diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2024-04-18 11:40:54 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2024-04-18 11:40:54 -0700 |
commit | 7586c8501d090609c6eb1af6ba05e3ed68806c83 (patch) | |
tree | 2877f311f9be4bd2f70e16c34e632c96a25a1977 | |
parent | 360a348fd7fe72ec42a80d025e6fc81cda19f48e (diff) | |
parent | c24cd679b075b0e953ea167b0aa2b2d59e4eba7f (diff) |
Merge tag 'net-6.9-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"A little calmer than usual, probably just the timing of sub-tree PRs.
Including fixes from netfilter.
Current release - regressions:
- inet: bring NLM_DONE out to a separate recv() again, fix user space
which assumes multiple recv()s will happen and gets blocked forever
- drv: mlx5:
- restore mistakenly dropped parts in register devlink flow
- use channel mdev reference instead of global mdev instance for
coalescing
- acquire RTNL lock before RQs/SQs activation/deactivation
Previous releases - regressions:
- net: change maximum number of UDP segments to 128, fix virtio
compatibility with Windows peers
- usb: ax88179_178a: avoid writing the mac address before first
reading
Previous releases - always broken:
- sched: fix mirred deadlock on device recursion
- netfilter:
- br_netfilter: skip conntrack input hook for promisc packets
- fixes removal of duplicate elements in the pipapo set backend
- various fixes for abort paths and error handling
- af_unix: don't peek OOB data without MSG_OOB
- drv: flower: fix fragment flags handling in multiple drivers
- drv: ravb: fix jumbo frames and packet stats accounting
Misc:
- kselftest_harness: fix Clang warning about zero-length format
- tun: limit printing rate when illegal packet received by tun dev"
* tag 'net-6.9-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (46 commits)
net: ethernet: ti: am65-cpsw-nuss: cleanup DMA Channels before using them
net: usb: ax88179_178a: avoid writing the mac address before first reading
net: ravb: Fix RX byte accounting for jumbo packets
net: ravb: Fix GbEth jumbo packet RX checksum handling
net: ravb: Allow RX loop to move past DMA mapping errors
net: ravb: Count packets instead of descriptors in R-Car RX path
net: ethernet: mtk_eth_soc: fix WED + wifi reset
net:usb:qmi_wwan: support Rolling modules
selftests: kselftest_harness: fix Clang warning about zero-length format
net/sched: Fix mirred deadlock on device recursion
netfilter: nf_tables: fix memleak in map from abort path
netfilter: nf_tables: restore set elements when delete set fails
netfilter: nf_tables: missing iterator type in lookup walk
s390/ism: Properly fix receive message buffer allocation
net: dsa: mt7530: fix port mirroring for MT7988 SoC switch
net: dsa: mt7530: fix mirroring frames received on local port
tun: limit printing rate when illegal packet received by tun dev
ice: Fix checking for unsupported keys on non-tunnel device
ice: tc: allow zero flags in parsing tc flower
ice: tc: check src_vsi in case of traffic from VF
...
56 files changed, 438 insertions, 219 deletions
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index c0d0bce0b594..8090390edaf9 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1883,14 +1883,16 @@ mt7530_port_vlan_del(struct dsa_switch *ds, int port, static int mt753x_mirror_port_get(unsigned int id, u32 val) { - return (id == ID_MT7531) ? MT7531_MIRROR_PORT_GET(val) : - MIRROR_PORT(val); + return (id == ID_MT7531 || id == ID_MT7988) ? + MT7531_MIRROR_PORT_GET(val) : + MIRROR_PORT(val); } static int mt753x_mirror_port_set(unsigned int id, u32 val) { - return (id == ID_MT7531) ? MT7531_MIRROR_PORT_SET(val) : - MIRROR_PORT(val); + return (id == ID_MT7531 || id == ID_MT7988) ? + MT7531_MIRROR_PORT_SET(val) : + MIRROR_PORT(val); } static int mt753x_port_mirror_add(struct dsa_switch *ds, int port, @@ -2480,6 +2482,9 @@ mt7530_setup(struct dsa_switch *ds) PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT)); } + /* Allow mirroring frames received on the local port (monitor port). */ + mt7530_set(priv, MT753X_AGC, LOCAL_EN); + /* Setup VLAN ID 0 for VLAN-unaware bridges */ ret = mt7530_setup_vlan0(priv); if (ret) @@ -2591,6 +2596,9 @@ mt7531_setup_common(struct dsa_switch *ds) PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT)); } + /* Allow mirroring frames received on the local port (monitor port). */ + mt7530_set(priv, MT753X_AGC, LOCAL_EN); + /* Flush the FDB table */ ret = mt7530_fdb_cmd(priv, MT7530_FDB_FLUSH, NULL); if (ret < 0) diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index 585db03c0548..a08053390b28 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -32,6 +32,10 @@ enum mt753x_id { #define SYSC_REG_RSTCTRL 0x34 #define RESET_MCM BIT(2) +/* Register for ARL global control */ +#define MT753X_AGC 0xc +#define LOCAL_EN BIT(7) + /* Registers to mac forward control for unknown frames */ #define MT7530_MFC 0x10 #define BC_FFP(x) (((x) & 0xff) << 24) diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index b890410a2bc0..688ccb0615ab 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -28,6 +28,8 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, * - ICE_TC_FLWR_FIELD_VLAN_TPID (present if specified) * - Tunnel flag (present if tunnel) */ + if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS) + lkups_cnt++; if (flags & ICE_TC_FLWR_FIELD_TENANT_ID) lkups_cnt++; @@ -363,6 +365,11 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags, /* Always add direction metadata */ ice_rule_add_direction_metadata(&list[ICE_TC_METADATA_LKUP_IDX]); + if (tc_fltr->direction == ICE_ESWITCH_FLTR_EGRESS) { + ice_rule_add_src_vsi_metadata(&list[i]); + i++; + } + rule_info->tun_type = ice_sw_type_from_tunnel(tc_fltr->tunnel_type); if (tc_fltr->tunnel_type != TNL_LAST) { i = ice_tc_fill_tunnel_outer(flags, tc_fltr, list, i); @@ -772,7 +779,7 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) int ret; int i; - if (!flags || (flags & ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT)) { + if (flags & ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT) { NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported encap field(s)"); return -EOPNOTSUPP; } @@ -820,6 +827,7 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) /* specify the cookie as filter_rule_id */ rule_info.fltr_rule_id = fltr->cookie; + rule_info.src_vsi = vsi->idx; ret = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, &rule_added); if (ret == -EEXIST) { @@ -1481,7 +1489,10 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, (BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) | - BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS))) { + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_OPTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL))) { NL_SET_ERR_MSG_MOD(fltr->extack, "Tunnel key used, but device isn't a tunnel"); return -EOPNOTSUPP; } else { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index 87bdb93cb066..f4655a8c0705 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -689,6 +689,7 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node, if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { struct flow_match_control match; + u32 val; flow_rule_match_control(rule, &match); if (match.mask->flags & FLOW_DIS_FIRST_FRAG) { @@ -697,12 +698,14 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node, } if (match.mask->flags & FLOW_DIS_IS_FRAGMENT) { + val = match.key->flags & FLOW_DIS_IS_FRAGMENT; if (ntohs(flow_spec->etype) == ETH_P_IP) { - flow_spec->ip_flag = IPV4_FLAG_MORE; + flow_spec->ip_flag = val ? IPV4_FLAG_MORE : 0; flow_mask->ip_flag = IPV4_FLAG_MORE; req->features |= BIT_ULL(NPC_IPFRAG_IPV4); } else if (ntohs(flow_spec->etype) == ETH_P_IPV6) { - flow_spec->next_header = IPPROTO_FRAGMENT; + flow_spec->next_header = val ? + IPPROTO_FRAGMENT : 0; flow_mask->next_header = 0xff; req->features |= BIT_ULL(NPC_IPFRAG_IPV6); } else { diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index