diff options
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/dev.c | 305 | ||||
-rw-r--r-- | net/core/devlink.c | 315 | ||||
-rw-r--r-- | net/core/filter.c | 25 | ||||
-rw-r--r-- | net/core/flow_dissector.c | 29 | ||||
-rw-r--r-- | net/core/neighbour.c | 1 | ||||
-rw-r--r-- | net/core/pktgen.c | 2 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 2 | ||||
-rw-r--r-- | net/core/skbuff.c | 82 | ||||
-rw-r--r-- | net/core/sock.c | 200 | ||||
-rw-r--r-- | net/core/sock_map.c | 2 | ||||
-rw-r--r-- | net/core/sysctl_net_core.c | 2 |
11 files changed, 641 insertions, 324 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index a979b86dbacd..aae116d059da 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3617,11 +3617,22 @@ static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb, int skb_csum_hwoffload_help(struct sk_buff *skb, const netdev_features_t features) { - if (unlikely(skb->csum_not_inet)) + if (unlikely(skb_csum_is_sctp(skb))) return !!(features & NETIF_F_SCTP_CRC) ? 0 : skb_crc32c_csum_help(skb); - return !!(features & NETIF_F_CSUM_MASK) ? 0 : skb_checksum_help(skb); + if (features & NETIF_F_HW_CSUM) + return 0; + + if (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) { + switch (skb->csum_offset) { + case offsetof(struct tcphdr, check): + case offsetof(struct udphdr, check): + return 0; + } + } + + return skb_checksum_help(skb); } EXPORT_SYMBOL(skb_csum_hwoffload_help); @@ -3878,6 +3889,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) /* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */ qdisc_skb_cb(skb)->mru = 0; + qdisc_skb_cb(skb)->post_ct = false; mini_qdisc_bstats_cpu_update(miniq, skb); switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) { @@ -4083,7 +4095,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) skb_reset_mac_header(skb); if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP)) - __skb_tstamp_tx(skb, NULL, skb->sk, SCM_TSTAMP_SCHED); + __skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SCHED); /* Disable soft irqs for various locks below. Also * stops preemption for RCU. @@ -4603,14 +4615,14 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { + void *orig_data, *orig_data_end, *hard_start; struct netdev_rx_queue *rxqueue; - void *orig_data, *orig_data_end; u32 metalen, act = XDP_DROP; + u32 mac_len, frame_sz; __be16 orig_eth_type; struct ethhdr *eth; bool orig_bcast; - int hlen, off; - u32 mac_len; + int off; /* Reinjected packets coming from act_mirred or similar should * not get XDP generic processing. @@ -4642,15 +4654,16 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, * header. */ mac_len = skb->data - skb_mac_header(skb); - hlen = skb_headlen(skb) + mac_len; - xdp->data = skb->data - mac_len; - xdp->data_meta = xdp->data; - xdp->data_end = xdp->data + hlen; - xdp->data_hard_start = skb->data - skb_headroom(skb); + hard_start = skb->data - skb_headroom(skb); /* SKB "head" area always have tailroom for skb_shared_info */ - xdp->frame_sz = (void *)skb_end_pointer(skb) - xdp->data_hard_start; - xdp->frame_sz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + frame_sz = (void *)skb_end_pointer(skb) - hard_start; + frame_sz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + + rxqueue = netif_get_rxqueue(skb); + xdp_init_buff(xdp, frame_sz, &rxqueue->xdp_rxq); + xdp_prepare_buff(xdp, hard_start, skb_headroom(skb) - mac_len, + skb_headlen(skb) + mac_len, true); orig_data_end = xdp->data_end; orig_data = xdp->data; @@ -4658,9 +4671,6 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, orig_bcast = is_multicast_ether_addr_64bits(eth->h_dest); orig_eth_type = eth->h_proto; - rxqueue = netif_get_rxqueue(skb); - xdp->rxq = &rxqueue->xdp_rxq; - act = bpf_prog_run_xdp(xdp_prog, xdp); /* check if bpf_xdp_adjust_head was used */ @@ -4962,6 +4972,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, qdisc_skb_cb(skb)->pkt_len = skb->len; qdisc_skb_cb(skb)->mru = 0; + qdisc_skb_cb(skb)->post_ct = false; skb->tc_at_ingress = 1; mini_qdisc_bstats_cpu_update(miniq, skb); @@ -5151,8 +5162,7 @@ another_round: skb_reset_mac_len(skb); } - if (skb->protocol == cpu_to_be16(ETH_P_8021Q) || - skb->protocol == cpu_to_be16(ETH_P_8021AD)) { + if (eth_type_vlan(skb->protocol)) { skb = skb_vlan_untag(skb); if (unlikely(!skb)) goto out; @@ -5236,8 +5246,7 @@ check_vlan_id: * find vlan device. */ skb->pkt_type = PACKET_OTHERHOST; - } else if (skb->protocol == cpu_to_be16(ETH_P_8021Q) || - skb->protocol == cpu_to_be16(ETH_P_8021AD)) { + } else if (eth_type_vlan(skb->protocol)) { /* Outer header is 802.1P with vlan 0, inner header is * 802.1Q or 802.1AD and vlan_do_receive() above could * not find vlan dev for vlan id 0. @@ -5713,7 +5722,7 @@ static void flush_all_backlogs(void) } /* we can have in flight packet[s] on the cpus we are not flushing, - * synchronize_net() in rollback_registered_many() will take care of + * synchronize_net() in unregister_netdevice_many() will take care of * them */ for_each_cpu(cpu, &flush_cpus) @@ -6070,10 +6079,6 @@ static gro_result_t napi_skb_finish(struct napi_struct *napi, gro_normal_one(napi, skb); break; - case GRO_DROP: - kfree_skb(skb); - break; - case GRO_MERGED_FREE: if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) napi_skb_free_stolen_head(skb); @@ -6158,10 +6163,6 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, gro_normal_one(napi, skb); break; - case GRO_DROP: - napi_reuse_skb(napi, skb); - break; - case GRO_MERGED_FREE: if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) napi_skb_free_stolen_head(skb); @@ -6223,9 +6224,6 @@ gro_result_t napi_gro_frags(struct napi_struct *napi) gro_result_t ret; struct sk_buff *skb = napi_frags_skb(napi); - if (!skb) - return GRO_DROP; - trace_napi_gro_frags_entry(skb); ret = napi_frags_finish(napi, skb, dev_gro_receive(napi, skb)); @@ -8120,6 +8118,39 @@ struct net_device *netdev_get_xmit_slave(struct net_device *dev, } EXPORT_SYMBOL(netdev_get_xmit_slave); +static struct net_device *netdev_sk_get_lower_dev(struct net_device *dev, + struct sock *sk) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (!ops->ndo_sk_get_lower_dev) + return NULL; + return ops->ndo_sk_get_lower_dev(dev, sk); +} + +/** + * netdev_sk_get_lowest_dev - Get the lowest device in chain given device and socket + * @dev: device + * @sk: the socket + * + * %NULL is returned if no lower device is found. + */ + +struct net_device *netdev_sk_get_lowest_dev(struct net_device *dev, + struct sock *sk) +{ + struct net_device *lower; + + lower = netdev_sk_get_lower_dev(dev, sk); + while (lower) { + dev = lower; + lower = netdev_sk_get_lower_dev(dev, sk); + } + + return dev; +} +EXPORT_SYMBOL(netdev_sk_get_lowest_dev); + static void netdev_adjacent_add_links(struct net_device *dev) { struct netdev_adjacent *iter; @@ -9441,106 +9472,6 @@ static void net_set_todo(struct net_device *dev) dev_net(dev)->dev_unreg_count++; } -static void rollback_registered_many(struct list_head *head) -{ - struct net_device *dev, *tmp; - LIST_HEAD(close_head); - - BUG_ON(dev_boot_phase); - ASSERT_RTNL(); - - list_for_each_entry_safe(dev, tmp, head, unreg_list) { - /* Some devices call without registering - * for initialization unwind. Remove those - * devices and proceed with the remaining. - */ - if (dev->reg_state == NETREG_UNINITIALIZED) { - pr_debug("unregister_netdevice: device %s/%p never was registered\n", - dev->name, dev); - - WARN_ON(1); - list_del(&dev->unreg_list); - continue; - } - dev->dismantle = true; - BUG_ON(dev->reg_state != NETREG_REGISTERED); - } - - /* If device is running, close it first. */ - list_for_each_entry(dev, head, unreg_list) - list_add_tail(&dev->close_list, &close_head); - dev_close_many(&close_head, true); - - list_for_each_entry(dev, head, unreg_list) { - /* And unlink it from device chain. */ - unlist_netdevice(dev); - - dev->reg_state = NETREG_UNREGISTERING; - } - flush_all_backlogs(); - - synchronize_net(); - - list_for_each_entry(dev, head, unreg_list) { - struct sk_buff *skb = NULL; - - /* Shutdown queueing discipline. */ - dev_shutdown(dev); - - dev_xdp_uninstall(dev); - - /* Notify protocols, that we are about to destroy - * this device. They should clean all the things. - */ - call_netdevice_notifiers(NETDEV_UNREGISTER, dev); - - if (!dev->rtnl_link_ops || - dev->rtnl_link_state == RTNL_LINK_INITIALIZED) - skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, - GFP_KERNEL, NULL, 0); - - /* - * Flush the unicast and multicast chains - */ - dev_uc_flush(dev); - dev_mc_flush(dev); - - netdev_name_node_alt_flush(dev); - netdev_name_node_free(dev->name_node); - - if (dev->netdev_ops->ndo_uninit) - dev->netdev_ops->ndo_uninit(dev); - - if (skb) - rtmsg_ifinfo_send(skb, dev, GFP_KERNEL); - - /* Notifier chain MUST detach us all upper devices. */ - WARN_ON(netdev_has_any_upper_dev(dev)); - WARN_ON(netdev_has_any_lower_dev(dev)); - - /* Remove entries from kobject tree */ - netdev_unregister_kobject(dev); -#ifdef CONFIG_XPS - /* Remove XPS queueing entries */ - netif_reset_xps_queues_gt(dev, 0); -#endif - } - - synchronize_net(); - - list_for_each_entry(dev, head, unreg_list) - dev_put(dev); -} - -static void rollback_registered(struct net_device *dev) -{ - LIST_HEAD(single); - - list_add(&dev->unreg_list, &single); - rollback_registered_many(&single); - list_del(&single); -} - static netdev_features_t netdev_sync_upper_features(struct net_device *lower, struct net_device *upper, netdev_features_t features) { @@ -10013,7 +9944,7 @@ int register_netdevice(struct net_device *dev) dev->hw_features |= (NETIF_F_SOFT_FEATURES | NETIF_F_SOFT_FEATURES_OFF); dev->features |= NETIF_F_SOFT_FEATURES; - if (dev->netdev_ops->ndo_udp_tunnel_add) { + if (dev->udp_tunnel_nic_info) { dev->features |= NETIF_F_RX_UDP_TUNNEL_PORT; dev->hw_features |= NETIF_F_RX_UDP_TUNNEL_PORT; } @@ -10090,8 +10021,7 @@ int register_netdevice(struct net_device *dev) if (ret) { /* Expect explicit free_netdev() on failure */ dev->needs_free_netdev = false; - rollback_registered(dev); - net_set_todo(dev); + unregister_netdevice_queue(dev, NULL); goto out; } /* @@ -10713,9 +10643,10 @@ void unregister_netdevice_queue(struct net_device *dev, struct list_head *head) if (head) { list_move_tail(&dev->unreg_list, head); } else { - rollback_registered(dev); - /* Finish processing unregister after unlock */ - net_set_todo(dev); + LIST_HEAD(single); + + list_add(&dev->unreg_list, &single); + unregister_netdevice_many(&single); } } EXPORT_SYMBOL(unregister_netdevice_queue); @@ -10729,14 +10660,100 @@ EXPORT_SYMBOL(unregister_netdevice_queue); */ void unregister_netdevice_many(struct list_head *head) { - struct net_device *dev; + struct net_device *dev, *tmp; + LIST_HEAD(close_head); - if (!list_empty(head)) { - rollback_registered_many(head); - list_for_each_entry(dev, head, unreg_list) - net_set_todo(dev); - list_del(head); + BUG_ON(dev_boot_phase); + ASSERT_RTNL(); + + if (list_empty(head)) + return; + + list_for_each_entry_safe(dev, tmp, head, unreg_list) { + /* Some devices call without registering + * for initialization unwind. Remove