_ver]); - if (count) - table->count--; + table->count--; if (ovs_identifier_is_ufid(&flow->id)) { hlist_del_rcu(&flow->ufid_table.node[ufid_ti->node_ver]); - - if (count) - table->ufid_count--; + table->ufid_count--; } flow_mask_remove(table, flow->mask); @@ -480,22 +481,25 @@ void table_instance_flow_flush(struct flow_table *table, { int i; - if (ti->keep_flows) - return; - for (i = 0; i < ti->n_buckets; i++) { - struct sw_flow *flow; struct hlist_head *head = &ti->buckets[i]; struct hlist_node *n; + struct sw_flow *flow; hlist_for_each_entry_safe(flow, n, head, flow_table.node[ti->node_ver]) { table_instance_flow_free(table, ti, ufid_ti, - flow, false); + flow); ovs_flow_free(flow, true); } } + + if (WARN_ON(table->count != 0 || + table->ufid_count != 0)) { + table->count = 0; + table->ufid_count = 0; + } } static void table_instance_destroy(struct table_instance *ti, @@ -596,8 +600,6 @@ static void flow_table_copy_flows(struct table_instance *old, lockdep_ovsl_is_held()) table_instance_insert(new, flow); } - - old->keep_flows = true; } static struct table_instance *table_instance_rehash(struct table_instance *ti, @@ -632,8 +634,6 @@ int ovs_flow_tbl_flush(struct flow_table *flow_table) rcu_assign_pointer(flow_table->ti, new_ti); rcu_assign_pointer(flow_table->ufid_ti, new_ufid_ti); flow_table->last_rehash = jiffies; - flow_table->count = 0; - flow_table->ufid_count = 0; table_instance_flow_flush(flow_table, old_ti, old_ufid_ti); table_instance_destroy(old_ti, old_ufid_ti); @@ -661,7 +661,7 @@ static int flow_key_start(const struct sw_flow_key *key) return 0; else return rounddown(offsetof(struct sw_flow_key, phy), - sizeof(long)); + sizeof(long)); } static bool cmp_key(const struct sw_flow_key *key1, @@ -673,7 +673,7 @@ static bool cmp_key(const struct sw_flow_key *key1, long diffs = 0; int i; - for (i = key_start; i < key_end; i += sizeof(long)) + for (i = key_start; i < key_end; i += sizeof(long)) diffs |= *cp1++ ^ *cp2++; return diffs == 0; @@ -713,7 +713,7 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti, (*n_mask_hit)++; hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver], - lockdep_ovsl_is_held()) { + lockdep_ovsl_is_held()) { if (flow->mask == mask && flow->flow_table.hash == hash && flow_cmp_masked_key(flow, &masked_key, &mask->range)) return flow; @@ -723,6 +723,8 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti, /* Flow lookup does full lookup on flow table. It starts with * mask from index passed in *index. + * This function MUST be called with BH disabled due to the use + * of CPU specific variables. */ static struct sw_flow *flow_lookup(struct flow_table *tbl, struct table_instance *ti, @@ -732,7 +734,7 @@ static struct sw_flow *flow_lookup(struct flow_table *tbl, u32 *n_cache_hit, u32 *index) { - u64 *usage_counters = this_cpu_ptr(ma->masks_usage_cntr); + struct mask_array_stats *stats = this_cpu_ptr(ma->masks_usage_stats); struct sw_flow *flow; struct sw_flow_mask *mask; int i; @@ -742,9 +744,9 @@ static struct sw_flow *flow_lookup(struct flow_table *tbl, if (mask) { flow = masked_flow_lookup(ti, key, mask, n_mask_hit); if (flow) { - u64_stats_update_begin(&ma->syncp); - usage_counters[*index]++; - u64_stats_update_end(&ma->syncp); + u64_stats_update_begin(&stats->syncp); + stats->usage_cntrs[*index]++; + u64_stats_update_end(&stats->syncp); (*n_cache_hit)++; return flow; } @@ -763,9 +765,9 @@ static struct sw_flow *flow_lookup(struct flow_table *tbl, flow = masked_flow_lookup(ti, key, mask, n_mask_hit); if (flow) { /* Found */ *index = i; - u64_stats_update_begin(&ma->syncp); - usage_counters[*index]++; - u64_stats_update_end(&ma->syncp); + u64_stats_update_begin(&stats->syncp); + stats->usage_cntrs[*index]++; + u64_stats_update_end(&stats->syncp); return flow; } } @@ -851,9 +853,17 @@ struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl, struct mask_array *ma = rcu_dereference_ovsl(tbl->mask_array); u32 __always_unused n_mask_hit; u32 __always_unused n_cache_hit; + struct sw_flow *flow; u32 index = 0; - return flow_lookup(tbl, ti, ma, key, &n_mask_hit, &n_cache_hit, &index); + /* This function gets called trough the netlink interface and therefore + * is preemptible. However, flow_lookup() function needs to be called + * with BH disabled due to CPU specific variables. + */ + local_bh_disable(); + flow = flow_lookup(tbl, ti, ma, key, &n_mask_hit, &n_cache_hit, &index); + local_bh_enable(); + return flow; } struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl, @@ -897,7 +907,8 @@ static bool ovs_flow_cmp_ufid(const struct sw_flow *flow, return !memcmp(flow->id.ufid, sfid->ufid, sfid->ufid_len); } -bool ovs_flow_cmp(const struct sw_flow *flow, const struct sw_flow_match *match) +bool ovs_flow_cmp(const struct sw_flow *flow, + const struct sw_flow_match *match) { if (ovs_identifier_is_ufid(&flow->id)) return flow_cmp_masked_key(flow, match->key, &match->range); @@ -916,7 +927,7 @@ struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *tbl, hash = ufid_hash(ufid); head = find_bucket(ti, hash); hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver], - lockdep_ovsl_is_held()) { + lockdep_ovsl_is_held()) { if (flow->ufid_table.hash == hash && ovs_flow_cmp_ufid(flow, ufid)) return flow; @@ -950,7 +961,7 @@ void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow) struct table_instance *ufid_ti = ovsl_dereference(table->ufid_ti); BUG_ON(table->count == 0); - table_instance_flow_free(table, ti, ufid_ti, flow, true); + table_instance_flow_free(table, ti, ufid_ti, flow); } static struct sw_flow_mask *mask_alloc(void) @@ -1107,9 +1118,8 @@ void ovs_flow_masks_rebalance(struct flow_table *table) if (!masks_and_count) return; - for (i = 0; i < ma->max; i++) { + for (i = 0; i < ma->max; i++) { struct sw_flow_mask *mask; - unsigned int start; int cpu; mask = rcu_dereference_ovsl(ma->masks[i]); @@ -1120,14 +1130,16 @@ void ovs_flow_masks_rebalance(struct flow_table *table) masks_and_count[i].counter = 0; for_each_possible_cpu(cpu) { - u64 *usage_counters = per_cpu_ptr(ma->masks_usage_cntr, - cpu); + struct mask_array_stats *stats; + unsigned int start; u64 counter; + stats = per_cpu_ptr(ma->masks_usage_stats, cpu); do { - start = u64_stats_fetch_begin_irq(&ma->syncp); - counter = usage_counters[i]; - } while (u64_stats_fetch_retry_irq(&ma->syncp, start)); + start = u64_stats_fetch_begin_irq(&stats->syncp); + counter = stats->usage_cntrs[i]; + } while (u64_stats_fetch_retry_irq(&stats->syncp, + start)); masks_and_count[i].counter += counter; } diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h index 6e7d4ac59353..9e659db78c05 100644 --- a/net/openvswitch/flow_table.h +++ b/net/openvswitch/flow_table.h @@ -38,12 +38,16 @@ struct mask_count { u64 counter; }; +struct mask_array_stats { + struct u64_stats_sync syncp; + u64 usage_cntrs[]; +}; + struct mask_array { struct rcu_head rcu; int count, max; - u64 __percpu *masks_usage_cntr; + struct mask_array_stats __percpu *masks_usage_stats; u64 *masks_usage_zero_cntr; - struct u64_stats_sync syncp; struct sw_flow_mask __rcu *masks[]; }; @@ -53,7 +57,6 @@ struct table_instance { struct rcu_head rcu; int node_ver; u32 hash_seed; - bool keep_flows; }; struct flow_table { diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index 3d3d8e094546..8fbefd52af7f 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -672,7 +672,7 @@ bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb, return false; } -static struct genl_ops dp_meter_genl_ops[] = { +static const struct genl_small_ops dp_meter_genl_ops[] = { { .cmd = OVS_METER_CMD_FEATURES, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, /* OK for unprivileged users. */ @@ -711,8 +711,8 @@ struct genl_family dp_meter_genl_family __ro_after_init = { .policy = meter_policy, .netnsok = true, .parallel_ops = true, - .ops = dp_meter_genl_ops, - .n_ops = ARRAY_SIZE(dp_meter_genl_ops), + .small_ops = dp_meter_genl_ops, + .n_small_ops = ARRAY_SIZE(dp_meter_genl_ops), .mcgrps = &ovs_meter_multicast_group, .n_mcgrps = 1, .module = THIS_MODULE, diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 58a7b8312c28..1e30d8df3ba5 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -86,31 +86,13 @@ static void internal_dev_destructor(struct net_device *dev) static void internal_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) { - int i; - memset(stats, 0, sizeof(*stats)); stats->rx_errors = dev->stats.rx_errors; stats->tx_errors = dev->stats.tx_errors; stats->tx_dropped = dev->stats.tx_dropped; stats->rx_dropped = dev->stats.rx_dropped; - for_each_possible_cpu(i) { - const struct pcpu_sw_netstats *percpu_stats; - struct pcpu_sw_netstats local_stats; - unsigned int start; - - percpu_stats = per_cpu_ptr(dev->tstats, i); - - do { - start = u64_stats_fetch_begin_irq(&percpu_stats->syncp); - local_stats = *percpu_stats; - } while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start)); - - stats->rx_bytes += local_stats.rx_bytes; - stats->rx_packets += local_stats.rx_packets; - stats->tx_bytes += local_stats.tx_bytes; - stats->tx_packets += local_stats.tx_packets; - } + dev_fetch_sw_netstats(stats, dev->tstats); } static const struct net_device_ops internal_dev_netdev_ops = { @@ -225,7 +207,6 @@ static void internal_dev_destroy(struct vport *vport) static netdev_tx_t internal_dev_recv(struct sk_buff *skb) { struct net_device *netdev = skb->dev; - struct pcpu_sw_netstats *stats; if (unlikely(!(netdev->flags & IFF_UP))) { kfree_skb(skb); @@ -240,12 +221,7 @@ static netdev_tx_t internal_dev_recv(struct sk_buff *skb) skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, netdev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); - - stats = this_cpu_ptr(netdev->tstats); - u64_stats_update_begin(&stats->syncp); - stats->rx_packets++; - stats->rx_bytes += skb->len; - u64_stats_update_end(&stats->syncp); + dev_sw_netstats_rx_add(netdev, skb->len); netif_rx(skb); return NETDEV_TX_OK; diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 0d44c5c013fa..82d801f063b7 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -98,7 +98,7 @@ struct vport *ovs_vport_locate(const struct net *net, const char *name) struct vport *vport; hlist_for_each_entry_rcu(vport, bucket, hash_node, - lockdep_ovsl_is_held()) + lockdep_ovsl_is_held()) if (!strcmp(name, ovs_vport_name(vport)) && net_eq(ovs_dp_get_net(vport->dp), net)) return vport; @@ -118,7 +118,7 @@ struct vport *ovs_vport_locate(const struct net *net, const char *name) * vport_free(). */ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops, - const struct vport_parms *parms) + const struct vport_parms *parms) { struct vport *vport; size_t alloc_size; @@ -397,7 +397,8 @@ int ovs_vport_get_upcall_portids(const struct vport *vport, * * Returns the portid of the target socket. Must be called with rcu_read_lock. */ -u32 ovs_vport_find_upcall_portid(const struct vport *vport, struct sk_buff *skb) +u32 ovs_vport_find_upcall_portid(const struct vport *vport, + struct sk_buff *skb) { struct vport_portids *ids; u32 ids_index; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 2b33e977a905..cefbd50c1090 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -93,52 +93,56 @@ /* Assumptions: - - if device has no dev->hard_header routine, it adds and removes ll header - inside itself. In this case ll header is invisible outside of device, - but higher levels still should reserve dev->hard_header_len. - Some devices are enough clever to reallocate skb, when header - will not fit to reserved space (tunnel), another ones are silly - (PPP). + - If the device has no dev->header_ops, there is no LL header visible + above the device. In this case, its hard_header_len should be 0. + The device may prepend its own header internally. In this case, its + needed_headroom should be set to the space needed for it to add its + internal header. + For example, a WiFi driver pretending to be an Ethernet driver should + set its hard_header_len to be the Ethernet header length, and set its + needed_headroom to be (the real WiFi header length - the fake Ethernet + header length). - packet socket receives packets with pulled ll header, so that SOCK_RAW should push it back. On receive: ----------- -Incoming, dev->hard_header!=NULL +Incoming, dev->header_ops != NULL mac_header -> ll header data -> data -Outgoing, dev->hard_header!=NULL +Outgoing, dev->header_ops != NULL mac_header -> ll header data -> ll header -Incoming, dev->hard_header==NULL - mac_header -> UNKNOWN position. It is very likely, that it points to ll - header. PPP makes it, that is wrong, because introduce - assymetry between rx and tx paths. +Incoming, dev->header_ops == NULL + mac_header -> data + However drivers often make it point to the ll header. + This is incorrect because the ll header should be invisible to us. data -> data -Outgoing, dev->hard_header==NULL - mac_header -> data. ll header is still not built! +Outgoing, dev->header_ops == NULL + mac_header -> data. ll header is invisible to us. data -> data Resume - If dev->hard_header==NULL we are unlikely to restore sensible ll header. + If dev->header_ops == NULL we are unable to restore the ll header, + because it is invisible to us. On transmit: ------------ -dev->hard_header != NULL +dev->header_ops != NULL mac_header -> ll header data -> ll header -dev->hard_header == NULL (ll header is added by device, we cannot control it) +dev->header_ops == NULL (ll header is invisible to us) mac_header -> data data -> data - We should set nh.raw on output to correct posistion, + We should set network_header on output to the correct position, packet classifier depends on it. */ @@ -177,7 +181,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, #define BLOCK_LEN(x) ((x)->hdr.bh1.blk_len) #define BLOCK_SNUM(x) ((x)->hdr.bh1.seq_num) #define BLOCK_O2PRIV(x) ((x)->offset_to_priv) -#define BLOCK_PRIV(x) ((void *)((char *)(x) + BLOCK_O2PRIV(x))) struct packet_sock; static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, diff --git a/net/psample/psample.c b/net/psample/psample.c index a042261a45c5..33e238c965bd 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -96,7 +96,7 @@ static int psample_nl_cmd_get_group_dumpit(struct sk_buff *msg, return msg->len; } -static const struct genl_ops psample_nl_ops[] = { +static const struct genl_small_ops psample_nl_ops[] = { { .cmd = PSAMPLE_CMD_GET_GROUP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, @@ -112,8 +112,8 @@ static struct genl_family psample_nl_family __ro_after_init = { .netnsok = true, .module = THIS_MODULE, .mcgrps = psample_nl_mcgrps, - .ops = psample_nl_ops, - .n_ops = ARRAY_SIZE(psample_nl_ops), + .small_ops = psample_nl_ops, + .n_small_ops = ARRAY_SIZE(psample_nl_ops), .n_mcgrps = ARRAY_SIZE(psample_nl_mcgrps), }; diff --git a/net/rds/cong.c b/net/rds/cong.c index ccdff09a79c8..8b689ebbd5b5 100644 --- a/net/rds/cong.c +++ b/net/rds/cong.c @@ -236,7 +236,7 @@ void rds_cong_queue_updates(struct rds_cong_map *map) * tcp_setsockopt and/or tcp_sendmsg will deadlock * when it tries to get the sock_lock()) * 2. Interrupts are masked so that we can mark the - * the port congested from both send and recv paths. + * port congested from both send and recv paths. * (See comment around declaration of rdc_cong_lock). * An attempt to get the sock_lock() here will * therefore trigger warnings. diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index c3319ff3ee11..b36b60668b1d 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -711,7 +711,7 @@ static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event, bool isv6) * original size. The only way to tell the difference is by looking at * the contents, which are initialized to zero. * If the protocol version fields aren't set, this is a connection attempt - * from an older version. This could could be 3.0 or 2.0 - we can't tell. + * from an older version. This could be 3.0 or 2.0 - we can't tell. * We really should have changed this for OFED 1.3 :-( */ @@ -956,9 +956,10 @@ int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id, bool isv6) rds_ib_cm_fill_conn_param(conn, &conn_param, &dp, conn->c_proposed_version, UINT_MAX, UINT_MAX, isv6); - ret = rdma_connect(cm_id, &conn_param); + ret = rdma_connect_locked(cm_id, &conn_param); if (ret) - rds_ib_conn_error(conn, "rdma_connect failed (%d)\n", ret); + rds_ib_conn_error(conn, "rdma_connect_locked failed (%d)\n", + ret); out: /* Beware - returning non-zero tells the rdma_cm to destroy diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 694d411dc72f..3cffcec5fb37 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -310,8 +310,8 @@ static int rds_ib_recv_refill_one(struct rds_connection *conn, struct rds_ib_connection *ic = conn->c_transport_data; struct ib_sge *sge; int ret = -ENOMEM; - gfp_t slab_mask = GFP_NOWAIT; - gfp_t page_mask = GFP_NOWAIT; + gfp_t slab_mask = gfp; + gfp_t page_mask = gfp; if (gfp & __GFP_DIRECT_RECLAIM) { slab_mask = GFP_KERNEL; @@ -1020,7 +1020,7 @@ void rds_ib_recv_cqe_handler(struct rds_ib_connection *ic, rds_ib_stats_inc(s_ib_rx_ring_empty); if (rds_ib_ring_low(&ic->i_recv_ring)) { - rds_ib_recv_refill(conn, 0, GFP_NOWAIT); + rds_ib_recv_refill(conn, 0, GFP_NOWAIT | __GFP_NOWARN); rds_ib_stats_inc(s_ib_rx_refill_from_cq); } } diff --git a/net/rds/rdma.c b/net/rds/rdma.c index ccdd304eae0a..1d0afb1dd77b 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -269,7 +269,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, goto out; } else { nents = ret; - sg = kcalloc(nents, sizeof(*sg), GFP_KERNEL); + sg = kmalloc_array(nents, sizeof(*sg), GFP_KERNEL); if (!sg) { ret = -ENOMEM; goto out; diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 186c8a889b16..0a2f4817ec6c 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -308,9 +308,10 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, key = NULL; /* a no-security key */ memset(&p, 0, sizeof(p)); - p.user_call_ID = user_call_ID; - p.tx_total_len = tx_total_len; - p.interruptibility = interruptibility; + p.user_call_ID = user_call_ID; + p.tx_total_len = tx_total_len; + p.interruptibility = interruptibility; + p.kernel = true; memset(&cp, 0, sizeof(cp)); cp.local = rx->local; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 97aebb5d19db..dce48162f6c2 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -76,14 +76,12 @@ struct rxrpc_net { struct work_struct service_conn_reaper; struct timer_list service_conn_reap_timer; - unsigned int nr_client_conns; - unsigned int nr_active_client_conns; - bool kill_all_client_conns; bool live; + + bool kill_all_client_conns; + atomic_t nr_client_conns; spinlock_t client_conn_cache_lock; /* Lock for ->*_client_conns */ spinlock_t client_conn_discard_lock; /* Prevent multiple discarders */ - struct list_head waiting_client_conns; - struct list_head active_client_conns; struct list_head idle_client_conns; struct work_struct client_conn_reaper; struct timer_list client_conn_reap_timer; @@ -275,8 +273,8 @@ struct rxrpc_local { struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */ struct sk_buff_head reject_queue; /* packets awaiting rejection */ struct sk_buff_head event_queue; /* endpoint event packets awaiting processing */ - struct rb_root client_conns; /* Client connections by socket params */ - spinlock_t client_conns_lock; /* Lock for client_conns */ + struct rb_root client_bundles; /* Client connection bundles by socket params */ + spinlock_t client_bundles_lock; /* Lock for client_bundles */ spinlock_t lock; /* access lock */ rwlock_t services_lock; /* lock for services list */ int debug_id; /* debug ID for printks */ @@ -353,10 +351,7 @@ struct rxrpc_conn_parameters { enum rxrpc_conn_flag { RXRPC_CONN_HAS_IDR, /* Has a client conn ID assigned */ RXRPC_CONN_IN_SERVICE_CONNS, /* Conn is in peer->service_conns */ - RXRPC_CONN_IN_CLIENT_CONNS, /* Conn is in local->client_conns */ - RXRPC_CONN_EXPOSED, /* Conn has extra ref for exposure */ RXRPC_CONN_DONT_REUSE, /* Don't reuse this connection */ - RXRPC_CONN_COUNTED, /* Counted by rxrpc_nr_client_conns */ RXRPC_CONN_PROBING_FOR_UPGRADE, /* Probing for service upgrade */ RXRPC_CONN_FINAL_ACK_0, /* Need final ACK for channel 0 */ RXRPC_CONN_FINAL_ACK_1, /* Need final ACK for channel 1 */ @@ -377,19 +372,6 @@ enum rxrpc_conn_event { }; /* - * The connection cache state. - */ -enum rxrpc_conn_cache_state { - RXRPC_CONN_CLIENT_INACTIVE, /* Conn is not yet listed */ - RXRPC_CONN_CLIENT_WAITING, /* Conn is on wait list, waiting for capacity */ - RXRPC_CONN_CLIENT_ACTIVE, /* Conn is on active list, doing calls */ - RXRPC_CONN_CLIENT_UPGRADE, /* Conn is on active list, probing for upgrade */ - RXRPC_CONN_CLIENT_CULLED, /* Conn is culled and delisted, doing calls */ - RXRPC_CONN_CLIENT_IDLE, /* Conn is on idle list, doing mostly nothing */ - RXRPC_CONN__NR_CACHE_STATES -}; - -/* * The connection protocol state. */ enum rxrpc_conn_proto_state { @@ -405,6 +387,23 @@ enum rxrpc_conn_proto_state { }; /* + * RxRPC client connection bundle. + */ +struct rxrpc_bundle { + struct rxrpc_conn_parameters params; + atomic_t usage; + unsigned int debug_id; + bool try_upgrade; /* True if the bundle is attempting upgrade */ + bool alloc_conn; /* True if someone's getting a conn */ + short alloc_error; /* Error from last conn allocation */ + spinlock_t channel_lock; + struct rb_node local_node; /* Node in local->client_conns */ + struct list_head waiting_calls; /* Calls waiting for channels */ + unsigned long avail_chans; /* Mask of available channels */ + struct rxrpc_connection *conns[4]; /* The connections in the bundle (max 4) */ +}; + +/* * RxRPC connection definition * - matched by { local, peer, epoch, conn_id, direction } * - each connection can only handle four simultaneous calls @@ -417,10 +416,7 @@ struct rxrpc_connection { struct rcu_head rcu; struct list_head cache_link; - spinlock_t channel_lock; - unsigned char active_chans; /* Mask of active channels */ -#define RXRPC_ACTIVE_CHANS_MASK ((1 << RXRPC_MAXCALLS) - 1) - struct list_head waiting_calls; /* Calls waiting for channels */ + unsigned char act_chans; /* Mask of active channels */ struct rxrpc_channel { unsigned long final_ack_at; /* Time at which to issue final ACK */ struct rxrpc_call __rcu *call; /* Active call */ @@ -437,10 +433,8 @@ struct rxrpc_connection { struct timer_list timer; /* Conn event timer */ struct work_struct processor; /* connection event processor */ - union { - struct rb_node client_node; /* Node in local->client_conns */ - struct rb_node service_node; /* Node in peer->service_conns */ - }; + struct rxrpc_bundle *bundle; /* Client connection bundle */ + struct rb_node service_node; /* Node in peer->service_conns */ struct list_head proc_link; /* link in procfs list */ struct list_head link; /* link in master connection list */ struct sk_buff_head rx_queue; /* received conn-level packets */ @@ -452,7 +446,6 @@ struct rxrpc_connection { unsigned long events; unsigned long idle_timestamp; /* Time at which last became idle */ spinlock_t state_lock; /* state-change lock */ - enum rxrpc_conn_cache_state cache_state; enum rxrpc_conn_proto_state state; /* current state of connection */ u32 abort_code; /* Abort code of connection abort */ int debug_id; /* debug ID for printks */ @@ -464,6 +457,7 @@ struct rxrpc_connection { u8 security_size; /* security header size */ u8 security_ix; /* security type */ u8 out_clientflag; /* RXRPC_CLIENT_INITIATED if we are client */ + u8 bundle_shift; /* Index into bundle->avail_chans */ short error; /* Local error code */ }; @@ -493,6 +487,8 @@ enum rxrpc_call_flag { RXRPC_CALL_RX_HEARD, /* The peer responded at least once to this call */ RXRPC_CALL_RX_UNDERRUN, /* Got data underrun */ RXRPC_CALL_DISCONNECTED, /* The call has been disconnected */ + RXRPC_CALL_KERNEL, /* The call was made by the kernel */ + RXRPC_CALL_UPGRADE, /* Service upgrade was requested for the call */ }; /* @@ -576,7 +572,7 @@ struct rxrpc_call { struct work_struct processor; /* Event processor */ rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */ struct list_head link; /* link in master call list */ - struct list_head chan_wait_link; /* Link in conn->waiting_calls */ + struct list_head chan_wait_link; /* Link in conn->bundle->waiting_calls */ struct hlist_node error_link; /* link in error distribution list */ struct list_head accept_link; /* Link in rx->acceptq */ struct list_head recvmsg_link; /* Link in rx->recvmsg_q */ @@ -726,6 +722,7 @@ struct rxrpc_call_params { u32 normal; /* Max time since last call packet (msec) */ } timeouts; u8 nr_timeouts; /* Number of timeouts specified */ + bool kernel; /* T if kernel is making the call */ enum rxrpc_interruptibility interruptibility; /* How is interruptible is the call? */ }; @@ -812,18 +809,19 @@ static inline bool rxrpc_is_client_call(const struct rxrpc_call *call) /* * conn_client.c */ -extern unsigned int rxrpc_max_client_connections; extern unsigned int rxrpc_reap_client_connections; extern unsigned long rxrpc_conn_idle_client_expiry; extern unsigned long rxrpc_conn_idle_client_fast_expiry; extern struct idr rxrpc_client_conn_ids; void rxrpc_destroy_client_conn_ids(void); +struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *); +void rxrpc_put_bundle(struct rxrpc_bundle *); int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_call *, struct rxrpc_conn_parameters *, struct sockaddr_rxrpc *, gfp_t); void rxrpc_expose_client_call(struct rxrpc_call *); -void rxrpc_disconnect_client_call(struct rxrpc_call *); +void rxrpc_disconnect_client_call(struct rxrpc_bundle *, struct rxrpc_call *); void rxrpc_put_client_conn(struct rxrpc_connection *); void rxrpc_discard_expired_client_conns(struct work_struct *); void rxrpc_destroy_all_client_connections(struct rxrpc_net *); @@ -833,6 +831,7 @@ void rxrpc_clean_up_local_conns(struct rxrpc_local *); * conn_event.c */ void rxrpc_process_connection(struct work_struct *); +void rxrpc_process_delayed_final_acks(struct rxrpc_connection *, bool); /* * conn_object.c @@ -849,7 +848,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *); void rxrpc_kill_connection(struct rxrpc_connection *); bool rxrpc_queue_conn(struct rxrpc_connection *); void rxrpc_see_connection(struct rxrpc_connection *); -void rxrpc_get_connection(struct rxrpc_connection *); +struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *); struct rxrpc_connection *rxrpc_get_connection_maybe(struct rxrpc_connection *); void rxrpc_put_service_conn(struct rxrpc_connection *); void rxrpc_service_connection_reaper(struct work_struct *); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index ed49769b459d..c845594b663f 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -40,6 +40,11 @@ const char *const rxrpc_call_completions[NR__RXRPC_CALL_COMPLETIONS] = { struct kmem_cache *rxrpc_call_jar; +static struct semaphore rxrpc_call_limiter = + __SEMAPHORE_INITIALIZER(rxrpc_call_limiter, 1000); +static struct semaphore rxrpc_kernel_call_limiter = + __SEMAPHORE_INITIALIZER(rxrpc_kernel_call_limiter, 1000); + static void rxrpc_call_timer_expired(struct timer_list *t) { struct rxrpc_call *call = from_timer(call, t, timer); @@ -209,6 +214,34 @@ static void rxrpc_start_call_timer(struct rxrpc_call *call) } /* + * Wait for a call slot to become available. + */ +static struct semaphore *rxrpc_get_call_slot(struct rxrpc_call_params *p, gfp_t gfp) +{ + struct semaphore *limiter = &rxrpc_call_limiter; + + if (p->kernel) + limiter = &rxrpc_kernel_call_limiter; + if (p->interruptibility == RXRPC_UNINTERRUPTIBLE) { + down(limiter); + return limiter; + } + return down_interruptible(limiter) < 0 ? NULL : limiter; +} + +/* + * Release a call slot. + */ +static void rxrpc_put_call_slot(struct rxrpc_call *call) +{ + struct semaphore *limiter = &rxrpc_call_limiter; + + if (test_bit(RXRPC_CALL_KERNEL, &call->flags)) + limiter = &rxrpc_kernel_call_limiter; + up(limiter); +} + +/* * Set up a call for the given parameters. * - Called with the socket lock held, which it must release. * - If it returns a call, the call's lock will need releasing by the caller. @@ -224,15 +257,21 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, { struct rxrpc_call *call, *xcall; struct rxrpc_net *rxnet; + struct semaphore *limiter; struct rb_node *parent, **pp; const void *here = __builtin_return_address(0); int ret; _enter("%p,%lx", rx, p->user_call_ID); + limiter = rxrpc_get_call_slot(p, gfp); + if (!limiter) + return ERR_PTR(-ERESTARTSYS); + call = rxrpc_alloc_client_call(rx, srx, gfp, debug_id); if (IS_ERR(call)) { release_sock(&rx->sk); + up(limiter); _leave(" = %ld", PTR_ERR(call)); return call; } @@ -242,6 +281,8 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, trace_rxrpc_call(call->debug_id, rxrpc_call_new_client, atomic_read(&call->usage), here, (const void *)p->user_call_ID); + if (p->kernel) + __set_bit(RXRPC_CALL_KERNEL, &call->flags); /* We need to protect a partially set up call against the user as we * will be acting outside the socket lock. @@ -468,6 +509,8 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) BUG(); spin_unlock_bh(&call->lock); + rxrpc_put_call_slot(call); + del_timer_sync(&call->timer); /* Make sure we don't get any more notifications */ diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 159e3eda7914..7e574c75be8e 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -1,63 +1,15 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* Client connection-specific management code. * - * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2016, 2020 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * Client connections need to be cached for a little while after they've made a * call so as to handle retransmitted DATA packets in case the server didn't * receive the final ACK or terminating ABORT we sent it. * - * Client connections can be in one of a number of cache states: - * - * (1) INACTIVE - The connection is not held in any list and may not have been - * exposed to the world. If it has been previously exposed, it was - * discarded from the idle list after expiring. - * - * (2) WAITING - The connection is waiting for the number of client conns to - * drop below the maximum capacity. Calls may be in progress upon it from - * when it was active and got culled. - * - * The connection is on the rxrpc_waiting_client_conns list which is kept - * in to-be-granted order. Culled conns with waiters go to the back of - * the queue just like new conns. - * - * (3) ACTIVE - The connection has at least one call in progress upon it, it - * may freely grant available channels to new calls and calls may be - * waiting on it for channels to become available. - * - * The connection is on the rxnet->active_client_conns list which is kept - * in activation order for culling purposes. - * - * rxrpc_nr_active_client_conns is held incremented also. - * - * (4) UPGRADE - As for ACTIVE, but only one call may be in progress and is - * being used to probe for service upgrade. - * - * (5) CULLED - The connection got summarily culled to try and free up - * capacity. Calls currently in progress on the connection are allowed to - * continue, but new calls will have to wait. There can be no waiters in - * this state - the conn would have to go to the WAITING state instead. - * - * (6) IDLE - The connection has no calls in progress upon it and must have - * been exposed to the world (ie. the EXPOSED flag must be set). When it - * expires, the EXPOSED flag is cleared and the connection transitions to - * the INACTIVE state. - * - * The connection is on the rxnet->idle_client_conns list which is kept in - * order of how soon they'll expire. - * * There are flags of relevance to the cache: * - * (1) EXPOSED - The connection ID got exposed to the world. If this flag is - * set, an extra ref is added to the connection preventing it from being - * reaped when it has no calls outstanding. This flag is cleared and the - * ref dropped when a conn is discarded from the idle list. - * - * This allows us to move terminal call state retransmission to the - * connection and to discard the call immediately we think it is done - * with. It also give us a chance to reuse the connection. - * * (2) DONT_REUSE - The connection should be discarded as soon as possible and * should not be reused. This is set when an exclusive connection is used * or a call ID counter overflows. @@ -78,7 +30,6 @@ #include "ar-internal.h" -__read_mostly unsigned int rxrpc_max_client_connections = 1000; __read_mostly unsigned int rxrpc_reap_client_connections = 900; __read_mostly unsigned long rxrpc_conn_idle_client_expiry = 2 * 60 * HZ; __read_mostly unsigned long rxrpc_conn_idle_client_fast_expiry = 2 * HZ; @@ -89,8 +40,6 @@ __read_mostly unsigned long rxrpc_conn_idle_client_fast_expiry = 2 * HZ; DEFINE_IDR(rxrpc_client_conn_ids); static DEFINE_SPINLOCK(rxrpc_conn_id_lock); -static void rxrpc_cull_active_client_conns(struct rxrpc_net *); - /* * Get a connection ID and epoch for a client connection from the global pool. * The connection struct pointer is then recorded in the idr radix tree. The @@ -162,13 +111,50 @@ void rxrpc_destroy_client_conn_ids(void) } /* + * Allocate a connection bundle. + */ +static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_conn_parameters *cp, + gfp_t gfp) +{ + struct rxrpc_bundle *bundle; + + bundle = kzalloc(sizeof(*bundle), gfp); + if (bundle) { + bundle->params = *cp; + rxrpc_get_peer(bundle->params.peer); + atomic_set(&bundle->usage, 1); + spin_lock_init(&bundle->channel_lock); + INIT_LIST_HEAD(&bundle->waiting_calls); + } + return bundle; +} + +struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *bundle) +{ + atomic_inc(&bundle->usage); + return bundle; +} + +void rxrpc_put_bundle(struct rxrpc_bundle *bundle) +{ + unsigned int d = bundle->debug_id; + unsigned int u = atomic_dec_return(&bundle->usage); + + _debug("PUT B=%x %u", d, u); + if (u == 0) { + rxrpc_put_peer(bundle->params.peer); + kfree(bundle); + } +} + +/* * Allocate a client connection. */ static struct rxrpc_connection * -rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp) +rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp) { struct rxrpc_connection *conn; - struct rxrpc_net *rxnet = cp->local->rxnet; + struct rxrpc_net *rxnet = bundle->params.local->rxnet; int ret; _enter(""); @@ -180,15 +166,11 @@ rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp) } atomic_set(&conn->usage, 1); - if (cp->exclusive) - __set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); - if (cp->upgrade) - __set_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags); - - conn->params = *cp; + conn->bundle = bundle; + conn->params = bundle->params; conn->out_clientflag = RXRPC_CLIENT_INITIATED; conn->state = RXRPC_CONN_CLIENT; - conn->service_id = cp->service_id; + conn->service_id = conn->params.service_id; ret = rxrpc_get_client_connection_id(conn, gfp); if (ret < 0) @@ -207,14 +189,16 @@ rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp) list_add_tail(&conn->proc_link, &rxnet->conn_proc_list); write_unlock(&rxnet->conn_lock); - /* We steal the caller's peer ref. */ - cp->peer = NULL; + rxrpc_get_bundle(bundle); + rxrpc_get_peer(conn->params.peer); rxrpc_get_local(conn->params.local); key_get(conn->params.key); trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_client, atomic_read(&conn->usage), __builtin_return_address(0)); + + atomic_inc(&rxnet->nr_client_conns); trace_rxrpc_client(conn, -1, rxrpc_client_alloc); _leave(" = %p", conn); return conn; @@ -234,13 +218,18 @@ error_0: */ static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn) { - struct rxrpc_net *rxnet = conn->params.local->rxnet; + struct rxrpc_net *rxnet; int id_cursor, id, distance, limit; + if (!conn) + goto dont_reuse; + + rxnet = conn->params.local->rxnet; if (test_bit(RXRPC_CONN_DONT_REUSE, &conn->flags)) goto dont_reuse; - if (conn->proto.epoch != rxnet->epoch) + if (conn->state != RXRPC_CONN_CLIENT || + conn->proto.epoch != rxnet->epoch) goto mark_dont_reuse; /* The IDR tree gets very expensive on memory if the connection IDs are @@ -254,7 +243,7 @@ static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn) distance = id - id_cursor; if (distance < 0) distance = -distance; - limit = max(rxrpc_max_client_connections * 4, 1024U); + limit = max_t(unsigned long, atomic_read(&rxnet->nr_conns) * 4, 1024); if (distance > limit) goto mark_dont_reuse; @@ -267,277 +256,247 @@ dont_reuse: } /* - * Create or find a client connection to use for a call. - * - * If we return with a connection, the call will be on its waiting list. It's - * left to the caller to assign a channel and wake up the call. + * Look up the conn bundle that matches the connection parameters, adding it if + * it doesn't yet exist. */ -static int rxrpc_get_client_conn(struct rxrpc_sock *rx, - struct rxrpc_call *call, - struct rxrpc_conn_parameters *cp, - struct sockaddr_rxrpc *srx, - gfp_t gfp) +static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *cp, + gfp_t gfp) { - struct rxrpc_connection *conn, *candidate = NULL; + static atomic_t rxrpc_bundle_id; + struct rxrpc_bundle *bundle, *candidate; struct rxrpc_local *local = cp->local; struct rb_node *p, **pp, *parent; long diff; - int ret = -ENOMEM; - _enter("{%d,%lx},", call->debug_id, call->user_call_ID); + _enter("{%px,%x,%u,%u}", + cp->peer, key_serial(cp->key), cp->security_level, cp->upgrade); - cp->peer = rxrpc_lookup_peer(rx, cp->local, srx, gfp); - if (!cp->peer) - goto error; + if (cp->exclusive) + return rxrpc_alloc_bundle(cp, gfp); - call->cong_cwnd = cp->peer->cong_cwnd; - if (call->cong_cwnd >= call->cong_ssthresh) - call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; - else - call->cong_mode = RXRPC_CALL_SLOW_START; + /* First, see if the bundle is already there. */ + _debug("search 1"); + spin_lock(&local->client_bundles_lock); + p = local->client_bundles.rb_node; + while (p) { + bundle = rb_entry(p, struct rxrpc_bundle, local_node); - /* If the connection is not meant to be exclusive, search the available - * connections to see if the connection we want to use already exists. - */ - if (!cp->exclusive) { - _debug("search 1"); - spin_lock(&local->client_conns_lock); - p = local->client_conns.rb_node; - while (p) { - conn = rb_entry(p, struct rxrpc_connection, client_node); - -#define cmp(X) ((long)conn->params.X - (long)cp->X) - diff = (cmp(peer) ?: - cmp(key) ?: - cmp(security_level) ?: - cmp(upgrade)); +#define cmp(X) ((long)bundle->params.X - (long)cp->X) + diff = (cmp(peer) ?: + cmp(key) ?: + cmp(security_level) ?: + cmp(upgrade)); #undef cmp - if (diff < 0) { - p = p->rb_left; - } else if (diff > 0) { - p = p->rb_right; - } else { - if (rxrpc_may_reuse_conn(conn) && - rxrpc_get_connection_maybe(conn)) - goto found_extant_conn; - /* The connection needs replacing. It's better - * to effect that when we have something to - * replace it with so that we don't have to - * rebalance the tree twice. - */ - break; - } - } - spin_unlock(&local->client_conns_lock); - } - - /* There wasn't a connection yet or we need an exclusive connection. - * We need to create a candidate and then potentially redo the search - * in case we're racing with another thread also trying to connect on a - * shareable connection. - */ - _debug("new conn"); - candidate = rxrpc_alloc_client_connection(cp, gfp); - if (IS_ERR(candidate)) { - ret = PTR_ERR(candidate); - goto error_peer; + if (diff < 0) + p = p->rb_left; + else if (diff > 0) + p = p->rb_right; + else + goto found_bundle; } + spin_unlock(&local->client_bundles_lock); + _debug("not found"); - /* Add the call to the new connection's waiting list in case we're - * going to have to wait for the connection to come live. It's our - * connection, so we want first dibs on the channel slots. We would - * normally have to take channel_lock but we do this before anyone else - * can see the connection. - */ - list_add(&call->chan_wait_link, &candidate->waiting_calls); - - if (cp->exclusive) { - call->conn = candidate; - call->security = candidate->security; - call->security_ix = candidate->security_ix; - call->service_id = candidate->service_id; - _leave(" = 0 [exclusive %d]", candidate->debug_id); - return 0; - } + /* It wasn't. We need to add one. */ + candidate = rxrpc_alloc_bundle(cp, gfp); + if (!candidate) + return NULL; - /* Publish the new connection for userspace to find. We need to redo - * the search before doing this lest we race with someone else adding a - * conflicting instance. - */ _debug("search 2"); - spin_lock(&local->client_conns_lock); - - pp = &local->client_conns.rb_node; + spin_lock(&local->client_bundles_lock); + pp = &local->client_bundles.rb_node; parent = NULL; while (*pp) { parent = *pp; - conn = rb_entry(parent, struct rxrpc_connection, client_node); + bundle = rb_entry(parent, struct rxrpc_bundle, local_node); -#define cmp(X) ((long)conn->params.X - (long)candidate->params.X) +#define cmp(X) ((long)bundle->params.X - (long)cp->X) diff = (cmp(peer) ?: cmp(key) ?: cmp(security_level) ?: cmp(upgrade)); #undef cmp - if (diff < 0) { + if (diff < 0) pp = &(*pp)->rb_left; - } else if (diff > 0) { + else if (diff > 0) pp = &(*pp)->rb_right; - } else { - if (rxrpc_may_reuse_conn(conn) && - rxrpc_get_connection_maybe(conn)) - goto found_extant_conn; - /* The old connection is from an outdated epoch. */ - _debug("replace conn"); - clear_bit(RXRPC_CONN_IN_CLIENT_CONNS, &conn->flags); - rb_replace_node(&conn->client_node, - &candidate->client_node, - &local->client_conns); - trace_rxrpc_client(conn, -1, rxrpc_client_replace); - goto candidate_published; - } + else + goto found_bundle_free; } - _debug("new conn"); - rb_link_node(&candidate->client_node, parent, pp); - rb_insert_color(&candidate->client_node, &local->client_conns); - -candidate_published: - set_bit(RXRPC_CONN_IN_CLIENT_CONNS, &candidate->flags); - call->conn = candidate; - call->security = candidate->security; - call->security_ix = candidate->security_ix; - call->service_id = candidate->service_id; - spin_unlock(&local->client_conns_lock); - _leave(" = 0 [new %d]", candidate->debug_id); - return 0; + _debug("new bundle"); + candidate->debug_id = atomic_inc_return(&rxrpc_bundle_id); + rb_link_node(&candidate->local_node, parent, pp); + rb_insert_color(&candidate->local_node, &local->client_bundles); + rxrpc_get_bundle(candidate); + spin_unlock(&local->client_bundles_lock); + _leave(" = %u [new]", candidate->debug_id); + return candidate; + +found_bundle_free: + kfree(candidate); +found_bundle: + rxrpc_get_bundle(bundle); + spin_unlock(&local->client_bundles_lock); + _leave(" = %u [found]", bundle->debug_id); + return bundle; +} - /* We come here if we found a suitable connection already in existence. - * Discard any candidate we may have allocated, and try to get a - * channel on this one. - */ -found_extant_conn: - _debug("found conn"); - spin_unlock(&local->client_conns_lock); +/* + * Create or find a client bundle to use for a call. + * + * If we return with a connection, the call will be on its waiting list. It's + * left to the caller to assign a channel and wake up the call. + */ +static struct rxrpc_bundle *rxrpc_prep_call(struct rxrpc_sock *rx, + struct rxrpc_call *call, + struct rxrpc_conn_parameters *cp, + struct sockaddr_rxrpc *srx, + gfp_t gfp) +{ + struct rxrpc_bundle *bundle; - if (candidate) { - trace_rxrpc_client(candidate, -1, rxrpc_client_duplicate); - rxrpc_put_connection(candidate); - candidate = NULL; - } + _enter("{%d,%lx},", call->debug_id, call->user_call_ID); - spin_lock(&conn->channel_lock); - call->conn = conn; - call->security = conn->security; - call->security_ix = conn->security_ix; - call->service_id = conn->service_id; - list_add_tail(&call->chan_wait_link, &conn->waiting_calls); - spin_unlock(&conn->channel_lock); - _leave(" = 0 [extant %d]", conn->debug_id); - return 0; + cp->peer = rxrpc_lookup_peer(rx, cp->local, srx, gfp); + if (!cp->peer) + goto error; + + call->cong_cwnd = cp->peer->cong_cwnd; + if (call->cong_cwnd >= call->cong_ssthresh) + call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; + else + call->cong_mode = RXRPC_CALL_SLOW_START; + if (cp->upgrade) + __set_bit(RXRPC_CALL_UPGRADE, &call->flags); + + /* Find the client connection bundle. */ + bundle = rxrpc_look_up_bundle(cp, gfp); + if (!bundle) + goto error; + + /* Get this call queued. Someone else may activate it whilst we're + * lining up a new connection, but that's fine. + */ + spin_lock(&bundle->channel_lock); + list_add_tail(&call->chan_wait_link, &bundle->waiting_calls); + spin_unlock(&bundle->channel_lock); + + _leave(" = [B=%x]", bundle->debug_id); + return bundle; -error_peer: - rxrpc_put_peer(cp->peer); - cp->peer = NULL; error: - _leave(" = %d", ret); - return ret; + _leave(" = -ENOMEM"); + return ERR_PTR(-ENOMEM); } /* - * Activate a connection. + * Allocate a new connection and add it into a bundle. */ -static void rxrpc_activate_conn(struct rxrpc_net *rxnet, - struct rxrpc_connection *conn) +static void rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, gfp_t gfp) + __releases(bundle->channel_lock) { - if (test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags)) { - trace_rxrpc_client(conn, -1, rxrpc_client_to_upgrade); - conn->cache_state = RXRPC_CONN_CLIENT_UPGRADE; - } else { - trace_rxrpc_client(conn, -1, rxrpc_client_to_active); - conn->cache_state = RXRPC_CONN_CLIENT_ACTIVE; - } - rxnet->nr_active_client_conns++; - list_move_tail(&conn->cache_link, &rxnet->active_client_conns); -} + struct rxrpc_connection *candidate = NULL, *old = NULL; + bool conflict; + int i; -/* - * Attempt to animate a connection for a new call. - * - * If it's not exclusive, the connection is in the endpoint tree, and we're in - * the conn's list of those waiting to grab a channel. There is, however, a - * limit on the number of live connections allowed at any one time, so we may - * have to wait for capacity to become available. - * - * Note that a connection on the waiting queue might *also* have active - * channels if it has been culled to make space and then re-requested by a new - * call. - */ -static void rxrpc_animate_client_conn(struct rxrpc_net *rxnet, - struct rxrpc_connection *conn) -{ - unsigned int nr_conns; + _enter(""); - _enter("%d,%d", conn->debug_id, conn->cache_state); + conflict = bundle->alloc_conn; + if (!conflict) + bundle->alloc_conn = true; + spin_unlock(&bundle->channel_lock); + if (conflict) { + _leave(" [conf]"); + return; + } - if (conn->cache_state == RXRPC_CONN_CLIENT_ACTIVE || - conn->cache_state == RXRPC_CONN_CLIENT_UPGRADE) - goto out; + candidate = rxrpc_alloc_client_connection(bundle, gfp); - spin_lock(&rxnet->client_conn_cache_lock); + spin_lock(&bundle->channel_lock); + bundle->alloc_conn = false; - nr_conns = rxnet->nr_client_conns; - if (!test_and_set_bit(RXRPC_CONN_COUNTED, &conn->flags)) { - trace_rxrpc_client(conn, -1, rxrpc_client_count); - rxnet->nr_client_conns = nr_conns + 1; + if (IS_ERR(candidate)) { + bundle->alloc_error = PTR_ERR(candidate); + spin_unlock(&bundle->channel_lock); + _leave(" [err %ld]", PTR_ERR(candidate)); + return; } - switch (conn->cache_state) { - case RXRPC_CONN_CLIENT_ACTIVE: - case RXRPC_CONN_CLIENT_UPGRADE: - case RXRPC_CONN_CLIENT_WAITING: - break; - - case RXRPC_CONN_CLIENT_INACTIVE: - case RXRPC_CONN_CLIENT_CULLED: - case RXRPC_CONN_CLIENT_IDLE: - if (nr_conns >= rxrpc_max_client_connections) - goto wait_for_capacity; - goto activate_conn; + bundle->alloc_error = 0; + + for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) { + unsigned int shift = i * RXRPC_MAXCALLS; + int j; + + old = bundle->conns[i]; + if (!rxrpc_may_reuse_conn(old)) { + if (old) + trace_rxrpc_client(old, -1, rxrpc_client_replace); + candidate->bundle_shift = shift; + bundle->conns[i] = candidate; + for (j = 0; j < RXRPC_MAXCALLS; j++) + set_bit(shift + j, &bundle->avail_chans); + candidate = NULL; + break; + } - default: - BUG(); + old = NULL; } -out_unlock: - spin_unlock(&rxnet->client_conn_cache_lock); -out: - _leave(" [%d]", conn->cache_state); - return; + spin_unlock(&bundle->channel_lock); -activate_conn: - _debug("activate"); - rxrpc_activate_conn(rxnet, conn); - goto out_unlock; - -wait_for_capacity: - _debug("wait"); - trace_rxrpc_client(conn, -1, rxrpc_client_to_waiting); - conn->cache_state = RXRPC_CONN_CLIENT_WAITING; - list_move_tail(&conn->cache_link, &rxnet->waiting_client_conns); - goto out_unlock; + if (candidate) { + _debug("discard C=%x", candidate->debug_id); + trace_rxrpc_client(candidate, -1, rxrpc_client_duplicate); + rxrpc_put_connection(candidate); + } + + rxrpc_put_connection(old); + _leave(""); } /* - * Deactivate a channel. + * Add a connection to a bundle if there are no usable connections or we have + * connections waiting for extra capacity. */ -static void rxrpc_deactivate_one_channel(struct rxrpc_connection *conn, - unsigned int channel) +static void rxrpc_maybe_add_conn(struct rxrpc_bundle *bundle, gfp_t gfp) { - struct rxrpc_channel *chan = &conn->channels[channel]; + struct rxrpc_call *call; + int i, usable; - rcu_assign_pointer(chan->call, NULL); - conn->active_chans &= ~(1 << channel); + _enter(""); + + spin_lock(&bundle->channel_lock); + + /* See if there are any usable connections. */ + usable = 0; + for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) + if (rxrpc_may_reuse_conn(bundle->conns[i])) + usable++; + + if (!usable && !list_empty(&bundle->waiting_calls)) { + call = list_first_entry(&bundle->waiting_calls, + struct rxrpc_call, chan_wait_link); + if (test_bit(RXRPC_CALL_UPGRADE, &call->flags)) + bundle->try_upgrade = true; + } + + if (!usable) + goto alloc_conn; + + if (!bundle->avail_chans && + !bundle->try_upgrade && + !list_empty(&bundle->waiting_calls) && + usable < ARRAY_SIZE(bundle->conns)) + goto alloc_conn; + + spin_unlock(&bundle->channel_lock); + _leave(""); + return; + +alloc_conn: + return rxrpc_add_conn_to_bundle(bundle, gfp); } /* @@ -549,35 +508,42 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, unsigned int channel) { struct rxrpc_channel *chan = &conn->channels[channel]; - struct rxrpc_call *call = list_entry(conn->waiting_calls.next, + struct rxrpc_bundle *bundle = conn->bundle; + struct rxrpc_call *call = list_entry(bundle->waiting_calls.next, struct rxrpc_call, chan_wait_link); u32 call_id = chan->call_counter + 1; + _enter("C=%x,%u", conn->debug_id, channel); + trace_rxrpc_client(conn, channel, rxrpc_client_chan_activate); /* Cancel the final ACK on the previous call if it hasn't been sent yet * as the DATA packet will implicitly ACK it. */ clear_bit(RXRPC_CONN_FINAL_ACK_0 + channel, &conn->flags); - - write_lock_bh(&call->state_lock); - call->state = RXRPC_CALL_CLIENT_SEND_REQUEST; - write_unlock_bh(&call->state_lock); + clear_bit(conn->bundle_shift + channel, &bundle->avail_chans); rxrpc_see_call(call); list_del_init(&call->chan_wait_link); - conn->active_chans |= 1 << channel; call->peer = rxrpc_get_peer(conn->params.peer); + call->conn = rxrpc_get_connection(conn); call->cid = conn->proto.cid | channel; call->call_id = call_id; + call->security = conn->security; + call->security_ix = conn->security_ix; + call->service_id = conn->service_id; trace_rxrpc_connect_call(call); _net("CONNECT call %08x:%08x as call %d on conn %d", call->cid, call->call_id, call->debug_id, conn->debug_id); - /* Paired with the read barrier in rxrpc_wait_for_channel(). This - * orders cid and epoch in the connection wrt to call_id without the - * need to take the channel_lock. + write_lock_bh(&call->state_lock); + call->state = RXRPC_CALL_CLIENT_SEND_REQUEST; + write_unlock_bh(&call->state_lock); + + /* Paired with the read barrier in rxrpc_connect_call(). This orders + * cid and epoch in the connection wrt to call_id without the need to + * take the channel_lock. * * We provisionally assign a callNumber at this point, but we don't * confirm it until the call is about to be exposed. @@ -586,101 +552,137 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, * at the call ID through a connection channel. */ smp_wmb(); - chan->call_id = call_id; - chan->call_debug_id = call->debug_id; + + chan->call_id = call_id; + chan->call_debug_id = call->debug_id; rcu_assign_pointer(chan->call, call); wake_up(&call->waitq); } /* + * Remove a connection from the idle list if it's on it. + */ +static void rxrpc_unidle_conn(struct rxrpc_bundle *bundle, struct rxrpc_connection *conn) +{ + struct rxrpc_net *rxnet = bundle->params.local->rxnet; + bool drop_ref; + + if (!list_empty(&conn->cache_link)) { + drop_ref = false; + spin_lock(&rxnet->client_conn_cache_lock); + if (!list_empty(&conn->cache_link)) { + list_del_init(&conn->cache_link); + drop_ref = true; + } + spin_unlock(&rxnet->client_conn_cache_lock); + if (drop_ref) + rxrpc_put_connection(conn); + } +} + +/* * Assign channels and callNumbers to waiting calls with channel_lock * held by caller. */ -static void rxrpc_activate_channels_locked(struct rxrpc_connection *conn) +static void rxrpc_activate_channels_locked(struct rxrpc_bundle *bundle) { - u8 avail, mask; - - switch (conn->cache_state) { - case RXRPC_CONN_CLIENT_ACTIVE: - mask = RXRPC_ACTIVE_CHANS_MASK; - break; - case RXRPC_CONN_CLIENT_UPGRADE: - mask = 0x01; - break; - default: - return; - } + struct rxrpc_connection *conn; + unsigned long avail, mask; + unsigned int channel, slot; - while (!list_empty(&conn->waiting_calls) && - (avail = ~conn->active_chans, - avail &= mask, - avail != 0)) - rxrpc_activate_one_channel(conn, __ffs(avail)); + if (bundle->try_upgrade) + mask = 1; + else + mask = ULONG_MAX; + + while (!list_empty(&bundle->waiting_calls)) { + avail = bundle->avail_chans & mask; + if (!avail) + break; + channel = __ffs(avail); + clear_bit(channel, &bundle->avail_chans); + + slot = channel / RXRPC_MAXCALLS; + conn = bundle->conns[slot]; + if (!conn) + break; + + if (bundle->try_upgrade) + set_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags); + rxrpc_unidle_conn(bundle, conn); + + channel &= (RXRPC_MAXCALLS - 1); + conn->act_chans |= 1 << channel; + rxrpc_activate_one_channel(conn, channel); + } } /* * Assign channels and callNumbers to waiting calls. */ -static void rxrpc_activate_channels(struct rxrpc_connection *conn) +static void rxrpc_activate_channels(struct rxrpc_bundle *bundle) { - _enter("%d", conn->debug_id); + _enter("B=%x", bundle->debug_id); - trace_rxrpc_client(conn, -1, rxrpc_client_activate_chans); + trace_rxrpc_client(NULL, -1, rxrpc_client_activate_chans); - if (conn->active_chans == RXRPC_ACTIVE_CHANS_MASK) + if (!bundle->avail_chans) return; - spin_lock(&conn->channel_lock); - rxrpc_activate_channels_locked(conn); - spin_unlock(&conn->channel_lock); + spin_lock(&bundle->channel_lock); + rxrpc_activate_channels_locked(bundle); + spin_unlock(&bundle->channel_lock); _leave(""); } /* * Wait for a callNumber and a channel to be granted to a call. */ -static int rxrpc_wait_for_channel(struct rxrpc_call *call, gfp_t gfp) +static int rxrpc_wait_for_channel(struct rxrpc_bundle *bundle, + struct rxrpc_call *call, gfp_t gfp) { + DECLARE_WAITQUEUE(myself, current); int ret = 0; _enter("%d", call->debug_id); - if (!call->call_id) { - DECLARE_WAITQUEUE(myself, current); + if (!gfpflags_allow_blocking(gfp)) { + rxrpc_maybe_add_conn(bundle, gfp); + rxrpc_activate_channels(bundle); + ret = bundle->alloc_error ?: -EAGAIN; + goto out; + } - if (!gfpflags_allow_blocking(gfp)) { - ret = -EAGAIN; - goto out; + add_wait_queue_exclusive(&call->waitq, &myself); + for (;;) { + rxrpc_maybe_add_conn(bundle, gfp); + rxrpc_activate_channels(bundle); + ret = bundle->alloc_error; + if (ret < 0) + break; + + switch (call->interruptibility) { + case RXRPC_INTERRUPTIBLE: + case RXRPC_PREINTERRUPTIBLE: + set_current_state(TASK_INTERRUPTIBLE); + break; + case RXRPC_UNINTERRUPTIBLE: + default: + set_current_state(TASK_UNINTERRUPTIBLE); + break; } - - add_wait_queue_exclusive(&call->waitq, &myself); - for (;;) { - switch (call->interruptibility) { - case RXRPC_INTERRUPTIBLE: - case RXRPC_PREINTERRUPTIBLE: - set_current_state(TASK_INTERRUPTIBLE); - break; - case RXRPC_UNINTERRUPTIBLE: - default: - set_current_state(TASK_UNINTERRUPTIBLE); - break; - } - if (call->call_id) - break; - if ((call->interruptibility == RXRPC_INTERRUPTIBLE || - call->interruptibility == RXRPC_PREINTERRUPTIBLE) && - signal_pending(current)) { - ret = -ERESTARTSYS; - break; - } - schedule(); + if (READ_ONCE(call->state) != RXRPC_CALL_CLIENT_AWAIT_CONN) + break; + if ((call->interruptibility == RXRPC_INTERRUPTIBLE || + call->interruptibility == RXRPC_PREINTERRUPTIBLE) && + signal_pending(current)) { + ret = -ERESTARTSYS; + break; } - remove_wait_queue(&call->waitq, &myself); - __set_current_state(TASK_RUNNING); + schedule(); } - - /* Paired with the write barrier in rxrpc_activate_one_channel(). */ - smp_rmb(); + remove_wait_queue(&call->waitq, &myself); + __set_current_state(TASK_RUNNING); out: _leave(" = %d", ret); @@ -697,52 +699,50 @@ int rxrpc_connect_call(struct rxrpc_sock *rx, struct sockaddr_rxrpc *srx, gfp_t gfp) { + struct rxrpc_bundle *bundle; struct rxrpc_net *rxnet = cp->local->rxnet; - int ret; + int ret = 0; _enter("{%d,%lx},", call->debug_id, call->user_call_ID); rxrpc_discard_expired_client_conns(&rxnet->client_conn_reaper); - rxrpc_cull_active_client_conns(rxnet); - ret = rxrpc_get_client_conn(rx, call, cp, srx, gfp); - if (ret < 0) + bundle = rxrpc_prep_call(rx, call, cp, srx, gfp); + if (IS_ERR(bundle)) { + ret = PTR_ERR(bundle); goto out; + } - rxrpc_animate_client_conn(rxnet, call->conn); - rxrpc_activate_channels(call->conn); - - ret = rxrpc_wait_for_channel(call, gfp); - if (ret < 0) { - trace_rxrpc_client(call->conn, ret, rxrpc_client_chan_wait_failed); - rxrpc_disconnect_client_call(call); - goto out; + if (call->state == RXRPC_CALL_CLIENT_AWAIT_CONN) { + ret = rxrpc_wait_for_channel(bundle, call, gfp); + if (ret < 0) + goto wait_failed; } - spin_lock_bh(&call->conn->params.peer->lock); - hlist_add_head_rcu(&call->error_link, - &call->conn->params.peer->error_targets); - spin_unlock_bh(&call->conn->params.peer->lock); +granted_channel: + /* Paired with the write barrier in rxrpc_activate_one_channel(). */ + smp_rmb(); +out_put_bundle: + rxrpc_put_bundle(bundle); out: _leave(" = %d", ret); return ret; -} -/* - * Note that a connection is about to be exposed to the world. Once it is - * exposed, we maintain an extra ref on it that stops it from being summarily - * discarded before it's (a) had a chance to deal with retransmission and (b) - * had a chance at re-use (the per-connection security negotiation is - * expensive). - */ -static void rxrpc_expose_client_conn(struct rxrpc_connection *conn, - unsigned int channel) -{ - if (!test_and_set_bit(RXRPC_CONN_EXPOSED, &conn->flags)) { - trace_rxrpc_client(conn, channel, rxrpc_client_exposed); - rxrpc_get_connection(conn); +wait_failed: + spin_lock(&bundle->channel_lock); + list_del_init(&call->chan_wait_link); + spin_unlock(&bundle->channel_lock); + + if (call->state != RXRPC_CALL_CLIENT_AWAIT_CONN) { + ret = 0; + goto granted_channel; } + + trace_rxrpc_client(call->conn, ret, rxrpc_client_chan_wait_failed); + rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret); + rxrpc_disconnect_client_call(bundle, call); + goto out_put_bundle; } /* @@ -764,7 +764,7 @@ void rxrpc_expose_client_call(struct rxrpc_call *call) chan->call_counter++; if (chan->call_counter >= INT_MAX) set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); - rxrpc_expose_client_conn(conn, channel); + trace_rxrpc_client(conn, channel, rxrpc_client_exposed); } } @@ -773,62 +773,56 @@ void rxrpc_expose_client_call(struct rxrpc_call *call) */ static void rxrpc_set_client_reap_timer(struct rxrpc_net *rxnet) { - unsigned long now = jiffies; - unsigned long reap_at = now + rxrpc_conn_idle_client_expiry; + if (!rxnet->kill_all_client_conns) { + unsigned long now = jiffies; + unsigned long reap_at = now + rxrpc_conn_idle_client_expiry; - if (rxnet->live) - timer_reduce(&rxnet->client_conn_reap_timer, reap_at); + if (rxnet->live) + timer_reduce(&rxnet->client_conn_reap_timer, reap_at); + } } /* * Disconnect a client call. */ -void rxrpc_disconnect_client_call(struct rxrpc_call *call) +void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call *call) { - struct rxrpc_connection *conn = call->conn; + struct rxrpc_connection *conn; struct rxrpc_channel *chan = NULL; - struct rxrpc_net *rxnet = conn->params.local->rxnet; - unsigned int channel = -1; + struct rxrpc_net *rxnet = bundle->params.local->rxnet; + unsigned int channel; + bool may_reuse; u32 cid; - spin_lock(&conn->channel_lock); - set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); + _enter("c=%x", call->debug_id); - cid = call->cid; - if (cid) { - channel = cid & RXRPC_CHANNELMASK; - chan = &conn->channels[channel]; - } - trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect); + spin_lock(&bundle->channel_lock); + set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); /* Calls that have never actually been assigned a channel can simply be - * discarded. If the conn didn't get used either, it will follow - * immediately unless someone else grabs it in the meantime. + * discarded. */ - if (!list_empty(&call->chan_wait_link)) { + conn = call->conn; + if (!conn) { _debug("call is waiting"); ASSERTCMP(call->call_id, ==, 0); ASSERT(!test_bit(RXRPC_CALL_EXPOSED, &call->flags)); list_del_init(&call->chan_wait_link); - - trace_rxrpc_client(conn, channel, rxrpc_client_chan_unstarted); - - /* We