diff options
Diffstat (limited to 'include')
-rw-r--r-- | include/linux/ieee80211.h | 31 | ||||
-rw-r--r-- | include/linux/if_macvlan.h | 6 | ||||
-rw-r--r-- | include/linux/if_team.h | 10 | ||||
-rw-r--r-- | include/linux/if_vlan.h | 10 | ||||
-rw-r--r-- | include/linux/mlx5/device.h | 36 | ||||
-rw-r--r-- | include/linux/mlx5/driver.h | 1 | ||||
-rw-r--r-- | include/linux/mlx5/fs.h | 14 | ||||
-rw-r--r-- | include/linux/mlx5/mlx5_ifc.h | 151 | ||||
-rw-r--r-- | include/linux/netdevice.h | 40 | ||||
-rw-r--r-- | include/linux/skbuff.h | 179 | ||||
-rw-r--r-- | include/linux/socket.h | 4 | ||||
-rw-r--r-- | include/net/bond_options.h | 3 | ||||
-rw-r--r-- | include/net/dropreason.h | 256 | ||||
-rw-r--r-- | include/net/ip_tunnels.h | 4 | ||||
-rw-r--r-- | include/net/mac80211.h | 35 | ||||
-rw-r--r-- | include/net/sock.h | 107 | ||||
-rw-r--r-- | include/net/tcp.h | 2 | ||||
-rw-r--r-- | include/net/udp.h | 1 | ||||
-rw-r--r-- | include/net/xfrm.h | 2 | ||||
-rw-r--r-- | include/trace/events/skb.h | 89 | ||||
-rw-r--r-- | include/uapi/linux/nl80211.h | 2 | ||||
-rw-r--r-- | include/uapi/rdma/mlx5_user_ioctl_verbs.h | 1 |
22 files changed, 549 insertions, 435 deletions
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 75d40acb60c1..5c65ae6b8154 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -76,6 +76,7 @@ #define IEEE80211_STYPE_ACTION 0x00D0 /* control */ +#define IEEE80211_STYPE_TRIGGER 0x0020 #define IEEE80211_STYPE_CTL_EXT 0x0060 #define IEEE80211_STYPE_BACK_REQ 0x0080 #define IEEE80211_STYPE_BACK 0x0090 @@ -295,6 +296,17 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) #define IEEE80211_HT_CTL_LEN 4 +/* trigger type within common_info of trigger frame */ +#define IEEE80211_TRIGGER_TYPE_MASK 0xf +#define IEEE80211_TRIGGER_TYPE_BASIC 0x0 +#define IEEE80211_TRIGGER_TYPE_BFRP 0x1 +#define IEEE80211_TRIGGER_TYPE_MU_BAR 0x2 +#define IEEE80211_TRIGGER_TYPE_MU_RTS 0x3 +#define IEEE80211_TRIGGER_TYPE_BSRP 0x4 +#define IEEE80211_TRIGGER_TYPE_GCR_MU_BAR 0x5 +#define IEEE80211_TRIGGER_TYPE_BQRP 0x6 +#define IEEE80211_TRIGGER_TYPE_NFRP 0x7 + struct ieee80211_hdr { __le16 frame_control; __le16 duration_id; @@ -324,6 +336,15 @@ struct ieee80211_qos_hdr { __le16 qos_ctrl; } __packed __aligned(2); +struct ieee80211_trigger { + __le16 frame_control; + __le16 duration; + u8 ra[ETH_ALEN]; + u8 ta[ETH_ALEN]; + __le64 common_info; + u8 variable[]; +} __packed __aligned(2); + /** * ieee80211_has_tods - check if IEEE80211_FCTL_TODS is set * @fc: frame control bytes in little-endian byteorder @@ -730,6 +751,16 @@ static inline bool ieee80211_is_qos_nullfunc(__le16 fc) } /** + * ieee80211_is_trigger - check if frame is trigger frame + * @fc: frame control field in little-endian byteorder + */ +static inline bool ieee80211_is_trigger(__le16 fc) +{ + return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == + cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_TRIGGER); +} + +/** * ieee80211_is_any_nullfunc - check if frame is regular or QoS nullfunc frame * @fc: frame control bytes in little-endian byteorder */ diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index b42294739063..523025106a64 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -46,10 +46,10 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan, pcpu_stats = get_cpu_ptr(vlan->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); - pcpu_stats->rx_packets++; - pcpu_stats->rx_bytes += len; + u64_stats_inc(&pcpu_stats->rx_packets); + u64_stats_add(&pcpu_stats->rx_bytes, len); if (multicast) - pcpu_stats->rx_multicast++; + u64_stats_inc(&pcpu_stats->rx_multicast); u64_stats_update_end(&pcpu_stats->syncp); put_cpu_ptr(vlan->pcpu_stats); } else { diff --git a/include/linux/if_team.h b/include/linux/if_team.h index add607943c95..fc985e5c739d 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -12,11 +12,11 @@ #include <uapi/linux/if_team.h> struct team_pcpu_stats { - u64 rx_packets; - u64 rx_bytes; - u64 rx_multicast; - u64 tx_packets; - u64 tx_bytes; + u64_stats_t rx_packets; + u64_stats_t rx_bytes; + u64_stats_t rx_multicast; + u64_stats_t tx_packets; + u64_stats_t tx_bytes; struct u64_stats_sync syncp; u32 rx_dropped; u32 tx_dropped; diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 2be4dd7e90a9..e00c4ee81ff7 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -118,11 +118,11 @@ static inline void vlan_drop_rx_stag_filter_info(struct net_device *dev) * @tx_dropped: number of tx drops */ struct vlan_pcpu_stats { - u64 rx_packets; - u64 rx_bytes; - u64 rx_multicast; - u64 tx_packets; - u64 tx_bytes; + u64_stats_t rx_packets; + u64_stats_t rx_bytes; + u64_stats_t rx_multicast; + u64_stats_t tx_packets; + u64_stats_t tx_bytes; struct u64_stats_sync syncp; u32 rx_errors; u32 tx_dropped; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 604b85dd770a..b5f58fd37a0f 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -387,21 +387,6 @@ enum { }; enum { - MLX5_DEV_CAP_FLAG_XRC = 1LL << 3, - MLX5_DEV_CAP_FLAG_BAD_PKEY_CNTR = 1LL << 8, - MLX5_DEV_CAP_FLAG_BAD_QKEY_CNTR = 1LL << 9, - MLX5_DEV_CAP_FLAG_APM = 1LL << 17, - MLX5_DEV_CAP_FLAG_ATOMIC = 1LL << 18, - MLX5_DEV_CAP_FLAG_BLOCK_MCAST = 1LL << 23, - MLX5_DEV_CAP_FLAG_ON_DMND_PG = 1LL << 24, - MLX5_DEV_CAP_FLAG_CQ_MODER = 1LL << 29, - MLX5_DEV_CAP_FLAG_RESIZE_CQ = 1LL << 30, - MLX5_DEV_CAP_FLAG_DCT = 1LL << 37, - MLX5_DEV_CAP_FLAG_SIG_HAND_OVER = 1LL << 40, - MLX5_DEV_CAP_FLAG_CMDIF_CSUM = 3LL << 46, -}; - -enum { MLX5_ROCE_VERSION_1 = 0, MLX5_ROCE_VERSION_2 = 2, }; @@ -455,6 +440,7 @@ enum { MLX5_OPCODE_UMR = 0x25, + MLX5_OPCODE_ACCESS_ASO = 0x2d, }; enum { @@ -496,10 +482,6 @@ enum { }; enum { - MLX5_CAP_OFF_CMDIF_CSUM = 46, -}; - -enum { /* * Max wqe size for rdma read is 512 bytes, so this * limits our max_sge_rd as the wqe needs to fit: @@ -840,7 +822,10 @@ struct mlx5_cqe64 { __be32 timestamp_l; __be32 sop_drop_qpn; __be16 wqe_counter; - u8 signature; + union { + u8 signature; + u8 validity_iteration_count; + }; u8 op_own; }; @@ -872,6 +857,11 @@ enum { MLX5_CQE_FORMAT_CSUM_STRIDX = 0x3, }; +enum { + MLX5_CQE_COMPRESS_LAYOUT_BASIC = 0, + MLX5_CQE_COMPRESS_LAYOUT_ENHANCED = 1, +}; + #define MLX5_MINI_CQE_ARRAY_SIZE 8 static inline u8 mlx5_get_cqe_format(struct mlx5_cqe64 *cqe) @@ -884,6 +874,12 @@ static inline u8 get_cqe_opcode(struct mlx5_cqe64 *cqe) return cqe->op_own >> 4; } +static inline