diff options
Diffstat (limited to 'net')
47 files changed, 462 insertions, 366 deletions
diff --git a/net/Kconfig b/net/Kconfig index 62da6148e9f8..1efe1f9ee492 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -429,21 +429,12 @@ config NET_SOCK_MSG with the help of BPF programs. config NET_DEVLINK - tristate "Network physical/parent device Netlink interface" + bool "Network physical/parent device Netlink interface" help Network physical/parent device Netlink interface provides infrastructure to support access to physical chip-wide config and monitoring. -config MAY_USE_DEVLINK - tristate - default m if NET_DEVLINK=m - default y if NET_DEVLINK=y || NET_DEVLINK=n - help - Drivers using the devlink infrastructure should have a dependency - on MAY_USE_DEVLINK to ensure they do not cause link errors when - devlink is a loadable module and the driver using it is built-in. - config PAGE_POOL bool diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index af57c4a2b78a..921310d3cbae 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -67,12 +67,18 @@ int br_switchdev_set_port_flag(struct net_bridge_port *p, .id = SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS, .u.brport_flags = mask, }; + struct switchdev_notifier_port_attr_info info = { + .attr = &attr, + }; int err; if (mask & ~BR_PORT_FLAGS_HW_OFFLOAD) return 0; - err = switchdev_port_attr_set(p->dev, &attr); + /* We run from atomic context here */ + err = call_switchdev_notifiers(SWITCHDEV_PORT_ATTR_SET, p->dev, + &info.info, NULL); + err = notifier_to_errno(err); if (err == -EOPNOTSUPP) return 0; diff --git a/net/core/devlink.c b/net/core/devlink.c index 4f31ddc883e7..6515fbec0dcd 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -723,7 +723,7 @@ static int devlink_port_type_set(struct devlink *devlink, { int err; - if (devlink->ops && devlink->ops->port_type_set) { + if (devlink->ops->port_type_set) { if (port_type == DEVLINK_PORT_TYPE_NOTSET) return -EINVAL; if (port_type == devlink_port->type) @@ -760,7 +760,7 @@ static int devlink_port_split(struct devlink *devlink, u32 port_index, u32 count, struct netlink_ext_ack *extack) { - if (devlink->ops && devlink->ops->port_split) + if (devlink->ops->port_split) return devlink->ops->port_split(devlink, port_index, count, extack); return -EOPNOTSUPP; @@ -786,7 +786,7 @@ static int devlink_port_unsplit(struct devlink *devlink, u32 port_index, struct netlink_ext_ack *extack) { - if (devlink->ops && devlink->ops->port_unsplit) + if (devlink->ops->port_unsplit) return devlink->ops->port_unsplit(devlink, port_index, extack); return -EOPNOTSUPP; } @@ -961,7 +961,7 @@ static int devlink_nl_cmd_sb_pool_get_doit(struct sk_buff *skb, if (err) return err; - if (!devlink->ops || !devlink->ops->sb_pool_get) + if (!devlink->ops->sb_pool_get) return -EOPNOTSUPP; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); @@ -1017,7 +1017,7 @@ static int devlink_nl_cmd_sb_pool_get_dumpit(struct sk_buff *msg, mutex_lock(&devlink_mutex); list_for_each_entry(devlink, &devlink_list, list) { if (!net_eq(devlink_net(devlink), sock_net(msg->sk)) || - !devlink->ops || !devlink->ops->sb_pool_get) + !devlink->ops->sb_pool_get) continue; mutex_lock(&devlink->lock); list_for_each_entry(devlink_sb, &devlink->sb_list, list) { @@ -1046,7 +1046,7 @@ static int devlink_sb_pool_set(struct devlink *devlink, unsigned int sb_index, { const struct devlink_ops *ops = devlink->ops; - if (ops && ops->sb_pool_set) + if (ops->sb_pool_set) return ops->sb_pool_set(devlink, sb_index, pool_index, size, threshold_type); return -EOPNOTSUPP; @@ -1151,7 +1151,7 @@ static int devlink_nl_cmd_sb_port_pool_get_doit(struct sk_buff *skb, if (err) return err; - if (!devlink->ops || !devlink->ops->sb_port_pool_get) + if (!devlink->ops->sb_port_pool_get) return -EOPNOTSUPP; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); @@ -1213,7 +1213,7 @@ static int devlink_nl_cmd_sb_port_pool_get_dumpit(struct sk_buff *msg, mutex_lock(&devlink_mutex); list_for_each_entry(devlink, &devlink_list, list) { if (!net_eq(devlink_net(devlink), sock_net(msg->sk)) || - !devlink->ops || !devlink->ops->sb_port_pool_get) + !devlink->ops->sb_port_pool_get) continue; mutex_lock(&devlink->lock); list_for_each_entry(devlink_sb, &devlink->sb_list, list) { @@ -1242,7 +1242,7 @@ static int devlink_sb_port_pool_set(struct devlink_port *devlink_port, { const struct devlink_ops *ops = devlink_port->devlink->ops; - if (ops && ops->sb_port_pool_set) + if (ops->sb_port_pool_set) return ops->sb_port_pool_set(devlink_port, sb_index, pool_index, threshold); return -EOPNOTSUPP; @@ -1355,7 +1355,7 @@ static int devlink_nl_cmd_sb_tc_pool_bind_get_doit(struct sk_buff *skb, if (err) return err; - if (!devlink->ops || !devlink->ops->sb_tc_pool_bind_get) + if (!devlink->ops->sb_tc_pool_bind_get) return -EOPNOTSUPP; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); @@ -1439,7 +1439,7 @@ devlink_nl_cmd_sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, mutex_lock(&devlink_mutex); list_for_each_entry(devlink, &devlink_list, list) { if (!net_eq(devlink_net(devlink), sock_net(msg->sk)) || - !devlink->ops || !devlink->ops->sb_tc_pool_bind_get) + !devlink->ops->sb_tc_pool_bind_get) continue; mutex_lock(&devlink->lock); @@ -1471,7 +1471,7 @@ static int devlink_sb_tc_pool_bind_set(struct devlink_port *devlink_port, { const struct devlink_ops *ops = devlink_port->devlink->ops; - if (ops && ops->sb_tc_pool_bind_set) + if (ops->sb_tc_pool_bind_set) return ops->sb_tc_pool_bind_set(devlink_port, sb_index, tc_index, pool_type, pool_index, threshold); @@ -1519,7 +1519,7 @@ static int devlink_nl_cmd_sb_occ_snapshot_doit(struct sk_buff *skb, struct devlink_sb *devlink_sb = info->user_ptr[1]; const struct devlink_ops *ops = devlink->ops; - if (ops && ops->sb_occ_snapshot) + if (ops->sb_occ_snapshot) return ops->sb_occ_snapshot(devlink, devlink_sb->index); return -EOPNOTSUPP; } @@ -1531,7 +1531,7 @@ static int devlink_nl_cmd_sb_occ_max_clear_doit(struct sk_buff *skb, struct devlink_sb *devlink_sb = info->user_ptr[1]; const struct devlink_ops *ops = devlink->ops; - if (ops && ops->sb_occ_max_clear) + if (ops->sb_occ_max_clear) return ops->sb_occ_max_clear(devlink, devlink_sb->index); return -EOPNOTSUPP; } @@ -1594,13 +1594,9 @@ static int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; - const struct devlink_ops *ops = devlink->ops; struct sk_buff *msg; int err; - if (!ops) - return -EOPNOTSUPP; - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; @@ -1625,9 +1621,6 @@ static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, int err = 0; u16 mode; - if (!ops) - return -EOPNOTSUPP; - if (info->attrs[DEVLINK_ATTR_ESWITCH_MODE]) { if (!ops->eswitch_mode_set) return -EOPNOTSUPP; @@ -3869,7 +3862,7 @@ static int devlink_nl_cmd_info_get_doit(struct sk_buff *skb, struct sk_buff *msg; int err; - if (!devlink->ops || !devlink->ops->info_get) + if (!devlink->ops->info_get) return -EOPNOTSUPP; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); @@ -5232,6 +5225,9 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) { struct devlink *devlink; + if (WARN_ON(!ops)) + return NULL; + devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL); if (!devlink) return NULL; @@ -5253,6 +5249,7 @@ EXPORT_SYMBOL_GPL(devlink_alloc); * devlink_register - Register devlink instance * * @devlink: devlink + * @dev: parent device */ int devlink_register(struct devlink *devlink, struct device *dev) { @@ -5303,7 +5300,7 @@ EXPORT_SYMBOL_GPL(devlink_free); * * @devlink: devlink * @devlink_port: devlink port - * @port_index + * @port_index: driver-specific numerical identifier of the port * * Register devlink port with provided port index. User can use * any indexing, even hw-related one. devlink_port structure @@ -5633,13 +5630,10 @@ EXPORT_SYMBOL_GPL(devlink_dpipe_table_unregister); * * @devlink: devlink * @resource_name: resource's name - * @top_hierarchy: top hierarchy - * @reload_required: reload is required for new configuration to - * apply * @resource_size: resource's size * @resource_id: resource's id - * @parent_reosurce_id: resource's parent id - * @size params: size parameters + * @parent_resource_id: resource's parent id + * @size_params: size parameters */ int devlink_resource_register(struct devlink *devlink, const char *resource_name, @@ -6091,7 +6085,7 @@ __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->ops || !devlink->ops->reload) + if (!devlink->ops->reload) return -EOPNOTSUPP; return __devlink_param_driverinit_value_get(&devlink->param_list, @@ -6138,7 +6132,7 @@ int devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, { struct devlink *devlink = devlink_port->devlink; - if (!devlink->ops || !devlink->ops->reload) + if (!devlink->ops->reload) return -EOPNOTSUPP; return __devlink_param_driverinit_value_get(&devlink_port->param_list, @@ -6336,7 +6330,7 @@ EXPORT_SYMBOL_GPL(devlink_region_shapshot_id_get); * Multiple snapshots can be created on a region. * The @snapshot_id should be obtained using the getter function. * - * @devlink_region: devlink region of the snapshot + * @region: devlink region of the snapshot * @data_len: size of snapshot data * @data: snapshot data * @snapshot_id: snapshot id to be created @@ -6397,9 +6391,6 @@ static void __devlink_compat_running_version(struct devlink *devlink, struct sk_buff *msg; int rem, err; - if (!devlink->ops->info_get) - return; - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; @@ -6431,71 +6422,54 @@ free_msg: void devlink_compat_running_version(struct net_device *dev, char *buf, size_t len) { - struct devlink_port *devlink_port; struct devlink *devlink; + dev_hold(dev); + rtnl_unlock(); + mutex_lock(&devlink_mutex); - list_for_each_entry(devlink, &devlink_list, list) { - mutex_lock(&devlink->lock); - list_for_each_entry(devlink_port, &devlink->port_list, list) { - if (devlink_port->type == DEVLINK_PORT_TYPE_ETH && - devlink_port->type_dev == dev) { - __devlink_compat_running_version(devlink, - buf, len); - mutex_unlock(&devlink->lock); - goto out; - } - } - mutex_unlock(&devlink->lock); - } -out: + devlink = netdev_to_devlink(dev); + if (!devlink || !devlink->ops->info_get) + goto unlock_list; + + mutex_lock(&devlink->lock); + __devlink_compat_running_version(devlink, buf, len); + mutex_unlock(&devlink->lock); +unlock_list: mutex_unlock(&devlink_mutex); + + rtnl_lock(); + dev_put(dev); } int devlink_compat_flash_update(struct net_device *dev, const char *file_name) { - struct devlink_port *devlink_port; struct devlink *devlink; + int ret = -EOPNOTSUPP; - mutex_lock(&devlink_mutex); - list_for_each_entry(devlink, &devlink_list, list) { - mutex_lock(&devlink->lock); - list_for_each_entry(devlink_port, &devlink->port_list, list) { - int ret = -EOPNOTSUPP; + dev_hold(dev); + rtnl_unlock(); - if (devlink_port->type != DEVLINK_PORT_TYPE_ETH || - devlink_port->type_dev != dev) - continue; + mutex_lock(&devlink_mutex); + devlink = netdev_to_devlink(dev); + if (!devlink || !devlink->ops->flash_update) + goto unlock_list; - mutex_unlock(&devlink_mutex); - if (devlink->ops->flash_update) - ret = devlink->ops->flash_update(devlink, - file_name, - NULL, NULL); - mutex_unlock(&devlink->lock); - return ret; - } - mutex_unlock(&devlink->lock); - } + mutex_lock(&devlink->lock); + ret = devlink->ops->flash_update(devlink, file_name, NULL, NULL); + mutex_unlock(&devlink->lock); +unlock_list: mutex_unlock(&devlink_mutex); - return -EOPNOTSUPP; -} + rtnl_lock(); + dev_put(dev); -static int __init devlink_module_init(void) -{ - return genl_register_family(&devlink_nl_family); + return ret; } -static void __exit devlink_module_exit(void) +static int __init devlink_init(void) { - genl_unregister_family(&devlink_nl_family); + return genl_register_family(&devlink_nl_family); } -module_init(devlink_module_init); -module_exit(devlink_module_exit); - -MODULE_LICENSE("GPL v2"); -MODULE_AUTHOR("Jiri Pirko <jiri@mellanox.com>"); -MODULE_DESCRIPTION("Network physical device Netlink interface"); -MODULE_ALIAS_GENL_FAMILY(DEVLINK_GENL_NAME); +subsys_initcall(devlink_init); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 1320e8dce559..d4918ffddda8 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -805,11 +805,9 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, if (ops->get_eeprom_len) info.eedump_len = ops->get_eeprom_len(dev); - rtnl_unlock(); if (!info.fw_version[0]) devlink_compat_running_version(dev, info.fw_version, sizeof(info.fw_version)); - rtnl_lock(); if (copy_to_user(useraddr, &info, sizeof(info))) return -EFAULT; @@ -1719,7 +1717,7 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev, static int ethtool_get_pauseparam(struct net_device *dev, void __user *useraddr) { - struct ethtool_pauseparam pauseparam = { ETHTOOL_GPAUSEPARAM }; + struct ethtool_pauseparam pauseparam = { .cmd = ETHTOOL_GPAUSEPARAM }; if (!dev->ethtool_ops->get_pauseparam) return -EOPNOTSUPP; @@ -2040,15 +2038,8 @@ static noinline_for_stack int ethtool_flash_device(struct net_device *dev, return -EFAULT; efl.data[ETHTOOL_FLASH_MAX_FILENAME - 1] = 0; - if (!dev->ethtool_ops->flash_device) { - int ret; - - rtnl_unlock(); - ret = devlink_compat_flash_update(dev, efl.data); - rtnl_lock(); - - return ret; - } + if (!dev->ethtool_ops->flash_device) + return devlink_compat_flash_update(dev, efl.data); return dev->ethtool_ops->flash_device(dev, &efl); } @@ -2512,7 +2503,7 @@ static int set_phy_tunable(struct net_device *dev, void __user *useraddr) static int ethtool_get_fecparam(struct net_device *dev, void __user *useraddr) { - struct ethtool_fecparam fecparam = { ETHTOOL_GFECPARAM }; + struct ethtool_fecparam fecparam = { .cmd = ETHTOOL_GFECPARAM }; int rc; if (!dev->ethtool_ops->get_fecparam) diff --git a/net/core/sock.c b/net/core/sock.c index f5d82f3fa474..782343bb925b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1108,15 +1108,23 @@ set_rcvbuf: #endif case SO_MAX_PACING_RATE: - if (val != ~0U) + { + unsigned long ulval = (val == ~0U) ? ~0UL : val; + + if (sizeof(ulval) != sizeof(val) && + optlen >= sizeof(ulval) && + get_user(ulval, (unsigned long __user *)optval)) { + ret = -EFAULT; + break; + } + if (ulval != ~0UL) cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); - sk->sk_max_pacing_rate = (val == ~0U) ? ~0UL : val; - sk->sk_pacing_rate = min(sk->sk_pacing_rate, - sk->sk_max_pacing_rate); + sk->sk_max_pacing_rate = ulval; + sk->sk_pacing_rate = min(sk->sk_pacing_rate, ulval); break; - + } case SO_INCOMING_CPU: sk->sk_incoming_cpu = val; break; @@ -1211,6 +1219,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, union { int val; u64 val64; + unsigned long ulval; struct linger ling; struct old_timeval32 tm32; struct __kernel_old_timeval tm; @@ -1456,8 +1465,13 @@ int sock_getsockopt(struct socket *sock, int level, int optname, #endif case SO_MAX_PACING_RATE: - /* 32bit version */ - v.val = min_t(unsigned long, sk->sk_max_pacing_rate, ~0U); + if (sizeof(v.ulval) != sizeof(v.val) && len >= sizeof(v.ulval)) { + lv = sizeof(v.ulval); + v.ulval = sk->sk_max_pacing_rate; + } else { + /* 32bit version */ + v.val = min_t(unsigned long, sk->sk_max_pacing_rate, ~0U); + } break; case SO_INCOMING_CPU: diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 91e52973ee13..fab49132345f 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -6,7 +6,7 @@ config HAVE_NET_DSA config NET_DSA tristate "Distributed Switch Architecture" - depends on HAVE_NET_DSA && MAY_USE_DEVLINK + depends on HAVE_NET_DSA depends on BRIDGE || BRIDGE=n select NET_SWITCHDEV select PHYLINK diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 8c431e0f3627..c00ee464afc7 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -612,8 +612,8 @@ static int dsa_switch_parse_ports_of(struct dsa_switch *ds, { struct device_node *ports, *port; struct dsa_port *dp; + int err = 0; u32 reg; - int err; ports = of_get_child_by_name(dn, "ports"); if (!ports) { @@ -624,19 +624,23 @@ static int dsa_switch_parse_ports_of(struct dsa_switch *ds, for_each_available_child_of_node(ports, port) { err = of_property_read_u32(port, "reg", ®); if (err) - return err; + goto out_put_node; - if (reg >= ds->num_ports) - return -EINVAL; + if (reg >= ds->num_ports) { + err = -EINVAL; + goto out_put_node; + } dp = &ds->ports[reg]; err = dsa_port_parse_of(dp, port); if (err) - return err; + goto out_put_node; } - return 0; +out_put_node: + of_node_put(ports); + return err; } static int dsa_switch_parse_member_of(struct dsa_switch *ds, diff --git a/net/dsa/port.c b/net/dsa/port.c index a2dad10646cb..caeef4c99dc0 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -337,6 +337,7 @@ static struct phy_device *dsa_port_get_phy_device(struct dsa_port *dp) return ERR_PTR(-EPROBE_DEFER); } + of_node_put(phy_dn); return phydev; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 7274499293c9..1808a2cd6872 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1118,10 +1118,6 @@ static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_vlan_rx_kill_vid = dsa_slave_vlan_rx_kill_vid, }; -static const struct switchdev_ops dsa_slave_switchdev_ops = { - .switchdev_port_attr_set = dsa_slave_port_attr_set, -}; - static struct device_type dsa_type = { .name = "dsa", }; @@ -1382,7 +1378,6 @@ int dsa_slave_create(struct dsa_port *port) eth_hw_addr_inherit(slave_dev, master); slave_dev->priv_flags |= IFF_NO_QUEUE; slave_dev->netdev_ops = &dsa_slave_netdev_ops; - slave_dev->switchdev_ops = &dsa_slave_switchdev_ops; slave_dev->min_mtu = 0; slave_dev->max_mtu = ETH_MAX_MTU; SET_NETDEV_DEVTYPE(slave_dev, &dsa_type); @@ -1524,6 +1519,19 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, return NOTIFY_DONE; } +static int +dsa_slave_switchdev_port_attr_set_event(struct net_device *netdev, + struct switchdev_notifier_port_attr_info *port_attr_info) +{ + int err; + + err = dsa_slave_port_attr_set(netdev, port_attr_info->attr, + port_attr_info->trans); + + port_attr_info->handled = true; + return notifier_from_errno(err); +} + struct dsa_switchdev_event_work { struct work_struct work; struct switchdev_notifier_fdb_info fdb_info; @@ -1602,6 +1610,9 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused, if (!dsa_slave_dev_check(dev)) return NOTIFY_DONE; + if (event == SWITCHDEV_PORT_ATTR_SET) + return dsa_slave_switchdev_port_attr_set_event(dev, ptr); + switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC); if (!switchdev_work) return NOTIFY_BAD; @@ -1664,6 +1675,8 @@ static int dsa_slave_switchdev_blocking_event(struct notifier_block *unused, case SWITCHDEV_PORT_OBJ_ADD: /* fall through */ case SWITCHDEV_PORT_OBJ_DEL: return dsa_slave_switchdev_port_obj_event(event, dev, ptr); + case SWITCHDEV_PORT_ATTR_SET: + return dsa_slave_switchdev_port_attr_set_event(dev, ptr); } return NOTIFY_DONE; diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index bd61633d2c32..4196bcd4105a 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -179,7 +179,6 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *skb, skb->dev = ldev; skb->tstamp = fq->q.stamp; - fq->q.fragments = NULL; fq->q.rb_fragments = RB_ROOT; fq->q.fragments_tail = NULL; fq->q.last_run_head = NULL; diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 777fa3b7fb13..f0165c5f376b 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -667,7 +667,8 @@ static int cipso_v4_map_lvl_valid(const struct cipso_v4_doi *doi_def, u8 level) case CIPSO_V4_MAP_PASS: return 0; case CIPSO_V4_MAP_TRANS: - if (doi_def->map.std->lvl.cipso[level] < CIPSO_V4_INV_LVL) + if ((level < doi_def->map.std->lvl.cipso_size) && + (doi_def->map.std->lvl.cipso[level] < CIPSO_V4_INV_LVL)) return 0; break; } @@ -1735,13 +1736,26 @@ validate_return: */ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) { + unsigned char optbuf[sizeof(struct ip_options) + 40]; + struct ip_options *opt = (struct ip_options *)optbuf; + if (ip_hdr(skb)->protocol == IPPROTO_ICMP || error != -EACCES) return; + /* + * We might be called above the IP layer, + * so we can not use icmp_send and IPCB here. + */ + + memset(opt, 0, sizeof(struct ip_options)); + opt->optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr); + if (__ip_options_compile(dev_net(skb->dev), opt, skb, NULL)) + return; + if (gateway) - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_NET_ANO, 0); + __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_NET_ANO, 0, opt); else - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_ANO, 0); + __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_ANO, 0, opt); } /** diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index fe4f6a624238..ed14ec245584 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -710,6 +710,10 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, case RTA_GATEWAY: cfg->fc_gw = nla_get_be32(attr); break; + case RTA_VIA: + NL_SET_ERR_MSG(extack, "IPv4 does not support RTA_VIA attribute"); + err = -EINVAL; + goto errout; case RTA_PRIORITY: cfg->fc_priority = nla_get_u32(attr); break; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 364cfe5e414b..f3a5893b1e86 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -570,7 +570,8 @@ relookup_failed: * MUST reply to only the first fragment. */ -void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) +void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, + const struct ip_options *opt) { struct iphdr *iph; int room; @@ -691,7 +692,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) iph->tos; mark = IP4_REPLY_MARK(net, skb_in->mark); - if (ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in)) + if (__ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in, opt)) goto out_unlock; @@ -742,7 +743,7 @@ out_bh_enable: local_bh_enable(); out:; } -EXPORT_SYMBOL(icmp_send); +EXPORT_SYMBOL(__icmp_send); static