those + * devices and proceed with the remaining. + */ + if (dev->reg_state == NETREG_UNINITIALIZED) { + pr_debug("unregister_netdevice: device %s/%p never was registered\n", + dev->name, dev); + + WARN_ON(1); + list_del(&dev->unreg_list); + continue; + } + dev->dismantle = true; + BUG_ON(dev->reg_state != NETREG_REGISTERED); + } + + /* If device is running, close it first. */ + list_for_each_entry(dev, head, unreg_list) + list_add_tail(&dev->close_list, &close_head); + dev_close_many(&close_head, true); + + list_for_each_entry(dev, head, unreg_list) { + /* And unlink it from device chain. */ + unlist_netdevice(dev); + + dev->reg_state = NETREG_UNREGISTERING; } + flush_all_backlogs(); + + synchronize_net(); + + list_for_each_entry(dev, head, unreg_list) { + struct sk_buff *skb = NULL; + + /* Shutdown queueing discipline. */ + dev_shutdown(dev); + + dev_xdp_uninstall(dev); + + /* Notify protocols, that we are about to destroy + * this device. They should clean all the things. + */ + call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + + if (!dev->rtnl_link_ops || + dev->rtnl_link_state == RTNL_LINK_INITIALIZED) + skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, + GFP_KERNEL, NULL, 0); + + /* + * Flush the unicast and multicast chains + */ + dev_uc_flush(dev); + dev_mc_flush(dev); + + netdev_name_node_alt_flush(dev); + netdev_name_node_free(dev->name_node); + + if (dev->netdev_ops->ndo_uninit) + dev->netdev_ops->ndo_uninit(dev); + + if (skb) + rtmsg_ifinfo_send(skb, dev, GFP_KERNEL); + + /* Notifier chain MUST detach us all upper devices. */ + WARN_ON(netdev_has_any_upper_dev(dev)); + WARN_ON(netdev_has_any_lower_dev(dev)); + + /* Remove entries from kobject tree */ + netdev_unregister_kobject(dev); +#ifdef CONFIG_XPS + /* Remove XPS queueing entries */ + netif_reset_xps_queues_gt(dev, 0); +#endif + } + + synchronize_net(); + + list_for_each_entry(dev, head, unreg_list) { + dev_put(dev); + net_set_todo(dev); + } + + list_del(head); } EXPORT_SYMBOL(unregister_netdevice_many); diff --git a/net/core/devlink.c b/net/core/devlink.c index 738d4344d679..737b61c2976e 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -87,6 +87,9 @@ 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 }, + [DEVLINK_PORT_FN_ATTR_STATE] = + NLA_POLICY_RANGE(NLA_U8, DEVLINK_PORT_FN_STATE_INACTIVE, + DEVLINK_PORT_FN_STATE_ACTIVE), }; static LIST_HEAD(devlink_list); @@ -690,6 +693,15 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg, if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_vf.external)) return -EMSGSIZE; break; + case DEVLINK_PORT_FLAVOUR_PCI_SF: + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, + attrs->pci_sf.controller) || + nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, + attrs->pci_sf.pf) || + nla_put_u32(msg, DEVLINK_ATTR_PORT_PCI_SF_NUMBER, + attrs->pci_sf.sf)) + return -EMSGSIZE; + break; case DEVLINK_PORT_FLAVOUR_PHYSICAL: case DEVLINK_PORT_FLAVOUR_CPU: case DEVLINK_PORT_FLAVOUR_DSA: @@ -713,42 +725,105 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg, } static int +devlink_port_fn_hw_addr_fill(struct devlink *devlink, const struct devlink_ops *ops, + struct devlink_port *port, struct sk_buff *msg, + struct netlink_ext_ack *extack, bool *msg_updated) +{ + u8 hw_addr[MAX_ADDR_LEN]; + int hw_addr_len; + int err; + + if (!ops->port_function_hw_addr_get) + return 0; + + err = ops->port_function_hw_addr_get(devlink, port, hw_addr, &hw_addr_len, extack); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + err = nla_put(msg, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, hw_addr_len, hw_addr); + if (err) + return err; + *msg_updated = true; + return 0; +} + +static bool +devlink_port_fn_state_valid(enum devlink_port_fn_state state) +{ + return state == DEVLINK_PORT_FN_STATE_INACTIVE || + state == DEVLINK_PORT_FN_STATE_ACTIVE; +} + +static bool +devlink_port_fn_opstate_valid(enum devlink_port_fn_opstate opstate) +{ + return opstate == DEVLINK_PORT_FN_OPSTATE_DETACHED || + opstate == DEVLINK_PORT_FN_OPSTATE_ATTACHED; +} + +static int +devlink_port_fn_state_fill(struct devlink *devlink, + const struct devlink_ops *ops, + struct devlink_port *port, struct sk_buff *msg, + struct netlink_ext_ack *extack, + bool *msg_updated) +{ + enum devlink_port_fn_opstate opstate; + enum devlink_port_fn_state state; + int err; + + if (!ops->port_fn_state_get) + return 0; + + err = ops->port_fn_state_get(devlink, port, &state, &opstate, extack); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + if (!devlink_port_fn_state_valid(state)) { + WARN_ON_ONCE(1); + NL_SET_ERR_MSG_MOD(extack, "Invalid state read from driver"); + return -EINVAL; + } + if (!devlink_port_fn_opstate_valid(opstate)) { + WARN_ON_ONCE(1); + NL_SET_ERR_MSG_MOD(extack, + "Invalid operational state read from driver"); + return -EINVAL; + } + if (nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_STATE, state) || + nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_OPSTATE, opstate)) + return -EMSGSIZE; + *msg_updated = true; + return 0; +} + +static int devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port, struct netlink_ext_ack *extack) { struct devlink *devlink = port->devlink; const struct devlink_ops *ops; struct nlattr *function_attr; - bool empty_nest = true; - int err = 0; + bool msg_updated = false; + int err; function_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_PORT_FUNCTION); if (!function_attr) return -EMSGSIZE; ops = devlink->ops; - if (ops->port_function_hw_addr_get) { - int hw_addr_len; - u8 