u8 get_cqe_enhanced_num_mini_cqes(struct mlx5_cqe64 *cqe) +{ + /* num_of_mini_cqes is zero based */ + return get_cqe_opcode(cqe) + 1; +} + static inline u8 get_cqe_lro_tcppsh(struct mlx5_cqe64 *cqe) { return (cqe->lro.tcppsh_abort_dupack >> 6) & 1; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 5040cd774c5a..76d7661e3e63 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -676,6 +676,7 @@ struct mlx5e_resources { enum mlx5_sw_icm_type { MLX5_SW_ICM_TYPE_STEERING, MLX5_SW_ICM_TYPE_HEADER_MODIFY, + MLX5_SW_ICM_TYPE_HEADER_MODIFY_PATTERN, }; #define MLX5_MAX_RESERVED_GIDS 8 diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 8135713b0d2d..ece3e35622d7 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -212,6 +212,19 @@ struct mlx5_flow_group * mlx5_create_flow_group(struct mlx5_flow_table *ft, u32 *in); void mlx5_destroy_flow_group(struct mlx5_flow_group *fg); +struct mlx5_exe_aso { + u32 object_id; + u8 type; + u8 return_reg_id; + union { + u32 ctrl_data; + struct { + u8 meter_idx; + u8 init_color; + } flow_meter; + }; +}; + struct mlx5_fs_vlan { u16 ethtype; u16 vid; @@ -237,6 +250,7 @@ struct mlx5_flow_act { struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH]; struct ib_counters *counters; struct mlx5_flow_group *fg; + struct mlx5_exe_aso exe_aso; }; #define MLX5_DECLARE_FLOW_ACT(name) \ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index fd7d083a34d3..8e87eb47f9dc 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -442,7 +442,9 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 max_modify_header_actions[0x8]; u8 max_ft_level[0x8]; - u8 reserved_at_40[0x20]; + u8 reserved_at_40[0x6]; + u8 execute_aso[0x1]; + u8 reserved_at_47[0x19]; u8 reserved_at_60[0x2]; u8 reformat_insert[0x1]; @@ -940,7 +942,17 @@ struct mlx5_ifc_qos_cap_bits { u8 max_tsar_bw_share[0x20]; - u8 reserved_at_100[0x700]; + u8 reserved_at_100[0x20]; + + u8 reserved_at_120[0x3]; + u8 log_meter_aso_granularity[0x5]; + u8 reserved_at_128[0x3]; + u8 log_meter_aso_max_alloc[0x5]; + u8 reserved_at_130[0x3]; + u8 log_max_num_meter_aso[0x5]; + u8 reserved_at_138[0x8]; + + u8 reserved_at_140[0x6c0]; }; struct mlx5_ifc_debug_cap_bits { @@ -1086,11 +1098,14 @@ struct mlx5_ifc_device_mem_cap_bits { u8 log_sw_icm_alloc_granularity[0x6]; u8 log_steering_sw_icm_size[0x8]; - u8 reserved_at_120[0x20]; + u8 reserved_at_120[0x18]; + u8 log_header_modify_pattern_sw_icm_size[0x8]; u8 header_modify_sw_icm_start_address[0x40]; - u8 reserved_at_180[0x80]; + u8 reserved_at_180[0x40]; + + u8 header_modify_pattern_sw_icm_start_address[0x40]; u8 memic_operations[0x20]; @@ -1426,7 +1441,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_120[0xa]; u8 log_max_ra_req_dc[0x6]; - u8 reserved_at_130[0xa]; + u8 reserved_at_130[0x9]; + u8 vnic_env_cq_overrun[0x1]; u8 log_max_ra_res_dc[0x6]; u8 reserved_at_140[0x5]; @@ -1621,7 +1637,11 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 nic_receive_steering_discard[0x1]; u8 receive_discard_vport_down[0x1]; u8 transmit_discard_vport_down[0x1]; - u8 reserved_at_343[0x5]; + u8 eq_overrun_count[0x1]; + u8 reserved_at_344[0x1]; + u8 invalid_command_count[0x1]; + u8 quota_exceeded_count[0x1]; + u8 reserved_at_347[0x1]; u8 log_max_flow_counter_bulk[0x8]; u8 max_flow_counter_15_0[0x10]; @@ -1719,7 +1739,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_dci_errored_streams[0x5]; u8 reserved_at_598[0x8]; - u8 reserved_at_5a0[0x13]; + u8 reserved_at_5a0[0x10]; + u8 enhanced_cqe_compression[0x1]; + u8 reserved_at_5b1[0x2]; u8 log_max_dek[0x5]; u8 reserved_at_5b8[0x4]; u8 mini_cqe_resp_stride_index[0x1]; @@ -3277,6 +3299,7 @@ enum { MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2 = 0x800, MLX5_FLOW_CONTEXT_ACTION_IPSEC_DECRYPT = 0x1000, MLX5_FLOW_CONTEXT_ACTION_IPSEC_ENCRYPT = 0x2000, + MLX5_FLOW_CONTEXT_ACTION_EXECUTE_ASO = 0x4000, }; enum { @@ -3292,6 +3315,38 @@ struct mlx5_ifc_vlan_bits { u8 vid[0xc]; }; +enum { + MLX5_FLOW_METER_COLOR_RED = 0x0, + MLX5_FLOW_METER_COLOR_YELLOW = 0x1, + MLX5_FLOW_METER_COLOR_GREEN = 0x2, + MLX5_FLOW_METER_COLOR_UNDEFINED = 0x3, +}; + +enum { + MLX5_EXE_ASO_FLOW_METER = 0x2, +}; + +struct mlx5_ifc_exe_aso_ctrl_flow_meter_bits { + u8 return_reg_id[0x4]; + u8 aso_type[0x4]; + u8 reserved_at_8[0x14]; + u8 action[0x1]; + u8 init_color[0x2]; + u8 meter_id[0x1]; +}; + +union mlx5_ifc_exe_aso_ctrl { + struct mlx5_ifc_exe_aso_ctrl_flow_meter_bits exe_aso_ctrl_flow_meter; +}; + +struct mlx5_ifc_execute_aso_bits { + u8 valid[0x1]; + u8 reserved_at_1[0x7]; + u8 aso_object_id[0x18]; + + union mlx5_ifc_exe_aso_ctrl exe_aso_ctrl; +}; + struct mlx5_ifc_flow_context_bits { struct mlx5_ifc_vlan_bits push_vlan; @@ -3323,7 +3378,9 @@ struct mlx5_ifc_flow_context_bits { struct mlx5_ifc_fte_match_param_bits match_value; - u8 reserved_at_1200[0x600]; + struct mlx5_ifc_execute_aso_bits execute_aso[4]; + + u8 reserved_at_1300[0x500]; union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits destination[]; }; @@ -3391,11 +3448,21 @@ struct mlx5_ifc_vnic_diagnostic_statistics_bits { u8 transmit_discard_vport_down[0x40]; - u8 reserved_at_140[0xa0]; + u8 async_eq_overrun[0x20]; + + u8 comp_eq_overrun[0x20]; + + u8 reserved_at_180[0x20]; + + u8 invalid_command[0x20]; + + u8 quota_exceeded_command[0x20]; u8 internal_rq_out_of_buffer[0x20]; - u8 reserved_at_200[0xe00]; + u8 cq_overrun[0x20]; + + u8 reserved_at_220[0xde0]; }; struct mlx5_ifc_traffic_counter_bits { @@ -4074,7 +4141,8 @@ struct mlx5_ifc_cqc_bits { u8 cqe_comp_en[0x1]; u8 mini_cqe_res_format[0x2]; u8 st[0x4]; - u8 reserved_at_18[0x8]; + u8 reserved_at_18[0x6]; + u8 cqe_compression_layout[0x2]; u8 reserved_at_20[0x20]; @@ -5970,7 +6038,9 @@ struct mlx5_ifc_general_obj_in_cmd_hdr_bits { u8 obj_id[0x20]; - u8 reserved_at_60[0x20]; + u8 reserved_at_60[0x3]; + u8 log_obj_range[0x5]; + u8 reserved_at_68[0x18]; }; struct mlx5_ifc_general_obj_out_cmd_hdr_bits { @@ -11370,12 +11440,14 @@ enum { MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = BIT_ULL(0xc), MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_IPSEC = BIT_ULL(0x13), MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_SAMPLER = BIT_ULL(0x20), + MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_FLOW_METER_ASO = BIT_ULL(0x24), }; enum { MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = 0xc, MLX5_GENERAL_OBJECT_TYPES_IPSEC = 0x13, MLX5_GENERAL_OBJECT_TYPES_SAMPLER = 0x20, + MLX5_GENERAL_OBJECT_TYPES_FLOW_METER_ASO = 0x24, }; enum { @@ -11448,6 +11520,61 @@ struct mlx5_ifc_create_encryption_key_in_bits { struct mlx5_ifc_encryption_key_obj_bits encryption_key_object; }; +enum { + MLX5_FLOW_METER_MODE_BYTES_IP_LENGTH = 0x0, + MLX5_FLOW_METER_MODE_BYTES_CALC_WITH_L2 = 0x1, + MLX5_FLOW_METER_MODE_BYTES_CALC_WITH_L2_IPG = 0x2, + MLX5_FLOW_METER_MODE_NUM_PACKETS = 0x3, +}; + +struct mlx5_ifc_flow_meter_parameters_bits { + u8 valid[0x1]; + u8 bucket_overflow[0x1]; + u8 start_color[0x2]; + u8 both_buckets_on_green[0x1]; + u8 reserved_at_5[0x1]; + u8 meter_mode[0x2]; + u8 reserved_at_8[0x18]; + + u8 reserved_at_20[0x20]; + + u8 reserved_at_40[0x3]; + u8 cbs_exponent[0x5]; + u8 cbs_mantissa[0x8]; + u8 reserved_at_50[0x3]; + u8 cir_exponent[0x5]; + u8 cir_mantissa[0x8]; + + u8 reserved_at_60[0x20]; + + u8 reserved_at_80[0x3]; + u8 ebs_exponent[0x5]; + u8 ebs_mantissa[0x8]; + u8 reserved_at_90[0x3]; + u8 eir_exponent[0x5]; + u8 eir_mantissa[0x8]; + + u8 reserved_at_a0[0x60]; +}; + +struct mlx5_ifc_flow_meter_aso_obj_bits { + u8 modify_field_select[0x40]; + + u8 reserved_at_40[0x40]; + + u8 reserved_at_80[0x8]; + u8 meter_aso_access_pd[0x18]; + + u8 reserved_at_a0[0x160]; + + struct mlx5_ifc_flow_meter_parameters_bits flow_meter_parameters[2]; +}; + +struct mlx5_ifc_create_flow_meter_aso_obj_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; + struct mlx5_ifc_flow_meter_aso_obj_bits flow_meter_aso_obj; +}; + struct mlx5_ifc_sampler_obj_bits { u8 modify_field_select[0x40]; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f615a66c89e9..89afa4f7747d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2636,10 +2636,10 @@ struct packet_offload { /* often modified stats are per-CPU, other are shared (netdev->stats) */ struct pcpu_sw_netstats { - u64 rx_packets; - u64 rx_bytes; - u64 tx_packets; - u64 tx_bytes; + u64_stats_t rx_packets; + u64_stats_t rx_bytes; + u64_stats_t tx_packets; + u64_stats_t tx_bytes; struct u64_stats_sync syncp; } __aligned(4 * sizeof(u64)); @@ -2656,8 +2656,8 @@ static inline void dev_sw_netstats_rx_add(struct net_device *dev, unsigned int l struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); - tstats->rx_bytes += len; - tstats->rx_packets++; + u64_stats_add(&tstats->rx_bytes, len); + u64_stats_inc(&tstats->rx_packets); u64_stats_update_end(&tstats->syncp); } @@ -2668,8 +2668,8 @@ static inline void dev_sw_netstats_tx_add(struct net_device *dev, struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); - tstats->tx_bytes += len; - tstats->tx_packets += packets; + u64_stats_add(&tstats->tx_bytes, len); + u64_stats_add(&tstats->tx_packets, packets); u64_stats_update_end(&tstats->syncp); } @@ -3981,8 +3981,8 @@ static inline void netdev_tracker_free(struct net_device *dev, #endif } -static inline void dev_hold_track(struct net_device *dev, - netdevice_tracker *tracker, gfp_t gfp) +static inline void netdev_hold(struct net_device *dev, + netdevice_tracker *tracker, gfp_t gfp) { if (dev) { __dev_hold(dev); @@ -3990,8 +3990,8 @@ static inline void dev_hold_track(struct net_device *dev, } } -static inline void dev_put_track(struct net_device *dev, - netdevice_tracker *tracker) +static inline void netdev_put(struct net_device *dev, + netdevice_tracker *tracker) { if (dev) { netdev_tracker_free(dev, tracker); @@ -4004,11 +4004,11 @@ static inline void dev_put_track(struct net_device *dev, * @dev: network device * * Hold reference to device to keep it from being freed. - * Try using dev_hold_track() instead. + * Try using netdev_hold() instead. */ static inline void dev_hold(struct net_device *dev) { - dev_hold_track(dev, NULL, GFP_ATOMIC); + netdev_hold(dev, NULL, GFP_ATOMIC); } /** @@ -4016,17 +4016,17 @@ static inline void dev_hold(struct net_device *dev) * @dev: network device * * Release reference to device to allow it to be freed. - * Try using dev_put_track() instead. + * Try using netdev_put() instead. */ static inline void dev_put(struct net_device *dev) { - dev_put_track(dev, NULL); + netdev_put(dev, NULL); } -static inline void dev_replace_track(struct net_device *odev, - struct net_device *ndev, - netdevice_tracker *tracker, - gfp_t gfp) +static inline void netdev_ref_replace(struct net_device *odev, + struct net_device *ndev, + netdevice_tracker *tracker, + gfp_t gfp) { if (odev) netdev_tracker_free(odev, tracker); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d3d10556f0fa..82edf0359ab3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -43,6 +43,7 @@ #include <linux/netfilter/nf_conntrack_common.h> #endif #include <net/net_debug.h> +#include <net/dropreason.h> /** * DOC: skb checksums @@ -337,184 +338,6 @@ struct sk_buff_head { struct sk_buff; -/* The reason of skb drop, which is used in kfree_skb_reason(). - * en...maybe they should be splited by group? - * - * Each item here should also be in 'TRACE_SKB_DROP_REASON', which is - * used to translate the reason to string. - */ -enum skb_drop_reason { - SKB_NOT_DROPPED_YET = 0, - SKB_DROP_REASON_NOT_SPECIFIED, /* drop reason is not specified */ - SKB_DROP_REASON_NO_SOCKET, /* socket not found */ - SKB_DROP_REASON_PKT_TOO_SMALL, /* packet size is too small */ - SKB_DROP_REASON_TCP_CSUM, /* TCP checksum error */ - SKB_DROP_REASON_SOCKET_FILTER, /* dropped by socket filter */ - SKB_DROP_REASON_UDP_CSUM, /* UDP checksum error */ - SKB_DROP_REASON_NETFILTER_DROP, /* dropped by netfilter */ - SKB_DROP_REASON_OTHERHOST, /* packet don't belong to current - * host (interface is in promisc - * mode) - */ - SKB_DROP_REASON_IP_CSUM, /* IP checksum error */ - SKB_DROP_REASON_IP_INHDR, /* there is something wrong with - * IP header (see - * IPSTATS_MIB_INHDRERRORS) - */ - SKB_DROP_REASON_IP_RPFILTER, /* IP rpfilter validate failed. - * see the document for rp_filter - * in ip-sysctl.rst for more - * information - */ - SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST, /* destination address of L2 - * is multicast, but L3 is - * unicast. - */ - SKB_DROP_REASON_XFRM_POLICY, /* xfrm policy check failed */ - SKB_DROP_REASON_IP_NOPROTO, /* no support for IP protocol */ - SKB_DROP_REASON_SOCKET_RCVBUFF, /* socket receive buff is full */ - SKB_DROP_REASON_PROTO_MEM, /* proto memory limition, such as - * udp packet drop out of - * udp_memory_allocated. - */ - SKB_DROP_REASON_TCP_MD5NOTFOUND, /* no MD5 