diff options
| author |   Linus Torvalds <torvalds@linux-foundation.org> | 2020-06-03 16:27:18 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-06-03 16:27:18 -0700 |
| commit | cb8e59cc87201af93dfbb6c3dccc8fcad72a09c2 (patch) | |
| tree | a334db9022f89654b777bbce8c4c6632e65b9031 /include/net | |
| parent | Merge branch 'uaccess.comedi' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs (diff) | |
| parent | selftests: net: ip_defrag: ignore EPERM (diff) | |
| download | wireguard-linux-cb8e59cc87201af93dfbb6c3dccc8fcad72a09c2.tar.xz wireguard-linux-cb8e59cc87201af93dfbb6c3dccc8fcad72a09c2.zip | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from David Miller:
1) Allow setting bluetooth L2CAP modes via socket option, from Luiz
Augusto von Dentz.
2) Add GSO partial support to igc, from Sasha Neftin.
3) Several cleanups and improvements to r8169 from Heiner Kallweit.
4) Add IF_OPER_TESTING link state and use it when ethtool triggers a
device self-test. From Andrew Lunn.
5) Start moving away from custom driver versions, use the globally
defined kernel version instead, from Leon Romanovsky.
6) Support GRO vis gro_cells in DSA layer, from Alexander Lobakin.
7) Allow hard IRQ deferral during NAPI, from Eric Dumazet.
8) Add sriov and vf support to hinic, from Luo bin.
9) Support Media Redundancy Protocol (MRP) in the bridging code, from
Horatiu Vultur.
10) Support netmap in the nft_nat code, from Pablo Neira Ayuso.
11) Allow UDPv6 encapsulation of ESP in the ipsec code, from Sabrina
Dubroca. Also add ipv6 support for espintcp.
12) Lots of ReST conversions of the networking documentation, from Mauro
Carvalho Chehab.
13) Support configuration of ethtool rxnfc flows in bcmgenet driver,
from Doug Berger.
14) Allow to dump cgroup id and filter by it in inet_diag code, from
Dmitry Yakunin.
15) Add infrastructure to export netlink attribute policies to
userspace, from Johannes Berg.
16) Several optimizations to sch_fq scheduler, from Eric Dumazet.
17) Fallback to the default qdisc if qdisc init fails because otherwise
a packet scheduler init failure will make a device inoperative. From
Jesper Dangaard Brouer.
18) Several RISCV bpf jit optimizations, from Luke Nelson.
19) Correct the return type of the ->ndo_start_xmit() method in several
drivers, it's netdev_tx_t but many drivers were using
'int'. From Yunjian Wang.
20) Add an ethtool interface for PHY master/slave config, from Oleksij
Rempel.
21) Add BPF iterators, from Yonghang Song.
22) Add cable test infrastructure, including ethool interfaces, from
Andrew Lunn. Marvell PHY driver is the first to support this
facility.
23) Remove zero-length arrays all over, from Gustavo A. R. Silva.
24) Calculate and maintain an explicit frame size in XDP, from Jesper
Dangaard Brouer.
25) Add CAP_BPF, from Alexei Starovoitov.
26) Support terse dumps in the packet scheduler, from Vlad Buslov.
27) Support XDP_TX bulking in dpaa2 driver, from Ioana Ciornei.
28) Add devm_register_netdev(), from Bartosz Golaszewski.
29) Minimize qdisc resets, from Cong Wang.
30) Get rid of kernel_getsockopt and kernel_setsockopt in order to
eliminate set_fs/get_fs calls. From Christoph Hellwig.
* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2517 commits)
selftests: net: ip_defrag: ignore EPERM
net_failover: fixed rollback in net_failover_open()
Revert "tipc: Fix potential tipc_aead refcnt leak in tipc_crypto_rcv"
Revert "tipc: Fix potential tipc_node refcnt leak in tipc_rcv"
vmxnet3: allow rx flow hash ops only when rss is enabled
hinic: add set_channels ethtool_ops support
selftests/bpf: Add a default $(CXX) value
tools/bpf: Don't use $(COMPILE.c)
bpf, selftests: Use bpf_probe_read_kernel
s390/bpf: Use bcr 0,%0 as tail call nop filler
s390/bpf: Maintain 8-byte stack alignment
selftests/bpf: Fix verifier test
selftests/bpf: Fix sample_cnt shared between two threads
bpf, selftests: Adapt cls_redirect to call csum_level helper
bpf: Add csum_level helper for fixing up csum levels
bpf: Fix up bpf_skb_adjust_room helper's skb csum setting
sfc: add missing annotation for efx_ef10_try_update_nic_stats_vf()
crypto/chtls: IPv6 support for inline TLS
Crypto/chcr: Fixes a coccinile check error
Crypto/chcr: Fixes compilations warnings
...
Diffstat (limited to 'include/net')
57 files changed, 1881 insertions, 509 deletions
diff --git a/include/net/act_api.h b/include/net/act_api.h index 124bd139886c..8c3934880670 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -194,7 +194,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack); int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int bind, - int ref); + int ref, bool terse); int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int); int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int); diff --git a/include/net/addrconf.h b/include/net/addrconf.h index e0eabe58aa8b..fdb07105384c 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -6,8 +6,6 @@ #define RTR_SOLICITATION_INTERVAL (4*HZ) #define RTR_SOLICITATION_MAX_INTERVAL (3600*HZ) /* 1 hour */ -#define MIN_VALID_LIFETIME (2*3600) /* 2 hours */ - #define TEMP_VALID_LIFETIME (7*86400) #define TEMP_PREFERRED_LIFETIME (86400) #define REGEN_MAX_RETRY (3) diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index ab988940bf04..91eacbdcf33d 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -72,4 +72,6 @@ bool rxrpc_kernel_call_is_complete(struct rxrpc_call *); void rxrpc_kernel_set_max_life(struct socket *, struct rxrpc_call *, unsigned long); +int rxrpc_sock_set_min_security_level(struct sock *sk, unsigned int val); + #endif /* _NET_RXRPC_H */ diff --git a/include/net/bareudp.h b/include/net/bareudp.h index cb03f6f15956..dc65a0d71d9b 100644 --- a/include/net/bareudp.h +++ b/include/net/bareudp.h @@ -5,6 +5,7 @@ #include <linux/types.h> #include <linux/skbuff.h> +#include <net/rtnetlink.h> struct bareudp_conf { __be16 ethertype; @@ -17,4 +18,10 @@ struct net_device *bareudp_dev_create(struct net *net, const char *name, u8 name_assign_type, struct bareudp_conf *info); +static inline bool netif_is_bareudp(const struct net_device *dev) +{ + return dev->rtnl_link_ops && + !strcmp(dev->rtnl_link_ops->kind, "bareudp"); +} + #endif diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 1576353a2773..18190055374c 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -139,12 +139,26 @@ struct bt_voice { #define BT_PHY_LE_CODED_TX 0x00002000 #define BT_PHY_LE_CODED_RX 0x00004000 +#define BT_MODE 15 + +#define BT_MODE_BASIC 