diff options
31 files changed, 217 insertions, 126 deletions
@@ -424,6 +424,9 @@ Krzysztof Wilczyński <kwilczynski@kernel.org> <krzysztof.wilczynski@linux.com> Krzysztof Wilczyński <kwilczynski@kernel.org> <kw@linux.com> Kshitiz Godara <quic_kgodara@quicinc.com> <kgodara@codeaurora.org> Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> +Kuniyuki Iwashima <kuniyu@google.com> <kuniyu@amazon.com> +Kuniyuki Iwashima <kuniyu@google.com> <kuniyu@amazon.co.jp> +Kuniyuki Iwashima <kuniyu@google.com> <kuni1840@gmail.com> Kuogee Hsieh <quic_khsieh@quicinc.com> <khsieh@codeaurora.org> Lee Jones <lee@kernel.org> <joneslee@google.com> Lee Jones <lee@kernel.org> <lee.jones@canonical.com> diff --git a/MAINTAINERS b/MAINTAINERS index f2668b81115c..bd09337f178d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17420,7 +17420,7 @@ F: tools/testing/selftests/net/srv6* NETWORKING [TCP] M: Eric Dumazet <edumazet@google.com> M: Neal Cardwell <ncardwell@google.com> -R: Kuniyuki Iwashima <kuniyu@amazon.com> +R: Kuniyuki Iwashima <kuniyu@google.com> L: netdev@vger.kernel.org S: Maintained F: Documentation/networking/net_cachelines/tcp_sock.rst @@ -17450,7 +17450,7 @@ F: net/tls/* NETWORKING [SOCKETS] M: Eric Dumazet <edumazet@google.com> -M: Kuniyuki Iwashima <kuniyu@amazon.com> +M: Kuniyuki Iwashima <kuniyu@google.com> M: Paolo Abeni <pabeni@redhat.com> M: Willem de Bruijn <willemb@google.com> S: Maintained @@ -17465,7 +17465,7 @@ F: net/core/scm.c F: net/socket.c NETWORKING [UNIX SOCKETS] -M: Kuniyuki Iwashima <kuniyu@amazon.com> +M: Kuniyuki Iwashima <kuniyu@google.com> S: Maintained F: include/net/af_unix.h F: include/net/netns/unix.h diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 3f089c3d47b2..d8595e84326d 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -477,10 +477,6 @@ static void e1000_down_and_stop(struct e1000_adapter *adapter) cancel_delayed_work_sync(&adapter->phy_info_task); cancel_delayed_work_sync(&adapter->fifo_stall_task); - - /* Only kill reset task if adapter is not resetting */ - if (!test_bit(__E1000_RESETTING, &adapter->flags)) - cancel_work_sync(&adapter->reset_task); } void e1000_down(struct e1000_adapter *adapter) @@ -1266,6 +1262,10 @@ static void e1000_remove(struct pci_dev *pdev) unregister_netdev(netdev); + /* Only kill reset task if adapter is not resetting */ + if (!test_bit(__E1000_RESETTING, &adapter->flags)) + cancel_work_sync(&adapter->reset_task); + e1000_phy_hw_reset(hw); kfree(adapter->tx_ring); diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 1120f8e4bb67..88e6bef69342 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1546,8 +1546,8 @@ static void i40e_cleanup_reset_vf(struct i40e_vf *vf) * @vf: pointer to the VF structure * @flr: VFLR was issued or not * - * Returns true if the VF is in reset, resets successfully, or resets - * are disabled and false otherwise. + * Return: True if reset was performed successfully or if resets are disabled. + * False if reset is already in progress. **/ bool i40e_reset_vf(struct i40e_vf *vf, bool flr) { @@ -1566,7 +1566,7 @@ bool i40e_reset_vf(struct i40e_vf *vf, bool flr) /* If VF is being reset already we don't need to continue. */ if (test_and_set_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) - return true; + return false; i40e_trigger_vf_reset(vf, flr); @@ -4328,7 +4328,10 @@ int i40e_vc_process_vflr_event(struct i40e_pf *pf) reg = rd32(hw, I40E_GLGEN_VFLRSTAT(reg_idx)); if (reg & BIT(bit_idx)) /* i40e_reset_vf will clear the bit in GLGEN_VFLRSTAT */ - i40e_reset_vf(vf, true); + if (!i40e_reset_vf(vf, true)) { + /* At least one VF did not finish resetting, retry next time */ + set_bit(__I40E_VFLR_EVENT_PENDING, pf->state); + } } return 0; diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 2c0bb41809a4..81d7249d1149 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -3209,6 +3209,17 @@ static void iavf_reset_task(struct work_struct *work) } continue_reset: + /* If we are still early in the state machine, just restart. */ + if (adapter->state <= __IAVF_INIT_FAILED) { + iavf_shutdown_adminq(hw); + iavf_change_state(adapter, __IAVF_STARTUP); + iavf_startup(adapter); + queue_delayed_work(adapter->wq, &adapter->watchdog_task, + msecs_to_jiffies(30)); + netdev_unlock(netdev); + return; + } + /* We don't use netif_running() because it may be true prior to * ndo_open() returning, so we can't assume it means all our open * tasks have finished, since we're not holding the rtnl_lock here. diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index a6f0e5990be2..07f0d0a0f1e2 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -79,6 +79,23 @@ iavf_poll_virtchnl_msg(struct iavf_hw *hw, struct iavf_arq_event_info *event, return iavf_status_to_errno(status); received_op = (enum virtchnl_ops)le32_to_cpu(event->desc.cookie_high); + + if (received_op == VIRTCHNL_OP_EVENT) { + struct iavf_adapter *adapter = hw->back; + struct virtchnl_pf_event *vpe = + (struct virtchnl_pf_event *)event->msg_buf; + + if (vpe->event != VIRTCHNL_EVENT_RESET_IMPENDING) + continue; + + dev_info(&adapter->pdev->dev, "Reset indication received from the PF\n"); + if (!(adapter->flags & IAVF_FLAG_RESET_PENDING)) + iavf_schedule_reset(adapter, + IAVF_FLAG_RESET_PENDING); + + return -EIO; + } + if (op_to_poll == received_op) break; } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index b79a148ed0f2..55cad824c5b9 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -2299,6 +2299,7 @@ static int ice_capture_crosststamp(ktime_t *device, ts = ((u64)ts_hi << 32) | ts_lo; system->cycles = ts; system->cs_id = CSID_X86_ART; + system->use_nsecs = true; /* Read Device source clock time */ ts_lo = rd32(hw, cfg->dev_time_l[tmr_idx]); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index ea078c9f5d15..3cb8d3bf9044 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -43,7 +43,6 @@ #include "en/fs_ethtool.h" #define LANES_UNKNOWN 0 -#define MAX_LANES 8 void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv, struct ethtool_drvinfo *drvinfo) @@ -1098,10 +1097,8 @@ static void get_link_properties(struct net_device *netdev, speed = info->speed; lanes = info->lanes; duplex = DUPLEX_FULL; - } else if (data_rate_oper) { + } else if (data_rate_oper) speed = 100 * data_rate_oper; - lanes = MAX_LANES; - } out: link_ksettings->base.duplex = duplex; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index f1d908f61134..fef418e1ed1a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -2028,9 +2028,8 @@ err_out: return err; } -static bool mlx5_flow_has_geneve_opt(struct mlx5e_tc_flow *flow) +static bool mlx5_flow_has_geneve_opt(struct mlx5_flow_spec *spec) { - struct mlx5_flow_spec *spec = &flow->attr->parse_attr->spec; void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters_3); @@ -2069,7 +2068,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, } complete_all(&flow->del_hw_done); - if (mlx5_flow_has_geneve_opt(flow)) + if (mlx5_flow_has_geneve_opt(&attr->parse_attr->spec)) mlx5_geneve_tlv_option_del(priv->mdev->geneve); if (flow->decap_route) @@ -2574,12 +2573,13 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, err = mlx5e_tc_tun_parse(filter_dev, priv, tmp_spec, f, match_level); if (err) { - kvfree(tmp_spec); NL_SET_ERR_MSG_MOD(extack, "Failed to parse tunnel attributes"); netdev_warn(priv->netdev, "Failed to parse tunnel attributes"); - return err; + } else { + err = mlx5e_tc_set_attr_rx_tun(flow, tmp_spec); } - err = mlx5e_tc_set_attr_rx_tun(flow, tmp_spec); + if (mlx5_flow_has_geneve_opt(tmp_spec)) + mlx5_geneve_tlv_option_del(priv->mdev->geneve); kvfree(tmp_spec); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 7fb8a3381f84..4917d185d0c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1295,12 +1295,15 @@ mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw, ret = mlx5_eswitch_load_pf_vf_vport(esw, MLX5_VPORT_ECPF, enabled_events); if (ret) goto ecpf_err; - if (mlx5_core_ec_sriov_enabled(esw->dev)) { - ret = mlx5_eswitch_load_ec_vf_vports(esw, esw->esw_funcs.num_ec_vfs, - enabled_events); - if (ret) - goto