hash and one - * expected, corresponding - * to LINUX_MIB_TCPMD5NOTFOUND - */ - SKB_DROP_REASON_TCP_MD5UNEXPECTED, /* MD5 hash and we're not - * expecting one, corresponding - * to LINUX_MIB_TCPMD5UNEXPECTED - */ - SKB_DROP_REASON_TCP_MD5FAILURE, /* MD5 hash and its wrong, - * corresponding to - * LINUX_MIB_TCPMD5FAILURE - */ - SKB_DROP_REASON_SOCKET_BACKLOG, /* failed to add skb to socket - * backlog (see - * LINUX_MIB_TCPBACKLOGDROP) - */ - SKB_DROP_REASON_TCP_FLAGS, /* TCP flags invalid */ - SKB_DROP_REASON_TCP_ZEROWINDOW, /* TCP receive window size is zero, - * see LINUX_MIB_TCPZEROWINDOWDROP - */ - SKB_DROP_REASON_TCP_OLD_DATA, /* the TCP data reveived is already - * received before (spurious retrans - * may happened), see - * LINUX_MIB_DELAYEDACKLOST - */ - SKB_DROP_REASON_TCP_OVERWINDOW, /* the TCP data is out of window, - * the seq of the first byte exceed - * the right edges of receive - * window - */ - SKB_DROP_REASON_TCP_OFOMERGE, /* the data of skb is already in - * the ofo queue, corresponding to - * LINUX_MIB_TCPOFOMERGE - */ - SKB_DROP_REASON_TCP_RFC7323_PAWS, /* PAWS check, corresponding to - * LINUX_MIB_PAWSESTABREJECTED - */ - SKB_DROP_REASON_TCP_INVALID_SEQUENCE, /* Not acceptable SEQ field */ - SKB_DROP_REASON_TCP_RESET, /* Invalid RST packet */ - SKB_DROP_REASON_TCP_INVALID_SYN, /* Incoming packet has unexpected SYN flag */ - SKB_DROP_REASON_TCP_CLOSE, /* TCP socket in CLOSE state */ - SKB_DROP_REASON_TCP_FASTOPEN, /* dropped by FASTOPEN request socket */ - SKB_DROP_REASON_TCP_OLD_ACK, /* TCP ACK is old, but in window */ - SKB_DROP_REASON_TCP_TOO_OLD_ACK, /* TCP ACK is too old */ - SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, /* TCP ACK for data we haven't sent yet */ - SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, /* pruned from TCP OFO queue */ - SKB_DROP_REASON_TCP_OFO_DROP, /* data already in receive queue */ - SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */ - SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by - * BPF_PROG_TYPE_CGROUP_SKB - * eBPF program - */ - SKB_DROP_REASON_IPV6DISABLED, /* IPv6 is disabled on the device */ - SKB_DROP_REASON_NEIGH_CREATEFAIL, /* failed to create neigh - * entry - */ - SKB_DROP_REASON_NEIGH_FAILED, /* neigh entry in failed state */ - SKB_DROP_REASON_NEIGH_QUEUEFULL, /* arp_queue for neigh - * entry is full - */ - SKB_DROP_REASON_NEIGH_DEAD, /* neigh entry is dead */ - SKB_DROP_REASON_TC_EGRESS, /* dropped in TC egress HOOK */ - SKB_DROP_REASON_QDISC_DROP, /* dropped by qdisc when packet - * outputting (failed to enqueue to - * current qdisc) - */ - SKB_DROP_REASON_CPU_BACKLOG, /* failed to enqueue the skb to - * the per CPU backlog queue. This - * can be caused by backlog queue - * full (see netdev_max_backlog in - * net.rst) or RPS flow limit - */ - SKB_DROP_REASON_XDP, /* dropped by XDP in input path */ - SKB_DROP_REASON_TC_INGRESS, /* dropped in TC ingress HOOK */ - SKB_DROP_REASON_UNHANDLED_PROTO, /* protocol not implemented - * or not supported - */ - SKB_DROP_REASON_SKB_CSUM, /* sk_buff checksum computation - * error - */ - SKB_DROP_REASON_SKB_GSO_SEG, /* gso segmentation error */ - SKB_DROP_REASON_SKB_UCOPY_FAULT, /* failed to copy data from - * user space, e.g., via - * zerocopy_sg_from_iter() - * or skb_orphan_frags_rx() - */ - SKB_DROP_REASON_DEV_HDR, /* device driver specific - * header/metadata is invalid - */ - /* the device is not ready to xmit/recv due to any of its data - * structure that is not up/ready/initialized, e.g., the IFF_UP is - * not set, or driver specific tun->tfiles[txq] is not initialized - */ - SKB_DROP_REASON_DEV_READY, - SKB_DROP_REASON_FULL_RING, /* ring buffer is full */ - SKB_DROP_REASON_NOMEM, /* error due to OOM */ - SKB_DROP_REASON_HDR_TRUNC, /* failed to trunc/extract the header - * from networking data, e.g., failed - * to pull the protocol header from - * frags via pskb_may_pull() - */ - SKB_DROP_REASON_TAP_FILTER, /* dropped by (ebpf) filter directly - * attached to tun/tap, e.g., via - * TUNSETFILTEREBPF - */ - SKB_DROP_REASON_TAP_TXFILTER, /* dropped by tx filter implemented - * at tun/tap, e.g., check_filter() - */ - SKB_DROP_REASON_ICMP_CSUM, /* ICMP checksum error */ - SKB_DROP_REASON_INVALID_PROTO, /* the packet doesn't follow RFC - * 2211, such as a broadcasts - * ICMP_TIMESTAMP - */ - SKB_DROP_REASON_IP_INADDRERRORS, /* host unreachable, corresponding - * to IPSTATS_MIB_INADDRERRORS - */ - SKB_DROP_REASON_IP_INNOROUTES, /* network unreachable, corresponding - * to IPSTATS_MIB_INADDRERRORS - */ - SKB_DROP_REASON_PKT_TOO_BIG, /* packet size is too big (maybe exceed - * the MTU) - */ - SKB_DROP_REASON_MAX, -}; - -#define SKB_DR_INIT(name, reason) \ - enum skb_drop_reason name = SKB_DROP_REASON_##reason -#define SKB_DR(name) \ - SKB_DR_INIT(name, NOT_SPECIFIED) -#define SKB_DR_SET(name, reason) \ - (name = SKB_DROP_REASON_##reason) -#define SKB_DR_OR(name, reason) \ - do { \ - if (name == SKB_DROP_REASON_NOT_SPECIFIED || \ - name == SKB_NOT_DROPPED_YET) \ - SKB_DR_SET(name, reason); \ - } while (0) - /* To allow 64K frame to be packed as single skb without frag_list we * require 64K/PAGE_SIZE pages plus 1 additional page to allow for * buffers which do not start on a page boundary. diff --git a/include/linux/socket.h b/include/linux/socket.h index 17311ad9f9af..414b8c7bb8f7 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -428,10 +428,6 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, extern int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, struct sockaddr __user *addr, int addr_len); -extern int __sys_accept4_file(struct file *file, unsigned file_flags, - struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen, int flags, - unsigned long nofile); extern struct file *do_accept(struct file *file, unsigned file_flags, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); diff --git a/include/net/bond_options.h b/include/net/bond_options.h index 61b49063791c..1618b76f4903 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -107,7 +107,8 @@ struct bond_option { }; int __bond_opt_set(struct bonding *bond, unsigned int option, - struct bond_opt_value *val); + struct bond_opt_value *val, + struct nlattr *bad_attr, struct netlink_ext_ack *extack); int __bond_opt_set_notify(struct bonding *bond, unsigned int option, struct bond_opt_value *val); int