0x00 +#define BT_MODE_ERTM 0x01 +#define BT_MODE_STREAMING 0x02 +#define BT_MODE_LE_FLOWCTL 0x03 +#define BT_MODE_EXT_FLOWCTL 0x04 + __printf(1, 2) void bt_info(const char *fmt, ...); __printf(1, 2) void bt_warn(const char *fmt, ...); __printf(1, 2) void bt_err(const char *fmt, ...); +#if IS_ENABLED(CONFIG_BT_FEATURE_DEBUG) +void bt_dbg_set(bool enable); +bool bt_dbg_get(void); +__printf(1, 2) +void bt_dbg(const char *fmt, ...); +#endif __printf(1, 2) void bt_warn_ratelimited(const char *fmt, ...); __printf(1, 2) @@ -153,7 +167,12 @@ void bt_err_ratelimited(const char *fmt, ...); #define BT_INFO(fmt, ...) bt_info(fmt "\n", ##__VA_ARGS__) #define BT_WARN(fmt, ...) bt_warn(fmt "\n", ##__VA_ARGS__) #define BT_ERR(fmt, ...) bt_err(fmt "\n", ##__VA_ARGS__) + +#if IS_ENABLED(CONFIG_BT_FEATURE_DEBUG) +#define BT_DBG(fmt, ...) bt_dbg(fmt "\n", ##__VA_ARGS__) +#else #define BT_DBG(fmt, ...) pr_debug(fmt "\n", ##__VA_ARGS__) +#endif #define bt_dev_info(hdev, fmt, ...) \ BT_INFO("%s: " fmt, (hdev)->name, ##__VA_ARGS__) diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 5f60e135aeb6..16ab6ce87883 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -53,6 +53,9 @@ #define HCI_NOTIFY_CONN_ADD 1 #define HCI_NOTIFY_CONN_DEL 2 #define HCI_NOTIFY_VOICE_SETTING 3 +#define HCI_NOTIFY_ENABLE_SCO_CVSD 4 +#define HCI_NOTIFY_ENABLE_SCO_TRANSP 5 +#define HCI_NOTIFY_DISABLE_SCO 6 /* HCI bus types */ #define HCI_VIRTUAL 0 @@ -65,6 +68,7 @@ #define HCI_SPI 7 #define HCI_I2C 8 #define HCI_SMD 9 +#define HCI_VIRTIO 10 /* HCI controller types */ #define HCI_PRIMARY 0x00 @@ -214,6 +218,15 @@ enum { * This quirk must be set before hci_register_dev is called. */ HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, + + /* When this quirk is set, the controller has validated that + * LE states reported through the HCI_LE_READ_SUPPORTED_STATES are + * valid. This mechanism is necessary as many controllers have + * been seen has having trouble initiating a connectable + * advertisement despite the state combination being reported as + * supported. + */ + HCI_QUIRK_VALID_LE_STATES, }; /* HCI device flags */ @@ -245,6 +258,7 @@ enum { HCI_MGMT_DEV_CLASS_EVENTS, HCI_MGMT_LOCAL_NAME_EVENTS, HCI_MGMT_OOB_DATA_EVENTS, + HCI_MGMT_EXP_FEATURE_EVENTS, }; /* @@ -294,6 +308,7 @@ enum { HCI_FORCE_STATIC_ADDR, HCI_LL_RPA_RESOLUTION, HCI_CMD_PENDING, + HCI_FORCE_NO_MITM, __HCI_NUM_FLAGS, }; @@ -455,12 +470,11 @@ enum { #define HCI_LE_SLAVE_FEATURES 0x08 #define HCI_LE_PING 0x10 #define HCI_LE_DATA_LEN_EXT 0x20 -#define HCI_LE_PHY_2M 0x01 -#define HCI_LE_PHY_CODED 0x08 -#define HCI_LE_EXT_ADV 0x10 +#define HCI_LE_LL_PRIVACY 0x40 #define HCI_LE_EXT_SCAN_POLICY 0x80 #define HCI_LE_PHY_2M 0x01 #define HCI_LE_PHY_CODED 0x08 +#define HCI_LE_EXT_ADV 0x10 #define HCI_LE_CHAN_SEL_ALG2 0x40 #define HCI_LE_CIS_MASTER 0x10 #define HCI_LE_CIS_SLAVE 0x20 @@ -1272,6 +1286,13 @@ struct hci_rp_read_data_block_size { #define HCI_OP_READ_LOCAL_CODECS 0x100b +#define HCI_OP_READ_LOCAL_PAIRING_OPTS 0x100c +struct hci_rp_read_local_pairing_opts { + __u8 status; + __u8 pairing_opts; + __u8 max_key_size; +} __packed; + #define HCI_OP_READ_PAGE_SCAN_ACTIVITY 0x0c1b struct hci_rp_read_page_scan_activity { __u8 status; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index d4e28773d378..cdd4f1db8670 