must deactivate or idle the connection if it's now - * waiting for nothing. - */ - spin_lock(&rxnet->client_conn_cache_lock); - if (conn->cache_state == RXRPC_CONN_CLIENT_WAITING && - list_empty(&conn->waiting_calls) && - !conn->active_chans) - goto idle_connection; goto out; } + cid = call->cid; + channel = cid & RXRPC_CHANNELMASK; + chan = &conn->channels[channel]; + trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect); + if (rcu_access_pointer(chan->call) != call) { - spin_unlock(&conn->channel_lock); + spin_unlock(&bundle->channel_lock); BUG(); } + may_reuse = rxrpc_may_reuse_conn(conn); + /* If a client call was exposed to the world, we save the result for * retransmission. * @@ -841,14 +835,21 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call) if (test_bit(RXRPC_CALL_EXPOSED, &call->flags)) { _debug("exposed %u,%u", call->call_id, call->abort_code); __rxrpc_disconnect_call(conn, call); + + if (test_and_clear_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags)) { + trace_rxrpc_client(conn, channel, rxrpc_client_to_active); + bundle->try_upgrade = false; + if (may_reuse) + rxrpc_activate_channels_locked(bundle); + } + } /* See if we can pass the channel directly to another call. */ - if (conn->cache_state == RXRPC_CONN_CLIENT_ACTIVE && - !list_empty(&conn->waiting_calls)) { + if (may_reuse && !list_empty(&bundle->waiting_calls)) { trace_rxrpc_client(conn, channel, rxrpc_client_chan_pass); rxrpc_activate_one_channel(conn, channel); - goto out_2; + goto out; } /* Schedule the final ACK to be transmitted in a short while so that it @@ -865,128 +866,99 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call) rxrpc_reduce_conn_timer(conn, final_ack_at); } - /* Things are more complex and we need the cache lock. We might be - * able to simply idle the conn or it might now be lurking on the wait - * list. It might even get moved back to the active list whilst we're - * waiting for the lock. - */ - spin_lock(&rxnet->client_conn_cache_lock); - - switch (conn->cache_state) { - case RXRPC_CONN_CLIENT_UPGRADE: - /* Deal with termination of a service upgrade probe. */ - if (test_bit(RXRPC_CONN_EXPOSED, &conn->flags)) { - clear_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags); - trace_rxrpc_client(conn, channel, rxrpc_client_to_active); - conn->cache_state = RXRPC_CONN_CLIENT_ACTIVE; - rxrpc_activate_channels_locked(conn); - } - fallthrough; - case RXRPC_CONN_CLIENT_ACTIVE: - if (list_empty(&conn->waiting_calls)) { - rxrpc_deactivate_one_channel(conn, channel); - if (!conn->active_chans) { - rxnet->nr_active_client_conns--; - goto idle_connection; - } - goto out; - } - - trace_rxrpc_client(conn, channel, rxrpc_client_chan_pass); - rxrpc_activate_one_channel(conn, channel); - goto out; + /* Deactivate the channel. */ + rcu_assign_pointer(chan->call, NULL); + set_bit(conn->bundle_shift + channel, &conn->bundle->avail_chans); + conn->act_chans &= ~(1 << channel); - case RXRPC_CONN_CLIENT_CULLED: - rxrpc_deactivate_one_channel(conn, channel); - ASSERT(list_empty(&conn->waiting_calls)); - if (!conn->active_chans) - goto idle_connection; - goto out; + /* If no channels remain active, then put the connection on the idle + * list for a short while. Give it a ref to stop it going away if it + * becomes unbundled. + */ + if (!conn->act_chans) { + trace_rxrpc_client(conn, channel, rxrpc_client_to_idle); + conn->idle_timestamp = jiffies; - case RXRPC_CONN_CLIENT_WAITING: - rxrpc_deactivate_one_channel(conn, channel); - goto out; + rxrpc_get_connection(conn); + spin_lock(&rxnet->client_conn_cache_lock); + list_move_tail(&conn->cache_link, &rxnet->idle_client_conns); + spin_unlock(&rxnet->client_conn_cache_lock); - default: - BUG(); + rxrpc_set_client_reap_timer(rxnet); } out: - spin_unlock(&rxnet->client_conn_cache_lock); -out_2: - spin_unlock(&conn->channel_lock); + spin_unlock(&bundle->channel_lock); _leave(""); return; +} -idle_connection: - /* As no channels remain active, the connection gets deactivated - * immediately or moved to the idle list for a short while. - */ - if (test_bit(RXRPC_CONN_EXPOSED, &conn->flags)) { - trace_rxrpc_client(conn, channel, rxrpc_client_to_idle); - conn->idle_timestamp = jiffies; - conn->cache_state = RXRPC_CONN_CLIENT_IDLE; - list_move_tail(&conn->cache_link, &rxnet->idle_client_conns); - if (rxnet->idle_client_conns.next == &conn->cache_link && - !rxnet->kill_all_client_conns) - rxrpc_set_client_reap_timer(rxnet); - } else { - trace_rxrpc_client(conn, channel, rxrpc_client_to_inactive); - conn->cache_state = RXRPC_CONN_CLIENT_INACTIVE; - list_del_init(&conn->cache_link); +/* + * Remove a connection from a bundle. + */ +static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) +{ + struct rxrpc_bundle *bundle = conn->bundle; + struct rxrpc_local *local = bundle->params.local; + unsigned int bindex; + bool need_drop = false, need_put = false; + int i; + + _enter("C=%x", conn->debug_id); + + if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK) + rxrpc_process_delayed_final_acks(conn, true); + + spin_lock(&bundle->channel_lock); + bindex = conn->bundle_shift / RXRPC_MAXCALLS; + if (bundle->conns[bindex] == conn) { + _debug("clear slot %u", bindex); + bundle->conns[bindex] = NULL; + for (i = 0; i < RXRPC_MAXCALLS; i++) + clear_bit(conn->bundle_shift + i, &bundle->avail_chans); + need_drop = true; + } + spin_unlock(&bundle->channel_lock); + + /* If there are no more connections, remove the bundle */ + if (!bundle->avail_chans) { + _debug("maybe unbundle"); + spin_lock(&local->client_bundles_lock); + + for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) + if (bundle->conns[i]) + break; + if (i == ARRAY_SIZE(bundle->conns) && !bundle->params.exclusive) { + _debug("erase bundle"); + rb_erase(&bundle->local_node, &local->client_bundles); + need_put = true; + } + + spin_unlock(&local->client_bundles_lock); + if (need_put) + rxrpc_put_bundle(bundle); } - goto out; + + if (need_drop) + rxrpc_put_connection(conn); + _leave(""); } /* * Clean up a dead client connection. */ -static struct rxrpc_connection * -rxrpc_put_one_client_conn(struct rxrpc_connection *conn) +static void rxrpc_kill_client_conn(struct rxrpc_connection *conn) { - struct rxrpc_connection *next = NULL; struct rxrpc_local *local = conn->params.local; struct rxrpc_net *rxnet = local->rxnet; - unsigned int nr_conns; - trace_rxrpc_client(conn, -1, rxrpc_client_cleanup); + _enter("C=%x", conn->debug_id); - if (test_bit(RXRPC_CONN_IN_CLIENT_CONNS, &conn->flags)) { - spin_lock(&local->client_conns_lock); - if (test_and_clear_bit(RXRPC_CONN_IN_CLIENT_CONNS, - &conn->flags)) - rb_erase(&conn->client_node, &local->client_conns); - spin_unlock(&local->client_conns_lock); - } + trace_rxrpc_client(conn, -1, rxrpc_client_cleanup); + atomic_dec(&rxnet->nr_client_conns); rxrpc_put_client_connection_id(conn); - - ASSERTCMP(conn->cache_state, ==, RXRPC_CONN_CLIENT_INACTIVE); - - if (test_bit(RXRPC_CONN_COUNTED, &conn->flags)) { - trace_rxrpc_client(conn, -1, rxrpc_client_uncount); - spin_lock(&rxnet->client_conn_cache_lock); - nr_conns = --rxnet->nr_client_conns; - - if (nr_conns < rxrpc_max_client_connections && - !list_empty(&rxnet->waiting_client_conns)) { - next = list_entry(rxnet->waiting_client_conns.next, - struct rxrpc_connection, cache_link); - rxrpc_get_connection(next); - rxrpc_activate_conn(rxnet, next); - } - - spin_unlock(&rxnet->client_conn_cache_lock); - } - rxrpc_kill_connection(conn); - if (next) - rxrpc_activate_channels(next); - - /* We need to get rid of the temporary ref we took upon next, but we - * can't call rxrpc_put_connection() recursively. - */ - return next; } /* @@ -998,63 +970,12 @@ void rxrpc_put_client_conn(struct rxrpc_connection *conn) unsigned int debug_id = conn->debug_id; int n; - do { - n = atomic_dec_return(&conn->usage); - trace_rxrpc_conn(debug_id, rxrpc_conn_put_client, n, here); - if (n > 0) - return; + n = atomic_dec_return(&conn->usage); + trace_rxrpc_conn(debug_id, rxrpc_conn_put_client, n, here); + if (n <= 0) { ASSERTCMP(n, >=, 0); - - conn = rxrpc_put_one_client_conn(conn); - } while (conn); -} - -/* - * Kill the longest-active client connections to make room for new ones. - */ -static void rxrpc_cull_active_client_conns(struct rxrpc_net *rxnet) -{ - struct rxrpc_connection *conn; - unsigned int nr_conns = rxnet->nr_client_conns; - unsigned int nr_active, limit; - - _enter(""); - - ASSERTCMP(nr_conns, >=, 0); - if (nr_conns < rxrpc_max_client_connections) { - _leave(" [ok]"); - return; - } - limit = rxrpc_reap_client_connections; - - spin_lock(&rxnet->client_conn_cache_lock); - nr_active = rxnet->nr_active_client_conns; - - while (nr_active > limit) { - ASSERT(!list_empty(&rxnet->active_client_conns)); - conn = list_entry(rxnet->active_client_conns.next, - struct rxrpc_connection, cache_link); - ASSERTIFCMP(conn->cache_state != RXRPC_CONN_CLIENT_ACTIVE, - conn->cache_state, ==, RXRPC_CONN_CLIENT_UPGRADE); - - if (list_empty(&conn->waiting_calls)) { - trace_rxrpc_client(conn, -1, rxrpc_client_to_culled); - conn->cache_state = RXRPC_CONN_CLIENT_CULLED; - list_del_init(&conn->cache_link); - } else { - trace_rxrpc_client(conn, -1, rxrpc_client_to_waiting); - conn->cache_state = RXRPC_CONN_CLIENT_WAITING; - list_move_tail(&conn->cache_link, - &rxnet->waiting_client_conns); - } - - nr_active--; + rxrpc_kill_client_conn(conn); } - - rxnet->nr_active_client_conns = nr_active; - spin_unlock(&rxnet->client_conn_cache_lock); - ASSERTCMP(nr_active, >=, 0); - _leave(" [culled]"); } /* @@ -1088,7 +1009,7 @@ void rxrpc_discard_expired_client_conns(struct work_struct *work) /* We keep an estimate of what the number of conns ought to be after * we've discarded some so that we don't overdo the discarding. */ - nr_conns = rxnet->nr_client_conns; + nr_conns = atomic_read(&rxnet->nr_client_conns); next: spin_lock(&rxnet->client_conn_cache_lock); @@ -1098,7 +1019,6 @@ next: conn = list_entry(rxnet->idle_client_conns.next, struct rxrpc_connection, cache_link); - ASSERT(test_bit(RXRPC_CONN_EXPOSED, &conn->flags)); if (!rxnet->kill_all_client_conns) { /* If the number of connections is over the reap limit, we @@ -1120,18 +1040,13 @@ next: } trace_rxrpc_client(conn, -1, rxrpc_client_discard); - if (!test_and_clear_bit(RXRPC_CONN_EXPOSED, &conn->flags)) - BUG(); - conn->cache_state = RXRPC_CONN_CLIENT_INACTIVE; list_del_init(&conn->cache_link); spin_unlock(&rxnet->client_conn_cache_lock); - /* When we cleared the EXPOSED flag, we took on responsibility for the - * reference that that had on the usage count. We deal with that here. - * If someone re-sets the flag and re-gets the ref, that's fine. - */ - rxrpc_put_connection(conn); + rxrpc_unbundle_conn(conn); + rxrpc_put_connection(conn); /* Drop the ->cache_link ref */ + nr_conns--; goto next; @@ -1145,8 +1060,7 @@ not_yet_expired: */ _debug("not yet"); if (!rxnet->kill_all_client_conns) - timer_reduce(&rxnet->client_conn_reap_timer, - conn_expires_at); + timer_reduce(&rxnet->client_conn_reap_timer, conn_expires_at); out: spin_unlock(&rxnet->client_conn_cache_lock); @@ -1181,37 +1095,27 @@ void rxrpc_clean_up_local_conns(struct rxrpc_local *local) { struct rxrpc_connection *conn, *tmp; struct rxrpc_net *rxnet = local->rxnet; - unsigned int nr_active; LIST_HEAD(graveyard); _enter(""); spin_lock(&rxnet->client_conn_cache_lock); - nr_active = rxnet->nr_active_client_conns; list_for_each_entry_safe(conn, tmp, &rxnet->idle_client_conns, cache_link) { if (conn->params.local == local) { - ASSERTCMP(conn->cache_state, ==, RXRPC_CONN_CLIENT_IDLE); - trace_rxrpc_client(conn, -1, rxrpc_client_discard); - if (!test_and_clear_bit(RXRPC_CONN_EXPOSED, &conn->flags)) - BUG(); - conn->cache_state = RXRPC_CONN_CLIENT_INACTIVE; list_move(&conn->cache_link, &graveyard); - nr_active--; } } - rxnet->nr_active_client_conns = nr_active; spin_unlock(&rxnet->client_conn_cache_lock); - ASSERTCMP(nr_active, >=, 0); while (!list_empty(&graveyard)) { conn = list_entry(graveyard.next, struct rxrpc_connection, cache_link); list_del_init(&conn->cache_link); - + rxrpc_unbundle_conn(conn); rxrpc_put_connection(conn); } diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 64ace2960ecc..aff184145ffa 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -157,12 +157,12 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn, _enter("{%d},%x", conn->debug_id, conn->abort_code); - spin_lock(&conn->channel_lock); + spin_lock(&conn->bundle->channel_lock); for (i = 0; i < RXRPC_MAXCALLS; i++) { call = rcu_dereference_protected( conn->channels[i].call, - lockdep_is_held(&conn->channel_lock)); + lockdep_is_held(&conn->bundle->channel_lock)); if (call) { if (compl == RXRPC_CALL_LOCALLY_ABORTED) trace_rxrpc_abort(call->debug_id, @@ -179,7 +179,7 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn, } } - spin_unlock(&conn->channel_lock); + spin_unlock(&conn->bundle->channel_lock); _leave(""); } @@ -210,6 +210,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, conn->error = error; conn->abort_code = abort_code; conn->state = RXRPC_CONN_LOCALLY_ABORTED; + set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); spin_unlock_bh(&conn->state_lock); msg.msg_name = &conn->params.peer->srx.transport; @@ -319,6 +320,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, conn->error = -ECONNABORTED; conn->abort_code = abort_code; conn->state = RXRPC_CONN_REMOTELY_ABORTED; + set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial); return -ECONNABORTED; @@ -339,7 +341,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, if (ret < 0) return ret; - spin_lock(&conn->channel_lock); + spin_lock(&conn->bundle->channel_lock); spin_lock_bh(&conn->state_lock); if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) { @@ -349,12 +351,12 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, rxrpc_call_is_secure( rcu_dereference_protected( conn->channels[loop].call, - lockdep_is_held(&conn->channel_lock))); + lockdep_is_held(&conn->bundle->channel_lock))); } else { spin_unlock_bh(&conn->state_lock); } - spin_unlock(&conn->channel_lock); + spin_unlock(&conn->bundle->channel_lock); return 0; default: @@ -395,7 +397,7 @@ abort: /* * Process delayed final ACKs that we haven't subsumed into a subsequent call. */ -static void rxrpc_process_delayed_final_acks(struct rxrpc_connection *conn) +void rxrpc_process_delayed_final_acks(struct rxrpc_connection *conn, bool force) { unsigned long j = jiffies, next_j; unsigned int channel; @@ -414,7 +416,7 @@ again: smp_rmb(); /* vs rxrpc_disconnect_client_call */ ack_at = READ_ONCE(chan->final_ack_at); - if (time_before(j, ack_at)) { + if (time_before(j, ack_at) && !force) { if (time_before(ack_at, next_j)) { next_j = ack_at; set = true; @@ -448,7 +450,7 @@ static void rxrpc_do_process_connection(struct rxrpc_connection *conn) /* Process delayed ACKs whose time has come. */ if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK) - rxrpc_process_delayed_final_acks(conn); + rxrpc_process_delayed_final_acks(conn, false); /* go through the conn-level event packets, releasing the ref on this * connection that each one has when we've finished with it */ diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 8cbe0bf20ed5..3bcbe0665f91 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -41,8 +41,6 @@ struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp) conn = kzalloc(sizeof(struct rxrpc_connection), gfp); if (conn) { INIT_LIST_HEAD(&conn->cache_link); - spin_lock_init(&conn->channel_lock); - INIT_LIST_HEAD(&conn->waiting_calls); timer_setup(&conn->timer, &rxrpc_connection_timer, 0); INIT_WORK(&conn->processor, &rxrpc_process_connection); INIT_LIST_HEAD(&conn->proc_link); @@ -219,11 +217,11 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) } if (rxrpc_is_client_call(call)) - return rxrpc_disconnect_client_call(call); + return rxrpc_disconnect_client_call(conn->bundle, call); - spin_lock(&conn->channel_lock); + spin_lock(&conn->bundle->channel_lock); __rxrpc_disconnect_call(conn, call); - spin_unlock(&conn->channel_lock); + spin_unlock(&conn->bundle->channel_lock); set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); conn->idle_timestamp = jiffies; @@ -292,12 +290,13 @@ void rxrpc_see_connection(struct rxrpc_connection *conn) /* * Get a ref on a connection. */ -void rxrpc_get_connection(struct rxrpc_connection *conn) +struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *conn) { const void *here = __builtin_return_address(0); int n = atomic_inc_return(&conn->usage); trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, n, here); + return conn; } /* @@ -365,6 +364,7 @@ static void rxrpc_destroy_connection(struct rcu_head *rcu) conn->security->clear(conn); key_put(conn->params.key); key_put(conn->server_key); + rxrpc_put_bundle(conn->bundle); rxrpc_put_peer(conn->params.peer); if (atomic_dec_and_test(&conn->params.local->rxnet->nr_conns)) diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index 21da48e3d2e5..6c847720494f 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -8,6 +8,12 @@ #include <linux/slab.h> #include "ar-internal.h" +static struct rxrpc_bundle rxrpc_service_dummy_bundle = { + .usage = ATOMIC_INIT(1), + .debug_id = UINT_MAX, + .channel_lock = __SPIN_LOCK_UNLOCKED(&rxrpc_service_dummy_bundle.channel_lock), +}; + /* * Find a service connection under RCU conditions. * @@ -127,6 +133,7 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn */ conn->state = RXRPC_CONN_SERVICE_PREALLOC; atomic_set(&conn->usage, 2); + conn->bundle = rxrpc_get_bundle(&rxrpc_service_dummy_bundle); atomic_inc(&rxnet->nr_conns); write_lock(&rxnet->conn_lock); diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index ede058f9cc15..8c2881054266 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -86,8 +86,8 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, init_rwsem(&local->defrag_sem); skb_queue_head_init(&local->reject_queue); skb_queue_head_init(&local->event_queue); - local->client_conns = RB_ROOT; - spin_lock_init(&local->client_conns_lock); + local->client_bundles = RB_ROOT; + spin_lock_init(&local->client_bundles_lock); spin_lock_init(&local->lock); rwlock_init(&local->services_lock); local->debug_id = atomic_inc_return(&rxrpc_debug_id); diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c index b312aab80fed..25bbc4cc8b13 100644 --- a/net/rxrpc/net_ns.c +++ b/net/rxrpc/net_ns.c @@ -62,13 +62,10 @@ static __net_init int rxrpc_init_net(struct net *net) timer_setup(&rxnet->service_conn_reap_timer, rxrpc_service_conn_reap_timeout, 0); - rxnet->nr_client_conns = 0; - rxnet->nr_active_client_conns = 0; + atomic_set(&rxnet->nr_client_conns, 0); rxnet->kill_all_client_conns = false; spin_lock_init(&rxnet->client_conn_cache_lock); spin_lock_init(&rxnet->client_conn_discard_lock); - INIT_LIST_HEAD(&rxnet->waiting_client_conns); - INIT_LIST_HEAD(&rxnet->active_client_conns); INIT_LIST_HEAD(&rxnet->idle_client_conns); INIT_WORK(&rxnet->client_conn_reaper, rxrpc_discard_expired_client_conns); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 3cfff7922ba8..10f2bf2e9068 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -357,6 +357,12 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, _enter(",{%d}", skb->len); + if (hlist_unhashed(&call->error_link)) { + spin_lock_bh(&call->peer->lock); + hlist_add_head_rcu(&call->error_link, &call->peer->error_targets); + spin_unlock_bh(&call->peer->lock); + } + /* Each transmission of a Tx packet needs a new serial number */ serial = atomic_inc_return(&conn->serial); diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 543afd9bd664..e2f990754f88 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -165,7 +165,7 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v) "Proto Local " " Remote " " SvID ConnID End Use State Key " - " Serial ISerial\n" + " Serial ISerial CallId0 CallId1 CallId2 CallId3\n" ); return 0; } diff --git a/net/rxrpc/rtt.c b/net/rxrpc/rtt.c index 1221b0637a7e..4e565eeab426 100644 --- a/net/rxrpc/rtt.c +++ b/net/rxrpc/rtt.c @@ -14,7 +14,6 @@ #define RXRPC_RTO_MAX ((unsigned)(120 * HZ)) #define RXRPC_TIMEOUT_INIT ((unsigned)(1*HZ)) /* RFC6298 2.1 initial RTO value */ #define rxrpc_jiffies32 ((u32)jiffies) /* As rxrpc_jiffies32 */ -#define rxrpc_min_rtt_wlen 300 /* As sysctl_tcp_min_rtt_wlen */ static u32 rxrpc_rto_min_us(struct rxrpc_peer *peer) { diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index e08130e5746b..f114dc2af5cf 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -1169,7 +1169,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, if (response->encrypted.checksum != csum) goto protocol_error_free; - spin_lock(&conn->channel_lock); + spin_lock(&conn->bundle->channel_lock); for (i = 0; i < RXRPC_MAXCALLS; i++) { struct rxrpc_call *call; u32 call_id = ntohl(response->encrypted.call_id[i]); @@ -1186,13 +1186,13 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, if (call_id > conn->channels[i].call_counter) { call = rcu_dereference_protected( conn->channels[i].call, - lockdep_is_held(&conn->channel_lock)); + lockdep_is_held(&conn->bundle->channel_lock)); if (call && call->state < RXRPC_CALL_COMPLETE) goto protocol_error_unlock; conn->channels[i].call_counter = call_id; } } - spin_unlock(&conn->channel_lock); + spin_unlock(&conn->bundle->channel_lock); eproto = tracepoint_string("rxkad_rsp_seq"); abort_code = RXKADOUTOFSEQUENCE; @@ -1219,7 +1219,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, return 0; protocol_error_unlock: - spin_unlock(&conn->channel_lock); + spin_unlock(&conn->bundle->channel_lock); protocol_error_free: kfree(ticket); protocol_error: diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c index e91acc95ff28..540351d6a5f4 100644 --- a/net/rxrpc/sysctl.c +++ b/net/rxrpc/sysctl.c @@ -74,21 +74,13 @@ static struct ctl_table rxrpc_sysctl_table[] = { /* Non-time values */ { - .procname = "max_client_conns", - .data = &rxrpc_max_client_connections, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = (void *)&rxrpc_reap_client_connections, - }, - { .procname = "reap_client_conns", .data = &rxrpc_reap_client_connections, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = (void *)SYSCTL_ONE, - .extra2 = (void *)&rxrpc_max_client_connections, + .extra2 = (void *)&n_65535, }, { .procname = "max_backlog", diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 798430e1a79f..f66417d5d2c3 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -982,7 +982,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, #endif NL_SET_ERR_MSG(extack, "Failed to load TC action module"); err = -ENOENT; - goto err_out; + goto err_free; } /* backward compatibility for policer */ @@ -1012,11 +1012,12 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, err_mod: module_put(a_o->owner); -err_out: +err_free: if (cookie) { kfree(cookie->data); kfree(cookie); } +err_out: return ERR_PTR(err); } diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index a780afdf570d..aba3cd85f284 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -156,11 +156,11 @@ tcf_ct_flow_table_add_action_nat_udp(const struct nf_conntrack_tuple *tuple, __be16 target_dst = target.dst.u.udp.port; if (target_src != tuple->src.u.udp.port) - tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP, + tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_UDP, offsetof(struct udphdr, source), 0xFFFF, be16_to_cpu(target_src)); if (target_dst != tuple->dst.u.udp.port) - tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP, + tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_UDP, offsetof(struct udphdr, dest), 0xFFFF, be16_to_cpu(target_dst)); } @@ -1039,7 +1039,7 @@ drop: static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = { [TCA_CT_ACTION] = { .type = NLA_U16 }, - [TCA_CT_PARMS] = { .type = NLA_EXACT_LEN, .len = sizeof(struct tc_ct) }, + [TCA_CT_PARMS] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_ct)), [TCA_CT_ZONE] = { .type = NLA_U16 }, [TCA_CT_MARK] = { .type = NLA_U32 }, [TCA_CT_MARK_MASK] = { .type = NLA_U32 }, @@ -1049,10 +1049,8 @@ static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = { .len = 128 / BITS_PER_BYTE }, [TCA_CT_NAT_IPV4_MIN] = { .type = NLA_U32 }, [TCA_CT_NAT_IPV4_MAX] = { .type = NLA_U32 }, - [TCA_CT_NAT_IPV6_MIN] = { .type = NLA_EXACT_LEN, - .len = sizeof(struct in6_addr) }, - [TCA_CT_NAT_IPV6_MAX] = { .type = NLA_EXACT_LEN, - .len = sizeof(struct in6_addr) }, + [TCA_CT_NAT_IPV6_MIN] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), + [TCA_CT_NAT_IPV6_MAX] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [TCA_CT_NAT_PORT_MIN] = { .type = NLA_U16 }, [TCA_CT_NAT_PORT_MAX] = { .type = NLA_U16 }, }; diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index 6084300e51ad..b20c8ce59905 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -144,9 +144,8 @@ out: } static const struct nla_policy ctinfo_policy[TCA_CTINFO_MAX + 1] = { - [TCA_CTINFO_ACT] = { .type = NLA_EXACT_LEN, - .len = sizeof(struct - tc_ctinfo) }, + [TCA_CTINFO_ACT] = + NLA_POLICY_EXACT_LEN(sizeof(struct tc_ctinfo)), [TCA_CTINFO_ZONE] = { .type = NLA_U16 }, [TCA_CTINFO_PARMS_DSCP_MASK] = { .type = NLA_U32 }, [TCA_CTINFO_PARMS_DSCP_STATEMASK] = { .type = NLA_U32 }, diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c index 7c0771dd77a3..a78cb7965718 100644 --- a/net/sched/act_gate.c +++ b/net/sched/act_gate.c @@ -159,8 +159,8 @@ static const struct nla_policy entry_policy[TCA_GATE_ENTRY_MAX + 1] = { }; static const struct nla_policy gate_policy[TCA_GATE_MAX + 1] = { - [TCA_GATE_PARMS] = { .len = sizeof(struct tc_gate), - .type = NLA_EXACT_LEN }, + [TCA_GATE_PARMS] = + NLA_POLICY_EXACT_LEN(sizeof(struct tc_gate)), [TCA_GATE_PRIORITY] = { .type = NLA_S32 }, [TCA_GATE_ENTRY_LIST] = { .type = NLA_NESTED }, [TCA_GATE_BASE_TIME] = { .type = NLA_U64 }, diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index e298ec3b3c9e..5c7456e5b5cf 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -87,6 +87,23 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, skb->dev && skb->dev->type == ARPHRD_ETHER)) goto drop; break; + case TCA_MPLS_ACT_MAC_PUSH: + if (skb_vlan_tag_present(skb)) { + if (__vlan_insert_inner_tag(skb, skb->vlan_proto, + skb_vlan_tag_get(skb), + ETH_HLEN) < 0) + goto drop; + + skb->protocol = skb->vlan_proto; + __vlan_hwaccel_clear_tag(skb); + } + + new_lse = tcf_mpls_get_lse(NULL, p, mac_len || + !eth_p_mpls(skb->protocol)); + + if (skb_mpls_push(skb, new_lse, p->tcfm_proto, 0, false)) + goto drop; + break; case TCA_MPLS_ACT_MODIFY: new_lse = tcf_mpls_get_lse(mpls_hdr(skb), p, false); if (skb_mpls_update_lse(skb, new_lse)) @@ -188,6 +205,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, } break; case TCA_MPLS_ACT_PUSH: + case TCA_MPLS_ACT_MAC_PUSH: if (!tb[TCA_MPLS_LABEL]) { NL_SET_ERR_MSG_MOD(extack, "Label is required for MPLS push"); return -EINVAL; @@ -408,6 +426,7 @@ static void __exit mpls_cleanup_module(void) module_init(mpls_init_module); module_exit(mpls_cleanup_module); +MODULE_SOFTDEP("post: mpls_gso"); MODULE_AUTHOR("Netronome Systems <oss-drivers@netronome.com>"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("MPLS manipulation actions"); diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index a229751ee8c4..85c0d0d5b9da 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -459,7 +459,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, metadata = __ipv6_tun_set_dst(&saddr, &daddr, tos, ttl, dst_port, 0, flags, - key_id, 0); + key_id, opts_len); } else { NL_SET_ERR_MSG(extack, "Missing either ipv4 or ipv6 src and dst"); ret = -EINVAL; diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 163b0385fd4c..1cac3c6fbb49 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -77,6 +77,16 @@ static int tcf_vlan_act(struct sk_buff *skb, const struct tc_action *a, /* put updated tci as hwaccel tag */ __vlan_hwaccel_put_tag(skb, p->tcfv_push_proto, tci); break; + case TCA_VLAN_ACT_POP_ETH: + err = skb_eth_pop(skb); + if (err) + goto drop; + break; + case TCA_VLAN_ACT_PUSH_ETH: + err = skb_eth_push(skb, p->tcfv_push_dst, p->tcfv_push_src); + if (err) + goto drop; + break; default: BUG(); } @@ -93,10 +103,13 @@ drop: } static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = { + [TCA_VLAN_UNSPEC] = { .strict_start_type = TCA_VLAN_PUSH_ETH_DST }, [TCA_VLAN_PARMS] = { .len = sizeof(struct tc_vlan) }, [TCA_VLAN_PUSH_VLAN_ID] = { .type = NLA_U16 }, [TCA_VLAN_PUSH_VLAN_PROTOCOL] = { .type = NLA_U16 }, [TCA_VLAN_PUSH_VLAN_PRIORITY] = { .type = NLA_U8 }, + [TCA_VLAN_PUSH_ETH_DST] = NLA_POLICY_ETH_ADDR, + [TCA_VLAN_PUSH_ETH_SRC] = NLA_POLICY_ETH_ADDR, }; static int tcf_vlan_init(struct net *net, struct nlattr *nla, @@ -179,6 +192,17 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (tb[TCA_VLAN_PUSH_VLAN_PRIORITY]) push_prio = nla_get_u8(tb[TCA_VLAN_PUSH_VLAN_PRIORITY]); break; + case TCA_VLAN_ACT_POP_ETH: + break; + case TCA_VLAN_ACT_PUSH_ETH: + if (!tb[TCA_VLAN_PUSH_ETH_DST] || !tb[TCA_VLAN_PUSH_ETH_SRC]) { + if (exists) + tcf_idr_release(*a, bind); + else + tcf_idr_cleanup(tn, index); + return -EINVAL; + } + break; default: if (exists) tcf_idr_release(*a, bind); @@ -219,6 +243,13 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, p->tcfv_push_prio = push_prio; p->tcfv_push_proto = push_proto; + if (action == TCA_VLAN_ACT_PUSH_ETH) { + nla_memcpy(&p->tcfv_push_dst, tb[TCA_VLAN_PUSH_ETH_DST], + ETH_ALEN); + nla_memcpy(&p->tcfv_push_src, tb[TCA_VLAN_PUSH_ETH_SRC], + ETH_ALEN); + } + spin_lock_bh(&v->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); p = rcu_replace_pointer(v->vlan_p, p, lockdep_is_held(&v->tcf_lock)); @@ -277,6 +308,15 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a, p->tcfv_push_prio)))) goto nla_put_failure; + if (p->tcfv_action == TCA_VLAN_ACT_PUSH_ETH) { + if (nla_put(skb, TCA_VLAN_PUSH_ETH_DST, ETH_ALEN, + p->tcfv_push_dst)) + goto nla_put_failure; + if (nla_put(skb, TCA_VLAN_PUSH_ETH_SRC, ETH_ALEN, + p->tcfv_push_src)) + goto nla_put_failure; + } + tcf_tm_dump(&t, &v->tcf_tm); if (nla_put_64bit(skb, TCA_VLAN_TM, sizeof(t), &t, TCA_VLAN_PAD)) goto nla_put_failure; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 41a55c6cbeb8..838b3fd94d77 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -652,12 +652,12 @@ static void tc_block_indr_cleanup(struct flow_block_cb *block_cb) block_cb->indr.binder_type, &block->flow_block, tcf_block_shared(block), &extack); + rtnl_lock(); down_write(&block->cb_lock); list_del(&block_cb->driver_list); list_move(&block_cb->list, &bo.cb_list); - up_write(&block->cb_lock); - rtnl_lock(); tcf_block_unbind(block, &bo); + up_write(&block->cb_lock); rtnl_unlock(); } @@ -3712,7 +3712,7 @@ int tc_setup_flow_action(struct flow_action *flow_action, entry->gate.num_entries = tcf_gate_num_entries(act); err = tcf_gate_get_entries(entry, act); if (err) - goto err_out; + goto err_out_locked; } else { err = -EOPNOTSUPP; goto err_out_locked; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 7b69ab1993ba..54209a18d7fe 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -79,7 +79,7 @@ struct tc_u_hnode { /* The 'ht' field MUST be the last field in structure to allow for * more entries allocated at end of structure. */ - struct tc_u_knode __rcu *ht[1]; + struct tc_u_knode __rcu *ht[]; }; struct tc_u_common { @@ -353,7 +353,7 @@ static int u32_init(struct tcf_proto *tp) void *key = tc_u_common_ptr(tp); struct tc_u_common *tp_c = tc_u_common_find(key); - root_ht = kzalloc(sizeof(*root_ht), GFP_KERNEL); + root_ht = kzalloc(struct_size(root_ht, ht, 1), GFP_KERNEL); if (root_ht == NULL) return -ENOBUFS; @@ -364,7 +364,7 @@ static int u32_init(struct tcf_proto *tp) idr_init(&root_ht->handle_idr); if (tp_c == NULL) { - tp_c = kzalloc(sizeof(*tp_c), GFP_KERNEL); + tp_c = kzalloc(struct_size(tp_c, hlist->ht, 1), GFP_KERNEL); if (tp_c == NULL) { kfree(root_ht); return -ENOBUFS; @@ -933,7 +933,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, NL_SET_ERR_MSG_MOD(extack, "Divisor can only be used on a hash table"); return -EINVAL; } - ht = kzalloc(sizeof(*ht) + divisor*sizeof(void *), GFP_KERNEL); + ht = kzalloc(struct_size(ht, ht, divisor + 1), GFP_KERNEL); if (ht == NULL) return -ENOBUFS; if (handle == 0) { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 54c417244642..49eae93d1489 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -802,9 +802,8 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, struct netlink_ext_ack *extack) { - void *p; struct Qdisc *sch; - unsigned int size = QDISC_ALIGN(sizeof(*sch)) + ops->priv_size; + unsigned int size = sizeof(*sch) + ops->priv_size; int err = -ENOBUFS; struct net_device *dev; @@ -815,22 +814,10 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, } dev = dev_queue->dev; - p = kzalloc_node(size, GFP_KERNEL, - netdev_queue_numa_node_read(dev_queue)); + sch = kzalloc_node(size, GFP_KERNEL, netdev_queue_numa_node_read(dev_queue)); - if (!p) + if (!sch) goto errout; - sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p); - /* if we got non aligned memory, ask more and do alignment ourself */ - if (sch != p) { - kfree(p); - p = kzalloc_node(size + QDISC_ALIGNTO - 1, GFP_KERNEL, - netdev_queue_numa_node_read(dev_queue)); - if (!p) - goto errout; - sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p); - sch->padded = (char *) sch - (char *) p; - } __skb_queue_head_init(&sch->gso_skb); __skb_queue_head_init(&sch->skb_bad_txq); qdisc_skb_head_init(&sch->q); @@ -873,7 +860,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, return sch; errout1: - kfree(p); + kfree(sch); errout: return ERR_PTR(err); } @@ -941,7 +928,7 @@ void qdisc_free(struct Qdisc *qdisc) free_percpu(qdisc->cpu_qstats); } - kfree((char *) qdisc - qdisc->padded); + kfree(qdisc); } static void qdisc_free_cb(struct rcu_head *head) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 84f82771cdf5..0c345e43a09a 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -330,7 +330,7 @@ static s64 tabledist(s64 mu, s32 sigma, /* default uniform distribution */ if (dist == NULL) - return ((rnd % (2 * sigma)) + mu) - sigma; + return ((rnd % (2 * (u32)sigma)) + mu) - sigma; t = dist->table[rnd % dist->size]; x = (sigma % NETEM_DIST_SCALE) * t; @@ -812,6 +812,10 @@ static void get_slot(struct netem_sched_data *q, const struct nlattr *attr) q->slot_config.max_packets = INT_MAX; if (q->slot_config.max_bytes == 0) q->slot_config.max_bytes = INT_MAX; + + /* capping dist_jitter to the range acceptable by tabledist() */ + q->slot_config.dist_jitter = min_t(__s64, INT_MAX, abs(q->slot_config.dist_jitter)); + q->slot.packets_left = q->slot_config.max_packets; q->slot.bytes_left = q->slot_config.max_bytes; if (q->slot_config.min_delay | q->slot_config.max_delay | @@ -1037,6 +1041,9 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, if (tb[TCA_NETEM_SLOT]) get_slot(q, tb[TCA_NETEM_SLOT]); + /* capping jitter to the range acceptable by tabledist() */ + q->jitter = min_t(s64, abs(q->jitter), INT_MAX); + return ret; get_table_failure: diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 8d735461fa19..fdb69d46276d 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1351,7 +1351,7 @@ static void sctp_select_active_and_retran_path(struct sctp_association *asoc) } /* We did not find anything useful for a possible retransmission - * path; either primary path that we found is the the same as + * path; either primary path that we found is the same as * the current one, or we didn't generally find an active one. */ if (trans_sec == NULL) @@ -1537,7 +1537,7 @@ void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len) /* If we've reached or overflowed our receive buffer, announce * a 0 rwnd if rwnd would still be positive. Store the - * the potential pressure overflow so that the window can be restored + * potential pressure overflow so that the window can be restored * back to original value. */ if (rx_count >= asoc->base.sk->sk_rcvbuf) diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 7e59d8a18f3e..6f8319b828b0 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -445,7 +445,7 @@ struct sctp_shared_key *sctp_auth_get_shkey( } /* - * Initialize all the possible digest transforms that we can use. Right now + * Initialize all the possible digest transforms that we can use. Right * now, the supported digests are SHA1 and SHA256. We do this here once * because of the restrictiong that transforms may only be allocated in * user context. This forces us to pre-allocated all possible transforms @@ -811,7 +811,7 @@ int sctp_auth_ep_set_hmacs(struct sctp_endpoint *ep, } /* Set a new shared key on either endpoint or association. If the - * the key with a same ID already exists, replace the key (remove the + * key with a same ID already exists, replace the key (remove the * old key and add a new one). */ int sctp_auth_set_key(struct sctp_endpoint *ep, diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index 701c5a4e441d..53e5ed79f63f 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -505,7 +505,7 @@ int sctp_in_scope(struct net *net, const union sctp_addr *addr, return 0; /* * For INIT and INIT-ACK address list, let L be the level of - * of requested destination address, sender and receiver + * requested destination address, sender and receiver * SHOULD include all of its addresses with level greater * than or equal to L. * diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index ab6a997e222f..fd4f8243cc35 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -179,7 +179,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, __func__, asoc, max_data); } - /* If the the peer requested that we authenticate DATA chunks + /* If the peer requested that we authenticate DATA chunks * we need to account for bundling of the AUTH chunks along with * DATA. */ diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index d19db22262fd..25833238fe93 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -372,7 +372,7 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp) * Level 3 - private addresses. * Level 4 - global addresses * For INIT and INIT-ACK address list, let L be the level of - * of requested destination address, sender and receiver + * requested destination address, sender and receiver * SHOULD include all of its addresses with level greater * than or equal to L. * @@ -1483,10 +1483,10 @@ static __init int sctp_init(void) num_entries = (1UL << order) * PAGE_SIZE / sizeof(struct sctp_bind_hashbucket); - /* And finish by rounding it down to the nearest power of two - * this wastes some memory of course, but its needed because + /* And finish by rounding it down to the nearest power of two. + * This wastes some memory of course, but it's needed because * the hash function operates based on the assumption that - * that the number of entries is a power of two + * the number of entries is a power of two. */ sctp_port_hashsize = rounddown_pow_of_two(num_entries); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index c11c24524652..9a56ae2f3651 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1235,7 +1235,7 @@ nodata: /* Create an Operation Error chunk of a fixed size, specifically, * min(asoc->pathmtu, SCTP_DEFAULT_MAXSEGMENT) - overheads. - * This is a helper function to allocate an error chunk for for those + * This is a helper function to allocate an error chunk for those * invalid parameter codes in which we may not want to report all the * errors, if the incoming chunk is large. If it can't fit in a single * packet, we ignore it. @@ -1780,7 +1780,7 @@ no_hmac: * for init collision case of lost COOKIE ACK. * If skb has been timestamped, then use the stamp, otherwise * use current time. This introduces a small possibility that - * that a cookie may be considered expired, but his would only slow + * a cookie may be considered expired, but this would only slow * down the new association establishment instead of every packet. */ if (sock_flag(ep->base.sk, SOCK_TIMESTAMP)) @@ -2319,7 +2319,7 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, /* This implementation defaults to making the first transport * added as the primary transport. The source address seems to - * be a a better choice than any of the embedded addresses. + * be a better choice than any of the embedded addresses. */ if (!sctp_assoc_add_peer(asoc, peer_addr, gfp, SCTP_ACTIVE)) goto nomem; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index aa821e71f05e..813d30767204 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1601,12 +1601,12 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, break; case SCTP_CMD_INIT_FAILED: - sctp_cmd_init_failed(commands, asoc, cmd->obj.u32); + sctp_cmd_init_failed(commands, asoc, cmd->obj.u16); break; case SCTP_CMD_ASSOC_FAILED: sctp_cmd_assoc_failed(commands, asoc, event_type, - subtype, chunk, cmd->obj.u32); + subtype, chunk, cmd->obj.u16); break; case SCTP_CMD_INIT_COUNTER_INC: diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 1c6c640607c5..407fed46931b 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -740,7 +740,7 @@ static void sctp_ulpq_reasm_drain(struct sctp_ulpq *ulpq) /* Helper function to gather skbs that have possibly become - * ordered by an an incoming chunk. + * ordered by an incoming chunk. */ static void sctp_ulpq_retrieve_ordered(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index e7649bbc2b87..e9f487c8c6d5 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -26,6 +26,7 @@ #include <linux/sched/signal.h> #include <linux/if_vlan.h> #include <linux/rcupdate_wait.h> +#include <linux/ctype.h> #include <net/sock.h> #include <net/tcp.h> @@ -55,6 +56,9 @@ static DEFINE_MUTEX(smc_client_lgr_pending); /* serialize link group * creation on client */ +struct workqueue_struct *smc_hs_wq; /* wq for handshake work */ +struct workqueue_struct *smc_close_wq; /* wq for close work */ + static void smc_tcp_listen_work(struct work_struct *); static void smc_connect_work(struct work_struct *); @@ -436,26 +440,52 @@ static int smcr_clnt_conf_first_link(struct smc_sock *smc) static void smcr_conn_save_peer_info(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *clc) { - int bufsize = smc_uncompress_bufsize(clc->rmbe_size); + int bufsize = smc_uncompress_bufsize(clc->r0.rmbe_size); - smc->conn.peer_rmbe_idx = clc->rmbe_idx; - smc->conn.local_tx_ctrl.token = ntohl(clc->rmbe_alert_token); + smc->conn.peer_rmbe_idx = clc->r0.rmbe_idx; + smc->conn.local_tx_ctrl.token = ntohl(clc->r0.rmbe_alert_token); smc->conn.peer_rmbe_size = bufsize; atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size); smc->conn.tx_off = bufsize * (smc->conn.peer_rmbe_idx - 1); } +static bool smc_isascii(char *hostname) +{ + int i; + + for (i = 0; i < SMC_MAX_HOSTNAME_LEN; i++) + if (!isascii(hostname[i])) + return false; + return true; +} + static void smcd_conn_save_peer_info(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *clc) { - int bufsize = smc_uncompress_bufsize(clc->dmbe_size); + int bufsize = smc_uncompress_bufsize(clc->d0.dmbe_size); - smc->conn.peer_rmbe_idx = clc->dmbe_idx; - smc->conn.peer_token = clc->token; + smc->conn.peer_rmbe_idx = clc->d0.dmbe_idx; + smc->conn.peer_token = clc->d0.token; /* msg header takes up space in the buffer */ smc->conn.peer_rmbe_size = bufsize - sizeof(struct smcd_cdc_msg); atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size); smc->conn.tx_off = bufsize * smc->conn.peer_rmbe_idx; + if (clc->hdr.version > SMC_V1 && + (clc->hdr.typev2 & SMC_FIRST_CONTACT_MASK)) { + struct smc_clc_msg_accept_confirm_v2 *clc_v2 = + (struct smc_clc_msg_accept_confirm_v2 *)clc; + struct smc_clc_first_contact_ext *fce = + (struct smc_clc_first_contact_ext *) + (((u8 *)clc_v2) + sizeof(*clc_v2)); + + memcpy(smc->conn.lgr->negotiated_eid, clc_v2->eid, + SMC_MAX_EID_LEN); + smc->conn.lgr->peer_os = fce->os_type; + smc->conn.lgr->peer_smc_release = fce->release; + if (smc_isascii(fce->hostname)) + memcpy(smc->conn.lgr->peer_hostname, fce->hostname, + SMC_MAX_HOSTNAME_LEN); + } } static void smc_conn_save_peer_info(struct smc_sock *smc, @@ -470,11 +500,11 @@ static void smc_conn_save_peer_info(struct smc_sock *smc, static void smc_link_save_peer_info(struct smc_link *link, struct smc_clc_msg_accept_confirm *clc) { - link->peer_qpn = ntoh24(clc->qpn); - memcpy(link->peer_gid, clc->lcl.gid, SMC_GID_SIZE); - memcpy(link->peer_mac, clc->lcl.mac, sizeof(link->peer_mac)); - link->peer_psn = ntoh24(clc->psn); - link->peer_mtu = clc->qp_mtu; + link->peer_qpn = ntoh24(clc->r0.qpn); + memcpy(link->peer_gid, clc->r0.lcl.gid, SMC_GID_SIZE); + memcpy(link->peer_mac, clc->r0.lcl.mac, sizeof(link->peer_mac)); + link->peer_psn = ntoh24(clc->r0.psn); + link->peer_mtu = clc->r0.qp_mtu; } static void smc_switch_to_fallback(struct smc_sock *smc) @@ -501,7 +531,8 @@ static int smc_connect_fallback(struct smc_sock *smc, int reason_code) } /* decline and fall back during connect */ -static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code) +static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code, + u8 version) { int rc; @@ -511,7 +542,7 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code) return reason_code; } if (reason_code != SMC_CLC_DECL_PEERDECL) { - rc = smc_clc_send_decline(smc, reason_code); + rc = smc_clc_send_decline(smc, reason_code, version); if (rc < 0) { if (smc->sk.sk_state == SMC_INIT) sock_put(&smc->sk); /* passive closing */ @@ -522,23 +553,12 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code) } /* abort connecting */ -static int smc_connect_abort(struct smc_sock *smc, int reason_code, - int local_contact) +static void smc_connect_abort(struct smc_sock *smc, int local_first) { - bool is_smcd = smc->conn.lgr->is_smcd; - - if (local_contact == SMC_FIRST_CONTACT) + if (local_first) smc_lgr_cleanup_early(&smc->conn); else smc_conn_free(&smc->conn); - if (is_smcd) - /* there is only one lgr role for SMC-D; use server lock */ - mutex_unlock(&smc_server_lgr_pending); - else - mutex_unlock(&smc_client_lgr_pending); - - smc->connect_nonblock = 0; - return reason_code; } /* check if there is a rdma device available for this connection. */ @@ -561,47 +581,137 @@ static int smc_find_ism_device(struct smc_sock *smc, struct smc_init_info *ini) { /* Find ISM device with same PNETID as connecting interface */ smc_pnet_find_ism_resource(smc->clcsock->sk, ini); - if (!ini->ism_dev) + if (!ini->ism_dev[0]) return SMC_CLC_DECL_NOSMCDDEV; + else + ini->ism_chid[0] = smc_ism_get_chid(ini->ism_dev[0]); return 0; } +/* is chid unique for the ism devices that are already determined? */ +static bool smc_find_ism_v2_is_unique_chid(u16 chid, struct smc_init_info *ini, + int cnt) +{ + int i = (!ini->ism_dev[0]) ? 1 : 0; + + for (; i < cnt; i++) + if (ini->ism_chid[i] == chid) + return false; + return true; +} + +/* determine possible V2 ISM devices (either without PNETID or with PNETID plus + * PNETID matching net_device) + */ +static int smc_find_ism_v2_device_clnt(struct smc_sock *smc, + struct smc_init_info *ini) +{ + int rc = SMC_CLC_DECL_NOSMCDDEV; + struct smcd_dev *smcd; + int i = 1; + u16 chid; + + if (smcd_indicated(ini->smc_type_v1)) + rc = 0; /* already initialized for V1 */ + mutex_lock(&smcd_dev_list.mutex); + list_for_each_entry(smcd, &smcd_dev_list.list, list) { + if (smcd->going_away || smcd == ini->ism_dev[0]) + continue; + chid = smc_ism_get_chid(smcd); + if (!smc_find_ism_v2_is_unique_chid(chid, ini, i)) + continue; + if (!smc_pnet_is_pnetid_set(smcd->pnetid) || + smc_pnet_is_ndev_pnetid(sock_net(&smc->sk), smcd->pnetid)) { + ini->ism_dev[i] = smcd; + ini->ism_chid[i] = chid; + ini->is_smcd = true; + rc = 0; + i++; + if (i > SMC_MAX_ISM_DEVS) + break; + } + } + mutex_unlock(&smcd_dev_list.mutex); + ini->ism_offered_cnt = i - 1; + if (!ini->ism_dev[0] && !ini->ism_dev[1]) + ini->smcd_version = 0; + + return rc; +} + /* Check for VLAN ID and register it on ISM device just for CLC handshake */ static int smc_connect_ism_vlan_setup(struct smc_sock *smc, struct smc_init_info *ini) { - if (ini->vlan_id && smc_ism_get_vlan(ini->ism_dev, ini->vlan_id)) + if (ini->vlan_id && smc_ism_get_vlan(ini->ism_dev[0], ini->vlan_id)) return SMC_CLC_DECL_ISMVLANERR; return 0; } +static int smc_find_proposal_devices(struct smc_sock *smc, + struct smc_init_info *ini) +{ + int rc = 0; + + /* check if there is an ism device available */ + if (ini->smcd_version & SMC_V1) { + if (smc_find_ism_device(smc, ini) || + smc_connect_ism_vlan_setup(smc, ini)) { + if (ini->smc_type_v1 == SMC_TYPE_B) + ini->smc_type_v1 = SMC_TYPE_R; + else + ini->smc_type_v1 = SMC_TYPE_N; + } /* else ISM V1 is supported for this connection */ + if (smc_find_rdma_device(smc, ini)) { + if (ini->smc_type_v1 == SMC_TYPE_B) + ini->smc_type_v1 = SMC_TYPE_D; + else + ini->smc_type_v1 = SMC_TYPE_N; + } /* else RDMA is supported for this connection */ + } + if (smc_ism_v2_capable && smc_find_ism_v2_device_clnt(smc, ini)) + ini->smc_type_v2 = SMC_TYPE_N; + + /* if neither ISM nor RDMA are supported, fallback */ + if (!smcr_indicated(ini->smc_type_v1) && + ini->smc_type_v1 == SMC_TYPE_N && ini->smc_type_v2 == SMC_TYPE_N) + rc = SMC_CLC_DECL_NOSMCDEV; + + return rc; +} + /* cleanup temporary VLAN ID registration used for CLC handshake. If ISM is * used, the VLAN ID will be registered again during the connection setup. */ -static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc, bool is_smcd, +static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc, struct smc_init_info *ini) { - if (!is_smcd) + if (!smcd_indicated(ini->smc_type_v1)) return 0; - if (ini->vlan_id && smc_ism_put_vlan(ini->ism_dev, ini->vlan_id)) + if (ini->vlan_id && smc_ism_put_vlan(ini->ism_dev[0], ini->vlan_id)) return SMC_CLC_DECL_CNFERR; return 0; } +#define SMC_CLC_MAX_ACCEPT_LEN \ + (sizeof(struct smc_clc_msg_accept_confirm_v2) + \ + sizeof(struct smc_clc_first_contact_ext) + \ + sizeof(struct smc_clc_msg_trail)) + /* CLC handshake during connect */ -static int smc_connect_clc(struct smc_sock *smc, int smc_type, - struct smc_clc_msg_accept_confirm *aclc, +static int smc_connect_clc(struct smc_sock *smc, + struct smc_clc_msg_accept_confirm_v2 *aclc2, struct smc_init_info *ini) { int rc = 0; /* do inband token exchange */ - rc = smc_clc_send_proposal(smc, smc_type, ini); + rc = smc_clc_send_proposal(smc, ini); if (rc) return rc; /* receive SMC Accept CLC message */ - return smc_clc_wait_msg(smc, aclc, sizeof(*aclc), SMC_CLC_ACCEPT, - CLC_WAIT_TIME); + return smc_clc_wait_msg(smc, aclc2, SMC_CLC_MAX_ACCEPT_LEN, + SMC_CLC_ACCEPT, CLC_WAIT_TIME); } /* setup for RDMA connection of client */ @@ -613,9 +723,9 @@ static int smc_connect_rdma(struct smc_sock *smc, struct smc_link *link; ini->is_smcd = false; - ini->ib_lcl = &aclc->lcl; - ini->ib_clcqpn = ntoh24(aclc->qpn); - ini->srv_first_contact = aclc->hdr.flag; + ini->ib_lcl = &aclc->r0.lcl; + ini->ib_clcqpn = ntoh24(aclc->r0.qpn); + ini->first_contact_peer = aclc->hdr.typev2 & SMC_FIRST_CONTACT_MASK; mutex_lock(&smc_client_lgr_pending); reason_code = smc_conn_create(smc, ini); @@ -626,7 +736,7 @@ static int smc_connect_rdma(struct smc_sock *smc, smc_conn_save_peer_info(smc, aclc); - if (ini->cln_first_contact == SMC_FIRST_CONTACT) { + if (ini->first_contact_local) { link = smc->conn.lnk; } else { /* set link that was assigned by server */ @@ -634,60 +744,66 @@ static int smc_connect_rdma(struct smc_sock *smc, for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *l = &smc->conn.lgr->lnk[i]; - if (l->peer_qpn == ntoh24(aclc->qpn) && - !memcmp(l->peer_gid, &aclc->lcl.gid, SMC_GID_SIZE) && - !memcmp(l->peer_mac, &aclc->lcl.mac, sizeof(l->peer_mac))) { + if (l->peer_qpn == ntoh24(aclc->r0.qpn) && + !memcmp(l->peer_gid, &aclc->r0.lcl.gid, + SMC_GID_SIZE) && + !memcmp(l->peer_mac, &aclc->r0.lcl.mac, + sizeof(l->peer_mac))) { link = l; break; } } - if (!link) - return smc_connect_abort(smc, SMC_CLC_DECL_NOSRVLINK, - ini->cln_first_contact); + if (!link) { + reason_code = SMC_CLC_DECL_NOSRVLINK; + goto connect_abort; + } smc->conn.lnk = link; } /* create send buffer and rmb */ - if (smc_buf_create(smc, false)) - return smc_connect_abort(smc, SMC_CLC_DECL_MEM, - ini->cln_first_contact); + if (smc_buf_create(smc, false)) { + reason_code = SMC_CLC_DECL_MEM; + goto connect_abort; + } - if (ini->cln_first_contact == SMC_FIRST_CONTACT) + if (ini->first_contact_local) smc_link_save_peer_info(link, aclc); - if (smc_rmb_rtoken_handling(&smc->conn, link, aclc)) - return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RTOK, - ini->cln_first_contact); + if (smc_rmb_rtoken_handling(&smc->conn, link, aclc)) { + reason_code = SMC_CLC_DECL_ERR_RTOK; + goto connect_abort; + } smc_close_init(smc); smc_rx_init(smc); - if (ini->cln_first_contact == SMC_FIRST_CONTACT) { - if (smc_ib_ready_link(link)) - return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RDYLNK, - ini->cln_first_contact); + if (ini->first_contact_local) { + if (smc_ib_ready_link(link)) { + reason_code = SMC_CLC_DECL_ERR_RDYLNK; + goto connect_abort; + } } else { - if (smcr_lgr_reg_rmbs(link, smc->conn.rmb_desc)) - return smc_connect_abort(smc, SMC_CLC_DECL_ERR_REGRMB, - ini->cln_first_contact); + if (smcr_lgr_reg_rmbs(link, smc->conn.rmb_desc)) { + reason_code = SMC_CLC_DECL_ERR_REGRMB; + goto connect_abort; + } } smc_rmb_sync_sg_for_device(&smc->conn); - reason_code = smc_clc_send_confirm(smc); + reason_code = smc_clc_send_confirm(smc, ini->first_contact_local, + SMC_V1); if (reason_code) - return smc_connect_abort(smc, reason_code, - ini->cln_first_contact); + goto connect_abort; smc_tx_init(smc); - if (ini->cln_first_contact == SMC_FIRST_CONTACT) { + if (ini->first_contact_local) { /* QP confirmation over RoCE fabric */ smc_llc_flow_initiate(link->lgr, SMC_LLC_FLOW_ADD_LINK); reason_code = smcr_clnt_conf_first_link(smc); smc_llc_flow_stop(link->lgr, &link->lgr->llc_flow_lcl); if (reason_code) - return smc_connect_abort(smc, reason_code, - ini->cln_first_contact); + goto connect_abort; } mutex_unlock(&smc_client_lgr_pending); @@ -697,6 +813,31 @@ static int smc_connect_rdma(struct smc_sock *smc, smc->sk.sk_state = SMC_ACTIVE; return 0; +connect_abort: + smc_connect_abort(smc, ini->first_contact_local); + mutex_unlock(&smc_client_lgr_pending); + smc->connect_nonblock = 0; + + return reason_code; +} + +/* The server has chosen one of the proposed ISM devices for the communication. + * Determine from the CHID of the received CLC ACCEPT the ISM device chosen. + */ +static int +smc_v2_determine_accepted_chid(struct smc_clc_msg_accept_confirm_v2 *aclc, + struct smc_init_info *ini) +{ + int i; + + for (i = 0; i < ini->ism_offered_cnt + 1; i++) { + if (ini->ism_chid[i] == ntohs(aclc->chid)) { + ini->ism_selected = i; + return 0; + } + } + + return -EPROTO; } /* setup for ISM connection of client */ @@ -707,8 +848,17 @@ static int smc_connect_ism(struct smc_sock *smc, int rc = 0; ini->is_smcd = true; - ini->ism_gid = aclc->gid; - ini->srv_first_contact = aclc->hdr.flag; + ini->first_contact_peer = aclc->hdr.typev2 & SMC_FIRST_CONTACT_MASK; + + if (aclc->hdr.version == SMC_V2) { + struct smc_clc_msg_accept_confirm_v2 *aclc_v2 = + (struct smc_clc_msg_accept_confirm_v2 *)aclc; + + rc = smc_v2_determine_accepted_chid(aclc_v2, ini); + if (rc) + return rc; + } + ini->ism_peer_gid[ini->ism_selected] = aclc->d0.gid; /* there is only one lgr role for SMC-D; use server lock */ mutex_lock(&smc_server_lgr_pending); @@ -720,20 +870,20 @@ static int smc_connect_ism(struct smc_sock *smc, /* Create send and receive buffers */ rc = smc_buf_create(smc, true); - if (rc) - return smc_connect_abort(smc, (rc == -ENOSPC) ? - SMC_CLC_DECL_MAX_DMB : - SMC_CLC_DECL_MEM, - ini->cln_first_contact); + if (rc) { + rc = (rc == -ENOSPC) ? SMC_CLC_DECL_MAX_DMB : SMC_CLC_DECL_MEM; + goto connect_abort; + } smc_conn_save_peer_info(smc, aclc); smc_close_init(smc); smc_rx_init(smc); smc_tx_init(smc); - rc = smc_clc_send_confirm(smc); + rc = smc_clc_send_confirm(smc, ini->first_contact_local, + aclc->hdr.version); if (rc) - return smc_connect_abort(smc, rc, ini->cln_first_contact); + goto connect_abort; mutex_unlock(&smc_server_lgr_pending); smc_copy_sock_settings_to_clc(smc); @@ -742,15 +892,40 @@ static int smc_connect_ism(struct smc_sock *smc, smc->sk.sk_state = SMC_ACTIVE; return 0; +connect_abort: + smc_connect_abort(smc, ini->first_contact_local); + mutex_unlock(&smc_server_lgr_pending); + smc->connect_nonblock = 0; + + return rc; +} + +/* check if received accept type and version matches a proposed one */ +static int smc_connect_check_aclc(struct smc_init_info *ini, + struct smc_clc_msg_accept_confirm *aclc) +{ + if ((aclc->hdr.typev1 == SMC_TYPE_R && + !smcr_indicated(ini->smc_type_v1)) || + (aclc->hdr.typev1 == SMC_TYPE_D && + ((!smcd_indicated(ini->smc_type_v1) && + !smcd_indicated(ini->smc_type_v2)) || + (aclc->hdr.version == SMC_V1 && + !smcd_indicated(ini->smc_type_v1)) || + (aclc->hdr.version == SMC_V2 && + !smcd_indicated(ini->smc_type_v2))))) + return SMC_CLC_DECL_MODEUNSUPP; + + return 0; } /* perform steps before actually connecting */ static int __smc_connect(struct smc_sock *smc) { - bool ism_supported = false, rdma_supported = false; - struct smc_clc_msg_accept_confirm aclc; - struct smc_init_info ini = {0}; - int smc_type; + u8 version = smc_ism_v2_capable ? SMC_V2 : SMC_V1; + struct smc_clc_msg_accept_confirm_v2 *aclc2; + struct smc_clc_msg_accept_confirm *aclc; + struct smc_init_info *ini = NULL; + u8 *buf = NULL; int rc = 0; if (smc->use_fallback) @@ -760,58 +935,73 @@ static int __smc_connect(struct smc_sock *smc) if (!tcp_sk(smc->clcsock->sk)->syn_smc) return smc_connect_fallback(smc, SMC_CLC_DECL_PEERNOSMC); - /* IPSec connections opt out of SMC-R optimizations */ + /* IPSec connections opt out of SMC optimizations */ if (using_ipsec(smc)) - return smc_connect_decline_fallback(smc, SMC_CLC_DECL_IPSEC); + return smc_connect_decline_fallback(smc, SMC_CLC_DECL_IPSEC, + version); - /* get vlan id from IP device */ - if (smc_vlan_by_tcpsk(smc->clcsock, &ini)) - return smc_connect_decline_fallback(smc, - SMC_CLC_DECL_GETVLANERR); + ini = kzalloc(sizeof(*ini), GFP_KERNEL); + if (!ini) + return smc_connect_decline_fallback(smc, SMC_CLC_DECL_MEM, + version); - /* check if there is an ism device available */ - if (!smc_find_ism_device(smc, &ini) && - !smc_connect_ism_vlan_setup(smc, &ini)) { - /* ISM is supported for this connection */ - ism_supported = true; - smc_type = SMC_TYPE_D; - } - - /* check if there is a rdma device available */ - if (!smc_find_rdma_device(smc, &ini)) { - /* RDMA is supported for this connection */ - rdma_supported = true; - if (ism_supported) - smc_type = SMC_TYPE_B; /* both */ - else - smc_type = SMC_TYPE_R; /* only RDMA */ + ini->smcd_version = SMC_V1; + ini->smcd_version |= smc_ism_v2_capable ? SMC_V2 : 0; + ini->smc_type_v1 = SMC_TYPE_B; + ini->smc_type_v2 = smc_ism_v2_capable ? SMC_TYPE_D : SMC_TYPE_N; + + /* get vlan id from IP device */ + if (smc_vlan_by_tcpsk(smc->clcsock, ini)) { + ini->smcd_version &= ~SMC_V1; + ini->smc_type_v1 = SMC_TYPE_N; + if (!ini->smcd_version) { + rc = SMC_CLC_DECL_GETVLANERR; + goto fallback; + } } - /* if neither ISM nor RDMA are supported, fallback */ - if (!rdma_supported && !ism_supported) - return smc_connect_decline_fallback(smc, SMC_CLC_DECL_NOSMCDEV); + rc = smc_find_proposal_devices(smc, ini); + if (rc) + goto fallback; - /* perform CLC handshake */ - rc = smc_connect_clc(smc, smc_type, &aclc, &ini); - if (rc) { - smc_connect_ism_vlan_cleanup(smc, ism_supported, &ini); - return smc_connect_decline_fallback(smc, rc); + buf = kzalloc(SMC_CLC_MAX_ACCEPT_LEN, GFP_KERNEL); + if (!buf) { + rc = SMC_CLC_DECL_MEM; + goto fallback; } + aclc2 = (struct smc_clc_msg_accept_confirm_v2 *)buf; + aclc = (struct smc_clc_msg_accept_confirm *)aclc2; + + /* perform CLC handshake */ + rc = smc_connect_clc(smc, aclc2, ini); + if (rc) + goto vlan_cleanup; + + /* check if smc modes and versions of CLC proposal and accept match */ + rc = smc_connect_check_aclc(ini, aclc); + version = aclc->hdr.version == SMC_V1 ? SMC_V1 : version; + if (rc) + goto vlan_cleanup; /* depending on previous steps, connect using rdma or ism */ - if (rdma_supported && aclc.hdr.path == SMC_TYPE_R) - rc = smc_connect_rdma(smc, &aclc, &ini); - else if (ism_supported && aclc.hdr.path == SMC_TYPE_D) - rc = smc_connect_ism(smc, &aclc, &ini); - else - rc = SMC_CLC_DECL_MODEUNSUPP; - if (rc) { - smc_connect_ism_vlan_cleanup(smc, ism_supported, &ini); - return smc_connect_decline_fallback(smc, rc); - } + if (aclc->hdr.typev1 == SMC_TYPE_R) + rc = smc_connect_rdma(smc, aclc, ini); + else if (aclc->hdr.typev1 == SMC_TYPE_D) + rc = smc_connect_ism(smc, aclc, ini); + if (rc) + goto vlan_cleanup; - smc_connect_ism_vlan_cleanup(smc, ism_supported, &ini); + smc_connect_ism_vlan_cleanup(smc, ini); + kfree(buf); + kfree(ini); return 0; + +vlan_cleanup: + smc_connect_ism_vlan_cleanup(smc, ini); + kfree(buf); +fallback: + kfree(ini); + return smc_connect_decline_fallback(smc, rc, version); } static void smc_connect_work(struct work_struct *work) @@ -903,7 +1093,7 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr, if (smc->use_fallback) goto out; if (flags & O_NONBLOCK) { - if (schedule_work(&smc->connect_work)) + if (queue_work(smc_hs_wq, &smc->connect_work)) smc->connect_nonblock = 1; rc = -EINPROGRESS; } else { @@ -940,10 +1130,10 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) mutex_lock(&lsmc->clcsock_release_lock); if (lsmc->clcsock) - rc = kernel_accept(lsmc->clcsock, &new_clcsock, 0); + rc = kernel_accept(lsmc->clcsock, &new_clcsock, SOCK_NONBLOCK); mutex_unlock(&lsmc->clcsock_release_lock); lock_sock(lsk); - if (rc < 0) + if (rc < 0 && rc != -EAGAIN) lsk->sk_err = -rc; if (rc < 0 || lsk->sk_state == SMC_CLOSED) { new_sk->sk_prot->unhash(new_sk); @@ -956,6 +1146,10 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) goto out; } + /* new clcsock has inherited the smc listen-specific sk_data_ready + * function; switch it back to the original sk_data_ready function + */ + new_clcsock->sk->sk_data_ready = lsmc->clcsk_data_ready; (*new_smc)->clcsock = new_clcsock; out: return rc; @@ -1123,10 +1317,10 @@ static void smc_listen_out_err(struct smc_sock *new_smc) /* listen worker: decline and fall back if possible */ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code, - int local_contact) + int local_first, u8 version) { /* RDMA setup failed, switch back to TCP */ - if (local_contact == SMC_FIRST_CONTACT) + if (local_first) smc_lgr_cleanup_early(&new_smc->conn); else smc_conn_free(&new_smc->conn); @@ -1137,7 +1331,7 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code, smc_switch_to_fallback(new_smc); new_smc->fallback_rsn = reason_code; if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) { - if (smc_clc_send_decline(new_smc, reason_code) < 0) { + if (smc_clc_send_decline(new_smc, reason_code, version) < 0) { smc_listen_out_err(new_smc); return; } @@ -1145,6 +1339,47 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code, smc_listen_out_connected(new_smc); } +/* listen worker: version checking */ +static int smc_listen_v2_check(struct smc_sock *new_smc, + struct smc_clc_msg_proposal *pclc, + struct smc_init_info *ini) +{ + struct smc_clc_smcd_v2_extension *pclc_smcd_v2_ext; + struct smc_clc_v2_extension *pclc_v2_ext; + + ini->smc_type_v1 = pclc->hdr.typev1; + ini->smc_type_v2 = pclc->hdr.typev2; + ini->smcd_version = ini->smc_type_v1 != SMC_TYPE_N ? SMC_V1 : 0; + if (pclc->hdr.version > SMC_V1) + ini->smcd_version |= + ini->smc_type_v2 != SMC_TYPE_N ? SMC_V2 : 0; + if (!smc_ism_v2_capable) { + ini->smcd_version &= ~SMC_V2; + goto out; + } + pclc_v2_ext = smc_get_clc_v2_ext(pclc); + if (!pclc_v2_ext) { + ini->smcd_version &= ~SMC_V2; + goto out; + } + pclc_smcd_v2_ext = smc_get_clc_smcd_v2_ext(pclc_v2_ext); + if (!pclc_smcd_v2_ext) + ini->smcd_version &= ~SMC_V2; + +out: + if (!ini->smcd_version) { + if (pclc->hdr.typev1 == SMC_TYPE_B || + pclc->hdr.typev2 == SMC_TYPE_B) + return SMC_CLC_DECL_NOSMCDEV; + if (pclc->hdr.typev1 == SMC_TYPE_D || + pclc->hdr.typev2 == SMC_TYPE_D) + return SMC_CLC_DECL_NOSMCDDEV; + return SMC_CLC_DECL_NOSMCRDEV; + } + + return 0; +} + /* listen worker: check prefixes */ static int smc_listen_prfx_check(struct smc_sock *new_smc, struct smc_clc_msg_proposal *pclc) @@ -1152,6 +1387,8 @@ static int smc_listen_prfx_check(struct smc_sock *new_smc, struct smc_clc_msg_proposal_prefix *pclc_prfx; struct socket *newclcsock = new_smc->clcsock; + if (pclc->hdr.typev1 == SMC_TYPE_N) + return 0; pclc_prfx = smc_clc_proposal_get_prefix(pclc); if (smc_clc_prfx_match(newclcsock, pclc_prfx)) return SMC_CLC_DECL_DIFFPREFIX; @@ -1179,33 +1416,18 @@ static int smc_listen_rdma_init(struct smc_sock *new_smc, /* listen worker: initialize connection and buffers for SMC-D */ static int smc_listen_ism_init(struct smc_sock *new_smc, - struct smc_clc_msg_proposal *pclc, struct smc_init_info *ini) { - struct smc_clc_msg_smcd *pclc_smcd; int rc; - pclc_smcd = smc_get_clc_msg_smcd(pclc); - ini->ism_gid = pclc_smcd->gid; rc = smc_conn_create(new_smc, ini); if (rc) return rc; - /* Check if peer can be reached via ISM device */ - if (smc_ism_cantalk(new_smc->conn.lgr->peer_gid, - new_smc->conn.lgr->vlan_id, - new_smc->conn.lgr->smcd)) { - if (ini->cln_first_contact == SMC_FIRST_CONTACT) - smc_lgr_cleanup_early(&new_smc->conn); - else - smc_conn_free(&new_smc->conn); - return SMC_CLC_DECL_SMCDNOTALK; - } - /* Create send and receive buffers */ rc = smc_buf_create(new_smc, true); if (rc) { - if (ini->cln_first_contact == SMC_FIRST_CONTACT) + if (ini->first_contact_local) smc_lgr_cleanup_early(&new_smc->conn); else smc_conn_free(&new_smc->conn); @@ -1216,12 +1438,135 @@ static int smc_listen_ism_init(struct smc_sock *new_smc, return 0; } +static bool smc_is_already_selected(struct smcd_dev *smcd, + struct smc_init_info *ini, + int matches) +{ + int i; + + for (i = 0; i < matches; i++) + if (smcd == ini->ism_dev[i]) + return true; + + return false; +} + +/* check for ISM devices matching proposed ISM devices */ +static void smc_check_ism_v2_match(struct smc_init_info *ini, + u16 proposed_chid, u64 proposed_gid, + unsigned int *matches) +{ + struct smcd_dev *smcd; + + list_for_each_entry(smcd, &smcd_dev_list.list, list) { + if (smcd->going_away) + continue; + if (smc_is_already_selected(smcd, ini, *matches)) + continue; + if (smc_ism_get_chid(smcd) == proposed_chid && + !smc_ism_cantalk(proposed_gid, ISM_RESERVED_VLANID, smcd)) { + ini->ism_peer_gid[*matches] = proposed_gid; + ini->ism_dev[*matches] = smcd; + (*matches)++; + break; + } + } +} + +static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, + struct smc_clc_msg_proposal *pclc, + struct smc_init_info *ini) +{ + struct smc_clc_smcd_v2_extension *smcd_v2_ext; + struct smc_clc_v2_extension *smc_v2_ext; + struct smc_clc_msg_smcd *pclc_smcd; + unsigned int matches = 0; + u8 smcd_version; + u8 *eid = NULL; + int i; + + if (!