bond_opt_tryset_rtnl(struct bonding *bond, unsigned int option, char *buf); diff --git a/include/net/dropreason.h b/include/net/dropreason.h new file mode 100644 index 000000000000..fae9b40e54fa --- /dev/null +++ b/include/net/dropreason.h @@ -0,0 +1,256 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef _LINUX_DROPREASON_H +#define _LINUX_DROPREASON_H + +/** + * enum skb_drop_reason - the reasons of skb drops + * + * The reason of skb drop, which is used in kfree_skb_reason(). + */ +enum skb_drop_reason { + /** + * @SKB_NOT_DROPPED_YET: skb is not dropped yet (used for no-drop case) + */ + SKB_NOT_DROPPED_YET = 0, + /** @SKB_DROP_REASON_NOT_SPECIFIED: drop reason is not specified */ + SKB_DROP_REASON_NOT_SPECIFIED, + /** @SKB_DROP_REASON_NO_SOCKET: socket not found */ + SKB_DROP_REASON_NO_SOCKET, + /** @SKB_DROP_REASON_PKT_TOO_SMALL: packet size is too small */ + SKB_DROP_REASON_PKT_TOO_SMALL, + /** @SKB_DROP_REASON_TCP_CSUM: TCP checksum error */ + SKB_DROP_REASON_TCP_CSUM, + /** @SKB_DROP_REASON_SOCKET_FILTER: dropped by socket filter */ + SKB_DROP_REASON_SOCKET_FILTER, + /** @SKB_DROP_REASON_UDP_CSUM: UDP checksum error */ + SKB_DROP_REASON_UDP_CSUM, + /** @SKB_DROP_REASON_NETFILTER_DROP: dropped by netfilter */ + SKB_DROP_REASON_NETFILTER_DROP, + /** + * @SKB_DROP_REASON_OTHERHOST: packet don't belong to current host + * (interface is in promisc mode) + */ + SKB_DROP_REASON_OTHERHOST, + /** @SKB_DROP_REASON_IP_CSUM: IP checksum error */ + SKB_DROP_REASON_IP_CSUM, + /** + * @SKB_DROP_REASON_IP_INHDR: there is something wrong with IP header (see + * IPSTATS_MIB_INHDRERRORS) + */ + SKB_DROP_REASON_IP_INHDR, + /** + * @SKB_DROP_REASON_IP_RPFILTER: IP rpfilter validate failed. see the + * document for rp_filter in ip-sysctl.rst for more information + */ + SKB_DROP_REASON_IP_RPFILTER, + /** + * @SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST: destination address of L2 is + * multicast, but L3 is unicast. + */ + SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST, + /** @SKB_DROP_REASON_XFRM_POLICY: xfrm policy check failed */ + SKB_DROP_REASON_XFRM_POLICY, + /** @SKB_DROP_REASON_IP_NOPROTO: no support for IP protocol */ + SKB_DROP_REASON_IP_NOPROTO, + /** @SKB_DROP_REASON_SOCKET_RCVBUFF: socket receive buff is full */ + SKB_DROP_REASON_SOCKET_RCVBUFF, + /** + * @SKB_DROP_REASON_PROTO_MEM: proto memory limition, such as udp packet + * drop out of udp_memory_allocated. + */ + SKB_DROP_REASON_PROTO_MEM, + /** + * @SKB_DROP_REASON_TCP_MD5NOTFOUND: no MD5 hash and one expected, + * corresponding to LINUX_MIB_TCPMD5NOTFOUND + */ + SKB_DROP_REASON_TCP_MD5NOTFOUND, + /** + * @SKB_DROP_REASON_TCP_MD5UNEXPECTED: MD5 hash and we're not expecting + * one, corresponding to LINUX_MIB_TCPMD5UNEXPECTED + */ + SKB_DROP_REASON_TCP_MD5UNEXPECTED, + /** + * @SKB_DROP_REASON_TCP_MD5FAILURE: MD5 hash and its wrong, corresponding + * to LINUX_MIB_TCPMD5FAILURE + */ + SKB_DROP_REASON_TCP_MD5FAILURE, + /** + * @SKB_DROP_REASON_SOCKET_BACKLOG: failed to add skb to socket backlog ( + * see LINUX_MIB_TCPBACKLOGDROP) + */ + SKB_DROP_REASON_SOCKET_BACKLOG, + /** @SKB_DROP_REASON_TCP_FLAGS: TCP flags invalid */ + SKB_DROP_REASON_TCP_FLAGS, + /** + * @SKB_DROP_REASON_TCP_ZEROWINDOW: TCP receive window size is zero, + * see LINUX_MIB_TCPZEROWINDOWDROP + */ + SKB_DROP_REASON_TCP_ZEROWINDOW, + /** + * @SKB_DROP_REASON_TCP_OLD_DATA: the TCP data reveived is already + * received before (spurious retrans may happened), see + * LINUX_MIB_DELAYEDACKLOST + */ + SKB_DROP_REASON_TCP_OLD_DATA, + /** + * @SKB_DROP_REASON_TCP_OVERWINDOW: the TCP data is out of window, + * the seq of the first byte exceed the right edges of receive + * window + */ + SKB_DROP_REASON_TCP_OVERWINDOW, + /** + * @SKB_DROP_REASON_TCP_OFOMERGE: the data of skb is already in the ofo + * queue, corresponding to LINUX_MIB_TCPOFOMERGE + */ + SKB_DROP_REASON_TCP_OFOMERGE, + /** + * @SKB_DROP_REASON_TCP_RFC7323_PAWS: PAWS check, corresponding to + * LINUX_MIB_PAWSESTABREJECTED + */ + SKB_DROP_REASON_TCP_RFC7323_PAWS, + /** @SKB_DROP_REASON_TCP_INVALID_SEQUENCE: Not acceptable SEQ field */ + SKB_DROP_REASON_TCP_INVALID_SEQUENCE, + /** @SKB_DROP_REASON_TCP_RESET: Invalid RST packet */ + SKB_DROP_REASON_TCP_RESET, + /** + * @SKB_DROP_REASON_TCP_INVALID_SYN: Incoming packet has unexpected + * SYN flag + */ + SKB_DROP_REASON_TCP_INVALID_SYN, + /** @SKB_DROP_REASON_TCP_CLOSE: TCP socket in CLOSE state */ + SKB_DROP_REASON_TCP_CLOSE, + /** @SKB_DROP_REASON_TCP_FASTOPEN: dropped by FASTOPEN request socket */ + SKB_DROP_REASON_TCP_FASTOPEN, + /** @SKB_DROP_REASON_TCP_OLD_ACK: TCP ACK is old, but in window */ + SKB_DROP_REASON_TCP_OLD_ACK, + /** @SKB_DROP_REASON_TCP_TOO_OLD_ACK: TCP ACK is too old */ + SKB_DROP_REASON_TCP_TOO_OLD_ACK, + /** + * @SKB_DROP_REASON_TCP_ACK_UNSENT_DATA: TCP ACK for data we haven't + * sent yet + */ + SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, + /** @SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE: pruned from TCP OFO queue */ + SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, + /** @SKB_DROP_REASON_TCP_OFO_DROP: data already in receive queue */ + SKB_DROP_REASON_TCP_OFO_DROP, + /** @SKB_DROP_REASON_IP_OUTNOROUTES: route lookup failed */ + SKB_DROP_REASON_IP_OUTNOROUTES, + /** + * @SKB_DROP_REASON_BPF_CGROUP_EGRESS: dropped by BPF_PROG_TYPE_CGROUP_SKB + * eBPF program + */ + SKB_DROP_REASON_BPF_CGROUP_EGRESS, + /** @SKB_DROP_REASON_IPV6DISABLED: IPv6 is disabled on the device */ + SKB_DROP_REASON_IPV6DISABLED, + /** @SKB_DROP_REASON_NEIGH_CREATEFAIL: failed to create neigh entry */ + SKB_DROP_REASON_NEIGH_CREATEFAIL, + /** @SKB_DROP_REASON_NEIGH_FAILED: neigh entry in failed state */ + SKB_DROP_REASON_NEIGH_FAILED, + /** @SKB_DROP_REASON_NEIGH_QUEUEFULL: arp_queue for neigh entry is full */ + SKB_DROP_REASON_NEIGH_QUEUEFULL, + /** @SKB_DROP_REASON_NEIGH_DEAD: neigh entry is dead */ + SKB_DROP_REASON_NEIGH_DEAD, + /** @SKB_DROP_REASON_TC_EGRESS: dropped in TC egress HOOK */ + SKB_DROP_REASON_TC_EGRESS, + /** + * @SKB_DROP_REASON_QDISC_DROP: dropped by qdisc when packet outputting ( + * failed to enqueue to current qdisc) + */ + SKB_DROP_REASON_QDISC_DROP, + /** + * @SKB_DROP_REASON_CPU_BACKLOG: failed to enqueue the skb to the per CPU + * backlog queue. This can be caused by backlog queue full (see + * netdev_max_backlog in net.rst) or RPS