void icmp_socket_deliver(struct sk_buff *skb, u32 info) diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 9f69411251d0..737808e27f8b 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -203,7 +203,6 @@ EXPORT_SYMBOL(inet_frag_rbtree_purge); void inet_frag_destroy(struct inet_frag_queue *q) { - struct sk_buff *fp; struct netns_frags *nf; unsigned int sum, sum_truesize = 0; struct inet_frags *f; @@ -212,20 +211,9 @@ void inet_frag_destroy(struct inet_frag_queue *q) WARN_ON(del_timer(&q->timer) != 0); /* Release all fragment data. */ - fp = q->fragments; nf = q->net; f = nf->f; - if (fp) { - do { - struct sk_buff *xp = fp->next; - - sum_truesize += fp->truesize; - kfree_skb(fp); - fp = xp; - } while (fp); - } else { - sum_truesize = inet_frag_rbtree_purge(&q->rb_fragments); - } + sum_truesize = inet_frag_rbtree_purge(&q->rb_fragments); sum = sum_truesize + f->qsize; call_rcu(&q->rcu, inet_frag_destroy_rcu); @@ -489,26 +477,20 @@ EXPORT_SYMBOL(inet_frag_reasm_finish); struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q) { - struct sk_buff *head; + struct sk_buff *head, *skb; - if (q->fragments) { - head = q->fragments; - q->fragments = head->next; - } else { - struct sk_buff *skb; + head = skb_rb_first(&q->rb_fragments); + if (!head) + return NULL; + skb = FRAG_CB(head)->next_frag; + if (skb) + rb_replace_node(&head->rbnode, &skb->rbnode, + &q->rb_fragments); + else + rb_erase(&head->rbnode, &q->rb_fragments); + memset(&head->rbnode, 0, sizeof(head->rbnode)); + barrier(); - head = skb_rb_first(&q->rb_fragments); - if (!head) - return NULL; - skb = FRAG_CB(head)->next_frag; - if (skb) - rb_replace_node(&head->rbnode, &skb->rbnode, - &q->rb_fragments); - else - rb_erase(&head->rbnode, &q->rb_fragments); - memset(&head->rbnode, 0, sizeof(head->rbnode)); - barrier(); - } if (head == q->fragments_tail) q->fragments_tail = NULL; diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 486ecb0aeb87..cf2b0a6a3337 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -261,7 +261,6 @@ static int ip_frag_reinit(struct ipq *qp) qp->q.flags = 0; qp->q.len = 0; qp->q.meat = 0; - qp->q.fragments = NULL; qp->q.rb_fragments = RB_ROOT; qp->q.fragments_tail = NULL; qp->q.last_run_head = NULL; @@ -451,7 +450,6 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, ip_send_check(iph); __IP_INC_STATS(net, IPSTATS_MIB_REASMOKS); - qp->q.fragments = NULL; qp->q.rb_fragments = RB_ROOT; qp->q.fragments_tail = NULL; qp->q.last_run_head = NULL; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 0f4925a0d6b2..fd219f7bd3ea 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -578,7 +578,7 @@ static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) key = &info->key; ip_tunnel_init_flow(&fl4, IPPROTO_GRE, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), key->tos, 0, - skb->mark); + skb->mark, skb_get_hash(skb)); rt = ip_route_output_key(dev_net(dev), &fl4); if (IS_ERR(rt)) return PTR_ERR(rt); diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index cd6b5694f99e..ecce2dc78f17 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -307,11 +307,10 @@ drop: } static int ip_rcv_finish_core(struct net *net, struct sock *sk, - struct sk_buff *skb) + struct sk_buff *skb, struct net_device *dev) { const struct iphdr *iph = ip_hdr(skb); int (*edemux)(struct sk_buff *skb); - struct net_device *dev = skb->dev; struct rtable *rt; int err; @@ -400,6 +399,7 @@ drop_error: static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { + struct net_device *dev = skb->dev; int ret; /* if ingress device is enslaved to an L3 master device pass the @@ -409,7 +409,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) if (!skb) return NET_RX_SUCCESS; - ret = ip_rcv_finish_core(net, sk, skb); + ret = ip_rcv_finish_core(net, sk, skb, dev); if (ret != NET_RX_DROP) ret = dst_input(skb); return ret; @@ -545,6 +545,7 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk, INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { + struct net_device *dev = skb->dev; struct dst_entry *dst; skb_list_del_init(skb); @@ -554,7 +555,7 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk, skb = l3mdev_ip_rcv(skb); if (!skb) continue; - if (ip_rcv_finish_core(net, sk, skb) == NET_RX_DROP) + if (ip_rcv_finish_core(net, sk, skb, dev) == NET_RX_DROP) continue; dst = skb_dst(skb); diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index ed194d46c00e..32a35043c9f5 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -251,8 +251,9 @@ static void spec_dst_fill(__be32 *spec_dst, struct sk_buff *skb) * If opt == NULL, then skb->data should point to IP header. */ -int ip_options_compile(struct net *net, - struct ip_options *opt, struct sk_buff *skb) +int __ip_options_compile(struct net *net, + struct ip_options *opt, struct sk_buff *skb, + __be32 *info) { __be32 spec_dst = htonl(INADDR_ANY); unsigned char *pp_ptr = NULL; @@ -468,11 +469,22 @@ eol: return 0; error: - if (skb) { - icmp_send(skb, ICMP_PARAMETERPROB, 0, htonl((pp_ptr-iph)<<24)); - } + if (info) + *info = htonl((pp_ptr-iph)<<24); return -EINVAL; } + +int ip_options_compile(struct net *net, + struct ip_options *opt, struct sk_buff *skb) +{ + int ret; + __be32 info; + + ret = __ip_options_compile(net, opt, skb, &info); + if (ret != 0 && skb) + icmp_send(skb, ICMP_PARAMETERPROB, 0, info); + return ret; +} EXPORT_SYMBOL(ip_options_compile); /* diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 2973067b831d..2756fb725bf0 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -310,7 +310,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev) ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr, iph->saddr, tunnel->parms.o_key, RT_TOS(iph->tos), tunnel->parms.link, - tunnel->fwmark); + tunnel->fwmark, 0); rt = ip_route_output_key(tunnel->net, &fl4); if (!IS_ERR(rt)) { @@ -584,7 +584,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), RT_TOS(tos), - 0, skb->mark); + 0, skb->mark, skb_get_hash(skb)); if (tunnel->encap.type != TUNNEL_ENCAP_NONE) goto tx_error; @@ -744,7 +744,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, - tunnel->fwmark); + tunnel->fwmark, skb_get_hash(skb)); if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) goto tx_error; diff --git a/net/ipv4/netlink.c b/net/ipv4/netlink.c index f86bb4f06609..d8e3a1fb8e82 100644 --- a/net/ipv4/netlink.c +++ b/net/ipv4/netlink.c @@ -3,9 +3,10 @@ #include <linux/types.h> #include <net/net_namespace.h> #include <net/netlink.h> +#include <linux/in6.h> #include <net/ip.h> -int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, +int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family, struct netlink_ext_ack *extack) { *ip_proto = nla_get_u8(attr); @@ -13,11 +14,19 @@ int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, switch (*ip_proto) { case IPPROTO_TCP: case IPPROTO_UDP: + return 0; case IPPROTO_ICMP: + if (family != AF_INET) + break; + return 0; +#if IS_ENABLED(CONFIG_IPV6) + case IPPROTO_ICMPV6: + if (family != AF_INET6) + break; return 0; - default: - NL_SET_ERR_MSG(extack, "Unsupported ip proto"); - return -EOPNOTSUPP; +#endif } + NL_SET_ERR_MSG(extack, "Unsupported ip proto"); + return -EOPNOTSUPP; } EXPORT_SYMBOL_GPL(rtm_getroute_parse_ip_proto); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ecc12a768191..738ff0a1a048 