(ini->smcd_version & SMC_V2) || !smcd_indicated(ini->smc_type_v2)) + goto not_found; + + pclc_smcd = smc_get_clc_msg_smcd(pclc); + smc_v2_ext = smc_get_clc_v2_ext(pclc); + smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext); + if (!smcd_v2_ext || + !smc_v2_ext->hdr.flag.seid) /* no system EID support for SMCD */ + goto not_found; + + mutex_lock(&smcd_dev_list.mutex); + if (pclc_smcd->ism.chid) + /* check for ISM device matching proposed native ISM device */ + smc_check_ism_v2_match(ini, ntohs(pclc_smcd->ism.chid), + ntohll(pclc_smcd->ism.gid), &matches); + for (i = 1; i <= smc_v2_ext->hdr.ism_gid_cnt; i++) { + /* check for ISM devices matching proposed non-native ISM + * devices + */ + smc_check_ism_v2_match(ini, + ntohs(smcd_v2_ext->gidchid[i - 1].chid), + ntohll(smcd_v2_ext->gidchid[i - 1].gid), + &matches); + } + mutex_unlock(&smcd_dev_list.mutex); + + if (ini->ism_dev[0]) { + smc_ism_get_system_eid(ini->ism_dev[0], &eid); + if (memcmp(eid, smcd_v2_ext->system_eid, SMC_MAX_EID_LEN)) + goto not_found; + } else { + goto not_found; + } + + /* separate - outside the smcd_dev_list.lock */ + smcd_version = ini->smcd_version; + for (i = 0; i < matches; i++) { + ini->smcd_version = SMC_V2; + ini->is_smcd = true; + ini->ism_selected = i; + if (smc_listen_ism_init(new_smc, ini)) + /* try next active ISM device */ + continue; + return; /* matching and usable V2 ISM device found */ + } + /* no V2 ISM device could be initialized */ + ini->smcd_version = smcd_version; /* restore original value */ + +not_found: + ini->smcd_version &= ~SMC_V2; + ini->ism_dev[0] = NULL; + ini->is_smcd = false; +} + +static void smc_find_ism_v1_device_serv(struct smc_sock *new_smc, + struct smc_clc_msg_proposal *pclc, + struct smc_init_info *ini) +{ + struct smc_clc_msg_smcd *pclc_smcd = smc_get_clc_msg_smcd(pclc); + + /* check if ISM V1 is available */ + if (!(ini->smcd_version & SMC_V1) || !smcd_indicated(ini->smc_type_v1)) + goto not_found; + ini->is_smcd = true; /* prepare ISM check */ + ini->ism_peer_gid[0] = ntohll(pclc_smcd->ism.gid); + if (smc_find_ism_device(new_smc, ini)) + goto not_found; + ini->ism_selected = 0; + if (!smc_listen_ism_init(new_smc, ini)) + return; /* V1 ISM device found */ + +not_found: + ini->ism_dev[0] = NULL; + ini->is_smcd = false; +} + /* listen worker: register buffers */ -static int smc_listen_rdma_reg(struct smc_sock *new_smc, int local_contact) +static int smc_listen_rdma_reg(struct smc_sock *new_smc, bool local_first) { struct smc_connection *conn = &new_smc->conn; - if (local_contact != SMC_FIRST_CONTACT) { + if (!local_first) { if (smcr_lgr_reg_rmbs(conn->lnk, conn->rmb_desc)) return SMC_CLC_DECL_ERR_REGRMB; } @@ -1230,52 +1575,103 @@ static int smc_listen_rdma_reg(struct smc_sock *new_smc, int local_contact) return 0; } +static int smc_find_rdma_v1_device_serv(struct smc_sock *new_smc, + struct smc_clc_msg_proposal *pclc, + struct smc_init_info *ini) +{ + int rc; + + if (!smcr_indicated(ini->smc_type_v1)) + return SMC_CLC_DECL_NOSMCDEV; + + /* prepare RDMA check */ + ini->ib_lcl = &pclc->lcl; + rc = smc_find_rdma_device(new_smc, ini); + if (rc) { + /* no RDMA device found */ + if (ini->smc_type_v1 == SMC_TYPE_B) + /* neither ISM nor RDMA device found */ + rc = SMC_CLC_DECL_NOSMCDEV; + return rc; + } + rc = smc_listen_rdma_init(new_smc, ini); + if (rc) + return rc; + return smc_listen_rdma_reg(new_smc, ini->first_contact_local); +} + +/* determine the local device matching to proposal */ +static int smc_listen_find_device(struct smc_sock *new_smc, + struct smc_clc_msg_proposal *pclc, + struct smc_init_info *ini) +{ + int rc; + + /* check for ISM device matching V2 proposed device */ + smc_find_ism_v2_device_serv(new_smc, pclc, ini); + if (ini->ism_dev[0]) + return 0; + + if (!(ini->smcd_version & SMC_V1)) + return SMC_CLC_DECL_NOSMCDEV; + + /* check for matching IP prefix and subnet length */ + rc = smc_listen_prfx_check(new_smc, pclc); + if (rc) + return rc; + + /* get vlan id from IP device */ + if (smc_vlan_by_tcpsk(new_smc->clcsock, ini)) + return SMC_CLC_DECL_GETVLANERR; + + /* check for ISM device matching V1 proposed device */ + smc_find_ism_v1_device_serv(new_smc, pclc, ini); + if (ini->ism_dev[0]) + return 0; + + if (pclc->hdr.typev1 == SMC_TYPE_D) + return SMC_CLC_DECL_NOSMCDDEV; /* skip RDMA and decline */ + + /* check if RDMA is available */ + return smc_find_rdma_v1_device_serv(new_smc, pclc, ini); +} + /* listen worker: finish RDMA setup */ static int smc_listen_rdma_finish(struct smc_sock *new_smc, struct smc_clc_msg_accept_confirm *cclc, - int local_contact) + bool local_first) { struct smc_link *link = new_smc->conn.lnk; int reason_code = 0; - if (local_contact == SMC_FIRST_CONTACT) + if (local_first) smc_link_save_peer_info(link, cclc); - if (smc_rmb_rtoken_handling(&new_smc->conn, link, cclc)) { - reason_code = SMC_CLC_DECL_ERR_RTOK; - goto decline; - } + if (smc_rmb_rtoken_handling(&new_smc->conn, link, cclc)) + return SMC_CLC_DECL_ERR_RTOK; - if (local_contact == SMC_FIRST_CONTACT) { - if (smc_ib_ready_link(link)) { - reason_code = SMC_CLC_DECL_ERR_RDYLNK; - goto decline; - } + if (local_first) { + if (smc_ib_ready_link(link)) + return SMC_CLC_DECL_ERR_RDYLNK; /* QP confirmation over RoCE fabric */ smc_llc_flow_initiate(link->lgr, SMC_LLC_FLOW_ADD_LINK); reason_code = smcr_serv_conf_first_link(new_smc); smc_llc_flow_stop(link->lgr, &link->lgr->llc_flow_lcl); - if (reason_code) - goto decline; } - return 0; - -decline: - smc_listen_decline(new_smc, reason_code, local_contact); return reason_code; } -/* setup for RDMA connection of server */ +/* setup for connection of server */ static void smc_listen_work(struct work_struct *work) { struct smc_sock *new_smc = container_of(work, struct smc_sock, smc_listen_work); + u8 version = smc_ism_v2_capable ? SMC_V2 : SMC_V1; struct socket *newclcsock = new_smc->clcsock; - struct smc_clc_msg_accept_confirm cclc; + struct smc_clc_msg_accept_confirm *cclc; + struct smc_clc_msg_proposal_area *buf; struct smc_clc_msg_proposal *pclc; - struct smc_init_info ini = {0}; - bool ism_supported = false; - u8 buf[SMC_CLC_MAX_LEN]; + struct smc_init_info *ini = NULL; int rc = 0; if (new_smc->listen_smc->sk.sk_state != SMC_LISTEN) @@ -1297,102 +1693,86 @@ static void smc_listen_work(struct work_struct *work) /* do inband token exchange - * wait for and receive SMC Proposal CLC message */ - pclc = (struct smc_clc_msg_proposal *)&buf; - rc = smc_clc_wait_msg(new_smc, pclc, SMC_CLC_MAX_LEN, + buf = kzalloc(sizeof(*buf), GFP_KERNEL); + if (!buf) { + rc = SMC_CLC_DECL_MEM; + goto out_decl; + } + pclc = (struct smc_clc_msg_proposal *)buf; + rc = smc_clc_wait_msg(new_smc, pclc, sizeof(*buf), SMC_CLC_PROPOSAL, CLC_WAIT_TIME); if (rc) goto out_decl; + version = pclc->hdr.version == SMC_V1 ? SMC_V1 : version; - /* IPSec connections opt out of SMC-R optimizations */ + /* IPSec connections opt out of SMC optimizations */ if (using_ipsec(new_smc)) { rc = SMC_CLC_DECL_IPSEC; goto out_decl; } - /* check for matching IP prefix and subnet length */ - rc = smc_listen_prfx_check(new_smc, pclc); - if (rc) + ini = kzalloc(sizeof(*ini), GFP_KERNEL); + if (!ini) { + rc = SMC_CLC_DECL_MEM; goto out_decl; + } - /* get vlan id from IP device */ - if (smc_vlan_by_tcpsk(new_smc->clcsock, &ini)) { - rc = SMC_CLC_DECL_GETVLANERR; + /* initial version checking */ + rc = smc_listen_v2_check(new_smc, pclc, ini); + if (rc) goto out_decl; - } mutex_lock(&smc_server_lgr_pending); smc_close_init(new_smc); smc_rx_init(new_smc); smc_tx_init(new_smc); - /* check if ISM is available */ - if (pclc->hdr.path == SMC_TYPE_D || pclc->hdr.path == SMC_TYPE_B) { - ini.is_smcd = true; /* prepare ISM check */ - rc = smc_find_ism_device(new_smc, &ini); - if (!rc) - rc = smc_listen_ism_init(new_smc, pclc, &ini); - if (!rc) - ism_supported = true; - else if (pclc->hdr.path == SMC_TYPE_D) - goto out_unlock; /* skip RDMA and decline */ - } - - /* check if RDMA is available */ - if (!ism_supported) { /* SMC_TYPE_R or SMC_TYPE_B */ - /* prepare RDMA check */ - ini.is_smcd = false; - ini.ism_dev = NULL; - ini.ib_lcl = &pclc->lcl; - rc = smc_find_rdma_device(new_smc, &ini); - if (rc) { - /* no RDMA device found */ - if (pclc->hdr.path == SMC_TYPE_B) - /* neither ISM nor RDMA device found */ - rc = SMC_CLC_DECL_NOSMCDEV; - goto out_unlock; - } - rc = smc_listen_rdma_init(new_smc, &ini); - if (rc) - goto out_unlock; - rc = smc_listen_rdma_reg(new_smc, ini.cln_first_contact); - if (rc) - goto out_unlock; - } + /* determine ISM or RoCE device used for connection */ + rc = smc_listen_find_device(new_smc, pclc, ini); + if (rc) + goto out_unlock; /* send SMC Accept CLC message */ - rc = smc_clc_send_accept(new_smc, ini.cln_first_contact); + rc = smc_clc_send_accept(new_smc, ini->first_contact_local, + ini->smcd_version == SMC_V2 ? SMC_V2 : SMC_V1); if (rc) goto out_unlock; /* SMC-D does not need this lock any more */ - if (ism_supported) + if (ini->is_smcd) mutex_unlock(&smc_server_lgr_pending); /* receive SMC Confirm CLC message */ - rc = smc_clc_wait_msg(new_smc, &cclc, sizeof(cclc), + memset(buf, 0, sizeof(*buf)); + cclc = (struct smc_clc_msg_accept_confirm *)buf; + rc = smc_clc_wait_msg(new_smc, cclc, sizeof(*buf), SMC_CLC_CONFIRM, CLC_WAIT_TIME); if (rc) { - if (!ism_supported) + if (!ini->is_smcd) goto out_unlock; goto out_decl; } /* finish worker */ - if (!ism_supported) { - rc = smc_listen_rdma_finish(new_smc, &cclc, - ini.cln_first_contact); - mutex_unlock(&smc_server_lgr_pending); + if (!ini->is_smcd) { + rc = smc_listen_rdma_finish(new_smc, cclc, + ini->first_contact_local); if (rc) - return; + goto out_unlock; + mutex_unlock(&smc_server_lgr_pending); } - smc_conn_save_peer_info(new_smc, &cclc); + smc_conn_save_peer_info(new_smc, cclc); smc_listen_out_connected(new_smc); - return; + goto out_free; out_unlock: mutex_unlock(&smc_server_lgr_pending); out_decl: - smc_listen_decline(new_smc, rc, ini.cln_first_contact); + smc_listen_decline(new_smc, rc, ini ? ini->first_contact_local : 0, + version); +out_free: + kfree(ini); + kfree(buf); } static void smc_tcp_listen_work(struct work_struct *work) @@ -1406,7 +1786,7 @@ static void smc_tcp_listen_work(struct work_struct *work) lock_sock(lsk); while (lsk->sk_state == SMC_LISTEN) { rc = smc_clcsock_accept(lsmc, &new_smc); - if (rc) + if (rc) /* clcsock accept queue empty or error */ goto out; if (!new_smc) continue; @@ -1420,13 +1800,29 @@ static void smc_tcp_listen_work(struct work_struct *work) new_smc->sk.sk_sndbuf = lsmc->sk.sk_sndbuf; new_smc->sk.sk_rcvbuf = lsmc->sk.sk_rcvbuf; sock_hold(&new_smc->sk); /* sock_put in passive closing */ - if (!schedule_work(&new_smc->smc_listen_work)) + if (!queue_work(smc_hs_wq, &new_smc->smc_listen_work)) sock_put(&new_smc->sk); } out: release_sock(lsk); - sock_put(&lsmc->sk); /* sock_hold in smc_listen */ + sock_put(&lsmc->sk); /* sock_hold in smc_clcsock_data_ready() */ +} + +static void smc_clcsock_data_ready(struct sock *listen_clcsock) +{ + struct smc_sock *lsmc; + + lsmc = (struct smc_sock *) + ((uintptr_t)listen_clcsock->sk_user_data & ~SK_USER_DATA_NOCOPY); + if (!lsmc) + return; + lsmc->clcsk_data_ready(listen_clcsock); + if (lsmc->sk.sk_state == SMC_LISTEN) { + sock_hold(&lsmc->sk); /* sock_put in smc_tcp_listen_work() */ + if (!queue_work(smc_hs_wq, &lsmc->tcp_listen_work)) + sock_put(&lsmc->sk); + } } static int smc_listen(struct socket *sock, int backlog) @@ -1455,15 +1851,19 @@ static int smc_listen(struct socket *sock, int backlog) if (!smc->use_fallback) tcp_sk(smc->clcsock->sk)->syn_smc = 1; + /* save original sk_data_ready function and establish + * smc-specific sk_data_ready function + */ + smc->clcsk_data_ready = smc->clcsock->sk->sk_data_ready; + smc->clcsock->sk->sk_data_ready = smc_clcsock_data_ready; + smc->clcsock->sk->sk_user_data = + (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); rc = kernel_listen(smc->clcsock, backlog); if (rc) goto out; sk->sk_max_ack_backlog = backlog; sk->sk_ack_backlog = 0; sk->sk_state = SMC_LISTEN; - sock_hold(sk); /* sock_hold in tcp_listen_worker */ - if (!schedule_work(&smc->tcp_listen_work)) - sock_put(sk); out: release_sock(sk); @@ -1788,8 +2188,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { if (val) - mod_delayed_work(system_wq, &smc->conn.tx_work, - 0); + mod_delayed_work(smc->conn.lgr->tx_wq, + &smc->conn.tx_work, 0); } break; case TCP_CORK: @@ -1797,8 +2197,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { if (!val) - mod_delayed_work(system_wq, &smc->conn.tx_work, - 0); + mod_delayed_work(smc->conn.lgr->tx_wq, + &smc->conn.tx_work, 0); } break; case TCP_DEFER_ACCEPT: @@ -2077,14 +2477,26 @@ static int __init smc_init(void) if (rc) return rc; + smc_ism_init(); + smc_clc_init(); + rc = smc_pnet_init(); if (rc) goto out_pernet_subsys; + rc = -ENOMEM; + smc_hs_wq = alloc_workqueue("smc_hs_wq", 0, 0); + if (!smc_hs_wq) + goto out_pnet; + + smc_close_wq = alloc_workqueue("smc_close_wq", 0, 0); + if (!smc_close_wq) + goto out_alloc_hs_wq; + rc = smc_core_init(); if (rc) { pr_err("%s: smc_core_init fails with %d\n", __func__, rc); - goto out_pnet; + goto out_alloc_wqs; } rc = smc_llc_init(); @@ -2136,6 +2548,10 @@ out_proto: proto_unregister(&smc_proto); out_core: smc_core_exit(); +out_alloc_wqs: + destroy_workqueue(smc_close_wq); +out_alloc_hs_wq: + destroy_workqueue(smc_hs_wq); out_pnet: smc_pnet_exit(); out_pernet_subsys: @@ -2150,6 +2566,8 @@ static void __exit smc_exit(void) sock_unregister(PF_SMC); smc_core_exit(); smc_ib_unregister_client(); + destroy_workqueue(smc_close_wq); + destroy_workqueue(smc_hs_wq); proto_unregister(&smc_proto6); proto_unregister(&smc_proto); smc_pnet_exit(); diff --git a/net/smc/smc.h b/net/smc/smc.h index 6f1c42da7a4c..d65e15f0c944 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -18,9 +18,20 @@ #include "smc_ib.h" +#define SMC_V1 1 /* SMC version V1 */ +#define SMC_V2 2 /* SMC version V2 */ +#define SMC_RELEASE 0 + #define SMCPROTO_SMC 0 /* SMC protocol, IPv4 */ #define SMCPROTO_SMC6 1 /* SMC protocol, IPv6 */ +#define SMC_MAX_ISM_DEVS 8 /* max # of proposed non-native ISM + * devices + */ + +#define SMC_MAX_HOSTNAME_LEN 32 +#define SMC_MAX_EID_LEN 32 + extern struct proto smc_proto; extern struct proto smc_proto6; @@ -201,6 +212,8 @@ struct smc_connection { struct smc_sock { /* smc sock container */ struct sock sk; struct socket *clcsock; /* internal tcp socket */ + void (*clcsk_data_ready)(struct sock *sk); + /* original data_ready fct. **/ struct smc_connection conn; /* smc connection */ struct smc_sock *listen_smc; /* listen parent */ struct work_struct connect_work; /* handle non-blocking connect*/ @@ -235,10 +248,16 @@ static inline struct smc_sock *smc_sk(const struct sock *sk) return (struct smc_sock *)sk; } +extern struct workqueue_struct *smc_hs_wq; /* wq for handshake work */ +extern struct workqueue_struct *smc_close_wq; /* wq for close work */ + #define SMC_SYSTEMID_LEN 8 extern u8 local_systemid[SMC_SYSTEMID_LEN]; /* unique system identifier */ +#define ntohll(x) be64_to_cpu(x) +#define htonll(x) cpu_to_be64(x) + /* convert an u32 value into network byte order, store it into a 3 byte field */ static inline void hton24(u8 *net, u32 host) { diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index ce468ff62a19..b1ce6ccbfaec 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -299,7 +299,7 @@ static void smc_cdc_msg_validate(struct smc_sock *smc, struct smc_cdc_msg *cdc, conn->lnk = link; spin_unlock_bh(&conn->send_lock); sock_hold(&smc->sk); /* sock_put in abort_work */ - if (!schedule_work(&conn->abort_work)) + if (!queue_work(smc_close_wq, &conn->abort_work)) sock_put(&smc->sk); } } @@ -368,7 +368,7 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc, smc->clcsock->sk->sk_shutdown |= RCV_SHUTDOWN; sock_set_flag(&smc->sk, SOCK_DONE); sock_hold(&smc->sk); /* sock_put in close_work */ - if (!schedule_work(&conn->close_work)) + if (!queue_work(smc_close_wq, &conn->close_work)) sock_put(&smc->sk); } } diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 779f4142a11d..696d89c2dce4 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -14,6 +14,8 @@ #include <linux/inetdevice.h> #include <linux/if_ether.h> #include <linux/sched/signal.h> +#include <linux/utsname.h> +#include <linux/ctype.h> #include <net/addrconf.h> #include <net/sock.h> @@ -27,6 +29,7 @@ #define SMCR_CLC_ACCEPT_CONFIRM_LEN 68 #define SMCD_CLC_ACCEPT_CONFIRM_LEN 48 +#define SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 78 #define SMC_CLC_RECV_BUF_LEN 100 /* eye catcher "SMCR" EBCDIC for CLC messages */ @@ -34,13 +37,88 @@ static const char SMC_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xd9'}; /* eye catcher "SMCD" EBCDIC for CLC messages */ static const char SMCD_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xc4'}; +static u8 smc_hostname[SMC_MAX_HOSTNAME_LEN]; + +/* check arriving CLC proposal */ +static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc) +{ + struct smc_clc_msg_proposal_prefix *pclc_prfx; + struct smc_clc_smcd_v2_extension *smcd_v2_ext; + struct smc_clc_msg_hdr *hdr = &pclc->hdr; + struct smc_clc_v2_extension *v2_ext; + + v2_ext = smc_get_clc_v2_ext(pclc); + pclc_prfx = smc_clc_proposal_get_prefix(pclc); + if (hdr->version == SMC_V1) { + if (hdr->typev1 == SMC_TYPE_N) + return false; + if (ntohs(hdr->length) != + sizeof(*pclc) + ntohs(pclc->iparea_offset) + + sizeof(*pclc_prfx) + + pclc_prfx->ipv6_prefixes_cnt * + sizeof(struct smc_clc_ipv6_prefix) + + sizeof(struct smc_clc_msg_trail)) + return false; + } else { + if (ntohs(hdr->length) != + sizeof(*pclc) + + sizeof(struct smc_clc_msg_smcd) + + (hdr->typev1 != SMC_TYPE_N ? + sizeof(*pclc_prfx) + + pclc_prfx->ipv6_prefixes_cnt * + sizeof(struct smc_clc_ipv6_prefix) : 0) + + (hdr->typev2 != SMC_TYPE_N ? + sizeof(*v2_ext) + + v2_ext->hdr.eid_cnt * SMC_MAX_EID_LEN : 0) + + (smcd_indicated(hdr->typev2) ? + sizeof(*smcd_v2_ext) + v2_ext->hdr.ism_gid_cnt * + sizeof(struct smc_clc_smcd_gid_chid) : + 0) + + sizeof(struct smc_clc_msg_trail)) + return false; + } + return true; +} + +/* check arriving CLC accept or confirm */ +static bool +smc_clc_msg_acc_conf_valid(struct smc_clc_msg_accept_confirm_v2 *clc_v2) +{ + struct smc_clc_msg_hdr *hdr = &clc_v2->hdr; + + if (hdr->typev1 != SMC_TYPE_R && hdr->typev1 != SMC_TYPE_D) + return false; + if (hdr->version == SMC_V1) { + if ((hdr->typev1 == SMC_TYPE_R && + ntohs(hdr->length) != SMCR_CLC_ACCEPT_CONFIRM_LEN) || + (hdr->typev1 == SMC_TYPE_D && + ntohs(hdr->length) != SMCD_CLC_ACCEPT_CONFIRM_LEN)) + return false; + } else { + if (hdr->typev1 == SMC_TYPE_D && + ntohs(hdr->length) != SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 && + (ntohs(hdr->length) != SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 + + sizeof(struct smc_clc_first_contact_ext))) + return false; + } + return true; +} + +static void smc_clc_fill_fce(struct smc_clc_first_contact_ext *fce, int *len) +{ + memset(fce, 0, sizeof(*fce)); + fce->os_type = SMC_CLC_OS_LINUX; + fce->release = SMC_RELEASE; + memcpy(fce->hostname, smc_hostname, sizeof(smc_hostname)); + (*len) += sizeof(*fce); +} + /* check if received message has a correct header length and contains valid * heading and trailing eyecatchers */ static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm, bool check_trl) { - struct smc_clc_msg_proposal_prefix *pclc_prfx; - struct smc_clc_msg_accept_confirm *clc; + struct smc_clc_msg_accept_confirm_v2 *clc_v2; struct smc_clc_msg_proposal *pclc; struct smc_clc_msg_decline *dclc; struct smc_clc_msg_trail *trl; @@ -51,29 +129,19 @@ static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm, bool check_trl) switch (clcm->type) { case SMC_CLC_PROPOSAL: pclc = (struct smc_clc_msg_proposal *)clcm; - pclc_prfx = smc_clc_proposal_get_prefix(pclc); - if (ntohs(pclc->hdr.length) < - sizeof(*pclc) + ntohs(pclc->iparea_offset) + - sizeof(*pclc_prfx) + - pclc_prfx->ipv6_prefixes_cnt * - sizeof(struct smc_clc_ipv6_prefix) + - sizeof(*trl)) + if (!smc_clc_msg_prop_valid(pclc)) return false; trl = (struct smc_clc_msg_trail *) ((u8 *)pclc + ntohs(pclc->hdr.length) - sizeof(*trl)); break; case SMC_CLC_ACCEPT: case SMC_CLC_CONFIRM: - if (clcm->path != SMC_TYPE_R && clcm->path != SMC_TYPE_D) - return false; - clc = (struct smc_clc_msg_accept_confirm *)clcm; - if ((clcm->path == SMC_TYPE_R && - ntohs(clc->hdr.length) != SMCR_CLC_ACCEPT_CONFIRM_LEN) || - (clcm->path == SMC_TYPE_D && - ntohs(clc->hdr.length) != SMCD_CLC_ACCEPT_CONFIRM_LEN)) + clc_v2 = (struct smc_clc_msg_accept_confirm_v2 *)clcm; + if (!smc_clc_msg_acc_conf_valid(clc_v2)) return false; trl = (struct smc_clc_msg_trail *) - ((u8 *)clc + ntohs(clc->hdr.length) - sizeof(*trl)); + ((u8 *)clc_v2 + ntohs(clc_v2->hdr.length) - + sizeof(*trl)); break; case SMC_CLC_DECLINE: dclc = (struct smc_clc_msg_decline *)clcm; @@ -153,7 +221,6 @@ static int smc_clc_prfx_set(struct socket *clcsock, struct sockaddr_in *addr; int rc = -ENOENT; - memset(prop, 0, sizeof(*prop)); if (!dst) { rc = -ENOTCONN; goto out; @@ -320,7 +387,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, } datlen = ntohs(clcm->length); if ((len < sizeof(struct smc_clc_msg_hdr)) || - (clcm->version < SMC_CLC_V1) || + (clcm->version < SMC_V1) || ((clcm->type != SMC_CLC_DECLINE) && (clcm->type != expected_type))) { smc->sk.sk_err = EPROTO; @@ -328,9 +395,6 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, goto out; } - if (clcm->type == SMC_CLC_PROPOSAL && clcm->path == SMC_TYPE_N) - reason_code = SMC_CLC_DECL_VERSMISMAT; /* just V2 offered */ - /* receive the complete CLC message */ memset(&msg, 0, sizeof(struct msghdr)); if (datlen > buflen) { @@ -366,7 +430,8 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, dclc = (struct smc_clc_msg_decline *)clcm; reason_code = SMC_CLC_DECL_PEERDECL; smc->peer_diagnosis = ntohl(dclc->peer_diagnosis); - if (((struct smc_clc_msg_decline *)buf)->hdr.flag) { + if (((struct smc_clc_msg_decline *)buf)->hdr.typev2 & + SMC_FIRST_CONTACT_MASK) { smc->conn.lgr->sync_err = 1; smc_lgr_terminate_sched(smc->conn.lgr); } @@ -378,7 +443,7 @@ out: } /* send CLC DECLINE message across internal TCP socket */ -int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info) +int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info, u8 version) { struct smc_clc_msg_decline dclc; struct msghdr msg; @@ -389,8 +454,10 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info) memcpy(dclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); dclc.hdr.type = SMC_CLC_DECLINE; dclc.hdr.length = htons(sizeof(struct smc_clc_msg_decline)); - dclc.hdr.version = SMC_CLC_V1; - dclc.hdr.flag = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? 1 : 0; + dclc.hdr.version = version; + dclc.os_type = version == SMC_V1 ? 0 : SMC_CLC_OS_LINUX; + dclc.hdr.typev2 = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? + SMC_FIRST_CONTACT_MASK : 0; if ((!smc->conn.lgr || !smc->conn.lgr->is_smcd) && smc_ib_is_valid_local_systemid()) memcpy(dclc.id_for_peer, local_systemid, @@ -409,142 +476,274 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info) } /* send CLC PROPOSAL message across internal TCP socket */ -int smc_clc_send_proposal(struct smc_sock *smc, int smc_type, - struct smc_init_info *ini) +int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) { - struct smc_clc_ipv6_prefix ipv6_prfx[SMC_CLC_MAX_V6_PREFIX]; - struct smc_clc_msg_proposal_prefix pclc_prfx; - struct smc_clc_msg_smcd pclc_smcd; - struct smc_clc_msg_proposal pclc; - struct smc_clc_msg_trail trl; + struct smc_clc_smcd_v2_extension *smcd_v2_ext; + struct smc_clc_msg_proposal_prefix *pclc_prfx; + struct smc_clc_msg_proposal *pclc_base; + struct smc_clc_smcd_gid_chid *gidchids; + struct smc_clc_msg_proposal_area *pclc; + struct smc_clc_ipv6_prefix *ipv6_prfx; + struct smc_clc_v2_extension *v2_ext; + struct smc_clc_msg_smcd *pclc_smcd; + struct smc_clc_msg_trail *trl; int len, i, plen, rc; int reason_code = 0; - struct kvec vec[5]; + struct kvec vec[8]; struct msghdr msg; + pclc = kzalloc(sizeof(*pclc), GFP_KERNEL); + if (!pclc) + return -ENOMEM; + + pclc_base = &pclc->pclc_base; + pclc_smcd = &pclc->pclc_smcd; + pclc_prfx = &pclc->pclc_prfx; + ipv6_prfx = pclc->pclc_prfx_ipv6; + v2_ext = &pclc->pclc_v2_ext; + smcd_v2_ext = &pclc->pclc_smcd_v2_ext; + gidchids = pclc->pclc_gidchids; + trl = &pclc->pclc_trl; + + pclc_base->hdr.version = SMC_V2; + pclc_base->hdr.typev1 = ini->smc_type_v1; + pclc_base->hdr.typev2 = ini->smc_type_v2; + plen = sizeof(*pclc_base) + sizeof(*pclc_smcd) + sizeof(*trl); + /* retrieve ip prefixes for CLC proposal msg */ - rc = smc_clc_prfx_set(smc->clcsock, &pclc_prfx, ipv6_prfx); - if (rc) - return SMC_CLC_DECL_CNFERR; /* configuration error */ + if (ini->smc_type_v1 != SMC_TYPE_N) { + rc = smc_clc_prfx_set(smc->clcsock, pclc_prfx, ipv6_prfx); + if (rc) { + if (ini->smc_type_v2 == SMC_TYPE_N) { + kfree(pclc); + return SMC_CLC_DECL_CNFERR; + } + pclc_base->hdr.typev1 = SMC_TYPE_N; + } else { + pclc_base->iparea_offset = htons(sizeof(*pclc_smcd)); + plen += sizeof(*pclc_prfx) + + pclc_prfx->ipv6_prefixes_cnt * + sizeof(ipv6_prfx[0]); + } + } - /* send SMC Proposal CLC message */ - plen = sizeof(pclc) + sizeof(pclc_prfx) + - (pclc_prfx.ipv6_prefixes_cnt * sizeof(ipv6_prfx[0])) + - sizeof(trl); - memset(&pclc, 0, sizeof(pclc)); - memcpy(pclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); - pclc.hdr.type = SMC_CLC_PROPOSAL; - pclc.hdr.version = SMC_CLC_V1; /* SMC version */ - pclc.hdr.path = smc_type; - if (smc_type == SMC_TYPE_R || smc_type == SMC_TYPE_B) { + /* build SMC Proposal CLC message */ + memcpy(pclc_base->hdr.eyecatcher, SMC_EYECATCHER, + sizeof(SMC_EYECATCHER)); + pclc_base->hdr.type = SMC_CLC_PROPOSAL; + if (smcr_indicated(ini->smc_type_v1)) { /* add SMC-R specifics */ - memcpy(pclc.lcl.id_for_peer, local_systemid, + memcpy(pclc_base->lcl.id_for_peer, local_systemid, sizeof(local_systemid)); - memcpy(&pclc.lcl.gid, ini->ib_gid, SMC_GID_SIZE); - memcpy(&pclc.lcl.mac, &ini->ib_dev->mac[ini->ib_port - 1], + memcpy(pclc_base->lcl.gid, ini->ib_gid, SMC_GID_SIZE); + memcpy(pclc_base->lcl.mac, &ini->ib_dev->mac[ini->ib_port - 1], ETH_ALEN); - pclc.iparea_offset = htons(0); } - if (smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B) { + if (smcd_indicated(ini->smc_type_v1)) { /* add SMC-D specifics */ - memset(&pclc_smcd, 0, sizeof(pclc_smcd)); - plen += sizeof(pclc_smcd); - pclc.iparea_offset = htons(SMC_CLC_PROPOSAL_MAX_OFFSET); - pclc_smcd.gid = ini->ism_dev->local_gid; + if (ini->ism_dev[0]) { + pclc_smcd->ism.gid = htonll(ini->ism_dev[0]->local_gid); + pclc_smcd->ism.chid = + htons(smc_ism_get_chid(ini->ism_dev[0])); + } + } + if (ini->smc_type_v2 == SMC_TYPE_N) { + pclc_smcd->v2_ext_offset = 0; + } else { + u16 v2_ext_offset; + u8 *eid = NULL; + + v2_ext_offset = sizeof(*pclc_smcd) - + offsetofend(struct smc_clc_msg_smcd, v2_ext_offset); + if (ini->smc_type_v1 != SMC_TYPE_N) + v2_ext_offset += sizeof(*pclc_prfx) + + pclc_prfx->ipv6_prefixes_cnt * + sizeof(ipv6_prfx[0]); + pclc_smcd->v2_ext_offset = htons(v2_ext_offset); + v2_ext->hdr.eid_cnt = 0; + v2_ext->hdr.ism_gid_cnt = ini->ism_offered_cnt; + v2_ext->hdr.flag.release = SMC_RELEASE; + v2_ext->hdr.flag.seid = 1; + v2_ext->hdr.smcd_v2_ext_offset = htons(sizeof(*v2_ext) - + offsetofend(struct smc_clnt_opts_area_hdr, + smcd_v2_ext_offset) + + v2_ext->hdr.eid_cnt * SMC_MAX_EID_LEN); + if (ini->ism_dev[0]) + smc_ism_get_system_eid(ini->ism_dev[0], &eid); + else + smc_ism_get_system_eid(ini->ism_dev[1], &eid); + if (eid) + memcpy(smcd_v2_ext->system_eid, eid, SMC_MAX_EID_LEN); + plen += sizeof(*v2_ext) + sizeof(*smcd_v2_ext); + if (ini->ism_offered_cnt) { + for (i = 1; i <= ini->ism_offered_cnt; i++) { + gidchids[i - 1].gid = + htonll(ini->ism_dev[i]->local_gid); + gidchids[i - 1].chid = + htons(smc_ism_get_chid(ini->ism_dev[i])); + } + plen += ini->ism_offered_cnt * + sizeof(struct smc_clc_smcd_gid_chid); + } } - pclc.hdr.length = htons(plen); + pclc_base->hdr.length = htons(plen); + memcpy(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); - memcpy(trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); + /* send SMC Proposal CLC message */ memset(&msg, 0, sizeof(msg)); i = 0; - vec[i].iov_base = &pclc; - vec[i++].iov_len = sizeof(pclc); - if (smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B) { - vec[i].iov_base = &pclc_smcd; - vec[i++].iov_len = sizeof(pclc_smcd); + vec[i].iov_base = pclc_base; + vec[i++].iov_len = sizeof(*pclc_base); + vec[i].iov_base = pclc_smcd; + vec[i++].iov_len = sizeof(*pclc_smcd); + if (ini->smc_type_v1 != SMC_TYPE_N) { + vec[i].iov_base = pclc_prfx; + vec[i++].iov_len = sizeof(*pclc_prfx); + if (pclc_prfx->ipv6_prefixes_cnt > 0) { + vec[i].iov_base = ipv6_prfx; + vec[i++].iov_len = pclc_prfx->ipv6_prefixes_cnt * + sizeof(ipv6_prfx[0]); + } } - vec[i].iov_base = &pclc_prfx; - vec[i++].iov_len = sizeof(pclc_prfx); - if (pclc_prfx.ipv6_prefixes_cnt > 0) { - vec[i].iov_base = &ipv6_prfx[0]; - vec[i++].iov_len = pclc_prfx.ipv6_prefixes_cnt * - sizeof(ipv6_prfx[0]); + if (ini->smc_type_v2 != SMC_TYPE_N) { + vec[i].iov_base = v2_ext; + vec[i++].iov_len = sizeof(*v2_ext); + vec[i].iov_base = smcd_v2_ext; + vec[i++].iov_len = sizeof(*smcd_v2_ext); + if (ini->ism_offered_cnt) { + vec[i].iov_base = gidchids; + vec[i++].iov_len = ini->ism_offered_cnt * + sizeof(struct smc_clc_smcd_gid_chid); + } } - vec[i].iov_base = &trl; - vec[i++].iov_len = sizeof(trl); + vec[i].iov_base = trl; + vec[i++].iov_len = sizeof(*trl); /* due to the few bytes needed for clc-handshake this cannot block */ len = kernel_sendmsg(smc->clcsock, &msg, vec, i, plen); if (len < 0) { smc->sk.sk_err = smc->clcsock->sk->sk_err; reason_code = -smc->sk.sk_err; - } else if (len < (int)sizeof(pclc)) { + } else if (len < ntohs(pclc_base->hdr.length)) { reason_code = -ENETUNREACH; smc->sk.sk_err = -reason_code; } + kfree(pclc); return reason_code; } -/* send CLC CONFIRM message across internal TCP socket */ -int smc_clc_send_confirm(struct smc_sock *smc) +/* build and send CLC CONFIRM / ACCEPT message */ +static int smc_clc_send_confirm_accept(struct smc_sock *smc, + struct smc_clc_msg_accept_confirm_v2 *clc_v2, + int first_contact, u8 version) { struct smc_connection *conn = &smc->conn; - struct smc_clc_msg_accept_confirm cclc; - struct smc_link *link; - int reason_code = 0; + struct smc_clc_msg_accept_confirm *clc; + struct smc_clc_first_contact_ext fce; + struct smc_clc_msg_trail trl; + struct kvec vec[3]; struct msghdr msg; - struct kvec vec; - int len; + int i, len; /* send SMC Confirm CLC msg */ - memset(&cclc, 0, sizeof(cclc)); - cclc.hdr.type = SMC_CLC_CONFIRM; - cclc.hdr.version = SMC_CLC_V1; /* SMC version */ - if (smc->conn.lgr->is_smcd) { + clc = (struct smc_clc_msg_accept_confirm *)clc_v2; + clc->hdr.version = version; /* SMC version */ + if (first_contact) + clc->hdr.typev2 |= SMC_FIRST_CONTACT_MASK; + if (conn->lgr->is_smcd) { /* SMC-D specific settings */ - memcpy(cclc.hdr.eyecatcher, SMCD_EYECATCHER, + memcpy(clc->hdr.eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_EYECATCHER)); - cclc.hdr.path = SMC_TYPE_D; - cclc.hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN); - cclc.gid = conn->lgr->smcd->local_gid; - cclc.token = conn->rmb_desc->token; - cclc.dmbe_size = conn->rmbe_size_short; - cclc.dmbe_idx = 0; - memcpy(&cclc.linkid, conn->lgr->id, SMC_LGR_ID_SIZE); - memcpy(cclc.smcd_trl.eyecatcher, SMCD_EYECATCHER, + clc->hdr.typev1 = SMC_TYPE_D; + clc->d0.gid = conn->lgr->smcd->local_gid; + clc->d0.token = conn->rmb_desc->token; + clc->d0.dmbe_size = conn->rmbe_size_short; + clc->d0.dmbe_idx = 0; + memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE); + if (version == SMC_V1) { + clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN); + } else { + u8 *eid = NULL; + + clc_v2->chid = htons(smc_ism_get_chid(conn->lgr->smcd)); + smc_ism_get_system_eid(conn->lgr->smcd, &eid); + if (eid) + memcpy(clc_v2->eid, eid, SMC_MAX_EID_LEN); + len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2; + if (first_contact) + smc_clc_fill_fce(&fce, &len); + clc_v2->hdr.length = htons(len); + } + memcpy(trl.eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_EYECATCHER)); } else { + struct smc_link *link = conn->lnk; + /* SMC-R specific settings */ link = conn->lnk; - memcpy(cclc.hdr.eyecatcher, SMC_EYECATCHER, + memcpy(clc->hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); - cclc.hdr.path = SMC_TYPE_R; - cclc.hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN); - memcpy(cclc.lcl.id_for_peer, local_systemid, + clc->hdr.typev1 = SMC_TYPE_R; + clc->hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN); + memcpy(clc->r0.lcl.id_for_peer, local_systemid, sizeof(local_systemid)); - memcpy(&cclc.lcl.gid, link->gid, SMC_GID_SIZE); - memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1], + memcpy(&clc->r0.lcl.gid, link->gid, SMC_GID_SIZE); + memcpy(&clc->r0.lcl.mac, &link->smcibdev->mac[link->ibport - 1], ETH_ALEN); - hton24(cclc.qpn, link->roce_qp->qp_num); - cclc.rmb_rkey = + hton24(clc->r0.qpn, link->roce_qp->qp_num); + clc->r0.rmb_rkey = htonl(conn->rmb_desc->mr_rx[link->link_idx]->rkey); - cclc.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */ - cclc.rmbe_alert_token = htonl(conn->alert_token_local); - cclc.qp_mtu = min(link->path_mtu, link->peer_mtu); - cclc.rmbe_size = conn->rmbe_size_short; - cclc.rmb_dma_addr = cpu_to_be64((u64)sg_dma_address + clc->r0.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */ + clc->r0.rmbe_alert_token = htonl(conn->alert_token_local); + switch (clc->hdr.type) { + case SMC_CLC_ACCEPT: + clc->r0.qp_mtu = link->path_mtu; + break; + case SMC_CLC_CONFIRM: + clc->r0.qp_mtu = min(link->path_mtu, link->peer_mtu); + break; + } + clc->r0.rmbe_size = conn->rmbe_size_short; + clc->r0.rmb_dma_addr = cpu_to_be64((u64)sg_dma_address (conn->rmb_desc->sgt[link->link_idx].sgl)); - hton24(cclc.psn, link->psn_initial); - memcpy(cclc.smcr_trl.eyecatcher, SMC_EYECATCHER, - sizeof(SMC_EYECATCHER)); + hton24(clc->r0.psn, link->psn_initial); + memcpy(trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); } memset(&msg, 0, sizeof(msg)); - vec.iov_base = &cclc; - vec.iov_len = ntohs(cclc.hdr.length); - len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1, - ntohs(cclc.hdr.length)); - if (len < ntohs(cclc.hdr.length)) { + i = 0; + vec[i].iov_base = clc_v2; + if (version > SMC_V1) + vec[i++].iov_len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 - sizeof(trl); + else + vec[i++].iov_len = (clc->hdr.typev1 == SMC_TYPE_D ? + SMCD_CLC_ACCEPT_CONFIRM_LEN : + SMCR_CLC_ACCEPT_CONFIRM_LEN) - + sizeof(trl); + if (version > SMC_V1 && first_contact) { + vec[i].iov_base = &fce; + vec[i++].iov_len = sizeof(fce); + } + vec[i].iov_base = &trl; + vec[i++].iov_len = sizeof(trl); + return kernel_sendmsg(smc->clcsock, &msg, vec, 1, + ntohs(clc->hdr.length)); +} + +/* send CLC CONFIRM message across internal TCP socket */ +int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, + u8 version) +{ + struct smc_clc_msg_accept_confirm_v2 cclc_v2; + int reason_code = 0; + int len; + + /* send SMC Confirm CLC msg */ + memset(&cclc_v2, 0, sizeof(cclc_v2)); + cclc_v2.hdr.type = SMC_CLC_CONFIRM; + len = smc_clc_send_confirm_accept(smc, &cclc_v2, clnt_first_contact, + version); + if (len < ntohs(cclc_v2.hdr.length)) { if (len >= 0) { reason_code = -ENETUNREACH; smc->sk.sk_err = -reason_code; @@ -557,67 +756,28 @@ int smc_clc_send_confirm(struct smc_sock *smc) } /* send CLC ACCEPT message across internal TCP socket */ -int smc_clc_send_accept(struct smc_sock *new_smc, int srv_first_contact) +int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact, + u8 version) { - struct smc_connection *conn = &new_smc->conn; - struct smc_clc_msg_accept_confirm aclc; - struct smc_link *link; - struct msghdr msg; - struct kvec vec; + struct smc_clc_msg_accept_confirm_v2 aclc_v2; int len; - memset(&aclc, 0, sizeof(aclc)); - aclc.hdr.type = SMC_CLC_ACCEPT; - aclc.hdr.version = SMC_CLC_V1; /* SMC version */ - if (srv_first_contact) - aclc.hdr.flag = 1; - - if (new_smc->conn.lgr->is_smcd) { - /* SMC-D specific settings */ - aclc.hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN); - memcpy(aclc.hdr.eyecatcher, SMCD_EYECATCHER, - sizeof(SMCD_EYECATCHER)); - aclc.hdr.path = SMC_TYPE_D; - aclc.gid = conn->lgr->smcd->local_gid; - aclc.token = conn->rmb_desc->token; - aclc.dmbe_size = conn->rmbe_size_short; - aclc.dmbe_idx = 0; - memcpy(&aclc.linkid, conn->lgr->id, SMC_LGR_ID_SIZE); - memcpy(aclc.smcd_trl.eyecatcher, SMCD_EYECATCHER, - sizeof(SMCD_EYECATCHER)); - } else { - /* SMC-R specific settings */ - aclc.hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN); - memcpy(aclc.hdr.eyecatcher, SMC_EYECATCHER, - sizeof(SMC_EYECATCHER)); - aclc.hdr.path = SMC_TYPE_R; - link = conn->lnk; - memcpy(aclc.lcl.id_for_peer, local_systemid, - sizeof(local_systemid)); - memcpy(&aclc.lcl.gid, link->gid, SMC_GID_SIZE); - memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1], - ETH_ALEN); - hton24(aclc.qpn, link->roce_qp->qp_num); - aclc.rmb_rkey = - htonl(conn->rmb_desc->mr_rx[link->link_idx]->rkey); - aclc.rmbe_idx = 1; /* as long as 1 RMB = 1 RMBE */ - aclc.rmbe_alert_token = htonl(conn->alert_token_local); - aclc.qp_mtu = link->path_mtu; - aclc.rmbe_size = conn->rmbe_size_short, - aclc.rmb_dma_addr = cpu_to_be64((u64)sg_dma_address - (conn->rmb_desc->sgt[link->link_idx].sgl)); - hton24(aclc.psn, link->psn_initial); - memcpy(aclc.smcr_trl.eyecatcher, SMC_EYECATCHER, - sizeof(SMC_EYECATCHER)); - } - - memset(&msg, 0, sizeof(msg)); - vec.iov_base = &aclc; - vec.iov_len = ntohs(aclc.hdr.length); - len = kernel_sendmsg(new_smc->clcsock, &msg, &vec, 1, - ntohs(aclc.hdr.length)); - if (len < ntohs(aclc.hdr.length)) + memset(&aclc_v2, 0, sizeof(aclc_v2)); + aclc_v2.hdr.type = SMC_CLC_ACCEPT; + len = smc_clc_send_confirm_accept(new_smc, &aclc_v2, srv_first_contact, + version); + if (len < ntohs(aclc_v2.hdr.length)) len = len >= 0 ? -EPROTO : -new_smc->clcsock->sk->sk_err; return len > 0 ? 0 : len; } + +void __init smc_clc_init(void) +{ + struct new_utsname *u; + + memset(smc_hostname, _S, sizeof(smc_hostname)); /* ASCII blanks */ + u = utsname(); + memcpy(smc_hostname, u->nodename, + min_t(size_t, strlen(u->nodename), sizeof(smc_hostname))); +} diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index cf7b45306f4e..b3f46ab79e47 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -22,7 +22,6 @@ #define SMC_CLC_CONFIRM 0x03 #define SMC_CLC_DECLINE 0x04 -#define SMC_CLC_V1 0x1 /* SMC version */ #define SMC_TYPE_R 0 /* SMC-R only */ #define SMC_TYPE_D 1 /* SMC-D only */ #define SMC_TYPE_N 2 /* neither SMC-R nor SMC-D */ @@ -38,7 +37,6 @@ #define SMC_CLC_DECL_NOSMCDEV 0x03030000 /* no SMC device found (R or D) */ #define SMC_CLC_DECL_NOSMCDDEV 0x03030001 /* no SMC-D device found */ #define SMC_CLC_DECL_NOSMCRDEV 0x03030002 /* no SMC-R device found */ -#define SMC_CLC_DECL_SMCDNOTALK 0x03030003 /* SMC-D dev can't talk to peer */ #define SMC_CLC_DECL_MODEUNSUPP 0x03040000 /* smc modes do not match (R or D)*/ #define SMC_CLC_DECL_RMBE_EC 0x03050000 /* peer has eyecatcher in RMBE */ #define SMC_CLC_DECL_OPTUNSUPP 0x03060000 /* fastopen sockopt not supported */ @@ -56,19 +54,19 @@ #define SMC_CLC_DECL_ERR_RDYLNK 0x09990002 /* ib ready link failed */ #define SMC_CLC_DECL_ERR_REGRMB 0x09990003 /* reg rmb failed */ +#define SMC_FIRST_CONTACT_MASK 0b10 /* first contact bit within typev2 */ + struct smc_clc_msg_hdr { /* header1 of clc messages */ u8 eyecatcher[4]; /* eye catcher */ u8 type; /* proposal / accept / confirm / decline */ __be16 length; #if defined(__BIG_ENDIAN_BITFIELD) u8 version : 4, - flag : 1, - rsvd : 1, - path : 2; + typev2 : 2, + typev1 : 2; #elif defined(__LITTLE_ENDIAN_BITFIELD) - u8 path : 2, - rsvd : 1, - flag : 1, + u8 typev1 : 2, + typev2 : 2, version : 4; #endif } __packed; /* format defined in RFC7609 */ @@ -83,8 +81,6 @@ struct smc_clc_msg_local { /* header2 of clc messages */ u8 mac[6]; /* mac of ib_device port */ }; -#define SMC_CLC_MAX_V6_PREFIX 8 - /* Struct would be 4 byte aligned, but it is used in an array that is sent * to peers and must conform to RFC7609, hence we need to use packed here. */ @@ -93,6 +89,44 @@ struct smc_clc_ipv6_prefix { u8 prefix_len; } __packed; /* format defined in RFC7609 */ +#if defined(__BIG_ENDIAN_BITFIELD) +struct smc_clc_v2_flag { + u8 release : 4, + rsvd : 3, + seid : 1; +}; +#elif defined(__LITTLE_ENDIAN_BITFIELD) +struct smc_clc_v2_flag { + u8 seid : 1, + rsvd : 3, + release : 4; +}; +#endif + +struct smc_clnt_opts_area_hdr { + u8 eid_cnt; /* number of user defined EIDs */ + u8 ism_gid_cnt; /* number of ISMv2 GIDs */ + u8 reserved1; + struct smc_clc_v2_flag flag; + u8 reserved2[2]; + __be16 smcd_v2_ext_offset; /* SMC-Dv2 Extension Offset */ +}; + +struct smc_clc_smcd_gid_chid { + __be64 gid; /* ISM GID */ + __be16 chid; /* ISMv2 CHID */ +} __packed; /* format defined in + * IBM Shared Memory Communications Version 2 + * (https://www.ibm.com/support/pages/node/6326337) + */ + +struct smc_clc_v2_extension { + struct smc_clnt_opts_area_hdr hdr; + u8 roce[16]; /* RoCEv2 GID */ + u8 reserved[16]; + u8 user_eids[0][SMC_MAX_EID_LEN]; +}; + struct smc_clc_msg_proposal_prefix { /* prefix part of clc proposal message*/ __be32 outgoing_subnet; /* subnet mask */ u8 prefix_len; /* number of significant bits in mask */ @@ -101,8 +135,15 @@ struct smc_clc_msg_proposal_prefix { /* prefix part of clc proposal message*/ } __aligned(4); struct smc_clc_msg_smcd { /* SMC-D GID information */ - u64 gid; /* ISM GID of requestor */ - u8 res[32]; + struct smc_clc_smcd_gid_chid ism; /* ISM native GID+CHID of requestor */ + __be16 v2_ext_offset; /* SMC Version 2 Extension Offset */ + u8 reserved[28]; +}; + +struct smc_clc_smcd_v2_extension { + u8 system_eid[SMC_MAX_EID_LEN]; + u8 reserved[16]; + struct smc_clc_smcd_gid_chid gidchid[0]; }; struct smc_clc_msg_proposal { /* clc proposal message sent by Linux */ @@ -111,64 +152,107 @@ struct smc_clc_msg_proposal { /* clc proposal message sent by Linux */ __be16 iparea_offset; /* offset to IP address information area */ } __aligned(4); -#define SMC_CLC_PROPOSAL_MAX_OFFSET 0x28 -#define SMC_CLC_PROPOSAL_MAX_PREFIX (SMC_CLC_MAX_V6_PREFIX * \ - sizeof(struct smc_clc_ipv6_prefix)) -#define SMC_CLC_MAX_LEN (sizeof(struct smc_clc_msg_proposal) + \ - SMC_CLC_PROPOSAL_MAX_OFFSET + \ - sizeof(struct smc_clc_msg_proposal_prefix) + \ - SMC_CLC_PROPOSAL_MAX_PREFIX + \ - sizeof(struct smc_clc_msg_trail)) +#define SMC_CLC_MAX_V6_PREFIX 8 -struct smc_clc_msg_accept_confirm { /* clc accept / confirm message */ - struct smc_clc_msg_hdr hdr; - union { - struct { /* SMC-R */ - struct smc_clc_msg_local lcl; - u8 qpn[3]; /* QP number */ - __be32 rmb_rkey; /* RMB rkey */ - u8 rmbe_idx; /* Index of RMBE in RMB */ - __be32 rmbe_alert_token;/* unique connection id */ +struct smc_clc_msg_proposal_area { + struct smc_clc_msg_proposal pclc_base; + struct smc_clc_msg_smcd pclc_smcd; + struct smc_clc_msg_proposal_prefix pclc_prfx; + struct smc_clc_ipv6_prefix pclc_prfx_ipv6[SMC_CLC_MAX_V6_PREFIX]; + struct smc_clc_v2_extension pclc_v2_ext; + struct smc_clc_smcd_v2_extension pclc_smcd_v2_ext; + struct smc_clc_smcd_gid_chid pclc_gidchids[SMC_MAX_ISM_DEVS]; + struct smc_clc_msg_trail pclc_trl; +}; + +struct smcr_clc_msg_accept_confirm { /* SMCR accept/confirm */ + struct smc_clc_msg_local lcl; + u8 qpn[3]; /* QP number */ + __be32 rmb_rkey; /* RMB rkey */ + u8 rmbe_idx; /* Index of RMBE in RMB */ + __be32 rmbe_alert_token; /* unique connection id */ + #if defined(__BIG_ENDIAN_BITFIELD) + u8 rmbe_size : 4, /* buf size (compressed) */ + qp_mtu : 4; /* QP mtu */ +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u8 qp_mtu : 4, + rmbe_size : 4; +#endif + u8 reserved; + __be64 rmb_dma_addr; /* RMB virtual address */ + u8 reserved2; + u8 psn[3]; /* packet sequence number */ +} __packed; + +struct smcd_clc_msg_accept_confirm_common { /* SMCD accept/confirm */ + u64 gid; /* Sender GID */ + u64 token; /* DMB token */ + u8 dmbe_idx; /* DMBE index */ #if defined(__BIG_ENDIAN_BITFIELD) - u8 rmbe_size : 4, /* buf size (compressed) */ - qp_mtu : 4; /* QP mtu */ + u8 dmbe_size : 4, /* buf size (compressed) */ + reserved3 : 4; #elif defined(__LITTLE_ENDIAN_BITFIELD) - u8 qp_mtu : 4, - rmbe_size : 4; + u8 reserved3 : 4, + dmbe_size : 4; #endif - u8 reserved; - __be64 rmb_dma_addr; /* RMB virtual address */ - u8 reserved2; - u8 psn[3]; /* packet sequence number */ - struct smc_clc_msg_trail smcr_trl; - /* eye catcher "SMCR" EBCDIC */ - } __packed; - struct { /* SMC-D */ - u64 gid; /* Sender GID */ - u64 token; /* DMB token */ - u8 dmbe_idx; /* DMBE index */ + u16 reserved4; + __be32 linkid; /* Link identifier */ +} __packed; + +#define SMC_CLC_OS_ZOS 1 +#define SMC_CLC_OS_LINUX 2 +#define SMC_CLC_OS_AIX 3 + +struct smc_clc_first_contact_ext { + u8 reserved1; #if defined(__BIG_ENDIAN_BITFIELD) - u8 dmbe_size : 4, /* buf size (compressed) */ - reserved3 : 4; + u8 os_type : 4, + release : 4; #elif defined(__LITTLE_ENDIAN_BITFIELD) - u8 reserved3 : 4, - dmbe_size : 4; + u8 release : 4, + os_type : 4; #endif - u16 reserved4; - u32 linkid; /* Link identifier */ + u8 reserved2[2]; + u8 hostname[SMC_MAX_HOSTNAME_LEN]; +}; + +struct smc_clc_msg_accept_confirm { /* clc accept / confirm message */ + struct smc_clc_msg_hdr hdr; + union { + struct smcr_clc_msg_accept_confirm r0; /* SMC-R */ + struct { /* SMC-D */ + struct smcd_clc_msg_accept_confirm_common d0; u32 reserved5[3]; - struct smc_clc_msg_trail smcd_trl; - /* eye catcher "SMCD" EBCDIC */ - } __packed; + }; }; } __packed; /* format defined in RFC7609 */ +struct smc_clc_msg_accept_confirm_v2 { /* clc accept / confirm message */ + struct smc_clc_msg_hdr hdr; + union { + struct smcr_clc_msg_accept_confirm r0; /* SMC-R */ + struct { /* SMC-D */ + struct smcd_clc_msg_accept_confirm_common d0; + __be16 chid; + u8 eid[SMC_MAX_EID_LEN]; + u8 reserved5[8]; + }; + }; +}; + struct smc_clc_msg_decline { /* clc decline message */ struct smc_clc_msg_hdr hdr; u8 id_for_peer[SMC_SYSTEMID_LEN]; /* sender peer_id */ __be32 peer_diagnosis; /* diagnosis information */ - u8 reserved2[4]; - struct smc_clc_msg_trail trl; /* eye catcher "SMCR" EBCDIC */ +#if defined(__BIG_ENDIAN_BITFIELD) + u8 os_type : 4, + reserved : 4; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u8 reserved : 4, + os_type : 4; +#endif + u8 reserved2[3]; + struct smc_clc_msg_trail trl; /* eye catcher "SMCD" or "SMCR" EBCDIC */ } __aligned(4); /* determine start of the prefix area within the proposal message */ @@ -179,16 +263,58 @@ smc_clc_proposal_get_prefix(struct smc_clc_msg_proposal *pclc) ((u8 *)pclc + sizeof(*pclc) + ntohs(pclc->iparea_offset)); } +static inline bool smcr_indicated(int smc_type) +{ + return smc_type == SMC_TYPE_R || smc_type == SMC_TYPE_B; +} + +static inline bool smcd_indicated(int smc_type) +{ + return smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B; +} + /* get SMC-D info from proposal message */ static inline struct smc_clc_msg_smcd * smc_get_clc_msg_smcd(struct smc_clc_msg_proposal *prop) { - if (ntohs(prop->iparea_offset) != sizeof(struct smc_clc_msg_smcd)) + if (smcd_indicated(prop->hdr.typev1) && + ntohs(prop->iparea_offset) != sizeof(struct smc_clc_msg_smcd)) return NULL; return (struct smc_clc_msg_smcd *)(prop + 1); } +static inline struct smc_clc_v2_extension * +smc_get_clc_v2_ext(struct smc_clc_msg_proposal *prop) +{ + struct smc_clc_msg_smcd *prop_smcd = smc_get_clc_msg_smcd(prop); + + if (!prop_smcd || !ntohs(prop_smcd->v2_ext_offset)) + return NULL; + + return (struct smc_clc_v2_extension *) + ((u8 *)prop_smcd + + offsetof(struct smc_clc_msg_smcd, v2_ext_offset) + + sizeof(prop_smcd->v2_ext_offset) + + ntohs(prop_smcd->v2_ext_offset)); +} + +static inline struct smc_clc_smcd_v2_extension * +smc_get_clc_smcd_v2_ext(struct smc_clc_v2_extension *prop_v2ext) +{ + if (!prop_v2ext) + return NULL; + if (!ntohs(prop_v2ext->hdr.smcd_v2_ext_offset)) + return NULL; + + return (struct smc_clc_smcd_v2_extension *) + ((u8 *)prop_v2ext + + offsetof(struct smc_clc_v2_extension, hdr) + + offsetof(struct smc_clnt_opts_area_hdr, smcd_v2_ext_offset) + + sizeof(prop_v2ext->hdr.smcd_v2_ext_offset) + + ntohs(prop_v2ext->hdr.smcd_v2_ext_offset)); +} + struct smcd_dev; struct smc_init_info; @@ -196,10 +322,12 @@ int smc_clc_prfx_match(struct socket *clcsock, struct smc_clc_msg_proposal_prefix *prop); int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, u8 expected_type, unsigned long timeout); -int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info); -int smc_clc_send_proposal(struct smc_sock *smc, int smc_type, - struct smc_init_info *ini); -int smc_clc_send_confirm(struct smc_sock *smc); -int smc_clc_send_accept(struct smc_sock *smc, int srv_first_contact); +int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info, u8 version); +int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini); +int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, + u8 version); +int smc_clc_send_accept(struct smc_sock *smc, bool srv_first_contact, + u8 version); +void smc_clc_init(void) __init; #endif diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 0e7409e469c0..0f9ffba07d26 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -210,9 +210,9 @@ again: sk->sk_state = SMC_CLOSED; sk->sk_state_change(sk); /* wake up accept */ if (smc->clcsock && smc->clcsock->sk) { + smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready; + smc->clcsock->sk->sk_user_data = NULL; rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); - /* wake up kernel_accept of smc_tcp_listen_worker */ - smc->clcsock->sk->sk_data_ready(smc->clcsock->sk); } smc_close_cleanup_listen(sk); release_sock(sk); diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index a406627b1d55..2b19863f7171 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -34,7 +34,6 @@ #define SMC_LGR_NUM_INCR 256 #define SMC_LGR_FREE_DELAY_SERV (600 * HZ) #define SMC_LGR_FREE_DELAY_CLNT (SMC_LGR_FREE_DELAY_SERV + 10 * HZ) -#define SMC_LGR_FREE_DELAY_FAST (8 * HZ) static struct smc_lgr_list smc_lgr_list = { /* established link groups */ .lock = __SPIN_LOCK_UNLOCKED(smc_lgr_list.lock), @@ -70,7 +69,7 @@ static void smc_lgr_schedule_free_work(struct smc_link_group *lgr) * creation. For client use a somewhat higher removal delay time, * otherwise there is a risk of out-of-sync link groups. */ - if (!lgr->freeing && !lgr->freefast) { + if (!lgr->freeing) { mod_delayed_work(system_wq, &lgr->free_work, (!lgr->is_smcd && lgr->role == SMC_CLNT) ? SMC_LGR_FREE_DELAY_CLNT : @@ -78,15 +77,6 @@ static void smc_lgr_schedule_free_work(struct smc_link_group *lgr) } } -void smc_lgr_schedule_free_work_fast(struct smc_link_group *lgr) -{ - if (!lgr->freeing && !lgr->freefast) { - lgr->freefast = 1; - mod_delayed_work(system_wq, &lgr->free_work, - SMC_LGR_FREE_DELAY_FAST); - } -} - /* Register connection's alert token in our lookup structure. * To use rbtrees we have to implement our own insert core. * Requires @conns_lock @@ -227,7 +217,7 @@ void smc_lgr_cleanup_early(struct smc_connection *conn) if (!list_empty(lgr_list)) list_del_init(lgr_list); spin_unlock_bh(lgr_lock); - smc_lgr_schedule_free_work_fast(lgr); + __smc_lgr_terminate(lgr, true); } static void smcr_lgr_link_deactivate_all(struct smc_link_group *lgr) @@ -385,7 +375,8 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) int i; if (ini->is_smcd && ini->vlan_id) { - if (smc_ism_get_vlan(ini->ism_dev, ini->vlan_id)) { + if (smc_ism_get_vlan(ini->ism_dev[ini->ism_selected], + ini->vlan_id)) { rc = SMC_CLC_DECL_ISMVLANERR; goto out; } @@ -396,10 +387,15 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) rc = SMC_CLC_DECL_MEM; goto ism_put_vlan; } + lgr->tx_wq = alloc_workqueue("smc_tx_wq-%*phN", 0, 0, + SMC_LGR_ID_SIZE, &lgr->id); + if (!lgr->tx_wq) { + rc = -ENOMEM; + goto free_lgr; + } lgr->is_smcd = ini->is_smcd; lgr->sync_err = 0; lgr->terminating = 0; - lgr->freefast = 0; lgr->freeing = 0; lgr->vlan_id = ini->vlan_id; mutex_init(&lgr->sndbufs_lock); @@ -417,13 +413,14 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) lgr->conns_all = RB_ROOT; if (ini->is_smcd) { /* SMC-D specific settings */ - get_device(&ini->ism_dev->dev); - lgr->peer_gid = ini->ism_gid; - lgr->smcd = ini->ism_dev; - lgr_list = &ini->ism_dev->lgr_list; + get_device(&ini->ism_dev[ini->ism_selected]->dev); + lgr->peer_gid = ini->ism_peer_gid[ini->ism_selected]; + lgr->smcd = ini->ism_dev[ini->ism_selected]; + lgr_list = &ini->ism_dev[ini->ism_selected]->lgr_list; lgr_lock = &lgr->smcd->lgr_lock; + lgr->smc_version = ini->smcd_version; lgr->peer_shutdown = 0; - atomic_inc(&ini->ism_dev->lgr_cnt); + atomic_inc(&ini->ism_dev[ini->ism_selected]->lgr_cnt); } else { /* SMC-R specific settings */ lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT; @@ -437,7 +434,7 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) lnk = &lgr->lnk[link_idx]; rc = smcr_link_init(lgr, lnk, link_idx, ini); if (rc) - goto free_lgr; + goto free_wq; lgr_list = &smc_lgr_list.list; lgr_lock = &smc_lgr_list.lock; atomic_inc(&lgr_cnt); @@ -448,11 +445,13 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) spin_unlock_bh(lgr_lock); return 0; +free_wq: + destroy_workqueue(lgr->tx_wq); free_lgr: kfree(lgr); ism_put_vlan: if (ini->is_smcd && ini->vlan_id) - smc_ism_put_vlan(ini->ism_dev, ini->vlan_id); + smc_ism_put_vlan(ini->ism_dev[ini->ism_selected], ini->vlan_id); out: if (rc < 0) { if (rc == -ENOMEM) @@ -517,7 +516,7 @@ static int smc_switch_cursor(struct smc_sock *smc, struct smc_cdc_tx_pend *pend, smc->sk.sk_state != SMC_CLOSED) { rc = smcr_cdc_msg_send_validation(conn, pend, wr_buf); if (!rc) { - schedule_delayed_work(&conn->tx_work, 0); + queue_delayed_work(conn->lgr->tx_wq, &conn->tx_work, 0); smc->sk.sk_data_ready(&smc->sk); } } else { @@ -824,11 +823,10 @@ static void smc_lgr_free(struct smc_link_group *lgr) } smc_lgr_free_bufs(lgr); + destroy_workqueue(lgr->tx_wq); if (lgr->is_smcd) { - if (!lgr->terminating) { - smc_ism_put_vlan(lgr->smcd, lgr->vlan_id); - put_device(&lgr->smcd->dev); - } + smc_ism_put_vlan(lgr->smcd, lgr->vlan_id); + put_device(&lgr->smcd->dev); if (!atomic_dec_return(&lgr->smcd->lgr_cnt)) wake_up(&lgr->smcd->lgrs_deleted); } else { @@ -889,8 +887,6 @@ static void smc_lgr_cleanup(struct smc_link_group *lgr) if (lgr->is_smcd) { smc_ism_signal_shutdown(lgr); smcd_unregister_all_dmbs(lgr); - smc_ism_put_vlan(lgr->smcd, lgr->vlan_id); - put_device(&lgr->smcd->dev); } else { u32 rsn = lgr->llc_termination_rsn; @@ -1294,11 +1290,13 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini) spinlock_t *lgr_lock; int rc = 0; - lgr_list = ini->is_smcd ? &ini->ism_dev->lgr_list : &smc_lgr_list.list; - lgr_lock = ini->is_smcd ? &ini->ism_dev->lgr_lock : &smc_lgr_list.lock; - ini->cln_first_contact = SMC_FIRST_CONTACT; + lgr_list = ini->is_smcd ? &ini->ism_dev[ini->ism_selected]->lgr_list : + &smc_lgr_list.list; + lgr_lock = ini->is_smcd ? &ini->ism_dev[ini->ism_selected]->lgr_lock : + &smc_lgr_list.lock; + ini->first_contact_local = 1; role = smc->listen_smc ? SMC_SERV : SMC_CLNT; - if (role == SMC_CLNT && ini->srv_first_contact) + if (role == SMC_CLNT && ini->first_contact_peer) /* create new link group as well */ goto create; @@ -1307,14 +1305,15 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini) list_for_each_entry(lgr, lgr_list, list) { write_lock_bh(&lgr->conns_lock); if ((ini->is_smcd ? - smcd_lgr_match(lgr, ini->ism_dev, ini->ism_gid) : + smcd_lgr_match(lgr, ini->ism_dev[ini->ism_selected], + ini->ism_peer_gid[ini->ism_selected]) : smcr_lgr_match(lgr, ini->ib_lcl, role, ini->ib_clcqpn)) && !lgr->sync_err && lgr->vlan_id == ini->vlan_id && (role == SMC_CLNT || ini->is_smcd || lgr->conns_num < SMC_RMBS_PER_LGR_MAX)) { /* link group found */ - ini->cln_first_contact = SMC_REUSE_CONTACT; + ini->first_contact_local = 0; conn->lgr = lgr; rc = smc_lgr_register_conn(conn, false); write_unlock_bh(&lgr->conns_lock); @@ -1328,8 +1327,8 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini) if (rc) return rc; - if (role == SMC_CLNT && !ini->srv_first_contact && - ini->cln_first_contact == SMC_FIRST_CONTACT) { + if (role == SMC_CLNT && !ini->first_contact_peer && + ini->first_contact_local) { /* Server reuses a link group, but Client wants to start * a new one * send out_of_sync decline, reason synchr. error @@ -1338,7 +1337,7 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini) } create: - if (ini->cln_first_contact == SMC_FIRST_CONTACT) { + if (ini->first_contact_local) { rc = smc_lgr_create(smc, ini); if (rc) goto out; @@ -1597,7 +1596,7 @@ out: return rc; } -#define SMCD_DMBE_SIZES 7 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */ +#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) @@ -1616,7 +1615,11 @@ static struct smc_buf_desc *smcd_new_buf_create(struct smc_link_group *lgr, rc = smc_ism_register_dmb(lgr, bufsize, buf_desc); if (rc) { kfree(buf_desc); - return (rc == -ENOMEM) ? ERR_PTR(-EAGAIN) : ERR_PTR(rc); + if (rc == -ENOMEM) + return ERR_PTR(-EAGAIN); + if (rc == -ENOSPC) + return ERR_PTR(-ENOSPC); + return ERR_PTR(-EIO); } buf_desc->pages = virt_to_page(buf_desc->cpu_addr); /* CDC header stored in buf. So, pretend it was smaller */ @@ -1892,8 +1895,8 @@ int smc_rmb_rtoken_handling(struct smc_connection *conn, struct smc_link *lnk, struct smc_clc_msg_accept_confirm *clc) { - conn->rtoken_idx = smc_rtoken_add(lnk, clc->rmb_dma_addr, - clc->rmb_rkey); + conn->rtoken_idx = smc_rtoken_add(lnk, clc->r0.rmb_dma_addr, + clc->r0.rmb_rkey); if (conn->rtoken_idx < 0) return conn->rtoken_idx; return 0; diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 1c4d5439d0ff..f1e867ce2e63 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -137,9 +137,6 @@ struct smc_link { #define SMC_LINKS_PER_LGR_MAX 3 #define SMC_SINGLE_LINK 0 -#define SMC_FIRST_CONTACT 1 /* first contact to a peer */ -#define SMC_REUSE_CONTACT 0 /* follow-on contact to a peer*/ - /* tx/rx buffer list element for sndbufs list and rmbs list of a lgr */ struct smc_buf_desc { struct list_head list; @@ -228,12 +225,17 @@ struct smc_link_group { u8 id[SMC_LGR_ID_SIZE]; /* unique lgr id */ struct delayed_work free_work; /* delayed freeing of an lgr */ struct work_struct terminate_work; /* abnormal lgr termination */ + struct workqueue_struct *tx_wq; /* wq for conn. tx workers */ u8 sync_err : 1; /* lgr no longer fits to peer */ u8 terminating : 1;/* lgr is terminating */ - u8 freefast : 1; /* free worker scheduled fast */ u8 freeing : 1; /* lgr is being freed */ bool is_smcd; /* SMC-R or SMC-D */ + u8 smc_version; + u8 negotiated_eid[SMC_MAX_EID_LEN]; + u8 peer_os; /* peer operating system */ + u8 peer_smc_release; + u8 peer_hostname[SMC_MAX_HOSTNAME_LEN]; union { struct { /* SMC-R */ enum smc_lgr_role role; @@ -294,9 +296,11 @@ struct smc_clc_msg_local; struct smc_init_info { u8 is_smcd; + u8 smc_type_v1; + u8 smc_type_v2; + u8 first_contact_peer; + u8 first_contact_local; unsigned short vlan_id; - int srv_first_contact; - int cln_first_contact; /* SMC-R */ struct smc_clc_msg_local *ib_lcl; struct smc_ib_device *ib_dev; @@ -304,8 +308,12 @@ struct smc_init_info { u8 ib_port; u32 ib_clcqpn; /* SMC-D */ - u64 ism_gid; - struct smcd_dev *ism_dev; + u64 ism_peer_gid[SMC_MAX_ISM_DEVS + 1]; + struct smcd_dev *ism_dev[SMC_MAX_ISM_DEVS + 1]; + u16 ism_chid[SMC_MAX_ISM_DEVS + 1]; + u8 ism_offered_cnt; /* # of ISM devices offered */ + u8 ism_selected; /* index of selected ISM dev*/ + u8 smcd_version; }; /* Find the connection associated with the given alert token in the link group. diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index da9ba6d1679b..f15fca59b4b2 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -22,6 +22,15 @@ #include "smc.h" #include "smc_core.h" +struct smc_diag_dump_ctx { + int pos[2]; +}; + +static struct smc_diag_dump_ctx *smc_dump_context(struct netlink_callback *cb) +{ + return (struct smc_diag_dump_ctx *)cb->ctx; +} + static void smc_gid_be16_convert(__u8 *buf, u8 *gid_raw) { sprintf(buf, "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x", @@ -193,13 +202,15 @@ errout: } static int smc_diag_dump_proto(struct proto *prot, struct sk_buff *skb, - struct netlink_callback *cb) + struct netlink_callback *cb, int p_type) { + struct smc_diag_dump_ctx *cb_ctx = smc_dump_context(cb); struct net *net = sock_net(skb->sk); + int snum = cb_ctx->pos[p_type]; struct nlattr *bc = NULL; struct hlist_head *head; + int rc = 0, num = 0; struct sock *sk; - int rc = 0; read_lock(&prot->h.smc_hash->lock); head = &prot->h.smc_hash->ht; @@ -209,13 +220,18 @@ static int smc_diag_dump_proto(struct proto *prot, struct sk_buff *skb, sk_for_each(sk, head) { if (!net_eq(sock_net(sk), net)) continue; + if (num < snum) + goto next; rc = __smc_diag_dump(sk, skb, cb, nlmsg_data(cb->nlh), bc); - if (rc) - break; + if (rc < 0) + goto out; +next: + num++; } out: read_unlock(&prot->h.smc_hash->lock); + cb_ctx->pos[p_type] = num; return rc; } @@ -223,10 +239,10 @@ static int smc_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) { int rc = 0; - rc = smc_diag_dump_proto(&smc_proto, skb, cb); + rc = smc_diag_dump_proto(&smc_proto, skb, cb, SMCPROTO_SMC); if (!rc) - rc = smc_diag_dump_proto(&smc_proto6, skb, cb); - return rc; + smc_diag_dump_proto(&smc_proto6, skb, cb, SMCPROTO_SMC6); + return skb->len; } static int smc_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c index 998c525de785..6abbdd09a580 100644 --- a/net/smc/smc_ism.c +++ b/net/smc/smc_ism.c @@ -21,7 +21,9 @@ struct smcd_dev_list smcd_dev_list = { .mutex = __MUTEX_INITIALIZER(smcd_dev_list.mutex) }; -/* Test if an ISM communication is possible. */ +bool smc_ism_v2_capable; + +/* Test if an ISM communication is possible - same CPC */ int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *smcd) { return smcd->ops->query_remote_gid(smcd, peer_gid, vlan_id ? 