ec_vf_err; - } + } + + /* Enable ECVF vports */ + if (mlx5_core_ec_sriov_enabled(esw->dev)) { + ret = mlx5_eswitch_load_ec_vf_vports(esw, + esw->esw_funcs.num_ec_vfs, + enabled_events); + if (ret) + goto ec_vf_err; } /* Enable VF vports */ @@ -1331,9 +1334,11 @@ void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw) { mlx5_eswitch_unload_vf_vports(esw, esw->esw_funcs.num_vfs); + if (mlx5_core_ec_sriov_enabled(esw->dev)) + mlx5_eswitch_unload_ec_vf_vports(esw, + esw->esw_funcs.num_ec_vfs); + if (mlx5_ecpf_vport_exists(esw->dev)) { - if (mlx5_core_ec_sriov_enabled(esw->dev)) - mlx5_eswitch_unload_ec_vf_vports(esw, esw->esw_funcs.num_vfs); mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_ECPF); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 23a7e8e7adfa..a8046200d376 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2228,6 +2228,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft, struct mlx5_flow_handle *rule; struct match_list *iter; bool take_write = false; + bool try_again = false; struct fs_fte *fte; u64 version = 0; int err; @@ -2292,6 +2293,7 @@ skip_search: nested_down_write_ref_node(&g->node, FS_LOCK_PARENT); if (!g->node.active) { + try_again = true; up_write_ref_node(&g->node, false); continue; } @@ -2313,7 +2315,8 @@ skip_search: tree_put_node(&fte->node, false); return rule; } - rule = ERR_PTR(-ENOENT); + err = try_again ? -EAGAIN : -ENOENT; + rule = ERR_PTR(err); out: kmem_cache_free(steering->ftes_cache, fte); return rule; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index 972e8e9df585..9bc9bd83c232 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -291,7 +291,7 @@ static void free_4k(struct mlx5_core_dev *dev, u64 addr, u32 function) static int alloc_system_page(struct mlx5_core_dev *dev, u32 function) { struct device *device = mlx5_core_dma_dev(dev); - int nid = dev_to_node(device); + int nid = dev->priv.numa_node; struct page *page; u64 zero_addr = 1; u64 addr; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c index fb62f3bc4bd4..447ea3f8722c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c @@ -1370,8 +1370,8 @@ mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx, struct mlx5hws_cmd_set_fte_attr fte_attr = {0}; struct mlx5hws_cmd_forward_tbl *fw_island; struct mlx5hws_action *action; - u32 i /*, packet_reformat_id*/; - int ret; + int ret, last_dest_idx = -1; + u32 i; if (num_dest <= 1) { mlx5hws_err(ctx, "Action must have multiple dests\n"); @@ -1401,11 +1401,8 @@ mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx, dest_list[i].destination_id = dests[i].dest->dest_obj.obj_id; fte_attr.action_flags |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; fte_attr.ignore_flow_level = ignore_flow_level; - /* ToDo: In SW steering we have a handling of 'go to WIRE' - * destination here by upper layer setting 'is_wire_ft' flag - * if the destination is wire. - * This is because uplink should be last dest in the list. - */ + if (dests[i].is_wire_ft) + last_dest_idx = i; break; case MLX5HWS_ACTION_TYP_VPORT: dest_list[i].destination_type = MLX5_FLOW_DESTINATION_TYPE_VPORT; @@ -1429,6 +1426,9 @@ mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx, } } + if (last_dest_idx != -1) + swap(dest_list[last_dest_idx], dest_list[num_dest - 1]); + fte_attr.dests_num = num_dest; fte_attr.dests = dest_list; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c index 70768953a4f6..ca7501c57468 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c @@ -1070,7 +1070,7 @@ hws_bwc_rule_complex_hash_node_get(struct mlx5hws_bwc_rule *bwc_rule, struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher; struct mlx5hws_bwc_complex_rule_hash_node *node, *old_node; struct rhashtable *refcount_hash; - int i; + int ret, i; bwc_rule->complex_hash_node = NULL; @@ -1078,7 +1078,11 @@ hws_bwc_rule_complex_hash_node_get(struct mlx5hws_bwc_rule *bwc_rule, if (unlikely(!node)) return -ENOMEM; - node->tag = ida_alloc(&bwc_matcher->complex->metadata_ida, GFP_KERNEL); + ret = ida_alloc(&bwc_matcher->complex->metadata_ida, GFP_KERNEL); + if (ret < 0) + goto err_free_node; + node->tag = ret; + refcount_set(&node->refcount, 1); /* Clear match buffer - turn off all the unrelated fields @@ -1094,6 +1098,11 @@ hws_bwc_rule_complex_hash_node_get(struct mlx5hws_bwc_rule *bwc_rule, old_node = rhashtable_lookup_get_insert_fast(refcount_hash, &node->hash_node, hws_refcount_hash); + if (IS_ERR(old_node)) { + ret = PTR_ERR(old_node); + goto err_free_ida; + } + if (old_node) { /* Rule with the same tag already exists - update refcount */ refcount_inc(&old_node->refcount); @@ -1112,6 +1121,12 @@ hws_bwc_rule_complex_hash_node_get(struct mlx5hws_bwc_rule *bwc_rule, bwc_rule->complex_hash_node = node; return 0; + +err_free_ida: + ida_free(&bwc_matcher->complex->metadata_ida, node->tag); +err_free_node: + kfree(node); + return ret; } static void diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c index 5cc0dc002ac1..d45e1145d197 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c @@ -785,6 +785,9 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd, HWS_SET_HDR(fc, match_param, IP_PROTOCOL_O, outer_headers.ip_protocol, eth_l3_outer.protocol_next_header); + HWS_SET_HDR(fc, match_param, IP_VERSION_O, + outer_headers.ip_version, + eth_l3_outer.ip_version); HWS_SET_HDR(fc, match_param, IP_TTL_O, outer_headers.ttl_hoplimit, eth_l3_outer.time_to_live_hop_limit); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c index 9d1c0e4b224a..bf4643d0ce17 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c @@ -966,6 +966,9 @@ static int mlx5_fs_fte_get_hws_actions(struct mlx5_flow_root_namespace *ns, switch (attr->type) { case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE: dest_action = mlx5_fs_get_dest_action_ft(fs_ctx, dst); + if (dst->dest_attr.ft->flags & + MLX5_FLOW_TABLE_UPLINK_VPORT) + dest_actions[num_dest_actions].is_wire_ft = true; break; case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM: dest_action = mlx5_fs_get_dest_action_table_num(fs_ctx, @@ -1357,6 +1360,7 @@ mlx5_cmd_hws_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, pkt_reformat->fs_hws_action.pr_data = pr_data; } + mutex_init(&pkt_reformat->fs_hws_action.lock); pkt_reformat->owner = MLX5_FLOW_RESOURCE_OWNER_HWS; pkt_reformat->fs_hws_action.hws_action = hws_action; return 0; @@ -1503,7 +1507,6 @@ static int mlx5_cmd_hws_modify_header_alloc(struct mlx5_flow_root_namespace *ns, err = -ENOMEM; goto release_mh; } - mutex_init(&modify_hdr->fs_hws_action.lock); modify_hdr->fs_hws_action.mh_data = mh_data; modify_hdr->fs_hws_action.fs_pool = pool; modify_hdr->owner = MLX5_FLOW_RESOURCE_OWNER_SW; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h index 9bbadc4d8a0b..d8ac6c196211 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h @@ -213,6 +213,7 @@ struct mlx5hws_action_dest_attr { struct mlx5hws_action *dest; /* Optional reformat action */ struct mlx5hws_action *reformat; + bool is_wire_ft; }; /** diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index af545d42961c..fa5fbd97ad69 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -371,7 +371,8 @@ static int nsim_poll(struct napi_struct *napi, int budget) int done; done = nsim_rcv(rq, budget); - napi_complete(napi); + if (done < budget) + napi_complete_done(napi, done); return done; } diff --git a/drivers/net/phy/phy_caps.c b/drivers/net/phy/phy_caps.c index 703321689726..38417e288611 100644 --- a/drivers/net/phy/phy_caps.c +++ b/drivers/net/phy/phy_caps.c @@ -188,6 +188,9 @@ phy_caps_lookup_by_linkmode_rev(const unsigned long *linkmodes, bool fdx_only) * When @exact is not set, we return either an exact match, or matching capabilities * at lower speed, or the lowest matching speed, or NULL. * + * Non-exact matches will try to return an exact speed and duplex match, but may + * return matching capabilities with same speed but a different duplex. + * * Returns: a matched link_capabilities according to the above process, NULL * otherwise. */ @@ -195,7 +198,7 @@ const struct link_capabilities * phy_caps_lookup(int speed, unsigned