diff options
Diffstat (limited to 'net')
51 files changed, 377 insertions, 174 deletions
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 7d1e79f69cd1..7a879290dd28 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -339,7 +339,8 @@ static int hci_enhanced_setup_sync(struct hci_dev *hdev, void *data) case BT_CODEC_TRANSPARENT: if (!find_next_esco_param(conn, esco_param_msbc, ARRAY_SIZE(esco_param_msbc))) - return false; + return -EINVAL; + param = &esco_param_msbc[conn->attempt - 1]; cp.tx_coding_format.id = 0x03; cp.rx_coding_format.id = 0x03; @@ -830,7 +831,17 @@ static void bis_cleanup(struct hci_conn *conn) /* Check if ISO connection is a BIS and terminate advertising * set and BIG if there are no other connections using it. */ - bis = hci_conn_hash_lookup_big(hdev, conn->iso_qos.bcast.big); + bis = hci_conn_hash_lookup_big_state(hdev, + conn->iso_qos.bcast.big, + BT_CONNECTED, + HCI_ROLE_MASTER); + if (bis) + return; + + bis = hci_conn_hash_lookup_big_state(hdev, + conn->iso_qos.bcast.big, + BT_CONNECT, + HCI_ROLE_MASTER); if (bis) return; @@ -2249,7 +2260,7 @@ struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, * the start periodic advertising and create BIG commands have * been queued */ - hci_conn_hash_list_state(hdev, bis_mark_per_adv, PA_LINK, + hci_conn_hash_list_state(hdev, bis_mark_per_adv, BIS_LINK, BT_BOUND, &data); /* Queue start periodic advertising and create BIG */ diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 8aa5039b975a..fe7cdd67ad2a 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -6745,8 +6745,8 @@ static void hci_le_cis_established_evt(struct hci_dev *hdev, void *data, qos->ucast.out.latency = DIV_ROUND_CLOSEST(get_unaligned_le24(ev->p_latency), 1000); - qos->ucast.in.sdu = le16_to_cpu(ev->c_mtu); - qos->ucast.out.sdu = le16_to_cpu(ev->p_mtu); + qos->ucast.in.sdu = ev->c_bn ? le16_to_cpu(ev->c_mtu) : 0; + qos->ucast.out.sdu = ev->p_bn ? le16_to_cpu(ev->p_mtu) : 0; qos->ucast.in.phy = ev->c_phy; qos->ucast.out.phy = ev->p_phy; break; @@ -6760,8 +6760,8 @@ static void hci_le_cis_established_evt(struct hci_dev *hdev, void *data, qos->ucast.in.latency = DIV_ROUND_CLOSEST(get_unaligned_le24(ev->p_latency), 1000); - qos->ucast.out.sdu = le16_to_cpu(ev->c_mtu); - qos->ucast.in.sdu = le16_to_cpu(ev->p_mtu); + qos->ucast.out.sdu = ev->c_bn ? le16_to_cpu(ev->c_mtu) : 0; + qos->ucast.in.sdu = ev->p_bn ? le16_to_cpu(ev->p_mtu) : 0; qos->ucast.out.phy = ev->c_phy; qos->ucast.in.phy = ev->p_phy; break; @@ -6957,9 +6957,14 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, continue; } - if (ev->status != 0x42) + if (ev->status != 0x42) { /* Mark PA sync as established */ set_bit(HCI_CONN_PA_SYNC, &bis->flags); + /* Reset cleanup callback of PA Sync so it doesn't + * terminate the sync when deleting the connection. + */ + conn->cleanup = NULL; + } bis->sync_handle = conn->sync_handle; bis->iso_qos.bcast.big = ev->handle; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 2b4f21fbf9c1..31d72b9683ef 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -3344,7 +3344,7 @@ static int hci_powered_update_adv_sync(struct hci_dev *hdev) * advertising data. This also applies to the case * where BR/EDR was toggled during the AUTO_OFF phase. */ - if (hci_dev_test_flag(hdev, HCI_ADVERTISING) || + if (hci_dev_test_flag(hdev, HCI_ADVERTISING) && list_empty(&hdev->adv_instances)) { if (ext_adv_capable(hdev)) { err = hci_setup_ext_adv_instance_sync(hdev, 0x00); @@ -4531,14 +4531,14 @@ static int hci_le_set_host_feature_sync(struct hci_dev *hdev) { struct hci_cp_le_set_host_feature cp; - if (!cis_capable(hdev)) + if (!iso_capable(hdev)) return 0; memset(&cp, 0, sizeof(cp)); /* Connected Isochronous Channels (Host Support) */ cp.bit_number = 32; - cp.bit_value = 1; + cp.bit_value = iso_enabled(hdev) ? 0x01 : 0x00; return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_HOST_FEATURE, sizeof(cp), &cp, HCI_CMD_TIMEOUT); @@ -6985,8 +6985,6 @@ static void create_pa_complete(struct hci_dev *hdev, void *data, int err) hci_dev_lock(hdev); - hci_dev_clear_flag(hdev, HCI_PA_SYNC); - if (!hci_conn_valid(hdev, conn)) clear_bit(HCI_CONN_CREATE_PA_SYNC, &conn->flags); @@ -7047,10 +7045,13 @@ static int hci_le_pa_create_sync(struct hci_dev *hdev, void *data) /* SID has not been set listen for HCI_EV_LE_EXT_ADV_REPORT to update * it. */ - if (conn->sid == HCI_SID_INVALID) - __hci_cmd_sync_status_sk(hdev, HCI_OP_NOP, 0, NULL, - HCI_EV_LE_EXT_ADV_REPORT, - conn->conn_timeout, NULL); + if (conn->sid == HCI_SID_INVALID) { + err = __hci_cmd_sync_status_sk(hdev, HCI_OP_NOP, 0, NULL, + HCI_EV_LE_EXT_ADV_REPORT, + conn->conn_timeout, NULL); + if (err == -ETIMEDOUT) + goto done; + } memset(&cp, 0, sizeof(cp)); cp.options = qos->bcast.options; @@ -7080,6 +7081,12 @@ static int hci_le_pa_create_sync(struct hci_dev *hdev, void *data) __hci_cmd_sync_status(hdev, HCI_OP_LE_PA_CREATE_SYNC_CANCEL, 0, NULL, HCI_CMD_TIMEOUT); +done: + hci_dev_clear_flag(hdev, HCI_PA_SYNC); + + /* Update passive scan since HCI_PA_SYNC flag has been cleared */ + hci_update_passive_scan_sync(hdev); + return err; } diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 7bd3aa0a6db9..5ce823ca3aaf 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -1347,7 +1347,7 @@ static int iso_sock_getname(struct socket *sock, struct sockaddr *addr, bacpy(&sa->iso_bdaddr, &iso_pi(sk)->dst); sa->iso_bdaddr_type = iso_pi(sk)->dst_type; - if (hcon && hcon->type == BIS_LINK) { + if (hcon && (hcon->type == BIS_LINK || hcon->type == PA_LINK)) { sa->iso_bc->bc_sid = iso_pi(sk)->bc_sid; sa->iso_bc->bc_num_bis = iso_pi(sk)->bc_num_bis; memcpy(sa->iso_bc->bc_bis, iso_pi(sk)->bc_bis, @@ -2483,11 +2483,11 @@ static const struct net_proto_family iso_sock_family_ops = { .create = iso_sock_create, }; -static bool iso_inited; +static bool inited; -bool iso_enabled(void) +bool iso_inited(void) { - return iso_inited; + return inited; } int iso_init(void) @@ -2496,7 +2496,7 @@ int iso_init(void) BUILD_BUG_ON(sizeof(struct sockaddr_iso) > sizeof(struct sockaddr)); - if (iso_inited) + if (inited) return -EALREADY; err = proto_register(&iso_proto, 0); @@ -2524,7 +2524,7 @@ int iso_init(void) iso_debugfs = debugfs_create_file("iso", 