1 : 0, @@ -39,6 +41,16 @@ int smc_ism_write(struct smcd_dev *smcd, const struct smc_ism_position *pos, return rc < 0 ? rc : 0; } +void smc_ism_get_system_eid(struct smcd_dev *smcd, u8 **eid) +{ + smcd->ops->get_system_eid(smcd, eid); +} + +u16 smc_ism_get_chid(struct smcd_dev *smcd) +{ + return smcd->ops->get_chid(smcd); +} + /* Set a connection using this DMBE. */ void smc_ism_set_conn(struct smc_connection *conn) { @@ -319,7 +331,18 @@ EXPORT_SYMBOL_GPL(smcd_alloc_dev); int smcd_register_dev(struct smcd_dev *smcd) { mutex_lock(&smcd_dev_list.mutex); - list_add_tail(&smcd->list, &smcd_dev_list.list); + if (list_empty(&smcd_dev_list.list)) { + u8 *system_eid = NULL; + + smc_ism_get_system_eid(smcd, &system_eid); + if (system_eid[24] != '0' || system_eid[28] != '0') + smc_ism_v2_capable = true; + } + /* sort list: devices without pnetid before devices with pnetid */ + if (smcd->pnetid[0]) + list_add_tail(&smcd->list, &smcd_dev_list.list); + else + list_add(&smcd->list, &smcd_dev_list.list); mutex_unlock(&smcd_dev_list.mutex); pr_warn_ratelimited("smc: adding smcd device %s with pnetid %.16s%s\n", @@ -399,3 +422,8 @@ void smcd_handle_irq(struct smcd_dev *smcd, unsigned int dmbno) spin_unlock_irqrestore(&smcd->lock, flags); } EXPORT_SYMBOL_GPL(smcd_handle_irq); + +void __init smc_ism_init(void) +{ + smc_ism_v2_capable = false; +} diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h index 81cc4537efd3..8048e09ddcf8 100644 --- a/net/smc/smc_ism.h +++ b/net/smc/smc_ism.h @@ -19,7 +19,10 @@ struct smcd_dev_list { /* List of SMCD devices */ struct mutex mutex; /* Protects list of devices */ }; -extern struct smcd_dev_list smcd_dev_list; /* list of smcd devices */ +extern struct smcd_dev_list smcd_dev_list; /* list of smcd devices */ +extern bool smc_ism_v2_capable; /* HW supports ISM V2 and thus + * System EID is defined + */ struct smc_ism_vlanid { /* VLAN id set on ISM device */ struct list_head list; @@ -47,4 +50,7 @@ int smc_ism_unregister_dmb(struct smcd_dev *dev, struct smc_buf_desc *dmb_desc); int smc_ism_write(struct smcd_dev *dev, const struct smc_ism_position *pos, void *data, size_t len); int smc_ism_signal_shutdown(struct smc_link_group *lgr); +void smc_ism_get_system_eid(struct smcd_dev *dev, u8 **eid); +u16 smc_ism_get_chid(struct smcd_dev *dev); +void smc_ism_init(void); #endif diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 3ea33466ebe9..273eaf1bfe49 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -233,8 +233,6 @@ static bool smc_llc_flow_start(struct smc_llc_flow *flow, default: flow->type = SMC_LLC_FLOW_NONE; } - if (qentry == lgr->delayed_event) - lgr->delayed_event = NULL; smc_llc_flow_qentry_set(flow, qentry); spin_unlock_bh(&lgr->llc_flow_lock); return true; @@ -1209,7 +1207,7 @@ static void smc_llc_process_srv_add_link(struct smc_link_group *lgr) /* enqueue a local add_link req to trigger a new add_link flow */ void smc_llc_add_link_local(struct smc_link *link) { - struct smc_llc_msg_add_link add_llc = {0}; + struct smc_llc_msg_add_link add_llc = {}; add_llc.hd.length = sizeof(add_llc); add_llc.hd.common.type = SMC_LLC_ADD_LINK; @@ -1242,7 +1240,7 @@ out: */ void smc_llc_srv_delete_link_local(struct smc_link *link, u8 del_link_id) { - struct smc_llc_msg_del_link del_llc = {0}; + struct smc_llc_msg_del_link del_llc = {}; del_llc.hd.length = sizeof(del_llc); del_llc.hd.common.type = SMC_LLC_DELETE_LINK; @@ -1314,7 +1312,7 @@ out: */ void smc_llc_send_link_delete_all(struct smc_link_group *lgr, bool ord, u32 rsn) { - struct smc_llc_msg_del_link delllc = {0}; + struct smc_llc_msg_del_link delllc = {}; int i; delllc.hd.common.type = SMC_LLC_DELETE_LINK; @@ -1603,13 +1601,12 @@ static void smc_llc_event_work(struct work_struct *work) struct smc_llc_qentry *qentry; if (!lgr->llc_flow_lcl.type && lgr->delayed_event) { - if (smc_link_usable(lgr->delayed_event->link)) { - smc_llc_event_handler(lgr->delayed_event); - } else { - qentry = lgr->delayed_event; - lgr->delayed_event = NULL; + qentry = lgr->delayed_event; + lgr->delayed_event = NULL; + if (smc_link_usable(qentry->link)) + smc_llc_event_handler(qentry); + else kfree(qentry); - } } again: @@ -1691,7 +1688,7 @@ static void smc_llc_enqueue(struct smc_link *link, union smc_llc_msg *llc) spin_lock_irqsave(&lgr->llc_event_q_lock, flags); list_add_tail(&qentry->list, &lgr->llc_event_q); spin_unlock_irqrestore(&lgr->llc_event_q_lock, flags); - schedule_work(&lgr->llc_event_work); + queue_work(system_highpri_wq, &lgr->llc_event_work); } /* copy received msg and add it to the event queue */ diff --git a/net/smc/smc_netns.h b/net/smc/smc_netns.h index e7a8fc4ae02f..0f4f35aa43ad 100644 --- a/net/smc/smc_netns.h +++ b/net/smc/smc_netns.h @@ -16,5 +16,6 @@ extern unsigned int smc_net_id; /* per-network namespace private data */ struct smc_net { struct smc_pnettable pnettable; + struct smc_pnetids_ndev pnetids_ndev; }; #endif diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 30e5fac7034e..f3c18b991d35 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -29,8 +29,7 @@ #include "smc_ism.h" #include "smc_core.h" -#define SMC_ASCII_BLANK 32 - +static struct net_device *__pnet_find_base_ndev(struct net_device *ndev); static struct net_device *pnet_find_base_ndev(struct net_device *ndev); static const struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = { @@ -73,14 +72,22 @@ struct smc_pnetentry { }; }; +/* Check if the pnetid is set */ +bool smc_pnet_is_pnetid_set(u8 *pnetid) +{ + if (pnetid[0] == 0 || pnetid[0] == _S) + return false; + return true; +} + /* Check if two given pnetids match */ static bool smc_pnet_match(u8 *pnetid1, u8 *pnetid2) { int i; for (i = 0; i < SMC_MAX_PNETID_LEN; i++) { - if ((pnetid1[i] == 0 || pnetid1[i] == SMC_ASCII_BLANK) && - (pnetid2[i] == 0 || pnetid2[i] == SMC_ASCII_BLANK)) + if ((pnetid1[i] == 0 || pnetid1[i] == _S) && + (pnetid2[i] == 0 || pnetid2[i] == _S)) break; if (pnetid1[i] != pnetid2[i]) return false; @@ -238,11 +245,10 @@ static int smc_pnet_remove_by_ndev(struct net_device *ndev) static bool smc_pnet_apply_ib(struct smc_ib_device *ib_dev, u8 ib_port, char *pnet_name) { - u8 pnet_null[SMC_MAX_PNETID_LEN] = {0}; bool applied = false; mutex_lock(&smc_ib_devices.mutex); - if (smc_pnet_match(ib_dev->pnetid[ib_port - 1], pnet_null)) { + if (!smc_pnet_is_pnetid_set(ib_dev->pnetid[ib_port - 1])) { memcpy(ib_dev->pnetid[ib_port - 1], pnet_name, SMC_MAX_PNETID_LEN); ib_dev->pnetid_by_user[ib_port - 1] = true; @@ -256,11 +262,10 @@ static bool smc_pnet_apply_ib(struct smc_ib_device *ib_dev, u8 ib_port, */ static bool smc_pnet_apply_smcd(struct smcd_dev *smcd_dev, char *pnet_name) { - u8 pnet_null[SMC_MAX_PNETID_LEN] = {0}; bool applied = false; mutex_lock(&smcd_dev_list.mutex); - if (smc_pnet_match(smcd_dev->pnetid, pnet_null)) { + if (!smc_pnet_is_pnetid_set(smcd_dev->pnetid)) { memcpy(smcd_dev->pnetid, pnet_name, SMC_MAX_PNETID_LEN); smcd_dev->pnetid_by_user = true; applied = true; @@ -708,10 +713,115 @@ static struct genl_family smc_pnet_nl_family __ro_after_init = { .n_ops = ARRAY_SIZE(smc_pnet_ops) }; +bool smc_pnet_is_ndev_pnetid(struct net *net, u8 *pnetid) +{ + struct smc_net *sn = net_generic(net, smc_net_id); + struct smc_pnetids_ndev_entry *pe; + bool rc = false; + + read_lock(&sn->pnetids_ndev.lock); + list_for_each_entry(pe, &sn->pnetids_ndev.list, list) { + if (smc_pnet_match(pnetid, pe->pnetid)) { + rc = true; + goto unlock; + } + } + +unlock: + read_unlock(&sn->pnetids_ndev.lock); + return rc; +} + +static int smc_pnet_add_pnetid(struct net *net, u8 *pnetid) +{ + struct smc_net *sn = net_generic(net, smc_net_id); + struct smc_pnetids_ndev_entry *pe, *pi; + + pe = kzalloc(sizeof(*pe), GFP_KERNEL); + if (!pe) + return -ENOMEM; + + write_lock(&sn->pnetids_ndev.lock); + list_for_each_entry(pi, &sn->pnetids_ndev.list, list) { + if (smc_pnet_match(pnetid, pe->pnetid)) { + refcount_inc(&pi->refcnt); + kfree(pe); + goto unlock; + } + } + refcount_set(&pe->refcnt, 1); + memcpy(pe->pnetid, pnetid, SMC_MAX_PNETID_LEN); + list_add_tail(&pe->list, &sn->pnetids_ndev.list); + +unlock: + write_unlock(&sn->pnetids_ndev.lock); + return 0; +} + +static void smc_pnet_remove_pnetid(struct net *net, u8 *pnetid) +{ + struct smc_net *sn = net_generic(net, smc_net_id); + struct smc_pnetids_ndev_entry *pe, *pe2; + + write_lock(&sn->pnetids_ndev.lock); + list_for_each_entry_safe(pe, pe2, &sn->pnetids_ndev.list, list) { + if (smc_pnet_match(pnetid, pe->pnetid)) { + if (refcount_dec_and_test(&pe->refcnt)) { + list_del(&pe->list); + kfree(pe); + } + break; + } + } + write_unlock(&sn->pnetids_ndev.lock); +} + +static void smc_pnet_add_base_pnetid(struct net *net, struct net_device *dev, + u8 *ndev_pnetid) +{ + struct net_device *base_dev; + + base_dev = __pnet_find_base_ndev(dev); + if (base_dev->flags & IFF_UP && + !smc_pnetid_by_dev_port(base_dev->dev.parent, base_dev->dev_port, + ndev_pnetid)) { + /* add to PNETIDs list */ + smc_pnet_add_pnetid(net, ndev_pnetid); + } +} + +/* create initial list of netdevice pnetids */ +static void smc_pnet_create_pnetids_list(struct net *net) +{ + u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; + struct net_device *dev; + + rtnl_lock(); + for_each_netdev(net, dev) + smc_pnet_add_base_pnetid(net, dev, ndev_pnetid); + rtnl_unlock(); +} + +/* clean up list of netdevice pnetids */ +static void smc_pnet_destroy_pnetids_list(struct net *net) +{ + struct smc_net *sn = net_generic(net, smc_net_id); + struct smc_pnetids_ndev_entry *pe, *temp_pe; + + write_lock(&sn->pnetids_ndev.lock); + list_for_each_entry_safe(pe, temp_pe, &sn->pnetids_ndev.list, list) { + list_del(&pe->list); + kfree(pe); + } + write_unlock(&sn->pnetids_ndev.lock); +} + static int smc_pnet_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); + struct net *net = dev_net(event_dev); + u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; switch (event) { case NETDEV_REBOOT: @@ -721,6 +831,17 @@ static int smc_pnet_netdev_event(struct notifier_block *this, case NETDEV_REGISTER: smc_pnet_add_by_ndev(event_dev); return NOTIFY_OK; + case NETDEV_UP: + smc_pnet_add_base_pnetid(net, event_dev, ndev_pnetid); + return NOTIFY_OK; + case NETDEV_DOWN: + event_dev = __pnet_find_base_ndev(event_dev); + if (!smc_pnetid_by_dev_port(event_dev->dev.parent, + event_dev->dev_port, ndev_pnetid)) { + /* remove from PNETIDs list */ + smc_pnet_remove_pnetid(net, ndev_pnetid); + } + return NOTIFY_OK; default: return NOTIFY_DONE; } @@ -735,9 +856,14 @@ int smc_pnet_net_init(struct net *net) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnettable *pnettable = &sn->pnettable; + struct smc_pnetids_ndev *pnetids_ndev = &sn->pnetids_ndev; INIT_LIST_HEAD(&pnettable->pnetlist); rwlock_init(&pnettable->lock); + INIT_LIST_HEAD(&pnetids_ndev->list); + rwlock_init(&pnetids_ndev->lock); + + smc_pnet_create_pnetids_list(net); return 0; } @@ -752,6 +878,7 @@ int __init smc_pnet_init(void) rc = register_netdevice_notifier(&smc_netdev_notifier); if (rc) genl_unregister_family(&smc_pnet_nl_family); + return rc; } @@ -760,6 +887,7 @@ void smc_pnet_net_exit(struct net *net) { /* flush pnet table */ smc_pnet_remove_by_pnetid(net, NULL); + smc_pnet_destroy_pnetids_list(net); } void smc_pnet_exit(void) @@ -768,16 +896,11 @@ void smc_pnet_exit(void) genl_unregister_family(&smc_pnet_nl_family); } -/* Determine one base device for stacked net devices. - * If the lower device level contains more than one devices - * (for instance with bonding slaves), just the first device - * is used to reach a base device. - */ -static struct net_device *pnet_find_base_ndev(struct net_device *ndev) +static struct net_device *__pnet_find_base_ndev(struct net_device *ndev) { int i, nest_lvl; - rtnl_lock(); + ASSERT_RTNL(); nest_lvl = ndev->lower_level; for (i = 0; i < nest_lvl; i++) { struct list_head *lower = &ndev->adj_list.lower; @@ -787,6 +910,18 @@ static struct net_device *pnet_find_base_ndev(struct net_device *ndev) lower = lower->next; ndev = netdev_lower_get_next(ndev, &lower); } + return ndev; +} + +/* Determine one base device for stacked net devices. + * If the lower device level contains more than one devices + * (for instance with bonding slaves), just the first device + * is used to reach a base device. + */ +static struct net_device *pnet_find_base_ndev(struct net_device *ndev) +{ + rtnl_lock(); + ndev = __pnet_find_base_ndev(ndev); rtnl_unlock(); return ndev; } @@ -928,8 +1063,11 @@ static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev, mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(ismdev, &smcd_dev_list.list, list) { if (smc_pnet_match(ismdev->pnetid, ndev_pnetid) && - !ismdev->going_away) { - ini->ism_dev = ismdev; + !ismdev->going_away && + (!ini->ism_peer_gid[0] || + !smc_ism_cantalk(ini->ism_peer_gid[0], ini->vlan_id, + ismdev))) { + ini->ism_dev[0] = ismdev; break; } } @@ -963,7 +1101,7 @@ void smc_pnet_find_ism_resource(struct sock *sk, struct smc_init_info *ini) { struct dst_entry *dst = sk_dst_get(sk); - ini->ism_dev = NULL; + ini->ism_dev[0] = NULL; if (!dst) goto out; if (!dst->dev) diff --git a/net/smc/smc_pnet.h b/net/smc/smc_pnet.h index 811a65986691..14039272f7e4 100644 --- a/net/smc/smc_pnet.h +++ b/net/smc/smc_pnet.h @@ -12,6 +12,8 @@ #ifndef _SMC_PNET_H #define _SMC_PNET_H +#include <net/smc.h> + #if IS_ENABLED(CONFIG_HAVE_PNETID) #include <asm/pnet.h> #endif @@ -31,6 +33,17 @@ struct smc_pnettable { struct list_head pnetlist; }; +struct smc_pnetids_ndev { /* list of pnetids for net devices in UP state*/ + struct list_head list; + rwlock_t lock; +}; + +struct smc_pnetids_ndev_entry { + struct list_head list; + u8 pnetid[SMC_MAX_PNETID_LEN]; + refcount_t refcnt; +}; + static inline int smc_pnetid_by_dev_port(struct device *dev, unsigned short port, u8 *pnetid) { @@ -52,4 +65,6 @@ int smc_pnetid_by_table_smcd(struct smcd_dev *smcd); void smc_pnet_find_alt_roce(struct smc_link_group *lgr, struct smc_init_info *ini, struct smc_ib_device *known_dev); +bool smc_pnet_is_ndev_pnetid(struct net *net, u8 *pnetid); +bool smc_pnet_is_pnetid_set(u8 *pnetid); #endif diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index 54ba0443847e..4532c16bf85e 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -228,8 +228,8 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len) /* for a corked socket defer the RDMA writes if there * is still sufficient sndbuf_space available */ - schedule_delayed_work(&conn->tx_work, - SMC_TX_CORK_DELAY); + queue_delayed_work(conn->lgr->tx_wq, &conn->tx_work, + SMC_TX_CORK_DELAY); else smc_tx_sndbuf_nonempty(conn); } /* while (msg_data_left(msg)) */ @@ -499,7 +499,7 @@ static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) if (conn->killed) return -EPIPE; rc = 0; - mod_delayed_work(system_wq, &conn->tx_work, + mod_delayed_work(conn->lgr->tx_wq, &conn->tx_work, SMC_TX_WORK_DELAY); } return rc; @@ -623,8 +623,8 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force) return; if ((smc_cdc_get_slot_and_msg_send(conn) < 0) && !conn->killed) { - schedule_delayed_work(&conn->tx_work, - SMC_TX_WORK_DELAY); + queue_delayed_work(conn->lgr->tx_wq, &conn->tx_work, + SMC_TX_WORK_DELAY); return; } } diff --git a/net/socket.c b/net/socket.c index 58cac2da5f66..6e6cccc2104f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2628,9 +2628,11 @@ long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg, struct user_msghdr __user *umsg, struct sockaddr __user *uaddr, unsigned int flags) { - /* disallow ancillary data requests from this path */ - if (msg->msg_control || msg->msg_controllen) - return -EINVAL; + if (msg->msg_control || msg->msg_controllen) { + /* disallow ancillary data reqs unless cmsg is plain data */ + if (!(sock->ops->flags & PROTO_CMSG_DATA_ONLY)) + return -EINVAL; + } return ____sys_recvmsg(sock, msg, umsg, uaddr, flags, 0); } diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig index 3bcf985507be..bbbb5af0af13 100644 --- a/net/sunrpc/Kconfig +++ b/net/sunrpc/Kconfig @@ -21,7 +21,6 @@ config RPCSEC_GSS_KRB5 depends on SUNRPC && CRYPTO depends on CRYPTO_MD5 && CRYPTO_DES && CRYPTO_CBC && CRYPTO_CTS depends on CRYPTO_ECB && CRYPTO_HMAC && CRYPTO_SHA1 && CRYPTO_AES - depends on CRYPTO_ARC4 default y select SUNRPC_GSS help diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 794fb3001880..634b6c6e0dcb 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -138,135 +138,6 @@ checksummer(struct scatterlist *sg, void *data) return crypto_ahash_update(req); } -static int -arcfour_hmac_md5_usage_to_salt(unsigned int usage, u8 salt[4]) -{ - unsigned int ms_usage; - - switch (usage) { - case KG_USAGE_SIGN: - ms_usage = 15; - break; - case KG_USAGE_SEAL: - ms_usage = 13; - break; - default: - return -EINVAL; - } - salt[0] = (ms_usage >> 0) & 0xff; - salt[1] = (ms_usage >> 8) & 0xff; - salt[2] = (ms_usage >> 16) & 0xff; - salt[3] = (ms_usage >> 24) & 0xff; - - return 0; -} - -static u32 -make_checksum_hmac_md5(struct krb5_ctx *kctx, char *header, int hdrlen, - struct xdr_buf *body, int body_offset, u8 *cksumkey, - unsigned int usage, struct xdr_netobj *cksumout) -{ - struct scatterlist sg[1]; - int err = -1; - u8 *checksumdata; - u8 *rc4salt; - struct crypto_ahash *md5; - struct crypto_ahash *hmac_md5; - struct ahash_request *req; - - if (cksumkey == NULL) - return GSS_S_FAILURE; - - if (cksumout->len < kctx->gk5e->cksumlength) { - dprintk("%s: checksum buffer length, %u, too small for %s\n", - __func__, cksumout->len, kctx->gk5e->name); - return GSS_S_FAILURE; - } - - rc4salt = kmalloc_array(4, sizeof(*rc4salt), GFP_NOFS); - if (!rc4salt) - return GSS_S_FAILURE; - - if (arcfour_hmac_md5_usage_to_salt(usage, rc4salt)) { - dprintk("%s: invalid usage value %u\n", __func__, usage); - goto out_free_rc4salt; - } - - checksumdata = kmalloc(GSS_KRB5_MAX_CKSUM_LEN, GFP_NOFS); - if (!checksumdata) - goto out_free_rc4salt; - - md5 = crypto_alloc_ahash("md5", 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(md5)) - goto out_free_cksum; - - hmac_md5 = crypto_alloc_ahash(kctx->gk5e->cksum_name, 0, - CRYPTO_ALG_ASYNC); - if (IS_ERR(hmac_md5)) - goto out_free_md5; - - req = ahash_request_alloc(md5, GFP_NOFS); - if (!req) - goto out_free_hmac_md5; - - ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL); - - err = crypto_ahash_init(req); - if (err) - goto out; - sg_init_one(sg, rc4salt, 4); - ahash_request_set_crypt(req, sg, NULL, 4); - err = crypto_ahash_update(req); - if (err) - goto out; - - sg_init_one(sg, header, hdrlen); - ahash_request_set_crypt(req, sg, NULL, hdrlen); - err = crypto_ahash_update(req); - if (err) - goto out; - err = xdr_process_buf(body, body_offset, body->len - body_offset, - checksummer, req); - if (err) - goto out; - ahash_request_set_crypt(req, NULL, checksumdata, 0); - err = crypto_ahash_final(req); - if (err) - goto out; - - ahash_request_free(req); - req = ahash_request_alloc(hmac_md5, GFP_NOFS); - if (!req) - goto out_free_hmac_md5; - - ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL); - - err = crypto_ahash_setkey(hmac_md5, cksumkey, kctx->gk5e->keylength); - if (err) - goto out; - - sg_init_one(sg, checksumdata, crypto_ahash_digestsize(md5)); - ahash_request_set_crypt(req, sg, checksumdata, - crypto_ahash_digestsize(md5)); - err = crypto_ahash_digest(req); - if (err) - goto out; - - memcpy(cksumout->data, checksumdata, kctx->gk5e->cksumlength); - cksumout->len = kctx->gk5e->cksumlength; -out: - ahash_request_free(req); -out_free_hmac_md5: - crypto_free_ahash(hmac_md5); -out_free_md5: - crypto_free_ahash(md5); -out_free_cksum: - kfree(checksumdata); -out_free_rc4salt: - kfree(rc4salt); - return err ? GSS_S_FAILURE : 0; -} - /* * checksum the plaintext data and hdrlen bytes of the token header * The checksum is performed over the first 8 bytes of the @@ -284,11 +155,6 @@ make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen, u8 *checksumdata; unsigned int checksumlen; - if (kctx->gk5e->ctype == CKSUMTYPE_HMAC_MD5_ARCFOUR) - return make_checksum_hmac_md5(kctx, header, hdrlen, - body, body_offset, - cksumkey, usage, cksumout); - if (cksumout->len < kctx->gk5e->cksumlength) { dprintk("%s: checksum buffer length, %u, too small for %s\n", __func__, cksumout->len, kctx->gk5e->name); @@ -942,145 +808,3 @@ out_err: ret = GSS_S_FAILURE; return ret; } - -/* - * Compute Kseq given the initial session key and the checksum. - * Set the key of the given cipher. - */ -int -krb5_rc4_setup_seq_key(struct krb5_ctx *kctx, - struct crypto_sync_skcipher *cipher, - unsigned char *cksum) -{ - struct crypto_shash *hmac; - struct shash_desc *desc; - u8 Kseq[GSS_KRB5_MAX_KEYLEN]; - u32 zeroconstant = 0; - int err; - - dprintk("%s: entered\n", __func__); - - hmac = crypto_alloc_shash(kctx->gk5e->cksum_name, 0, 0); - if (IS_ERR(hmac)) { - dprintk("%s: error %ld, allocating hash '%s'\n", - __func__, PTR_ERR(hmac), kctx->gk5e->cksum_name); - return PTR_ERR(hmac); - } - - desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(hmac), - GFP_NOFS); - if (!desc) { - dprintk("%s: failed to allocate shash descriptor for '%s'\n", - __func__, kctx->gk5e->cksum_name); - crypto_free_shash(hmac); - return -ENOMEM; - } - - desc->tfm = hmac; - - /* Compute intermediate Kseq from session key */ - err = crypto_shash_setkey(hmac, kctx->Ksess, kctx->gk5e->keylength); - if (err) - goto out_err; - - err = crypto_shash_digest(desc, (u8 *)&zeroconstant, 4, Kseq); - if (err) - goto out_err; - - /* Compute final Kseq from the checksum and intermediate Kseq */ - err = crypto_shash_setkey(hmac, Kseq, kctx->gk5e->keylength); - if (err) - goto out_err; - - err = crypto_shash_digest(desc, cksum, 8, Kseq); - if (err) - goto out_err; - - err = crypto_sync_skcipher_setkey(cipher, Kseq, kctx->gk5e->keylength); - if (err) - goto out_err; - - err = 0; - -out_err: - kfree_sensitive(desc); - crypto_free_shash(hmac); - dprintk("%s: returning %d\n", __func__, err); - return err; -} - -/* - * Compute Kcrypt given the initial session key and the plaintext seqnum. - * Set the key of cipher kctx->enc. - */ -int -krb5_rc4_setup_enc_key(struct krb5_ctx *kctx, - struct crypto_sync_skcipher *cipher, - s32 seqnum) -{ - struct crypto_shash *hmac; - struct shash_desc *desc; - u8 Kcrypt[GSS_KRB5_MAX_KEYLEN]; - u8 zeroconstant[4] = {0}; - u8 seqnumarray[4]; - int err, i; - - dprintk("%s: entered, seqnum %u\n", __func__, seqnum); - - hmac = crypto_alloc_shash(kctx->gk5e->cksum_name, 0, 0); - if (IS_ERR(hmac)) { - dprintk("%s: error %ld, allocating hash '%s'\n", - __func__, PTR_ERR(hmac), kctx->gk5e->cksum_name); - return PTR_ERR(hmac); - } - - desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(hmac), - GFP_NOFS); - if (!desc) { - dprintk("%s: failed to allocate shash descriptor for '%s'\n", - __func__, kctx->gk5e->cksum_name); - crypto_free_shash(hmac); - return -ENOMEM; - } - - desc->tfm = hmac; - - /* Compute intermediate Kcrypt from session key */ - for (i = 0; i < kctx->gk5e->keylength; i++) - Kcrypt[i] = kctx->Ksess[i] ^ 0xf0; - - err = crypto_shash_setkey(hmac, Kcrypt, kctx->gk5e->keylength); - if (err) - goto out_err; - - err = crypto_shash_digest(desc, zeroconstant, 4, Kcrypt); - if (err) - goto out_err; - - /* Compute final Kcrypt from the seqnum and intermediate Kcrypt */ - err = crypto_shash_setkey(hmac, Kcrypt, kctx->gk5e->keylength); - if (err) - goto out_err; - - seqnumarray[0] = (unsigned char) ((seqnum >> 24) & 0xff); - seqnumarray[1] = (unsigned char) ((seqnum >> 16) & 0xff); - seqnumarray[2] = (unsigned char) ((seqnum >> 8) & 0xff); - seqnumarray[3] = (unsigned char) ((seqnum >> 0) & 0xff); - - err = crypto_shash_digest(desc, seqnumarray, 4, Kcrypt); - if (err) - goto out_err; - - err = crypto_sync_skcipher_setkey(cipher, Kcrypt, - kctx->gk5e->keylength); - if (err) - goto out_err; - - err = 0; - -out_err: - kfree_sensitive(desc); - crypto_free_shash(hmac); - dprintk("%s: returning %d\n", __func__, err); - return err; -} diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index a84a5b289484..ae9acf3a7389 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -52,27 +52,6 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = { }, #endif /* CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES */ /* - * RC4-HMAC - */ - { - .etype = ENCTYPE_ARCFOUR_HMAC, - .ctype = CKSUMTYPE_HMAC_MD5_ARCFOUR, - .name = "rc4-hmac", - .encrypt_name = "ecb(arc4)", - .cksum_name = "hmac(md5)", - .encrypt = krb5_encrypt, - .decrypt = krb5_decrypt, - .mk_key = NULL, - .signalg = SGN_ALG_HMAC_MD5, - .sealalg = SEAL_ALG_MICROSOFT_RC4, - .keybytes = 16, - .keylength = 16, - .blocksize = 1, - .conflen = 8, - .cksumlength = 8, - .keyed_cksum = 1, - }, - /* * 3DES */ { @@ -401,78 +380,6 @@ out_err: return -EINVAL; } -/* - * Note that RC4 depends on deriving keys using the sequence - * number or the checksum of a token. Therefore, the final keys - * cannot be calculated until the token is being constructed! - */ -static int -context_derive_keys_rc4(struct krb5_ctx *ctx) -{ - struct crypto_shash *hmac; - char sigkeyconstant[] = "signaturekey"; - int slen = strlen(sigkeyconstant) + 1; /* include null terminator */ - struct shash_desc *desc; - int err; - - dprintk("RPC: %s: entered\n", __func__); - /* - * derive cksum (aka Ksign) key - */ - hmac = crypto_alloc_shash(ctx->gk5e->cksum_name, 0, 0); - if (IS_ERR(hmac)) { - dprintk("%s: error %ld allocating hash '%s'\n", - __func__, PTR_ERR(hmac), ctx->gk5e->cksum_name); - err = PTR_ERR(hmac); - goto out_err; - } - - err = crypto_shash_setkey(hmac, ctx->Ksess, ctx->gk5e->keylength); - if (err) - goto out_err_free_hmac; - - - desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(hmac), GFP_NOFS); - if (!desc) { - dprintk("%s: failed to allocate hash descriptor for '%s'\n", - __func__, ctx->gk5e->cksum_name); - err = -ENOMEM; - goto out_err_free_hmac; - } - - desc->tfm = hmac; - - err = crypto_shash_digest(desc, sigkeyconstant, slen, ctx->cksum); - kfree_sensitive(desc); - if (err) - goto out_err_free_hmac; - /* - * allocate hash, and skciphers for data and seqnum encryption - */ - ctx->enc = crypto_alloc_sync_skcipher(ctx->gk5e->encrypt_name, 0, 0); - if (IS_ERR(ctx->enc)) { - err = PTR_ERR(ctx->enc); - goto out_err_free_hmac; - } - - ctx->seq = crypto_alloc_sync_skcipher(ctx->gk5e->encrypt_name, 0, 0); - if (IS_ERR(ctx->seq)) { - crypto_free_sync_skcipher(ctx->enc); - err = PTR_ERR(ctx->seq); - goto out_err_free_hmac; - } - - dprintk("RPC: %s: returning success\n", __func__); - - err = 0; - -out_err_free_hmac: - crypto_free_shash(hmac); -out_err: - dprintk("RPC: %s: returning %d\n", __func__, err); - return err; -} - static int context_derive_keys_new(struct krb5_ctx *ctx, gfp_t gfp_mask) { @@ -649,8 +556,6 @@ gss_import_v2_context(const void *p, const void *end, struct krb5_ctx *ctx, switch (ctx->enctype) { case ENCTYPE_DES3_CBC_RAW: return context_derive_keys_des3(ctx, gfp_mask); - case ENCTYPE_ARCFOUR_HMAC: - return context_derive_keys_rc4(ctx); case ENCTYPE_AES128_CTS_HMAC_SHA1_96: case ENCTYPE_AES256_CTS_HMAC_SHA1_96: return context_derive_keys_new(ctx, gfp_mask); diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c index f1d280accf43..33061417ec97 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seal.c +++ b/net/sunrpc/auth_gss/gss_krb5_seal.c @@ -214,7 +214,6 @@ gss_get_mic_kerberos(struct gss_ctx *gss_ctx, struct xdr_buf *text, BUG(); case ENCTYPE_DES_CBC_RAW: case ENCTYPE_DES3_CBC_RAW: - case ENCTYPE_ARCFOUR_HMAC: return gss_get_mic_v1(ctx, text, token); case ENCTYPE_AES128_CTS_HMAC_SHA1_96: case ENCTYPE_AES256_CTS_HMAC_SHA1_96: diff --git a/net/sunrpc/auth_gss/gss_krb5_seqnum.c b/net/sunrpc/auth_gss/gss_krb5_seqnum.c index 507105127095..fb117817ff5d 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seqnum.c +++ b/net/sunrpc/auth_gss/gss_krb5_seqnum.c @@ -39,42 +39,6 @@ # define RPCDBG_FACILITY RPCDBG_AUTH #endif -static s32 -krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum, - unsigned char *cksum, unsigned char *buf) -{ - struct crypto_sync_skcipher *cipher; - unsigned char *plain; - s32 code; - - dprintk("RPC: %s:\n", __func__); - cipher = crypto_alloc_sync_skcipher(kctx->gk5e->encrypt_name, 0, 0); - if (IS_ERR(cipher)) - return PTR_ERR(cipher); - - plain = kmalloc(8, GFP_NOFS); - if (!plain) - return -ENOMEM; - - plain[0] = (unsigned char) ((seqnum >> 24) & 0xff); - plain[1] = (unsigned char) ((seqnum >> 16) & 0xff); - plain[2] = (unsigned char) ((seqnum >> 8) & 0xff); - plain[3] = (unsigned char) ((seqnum >> 0) & 0xff); - plain[4] = direction; - plain[5] = direction; - plain[6] = direction; - plain[7] = direction; - - code = krb5_rc4_setup_seq_key(kctx, cipher, cksum); - if (code) - goto out; - - code = krb5_encrypt(cipher, cksum, plain, buf, 8); -out: - kfree(plain); - crypto_free_sync_skcipher(cipher); - return code; -} s32 krb5_make_seq_num(struct krb5_ctx *kctx, struct crypto_sync_skcipher *key, @@ -85,10 +49,6 @@ krb5_make_seq_num(struct krb5_ctx *kctx, unsigned char *plain; s32 code; - if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) - return krb5_make_rc4_seq_num(kctx, direction, seqnum, - cksum, buf); - plain = kmalloc(8, GFP_NOFS); if (!plain) return -ENOMEM; @@ -108,50 +68,6 @@ krb5_make_seq_num(struct krb5_ctx *kctx, return code; } -static s32 -krb5_get_rc4_seq_num(struct krb5_ctx *kctx, unsigned char *cksum, - unsigned char *buf, int *direction, s32 *seqnum) -{ - struct crypto_sync_skcipher *cipher; - unsigned char *plain; - s32 code; - - dprintk("RPC: %s:\n", __func__); - cipher = crypto_alloc_sync_skcipher(kctx->gk5e->encrypt_name, 0, 0); - if (IS_ERR(cipher)) - return PTR_ERR(cipher); - - code = krb5_rc4_setup_seq_key(kctx, cipher, cksum); - if (code) - goto out; - - plain = kmalloc(8, GFP_NOFS); - if (!plain) { - code = -ENOMEM; - goto out; - } - - code = krb5_decrypt(cipher, cksum, buf, plain, 8); - if (code) - goto out_plain; - - if ((plain[4] != plain[5]) || (plain[4] != plain[6]) - || (plain[4] != plain[7])) { - code = (s32)KG_BAD_SEQ; - goto out_plain; - } - - *direction = plain[4]; - - *seqnum = ((plain[0] << 24) | (plain[1] << 16) | - (plain[2] << 8) | (plain[3])); -out_plain: - kfree(plain); -out: - crypto_free_sync_skcipher(cipher); - return code; -} - s32 krb5_get_seq_num(struct krb5_ctx *kctx, unsigned char *cksum, @@ -164,9 +80,6 @@ krb5_get_seq_num(struct krb5_ctx *kctx, dprintk("RPC: krb5_get_seq_num:\n"); - if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) - return krb5_get_rc4_seq_num(kctx, cksum, buf, - direction, seqnum); plain = kmalloc(8, GFP_NOFS); if (!plain) return -ENOMEM; diff --git a/net/sunrpc/auth_gss/gss_krb5_unseal.c b/net/sunrpc/auth_gss/gss_krb5_unseal.c index aaab91cf24c8..ba04e3ec970a 100644 --- a/net/sunrpc/auth_gss/gss_krb5_unseal.c +++ b/net/sunrpc/auth_gss/gss_krb5_unseal.c @@ -218,7 +218,6 @@ gss_verify_mic_kerberos(struct gss_ctx *gss_ctx, BUG(); case ENCTYPE_DES_CBC_RAW: case ENCTYPE_DES3_CBC_RAW: - case ENCTYPE_ARCFOUR_HMAC: return gss_verify_mic_v1(ctx, message_buffer, read_token); case ENCTYPE_AES128_CTS_HMAC_SHA1_96: case ENCTYPE_AES256_CTS_HMAC_SHA1_96: diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 8b300b74a722..e95c009bb869 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -236,26 +236,9 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset, seq_send, ptr + GSS_KRB5_TOK_HDR_LEN, ptr + 8))) return GSS_S_FAILURE; - if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) { - struct crypto_sync_skcipher *cipher; - int err; - cipher = crypto_alloc_sync_skcipher(kctx->gk5e->encrypt_name, - 0, 0); - if (IS_ERR(cipher)) - return GSS_S_FAILURE; - - krb5_rc4_setup_enc_key(kctx, cipher, seq_send); - - err = gss_encrypt_xdr_buf(cipher, buf, - offset + headlen - conflen, pages); - crypto_free_sync_skcipher(cipher); - if (err) - return GSS_S_FAILURE; - } else { - if (gss_encrypt_xdr_buf(kctx->enc, buf, - offset + headlen - conflen, pages)) - return GSS_S_FAILURE; - } + if (gss_encrypt_xdr_buf(kctx->enc, buf, + offset + headlen - conflen, pages)) + return GSS_S_FAILURE; return (kctx->endtime < now) ? GSS_S_CONTEXT_EXPIRED : GSS_S_COMPLETE; } @@ -316,37 +299,9 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, int len, crypt_offset = ptr + (GSS_KRB5_TOK_HDR_LEN + kctx->gk5e->cksumlength) - (unsigned char *)buf->head[0].iov_base; - /* - * Need plaintext seqnum to derive encryption key for arcfour-hmac - */ - if (krb5_get_seq_num(kctx, ptr + GSS_KRB5_TOK_HDR_LEN, - ptr + 8, &direction, &seqnum)) - return GSS_S_BAD_SIG; - - if ((kctx->initiate && direction != 0xff) || - (!kctx->initiate && direction != 0)) - return GSS_S_BAD_SIG; - buf->len = len; - if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) { - struct crypto_sync_skcipher *cipher; - int err; - - cipher = crypto_alloc_sync_skcipher(kctx->gk5e->encrypt_name, - 0, 0); - if (IS_ERR(cipher)) - return GSS_S_FAILURE; - - krb5_rc4_setup_enc_key(kctx, cipher, seqnum); - - err = gss_decrypt_xdr_buf(cipher, buf, crypt_offset); - crypto_free_sync_skcipher(cipher); - if (err) - return GSS_S_DEFECTIVE_TOKEN; - } else { - if (gss_decrypt_xdr_buf(kctx->enc, buf, crypt_offset)) - return GSS_S_DEFECTIVE_TOKEN; - } + if (gss_decrypt_xdr_buf(kctx->enc, buf, crypt_offset)) + return GSS_S_DEFECTIVE_TOKEN; if (kctx->gk5e->keyed_cksum) cksumkey = kctx->cksum; @@ -370,6 +325,14 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, int len, /* do sequencing checks */ + if (krb5_get_seq_num(kctx, ptr + GSS_KRB5_TOK_HDR_LEN, + ptr + 8, &direction, &seqnum)) + return GSS_S_BAD_SIG; + + if ((kctx->initiate && direction != 0xff) || + (!kctx->initiate && direction != 0)) + return GSS_S_BAD_SIG; + /* Copy the data back to the right position. XXX: Would probably be * better to copy and encrypt at the same time. */ @@ -605,7 +568,6 @@ gss_wrap_kerberos(struct gss_ctx *gctx, int offset, BUG(); case ENCTYPE_DES_CBC_RAW: case ENCTYPE_DES3_CBC_RAW: - case ENCTYPE_ARCFOUR_HMAC: return gss_wrap_kerberos_v1(kctx, offset, buf, pages); case ENCTYPE_AES128_CTS_HMAC_SHA1_96: case ENCTYPE_AES256_CTS_HMAC_SHA1_96: @@ -624,7 +586,6 @@ gss_unwrap_kerberos(struct gss_ctx *gctx, int offset, BUG(); case ENCTYPE_DES_CBC_RAW: case ENCTYPE_DES3_CBC_RAW: - case ENCTYPE_ARCFOUR_HMAC: return gss_unwrap_kerberos_v1(kctx, offset, len, buf, &gctx->slack, &gctx->align); case ENCTYPE_AES128_CTS_HMAC_SHA1_96: diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 258b04372f85..bd4678db9d76 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1147,9 +1147,9 @@ static int gss_read_proxy_verf(struct svc_rqst *rqstp, struct gssp_in_token *in_token) { struct kvec *argv = &rqstp->rq_arg.head[0]; - unsigned int page_base, length; - int pages, i, res; - size_t inlen; + unsigned int length, pgto_offs, pgfrom_offs; + int pages, i, res, pgto, pgfrom; + size_t inlen, to_offs, from_offs; res = gss_read_common_verf(gc, argv, authp, in_handle); if (res) @@ -1177,17 +1177,24 @@ static int gss_read_proxy_verf(struct svc_rqst *rqstp, memcpy(page_address(in_token->pages[0]), argv->iov_base, length); inlen -= length; - i = 1; - page_base = rqstp->rq_arg.page_base; + to_offs = length; + from_offs = rqstp->rq_arg.page_base; while (inlen) { - length = min_t(unsigned int, inlen, PAGE_SIZE); - memcpy(page_address(in_token->pages[i]), - page_address(rqstp->rq_arg.pages[i]) + page_base, + pgto = to_offs >> PAGE_SHIFT; + pgfrom = from_offs >> PAGE_SHIFT; + pgto_offs = to_offs & ~PAGE_MASK; + pgfrom_offs = from_offs & ~PAGE_MASK; + + length = min_t(unsigned int, inlen, + min_t(unsigned int, PAGE_SIZE - pgto_offs, + PAGE_SIZE - pgfrom_offs)); + memcpy(page_address(in_token->pages[pgto]) + pgto_offs, + page_address(rqstp->rq_arg.pages[pgfrom]) + pgfrom_offs, length); + to_offs += length; + from_offs += length; inlen -= length; - page_base = 0; - i++; } return 0; } diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index 195b40c5dae4..22a2c235abf1 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -5,7 +5,7 @@ NetApp provides this source code under the GPL v2 License. The GPL v2 license is available at -http://opensource.org/licenses/gpl-license.php. +https://opensource.org/licenses/gpl-license.php. THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT @@ -111,7 +111,7 @@ out_free: * by the backchannel. This function can be called multiple times * when creating new sessions that use the same rpc_xprt. The * preallocated buffers are added to the pool of resources used by - * the rpc_xprt. Anyone of these resources may be used used by an + * the rpc_xprt. Any one of these resources may be used by an * incoming callback request. It's up to the higher levels in the * stack to enforce that the maximum number of session slots is not * being exceeded. diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index baef5ee43dbb..20c93b68505e 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -498,16 +498,17 @@ static int cache_clean(void) */ static void do_cache_clean(struct work_struct *work) { - int delay = 5; - if (cache_clean() == -1) - delay = round_jiffies_relative(30*HZ); + int delay; if (list_empty(&cache_list)) - delay = 0; + return; + + if (cache_clean() == -1) + delay = round_jiffies_relative(30*HZ); + else + delay = 5; - if (delay) - queue_delayed_work(system_power_efficient_wq, - &cache_cleaner, delay); + queue_delayed_work(system_power_efficient_wq, &cache_cleaner, delay); } @@ -908,7 +909,7 @@ static ssize_t cache_do_downcall(char *kaddr, const char __user *buf, static ssize_t cache_slow_downcall(const char __user *buf, size_t count, struct cache_detail *cd) { - static char write_buf[8192]; /* protected by queue_io_mutex */ + static char write_buf[32768]; /* protected by queue_io_mutex */ ssize_t ret = -EINVAL; if (count >= sizeof(write_buf)) @@ -1436,10 +1437,10 @@ static int c_show(struct seq_file *m, void *p) cache_get(cp); if (cache_check(cd, cp, NULL)) /* cache_check does a cache_put on failure */ - seq_printf(m, "# "); + seq_puts(m, "# "); else { if (cache_is_expired(cd, cp)) - seq_printf(m, "# "); + seq_puts(m, "# "); cache_put(cp, cd); } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 62e0b6c1e8cf..3259120462ed 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -47,10 +47,6 @@ # define RPCDBG_FACILITY RPCDBG_CALL #endif -#define dprint_status(t) \ - dprintk("RPC: %5u %s (status %d)\n", t->tk_pid, \ - __func__, t->tk_status) - /* * All RPC clients are linked into this list */ @@ -1639,10 +1635,6 @@ call_start(struct rpc_task *task) int idx = task->tk_msg.rpc_proc->p_statidx; trace_rpc_request(task); - dprintk("RPC: %5u call_start %s%d proc %s (%s)\n", task->tk_pid, - clnt->cl_program->name, clnt->cl_vers, - rpc_proc_name(task), - (RPC_IS_ASYNC(task) ? "async" : "sync")); /* Increment call count (version might not be valid for ping) */ if (clnt->cl_program->version[clnt->cl_vers]) @@ -1658,8 +1650,6 @@ call_start(struct rpc_task *task) static void call_reserve(struct rpc_task *task) { - dprint_status(task); - task->tk_status = 0; task->tk_action = call_reserveresult; xprt_reserve(task); @@ -1675,8 +1665,6 @@ call_reserveresult(struct rpc_task *task) { int status = task->tk_status; - dprint_status(task); - /* * After a call to xprt_reserve(), we must have either * a request slot or else an error status. @@ -1717,8 +1705,6 @@ call_reserveresult(struct rpc_task *task) static void call_retry_reserve(struct rpc_task *task) { - dprint_status(task); - task->tk_status = 0; task->tk_action = call_reserveresult; xprt_retry_reserve(task); @@ -1730,8 +1716,6 @@ call_retry_reserve(struct rpc_task *task) static void call_refresh(struct rpc_task *task) { - dprint_status(task); - task->tk_action = call_refreshresult; task->tk_status = 0; task->tk_client->cl_stats->rpcauthrefresh++; @@ -1746,8 +1730,6 @@ call_refreshresult(struct rpc_task *task) { int status = task->tk_status; - dprint_status(task); - task->tk_status = 0; task->tk_action = call_refresh; switch (status) { @@ -1770,12 +1752,10 @@ call_refreshresult(struct rpc_task *task) if (!task->tk_cred_retry) break; task->tk_cred_retry--; - dprintk("RPC: %5u %s: retry refresh creds\n", - task->tk_pid, __func__); + trace_rpc_retry_refresh_status(task); return; } - dprintk("RPC: %5u %s: refresh creds failed with error %d\n", - task->tk_pid, __func__, status); + trace_rpc_refresh_status(task); rpc_call_rpcerror(task, status); } @@ -1792,8 +1772,6 @@ call_allocate(struct rpc_task *task) const struct rpc_procinfo *proc = task->tk_msg.rpc_proc; int status; - dprint_status(task); - task->tk_status = 0; task->tk_action = call_encode; @@ -1823,6 +1801,7 @@ call_allocate(struct rpc_task *task) req->rq_rcvsize <<= 2; status = xprt->ops->buf_alloc(task); + trace_rpc_buf_alloc(task, status); xprt_inject_disconnect(xprt); if (status == 0) return; @@ -1831,8 +1810,6 @@ call_allocate(struct rpc_task *task) return; } - dprintk("RPC: %5u rpc_buffer allocation failed\n", task->tk_pid); - if (RPC_IS_ASYNC(task) || !fatal_signal_pending(current)) { task->tk_action = call_allocate; rpc_delay(task, HZ>>4); @@ -1883,7 +1860,7 @@ call_encode(struct rpc_task *task) { if (!rpc_task_need_encode(task)) goto out; - dprint_status(task); + /* Dequeue task from the receive queue while we're encoding */ xprt_request_dequeue_xprt(task); /* Encode here so that rpcsec_gss can use correct sequence number. */ @@ -1902,8 +1879,7 @@ call_encode(struct rpc_task *task) } else { task->tk_action = call_refresh; task->tk_cred_retry--; - dprintk("RPC: %5u %s: retry refresh creds\n", - task->tk_pid, __func__); + trace_rpc_retry_refresh_status(task); } break; default: @@ -1960,8 +1936,6 @@ call_bind(struct rpc_task *task) return; } - dprint_status(task); - task->tk_action = call_bind_status; if (!xprt_prepare_transmit(task)) return; @@ -1983,8 +1957,6 @@ call_bind_status(struct rpc_task *task) return; } - dprint_status(task); - trace_rpc_bind_status(task); if (task->tk_status >= 0) goto out_next; if (xprt_bound(xprt)) { @@ -1994,12 +1966,10 @@ call_bind_status(struct rpc_task *task) switch (task->tk_status) { case -ENOMEM: - dprintk("RPC: %5u rpcbind out of memory\n", task->tk_pid); rpc_delay(task, HZ >> 2); goto retry_timeout; case -EACCES: - dprintk("RPC: %5u remote rpcbind: RPC program/version " - "unavailable\n", task->tk_pid); + trace_rpcb_prog_unavail_err(task); /* fail immediately if this is an RPC ping */ if (task->tk_msg.rpc_proc->p_proc == 0) { status = -EOPNOTSUPP; @@ -2016,17 +1986,14 @@ call_bind_status(struct rpc_task *task) case -EAGAIN: goto retry_timeout; case -ETIMEDOUT: - dprintk("RPC: %5u rpcbind request timed out\n", - task->tk_pid); + trace_rpcb_timeout_err(task); goto retry_timeout; case -EPFNOSUPPORT: /* server doesn't support any rpcbind version we know of */ - dprintk("RPC: %5u unrecognized remote rpcbind service\n", - task->tk_pid); + trace_rpcb_bind_version_err(task); break; case -EPROTONOSUPPORT: - dprintk("RPC: %5u remote rpcbind version unavailable, retrying\n", - task->tk_pid); + trace_rpcb_bind_version_err(task); goto retry_timeout; case -ECONNREFUSED: /* connection problems */ case -ECONNRESET: @@ -2037,8 +2004,7 @@ call_bind_status(struct rpc_task *task) case -EHOSTUNREACH: case -ENETUNREACH: case -EPIPE: - dprintk("RPC: %5u remote rpcbind unreachable: %d\n", - task->tk_pid, task->tk_status); + trace_rpcb_unreachable_err(task); if (!RPC_IS_SOFTCONN(task)) { rpc_delay(task, 5*HZ); goto retry_timeout; @@ -2046,8 +2012,7 @@ call_bind_status(struct rpc_task *task) status = task->tk_status; break; default: - dprintk("RPC: %5u unrecognized rpcbind error (%d)\n", - task->tk_pid, -task->tk_status); + trace_rpcb_unrecognized_err(task); } rpc_call_rpcerror(task, status); @@ -2079,10 +2044,6 @@ call_connect(struct rpc_task *task) return; } - dprintk("RPC: %5u call_connect xprt %p %s connected\n", - task->tk_pid, xprt, - (xprt_connected(xprt) ? "is" : "is not")); - task->tk_action = call_connect_status; if (task->tk_status < 0) return; @@ -2110,7 +2071,6 @@ call_connect_status(struct rpc_task *task) return; } - dprint_status(task); trace_rpc_connect_status(task); if (task->tk_status == 0) { @@ -2178,8 +2138,6 @@ call_transmit(struct rpc_task *task) return; } - dprint_status(task); - task->tk_action = call_transmit_status; if (!xprt_prepare_transmit(task)) return; @@ -2214,7 +2172,6 @@ call_transmit_status(struct rpc_task *task) switch (task->tk_status) { default: - dprint_status(task); break; case -EBADMSG: task->tk_status = 0; @@ -2296,8 +2253,6 @@ call_bc_transmit_status(struct rpc_task *task) if (rpc_task_transmitted(task)) task->tk_status = 0; - dprint_status(task); - switch (task->tk_status) { case 0: /* Success */ @@ -2357,8 +2312,6 @@ call_status(struct rpc_task *task) if (!task->tk_msg.rpc_proc->p_proc) trace_xprt_ping(task->tk_xprt, task->tk_status); - dprint_status(task); - status = task->tk_status; if (status >= 0) { task->tk_action = call_decode; @@ -2405,7 +2358,8 @@ call_status(struct rpc_task *task) goto out_exit; } task->tk_action = call_encode; - rpc_check_timeout(task); + if (status != -ECONNRESET && status != -ECONNABORTED) + rpc_check_timeout(task); return; out_exit: rpc_call_rpcerror(task, status); @@ -2433,7 +2387,7 @@ rpc_check_timeout(struct rpc_task *task) if (xprt_adjust_timeout(task->tk_rqstp) == 0) return; - dprintk("RPC: %5u call_timeout (major)\n", task->tk_pid); + trace_rpc_timeout_status(task); task->tk_timeouts++; if (RPC_IS_SOFTCONN(task) && !rpc_check_connected(task->tk_rqstp)) { @@ -2492,8 +2446,6 @@ call_decode(struct rpc_task *task) struct xdr_stream xdr; int err; - dprint_status(task); - if (!task->tk_msg.rpc_proc->p_decode) { task->tk_action = rpc_exit_task; return; @@ -2537,8 +2489,6 @@ out: case 0: task->tk_action = rpc_exit_task; task->tk_status = rpcauth_unwrap_resp(task, &xdr); - dprintk("RPC: %5u %s result %d\n", - task->tk_pid, __func__, task->tk_status); return; case -EAGAIN: task->tk_status = 0; diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 4a67685c83eb..38fe2ce8a5aa 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -31,11 +31,9 @@ #include <linux/sunrpc/sched.h> #include <linux/sunrpc/xprtsock.h> -#include "netns.h" +#include <trace/events/sunrpc.h> -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) -# define RPCDBG_FACILITY RPCDBG_BIND -#endif +#include "netns.h" #define RPCBIND_SOCK_PATHNAME "/var/run/rpcbind.sock" @@ -216,10 +214,6 @@ static void rpcb_set_local(struct net *net, struct rpc_clnt *clnt, sn->rpcb_is_af_local = is_af_local ? 1 : 0; smp_wmb(); sn->rpcb_users = 1; - dprintk("RPC: created new rpcb local clients (rpcb_local_clnt: " - "%p, rpcb_local_clnt4: %p) for net %x%s\n", - sn->rpcb_local_clnt, sn->rpcb_local_clnt4, - net->ns.inum, (net == &init_net) ? " (init_net)" : ""); } /* @@ -261,19 +255,13 @@ static int rpcb_create_local_unix(struct net *net) */ clnt = rpc_create(&args); if (IS_ERR(clnt)) { - dprintk("RPC: failed to create AF_LOCAL rpcbind " - "client (errno %ld).\n", PTR_ERR(clnt)); result = PTR_ERR(clnt); goto out; } clnt4 = rpc_bind_new_program(clnt, &rpcb_program, RPCBVERS_4); - if (IS_ERR(clnt4)) { - dprintk("RPC: failed to bind second program to " - "rpcbind v4 client (errno %ld).\n", - PTR_ERR(clnt4)); + if (IS_ERR(clnt4)) clnt4 = NULL; - } rpcb_set_local(net, clnt, clnt4, true); @@ -309,8 +297,6 @@ static int rpcb_create_local_net(struct net *net) clnt = rpc_create(&args); if (IS_ERR(clnt)) { - dprintk("RPC: failed to create local rpcbind " - "client (errno %ld).\n", PTR_ERR(clnt)); result = PTR_ERR(clnt); goto out; } @@ -321,12 +307,8 @@ static int rpcb_create_local_net(struct net *net) * v4 upcalls. */ clnt4 = rpc_bind_new_program(clnt, &rpcb_program, RPCBVERS_4); - if (IS_ERR(clnt4)) { - dprintk("RPC: failed to bind second program to " - "rpcbind v4 client (errno %ld).\n", - PTR_ERR(clnt4)); + if (IS_ERR(clnt4)) clnt4 = NULL; - } rpcb_set_local(net, clnt, clnt4, false); @@ -403,11 +385,8 @@ static int rpcb_register_call(struct sunrpc_net *sn, struct rpc_clnt *clnt, stru msg->rpc_resp = &result; error = rpc_call_sync(clnt, msg, flags); - if (error < 0) { - dprintk("RPC: failed to contact local rpcbind " - "server (errno %d).\n", -error); + if (error < 0) return error; - } if (!result) return -EACCES; @@ -461,9 +440,7 @@ int rpcb_register(struct net *net, u32 prog, u32 vers, int prot, unsigned short struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); bool is_set = false; - dprintk("RPC: %sregistering (%u, %u, %d, %u) with local " - "rpcbind\n", (port ? "" : "un"), - prog, vers, prot, port); + trace_pmap_register(prog, vers, prot, port); msg.rpc_proc = &rpcb_procedures2[RPCBPROC_UNSET]; if (port != 0) { @@ -489,11 +466,6 @@ static int rpcb_register_inet4(struct sunrpc_net *sn, map->r_addr = rpc_sockaddr2uaddr(sap, GFP_KERNEL); - dprintk("RPC: %sregistering [%u, %u, %s, '%s'] with " - "local rpcbind\n", (port ? "" : "un"), - map->r_prog, map->r_vers, - map->r_addr, map->r_netid); - msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET]; if (port != 0) { msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; @@ -520,11 +492,6 @@ static int rpcb_register_inet6(struct sunrpc_net *sn, map->r_addr = rpc_sockaddr2uaddr(sap, GFP_KERNEL); - dprintk("RPC: %sregistering [%u, %u, %s, '%s'] with " - "local rpcbind\n", (port ? "" : "un"), - map->r_prog, map->r_vers, - map->r_addr, map->r_netid); - msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET]; if (port != 0) { msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; @@ -541,9 +508,7 @@ static int rpcb_unregister_all_protofamilies(struct sunrpc_net *sn, { struct rpcbind_args *map = msg->rpc_argp; - dprintk("RPC: unregistering [%u, %u, '%s'] with " - "local rpcbind\n", - map->r_prog, map->r_vers, map->r_netid); + trace_rpcb_unregister(map->r_prog, map->r_vers, map->r_netid); map->r_addr = ""; msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET]; @@ -615,6 +580,8 @@ int rpcb_v4_register(struct net *net, const u32 program, const u32 version, if (address == NULL) return rpcb_unregister_all_protofamilies(sn, &msg); + trace_rpcb_register(map.r_prog, map.r_vers, map.r_addr, map.r_netid); + switch (address->sa_family) { case AF_INET: return rpcb_register_inet4(sn, address, &msg); @@ -693,18 +660,12 @@ void rpcb_getport_async(struct rpc_task *task) rcu_read_unlock(); xprt = xprt_get(task->tk_xprt); - dprintk("RPC: %5u %s(%s, %u, %u, %d)\n", - task->tk_pid, __func__, - xprt->servername, clnt->cl_prog, clnt->cl_vers, xprt->prot); - /* Put self on the wait queue to ensure we get notified if * some other task is already attempting to bind the port */ rpc_sleep_on_timeout(&xprt->binding, task, NULL, jiffies + xprt->bind_timeout); if (xprt_test_and_set_binding(xprt)) { - dprintk("RPC: %5u %s: waiting for another binder\n", - task->tk_pid, __func__); xprt_put(xprt); return; } @@ -712,8 +673,6 @@ void rpcb_getport_async(struct rpc_task *task) /* Someone else may have bound if we slept */ if (xprt_bound(xprt)) { status = 0; - dprintk("RPC: %5u %s: already bound\n", - task->tk_pid, __func__); goto bailout_nofree; } @@ -732,20 +691,15 @@ void rpcb_getport_async(struct rpc_task *task) break; default: status = -EAFNOSUPPORT; - dprintk("RPC: %5u %s: bad address family\n", - task->tk_pid, __func__); goto bailout_nofree; } if (proc == NULL) { xprt->bind_index = 0; status = -EPFNOSUPPORT; - dprintk("RPC: %5u %s: no more getport versions available\n", - task->tk_pid, __func__); goto bailout_nofree; } - dprintk("RPC: %5u %s: trying rpcbind version %u\n", - task->tk_pid, __func__, bind_version); + trace_rpcb_getport(clnt, task, bind_version); rpcb_clnt = rpcb_create(xprt->xprt_net, clnt->cl_nodename, @@ -754,16 +708,12 @@ void rpcb_getport_async(struct rpc_task *task) clnt->cl_cred); if (IS_ERR(rpcb_clnt)) { status = PTR_ERR(rpcb_clnt); - dprintk("RPC: %5u %s: rpcb_create failed, error %ld\n", - task->tk_pid, __func__, PTR_ERR(rpcb_clnt)); goto bailout_nofree; } map = kzalloc(sizeof(struct rpcbind_args), GFP_NOFS); if (!map) { status = -ENOMEM; - dprintk("RPC: %5u %s: no memory available\n", - task->tk_pid, __func__); goto bailout_release_client; } map->r_prog = clnt->cl_prog; @@ -780,8 +730,6 @@ void rpcb_getport_async(struct rpc_task *task) map->r_addr = rpc_sockaddr2uaddr(sap, GFP_NOFS); if (!map->r_addr) { status = -ENOMEM; - dprintk("RPC: %5u %s: no memory available\n", - task->tk_pid, __func__); goto bailout_free_args; } map->r_owner = ""; @@ -818,34 +766,33 @@ static void rpcb_getport_done(struct rpc_task *child, void *data) { struct rpcbind_args *map = data; struct rpc_xprt *xprt = map->r_xprt; - int status = child->tk_status; + + map->r_status = child->tk_status; /* Garbage reply: retry with a lesser rpcbind version */ - if (status == -EIO) - status = -EPROTONOSUPPORT; + if (map->r_status == -EIO) + map->r_status = -EPROTONOSUPPORT; /* rpcbind server doesn't support this rpcbind protocol version */ - if (status == -EPROTONOSUPPORT) + if (map->r_status == -EPROTONOSUPPORT) xprt->bind_index++; - if (status < 0) { + if (map->r_status < 0) { /* rpcbind server not available on remote host? */ - xprt->ops->set_port(xprt, 0); + map->r_port = 0; + } else if (map->r_port == 0) { /* Requested RPC service wasn't registered on remote host */ - xprt->ops->set_port(xprt, 0); - status = -EACCES; + map->r_status = -EACCES; } else { /* Succeeded */ - xprt->ops->set_port(xprt, map->r_port); - xprt_set_bound(xprt); - status = 0; + map->r_status = 0; } - dprintk("RPC: %5u rpcb_getport_done(status %d, port %u)\n", - child->tk_pid, status, map->r_port); - - map->r_status = status; + trace_rpcb_setport(child, map->r_status, map->r_port); + xprt->ops->set_port(xprt, map->r_port); + if (map->r_port) + xprt_set_bound(xprt); } /* @@ -858,11 +805,6 @@ static void rpcb_enc_mapping(struct rpc_rqst *req, struct xdr_stream *xdr, const struct rpcbind_args *rpcb = data; __be32 *p; - dprintk("RPC: %5u encoding PMAP_%s call (%u, %u, %d, %u)\n", - req->rq_task->tk_pid, - req->rq_task->tk_msg.rpc_proc->p_name, - rpcb->r_prog, rpcb->r_vers, rpcb->r_prot, rpcb->r_port); - p = xdr_reserve_space(xdr, RPCB_mappingargs_sz << 2); *p++ = cpu_to_be32(rpcb->r_prog); *p++ = cpu_to_be32(rpcb->r_vers); @@ -884,8 +826,6 @@ static int rpcb_dec_getport(struct rpc_rqst *req, struct xdr_stream *xdr, return -EIO; port = be32_to_cpup(p); - dprintk("RPC: %5u PMAP_%s result: %lu\n", req->rq_task->tk_pid, - req->rq_task->tk_msg.rpc_proc->p_name, port); if (unlikely(port > USHRT_MAX)) return -EIO; @@ -906,11 +846,6 @@ static int rpcb_dec_set(struct rpc_rqst *req, struct xdr_stream *xdr, *boolp = 0; if (*p != xdr_zero) *boolp = 1; - - dprintk("RPC: %5u RPCB_%s call %s\n", - req->rq_task->tk_pid, - req->rq_task->tk_msg.rpc_proc->p_name, - (*boolp ? "succeeded" : "failed")); return 0; } @@ -935,12 +870,6 @@ static void rpcb_enc_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr, const struct rpcbind_args *rpcb = data; __be32 *p; - dprintk("RPC: %5u encoding RPCB_%s call (%u, %u, '%s', '%s')\n", - req->rq_task->tk_pid, - req->rq_task->tk_msg.rpc_proc->p_name, - rpcb->r_prog, rpcb->r_vers, - rpcb->r_netid, rpcb->r_addr); - p = xdr_reserve_space(xdr, (RPCB_program_sz + RPCB_version_sz) << 2); *p++ = cpu_to_be32(rpcb->r_prog); *p = cpu_to_be32(rpcb->r_vers); @@ -970,11 +899,8 @@ static int rpcb_dec_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr, * If the returned universal address is a null string, * the requested RPC service was not registered. */ - if (len == 0) { - dprintk("RPC: %5u RPCB reply: program not registered\n", - req->rq_task->tk_pid); + if (len == 0) return 0; - } if (unlikely(len > RPCBIND_MAXUADDRLEN)) goto out_fail; @@ -982,8 +908,6 @@ static int rpcb_dec_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr, p = xdr_inline_decode(xdr, len); if (unlikely(p == NULL)) goto out_fail; - dprintk("RPC: %5u RPCB_%s reply: %*pE\n", req->rq_task->tk_pid, - req->rq_task->tk_msg.rpc_proc->p_name, len, (char *)p); if (rpc_uaddr2sockaddr(req->rq_xprt->xprt_net, (char *)p, len, sap, sizeof(address)) == 0) @@ -993,9 +917,6 @@ static int rpcb_dec_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr, return 0; out_fail: - dprintk("RPC: %5u malformed RPCB_%s reply\n", - req->rq_task->tk_pid, - req->rq_task->tk_msg.rpc_proc->p_name); return -EIO; } diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 7eba20a88438..f06d7c315017 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -27,10 +27,6 @@ #include "sunrpc.h" -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) -#define RPCDBG_FACILITY RPCDBG_SCHED -#endif - #define CREATE_TRACE_POINTS #include <trace/events/sunrpc.h> @@ -85,7 +81,6 @@ __rpc_disable_timer(struct rpc_wait_queue *queue, struct rpc_task *task) { if (list_empty(&task->u.tk_wait.timer_list)) return; - dprintk("RPC: %5u disabling timer\n", task->tk_pid); task->tk_timeout = 0; list_del(&task->u.tk_wait.timer_list); if (list_empty(&queue->timer_list.list)) @@ -111,9 +106,6 @@ static void __rpc_add_timer(struct rpc_wait_queue *queue, struct rpc_task *task, unsigned long timeout) { - dprintk("RPC: %5u setting alarm for %u ms\n", - task->tk_pid, jiffies_to_msecs(timeout - jiffies)); - task->tk_timeout = timeout; if (list_empty(&queue->timer_list.list) || time_before(timeout, queue->timer_list.expires)) rpc_set_queue_timer(queue, timeout); @@ -216,9 +208,6 @@ static void __rpc_add_wait_queue(struct rpc_wait_queue *queue, /* barrier matches the read in rpc_wake_up_task_queue_locked() */ smp_wmb(); rpc_set_queued(task); - - dprintk("RPC: %5u added to queue %p \"%s\"\n", - task->tk_pid, queue, rpc_qname(queue)); } /* @@ -241,8 +230,6 @@ static void __rpc_remove_wait_queue(struct rpc_wait_queue *queue, struct rpc_tas else list_del(&task->u.tk_wait.list); queue->qlen--; - dprintk("RPC: %5u removed from queue %p \"%s\"\n", - task->tk_pid, queue, rpc_qname(queue)); } static void __rpc_init_priority_wait_queue(struct rpc_wait_queue *queue, const char *qname, unsigned char nr_queues) @@ -382,13 +369,9 @@ static void __rpc_do_sleep_on_priority(struct rpc_wait_queue *q, struct rpc_task *task, unsigned char queue_priority) { - dprintk("RPC: %5u sleep_on(queue \"%s\" time %lu)\n", - task->tk_pid, rpc_qname(q), jiffies); - trace_rpc_task_sleep(task, q); __rpc_add_wait_queue(q, task, queue_priority); - } static void __rpc_sleep_on_priority(struct rpc_wait_queue *q, @@ -510,9 +493,6 @@ static void __rpc_do_wake_up_task_on_wq(struct workqueue_struct *wq, struct rpc_wait_queue *queue, struct rpc_task *task) { - dprintk("RPC: %5u __rpc_wake_up_task (now %lu)\n", - task->tk_pid, jiffies); - /* Has the task been executed yet? If not, we cannot wake it up! */ if (!RPC_IS_ACTIVATED(task)) { printk(KERN_ERR "RPC: Inactive task (%p) being woken up!