c895e265ae0e..61334a71058c 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -1074,13 +1074,13 @@ mtk_wed_dma_disable(struct mtk_wed_device *dev) static void mtk_wed_stop(struct mtk_wed_device *dev) { + mtk_wed_dma_disable(dev); mtk_wed_set_ext_int(dev, false); wed_w32(dev, MTK_WED_WPDMA_INT_TRIGGER, 0); wed_w32(dev, MTK_WED_WDMA_INT_TRIGGER, 0); wdma_w32(dev, MTK_WDMA_INT_MASK, 0); wdma_w32(dev, MTK_WDMA_INT_GRP2, 0); - wed_w32(dev, MTK_WED_WPDMA_INT_MASK, 0); if (!mtk_wed_get_rx_capa(dev)) return; @@ -1093,7 +1093,6 @@ static void mtk_wed_deinit(struct mtk_wed_device *dev) { mtk_wed_stop(dev); - mtk_wed_dma_disable(dev); wed_clr(dev, MTK_WED_CTRL, MTK_WED_CTRL_WDMA_INT_AGENT_EN | @@ -2605,9 +2604,6 @@ mtk_wed_irq_get(struct mtk_wed_device *dev, u32 mask) static void mtk_wed_irq_set_mask(struct mtk_wed_device *dev, u32 mask) { - if (!dev->running) - return; - mtk_wed_set_ext_int(dev, !!mask); wed_w32(dev, MTK_WED_INT_MASK, mask); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index 0ab9db319530..22918b2ef7f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -108,7 +108,10 @@ static int mlx5e_tx_reporter_err_cqe_recover(void *ctx) mlx5e_reset_txqsq_cc_pc(sq); sq->stats->recover++; clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state); + rtnl_lock(); mlx5e_activate_txqsq(sq); + rtnl_unlock(); + if (sq->channel) mlx5e_trigger_napi_icosq(sq->channel); else @@ -179,12 +182,16 @@ static int mlx5e_tx_reporter_ptpsq_unhealthy_recover(void *ctx) carrier_ok = netif_carrier_ok(netdev); netif_carrier_off(netdev); + rtnl_lock(); mlx5e_deactivate_priv_channels(priv); + rtnl_unlock(); mlx5e_ptp_close(chs->ptp); err = mlx5e_ptp_open(priv, &chs->params, chs->c[0]->lag_port, &chs->ptp); + rtnl_lock(); mlx5e_activate_priv_channels(priv); + rtnl_unlock(); /* return carrier back if needed */ if (carrier_ok) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index c7f542d0b8f0..93cf23278d93 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -46,6 +46,10 @@ struct arfs_table { struct hlist_head rules_hash[ARFS_HASH_SIZE]; }; +enum { + MLX5E_ARFS_STATE_ENABLED, +}; + enum arfs_type { ARFS_IPV4_TCP, ARFS_IPV6_TCP, @@ -60,6 +64,7 @@ struct mlx5e_arfs_tables { spinlock_t arfs_lock; int last_filter_id; struct workqueue_struct *wq; + unsigned long state; }; struct arfs_tuple { @@ -170,6 +175,8 @@ int mlx5e_arfs_enable(struct mlx5e_flow_steering *fs) return err; } } + set_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state); + return 0; } @@ -455,6 +462,8 @@ static void arfs_del_rules(struct mlx5e_flow_steering *fs) int i; int j; + clear_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state); + spin_lock_bh(&arfs->arfs_lock); mlx5e_for_each_arfs_rule(rule, htmp, arfs->arfs_tables, i, j) { hlist_del_init(&rule->hlist); @@ -627,17 +636,8 @@ static void arfs_handle_work(struct work_struct *work) struct mlx5_flow_handle *rule; arfs = mlx5e_fs_get_arfs(priv->fs); - mutex_lock(&priv->state_lock); - if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { - spin_lock_bh(&arfs->arfs_lock); - hlist_del(&arfs_rule->hlist); - spin_unlock_bh(&arfs->arfs_lock); - - mutex_unlock(&priv->state_lock); - kfree(arfs_rule); - goto out; - } - mutex_unlock(&priv->state_lock); + if (!test_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state)) + return; if (!arfs_rule->rule) { rule = arfs_add_rule(priv, arfs_rule); @@ -753,6 +753,11 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, return -EPROTONOSUPPORT; spin_lock_bh(&arfs->arfs_lock); + if (!test_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state)) { + spin_unlock_bh(&arfs->arfs_lock); + return -EPERM; + } + arfs_rule = arfs_find_rule(arfs_t, &fk); if (arfs_rule) { if (arfs_rule->rxq == rxq_index || work_busy(&arfs_rule->arfs_work)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 8f101181648c..67a29826bb57 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -589,12 +589,12 @@ static int mlx5e_get_coalesce(struct net_device *netdev, static void mlx5e_set_priv_channels_tx_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal) { - struct mlx5_core_dev *mdev = priv->mdev; int tc; int i; for (i = 0; i < priv->channels.num; ++i) { struct mlx5e_channel *c = priv->channels.c[i]; + struct mlx5_core_dev *mdev = c->mdev; for (tc = 0; tc < c->num_tc; tc++) { mlx5_core_modify_cq_moderation(mdev, @@ -608,11 +608,11 @@ mlx5e_set_priv_channels_tx_coalesce(struct mlx5e_priv *priv, struct ethtool_coal static void mlx5e_set_priv_channels_rx_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal) { - struct mlx5_core_dev *mdev = priv->mdev; int i; for (i = 0; i < priv->channels.num; ++i) { struct mlx5e_channel *c = priv->channels.c[i]; + struct mlx5_core_dev *mdev = c->mdev; mlx5_core_modify_cq_moderation(mdev, &c->rq.cq.mcq, coal->rx_coalesce_usecs, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b375ef268671..319930c04093 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -209,8 +209,8 @@ static int mlx5e_devcom_init_mpv(struct mlx5e_priv *priv, u64 *data) *data, mlx5e_devcom_event_mpv, priv); - if (IS_ERR_OR_NULL(priv->devcom)) - return -EOPNOTSUPP; + if (IS_ERR(priv->devcom)) + return PTR_ERR(priv->devcom); if (mlx5_core_is_mp_master(priv->mdev)) { mlx5_devcom_send_event(priv->devcom, MPV_DEVCOM_MASTER_UP, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 1f60954c12f7..844d3e3a65dd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -3060,7 +3060,7 @@ void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw, u64 key) key, mlx5_esw_offloads_devcom_event, esw); - if (IS_ERR_OR_NULL(esw->devcom)) + if (IS_ERR(esw->devcom)) return; mlx5_devcom_send_event(esw->devcom, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index d14459e5c04f..69d482f7c5a2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -703,8 +703,10 @@ int mlx5_deactivate_lag(struct mlx5_lag *ldev) return err; } - if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &flags)) + if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &flags)) { mlx5_lag_port_sel_destroy(ldev); + ldev->buckets = 1; + } if (mlx5_lag_has_drop_rule(ldev)) mlx5_lag_drop_rule_cleanup(ldev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c index e7d59cfa8708..7b0766c89f4c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c @@ -220,7 +220,7 @@ mlx5_devcom_register_component(struct mlx5_devcom_dev *devc, struct mlx5_devcom_comp *comp; if (IS_ERR_OR_NULL(devc)) - return NULL; + return ERR_PTR(-EINVAL); mutex_lock(&comp_list_lock); comp = devcom_component_get(devc, id, key, handler); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c index 5b28084e8a03..dd5d186dc614 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c @@ -213,8 +213,8 @@ static int sd_register(struct mlx5_core_dev *dev) sd = mlx5_get_sd(dev); devcom = mlx5_devcom_register_component(dev->priv.devc, MLX5_DEVCOM_SD_GROUP, sd->group_id, NULL, dev); - if (!devcom) - return -ENOMEM; + if (IS_ERR(devcom)) + return PTR_ERR(devcom); sd->devcom = devcom; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 59806553889e..331ce47f51a1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -956,7 +956,7 @@ static void mlx5_register_hca_devcom_comp(struct mlx5_core_dev *dev) mlx5_devcom_register_component(dev->priv.devc, MLX5_DEVCOM_HCA_PORTS, mlx5_query_nic_system_image_guid(dev), NULL, dev); - if (IS_ERR_OR_NULL(dev->priv.hca_devcom_comp)) + if (IS_ERR(dev->priv.hca_devcom_comp)) mlx5_core_err(dev, "Failed to register devcom HCA component\n"); } @@ -1699,12 +1699,15 @@ int mlx5_init_one_light(struct mlx5_core_dev *dev) err = mlx5_devlink_params_register(priv_to_devlink(dev)); if (err) { mlx5_core_warn(dev, "mlx5_devlink_param_reg err = %d\n", err); - goto query_hca_caps_err; + goto params_reg_err; } devl_unlock(devlink); return 0; +params_reg_err: + devl_unregister(devlink); + devl_unlock(devlink); query_hca_caps_err: devl_unregister(devlink); devl_unlock(devlink); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c index