int duplex, const unsigned long *supported, bool exact) { - const struct link_capabilities *lcap, *last = NULL; + const struct link_capabilities *lcap, *match = NULL, *last = NULL; for_each_link_caps_desc_speed(lcap) { if (linkmode_intersects(lcap->linkmodes, supported)) { @@ -204,16 +207,19 @@ phy_caps_lookup(int speed, unsigned int duplex, const unsigned long *supported, if (lcap->speed == speed && lcap->duplex == duplex) { return lcap; } else if (!exact) { - if (lcap->speed <= speed) - return lcap; + if (!match && lcap->speed <= speed) + match = lcap; + + if (lcap->speed < speed) + break; } } } - if (!exact) - return last; + if (!match && !exact) + match = last; - return NULL; + return match; } EXPORT_SYMBOL_GPL(phy_caps_lookup); diff --git a/drivers/net/veth.c b/drivers/net/veth.c index e58a0f1b5c5b..a3046142cb8e 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -909,7 +909,7 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget, /* NAPI functions as RCU section */ peer_dev = rcu_dereference_check(priv->peer, rcu_read_lock_bh_held()); - peer_txq = netdev_get_tx_queue(peer_dev, queue_idx); + peer_txq = peer_dev ? netdev_get_tx_queue(peer_dev, queue_idx) : NULL; for (i = 0; i < budget; i++) { void *ptr = __ptr_ring_consume(&rq->xdp_ring); @@ -959,7 +959,7 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget, rq->stats.vs.xdp_packets += done; u64_stats_update_end(&rq->stats.syncp); - if (unlikely(netif_tx_queue_stopped(peer_txq))) + if (peer_txq && unlikely(netif_tx_queue_stopped(peer_txq))) netif_tx_wake_queue(peer_txq); return done; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 629368ab2787..638948be4c50 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -973,14 +973,6 @@ static inline void qdisc_qstats_qlen_backlog(struct Qdisc *sch, __u32 *qlen, *backlog = qstats.backlog; } -static inline void qdisc_tree_flush_backlog(struct Qdisc *sch) -{ - __u32 qlen, backlog; - - qdisc_qstats_qlen_backlog(sch, &qlen, &backlog); - qdisc_tree_reduce_backlog(sch, qlen, backlog); -} - static inline void qdisc_purge_queue(struct Qdisc *sch) { __u32 qlen, backlog; diff --git a/net/core/filter.c b/net/core/filter.c index 327ca73f9cd7..7a72f766aacf 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3233,6 +3233,13 @@ static const struct bpf_func_proto bpf_skb_vlan_pop_proto = { .arg1_type = ARG_PTR_TO_CTX, }; +static void bpf_skb_change_protocol(struct sk_buff *skb, u16 proto) +{ + skb->protocol = htons(proto); + if (skb_valid_dst(skb)) + skb_dst_drop(skb); +} + static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len) { /* Caller already did skb_cow() with len as headroom, @@ -3329,7 +3336,7 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) } } - skb->protocol = htons(ETH_P_IPV6); + bpf_skb_change_protocol(skb, ETH_P_IPV6); skb_clear_hash(skb); return 0; @@ -3359,7 +3366,7 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) } } - skb->protocol = htons(ETH_P_IP); + bpf_skb_change_protocol(skb, ETH_P_IP); skb_clear_hash(skb); return 0; @@ -3550,10 +3557,10 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff, /* Match skb->protocol to new outer l3 protocol */ if (skb->protocol == htons(ETH_P_IP) && flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) - skb->protocol = htons(ETH_P_IPV6); + bpf_skb_change_protocol(skb, ETH_P_IPV6); else if (skb->protocol == htons(ETH_P_IPV6) && flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4) - skb->protocol = htons(ETH_P_IP); + bpf_skb_change_protocol(skb, ETH_P_IP); } if (skb_is_gso(skb)) { @@ -3606,10 +3613,10 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff, /* Match skb->protocol to new outer l3 protocol */ if (skb->protocol == htons(ETH_P_IP) && flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV6) - skb->protocol = htons(ETH_P_IPV6); + bpf_skb_change_protocol(skb, ETH_P_IPV6); else if (skb->protocol == htons(ETH_P_IPV6) && flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV4) - skb->protocol = htons(ETH_P_IP); + bpf_skb_change_protocol(skb, ETH_P_IP); if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 