flow limit + */ + SKB_DROP_REASON_CPU_BACKLOG, + /** @SKB_DROP_REASON_XDP: dropped by XDP in input path */ + SKB_DROP_REASON_XDP, + /** @SKB_DROP_REASON_TC_INGRESS: dropped in TC ingress HOOK */ + SKB_DROP_REASON_TC_INGRESS, + /** @SKB_DROP_REASON_UNHANDLED_PROTO: protocol not implemented or not supported */ + SKB_DROP_REASON_UNHANDLED_PROTO, + /** @SKB_DROP_REASON_SKB_CSUM: sk_buff checksum computation error */ + SKB_DROP_REASON_SKB_CSUM, + /** @SKB_DROP_REASON_SKB_GSO_SEG: gso segmentation error */ + SKB_DROP_REASON_SKB_GSO_SEG, + /** + * @SKB_DROP_REASON_SKB_UCOPY_FAULT: failed to copy data from user space, + * e.g., via zerocopy_sg_from_iter() or skb_orphan_frags_rx() + */ + SKB_DROP_REASON_SKB_UCOPY_FAULT, + /** @SKB_DROP_REASON_DEV_HDR: device driver specific header/metadata is invalid */ + SKB_DROP_REASON_DEV_HDR, + /** + * @SKB_DROP_REASON_DEV_READY: the device is not ready to xmit/recv due to + * any of its data structure that is not up/ready/initialized, + * e.g., the IFF_UP is not set, or driver specific tun->tfiles[txq] + * is not initialized + */ + SKB_DROP_REASON_DEV_READY, + /** @SKB_DROP_REASON_FULL_RING: ring buffer is full */ + SKB_DROP_REASON_FULL_RING, + /** @SKB_DROP_REASON_NOMEM: error due to OOM */ + SKB_DROP_REASON_NOMEM, + /** + * @SKB_DROP_REASON_HDR_TRUNC: failed to trunc/extract the header from + * networking data, e.g., failed to pull the protocol header from + * frags via pskb_may_pull() + */ + SKB_DROP_REASON_HDR_TRUNC, + /** + * @SKB_DROP_REASON_TAP_FILTER: dropped by (ebpf) filter directly attached + * to tun/tap, e.g., via TUNSETFILTEREBPF + */ + SKB_DROP_REASON_TAP_FILTER, + /** + * @SKB_DROP_REASON_TAP_TXFILTER: dropped by tx filter implemented at + * tun/tap, e.g., check_filter() + */ + SKB_DROP_REASON_TAP_TXFILTER, + /** @SKB_DROP_REASON_ICMP_CSUM: ICMP checksum error */ + SKB_DROP_REASON_ICMP_CSUM, + /** + * @SKB_DROP_REASON_INVALID_PROTO: the packet doesn't follow RFC 2211, + * such as a broadcasts ICMP_TIMESTAMP + */ + SKB_DROP_REASON_INVALID_PROTO, + /** + * @SKB_DROP_REASON_IP_INADDRERRORS: host unreachable, corresponding to + * IPSTATS_MIB_INADDRERRORS + */ + SKB_DROP_REASON_IP_INADDRERRORS, + /** + * @SKB_DROP_REASON_IP_INNOROUTES: network unreachable, corresponding to + * IPSTATS_MIB_INADDRERRORS + */ + SKB_DROP_REASON_IP_INNOROUTES, + /** + * @SKB_DROP_REASON_PKT_TOO_BIG: packet size is too big (maybe exceed the + * MTU) + */ + SKB_DROP_REASON_PKT_TOO_BIG, + /** + * @SKB_DROP_REASON_MAX: the maximum of drop reason, which shouldn't be + * used as a real 'reason' + */ + SKB_DROP_REASON_MAX, +}; + +#define SKB_DR_INIT(name, reason) \ + enum skb_drop_reason name = SKB_DROP_REASON_##reason +#define SKB_DR(name) \ + SKB_DR_INIT(name, NOT_SPECIFIED) +#define SKB_DR_SET(name, reason) \ + (name = SKB_DROP_REASON_##reason) +#define SKB_DR_OR(name, reason) \ + do { \ + if (name == SKB_DROP_REASON_NOT_SPECIFIED || \ + name == SKB_NOT_DROPPED_YET) \ + SKB_DR_SET(name, reason); \ + } while (0) + +extern const char * const drop_reasons[]; + +#endif diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index c24fa934221d..70cbc4a72669 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -456,8 +456,8 @@ static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len) struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); - tstats->tx_bytes += pkt_len; - tstats->tx_packets++; + u64_stats_add(&tstats->tx_bytes, pkt_len); + u64_stats_inc(&tstats->tx_packets); u64_stats_update_end(&tstats->syncp); put_cpu_ptr(tstats); } else { diff --git a/include/net/mac80211.h b/include/net/mac80211.h index ebadb2103968..5c9e97eca739 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1959,36 +1959,6 @@ struct ieee80211_key_seq { }; /** - * struct ieee80211_cipher_scheme - cipher scheme - * - * This structure contains a cipher scheme information defining - * the secure packet crypto handling. - * - * @cipher: a cipher suite selector - * @iftype: a cipher iftype bit mask indicating an allowed cipher usage - * @hdr_len: a length of a security header used the cipher - * @pn_len: a length of a packet number in the security header - * @pn_off: an offset of pn from the beginning of the security header - * @key_idx_off: an offset of key index byte in the security header - * @key_idx_mask: a bit mask of key_idx bits - * @key_idx_shift: a bit shift needed to get key_idx - * key_idx value calculation: - * (sec_header_base[key_idx_off] & key_idx_mask) >> key_idx_shift - * @mic_len: a mic length in bytes - */ -struct ieee80211_cipher_scheme { - u32 cipher; - u16 iftype; - u8 hdr_len; - u8 pn_len; - u8 pn_off; - u8 key_idx_off; - u8 key_idx_mask; - u8 key_idx_shift; - u8 mic_len; -}; - -/** * enum set_key_cmd - key command * * Used with the set_key() callback in &struct ieee80211_ops, this @@ -2664,9 +2634,6 @@ enum ieee80211_hw_flags { * deliver to a WMM STA during any Service Period triggered by the WMM STA. * Use IEEE80211_WMM_IE_STA_QOSINFO_SP_* for correct values. * - * @n_cipher_schemes: a size of an array of cipher schemes definitions. - * @cipher_schemes: a pointer to an array of cipher scheme definitions - * supported by HW. * @max_nan_de_entries: maximum number of NAN DE functions supported by the * device. * @@ -2716,8 +2683,6 @@ struct ieee80211_hw { netdev_features_t netdev_features; u8 uapsd_queues; u8 uapsd_max_sp_len; - u8 n_cipher_schemes; - const struct ieee80211_cipher_scheme *cipher_schemes; u8 max_nan_de_entries; u8 tx_sk_pacing_shift; u8 weight_multiplier; diff --git a/include/net/sock.h b/include/net/sock.h index 72ca97ccb460..5bed1ea7a722 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -609,7 +609,7 @@ void sock_net_set(struct sock *sk, struct net *net) int sk_set_peek_off(struct sock *sk, int val); -static inline int sk_peek_offset(struct sock *sk, int flags) +static inline int sk_peek_offset(const struct sock *sk, int flags) { if (unlikely(flags & MSG_PEEK)) { return READ_ONCE(sk->sk_peek_off); @@ -849,7 +849,7 @@ static inline void sk_add_bind_node(struct sock *sk, ({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;}); \ pos = rcu_dereference(hlist_next_rcu(pos))) -static inline struct user_namespace *sk_user_ns(struct sock *sk) +static inline struct user_namespace *sk_user_ns(const struct sock *sk) { /* Careful only use this in a context where these parameters * can not change