e3bf8c7e4baa..7ebe71280827 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c @@ -75,7 +75,6 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia goto peer_devlink_set_err; } - devlink_register(devlink); return 0; peer_devlink_set_err: diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c index 523e0c470894..55f255a3c9db 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c @@ -36,6 +36,27 @@ struct sparx5_tc_flower_template { u16 l3_proto; /* protocol specified in the template */ }; +/* SparX-5 VCAP fragment types: + * 0 = no fragment, 1 = initial fragment, + * 2 = suspicious fragment, 3 = valid follow-up fragment + */ +enum { /* key / mask */ + FRAG_NOT = 0x03, /* 0 / 3 */ + FRAG_SOME = 0x11, /* 1 / 1 */ + FRAG_FIRST = 0x13, /* 1 / 3 */ + FRAG_LATER = 0x33, /* 3 / 3 */ + FRAG_INVAL = 0xff, /* invalid */ +}; + +/* Flower fragment flag to VCAP fragment type mapping */ +static const u8 sparx5_vcap_frag_map[4][4] = { /* is_frag */ + { FRAG_INVAL, FRAG_INVAL, FRAG_INVAL, FRAG_FIRST }, /* 0/0 */ + { FRAG_NOT, FRAG_NOT, FRAG_INVAL, FRAG_INVAL }, /* 0/1 */ + { FRAG_INVAL, FRAG_INVAL, FRAG_INVAL, FRAG_INVAL }, /* 1/0 */ + { FRAG_SOME, FRAG_LATER, FRAG_INVAL, FRAG_FIRST } /* 1/1 */ + /* 0/0 0/1 1/0 1/1 <-- first_frag */ +}; + static int sparx5_tc_flower_es0_tpid(struct vcap_tc_flower_parse_usage *st) { @@ -145,29 +166,27 @@ sparx5_tc_flower_handler_control_usage(struct vcap_tc_flower_parse_usage *st) flow_rule_match_control(st->frule, &mt); if (mt.mask->flags) { - if (mt.mask->flags & FLOW_DIS_FIRST_FRAG) { - if (mt.key->flags & FLOW_DIS_FIRST_FRAG) { - value = 1; /* initial fragment */ - mask = 0x3; - } else { - if (mt.mask->flags & FLOW_DIS_IS_FRAGMENT) { - value = 3; /* follow up fragment */ - mask = 0x3; - } else { - value = 0; /* no fragment */ - mask = 0x3; - } - } - } else { - if (mt.mask->flags & FLOW_DIS_IS_FRAGMENT) { - value = 3; /* follow up fragment */ - mask = 0x3; - } else { - value = 0; /* no fragment */ - mask = 0x3; - } + u8 is_frag_key = !!(mt.key->flags & FLOW_DIS_IS_FRAGMENT); + u8 is_frag_mask = !!(mt.mask->flags & FLOW_DIS_IS_FRAGMENT); + u8 is_frag_idx = (is_frag_key << 1) | is_frag_mask; + + u8 first_frag_key = !!(mt.key->flags & FLOW_DIS_FIRST_FRAG); + u8 first_frag_mask = !!(mt.mask->flags & FLOW_DIS_FIRST_FRAG); + u8 first_frag_idx = (first_frag_key << 1) | first_frag_mask; + + /* Lookup verdict based on the 2 + 2 input bits */ + u8 vdt = sparx5_vcap_frag_map[is_frag_idx][first_frag_idx]; + + if (vdt == FRAG_INVAL) { + NL_SET_ERR_MSG_MOD(st->fco->common.extack, + "Match on invalid fragment flag combination"); + return -EINVAL; } + /* Extract VCAP fragment key and mask from verdict */ + value = (vdt >> 4) & 0x3; + mask = vdt & 0x3; + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L3_FRAGMENT_TYPE, value, mask); diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index ba01c8cc3c90..fcb756d77681 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -769,25 +769,28 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q) dma_addr_t dma_addr; int rx_packets = 0; u8 desc_status; - u16 pkt_len; + u16 desc_len; u8 die_dt; int entry; int limit; int i; - entry = priv->cur_rx[q] % priv->num_rx_ring[q]; limit = priv->dirty_rx[q] + priv->num_rx_ring[q] - priv->cur_rx[q]; stats = &priv->stats[q]; - desc = &priv->rx_ring[q].desc[entry]; - for (i = 0; i < limit && rx_packets < *quota && desc->die_dt != DT_FEMPTY; i++) { + for (i = 0; i < limit; i++, priv->cur_rx[q]++) { + entry = priv->cur_rx[q] % priv->num_rx_ring[q]; + desc = &priv->rx_ring[q].desc[entry]; + if (rx_packets == *quota || desc->die_dt == DT_FEMPTY) + break; + /* Descriptor type must be checked before all other reads */ dma_rmb(); desc_status = desc->msc; - pkt_len = le16_to_cpu(desc->ds_cc) & RX_DS; + desc_len = le16_to_cpu(desc->ds_cc) & RX_DS; /* We use 0-byte descriptors to mark the DMA mapping errors */ - if (!pkt_len) + if (!desc_len) continue; if (desc_status & MSC_MC) @@ -808,25 +811,25 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q) switch (die_dt) { case DT_FSINGLE: skb = ravb_get_skb_gbeth(ndev, entry, desc); - skb_put(skb, pkt_len); + skb_put(skb, desc_len); skb->protocol = eth_type_trans(skb, ndev); if (ndev->features & NETIF_F_RXCSUM) ravb_rx_csum_gbeth(skb); napi_gro_receive(&priv->napi[q], skb); rx_packets++; - stats->rx_bytes += pkt_len; + stats->rx_bytes += desc_len; break; case DT_FSTART: priv->rx_1st_skb = ravb_get_skb_gbeth(ndev, entry, desc); - skb_put(priv->rx_1st_skb, pkt_len); + skb_put(priv->rx_1st_skb, desc_len); break; case DT_FMID: skb = ravb_get_skb_gbeth(ndev, entry, desc); skb_copy_to_linear_data_offset(priv->rx_1st_skb, priv->rx_1st_skb->len, skb->data, - pkt_len); - skb_put(priv->rx_1st_skb, pkt_len); + desc_len); + skb_put(priv->rx_1st_skb, desc_len); dev_kfree_skb(skb); break; case DT_FEND: @@ -834,23 +837,20 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q) skb_copy_to_linear_data_offset(priv->rx_1st_skb, priv->rx_1st_skb->len, skb->data, - pkt_len); - skb_put(priv->rx_1st_skb, pkt_len); + desc_len); + skb_put(priv->rx_1st_skb, desc_len); dev_kfree_skb(skb); priv->rx_1st_skb->protocol = eth_type_trans(priv->rx_1st_skb, ndev); if (ndev->features & NETIF_F_RXCSUM) - ravb_rx_csum_gbeth(skb); + ravb_rx_csum_gbeth(priv->rx_1st_skb); + stats->rx_bytes += priv->rx_1st_skb->len; napi_gro_receive(&priv->napi[q], priv->rx_1st_skb); rx_packets++; - stats->rx_bytes += pkt_len; break; } } - - entry = (++priv->cur_rx[q]) % priv->num_rx_ring[q]; - desc = &priv->rx_ring[q].desc[entry]; } /* Refill the RX ring buffers. */ @@ -891,30 +891,29 @@ static bool ravb_rx_rcar(struct net_device *ndev, int *quota, int q) { struct ravb_private *priv = netdev_priv(ndev); const struct ravb_hw_info *info = priv->info; - int entry = priv->cur_rx[q] % priv->num_rx_ring[q]; - int boguscnt = (priv->dirty_rx[q] + priv->num_rx_ring[q]) - - priv->cur_rx[q]; struct net_device_stats *stats = &priv->stats[q]; struct ravb_ex_rx_desc *desc; + unsigned int limit, i; struct sk_buff *skb; dma_addr_t dma_addr; struct timespec64 ts; + int rx_packets = 0; u8 desc_status; u16 pkt_len; - int limit; + int entry; + + limit = priv->dirty_rx[q] + priv->num_rx_ring[q] - priv->cur_rx[q]; + for (i = 0; i < limit; i++, priv->cur_rx[q]++) { + entry = priv->cur_rx[q] % priv->num_rx_ring[q]; + desc = &priv->rx_ring[q].ex_desc[entry]; + if (rx_packets == *quota || desc->die_dt == DT_FEMPTY) + break; - boguscnt = min(boguscnt, *quota); - limit = boguscnt; - desc = &priv->rx_ring[q].ex_desc[entry]; - while (desc->die_dt != DT_FEMPTY) { /* Descriptor type must be checked before all other reads */ dma_rmb(); desc_status = desc->msc; pkt_len = le16_to_cpu(desc->ds_cc) & RX_DS; - if (--boguscnt < 0) - break; - /* We use 0-byte descriptors to mark the DMA mapping errors */ if (!pkt_len) continue; @@ -960,12 +959,9 @@ static bool ravb_rx_rcar(struct net_device *ndev, int *quota, int q) if (ndev->features & NETIF_F_RXCSUM) ravb_rx_csum(skb); napi_gro_receive(&priv->napi[q], skb); - stats->rx_packets++; + rx_packets++; stats->rx_bytes += pkt_len; } - - entry = (++priv->cur_rx[q]) % priv->num_rx_ring[q]; - desc = &priv->rx_ring[q].ex_desc[entry]; } /* Refill the RX ring buffers. */ @@ -995,9 +991,9 @@ static bool ravb_rx_rcar(struct net_device *ndev, int *quota, int q) desc->die_dt = DT_FEMPTY; } - *quota -= limit - (++boguscnt); - - return boguscnt <= 0; + stats->rx_packets += rx_packets; + *quota -= rx_packets; + return *quota == 0; } /* Packet receive function for Ethernet AVB */ diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index a6fefe675ef1..3b7d4ac1e7be 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -553,6 +553,7 @@ extern const struct stmmac_hwtimestamp stmmac_ptp; extern const struct stmmac_mode_ops dwmac4_ring_mode_ops; struct mac_link { + u32 caps; u32 speed_mask; u32 speed10; u32 speed100; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index b21d99faa2d0..e1b761dcfa1d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -1096,6 +1096,8 @@ static struct mac_device_info *sun8i_dwmac_setup(void *ppriv) priv->dev->priv_flags |= IFF_UNICAST_FLT; + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000; /* The loopback bit seems to be re-set when link change * Simply mask it each time * Speed 10/100/1000 are set in BIT(2)/BIT(3) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index 3927609abc44..8555299443f4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -539,6 +539,8 @@ int dwmac1000_setup(struct stmmac_priv *priv) if (mac->multicast_filter_bins) mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins); + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000; mac->link.duplex = GMAC_CONTROL_DM; mac->link.speed10 = GMAC_CONTROL_PS; mac->link.speed100 = GMAC_CONTROL_PS | GMAC_CONTROL_FES; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c index a6e8d7bd9588..7667d103cd0e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c @@ -175,6 +175,8 @@ int dwmac100_setup(struct stmmac_priv *priv) dev_info(priv->device, "\tDWMAC100\n"); mac->pcsr = priv->ioaddr; + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100; mac->link.duplex = MAC_CONTROL_F; mac->link.speed10 = 0; mac->link.speed100 = 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index cef25efbdff9..a38226d7cc6a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -70,7 +70,10 @@ static void dwmac4_core_init(struct mac_device_info *hw, static void dwmac4_phylink_get_caps(struct stmmac_priv *priv) { - priv->phylink_config.mac_capabilities |= MAC_2500FD; + if (priv->plat->tx_queues_to_use > 1) + priv->hw->link.caps &= ~(MAC_10HD | MAC_100HD | MAC_1000HD); + else + priv->hw->link.caps |= (MAC_10HD | MAC_100HD | MAC_1000HD); } static void dwmac4_rx_queue_enable(struct mac_device_info *hw, @@ -1378,6 +1381,8 @@ int dwmac4_setup(struct stmmac_priv *priv) if (mac->multicast_filter_bins) mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins); + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000 | MAC_2500FD; mac->link.duplex = GMAC_CONFIG_DM; mac->link.speed10 = GMAC_CONFIG_PS; mac->link.speed100 = GMAC_CONFIG_FES | GMAC_CONFIG_PS; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index e841e312077e..f8e7775bb633 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -47,14 +47,6 @@ static void dwxgmac2_core_init(struct mac_device_info *hw, writel(XGMAC_INT_DEFAULT_EN, ioaddr + XGMAC_INT_EN); } -static void xgmac_phylink_get_caps(struct stmmac_priv *priv) -{ - priv->phylink_config.mac_capabilities |= MAC_2500FD | MAC_5000FD | - MAC_10000FD | MAC_25000FD | - MAC_40000FD | MAC_50000FD | - MAC_100000FD; -} - static void dwxgmac2_set_mac(void __iomem *ioaddr, bool enable) { u32 tx = readl(ioaddr + XGMAC_TX_CONFIG); @@ -1540,7 +1532,6 @@ static void dwxgmac3_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg * const struct stmmac_ops dwxgmac210_ops = { .core_init = dwxgmac2_core_init, - .phylink_get_caps = xgmac_phylink_get_caps, .set_mac = dwxgmac2_set_mac, .rx_ipc = dwxgmac2_rx_ipc, .rx_queue_enable = dwxgmac2_rx_queue_enable, @@ -1601,7 +1592,6 @@ static void dwxlgmac2_rx_queue_enable(struct mac_device_info *hw, u8 mode, const struct stmmac_ops dwxlgmac2_ops = { .core_init = dwxgmac2_core_init, - .phylink_get_caps = xgmac_phylink_get_caps, .set_mac = dwxgmac2_set_mac, .rx_ipc = dwxgmac2_rx_ipc, .rx_queue_enable = dwxlgmac2_rx_queue_enable, @@ -1661,6 +1651,9 @@ int dwxgmac2_setup(struct stmmac_priv *priv) if (mac->multicast_filter_bins) mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins); + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_1000FD | MAC_2500FD | MAC_5000FD | + MAC_10000FD; mac->link.duplex = 0; mac->link.speed10 = XGMAC_CONFIG_SS_10_MII; mac->link.speed100 = XGMAC_CONFIG_SS_100_MII; @@ -1698,6 +1691,11 @@ int dwxlgmac2_setup(struct stmmac_priv *priv) if (mac->multicast_filter_bins) mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins); + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_1000FD | MAC_2500FD | MAC_5000FD | + MAC_10000FD | MAC_25000FD | + MAC_40000FD | MAC_50000FD | + MAC_100000FD; mac->link.duplex = 0; mac->link.speed1000 = XLGMAC_CONFIG_SS_1000; mac->link.speed2500 = XLGMAC_CONFIG_SS_2500; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 24cd80490d19..7c6fb14b5555 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1198,17 +1198,6 @@ static int stmmac_init_phy(struct net_device *dev) return ret; } -static void stmmac_set_half_duplex(struct stmmac_priv *priv) -{ - /* Half-Duplex can only work with single tx queue */ - if (priv->plat->tx_queues_to_use > 1) - priv->phylink_config.mac_capabilities &= - ~(MAC_10HD | MAC_100HD | MAC_1000HD); - else - priv->phylink_config.mac_capabilities |= - (MAC_10HD | MAC_100HD | MAC_1000HD); -} - static int stmmac_phy_setup(struct stmmac_priv *priv) { struct stmmac_mdio_bus_data *mdio_bus_data; @@ -1236,15 +1225,11 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) xpcs_get_interfaces(priv->hw->xpcs, priv->phylink_config.supported_interfaces); - priv->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | - MAC_10FD | MAC_100FD | - MAC_1000FD; - - stmmac_set_half_duplex(priv); - /* Get the MAC specific capabilities */ stmmac_mac_phylink_get_caps(priv); + priv->phylink_config.mac_capabilities = priv->hw->link.caps; + max_speed = priv->plat->max_speed; if (max_speed) phylink_limit_mac_speed(&priv->phylink_config, max_speed); @@ -7342,6 +7327,7 @@ int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt) { struct stmmac_priv *priv = netdev_priv(dev); int ret = 0, i; + int max_speed; if (netif_running(dev)) stmmac_release(dev); @@ -7355,7 +7341,14 @@ int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt) priv->rss.table[i] = ethtool_rxfh_indir_default(i, rx_cnt); - stmmac_set_half_duplex(priv); + stmmac_mac_phylink_get_caps(priv); + + priv->phylink_config.mac_capabilities = priv->hw->link.caps; + + max_speed = priv->plat->max_speed; + if (max_speed) + phylink_limit_mac_speed(&priv->phylink_config, max_speed); + stmmac_napi_add(dev); if (netif_running(dev)) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 2939a21ca74f..1d00e21808c1 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -2793,6 +2793,8 @@ static void am65_cpsw_unregister_devlink(struct am65_cpsw_common *common) static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) { + struct am65_cpsw_rx_chn *rx_chan = &common->rx_chns; + struct am65_cpsw_tx_chn *tx_chan = common->tx_chns; struct device *dev = common->dev; struct am65_cpsw_port *port; int ret = 0, i; @@ -2805,6 +2807,22 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) if (ret) return ret; + /* The DMA Channels are not guaranteed to be in a clean state. + * Reset and disable them to ensure that they are back to the + * clean state and ready to be used. + */ + for (i = 0; i < common->tx_ch_num; i++) { + k3_udma_glue_reset_tx_chn(tx_chan[i].tx_chn, &tx_chan[i], + am65_cpsw_nuss_tx_cleanup); + k3_udma_glue_disable_tx_chn(tx_chan[i].tx_chn); + } + + for (i = 0; i < AM65_CPSW_MAX_RX_FLOWS; i++) + k3_udma_glue_reset_rx_chn(rx_chan->rx_chn, i, rx_chan, + am65_cpsw_nuss_rx_cleanup, !!i); + + k3_udma_glue_disable_rx_chn(rx_chan->rx_chn); + ret = am65_cpsw_nuss_register_devlink(common); if (ret) return ret; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 0b3f21cba552..92da8c03d960 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -2125,14 +2125,16 @@ static ssize_t tun_put_user(struct tun_struct *tun, tun_is_little_endian(tun), true, vlan_hlen)) { struct skb_shared_info *sinfo = skb_shinfo(skb); - pr_err("unexpected GSO type: " - "0x%x, gso_size %d, hdr_len %d\n", - sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size), - tun16_to_cpu(tun, gso.hdr_len)); - print_hex_dump(KERN_ERR, "tun: ", - DUMP_PREFIX_NONE, - 16, 1, skb->head, - min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true); + + if (net_ratelimit()) { + netdev_err(tun->dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n", + sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size), + tun16_to_cpu(tun, gso.hdr_len)); + print_hex_dump(KERN_ERR, "tun: ", + DUMP_PREFIX_NONE, + 16, 1, skb->head, + min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true); + } WARN_ON_ONCE(1); return -EINVAL; } diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index a9c418890a1c..752f821a1990 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -1317,6 +1317,8 @@ static int ax88179_bind(struct usbnet *dev, struct usb_interface *intf) netif_set_tso_max_size(dev->net, 16384); + ax88179_reset(dev); + return 0; } @@ -1695,7 +1697,6 @@ static const struct driver_info ax88179_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1708,7 +1709,6 @@ static const struct driver_info ax88178a_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index e2e181378f41..edc34402e787 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1431,6 +1431,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x2692, 0x9025, 4)}, /* Cellient MPL200 (rebranded Qualcomm 05c6:9025) */ {QMI_QUIRK_SET_DTR(0x1546, 0x1312, 4)}, /* u-blox LARA-R6 01B */ {QMI_QUIRK_SET_DTR(0x1546, 0x1342, 4)}, /* u-blox LARA-L6 */ + {QMI_QUIRK_SET_DTR(0x33f8, 0x0104, 4)}, /* Rolling RW101 RMNET */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index 2c8e964425dc..43778b088ffa 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -292,13 +292,16 @@ out: static void ism_free_dmb(struct ism_dev *ism, struct ism_dmb *dmb) { clear_bit(dmb->sba_idx, ism->sba_bitmap); - dma_free_coherent(&ism->pdev->dev, dmb->dmb_len, - dmb->cpu_addr, dmb->dma_addr); + dma_unmap_page(&ism->pdev->dev, dmb->dma_addr, dmb->dmb_len, + DMA_FROM_DEVICE); + folio_put(virt_to_folio(dmb->cpu_addr)); } static int ism_alloc_dmb(struct ism_dev *ism, struct ism_dmb *dmb) { + struct folio *folio; unsigned long bit; + int rc; if (PAGE_ALIGN(dmb->dmb_len) > dma_get_max_seg_size(&ism->pdev->dev)) return -EINVAL; @@ -315,14 +318,30 @@ static int ism_alloc_dmb(struct ism_dev *ism, struct ism_dmb *dmb) test_and_set_bit(dmb->sba_idx, ism->sba_bitmap)) return -EINVAL; - dmb->cpu_addr = dma_alloc_coherent(&ism->pdev->dev, dmb->dmb_len, - &dmb->dma_addr, - GFP_KERNEL | __GFP_NOWARN | - __GFP_NOMEMALLOC | __GFP_NORETRY); - if (!dmb->cpu_addr) - clear_bit(dmb->sba_idx, ism->sba_bitmap); + folio = folio_alloc(GFP_KERNEL | __GFP_NOWARN | __GFP_NOMEMALLOC | + __GFP_NORETRY, get_order(dmb->dmb_len)); - return dmb->cpu_addr ? 0 : -ENOMEM; + if (!folio) { + rc = -ENOMEM; + goto out_bit; + } + + dmb->cpu_addr = folio_address(folio); + dmb->dma_addr = dma_map_page(&ism->pdev->dev, + virt_to_page(dmb->cpu_addr), 0, + dmb->dmb_len, DMA_FROM_DEVICE); + if (dma_mapping_error(&ism->pdev->dev, dmb->dma_addr)) { + rc = -ENOMEM; + goto out_free; + } + + return 0; + +out_free: + kfree(dmb->cpu_addr); +out_bit: + clear_bit(dmb->sba_idx, ism->sba_bitmap); + return rc; } int ism_register_dmb(struct ism_dev *ism, struct ism_dmb *dmb, diff --git a/include/linux/udp.h b/include/linux/udp.h index 17539d089666..e398e1dbd2d3 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -108,7 +108,7 @@ struct udp_sock { #define udp_assign_bit(nr, sk, val) \ assign_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags, val) -#define UDP_MAX_SEGMENTS (1 << 6UL) +#define UDP_MAX_SEGMENTS (1 << 7UL) #define udp_sk(ptr) container_of_const(ptr, struct udp_sock, inet.sk) diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index a763dd327c6e..9abb7ee40d72 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -336,7 +336,7 @@ int nf_flow_rule_route_ipv6(struct net *net, struct flow_offload *flow, int nf_flow_table_offload_init(void); void nf_flow_table_offload_exit(void); -static inline __be16 nf_flow_pppoe_proto(const struct sk_buff *skb) +static inline __be16 __nf_flow_pppoe_proto(const struct sk_buff *skb) { __be16 proto; @@ -352,6 +352,16 @@ static inline __be16 nf_flow_pppoe_proto(const struct sk_buff *skb) return 0; } +static inline bool nf_flow_pppoe_proto(struct sk_buff *skb, __be16 *inner_proto) +{ + if (!pskb_may_pull(skb, PPPOE_SES_HLEN)) + return false; + + *inner_proto = __nf_flow_pppoe_proto(skb); + + return true; +} + #define NF_FLOW_TABLE_STAT_INC(net, count) __this_cpu_inc((net)->ft.stat->count) #define NF_FLOW_TABLE_STAT_DEC(net, count) __this_cpu_dec((net)->ft.stat->count) #define NF_FLOW_TABLE_STAT_INC_ATOMIC(net, count) \ diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index e27c28b612e4..3f1ed467f951 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -307,9 +307,23 @@ static inline void *nft_elem_priv_cast(const struct nft_elem_priv *priv) return (void *)priv; } + +/** + * enum nft_iter_type - nftables set iterator type + * + * @NFT_ITER_READ: read-only iteration over set elements + * @NFT_ITER_UPDATE: iteration under mutex to update set element state + */ +enum nft_iter_type { + NFT_ITER_UNSPEC, + NFT_ITER_READ, + NFT_ITER_UPDATE, +}; + struct nft_set; struct nft_set_iter { u8 genmask; + enum nft_iter_type type:8; unsigned int count; unsigned int skip; int err; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index cefe0c4bdae3..41ca14e81d55 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -117,6 +117,7 @@ struct Qdisc { struct qdisc_skb_head q; struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; + int owner; unsigned long state; unsigned long state2; /* must be written under qdisc spinlock */ struct Qdisc *next_sched; diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index f21097e73482..ceaa5a89b947 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -30,7 +30,7 @@ br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb) return netif_receive_skb(skb); } -static int br_pass_frame_up(struct sk_buff *skb) +static int br_pass_frame_up(struct sk_buff *skb, bool promisc) { struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev; struct net_bridge *br = netdev_priv(brdev); @@ -65,6 +65,8 @@ static int br_pass_frame_up(struct sk_buff *skb) br_multicast_count(br, NULL, skb, br_multicast_igmp_type(skb), BR_MCAST_DIR_TX); + BR_INPUT_SKB_CB(skb)->promisc = promisc; + return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, dev_net(indev), NULL, skb, indev, NULL, br_netif_receive_skb); @@ -82,6 +84,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb struct net_bridge_mcast *brmctx; struct net_bridge_vlan *vlan; struct net_bridge *br; + bool promisc; u16 vid = 0; u8 state; @@ -137,7 +140,9 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if (p->flags & BR_LEARNING) br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, 0); - local_rcv = !!(br->dev->flags & IFF_PROMISC); + promisc = !!(br->dev->flags & IFF_PROMISC); + local_rcv = promisc; + if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) { /* by definition the broadcast is also a multicast address */ if (is_broadcast_ether_addr(eth_hdr(skb)->h_dest)) { @@ -200,7 +205,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb unsigned long now = jiffies; if (test_bit(BR_FDB_LOCAL, &dst->flags)) - return br_pass_frame_up(skb); + return br_pass_frame_up(skb, false); if (now != dst->used) dst->used = now; @@ -213,7 +218,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb } if (local_rcv) - return br_pass_frame_up(skb); + return br_pass_frame_up(skb, promisc); out: return 0; @@ -386,6 +391,8 @@ static rx_handler_result_t br_handle_frame(struct sk_buff **pskb) goto forward; } + BR_INPUT_SKB_CB(skb)->promisc = false; + /* The else clause should be hit when nf_hook(): * - returns < 0 (drop/error) * - returns = 0 (stolen/nf_queue) diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 35e10c5a766d..22e35623c148 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -600,11 +600,17 @@ static unsigned int br_nf_local_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { + bool promisc = BR_INPUT_SKB_CB(skb)->promisc; struct nf_conntrack *nfct = skb_nfct(skb); const struct nf_ct_hook *ct_hook; struct nf_conn *ct; int ret; + if (promisc) { + nf_reset_ct(skb); + return NF_ACCEPT; + } + if (!nfct || skb->pkt_type == PACKET_HOST) return NF_ACCEPT; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 86ea5e6689b5..d4bedc87b1d8 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -589,6 +589,7 @@ struct br_input_skb_cb { #endif u8 proxyarp_replied:1; u8 src_port_isolated:1; + u8 promisc:1; #ifdef CONFIG_BRIDGE_VLAN_FILTERING u8 vlan_filtered:1; #endif diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 6f877e31709b..c3c51b9a6826 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -294,18 +294,24 @@ static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb, static unsigned int nf_ct_bridge_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - enum ip_conntrack_info ctinfo; + bool promisc = BR_INPUT_SKB_CB(skb)->promisc; + struct nf_conntrack *nfct = skb_nfct(skb); struct nf_conn *ct; - if (skb->pkt_type == PACKET_HOST) + if (promisc) { + nf_reset_ct(skb); + return NF_ACCEPT; + } + + if (!nfct || skb->pkt_type == PACKET_HOST) return NF_ACCEPT; /* nf_conntrack_confirm() cannot handle concurrent clones, * this happens for broad/multicast frames with e.g. macvlan on top * of the bridge device. */ - ct = nf_ct_get(skb, &ctinfo); - if (!ct || nf_ct_is_confirmed(ct) || nf_ct_is_template(ct)) + ct = container_of(nfct, struct nf_conn, ct_general); + if (nf_ct_is_confirmed(ct) || nf_ct_is_template(ct)) return NF_ACCEPT; /* let inet prerouting call conntrack again */ diff --git a/net/core/dev.c b/net/core/dev.c index 984ff8b9d0e1..331848eca7d3 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3775,6 +3775,10 @@ no_lock_out: return rc; } + if (unlikely(READ_ONCE(q->owner) == smp_processor_id())) { + kfree_skb_reason(skb, SKB_DROP_REASON_TC_RECLASSIFY_LOOP); + return NET_XMIT_DROP; + } /* * Heuristic to force contended enqueues to serialize on a * separate lock before trying to get qdisc main lock. @@ -3814,7 +3818,9 @@ no_lock_out: qdisc_run_end(q); rc = NET_XMIT_SUCCESS; } else { + WRITE_ONCE(q->owner, smp_processor_id()); rc = dev_qdisc_enqueue(skb, q, &to_free, txq); + WRITE_ONCE(q->owner, -1); if (qdisc_run_begin(q)) { if (unlikely(contended)) { spin_unlock(&q->busylock); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 48741352a88a..c484b1c0fc00 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1050,6 +1050,11 @@ next: e++; } } + + /* Don't let NLM_DONE coalesce into a message, even if it could. + * Some user space expects NLM_DONE in a separate recv(). + */ + err = skb->len; out: cb->args[1] = e; diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c index 9505f9d188ff..6eef15648b7b 100644 --- a/net/netfilter/nf_flow_table_inet.c +++ b/net/netfilter/nf_flow_table_inet.c @@ -21,7 +21,8 @@ nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb, proto = veth->h_vlan_encapsulated_proto; break; case htons(ETH_P_PPP_SES): - proto = nf_flow_pppoe_proto(skb); + if (!nf_flow_pppoe_proto(skb, &proto)) + return NF_ACCEPT; break; default: proto = skb->protocol; diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index e45fade76409..5383bed3d3e0 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -157,7 +157,7 @@ static void nf_flow_tuple_encap(struct sk_buff *skb, tuple->encap[i].proto = skb->protocol; break; case htons(ETH_P_PPP_SES): - phdr = (struct pppoe_hdr *)skb_mac_header(skb); + phdr = (struct pppoe_hdr *)skb_network_header(skb); tuple->encap[i].id = ntohs(phdr->sid); tuple->encap[i].proto = skb->protocol; break; @@ -273,10 +273,11 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, return NF_STOLEN; } -static bool nf_flow_skb_encap_protocol(const struct sk_buff *skb, __be16 proto, +static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto, u32 *offset) { struct vlan_ethhdr *veth; + __be16 inner_proto; switch (skb->protocol) { case htons(ETH_P_8021Q): @@ -287,7 +288,8 @@ static bool nf_flow_skb_encap_protocol(const struct sk_buff *skb, __be16 proto, } break; case htons(ETH_P_PPP_SES): - if (nf_flow_pppoe_proto(skb) == proto) { + if (nf_flow_pppoe_proto(skb, &inner_proto) && + inner_proto == proto) { *offset += PPPOE_SES_HLEN; return true; } @@ -316,7 +318,7 @@ static void nf_flow_encap_pop(struct sk_buff *skb, skb_reset_network_header(skb); break; case htons(ETH_P_PPP_SES): - skb->protocol = nf_flow_pppoe_proto(skb); + skb->protocol = __nf_flow_pppoe_proto(skb); skb_pull(skb, PPPOE_SES_HLEN); skb_reset_network_header(skb); break; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d89d77946719..167074283ea9 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -594,6 +594,12 @@ static int nft_mapelem_deactivate(const struct nft_ctx *ctx, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { + struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); + + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + + nft_set_elem_change_active(ctx->net, set, ext); nft_setelem_data_deactivate(ctx->net, set, elem_priv); return 0; @@ -617,6 +623,7 @@ static void nft_map_catchall_deactivate(const struct nft_ctx *ctx, if (!nft_set_elem_active(ext, genmask)) continue; + nft_set_elem_change_active(ctx->net, set, ext); nft_setelem_data_deactivate(ctx->net, set, catchall->elem); break; } @@ -626,6 +633,7 @@ static void nft_map_deactivate(const struct nft_ctx *ctx, struct nft_set *set) { struct nft_set_iter iter = { .genmask = nft_genmask_next(ctx->net), + .type = NFT_ITER_UPDATE, .fn = nft_mapelem_deactivate, }; @@ -3060,7 +3068,7 @@ static const struct nft_expr_type *__nft_expr_type_get(u8 family, { const struct nft_expr_type *type, *candidate = NULL; - list_for_each_entry(type, &nf_tables_expressions, list) { + list_for_each_entry_rcu(type, &nf_tables_expressions, list) { if (!nla_strcmp(nla, type->name)) { if (!type->family && !candidate) candidate = type; @@ -3092,9 +3100,13 @@ static const struct nft_expr_type *nft_expr_type_get(struct net *net, if (nla == NULL) return ERR_PTR(-EINVAL); + rcu_read_lock(); type = __nft_expr_type_get(family, nla); - if (type != NULL && try_module_get(type->owner)) + if (type != NULL && try_module_get(type->owner)) { + rcu_read_unlock(); return type; + } + rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES @@ -3875,6 +3887,9 @@ int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_data *data; int err; + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) return 0; @@ -3898,17 +3913,20 @@ int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set) { - u8 genmask = nft_genmask_next(ctx->net); + struct nft_set_iter dummy_iter = { + .genmask = nft_genmask_next(ctx->net), + }; struct nft_set_elem_catchall *catchall; + struct nft_set_ext *ext; int ret = 0; list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_set_elem_active(ext, genmask)) + if (!nft_set_elem_active(ext, dummy_iter.genmask)) continue; - ret = nft_setelem_validate(ctx, set, NULL, catchall->elem); + ret = nft_setelem_validate(ctx, set, &dummy_iter, catchall->elem); if (ret < 0) return ret; } @@ -5397,6 +5415,11 @@ static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); + + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + return nft_setelem_data_validate(ctx, set, elem_priv); } @@ -5441,6 +5464,7 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, } iter.genmask = nft_genmask_next(ctx->net); + iter.type = NFT_ITER_UPDATE; iter.skip = 0; iter.count = 0; iter.err = 0; @@ -5488,6 +5512,13 @@ static int nft_mapelem_activate(const struct nft_ctx *ctx, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { + struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); + + /* called from abort path, reverse check to undo changes. */ + if (nft_set_elem_active(ext, iter->genmask)) + return 0; + + nft_clear(ctx->net, ext); nft_setelem_data_activate(ctx->net, set, elem_priv); return 0; @@ -5505,6 +5536,7 @@ static void nft_map_catchall_activate(const struct nft_ctx *ctx, if (!nft_set_elem_active(ext, genmask)) continue; + nft_clear(ctx->net, ext); nft_setelem_data_activate(ctx->net, set, catchall->elem); break; } @@ -5514,6 +5546,7 @@ static void nft_map_activate(const struct nft_ctx *ctx, struct nft_set *set) { struct nft_set_iter iter = { .genmask = nft_genmask_next(ctx->net), + .type = NFT_ITER_UPDATE, .fn = nft_mapelem_activate, }; @@ -5778,6 +5811,9 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx, const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_set_dump_args *args; + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + if (nft_set_elem_expired(ext) || nft_set_elem_is_dead(ext)) return 0; @@ -5888,6 +5924,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) args.skb = skb; args.reset = dump_ctx->reset; args.iter.genmask = nft_genmask_cur(net); + args.iter.type = NFT_ITER_READ; args.iter.skip = cb->args[0]; args.iter.count = 0; args.iter.err = 0; @@ -6627,7 +6664,7 @@ static void nft_setelem_activate(struct net *net, struct nft_set *set, struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_setelem_is_catchall(set, elem_priv)) { - nft_set_elem_change_active(net, set, ext); + nft_clear(net, ext); } else { set->ops->activate(net, set, elem_priv); } @@ -7186,6 +7223,16 @@ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) } } +static int nft_setelem_active_next(const struct net *net, + const struct nft_set *set, + struct nft_elem_priv *elem_priv) +{ + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); + u8 genmask = nft_genmask_next(net); + + return nft_set_elem_active(ext, genmask); +} + static void nft_setelem_data_activate(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) @@ -7309,8 +7356,12 @@ static int nft_setelem_flush(const struct nft_ctx *ctx, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_trans *trans; + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + trans = nft_trans_alloc_gfp(ctx, NFT_MSG_DELSETELEM, sizeof(struct nft_trans_elem), GFP_ATOMIC); if (!trans) @@ -7372,6 +7423,7 @@ static int nft_set_flush(struct nft_ctx *ctx, struct nft_set *set, u8 genmask) { struct nft_set_iter iter = { .genmask = genmask, + .type = NFT_ITER_UPDATE, .fn = nft_setelem_flush, }; @@ -7607,7 +7659,7 @@ static const struct nft_object_type *__nft_obj_type_get(u32 objtype, u8 family) { const struct nft_object_type *type; - list_for_each_entry(type, &nf_tables_objects, list) { + list_for_each_entry_rcu(type, &nf_tables_objects, list) { if (type->family != NFPROTO_UNSPEC && type->family != family) continue; @@ -7623,9 +7675,13 @@ nft_obj_type_get(struct net *net, u32 objtype, u8 family) { const struct nft_object_type *type; + rcu_read_lock(); type = __nft_obj_type_get(objtype, family); - if (type != NULL && try_module_get(type->owner)) + if (type != NULL && try_module_get(type->owner)) { + rcu_read_unlock(); return type; + } + rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES @@ -10598,8 +10654,10 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) case NFT_MSG_DESTROYSETELEM: te = (struct nft_trans_elem *)trans->data; - nft_setelem_data_activate(net, te->set, te->elem_priv); - nft_setelem_activate(net, te->set, te->elem_priv); + if (!nft_setelem_active_next(net, te->set, te->elem_priv)) { + nft_setelem_data_activate(net, te->set, te->elem_priv); + nft_setelem_activate(net, te->set, te->elem_priv); + } if (!nft_setelem_is_catchall(te->set, te->elem_priv)) te->set->ndeact--; @@ -10787,6 +10845,9 @@ static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx, { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) return 0; @@ -10871,6 +10932,7 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, continue; iter.genmask = nft_genmask_next(ctx->net); + iter.type = NFT_ITER_UPDATE; iter.skip = 0; iter.count = 0; iter.err = 0; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index a0055f510e31..b314ca728a29 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -216,6 +216,7 @@ static int nft_lookup_validate(const struct nft_ctx *ctx, return 0; iter.genmask = nft_genmask_next(ctx->net); + iter.type = NFT_ITER_UPDATE; iter.skip = 0; iter.count = 0; iter.err = 0; diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 32df7a16835d..1caa04619dc6 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -172,7 +172,7 @@ static void nft_bitmap_activate(const struct net *net, nft_bitmap_location(set, nft_set_ext_key(&be->ext), &idx, &off); /* Enter 11 state. */ priv->bitmap[idx] |= (genmask << off); - nft_set_elem_change_active(net, set, &be->ext); + nft_clear(net, &be->ext); } static void nft_bitmap_flush(const struct net *net, @@ -222,8 +222,6 @@ static void nft_bitmap_walk(const struct nft_ctx *ctx, list_for_each_entry_rcu(be, &priv->list, head) { if (iter->count < iter->skip) goto cont; - if (!nft_set_elem_active(&be->ext, iter->genmask)) - goto cont; iter->err = iter->fn(ctx, set, iter, &be->priv); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 6968a3b34236..daa56dda737a 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -199,7 +199,7 @@ static void nft_rhash_activate(const struct net *net, const struct nft_set *set, { struct nft_rhash_elem *he = nft_elem_priv_cast(elem_priv); - nft_set_elem_change_active(net, set, &he->ext); + nft_clear(net, &he->ext); } static void nft_rhash_flush(const struct net *net, @@ -286,8 +286,6 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, if (iter->count < iter->skip) goto cont; - if (!nft_set_elem_active(&he->ext, iter->genmask)) - goto cont; iter->err = iter->fn(ctx, set, iter, &he->priv); if (iter->err < 0) @@ -599,7 +597,7 @@ static void nft_hash_activate(const struct net *net, const struct nft_set *set, { struct nft_hash_elem *he = nft_elem_priv_cast(elem_priv); - nft_set_elem_change_active(net, set, &he->ext); + nft_clear(net, &he->ext); } static void nft_hash_flush(const struct net *net, @@ -652,8 +650,6 @@ static void nft_hash_walk(const struct nft_ctx *ctx, struct nft_set *set, hlist_for_each_entry_rcu(he, &priv->table[i], node) { if (iter->count < iter->skip) goto cont; - if (!nft_set_elem_active(&he->ext, iter->genmask)) - goto cont; iter->err = iter->fn(ctx, set, iter, &he->priv); if (iter->err < 0) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index df8de5090246..187138afac45 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1847,7 +1847,7 @@ static void nft_pipapo_activate(const struct net *net, { struct nft_pipapo_elem *e = nft_elem_priv_cast(elem_priv); - nft_set_elem_change_active(net, set, &e->ext); + nft_clear(net, &e->ext); } /** @@ -2077,6 +2077,8 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, rules_fx = rules_f0; nft_pipapo_for_each_field(f, i, m) { + bool last = i == m->field_count - 1; + if (!pipapo_match_field(f, start, rules_fx, match_start, match_end)) break; @@ -2089,16 +2091,18 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, match_start += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); match_end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); - } - if (i == m->field_count) { - priv->dirty = true; - pipapo_drop(m, rulemap); - return; + if (last && f->mt[rulemap[i].to].e == e) { + priv->dirty = true; + pipapo_drop(m, rulemap); + return; + } } first_rule += rules_f0; } + + WARN_ON_ONCE(1); /* elem_priv not found */ } /** @@ -2115,13 +2119,15 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_iter *iter) { struct nft_pipapo *priv = nft_set_priv(set); - struct net *net = read_pnet(&set->net); const struct nft_pipapo_match *m; const struct nft_pipapo_field *f; unsigned int i, r; + WARN_ON_ONCE(iter->type != NFT_ITER_READ && + iter->type != NFT_ITER_UPDATE); + rcu_read_lock(); - if (iter->genmask == nft_genmask_cur(net)) + if (iter->type == NFT_ITER_READ) m = rcu_dereference(priv->match); else m = priv->clone; @@ -2143,9 +2149,6 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, e = f->mt[r].e; - if (!nft_set_elem_active(&e->ext, iter->genmask)) - goto cont; - iter->err = iter->fn(ctx, set, iter, &e->priv); if (iter->err < 0) goto out; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 