hw_addr[MAX_ADDR_LEN]; - - err = ops->port_function_hw_addr_get(devlink, port, hw_addr, &hw_addr_len, extack); - if (err == -EOPNOTSUPP) { - /* Port function attributes are optional for a port. If port doesn't - * support function attribute, returning -EOPNOTSUPP is not an error. - */ - err = 0; - goto out; - } else if (err) { - goto out; - } - err = nla_put(msg, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, hw_addr_len, hw_addr); - if (err) - goto out; - empty_nest = false; - } - + err = devlink_port_fn_hw_addr_fill(devlink, ops, port, msg, + extack, &msg_updated); + if (err) + goto out; + err = devlink_port_fn_state_fill(devlink, ops, port, msg, extack, + &msg_updated); out: - if (err || empty_nest) + if (err || !msg_updated) nla_nest_cancel(msg, function_attr); else nla_nest_end(msg, function_attr); @@ -986,7 +1061,6 @@ devlink_port_function_hw_addr_set(struct devlink *devlink, struct devlink_port * const struct devlink_ops *ops; const u8 *hw_addr; int hw_addr_len; - int err; hw_addr = nla_data(attr); hw_addr_len = nla_len(attr); @@ -1011,12 +1085,25 @@ devlink_port_function_hw_addr_set(struct devlink *devlink, struct devlink_port * return -EOPNOTSUPP; } - err = ops->port_function_hw_addr_set(devlink, port, hw_addr, hw_addr_len, extack); - if (err) - return err; + return ops->port_function_hw_addr_set(devlink, port, hw_addr, hw_addr_len, extack); +} - devlink_port_notify(port, DEVLINK_CMD_PORT_NEW); - return 0; +static int devlink_port_fn_state_set(struct devlink *devlink, + struct devlink_port *port, + const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + enum devlink_port_fn_state state; + const struct devlink_ops *ops; + + state = nla_get_u8(attr); + ops = devlink->ops; + if (!ops->port_fn_state_set) { + NL_SET_ERR_MSG_MOD(extack, + "Function does not support state setting"); + return -EOPNOTSUPP; + } + return ops->port_fn_state_set(devlink, port, state, extack); } static int @@ -1034,9 +1121,21 @@ devlink_port_function_set(struct devlink *devlink, struct devlink_port *port, } attr = tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR]; - if (attr) + if (attr) { err = devlink_port_function_hw_addr_set(devlink, port, attr, extack); + if (err) + return err; + } + /* Keep this as the last function attribute set, so that when + * multiple port function attributes are set along with state, + * Those can be applied first before activating the state. + */ + attr = tb[DEVLINK_PORT_FN_ATTR_STATE]; + if (attr) + err = devlink_port_fn_state_set(devlink, port, attr, extack); + if (!err) + devlink_port_notify(port, DEVLINK_CMD_PORT_NEW); return err; } @@ -1136,6 +1235,111 @@ static int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb, return devlink_port_unsplit(devlink, port_index, info->extack); } +static int devlink_port_new_notifiy(struct devlink *devlink, + unsigned int port_index, + struct genl_info *info) +{ + struct devlink_port *devlink_port; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + mutex_lock(&devlink->lock); + devlink_port = devlink_port_get_by_index(devlink, port_index); + if (!devlink_port) { + err = -ENODEV; + goto out; + } + + err = devlink_nl_port_fill(msg, devlink, devlink_port, + DEVLINK_CMD_NEW, info->snd_portid, + info->snd_seq, 0, NULL); + if (err) + goto out; + + err = genlmsg_reply(msg, info); + mutex_unlock(&devlink->lock); + return err; + +out: + mutex_unlock(&devlink->lock); + nlmsg_free(msg); + return err; +} + +static int devlink_nl_cmd_port_new_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct devlink_port_new_attrs new_attrs = {}; + struct devlink *devlink = info->user_ptr[0]; + unsigned int new_port_index; + int err; + + if (!devlink->ops->port_new || !devlink->ops->port_del) + return -EOPNOTSUPP; + + if (!info->attrs[DEVLINK_ATTR_PORT_FLAVOUR] || + !info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]) { + NL_SET_ERR_MSG_MOD(extack, "Port flavour or PCI PF are not specified"); + return -EINVAL; + } + new_attrs.flavour = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_FLAVOUR]); + new_attrs.pfnum = + nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]); + + if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { + /* Port index of the new port being created by driver. */ + new_attrs.port_index = + nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + new_attrs.port_index_valid = true; + } + if (info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]) { + new_attrs.controller = + nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]); + new_attrs.controller_valid = true; + } + if (new_attrs.flavour == DEVLINK_PORT_FLAVOUR_PCI_SF && + info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]) { + new_attrs.sfnum = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]); + new_attrs.sfnum_valid = true; + } + + err = devlink->ops->port_new(devlink, &new_attrs, extack, + &new_port_index); + if (err) + return err; + + err = devlink_port_new_notifiy(devlink, new_port_index, info); + if (err && err != -ENODEV) { + /* Fail to send the response; destroy newly created port. */ + devlink->ops->port_del(devlink, new_port_index, extack); + } + return err; +} + +static int devlink_nl_cmd_port_del_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct devlink *devlink = info->user_ptr[0]; + unsigned int port_index; + + if (!devlink->ops->port_del) + return -EOPNOTSUPP; + + if (!info->attrs[DEVLINK_ATTR_PORT_INDEX]) { + NL_SET_ERR_MSG_MOD(extack, "Port index is not specified"); + return -EINVAL; + } + port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + + return devlink->ops->port_del(devlink, port_index, extack); +} + static int devlink_nl_sb_fill(struct sk_buff *msg, struct devlink *devlink, struct devlink_sb *devlink_sb, enum devlink_command cmd, u32 portid, @@ -7594,6 +7798,10 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [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), + [DEVLINK_ATTR_PORT_FLAVOUR] = { .type = NLA_U16 }, + [DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .type = NLA_U16 }, + [DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .type = NLA_U32 }, + [DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .type = NLA_U32 }, }; static const struct genl_small_ops devlink_nl_ops[] = { @@ -7634,6 +7842,18 @@ static const struct genl_small_ops devlink_nl_ops[] = { .internal_flags = DEVLINK_NL_FLAG_NO_LOCK, }, { + .cmd = DEVLINK_CMD_PORT_NEW, + .doit = devlink_nl_cmd_port_new_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NO_LOCK, + }, + { + .cmd = DEVLINK_CMD_PORT_DEL, + .doit = devlink_nl_cmd_port_del_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NO_LOCK, + }, + { .cmd = DEVLINK_CMD_SB_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_sb_get_doit, @@ -8372,6 +8592,32 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 contro } EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_vf_set); +/** + * devlink_port_attrs_pci_sf_set - Set PCI SF port attributes + * + * @devlink_port: devlink port + * @controller: associated controller number for the devlink port instance + * @pf: associated PF for the devlink port instance + * @sf: associated SF of a PF for the devlink port instance + */ +void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 controller, + u16 pf, u32 sf) +{ + struct devlink_port_attrs *attrs = &devlink_port->attrs; + int ret; + + if (WARN_ON(devlink_port->registered)) + return; + ret = __devlink_port_attrs_set(devlink_port, + DEVLINK_PORT_FLAVOUR_PCI_SF); + if (ret) + return; + attrs->pci_sf.controller = controller; + attrs->pci_sf.pf = pf; + attrs->pci_sf.sf = sf; +} +EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_sf_set); + static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, char *name, size_t len) { @@ -8420,6 +8666,10 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, n = snprintf(name, len, "pf%uvf%u", attrs->pci_vf.pf, attrs->pci_vf.vf); break; + case DEVLINK_PORT_FLAVOUR_PCI_SF: + n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf, + attrs->pci_sf.sf); + break; } if (n >= len) @@ -8617,6 +8867,10 @@ EXPORT_SYMBOL_GPL(devlink_dpipe_table_unregister); * @resource_id: resource's id * @parent_resource_id: resource's parent id * @size_params: size parameters + * + * Generic resources should reuse the same names across drivers. + * Please see the generic resources list at: + * Documentation/networking/devlink/devlink-resource.rst */ int devlink_resource_register(struct devlink *devlink, const char *resource_name, @@ -9508,6 +9762,7 @@ static const struct devlink_trap devlink_trap_generic[] = { DEVLINK_TRAP(GTP_PARSING, DROP), DEVLINK_TRAP(ESP_PARSING, DROP), DEVLINK_TRAP(BLACKHOLE_NEXTHOP, DROP), + DEVLINK_TRAP(DMAC_FILTER, DROP), }; #define DEVLINK_TRAP_GROUP(_id) \ diff --git a/net/core/filter.c b/net/core/filter.c index 255aeee72402..9ab94e90d660 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4770,6 +4770,10 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, ifindex = dev->ifindex; dev_put(dev); } + fallthrough; + case SO_BINDTOIFINDEX: + if (optname == SO_BINDTOIFINDEX) + ifindex = val; ret = sock_bindtoindex(sk, ifindex, false); break; case SO_KEEPALIVE: @@ -4932,8 +4936,25 @@ static int _bpf_getsockopt(struct sock *sk, int level, int optname, sock_owned_by_me(sk); + if (level == SOL_SOCKET) { + if (optlen != sizeof(int)) + goto err_clear; + + switch (optname) { + case SO_MARK: + *((int *)optval) = sk->sk_mark; + break; + case SO_PRIORITY: + *((int *)optval) = sk->sk_priority; + break; + case SO_BINDTOIFINDEX: + *((int *)optval) = sk->sk_bound_dev_if; + break; + default: + goto err_clear; + } #ifdef CONFIG_INET - if (level == SOL_TCP && sk->sk_prot->getsockopt == tcp_getsockopt) { + } else if (level == SOL_TCP && sk->sk_prot->getsockopt == tcp_getsockopt) { struct inet_connection_sock *icsk; struct tcp_sock *tp; @@ -4987,11 +5008,11 @@ static int _bpf_getsockopt(struct sock *sk, int level, int optname, goto err_clear; } #endif +#endif } else { goto err_clear; } return 0; -#endif err_clear: memset(optval, 0, optlen); return -EINVAL; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 6f1adba6695f..c565c7a17091 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -23,6 +23,7 @@ #include <linux/if_ether.h> #include <linux/mpls.h> #include <linux/tcp.h> +#include <linux/ptp_classify.h> #include <net/flow_dissector.h> #include <scsi/fc/fc_fcoe.h> #include <uapi/linux/batadv_packet.h> @@ -236,9 +237,8 @@ skb_flow_dissect_set_enc_addr_type(enum flow_dissector_key_id type, void skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, - void *target_container, - u16 *ctinfo_map, - size_t mapsize) + void *target_container, u16 *ctinfo_map, + size_t mapsize, bool post_ct) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) struct flow_dissector_key_ct *key; @@ -250,13 +250,19 @@ skb_flow_dissect_ct(const struct sk_buff *skb, return; ct = nf_ct_get(skb, &ctinfo); - if (!ct) + if (!ct && !post_ct) return; key = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CT, target_container); + if (!ct) { + key->ct_state = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | + TCA_FLOWER_KEY_CT_FLAGS_INVALID; + return; + } + if (ctinfo < mapsize) key->ct_state = ctinfo_map[ctinfo]; #if IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) @@ -1251,6 +1257,21 @@ proto_again: &proto, &nhoff, hlen, flags); break; + case htons(ETH_P_1588): { + struct ptp_header *hdr, _hdr; + + hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, + hlen, &_hdr); + if (!hdr) { + fdret = FLOW_DISSECT_RET_OUT_BAD; + break; + } + + nhoff += ntohs(hdr->message_length); + fdret = FLOW_DISSECT_RET_OUT_GOOD; + break; + } + default: fdret = FLOW_DISSECT_RET_OUT_BAD; break; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 6d2d557442dc..e2982b3970b8 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -41,7 +41,6 @@ #include <trace/events/neigh.h> -#define DEBUG #define NEIGH_DEBUG 1 #define neigh_dbg(level, fmt, ...) \ do { \ diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 105978604ffd..3fba429f1f57 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3464,7 +3464,7 @@ static int pktgen_thread_worker(void *arg) struct pktgen_dev *pkt_dev = NULL; int cpu = t->cpu; - BUG_ON(smp_processor_id() != cpu); + WARN_ON(smp_processor_id() != cpu); init_waitqueue_head(&t->queue); complete(&t->start_done); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 3d6ab194d0f5..c313aaf2bce1 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -55,7 +55,7 @@ #include <net/net_namespace.h> #define RTNL_MAX_TYPE 50 -#define RTNL_SLAVE_MAX_TYPE 36 +#define RTNL_SLAVE_MAX_TYPE 40 struct rtnl_link { rtnl_doit_func doit; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 785daff48030..2af12f7e170c 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -614,13 +614,14 @@ static void skb_release_data(struct sk_buff *skb) &shinfo->dataref)) return; + skb_zcopy_clear(skb, true); + for (i = 0; i < shinfo->nr_frags; i++) __skb_frag_unref(&shinfo->frags[i]); if (shinfo->frag_list) kfree_skb_list(shinfo->frag_list); - skb_zcopy_clear(skb, true); skb_free_head(skb); } @@ -1102,7 +1103,7 @@ void mm_unaccount_pinned_pages(struct mmpin *mmp) } EXPORT_SYMBOL_GPL(mm_unaccount_pinned_pages); -struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size) +struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size) { struct ubuf_info *uarg; struct sk_buff *skb; @@ -1122,25 +1123,26 @@ struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size) return NULL; } - uarg->callback = sock_zerocopy_callback; + uarg->callback = msg_zerocopy_callback; uarg->id = ((u32)atomic_inc_return(&sk->sk_zckey)) - 1; uarg->len = 1; uarg->bytelen = size; uarg->zerocopy = 1; + uarg->flags = SKBFL_ZEROCOPY_FRAG; refcount_set(&uarg->refcnt, 1); sock_hold(sk); return uarg; } -EXPORT_SYMBOL_GPL(sock_zerocopy_alloc); +EXPORT_SYMBOL_GPL(msg_zerocopy_alloc); static inline struct sk_buff *skb_from_uarg(struct ubuf_info *uarg) { return container_of((void *)uarg, struct sk_buff, cb); } -struct ubuf_info *sock_zerocopy_realloc(struct sock *sk, size_t size, - struct ubuf_info *uarg) +struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, + struct ubuf_info *uarg) { if (uarg) { const u32 byte_limit = 1 << 19; /* limit to a few TSO */ @@ -1172,16 +1174,16 @@ struct ubuf_info *sock_zerocopy_realloc(struct sock *sk, size_t size, /* no extra ref when appending to datagram (MSG_MORE) */ if (sk->sk_type == SOCK_STREAM) - sock_zerocopy_get(uarg); + net_zcopy_get(uarg); return uarg; } } new_alloc: - return sock_zerocopy_alloc(sk, size); + return msg_zerocopy_alloc(sk, size); } -EXPORT_SYMBOL_GPL(sock_zerocopy_realloc); +EXPORT_SYMBOL_GPL(msg_zerocopy_realloc); static bool skb_zerocopy_notify_extend(struct sk_buff *skb, u32 lo, u16 len) { @@ -1203,7 +1205,7 @@ static bool skb_zerocopy_notify_extend(struct sk_buff *skb, u32 lo, u16 len) return true; } -void sock_zerocopy_callback(struct ubuf_info *uarg, bool success) +static void __msg_zerocopy_callback(struct ubuf_info *uarg) { struct sk_buff *tail, *skb = skb_from_uarg(uarg); struct sock_exterr_skb *serr; @@ -1231,7 +1233,7 @@ void sock_zerocopy_callback(struct ubuf_info *uarg, bool success) serr->ee.ee_origin = SO_EE_ORIGIN_ZEROCOPY; serr->ee.ee_data = hi; serr->ee.ee_info = lo; - if (!success) + if (!uarg->zerocopy) serr->ee.ee_code |= SO_EE_CODE_ZEROCOPY_COPIED; q = &sk->sk_error_queue; @@ -1250,32 +1252,28 @@ release: consume_skb(skb); sock_put(sk); } -EXPORT_SYMBOL_GPL(sock_zerocopy_callback); -void sock_zerocopy_put(struct ubuf_info *uarg) +void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, + bool success) { - if (uarg && refcount_dec_and_test(&uarg->refcnt)) { - if (uarg->callback) - uarg->callback(uarg, uarg->zerocopy); - else - consume_skb(skb_from_uarg(uarg)); - } + uarg->zerocopy = uarg->zerocopy & success; + + if (refcount_dec_and_test(&uarg->refcnt)) + __msg_zerocopy_callback(uarg); } -EXPORT_SYMBOL_GPL(sock_zerocopy_put); +EXPORT_SYMBOL_GPL(msg_zerocopy_callback); -void sock_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref) +void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref) { - if (uarg) { - struct sock *sk = skb_from_uarg(uarg)->sk; + struct sock *sk = skb_from_uarg(uarg)->sk; - atomic_dec(&sk->sk_zckey); - uarg->len--; + atomic_dec(&sk->sk_zckey); + uarg->len--; - if (have_uref) - sock_zerocopy_put(uarg); - } + if (have_uref) + msg_zerocopy_callback(NULL, uarg, true); } -EXPORT_SYMBOL_GPL(sock_zerocopy_put_abort); +EXPORT_SYMBOL_GPL(msg_zerocopy_put_abort); int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len) { @@ -1339,7 +1337,7 @@ static int skb_zerocopy_clone(struct