0143262094b0..79c8f1acf8a3 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3737,6 +3737,53 @@ void fib6_nh_release_dsts(struct fib6_nh *fib6_nh) } } +static int fib6_config_validate(struct fib6_config *cfg, + struct netlink_ext_ack *extack) +{ + /* RTF_PCPU is an internal flag; can not be set by userspace */ + if (cfg->fc_flags & RTF_PCPU) { + NL_SET_ERR_MSG(extack, "Userspace can not set RTF_PCPU"); + goto errout; + } + + /* RTF_CACHE is an internal flag; can not be set by userspace */ + if (cfg->fc_flags & RTF_CACHE) { + NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE"); + goto errout; + } + + if (cfg->fc_type > RTN_MAX) { + NL_SET_ERR_MSG(extack, "Invalid route type"); + goto errout; + } + + if (cfg->fc_dst_len > 128) { + NL_SET_ERR_MSG(extack, "Invalid prefix length"); + goto errout; + } + +#ifdef CONFIG_IPV6_SUBTREES + if (cfg->fc_src_len > 128) { + NL_SET_ERR_MSG(extack, "Invalid source address length"); + goto errout; + } + + if (cfg->fc_nh_id && cfg->fc_src_len) { + NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing"); + goto errout; + } +#else + if (cfg->fc_src_len) { + NL_SET_ERR_MSG(extack, + "Specifying source address requires IPV6_SUBTREES to be enabled"); + goto errout; + } +#endif + return 0; +errout: + return -EINVAL; +} + static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) @@ -3886,6 +3933,10 @@ int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags, struct fib6_info *rt; int err; + err = fib6_config_validate(cfg, extack); + if (err) + return err; + rt = ip6_route_info_create(cfg, gfp_flags, extack); if (IS_ERR(rt)) return PTR_ERR(rt); @@ -4479,53 +4530,6 @@ void rt6_purge_dflt_routers(struct net *net) rcu_read_unlock(); } -static int fib6_config_validate(struct fib6_config *cfg, - struct netlink_ext_ack *extack) -{ - /* RTF_PCPU is an internal flag; can not be set by userspace */ - if (cfg->fc_flags & RTF_PCPU) { - NL_SET_ERR_MSG(extack, "Userspace can not set RTF_PCPU"); - goto errout; - } - - /* RTF_CACHE is an internal flag; can not be set by userspace */ - if (cfg->fc_flags & RTF_CACHE) { - NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE"); - goto errout; - } - - if (cfg->fc_type > RTN_MAX) { - NL_SET_ERR_MSG(extack, "Invalid route type"); - goto errout; - } - - if (cfg->fc_dst_len > 128) { - NL_SET_ERR_MSG(extack, "Invalid prefix length"); - goto errout; - } - -#ifdef CONFIG_IPV6_SUBTREES - if (cfg->fc_src_len > 128) { - NL_SET_ERR_MSG(extack, "Invalid source address length"); - goto errout; - } - - if (cfg->fc_nh_id && cfg->fc_src_len) { - NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing"); - goto errout; - } -#else - if (cfg->fc_src_len) { - NL_SET_ERR_MSG(extack, - "Specifying source address requires IPV6_SUBTREES to be enabled"); - goto errout; - } -#endif - return 0; -errout: - return -EINVAL; -} - static void rtmsg_to_fib6_config(struct net *net, struct in6_rtmsg *rtmsg, struct fib6_config *cfg) @@ -4563,10 +4567,6 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg) switch (cmd) { case SIOCADDRT: - err = fib6_config_validate(&cfg, NULL); - if (err) - break; - /* Only do the default setting of fc_metric in route adding */ if (cfg.fc_metric == 0) cfg.fc_metric = IP6_RT_PRIO_USER; @@ -5402,6 +5402,10 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, int nhn = 0; int err; + err = fib6_config_validate(cfg, extack); + if (err) + return err; + replace = (cfg->fc_nlinfo.nlh && (cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_REPLACE)); @@ -5636,10 +5640,6 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) return err; - err = fib6_config_validate(&cfg, extack); - if (err) - return err; - if (cfg.fc_metric == 0) cfg.fc_metric = IP6_RT_PRIO_USER; diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 2c069f0181c6..037f764822b9 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -661,7 +661,7 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, 