0444, bt_debugfs, NULL, &iso_debugfs_fops); - iso_inited = true; + inited = true; return 0; @@ -2535,7 +2535,7 @@ error: int iso_exit(void) { - if (!iso_inited) + if (!inited) return -EALREADY; bt_procfs_cleanup(&init_net, "iso"); @@ -2549,7 +2549,7 @@ int iso_exit(void) proto_unregister(&iso_proto); - iso_inited = false; + inited = false; return 0; } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 1ce682038b51..3166f5fb876b 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -922,19 +922,19 @@ static u32 get_current_settings(struct hci_dev *hdev) if (hci_dev_test_flag(hdev, HCI_WIDEBAND_SPEECH_ENABLED)) settings |= MGMT_SETTING_WIDEBAND_SPEECH; - if (cis_central_capable(hdev)) + if (cis_central_enabled(hdev)) settings |= MGMT_SETTING_CIS_CENTRAL; - if (cis_peripheral_capable(hdev)) + if (cis_peripheral_enabled(hdev)) settings |= MGMT_SETTING_CIS_PERIPHERAL; - if (bis_capable(hdev)) + if (bis_enabled(hdev)) settings |= MGMT_SETTING_ISO_BROADCASTER; - if (sync_recv_capable(hdev)) + if (sync_recv_enabled(hdev)) settings |= MGMT_SETTING_ISO_SYNC_RECEIVER; - if (ll_privacy_capable(hdev)) + if (ll_privacy_enabled(hdev)) settings |= MGMT_SETTING_LL_PRIVACY; return settings; @@ -4513,7 +4513,7 @@ static int read_exp_features_info(struct sock *sk, struct hci_dev *hdev, } if (IS_ENABLED(CONFIG_BT_LE)) { - flags = iso_enabled() ? BIT(0) : 0; + flags = iso_inited() ? BIT(0) : 0; memcpy(rp->features[idx].uuid, iso_socket_uuid, 16); rp->features[idx].flags = cpu_to_le32(flags); idx++; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 1377f31b719c..8ce145938b02 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -4818,6 +4818,14 @@ void br_multicast_set_query_intvl(struct net_bridge_mcast *brmctx, intvl_jiffies = BR_MULTICAST_QUERY_INTVL_MIN; } + if (intvl_jiffies > BR_MULTICAST_QUERY_INTVL_MAX) { + br_info(brmctx->br, + "trying to set multicast query interval above maximum, setting to %lu (%ums)\n", + jiffies_to_clock_t(BR_MULTICAST_QUERY_INTVL_MAX), + jiffies_to_msecs(BR_MULTICAST_QUERY_INTVL_MAX)); + intvl_jiffies = BR_MULTICAST_QUERY_INTVL_MAX; + } + brmctx->multicast_query_interval = intvl_jiffies; } @@ -4834,6 +4842,14 @@ void br_multicast_set_startup_query_intvl(struct net_bridge_mcast *brmctx, intvl_jiffies = BR_MULTICAST_STARTUP_QUERY_INTVL_MIN; } + if (intvl_jiffies > BR_MULTICAST_STARTUP_QUERY_INTVL_MAX) { + br_info(brmctx->br, + "trying to set multicast startup query interval above maximum, setting to %lu (%ums)\n", + jiffies_to_clock_t(BR_MULTICAST_STARTUP_QUERY_INTVL_MAX), + jiffies_to_msecs(BR_MULTICAST_STARTUP_QUERY_INTVL_MAX)); + intvl_jiffies = BR_MULTICAST_STARTUP_QUERY_INTVL_MAX; + } + brmctx->multicast_startup_query_interval = intvl_jiffies; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index b159aae594c0..8de0904b9627 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -31,6 +31,8 @@ #define BR_MULTICAST_DEFAULT_HASH_MAX 4096 #define BR_MULTICAST_QUERY_INTVL_MIN msecs_to_jiffies(1000) #define BR_MULTICAST_STARTUP_QUERY_INTVL_MIN BR_MULTICAST_QUERY_INTVL_MIN +#define BR_MULTICAST_QUERY_INTVL_MAX msecs_to_jiffies(86400000) /* 24 hours */ +#define BR_MULTICAST_STARTUP_QUERY_INTVL_MAX BR_MULTICAST_QUERY_INTVL_MAX #define BR_HWDOM_MAX BITS_PER_LONG diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig index 60f28e4fb5c0..4fd5a6ea26b4 100644 --- a/net/bridge/netfilter/Kconfig +++ b/net/bridge/netfilter/Kconfig @@ -43,6 +43,7 @@ config NF_CONNTRACK_BRIDGE config BRIDGE_NF_EBTABLES_LEGACY tristate "Legacy EBTABLES support" depends on BRIDGE && NETFILTER_XTABLES_LEGACY + depends on NETFILTER_XTABLES default n help Legacy ebtables packet/frame classifier. diff --git a/net/core/dev.c b/net/core/dev.c index 68dc47d7e700..93a25d87b86b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3779,6 +3779,18 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb, features &= ~NETIF_F_TSO_MANGLEID; } + /* NETIF_F_IPV6_CSUM does not support IPv6 extension headers, + * so neither does TSO that depends on it. + */ + if (features & NETIF_F_IPV6_CSUM && + (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6 || + (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && + vlan_get_protocol(skb) == htons(ETH_P_IPV6))) && + skb_transport_header_was_set(skb) && + skb_network_header_len(skb) != sizeof(struct ipv6hdr) && + !ipv6_has_hopopt_jumbo(skb)) + features &= ~(NETIF_F_IPV6_CSUM | NETIF_F_TSO6 | NETIF_F_GSO_UDP_L4); + return features; } @@ -6999,7 +7011,7 @@ int netif_set_threaded(struct net_device *dev, enum netdev_napi_threaded threaded) { struct napi_struct *napi; - int err = 0; + int i, err = 0; netdev_assert_locked_or_invisible(dev); @@ -7021,6 +7033,10 @@ int netif_set_threaded(struct net_device *dev, list_for_each_entry(napi, &dev->napi_list, dev_list) WARN_ON_ONCE(napi_set_threaded(napi, threaded)); + /* Override the config for all NAPIs even if currently not listed */ + for (i = 0; i < dev->num_napi_configs; i++) + dev->napi_config[i].threaded = threaded; + return err; } @@ -7353,8 +7369,9 @@ void netif_napi_add_weight_locked(struct net_device *dev, * Clear dev->threaded if kthread creation failed so that * threaded mode will not be enabled in napi_enable(). */ - if (dev->threaded && napi_kthread_create(napi)) - dev->threaded = NETDEV_NAPI_THREADED_DISABLED; + if (napi_get_threaded_config(dev, napi)) + if (napi_kthread_create(napi)) + dev->threaded = NETDEV_NAPI_THREADED_DISABLED; netif_napi_set_irq_locked(napi, -1); } EXPORT_SYMBOL(netif_napi_add_weight_locked); @@ -11873,6 +11890,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, goto free_all; dev->cfg_pending = dev->cfg; + dev->num_napi_configs = maxqs; napi_config_sz = array_size(maxqs, sizeof(*dev->napi_config)); dev->napi_config = kvzalloc(napi_config_sz, GFP_KERNEL_ACCOUNT); if (!dev->napi_config) diff --git a/net/core/dev.h b/net/core/dev.h index ab69edc0c3e3..d6b08d435479 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -323,6 +323,14 @@ static inline enum netdev_napi_threaded napi_get_threaded(struct napi_struct *n) return NETDEV_NAPI_THREADED_DISABLED; } +static inline enum netdev_napi_threaded +napi_get_threaded_config(struct net_device *dev, struct napi_struct *n) +{ + if (n->config) + return n->config->threaded; + return