\n", task); @@ -524,8 +504,6 @@ static void __rpc_do_wake_up_task_on_wq(struct workqueue_struct *wq, __rpc_remove_wait_queue(queue, task); rpc_make_runnable(wq, task); - - dprintk("RPC: __rpc_wake_up_task done\n"); } /* @@ -663,8 +641,6 @@ struct rpc_task *rpc_wake_up_first_on_wq(struct workqueue_struct *wq, { struct rpc_task *task = NULL; - dprintk("RPC: wake_up_first(%p \"%s\")\n", - queue, rpc_qname(queue)); spin_lock(&queue->lock); task = __rpc_find_next_queued(queue); if (task != NULL) @@ -770,7 +746,7 @@ static void __rpc_queue_timer_fn(struct work_struct *work) list_for_each_entry_safe(task, n, &queue->timer_list.list, u.tk_wait.timer_list) { timeo = task->tk_timeout; if (time_after_eq(now, timeo)) { - dprintk("RPC: %5u timeout\n", task->tk_pid); + trace_rpc_task_timeout(task, task->tk_action); task->tk_status = -ETIMEDOUT; rpc_wake_up_task_queue_locked(queue, task); continue; @@ -885,9 +861,6 @@ static void __rpc_execute(struct rpc_task *task) int task_is_async = RPC_IS_ASYNC(task); int status = 0; - dprintk("RPC: %5u __rpc_execute flags=0x%x\n", - task->tk_pid, task->tk_flags); - WARN_ON_ONCE(RPC_IS_QUEUED(task)); if (RPC_IS_QUEUED(task)) return; @@ -947,7 +920,7 @@ static void __rpc_execute(struct rpc_task *task) return; /* sync task: sleep here */ - dprintk("RPC: %5u sync task going to sleep\n", task->tk_pid); + trace_rpc_task_sync_sleep(task, task->tk_action); status = out_of_line_wait_on_bit(&task->tk_runstate, RPC_TASK_QUEUED, rpc_wait_bit_killable, TASK_KILLABLE); @@ -963,11 +936,9 @@ static void __rpc_execute(struct rpc_task *task) task->tk_rpc_status = -ERESTARTSYS; rpc_exit(task, -ERESTARTSYS); } - dprintk("RPC: %5u sync task resuming\n", task->tk_pid); + trace_rpc_task_sync_wake(task, task->tk_action); } - dprintk("RPC: %5u return %d, status %d\n", task->tk_pid, status, - task->tk_status); /* Release all resources associated with the task */ rpc_release_task(task); } @@ -1036,8 +1007,6 @@ int rpc_malloc(struct rpc_task *task) return -ENOMEM; buf->len = size; - dprintk("RPC: %5u allocated buffer of size %zu at %p\n", - task->tk_pid, size, buf); rqst->rq_buffer = buf->data; rqst->rq_rbuffer = (char *)rqst->rq_buffer + rqst->rq_callsize; return 0; @@ -1058,9 +1027,6 @@ void rpc_free(struct rpc_task *task) buf = container_of(buffer, struct rpc_buffer, data); size = buf->len; - dprintk("RPC: freeing buffer of size %zu at %p\n", - size, buf); - if (size <= RPC_BUFFER_MAXSIZE) mempool_free(buf, rpc_buffer_mempool); else @@ -1095,9 +1061,6 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta task->tk_action = rpc_prepare_task; rpc_init_task_statistics(task); - - dprintk("RPC: new task initialized, procpid %u\n", - task_pid_nr(current)); } static struct rpc_task * @@ -1121,7 +1084,6 @@ struct rpc_task *rpc_new_task(const struct rpc_task_setup *setup_data) rpc_init_task(task, setup_data); task->tk_flags |= flags; - dprintk("RPC: allocated task %p\n", task); return task; } @@ -1151,10 +1113,8 @@ static void rpc_free_task(struct rpc_task *task) put_rpccred(task->tk_op_cred); rpc_release_calldata(task->tk_ops, task->tk_calldata); - if (tk_flags & RPC_TASK_DYNAMIC) { - dprintk("RPC: %5u freeing task\n", task->tk_pid); + if (tk_flags & RPC_TASK_DYNAMIC) mempool_free(task, rpc_task_mempool); - } } static void rpc_async_release(struct work_struct *work) @@ -1208,8 +1168,6 @@ EXPORT_SYMBOL_GPL(rpc_put_task_async); static void rpc_release_task(struct rpc_task *task) { - dprintk("RPC: %5u release task\n", task->tk_pid); - WARN_ON_ONCE(RPC_IS_QUEUED(task)); rpc_release_resources_task(task); @@ -1250,7 +1208,6 @@ static int rpciod_start(void) /* * Create the rpciod thread and wait for it to start. */ - dprintk("RPC: creating workqueue rpciod\n"); wq = alloc_workqueue("rpciod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0); if (!wq) goto out_failed; @@ -1275,7 +1232,6 @@ static void rpciod_stop(void) if (rpciod_workqueue == NULL) return; - dprintk("RPC: destroying workqueue rpciod\n"); wq = rpciod_workqueue; rpciod_workqueue = NULL; diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c index 3fc8af8bb961..d52313af82bc 100644 --- a/net/sunrpc/socklib.c +++ b/net/sunrpc/socklib.c @@ -70,7 +70,7 @@ static size_t xdr_skb_read_and_csum_bits(struct xdr_skb_reader *desc, void *to, if (len > desc->count) len = desc->count; pos = desc->offset; - csum2 = skb_copy_and_csum_bits(desc->skb, pos, to, len, 0); + csum2 = skb_copy_and_csum_bits(desc->skb, pos, to, len); desc->csum = csum_block_add(desc->csum, csum2, pos); desc->count -= len; desc->offset += len; diff --git a/net/sunrpc/sunrpc.h b/net/sunrpc/sunrpc.h index f6fe2e6cd65a..2f59464e6524 100644 --- a/net/sunrpc/sunrpc.h +++ b/net/sunrpc/sunrpc.h @@ -4,7 +4,7 @@ NetApp provides this source code under the GPL v2 License. The GPL v2 license is available at -http://opensource.org/licenses/gpl-license.php. +https://opensource.org/licenses/gpl-license.php. THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c index 999eee1ed61c..a18b36b5422d 100644 --- a/net/sunrpc/sysctl.c +++ b/net/sunrpc/sysctl.c @@ -70,7 +70,13 @@ static int proc_do_xprt(struct ctl_table *table, int write, return 0; } len = svc_print_xprts(tmpbuf, sizeof(tmpbuf)); - return memory_read_from_buffer(buffer, *lenp, ppos, tmpbuf, len); + *lenp = memory_read_from_buffer(buffer, *lenp, ppos, tmpbuf, len); + + if (*lenp < 0) { + *lenp = 0; + return -EINVAL; + } + return 0; } static int @@ -108,8 +114,10 @@ proc_dodebug(struct ctl_table *table, int write, void *buffer, size_t *lenp, left -= (s - tmpbuf); if (left && !isspace(*s)) return -EINVAL; - while (left && isspace(*s)) - left--, s++; + while (left && isspace(*s)) { + left--; + s++; + } } else left = 0; *(unsigned int *) table->data = value; diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index be11d672b5b9..71e03b930b70 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -19,6 +19,9 @@ #include <linux/bvec.h> #include <trace/events/sunrpc.h> +static void _copy_to_pages(struct page **, size_t, const char *, size_t); + + /* * XDR functions for basic NFS types */ @@ -202,6 +205,88 @@ EXPORT_SYMBOL_GPL(xdr_inline_pages); */ /** + * _shift_data_left_pages + * @pages: vector of pages containing both the source and dest memory area. + * @pgto_base: page vector address of destination + * @pgfrom_base: page vector address of source + * @len: number of bytes to copy + * + * Note: the addresses pgto_base and pgfrom_base are both calculated in + * the same way: + * if a memory area starts at byte 'base' in page 'pages[i]', + * then its address is given as (i << PAGE_CACHE_SHIFT) + base + * Alse note: pgto_base must be < pgfrom_base, but the memory areas + * they point to may overlap. + */ +static void +_shift_data_left_pages(struct page **pages, size_t pgto_base, + size_t pgfrom_base, size_t len) +{ + struct page **pgfrom, **pgto; + char *vfrom, *vto; + size_t copy; + + BUG_ON(pgfrom_base <= pgto_base); + + pgto = pages + (pgto_base >> PAGE_SHIFT); + pgfrom = pages + (pgfrom_base >> PAGE_SHIFT); + + pgto_base &= ~PAGE_MASK; + pgfrom_base &= ~PAGE_MASK; + + do { + if (pgto_base >= PAGE_SIZE) { + pgto_base = 0; + pgto++; + } + if (pgfrom_base >= PAGE_SIZE){ + pgfrom_base = 0; + pgfrom++; + } + + copy = len; + if (copy > (PAGE_SIZE - pgto_base)) + copy = PAGE_SIZE - pgto_base; + if (copy > (PAGE_SIZE - pgfrom_base)) + copy = PAGE_SIZE - pgfrom_base; + + vto = kmap_atomic(*pgto); + if (*pgto != *pgfrom) { + vfrom = kmap_atomic(*pgfrom); + memcpy(vto + pgto_base, vfrom + pgfrom_base, copy); + kunmap_atomic(vfrom); + } else + memmove(vto + pgto_base, vto + pgfrom_base, copy); + flush_dcache_page(*pgto); + kunmap_atomic(vto); + + pgto_base += copy; + pgfrom_base += copy; + + } while ((len -= copy) != 0); +} + +static void +_shift_data_left_tail(struct xdr_buf *buf, unsigned int pgto, size_t len) +{ + struct kvec *tail = buf->tail; + + if (len > tail->iov_len) + len = tail->iov_len; + + _copy_to_pages(buf->pages, + buf->page_base + pgto, + (char *)tail->iov_base, + len); + tail->iov_len -= len; + + if (tail->iov_len > 0) + memmove((char *)tail->iov_base, + tail->iov_base + len, + tail->iov_len); +} + +/** * _shift_data_right_pages * @pages: vector of pages containing both the source and dest memory area. * @pgto_base: page vector address of destination @@ -266,6 +351,46 @@ _shift_data_right_pages(struct page **pages, size_t pgto_base, } while ((len -= copy) != 0); } +static unsigned int +_shift_data_right_tail(struct xdr_buf *buf, unsigned int pgfrom, size_t len) +{ + struct kvec *tail = buf->tail; + unsigned int tailbuf_len; + unsigned int result = 0; + size_t copy; + + tailbuf_len = buf->buflen - buf->head->iov_len - buf->page_len; + + /* Shift the tail first */ + if (tailbuf_len != 0) { + unsigned int free_space = tailbuf_len - tail->iov_len; + + if (len < free_space) + free_space = len; + if (len > free_space) + len = free_space; + + tail->iov_len += free_space; + copy = len; + + if (tail->iov_len > len) { + char *p = (char *)tail->iov_base + len; + memmove(p, tail->iov_base, tail->iov_len - free_space); + result += tail->iov_len - free_space; + } else + copy = tail->iov_len; + + /* Copy from the inlined pages into the tail */ + _copy_from_pages((char *)tail->iov_base, + buf->pages, + buf->page_base + pgfrom, + copy); + result += copy; + } + + return result; +} + /** * _copy_to_pages * @pages: array of pages @@ -351,6 +476,38 @@ _copy_from_pages(char *p, struct page **pages, size_t pgbase, size_t len) EXPORT_SYMBOL_GPL(_copy_from_pages); /** + * _zero_pages + * @pages: array of pages + * @pgbase: beginning page vector address + * @len: length + */ +static void +_zero_pages(struct page **pages, size_t pgbase, size_t len) +{ + struct page **page; + char *vpage; + size_t zero; + + page = pages + (pgbase >> PAGE_SHIFT); + pgbase &= ~PAGE_MASK; + + do { + zero = PAGE_SIZE - pgbase; + if (zero > len) + zero = len; + + vpage = kmap_atomic(*page); + memset(vpage + pgbase, 0, zero); + kunmap_atomic(vpage); + + flush_dcache_page(*page); + pgbase = 0; + page++; + + } while ((len -= zero) != 0); +} + +/** * xdr_shrink_bufhead * @buf: xdr_buf * @len: bytes to remove from buf->head[0] @@ -446,39 +603,13 @@ xdr_shrink_bufhead(struct xdr_buf *buf, size_t len) static unsigned int xdr_shrink_pagelen(struct xdr_buf *buf, size_t len) { - struct kvec *tail; - size_t copy; unsigned int pglen = buf->page_len; - unsigned int tailbuf_len; unsigned int result; - result = 0; - tail = buf->tail; if (len > buf->page_len) len = buf-> page_len; - tailbuf_len = buf->buflen - buf->head->iov_len - buf->page_len; - - /* Shift the tail first */ - if (tailbuf_len != 0) { - unsigned int free_space = tailbuf_len - tail->iov_len; - if (len < free_space) - free_space = len; - tail->iov_len += free_space; - - copy = len; - if (tail->iov_len > len) { - char *p = (char *)tail->iov_base + len; - memmove(p, tail->iov_base, tail->iov_len - len); - result += tail->iov_len - len; - } else - copy = tail->iov_len; - /* Copy from the inlined pages into the tail */ - _copy_from_pages((char *)tail->iov_base, - buf->pages, buf->page_base + pglen - len, - copy); - result += copy; - } + result = _shift_data_right_tail(buf, pglen - len, len); buf->page_len -= len; buf->buflen -= len; /* Have we truncated the message? */ @@ -506,6 +637,19 @@ unsigned int xdr_stream_pos(const struct xdr_stream *xdr) EXPORT_SYMBOL_GPL(xdr_stream_pos); /** + * xdr_page_pos - Return the current offset from the start of the xdr pages + * @xdr: pointer to struct xdr_stream + */ +unsigned int xdr_page_pos(const struct xdr_stream *xdr) +{ + unsigned int pos = xdr_stream_pos(xdr); + + WARN_ON(pos < xdr->buf->head[0].iov_len); + return pos - xdr->buf->head[0].iov_len; +} +EXPORT_SYMBOL_GPL(xdr_page_pos); + +/** * xdr_init_encode - Initialize a struct xdr_stream for sending data. * @xdr: pointer to xdr_stream struct * @buf: pointer to XDR buffer in which to encode data @@ -648,6 +792,51 @@ __be32 * xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes) } EXPORT_SYMBOL_GPL(xdr_reserve_space); + +/** + * xdr_reserve_space_vec - Reserves a large amount of buffer space for sending + * @xdr: pointer to xdr_stream + * @vec: pointer to a kvec array + * @nbytes: number of bytes to reserve + * + * Reserves enough buffer space to encode 'nbytes' of data and stores the + * pointers in 'vec'. The size argument passed to xdr_reserve_space() is + * determined based on the number of bytes remaining in the current page to + * avoid invalidating iov_base pointers when xdr_commit_encode() is called. + */ +int xdr_reserve_space_vec(struct xdr_stream *xdr, struct kvec *vec, size_t nbytes) +{ + int thislen; + int v = 0; + __be32 *p; + + /* + * svcrdma requires every READ payload to start somewhere + * in xdr->pages. + */ + if (xdr->iov == xdr->buf->head) { + xdr->iov = NULL; + xdr->end = xdr->p; + } + + while (nbytes) { + thislen = xdr->buf->page_len % PAGE_SIZE; + thislen = min_t(size_t, nbytes, PAGE_SIZE - thislen); + + p = xdr_reserve_space(xdr, thislen); + if (!p) + return -EIO; + + vec[v].iov_base = p; + vec[v].iov_len = thislen; + v++; + nbytes -= thislen; + } + + return v; +} +EXPORT_SYMBOL_GPL(xdr_reserve_space_vec); + /** * xdr_truncate_encode - truncate an encode buffer * @xdr: pointer to xdr_stream @@ -658,7 +847,7 @@ EXPORT_SYMBOL_GPL(xdr_reserve_space); * head, tail, and page lengths are adjusted to correspond. * * If this means moving xdr->p to a different buffer, we assume that - * that the end pointer should be set to the end of the current page, + * the end pointer should be set to the end of the current page, * except in the case of the head buffer when we assume the head * buffer's current length represents the end of the available buffer. * @@ -825,6 +1014,13 @@ static int xdr_set_page_base(struct xdr_stream *xdr, return 0; } +static void xdr_set_page(struct xdr_stream *xdr, unsigned int base, + unsigned int len) +{ + if (xdr_set_page_base(xdr, base, len) < 0) + xdr_set_iov(xdr, xdr->buf->tail, xdr->nwords << 2); +} + static void xdr_set_next_page(struct xdr_stream *xdr) { unsigned int newbase; @@ -832,8 +1028,7 @@ static void xdr_set_next_page(struct xdr_stream *xdr) newbase = (1 + xdr->page_ptr - xdr->buf->pages) << PAGE_SHIFT; newbase -= xdr->buf->page_base; - if (xdr_set_page_base(xdr, newbase, PAGE_SIZE) < 0) - xdr_set_iov(xdr, xdr->buf->tail, xdr->nwords << 2); + xdr_set_page(xdr, newbase, PAGE_SIZE); } static bool xdr_set_next_buffer(struct xdr_stream *xdr) @@ -841,8 +1036,7 @@ static bool xdr_set_next_buffer(struct xdr_stream *xdr) if (xdr->page_ptr != NULL) xdr_set_next_page(xdr); else if (xdr->iov == xdr->buf->head) { - if (xdr_set_page_base(xdr, 0, PAGE_SIZE) < 0) - xdr_set_iov(xdr, xdr->buf->tail, xdr->nwords << 2); + xdr_set_page(xdr, 0, PAGE_SIZE); } return xdr->p != xdr->end; } @@ -979,26 +1173,33 @@ out_overflow: } EXPORT_SYMBOL_GPL(xdr_inline_decode); -static unsigned int xdr_align_pages(struct xdr_stream *xdr, unsigned int len) +static void xdr_realign_pages(struct xdr_stream *xdr) { struct xdr_buf *buf = xdr->buf; - struct kvec *iov; - unsigned int nwords = XDR_QUADLEN(len); + struct kvec *iov = buf->head; unsigned int cur = xdr_stream_pos(xdr); unsigned int copied, offset; - if (xdr->nwords == 0) - return 0; - /* Realign pages to current pointer position */ - iov = buf->head; if (iov->iov_len > cur) { offset = iov->iov_len - cur; copied = xdr_shrink_bufhead(buf, offset); trace_rpc_xdr_alignment(xdr, offset, copied); xdr->nwords = XDR_QUADLEN(buf->len - cur); } +} + +static unsigned int xdr_align_pages(struct xdr_stream *xdr, unsigned int len) +{ + struct xdr_buf *buf = xdr->buf; + unsigned int nwords = XDR_QUADLEN(len); + unsigned int cur = xdr_stream_pos(xdr); + unsigned int copied, offset; + + if (xdr->nwords == 0) + return 0; + xdr_realign_pages(xdr); if (nwords > xdr->nwords) { nwords = xdr->nwords; len = nwords << 2; @@ -1057,6 +1258,79 @@ unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len) } EXPORT_SYMBOL_GPL(xdr_read_pages); +uint64_t xdr_align_data(struct xdr_stream *xdr, uint64_t offset, uint32_t length) +{ + struct xdr_buf *buf = xdr->buf; + unsigned int from, bytes; + unsigned int shift = 0; + + if ((offset + length) < offset || + (offset + length) > buf->page_len) + length = buf->page_len - offset; + + xdr_realign_pages(xdr); + from = xdr_page_pos(xdr); + bytes = xdr->nwords << 2; + if (length < bytes) + bytes = length; + + /* Move page data to the left */ + if (from > offset) { + shift = min_t(unsigned int, bytes, buf->page_len - from); + _shift_data_left_pages(buf->pages, + buf->page_base + offset, + buf->page_base + from, + shift); + bytes -= shift; + + /* Move tail data into the pages, if necessary */ + if (bytes > 0) + _shift_data_left_tail(buf, offset + shift, bytes); + } + + xdr->nwords -= XDR_QUADLEN(length); + xdr_set_page(xdr, from + length, PAGE_SIZE); + return length; +} +EXPORT_SYMBOL_GPL(xdr_align_data); + +uint64_t xdr_expand_hole(struct xdr_stream *xdr, uint64_t offset, uint64_t length) +{ + struct xdr_buf *buf = xdr->buf; + unsigned int bytes; + unsigned int from; + unsigned int truncated = 0; + + if ((offset + length) < offset || + (offset + length) > buf->page_len) + length = buf->page_len - offset; + + xdr_realign_pages(xdr); + from = xdr_page_pos(xdr); + bytes = xdr->nwords << 2; + + if (offset + length + bytes > buf->page_len) { + unsigned int shift = (offset + length + bytes) - buf->page_len; + unsigned int res = _shift_data_right_tail(buf, from + bytes - shift, shift); + truncated = shift - res; + xdr->nwords -= XDR_QUADLEN(truncated); + bytes -= shift; + } + + /* Now move the page data over and zero pages */ + if (bytes > 0) + _shift_data_right_pages(buf->pages, + buf->page_base + offset + length, + buf->page_base + from, + bytes); + _zero_pages(buf->pages, buf->page_base + offset, length); + + buf->len += length - (from - offset) - truncated; + xdr_set_page(xdr, offset + length, PAGE_SIZE); + return length; +} +EXPORT_SYMBOL_GPL(xdr_expand_hole); + /** * xdr_enter_page - decode data from the XDR page * @xdr: pointer to xdr_stream struct diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 5a8e47bbfb9f..f6c17e75f20e 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -834,8 +834,7 @@ void xprt_connect(struct rpc_task *task) { struct rpc_xprt *xprt = task->tk_rqstp->rq_xprt; - dprintk("RPC: %5u xprt_connect xprt %p %s connected\n", task->tk_pid, - xprt, (xprt_connected(xprt) ? "is" : "is not")); + trace_xprt_connect(xprt); if (!xprt_bound(xprt)) { task->tk_status = -EAGAIN; @@ -1131,8 +1130,6 @@ void xprt_complete_rqst(struct rpc_task *task, int copied) struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; - trace_xprt_complete_rqst(xprt, req->rq_xid, copied); - xprt->stat.recvs++; req->rq_private_buf.len = copied; @@ -1269,7 +1266,6 @@ xprt_request_enqueue_transmit(struct rpc_task *task) /* Note: req is added _before_ pos */ list_add_tail(&req->rq_xmit, &pos->rq_xmit); INIT_LIST_HEAD(&req->rq_xmit2); - trace_xprt_enq_xmit(task, 1); goto out; } } else if (RPC_IS_SWAPPER(task)) { @@ -1281,7 +1277,6 @@ xprt_request_enqueue_transmit(struct rpc_task *task) /* Note: req is added _before_ pos */ list_add_tail(&req->rq_xmit, &pos->rq_xmit); INIT_LIST_HEAD(&req->rq_xmit2); - trace_xprt_enq_xmit(task, 2); goto out; } } else if (!req->rq_seqno) { @@ -1290,13 +1285,11 @@ xprt_request_enqueue_transmit(struct rpc_task *task) continue; list_add_tail(&req->rq_xmit2, &pos->rq_xmit2); INIT_LIST_HEAD(&req->rq_xmit); - trace_xprt_enq_xmit(task, 3); goto out; } } list_add_tail(&req->rq_xmit, &xprt->xmit_queue); INIT_LIST_HEAD(&req->rq_xmit2); - trace_xprt_enq_xmit(task, 4); out: set_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate); spin_unlock(&xprt->queue_lock); @@ -1414,9 +1407,9 @@ bool xprt_prepare_transmit(struct rpc_task *task) struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; - dprintk("RPC: %5u xprt_prepare_transmit\n", task->tk_pid); - if (!xprt_lock_write(xprt, task)) { + trace_xprt_transmit_queued(xprt, task); + /* Race breaker: someone may have transmitted us */ if (!test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate)) rpc_wake_up_queued_task_set_status(&xprt->sending, @@ -1520,10 +1513,13 @@ xprt_transmit(struct rpc_task *task) { struct rpc_rqst *next, *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; - int status; + int counter, status; spin_lock(&xprt->queue_lock); + counter = 0; while (!list_empty(&xprt->xmit_queue)) { + if (++counter == 20) + break; next = list_first_entry(&xprt->xmit_queue, struct rpc_rqst, rq_xmit); xprt_pin_rqst(next); @@ -1531,7 +1527,6 @@ xprt_transmit(struct rpc_task *task) status = xprt_request_transmit(next, task); if (status == -EBADMSG && next != req) status = 0; - cond_resched(); spin_lock(&xprt->queue_lock); xprt_unpin_rqst(next); if (status == 0) { @@ -1747,8 +1742,8 @@ xprt_request_init(struct rpc_task *task) req->rq_rcv_buf.bvec = NULL; req->rq_release_snd_buf = NULL; xprt_init_majortimeo(task, req); - dprintk("RPC: %5u reserved req %p xid %08x\n", task->tk_pid, - req, ntohl(req->rq_xid)); + + trace_xprt_reserve(req); } static void @@ -1838,7 +1833,6 @@ void xprt_release(struct rpc_task *task) if (req->rq_release_snd_buf) req->rq_release_snd_buf(req); - dprintk("RPC: %5u release request %p\n", task->tk_pid, req); if (likely(!bc_prealloc(req))) xprt->ops->free_slot(xprt, req); else diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 7f94c9a19fd3..44888f5badef 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -124,7 +124,7 @@ int frwr_mr_init(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr *mr) if (IS_ERR(frmr)) goto out_mr_err; - sg = kcalloc(depth, sizeof(*sg), GFP_NOFS); + sg = kmalloc_array(depth, sizeof(*sg), GFP_NOFS); if (!sg) goto out_list_err; diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index fe54cbe97a46..80a0c0e87590 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -137,7 +137,7 @@ static int svc_rdma_rw_ctx_init(struct svcxprt_rdma *rdma, } /* A chunk context tracks all I/O for moving one Read or Write - * chunk. This is a a set of rdma_rw's that handle data movement + * chunk. This is a set of rdma_rw's that handle data movement * for all segments of one chunk. * * These are small, acquired with a single allocator call, and diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 7b94d971feb3..c3d588b149aa 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -638,10 +638,11 @@ static int svc_rdma_pull_up_reply_msg(struct svcxprt_rdma *rdma, while (remaining) { len = min_t(u32, PAGE_SIZE - pageoff, remaining); - memcpy(dst, page_address(*ppages), len); + memcpy(dst, page_address(*ppages) + pageoff, len); remaining -= len; dst += len; pageoff = 0; + ppages++; } } diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 053c8ab1265a..8915e42240d3 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -413,9 +413,6 @@ xprt_rdma_set_port(struct rpc_xprt *xprt, u16 port) kfree(xprt->address_strings[RPC_DISPLAY_HEX_PORT]); snprintf(buf, sizeof(buf), "%4hx", port); xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL); - - trace_xprtrdma_op_setport(container_of(xprt, struct rpcrdma_xprt, - rx_xprt)); } /** @@ -586,11 +583,9 @@ xprt_rdma_allocate(struct rpc_task *task) rqst->rq_buffer = rdmab_data(req->rl_sendbuf); rqst->rq_rbuffer = rdmab_data(req->rl_recvbuf); - trace_xprtrdma_op_allocate(task, req); return 0; out_fail: - trace_xprtrdma_op_allocate(task, NULL); return -ENOMEM; } @@ -607,8 +602,6 @@ xprt_rdma_free(struct rpc_task *task) struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(rqst->rq_xprt); struct rpcrdma_req *req = rpcr_to_rdmar(rqst); - trace_xprtrdma_op_free(task, req); - if (!list_empty(&req->rl_registered)) frwr_unmap_sync(r_xprt, req); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 554e1bb4c1c7..7090bbee0ec5 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -762,10 +762,7 @@ static int xs_nospace(struct rpc_rqst *req) struct sock *sk = transport->inet; int ret = -EAGAIN; - dprintk("RPC: %5u xmit incomplete (%u left of %u)\n", - req->rq_task->tk_pid, - req->rq_slen - transport->xmit.offset, - req->rq_slen); + trace_rpc_socket_nospace(req, transport); /* Protect against races with write_space */ spin_lock(&xprt->transport_lock); diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 940d176e0e87..d4beca895992 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -108,6 +108,8 @@ static void tipc_bcbase_select_primary(struct net *net) { struct tipc_bc_base *bb = tipc_bc_base(net); int all_dests = tipc_link_bc_peers(bb->link); + int max_win = tipc_link_max_win(bb->link); + int min_win = tipc_link_min_win(bb->link); int i, mtu, prim; bb->primary_bearer = INVALID_BEARER_ID; @@ -121,8 +123,12 @@ static void tipc_bcbase_select_primary(struct net *net) continue; mtu = tipc_bearer_mtu(net, i); - if (mtu < tipc_link_mtu(bb->link)) + if (mtu < tipc_link_mtu(bb->link)) { tipc_link_set_mtu(bb->link, mtu); + tipc_link_set_queue_limits(bb->link, + min_win, + max_win); + } bb->bcast_support &= tipc_bearer_bcast_support(net, i); if (bb->dests[i] < all_dests) continue; @@ -585,7 +591,7 @@ static int tipc_bc_link_set_queue_limits(struct net *net, u32 max_win) if (max_win > TIPC_MAX_LINK_WIN) return -EINVAL; tipc_bcast_lock(net); - tipc_link_set_queue_limits(l, BCLINK_WIN_MIN, max_win); + tipc_link_set_queue_limits(l, tipc_link_min_win(l), max_win); tipc_bcast_unlock(net); return 0; } diff --git a/net/tipc/core.c b/net/tipc/core.c index 4f6dc74adf45..c2ff42900b53 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -60,6 +60,7 @@ static int __net_init tipc_init_net(struct net *net) tn->trial_addr = 0; tn->addr_trial_end = 0; tn->capabilities = TIPC_NODE_CAPABILITIES; + INIT_WORK(&tn->final_work.work, tipc_net_finalize_work); memset(tn->node_id, 0, sizeof(tn->node_id)); memset(tn->node_id_string, 0, sizeof(tn->node_id_string)); tn->mon_threshold = TIPC_DEF_MON_THRESHOLD; @@ -107,8 +108,13 @@ out_crypto: static void __net_exit tipc_exit_net(struct net *net) { + struct tipc_net *tn = tipc_net(net); + tipc_detach_loopback(net); + /* Make sure the tipc_net_finalize_work() finished */ + cancel_work_sync(&tn->final_work.work); tipc_net_stop(net); + tipc_bcast_stop(net); tipc_nametbl_stop(net); tipc_sk_rht_destroy(net); diff --git a/net/tipc/core.h b/net/tipc/core.h index 631d83c9705f..1d57a4d3b05e 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -90,6 +90,12 @@ extern unsigned int tipc_net_id __read_mostly; extern int sysctl_tipc_rmem[3] __read_mostly; extern int sysctl_tipc_named_timeout __read_mostly; +struct tipc_net_work { + struct work_struct work; + struct net *net; + u32 addr; +}; + struct tipc_net { u8 node_id[NODE_ID_LEN]; u32 node_addr; @@ -143,6 +149,8 @@ struct tipc_net { /* TX crypto handler */ struct tipc_crypto *crypto_tx; #endif + /* Work item for net finalize */ + struct tipc_net_work final_work; }; static inline struct tipc_net *tipc_net(struct net *net) diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index 7c523dc81575..740ab9ae41a6 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -36,22 +36,28 @@ #include <crypto/aead.h> #include <crypto/aes.h> +#include <crypto/rng.h> #include "crypto.h" +#include "msg.h" +#include "bcast.h" -#define TIPC_TX_PROBE_LIM msecs_to_jiffies(1000) /* > 1s */ -#define TIPC_TX_LASTING_LIM msecs_to_jiffies(120000) /* 2 mins */ +#define TIPC_TX_GRACE_PERIOD msecs_to_jiffies(5000) /* 5s */ +#define TIPC_TX_LASTING_TIME msecs_to_jiffies(10000) /* 10s */ #define TIPC_RX_ACTIVE_LIM msecs_to_jiffies(3000) /* 3s */ -#define TIPC_RX_PASSIVE_LIM msecs_to_jiffies(180000) /* 3 mins */ +#define TIPC_RX_PASSIVE_LIM msecs_to_jiffies(15000) /* 15s */ + #define TIPC_MAX_TFMS_DEF 10 #define TIPC_MAX_TFMS_LIM 1000 +#define TIPC_REKEYING_INTV_DEF (60 * 24) /* default: 1 day */ + /** * TIPC Key ids */ enum { - KEY_UNUSED = 0, - KEY_MIN, - KEY_1 = KEY_MIN, + KEY_MASTER = 0, + KEY_MIN = KEY_MASTER, + KEY_1 = 1, KEY_2, KEY_3, KEY_MAX = KEY_3, @@ -81,6 +87,8 @@ static const char *hstats[MAX_STATS] = {"ok", "nok", "async", "async_ok", /* Max TFMs number per key */ int sysctl_tipc_max_tfms __read_mostly = TIPC_MAX_TFMS_DEF; +/* Key exchange switch, default: on */ +int sysctl_tipc_key_exchange_enabled __read_mostly = 1; /** * struct tipc_key - TIPC keys' status indicator @@ -132,6 +140,8 @@ struct tipc_tfm { * @mode: crypto mode is applied to the key * @hint[]: a hint for user key * @rcu: struct rcu_head + * @key: the aead key + * @gen: the key's generation * @seqno: the key seqno (cluster scope) * @refcnt: the key reference counter */ @@ -144,8 +154,10 @@ struct tipc_aead { u32 salt; u8 authsize; u8 mode; - char hint[TIPC_AEAD_HINT_LEN + 1]; + char hint[2 * TIPC_AEAD_HINT_LEN + 1]; struct rcu_head rcu; + struct tipc_aead_key *key; + u16 gen; atomic64_t seqno ____cacheline_aligned; refcount_t refcnt ____cacheline_aligned; @@ -165,26 +177,56 @@ struct tipc_crypto_stats { * @node: TIPC node (RX) * @aead: array of pointers to AEAD keys for encryption/decryption * @peer_rx_active: replicated peer RX active key index + * @key_gen: TX/RX key generation * @key: the key states - * @working: the crypto is working or not + * @skey_mode: session key's mode + * @skey: received session key + * @wq: common workqueue on TX crypto + * @work: delayed work sched for TX/RX + * @key_distr: key distributing state + * @rekeying_intv: rekeying interval (in minutes) * @stats: the crypto statistics + * @name: the crypto name * @sndnxt: the per-peer sndnxt (TX) * @timer1: general timer 1 (jiffies) - * @timer2: general timer 1 (jiffies) + * @timer2: general timer 2 (jiffies) + * @working: the crypto is working or not + * @key_master: flag indicates if master key exists + * @legacy_user: flag indicates if a peer joins w/o master key (for bwd comp.) + * @nokey: no key indication * @lock: tipc_key lock */ struct tipc_crypto { struct net *net; struct tipc_node *node; - struct tipc_aead __rcu *aead[KEY_MAX + 1]; /* key[0] is UNUSED */ + struct tipc_aead __rcu *aead[KEY_MAX + 1]; atomic_t peer_rx_active; + u16 key_gen; struct tipc_key key; - u8 working:1; + u8 skey_mode; + struct tipc_aead_key *skey; + struct workqueue_struct *wq; + struct delayed_work work; +#define KEY_DISTR_SCHED 1 +#define KEY_DISTR_COMPL 2 + atomic_t key_distr; + u32 rekeying_intv; + struct tipc_crypto_stats __percpu *stats; + char name[48]; atomic64_t sndnxt ____cacheline_aligned; unsigned long timer1; unsigned long timer2; + union { + struct { + u8 working:1; + u8 key_master:1; + u8 legacy_user:1; + u8 nokey: 1; + }; + u8 flags; + }; spinlock_t lock; /* crypto lock */ } ____cacheline_aligned; @@ -234,23 +276,35 @@ static inline void tipc_crypto_key_set_state(struct tipc_crypto *c, u8 new_active, u8 new_pending); static int tipc_crypto_key_attach(struct tipc_crypto *c, - struct tipc_aead *aead, u8 pos); + struct tipc_aead *aead, u8 pos, + bool master_key); static bool tipc_crypto_key_try_align(struct tipc_crypto *rx, u8 new_pending); static struct tipc_aead *tipc_crypto_key_pick_tx(struct tipc_crypto *tx, struct tipc_crypto *rx, - struct sk_buff *skb); -static void tipc_crypto_key_synch(struct tipc_crypto *rx, u8 new_rx_active, - struct tipc_msg *hdr); + struct sk_buff *skb, + u8 tx_key); +static void tipc_crypto_key_synch(struct tipc_crypto *rx, struct sk_buff *skb); static int tipc_crypto_key_revoke(struct net *net, u8 tx_key); +static inline void tipc_crypto_clone_msg(struct net *net, struct sk_buff *_skb, + struct tipc_bearer *b, + struct tipc_media_addr *dst, + struct tipc_node *__dnode, u8 type); static void tipc_crypto_rcv_complete(struct net *net, struct tipc_aead *aead, struct tipc_bearer *b, struct sk_buff **skb, int err); static void tipc_crypto_do_cmd(struct net *net, int cmd); static char *tipc_crypto_key_dump(struct tipc_crypto *c, char *buf); -#ifdef TIPC_CRYPTO_DEBUG static char *tipc_key_change_dump(struct tipc_key old, struct tipc_key new, char *buf); -#endif +static int tipc_crypto_key_xmit(struct net *net, struct tipc_aead_key *skey, + u16 gen, u8 mode, u32 dnode); +static bool tipc_crypto_key_rcv(struct tipc_crypto *rx, struct tipc_msg *hdr); +static void tipc_crypto_work_tx(struct work_struct *work); +static void tipc_crypto_work_rx(struct work_struct *work); +static int tipc_aead_key_generate(struct tipc_aead_key *skey); + +#define is_tx(crypto) (!(crypto)->node) +#define is_rx(crypto) (!is_tx(crypto)) #define key_next(cur) ((cur) % KEY_MAX + 1) @@ -271,30 +325,55 @@ do { \ /** * tipc_aead_key_validate - Validate a AEAD user key */ -int tipc_aead_key_validate(struct tipc_aead_key *ukey) +int tipc_aead_key_validate(struct tipc_aead_key *ukey, struct genl_info *info) { int keylen; /* Check if algorithm exists */ if (unlikely(!crypto_has_alg(ukey->alg_name, 0, 0))) { - pr_info("Not found cipher: \"%s\"!\n", ukey->alg_name); + GENL_SET_ERR_MSG(info, "unable to load the algorithm (module existed?)"); return -ENODEV; } /* Currently, we only support the "gcm(aes)" cipher algorithm */ - if (strcmp(ukey->alg_name, "gcm(aes)")) + if (strcmp(ukey->alg_name, "gcm(aes)")) { + GENL_SET_ERR_MSG(info, "not supported yet the algorithm"); return -ENOTSUPP; + } /* Check if key size is correct */ keylen = ukey->keylen - TIPC_AES_GCM_SALT_SIZE; if (unlikely(keylen != TIPC_AES_GCM_KEY_SIZE_128 && keylen != TIPC_AES_GCM_KEY_SIZE_192 && - keylen != TIPC_AES_GCM_KEY_SIZE_256)) - return -EINVAL; + keylen != TIPC_AES_GCM_KEY_SIZE_256)) { + GENL_SET_ERR_MSG(info, "incorrect key length (20, 28 or 36 octets?)"); + return -EKEYREJECTED; + } return 0; } +/** + * tipc_aead_key_generate - Generate new session key + * @skey: input/output key with new content + * + * Return: 0 in case of success, otherwise < 0 + */ +static int tipc_aead_key_generate(struct tipc_aead_key *skey) +{ + int rc = 0; + + /* Fill the key's content with a random value via RNG cipher */ + rc = crypto_get_default_rng(); + if (likely(!rc)) { + rc = crypto_rng_get_bytes(crypto_default_rng, skey->key, + skey->keylen); + crypto_put_default_rng(); + } + + return rc; +} + static struct tipc_aead *tipc_aead_get(struct tipc_aead __rcu *aead) { struct tipc_aead *tmp; @@ -339,6 +418,7 @@ static void tipc_aead_free(struct rcu_head *rp) kfree(head); } free_percpu(aead->tfm_entry); + kfree_sensitive(aead->key); kfree(aead); } @@ -501,14 +581,15 @@ static int tipc_aead_init(struct tipc_aead **aead, struct tipc_aead_key *ukey, return err; } - /* Copy some chars from the user key as a hint */ - memcpy(tmp->hint, ukey->key, TIPC_AEAD_HINT_LEN); - tmp->hint[TIPC_AEAD_HINT_LEN] = '\0'; + /* Form a hex string of some last bytes as the key's hint */ + bin2hex(tmp->hint, ukey->key + keylen - TIPC_AEAD_HINT_LEN, + TIPC_AEAD_HINT_LEN); /* Initialize the other data */ tmp->mode = mode; tmp->cloned = NULL; tmp->authsize = TIPC_AES_GCM_TAG_SIZE; + tmp->key = kmemdup(ukey, tipc_aead_key_size(ukey), GFP_KERNEL); memcpy(&tmp->salt, ukey->key + keylen, TIPC_AES_GCM_SALT_SIZE); atomic_set(&tmp->users, 0); atomic64_set(&tmp->seqno, 0); @@ -663,13 +744,11 @@ static int tipc_aead_encrypt(struct tipc_aead *aead, struct sk_buff *skb, * but there is no frag_list, it should be still fine! * Otherwise, we must cow it to be a writable buffer with the tailroom. */ -#ifdef TIPC_CRYPTO_DEBUG SKB_LINEAR_ASSERT(skb); if (tailen > skb_tailroom(skb)) { - pr_warn("TX: skb tailroom is not enough: %d, requires: %d\n", - skb_tailroom(skb), tailen); + pr_debug("TX(): skb tailroom is not enough: %d, requires: %d\n", + skb_tailroom(skb), tailen); } -#endif if (unlikely(!skb_cloned(skb) && tailen <= skb_tailroom(skb))) { nsg = 1; @@ -940,8 +1019,6 @@ bool tipc_ehdr_validate(struct sk_buff *skb) return false; if (unlikely(skb->len <= ehsz + TIPC_AES_GCM_TAG_SIZE)) return false; - if (unlikely(!ehdr->tx_key)) - return false; return true; } @@ -994,6 +1071,8 @@ static int tipc_ehdr_build(struct net *net, struct tipc_aead *aead, ehdr->tx_key = tx_key; ehdr->destined = (__rx) ? 1 : 0; ehdr->rx_key_active = (__rx) ? __rx->key.active : 0; + ehdr->rx_nokey = (__rx) ? __rx->nokey : 0; + ehdr->master_key = aead->crypto->key_master; ehdr->reserved_1 = 0; ehdr->reserved_2 = 0; @@ -1019,23 +1098,16 @@ static inline void tipc_crypto_key_set_state(struct tipc_crypto *c, u8 new_active, u8 new_pending) { -#ifdef TIPC_CRYPTO_DEBUG struct tipc_key old = c->key; char buf[32]; -#endif c->key.keys = ((new_passive & KEY_MASK) << (KEY_BITS * 2)) | ((new_active & KEY_MASK) << (KEY_BITS)) | ((new_pending & KEY_MASK)); -#ifdef TIPC_CRYPTO_DEBUG - pr_info("%s(%s): key changing %s ::%pS\n", - (c->node) ? "RX" : "TX", - (c->node) ? tipc_node_get_id_str(c->node) : - tipc_own_id_string(c->net), - tipc_key_change_dump(old, c->key, buf), - __builtin_return_address(0)); -#endif + pr_debug("%s: key changing %s ::%pS\n", c->name, + tipc_key_change_dump(old, c->key, buf), + __builtin_return_address(0)); } /** @@ -1043,6 +1115,7 @@ static inline void tipc_crypto_key_set_state(struct tipc_crypto *c, * @c: TIPC crypto to which new key is attached * @ukey: the user key * @mode: the key mode (CLUSTER_KEY or PER_NODE_KEY) + * @master_key: specify this is a cluster master key * * A new TIPC AEAD key will be allocated and initiated with the specified user * key, then attached to the TIPC crypto. @@ -1050,7 +1123,7 @@ static inline void tipc_crypto_key_set_state(struct tipc_crypto *c, * Return: new key id in case of success, otherwise: < 0 */ int tipc_crypto_key_init(struct tipc_crypto *c, struct tipc_aead_key *ukey, - u8 mode) + u8 mode, bool master_key) { struct tipc_aead *aead = NULL; int rc = 0; @@ -1060,17 +1133,11 @@ int tipc_crypto_key_init(struct tipc_crypto *c, struct tipc_aead_key *ukey, /* Attach it to the crypto */ if (likely(!rc)) { - rc = tipc_crypto_key_attach(c, aead, 0); + rc = tipc_crypto_key_attach(c, aead, 0, master_key); if (rc < 0) tipc_aead_free(&aead->rcu); } - pr_info("%s(%s): key initiating, rc %d!\n", - (c->node) ? "RX" : "TX", - (c->node) ? tipc_node_get_id_str(c->node) : - tipc_own_id_string(c->net), - rc); - return rc; } @@ -1079,58 +1146,58 @@ int tipc_crypto_key_init(struct tipc_crypto *c, struct tipc_aead_key *ukey, * @c: TIPC crypto to which the new AEAD key is attached * @aead: the new AEAD key pointer * @pos: desired slot in the crypto key array, = 0 if any! + * @master_key: specify this is a cluster master key * * Return: new key id in case of success, otherwise: -EBUSY */ static int tipc_crypto_key_attach(struct tipc_crypto *c, - struct tipc_aead *aead, u8 pos) + struct tipc_aead *aead, u8 pos, + bool master_key) { - u8 new_pending, new_passive, new_key; struct tipc_key key; int rc = -EBUSY; + u8 new_key; spin_lock_bh(&c->lock); key = c->key; + if (master_key) { + new_key = KEY_MASTER; + goto attach; + } if (key.active && key.passive) goto exit; - if (key.passive && !tipc_aead_users(c->aead[key.passive])) - goto exit; if (key.pending) { - if (pos) - goto exit; if (tipc_aead_users(c->aead[key.pending]) > 0) goto exit; + /* if (pos): ok with replacing, will be aligned when needed */ /* Replace it */ - new_pending = key.pending; - new_passive = key.passive; - new_key = new_pending; + new_key = key.pending; } else { if (pos) { if (key.active && pos != key_next(key.active)) { - new_pending = key.pending; - new_passive = pos; - new_key = new_passive; + key.passive = pos; + new_key = pos; goto attach; } else if (!key.active && !key.passive) { - new_pending = pos; - new_passive = key.passive; - new_key = new_pending; + key.pending = pos; + new_key = pos; goto attach; } } - new_pending = key_next(key.active ?: key.passive); - new_passive = key.passive; - new_key = new_pending; + key.pending = key_next(key.active ?: key.passive); + new_key = key.pending; } attach: aead->crypto = c; - tipc_crypto_key_set_state(c, new_passive, key.active, new_pending); + aead->gen = (is_tx(c)) ? ++c->key_gen : c->key_gen; tipc_aead_rcu_replace(c->aead[new_key], aead, &c->lock); - + if (likely(c->key.keys != key.keys)) + tipc_crypto_key_set_state(c, key.passive, key.active, + key.pending); c->working = 1; - c->timer1 = jiffies; - c->timer2 = jiffies; + c->nokey = 0; + c->key_master |= master_key; rc = new_key; exit: @@ -1140,14 +1207,33 @@ exit: void tipc_crypto_key_flush(struct tipc_crypto *c) { + struct tipc_crypto *tx, *rx; int k; spin_lock_bh(&c->lock); - c->working = 0; + if (is_rx(c)) { + /* Try to cancel pending work */ + rx = c; + tx = tipc_net(rx->net)->crypto_tx; + if (cancel_delayed_work(&rx->work)) { + kfree(rx->skey); + rx->skey = NULL; + atomic_xchg(&rx->key_distr, 0); + tipc_node_put(rx->node); + } + /* RX stopping => decrease TX key users if any */ + k = atomic_xchg(&rx->peer_rx_active, 0); + if (k) { + tipc_aead_users_dec(tx->aead[k], 0); + /* Mark the point TX key users changed */ + tx->timer1 = jiffies; + } + } + + c->flags = 0; tipc_crypto_key_set_state(c, 0, 0, 0); for (k = KEY_MIN; k <= KEY_MAX; k++) tipc_crypto_key_detach(c->aead[k], &c->lock); - atomic_set(&c->peer_rx_active, 0); atomic64_set(&c->sndnxt, 0); spin_unlock_bh(&c->lock); } @@ -1206,7 +1292,8 @@ static bool tipc_crypto_key_try_align(struct tipc_crypto *rx, u8 new_pending) rcu_assign_pointer(rx->aead[new_passive], tmp2); refcount_set(&tmp1->refcnt, 1); aligned = true; - pr_info("RX(%s): key is aligned!\n", tipc_node_get_id_str(rx->node)); + pr_info_ratelimited("%s: key[%d] -> key[%d]\n", rx->name, key.pending, + new_pending); exit: spin_unlock(&rx->lock); @@ -1218,6 +1305,7 @@ exit: * @tx: TX crypto handle * @rx: RX crypto handle (can be NULL) * @skb: the message skb which will be decrypted later + * @tx_key: peer TX key id * * This function looks up the existing TX keys and pick one which is suitable * for the message decryption, that must be a cluster key and not used before @@ -1227,7 +1315,8 @@ exit: */ static struct tipc_aead *tipc_crypto_key_pick_tx(struct tipc_crypto *tx, struct tipc_crypto *rx, - struct sk_buff *skb) + struct sk_buff *skb, + u8 tx_key) { struct tipc_skb_cb *skb_cb = TIPC_SKB_CB(skb); struct tipc_aead *aead = NULL; @@ -1246,6 +1335,10 @@ static struct tipc_aead *tipc_crypto_key_pick_tx(struct tipc_crypto *tx, /* Pick one TX key */ spin_lock(&tx->lock); + if (tx_key == KEY_MASTER) { + aead = tipc_aead_rcu_ptr(tx->aead[KEY_MASTER], &tx->lock); + goto done; + } do { k = (i == 0) ? key.pending : ((i == 1) ? key.active : key.passive); @@ -1265,9 +1358,12 @@ static struct tipc_aead *tipc_crypto_key_pick_tx(struct tipc_crypto *tx, skb->next = skb_clone(skb, GFP_ATOMIC); if (unlikely(!skb->next)) pr_warn("Failed to clone skb for next round if any\n"); - WARN_ON(!refcount_inc_not_zero(&aead->refcnt)); break; } while (++i < 3); + +done: + if (likely(aead)) + WARN_ON(!refcount_inc_not_zero(&aead->refcnt)); spin_unlock(&tx->lock); return aead; @@ -1276,53 +1372,73 @@ static struct tipc_aead *tipc_crypto_key_pick_tx(struct tipc_crypto *tx, /** * tipc_crypto_key_synch: Synch own key data according to peer key status * @rx: RX crypto handle - * @new_rx_active: latest RX active key from peer - * @hdr: TIPCv2 message + * @skb: TIPCv2 message buffer (incl. the ehdr from peer) * * This function updates the peer node related data as the peer RX active key * has changed, so the number of TX keys' users on this node are increased and * decreased correspondingly. * + * It also considers if peer has no key, then we need to make own master key + * (if any) taking over i.e. starting grace period and also trigger key + * distributing process. + * * The "per-peer" sndnxt is also reset when the peer key has switched. */ -static void tipc_crypto_key_synch(struct tipc_crypto *rx, u8 new_rx_active, - struct tipc_msg *hdr) +static void tipc_crypto_key_synch(struct tipc_crypto *rx, struct sk_buff *skb) { - struct net *net = rx->net; - struct tipc_crypto *tx = tipc_net(net)->crypto_tx; - u8 cur_rx_active; + struct tipc_ehdr *ehdr = (struct tipc_ehdr *)skb_network_header(skb); + struct tipc_crypto *tx = tipc_net(rx->net)->crypto_tx; + struct tipc_msg *hdr = buf_msg(skb); + u32 self = tipc_own_addr(rx->net); + u8 cur, new; + unsigned long delay; - /* TX might be even not ready yet */ - if (unlikely(!tx->key.active && !tx->key.pending)) - return; + /* Update RX 'key_master' flag according to peer, also mark "legacy" if + * a peer has no master key. + */ + rx->key_master = ehdr->master_key; + if (!rx->key_master) + tx->legacy_user = 1; - cur_rx_active = atomic_read(&rx->peer_rx_active); - if (likely(cur_rx_active == new_rx_active)) + /* For later cases, apply only if message is destined to this node */ + if (!ehdr->destined || msg_short(hdr) || msg_destnode(hdr) != self) return; - /* Make sure this message destined for this node */ - if (unlikely(msg_short(hdr) || - msg_destnode(hdr) != tipc_own_addr(net))) - return; + /* Case 1: Peer has no keys, let's make master key take over */ + if (ehdr->rx_nokey) { + /* Set or extend grace period */ + tx->timer2 = jiffies; + /* Schedule key distributing for the peer if not yet */ + if (tx->key.keys && + !atomic_cmpxchg(&rx->key_distr, 0, KEY_DISTR_SCHED)) { + get_random_bytes(&delay, 2); + delay %= 5; + delay = msecs_to_jiffies(500 * ++delay); + if (queue_delayed_work(tx->wq, &rx->work, delay)) + tipc_node_get(rx->node); + } + } else { + /* Cancel a pending key distributing if any */ + atomic_xchg(&rx->key_distr, 0); + } - /* Peer RX active key has changed, try to update owns' & TX users */ - if (atomic_cmpxchg(&rx->peer_rx_active, - cur_rx_active, - new_rx_active) == cur_rx_active) { - if (new_rx_active) - tipc_aead_users_inc(tx->aead[new_rx_active], INT_MAX); - if (cur_rx_active) - tipc_aead_users_dec(tx->aead[cur_rx_active], 0); + /* Case 2: Peer RX active key has changed, let's update own TX users */ + cur = atomic_read(&rx->peer_rx_active); + new = ehdr->rx_key_active; + if (tx->key.keys && + cur != new && + atomic_cmpxchg(&rx->peer_rx_active, cur, new) == cur) { + if (new) + tipc_aead_users_inc(tx->aead[new], INT_MAX); + if (cur) + tipc_aead_users_dec(tx->aead[cur], 0); atomic64_set(&rx->sndnxt, 0); /* Mark the point TX key users changed */ tx->timer1 = jiffies; -#ifdef TIPC_CRYPTO_DEBUG - pr_info("TX(%s): key users changed %d-- %d++, peer RX(%s)\n", - tipc_own_id_string(net), cur_rx_active, - new_rx_active, tipc_node_get_id_str(rx->node)); -#endif + pr_debug("%s: key users changed %d-- %d++, peer %s\n", + tx->name, cur, new, rx->name); } } @@ -1340,7 +1456,7 @@ static int tipc_crypto_key_revoke(struct net *net, u8 tx_key) tipc_crypto_key_detach(tx->aead[key.active], &tx->lock); spin_unlock(&tx->lock); - pr_warn("TX(%s): key is revoked!\n", tipc_own_id_string(net)); + pr_warn("%s: key is revoked\n", tx->name); return -EKEYREVOKED; } @@ -1357,6 +1473,15 @@ int tipc_crypto_start(struct tipc_crypto **crypto, struct net *net, if (!c) return -ENOMEM; + /* Allocate workqueue on TX */ + if (!node) { + c->wq = alloc_ordered_workqueue("tipc_crypto", 0); + if (!c->wq) { + kfree(c); + return -ENOMEM; + } + } + /* Allocate statistic structure */ c->stats = alloc_percpu_gfp(struct tipc_crypto_stats, GFP_ATOMIC); if (!c->stats) { @@ -1364,53 +1489,52 @@ int tipc_crypto_start(struct tipc_crypto **crypto, struct net *net, return -ENOMEM; } - c->working = 0; + c->flags = 0; c->net = net; c->node = node; + get_random_bytes(&c->key_gen, 2); tipc_crypto_key_set_state(c, 0, 0, 0); + atomic_set(&c->key_distr, 0); atomic_set(&c->peer_rx_active, 0); atomic64_set(&c->sndnxt, 0); c->timer1 = jiffies; c->timer2 = jiffies; + c->rekeying_intv = TIPC_REKEYING_INTV_DEF; spin_lock_init(&c->lock); - *crypto = c; + scnprintf(c->name, 48, "%s(%s)", (is_rx(c)) ? "RX" : "TX", + (is_rx(c)) ? tipc_node_get_id_str(c->node) : + tipc_own_id_string(c->net)); + + if (is_rx(c)) + INIT_DELAYED_WORK(&c->work, tipc_crypto_work_rx); + else + INIT_DELAYED_WORK(&c->work, tipc_crypto_work_tx); + *crypto = c; return 0; } void tipc_crypto_stop(struct tipc_crypto **crypto) { - struct tipc_crypto *c, *tx, *rx; - bool is_rx; + struct tipc_crypto *c = *crypto; u8 k; - if (!*crypto) + if (!c) return; - rcu_read_lock(); - /* RX stopping? => decrease TX key users if any */ - is_rx = !!((*crypto)->node); - if (is_rx) { - rx = *crypto; - tx = tipc_net(rx->net)->crypto_tx; - k = atomic_read(&rx->peer_rx_active); - if (k) { - tipc_aead_users_dec(tx->aead[k], 0); - /* Mark the point TX key users changed */ - tx->timer1 = jiffies; - } + /* Flush any queued works & destroy wq */ + if (is_tx(c)) { + c->rekeying_intv = 0; + cancel_delayed_work_sync(&c->work); + destroy_workqueue(c->wq); } /* Release AEAD keys */ - c = *crypto; + rcu_read_lock(); for (k = KEY_MIN; k <= KEY_MAX; k++) tipc_aead_put(rcu_dereference(c->aead[k])); rcu_read_unlock(); - - pr_warn("%s(%s) has been purged, node left!\n", - (is_rx) ? "RX" : "TX", - (is_rx) ? tipc_node_get_id_str((*crypto)->node) : - tipc_own_id_string((*crypto)->net)); + pr_debug("%s: has been stopped\n", c->name); /* Free this crypto statistics */ free_percpu(c->stats); @@ -1424,106 +1548,91 @@ void tipc_crypto_timeout(struct tipc_crypto *rx) struct tipc_net *tn = tipc_net(rx->net); struct tipc_crypto *tx = tn->crypto_tx; struct tipc_key key; - u8 new_pending, new_passive; int cmd; - /* TX key activating: - * The pending key (users > 0) -> active - * The active key if any (users == 0) -> free - */ + /* TX pending: taking all users & stable -> active */ spin_lock(&tx->lock); key = tx->key; if (key.active && tipc_aead_users(tx->aead[key.active]) > 0) goto s1; if (!key.pending || tipc_aead_users(tx->aead[key.pending]) <= 0) goto s1; - if (time_before(jiffies, tx->timer1 + TIPC_TX_LASTING_LIM)) + if (time_before(jiffies, tx->timer1 + TIPC_TX_LASTING_TIME)) goto s1; tipc_crypto_key_set_state(tx, key.passive, key.pending, 0); if (key.active) tipc_crypto_key_detach(tx->aead[key.active], &tx->lock); this_cpu_inc(tx->stats->stat[STAT_SWITCHES]); - pr_info("TX(%s): key %d is activated!\n", tipc_own_id_string(tx->net), - key.pending); + pr_info("%s: key[%d] is activated\n", tx->name, key.pending); s1: spin_unlock(&tx->lock); - /* RX key activating: - * The pending key (users > 0) -> active - * The active key if any -> passive, freed later - */ + /* RX pending: having user -> active */ spin_lock(&rx->lock); key = rx->key; if (!key.pending || tipc_aead_users(rx->aead[key.pending]) <= 0) goto s2; - new_pending = (key.passive && - !tipc_aead_users(rx->aead[key.passive])) ? - key.passive : 0; - new_passive = (key.active) ?: ((new_pending) ? 0 : key.passive); - tipc_crypto_key_set_state(rx, new_passive, key.pending, new_pending); + if (key.active) + key.passive = key.active; + key.active = key.pending; + rx->timer2 = jiffies; + tipc_crypto_key_set_state(rx, key.passive, key.active, 0); this_cpu_inc(rx->stats->stat[STAT_SWITCHES]); - pr_info("RX(%s): key %d is activated!\n", - tipc_node_get_id_str(rx->node), key.pending); + pr_info("%s: key[%d] is activated\n", rx->name, key.pending); goto s5; s2: - /* RX key "faulty" switching: - * The faulty pending key (users < -30) -> passive - * The passive key (users = 0) -> pending - * Note: This only happens after RX deactivated - s3! - */ - key = rx->key; - if (!key.pending || tipc_aead_users(rx->aead[key.pending]) > -30) - goto s3; - if (!key.passive || tipc_aead_users(rx->aead[key.passive]) != 0) + /* RX pending: not working -> remove */ + if (!key.pending || tipc_aead_users(rx->aead[key.pending]) > -10) goto s3; - new_pending = key.passive; - new_passive = key.pending; - tipc_crypto_key_set_state(rx, new_passive, key.active, new_pending); + tipc_crypto_key_set_state(rx, key.passive, key.active, 0); + tipc_crypto_key_detach(rx->aead[key.pending], &rx->lock); + pr_debug("%s: key[%d] is removed\n", rx->name, key.pending); goto s5; s3: - /* RX key deactivating: - * The passive key if any -> pending - * The active key -> passive (users = 0) / pending - * The pending key if any -> passive (users = 0) - */ - key = rx->key; + /* RX active: timed out or no user -> pending */ if (!key.active) goto s4; - if (time_before(jiffies, rx->timer1 + TIPC_RX_ACTIVE_LIM)) + if (time_before(jiffies, rx->timer1 + TIPC_RX_ACTIVE_LIM) && + tipc_aead_users(rx->aead[key.active]) > 0) goto s4; - new_pending = (key.passive) ?: key.active; - new_passive = (key.passive) ? key.active : key.pending; - tipc_aead_users_set(rx->aead[new_pending], 0); - if (new_passive) - tipc_aead_users_set(rx->aead[new_passive], 0); - tipc_crypto_key_set_state(rx, new_passive, 0, new_pending); - pr_info("RX(%s): key %d is deactivated!\n", - tipc_node_get_id_str(rx->node), key.active); + if (key.pending) + key.passive = key.active; + else + key.pending = key.active; + rx->timer2 = jiffies; + tipc_crypto_key_set_state(rx, key.passive, 0, key.pending); + tipc_aead_users_set(rx->aead[key.pending], 0); + pr_debug("%s: key[%d] is deactivated\n", rx->name, key.active); goto s5; s4: - /* RX key passive -> freed: */ - key = rx->key; - if (!key.passive || !tipc_aead_users(rx->aead[key.passive])) + /* RX passive: outdated or not working -> free */ + if (!key.passive) goto s5; - if (time_before(jiffies, rx->timer2 + TIPC_RX_PASSIVE_LIM)) + if (time_before(jiffies, rx->timer2 + TIPC_RX_PASSIVE_LIM) && + tipc_aead_users(rx->aead[key.passive]) > -10) goto s5; tipc_crypto_key_set_state(rx, 0, key.active, key.pending); tipc_crypto_key_detach(rx->aead[key.passive], &rx->lock); - pr_info("RX(%s): key %d is freed!\n", tipc_node_get_id_str(rx->node), - key.passive); + pr_debug("%s: key[%d] is freed\n", rx->name, key.passive); s5: spin_unlock(&rx->lock); + /* Relax it here, the flag will be set again if it really is, but only + * when we are not in grace period for safety! + */ + if (time_after(jiffies, tx->timer2 + TIPC_TX_GRACE_PERIOD)) + tx->legacy_user = 0; + /* Limit max_tfms & do debug commands if needed */ if (likely(sysctl_tipc_max_tfms <= TIPC_MAX_TFMS_LIM)) return; @@ -1533,6 +1642,22 @@ s5: tipc_crypto_do_cmd(rx->net, cmd); } +static inline void tipc_crypto_clone_msg(struct net *net, struct sk_buff *_skb, + struct tipc_bearer *b, + struct tipc_media_addr *dst, + struct tipc_node *__dnode, u8 type) +{ + struct sk_buff *skb; + + skb = skb_clone(_skb, GFP_ATOMIC); + if (skb) { + TIPC_SKB_CB(skb)->xmit_type = type; + tipc_crypto_xmit(net, &skb, b, dst, __dnode); + if (skb) + b->media->send_msg(net, skb, b, dst); + } +} + /** * tipc_crypto_xmit - Build & encrypt TIPC message for xmit * @net: struct net @@ -1542,7 +1667,8 @@ s5: * @__dnode: destination node for reference if any * * First, build an encryption message header on the top of the message, then - * encrypt the original TIPC message by using the active or pending TX key. + * encrypt the original TIPC message by using the pending, master or active + * key with this preference order. * If the encryption is successful, the encrypted skb is returned directly or * via the callback. * Otherwise, the skb is freed! @@ -1562,46 +1688,67 @@ int tipc_crypto_xmit(struct net *net, struct sk_buff **skb, struct tipc_crypto *__rx = tipc_node_crypto_rx(__dnode); struct tipc_crypto *tx = tipc_net(net)->crypto_tx; struct tipc_crypto_stats __percpu *stats = tx->stats; + struct tipc_msg *hdr = buf_msg(*skb); struct tipc_key key = tx->key; struct tipc_aead *aead = NULL; - struct sk_buff *probe; + u32 user = msg_user(hdr); + u32 type = msg_type(hdr); int rc = -ENOKEY; - u8 tx_key; + u8 tx_key = 0; /* No encryption? */ if (!tx->working) return 0; - /* Try with the pending key if available and: - * 1) This is the only choice (i.e. no active key) or; - * 2) Peer has switched to this key (unicast only) or; - * 3) It is time to do a pending key probe; - */ + /* Pending key if peer has active on it or probing time */ if (unlikely(key.pending)) { tx_key = key.pending; - if (!key.active) + if (!tx->key_master && !key.active) goto encrypt; if (__rx && atomic_read(&__rx->peer_rx_active) == tx_key) goto encrypt; - if (TIPC_SKB_CB(*skb)->probe) + if (TIPC_SKB_CB(*skb)->xmit_type == SKB_PROBING) { + pr_debug("%s: probing for key[%d]\n", tx->name, + key.pending); + goto encrypt; + } + if (user == LINK_CONFIG || user == LINK_PROTOCOL) + tipc_crypto_clone_msg(net, *skb, b, dst, __dnode, + SKB_PROBING); + } + + /* Master key if this is a *vital* message or in grace period */ + if (tx->key_master) { + tx_key = KEY_MASTER; + if (!key.active) + goto encrypt; + if (TIPC_SKB_CB(*skb)->xmit_type == SKB_GRACING) { + pr_debug("%s: gracing for msg (%d %d)\n", tx->name, + user, type); goto encrypt; - if (!__rx && - time_after(jiffies, tx->timer2 + TIPC_TX_PROBE_LIM)) { - tx->timer2 = jiffies; - probe = skb_clone(*skb, GFP_ATOMIC); - if (probe) { - TIPC_SKB_CB(probe)->probe = 1; - tipc_crypto_xmit(net, &probe, b, dst, __dnode); - if (probe) - b->media->send_msg(net, probe, b, dst); + } + if (user == LINK_CONFIG || + (user == LINK_PROTOCOL && type == RESET_MSG) || + (user == MSG_CRYPTO && type == KEY_DISTR_MSG) || + time_before(jiffies, tx->timer2 + TIPC_TX_GRACE_PERIOD)) { + if (__rx && __rx->key_master && + !atomic_read(&__rx->peer_rx_active)) + goto encrypt; + if (!__rx) { + if (likely(!tx->legacy_user)) + goto encrypt; + tipc_crypto_clone_msg(net, *skb, b, dst, + __dnode, SKB_GRACING); } } } + /* Else, use the active key if any */ if (likely(key.active)) { tx_key = key.active; goto encrypt; } + goto exit; encrypt: @@ -1667,30 +1814,21 @@ int tipc_crypto_rcv(struct net *net, struct tipc_crypto *rx, struct tipc_aead *aead = NULL; struct tipc_key key; int rc = -ENOKEY; - u8 tx_key = 0; + u8 tx_key, n; + + tx_key = ((struct tipc_ehdr *)(*skb)->data)->tx_key; /* New peer? * Let's try with TX key (i.e. cluster mode) & verify the skb first! */ - if (unlikely(!rx)) + if (unlikely(!rx || tx_key == KEY_MASTER)) goto pick_tx; - /* Pick RX key according to TX key, three cases are possible: - * 1) The current active key (likely) or; - * 2) The pending (new or deactivated) key (if any) or; - * 3) The passive or old active key (i.e. users > 0); - */ - tx_key = ((struct tipc_ehdr *)(*skb)->data)->tx_key; + /* Pick RX key according to TX key if any */ key = rx->key; - if (likely(tx_key == key.active)) + if (tx_key == key.active || tx_key == key.pending || + tx_key == key.passive) goto decrypt; - if (tx_key == key.pending) - goto decrypt; - if (tx_key == key.passive) { - rx->timer2 = jiffies; - if (tipc_aead_users(rx->aead[key.passive]) > 0) - goto decrypt; - } /* Unknown key, let's try to align RX key(s) */ if (tipc_crypto_key_try_align(rx, tx_key)) @@ -1698,7 +1836,7 @@ int tipc_crypto_rcv(struct net *net, struct tipc_crypto *rx, pick_tx: /* No key suitable? Try to pick one from TX... */ - aead = tipc_crypto_key_pick_tx(tx, rx, *skb); + aead = tipc_crypto_key_pick_tx(tx, rx, *skb, tx_key); if (aead) goto decrypt; goto exit; @@ -1726,8 +1864,19 @@ exit: if (rc == -ENOKEY) { kfree_skb(*skb); *skb = NULL; - if (rx) + if (rx) { + /* Mark rx->nokey only if we dont have a + * pending received session key, nor a newer + * one i.e. in the next slot. + */ + n = key_next(tx_key); + rx->nokey = !