and must all be valid, such as recvmsg from @@ -895,7 +895,7 @@ enum sock_flags { #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) -static inline void sock_copy_flags(struct sock *nsk, struct sock *osk) +static inline void sock_copy_flags(struct sock *nsk, const struct sock *osk) { nsk->sk_flags = osk->sk_flags; } @@ -1240,6 +1240,7 @@ struct proto { void (*enter_memory_pressure)(struct sock *sk); void (*leave_memory_pressure)(struct sock *sk); atomic_long_t *memory_allocated; /* Current allocated memory. */ + int __percpu *per_cpu_fw_alloc; struct percpu_counter *sockets_allocated; /* Current number of sockets. */ /* @@ -1383,21 +1384,46 @@ static inline bool sk_under_memory_pressure(const struct sock *sk) } static inline long -sk_memory_allocated(const struct sock *sk) +proto_memory_allocated(const struct proto *prot) { - return atomic_long_read(sk->sk_prot->memory_allocated); + return max(0L, atomic_long_read(prot->memory_allocated)); } static inline long +sk_memory_allocated(const struct sock *sk) +{ + return proto_memory_allocated(sk->sk_prot); +} + +/* 1 MB per cpu, in page units */ +#define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT)) + +static inline void sk_memory_allocated_add(struct sock *sk, int amt) { - return atomic_long_add_return(amt, sk->sk_prot->memory_allocated); + int local_reserve; + + preempt_disable(); + local_reserve = __this_cpu_add_return(*sk->sk_prot->per_cpu_fw_alloc, amt); + if (local_reserve >= SK_MEMORY_PCPU_RESERVE) { + __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); + atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); + } + preempt_enable(); } static inline void sk_memory_allocated_sub(struct sock *sk, int amt) { - atomic_long_sub(amt, sk->sk_prot->memory_allocated); + int local_reserve; + + preempt_disable(); + local_reserve = __this_cpu_sub_return(*sk->sk_prot->per_cpu_fw_alloc, amt); + if (local_reserve <= -SK_MEMORY_PCPU_RESERVE) { + __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); + atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); + } + preempt_enable(); } #define SK_ALLOC_PERCPU_COUNTER_BATCH 16 @@ -1426,12 +1452,6 @@ proto_sockets_allocated_sum_positive(struct proto *prot) return percpu_counter_sum_positive(prot->sockets_allocated); } -static inline long -proto_memory_allocated(struct proto *prot) -{ - return atomic_long_read(prot->memory_allocated); -} - static inline bool proto_memory_pressure(struct proto *prot) { @@ -1518,30 +1538,18 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind); void __sk_mem_reduce_allocated(struct sock *sk, int amount); void __sk_mem_reclaim(struct sock *sk, int amount); -/* We used to have PAGE_SIZE here, but systems with 64KB pages - * do not necessarily have 16x time more memory than 4KB ones. - */ -#define SK_MEM_QUANTUM 4096 -#define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM) #define SK_MEM_SEND 0 #define SK_MEM_RECV 1 -/* sysctl_mem values are in pages, we convert them in SK_MEM_QUANTUM units */ +/* sysctl_mem values are in pages */ static inline long sk_prot_mem_limits(const struct sock *sk, int index) { - long val = sk->sk_prot->sysctl_mem[index]; - -#if PAGE_SIZE > SK_MEM_QUANTUM - val <<= PAGE_SHIFT - SK_MEM_QUANTUM_SHIFT; -#elif PAGE_SIZE < SK_MEM_QUANTUM - val >>= SK_MEM_QUANTUM_SHIFT - PAGE_SHIFT; -#endif - return val; + return sk->sk_prot->sysctl_mem[index]; } static inline int sk_mem_pages(int amt) { - return (amt + SK_MEM_QUANTUM - 1) >> SK_MEM_QUANTUM_SHIFT; + return (amt + PAGE_SIZE - 1) >> PAGE_SHIFT; } static inline bool sk_has_account(struct sock *sk) @@ -1552,19 +1560,23 @@ static inline bool sk_has_account(struct sock *sk) static inline bool sk_wmem_schedule(struct sock *sk, int size) { + int delta; + if (!sk_has_account(sk)) return true; - return size <= sk->sk_forward_alloc || - __sk_mem_schedule(sk, size, SK_MEM_SEND); + delta = size - sk->sk_forward_alloc; + return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_SEND); } static inline bool sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) { + int delta; + if (!sk_has_account(sk)) return true; - return size <= sk->sk_forward_alloc || - __sk_mem_schedule(sk, size, SK_MEM_RECV) || + delta = size - sk->sk_forward_alloc; + return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_RECV) || skb_pfmemalloc(skb); } @@ -1590,7 +1602,7 @@ static inline void sk_mem_reclaim(struct sock *sk) reclaimable = sk->sk_forward_alloc - sk_unused_reserved_mem(sk); - if (reclaimable >= SK_MEM_QUANTUM) + if (reclaimable >= (int)PAGE_SIZE) __sk_mem_reclaim(sk, reclaimable); } @@ -1600,19 +1612,6 @@ static inline void sk_mem_reclaim_final(struct sock *sk) sk_mem_reclaim(sk); } -static inline void sk_mem_reclaim_partial(struct sock *sk) -{ - int reclaimable; - - if (!sk_has_account(sk)) - return; - - reclaimable = sk->sk_forward_alloc - sk_unused_reserved_mem(sk); - - if (reclaimable > SK_MEM_QUANTUM) - __sk_mem_reclaim(sk, reclaimable - 1); -} - static inline void sk_mem_charge(struct sock *sk, int size) { if (!sk_has_account(sk)) @@ -1620,29 +1619,17 @@ static inline void sk_mem_charge(struct sock *sk, int size) sk->sk_forward_alloc -= size; } -/* the following macros control memory reclaiming in sk_mem_uncharge() +/* the following macros control memory reclaiming in mptcp_rmem_uncharge() */ #define SK_RECLAIM_THRESHOLD (1 << 21) #define SK_RECLAIM_CHUNK (1 << 20) static inline void sk_mem_uncharge(struct sock *sk, int size) { - int reclaimable; - if (!sk_has_account(sk)) return; sk->sk_forward_alloc += size; - reclaimable = sk->sk_forward_alloc - sk_unused_reserved_mem(sk); - - /* Avoid a possible overflow. - * TCP send queues can make this happen, if sk_mem_reclaim() - * is not called and more than 2 GBytes are released at once. - * - * If we reach 2 MBytes, reclaim 1 MBytes right now, there is - * no need to hold that much forward allocation anyway. - */ - if (unlikely(reclaimable >= SK_RECLAIM_THRESHOLD)) - __sk_mem_reclaim(sk, SK_RECLAIM_CHUNK); + sk_mem_reclaim(sk); } /* diff --git a/include/net/tcp.h b/include/net/tcp.h index 1e99f5c61f84..4794cae4577e 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -253,6 +253,8 @@ extern long sysctl_tcp_mem[3]; #define TCP_RACK_NO_DUPTHRESH 0x4 /* Do not use DUPACK threshold in RACK */ extern atomic_long_t tcp_memory_allocated; +DECLARE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc); + extern