dev->threaded; +} + int napi_set_threaded(struct napi_struct *n, enum netdev_napi_threaded threaded); diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 05e2e22a8f7c..343a6cac21e3 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -1201,6 +1201,35 @@ void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), pool->xdp_mem_id = mem->id; } +/** + * page_pool_enable_direct_recycling() - mark page pool as owned by NAPI + * @pool: page pool to modify + * @napi: NAPI instance to associate the page pool with + * + * Associate a page pool with a NAPI instance for lockless page recycling. + * This is useful when a new page pool has to be added to a NAPI instance + * without disabling that NAPI instance, to mark the point at which control + * path "hands over" the page pool to the NAPI instance. In most cases driver + * can simply set the @napi field in struct page_pool_params, and does not + * have to call this helper. + * + * The function is idempotent, but does not implement any refcounting. + * Single page_pool_disable_direct_recycling() will disable recycling, + * no matter how many times enable was called. + */ +void page_pool_enable_direct_recycling(struct page_pool *pool, + struct napi_struct *napi) +{ + if (READ_ONCE(pool->p.napi) == napi) + return; + WARN_ON(!napi || pool->p.napi); + + mutex_lock(&page_pools_lock); + WRITE_ONCE(pool->p.napi, napi); + mutex_unlock(&page_pools_lock); +} +EXPORT_SYMBOL(page_pool_enable_direct_recycling); + void page_pool_disable_direct_recycling(struct page_pool *pool) { /* Disable direct recycling based on pool->cpuid. diff --git a/net/devlink/port.c b/net/devlink/port.c index 939081a0e615..cb8d4df61619 100644 --- a/net/devlink/port.c +++ b/net/devlink/port.c @@ -1519,7 +1519,7 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, struct devlink_port_attrs *attrs = &devlink_port->attrs; int n = 0; - if (!devlink_port->attrs_set) + if (!devlink_port->attrs_set || devlink_port->attrs.no_phys_port_name) return -EOPNOTSUPP; switch (attrs->flavour) { diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index b87b6a6fe070..102eccf5ead7 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -63,8 +63,14 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) skb_push(skb, ETH_HLEN); skb_reset_mac_header(skb); if ((!hsr->prot_version && protocol == htons(ETH_P_PRP)) || - protocol == htons(ETH_P_HSR)) + protocol == htons(ETH_P_HSR)) { + if (!pskb_may_pull(skb, ETH_HLEN + HSR_HLEN)) { + kfree_skb(skb); + goto finish_consume; + } + skb_set_network_header(skb, ETH_HLEN + HSR_HLEN); + } skb_reset_mac_len(skb); /* Only the frames received over the interlink port will assign a diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 2c438b140e88..7dc9772fe2d8 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -14,6 +14,7 @@ config NF_DEFRAG_IPV4 config IP_NF_IPTABLES_LEGACY tristate "Legacy IP tables support" depends on NETFILTER_XTABLES_LEGACY + depends on NETFILTER_XTABLES default m if NETFILTER_XTABLES_LEGACY help iptables is a legacy packet classifier. @@ -326,6 +327,7 @@ endif # IP_NF_IPTABLES config IP_NF_ARPTABLES tristate "Legacy ARPTABLES support" depends on NETFILTER_XTABLES_LEGACY + depends on NETFILTER_XTABLES default n help arptables is a legacy packet classifier. @@ -343,6 +345,7 @@ config IP_NF_ARPFILTER select IP_NF_ARPTABLES select NETFILTER_FAMILY_ARP depends on NETFILTER_XTABLES_LEGACY + depends on NETFILTER_XTABLES help ARP packet filtering defines a table `filter', which has a series of rules for simple ARP packet filtering at local input and diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 87fd945a0d27..0d3cb2ba6fc8 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -247,8 +247,7 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb, if (!oth) return; - if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) && - nf_reject_fill_skb_dst(oldskb) < 0) + if (!skb_dst(oldskb) && nf_reject_fill_skb_dst(oldskb) < 0) return; if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) @@ -321,8 +320,7 @@ void nf_send_unreach(struct sk_buff *skb_in, int code, int hook) if (iph->frag_off & htons(IP_OFFSET)) return; - if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) && - nf_reject_fill_skb_dst(skb_in) < 0) + if (!skb_dst(skb_in) && nf_reject_fill_skb_dst(skb_in) < 0) return; if (skb_csum_unnecessary(skb_in) || diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 5128e2a5b00a..b1f3fd302e9d 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -217,7 +217,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, remcsum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TUNNEL_REMCSUM); skb->remcsum_offload = remcsum; - need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb)); + need_ipsec = (skb_dst(skb) && dst_xfrm(skb_dst(skb))) || skb_sec_path(skb); /* Try to offload checksum if possible */ offload_csum = !!(need_csum && !need_ipsec && diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 276860f65baa..81daf82ddc2d 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -10,6 +10,7 @@ menu "IPv6: Netfilter Configuration" config IP6_NF_IPTABLES_LEGACY tristate "Legacy IP6 tables support" depends on INET && IPV6 && NETFILTER_XTABLES_LEGACY + depends on NETFILTER_XTABLES default m if NETFILTER_XTABLES_LEGACY help ip6tables is a legacy packet classifier. diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index 838295fa32e3..cb2d38e80de9 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -293,7 +293,7 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, fl6.fl6_sport = otcph->dest; fl6.fl6_dport = otcph->source; - if (hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) { + if (!skb_dst(oldskb)) { nf_ip6_route(net, &dst, flowi6_to_flowi(&fl6), false); if (!dst) return; @@ -397,8 +397,7 @@ void nf_send_unreach6(struct net *net, struct sk_buff *skb_in, if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL) skb_in->dev = net->loopback_dev; - if ((hooknum == NF_INET_PRE_ROUTING || hooknum == NF_INET_INGRESS) && - nf_reject6_fill_skb_dst(skb_in) < 0) + if (!skb_dst(skb_in) && nf_reject6_fill_skb_dst(skb_in) < 0) return; icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0); diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c index f78ecb6ad838..fd58426f222b 100644 --- a/net/ipv6/seg6_hmac.c +++ b/net/ipv6/seg6_hmac.c @@ -35,6 +35,7 @@ #include <net/xfrm.h> #include <crypto/hash.h> +#include <crypto/utils.h> #include <net/seg6.h> #include <net/genetlink.h> #include <net/seg6_hmac.h> @@ -280,7 +281,7 @@ bool seg6_hmac_validate_skb(struct sk_buff *skb) if (seg6_hmac_compute(hinfo, srh, &ipv6_hdr(skb)->saddr, hmac_output)) return false; - if (memcmp(hmac_output, tlv->hmac, SEG6_HMAC_FIELD_LEN) != 0) + if (crypto_memneq(hmac_output, tlv->hmac, SEG6_HMAC_FIELD_LEN)) return false; return true; @@ -304,6 +305,9 @@ int seg6_hmac_info_add(struct net *net, u32 key, struct seg6_hmac_info *hinfo) struct seg6_pernet_data *sdata = seg6_pernet(net); int err; + if (!