(rx->skey || + rcu_access_pointer(rx->aead[n])); + pr_debug_ratelimited("%s: nokey %d, key %d/%x\n", + rx->name, rx->nokey, + tx_key, rx->key.keys); tipc_node_put(rx->node); + } this_cpu_inc(stats->stat[STAT_NOKEYS]); return rc; } else if (rc == -EBADMSG) { @@ -1749,21 +1898,17 @@ static void tipc_crypto_rcv_complete(struct net *net, struct tipc_aead *aead, struct tipc_aead *tmp = NULL; struct tipc_ehdr *ehdr; struct tipc_node *n; - u8 rx_key_active; - bool destined; /* Is this completed by TX? */ - if (unlikely(!rx->node)) { + if (unlikely(is_tx(aead->crypto))) { rx = skb_cb->tx_clone_ctx.rx; -#ifdef TIPC_CRYPTO_DEBUG - pr_info("TX->RX(%s): err %d, aead %p, skb->next %p, flags %x\n", - (rx) ? tipc_node_get_id_str(rx->node) : "-", err, aead, - (*skb)->next, skb_cb->flags); - pr_info("skb_cb [recurs %d, last %p], tx->aead [%p %p %p]\n", - skb_cb->tx_clone_ctx.recurs, skb_cb->tx_clone_ctx.last, - aead->crypto->aead[1], aead->crypto->aead[2], - aead->crypto->aead[3]); -#endif + pr_debug("TX->RX(%s): err %d, aead %p, skb->next %p, flags %x\n", + (rx) ? tipc_node_get_id_str(rx->node) : "-", err, aead, + (*skb)->next, skb_cb->flags); + pr_debug("skb_cb [recurs %d, last %p], tx->aead [%p %p %p]\n", + skb_cb->tx_clone_ctx.recurs, skb_cb->tx_clone_ctx.last, + aead->crypto->aead[1], aead->crypto->aead[2], + aead->crypto->aead[3]); if (unlikely(err)) { if (err == -EBADMSG && (*skb)->next) tipc_rcv(net, (*skb)->next, b); @@ -1784,12 +1929,12 @@ static void tipc_crypto_rcv_complete(struct net *net, struct tipc_aead *aead, goto free_skb; } - /* Skip cloning this time as we had a RX pending key */ - if (rx->key.pending) + /* Ignore cloning if it was TX master key */ + if (ehdr->tx_key == KEY_MASTER) goto rcv; if (tipc_aead_clone(&tmp, aead) < 0) goto rcv; - if (tipc_crypto_key_attach(rx, tmp, ehdr->tx_key) < 0) { + if (tipc_crypto_key_attach(rx, tmp, ehdr->tx_key, false) < 0) { tipc_aead_free(&tmp->rcu); goto rcv; } @@ -1805,14 +1950,18 @@ static void tipc_crypto_rcv_complete(struct net *net, struct tipc_aead *aead, /* Set the RX key's user */ tipc_aead_users_set(aead, 1); -rcv: /* Mark this point, RX works */ rx->timer1 = jiffies; +rcv: /* Remove ehdr & auth. tag prior to tipc_rcv() */ ehdr = (struct tipc_ehdr *)(*skb)->data; - destined = ehdr->destined; - rx_key_active = ehdr->rx_key_active; + + /* Mark this point, RX passive still works */ + if (rx->key.passive && ehdr->tx_key == rx->key.passive) + rx->timer2 = jiffies; + + skb_reset_network_header(*skb); skb_pull(*skb, tipc_ehdr_size(ehdr)); pskb_trim(*skb, (*skb)->len - aead->authsize); @@ -1822,9 +1971,8 @@ rcv: goto free_skb; } - /* Update peer RX active key & TX users */ - if (destined) - tipc_crypto_key_synch(rx, rx_key_active, buf_msg(*skb)); + /* Ok, everything's fine, try to synch own keys according to peers' */ + tipc_crypto_key_synch(rx, *skb); /* Mark skb decrypted */ skb_cb->decrypted = 1; @@ -1883,7 +2031,7 @@ print_stats: /* Print crypto statistics */ for (i = 0, j = 0; i < MAX_STATS; i++) j += scnprintf(buf + j, 200 - j, "|%11s ", hstats[i]); - pr_info("\nCounter %s", buf); + pr_info("Counter %s", buf); memset(buf, '-', 115); buf[115] = '\0'; @@ -1927,21 +2075,31 @@ static char *tipc_crypto_key_dump(struct tipc_crypto *c, char *buf) char *s; for (k = KEY_MIN; k <= KEY_MAX; k++) { - if (k == key.passive) - s = "PAS"; - else if (k == key.active) - s = "ACT"; - else if (k == key.pending) - s = "PEN"; - else - s = "-"; + if (k == KEY_MASTER) { + if (is_rx(c)) + continue; + if (time_before(jiffies, + c->timer2 + TIPC_TX_GRACE_PERIOD)) + s = "ACT"; + else + s = "PAS"; + } else { + if (k == key.passive) + s = "PAS"; + else if (k == key.active) + s = "ACT"; + else if (k == key.pending) + s = "PEN"; + else + s = "-"; + } i += scnprintf(buf + i, 200 - i, "\tKey%d: %s", k, s); rcu_read_lock(); aead = rcu_dereference(c->aead[k]); if (aead) i += scnprintf(buf + i, 200 - i, - "{\"%s...\", \"%s\"}/%d:%d", + "{\"0x...%s\", \"%s\"}/%d:%d", aead->hint, (aead->mode == CLUSTER_KEY) ? "c" : "p", atomic_read(&aead->users), @@ -1950,14 +2108,13 @@ static char *tipc_crypto_key_dump(struct tipc_crypto *c, char *buf) i += scnprintf(buf + i, 200 - i, "\n"); } - if (c->node) + if (is_rx(c)) i += scnprintf(buf + i, 200 - i, "\tPeer RX active: %d\n", atomic_read(&c->peer_rx_active)); return buf; } -#ifdef TIPC_CRYPTO_DEBUG static char *tipc_key_change_dump(struct tipc_key old, struct tipc_key new, char *buf) { @@ -1968,7 +2125,7 @@ static char *tipc_key_change_dump(struct tipc_key old, struct tipc_key new, /* Output format: "[%s %s %s] -> [%s %s %s]", max len = 32 */ again: i += scnprintf(buf + i, 32 - i, "["); - for (k = KEY_MIN; k <= KEY_MAX; k++) { + for (k = KEY_1; k <= KEY_3; k++) { if (k == key->passive) s = "pas"; else if (k == key->active) @@ -1978,7 +2135,7 @@ again: else s = "-"; i += scnprintf(buf + i, 32 - i, - (k != KEY_MAX) ? "%s " : "%s", s); + (k != KEY_3) ? "%s " : "%s", s); } if (key != &new) { i += scnprintf(buf + i, 32 - i, "] -> "); @@ -1988,4 +2145,320 @@ again: i += scnprintf(buf + i, 32 - i, "]"); return buf; } -#endif + +/** + * tipc_crypto_msg_rcv - Common 'MSG_CRYPTO' processing point + * @net: the struct net + * @skb: the receiving message buffer + */ +void tipc_crypto_msg_rcv(struct net *net, struct sk_buff *skb) +{ + struct tipc_crypto *rx; + struct tipc_msg *hdr; + + if (unlikely(skb_linearize(skb))) + goto exit; + + hdr = buf_msg(skb); + rx = tipc_node_crypto_rx_by_addr(net, msg_prevnode(hdr)); + if (unlikely(!rx)) + goto exit; + + switch (msg_type(hdr)) { + case KEY_DISTR_MSG: + if (tipc_crypto_key_rcv(rx, hdr)) + goto exit; + break; + default: + break; + } + + tipc_node_put(rx->node); + +exit: + kfree_skb(skb); +} + +/** + * tipc_crypto_key_distr - Distribute a TX key + * @tx: the TX crypto + * @key: the key's index + * @dest: the destination tipc node, = NULL if distributing to all nodes + * + * Return: 0 in case of success, otherwise < 0 + */ +int tipc_crypto_key_distr(struct tipc_crypto *tx, u8 key, + struct tipc_node *dest) +{ + struct tipc_aead *aead; + u32 dnode = tipc_node_get_addr(dest); + int rc = -ENOKEY; + + if (!sysctl_tipc_key_exchange_enabled) + return 0; + + if (key) { + rcu_read_lock(); + aead = tipc_aead_get(tx->aead[key]); + if (likely(aead)) { + rc = tipc_crypto_key_xmit(tx->net, aead->key, + aead->gen, aead->mode, + dnode); + tipc_aead_put(aead); + } + rcu_read_unlock(); + } + + return rc; +} + +/** + * tipc_crypto_key_xmit - Send a session key + * @net: the struct net + * @skey: the session key to be sent + * @gen: the key's generation + * @mode: the key's mode + * @dnode: the destination node address, = 0 if broadcasting to all nodes + * + * The session key 'skey' is packed in a TIPC v2 'MSG_CRYPTO/KEY_DISTR_MSG' + * as its data section, then xmit-ed through the uc/bc link. + * + * Return: 0 in case of success, otherwise < 0 + */ +static int tipc_crypto_key_xmit(struct net *net, struct tipc_aead_key *skey, + u16 gen, u8 mode, u32 dnode) +{ + struct sk_buff_head pkts; + struct tipc_msg *hdr; + struct sk_buff *skb; + u16 size, cong_link_cnt; + u8 *data; + int rc; + + size = tipc_aead_key_size(skey); + skb = tipc_buf_acquire(INT_H_SIZE + size, GFP_ATOMIC); + if (!skb) + return -ENOMEM; + + hdr = buf_msg(skb); + tipc_msg_init(tipc_own_addr(net), hdr, MSG_CRYPTO, KEY_DISTR_MSG, + INT_H_SIZE, dnode); + msg_set_size(hdr, INT_H_SIZE + size); + msg_set_key_gen(hdr, gen); + msg_set_key_mode(hdr, mode); + + data = msg_data(hdr); + *((__be32 *)(data + TIPC_AEAD_ALG_NAME)) = htonl(skey->keylen); + memcpy(data, skey->alg_name, TIPC_AEAD_ALG_NAME); + memcpy(data + TIPC_AEAD_ALG_NAME + sizeof(__be32), skey->key, + skey->keylen); + + __skb_queue_head_init(&pkts); + __skb_queue_tail(&pkts, skb); + if (dnode) + rc = tipc_node_xmit(net, &pkts, dnode, 0); + else + rc = tipc_bcast_xmit(net, &pkts, &cong_link_cnt); + + return rc; +} + +/** + * tipc_crypto_key_rcv - Receive a session key + * @rx: the RX crypto + * @hdr: the TIPC v2 message incl. the receiving session key in its data + * + * This function retrieves the session key in the message from peer, then + * schedules a RX work to attach the key to the corresponding RX crypto. + * + * Return: "true" if the key has been scheduled for attaching, otherwise + * "false". + */ +static bool tipc_crypto_key_rcv(struct tipc_crypto *rx, struct tipc_msg *hdr) +{ + struct tipc_crypto *tx = tipc_net(rx->net)->crypto_tx; + struct tipc_aead_key *skey = NULL; + u16 key_gen = msg_key_gen(hdr); + u16 size = msg_data_sz(hdr); + u8 *data = msg_data(hdr); + + spin_lock(&rx->lock); + if (unlikely(rx->skey || (key_gen == rx->key_gen && rx->key.keys))) { + pr_err("%s: key existed <%p>, gen %d vs %d\n", rx->name, + rx->skey, key_gen, rx->key_gen); + goto exit; + } + + /* Allocate memory for the key */ + skey = kmalloc(size, GFP_ATOMIC); + if (unlikely(!skey)) { + pr_err("%s: unable to allocate memory for skey\n", rx->name); + goto exit; + } + + /* Copy key from msg data */ + skey->keylen = ntohl(*((__be32 *)(data + TIPC_AEAD_ALG_NAME))); + memcpy(skey->alg_name, data, TIPC_AEAD_ALG_NAME); + memcpy(skey->key, data + TIPC_AEAD_ALG_NAME + sizeof(__be32), + skey->keylen); + + /* Sanity check */ + if (unlikely(size != tipc_aead_key_size(skey))) { + kfree(skey); + skey = NULL; + goto exit; + } + + rx->key_gen = key_gen; + rx->skey_mode = msg_key_mode(hdr); + rx->skey = skey; + rx->nokey = 0; + mb(); /* for nokey flag */ + +exit: + spin_unlock(&rx->lock); + + /* Schedule the key attaching on this crypto */ + if (likely(skey && queue_delayed_work(tx->wq, &rx->work, 0))) + return true; + + return false; +} + +/** + * tipc_crypto_work_rx - Scheduled RX works handler + * @work: the struct RX work + * + * The function processes the previous scheduled works i.e. distributing TX key + * or attaching a received session key on RX crypto. + */ +static void tipc_crypto_work_rx(struct work_struct *work) +{ + struct delayed_work *dwork = to_delayed_work(work); + struct tipc_crypto *rx = container_of(dwork, struct tipc_crypto, work); + struct tipc_crypto *tx = tipc_net(rx->net)->crypto_tx; + unsigned long delay = msecs_to_jiffies(5000); + bool resched = false; + u8 key; + int rc; + + /* Case 1: Distribute TX key to peer if scheduled */ + if (atomic_cmpxchg(&rx->key_distr, + KEY_DISTR_SCHED, + KEY_DISTR_COMPL) == KEY_DISTR_SCHED) { + /* Always pick the newest one for distributing */ + key = tx->key.pending ?: tx->key.active; + rc = tipc_crypto_key_distr(tx, key, rx->node); + if (unlikely(rc)) + pr_warn("%s: unable to distr key[%d] to %s, err %d\n", + tx->name, key, tipc_node_get_id_str(rx->node), + rc); + + /* Sched for key_distr releasing */ + resched = true; + } else { + atomic_cmpxchg(&rx->key_distr, KEY_DISTR_COMPL, 0); + } + + /* Case 2: Attach a pending received session key from peer if any */ + if (rx->skey) { + rc = tipc_crypto_key_init(rx, rx->skey, rx->skey_mode, false); + if (unlikely(rc < 0)) + pr_warn("%s: unable to attach received skey, err %d\n", + rx->name, rc); + switch (rc) { + case -EBUSY: + case -ENOMEM: + /* Resched the key attaching */ + resched = true; + break; + default: + synchronize_rcu(); + kfree(rx->skey); + rx->skey = NULL; + break; + } + } + + if (resched && queue_delayed_work(tx->wq, &rx->work, delay)) + return; + + tipc_node_put(rx->node); +} + +/** + * tipc_crypto_rekeying_sched - (Re)schedule rekeying w/o new interval + * @tx: TX crypto + * @changed: if the rekeying needs to be rescheduled with new interval + * @new_intv: new rekeying interval (when "changed" = true) + */ +void tipc_crypto_rekeying_sched(struct tipc_crypto *tx, bool changed, + u32 new_intv) +{ + unsigned long delay; + bool now = false; + + if (changed) { + if (new_intv == TIPC_REKEYING_NOW) + now = true; + else + tx->rekeying_intv = new_intv; + cancel_delayed_work_sync(&tx->work); + } + + if (tx->rekeying_intv || now) { + delay = (now) ? 0 : tx->rekeying_intv * 60 * 1000; + queue_delayed_work(tx->wq, &tx->work, msecs_to_jiffies(delay)); + } +} + +/** + * tipc_crypto_work_tx - Scheduled TX works handler + * @work: the struct TX work + * + * The function processes the previous scheduled work, i.e. key rekeying, by + * generating a new session key based on current one, then attaching it to the + * TX crypto and finally distributing it to peers. It also re-schedules the + * rekeying if needed. + */ +static void tipc_crypto_work_tx(struct work_struct *work) +{ + struct delayed_work *dwork = to_delayed_work(work); + struct tipc_crypto *tx = container_of(dwork, struct tipc_crypto, work); + struct tipc_aead_key *skey = NULL; + struct tipc_key key = tx->key; + struct tipc_aead *aead; + int rc = -ENOMEM; + + if (unlikely(key.pending)) + goto resched; + + /* Take current key as a template */ + rcu_read_lock(); + aead = rcu_dereference(tx->aead[key.active ?: KEY_MASTER]); + if (unlikely(!aead)) { + rcu_read_unlock(); + /* At least one key should exist for securing */ + return; + } + + /* Lets duplicate it first */ + skey = kmemdup(aead->key, tipc_aead_key_size(aead->key), GFP_ATOMIC); + rcu_read_unlock(); + + /* Now, generate new key, initiate & distribute it */ + if (likely(skey)) { + rc = tipc_aead_key_generate(skey) ?: + tipc_crypto_key_init(tx, skey, PER_NODE_KEY, false); + if (likely(rc > 0)) + rc = tipc_crypto_key_distr(tx, rc, NULL); + kfree_sensitive(skey); + } + + if (unlikely(rc)) + pr_warn_ratelimited("%s: rekeying returns %d\n", tx->name, rc); + +resched: + /* Re-schedule rekeying if any */ + tipc_crypto_rekeying_sched(tx, false, 0); +} diff --git a/net/tipc/crypto.h b/net/tipc/crypto.h index c3de769f49e8..e71193bd5e36 100644 --- a/net/tipc/crypto.h +++ b/net/tipc/crypto.h @@ -67,6 +67,7 @@ enum { }; extern int sysctl_tipc_max_tfms __read_mostly; +extern int sysctl_tipc_key_exchange_enabled __read_mostly; /** * TIPC encryption message format: @@ -74,7 +75,7 @@ extern int sysctl_tipc_max_tfms __read_mostly; * 3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 0 0 0 0 0 0 0 0 0 0 * 1 0 9 8 7 6 5 4|3 2 1 0 9 8 7 6|5 4 3 2 1 0 9 8|7 6 5 4 3 2 1 0 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * w0:|Ver=7| User |D|TX |RX |K| Rsvd | + * w0:|Ver=7| User |D|TX |RX |K|M|N| Rsvd | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * w1:| Seqno | * w2:| (8 octets) | @@ -101,6 +102,9 @@ extern int sysctl_tipc_max_tfms __read_mostly; * RX : Currently RX active key corresponding to the destination * node's TX key (when the "D" bit is set) * K : Keep-alive bit (for RPS, LINK_PROTOCOL/STATE_MSG only) + * M : Bit indicates if sender has master key + * N : Bit indicates if sender has no RX keys corresponding to the + * receiver's TX (when the "D" bit is set) * Rsvd : Reserved bit, field * Word1-2: * Seqno : The 64-bit sequence number of the encrypted message, also @@ -117,7 +121,9 @@ struct tipc_ehdr { __u8 destined:1, user:4, version:3; - __u8 reserved_1:3, + __u8 reserved_1:1, + rx_nokey:1, + master_key:1, keepalive:1, rx_key_active:2, tx_key:2; @@ -128,7 +134,9 @@ struct tipc_ehdr { __u8 tx_key:2, rx_key_active:2, keepalive:1, - reserved_1:3; + master_key:1, + rx_nokey:1, + reserved_1:1; #else #error "Please fix <asm/byteorder.h>" #endif @@ -158,10 +166,35 @@ int tipc_crypto_xmit(struct net *net, struct sk_buff **skb, int tipc_crypto_rcv(struct net *net, struct tipc_crypto *rx, struct sk_buff **skb, struct tipc_bearer *b); int tipc_crypto_key_init(struct tipc_crypto *c, struct tipc_aead_key *ukey, - u8 mode); + u8 mode, bool master_key); void tipc_crypto_key_flush(struct tipc_crypto *c); -int tipc_aead_key_validate(struct tipc_aead_key *ukey); +int tipc_crypto_key_distr(struct tipc_crypto *tx, u8 key, + struct tipc_node *dest); +void tipc_crypto_msg_rcv(struct net *net, struct sk_buff *skb); +void tipc_crypto_rekeying_sched(struct tipc_crypto *tx, bool changed, + u32 new_intv); +int tipc_aead_key_validate(struct tipc_aead_key *ukey, struct genl_info *info); bool tipc_ehdr_validate(struct sk_buff *skb); +static inline u32 msg_key_gen(struct tipc_msg *m) +{ + return msg_bits(m, 4, 16, 0xffff); +} + +static inline void msg_set_key_gen(struct tipc_msg *m, u32 gen) +{ + msg_set_bits(m, 4, 16, 0xffff, gen); +} + +static inline u32 msg_key_mode(struct tipc_msg *m) +{ + return msg_bits(m, 4, 0, 0xf); +} + +static inline void msg_set_key_mode(struct tipc_msg *m, u32 mode) +{ + msg_set_bits(m, 4, 0, 0xf, mode); +} + #endif /* _TIPC_CRYPTO_H */ #endif diff --git a/net/tipc/link.c b/net/tipc/link.c index cef38a910107..06b880da2a8e 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -216,11 +216,6 @@ enum { #define TIPC_BC_RETR_LIM (jiffies + msecs_to_jiffies(10)) #define TIPC_UC_RETR_TIME (jiffies + msecs_to_jiffies(1)) -/* - * Interval between NACKs when packets arrive out of order - */ -#define TIPC_NACK_INTV (TIPC_MIN_LINK_WIN * 2) - /* Link FSM states: */ enum { @@ -1256,6 +1251,11 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, case MSG_FRAGMENTER: case BCAST_PROTOCOL: return false; +#ifdef CONFIG_TIPC_CRYPTO + case MSG_CRYPTO: + tipc_crypto_msg_rcv(l->net, skb); + return true; +#endif default: pr_warn("Dropping received illegal msg type\n"); kfree_skb(skb); diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 52e93ba4d8e2..32c79c59052b 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -150,11 +150,11 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) if (fragid == FIRST_FRAGMENT) { if (unlikely(head)) goto err; + *buf = NULL; frag = skb_unshare(frag, GFP_ATOMIC); if (unlikely(!frag)) goto err; head = *headbuf = frag; - *buf = NULL; TIPC_SKB_CB(head)->tail = NULL; if (skb_is_nonlinear(head)) { skb_walk_frags(head, tail) { @@ -582,7 +582,7 @@ bundle: * @pos: position in outer message of msg to be extracted. * Returns position of next msg * Consumes outer buffer when last packet extracted - * Returns true when when there is an extracted buffer, otherwise false + * Returns true when there is an extracted buffer, otherwise false */ bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos) { diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 1016e96db5c4..5d64596ba987 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -82,6 +82,7 @@ struct plist; #define NAME_DISTRIBUTOR 11 #define MSG_FRAGMENTER 12 #define LINK_CONFIG 13 +#define MSG_CRYPTO 14 #define SOCK_WAKEUP 14 /* pseudo user */ #define TOP_SRV 15 /* pseudo user */ @@ -127,7 +128,9 @@ struct tipc_skb_cb { #ifdef CONFIG_TIPC_CRYPTO u8 encrypted:1; u8 decrypted:1; - u8 probe:1; +#define SKB_PROBING 1 +#define SKB_GRACING 2 + u8 xmit_type:2; u8 tx_clone_deferred:1; #endif }; @@ -747,6 +750,9 @@ static inline void msg_set_nameupper(struct tipc_msg *m, u32 n) #define GRP_RECLAIM_MSG 4 #define GRP_REMIT_MSG 5 +/* Crypto message types */ +#define KEY_DISTR_MSG 0 + /* * Word 1 */ diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index 2f9c148f17e2..fe4edce459ad 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -327,8 +327,13 @@ static struct sk_buff *tipc_named_dequeue(struct sk_buff_head *namedq, struct tipc_msg *hdr; u16 seqno; + spin_lock_bh(&namedq->lock); skb_queue_walk_safe(namedq, skb, tmp) { - skb_linearize(skb); + if (unlikely(skb_linearize(skb))) { + __skb_unlink(skb, namedq); + kfree_skb(skb); + continue; + } hdr = buf_msg(skb); seqno = msg_named_seqno(hdr); if (msg_is_last_bulk(hdr)) { @@ -338,12 +343,14 @@ static struct sk_buff *tipc_named_dequeue(struct sk_buff_head *namedq, if (msg_is_bulk(hdr) || msg_is_legacy(hdr)) { __skb_unlink(skb, namedq); + spin_unlock_bh(&namedq->lock); return skb; } if (*open && (*rcv_nxt == seqno)) { (*rcv_nxt)++; __skb_unlink(skb, namedq); + spin_unlock_bh(&namedq->lock); return skb; } @@ -353,6 +360,7 @@ static struct sk_buff *tipc_named_dequeue(struct sk_buff_head *namedq, continue; } } + spin_unlock_bh(&namedq->lock); return NULL; } diff --git a/net/tipc/net.c b/net/tipc/net.c index 85400e4242de..0bb2323201da 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -105,12 +105,6 @@ * - A local spin_lock protecting the queue of subscriber events. */ -struct tipc_net_work { - struct work_struct work; - struct net *net; - u32 addr; -}; - static void tipc_net_finalize(struct net *net, u32 addr); int tipc_net_init(struct net *net, u8 *node_id, u32 addr) @@ -142,25 +136,21 @@ static void tipc_net_finalize(struct net *net, u32 addr) TIPC_CLUSTER_SCOPE, 0, addr); } -static void tipc_net_finalize_work(struct work_struct *work) +void tipc_net_finalize_work(struct work_struct *work) { struct tipc_net_work *fwork; fwork = container_of(work, struct tipc_net_work, work); tipc_net_finalize(fwork->net, fwork->addr); - kfree(fwork); } void tipc_sched_net_finalize(struct net *net, u32 addr) { - struct tipc_net_work *fwork = kzalloc(sizeof(*fwork), GFP_ATOMIC); + struct tipc_net *tn = tipc_net(net); - if (!fwork) - return; - INIT_WORK(&fwork->work, tipc_net_finalize_work); - fwork->net = net; - fwork->addr = addr; - schedule_work(&fwork->work); + tn->final_work.net = net; + tn->final_work.addr = addr; + schedule_work(&tn->final_work.work); } void tipc_net_stop(struct net *net) diff --git a/net/tipc/net.h b/net/tipc/net.h index 6740d97c706e..d0c91d2df20a 100644 --- a/net/tipc/net.h +++ b/net/tipc/net.h @@ -42,6 +42,7 @@ extern const struct nla_policy tipc_nl_net_policy[]; int tipc_net_init(struct net *net, u8 *node_id, u32 addr); +void tipc_net_finalize_work(struct work_struct *work); void tipc_sched_net_finalize(struct net *net, u32 addr); void tipc_net_stop(struct net *net); int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb); diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index c4aee6247d55..c447cb5f879e 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -108,6 +108,8 @@ const struct nla_policy tipc_nl_node_policy[TIPC_NLA_NODE_MAX + 1] = { .len = TIPC_NODEID_LEN}, [TIPC_NLA_NODE_KEY] = { .type = NLA_BINARY, .len = TIPC_AEAD_KEY_SIZE_MAX}, + [TIPC_NLA_NODE_KEY_MASTER] = { .type = NLA_FLAG }, + [TIPC_NLA_NODE_REKEYING] = { .type = NLA_U32 }, }; /* Properties valid for media, bearer and link */ diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 90e3c70a91ad..1c7aa51cc2a3 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -1337,7 +1337,7 @@ send: return err; } -static const struct genl_ops tipc_genl_compat_ops[] = { +static const struct genl_small_ops tipc_genl_compat_ops[] = { { .cmd = TIPC_GENL_CMD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, @@ -1352,8 +1352,8 @@ static struct genl_family tipc_genl_compat_family __ro_after_init = { .maxattr = 0, .netnsok = true, .module = THIS_MODULE, - .ops = tipc_genl_compat_ops, - .n_ops = ARRAY_SIZE(tipc_genl_compat_ops), + .small_ops = tipc_genl_compat_ops, + .n_small_ops = ARRAY_SIZE(tipc_genl_compat_ops), }; int __init tipc_netlink_compat_start(void) diff --git a/net/tipc/node.c b/net/tipc/node.c index 4edcee3088da..d269ebe382e1 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -278,6 +278,14 @@ struct tipc_crypto *tipc_node_crypto_rx_by_list(struct list_head *pos) { return container_of(pos, struct tipc_node, list)->crypto_rx; } + +struct tipc_crypto *tipc_node_crypto_rx_by_addr(struct net *net, u32 addr) +{ + struct tipc_node *n; + + n = tipc_node_find(net, addr); + return (n) ? n->crypto_rx : NULL; +} #endif static void tipc_node_free(struct rcu_head *rp) @@ -303,7 +311,7 @@ void tipc_node_put(struct tipc_node *node) kref_put(&node->kref, tipc_node_kref_release); } -static void tipc_node_get(struct tipc_node *node) +void tipc_node_get(struct tipc_node *node) { kref_get(&node->kref); } @@ -584,6 +592,9 @@ static void tipc_node_calculate_timer(struct tipc_node *n, struct tipc_link *l) static void tipc_node_delete_from_list(struct tipc_node *node) { +#ifdef CONFIG_TIPC_CRYPTO + tipc_crypto_key_flush(node->crypto_rx); +#endif list_del_rcu(&node->list); hlist_del_rcu(&node->hash); tipc_node_put(node); @@ -1485,7 +1496,7 @@ static void node_lost_contact(struct tipc_node *n, /* Clean up broadcast state */ tipc_bcast_remove_peer(n->net, n->bc_entry.link); - __skb_queue_purge(&n->bc_entry.namedq); + skb_queue_purge(&n->bc_entry.namedq); /* Abort any ongoing link failover */ for (i = 0; i < MAX_BEARERS; i++) { @@ -2868,15 +2879,27 @@ static int tipc_nl_retrieve_nodeid(struct nlattr **attrs, u8 **node_id) return 0; } +static int tipc_nl_retrieve_rekeying(struct nlattr **attrs, u32 *intv) +{ + struct nlattr *attr = attrs[TIPC_NLA_NODE_REKEYING]; + + if (!attr) + return -ENODATA; + + *intv = nla_get_u32(attr); + return 0; +} + static int __tipc_nl_node_set_key(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attrs[TIPC_NLA_NODE_MAX + 1]; struct net *net = sock_net(skb->sk); - struct tipc_net *tn = tipc_net(net); + struct tipc_crypto *tx = tipc_net(net)->crypto_tx, *c = tx; struct tipc_node *n = NULL; struct tipc_aead_key *ukey; - struct tipc_crypto *c; - u8 *id, *own_id; + bool rekeying = true, master_key = false; + u8 *id, *own_id, mode; + u32 intv = 0; int rc = 0; if (!info->attrs[TIPC_NLA_NODE]) @@ -2886,52 +2909,66 @@ static int __tipc_nl_node_set_key(struct sk_buff *skb, struct genl_info *info) info->attrs[TIPC_NLA_NODE], tipc_nl_node_policy, info->extack); if (rc) - goto exit; + return rc; own_id = tipc_own_id(net); if (!own_id) { - rc = -EPERM; - goto exit; + GENL_SET_ERR_MSG(info, "not found own node identity (set id?)"); + return -EPERM; } + rc = tipc_nl_retrieve_rekeying(attrs, &intv); + if (rc == -ENODATA) + rekeying = false; + rc = tipc_nl_retrieve_key(attrs, &ukey); - if (rc) - goto exit; + if (rc == -ENODATA && rekeying) + goto rekeying; + else if (rc) + return rc; - rc = tipc_aead_key_validate(ukey); + rc = tipc_aead_key_validate(ukey, info); if (rc) - goto exit; + return rc; rc = tipc_nl_retrieve_nodeid(attrs, &id); switch (rc) { case -ENODATA: - /* Cluster key mode */ - rc = tipc_crypto_key_init(tn->crypto_tx, ukey, CLUSTER_KEY); + mode = CLUSTER_KEY; + master_key = !!(attrs[TIPC_NLA_NODE_KEY_MASTER]); break; case 0: - /* Per-node key mode */ - if (!memcmp(id, own_id, NODE_ID_LEN)) { - c = tn->crypto_tx; - } else { + mode = PER_NODE_KEY; + if (memcmp(id, own_id, NODE_ID_LEN)) { n = tipc_node_find_by_id(net, id) ?: tipc_node_create(net, 0, id, 0xffffu, 0, true); - if (unlikely(!n)) { - rc = -ENOMEM; - break; - } + if (unlikely(!n)) + return -ENOMEM; c = n->crypto_rx; } - - rc = tipc_crypto_key_init(c, ukey, PER_NODE_KEY); - if (n) - tipc_node_put(n); break; default: - break; + return rc; } -exit: - return (rc < 0) ? rc : 0; + /* Initiate the TX/RX key */ + rc = tipc_crypto_key_init(c, ukey, mode, master_key); + if (n) + tipc_node_put(n); + + if (unlikely(rc < 0)) { + GENL_SET_ERR_MSG(info, "unable to initiate or attach new key"); + return rc; + } else if (c == tx) { + /* Distribute TX key but not master one */ + if (!master_key && tipc_crypto_key_distr(tx, rc, NULL)) + GENL_SET_ERR_MSG(info, "failed to replicate new key"); +rekeying: + /* Schedule TX rekeying if needed */ + tipc_crypto_rekeying_sched(tx, rekeying, intv); + } + + return 0; } int tipc_nl_node_set_key(struct sk_buff *skb, struct genl_info *info) @@ -2958,7 +2995,6 @@ static int __tipc_nl_node_flush_key(struct sk_buff *skb, tipc_crypto_key_flush(n->crypto_rx); rcu_read_unlock(); - pr_info("All keys are flushed!\n"); return 0; } diff --git a/net/tipc/node.h b/net/tipc/node.h index 9f6f13f1604f..154a5bbb0d29 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -79,12 +79,14 @@ bool tipc_node_get_id(struct net *net, u32 addr, u8 *id); u32 tipc_node_get_addr(struct tipc_node *node); char *tipc_node_get_id_str(struct tipc_node *node); void tipc_node_put(struct tipc_node *node); +void tipc_node_get(struct tipc_node *node); struct tipc_node *tipc_node_create(struct net *net, u32 addr, u8 *peer_id, u16 capabilities, u32 hash_mixes, bool preliminary); #ifdef CONFIG_TIPC_CRYPTO struct tipc_crypto *tipc_node_crypto_rx(struct tipc_node *__n); struct tipc_crypto *tipc_node_crypto_rx_by_list(struct list_head *pos); +struct tipc_crypto *tipc_node_crypto_rx_by_addr(struct net *net, u32 addr); #endif u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr); void tipc_node_check_dest(struct net *net, u32 onode, u8 *peer_id128, diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 11b27ddc75ba..e795a8a2955b 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -52,10 +52,9 @@ #define NAGLE_START_MAX 1024 #define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */ #define CONN_PROBING_INTV msecs_to_jiffies(3600000) /* [ms] => 1 h */ -#define TIPC_FWD_MSG 1 #define TIPC_MAX_PORT 0xffffffff #define TIPC_MIN_PORT 1 -#define TIPC_ACK_RATE 4 /* ACK at 1/4 of of rcv window size */ +#define TIPC_ACK_RATE 4 /* ACK at 1/4 of rcv window size */ enum { TIPC_LISTEN = TCP_LISTEN, diff --git a/net/tipc/sysctl.c b/net/tipc/sysctl.c index 97a6264a2993..9fb65c988f7f 100644 --- a/net/tipc/sysctl.c +++ b/net/tipc/sysctl.c @@ -74,6 +74,15 @@ static struct ctl_table tipc_table[] = { .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, }, + { + .procname = "key_exchange_enabled", + .data = &sysctl_tipc_key_exchange_enabled, + .maxlen = sizeof(sysctl_tipc_key_exchange_enabled), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, #endif { .procname = "bc_retruni", diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 1489cfb941d8..5f6f86051c83 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -48,7 +48,6 @@ #define MAX_SEND_MSG_COUNT 25 #define MAX_RECV_MSG_COUNT 25 #define CF_CONNECTED 1 -#define CF_SERVER 2 #define TIPC_SERVER_NAME_LEN 32 diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 911d13cd2e67..1d17f4470ee2 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -52,6 +52,7 @@ #include "bearer.h" #include "netlink.h" #include "msg.h" +#include "udp_media.h" /* IANA assigned UDP port */ #define UDP_PORT_DEFAULT 6118 diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index b74e2741f74f..cec86229a6a0 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -418,14 +418,14 @@ static int tls_push_data(struct sock *sk, struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_prot_info *prot = &tls_ctx->prot_info; struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx); - int more = flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE); struct tls_record_info *record = ctx->open_record; int tls_push_record_flags; struct page_frag *pfrag; size_t orig_size = size; u32 max_open_record_len; - int copy, rc = 0; + bool more = false; bool done = false; + int copy, rc = 0; long timeo; if (flags & @@ -492,9 +492,8 @@ handle_error: if (!size) { last_record: tls_push_record_flags = flags; - if (more) { - tls_ctx->pending_open_record_frags = - !!record->num_frags; + if (flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE)) { + more = true; break; } @@ -526,6 +525,8 @@ last_record: } } while (!done); + tls_ctx->pending_open_record_frags = more; + if (orig_size - size > 0) rc = orig_size - size; diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index bbc52b088d29..8d93cea99f2c 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -330,12 +330,13 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) tls_ctx_free(sk, ctx); } -static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, - int __user *optlen) +static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval, + int __user *optlen, int tx) { int rc = 0; struct tls_context *ctx = tls_get_ctx(sk); struct tls_crypto_info *crypto_info; + struct cipher_context *cctx; int len; if (get_user(len, optlen)) @@ -352,7 +353,13 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, } /* get user crypto info */ - crypto_info = &ctx->crypto_send.info; + if (tx) { + crypto_info = &ctx->crypto_send.info; + cctx = &ctx->tx; + } else { + crypto_info = &ctx->crypto_recv.info; + cctx = &ctx->rx; + } if (!TLS_CRYPTO_INFO_READY(crypto_info)) { rc = -EBUSY; @@ -379,9 +386,9 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, } lock_sock(sk); memcpy(crypto_info_aes_gcm_128->iv, - ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, + cctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, TLS_CIPHER_AES_GCM_128_IV_SIZE); - memcpy(crypto_info_aes_gcm_128->rec_seq, ctx->tx.rec_seq, + memcpy(crypto_info_aes_gcm_128->rec_seq, cctx->rec_seq, TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE); release_sock(sk); if (copy_to_user(optval, @@ -403,9 +410,9 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, } lock_sock(sk); memcpy(crypto_info_aes_gcm_256->iv, - ctx->tx.iv + TLS_CIPHER_AES_GCM_256_SALT_SIZE, + cctx->iv + TLS_CIPHER_AES_GCM_256_SALT_SIZE, TLS_CIPHER_AES_GCM_256_IV_SIZE); - memcpy(crypto_info_aes_gcm_256->rec_seq, ctx->tx.rec_seq, + memcpy(crypto_info_aes_gcm_256->rec_seq, cctx->rec_seq, TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE); release_sock(sk); if (copy_to_user(optval, @@ -429,7 +436,9 @@ static int do_tls_getsockopt(struct sock *sk, int optname, switch (optname) { case TLS_TX: - rc = do_tls_getsockopt_tx(sk, optval, optlen); + case TLS_RX: + rc = do_tls_getsockopt_conf(sk, optval, optlen, + optname == TLS_TX); break; default: rc = -ENOPROTOOPT; @@ -860,7 +869,7 @@ static int __init tls_register(void) tls_sw_proto_ops = inet_stream_ops; tls_sw_proto_ops.splice_read = tls_sw_splice_read; - tls_sw_proto_ops.sendpage_locked = tls_sw_sendpage_locked, + tls_sw_proto_ops.sendpage_locked = tls_sw_sendpage_locked; tls_device_init(); tcp_register_ulp(&tcp_tls_ulp_ops); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 92784e51ee7d..41c3303c3357 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -613,7 +613,6 @@ static int unix_listen(struct socket *sock, int backlog) int err; struct sock *sk = sock->sk; struct unix_sock *u = unix_sk(sk); - struct pid *old_pid = NULL; err = -EOPNOTSUPP; if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET) @@ -634,7 +633,6 @@ static int unix_listen(struct socket *sock, int backlog) out_unlock: unix_state_unlock(sk); - put_pid(old_pid); out: return err; } @@ -878,7 +876,6 @@ static int unix_autobind(struct socket *sock) if (err) return err; - err = 0; if (u->addr) goto out; diff --git a/net/unix/scm.c b/net/unix/scm.c index 8c40f2b32392..052ae709ce28 100644 --- a/net/unix/scm.c +++ b/net/unix/scm.c @@ -8,6 +8,7 @@ #include <net/af_unix.h> #include <net/scm.h> #include <linux/init.h> +#include <linux/io_uring.h> #include "scm.h" diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 9e93bc201cc0..b4d7b8aba003 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -739,7 +739,7 @@ static struct sock *__vsock_create(struct net *net, vsk->buffer_min_size = psk->buffer_min_size; vsk->buffer_max_size = psk->buffer_max_size; } else { - vsk->trusted = capable(CAP_NET_ADMIN); + vsk->trusted = ns_capable_noaudit(&init_user_ns, CAP_NET_ADMIN); vsk->owner = get_current_cred(); vsk->connect_timeout = VSOCK_DEFAULT_CONNECT_TIMEOUT; vsk->buffer_size = VSOCK_DEFAULT_BUFFER_SIZE; diff --git a/net/wimax/stack.c b/net/wimax/stack.c index 4b9b1c5e8f3a..b6dd9d956ed8 100644 --- a/net/wimax/stack.c +++ b/net/wimax/stack.c @@ -401,7 +401,7 @@ static const struct nla_policy wimax_gnl_policy[WIMAX_GNL_ATTR_MAX + 1] = { }, }; -static const struct genl_ops wimax_gnl_ops[] = { +static const struct genl_small_ops wimax_gnl_ops[] = { { .cmd = WIMAX_GNL_OP_MSG_FROM_USER, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, @@ -560,8 +560,8 @@ struct genl_family wimax_gnl_family __ro_after_init = { .maxattr = WIMAX_GNL_ATTR_MAX, .policy = wimax_gnl_policy, .module = THIS_MODULE, - .ops = wimax_gnl_ops, - .n_ops = ARRAY_SIZE(wimax_gnl_ops), + .small_ops = wimax_gnl_ops, + .n_small_ops = ARRAY_SIZE(wimax_gnl_ops), .mcgrps = wimax_gnl_mcgrps, .n_mcgrps = ARRAY_SIZE(wimax_gnl_mcgrps), }; diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 6a6f2f214c10..22d1779ab2b1 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -141,9 +141,62 @@ static bool cfg80211_edmg_chandef_valid(const struct cfg80211_chan_def *chandef) return true; } +static int nl80211_chan_width_to_mhz(enum nl80211_chan_width chan_width) +{ + int mhz; + + switch (chan_width) { + case NL80211_CHAN_WIDTH_1: + mhz = 1; + break; + case NL80211_CHAN_WIDTH_2: + mhz = 2; + break; + case NL80211_CHAN_WIDTH_4: + mhz = 4; + break; + case NL80211_CHAN_WIDTH_8: + mhz = 8; + break; + case NL80211_CHAN_WIDTH_16: + mhz = 16; + break; + case NL80211_CHAN_WIDTH_5: + mhz = 5; + break; + case NL80211_CHAN_WIDTH_10: + mhz = 10; + break; + case NL80211_CHAN_WIDTH_20: + case NL80211_CHAN_WIDTH_20_NOHT: + mhz = 20; + break; + case NL80211_CHAN_WIDTH_40: + mhz = 40; + break; + case NL80211_CHAN_WIDTH_80P80: + case NL80211_CHAN_WIDTH_80: + mhz = 80; + break; + case NL80211_CHAN_WIDTH_160: + mhz = 160; + break; + default: + WARN_ON_ONCE(1); + return -1; + } + return mhz; +} + +static int cfg80211_chandef_get_width(const struct cfg80211_chan_def *c) +{ + return nl80211_chan_width_to_mhz(c->width); +} + bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef) { - u32 control_freq; + u32 control_freq, oper_freq; + int oper_width, control_width; if (!chandef->chan) return false; @@ -154,11 +207,6 @@ bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef) control_freq = chandef->chan->center_freq; switch (chandef->width) { - case NL80211_CHAN_WIDTH_1: - case NL80211_CHAN_WIDTH_2: - case NL80211_CHAN_WIDTH_4: - case NL80211_CHAN_WIDTH_8: - case NL80211_CHAN_WIDTH_16: case NL80211_CHAN_WIDTH_5: case NL80211_CHAN_WIDTH_10: case NL80211_CHAN_WIDTH_20: @@ -169,6 +217,34 @@ bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef) if (chandef->center_freq2) return false; break; + case NL80211_CHAN_WIDTH_1: + case NL80211_CHAN_WIDTH_2: + case NL80211_CHAN_WIDTH_4: + case NL80211_CHAN_WIDTH_8: + case NL80211_CHAN_WIDTH_16: + if (chandef->chan->band != NL80211_BAND_S1GHZ) + return false; + + control_freq = ieee80211_channel_to_khz(chandef->chan); + oper_freq = ieee80211_chandef_to_khz(chandef); + control_width = nl80211_chan_width_to_mhz( + ieee80211_s1g_channel_width( + chandef->chan)); + oper_width = cfg80211_chandef_get_width(chandef); + + if (oper_width < 0 || control_width < 0) + return false; + if (chandef->center_freq2) + return false; + + if (control_freq + MHZ_TO_KHZ(control_width) / 2 > + oper_freq + MHZ_TO_KHZ(oper_width) / 2) + return false; + + if (control_freq - MHZ_TO_KHZ(control_width) / 2 < + oper_freq - MHZ_TO_KHZ(oper_width) / 2) + return false; + break; case NL80211_CHAN_WIDTH_40: if (chandef->center_freq1 != control_freq + 10 && chandef->center_freq1 != control_freq - 10) @@ -264,53 +340,6 @@ static void chandef_primary_freqs(const struct cfg80211_chan_def *c, } } -static int cfg80211_chandef_get_width(const struct cfg80211_chan_def *c) -{ - int width; - - switch (c->width) { - case NL80211_CHAN_WIDTH_1: - width = 1; - break; - case NL80211_CHAN_WIDTH_2: - width = 2; - break; - case NL80211_CHAN_WIDTH_4: - width = 4; - break; - case NL80211_CHAN_WIDTH_8: - width = 8; - break; - case NL80211_CHAN_WIDTH_16: - width = 16; - break; - case NL80211_CHAN_WIDTH_5: - width = 5; - break; - case NL80211_CHAN_WIDTH_10: - width = 10; - break; - case NL80211_CHAN_WIDTH_20: - case NL80211_CHAN_WIDTH_20_NOHT: - width = 20; - break; - case NL80211_CHAN_WIDTH_40: - width = 40; - break; - case NL80211_CHAN_WIDTH_80P80: - case NL80211_CHAN_WIDTH_80: - width = 80; - break; - case NL80211_CHAN_WIDTH_160: - width = 160; - break; - default: - WARN_ON_ONCE(1); - return -1; - } - return width; -} - const struct cfg80211_chan_def * cfg80211_chandef_compatible(const struct cfg80211_chan_def *c1, const struct cfg80211_chan_def *c2) diff --git a/net/wireless/core.c b/net/wireless/core.c index 354b0ccbdc24..240282c083aa 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -236,7 +236,9 @@ void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev, rdev->opencount--; if (rdev->scan_req && rdev->scan_req->wdev == wdev) { - if (WARN_ON(!rdev->scan_req->notified)) + if (WARN_ON(!rdev->scan_req->notified && + (!rdev->int_scan_req || + !rdev->int_scan_req->notified))) rdev->scan_req->info.aborted = true; ___cfg80211_scan_done(rdev, false); } @@ -1248,8 +1250,7 @@ void cfg80211_stop_iface(struct wiphy *wiphy, struct wireless_dev *wdev, } EXPORT_SYMBOL(cfg80211_stop_iface); -void cfg80211_init_wdev(struct cfg80211_registered_device *rdev, - struct wireless_dev *wdev) +void cfg80211_init_wdev(struct wireless_dev *wdev) { mutex_init(&wdev->mtx); INIT_LIST_HEAD(&wdev->event_list); @@ -1260,6 +1261,30 @@ void cfg80211_init_wdev(struct cfg80211_registered_device *rdev, spin_lock_init(&wdev->pmsr_lock); INIT_WORK(&wdev->pmsr_free_wk, cfg80211_pmsr_free_wk); +#ifdef CONFIG_CFG80211_WEXT + wdev->wext.default_key = -1; + wdev->wext.default_mgmt_key = -1; + wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC; +#endif + + if (wdev->wiphy->flags & WIPHY_FLAG_PS_ON_BY_DEFAULT) + wdev->ps = true; + else + wdev->ps = false; + /* allow mac80211 to determine the timeout */ + wdev->ps_timeout = -1; + + if ((wdev->iftype == NL80211_IFTYPE_STATION || + wdev->iftype == NL80211_IFTYPE_P2P_CLIENT || + wdev->iftype == NL80211_IFTYPE_ADHOC) && !wdev->use_4addr) + wdev->netdev->priv_flags |= IFF_DONT_BRIDGE; + + INIT_WORK(&wdev->disconnect_wk, cfg80211_autodisconnect_wk); +} + +void cfg80211_register_wdev(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev) +{ /* * We get here also when the interface changes network namespaces, * as it's registered into the new one, but we don't want it to @@ -1293,6 +1318,11 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, switch (state) { case NETDEV_POST_INIT: SET_NETDEV_DEVTYPE(dev, &wiphy_type); + wdev->netdev = dev; + /* can only change netns with wiphy */ + dev->features |= NETIF_F_NETNS_LOCAL; + + cfg80211_init_wdev(wdev); break; case NETDEV_REGISTER: /* @@ -1300,35 +1330,12 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, * called within code protected by it when interfaces * are added with nl80211. */ - /* can only change netns with wiphy */ - dev->features |= NETIF_F_NETNS_LOCAL; - if (sysfs_create_link(&dev->dev.kobj, &rdev->wiphy.dev.kobj, "phy80211")) { pr_err("failed to add phy80211 symlink to netdev!\n"); } - wdev->netdev = dev; -#ifdef CONFIG_CFG80211_WEXT - wdev->wext.default_key = -1; - wdev->wext.default_mgmt_key = -1; - wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC; -#endif - - if (wdev->wiphy->flags & WIPHY_FLAG_PS_ON_BY_DEFAULT) - wdev->ps = true; - else - wdev->ps = false; - /* allow mac80211 to determine the timeout */ - wdev->ps_timeout = -1; - - if ((wdev->iftype == NL80211_IFTYPE_STATION || - wdev->iftype == NL80211_IFTYPE_P2P_CLIENT || - wdev->iftype == NL80211_IFTYPE_ADHOC) && !wdev->use_4addr) - dev->priv_flags |= IFF_DONT_BRIDGE; - - INIT_WORK(&wdev->disconnect_wk, cfg80211_autodisconnect_wk); - cfg80211_init_wdev(rdev, wdev); + cfg80211_register_wdev(rdev, wdev); break; case NETDEV_GOING_DOWN: cfg80211_leave(rdev, wdev); @@ -1336,7 +1343,9 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, case NETDEV_DOWN: cfg80211_update_iface_num(rdev, wdev->iftype, -1); if (rdev->scan_req && rdev->scan_req->wdev == wdev) { - if (WARN_ON(!rdev->scan_req->notified)) + if (WARN_ON(!rdev->scan_req->notified && + (!rdev->int_scan_req || + !rdev->int_scan_req->notified))) rdev->scan_req->info.aborted = true; ___cfg80211_scan_done(rdev, false); } diff --git a/net/wireless/core.h b/net/wireless/core.h index 67b0389fca4d..e3e9686859d4 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -3,7 +3,7 @@ * Wireless configuration interface internals. * * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> - * Copyright (C) 2018-2019 Intel Corporation + * Copyright (C) 2018-2020 Intel Corporation */ #ifndef __NET_WIRELESS_CORE_H #define __NET_WIRELESS_CORE_H @@ -72,6 +72,7 @@ struct cfg80211_registered_device { u32 bss_generation; u32 bss_entries; struct cfg80211_scan_request *scan_req; /* protected by RTNL */ + struct cfg80211_scan_request *int_scan_req; struct sk_buff *scan_msg; struct list_head sched_scan_req_list; time64_t suspend_at; @@ -208,8 +209,9 @@ struct wiphy *wiphy_idx_to_wiphy(int wiphy_idx); int cfg80211_switch_netns(struct cfg80211_registered_device *rdev, struct net *net); -void cfg80211_init_wdev(struct cfg80211_registered_device *rdev, - struct wireless_dev *wdev); +void cfg80211_init_wdev(struct wireless_dev *wdev); +void cfg80211_register_wdev(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev); static inline void wdev_lock(struct wireless_dev *wdev) __acquires(wdev) @@ -457,6 +459,8 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev); bool cfg80211_does_bw_fit_range(const struct ieee80211_freq_range *freq_range, u32 center_freq_khz, u32 bw_khz); +int cfg80211_scan(struct cfg80211_registered_device *rdev); + extern struct work_struct cfg80211_disconnect_work; /** @@ -466,8 +470,8 @@ extern struct work_struct cfg80211_disconnect_work; * * Checks if chandef is usable and we can/need start CAC on such channel. * - * Return: Return true if all channels available and at least - * one channel require CAC (NL80211_DFS_USABLE) + * Return: true if all channels available and at least + * one channel requires CAC (NL80211_DFS_USABLE) */ bool cfg80211_chandef_dfs_usable(struct wiphy *wiphy, const struct cfg80211_chan_def *chandef); diff --git a/net/wireless/lib80211.c b/net/wireless/lib80211.c index cc7b9fd5c166..d66a913027e0 100644 --- a/net/wireless/lib80211.c +++ b/net/wireless/lib80211.c @@ -26,8 +26,6 @@ #include <net/lib80211.h> -#define DRV_NAME "lib80211" - #define DRV_DESCRIPTION "common routines for IEEE802.11 drivers" MODULE_DESCRIPTION(DRV_DESCRIPTION); diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index db7333e20dd7..0ac820780437 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -30,6 +30,15 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, struct cfg80211_bss *bss, struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf; struct cfg80211_connect_resp_params cr; + const u8 *resp_ie = mgmt->u.assoc_resp.variable; + size_t resp_ie_len = len - offsetof(struct ieee80211_mgmt, + u.assoc_resp.variable); + + if (bss->channel->band == NL80211_BAND_S1GHZ) { + resp_ie = (u8 *)&mgmt->u.s1g_assoc_resp.variable; + resp_ie_len = len - offsetof(struct ieee80211_mgmt, + u.s1g_assoc_resp.variable); + } memset(&cr, 0, sizeof(cr)); cr.status = (int)le16_to_cpu(mgmt->u.assoc_resp.status_code); @@ -37,9 +46,8 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, struct cfg80211_bss *bss, cr.bss = bss; cr.req_ie = req_ies; cr.req_ie_len = req_ies_len; - cr.resp_ie = mgmt->u.assoc_resp.variable; - cr.resp_ie_len = - len - offsetof(struct ieee80211_mgmt, u.assoc_resp.variable); + cr.resp_ie = resp_ie; + cr.resp_ie_len = resp_ie_len; cr.timeout_reason = NL80211_TIMEOUT_UNSPECIFIED; trace_cfg80211_send_rx_assoc(dev, bss); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 7fd45f6ddb05..a77174b99b07 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -209,14 +209,23 @@ static int validate_beacon_head(const struct nlattr *attr, unsigned int len = nla_len(attr); const struct element *elem; const struct ieee80211_mgmt *mgmt = (void *)data; - unsigned int fixedlen = offsetof(struct ieee80211_mgmt, - u.beacon.variable); + bool s1g_bcn = ieee80211_is_s1g_beacon(mgmt->frame_control); + unsigned int fixedlen, hdrlen; + + if (s1g_bcn) { + fixedlen = offsetof(struct ieee80211_ext, + u.s1g_beacon.variable); + hdrlen = offsetof(struct ieee80211_ext, u.s1g_beacon); + } else { + fixedlen = offsetof(struct ieee80211_mgmt, + u.beacon.variable); + hdrlen = offsetof(struct ieee80211_mgmt, u.beacon); + } if (len < fixedlen) goto err; - if (ieee80211_hdrlen(mgmt->frame_control) != - offsetof(struct ieee80211_mgmt, u.beacon)) + if (ieee80211_hdrlen(mgmt->frame_control) != hdrlen) goto err; data += fixedlen; @@ -320,6 +329,13 @@ he_obss_pd_policy[NL80211_HE_OBSS_PD_ATTR_MAX + 1] = { NLA_POLICY_RANGE(NLA_U8, 1, 20), [NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET] = NLA_POLICY_RANGE(NLA_U8, 1, 20), + [NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET] = + NLA_POLICY_RANGE(NLA_U8, 1, 20), + [NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP] = + NLA_POLICY_EXACT_LEN(8), + [NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP] = + NLA_POLICY_EXACT_LEN(8), + [NL80211_HE_OBSS_PD_ATTR_SR_CTRL] = { .type = NLA_U8 }, }; static const struct nla_policy @@ -336,6 +352,13 @@ static const struct nla_policy nl80211_txattr_policy[NL80211_TXRATE_MAX + 1] = { .len = NL80211_MAX_SUPP_HT_RATES }, [NL80211_TXRATE_VHT] = NLA_POLICY_EXACT_LEN_WARN(sizeof(struct nl80211_txrate_vht)), [NL80211_TXRATE_GI] = { .type = NLA_U8 }, + [NL80211_TXRATE_HE] = NLA_POLICY_EXACT_LEN(sizeof(struct nl80211_txrate_he)), + [NL80211_TXRATE_HE_GI] = NLA_POLICY_RANGE(NLA_U8, + NL80211_RATE_INFO_HE_GI_0_8, + NL80211_RATE_INFO_HE_GI_3_2), + [NL80211_TXRATE_HE_LTF] = NLA_POLICY_RANGE(NLA_U8, + NL80211_RATE_INFO_HE_1XLTF, + NL80211_RATE_INFO_HE_4XLTF), }; static const struct nla_policy @@ -360,6 +383,22 @@ nl80211_tid_config_attr_policy[NL80211_TID_CONFIG_ATTR_MAX + 1] = { NLA_POLICY_NESTED(nl80211_txattr_policy), }; +static const struct nla_policy +nl80211_fils_discovery_policy[NL80211_FILS_DISCOVERY_ATTR_MAX + 1] = { + [NL80211_FILS_DISCOVERY_ATTR_INT_MIN] = NLA_POLICY_MAX(NLA_U32, 10000), + [NL80211_FILS_DISCOVERY_ATTR_INT_MAX] = NLA_POLICY_MAX(NLA_U32, 10000), + NLA_POLICY_RANGE(NLA_BINARY, + NL80211_FILS_DISCOVERY_TMPL_MIN_LEN, + IEEE80211_MAX_DATA_LEN), +}; + +static const struct nla_policy +nl80211_unsol_bcast_probe_resp_policy[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_MAX + 1] = { + [NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INT] = NLA_POLICY_MAX(NLA_U32, 20), + [NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL] = { .type = NLA_BINARY, + .len = IEEE80211_MAX_DATA_LEN } +}; + static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [0] = { .strict_start_type = NL80211_ATTR_HE_OBSS_PD }, [NL80211_ATTR_WIPHY] = { .type = NLA_U32 }, @@ -539,7 +578,10 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_BG_SCAN_PERIOD] = { .type = NLA_U16 }, [NL80211_ATTR_WDEV] = { .type = NLA_U64 }, [NL80211_ATTR_USER_REG_HINT_TYPE] = { .type = NLA_U32 }, - [NL80211_ATTR_AUTH_DATA] = { .type = NLA_BINARY, }, + + /* need to include at least Auth Transaction and Status Code */ + [NL80211_ATTR_AUTH_DATA] = NLA_POLICY_MIN_LEN(4), + [NL80211_ATTR_VHT_CAPABILITY] = NLA_POLICY_EXACT_LEN_WARN(NL80211_VHT_CAPABILITY_LEN), [NL80211_ATTR_SCAN_FLAGS] = { .type = NLA_U32 }, [NL80211_ATTR_P2P_CTWINDOW] = NLA_POLICY_MAX(NLA_U8, 127), @@ -561,23 +603,30 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_IE_RIC] = { .type = NLA_BINARY, .len = IEEE80211_MAX_DATA_LEN }, [NL80211_ATTR_CRIT_PROT_ID] = { .type = NLA_U16 }, - [NL80211_ATTR_MAX_CRIT_PROT_DURATION] = { .type = NLA_U16 }, + [NL80211_ATTR_MAX_CRIT_PROT_DURATION] = + NLA_POLICY_MAX(NLA_U16, NL80211_CRIT_PROTO_MAX_DURATION), [NL80211_ATTR_PEER_AID] = NLA_POLICY_RANGE(NLA_U16, 1, IEEE80211_MAX_AID), [NL80211_ATTR_CH_SWITCH_COUNT] = { .type = NLA_U32 }, [NL80211_ATTR_CH_SWITCH_BLOCK_TX] = { .type = NLA_FLAG }, [NL80211_ATTR_CSA_IES] = { .type = NLA_NESTED }, - [NL80211_ATTR_CSA_C_OFF_BEACON] = { .type = NLA_BINARY }, - [NL80211_ATTR_CSA_C_OFF_PRESP] = { .type = NLA_BINARY }, - [NL80211_ATTR_STA_SUPPORTED_CHANNELS] = { .type = NLA_BINARY }, - [NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES] = { .type = NLA_BINARY }, + [NL80211_ATTR_CNTDWN_OFFS_BEACON] = { .type = NLA_BINARY }, + [NL80211_ATTR_CNTDWN_OFFS_PRESP] = { .type = NLA_BINARY }, + [NL80211_ATTR_STA_SUPPORTED_CHANNELS] = NLA_POLICY_MIN_LEN(2), + /* + * The value of the Length field of the Supported Operating + * Classes element is between 2 and 253. + */ + [NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES] = + NLA_POLICY_RANGE(NLA_BINARY, 2, 253), [NL80211_ATTR_HANDLE_DFS] = { .type = NLA_FLAG }, [NL80211_ATTR_OPMODE_NOTIF] = { .type = NLA_U8 }, [NL80211_ATTR_VENDOR_ID] = { .type = NLA_U32 }, [NL80211_ATTR_VENDOR_SUBCMD] = { .type = NLA_U32 }, [NL80211_ATTR_VENDOR_DATA] = { .type = NLA_BINARY }, - [NL80211_ATTR_QOS_MAP] = { .type = NLA_BINARY, - .len = IEEE80211_QOS_MAP_LEN_MAX }, + [NL80211_ATTR_QOS_MAP] = NLA_POLICY_RANGE(NLA_BINARY, + IEEE80211_QOS_MAP_LEN_MIN, + IEEE80211_QOS_MAP_LEN_MAX), [NL80211_ATTR_MAC_HINT] = NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN), [NL80211_ATTR_WIPHY_FREQ_HINT] = { .type = NLA_U32 }, [NL80211_ATTR_TDLS_PEER_CAPABILITY] = { .type = NLA_U32 }, @@ -625,15 +674,17 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { .len = FILS_ERP_MAX_RRK_LEN }, [NL80211_ATTR_FILS_CACHE_ID] = NLA_POLICY_EXACT_LEN_WARN(2), [NL80211_ATTR_PMK] = { .type = NLA_BINARY, .len = PMK_MAX_LEN }, + [NL80211_ATTR_PMKR0_NAME] = NLA_POLICY_EXACT_LEN(WLAN_PMK_NAME_LEN), [NL80211_ATTR_SCHED_SCAN_MULTI] = { .type = NLA_FLAG }, [NL80211_ATTR_EXTERNAL_AUTH_SUPPORT] = { .type = NLA_FLAG }, [NL80211_ATTR_TXQ_LIMIT] = { .type = NLA_U32 }, [NL80211_ATTR_TXQ_MEMORY_LIMIT] = { .type = NLA_U32 }, [NL80211_ATTR_TXQ_QUANTUM] = { .type = NLA_U32 }, - [NL80211_ATTR_HE_CAPABILITY] = { .type = NLA_BINARY, - .len = NL80211_HE_MAX_CAPABILITY_LEN }, - + [NL80211_ATTR_HE_CAPABILITY] = + NLA_POLICY_RANGE(NLA_BINARY, + NL80211_HE_MIN_CAPABILITY_LEN, + NL80211_HE_MAX_CAPABILITY_LEN), [NL80211_ATTR_FTM_RESPONDER] = NLA_POLICY_NESTED(nl80211_ftm_responder_policy), [NL80211_ATTR_TIMEOUT] = NLA_POLICY_MIN(NLA_U32, 1), @@ -654,10 +705,16 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_RECEIVE_MULTICAST] = { .type = NLA_FLAG }, [NL80211_ATTR_WIPHY_FREQ_OFFSET] = NLA_POLICY_RANGE(NLA_U32, 0, 999), [NL80211_ATTR_SCAN_FREQ_KHZ] = { .type = NLA_NESTED }, - [NL80211_ATTR_HE_6GHZ_CAPABILITY] = { - .type = NLA_EXACT_LEN, - .len = sizeof(struct ieee80211_he_6ghz_capa), - }, + [NL80211_ATTR_HE_6GHZ_CAPABILITY] = + NLA_POLICY_EXACT_LEN(sizeof(struct ieee80211_he_6ghz_capa)), + [NL80211_ATTR_FILS_DISCOVERY] = + NLA_POLICY_NESTED(nl80211_fils_discovery_policy), + [NL80211_ATTR_UNSOL_BCAST_PROBE_RESP] = + NLA_POLICY_NESTED(nl80211_unsol_bcast_probe_resp_policy), + [NL80211_ATTR_S1G_CAPABILITY] = + NLA_POLICY_EXACT_LEN(IEEE80211_S1G_CAPABILITY_LEN), + [NL80211_ATTR_S1G_CAPABILITY_MASK] = + NLA_POLICY_EXACT_LEN(IEEE80211_S1G_CAPABILITY_LEN), }; /* policy for the key attributes */ @@ -703,7 +760,7 @@ nl80211_wowlan_tcp_policy[NUM_NL80211_WOWLAN_TCP] = { [NL80211_WOWLAN_TCP_DST_MAC] = NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN), [NL80211_WOWLAN_TCP_SRC_PORT] = { .type = NLA_U16 }, [NL80211_WOWLAN_TCP_DST_PORT] = { .type = NLA_U16 }, - [NL80211_WOWLAN_TCP_DATA_PAYLOAD] = { .type = NLA_MIN_LEN, .len = 1 }, + [NL80211_WOWLAN_TCP_DATA_PAYLOAD] = NLA_POLICY_MIN_LEN(1), [NL80211_WOWLAN_TCP_DATA_PAYLOAD_SEQ] = { .len = sizeof(struct nl80211_wowlan_tcp_data_seq) }, @@ -711,8 +768,8 @@ nl80211_wowlan_tcp_policy[NUM_NL80211_WOWLAN_TCP] = { .len = sizeof(struct nl80211_wowlan_tcp_data_token) }, [NL80211_WOWLAN_TCP_DATA_INTERVAL] = { .type = NLA_U32 }, - [NL80211_WOWLAN_TCP_WAKE_PAYLOAD] = { .type = NLA_MIN_LEN, .len = 1 }, - [NL80211_WOWLAN_TCP_WAKE_MASK] = { .type = NLA_MIN_LEN, .len = 1 }, + [NL80211_WOWLAN_TCP_WAKE_PAYLOAD] = NLA_POLICY_MIN_LEN(1), + [NL80211_WOWLAN_TCP_WAKE_MASK] = NLA_POLICY_MIN_LEN(1), }; #endif /* CONFIG_PM */ @@ -738,7 +795,7 @@ nl80211_rekey_policy[NUM_NL80211_REKEY_DATA] = { .type = NLA_BINARY, .len = NL80211_KCK_EXT_LEN }, - [NL80211_REKEY_DATA_REPLAY_CTR] = NLA_POLICY_EXACT_LEN_WARN(NL80211_REPLAY_CTR_LEN), + [NL80211_REKEY_DATA_REPLAY_CTR] = NLA_POLICY_EXACT_LEN(NL80211_REPLAY_CTR_LEN), [NL80211_REKEY_DATA_AKM] = { .type = NLA_U32 }, }; @@ -778,7 +835,8 @@ nl80211_bss_select_policy[NL80211_BSS_SELECT_ATTR_MAX + 1] = { /* policy for NAN function attributes */ static const struct nla_policy nl80211_nan_func_policy[NL80211_NAN_FUNC_ATTR_MAX + 1] = { - [NL80211_NAN_FUNC_TYPE] = { .type = NLA_U8 }, + [NL80211_NAN_FUNC_TYPE] = + NLA_POLICY_MAX(NLA_U8, NL80211_NAN_FUNC_MAX_TYPE), [NL80211_NAN_FUNC_SERVICE_ID] = { .len = NL80211_NAN_FUNC_SERVICE_ID_LEN }, [NL80211_NAN_FUNC_PUBLISH_TYPE] = { .type = NLA_U8 }, @@ -926,6 +984,8 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy, if (!large && chan->flags & (IEEE80211_CHAN_NO_10MHZ | IEEE80211_CHAN_NO_20MHZ)) return 0; + if (!large && chan->freq_offset) + return 0; if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_FREQ, chan->center_freq)) @@ -992,6 +1052,21 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy, if ((chan->flags & IEEE80211_CHAN_NO_HE) && nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_HE)) goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_1MHZ) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_1MHZ)) + goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_2MHZ) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_2MHZ)) + goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_4MHZ) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_4MHZ)) + goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_8MHZ) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_8MHZ)) + goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_16MHZ) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_16MHZ)) + goto nla_put_failure; } if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER, @@ -1603,7 +1678,8 @@ nl80211_send_iftype_data(struct sk_buff *msg, } static int nl80211_send_band_rateinfo(struct sk_buff *msg, - struct ieee80211_supported_band *sband) + struct ieee80211_supported_band *sband, + bool large) { struct nlattr *nl_rates, *nl_rate; struct ieee80211_rate *rate; @@ -1631,7 +1707,7 @@ static int nl80211_send_band_rateinfo(struct sk_buff *msg, sband->vht_cap.cap))) return -ENOBUFS; - if (sband->n_iftype_data) { + if (large && sband->n_iftype_data) { struct nlattr *nl_iftype_data = nla_nest_start_noflag(msg, NL80211_BAND_ATTR_IFTYPE_DATA); @@ -1659,7 +1735,7 @@ static int nl80211_send_band_rateinfo(struct sk_buff *msg, } /* add EDMG info */ - if (sband->edmg_cap.channels && + if (large && sband->edmg_cap.channels && (nla_put_u8(msg, NL80211_BAND_ATTR_EDMG_CHANNELS, sband->edmg_cap.channels) || nla_put_u8(msg, NL80211_BAND_ATTR_EDMG_BW_CONFIG, @@ -2077,13 +2153,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, nla_put_u16(msg, NL80211_ATTR_MAX_SCHED_SCAN_IE_LEN, rdev->wiphy.max_sched_scan_ie_len) || nla_put_u8(msg, NL80211_ATTR_MAX_MATCH_SETS, - rdev->wiphy.max_match_sets) || - nla_put_u32(msg, NL80211_ATTR_MAX_NUM_SCHED_SCAN_PLANS, - rdev->wiphy.max_sched_scan_plans) || - nla_put_u32(msg, NL80211_ATTR_MAX_SCAN_PLAN_INTERVAL, - rdev->wiphy.max_sched_scan_plan_interval) || - nla_put_u32(msg, NL80211_ATTR_MAX_SCAN_PLAN_ITERATIONS, - rdev->wiphy.max_sched_scan_plan_iterations)) + rdev->wiphy.max_match_sets)) goto nla_put_failure; if ((rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN) && @@ -2173,6 +2243,10 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, band < NUM_NL80211_BANDS; band++) { struct ieee80211_supported_band *sband; + /* omit higher bands for ancient software */ + if (band > NL80211_BAND_5GHZ && !state->split) + break; + sband = rdev->wiphy.bands[band]; if (!sband) @@ -2184,7 +2258,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, switch (state->chan_start) { case 0: - if (nl80211_send_band_rateinfo(msg, sband)) + if (nl80211_send_band_rateinfo(msg, sband, + state->split)) goto nla_put_failure; state->chan_start++; if (state->split) @@ -2286,8 +2361,6 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, nla_put_flag(msg, NL80211_ATTR_OFFCHANNEL_TX_OK)) goto nla_put_failure; - if (nl80211_send_mgmt_stypes(msg, mgmt_stypes)) - goto nla_put_failure; state->split_start++; if (state->split) break; @@ -2355,9 +2428,23 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, * case we'll continue with more data in the next round, * but break unconditionally so unsplit data stops here. */ - state->split_start++; + if (state->split) + state->split_start++; + else + state->split_start = 0; break; case 9: + if (nl80211_send_mgmt_stypes(msg, mgmt_stypes)) + goto nla_put_failure; + + if (nla_put_u32(msg, NL80211_ATTR_MAX_NUM_SCHED_SCAN_PLANS, + rdev->wiphy.max_sched_scan_plans) || + nla_put_u32(msg, NL80211_ATTR_MAX_SCAN_PLAN_INTERVAL, + rdev->wiphy.max_sched_scan_plan_interval) || + nla_put_u32(msg, NL80211_ATTR_MAX_SCAN_PLAN_ITERATIONS, + rdev->wiphy.max_sched_scan_plan_iterations)) + goto nla_put_failure; + if (rdev->wiphy.extended_capabilities && (nla_put(msg, NL80211_ATTR_EXT_CAPA, rdev->wiphy.extended_capabilities_len, @@ -3798,7 +3885,8 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) * P2P Device and NAN do not have a netdev, so don't go * through the netdev notifier and must be added here */ - cfg80211_init_wdev(rdev, wdev); + cfg80211_init_wdev(wdev); + cfg80211_register_wdev(rdev, wdev); break; default: break; @@ -4422,21 +4510,106 @@ static bool vht_set_mcs_mask(struct ieee80211_supported_band *sband, return true; } +static u16 he_mcs_map_to_mcs_mask(u8 he_mcs_map) +{ + switch (he_mcs_map) { + case IEEE80211_HE_MCS_NOT_SUPPORTED: + return 0; + case IEEE80211_HE_MCS_SUPPORT_0_7: + return 0x00FF; + case IEEE80211_HE_MCS_SUPPORT_0_9: + return 0x03FF; + case IEEE80211_HE_MCS_SUPPORT_0_11: + return 0xFFF; + default: + break; + } + return 0; +} + +static void he_build_mcs_mask(u16 he_mcs_map, + u16 he_mcs_mask[NL80211_HE_NSS_MAX]) +{ + u8 nss; + + for (nss = 0; nss < NL80211_HE_NSS_MAX; nss++) { + he_mcs_mask[nss] = he_mcs_map_to_mcs_mask(he_mcs_map & 0x03); + he_mcs_map >>= 2; + } +} + +static u16 he_get_txmcsmap(struct genl_info *info, + const struct ieee80211_sta_he_cap *he_cap) +{ + struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; + __le16 tx_mcs; + + switch (wdev->chandef.width) { + case NL80211_CHAN_WIDTH_80P80: + tx_mcs = he_cap->he_mcs_nss_supp.tx_mcs_80p80; + break; + case NL80211_CHAN_WIDTH_160: + tx_mcs = he_cap->he_mcs_nss_supp.tx_mcs_160; + break; + default: + tx_mcs = he_cap->he_mcs_nss_supp.tx_mcs_80; + break; + } + return le16_to_cpu(tx_mcs); +} + +static bool he_set_mcs_mask(struct genl_info *info, + struct wireless_dev *wdev, + struct ieee80211_supported_band *sband, + struct nl80211_txrate_he *txrate, + u16 mcs[NL80211_HE_NSS_MAX]) +{ + const struct ieee80211_sta_he_cap *he_cap; + u16 tx_mcs_mask[NL80211_HE_NSS_MAX] = {}; + u16 tx_mcs_map = 0; + u8 i; + + he_cap = ieee80211_get_he_iftype_cap(sband, wdev->iftype); + if (!he_cap) + return false; + + memset(mcs, 0, sizeof(u16) * NL80211_HE_NSS_MAX); + + tx_mcs_map = he_get_txmcsmap(info, he_cap); + + /* Build he_mcs_mask from HE capabilities */ + he_build_mcs_mask(tx_mcs_map, tx_mcs_mask); + + for (i = 0; i < NL80211_HE_NSS_MAX; i++) { + if ((tx_mcs_mask[i] & txrate->mcs[i]) == txrate->mcs[i]) + mcs[i] = txrate->mcs[i]; + else + return false; + } + + return true; +} + static int nl80211_parse_tx_bitrate_mask(struct genl_info *info, struct nlattr *attrs[], enum nl80211_attrs attr, - struct cfg80211_bitrate_mask *mask) + struct cfg80211_bitrate_mask *mask, + struct net_device *dev) { struct nlattr *tb[NL80211_TXRATE_MAX + 1]; struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct wireless_dev *wdev = dev->ieee80211_ptr; int rem, i; struct nlattr *tx_rates; struct ieee80211_supported_band *sband; - u16 vht_tx_mcs_map; + u16 vht_tx_mcs_map, he_tx_mcs_map; memset(mask, 0, sizeof(*mask)); /* Default to all rates enabled */ for (i = 0; i < NUM_NL80211_BANDS; i++) { + const struct ieee80211_sta_he_cap *he_cap; + sband = rdev->wiphy.bands[i]; if (!sband) @@ -4452,6 +4625,16 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info, vht_tx_mcs_map = le16_to_cpu(sband->vht_cap.vht_mcs.tx_mcs_map); vht_build_mcs_mask(vht_tx_mcs_map, mask->control[i].vht_mcs); + + he_cap = ieee80211_get_he_iftype_cap(sband, wdev->iftype); + if (!he_cap) + continue; + + he_tx_mcs_map = he_get_txmcsmap(info, he_cap); + he_build_mcs_mask(he_tx_mcs_map, mask->control[i].he_mcs); + + mask->control[i].he_gi = 0xFF; + mask->control[i].he_ltf = 0xFF; } /* if no rates are given set it back to the defaults */ @@ -4507,13 +4690,25 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info, if (mask->control[band].gi > NL80211_TXRATE_FORCE_LGI) return -EINVAL; } + if (tb[NL80211_TXRATE_HE] && + !he_set_mcs_mask(info, wdev, sband, + nla_data(tb[NL80211_TXRATE_HE]), + mask->control[band].he_mcs)) + return -EINVAL; + if (tb[NL80211_TXRATE_HE_GI]) + mask->control[band].he_gi = + nla_get_u8(tb[NL80211_TXRATE_HE_GI]); + if (tb[NL80211_TXRATE_HE_LTF]) + mask->control[band].he_ltf = + nla_get_u8(tb[NL80211_TXRATE_HE_LTF]); if (mask->control[band].legacy == 0) { - /* don't allow empty legacy rates if HT or VHT + /* don't allow empty legacy rates if HT, VHT or HE * are not even supported. */ if (!