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1820,6 +1820,7 @@ out: int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, const struct sk_buff *skb, struct flow_keys *flkeys) { + u32 multipath_hash = fl4 ? fl4->flowi4_multipath_hash : 0; struct flow_keys hash_keys; u32 mhash; @@ -1870,6 +1871,9 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, } mhash = flow_hash_from_keys(&hash_keys); + if (multipath_hash) + mhash = jhash_2words(mhash, multipath_hash, 0); + return mhash >> 1; } #endif /* CONFIG_IP_ROUTE_MULTIPATH */ @@ -2872,7 +2876,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (tb[RTA_IP_PROTO]) { err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO], - &ip_proto, extack); + &ip_proto, AF_INET, extack); if (err) return err; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 769508c75dce..ad07dd71063d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1412,7 +1412,8 @@ do_fault: /* It is the one place in all of TCP, except connection * reset, where we can be unlinking the send_head. */ - tcp_check_send_head(sk, skb); + if (tcp_write_queue_empty(sk)) + tcp_chrono_stop(sk, TCP_CHRONO_BUSY); sk_wmem_free_skb(sk, skb); } @@ -3698,7 +3699,7 @@ bool tcp_alloc_md5sig_pool(void) if (!tcp_md5sig_pool_populated) { __tcp_alloc_md5sig_pool(); if (tcp_md5sig_pool_populated) - static_key_slow_inc(&tcp_md5_needed); + static_branch_inc(&tcp_md5_needed); } mutex_unlock(&tcp_md5sig_mutex); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 4010ae3644f3..831d844a27ca 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -973,7 +973,7 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req) * We need to maintain these in the sk structure. */ -struct static_key tcp_md5_needed __read_mostly; +DEFINE_STATIC_KEY_FALSE(tcp_md5_needed); EXPORT_SYMBOL(tcp_md5_needed); /* Find the Key structure for an address. */ diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 182595e2d40f..79900f783e0d 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -294,12 +294,15 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) * so the timewait ack generating code has the key. */ do { - struct tcp_md5sig_key *key; tcptw->tw_md5_key = NULL; - key = tp->af_specific->md5_lookup(sk, sk); - if (key) { - tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC); - BUG_ON(tcptw->tw_md5_key && !tcp_alloc_md5sig_pool()); + if (static_branch_unlikely(&tcp_md5_needed)) { + struct tcp_md5sig_key *key; + + key = tp->af_specific->md5_lookup(sk, sk); + if (key) { + tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC); + BUG_ON(tcptw->tw_md5_key && !tcp_alloc_md5sig_pool()); + } } } while (0); #endif @@ -338,10 +341,12 @@ EXPORT_SYMBOL(tcp_time_wait); void tcp_twsk_destructor(struct sock *sk) { #ifdef CONFIG_TCP_MD5SIG - struct tcp_timewait_sock *twsk = tcp_twsk(sk); + if (static_branch_unlikely(&tcp_md5_needed)) { + struct tcp_timewait_sock *twsk = tcp_twsk(sk); - if (twsk->tw_md5_key) - kfree_rcu(twsk->tw_md5_key, rcu); + if (twsk->tw_md5_key) + kfree_rcu(twsk->tw_md5_key, rcu); + } #endif } EXPORT_SYMBOL_GPL(tcp_twsk_destructor); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index e72aa0ff5785..4522579aaca2 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -597,7 +597,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, *md5 = NULL; #ifdef CONFIG_TCP_MD5SIG - if (static_key_false(&tcp_md5_needed) && + if (static_branch_unlikely(&tcp_md5_needed) && rcu_access_pointer(tp->md5sig_info)) { *md5 = tp->af_specific->md5_lookup(sk, sk); if (*md5) { @@ -734,7 +734,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb *md5 = NULL; #ifdef CONFIG_TCP_MD5SIG - if (static_key_false(&tcp_md5_needed) && + if (static_branch_unlikely(&tcp_md5_needed) && rcu_access_pointer(tp->md5sig_info)) { *md5 = tp->af_specific->md5_lookup(sk, sk); if (*md5) { @@ -1846,17 +1846,17 @@ static bool tcp_snd_wnd_test(const struct tcp_sock *tp, * know that all the data is in scatter-gather pages, and that the * packet has never been sent out before (and thus is not cloned). */ -static int tso_fragment(struct sock *sk, enum tcp_queue tcp_queue, - struct sk_buff *skb, unsigned int len, +static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, unsigned int mss_now, gfp_t gfp) { - struct sk_buff *buff; int nlen = skb->len - len; + struct sk_buff *buff; u8 flags; /* All of a TSO frame must be composed of paged data. */ if (skb->len != skb->data_len) - return tcp_fragment(sk, tcp_queue, skb, len, mss_now, gfp); + return tcp_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE, + skb, len, mss_now, gfp); buff = sk_stream_alloc_skb(sk, 0, gfp, true); if (unlikely(!buff)) @@ -1892,7 +1892,7 @@ static int tso_fragment(struct sock *sk, enum tcp_queue tcp_queue, /* Link BUFF into the send queue. */ __skb_header_release(buff); - tcp_insert_write_queue_after(skb, buff, sk, tcp_queue); + tcp_insert_write_queue_after(skb, buff, sk, TCP_FRAG_IN_WRITE_QUEUE); return 0; } @@ -2391,8 +2391,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, nonagle); if (skb->len > limit && - unlikely(tso_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE, - skb, limit, mss_now, gfp))) + unlikely(tso_fragment(sk, skb, limit, mss_now, gfp))) break; if (tcp_small_queue_check(sk, skb, 0)) diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index cb1b4772dac0..3de0e9b0a482 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -365,7 +365,6 @@ static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, skb_network_header_len(skb), skb->csum); - fq->q.fragments = NULL; fq->q.rb_fragments = RB_ROOT; fq->q.fragments_tail = NULL; fq->q.last_run_head = NULL; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 24264d0a4b85..1a832f5e190b 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -304,7 +304,6 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb, rcu_read_lock(); __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS); rcu_read_unlock(); - fq->q.fragments = NULL; fq->q.rb_fragments = RB_ROOT; fq->q.fragments_tail = NULL; fq->q.last_run_head = NULL; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 6181b4a18178..4ef4bbdb49d4 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -4176,6 +4176,10 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->fc_gateway = nla_get_in6_addr(tb[RTA_GATEWAY]); cfg->fc_flags |= RTF_GATEWAY; } + if (tb[RTA_VIA]) { + NL_SET_ERR_MSG(extack, "IPv6 does not support RTA_VIA attribute"); + goto errout; + } if (tb[RTA_DST]) { int plen = (rtm->rtm_dst_len + 7) >> 3; @@ -4949,7 +4953,8 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (tb[RTA_IP_PROTO]) { err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO], - &fl6.flowi6_proto, extack); + &fl6.flowi6_proto, AF_INET6, + extack); if (err) goto errout; } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index e8a1dabef803..09e440e8dfae 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1873,6 +1873,7 @@ static int __net_init sit_init_net(struct net *net) err_reg_dev: ipip6_dev_free(sitn->fb_tunnel_dev); + free_netdev(sitn->fb_tunnel_dev); err_alloc_dev: return err; } diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 2662a23c658e..f7c544592ec8 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1874,6 +1874,9 @@ static int rtm_to_route_config(struct sk_buff *skb, goto errout; break; } + case RTA_GATEWAY: + NL_SET_ERR_MSG(extack, "MPLS does not support RTA_GATEWAY attribute"); + goto errout; case RTA_VIA: { if (nla_get_via(nla, &cfg->rc_via_alen, diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index ea7c67050792..ee3e5b6471a6 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -903,7 +903,8 @@ int netlbl_bitmap_walk(const unsigned char *bitmap, u32 bitmap_len, (state == 0 && (byte & bitmask) == 0)) return bit_spot; - bit_spot++; + if (++bit_spot >= bitmap_len) + return -1; bitmask >>= 1; if (bitmask == 0) { byte = bitmap[++byte_offset]; diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index 6a196e438b6c..d1fc019e932e 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -419,6 +419,10 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) sock->service_name, sock->service_name_len, &service_name_tlv_length); + if (!service_name_tlv) { + err = -ENOMEM; + goto error_tlv; + } size += service_name_tlv_length; } @@ -429,9 +433,17 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0, &miux_tlv_length); + if (!miux_tlv) { + err = -ENOMEM; + goto error_tlv; + } size += miux_tlv_length; rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &rw, 0, &rw_tlv_length); + if (!rw_tlv) { + err = -ENOMEM; + goto error_tlv; + } size += rw_tlv_length; pr_debug("SKB size %d SN length %zu\n", size, sock->service_name_len); @@ -484,9 +496,17 @@ int nfc_llcp_send_cc(struct nfc_llcp_sock *sock) miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0, &miux_tlv_length); + if (!miux_tlv) { + err = -ENOMEM; + goto error_tlv; + } size += miux_tlv_length; rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &rw, 0, &rw_tlv_length); + if (!rw_tlv) { + err = -ENOMEM; + goto error_tlv; + } size += rw_tlv_length; skb = llcp_allocate_pdu(sock, LLCP_PDU_CC, size); diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index ef4026a23e80..4fa015208aab 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -532,10 +532,10 @@ static u8 nfc_llcp_reserve_sdp_ssap(struct nfc_llcp_local *local) static int nfc_llcp_build_gb(struct nfc_llcp_local *local) { - u8 *gb_cur, *version_tlv, version, version_length; - u8 *lto_tlv, lto_length; - u8 *wks_tlv, wks_length; - u8 *miux_tlv, miux_length; + u8 *gb_cur, version, version_length; + u8 lto_length, wks_length, miux_length; + u8 *version_tlv = NULL, *lto_tlv = NULL, + *wks_tlv = NULL, *miux_tlv = NULL; __be16 wks = cpu_to_be16(local->local_wks); u8 gb_len = 0; int ret = 0; @@ -543,17 +543,33 @@ static int nfc_llcp_build_gb(struct nfc_llcp_local *local) version = LLCP_VERSION_11; version_tlv = nfc_llcp_build_tlv(LLCP_TLV_VERSION, &version, 1, &version_length); + if (!version_tlv) { + ret = -ENOMEM; + goto out; + } gb_len += version_length; lto_tlv = nfc_llcp_build_tlv(LLCP_TLV_LTO, &local->lto, 1, <o_length); + if (!lto_tlv) { + ret = -ENOMEM; + goto out; + } gb_len += lto_length; pr_debug("Local wks 0x%lx\n", local->local_wks); wks_tlv = nfc_llcp_build_tlv(LLCP_TLV_WKS, (u8 *)&wks, 2, &wks_length); + if (!wks_tlv) { + ret = -ENOMEM; + goto out; + } gb_len += wks_length; miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&local->miux, 0, &miux_length); + if (!miux_tlv) { + ret = -ENOMEM; + goto out; + } gb_len += miux_length; gb_len += ARRAY_SIZE(llcp_magic); diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 945fb34ae721..c79aca29505e 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -559,8 +559,11 @@ static int tcf_csum_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_csum *p = to_tcf_csum(a); + bool orig_vlan_tag_present = false; + unsigned int vlan_hdr_count = 0; struct tcf_csum_params *params; u32 update_flags; + __be16 protocol; int action; params = rcu_dereference_bh(p->params); @@ -573,7 +576,9 @@ static int tcf_csum_act(struct sk_buff *skb, const struct tc_action *a, goto drop; update_flags = params->update_flags; - switch (tc_skb_protocol(skb)) { + protocol = tc_skb_protocol(skb); +again: + switch (protocol) { case cpu_to_be16(ETH_P_IP): if (!tcf_csum_ipv4(skb, update_flags)) goto drop; @@ -582,13 +587,35 @@ static int tcf_csum_act(struct sk_buff *skb, const struct tc_action *a, if (!tcf_csum_ipv6(skb, update_flags)) goto drop; break; + case cpu_to_be16(ETH_P_8021AD): /* fall through */ + case cpu_to_be16(ETH_P_8021Q): + if (skb_vlan_tag_present(skb) && !orig_vlan_tag_present) { + protocol = skb->protocol; + orig_vlan_tag_present = true; + } else { + struct vlan_hdr *vlan = (struct vlan_hdr *)skb->data; + + protocol = vlan->h_vlan_encapsulated_proto; + skb_pull(skb, VLAN_HLEN); + skb_reset_network_header(skb); + vlan_hdr_count++; + } + goto again; + } + +out: + /* Restore the skb for the pulled VLAN tags */ + while (vlan_hdr_count--) { + skb_push(skb, VLAN_HLEN); + skb_reset_network_header(skb); } return action; drop: qstats_drop_inc(this_cpu_ptr(p->common.cpu_qstats)); - return TC_ACT_SHOT; + action = TC_ACT_SHOT; + goto out; } static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind, diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 1bad190710ad..98f5b6ea77b4 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -199,8 +199,7 @@ err3: err2: kfree(tname); err1: - if (ret == ACT_P_CREATED) - tcf_idr_release(*a, bind); + tcf_idr_release(*a, bind); return err; } diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 39f8a67ea940..65879500b688 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -189,8 +189,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); if (unlikely(!params_new)) { - if (ret == ACT_P_CREATED) - tcf_idr_release(*a, bind); + tcf_idr_release(*a, bind); return -ENOMEM; } diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 3404af72b4c1..2a5f215ae876 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -201,8 +201,14 @@ static void tunnel_key_release_params(struct tcf_tunnel_key_params *p) { if (!p) return; - if (p->tcft_action == TCA_TUNNEL_KEY_ACT_SET) + if (p->tcft_action == TCA_TUNNEL_KEY_ACT_SET) { +#ifdef CONFIG_DST_CACHE + struct ip_tunnel_info *info = &p->tcft_enc_metadata->u.tun_info; + + dst_cache_destroy(&info->dst_cache); +#endif dst_release(&p->tcft_enc_metadata->dst); + } kfree_rcu(p, rcu); } @@ -384,10 +390,12 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, release_dst_cache: #ifdef CONFIG_DST_CACHE - dst_cache_destroy(&metadata->u.tun_info.dst_cache); + if (metadata) + dst_cache_destroy(&metadata->u.tun_info.dst_cache); #endif release_tun_meta: - dst_release(&metadata->dst); + if (metadata) + dst_release(&metadata->dst); err_out: if (exists) @@ -401,15 +409,8 @@ static void tunnel_key_release(struct tc_action *a) { struct tcf_tunnel_key *t = to_tunnel_key(a); struct tcf_tunnel_key_params *params; -#ifdef CONFIG_DST_CACHE - struct ip_tunnel_info *info; -#endif params = rcu_dereference_protected(t->params, 1); -#ifdef CONFIG_DST_CACHE - info = ¶ms->tcft_enc_metadata->u.tun_info; - dst_cache_destroy(&info->dst_cache); -#endif tunnel_key_release_params(params); } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index befc06f658df..478095d50f95 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -238,10 +238,10 @@ static void tcf_proto_put(struct tcf_proto *tp, bool rtnl_held, tcf_proto_destroy(tp, rtnl_held, extack); } -static int walker_check_empty(struct tcf_proto *tp, void *d, +static int walker_check_empty(struct tcf_proto *tp, void *fh, struct tcf_walker *arg) { - if (tp) { + if (fh) { arg->nonempty = true; return -1; } diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 456ee6e62dfa..ad036b00427d 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -363,7 +363,10 @@ static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg, struct fw_head *head = rtnl_dereference(tp->root); int h; - if (head == NULL || arg->stop) + if (head == NULL) + arg->stop = 1; + + if (arg->stop) return; for (h = 0; h < HTSIZE; h++) { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 38e5add14fab..7bcee8b8f803 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -559,7 +559,7 @@ struct Qdisc_ops noop_qdisc_ops __read_mostly = { }; static struct netdev_queue noop_netdev_queue = { - .qdisc = &noop_qdisc, + RCU_POINTER_INITIALIZER(qdisc, &noop_qdisc), .qdisc_sleeping = &noop_qdisc, }; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 75046ec72144..cc9d8133afcd 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -447,6 +447,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, int nb = 0; int count = 1; int rc = NET_XMIT_SUCCESS; + int rc_drop = NET_XMIT_DROP; /* Do not fool qdisc_drop_all() */ skb->prev = NULL; @@ -486,6 +487,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, q->duplicate = 0; rootq->enqueue(skb2, rootq, to_free); q->duplicate = dupsave; + rc_drop = NET_XMIT_SUCCESS; } /* @@ -498,7 +500,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (skb_is_gso(skb)) { segs = netem_segment(skb, sch, to_free); if (!segs) - return NET_XMIT_DROP; + return rc_drop; } else { segs = skb; } @@ -521,8 +523,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, 1<<(prandom_u32() % 8); } - if (unlikely(sch->q.qlen >= sch->limit)) - return qdisc_drop_all(skb, sch, to_free); + if (unlikely(sch->q.qlen >= sch->limit)) { + qdisc_drop_all(skb, sch, to_free); + return rc_drop; + } qdisc_qstats_backlog_inc(sch, skb); diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index f8314a14a256..1cc0c7b74aa3 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -17,7 +17,7 @@ * University of Oslo, Norway. * * References: - * RFC 8033: https://tools.ietf.org/html/rfc8034 + * RFC 8033: https://tools.ietf.org/html/rfc8033 */ #include <linux/module.h> @@ -429,7 +429,8 @@ static void calculate_probability(struct Qdisc *sch) */ if (qdelay == 0 && qdelay_old == 0 && update_prob) - q->vars.prob = (q->vars.prob * 98) / 100; + /* Reduce drop probability to 98.4% */ + q->vars.prob -= q->vars.prob / 64u; q->vars.qdelay = qdelay; q->vars.qlen_old = qlen; diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 64bef313d436..5cb7c1ff97e9 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -192,7 +192,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, if (unlikely(!max_data)) { max_data = sctp_min_frag_point(sctp_sk(asoc->base.sk), sctp_datachk_len(&asoc->stream)); - pr_warn_ratelimited("%s: asoc:%p frag_point is zero, forcing max_data to default minimum (%Zu)", + pr_warn_ratelimited("%s: asoc:%p frag_point is zero, forcing max_data to default minimum (%zu)", __func__, asoc, max_data); } diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 25dfbe343e26..8d2f6296279c 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -754,9 +754,47 @@ static int smc_pnet_find_ndev_pnetid_by_table(struct net_device *ndev, return rc; } +/* if handshake network device belongs to a roce device, return its + * IB device and port + */ +static void smc_pnet_find_rdma_dev(struct net_device *netdev, + struct smc_ib_device **smcibdev, + u8 *ibport, unsigned short vlan_id, u8 gid[]) +{ + struct smc_ib_device *ibdev; + + spin_lock(&smc_ib_devices.lock); + list_for_each_entry(ibdev, &smc_ib_devices.list, list) { + struct net_device *ndev; + int i; + + for (i = 1; i <= SMC_MAX_PORTS; i++) { + if (!rdma_is_port_valid(ibdev->ibdev, i)) + continue; + if (!ibdev->ibdev->ops.get_netdev) + continue; + ndev = ibdev->ibdev->ops.get_netdev(ibdev->ibdev, i); + if (!ndev) + continue; + dev_put(ndev); + if (netdev == ndev && + smc_ib_port_active(ibdev, i) && + !smc_ib_determine_gid(ibdev, i, vlan_id, gid, + NULL)) { + *smcibdev = ibdev; + *ibport = i; + break; + } + } + } + spin_unlock(&smc_ib_devices.lock); +} + /* Determine the corresponding IB device port based on the hardware PNETID. * Searching stops at the first matching active IB device port with vlan_id * configured. + * If nothing found, check pnetid table. + * If nothing found, try to use handshake device */ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev, struct smc_ib_device **smcibdev, @@ -770,8 +808,10 @@ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev, ndev = pnet_find_base_ndev(ndev); if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port, ndev_pnetid) && - smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) + smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) { + smc_pnet_find_rdma_dev(ndev, smcibdev, ibport, vlan_id, gid); return; /* pnetid could not be determined */ + } spin_lock(&smc_ib_devices.lock); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { diff --git a/net/socket.c b/net/socket.c index 643a1648fcc2..3c176a12fe48 100644 --- a/net/socket.c +++ b/net/socket.c @@ -577,6 +577,7 @@ static void __sock_release(struct socket *sock, struct inode *inode) if (inode) inode_lock(inode); sock->ops->release(sock); + sock->sk = NULL; if (inode) inode_unlock(inode); sock->ops = NULL; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 362413c9b389..90ba4a1f0a6d 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -23,78 +23,6 @@ #include <linux/rtnetlink.h> #include <net/switchdev.h> -/** - * switchdev_trans_item_enqueue - Enqueue data item to transaction queue - * - * @trans: transaction - * @data: pointer to data being queued - * @destructor: data destructor - * @tritem: transaction item being queued - * - * Enqeueue data item to transaction queue. tritem is typically placed in - * cointainter pointed at by data pointer. Destructor is called on - * transaction abort and after successful commit phase in case - * the caller did not dequeue the item before. - */ -void switchdev_trans_item_enqueue(struct switchdev_trans *trans, - void *data, void (*destructor)(void const *), - struct switchdev_trans_item *tritem) -{ - tritem->data = data; - tritem->destructor = destructor; - list_add_tail(&tritem->list, &trans->item_list); -} -EXPORT_SYMBOL_GPL(switchdev_trans_item_enqueue); - -static struct switchdev_trans_item * -__switchdev_trans_item_dequeue(struct switchdev_trans *trans) -{ - struct switchdev_trans_item *tritem; - - if (list_empty(&trans->item_list)) - return NULL; - tritem = list_first_entry(&trans->item_list, - struct switchdev_trans_item, list); - list_del(&tritem->list); - return tritem; -} - -/** - * switchdev_trans_item_dequeue - Dequeue data item from transaction queue - * - * @trans: transaction - */ -void *switchdev_trans_item_dequeue(struct switchdev_trans *trans) -{ - struct switchdev_trans_item *tritem; - - tritem = __switchdev_trans_item_dequeue(trans); - BUG_ON(!tritem); - return tritem->data; -} -EXPORT_SYMBOL_GPL(switchdev_trans_item_dequeue); - -static void switchdev_trans_init(struct switchdev_trans *trans) -{ - INIT_LIST_HEAD(&trans->item_list); -} - -static void switchdev_trans_items_destroy(struct switchdev_trans *trans) -{ - struct switchdev_trans_item *tritem; - - while ((tritem = __switchdev_trans_item_dequeue(trans))) - tritem->destructor(tritem->data); -} - -static void switchdev_trans_items_warn_destroy(struct net_device *dev, - struct switchdev_trans *trans) -{ - WARN(!list_empty(&trans->item_list), "%s: transaction item queue is not empty.