sk_buff *nskb, struct sk_buff *orig, * @skb: the skb to modify * @gfp_mask: allocation priority * - * This must be called on SKBTX_DEV_ZEROCOPY skb. + * This must be called on skb with SKBFL_ZEROCOPY_ENABLE. * It will copy all frags into kernel and drop the reference * to userspace pages. * @@ -3276,8 +3274,7 @@ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) { int pos = skb_headlen(skb); - skb_shinfo(skb1)->tx_flags |= skb_shinfo(skb)->tx_flags & - SKBTX_SHARED_FRAG; + skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; skb_zerocopy_clone(skb1, skb, 0); if (len < pos) /* Split line is inside header. */ skb_split_inside_header(skb, skb1, len, pos); @@ -3901,12 +3898,8 @@ normal: } hsize = skb_headlen(head_skb) - offset; - if (hsize < 0) - hsize = 0; - if (hsize > len || !sg) - hsize = len; - if (!hsize && i >= nfrags && skb_headlen(list_skb) && + if (hsize <= 0 && i >= nfrags && skb_headlen(list_skb) && (skb_headlen(list_skb) == len || sg)) { BUG_ON(skb_headlen(list_skb) > len); @@ -3949,6 +3942,11 @@ normal: skb_release_head_state(nskb); __skb_push(nskb, doffset); } else { + if (hsize < 0) + hsize = 0; + if (hsize > len || !sg) + hsize = len; + nskb = __alloc_skb(hsize + doffset + headroom, GFP_ATOMIC, skb_alloc_rx_flag(head_skb), NUMA_NO_NODE); @@ -4002,8 +4000,8 @@ normal: skb_copy_from_linear_data_offset(head_skb, offset, skb_put(nskb, hsize), hsize); - skb_shinfo(nskb)->tx_flags |= skb_shinfo(head_skb)->tx_flags & - SKBTX_SHARED_FRAG; + skb_shinfo(nskb)->flags |= skb_shinfo(head_skb)->flags & + SKBFL_SHARED_FRAG; if (skb_orphan_frags(frag_skb, GFP_ATOMIC) || skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC)) @@ -4723,6 +4721,7 @@ err: EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp); void __skb_tstamp_tx(struct sk_buff *orig_skb, + const struct sk_buff *ack_skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype) { @@ -4745,7 +4744,8 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) && sk->sk_protocol == IPPROTO_TCP && sk->sk_type == SOCK_STREAM) { - skb = tcp_get_timestamping_opt_stats(sk, orig_skb); + skb = tcp_get_timestamping_opt_stats(sk, orig_skb, + ack_skb); opt_stats = true; } else #endif @@ -4774,7 +4774,7 @@ EXPORT_SYMBOL_GPL(__skb_tstamp_tx); void skb_tstamp_tx(struct sk_buff *orig_skb, struct skb_shared_hwtstamps *hwtstamps) { - return __skb_tstamp_tx(orig_skb, hwtstamps, orig_skb->sk, + return __skb_tstamp_tx(orig_skb, NULL, hwtstamps, orig_skb->sk, SCM_TSTAMP_SND); } EXPORT_SYMBOL_GPL(skb_tstamp_tx); diff --git a/net/core/sock.c b/net/core/sock.c index bbcd4b97eddd..648a5cb46209 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1657,6 +1657,16 @@ static void sock_copy(struct sock *nsk, const struct sock *osk) #ifdef CONFIG_SECURITY_NETWORK void *sptr = nsk->sk_security; #endif + + /* If we move sk_tx_queue_mapping out of the private section, + * we must check if sk_tx_queue_clear() is called after + * sock_copy() in sk_clone_lock(). + */ + BUILD_BUG_ON(offsetof(struct sock, sk_tx_queue_mapping) < + offsetof(struct sock, sk_dontcopy_begin) || + offsetof(struct sock, sk_tx_queue_mapping) >= + offsetof(struct sock, sk_dontcopy_end)); + memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin)); memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end, @@ -1690,7 +1700,6 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, if (!try_module_get(prot->owner)) goto out_free_sec; - sk_tx_queue_clear(sk); } return sk; @@ -1876,123 +1885,120 @@ static void sk_init_common(struct sock *sk) struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) { struct proto *prot = READ_ONCE(sk->sk_prot); - struct sock *newsk; + struct sk_filter *filter; bool is_charged = true; + struct sock *newsk; newsk = sk_prot_alloc(prot, priority, sk->sk_family); - if (newsk != NULL) { - struct sk_filter *filter; + if (!newsk) + goto out; - sock_copy(newsk, sk); + sock_copy(newsk, sk); - newsk->sk_prot_creator = prot; + newsk->sk_prot_creator = prot; - /* SANITY */ - if (likely(newsk->sk_net_refcnt)) - get_net(sock_net(newsk)); - sk_node_init(&newsk->sk_node); - sock_lock_init(newsk); - bh_lock_sock(newsk); - newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL; - newsk->sk_backlog.len = 0; + /* SANITY */ + if (likely(newsk->sk_net_refcnt)) + get_net(sock_net(newsk)); + sk_node_init(&newsk->sk_node); + sock_lock_init(newsk); + bh_lock_sock(newsk); + newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL; + newsk->sk_backlog.len = 0; - atomic_set(&newsk->sk_rmem_alloc, 0); - /* - * sk_wmem_alloc set to one (see sk_free() and sock_wfree()) - */ - refcount_set(&newsk->sk_wmem_alloc, 1); - atomic_set(&newsk->sk_omem_alloc, 0); - sk_init_common(newsk); + atomic_set(&newsk->sk_rmem_alloc, 0); - newsk->sk_dst_cache = NULL; - newsk->sk_dst_pending_confirm = 0; - newsk->sk_wmem_queued = 0; - newsk->sk_forward_alloc = 0; - atomic_set(&newsk->sk_drops, 0); - newsk->sk_send_head = NULL; - newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; - atomic_set(&newsk->sk_zckey, 0); + /* sk_wmem_alloc set to one (see sk_free() and sock_wfree()) */ + refcount_set(&newsk->sk_wmem_alloc, 1); - sock_reset_flag(newsk, SOCK_DONE); + atomic_set(&newsk->sk_omem_alloc, 0); + sk_init_common(newsk); - /* sk->sk_memcg will be populated at accept() time */ - newsk->sk_memcg = NULL; + newsk->sk_dst_cache = NULL; + newsk->sk_dst_pending_confirm = 0; + newsk->sk_wmem_queued = 0; + newsk->sk_forward_alloc = 0; + atomic_set(&newsk->sk_drops, 0); + newsk->sk_send_head = NULL; + newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; + atomic_set(&newsk->sk_zckey, 0); - cgroup_sk_clone(&newsk->sk_cgrp_data); + sock_reset_flag(newsk, SOCK_DONE); - rcu_read_lock(); - filter = rcu_dereference(sk->sk_filter); - if (filter != NULL) - /* though it's an empty new sock, the charging may fail - * if sysctl_optmem_max was changed between creation of - * original socket and cloning - */ - is_charged = sk_filter_charge(newsk, filter); - RCU_INIT_POINTER(newsk->sk_filter, filter); - rcu_read_unlock(); + /* sk->sk_memcg will be populated at accept() time */ + newsk->sk_memcg = NULL; - if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) { - /* We need to make sure that we don't uncharge the new - * socket if we couldn't charge it in the first place - * as otherwise we uncharge the parent's filter. - */ - if (!is_charged) - RCU_INIT_POINTER(newsk->sk_filter, NULL); - sk_free_unlock_clone(newsk); - newsk = NULL; - goto out; - } - RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL); + cgroup_sk_clone(&newsk->sk_cgrp_data); - if (bpf_sk_storage_clone(sk, newsk)) { - sk_free_unlock_clone(newsk); - newsk = NULL; - goto out; - } + rcu_read_lock(); + filter = rcu_dereference(sk->sk_filter); + if (filter != NULL) + /* though it's an empty new sock, the charging may fail + * if sysctl_optmem_max was changed between creation of + * original socket and cloning + */ + is_charged = sk_filter_charge(newsk, filter); + RCU_INIT_POINTER(newsk->sk_filter, filter); + rcu_read_unlock(); - /* Clear sk_user_data if parent had the pointer tagged - * as not suitable for copying when cloning. + if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) { + /* We need to make sure that we don't uncharge the new + * socket if we couldn't charge it in the first place + * as otherwise we uncharge the parent's filter. */ - if (sk_user_data_is_nocopy(newsk)) - newsk->sk_user_data = NULL; + if (!is_charged) + RCU_INIT_POINTER(newsk->sk_filter, NULL); + sk_free_unlock_clone(newsk); + newsk = NULL; + goto out; + } + RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL); - newsk->sk_err = 0; - newsk->sk_err_soft = 0; - newsk->sk_priority = 0; - newsk->sk_incoming_cpu = raw_smp_processor_id(); - if (likely(newsk->sk_net_refcnt)) - sock_inuse_add(sock_net(newsk), 1); + if (bpf_sk_storage_clone(sk, newsk)) { + sk_free_unlock_clone(newsk); + newsk = NULL; + goto out; + } - /* - * Before updating sk_refcnt, we must commit prior changes to memory - * (Documentation/RCU/rculist_nulls.rst for details) - */ - smp_wmb(); - refcount_set(&newsk->sk_refcnt, 2); + /* Clear sk_user_data if parent had the pointer tagged + * as not suitable for copying when cloning. + */ + if (sk_user_data_is_nocopy(newsk)) + newsk->sk_user_data = NULL; - /* - * Increment the counter in the same struct proto as the master - * sock (sk_refcnt_debug_inc uses newsk->sk_prot->socks, that - * is the same as sk->sk_prot->socks, as this field was copied - * with memcpy). - * - * This _changes_ the previous behaviour, where - * tcp_create_openreq_child always was incrementing the - * equivalent to tcp_prot->socks (inet_sock_nr), so this have - * to be taken into account in all callers. -acme - */ - sk_refcnt_debug_inc(newsk); - sk_set_socket(newsk, NULL); - sk_tx_queue_clear(newsk); - RCU_INIT_POINTER(newsk->sk_wq, NULL); + newsk->sk_err = 0; + newsk->sk_err_soft = 0; + newsk->sk_priority = 0; + newsk->sk_incoming_cpu = raw_smp_processor_id(); + if (likely(newsk->sk_net_refcnt)) + sock_inuse_add(sock_net(newsk), 1); - if (newsk->sk_prot->sockets_allocated) - sk_sockets_allocated_inc(newsk); + /* Before updating sk_refcnt, we must commit prior changes to memory + * (Documentation/RCU/rculist_nulls.rst for details) + */ + smp_wmb(); + refcount_set(&newsk->sk_refcnt, 2); - if (sock_needs_netstamp(sk) && - newsk->sk_flags & SK_FLAGS_TIMESTAMP) - net_enable_timestamp(); - } + /* Increment the counter in the same struct proto as the master + * sock (sk_refcnt_debug_inc uses newsk->sk_prot->socks, that + * is the same as sk->sk_prot->socks, as this field was copied + * with memcpy). + * + * This _changes_ the previous behaviour, where + * tcp_create_openreq_child always was incrementing the + * equivalent to tcp_prot->socks (inet_sock_nr), so this have + * to be taken into account in all callers. -acme + */ + sk_refcnt_debug_inc(newsk); + sk_set_socket(newsk, NULL); + sk_tx_queue_clear(newsk); + RCU_INIT_POINTER(newsk->sk_wq, NULL); + + if (newsk->sk_prot->sockets_allocated) + sk_sockets_allocated_inc(newsk); + + if (sock_needs_netstamp(sk) && newsk->sk_flags & SK_FLAGS_TIMESTAMP) + net_enable_timestamp(); out: return newsk; } diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 64b5ec14ff50..d758fb83c884 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -602,7 +602,7 @@ int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, ret = sock_hash_update_common(map, key, sk, flags); sock_map_sk_release(sk); out: - fput(sock->file); + sockfd_put(sock); return ret; } diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index d86d8d11cfe4..4567de519603 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -309,7 +309,6 @@ proc_dolongvec_minmax_bpf_restricted(struct ctl_table *table, int write, #endif static struct ctl_table net_core_table[] = { -#ifdef CONFIG_NET { .procname = "wmem_max", .data = &sysctl_wmem_max, @@ -507,7 +506,6 @@ static struct ctl_table net_core_table[] = { .proc_handler = set_default_qdisc }, #endif -#endif /* CONFIG_NET */ { .procname = "netdev_budget", .data = &netdev_budget, |