__hmac_get_algo(hinfo->alg_id)) + return -EINVAL; + err = rhashtable_lookup_insert_fast(&sdata->hmac_infos, &hinfo->node, rht_params); diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 5120a763da0d..0a0eeaed0591 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -334,7 +334,7 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net) struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); unsigned int i; - xfrm_state_flush(net, IPSEC_PROTO_ANY, false); + xfrm_state_flush(net, 0, false); xfrm_flush_gc(); for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index a4971e6fa943..b4f01cb07561 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -430,7 +430,7 @@ static void psock_write_space(struct sock *sk) /* Check if the socket is reserved so someone is waiting for sending. */ kcm = psock->tx_kcm; - if (kcm && !unlikely(kcm->tx_stopped)) + if (kcm) queue_work(kcm_wq, &kcm->tx_work); spin_unlock_bh(&mux->lock); @@ -1693,12 +1693,6 @@ static int kcm_release(struct socket *sock) */ __skb_queue_purge(&sk->sk_write_queue); - /* Set tx_stopped. This is checked when psock is bound to a kcm and we - * get a writespace callback. This prevents further work being queued - * from the callback (unbinding the psock occurs after canceling work. - */ - kcm->tx_stopped = 1; - release_sock(sk); spin_lock_bh(&mux->lock); @@ -1714,7 +1708,7 @@ static int kcm_release(struct socket *sock) /* Cancel work. After this point there should be no outside references * to the kcm socket. */ - cancel_work_sync(&kcm->tx_work); + disable_work_sync(&kcm->tx_work); lock_sock(sk); psock = kcm->tx_psock; diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c index fb6b46a952cb..69a3ccfc6310 100644 --- a/net/mctp/test/route-test.c +++ b/net/mctp/test/route-test.c @@ -1586,7 +1586,6 @@ static void mctp_test_bind_lookup(struct kunit *test) cleanup: kfree_skb(skb_sock); - kfree_skb(skb_pkt); /* Drop all binds */ for (size_t i = 0; i < ARRAY_SIZE(lookup_binds); i++) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 70c0ab0ecf90..2a8ea28442b2 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1118,7 +1118,9 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk, return hmac == mp_opt->ahmac; } -/* Return false if a subflow has been reset, else return true */ +/* Return false in case of error (or subflow has been reset), + * else return true. + */ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); @@ -1222,7 +1224,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) mpext = skb_ext_add(skb, SKB_EXT_MPTCP); if (!mpext) - return true; + return false; memset(mpext, 0, sizeof(*mpext)); diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 420d416e2603..136a380602ca 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -274,6 +274,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer) add_timer); struct mptcp_sock *msk = entry->sock; struct sock *sk = (struct sock *)msk; + unsigned int timeout; pr_debug("msk=%p\n", msk); @@ -291,6 +292,10 @@ static void mptcp_pm_add_timer(struct timer_list *timer) goto out; } + timeout = mptcp_get_add_addr_timeout(sock_net(sk)); + if (!timeout) + goto out; + spin_lock_bh(&msk->pm.lock); if (!mptcp_pm_should_add_signal_addr(msk)) { @@ -302,7 +307,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer) if (entry->retrans_times < ADD_ADDR_RETRANS_MAX) sk_reset_timer(sk, timer, - jiffies + mptcp_get_add_addr_timeout(sock_net(sk))); + jiffies + timeout); spin_unlock_bh(&msk->pm.lock); @@ -344,6 +349,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, struct mptcp_pm_add_entry *add_entry = NULL; struct sock *sk = (struct sock *)msk; struct net *net = sock_net(sk); + unsigned int timeout; lockdep_assert_held(&msk->pm.lock); @@ -353,9 +359,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, if (WARN_ON_ONCE(mptcp_pm_is_kernel(msk))) return false; - sk_reset_timer(sk, &add_entry->add_timer, - jiffies + mptcp_get_add_addr_timeout(net)); - return true; + goto reset_timer; } add_entry = kmalloc(sizeof(*add_entry), GFP_ATOMIC); @@ -369,8 +373,10 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, add_entry->retrans_times = 0; timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0); - sk_reset_timer(sk, &add_entry->add_timer, - jiffies + mptcp_get_add_addr_timeout(net)); +reset_timer: + timeout = mptcp_get_add_addr_timeout(net); + if (timeout) + sk_reset_timer(sk, &add_entry->add_timer, jiffies + timeout); return true; } diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c index d39e7c178460..667803d72b64 100644 --- a/net/mptcp/pm_kernel.c +++ b/net/mptcp/pm_kernel.c @@ -1085,7 +1085,6 @@ static void __flush_addrs(struct list_head *list) static void __reset_counters(struct pm_nl_pernet *pernet) { WRITE_ONCE(pernet->add_addr_signal_max, 0); - WRITE_ONCE(pernet->add_addr_accept_max, 0); WRITE_ONCE(pernet->local_addr_max, 0); pernet->addrs = 0; } diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index f821ad2e19b3..15049b826732 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -265,7 +265,8 @@ int ip_vs_est_kthread_start(struct netns_ipvs *ipvs, } set_user_nice(kd->task, sysctl_est_nice(ipvs)); - set_cpus_allowed_ptr(kd->task, sysctl_est_cpulist(ipvs)); + if (sysctl_est_preferred_cpulist(ipvs)) + kthread_affine_preferred(kd->task, sysctl_est_preferred_cpulist(ipvs)); pr_info("starting estimator thread %d...