(rdev->wiphy.bands[band]->ht_cap.ht_supported || - rdev->wiphy.bands[band]->vht_cap.vht_supported)) + rdev->wiphy.bands[band]->vht_cap.vht_supported || + ieee80211_get_he_iftype_cap(sband, wdev->iftype))) return -EINVAL; for (i = 0; i < IEEE80211_HT_MCS_MASK_LEN; i++) @@ -4524,6 +4719,10 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info, if (mask->control[band].vht_mcs[i]) goto out; + for (i = 0; i < NL80211_HE_NSS_MAX; i++) + if (mask->control[band].he_mcs[i]) + goto out; + /* legacy and mcs rates may not be both empty */ return -EINVAL; } @@ -4683,18 +4882,34 @@ static int nl80211_parse_he_obss_pd(struct nlattr *attrs, if (err) return err; - if (!tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET] || - !tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET]) + if (!tb[NL80211_HE_OBSS_PD_ATTR_SR_CTRL]) return -EINVAL; - he_obss_pd->min_offset = - nla_get_u32(tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET]); - he_obss_pd->max_offset = - nla_get_u32(tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET]); + he_obss_pd->sr_ctrl = nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_SR_CTRL]); + + if (tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET]) + he_obss_pd->min_offset = + nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET]); + if (tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET]) + he_obss_pd->max_offset = + nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET]); + if (tb[NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET]) + he_obss_pd->non_srg_max_offset = + nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET]); - if (he_obss_pd->min_offset >= he_obss_pd->max_offset) + if (he_obss_pd->min_offset > he_obss_pd->max_offset) return -EINVAL; + if (tb[NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP]) + memcpy(he_obss_pd->bss_color_bitmap, + nla_data(tb[NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP]), + sizeof(he_obss_pd->bss_color_bitmap)); + + if (tb[NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP]) + memcpy(he_obss_pd->partial_bssid_bitmap, + nla_data(tb[NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP]), + sizeof(he_obss_pd->partial_bssid_bitmap)); + he_obss_pd->enable = true; return 0; @@ -4724,6 +4939,65 @@ static int nl80211_parse_he_bss_color(struct nlattr *attrs, return 0; } +static int nl80211_parse_fils_discovery(struct cfg80211_registered_device *rdev, + struct nlattr *attrs, + struct cfg80211_ap_settings *params) +{ + struct nlattr *tb[NL80211_FILS_DISCOVERY_ATTR_MAX + 1]; + int ret; + struct cfg80211_fils_discovery *fd = ¶ms->fils_discovery; + + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_FILS_DISCOVERY)) + return -EINVAL; + + ret = nla_parse_nested(tb, NL80211_FILS_DISCOVERY_ATTR_MAX, attrs, + NULL, NULL); + if (ret) + return ret; + + if (!tb[NL80211_FILS_DISCOVERY_ATTR_INT_MIN] || + !tb[NL80211_FILS_DISCOVERY_ATTR_INT_MAX] || + !tb[NL80211_FILS_DISCOVERY_ATTR_TMPL]) + return -EINVAL; + + fd->tmpl_len = nla_len(tb[NL80211_FILS_DISCOVERY_ATTR_TMPL]); + fd->tmpl = nla_data(tb[NL80211_FILS_DISCOVERY_ATTR_TMPL]); + fd->min_interval = nla_get_u32(tb[NL80211_FILS_DISCOVERY_ATTR_INT_MIN]); + fd->max_interval = nla_get_u32(tb[NL80211_FILS_DISCOVERY_ATTR_INT_MAX]); + + return 0; +} + +static int +nl80211_parse_unsol_bcast_probe_resp(struct cfg80211_registered_device *rdev, + struct nlattr *attrs, + struct cfg80211_ap_settings *params) +{ + struct nlattr *tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_MAX + 1]; + int ret; + struct cfg80211_unsol_bcast_probe_resp *presp = + ¶ms->unsol_bcast_probe_resp; + + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_UNSOL_BCAST_PROBE_RESP)) + return -EINVAL; + + ret = nla_parse_nested(tb, NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_MAX, + attrs, NULL, NULL); + if (ret) + return ret; + + if (!tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INT] || + !tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL]) + return -EINVAL; + + presp->tmpl = nla_data(tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL]); + presp->tmpl_len = nla_len(tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL]); + presp->interval = nla_get_u32(tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INT]); + return 0; +} + static void nl80211_check_ap_rate_selectors(struct cfg80211_ap_settings *params, const u8 *rates) { @@ -4834,8 +5108,9 @@ static bool nl80211_valid_auth_type(struct cfg80211_registered_device *rdev, return false; return true; case NL80211_CMD_START_AP: - /* SAE not supported yet */ - if (auth_type == NL80211_AUTHTYPE_SAE) + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_SAE_OFFLOAD_AP) && + auth_type == NL80211_AUTHTYPE_SAE) return false; /* FILS not supported yet */ if (auth_type == NL80211_AUTHTYPE_FILS_SK || @@ -4899,8 +5174,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) params.ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); params.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); - if (params.ssid_len == 0 || - params.ssid_len > IEEE80211_MAX_SSID_LEN) + if (params.ssid_len == 0) return -EINVAL; } @@ -4969,7 +5243,8 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_TX_RATES]) { err = nl80211_parse_tx_bitrate_mask(info, info->attrs, NL80211_ATTR_TX_RATES, - ¶ms.beacon_rate); + ¶ms.beacon_rate, + dev); if (err) return err; @@ -5031,6 +5306,22 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) goto out; } + if (info->attrs[NL80211_ATTR_FILS_DISCOVERY]) { + err = nl80211_parse_fils_discovery(rdev, + info->attrs[NL80211_ATTR_FILS_DISCOVERY], + ¶ms); + if (err) + goto out; + } + + if (info->attrs[NL80211_ATTR_UNSOL_BCAST_PROBE_RESP]) { + err = nl80211_parse_unsol_bcast_probe_resp( + rdev, info->attrs[NL80211_ATTR_UNSOL_BCAST_PROBE_RESP], + ¶ms); + if (err) + return err; + } + nl80211_calculate_ap_params(¶ms); if (info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT]) @@ -5840,11 +6131,9 @@ static int nl80211_parse_sta_channel_info(struct genl_info *info, nla_len(info->attrs[NL80211_ATTR_STA_SUPPORTED_CHANNELS]); /* * Need to include at least one (first channel, number of - * channels) tuple for each subband, and must have proper - * tuples for the rest of the data as well. + * channels) tuple for each subband (checked in policy), + * and must have proper tuples for the rest of the data as well. */ - if (params->supported_channels_len < 2) - return -EINVAL; if (params->supported_channels_len % 2) return -EINVAL; } @@ -5854,13 +6143,6 @@ static int nl80211_parse_sta_channel_info(struct genl_info *info, nla_data(info->attrs[NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES]); params->supported_oper_classes_len = nla_len(info->attrs[NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES]); - /* - * The value of the Length field of the Supported Operating - * Classes element is between 2 and 253. - */ - if (params->supported_oper_classes_len < 2 || - params->supported_oper_classes_len > 253) - return -EINVAL; } return 0; } @@ -5883,9 +6165,6 @@ static int nl80211_set_station_tdls(struct genl_info *info, nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]); params->he_capa_len = nla_len(info->attrs[NL80211_ATTR_HE_CAPABILITY]); - - if (params->he_capa_len < NL80211_HE_MIN_CAPABILITY_LEN) - return -EINVAL; } err = nl80211_parse_sta_channel_info(info, params); @@ -6144,10 +6423,6 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]); params.he_capa_len = nla_len(info->attrs[NL80211_ATTR_HE_CAPABILITY]); - - /* max len is validated in nla policy */ - if (params.he_capa_len < NL80211_HE_MIN_CAPABILITY_LEN) - return -EINVAL; } if (info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY]) @@ -8006,7 +8281,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) request->scan_start = jiffies; rdev->scan_req = request; - err = rdev_scan(rdev, request); + err = cfg80211_scan(rdev); if (err) goto out_free; @@ -8419,23 +8694,14 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, } if (ssid) { - if (nla_len(ssid) > IEEE80211_MAX_SSID_LEN) { - err = -EINVAL; - goto out_free; - } memcpy(request->match_sets[i].ssid.ssid, nla_data(ssid), nla_len(ssid)); request->match_sets[i].ssid.ssid_len = nla_len(ssid); } - if (bssid) { - if (nla_len(bssid) != ETH_ALEN) { - err = -EINVAL; - goto out_free; - } + if (bssid) memcpy(request->match_sets[i].bssid, nla_data(bssid), ETH_ALEN); - } /* special attribute - old implementation w/a */ request->match_sets[i].rssi_thold = default_match_rssi; @@ -8790,10 +9056,10 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) if (err) return err; - if (!csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]) + if (!csa_attrs[NL80211_ATTR_CNTDWN_OFFS_BEACON]) return -EINVAL; - len = nla_len(csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]); + len = nla_len(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_BEACON]); if (!len || (len % sizeof(u16))) return -EINVAL; @@ -8804,7 +9070,7 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) return -EINVAL; params.counter_offsets_beacon = - nla_data(csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]); + nla_data(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_BEACON]); /* sanity checks - counters should fit and be the same */ for (i = 0; i < params.n_counter_offsets_beacon; i++) { @@ -8817,8 +9083,8 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } - if (csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]) { - len = nla_len(csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]); + if (csa_attrs[NL80211_ATTR_CNTDWN_OFFS_PRESP]) { + len = nla_len(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_PRESP]); if (!len || (len % sizeof(u16))) return -EINVAL; @@ -8829,7 +9095,7 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) return -EINVAL; params.counter_offsets_presp = - nla_data(csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]); + nla_data(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_PRESP]); /* sanity checks - counters should fit and be the same */ for (i = 0; i < params.n_counter_offsets_presp; i++) { @@ -9094,6 +9360,11 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq, survey->channel->center_freq)) goto nla_put_failure; + if (survey->channel && survey->channel->freq_offset && + nla_put_u32(msg, NL80211_SURVEY_INFO_FREQUENCY_OFFSET, + survey->channel->freq_offset)) + goto nla_put_failure; + if ((survey->filled & SURVEY_INFO_NOISE_DBM) && nla_put_u8(msg, NL80211_SURVEY_INFO_NOISE, survey->noise)) goto nla_put_failure; @@ -9312,9 +9583,6 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) return -EINVAL; auth_data = nla_data(info->attrs[NL80211_ATTR_AUTH_DATA]); auth_data_len = nla_len(info->attrs[NL80211_ATTR_AUTH_DATA]); - /* need to include at least Auth Transaction and Status Code */ - if (auth_data_len < 4) - return -EINVAL; } local_state_change = !!info->attrs[NL80211_ATTR_LOCAL_STATE_CHANGE]; @@ -9454,7 +9722,9 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev, if (info->attrs[NL80211_ATTR_SAE_PASSWORD]) { if (!wiphy_ext_feature_isset(&rdev->wiphy, - NL80211_EXT_FEATURE_SAE_OFFLOAD)) + NL80211_EXT_FEATURE_SAE_OFFLOAD) && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_SAE_OFFLOAD_AP)) return -EINVAL; settings->sae_pwd = nla_data(info->attrs[NL80211_ATTR_SAE_PASSWORD]); @@ -9572,6 +9842,22 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) nla_data(info->attrs[NL80211_ATTR_FILS_NONCES]); } + if (info->attrs[NL80211_ATTR_S1G_CAPABILITY_MASK]) { + if (!info->attrs[NL80211_ATTR_S1G_CAPABILITY]) + return -EINVAL; + memcpy(&req.s1g_capa_mask, + nla_data(info->attrs[NL80211_ATTR_S1G_CAPABILITY_MASK]), + sizeof(req.s1g_capa_mask)); + } + + if (info->attrs[NL80211_ATTR_S1G_CAPABILITY]) { + if (!info->attrs[NL80211_ATTR_S1G_CAPABILITY_MASK]) + return -EINVAL; + memcpy(&req.s1g_capa, + nla_data(info->attrs[NL80211_ATTR_S1G_CAPABILITY]), + sizeof(req.s1g_capa)); + } + err = nl80211_crypto_settings(rdev, info, &req.crypto, 1); if (!err) { wdev_lock(dev->ieee80211_ptr); @@ -10801,7 +11087,8 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb, return -EOPNOTSUPP; err = nl80211_parse_tx_bitrate_mask(info, info->attrs, - NL80211_ATTR_TX_RATES, &mask); + NL80211_ATTR_TX_RATES, &mask, + dev); if (err) return err; @@ -11409,7 +11696,8 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_TX_RATES]) { err = nl80211_parse_tx_bitrate_mask(info, info->attrs, NL80211_ATTR_TX_RATES, - &setup.beacon_rate); + &setup.beacon_rate, + dev); if (err) return err; @@ -12361,8 +12649,6 @@ static int nl80211_set_rekey_data(struct sk_buff *skb, struct genl_info *info) if (!tb[NL80211_REKEY_DATA_REPLAY_CTR] || !tb[NL80211_REKEY_DATA_KEK] || !tb[NL80211_REKEY_DATA_KCK]) return -EINVAL; - if (nla_len(tb[NL80211_REKEY_DATA_REPLAY_CTR]) != NL80211_REPLAY_CTR_LEN) - return -ERANGE; if (nla_len(tb[NL80211_REKEY_DATA_KEK]) != NL80211_KEK_LEN && !(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK && nla_len(tb[NL80211_REKEY_DATA_KEK]) == NL80211_KEK_EXT_LEN)) @@ -12687,8 +12973,7 @@ static int nl80211_nan_add_func(struct sk_buff *skb, func->cookie = cfg80211_assign_cookie(rdev); - if (!tb[NL80211_NAN_FUNC_TYPE] || - nla_get_u8(tb[NL80211_NAN_FUNC_TYPE]) > NL80211_NAN_FUNC_MAX_TYPE) { + if (!tb[NL80211_NAN_FUNC_TYPE]) { err = -EINVAL; goto out; } @@ -13178,9 +13463,6 @@ static int nl80211_crit_protocol_start(struct sk_buff *skb, duration = nla_get_u16(info->attrs[NL80211_ATTR_MAX_CRIT_PROT_DURATION]); - if (duration > NL80211_CRIT_PROTO_MAX_DURATION) - return -ERANGE; - ret = rdev_crit_proto_start(rdev, wdev, proto, duration); if (!ret) rdev->crit_proto_nlportid = info->snd_portid; @@ -13565,8 +13847,7 @@ static int nl80211_set_qos_map(struct sk_buff *skb, pos = nla_data(info->attrs[NL80211_ATTR_QOS_MAP]); len = nla_len(info->attrs[NL80211_ATTR_QOS_MAP]); - if (len % 2 || len < IEEE80211_QOS_MAP_LEN_MIN || - len > IEEE80211_QOS_MAP_LEN_MAX) + if (len % 2) return -EINVAL; qos_map = kzalloc(sizeof(struct cfg80211_qos_map), GFP_KERNEL); @@ -13834,17 +14115,9 @@ static int nl80211_set_pmk(struct sk_buff *skb, struct genl_info *info) goto out; } - if (info->attrs[NL80211_ATTR_PMKR0_NAME]) { - int r0_name_len = nla_len(info->attrs[NL80211_ATTR_PMKR0_NAME]); - - if (r0_name_len != WLAN_PMK_NAME_LEN) { - ret = -EINVAL; - goto out; - } - + if (info->attrs[NL80211_ATTR_PMKR0_NAME]) pmk_conf.pmk_r0_name = nla_data(info->attrs[NL80211_ATTR_PMKR0_NAME]); - } ret = rdev_set_pmk(rdev, dev, &pmk_conf); out: @@ -13903,8 +14176,7 @@ static int nl80211_external_auth(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_SSID]) { params.ssid.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); - if (params.ssid.ssid_len == 0 || - params.ssid.ssid_len > IEEE80211_MAX_SSID_LEN) + if (params.ssid.ssid_len == 0) return -EINVAL; memcpy(params.ssid.ssid, nla_data(info->attrs[NL80211_ATTR_SSID]), @@ -14205,7 +14477,7 @@ static int parse_tid_conf(struct cfg80211_registered_device *rdev, if (tid_conf->txrate_type != NL80211_TX_RATE_AUTOMATIC) { attr = NL80211_TID_CONFIG_ATTR_TX_RATE; err = nl80211_parse_tx_bitrate_mask(info, attrs, attr, - &tid_conf->txrate_mask); + &tid_conf->txrate_mask, dev); if (err) return err; @@ -14397,6 +14669,9 @@ static const struct genl_ops nl80211_ops[] = { .internal_flags = NL80211_FLAG_NEED_WIPHY | NL80211_FLAG_NEED_RTNL, }, +}; + +static const struct genl_small_ops nl80211_small_ops[] = { { .cmd = NL80211_CMD_SET_WIPHY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, @@ -15258,6 +15533,8 @@ static struct genl_family nl80211_fam __ro_after_init = { .module = THIS_MODULE, .ops = nl80211_ops, .n_ops = ARRAY_SIZE(nl80211_ops), + .small_ops = nl80211_small_ops, + .n_small_ops = ARRAY_SIZE(nl80211_small_ops), .mcgrps = nl80211_mcgrps, .n_mcgrps = ARRAY_SIZE(nl80211_mcgrps), .parallel_ops = true, @@ -15312,6 +15589,7 @@ static int nl80211_add_scan_req(struct sk_buff *msg, struct cfg80211_scan_request *req = rdev->scan_req; struct nlattr *nest; int i; + struct cfg80211_scan_info *info; if (WARN_ON(!req)) return 0; @@ -15355,11 +15633,13 @@ static int nl80211_add_scan_req(struct sk_buff *msg, nla_put_u32(msg, NL80211_ATTR_SCAN_FLAGS, req->flags)) goto nla_put_failure; - if (req->info.scan_start_tsf && + info = rdev->int_scan_req ? &rdev->int_scan_req->info : + &rdev->scan_req->info; + if (info->scan_start_tsf && (nla_put_u64_64bit(msg, NL80211_ATTR_SCAN_START_TIME_TSF, - req->info.scan_start_tsf, NL80211_BSS_PAD) || + info->scan_start_tsf, NL80211_BSS_PAD) || nla_put(msg, NL80211_ATTR_SCAN_START_TIME_TSF_BSSID, ETH_ALEN, - req->info.tsf_bssid))) + info->tsf_bssid))) goto nla_put_failure; return 0; diff --git a/net/wireless/radiotap.c b/net/wireless/radiotap.c index d5e28239e030..36f1b59a78bf 100644 --- a/net/wireless/radiotap.c +++ b/net/wireless/radiotap.c @@ -59,6 +59,7 @@ static const struct ieee80211_radiotap_namespace radiotap_ns = { * @iterator: radiotap_iterator to initialize * @radiotap_header: radiotap header to parse * @max_length: total length we can parse into (eg, whole packet length) + * @vns: vendor namespaces to parse * * Returns: 0 or a negative error code if there is a problem. * diff --git a/net/wireless/reg.c b/net/wireless/reg.c index d8a90d397423..a04fdfb35f07 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1594,7 +1594,7 @@ freq_reg_info_regd(u32 center_freq, /* * We only need to know if one frequency rule was - * was in center_freq's band, that's enough, so lets + * in center_freq's band, that's enough, so let's * not overwrite it once found */ if (!band_rule_found) @@ -1616,10 +1616,12 @@ static const struct ieee80211_reg_rule * __freq_reg_info(struct wiphy *wiphy, u32 center_freq, u32 min_bw) { const struct ieee80211_regdomain *regd = reg_get_regdomain(wiphy); - const struct ieee80211_reg_rule *reg_rule = NULL; + const u32 bws[] = {0, 1, 2, 4, 5, 8, 10, 16, 20}; + const struct ieee80211_reg_rule *reg_rule; + int i = ARRAY_SIZE(bws) - 1; u32 bw; - for (bw = MHZ_TO_KHZ(20); bw >= min_bw; bw = bw / 2) { + for (bw = MHZ_TO_KHZ(bws[i]); bw >= min_bw; bw = MHZ_TO_KHZ(bws[i--])) { reg_rule = freq_reg_info_regd(center_freq, regd, bw); if (!IS_ERR(reg_rule)) return reg_rule; @@ -1631,7 +1633,9 @@ __freq_reg_info(struct wiphy *wiphy, u32 center_freq, u32 min_bw) const struct ieee80211_reg_rule *freq_reg_info(struct wiphy *wiphy, u32 center_freq) { - return __freq_reg_info(wiphy, center_freq, MHZ_TO_KHZ(20)); + u32 min_bw = center_freq < MHZ_TO_KHZ(1000) ? 1 : 20; + + return __freq_reg_info(wiphy, center_freq, MHZ_TO_KHZ(min_bw)); } EXPORT_SYMBOL(freq_reg_info); @@ -1659,6 +1663,7 @@ static uint32_t reg_rule_to_chan_bw_flags(const struct ieee80211_regdomain *regd { const struct ieee80211_freq_range *freq_range = NULL; u32 max_bandwidth_khz, center_freq_khz, bw_flags = 0; + bool is_s1g = chan->band == NL80211_BAND_S1GHZ; freq_range = ®_rule->freq_range; @@ -1678,70 +1683,72 @@ static uint32_t reg_rule_to_chan_bw_flags(const struct ieee80211_regdomain *regd MHZ_TO_KHZ(20))) bw_flags |= IEEE80211_CHAN_NO_20MHZ; - if (max_bandwidth_khz < MHZ_TO_KHZ(10)) - bw_flags |= IEEE80211_CHAN_NO_10MHZ; - if (max_bandwidth_khz < MHZ_TO_KHZ(20)) - bw_flags |= IEEE80211_CHAN_NO_20MHZ; - if (max_bandwidth_khz < MHZ_TO_KHZ(40)) - bw_flags |= IEEE80211_CHAN_NO_HT40; - if (max_bandwidth_khz < MHZ_TO_KHZ(80)) - bw_flags |= IEEE80211_CHAN_NO_80MHZ; - if (max_bandwidth_khz < MHZ_TO_KHZ(160)) - bw_flags |= IEEE80211_CHAN_NO_160MHZ; + if (is_s1g) { + /* S1G is strict about non overlapping channels. We can + * calculate which bandwidth is allowed per channel by finding + * the largest bandwidth which cleanly divides the freq_range. + */ + int edge_offset; + int ch_bw = max_bandwidth_khz; + + while (ch_bw) { + edge_offset = (center_freq_khz - ch_bw / 2) - + freq_range->start_freq_khz; + if (edge_offset % ch_bw == 0) { + switch (KHZ_TO_MHZ(ch_bw)) { + case 1: + bw_flags |= IEEE80211_CHAN_1MHZ; + break; + case 2: + bw_flags |= IEEE80211_CHAN_2MHZ; + break; + case 4: + bw_flags |= IEEE80211_CHAN_4MHZ; + break; + case 8: + bw_flags |= IEEE80211_CHAN_8MHZ; + break; + case 16: + bw_flags |= IEEE80211_CHAN_16MHZ; + break; + default: + /* If we got here, no bandwidths fit on + * this frequency, ie. band edge. + */ + bw_flags |= IEEE80211_CHAN_DISABLED; + break; + } + break; + } + ch_bw /= 2; + } + } else { + if (max_bandwidth_khz < MHZ_TO_KHZ(10)) + bw_flags |= IEEE80211_CHAN_NO_10MHZ; + if (max_bandwidth_khz < MHZ_TO_KHZ(20)) + bw_flags |= IEEE80211_CHAN_NO_20MHZ; + if (max_bandwidth_khz < MHZ_TO_KHZ(40)) + bw_flags |= IEEE80211_CHAN_NO_HT40; + if (max_bandwidth_khz < MHZ_TO_KHZ(80)) + bw_flags |= IEEE80211_CHAN_NO_80MHZ; + if (max_bandwidth_khz < MHZ_TO_KHZ(160)) + bw_flags |= IEEE80211_CHAN_NO_160MHZ; + } return bw_flags; } -/* - * Note that right now we assume the desired channel bandwidth - * is always 20 MHz for each individual channel (HT40 uses 20 MHz - * per channel, the primary and the extension channel). - */ -static void handle_channel(struct wiphy *wiphy, - enum nl80211_reg_initiator initiator, - struct ieee80211_channel *chan) +static void handle_channel_single_rule(struct wiphy *wiphy, + enum nl80211_reg_initiator initiator, + struct ieee80211_channel *chan, + u32 flags, + struct regulatory_request *lr, + struct wiphy *request_wiphy, + const struct ieee80211_reg_rule *reg_rule) { - u32 flags, bw_flags = 0; - const struct ieee80211_reg_rule *reg_rule = NULL; + u32 bw_flags = 0; const struct ieee80211_power_rule *power_rule = NULL; - struct wiphy *request_wiphy = NULL; - struct regulatory_request *lr = get_last_request(); const struct ieee80211_regdomain *regd; - request_wiphy = wiphy_idx_to_wiphy(lr->wiphy_idx); - - flags = chan->orig_flags; - - reg_rule = freq_reg_info(wiphy, ieee80211_channel_to_khz(chan)); - if (IS_ERR(reg_rule)) { - /* - * We will disable all channels that do not match our - * received regulatory rule unless the hint is coming - * from a Country IE and the Country IE had no information - * about a band. The IEEE 802.11 spec allows for an AP - * to send only a subset of the regulatory rules allowed, - * so an AP in the US that only supports 2.4 GHz may only send - * a country IE with information for the 2.4 GHz band - * while 5 GHz is still supported. - */ - if (initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE && - PTR_ERR(reg_rule) == -ERANGE) - return; - - if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER && - request_wiphy && request_wiphy == wiphy && - request_wiphy->regulatory_flags & REGULATORY_STRICT_REG) { - pr_debug("Disabling freq %d.%03d MHz for good\n", - chan->center_freq, chan->freq_offset); - chan->orig_flags |= IEEE80211_CHAN_DISABLED; - chan->flags = chan->orig_flags; - } else { - pr_debug("Disabling freq %d.%03d MHz\n", - chan->center_freq, chan->freq_offset); - chan->flags |= IEEE80211_CHAN_DISABLED; - } - return; - } - regd = reg_get_regdomain(wiphy); power_rule = ®_rule->power_rule; @@ -1803,6 +1810,204 @@ static void handle_channel(struct wiphy *wiphy, chan->max_power = chan->max_reg_power; } +static void handle_channel_adjacent_rules(struct wiphy *wiphy, + enum nl80211_reg_initiator initiator, + struct ieee80211_channel *chan, + u32 flags, + struct regulatory_request *lr, + struct wiphy *request_wiphy, + const struct ieee80211_reg_rule *rrule1, + const struct ieee80211_reg_rule *rrule2, + struct ieee80211_freq_range *comb_range) +{ + u32 bw_flags1 = 0; + u32 bw_flags2 = 0; + const struct ieee80211_power_rule *power_rule1 = NULL; + const struct ieee80211_power_rule *power_rule2 = NULL; + const struct ieee80211_regdomain *regd; + + regd = reg_get_regdomain(wiphy); + + power_rule1 = &rrule1->power_rule; + power_rule2 = &rrule2->power_rule; + bw_flags1 = reg_rule_to_chan_bw_flags(regd, rrule1, chan); + bw_flags2 = reg_rule_to_chan_bw_flags(regd, rrule2, chan); + + if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER && + request_wiphy && request_wiphy == wiphy && + request_wiphy->regulatory_flags & REGULATORY_STRICT_REG) { + /* This guarantees the driver's requested regulatory domain + * will always be used as a base for further regulatory + * settings + */ + chan->flags = + map_regdom_flags(rrule1->flags) | + map_regdom_flags(rrule2->flags) | + bw_flags1 | + bw_flags2; + chan->orig_flags = chan->flags; + chan->max_antenna_gain = + min_t(int, MBI_TO_DBI(power_rule1->max_antenna_gain), + MBI_TO_DBI(power_rule2->max_antenna_gain)); + chan->orig_mag = chan->max_antenna_gain; + chan->max_reg_power = + min_t(int, MBM_TO_DBM(power_rule1->max_eirp), + MBM_TO_DBM(power_rule2->max_eirp)); + chan->max_power = chan->max_reg_power; + chan->orig_mpwr = chan->max_reg_power; + + if (chan->flags & IEEE80211_CHAN_RADAR) { + chan->dfs_cac_ms = IEEE80211_DFS_MIN_CAC_TIME_MS; + if (rrule1->dfs_cac_ms || rrule2->dfs_cac_ms) + chan->dfs_cac_ms = max_t(unsigned int, + rrule1->dfs_cac_ms, + rrule2->dfs_cac_ms); + } + + return; + } + + chan->dfs_state = NL80211_DFS_USABLE; + chan->dfs_state_entered = jiffies; + + chan->beacon_found = false; + chan->flags = flags | bw_flags1 | bw_flags2 | + map_regdom_flags(rrule1->flags) | + map_regdom_flags(rrule2->flags); + + /* reg_rule_to_chan_bw_flags may forbids 10 and forbids 20 MHz + * (otherwise no adj. rule case), recheck therefore + */ + if (cfg80211_does_bw_fit_range(comb_range, + ieee80211_channel_to_khz(chan), + MHZ_TO_KHZ(10))) + chan->flags &= ~IEEE80211_CHAN_NO_10MHZ; + if (cfg80211_does_bw_fit_range(comb_range, + ieee80211_channel_to_khz(chan), + MHZ_TO_KHZ(20))) + chan->flags &= ~IEEE80211_CHAN_NO_20MHZ; + + chan->max_antenna_gain = + min_t(int, chan->orig_mag, + min_t(int, + MBI_TO_DBI(power_rule1->max_antenna_gain), + MBI_TO_DBI(power_rule2->max_antenna_gain))); + chan->max_reg_power = min_t(int, + MBM_TO_DBM(power_rule1->max_eirp), + MBM_TO_DBM(power_rule2->max_eirp)); + + if (chan->flags & IEEE80211_CHAN_RADAR) { + if (rrule1->dfs_cac_ms || rrule2->dfs_cac_ms) + chan->dfs_cac_ms = max_t(unsigned int, + rrule1->dfs_cac_ms, + rrule2->dfs_cac_ms); + else + chan->dfs_cac_ms = IEEE80211_DFS_MIN_CAC_TIME_MS; + } + + if (chan->orig_mpwr) { + /* Devices that use REGULATORY_COUNTRY_IE_FOLLOW_POWER + * will always follow the passed country IE power settings. + */ + if (initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE && + wiphy->regulatory_flags & REGULATORY_COUNTRY_IE_FOLLOW_POWER) + chan->max_power = chan->max_reg_power; + else + chan->max_power = min(chan->orig_mpwr, + chan->max_reg_power); + } else { + chan->max_power = chan->max_reg_power; + } +} + +/* Note that right now we assume the desired channel bandwidth + * is always 20 MHz for each individual channel (HT40 uses 20 MHz + * per channel, the primary and the extension channel). + */ +static void handle_channel(struct wiphy *wiphy, + enum nl80211_reg_initiator initiator, + struct ieee80211_channel *chan) +{ + const u32 orig_chan_freq = ieee80211_channel_to_khz(chan); + struct regulatory_request *lr = get_last_request(); + struct wiphy *request_wiphy = wiphy_idx_to_wiphy(lr->wiphy_idx); + const struct ieee80211_reg_rule *rrule = NULL; + const struct ieee80211_reg_rule *rrule1 = NULL; + const struct ieee80211_reg_rule *rrule2 = NULL; + + u32 flags = chan->orig_flags; + + rrule = freq_reg_info(wiphy, orig_chan_freq); + if (IS_ERR(rrule)) { + /* check for adjacent match, therefore get rules for + * chan - 20 MHz and chan + 20 MHz and test + * if reg rules are adjacent + */ + rrule1 = freq_reg_info(wiphy, + orig_chan_freq - MHZ_TO_KHZ(20)); + rrule2 = freq_reg_info(wiphy, + orig_chan_freq + MHZ_TO_KHZ(20)); + if (!IS_ERR(rrule1) && !IS_ERR(rrule2)) { + struct ieee80211_freq_range comb_range; + + if (rrule1->freq_range.end_freq_khz != + rrule2->freq_range.start_freq_khz) + goto disable_chan; + + comb_range.start_freq_khz = + rrule1->freq_range.start_freq_khz; + comb_range.end_freq_khz = + rrule2->freq_range.end_freq_khz; + comb_range.max_bandwidth_khz = + min_t(u32, + rrule1->freq_range.max_bandwidth_khz, + rrule2->freq_range.max_bandwidth_khz); + + if (!cfg80211_does_bw_fit_range(&comb_range, + orig_chan_freq, + MHZ_TO_KHZ(20))) + goto disable_chan; + + handle_channel_adjacent_rules(wiphy, initiator, chan, + flags, lr, request_wiphy, + rrule1, rrule2, + &comb_range); + return; + } + +disable_chan: + /* We will disable all channels that do not match our + * received regulatory rule unless the hint is coming + * from a Country IE and the Country IE had no information + * about a band. The IEEE 802.11 spec allows for an AP + * to send only a subset of the regulatory rules allowed, + * so an AP in the US that only supports 2.4 GHz may only send + * a country IE with information for the 2.4 GHz band + * while 5 GHz is still supported. + */ + if (initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE && + PTR_ERR(rrule) == -ERANGE) + return; + + if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER && + request_wiphy && request_wiphy == wiphy && + request_wiphy->regulatory_flags & REGULATORY_STRICT_REG) { + pr_debug("Disabling freq %d.%03d MHz for good\n", + chan->center_freq, chan->freq_offset); + chan->orig_flags |= IEEE80211_CHAN_DISABLED; + chan->flags = chan->orig_flags; + } else { + pr_debug("Disabling freq %d.%03d MHz\n", + chan->center_freq, chan->freq_offset); + chan->flags |= IEEE80211_CHAN_DISABLED; + } + return; + } + + handle_channel_single_rule(wiphy, initiator, chan, flags, lr, + request_wiphy, rrule); +} + static void handle_band(struct wiphy *wiphy, enum nl80211_reg_initiator initiator, struct ieee80211_supported_band *sband) @@ -3170,7 +3375,7 @@ static void restore_custom_reg_settings(struct wiphy *wiphy) * - send a user regulatory hint if applicable * * Device drivers that send a regulatory hint for a specific country - * keep their own regulatory domain on wiphy->regd so that does does + * keep their own regulatory domain on wiphy->regd so that does * not need to be remembered. */ static void restore_regulatory_settings(bool reset_user, bool cached) @@ -3411,7 +3616,7 @@ static void print_rd_rules(const struct ieee80211_regdomain *rd) power_rule = ®_rule->power_rule; if (reg_rule->flags & NL80211_RRF_AUTO_BW) - snprintf(bw, sizeof(bw), "%d KHz, %d KHz AUTO", + snprintf(bw, sizeof(bw), "%d KHz, %u KHz AUTO", freq_range->max_bandwidth_khz, reg_get_max_bandwidth(rd, reg_rule)); else diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 04f2d198c215..8d0e49c46db3 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -5,7 +5,7 @@ * Copyright 2008 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2016 Intel Deutschland GmbH - * Copyright (C) 2018-2019 Intel Corporation + * Copyright (C) 2018-2020 Intel Corporation */ #include <linux/kernel.h> #include <linux/slab.h> @@ -14,6 +14,8 @@ #include <linux/wireless.h> #include <linux/nl80211.h> #include <linux/etherdevice.h> +#include <linux/crc32.h> +#include <linux/bitfield.h> #include <net/arp.h> #include <net/cfg80211.h> #include <net/cfg80211-wext.h> @@ -55,7 +57,7 @@ * * Also note that the hidden_beacon_bss pointer is only relevant * if the driver uses something other than the IEs, e.g. private - * data stored stored in the BSS struct, since the beacon IEs are + * data stored in the BSS struct, since the beacon IEs are * also linked into the probe response struct. */ @@ -74,6 +76,43 @@ MODULE_PARM_DESC(bss_entries_limit, #define IEEE80211_SCAN_RESULT_EXPIRE (30 * HZ) +/** + * struct cfg80211_colocated_ap - colocated AP information + * + * @list: linked list to all colocated aPS + * @bssid: BSSID of the reported AP + * @ssid: SSID of the reported AP + * @ssid_len: length of the ssid + * @center_freq: frequency the reported AP is on + * @unsolicited_probe: the reported AP is part of an ESS, where all the APs + * that operate in the same channel as the reported AP and that might be + * detected by a STA receiving this frame, are transmitting unsolicited + * Probe Response frames every 20 TUs + * @oct_recommended: OCT is recommended to exchange MMPDUs with the reported AP + * @same_ssid: the reported AP has the same SSID as the reporting AP + * @multi_bss: the reported AP is part of a multiple BSSID set + * @transmitted_bssid: the reported AP is the transmitting BSSID + * @colocated_ess: all the APs that share the same ESS as the reported AP are + * colocated and can be discovered via legacy bands. + * @short_ssid_valid: short_ssid is valid and can be used + * @short_ssid: the short SSID for this SSID + */ +struct cfg80211_colocated_ap { + struct list_head list; + u8 bssid[ETH_ALEN]; + u8 ssid[IEEE80211_MAX_SSID_LEN]; + size_t ssid_len; + u32 short_ssid; + u32 center_freq; + u8 unsolicited_probe:1, + oct_recommended:1, + same_ssid:1, + multi_bss:1, + transmitted_bssid:1, + colocated_ess:1, + short_ssid_valid:1; +}; + static void bss_free(struct cfg80211_internal_bss *bss) { struct cfg80211_bss_ies *ies; @@ -448,10 +487,433 @@ static bool cfg80211_bss_expire_oldest(struct cfg80211_registered_device *rdev) return ret; } +static u8 cfg80211_parse_bss_param(u8 data, + struct cfg80211_colocated_ap *coloc_ap) +{ + coloc_ap->oct_recommended = + u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_OCT_RECOMMENDED); + coloc_ap->same_ssid = + u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_SAME_SSID); + coloc_ap->multi_bss = + u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_MULTI_BSSID); + coloc_ap->transmitted_bssid = + u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_TRANSMITTED_BSSID); + coloc_ap->unsolicited_probe = + u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_PROBE_ACTIVE); + coloc_ap->colocated_ess = + u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_COLOC_ESS); + + return u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_COLOC_AP); +} + +static int cfg80211_calc_short_ssid(const struct cfg80211_bss_ies *ies, + const struct element **elem, u32 *s_ssid) +{ + + *elem = cfg80211_find_elem(WLAN_EID_SSID, ies->data, ies->len); + if (!*elem || (*elem)->datalen > IEEE80211_MAX_SSID_LEN) + return -EINVAL; + + *s_ssid = ~crc32_le(~0, (*elem)->data, (*elem)->datalen); + return 0; +} + +static void cfg80211_free_coloc_ap_list(struct list_head *coloc_ap_list) +{ + struct cfg80211_colocated_ap *ap, *tmp_ap; + + list_for_each_entry_safe(ap, tmp_ap, coloc_ap_list, list) { + list_del(&ap->list); + kfree(ap); + } +} + +static int cfg80211_parse_ap_info(struct cfg80211_colocated_ap *entry, + const u8 *pos, u8 length, + const struct element *ssid_elem, + int s_ssid_tmp) +{ + /* skip the TBTT offset */ + pos++; + + memcpy(entry->bssid, pos, ETH_ALEN); + pos += ETH_ALEN; + + if (length == IEEE80211_TBTT_INFO_OFFSET_BSSID_SSSID_BSS_PARAM) { + memcpy(&entry->short_ssid, pos, + sizeof(entry->short_ssid)); + entry->short_ssid_valid = true; + pos += 4; + } + + /* skip non colocated APs */ + if (!cfg80211_parse_bss_param(*pos, entry)) + return -EINVAL; + pos++; + + if (length == IEEE80211_TBTT_INFO_OFFSET_BSSID_BSS_PARAM) { + /* + * no information about the short ssid. Consider the entry valid + * for now. It would later be dropped in case there are explicit + * SSIDs that need to be matched + */ + if (!entry->same_ssid) + return 0; + } + + if (entry->same_ssid) { + entry->short_ssid = s_ssid_tmp; + entry->short_ssid_valid = true; + + /* + * This is safe because we validate datalen in + * cfg80211_parse_colocated_ap(), before calling this + * function. + */ + memcpy(&entry->ssid, &ssid_elem->data, + ssid_elem->datalen); + entry->ssid_len = ssid_elem->datalen; + } + return 0; +} + +static int cfg80211_parse_colocated_ap(const struct cfg80211_bss_ies *ies, + struct list_head *list) +{ + struct ieee80211_neighbor_ap_info *ap_info; + const struct element *elem, *ssid_elem; + const u8 *pos, *end; + u32 s_ssid_tmp; + int n_coloc = 0, ret; + LIST_HEAD(ap_list); + + elem = cfg80211_find_elem(WLAN_EID_REDUCED_NEIGHBOR_REPORT, ies->data, + ies->len); + if (!elem || elem->datalen > IEEE80211_MAX_SSID_LEN) + return 0; + + pos = elem->data; + end = pos + elem->datalen; + + ret = cfg80211_calc_short_ssid(ies, &ssid_elem, &s_ssid_tmp); + if (ret) + return ret; + + /* RNR IE may contain more than one NEIGHBOR_AP_INFO */ + while (pos + sizeof(*ap_info) <= end) { + enum nl80211_band band; + int freq; + u8 length, i, count; + + ap_info = (void *)pos; + count = u8_get_bits(ap_info->tbtt_info_hdr, + IEEE80211_AP_INFO_TBTT_HDR_COUNT) + 1; + length = ap_info->tbtt_info_len; + + pos += sizeof(*ap_info); + + if (!ieee80211_operating_class_to_band(ap_info->op_class, + &band)) + break; + + freq = ieee80211_channel_to_frequency(ap_info->channel, band); + + if (end - pos < count * ap_info->tbtt_info_len) + break; + + /* + * TBTT info must include bss param + BSSID + + * (short SSID or same_ssid bit to be set). + * ignore other options, and move to the + * next AP info + */ + if (band != NL80211_BAND_6GHZ || + (length != IEEE80211_TBTT_INFO_OFFSET_BSSID_BSS_PARAM && + length < IEEE80211_TBTT_INFO_OFFSET_BSSID_SSSID_BSS_PARAM)) { + pos += count * ap_info->tbtt_info_len; + continue; + } + + for (i = 0; i < count; i++) { + struct cfg80211_colocated_ap *entry; + + entry = kzalloc(sizeof(*entry) + IEEE80211_MAX_SSID_LEN, + GFP_ATOMIC); + + if (!entry) + break; + + entry->center_freq = freq; + + if (!cfg80211_parse_ap_info(entry, pos, length, + ssid_elem, s_ssid_tmp)) { + n_coloc++; + list_add_tail(&entry->list, &ap_list); + } else { + kfree(entry); + } + + pos += ap_info->tbtt_info_len; + } + } + + if (pos != end) { + cfg80211_free_coloc_ap_list(&ap_list); + return 0; + } + + list_splice_tail(&ap_list, list); + return n_coloc; +} + +static void cfg80211_scan_req_add_chan(struct cfg80211_scan_request *request, + struct ieee80211_channel *chan, + bool add_to_6ghz) +{ + int i; + u32 n_channels = request->n_channels; + struct cfg80211_scan_6ghz_params *params = + &request->scan_6ghz_params[request->n_6ghz_params]; + + for (i = 0; i < n_channels; i++) { + if (request->channels[i] == chan) { + if (add_to_6ghz) + params->channel_idx = i; + return; + } + } + + request->channels[n_channels] = chan; + if (add_to_6ghz) + request->scan_6ghz_params[request->n_6ghz_params].channel_idx = + n_channels; + + request->n_channels++; +} + +static bool cfg80211_find_ssid_match(struct cfg80211_colocated_ap *ap, + struct cfg80211_scan_request *request) +{ + u8 i; + u32 s_ssid; + + for (i = 0; i < request->n_ssids; i++) { + /* wildcard ssid in the scan request */ + if (!request->ssids[i].ssid_len) + return true; + + if (ap->ssid_len && + ap->ssid_len == request->ssids[i].ssid_len) { + if (!memcmp(request->ssids[i].ssid, ap->ssid, + ap->ssid_len)) + return true; + } else if (ap->short_ssid_valid) { + s_ssid = ~crc32_le(~0, request->ssids[i].ssid, + request->ssids[i].ssid_len); + + if (ap->short_ssid == s_ssid) + return true; + } + } + + return false; +} + +static int cfg80211_scan_6ghz(struct cfg80211_registered_device *rdev) +{ + u8 i; + struct cfg80211_colocated_ap *ap; + int n_channels, count = 0, err; + struct cfg80211_scan_request *request, *rdev_req = rdev->scan_req; + LIST_HEAD(coloc_ap_list); + bool need_scan_psc; + const struct ieee80211_sband_iftype_data *iftd; + + rdev_req->scan_6ghz = true; + + if (!rdev->wiphy.bands[NL80211_BAND_6GHZ]) + return -EOPNOTSUPP; + + iftd = ieee80211_get_sband_iftype_data(rdev->wiphy.bands[NL80211_BAND_6GHZ], + rdev_req->wdev->iftype); + if (!iftd || !iftd->he_cap.has_he) + return -EOPNOTSUPP; + + n_channels = rdev->wiphy.bands[NL80211_BAND_6GHZ]->n_channels; + + if (rdev_req->flags & NL80211_SCAN_FLAG_COLOCATED_6GHZ) { + struct cfg80211_internal_bss *intbss; + + spin_lock_bh(&rdev->bss_lock); + list_for_each_entry(intbss, &rdev->bss_list, list) { + struct cfg80211_bss *res = &intbss->pub; + const struct cfg80211_bss_ies *ies; + + ies = rcu_access_pointer(res->ies); + count += cfg80211_parse_colocated_ap(ies, + &coloc_ap_list); + } + spin_unlock_bh(&rdev->bss_lock); + } + + request = kzalloc(struct_size(request, channels, n_channels) + + sizeof(*request->scan_6ghz_params) * count, + GFP_KERNEL); + if (!request) { + cfg80211_free_coloc_ap_list(&coloc_ap_list); + return -ENOMEM; + } + + *request = *rdev_req; + request->n_channels = 0; + request->scan_6ghz_params = + (void *)&request->channels[n_channels]; + + /* + * PSC channels should not be scanned if all the reported co-located APs + * are indicating that all APs in the same ESS are co-located + */ + if (count) { + need_scan_psc = false; + + list_for_each_entry(ap, &coloc_ap_list, list) { + if (!ap->colocated_ess) { + need_scan_psc = true; + break; + } + } + } else { + need_scan_psc = true; + } + + /* + * add to the scan request the channels that need to be scanned + * regardless of the collocated APs (PSC channels or all channels + * in case that NL80211_SCAN_FLAG_COLOCATED_6GHZ is not set) + */ + for (i = 0; i < rdev_req->n_channels; i++) { + if (rdev_req->channels[i]->band == NL80211_BAND_6GHZ && + ((need_scan_psc && + cfg80211_channel_is_psc(rdev_req->channels[i])) || + !(rdev_req->flags & NL80211_SCAN_FLAG_COLOCATED_6GHZ))) { + cfg80211_scan_req_add_chan(request, + rdev_req->channels[i], + false); + } + } + + if (!(rdev_req->flags & NL80211_SCAN_FLAG_COLOCATED_6GHZ)) + goto skip; + + list_for_each_entry(ap, &coloc_ap_list, list) { + bool found = false; + struct cfg80211_scan_6ghz_params *scan_6ghz_params = + &request->scan_6ghz_params[request->n_6ghz_params]; + struct ieee80211_channel *chan = + ieee80211_get_channel(&rdev->wiphy, ap->center_freq); + + if (!chan || chan->flags & IEEE80211_CHAN_DISABLED) + continue; + + for (i = 0; i < rdev_req->n_channels; i++) { + if (rdev_req->channels[i] == chan) + found = true; + } + + if (!found) + continue; + + if (request->n_ssids > 0 && + !cfg80211_find_ssid_match(ap, request)) + continue; + + cfg80211_scan_req_add_chan(request, chan, true); + memcpy(scan_6ghz_params->bssid, ap->bssid, ETH_ALEN); + scan_6ghz_params->short_ssid = ap->short_ssid; + scan_6ghz_params->short_ssid_valid = ap->short_ssid_valid; + scan_6ghz_params->unsolicited_probe = ap->unsolicited_probe; + + /* + * If a PSC channel is added to the scan and 'need_scan_psc' is + * set to false, then all the APs that the scan logic is + * interested with on the channel are collocated and thus there + * is no need to perform the initial PSC channel listen. + */ + if (cfg80211_channel_is_psc(chan) && !need_scan_psc) + scan_6ghz_params->psc_no_listen = true; + + request->n_6ghz_params++; + } + +skip: + cfg80211_free_coloc_ap_list(&coloc_ap_list); + + if (request->n_channels) { + struct cfg80211_scan_request *old = rdev->int_scan_req; + + rdev->int_scan_req = request; + + /* + * If this scan follows a previous scan, save the scan start + * info from the first part of the scan + */ + if (old) + rdev->int_scan_req->info = old->info; + + err = rdev_scan(rdev, request); + if (err) { + rdev->int_scan_req = old; + kfree(request); + } else { + kfree(old); + } + + return err; + } + + kfree(request); + return -EINVAL; +} + +int cfg80211_scan(struct cfg80211_registered_device *rdev) +{ + struct cfg80211_scan_request *request; + struct cfg80211_scan_request *rdev_req = rdev->scan_req; + u32 n_channels = 0, idx, i; + + if (!(rdev->wiphy.flags & WIPHY_FLAG_SPLIT_SCAN_6GHZ)) + return rdev_scan(rdev, rdev_req); + + for (i = 0; i < rdev_req->n_channels; i++) { + if (rdev_req->channels[i]->band != NL80211_BAND_6GHZ) + n_channels++; + } + + if (!n_channels) + return cfg80211_scan_6ghz(rdev); + + request = kzalloc(struct_size(request, channels, n_channels), + GFP_KERNEL); + if (!request) + return -ENOMEM; + + *request = *rdev_req; + request->n_channels = n_channels; + + for (i = idx = 0; i < rdev_req->n_channels; i++) { + if (rdev_req->channels[i]->band != NL80211_BAND_6GHZ) + request->channels[idx++] = rdev_req->channels[i]; + } + + rdev_req->scan_6ghz = false; + rdev->int_scan_req = request; + return rdev_scan(rdev, request); +} + void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool send_message) { - struct cfg80211_scan_request *request; + struct cfg80211_scan_request *request, *rdev_req; struct wireless_dev *wdev; struct sk_buff *msg; #ifdef CONFIG_CFG80211_WEXT @@ -466,11 +928,18 @@ void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, return; } - request = rdev->scan_req; - if (!request) + rdev_req = rdev->scan_req; + if (!rdev_req) return; - wdev = request->wdev; + wdev = rdev_req->wdev; + request = rdev->int_scan_req ? rdev->int_scan_req : rdev_req; + + if (wdev_running(wdev) && + (rdev->wiphy.flags & WIPHY_FLAG_SPLIT_SCAN_6GHZ) && + !rdev_req->scan_6ghz && !request->info.aborted && + !cfg80211_scan_6ghz(rdev)) + return; /* * This must be before sending the other events! @@ -501,8 +970,11 @@ void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, if (wdev->netdev) dev_put(wdev->netdev); + kfree(rdev->int_scan_req); + rdev->int_scan_req = NULL; + + kfree(rdev->scan_req); rdev->scan_req = NULL; - kfree(request); if (!send_message) rdev->scan_msg = msg; @@ -525,10 +997,25 @@ void __cfg80211_scan_done(struct work_struct *wk) void cfg80211_scan_done(struct cfg80211_scan_request *request, struct cfg80211_scan_info *info) { + struct cfg80211_scan_info old_info = request->info; + trace_cfg80211_scan_done(request, info); - WARN_ON(request != wiphy_to_rdev(request->wiphy)->scan_req); + WARN_ON(request != wiphy_to_rdev(request->wiphy)->scan_req && + request != wiphy_to_rdev(request->wiphy)->int_scan_req); request->info = *info; + + /* + * In case the scan is split, the scan_start_tsf and tsf_bssid should + * be of the first part. In such a case old_info.scan_start_tsf should + * be non zero. + */ + if (request->scan_6ghz && old_info.scan_start_tsf) { + request->info.scan_start_tsf = old_info.scan_start_tsf; + memcpy(request->info.tsf_bssid, old_info.tsf_bssid, + sizeof(request->info.tsf_bssid)); + } + request->notified = true; queue_work(cfg80211_wq, &wiphy_to_rdev(request->wiphy)->scan_done_wk); } @@ -1315,15 +1802,24 @@ cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen, int channel_number = -1; struct ieee80211_channel *alt_channel; - tmp = cfg80211_find_ie(WLAN_EID_DS_PARAMS, ie, ielen); - if (tmp && tmp[1] == 1) { - channel_number = tmp[2]; + if (channel->band == NL80211_BAND_S1GHZ) { + tmp = cfg80211_find_ie(WLAN_EID_S1G_OPERATION, ie, ielen); + if (tmp && tmp[1] >= sizeof(struct ieee80211_s1g_oper_ie)) { + struct ieee80211_s1g_oper_ie *s1gop = (void *)(tmp + 2); + + channel_number = s1gop->primary_ch; + } } else { - tmp = cfg80211_find_ie(WLAN_EID_HT_OPERATION, ie, ielen); - if (tmp && tmp[1] >= sizeof(struct ieee80211_ht_operation)) { - struct ieee80211_ht_operation *htop = (void *)(tmp + 2); + tmp = cfg80211_find_ie(WLAN_EID_DS_PARAMS, ie, ielen); + if (tmp && tmp[1] == 1) { + channel_number = tmp[2]; + } else { + tmp = cfg80211_find_ie(WLAN_EID_HT_OPERATION, ie, ielen); + if (tmp && tmp[1] >= sizeof(struct ieee80211_ht_operation)) { + struct ieee80211_ht_operation *htop = (void *)(tmp + 2); - channel_number = htop->primary_chan; + channel_number = htop->primary_chan; + } } } @@ -1488,7 +1984,7 @@ static const struct element ielen - (mbssid_end - ie)); /* - * If is is not the last subelement in current MBSSID IE or there isn't + * If it is not the last subelement in current MBSSID IE or there isn't * a next MBSSID IE - profile is complete. */ if ((sub_elem->data + sub_elem->datalen < mbssid_end - 1) || @@ -1807,8 +2303,11 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy, struct cfg80211_bss_ies *ies; struct ieee80211_channel *channel; bool signal_valid; - size_t ielen = len - offsetof(struct ieee80211_mgmt, - u.probe_resp.variable); + struct ieee80211_ext *ext = NULL; + u8 *bssid, *variable; + u16 capability, beacon_int; + size_t ielen, min_hdr_len = offsetof(struct ieee80211_mgmt, + u.probe_resp.variable); int bss_type; BUILD_BUG_ON(offsetof(struct ieee80211_mgmt, u.probe_resp.variable) != @@ -1826,21 +2325,57 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy, (data->signal < 0 || data->signal > 100))) return NULL; - if (WARN_ON(len < offsetof(struct ieee80211_mgmt, u.probe_resp.variable))) + if (ieee80211_is_s1g_beacon(mgmt->frame_control)) { + ext = (void *) mgmt; + min_hdr_len = offsetof(struct ieee80211_ext, u.s1g_beacon); + if (ieee80211_is_s1g_short_beacon(mgmt->frame_control)) + min_hdr_len = offsetof(struct ieee80211_ext, + u.s1g_short_beacon.variable); + } + + if (WARN_ON(len < min_hdr_len)) return NULL; - channel = cfg80211_get_bss_channel(wiphy, mgmt->u.beacon.variable, + ielen = len - min_hdr_len; + variable = mgmt->u.probe_resp.variable; + if (ext) { + if (ieee80211_is_s1g_short_beacon(mgmt->frame_control)) + variable = ext->u.s1g_short_beacon.variable; + else + variable = ext->u.s1g_beacon.variable; + } + + channel = cfg80211_get_bss_channel(wiphy, variable, ielen, data->chan, data->scan_width); if (!channel) return NULL; + if (ext) { + struct ieee80211_s1g_bcn_compat_ie *compat; + u8 *ie; + + ie = (void *)cfg80211_find_ie(WLAN_EID_S1G_BCN_COMPAT, + variable, ielen); + if (!ie) + return NULL; + compat = (void *)(ie + 2); + bssid = ext->u.s1g_beacon.sa; + capability = le16_to_cpu(compat->compat_info); + beacon_int = le16_to_cpu(compat->beacon_int); + } else { + bssid = mgmt->bssid; + beacon_int = le16_to_cpu(mgmt->u.probe_resp.beacon_int); + capability = le16_to_cpu(mgmt->u.probe_resp.capab_info); + } + ies = kzalloc(sizeof(*ies) + ielen, gfp); if (!ies) return NULL; ies->len = ielen; ies->tsf = le64_to_cpu(mgmt->u.probe_resp.timestamp); - ies->from_beacon = ieee80211_is_beacon(mgmt->frame_control); - memcpy(ies->data, mgmt->u.probe_resp.variable, ielen); + ies->from_beacon = ieee80211_is_beacon(mgmt->frame_control) || + ieee80211_is_s1g_beacon(mgmt->frame_control); + memcpy(ies->data, variable, ielen); if (ieee80211_is_probe_resp(mgmt->frame_control)) rcu_assign_pointer(tmp.pub.proberesp_ies, ies); @@ -1848,12 +2383,12 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy, rcu_assign_pointer(tmp.pub.beacon_ies, ies); rcu_assign_pointer(tmp.pub.ies, ies); - memcpy(tmp.pub.bssid, mgmt->bssid, ETH_ALEN); + memcpy(tmp.pub.bssid, bssid, ETH_ALEN); + tmp.pub.beacon_interval = beacon_int; + tmp.pub.capability = capability; tmp.pub.channel = channel; tmp.pub.scan_width = data->scan_width; tmp.pub.signal = data->signal; - tmp.pub.beacon_interval = le16_to_cpu(mgmt->u.probe_resp.beacon_int); - tmp.pub.capability = le16_to_cpu(mgmt->u.probe_resp.capab_info); tmp.ts_boottime = data->boottime_ns; tmp.parent_tsf = data->parent_tsf; tmp.pub.chains = data->chains; diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 079ce320dc1e..38df713f2e2e 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -24,7 +24,7 @@ /* * Software SME in cfg80211, using auth/assoc/deauth calls to the - * driver. This is is for implementing nl80211's connect/disconnect + * driver. This is for implementing nl80211's connect/disconnect * and wireless extensions (if configured.) */ diff --git a/net/wireless/util.c b/net/wireless/util.c index 6fa99df52f86..f01746894a4e 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -111,6 +111,33 @@ u32 ieee80211_channel_to_freq_khz(int chan, enum nl80211_band band) } EXPORT_SYMBOL(ieee80211_channel_to_freq_khz); +enum nl80211_chan_width +ieee80211_s1g_channel_width(const struct ieee80211_channel *chan) +{ + if (WARN_ON(!chan || chan->band != NL80211_BAND_S1GHZ)) + return NL80211_CHAN_WIDTH_20_NOHT; + + /*S1G defines a single allowed channel width per channel. + * Extract that width here. + */ + if (chan->flags & IEEE80211_CHAN_1MHZ) + return NL80211_CHAN_WIDTH_1; + else if (chan->flags & IEEE80211_CHAN_2MHZ) + return NL80211_CHAN_WIDTH_2; + else if (chan->flags & IEEE80211_CHAN_4MHZ) + return NL80211_CHAN_WIDTH_4; + else if (chan->flags & IEEE80211_CHAN_8MHZ) + return NL80211_CHAN_WIDTH_8; + else if (chan->flags & IEEE80211_CHAN_16MHZ) + return NL80211_CHAN_WIDTH_16; + + pr_err("unknown channel width for channel at %dKHz?\n", + ieee80211_channel_to_khz(chan)); + + return NL80211_CHAN_WIDTH_1; +} +EXPORT_SYMBOL(ieee80211_s1g_channel_width); + int ieee80211_freq_khz_to_channel(u32 freq) { /* TODO: just handle MHz for now */ @@ -399,6 +426,11 @@ unsigned int __attribute_const__ ieee80211_hdrlen(__le16 fc) { unsigned int hdrlen = 24; + if (ieee80211_is_ext(fc)) { + hdrlen = 4; + goto out; + } + if (ieee80211_is_data(fc)) { if (ieee80211_has_a4(fc)) hdrlen = 30; diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 4d2160c989a3..78f2927ead7f 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -497,7 +497,7 @@ static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev, /* * We only need to store WEP keys, since they're the only keys that - * can be be set before a connection is established and persist after + * can be set before a connection is established and persist after * disconnecting. */ if (!addr && (params->cipher == WLAN_CIPHER_SUITE_WEP40 || diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index b010bfde0149..56d052bc65cb 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -23,162 +23,6 @@ static DEFINE_IDA(umem_ida); -void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) -{ - unsigned long flags; - - if (!xs->tx) - return; - - spin_lock_irqsave(&umem->xsk_tx_list_lock, flags); - list_add_rcu(&xs->list, &umem->xsk_tx_list); - spin_unlock_irqrestore(&umem->xsk_tx_list_lock, flags); -} - -void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) -{ - unsigned long flags; - - if (!xs->tx) - return; - - spin_lock_irqsave(&umem->xsk_tx_list_lock, flags); - list_del_rcu(&xs->list); - spin_unlock_irqrestore(&umem->xsk_tx_list_lock, flags); -} - -/* The umem is stored both in the _rx struct and the _tx struct as we do - * not know if the device has more tx queues than rx, or the opposite. - * This might also change during run time. - */ -static int xdp_reg_umem_at_qid(struct net_device *dev, struct xdp_umem *umem, - u16 queue_id) -{ - if (queue_id >= max_t(unsigned int, - dev->real_num_rx_queues, - dev->real_num_tx_queues)) - return -EINVAL; - - if (queue_id < dev->real_num_rx_queues) - dev->_rx[queue_id].umem = umem; - if (queue_id < dev->real_num_tx_queues) - dev->_tx[queue_id].umem = umem; - - return 0; -} - -struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, - u16 queue_id) -{ - if (queue_id < dev->real_num_rx_queues) - return dev->_rx[queue_id].umem; - if (queue_id < dev->real_num_tx_queues) - return dev->_tx[queue_id].umem; - - return NULL; -} -EXPORT_SYMBOL(xdp_get_umem_from_qid); - -static void xdp_clear_umem_at_qid(struct net_device *dev, u16 queue_id) -{ - if (queue_id < dev->real_num_rx_queues) - dev->_rx[queue_id].umem = NULL; - if (queue_id < dev->real_num_tx_queues) - dev->_tx[queue_id].umem = NULL; -} - -int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, - u16 queue_id, u16 flags) -{ - bool force_zc, force_copy; - struct netdev_bpf bpf; - int err = 0; - - ASSERT_RTNL(); - - force_zc = flags & XDP_ZEROCOPY; - force_copy = flags & XDP_COPY; - - if (force_zc && force_copy) - return -EINVAL; - - if (xdp_get_umem_from_qid(dev, queue_id)) - return -EBUSY; - - err = xdp_reg_umem_at_qid(dev, umem, queue_id); - if (err) - return err; - - umem->dev = dev; - umem->queue_id = queue_id; - - if (flags & XDP_USE_NEED_WAKEUP) { - umem->flags |= XDP_UMEM_USES_NEED_WAKEUP; - /* Tx needs to be explicitly woken up the first time. - * Also for supporting drivers that do not implement this - * feature. They will always have to call sendto(). - */ - xsk_set_tx_need_wakeup(umem); - } - - dev_hold(dev); - - if (force_copy) - /* For copy-mode, we are done. */ - return 0; - - if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_wakeup) { - err = -EOPNOTSUPP; - goto err_unreg_umem; - } - - bpf.command = XDP_SETUP_XSK_UMEM; - bpf.xsk.umem = umem; - bpf.xsk.queue_id = queue_id; - - err = dev->netdev_ops->ndo_bpf(dev, &bpf); - if (err) - goto err_unreg_umem; - - umem->zc = true; - return 0; - -err_unreg_umem: - if (!force_zc) - err = 0; /* fallback to copy mode */ - if (err) - xdp_clear_umem_at_qid(dev, queue_id); - return err; -} - -void xdp_umem_clear_dev(struct xdp_umem *umem) -{ - struct netdev_bpf bpf; - int err; - - ASSERT_RTNL(); - - if (!umem->dev) - return; - - if (umem->zc) { - bpf.command = XDP_SETUP_XSK_UMEM; - bpf.xsk.umem = NULL; - bpf.xsk.queue_id = umem->queue_id; - - err = umem->dev->netdev_ops->ndo_bpf(umem->dev, &bpf); - - if (err) - WARN(1, "failed to disable umem!