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_tree_flush_backlog(q->classes[i].qdisc); + qdisc_purge_queue(q->classes[i].qdisc); } WRITE_ONCE(q->nstrict, nstrict); memcpy(q->prio2band, priomap, sizeof(priomap)); diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index cc30f7a32f1a..9e2b9a490db2 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -211,7 +211,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt, memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1); for (i = q->bands; i < oldbands; i++) - qdisc_tree_flush_backlog(q->queues[i]); + qdisc_purge_queue(q->queues[i]); for (i = oldbands; i < q->bands; i++) { q->queues[i] = queues[i]; diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 1ba3e0bba54f..4696c893cf55 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -285,7 +285,7 @@ static int __red_change(struct Qdisc *sch, struct nlattr **tb, q->userbits = userbits; q->limit = ctl->limit; if (child) { - qdisc_tree_flush_backlog(q->qdisc); + qdisc_purge_queue(q->qdisc); old_child = q->qdisc; q->qdisc = child; } diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 77fa02f2bfcd..a8cca549b5a2 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -656,6 +656,14 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt, NL_SET_ERR_MSG_MOD(extack, "invalid quantum"); return -EINVAL; } + + if (ctl->perturb_period < 0 || + ctl->perturb_period > INT_MAX / HZ) { + NL_SET_ERR_MSG_MOD(extack, "invalid perturb period"); + return -EINVAL; + } + perturb_period = ctl->perturb_period * HZ; + if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max, ctl_v1->Wlog, ctl_v1->Scell_log, NULL)) return -EINVAL; @@ -672,14 +680,12 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt, headdrop = q->headdrop; maxdepth = q->maxdepth; maxflows = q->maxflows; - perturb_period = q->perturb_period; quantum = q->quantum; flags = q->flags; /* update and validate configuration */ if (ctl->quantum) quantum = ctl->quantum; - perturb_period = ctl->perturb_period * HZ; if (ctl->flows) maxflows = min_t(u32, ctl->flows, SFQ_MAX_FLOWS); if (ctl->divisor) { diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index dc26b22d53c7..4c977f049670 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -452,7 +452,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt, sch_tree_lock(sch); if (child) { - qdisc_tree_flush_backlog(q->qdisc); + qdisc_purge_queue(q->qdisc); old = q->qdisc; q->qdisc = child; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 2e2e9997a68e..22e170fb5dda 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1971,7 +1971,8 @@ static void unix_maybe_add_creds(struct sk_buff *skb, const struct sock *sk, if (UNIXCB(skb).pid) return; - if (unix_may_passcred(sk) || unix_may_passcred(other)) { + if (unix_may_passcred(sk) || unix_may_passcred(other) || + !other->sk_socket) { UNIXCB(skb).pid = get_pid(task_tgid(current)); current_uid_gid(&UNIXCB(skb).uid, &UNIXCB(skb).gid); } diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index ea84b88bcb30..ab996bd22a5f 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -27,6 +27,7 @@ TEST_PROGS += amt.sh TEST_PROGS += unicast_extensions.sh TEST_PROGS += udpgro_fwd.sh TEST_PROGS += udpgro_frglist.sh +TEST_PROGS += nat6to4.sh TEST_PROGS += veth.sh TEST_PROGS += ioam6.sh TEST_PROGS += gro.sh diff --git a/tools/testing/selftests/net/nat6to4.sh b/tools/testing/selftests/net/nat6to4.sh new file mode 100755 index 000000000000..0ee859b622a4 --- /dev/null +++ b/tools/testing/selftests/net/nat6to4.sh @@ -0,0 +1,15 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +NS="ns-peer-$(mktemp -u XXXXXX)" + +ip netns add "${NS}" +ip -netns "${NS}" link set lo up +ip -netns "${NS}" route add default via 127.0.0.2 dev lo + +tc -n "${NS}" qdisc add dev lo ingress +tc -n "${NS}" filter add dev lo ingress prio 4 protocol ip \ + bpf object-file nat6to4.bpf.o section schedcls/egress4/snat4 direct-action + +ip netns exec "${NS}" \ + bash -c 'echo 012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789abc | socat - UDP4-DATAGRAM:224.1.0.1:6666,ip-multicast-loop=1' |