\n", kd->id); wake_up_process(kd->task); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 486d52b45fe5..50fd6809380f 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -884,8 +884,6 @@ errout: static int ctnetlink_done(struct netlink_callback *cb) { - if (cb->args[1]) - nf_ct_put((struct nf_conn *)cb->args[1]); kfree(cb->data); return 0; } @@ -1208,19 +1206,26 @@ ignore_entry: return 0; } +static unsigned long ctnetlink_get_id(const struct nf_conn *ct) +{ + unsigned long id = nf_ct_get_id(ct); + + return id ? id : 1; +} + static int ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { unsigned int flags = cb->data ? NLM_F_DUMP_FILTERED : 0; struct net *net = sock_net(skb->sk); - struct nf_conn *ct, *last; + unsigned long last_id = cb->args[1]; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; struct nf_conn *nf_ct_evict[8]; + struct nf_conn *ct; int res, i; spinlock_t *lockp; - last = (struct nf_conn *)cb->args[1]; i = 0; local_bh_disable(); @@ -1257,7 +1262,7 @@ restart: continue; if (cb->args[1]) { - if (ct != last) + if (ctnetlink_get_id(ct) != last_id) continue; cb->args[1] = 0; } @@ -1270,8 +1275,7 @@ restart: NFNL_MSG_TYPE(cb->nlh->nlmsg_type), ct, true, flags); if (res < 0) { - nf_conntrack_get(&ct->ct_general); - cb->args[1] = (unsigned long)ct; + cb->args[1] = ctnetlink_get_id(ct); spin_unlock(lockp); goto out; } @@ -1284,12 +1288,10 @@ restart: } out: local_bh_enable(); - if (last) { + if (last_id) { /* nf ct hash resize happened, now clear the leftover. */ - if ((struct nf_conn *)cb->args[1] == last) + if (cb->args[1] == last_id) cb->args[1] = 0; - - nf_ct_put(last); } while (i) { @@ -3168,23 +3170,27 @@ errout: return 0; } #endif -static int ctnetlink_exp_done(struct netlink_callback *cb) + +static unsigned long ctnetlink_exp_id(const struct nf_conntrack_expect *exp) { - if (cb->args[1]) - nf_ct_expect_put((struct nf_conntrack_expect *)cb->args[1]); - return 0; + unsigned long id = (unsigned long)exp; + + id += nf_ct_get_id(exp->master); + id += exp->class; + + return id ? id : 1; } static int ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); - struct nf_conntrack_expect *exp, *last; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; + unsigned long last_id = cb->args[1]; + struct nf_conntrack_expect *exp; rcu_read_lock(); - last = (struct nf_conntrack_expect *)cb->args[1]; for (; cb->args[0] < nf_ct_expect_hsize; cb->args[0]++) { restart: hlist_for_each_entry_rcu(exp, &nf_ct_expect_hash[cb->args[0]], @@ -3196,7 +3202,7 @@ restart: continue; if (cb->args[1]) { - if (exp != last) + if (ctnetlink_exp_id(exp) != last_id) continue; cb->args[1] = 0; } @@ -3205,9 +3211,7 @@ restart: cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp) < 0) { - if (!refcount_inc_not_zero(&exp->use)) - continue; - cb->args[1] = (unsigned long)exp; + cb->args[1] = ctnetlink_exp_id(exp); goto out; } } @@ -3218,32 +3222,30 @@ restart: } out: rcu_read_unlock(); - if (last) - nf_ct_expect_put(last); - return skb->len; } static int ctnetlink_exp_ct_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { - struct nf_conntrack_expect *exp, *last; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); struct nf_conn *ct = cb->data; struct nf_conn_help *help = nfct_help(ct); u_int8_t l3proto = nfmsg->nfgen_family; + unsigned long last_id = cb->args[1]; + struct nf_conntrack_expect *exp; if (cb->args[0]) return 0; rcu_read_lock(); - last = (struct nf_conntrack_expect *)cb->args[1]; + restart: hlist_for_each_entry_rcu(exp, &help->expectations, lnode) { if (l3proto && exp->tuple.src.l3num != l3proto) continue; if (cb->args[1]) { - if (exp != last) + if (ctnetlink_exp_id(exp) != last_id) continue; cb->args[1] = 0; } @@ -3251,9 +3253,7 @@ restart: cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp) < 0) { - if (!refcount_inc_not_zero(&exp->use)) - continue; - cb->args[1] = (unsigned long)exp; + cb->args[1] = ctnetlink_exp_id(exp); goto out; } } @@ -3264,9 +3264,6 @@ restart: cb->args[0] = 1; out: rcu_read_unlock(); - if (last) - nf_ct_expect_put(last); - return skb->len; } @@ -3285,7 +3282,6 @@ static int ctnetlink_dump_exp_ct(struct net *net, struct sock *ctnl, struct nf_conntrack_zone zone; struct netlink_dump_control c = { .dump = ctnetlink_exp_ct_dump_table, - .done = ctnetlink_exp_done, }; err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER, @@ -3335,7 +3331,6 @@ static int ctnetlink_get_expect(struct sk_buff *skb, else { struct netlink_dump_control c = { .dump = ctnetlink_exp_dump_table, - .done = ctnetlink_exp_done, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 9b8b10a85233..1f14ef0436c6 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -567,16 +567,16 @@ nf_conntrack_log_invalid_sysctl(const struct ctl_table *table, int write, return ret; if (*(u8 *)table->data == 0) - return ret; + return 0; /* Load nf_log_syslog only if no logger is currently registered */ for (i = 0; i < NFPROTO_NUMPROTO; i++) { if (nf_log_is_registered(i)) - return ret; + return 0; } request_module("%s", "nf_log_syslog"); - return ret; + return 0; } static struct ctl_table_header *nf_ct_netfilter_header; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 13d0ed9d1895..58c5425d61c2 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2803,6 +2803,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, struct nft_chain *chain = ctx->chain; struct nft_chain_hook hook = {}; struct nft_stats __percpu *stats = NULL; + struct nftables_pernet *nft_net; struct nft_hook *h, *next; struct nf_hook_ops *ops; struct nft_trans *trans; @@ -2845,6 +2846,20 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, if (nft_hook_list_find(&basechain->hook_list, h)) { list_del(&h->list); nft_netdev_hook_free(h); + continue; + } + + nft_net = nft_pernet(ctx->net); + list_for_each_entry(trans, &nft_net->commit_list, list) { + if (trans->msg_type != NFT_MSG_NEWCHAIN || + trans->table != ctx->table || + !nft_trans_chain_update(trans)) + continue; + + if (nft_hook_list_find(&nft_trans_chain_hooks(trans), h)) { + nft_chain_release_hook(&hook); + return -EEXIST; + } } } } else { @@ -9060,6 +9075,7 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, { const struct nlattr * const *nla = ctx->nla; struct nft_flowtable_hook flowtable_hook; + struct nftables_pernet *nft_net; struct nft_hook *hook, *next; struct nf_hook_ops *ops; struct