\n"); - } - - xdp_clear_umem_at_qid(umem->dev, umem->queue_id); - - dev_put(umem->dev); - umem->dev = NULL; - umem->zc = false; -} - static void xdp_umem_unpin_pages(struct xdp_umem *umem) { unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true); @@ -195,38 +39,33 @@ static void xdp_umem_unaccount_pages(struct xdp_umem *umem) } } -static void xdp_umem_release(struct xdp_umem *umem) +static void xdp_umem_addr_unmap(struct xdp_umem *umem) { - rtnl_lock(); - xdp_umem_clear_dev(umem); - rtnl_unlock(); - - ida_simple_remove(&umem_ida, umem->id); + vunmap(umem->addrs); + umem->addrs = NULL; +} - if (umem->fq) { - xskq_destroy(umem->fq); - umem->fq = NULL; - } +static int xdp_umem_addr_map(struct xdp_umem *umem, struct page **pages, + u32 nr_pages) +{ + umem->addrs = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL); + if (!umem->addrs) + return -ENOMEM; + return 0; +} - if (umem->cq) { - xskq_destroy(umem->cq); - umem->cq = NULL; - } +static void xdp_umem_release(struct xdp_umem *umem) +{ + umem->zc = false; + ida_simple_remove(&umem_ida, umem->id); - xp_destroy(umem->pool); + xdp_umem_addr_unmap(umem); xdp_umem_unpin_pages(umem); xdp_umem_unaccount_pages(umem); kfree(umem); } -static void xdp_umem_release_deferred(struct work_struct *work) -{ - struct xdp_umem *umem = container_of(work, struct xdp_umem, work); - - xdp_umem_release(umem); -} - void xdp_get_umem(struct xdp_umem *umem) { refcount_inc(&umem->users); @@ -237,10 +76,8 @@ void xdp_put_umem(struct xdp_umem *umem) if (!umem) return; - if (refcount_dec_and_test(&umem->users)) { - INIT_WORK(&umem->work, xdp_umem_release_deferred); - schedule_work(&umem->work); - } + if (refcount_dec_and_test(&umem->users)) + xdp_umem_release(umem); } static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address) @@ -319,8 +156,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) return -EINVAL; } - if (mr->flags & ~(XDP_UMEM_UNALIGNED_CHUNK_FLAG | - XDP_UMEM_USES_NEED_WAKEUP)) + if (mr->flags & ~XDP_UMEM_UNALIGNED_CHUNK_FLAG) return -EINVAL; if (!unaligned_chunks && !is_power_of_2(chunk_size)) @@ -355,13 +191,13 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) umem->size = size; umem->headroom = headroom; umem->chunk_size = chunk_size; + umem->chunks = chunks; umem->npgs = (u32)npgs; umem->pgs = NULL; umem->user = NULL; umem->flags = mr->flags; - INIT_LIST_HEAD(&umem->xsk_tx_list); - spin_lock_init(&umem->xsk_tx_list_lock); + INIT_LIST_HEAD(&umem->xsk_dma_list); refcount_set(&umem->users, 1); err = xdp_umem_account_pages(umem); @@ -372,15 +208,13 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if (err) goto out_account; - umem->pool = xp_create(umem->pgs, umem->npgs, chunks, chunk_size, - headroom, size, unaligned_chunks); - if (!umem->pool) { - err = -ENOMEM; - goto out_pin; - } + err = xdp_umem_addr_map(umem, umem->pgs, umem->npgs); + if (err) + goto out_unpin; + return 0; -out_pin: +out_unpin: xdp_umem_unpin_pages(umem); out_account: xdp_umem_unaccount_pages(umem); @@ -412,8 +246,3 @@ struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr) return umem; } - -bool xdp_umem_validate_queues(struct xdp_umem *umem) -{ - return umem->fq && umem->cq; -} diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h index 32067fe98f65..181fdda2f2a8 100644 --- a/net/xdp/xdp_umem.h +++ b/net/xdp/xdp_umem.h @@ -8,14 +8,8 @@ #include <net/xdp_sock_drv.h> -int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, - u16 queue_id, u16 flags); -void xdp_umem_clear_dev(struct xdp_umem *umem); -bool xdp_umem_validate_queues(struct xdp_umem *umem); void xdp_get_umem(struct xdp_umem *umem); void xdp_put_umem(struct xdp_umem *umem); -void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs); -void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs); struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr); #endif /* XDP_UMEM_H_ */ diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 6c5e09e7440a..b71a32eeae65 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -33,71 +33,105 @@ static DEFINE_PER_CPU(struct list_head, xskmap_flush_list); -bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) +void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool) { - return READ_ONCE(xs->rx) && READ_ONCE(xs->umem) && - READ_ONCE(xs->umem->fq); -} - -void xsk_set_rx_need_wakeup(struct xdp_umem *umem) -{ - if (umem->need_wakeup & XDP_WAKEUP_RX) + if (pool->cached_need_wakeup & XDP_WAKEUP_RX) return; - umem->fq->ring->flags |= XDP_RING_NEED_WAKEUP; - umem->need_wakeup |= XDP_WAKEUP_RX; + pool->fq->ring->flags |= XDP_RING_NEED_WAKEUP; + pool->cached_need_wakeup |= XDP_WAKEUP_RX; } EXPORT_SYMBOL(xsk_set_rx_need_wakeup); -void xsk_set_tx_need_wakeup(struct xdp_umem *umem) +void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool) { struct xdp_sock *xs; - if (umem->need_wakeup & XDP_WAKEUP_TX) + if (pool->cached_need_wakeup & XDP_WAKEUP_TX) return; rcu_read_lock(); - list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) { + list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { xs->tx->ring->flags |= XDP_RING_NEED_WAKEUP; } rcu_read_unlock(); - umem->need_wakeup |= XDP_WAKEUP_TX; + pool->cached_need_wakeup |= XDP_WAKEUP_TX; } EXPORT_SYMBOL(xsk_set_tx_need_wakeup); -void xsk_clear_rx_need_wakeup(struct xdp_umem *umem) +void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool) { - if (!(umem->need_wakeup & XDP_WAKEUP_RX)) + if (!(pool->cached_need_wakeup & XDP_WAKEUP_RX)) return; - umem->fq->ring->flags &= ~XDP_RING_NEED_WAKEUP; - umem->need_wakeup &= ~XDP_WAKEUP_RX; + pool->fq->ring->flags &= ~XDP_RING_NEED_WAKEUP; + pool->cached_need_wakeup &= ~XDP_WAKEUP_RX; } EXPORT_SYMBOL(xsk_clear_rx_need_wakeup); -void xsk_clear_tx_need_wakeup(struct xdp_umem *umem) +void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool) { struct xdp_sock *xs; - if (!(umem->need_wakeup & XDP_WAKEUP_TX)) + if (!(pool->cached_need_wakeup & XDP_WAKEUP_TX)) return; rcu_read_lock(); - list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) { + list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { xs->tx->ring->flags &= ~XDP_RING_NEED_WAKEUP; } rcu_read_unlock(); - umem->need_wakeup &= ~XDP_WAKEUP_TX; + pool->cached_need_wakeup &= ~XDP_WAKEUP_TX; } EXPORT_SYMBOL(xsk_clear_tx_need_wakeup); -bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem) +bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool) +{ + return pool->uses_need_wakeup; +} +EXPORT_SYMBOL(xsk_uses_need_wakeup); + +struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev, + u16 queue_id) +{ + if (queue_id < dev->real_num_rx_queues) + return dev->_rx[queue_id].pool; + if (queue_id < dev->real_num_tx_queues) + return dev->_tx[queue_id].pool; + + return NULL; +} +EXPORT_SYMBOL(xsk_get_pool_from_qid); + +void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id) +{ + if (queue_id < dev->real_num_rx_queues) + dev->_rx[queue_id].pool = NULL; + if (queue_id < dev->real_num_tx_queues) + dev->_tx[queue_id].pool = NULL; +} + +/* The buffer pool is stored both in the _rx struct and the _tx struct as we do + * not know if the device has more tx queues than rx, or the opposite. + * This might also change during run time. + */ +int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool, + u16 queue_id) { - return umem->flags & XDP_UMEM_USES_NEED_WAKEUP; + if (queue_id >= max_t(unsigned int, + dev->real_num_rx_queues, + dev->real_num_tx_queues)) + return -EINVAL; + + if (queue_id < dev->real_num_rx_queues) + dev->_rx[queue_id].pool = pool; + if (queue_id < dev->real_num_tx_queues) + dev->_tx[queue_id].pool = pool; + + return 0; } -EXPORT_SYMBOL(xsk_umem_uses_need_wakeup); void xp_release(struct xdp_buff_xsk *xskb) { @@ -155,12 +189,12 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len, struct xdp_buff *xsk_xdp; int err; - if (len > xsk_umem_get_rx_frame_size(xs->umem)) { + if (len > xsk_pool_get_rx_frame_size(xs->pool)) { xs->rx_dropped++; return -ENOSPC; } - xsk_xdp = xsk_buff_alloc(xs->umem); + xsk_xdp = xsk_buff_alloc(xs->pool); if (!xsk_xdp) { xs->rx_dropped++; return -ENOSPC; @@ -208,7 +242,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, static void xsk_flush(struct xdp_sock *xs) { xskq_prod_submit(xs->rx); - __xskq_cons_release(xs->umem->fq); + __xskq_cons_release(xs->pool->fq); sock_def_readable(&xs->sk); } @@ -249,32 +283,32 @@ void __xsk_map_flush(void) } } -void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries) +void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries) { - xskq_prod_submit_n(umem->cq, nb_entries); + xskq_prod_submit_n(pool->cq, nb_entries); } -EXPORT_SYMBOL(xsk_umem_complete_tx); +EXPORT_SYMBOL(xsk_tx_completed); -void xsk_umem_consume_tx_done(struct xdp_umem *umem) +void xsk_tx_release(struct xsk_buff_pool *pool) { struct xdp_sock *xs; rcu_read_lock(); - list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) { + list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { __xskq_cons_release(xs->tx); xs->sk.sk_write_space(&xs->sk); } rcu_read_unlock(); } -EXPORT_SYMBOL(xsk_umem_consume_tx_done); +EXPORT_SYMBOL(xsk_tx_release); -bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc) +bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { struct xdp_sock *xs; rcu_read_lock(); - list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) { - if (!xskq_cons_peek_desc(xs->tx, desc, umem)) { + list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { + if (!xskq_cons_peek_desc(xs->tx, desc, pool)) { xs->tx->queue_empty_descs++; continue; } @@ -284,7 +318,7 @@ bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc) * if there is space in it. This avoids having to implement * any buffering in the Tx path. */ - if (xskq_prod_reserve_addr(umem->cq, desc->addr)) + if (xskq_prod_reserve_addr(pool->cq, desc->addr)) goto out; xskq_cons_release(xs->tx); @@ -296,7 +330,7 @@ out: rcu_read_unlock(); return false; } -EXPORT_SYMBOL(xsk_umem_consume_tx); +EXPORT_SYMBOL(xsk_tx_peek_desc); static int xsk_wakeup(struct xdp_sock *xs, u8 flags) { @@ -322,7 +356,7 @@ static void xsk_destruct_skb(struct sk_buff *skb) unsigned long flags; spin_lock_irqsave(&xs->tx_completion_lock, flags); - xskq_prod_submit_addr(xs->umem->cq, addr); + xskq_prod_submit_addr(xs->pool->cq, addr); spin_unlock_irqrestore(&xs->tx_completion_lock, flags); sock_wfree(skb); @@ -342,7 +376,7 @@ static int xsk_generic_xmit(struct sock *sk) if (xs->queue_id >= xs->dev->real_num_tx_queues) goto out; - while (xskq_cons_peek_desc(xs->tx, &desc, xs->umem)) { + while (xskq_cons_peek_desc(xs->tx, &desc, xs->pool)) { char *buffer; u64 addr; u32 len; @@ -359,14 +393,14 @@ static int xsk_generic_xmit(struct sock *sk) skb_put(skb, len); addr = desc.addr; - buffer = xsk_buff_raw_get_data(xs->umem, addr); + buffer = xsk_buff_raw_get_data(xs->pool, addr); err = skb_store_bits(skb, 0, buffer, len); /* This is the backpressure mechanism for the Tx path. * Reserve space in the completion queue and only proceed * if there is space in it. This avoids having to implement * any buffering in the Tx path. */ - if (unlikely(err) || xskq_prod_reserve(xs->umem->cq)) { + if (unlikely(err) || xskq_prod_reserve(xs->pool->cq)) { kfree_skb(skb); goto out; } @@ -446,16 +480,16 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, __poll_t mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); - struct xdp_umem *umem; + struct xsk_buff_pool *pool; if (unlikely(!xsk_is_bound(xs))) return mask; - umem = xs->umem; + pool = xs->pool; - if (umem->need_wakeup) { + if (pool->cached_need_wakeup) { if (xs->zc) - xsk_wakeup(xs, umem->need_wakeup); + xsk_wakeup(xs, pool->cached_need_wakeup); else /* Poll needs to drive Tx also in copy mode */ __xsk_sendmsg(sk); @@ -496,7 +530,7 @@ static void xsk_unbind_dev(struct xdp_sock *xs) WRITE_ONCE(xs->state, XSK_UNBOUND); /* Wait for driver to stop using the xdp socket. */ - xdp_del_sk_umem(xs->umem, xs); + xp_del_xsk(xs->pool, xs); xs->dev = NULL; synchronize_net(); dev_put(dev); @@ -574,6 +608,8 @@ static int xsk_release(struct socket *sock) xskq_destroy(xs->rx); xskq_destroy(xs->tx); + xskq_destroy(xs->fq_tmp); + xskq_destroy(xs->cq_tmp); sock_orphan(sk); sock->sk = NULL; @@ -601,6 +637,11 @@ static struct socket *xsk_lookup_xsk_from_fd(int fd) return sock; } +static bool xsk_validate_queues(struct xdp_sock *xs) +{ + return xs->fq_tmp && xs->cq_tmp; +} + static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { struct sockaddr_xdp *sxdp = (struct sockaddr_xdp *)addr; @@ -669,29 +710,66 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) sockfd_put(sock); goto out_unlock; } - if (umem_xs->dev != dev || umem_xs->queue_id != qid) { - err = -EINVAL; - sockfd_put(sock); - goto out_unlock; + + if (umem_xs->queue_id != qid || umem_xs->dev != dev) { + /* Share the umem with another socket on another qid + * and/or device. + */ + xs->pool = xp_create_and_assign_umem(xs, + umem_xs->umem); + if (!xs->pool) { + err = -ENOMEM; + sockfd_put(sock); + goto out_unlock; + } + + err = xp_assign_dev_shared(xs->pool, umem_xs->umem, + dev, qid); + if (err) { + xp_destroy(xs->pool); + xs->pool = NULL; + sockfd_put(sock); + goto out_unlock; + } + } else { + /* Share the buffer pool with the other socket. */ + if (xs->fq_tmp || xs->cq_tmp) { + /* Do not allow setting your own fq or cq. */ + err = -EINVAL; + sockfd_put(sock); + goto out_unlock; + } + + xp_get_pool(umem_xs->pool); + xs->pool = umem_xs->pool; } xdp_get_umem(umem_xs->umem); WRITE_ONCE(xs->umem, umem_xs->umem); sockfd_put(sock); - } else if (!xs->umem || !xdp_umem_validate_queues(xs->umem)) { + } else if (!xs->umem || !xsk_validate_queues(xs)) { err = -EINVAL; goto out_unlock; } else { /* This xsk has its own umem. */ - err = xdp_umem_assign_dev(xs->umem, dev, qid, flags); - if (err) + xs->pool = xp_create_and_assign_umem(xs, xs->umem); + if (!xs->pool) { + err = -ENOMEM; goto out_unlock; + } + + err = xp_assign_dev(xs->pool, dev, qid, flags); + if (err) { + xp_destroy(xs->pool); + xs->pool = NULL; + goto out_unlock; + } } xs->dev = dev; xs->zc = xs->umem->zc; xs->queue_id = qid; - xdp_add_sk_umem(xs->umem, xs); + xp_add_xsk(xs->pool, xs); out_unlock: if (err) { @@ -797,16 +875,10 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname, mutex_unlock(&xs->mutex); return -EBUSY; } - if (!xs->umem) { - mutex_unlock(&xs->mutex); - return -EINVAL; - } - q = (optname == XDP_UMEM_FILL_RING) ? &xs->umem->fq : - &xs->umem->cq; + q = (optname == XDP_UMEM_FILL_RING) ? &xs->fq_tmp : + &xs->cq_tmp; err = xsk_init_queue(entries, q, true); - if (optname == XDP_UMEM_FILL_RING) - xp_set_fq(xs->umem->pool, *q); mutex_unlock(&xs->mutex); return err; } @@ -873,7 +945,7 @@ static int xsk_getsockopt(struct socket *sock, int level, int optname, if (extra_stats) { stats.rx_ring_full = xs->rx_queue_full; stats.rx_fill_ring_empty_descs = - xs->umem ? xskq_nb_queue_empty_descs(xs->umem->fq) : 0; + xs->pool ? xskq_nb_queue_empty_descs(xs->pool->fq) : 0; stats.tx_ring_empty_descs = xskq_nb_queue_empty_descs(xs->tx); } else { stats.rx_dropped += xs->rx_queue_full; @@ -975,7 +1047,6 @@ static int xsk_mmap(struct file *file, struct socket *sock, unsigned long size = vma->vm_end - vma->vm_start; struct xdp_sock *xs = xdp_sk(sock->sk); struct xsk_queue *q = NULL; - struct xdp_umem *umem; unsigned long pfn; struct page *qpg; @@ -987,16 +1058,12 @@ static int xsk_mmap(struct file *file, struct socket *sock, } else if (offset == XDP_PGOFF_TX_RING) { q = READ_ONCE(xs->tx); } else { - umem = READ_ONCE(xs->umem); - if (!umem) - return -EINVAL; - /* Matches the smp_wmb() in XDP_UMEM_REG */ smp_rmb(); if (offset == XDP_UMEM_PGOFF_FILL_RING) - q = READ_ONCE(umem->fq); + q = READ_ONCE(xs->fq_tmp); else if (offset == XDP_UMEM_PGOFF_COMPLETION_RING) - q = READ_ONCE(umem->cq); + q = READ_ONCE(xs->cq_tmp); } if (!q) @@ -1034,8 +1101,8 @@ static int xsk_notifier(struct notifier_block *this, xsk_unbind_dev(xs); - /* Clear device references in umem. */ - xdp_umem_clear_dev(xs->umem); + /* Clear device references. */ + xp_clear_dev(xs->pool); } mutex_unlock(&xs->mutex); } @@ -1079,7 +1146,7 @@ static void xsk_destruct(struct sock *sk) if (!sock_flag(sk, SOCK_DEAD)) return; - xdp_put_umem(xs->umem); + xp_put_pool(xs->pool); sk_refcnt_debug_dec(sk); } @@ -1087,8 +1154,8 @@ static void xsk_destruct(struct sock *sk) static int xsk_create(struct net *net, struct socket *sock, int protocol, int kern) { - struct sock *sk; struct xdp_sock *xs; + struct sock *sk; if (!ns_capable(net->user_ns, CAP_NET_RAW)) return -EPERM; diff --git a/net/xdp/xsk.h b/net/xdp/xsk.h index 455ddd480f3d..b9e896cee5bb 100644 --- a/net/xdp/xsk.h +++ b/net/xdp/xsk.h @@ -11,13 +11,6 @@ #define XSK_NEXT_PG_CONTIG_SHIFT 0 #define XSK_NEXT_PG_CONTIG_MASK BIT_ULL(XSK_NEXT_PG_CONTIG_SHIFT) -/* Flags for the umem flags field. - * - * The NEED_WAKEUP flag is 1 due to the reuse of the flags field for public - * flags. See inlude/uapi/include/linux/if_xdp.h. - */ -#define XDP_UMEM_USES_NEED_WAKEUP BIT(1) - struct xdp_ring_offset_v1 { __u64 producer; __u64 consumer; @@ -46,10 +39,12 @@ static inline struct xdp_sock *xdp_sk(struct sock *sk) return (struct xdp_sock *)sk; } -bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs); void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, struct xdp_sock **map_entry); int xsk_map_inc(struct xsk_map *map); void xsk_map_put(struct xsk_map *map); +void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id); +int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool, + u16 queue_id); #endif /* XSK_H_ */ diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index a2044c245215..64c9e55d4d4e 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -2,21 +2,34 @@ #include <net/xsk_buff_pool.h> #include <net/xdp_sock.h> +#include <net/xdp_sock_drv.h> #include "xsk_queue.h" +#include "xdp_umem.h" +#include "xsk.h" -static void xp_addr_unmap(struct xsk_buff_pool *pool) +void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs) { - vunmap(pool->addrs); + unsigned long flags; + + if (!xs->tx) + return; + + spin_lock_irqsave(&pool->xsk_tx_list_lock, flags); + list_add_rcu(&xs->tx_list, &pool->xsk_tx_list); + spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags); } -static int xp_addr_map(struct xsk_buff_pool *pool, - struct page **pages, u32 nr_pages) +void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs) { - pool->addrs = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL); - if (!pool->addrs) - return -ENOMEM; - return 0; + unsigned long flags; + + if (!xs->tx) + return; + + spin_lock_irqsave(&pool->xsk_tx_list_lock, flags); + list_del_rcu(&xs->tx_list); + spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags); } void xp_destroy(struct xsk_buff_pool *pool) @@ -24,59 +37,61 @@ void xp_destroy(struct xsk_buff_pool *pool) if (!pool) return; - xp_addr_unmap(pool); kvfree(pool->heads); kvfree(pool); } -struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks, - u32 chunk_size, u32 headroom, u64 size, - bool unaligned) +struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, + struct xdp_umem *umem) { struct xsk_buff_pool *pool; struct xdp_buff_xsk *xskb; - int err; u32 i; - pool = kvzalloc(struct_size(pool, free_heads, chunks), GFP_KERNEL); + pool = kvzalloc(struct_size(pool, free_heads, umem->chunks), + GFP_KERNEL); if (!pool) goto out; - pool->heads = kvcalloc(chunks, sizeof(*pool->heads), GFP_KERNEL); + pool->heads = kvcalloc(umem->chunks, sizeof(*pool->heads), GFP_KERNEL); if (!pool->heads) goto out; - pool->chunk_mask = ~((u64)chunk_size - 1); - pool->addrs_cnt = size; - pool->heads_cnt = chunks; - pool->free_heads_cnt = chunks; - pool->headroom = headroom; - pool->chunk_size = chunk_size; - pool->unaligned = unaligned; - pool->frame_len = chunk_size - headroom - XDP_PACKET_HEADROOM; + pool->chunk_mask = ~((u64)umem->chunk_size - 1); + pool->addrs_cnt = umem->size; + pool->heads_cnt = umem->chunks; + pool->free_heads_cnt = umem->chunks; + pool->headroom = umem->headroom; + pool->chunk_size = umem->chunk_size; + pool->unaligned = umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG; + pool->frame_len = umem->chunk_size - umem->headroom - + XDP_PACKET_HEADROOM; + pool->umem = umem; + pool->addrs = umem->addrs; INIT_LIST_HEAD(&pool->free_list); + INIT_LIST_HEAD(&pool->xsk_tx_list); + spin_lock_init(&pool->xsk_tx_list_lock); + refcount_set(&pool->users, 1); + + pool->fq = xs->fq_tmp; + pool->cq = xs->cq_tmp; + xs->fq_tmp = NULL; + xs->cq_tmp = NULL; for (i = 0; i < pool->free_heads_cnt; i++) { xskb = &pool->heads[i]; xskb->pool = pool; - xskb->xdp.frame_sz = chunk_size - headroom; + xskb->xdp.frame_sz = umem->chunk_size - umem->headroom; pool->free_heads[i] = xskb; } - err = xp_addr_map(pool, pages, nr_pages); - if (!err) - return pool; + return pool; out: xp_destroy(pool); return NULL; } -void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq) -{ - pool->fq = fq; -} - void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) { u32 i; @@ -86,70 +101,320 @@ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) } EXPORT_SYMBOL(xp_set_rxq_info); -void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) +static void xp_disable_drv_zc(struct xsk_buff_pool *pool) { - dma_addr_t *dma; - u32 i; + struct netdev_bpf bpf; + int err; - if (pool->dma_pages_cnt == 0) + ASSERT_RTNL(); + + if (pool->umem->zc) { + bpf.command = XDP_SETUP_XSK_POOL; + bpf.xsk.pool = NULL; + bpf.xsk.queue_id = pool->queue_id; + + err = pool->netdev->netdev_ops->ndo_bpf(pool->netdev, &bpf); + + if (err) + WARN(1, "Failed to disable zero-copy!\n"); + } +} + +static int __xp_assign_dev(struct xsk_buff_pool *pool, + struct net_device *netdev, u16 queue_id, u16 flags) +{ + bool force_zc, force_copy; + struct netdev_bpf bpf; + int err = 0; + + ASSERT_RTNL(); + + force_zc = flags & XDP_ZEROCOPY; + force_copy = flags & XDP_COPY; + + if (force_zc && force_copy) + return -EINVAL; + + if (xsk_get_pool_from_qid(netdev, queue_id)) + return -EBUSY; + + pool->netdev = netdev; + pool->queue_id = queue_id; + err = xsk_reg_pool_at_qid(netdev, pool, queue_id); + if (err) + return err; + + if (flags & XDP_USE_NEED_WAKEUP) { + pool->uses_need_wakeup = true; + /* Tx needs to be explicitly woken up the first time. + * Also for supporting drivers that do not implement this + * feature. They will always have to call sendto(). + */ + pool->cached_need_wakeup = XDP_WAKEUP_TX; + } + + dev_hold(netdev); + + if (force_copy) + /* For copy-mode, we are done. */ + return 0; + + if (!netdev->netdev_ops->ndo_bpf || + !netdev->netdev_ops->ndo_xsk_wakeup) { + err = -EOPNOTSUPP; + goto err_unreg_pool; + } + + bpf.command = XDP_SETUP_XSK_POOL; + bpf.xsk.pool = pool; + bpf.xsk.queue_id = queue_id; + + err = netdev->netdev_ops->ndo_bpf(netdev, &bpf); + if (err) + goto err_unreg_pool; + + if (!pool->dma_pages) { + WARN(1, "Driver did not DMA map zero-copy buffers"); + goto err_unreg_xsk; + } + pool->umem->zc = true; + return 0; + +err_unreg_xsk: + xp_disable_drv_zc(pool); +err_unreg_pool: + if (!force_zc) + err = 0; /* fallback to copy mode */ + if (err) + xsk_clear_pool_at_qid(netdev, queue_id); + return err; +} + +int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, + u16 queue_id, u16 flags) +{ + return __xp_assign_dev(pool, dev, queue_id, flags); +} + +int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem, + struct net_device *dev, u16 queue_id) +{ + u16 flags; + + /* One fill and completion ring required for each queue id. */ + if (!pool->fq || !pool->cq) + return -EINVAL; + + flags = umem->zc ? XDP_ZEROCOPY : XDP_COPY; + if (pool->uses_need_wakeup) + flags |= XDP_USE_NEED_WAKEUP; + + return __xp_assign_dev(pool, dev, queue_id, flags); +} + +void xp_clear_dev(struct xsk_buff_pool *pool) +{ + if (!pool->netdev) return; - for (i = 0; i < pool->dma_pages_cnt; i++) { - dma = &pool->dma_pages[i]; + xp_disable_drv_zc(pool); + xsk_clear_pool_at_qid(pool->netdev, pool->queue_id); + dev_put(pool->netdev); + pool->netdev = NULL; +} + +static void xp_release_deferred(struct work_struct *work) +{ + struct xsk_buff_pool *pool = container_of(work, struct xsk_buff_pool, + work); + + rtnl_lock(); + xp_clear_dev(pool); + rtnl_unlock(); + + if (pool->fq) { + xskq_destroy(pool->fq); + pool->fq = NULL; + } + + if (pool->cq) { + xskq_destroy(pool->cq); + pool->cq = NULL; + } + + xdp_put_umem(pool->umem); + xp_destroy(pool); +} + +void xp_get_pool(struct xsk_buff_pool *pool) +{ + refcount_inc(&pool->users); +} + +void xp_put_pool(struct xsk_buff_pool *pool) +{ + if (!pool) + return; + + if (refcount_dec_and_test(&pool->users)) { + INIT_WORK(&pool->work, xp_release_deferred); + schedule_work(&pool->work); + } +} + +static struct xsk_dma_map *xp_find_dma_map(struct xsk_buff_pool *pool) +{ + struct xsk_dma_map *dma_map; + + list_for_each_entry(dma_map, &pool->umem->xsk_dma_list, list) { + if (dma_map->netdev == pool->netdev) + return dma_map; + } + + return NULL; +} + +static struct xsk_dma_map *xp_create_dma_map(struct device *dev, struct net_device *netdev, + u32 nr_pages, struct xdp_umem *umem) +{ + struct xsk_dma_map *dma_map; + + dma_map = kzalloc(sizeof(*dma_map), GFP_KERNEL); + if (!dma_map) + return NULL; + + dma_map->dma_pages = kvcalloc(nr_pages, sizeof(*dma_map->dma_pages), GFP_KERNEL); + if (!dma_map->dma_pages) { + kfree(dma_map); + return NULL; + } + + dma_map->netdev = netdev; + dma_map->dev = dev; + dma_map->dma_need_sync = false; + dma_map->dma_pages_cnt = nr_pages; + refcount_set(&dma_map->users, 1); + list_add(&dma_map->list, &umem->xsk_dma_list); + return dma_map; +} + +static void xp_destroy_dma_map(struct xsk_dma_map *dma_map) +{ + list_del(&dma_map->list); + kvfree(dma_map->dma_pages); + kfree(dma_map); +} + +static void __xp_dma_unmap(struct xsk_dma_map *dma_map, unsigned long attrs) +{ + dma_addr_t *dma; + u32 i; + + for (i = 0; i < dma_map->dma_pages_cnt; i++) { + dma = &dma_map->dma_pages[i]; if (*dma) { - dma_unmap_page_attrs(pool->dev, *dma, PAGE_SIZE, + dma_unmap_page_attrs(dma_map->dev, *dma, PAGE_SIZE, DMA_BIDIRECTIONAL, attrs); *dma = 0; } } + xp_destroy_dma_map(dma_map); +} + +void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) +{ + struct xsk_dma_map *dma_map; + + if (pool->dma_pages_cnt == 0) + return; + + dma_map = xp_find_dma_map(pool); + if (!dma_map) { + WARN(1, "Could not find dma_map for device"); + return; + } + + if (!refcount_dec_and_test(&dma_map->users)) + return; + + __xp_dma_unmap(dma_map, attrs); kvfree(pool->dma_pages); pool->dma_pages_cnt = 0; pool->dev = NULL; } EXPORT_SYMBOL(xp_dma_unmap); -static void xp_check_dma_contiguity(struct xsk_buff_pool *pool) +static void xp_check_dma_contiguity(struct xsk_dma_map *dma_map) { u32 i; - for (i = 0; i < pool->dma_pages_cnt - 1; i++) { - if (pool->dma_pages[i] + PAGE_SIZE == pool->dma_pages[i + 1]) - pool->dma_pages[i] |= XSK_NEXT_PG_CONTIG_MASK; + for (i = 0; i < dma_map->dma_pages_cnt - 1; i++) { + if (dma_map->dma_pages[i] + PAGE_SIZE == dma_map->dma_pages[i + 1]) + dma_map->dma_pages[i] |= XSK_NEXT_PG_CONTIG_MASK; else - pool->dma_pages[i] &= ~XSK_NEXT_PG_CONTIG_MASK; + dma_map->dma_pages[i] &= ~XSK_NEXT_PG_CONTIG_MASK; } } +static int xp_init_dma_info(struct xsk_buff_pool *pool, struct xsk_dma_map *dma_map) +{ + pool->dma_pages = kvcalloc(dma_map->dma_pages_cnt, sizeof(*pool->dma_pages), GFP_KERNEL); + if (!pool->dma_pages) + return -ENOMEM; + + pool->dev = dma_map->dev; + pool->dma_pages_cnt = dma_map->dma_pages_cnt; + pool->dma_need_sync = dma_map->dma_need_sync; + memcpy(pool->dma_pages, dma_map->dma_pages, + pool->dma_pages_cnt * sizeof(*pool->dma_pages)); + + return 0; +} + int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, unsigned long attrs, struct page **pages, u32 nr_pages) { + struct xsk_dma_map *dma_map; dma_addr_t dma; + int err; u32 i; - pool->dma_pages = kvcalloc(nr_pages, sizeof(*pool->dma_pages), - GFP_KERNEL); - if (!pool->dma_pages) - return -ENOMEM; + dma_map = xp_find_dma_map(pool); + if (dma_map) { + err = xp_init_dma_info(pool, dma_map); + if (err) + return err; + + refcount_inc(&dma_map->users); + return 0; + } - pool->dev = dev; - pool->dma_pages_cnt = nr_pages; - pool->dma_need_sync = false; + dma_map = xp_create_dma_map(dev, pool->netdev, nr_pages, pool->umem); + if (!dma_map) + return -ENOMEM; - for (i = 0; i < pool->dma_pages_cnt; i++) { + for (i = 0; i < dma_map->dma_pages_cnt; i++) { dma = dma_map_page_attrs(dev, pages[i], 0, PAGE_SIZE, DMA_BIDIRECTIONAL, attrs); if (dma_mapping_error(dev, dma)) { - xp_dma_unmap(pool, attrs); + __xp_dma_unmap(dma_map, attrs); return -ENOMEM; } if (dma_need_sync(dev, dma)) - pool->dma_need_sync = true; - pool->dma_pages[i] = dma; + dma_map->dma_need_sync = true; + dma_map->dma_pages[i] = dma; } if (pool->unaligned) - xp_check_dma_contiguity(pool); + xp_check_dma_contiguity(dma_map); + + err = xp_init_dma_info(pool, dma_map); + if (err) { + __xp_dma_unmap(dma_map, attrs); + return err; + } + return 0; } EXPORT_SYMBOL(xp_dma_map); diff --git a/net/xdp/xsk_diag.c b/net/xdp/xsk_diag.c index 21e9c2d123ee..c014217f5fa7 100644 --- a/net/xdp/xsk_diag.c +++ b/net/xdp/xsk_diag.c @@ -46,6 +46,7 @@ static int xsk_diag_put_rings_cfg(const struct xdp_sock *xs, static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb) { + struct xsk_buff_pool *pool = xs->pool; struct xdp_umem *umem = xs->umem; struct xdp_diag_umem du = {}; int err; @@ -58,21 +59,20 @@ static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb) du.num_pages = umem->npgs; du.chunk_size = umem->chunk_size; du.headroom = umem->headroom; - du.ifindex = umem->dev ? umem->dev->ifindex : 0; - du.queue_id = umem->queue_id; + du.ifindex = (pool && pool->netdev) ? pool->netdev->ifindex : 0; + du.queue_id = pool ? pool->queue_id : 0; du.flags = 0; if (umem->zc) du.flags |= XDP_DU_F_ZEROCOPY; du.refs = refcount_read(&umem->users); err = nla_put(nlskb, XDP_DIAG_UMEM, sizeof(du), &du); - - if (!err && umem->fq) - err = xsk_diag_put_ring(umem->fq, XDP_DIAG_UMEM_FILL_RING, nlskb); - if (!err && umem->cq) { - err = xsk_diag_put_ring(umem->cq, XDP_DIAG_UMEM_COMPLETION_RING, - nlskb); - } + if (!err && pool && pool->fq) + err = xsk_diag_put_ring(pool->fq, + XDP_DIAG_UMEM_FILL_RING, nlskb); + if (!err && pool && pool->cq) + err = xsk_diag_put_ring(pool->cq, + XDP_DIAG_UMEM_COMPLETION_RING, nlskb); return err; } @@ -83,7 +83,7 @@ static int xsk_diag_put_stats(const struct xdp_sock *xs, struct sk_buff *nlskb) du.n_rx_dropped = xs->rx_dropped; du.n_rx_invalid = xskq_nb_invalid_descs(xs->rx); du.n_rx_full = xs->rx_queue_full; - du.n_fill_ring_empty = xs->umem ? xskq_nb_queue_empty_descs(xs->umem->fq) : 0; + du.n_fill_ring_empty = xs->pool ? xskq_nb_queue_empty_descs(xs->pool->fq) : 0; du.n_tx_invalid = xskq_nb_invalid_descs(xs->tx); du.n_tx_ring_empty = xskq_nb_queue_empty_descs(xs->tx); return nla_put(nlskb, XDP_DIAG_STATS, sizeof(du), &du); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index bf42cfd74b89..cdb9cf3cd136 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -15,6 +15,10 @@ struct xdp_ring { u32 producer ____cacheline_aligned_in_smp; + /* Hinder the adjacent cache prefetcher to prefetch the consumer + * pointer if the producer pointer is touched and vice versa. + */ + u32 pad ____cacheline_aligned_in_smp; u32 consumer ____cacheline_aligned_in_smp; u32 flags; }; @@ -96,7 +100,7 @@ struct xsk_queue { * seen and read by the consumer. * * The consumer peeks into the ring to see if the producer has written - * any new entries. If so, the producer can then read these entries + * any new entries. If so, the consumer can then read these entries * and when it is done reading them release them back to the producer * so that the producer can use these slots to fill in new entries. * @@ -166,9 +170,9 @@ static inline bool xp_validate_desc(struct xsk_buff_pool *pool, static inline bool xskq_cons_is_valid_desc(struct xsk_queue *q, struct xdp_desc *d, - struct xdp_umem *umem) + struct xsk_buff_pool *pool) { - if (!xp_validate_desc(umem->pool, d)) { + if (!xp_validate_desc(pool, d)) { q->invalid_descs++; return false; } @@ -177,14 +181,14 @@ static inline bool xskq_cons_is_valid_desc(struct xsk_queue *q, static inline bool xskq_cons_read_desc(struct xsk_queue *q, struct xdp_desc *desc, - struct xdp_umem *umem) + struct xsk_buff_pool *pool) { while (q->cached_cons != q->cached_prod) { struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; u32 idx = q->cached_cons & q->ring_mask; *desc = ring->desc[idx]; - if (xskq_cons_is_valid_desc(q, desc, umem)) + if (xskq_cons_is_valid_desc(q, desc, pool)) return true; q->cached_cons++; @@ -236,11 +240,11 @@ static inline bool xskq_cons_peek_addr_unchecked(struct xsk_queue *q, u64 *addr) static inline bool xskq_cons_peek_desc(struct xsk_queue *q, struct xdp_desc *desc, - struct xdp_umem *umem) + struct xsk_buff_pool *pool) { if (q->cached_prod == q->cached_cons) xskq_cons_get_entries(q); - return xskq_cons_read_desc(q, desc, umem); + return xskq_cons_read_desc(q, desc, pool); } static inline void xskq_cons_release(struct xsk_queue *q) diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c index 8367adbbe9df..49da2b8ace8b 100644 --- a/net/xdp/xskmap.c +++ b/net/xdp/xskmap.c @@ -132,7 +132,7 @@ static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key) return 0; } -static u32 xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) +static int xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { const int ret = BPF_REG_0, mp = BPF_REG_1, index = BPF_REG_2; struct bpf_insn *insn = insn_buf; @@ -185,11 +185,6 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, xs = (struct xdp_sock *)sock->sk; - if (!xsk_is_setup_for_bpf_map(xs)) { - sockfd_put(sock); - return -EOPNOTSUPP; - } - map_entry = &m->xsk_map[i]; node = xsk_map_node_alloc(m, map_entry); if (IS_ERR(node)) { @@ -254,8 +249,16 @@ void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, spin_unlock_bh(&map->lock); } +static bool xsk_map_meta_equal(const struct bpf_map *meta0, + const struct bpf_map *meta1) +{ + return meta0->max_entries == meta1->max_entries && + bpf_map_meta_equal(meta0, meta1); +} + static int xsk_map_btf_id; const struct bpf_map_ops xsk_map_ops = { + .map_meta_equal = xsk_map_meta_equal, .map_alloc = xsk_map_alloc, .map_free = xsk_map_free, .map_get_next_key = xsk_map_get_next_key, diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig index 5b9a5ab48111..3adf31a83a79 100644 --- a/net/xfrm/Kconfig +++ b/net/xfrm/Kconfig @@ -28,6 +28,17 @@ config XFRM_USER If unsure, say Y. +config XFRM_USER_COMPAT + tristate "Compatible ABI support" + depends on XFRM_USER && COMPAT_FOR_U64_ALIGNMENT && \ + HAVE_EFFICIENT_UNALIGNED_ACCESS + select WANT_COMPAT_NETLINK_MESSAGES + help + Transformation(XFRM) user configuration interface like IPsec + used by compatible Linux applications. + + If unsure, say N. + config XFRM_INTERFACE tristate "Transformation virtual interface" depends on XFRM && IPV6 diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile index 2d4bb4b9f75e..494aa744bfb9 100644 --- a/net/xfrm/Makefile +++ b/net/xfrm/Makefile @@ -9,6 +9,7 @@ obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_hash.o \ obj-$(CONFIG_XFRM_STATISTICS) += xfrm_proc.o obj-$(CONFIG_XFRM_ALGO) += xfrm_algo.o obj-$(CONFIG_XFRM_USER) += xfrm_user.o +obj-$(CONFIG_XFRM_USER_COMPAT) += xfrm_compat.o obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o obj-$(CONFIG_XFRM_INTERFACE) += xfrm_interface.o obj-$(CONFIG_XFRM_ESPINTCP) += espintcp.o diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c new file mode 100644 index 000000000000..e28f0c9ecd6a --- /dev/null +++ b/net/xfrm/xfrm_compat.c @@ -0,0 +1,625 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * XFRM compat layer + * Author: Dmitry Safonov <dima@arista.com> + * Based on code and translator idea by: Florian Westphal <fw@strlen.de> + */ +#include <linux/compat.h> +#include <linux/xfrm.h> +#include <net/xfrm.h> + +struct compat_xfrm_lifetime_cfg { + compat_u64 soft_byte_limit, hard_byte_limit; + compat_u64 soft_packet_limit, hard_packet_limit; + compat_u64 soft_add_expires_seconds, hard_add_expires_seconds; + compat_u64 soft_use_expires_seconds, hard_use_expires_seconds; +}; /* same size on 32bit, but only 4 byte alignment required */ + +struct compat_xfrm_lifetime_cur { + compat_u64 bytes, packets, add_time, use_time; +}; /* same size on 32bit, but only 4 byte alignment required */ + +struct compat_xfrm_userpolicy_info { + struct xfrm_selector sel; + struct compat_xfrm_lifetime_cfg lft; + struct compat_xfrm_lifetime_cur curlft; + __u32 priority, index; + u8 dir, action, flags, share; + /* 4 bytes additional padding on 64bit */ +}; + +struct compat_xfrm_usersa_info { + struct xfrm_selector sel; + struct xfrm_id id; + xfrm_address_t saddr; + struct compat_xfrm_lifetime_cfg lft; + struct compat_xfrm_lifetime_cur curlft; + struct xfrm_stats stats; + __u32 seq, reqid; + u16 family; + u8 mode, replay_window, flags; + /* 4 bytes additional padding on 64bit */ +}; + +struct compat_xfrm_user_acquire { + struct xfrm_id id; + xfrm_address_t saddr; + struct xfrm_selector sel; + struct compat_xfrm_userpolicy_info policy; + /* 4 bytes additional padding on 64bit */ + __u32 aalgos, ealgos, calgos, seq; +}; + +struct compat_xfrm_userspi_info { + struct compat_xfrm_usersa_info info; + /* 4 bytes additional padding on 64bit */ + __u32 min, max; +}; + +struct compat_xfrm_user_expire { + struct compat_xfrm_usersa_info state; + /* 8 bytes additional padding on 64bit */ + u8 hard; +}; + +struct compat_xfrm_user_polexpire { + struct compat_xfrm_userpolicy_info pol; + /* 8 bytes additional padding on 64bit */ + u8 hard; +}; + +#define XMSGSIZE(type) sizeof(struct type) + +static const int compat_msg_min[XFRM_NR_MSGTYPES] = { + [XFRM_MSG_NEWSA - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_usersa_info), + [XFRM_MSG_DELSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id), + [XFRM_MSG_GETSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id), + [XFRM_MSG_NEWPOLICY - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userpolicy_info), + [XFRM_MSG_DELPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id), + [XFRM_MSG_GETPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id), + [XFRM_MSG_ALLOCSPI - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userspi_info), + [XFRM_MSG_ACQUIRE - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_acquire), + [XFRM_MSG_EXPIRE - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_expire), + [XFRM_MSG_UPDPOLICY - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userpolicy_info), + [XFRM_MSG_UPDSA - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_usersa_info), + [XFRM_MSG_POLEXPIRE - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_polexpire), + [XFRM_MSG_FLUSHSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_flush), + [XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = 0, + [XFRM_MSG_NEWAE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id), + [XFRM_MSG_GETAE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id), + [XFRM_MSG_REPORT - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_report), + [XFRM_MSG_MIGRATE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id), + [XFRM_MSG_NEWSADINFO - XFRM_MSG_BASE] = sizeof(u32), + [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_MAPPING - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_mapping) +}; + +static const struct nla_policy compat_policy[XFRMA_MAX+1] = { + [XFRMA_SA] = { .len = XMSGSIZE(compat_xfrm_usersa_info)}, + [XFRMA_POLICY] = { .len = XMSGSIZE(compat_xfrm_userpolicy_info)}, + [XFRMA_LASTUSED] = { .type = NLA_U64}, + [XFRMA_ALG_AUTH_TRUNC] = { .len = sizeof(struct xfrm_algo_auth)}, + [XFRMA_ALG_AEAD] = { .len = sizeof(struct xfrm_algo_aead) }, + [XFRMA_ALG_AUTH] = { .len = sizeof(struct xfrm_algo) }, + [XFRMA_ALG_CRYPT] = { .len = sizeof(struct xfrm_algo) }, + [XFRMA_ALG_COMP] = { .len = sizeof(struct xfrm_algo) }, + [XFRMA_ENCAP] = { .len = sizeof(struct xfrm_encap_tmpl) }, + [XFRMA_TMPL] = { .len = sizeof(struct xfrm_user_tmpl) }, + [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_sec_ctx) }, + [XFRMA_LTIME_VAL] = { .len = sizeof(struct xfrm_lifetime_cur) }, + [XFRMA_REPLAY_VAL] = { .len = sizeof(struct xfrm_replay_state) }, + [XFRMA_REPLAY_THRESH] = { .type = NLA_U32 }, + [XFRMA_ETIMER_THRESH] = { .type = NLA_U32 }, + [XFRMA_SRCADDR] = { .len = sizeof(xfrm_address_t) }, + [XFRMA_COADDR] = { .len = sizeof(xfrm_address_t) }, + [XFRMA_POLICY_TYPE] = { .len = sizeof(struct xfrm_userpolicy_type)}, + [XFRMA_MIGRATE] = { .len = sizeof(struct xfrm_user_migrate) }, + [XFRMA_KMADDRESS] = { .len = sizeof(struct xfrm_user_kmaddress) }, + [XFRMA_MARK] = { .len = sizeof(struct xfrm_mark) }, + [XFRMA_TFCPAD] = { .type = NLA_U32 }, + [XFRMA_REPLAY_ESN_VAL] = { .len = sizeof(struct xfrm_replay_state_esn) }, + [XFRMA_SA_EXTRA_FLAGS] = { .type = NLA_U32 }, + [XFRMA_PROTO] = { .type = NLA_U8 }, + [XFRMA_ADDRESS_FILTER] = { .len = sizeof(struct xfrm_address_filter) }, + [XFRMA_OFFLOAD_DEV] = { .len = sizeof(struct xfrm_user_offload) }, + [XFRMA_SET_MARK] = { .type = NLA_U32 }, + [XFRMA_SET_MARK_MASK] = { .type = NLA_U32 }, + [XFRMA_IF_ID] = { .type = NLA_U32 }, +}; + +static struct nlmsghdr *xfrm_nlmsg_put_compat(struct sk_buff *skb, + const struct nlmsghdr *nlh_src, u16 type) +{ + int payload = compat_msg_min[type]; + int src_len = xfrm_msg_min[type]; + struct nlmsghdr *nlh_dst; + + /* Compat messages are shorter or equal to native (+padding) */ + if (WARN_ON_ONCE(src_len < payload)) + return ERR_PTR(-EMSGSIZE); + + nlh_dst = nlmsg_put(skb, nlh_src->nlmsg_pid, nlh_src->nlmsg_seq, + nlh_src->nlmsg_type, payload, nlh_src->nlmsg_flags); + if (!nlh_dst) + return ERR_PTR(-EMSGSIZE); + + memset(nlmsg_data(nlh_dst), 0, payload); + + switch (nlh_src->nlmsg_type) { + /* Compat message has the same layout as native */ + case XFRM_MSG_DELSA: + case XFRM_MSG_DELPOLICY: + case XFRM_MSG_FLUSHSA: + case XFRM_MSG_FLUSHPOLICY: + case XFRM_MSG_NEWAE: + case XFRM_MSG_REPORT: + case XFRM_MSG_MIGRATE: + case XFRM_MSG_NEWSADINFO: + case XFRM_MSG_NEWSPDINFO: + case XFRM_MSG_MAPPING: + WARN_ON_ONCE(src_len != payload); + memcpy(nlmsg_data(nlh_dst), nlmsg_data(nlh_src), src_len); + break; + /* 4 byte alignment for trailing u64 on native, but not on compat */ + case XFRM_MSG_NEWSA: + case XFRM_MSG_NEWPOLICY: + case XFRM_MSG_UPDSA: + case XFRM_MSG_UPDPOLICY: + WARN_ON_ONCE(src_len != payload + 4); + memcpy(nlmsg_data(nlh_dst), nlmsg_data(nlh_src), payload); + break; + case XFRM_MSG_EXPIRE: { + const struct xfrm_user_expire *src_ue = nlmsg_data(nlh_src); + struct compat_xfrm_user_expire *dst_ue = nlmsg_data(nlh_dst); + + /* compat_xfrm_user_expire has 4-byte smaller state */ + memcpy(dst_ue, src_ue, sizeof(dst_ue->state)); + dst_ue->hard = src_ue->hard; + break; + } + case XFRM_MSG_ACQUIRE: { + const struct xfrm_user_acquire *src_ua = nlmsg_data(nlh_src); + struct compat_xfrm_user_acquire *dst_ua = nlmsg_data(nlh_dst); + + memcpy(dst_ua, src_ua, offsetof(struct compat_xfrm_user_acquire, aalgos)); + dst_ua->aalgos = src_ua->aalgos; + dst_ua->ealgos = src_ua->ealgos; + dst_ua->calgos = src_ua->calgos; + dst_ua->seq = src_ua->seq; + break; + } + case XFRM_MSG_POLEXPIRE: { + const struct xfrm_user_polexpire *src_upe = nlmsg_data(nlh_src); + struct compat_xfrm_user_polexpire *dst_upe = nlmsg_data(nlh_dst); + + /* compat_xfrm_user_polexpire has 4-byte smaller state */ + memcpy(dst_upe, src_upe, sizeof(dst_upe->pol)); + dst_upe->hard = src_upe->hard; + break; + } + case XFRM_MSG_ALLOCSPI: { + const struct xfrm_userspi_info *src_usi = nlmsg_data(nlh_src); + struct compat_xfrm_userspi_info *dst_usi = nlmsg_data(nlh_dst); + + /* compat_xfrm_user_polexpire has 4-byte smaller state */ + memcpy(dst_usi, src_usi, sizeof(src_usi->info)); + dst_usi->min = src_usi->min; + dst_usi->max = src_usi->max; + break; + } + /* Not being sent by kernel */ + case XFRM_MSG_GETSA: + case XFRM_MSG_GETPOLICY: + case XFRM_MSG_GETAE: + case XFRM_MSG_GETSADINFO: + case XFRM_MSG_GETSPDINFO: + default: + WARN_ONCE(1, "unsupported nlmsg_type %d", nlh_src->nlmsg_type); + return ERR_PTR(-EOPNOTSUPP); + } + + return nlh_dst; +} + +static int xfrm_nla_cpy(struct sk_buff *dst, const struct nlattr *src, int len) +{ + return nla_put(dst, src->nla_type, len, nla_data(src)); +} + +static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src) +{ + switch (src->nla_type) { + case XFRMA_PAD: + /* Ignore */ + return 0; + case XFRMA_ALG_AUTH: + case XFRMA_ALG_CRYPT: + case XFRMA_ALG_COMP: + case XFRMA_ENCAP: + case XFRMA_TMPL: + return xfrm_nla_cpy(dst, src, nla_len(src)); + case XFRMA_SA: + return xfrm_nla_cpy(dst, src, XMSGSIZE(compat_xfrm_usersa_info)); + case XFRMA_POLICY: + return xfrm_nla_cpy(dst, src, XMSGSIZE(compat_xfrm_userpolicy_info)); + case XFRMA_SEC_CTX: + return xfrm_nla_cpy(dst, src, nla_len(src)); + case XFRMA_LTIME_VAL: + return nla_put_64bit(dst, src->nla_type, nla_len(src), + nla_data(src), XFRMA_PAD); + case XFRMA_REPLAY_VAL: + case XFRMA_REPLAY_THRESH: + case XFRMA_ETIMER_THRESH: + case XFRMA_SRCADDR: + case XFRMA_COADDR: + return xfrm_nla_cpy(dst, src, nla_len(src)); + case XFRMA_LASTUSED: + return nla_put_64bit(dst, src->nla_type, nla_len(src), + nla_data(src), XFRMA_PAD); + case XFRMA_POLICY_TYPE: + case XFRMA_MIGRATE: + case XFRMA_ALG_AEAD: + case XFRMA_KMADDRESS: + case XFRMA_ALG_AUTH_TRUNC: + case XFRMA_MARK: + case XFRMA_TFCPAD: + case XFRMA_REPLAY_ESN_VAL: + case XFRMA_SA_EXTRA_FLAGS: + case XFRMA_PROTO: + case XFRMA_ADDRESS_FILTER: + case XFRMA_OFFLOAD_DEV: + case XFRMA_SET_MARK: + case XFRMA_SET_MARK_MASK: + case XFRMA_IF_ID: + return xfrm_nla_cpy(dst, src, nla_len(src)); + default: + BUILD_BUG_ON(XFRMA_MAX != XFRMA_IF_ID); + WARN_ONCE(1, "unsupported nla_type %d", src->nla_type); + return -EOPNOTSUPP; + } +} + +/* Take kernel-built (64bit layout) and create 32bit layout for userspace */ +static int xfrm_xlate64(struct sk_buff *dst, const struct nlmsghdr *nlh_src) +{ + u16 type = nlh_src->nlmsg_type - XFRM_MSG_BASE; + const struct nlattr *nla, *attrs; + struct nlmsghdr *nlh_dst; + int len, remaining; + + nlh_dst = xfrm_nlmsg_put_compat(dst, nlh_src, type); + if (IS_ERR(nlh_dst)) + return PTR_ERR(nlh_dst); + + attrs = nlmsg_attrdata(nlh_src, xfrm_msg_min[type]); + len = nlmsg_attrlen(nlh_src, xfrm_msg_min[type]); + + nla_for_each_attr(nla, attrs, len, remaining) { + int err = xfrm_xlate64_attr(dst, nla); + + if (err) + return err; + } + + nlmsg_end(dst, nlh_dst); + + return 0; +} + +static int xfrm_alloc_compat(struct sk_buff *skb, const struct nlmsghdr *nlh_src) +{ + u16 type = nlh_src->nlmsg_type - XFRM_MSG_BASE; + struct sk_buff *new = NULL; + int err; + + if (WARN_ON_ONCE(type >= ARRAY_SIZE(xfrm_msg_min))) + return -EOPNOTSUPP; + + if (skb_shinfo(skb)->frag_list == NULL) { + new = alloc_skb(skb->len + skb_tailroom(skb), GFP_ATOMIC); + if (!new) + return -ENOMEM; + skb_shinfo(skb)->frag_list = new; + } + + err = xfrm_xlate64(skb_shinfo(skb)->frag_list, nlh_src); + if (err) { + if (new) { + kfree_skb(new); + skb_shinfo(skb)->frag_list = NULL; + } + return err; + } + + return 0; +} + +/* 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]) +{ + size_t len = nlmsg_len(src); + + switch (src->nlmsg_type) { + case XFRM_MSG_NEWSA: + case XFRM_MSG_NEWPOLICY: + case XFRM_MSG_ALLOCSPI: + case XFRM_MSG_ACQUIRE: + case XFRM_MSG_UPDPOLICY: + case XFRM_MSG_UPDSA: + len += 4; + break; + case XFRM_MSG_EXPIRE: + case XFRM_MSG_POLEXPIRE: + len += 8; + break; + default: + break; + } + + if (attrs[XFRMA_SA]) + len += 4; + if (attrs[XFRMA_POLICY]) + len += 4; + + /* XXX: some attrs may need to be realigned + * if !CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + */ + + return len; +} + +static int xfrm_attr_cpy32(void *dst, size_t *pos, const struct nlattr *src, + size_t size, int copy_len, int payload) +{ + struct nlmsghdr *nlmsg = dst; + struct nlattr *nla; + + if (WARN_ON_ONCE(copy_len > payload)) + copy_len = payload; + + if (size - *pos < nla_attr_size(payload)) + return -ENOBUFS; + + nla = dst + *pos; + + memcpy(nla, src, nla_attr_size(copy_len)); + nla->nla_len = nla_attr_size(payload); + *pos += nla_attr_size(payload); + nlmsg->nlmsg_len += nla->nla_len; + + memset(dst + *pos, 0, payload - copy_len); + *pos += payload - copy_len; + + return 0; +} + +static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla, + size_t *pos, size_t size, + struct netlink_ext_ack *extack) +{ + int type = nla_type(nla); + u16 pol_len32, pol_len64; + int err; + + if (type > XFRMA_MAX) { + BUILD_BUG_ON(XFRMA_MAX != XFRMA_IF_ID); + NL_SET_ERR_MSG(extack, "Bad attribute"); + return -EOPNOTSUPP; + } + if (nla_len(nla) < compat_policy[type].len) { + NL_SET_ERR_MSG(extack, "Attribute bad length"); + return -EOPNOTSUPP; + } + + pol_len32 = compat_policy[type].len; + pol_len64 = xfrma_policy[type].len; + + /* XFRMA_SA and XFRMA_POLICY - need to know how-to translate */ + if (pol_len32 != pol_len64) { + if (nla_len(nla) != compat_policy[type].len) { + NL_SET_ERR_MSG(extack, "Attribute bad length"); + return -EOPNOTSUPP; + } + err = xfrm_attr_cpy32(dst, pos, nla, size, pol_len32, pol_len64); + if (err) + return err; + } + + return xfrm_attr_cpy32(dst, pos, nla, size, nla_len(nla), nla_len(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 pos; + int i; + + memcpy(dst, src, NLMSG_HDRLEN); + dst->nlmsg_len = NLMSG_HDRLEN + xfrm_msg_min[type]; + memset(nlmsg_data(dst), 0, xfrm_msg_min[type]); + + switch (src->nlmsg_type) { + /* Compat message has the same layout as native */ + case XFRM_MSG_DELSA: + case XFRM_MSG_GETSA: + case XFRM_MSG_DELPOLICY: + case XFRM_MSG_GETPOLICY: + case XFRM_MSG_FLUSHSA: + case XFRM_MSG_FLUSHPOLICY: + case XFRM_MSG_NEWAE: + case XFRM_MSG_GETAE: + case XFRM_MSG_REPORT: + case XFRM_MSG_MIGRATE: + case XFRM_MSG_NEWSADINFO: + case XFRM_MSG_GETSADINFO: + case XFRM_MSG_NEWSPDINFO: + case XFRM_MSG_GETSPDINFO: + case XFRM_MSG_MAPPING: + memcpy(nlmsg_data(dst), nlmsg_data(src), compat_msg_min[type]); + break; + /* 4 byte alignment for trailing u64 on native, but not on compat */ + case XFRM_MSG_NEWSA: + case XFRM_MSG_NEWPOLICY: + case XFRM_MSG_UPDSA: + case XFRM_MSG_UPDPOLICY: + memcpy(nlmsg_data(dst), nlmsg_data(src), compat_msg_min[type]); + break; + case XFRM_MSG_EXPIRE: { + const struct compat_xfrm_user_expire *src_ue = nlmsg_data(src); + struct xfrm_user_expire *dst_ue = nlmsg_data(dst); + + /* compat_xfrm_user_expire has 4-byte smaller state */ + memcpy(dst_ue, src_ue, sizeof(src_ue->state)); + dst_ue->hard = src_ue->hard; + break; + } + case XFRM_MSG_ACQUIRE: { + const struct compat_xfrm_user_acquire *src_ua = nlmsg_data(src); + struct xfrm_user_acquire *dst_ua = nlmsg_data(dst); + + memcpy(dst_ua, src_ua, offsetof(struct compat_xfrm_user_acquire, aalgos)); + dst_ua->aalgos = src_ua->aalgos; + dst_ua->ealgos = src_ua->ealgos; + dst_ua->calgos = src_ua->calgos; + dst_ua->seq = src_ua->seq; + break; + } + case XFRM_MSG_POLEXPIRE: { + const struct compat_xfrm_user_polexpire *src_upe = nlmsg_data(src); + struct xfrm_user_polexpire *dst_upe = nlmsg_data(dst); + + /* compat_xfrm_user_polexpire has 4-byte smaller state */ + memcpy(dst_upe, src_upe, sizeof(src_upe->pol)); + dst_upe->hard = src_upe->hard; + break; + } + case XFRM_MSG_ALLOCSPI: { + const struct compat_xfrm_userspi_info *src_usi = nlmsg_data(src); + struct xfrm_userspi_info *dst_usi = nlmsg_data(dst); + + /* compat_xfrm_user_polexpire has 4-byte smaller state */ + memcpy(dst_usi, src_usi, sizeof(src_usi->info)); + dst_usi->min = src_usi->min; + dst_usi->max = src_usi->max; + break; + } + default: + NL_SET_ERR_MSG(extack, "Unsupported message type"); + return -EOPNOTSUPP; + } + pos = dst->nlmsg_len; + + for (i = 1; i < XFRMA_MAX + 1; i++) { + int err; + + if (i == XFRMA_PAD) + continue; + + if (!attrs[i]) + continue; + + err = xfrm_xlate32_attr(dst, attrs[i], &pos, size, extack); + if (err) + return err; + } + + return 0; +} + +static struct nlmsghdr *xfrm_user_rcv_msg_compat(const struct nlmsghdr *h32, + int maxtype, const struct nla_policy *policy, + struct netlink_ext_ack *extack) +{ + /* netlink_rcv_skb() checks if a message has full (struct nlmsghdr) */ + u16 type = h32->nlmsg_type - XFRM_MSG_BASE; + struct nlattr *attrs[XFRMA_MAX+1]; + struct nlmsghdr *h64; + size_t len; + int err; + + BUILD_BUG_ON(ARRAY_SIZE(xfrm_msg_min) != ARRAY_SIZE(compat_msg_min)); + + if (type >= ARRAY_SIZE(xfrm_msg_min)) + return ERR_PTR(-EINVAL); + + /* Don't call parse: the message might have only nlmsg header */ + if ((h32->nlmsg_type == XFRM_MSG_GETSA || + h32->nlmsg_type == XFRM_MSG_GETPOLICY) && + (h32->nlmsg_flags & NLM_F_DUMP)) + return NULL; + + err = nlmsg_parse_deprecated(h32, compat_msg_min[type], attrs, + maxtype ? : XFRMA_MAX, policy ? : compat_policy, extack); + if (err < 0) + return ERR_PTR(err); + + len = xfrm_user_rcv_calculate_len64(h32, attrs); + /* The message doesn't need translation */ + if (len == nlmsg_len(h32)) + return NULL; + + len += NLMSG_HDRLEN; + h64 = kvmalloc(len, GFP_KERNEL | __GFP_ZERO); + if (!h64) + return ERR_PTR(-ENOMEM); + + err = xfrm_xlate32(h64, h32, attrs, len, type, extack); + if (err < 0) { + kvfree(h64); + return ERR_PTR(err); + } + + return h64; +} + +static int xfrm_user_policy_compat(u8 **pdata32, int optlen) +{ + struct compat_xfrm_userpolicy_info *p = (void *)*pdata32; + u8 *src_templates, *dst_templates; + u8 *data64; + + if (optlen < sizeof(*p)) + return -EINVAL; + + data64 = kmalloc_track_caller(optlen + 4, GFP_USER | __GFP_NOWARN); + if (!data64) + return -ENOMEM; + + memcpy(data64, *pdata32, sizeof(*p)); + memset(data64 + sizeof(*p), 0, 4); + + src_templates = *pdata32 + sizeof(*p); + dst_templates = data64 + sizeof(*p) + 4; + memcpy(dst_templates, src_templates, optlen - sizeof(*p)); + + kfree(*pdata32); + *pdata32 = data64; + return 0; +} + +static struct xfrm_translator xfrm_translator = { + .owner = THIS_MODULE, + .alloc_compat = xfrm_alloc_compat, + .rcv_msg_compat = xfrm_user_rcv_msg_compat, + .xlate_user_policy_sockptr = xfrm_user_policy_compat, +}; + +static int __init xfrm_compat_init(void) +{ + return xfrm_register_translator(&xfrm_translator); +} + +static void __exit xfrm_compat_exit(void) +{ + xfrm_unregister_translator(&xfrm_translator); +} + +module_init(xfrm_compat_init); +module_exit(xfrm_compat_exit); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Dmitry Safonov"); +MODULE_DESCRIPTION("XFRM 32-bit compatibility layer"); diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index 0bb7963b9f6b..9b8e292a7c6a 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -210,7 +210,6 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) static int xfrmi_rcv_cb(struct sk_buff *skb, int err) { const struct xfrm_mode *inner_mode; - struct pcpu_sw_netstats *tstats; struct net_device *dev; struct xfrm_state *x; struct xfrm_if *xi; @@ -255,13 +254,7 @@ static int xfrmi_rcv_cb(struct sk_buff *skb, int err) } xfrmi_scrub_packet(skb, xnet); - - tstats = this_cpu_ptr(dev->tstats); - - u64_stats_update_begin(&tstats->syncp); - tstats->rx_packets++; - tstats->rx_bytes += skb->len; - u64_stats_update_end(&tstats->syncp); + dev_sw_netstats_rx_add(dev, skb->len); return 0; } @@ -548,27 +541,7 @@ static int xfrmi_update(struct xfrm_if *xi, struct xfrm_if_parms *p) static void xfrmi_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *s) { - int cpu; - - for_each_possible_cpu(cpu) { - struct pcpu_sw_netstats *stats; - struct pcpu_sw_netstats tmp; - int start; - - stats = per_cpu_ptr(dev->tstats, cpu); - do { - start = u64_stats_fetch_begin_irq(&stats->syncp); - tmp.rx_packets = stats->rx_packets; - tmp.rx_bytes = stats->rx_bytes; - tmp.tx_packets = stats->tx_packets; - tmp.tx_bytes = stats->tx_bytes; - } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); - - s->rx_packets += tmp.rx_packets; - s->rx_bytes += tmp.rx_bytes; - s->tx_packets += tmp.tx_packets; - s->tx_bytes += tmp.tx_bytes; - } + dev_fetch_sw_netstats(s, dev->tstats); s->rx_dropped = dev->stats.rx_dropped; s->tx_dropped = dev->stats.tx_dropped; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index ee6ac32bb06d..a77da7aae6fe 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2298,6 +2298,66 @@ static bool km_is_alive(const struct km_event *c) return is_alive; } +#if IS_ENABLED(CONFIG_XFRM_USER_COMPAT) +static DEFINE_SPINLOCK(xfrm_translator_lock); +static struct xfrm_translator __rcu *xfrm_translator; + +struct xfrm_translator *xfrm_get_translator(void) +{ + struct xfrm_translator *xtr; + + rcu_read_lock(); + xtr = rcu_dereference(xfrm_translator); + if (unlikely(!xtr)) + goto out; + if (!try_module_get(xtr->owner)) + xtr = NULL; +out: + rcu_read_unlock(); + return xtr; +} +EXPORT_SYMBOL_GPL(xfrm_get_translator); + +void xfrm_put_translator(struct xfrm_translator *xtr) +{ + module_put(xtr->owner); +} +EXPORT_SYMBOL_GPL(xfrm_put_translator); + +int xfrm_register_translator(struct xfrm_translator *xtr) +{ + int err = 0; + + spin_lock_bh(&xfrm_translator_lock); + if (unlikely(xfrm_translator != NULL)) + err = -EEXIST; + else + rcu_assign_pointer(xfrm_translator, xtr); + spin_unlock_bh(&xfrm_translator_lock); + + return err; +} +EXPORT_SYMBOL_GPL(xfrm_register_translator); + +int xfrm_unregister_translator(struct xfrm_translator *xtr) +{ + int err = 0; + + spin_lock_bh(&xfrm_translator_lock); + if (likely(xfrm_translator != NULL)) { + if (rcu_access_pointer(xfrm_translator) != xtr) + err = -EINVAL; + else + RCU_INIT_POINTER(xfrm_translator, NULL); + } + spin_unlock_bh(&xfrm_translator_lock); + synchronize_rcu(); + + return err; +} +EXPORT_SYMBOL_GPL(xfrm_unregister_translator); +#endif + int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen) { int err; @@ -2305,9 +2365,6 @@ int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen) struct xfrm_mgr *km; struct xfrm_policy *pol = NULL; - if (in_compat_syscall()) - return -EOPNOTSUPP; - if (sockptr_is_null(optval) && !optlen) { xfrm_sk_policy_insert(sk, XFRM_POLICY_IN, NULL); xfrm_sk_policy_insert(sk, XFRM_POLICY_OUT, NULL); @@ -2322,6 +2379,20 @@ int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen) if (IS_ERR(data)) return PTR_ERR(data); + if (in_compat_syscall()) { + struct xfrm_translator *xtr = xfrm_get_translator(); + + if (!xtr) + return -EOPNOTSUPP; + + err = xtr->xlate_user_policy_sockptr(&data, optlen); + xfrm_put_translator(xtr); + if (err) { + kfree(data); + return err; + } + } + err = -EINVAL; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index fbb7d9d06478..d0c32a8fcc4a 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -975,6 +975,7 @@ static int dump_one_state(struct xfrm_state *x, int count, void *ptr) struct xfrm_dump_info *sp = ptr; struct sk_buff *in_skb = sp->in_skb; struct sk_buff *skb = sp->out_skb; + struct xfrm_translator *xtr; struct xfrm_usersa_info *p; struct nlmsghdr *nlh; int err; @@ -992,6 +993,18 @@ static int dump_one_state(struct xfrm_state *x, int count, void *ptr) return err; } nlmsg_end(skb, nlh); + + xtr = xfrm_get_translator(); + if (xtr) { + err = xtr->alloc_compat(skb, nlh); + + xfrm_put_translator(xtr); + if (err) { + nlmsg_cancel(skb, nlh); + return err; + } + } + return 0; } @@ -1006,7 +1019,6 @@ static int xfrm_dump_sa_done(struct netlink_callback *cb) return 0; } -static const struct nla_policy xfrma_policy[XFRMA_MAX+1]; static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); @@ -1083,12 +1095,24 @@ static inline int xfrm_nlmsg_multicast(struct net *net, struct sk_buff *skb, u32 pid, unsigned int group) { struct sock *nlsk = rcu_dereference(net->xfrm.nlsk); + struct xfrm_translator *xtr; if (!nlsk) { kfree_skb(skb); return -EPIPE; } + xtr = xfrm_get_translator(); + if (xtr) { + int err = xtr->alloc_compat(skb, nlmsg_hdr(skb)); + + xfrm_put_translator(xtr); + if (err) { + kfree_skb(skb); + return err; + } + } + return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC); } @@ -1308,6 +1332,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); struct xfrm_state *x; struct xfrm_userspi_info *p; + struct xfrm_translator *xtr; struct sk_buff *resp_skb; xfrm_address_t *daddr; int family; @@ -1358,6 +1383,17 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, goto out; } + xtr = xfrm_get_translator(); + if (xtr) { + err = xtr->alloc_compat(skb, nlmsg_hdr(skb)); + + xfrm_put_translator(xtr); + if (err) { + kfree_skb(resp_skb); + goto out; + } + } + err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, NETLINK_CB(skb).portid); out: @@ -1764,6 +1800,7 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr struct xfrm_userpolicy_info *p; struct sk_buff *in_skb = sp->in_skb; struct sk_buff *skb = sp->out_skb; + struct xfrm_translator *xtr; struct nlmsghdr *nlh; int err; @@ -1788,6 +1825,18 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr return err; } nlmsg_end(skb, nlh); + + xtr = xfrm_get_translator(); + if (xtr) { + err = xtr->alloc_compat(skb, nlh); + + xfrm_put_translator(xtr); + if (err) { + nlmsg_cancel(skb, nlh); + return err; + } + } + return 0; } @@ -2533,7 +2582,7 @@ static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, #define XMSGSIZE(type) sizeof(struct type) -static const int xfrm_msg_min[XFRM_NR_MSGTYPES] = { +const int xfrm_msg_min[XFRM_NR_MSGTYPES] = { [XFRM_MSG_NEWSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_info), [XFRM_MSG_DELSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id), [XFRM_MSG_GETSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id), @@ -2556,10 +2605,11 @@ static const int xfrm_msg_min[XFRM_NR_MSGTYPES] = { [XFRM_MSG_NEWSPDINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_GETSPDINFO - XFRM_MSG_BASE] = sizeof(u32), }; +EXPORT_SYMBOL_GPL(xfrm_msg_min); #undef XMSGSIZE -static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { +const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_SA] = { .len = sizeof(struct xfrm_usersa_info)}, [XFRMA_POLICY] = { .len = sizeof(struct xfrm_userpolicy_info)}, [XFRMA_LASTUSED] = { .type = NLA_U64}, @@ -2591,6 +2641,7 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_SET_MARK_MASK] = { .type = NLA_U32 }, [XFRMA_IF_ID] = { .type = NLA_U32 }, }; +EXPORT_SYMBOL_GPL(xfrma_policy); static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = { [XFRMA_SPD_IPV4_HTHRESH] = { .len = sizeof(struct xfrmu_spdhthresh) }, @@ -2640,11 +2691,9 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); struct nlattr *attrs[XFRMA_MAX+1]; const struct xfrm_link *link; + struct nlmsghdr *nlh64 = NULL; int type, err; - if (in_compat_syscall()) - return -EOPNOTSUPP; - type = nlh->nlmsg_type; if (type > XFRM_MSG_MAX) return -EINVAL; @@ -2656,32 +2705,55 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, if (!netlink_net_capable(skb, CAP_NET_ADMIN)) return -EPERM; + if (in_compat_syscall()) { + struct xfrm_translator *xtr = xfrm_get_translator(); + + if (!xtr) + return -EOPNOTSUPP; + + nlh64 = xtr->rcv_msg_compat(nlh, link->nla_max, + link->nla_pol, extack); + xfrm_put_translator(xtr); + if (IS_ERR(nlh64)) + return PTR_ERR(nlh64); + if (nlh64) + nlh = nlh64; + } + if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) || type == (XFRM_MSG_GETPOLICY - XFRM_MSG_BASE)) && (nlh->nlmsg_flags & NLM_F_DUMP)) { - if (link->dump == NULL) - return -EINVAL; + struct netlink_dump_control c = { + .start = link->start, + .dump = link->dump, + .done = link->done, + }; - { - struct netlink_dump_control c = { - .start = link->start, - .dump = link->dump, - .done = link->done, - }; - return netlink_dump_start(net->xfrm.nlsk, skb, nlh, &c); + if (link->dump == NULL) { + err = -EINVAL; + goto err; } + + err = netlink_dump_start(net->xfrm.nlsk, skb, nlh, &c); + goto err; } err = nlmsg_parse_deprecated(nlh, xfrm_msg_min[type], attrs, link->nla_max ? : XFRMA_MAX, link->nla_pol ? : xfrma_policy, extack); if (err < 0) - return err; + goto err; - if (link->doit == NULL) - return -EINVAL; + if (link->doit == NULL) { + err = -EINVAL; + goto err; + } - return link->doit(skb, nlh, attrs); + err = link->doit(skb, nlh, attrs); + +err: + kvfree(nlh64); + return err; } static void xfrm_netlink_rcv(struct sk_buff *skb) |