9944fe479e53..b7ea21327549 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -532,7 +532,7 @@ static void nft_rbtree_activate(const struct net *net, { struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem_priv); - nft_set_elem_change_active(net, set, &rbe->ext); + nft_clear(net, &rbe->ext); } static void nft_rbtree_flush(const struct net *net, @@ -600,8 +600,6 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, if (iter->count < iter->skip) goto cont; - if (!nft_set_elem_active(&rbe->ext, iter->genmask)) - goto cont; iter->err = iter->fn(ctx, set, iter, &rbe->priv); if (iter->err < 0) { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index ff5336493777..4a2c763e2d11 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -974,6 +974,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, sch->enqueue = ops->enqueue; sch->dequeue = ops->dequeue; sch->dev_queue = dev_queue; + sch->owner = -1; netdev_hold(dev, &sch->dev_tracker, GFP_KERNEL); refcount_set(&sch->refcnt, 1); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index d032eb5fa6df..9a6ad5974dff 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2663,7 +2663,9 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, WRITE_ONCE(u->oob_skb, NULL); consume_skb(skb); } - } else if (!(flags & MSG_PEEK)) { + } else if (flags & MSG_PEEK) { + skb = NULL; + } else { skb_unlink(skb, &sk->sk_receive_queue); WRITE_ONCE(u->oob_skb, NULL); if (!WARN_ON_ONCE(skb_unref(skb))) @@ -2741,18 +2743,16 @@ redo: last = skb = skb_peek(&sk->sk_receive_queue); last_len = last ? last->len : 0; +again: #if IS_ENABLED(CONFIG_AF_UNIX_OOB) if (skb) { skb = manage_oob(skb, sk, flags, copied); - if (!skb) { + if (!skb && copied) { unix_state_unlock(sk); - if (copied) - break; - goto redo; + break; } } #endif -again: if (skb == NULL) { if (copied >= target) goto unlock; diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 7b89362da4bf..14bbab0cce13 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -292,15 +292,17 @@ void ksft_test_result_code(int exit_code, const char *test_name, } /* Docs seem to call for double space if directive is absent */ - if (!directive[0] && msg[0]) + if (!directive[0] && msg) directive = " # "; - va_start(args, msg); printf("%s %u %s%s", tap_code, ksft_test_num(), test_name, directive); errno = saved_errno; - vprintf(msg, args); + if (msg) { + va_start(args, msg); + vprintf(msg, args); + va_end(args); + } printf("\n"); - va_end(args); } static inline __noreturn int ksft_exit_pass(void) diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 230d62884885..ba3ddeda24bf 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -1205,7 +1205,7 @@ void __run_test(struct __fixture_metadata *f, diagnostic = "unknown"; ksft_test_result_code(t->exit_code, test_name, - diagnostic ? "%s" : "", diagnostic); + diagnostic ? "%s" : NULL, diagnostic); } static int test_harness_run(int argc, char **argv) diff --git a/tools/testing/selftests/net/tcp_ao/lib/proc.c b/tools/testing/selftests/net/tcp_ao/lib/proc.c index 2fb6dd8adba6..8b984fa04286 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/proc.c +++ b/tools/testing/selftests/net/tcp_ao/lib/proc.c @@ -86,7 +86,7 @@ static void netstat_read_type(FILE *fnetstat, struct netstat **dest, char *line) pos = strchr(line, ' ') + 1; - if (fscanf(fnetstat, type->header_name) == EOF) + if (fscanf(fnetstat, "%[^ :]", type->header_name) == EOF) test_error("fscanf(%s)", type->header_name); if (fread(&tmp, 1, 1, fnetstat) != 1 || tmp != ':') test_error("Unexpected netstat format (%c)", tmp); diff --git a/tools/testing/selftests/net/tcp_ao/lib/setup.c b/tools/testing/selftests/net/tcp_ao/lib/setup.c index 92276f916f2f..e408b9243b2c 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/setup.c +++ b/tools/testing/selftests/net/tcp_ao/lib/setup.c @@ -17,37 +17,37 @@ static pthread_mutex_t ksft_print_lock = PTHREAD_MUTEX_INITIALIZER; void __test_msg(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_print_msg(buf); + ksft_print_msg("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_ok(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_pass(buf); + ksft_test_result_pass("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_fail(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_fail(buf); + ksft_test_result_fail("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_xfail(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_xfail(buf); + ksft_test_result_xfail("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_error(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_error(buf); + ksft_test_result_error("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_skip(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_skip(buf); + ksft_test_result_skip("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } diff --git a/tools/testing/selftests/net/tcp_ao/rst.c b/tools/testing/selftests/net/tcp_ao/rst.c index 7df8b8700e39..a2fe88d35ac0 100644 --- a/tools/testing/selftests/net/tcp_ao/rst.c +++ b/tools/testing/selftests/net/tcp_ao/rst.c @@ -256,8 +256,6 @@ static int test_wait_fds(int sk[], size_t nr, bool is_writable[], static void test_client_active_rst(unsigned int port) { - /* one in queue, another accept()ed */ - unsigned int wait_for = backlog + 2; int i, sk[3], err; bool is_writable[ARRAY_SIZE(sk)] = {false}; unsigned int last = ARRAY_SIZE(sk) - 1; @@ -275,16 +273,20 @@ static void test_client_active_rst(unsigned int port) for (i = 0; i < last; i++) { err = _test_connect_socket(sk[i], this_ip_dest, port, (i == 0) ? TEST_TIMEOUT_SEC : -1); - if (err < 0) test_error("failed to connect()"); } - synchronize_threads(); /* 2: connection accept()ed, another queued */ - err = test_wait_fds(sk, last, is_writable, wait_for, TEST_TIMEOUT_SEC); + synchronize_threads(); /* 2: two connections: one accept()ed, another queued */ + err = test_wait_fds(sk, last, is_writable, last, TEST_TIMEOUT_SEC); if (err < 0) test_error("test_wait_fds(): %d", err); + /* async connect() with third sk to get into request_sock_queue */ + err = _test_connect_socket(sk[last], this_ip_dest, port, -1); + if (err < 0) + test_error("failed to connect()"); + synchronize_threads(); /* 3: close listen socket */ if (test_client_verify(sk[0], packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC)) test_fail("Failed to send data on connected socket"); @@ -292,13 +294,14 @@ static void test_client_active_rst(unsigned int port) test_ok("Verified established tcp connection"); synchronize_threads(); /* 4: finishing up */ - err = _test_connect_socket(sk[last], this_ip_dest, port, -1); - if (err < 0) - test_error("failed to connect()"); synchronize_threads(); /* 5: closed active sk */ - err = test_wait_fds(sk, ARRAY_SIZE(sk), NULL, - wait_for, TEST_TIMEOUT_SEC); + /* + * Wait for 2 connections: one accepted, another in the accept queue, + * the one in request_sock_queue won't get fully established, so + * doesn't receive an active RST, see inet_csk_listen_stop(). + */ + err = test_wait_fds(sk, last, NULL, last, TEST_TIMEOUT_SEC); if (err < 0) test_error("select(): %d", err); diff --git a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c index 452de131fa3a..517930f9721b 100644 --- a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c +++ b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c @@ -21,7 +21,7 @@ static void make_listen(int sk) static void test_vefify_ao_info(int sk, struct tcp_ao_info_opt *info, const char *tst) { - struct tcp_ao_info_opt tmp; + struct tcp_ao_info_opt tmp = {}; socklen_t len = sizeof(tmp); if (getsockopt(sk, IPPROTO_TCP, TCP_AO_INFO, &tmp, &len)) diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c index 1d975bf52af3..85b3baa3f7f3 100644 --- a/tools/testing/selftests/net/udpgso.c +++ b/tools/testing/selftests/net/udpgso.c @@ -34,7 +34,7 @@ #endif #ifndef UDP_MAX_SEGMENTS -#define UDP_MAX_SEGMENTS (1 << 6UL) +#define UDP_MAX_SEGMENTS (1 << 7UL) #endif #define CONST_MTU_TEST 1500 |