nft_trans *trans; @@ -9076,6 +9092,20 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, if (nft_hook_list_find(&flowtable->hook_list, hook)) { list_del(&hook->list); nft_netdev_hook_free(hook); + continue; + } + + nft_net = nft_pernet(ctx->net); + list_for_each_entry(trans, &nft_net->commit_list, list) { + if (trans->msg_type != NFT_MSG_NEWFLOWTABLE || + trans->table != ctx->table || + !nft_trans_flowtable_update(trans)) + continue; + + if (nft_hook_list_find(&nft_trans_flowtable_hooks(trans), hook)) { + err = -EEXIST; + goto err_flowtable_update_hook; + } } } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 1a19649c2851..9a10251228fd 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -426,10 +426,9 @@ static struct nft_pipapo_elem *pipapo_get(const struct nft_pipapo_match *m, local_bh_disable(); - if (unlikely(!raw_cpu_ptr(m->scratch))) - goto out; - scratch = *raw_cpu_ptr(m->scratch); + if (unlikely(!scratch)) + goto out; map_index = scratch->map_index; diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index db5d367e43c4..2f090e253caf 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -1150,12 +1150,12 @@ nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, const u32 *key) { struct nft_pipapo *priv = nft_set_priv(set); + const struct nft_set_ext *ext = NULL; struct nft_pipapo_scratch *scratch; u8 genmask = nft_genmask_cur(net); const struct nft_pipapo_match *m; const struct nft_pipapo_field *f; const u8 *rp = (const u8 *)key; - const struct nft_set_ext *ext; unsigned long *res, *fill; bool map_index; int i; @@ -1246,13 +1246,13 @@ next_match: goto out; if (last) { - ext = &f->mt[ret].e->ext; - if (unlikely(nft_set_elem_expired(ext) || - !nft_set_elem_active(ext, genmask))) { - ext = NULL; + const struct nft_set_ext *e = &f->mt[ret].e->ext; + + if (unlikely(nft_set_elem_expired(e) || + !nft_set_elem_active(e, genmask))) goto next_match; - } + ext = e; goto out; } diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 35d0409b0095..36affbb697c2 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -217,7 +217,7 @@ static int nft_socket_init(const struct nft_ctx *ctx, level += err; /* Implies a giant cgroup tree */ - if (WARN_ON_ONCE(level > 255)) + if (level > 255) return -EOPNOTSUPP; priv->level = level; diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index dbcfb948c867..32bacfc314c2 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1750,7 +1750,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, ktime_t now = ktime_get(); struct cake_tin_data *b; struct cake_flow *flow; - u32 idx; + u32 idx, tin; /* choose flow to insert into */ idx = cake_classify(sch, &b, skb, q->flow_mode, &ret); @@ -1760,6 +1760,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, __qdisc_drop(skb, to_free); return ret; } + tin = (u32)(b - q->tins); idx--; flow = &b->flows[idx]; @@ -1927,13 +1928,22 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, q->buffer_max_used = q->buffer_used; if (q->buffer_used > q->buffer_limit) { + bool same_flow = false; u32 dropped = 0; + u32 drop_id; while (q->buffer_used > q->buffer_limit) { dropped++; - cake_drop(sch, to_free); + drop_id = cake_drop(sch, to_free); + + if ((drop_id >> 16) == tin && + (drop_id & 0xFFFF) == idx) + same_flow = true; } b->drop_overlimit += dropped; + + if (same_flow) + return NET_XMIT_CN; } return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index c93761040c6e..fa0314679e43 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -101,9 +101,9 @@ static const struct nla_policy codel_policy[TCA_CODEL_MAX + 1] = { static int codel_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct codel_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_CODEL_MAX + 1]; - unsigned int qlen, dropped = 0; int err; err = nla_parse_nested_deprecated(tb, TCA_CODEL_MAX, opt, @@ -142,15 +142,17 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt, WRITE_ONCE(q->params.ecn, !!nla_get_u32(tb[TCA_CODEL_ECN])); - qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, true); - dropped += qdisc_pkt_len(skb); - qdisc_qstats_backlog_dec(sch, skb); + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_qdisc_drop(skb, sch); } - qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_dualpi2.c b/net/sched/sch_dualpi2.c index 845375ebd4ea..4b975feb52b1 100644 --- a/net/sched/sch_dualpi2.c +++ b/net/sched/sch_dualpi2.c @@ -927,7 +927,8 @@ static int dualpi2_init(struct Qdisc *sch, struct nlattr *opt, q->sch = sch; dualpi2_reset_default(sch); - hrtimer_setup(&q->pi2_timer, dualpi2_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); + hrtimer_setup(&q->pi2_timer, dualpi2_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_ABS_PINNED_SOFT); if (opt && nla_len(opt)) { err = dualpi2_change(sch, opt, extack); @@ -937,7 +938,7 @@ static int dualpi2_init(struct Qdisc *sch, struct nlattr *opt, } hrtimer_start(&q->pi2_timer, next_pi2_timeout(q), - HRTIMER_MODE_ABS_PINNED); + HRTIMER_MODE_ABS_PINNED_SOFT); return 0; } diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 037f764822b9..82635dd2cfa5 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -651,6 +651,12 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, sch_tree_lock(sch); + for (i = nbands; i < oldbands; i++) { + if (i >= q->nstrict && q->classes[i].qdisc->q.qlen) + list_del_init(&q->classes[i].alist); + qdisc_purge_queue(q->classes[i].qdisc); + } + WRITE_ONCE(q->nbands, nbands); for (i = nstrict; i < q->nstrict; i++) { if (q->classes[i].qdisc->q.qlen) { @@ -658,11 +664,6 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, q->classes[i].deficit = quanta[i]; } } - for (i = q->nbands; i < oldbands; i++) { - if (i >= q->nstrict && q->classes[i].qdisc->q.qlen) - list_del_init(&q->classes[i].alist); - qdisc_purge_queue(q->classes[i].qdisc); - } WRITE_ONCE(q->nstrict, nstrict); memcpy(q->prio2band, priomap, sizeof(priomap)); diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 902ff5470607..fee922da2f99 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -1013,11 +1013,11 @@ static int fq_load_priomap(struct fq_sched_data *q, static int fq_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct fq_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_FQ_MAX + 1]; - int err, drop_count = 0; - unsigned drop_len = 0; u32 fq_log; + int err; err = nla_parse_nested_deprecated(tb, TCA_FQ_MAX, opt, fq_policy, NULL); @@ -1135,16 +1135,18 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, err = fq_resize(sch, fq_log); sch_tree_lock(sch); } + while (sch->q.qlen > sch->limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, false); if (!skb) break; - drop_len += qdisc_pkt_len(skb); + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); - drop_count++; } - qdisc_tree_reduce_backlog(sch, drop_count, drop_len); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return err; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 2a0f3a513bfa..a14142392939 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -366,6 +366,7 @@ static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = { static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct fq_codel_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_FQ_CODEL_MAX + 1]; u32 quantum = 0; @@ -443,13 +444,14 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, q->memory_usage > q->memory_limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, false); - q->cstats.drop_len += qdisc_pkt_len(skb); + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); - q->cstats.drop_count++; } - qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, q->cstats.drop_len); - q->cstats.drop_count = 0; - q->cstats.drop_len = 0; + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index b0e34daf1f75..7b96bc3ff891 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -287,10 +287,9 @@ begin: static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct fq_pie_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_FQ_PIE_MAX + 1]; - unsigned int len_dropped = 0; - unsigned int num_dropped = 0; int err; err = nla_parse_nested(tb, TCA_FQ_PIE_MAX, opt, fq_pie_policy, extack); @@ -368,11 +367,14 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, while (sch->q.qlen > sch->limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, false); - len_dropped += qdisc_pkt_len(skb); - num_dropped += 1; + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); } - qdisc_tree_reduce_backlog(sch, num_dropped, len_dropped); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 5aa434b46707..2d4855e28a28 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -508,9 +508,9 @@ static const struct nla_policy hhf_policy[TCA_HHF_MAX + 1] = { static int hhf_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct hhf_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_HHF_MAX + 1]; - unsigned int qlen, prev_backlog; int err; u64 non_hh_quantum; u32 new_quantum = q->quantum; @@ -561,15 +561,17 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt, usecs_to_jiffies(us)); } - qlen = sch->q.qlen; - prev_backlog = sch->qstats.backlog; while (sch->q.qlen > sch->limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, false); + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); } - qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, - prev_backlog - sch->qstats.backlog); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index c968ea763774..b5e40c51655a 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -592,7 +592,7 @@ htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff) */ static inline void htb_activate(struct htb_sched *q, struct htb_class *cl) { - WARN_ON(cl->level || !cl->leaf.q || !cl->leaf.q->q.qlen); + WARN_ON(cl->level || !cl->leaf.q); if (!cl->prio_activity) { cl->prio_activity = 1 << cl->prio; diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index ad46ee3ed5a9..0a377313b6a9 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -141,9 +141,9 @@ static const struct nla_policy pie_policy[TCA_PIE_MAX + 1] = { static int pie_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct pie_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_PIE_MAX + 1]; - unsigned int qlen, dropped = 0; int err; err = nla_parse_nested_deprecated(tb, TCA_PIE_MAX, opt, pie_policy, @@ -193,15 +193,17 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt, nla_get_u32(tb[TCA_PIE_DQ_RATE_ESTIMATOR])); /* Drop excess packets if new limit is lower */ - qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, true); - dropped += qdisc_pkt_len(skb); - qdisc_qstats_backlog_dec(sch, skb); + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_qdisc_drop(skb, sch); } - qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; diff --git a/net/sctp/input.c b/net/sctp/input.c index 2dc2666988fb..7e99894778d4 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -117,7 +117,7 @@ int sctp_rcv(struct sk_buff *skb) * it's better to just linearize it otherwise crc computing * takes longer. */ - if ((!is_gso && skb_linearize(skb)) || + if (((!is_gso || skb_cloned(skb)) && skb_linearize(skb)) || !pskb_may_pull(skb, sizeof(struct sctphdr))) goto discard_it; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 9311c38f7abe..e0e48f24cd61 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2568,8 +2568,9 @@ static void smc_listen_work(struct work_struct *work) goto out_decl; } - smc_listen_out_connected(new_smc); SMC_STAT_SERV_SUCC_INC(sock_net(newclcsock->sk), ini); + /* smc_listen_out() will release smcsk */ + smc_listen_out_connected(new_smc); goto out_free; out_unlock: diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 46c156b121db..e2c5e0e626f9 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -257,20 +257,47 @@ svc_tcp_sock_process_cmsg(struct socket *sock, struct msghdr *msg, } static int -svc_tcp_sock_recv_cmsg(struct svc_sock *svsk, struct msghdr *msg) +svc_tcp_sock_recv_cmsg(struct socket *sock, unsigned int *msg_flags) { union { struct cmsghdr cmsg; u8 buf[CMSG_SPACE(sizeof(u8))]; } u; - struct socket *sock = svsk->sk_sock; + u8 alert[2]; + struct kvec alert_kvec = { + .iov_base = alert, + .iov_len = sizeof(alert), + }; + struct msghdr msg = { + .msg_flags = *msg_flags, + .msg_control = &u, + .msg_controllen = sizeof(u), + }; + int ret; + + iov_iter_kvec(&msg.msg_iter, ITER_DEST, &alert_kvec, 1, + alert_kvec.iov_len); + ret = sock_recvmsg(sock, &msg, MSG_DONTWAIT); + if (ret > 0 && + tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) { + iov_iter_revert(&msg.msg_iter, ret); + ret = svc_tcp_sock_process_cmsg(sock, &msg, &u.cmsg, -EAGAIN); + } + return ret; +} + +static int +svc_tcp_sock_recvmsg(struct svc_sock *svsk, struct msghdr *msg) +{ int ret; + struct socket *sock = svsk->sk_sock; - msg->msg_control = &u; - msg->msg_controllen = sizeof(u); ret = sock_recvmsg(sock, msg, MSG_DONTWAIT); - if (unlikely(msg->msg_controllen != sizeof(u))) - ret = svc_tcp_sock_process_cmsg(sock, msg, &u.cmsg, ret); + if (msg->msg_flags & MSG_CTRUNC) { + msg->msg_flags &= ~(MSG_CTRUNC | MSG_EOR); + if (ret == 0 || ret == -EIO) + ret = svc_tcp_sock_recv_cmsg(sock, &msg->msg_flags); + } return ret; } @@ -321,7 +348,7 @@ static ssize_t svc_tcp_read_msg(struct svc_rqst *rqstp, size_t buflen, iov_iter_advance(&msg.msg_iter, seek); buflen -= seek; } - len = svc_tcp_sock_recv_cmsg(svsk, &msg); + len = svc_tcp_sock_recvmsg(svsk, &msg); if (len > 0) svc_flush_bvec(bvec, len, seek); @@ -1018,7 +1045,7 @@ static ssize_t svc_tcp_read_marker(struct svc_sock *svsk, iov.iov_base = ((char *)&svsk->sk_marker) + svsk->sk_tcplen; iov.iov_len = want; iov_iter_kvec(&msg.msg_iter, ITER_DEST, &iov, 1, want); - len = svc_tcp_sock_recv_cmsg(svsk, &msg); + len = svc_tcp_sock_recvmsg(svsk, &msg); if (len < 0) return len; svsk->sk_tcplen += len; diff --git a/net/tls/tls.h b/net/tls/tls.h index 774859b63f0d..4e077068e6d9 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -196,7 +196,7 @@ void tls_strp_msg_done(struct tls_strparser *strp); int tls_rx_msg_size(struct tls_strparser *strp, struct sk_buff *skb); void tls_rx_msg_ready(struct tls_strparser *strp); -void tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh); +bool tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh); int tls_strp_msg_cow(struct tls_sw_context_rx *ctx); struct sk_buff *tls_strp_msg_detach(struct tls_sw_context_rx *ctx); int tls_strp_msg_hold(struct tls_strparser *strp, struct sk_buff_head *dst); diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 095cf31bae0b..d71643b494a1 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -475,7 +475,7 @@ static void tls_strp_load_anchor_with_queue(struct tls_strparser *strp, int len) strp->stm.offset = offset; } -void tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh) +bool tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh) { struct strp_msg *rxm; struct tls_msg *tlm; @@ -484,8 +484,11 @@ void tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh) DEBUG_NET_WARN_ON_ONCE(!strp->stm.full_len); if (!strp->copy_mode && force_refresh) { - if (WARN_ON(tcp_inq(strp->sk) < strp->stm.full_len)) - return; + if (unlikely(tcp_inq(strp->sk) < strp->stm.full_len)) { + WRITE_ONCE(strp->msg_ready, 0); + memset(&strp->stm, 0, sizeof(strp->stm)); + return false; + } tls_strp_load_anchor_with_queue(strp, strp->stm.full_len); } @@ -495,6 +498,8 @@ void tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh) rxm->offset = strp->stm.offset; tlm = tls_msg(strp->anchor); tlm->control = strp->mark; + + return true; } /* Called with lock held on lower socket */ diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 549d1ea01a72..bac65d0d4e3e 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1384,7 +1384,8 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock, return sock_intr_errno(timeo); } - tls_strp_msg_load(&ctx->strp, released); + if (unlikely(!tls_strp_msg_load(&ctx->strp, released))) + return tls_rx_rec_wait(sk, psock, nonblock, false); return 1; } @@ -1807,6 +1808,9 @@ int decrypt_skb(struct sock *sk, struct scatterlist *sgout) return tls_decrypt_sg(sk, NULL, sgout, &darg); } +/* All records returned from a recvmsg() call must have the same type. + * 0 is not a valid content type. Use it as "no type reported, yet". + */ static int tls_record_content_type(struct msghdr *msg, struct tls_msg *tlm, u8 *control) { @@ -2050,8 +2054,10 @@ int tls_sw_recvmsg(struct sock *sk, if (err < 0) goto end; + /* process_rx_list() will set @control if it processed any records */ copied = err; - if (len <= copied || (copied && control != TLS_RECORD_TYPE_DATA) || rx_more) + if (len <= copied || rx_more || + (control && control != TLS_RECORD_TYPE_DATA)) goto end; target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index ead6a3c14b87..bebb355f3ffe 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -689,7 +689,8 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk, unsigned int i; for (i = 0; i < MAX_PORT_RETRIES; i++) { - if (port <= LAST_RESERVED_PORT) + if (port == VMADDR_PORT_ANY || + port <= LAST_RESERVED_PORT) port = LAST_RESERVED_PORT + 1; new_addr.svm_port = port++; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index d2819baea414..c7a1f080d2de 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -155,7 +155,8 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur return skb; } - if (skb_is_gso(skb) && unlikely(xmit_xfrm_check_overflow(skb))) { + if (skb_is_gso(skb) && (unlikely(x->xso.dev != dev) || + unlikely(xmit_xfrm_check_overflow(skb)))) { struct sk_buff *segs; /* Packet got rerouted, fixup features and segment it. */ @@ -415,10 +416,12 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) struct net_device *dev = x->xso.dev; bool check_tunnel_size; - if (x->xso.type == XFRM_DEV_OFFLOAD_UNSPECIFIED) + if (!x->type_offload || + (x->xso.type == XFRM_DEV_OFFLOAD_UNSPECIFIED && x->encap)) return false; - if ((dev == xfrm_dst_path(dst)->dev) && !xdst->child->xfrm) { + if ((!dev || dev == xfrm_dst_path(dst)->dev) && + !xdst->child->xfrm) { mtu = xfrm_state_mtu(x, xdst->child_mtu_cached); if (skb->len <= mtu) goto ok; @@ -430,6 +433,9 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) return false; ok: + if (!dev) + return true; + check_tunnel_size = x->xso.type == XFRM_DEV_OFFLOAD_PACKET && x->props.mode == XFRM_MODE_TUNNEL; switch (x->props.family) { diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 77db3b5fe4ac..78fcbb89cf32 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -3297,7 +3297,7 @@ void xfrm_state_fini(struct net *net) unsigned int sz; flush_work(&net->xfrm.state_hash_work); - xfrm_state_flush(net, IPSEC_PROTO_ANY, false); + xfrm_state_flush(net, 0, false); flush_work(&xfrm_state_gc_work); WARN_ON(!list_empty(&net->xfrm.state_all)); |