\n", - dev->name); - switchdev_trans_items_destroy(trans); -} - static LIST_HEAD(deferred); static DEFINE_SPINLOCK(deferred_lock); @@ -174,39 +102,32 @@ static int switchdev_deferred_enqueue(struct net_device *dev, return 0; } -static int __switchdev_port_attr_set(struct net_device *dev, - const struct switchdev_attr *attr, - struct switchdev_trans *trans) +static int switchdev_port_attr_notify(enum switchdev_notifier_type nt, + struct net_device *dev, + const struct switchdev_attr *attr, + struct switchdev_trans *trans) { - const struct switchdev_ops *ops = dev->switchdev_ops; - struct net_device *lower_dev; - struct list_head *iter; - int err = -EOPNOTSUPP; - - if (ops && ops->switchdev_port_attr_set) { - err = ops->switchdev_port_attr_set(dev, attr, trans); - goto done; - } - - if (attr->flags & SWITCHDEV_F_NO_RECURSE) - goto done; + int err; + int rc; - /* Switch device port(s) may be stacked under - * bond/team/vlan dev, so recurse down to set attr on - * each port. - */ + struct switchdev_notifier_port_attr_info attr_info = { + .attr = attr, + .trans = trans, + .handled = false, + }; - netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = __switchdev_port_attr_set(lower_dev, attr, trans); - if (err) - break; + rc = call_switchdev_blocking_notifiers(nt, dev, + &attr_info.info, NULL); + err = notifier_to_errno(rc); + if (err) { + WARN_ON(!attr_info.handled); + return err; } -done: - if (err == -EOPNOTSUPP && attr->flags & SWITCHDEV_F_SKIP_EOPNOTSUPP) - err = 0; + if (!attr_info.handled) + return -EOPNOTSUPP; - return err; + return 0; } static int switchdev_port_attr_set_now(struct net_device *dev, @@ -215,8 +136,6 @@ static int switchdev_port_attr_set_now(struct net_device *dev, struct switchdev_trans trans; int err; - switchdev_trans_init(&trans); - /* Phase I: prepare for attr set. Driver/device should fail * here if there are going to be issues in the commit phase, * such as lack of resources or support. The driver/device @@ -225,18 +144,10 @@ static int switchdev_port_attr_set_now(struct net_device *dev, */ trans.ph_prepare = true; - err = __switchdev_port_attr_set(dev, attr, &trans); - if (err) { - /* Prepare phase failed: abort the transaction. Any - * resources reserved in the prepare phase are - * released. - */ - - if (err != -EOPNOTSUPP) - switchdev_trans_items_destroy(&trans); - + err = switchdev_port_attr_notify(SWITCHDEV_PORT_ATTR_SET, dev, attr, + &trans); + if (err) return err; - } /* Phase II: commit attr set. This cannot fail as a fault * of driver/device. If it does, it's a bug in the driver/device @@ -244,10 +155,10 @@ static int switchdev_port_attr_set_now(struct net_device *dev, */ trans.ph_prepare = false; - err = __switchdev_port_attr_set(dev, attr, &trans); + err = switchdev_port_attr_notify(SWITCHDEV_PORT_ATTR_SET, dev, attr, + &trans); WARN(err, "%s: Commit of attribute (id=%d) failed.\n", dev->name, attr->id); - switchdev_trans_items_warn_destroy(dev, &trans); return err; } @@ -346,8 +257,6 @@ static int switchdev_port_obj_add_now(struct net_device *dev, ASSERT_RTNL(); - switchdev_trans_init(&trans); - /* Phase I: prepare for obj add. Driver/device should fail * here if there are going to be issues in the commit phase, * such as lack of resources or support. The driver/device @@ -358,17 +267,8 @@ static int switchdev_port_obj_add_now(struct net_device *dev, trans.ph_prepare = true; err = switchdev_port_obj_notify(SWITCHDEV_PORT_OBJ_ADD, dev, obj, &trans, extack); - if (err) { - /* Prepare phase failed: abort the transaction. Any - * resources reserved in the prepare phase are - * released. - */ - - if (err != -EOPNOTSUPP) - switchdev_trans_items_destroy(&trans); - + if (err) return err; - } /* Phase II: commit obj add. This cannot fail as a fault * of driver/device. If it does, it's a bug in the driver/device @@ -379,7 +279,6 @@ static int switchdev_port_obj_add_now(struct net_device *dev, err = switchdev_port_obj_notify(SWITCHDEV_PORT_OBJ_ADD, dev, obj, &trans, extack); WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, obj->id); - switchdev_trans_items_warn_destroy(dev, &trans); return err; } @@ -655,3 +554,54 @@ int switchdev_handle_port_obj_del(struct net_device *dev, return err; } EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_del); + +static int __switchdev_handle_port_attr_set(struct net_device *dev, + struct switchdev_notifier_port_attr_info *port_attr_info, + bool (*check_cb)(const struct net_device *dev), + int (*set_cb)(struct net_device *dev, + const struct switchdev_attr *attr, + struct switchdev_trans *trans)) +{ + struct net_device *lower_dev; + struct list_head *iter; + int err = -EOPNOTSUPP; + + if (check_cb(dev)) { + port_attr_info->handled = true; + return set_cb(dev, port_attr_info->attr, + port_attr_info->trans); + } + + /* Switch ports might be stacked under e.g. a LAG. Ignore the + * unsupported devices, another driver might be able to handle them. But + * propagate to the callers any hard errors. + * + * If the driver does its own bookkeeping of stacked ports, it's not + * necessary to go through this helper. + */ + netdev_for_each_lower_dev(dev, lower_dev, iter) { + err = __switchdev_handle_port_attr_set(lower_dev, port_attr_info, + check_cb, set_cb); + if (err && err != -EOPNOTSUPP) + return err; + } + + return err; +} + +int switchdev_handle_port_attr_set(struct net_device *dev, + struct switchdev_notifier_port_attr_info *port_attr_info, + bool (*check_cb)(const struct net_device *dev), + int (*set_cb)(struct net_device *dev, + const struct switchdev_attr *attr, + struct switchdev_trans *trans)) +{ + int err; + + err = __switchdev_handle_port_attr_set(dev, port_attr_info, check_cb, + set_cb); + if (err == -EOPNOTSUPP) + err = 0; + return err; +} +EXPORT_SYMBOL_GPL(switchdev_handle_port_attr_set); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 8c81db337431..e482b342bfa8 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -379,11 +379,13 @@ static int tipc_sk_sock_err(struct socket *sock, long *timeout) #define tipc_wait_for_cond(sock_, timeo_, condition_) \ ({ \ + DEFINE_WAIT_FUNC(wait_, woken_wake_function); \ struct sock *sk_; \ int rc_; \ \ while ((rc_ = !(condition_))) { \ - DEFINE_WAIT_FUNC(wait_, woken_wake_function); \ + /* coupled with smp_wmb() in tipc_sk_proto_rcv() */ \ + smp_rmb(); \ sk_ = (sock_)->sk; \ rc_ = tipc_sk_sock_err((sock_), timeo_); \ if (rc_) \ @@ -1983,6 +1985,8 @@ static void tipc_sk_proto_rcv(struct sock *sk, return; case SOCK_WAKEUP: tipc_dest_del(&tsk->cong_links, msg_orignode(hdr), 0); + /* coupled with smp_rmb() in tipc_wait_for_cond() */ + smp_wmb(); tsk->cong_link_cnt--; wakeup = true; break; |