struct percpu_counter tcp_sockets_allocated; extern unsigned long tcp_memory_pressure; diff --git a/include/net/udp.h b/include/net/udp.h index b83a00330566..b60eea2e3fae 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -95,6 +95,7 @@ static inline struct udp_hslot *udp_hashslot2(struct udp_table *table, extern struct proto udp_prot; extern atomic_long_t udp_memory_allocated; +DECLARE_PER_CPU(int, udp_memory_per_cpu_fw_alloc); /* sysctl variables for udp */ extern long sysctl_udp_mem[3]; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index c39d910d4b45..9287712ad977 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1923,7 +1923,7 @@ static inline void xfrm_dev_state_free(struct xfrm_state *x) if (dev->xfrmdev_ops->xdo_dev_state_free) dev->xfrmdev_ops->xdo_dev_state_free(x); xso->dev = NULL; - dev_put_track(dev, &xso->dev_tracker); + netdev_put(dev, &xso->dev_tracker); } } #else diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index a477bf907498..45264e4bb254 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -9,92 +9,6 @@ #include <linux/netdevice.h> #include <linux/tracepoint.h> -#define TRACE_SKB_DROP_REASON \ - EM(SKB_DROP_REASON_NOT_SPECIFIED, NOT_SPECIFIED) \ - EM(SKB_DROP_REASON_NO_SOCKET, NO_SOCKET) \ - EM(SKB_DROP_REASON_PKT_TOO_SMALL, PKT_TOO_SMALL) \ - EM(SKB_DROP_REASON_TCP_CSUM, TCP_CSUM) \ - EM(SKB_DROP_REASON_SOCKET_FILTER, SOCKET_FILTER) \ - EM(SKB_DROP_REASON_UDP_CSUM, UDP_CSUM) \ - EM(SKB_DROP_REASON_NETFILTER_DROP, NETFILTER_DROP) \ - EM(SKB_DROP_REASON_OTHERHOST, OTHERHOST) \ - EM(SKB_DROP_REASON_IP_CSUM, IP_CSUM) \ - EM(SKB_DROP_REASON_IP_INHDR, IP_INHDR) \ - EM(SKB_DROP_REASON_IP_RPFILTER, IP_RPFILTER) \ - EM(SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST, \ - UNICAST_IN_L2_MULTICAST) \ - EM(SKB_DROP_REASON_XFRM_POLICY, XFRM_POLICY) \ - EM(SKB_DROP_REASON_IP_NOPROTO, IP_NOPROTO) \ - EM(SKB_DROP_REASON_SOCKET_RCVBUFF, SOCKET_RCVBUFF) \ - EM(SKB_DROP_REASON_PROTO_MEM, PROTO_MEM) \ - EM(SKB_DROP_REASON_TCP_MD5NOTFOUND, TCP_MD5NOTFOUND) \ - EM(SKB_DROP_REASON_TCP_MD5UNEXPECTED, \ - TCP_MD5UNEXPECTED) \ - EM(SKB_DROP_REASON_TCP_MD5FAILURE, TCP_MD5FAILURE) \ - EM(SKB_DROP_REASON_SOCKET_BACKLOG, SOCKET_BACKLOG) \ - EM(SKB_DROP_REASON_TCP_FLAGS, TCP_FLAGS) \ - EM(SKB_DROP_REASON_TCP_ZEROWINDOW, TCP_ZEROWINDOW) \ - EM(SKB_DROP_REASON_TCP_OLD_DATA, TCP_OLD_DATA) \ - EM(SKB_DROP_REASON_TCP_OVERWINDOW, TCP_OVERWINDOW) \ - EM(SKB_DROP_REASON_TCP_OFOMERGE, TCP_OFOMERGE) \ - EM(SKB_DROP_REASON_TCP_OFO_DROP, TCP_OFO_DROP) \ - EM(SKB_DROP_REASON_TCP_RFC7323_PAWS, TCP_RFC7323_PAWS) \ - EM(SKB_DROP_REASON_TCP_INVALID_SEQUENCE, \ - TCP_INVALID_SEQUENCE) \ - EM(SKB_DROP_REASON_TCP_RESET, TCP_RESET) \ - EM(SKB_DROP_REASON_TCP_INVALID_SYN, TCP_INVALID_SYN) \ - EM(SKB_DROP_REASON_TCP_CLOSE, TCP_CLOSE) \ - EM(SKB_DROP_REASON_TCP_FASTOPEN, TCP_FASTOPEN) \ - EM(SKB_DROP_REASON_TCP_OLD_ACK, TCP_OLD_ACK) \ - EM(SKB_DROP_REASON_TCP_TOO_OLD_ACK, TCP_TOO_OLD_ACK) \ - EM(SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, \ - TCP_ACK_UNSENT_DATA) \ - EM(SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, \ - TCP_OFO_QUEUE_PRUNE) \ - EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES) \ - EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS, \ - BPF_CGROUP_EGRESS) \ - EM(SKB_DROP_REASON_IPV6DISABLED, IPV6DISABLED) \ - EM(SKB_DROP_REASON_NEIGH_CREATEFAIL, NEIGH_CREATEFAIL) \ - EM(SKB_DROP_REASON_NEIGH_FAILED, NEIGH_FAILED) \ - EM(SKB_DROP_REASON_NEIGH_QUEUEFULL, NEIGH_QUEUEFULL) \ - EM(SKB_DROP_REASON_NEIGH_DEAD, NEIGH_DEAD) \ - EM(SKB_DROP_REASON_TC_EGRESS, TC_EGRESS) \ - EM(SKB_DROP_REASON_QDISC_DROP, QDISC_DROP) \ - EM(SKB_DROP_REASON_CPU_BACKLOG, CPU_BACKLOG) \ - EM(SKB_DROP_REASON_XDP, XDP) \ - EM(SKB_DROP_REASON_TC_INGRESS, TC_INGRESS) \ - EM(SKB_DROP_REASON_UNHANDLED_PROTO, UNHANDLED_PROTO) \ - EM(SKB_DROP_REASON_SKB_CSUM, SKB_CSUM) \ - EM(SKB_DROP_REASON_SKB_GSO_SEG, SKB_GSO_SEG) \ - EM(SKB_DROP_REASON_SKB_UCOPY_FAULT, SKB_UCOPY_FAULT) \ - EM(SKB_DROP_REASON_DEV_HDR, DEV_HDR) \ - EM(SKB_DROP_REASON_DEV_READY, DEV_READY) \ - EM(SKB_DROP_REASON_FULL_RING, FULL_RING) \ - EM(SKB_DROP_REASON_NOMEM, NOMEM) \ - EM(SKB_DROP_REASON_HDR_TRUNC, HDR_TRUNC) \ - EM(SKB_DROP_REASON_TAP_FILTER, TAP_FILTER) \ - EM(SKB_DROP_REASON_TAP_TXFILTER, TAP_TXFILTER) \ - EM(SKB_DROP_REASON_ICMP_CSUM, ICMP_CSUM) \ - EM(SKB_DROP_REASON_INVALID_PROTO, INVALID_PROTO) \ - EM(SKB_DROP_REASON_IP_INADDRERRORS, IP_INADDRERRORS) \ - EM(SKB_DROP_REASON_IP_INNOROUTES, IP_INNOROUTES) \ - EM(SKB_DROP_REASON_PKT_TOO_BIG, PKT_TOO_BIG) \ - EMe(SKB_DROP_REASON_MAX, MAX) - -#undef EM -#undef EMe - -#define EM(a, b) TRACE_DEFINE_ENUM(a); -#define EMe(a, b) TRACE_DEFINE_ENUM(a); - -TRACE_SKB_DROP_REASON - -#undef EM -#undef EMe -#define EM(a, b) { a, #b }, -#define EMe(a, b) { a, #b } - /* * Tracepoint for free an sk_buff: */ @@ -121,8 +35,7 @@ TRACE_EVENT(kfree_skb, TP_printk("skbaddr=%p protocol=%u location=%p reason: %s", __entry->skbaddr, __entry->protocol, __entry->location, - __print_symbolic(__entry->reason, - TRACE_SKB_DROP_REASON)) + drop_reasons[__entry->reason]) ); TRACE_EVENT(consume_skb, diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index d9490e3062a7..98f905f16411 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -5874,7 +5874,7 @@ enum nl80211_ap_sme_features { * @NL80211_FEATURE_INACTIVITY_TIMER: This driver takes care of freeing up * the connected inactive stations in AP mode. * @NL80211_FEATURE_CELL_BASE_REG_HINTS: This driver has been tested - * to work properly to suppport receiving regulatory hints from + * to work properly to support receiving regulatory hints from * cellular base stations. * @NL80211_FEATURE_P2P_DEVICE_NEEDS_CHANNEL: (no longer available, only * here to reserve the value for API/ABI compatibility) diff --git a/include/uapi/rdma/mlx5_user_ioctl_verbs.h b/include/uapi/rdma/mlx5_user_ioctl_verbs.h index a21ca8ece8db..7af9e09ea556 100644 --- a/include/uapi/rdma/mlx5_user_ioctl_verbs.h +++ b/include/uapi/rdma/mlx5_user_ioctl_verbs.h @@ -63,6 +63,7 @@ enum mlx5_ib_uapi_dm_type { MLX5_IB_UAPI_DM_TYPE_MEMIC, MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM, MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM, + MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_PATTERN_SW_ICM, }; enum mlx5_ib_uapi_devx_create_event_channel_flags { |