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -110,7 +110,7 @@ enum suspend_tasks { enum suspended_state { BT_RUNNING = 0, BT_SUSPEND_DISCONNECT, - BT_SUSPEND_COMPLETE, + BT_SUSPEND_CONFIGURE_WAKE, }; struct hci_conn_hash { @@ -312,6 +312,8 @@ struct hci_dev { __u16 conn_info_max_age; __u16 auth_payload_timeout; __u8 min_enc_key_size; + __u8 max_enc_key_size; + __u8 pairing_opts; __u8 ssp_debug_mode; __u8 hw_error_code; __u32 clock; @@ -484,6 +486,11 @@ struct hci_dev { struct led_trigger *power_led; #endif +#if IS_ENABLED(CONFIG_BT_MSFTEXT) + __u16 msft_opcode; + void *msft_data; +#endif + int (*open)(struct hci_dev *hdev); int (*close)(struct hci_dev *hdev); int (*flush)(struct hci_dev *hdev); @@ -496,6 +503,7 @@ struct hci_dev { int (*set_diag)(struct hci_dev *hdev, bool enable); int (*set_bdaddr)(struct hci_dev *hdev, const bdaddr_t *bdaddr); void (*cmd_timeout)(struct hci_dev *hdev); + bool (*prevent_wake)(struct hci_dev *hdev); }; #define HCI_PHY_HANDLE(handle) (handle & 0xff) @@ -638,6 +646,7 @@ extern struct mutex hci_cb_list_lock; do { \ hci_dev_clear_flag(hdev, HCI_LE_SCAN); \ hci_dev_clear_flag(hdev, HCI_LE_ADV); \ + hci_dev_clear_flag(hdev, HCI_LL_RPA_RESOLUTION);\ hci_dev_clear_flag(hdev, HCI_PERIODIC_INQ); \ } while (0) @@ -1116,6 +1125,14 @@ int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb); int hci_recv_diag(struct hci_dev *hdev, struct sk_buff *skb); __printf(2, 3) void hci_set_hw_info(struct hci_dev *hdev, const char *fmt, ...); __printf(2, 3) void hci_set_fw_info(struct hci_dev *hdev, const char *fmt, ...); + +static inline void hci_set_msft_opcode(struct hci_dev *hdev, __u16 opcode) +{ +#if IS_ENABLED(CONFIG_BT_MSFTEXT) + hdev->msft_opcode = opcode; +#endif +} + int hci_dev_open(__u16 dev); int hci_dev_close(__u16 dev); int hci_dev_do_close(struct hci_dev *hdev); @@ -1364,10 +1381,26 @@ static inline void hci_auth_cfm(struct hci_conn *conn, __u8 status) conn->security_cfm_cb(conn, status); } -static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status, - __u8 encrypt) +static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status) { struct hci_cb *cb; + __u8 encrypt; + + if (conn->state == BT_CONFIG) { + if (status) + conn->state = BT_CONNECTED; + + hci_connect_cfm(conn, status); + hci_conn_drop(conn); + return; + } + + if (!test_bit(HCI_CONN_ENCRYPT, &conn->flags)) + encrypt = 0x00; + else if (test_bit(HCI_CONN_AES_CCM, &conn->flags)) + encrypt = 0x02; + else + encrypt = 0x01; if (conn->sec_level == BT_SECURITY_SDP) conn->sec_level = BT_SECURITY_LOW; @@ -1538,6 +1571,7 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event); #define HCI_MGMT_NO_HDEV BIT(1) #define HCI_MGMT_UNTRUSTED BIT(2) #define HCI_MGMT_UNCONFIGURED BIT(3) +#define HCI_MGMT_HDEV_OPTIONAL BIT(4) struct hci_mgmt_handler { int (*func) (struct sock *sk, struct hci_dev *hdev, void *data, diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index dada14d0622c..8f1e6a7a2df8 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -499,7 +499,7 @@ struct l2cap_ecred_conn_req { __le16 mtu; __le16 mps; __le16 credits; - __le16 scid[0]; + __le16 scid[]; } __packed; struct l2cap_ecred_conn_rsp { @@ -507,13 +507,13 @@ struct l2cap_ecred_conn_rsp { __le16 mps; __le16 credits; __le16 result; - __le16 dcid[0]; + __le16 dcid[]; }; struct l2cap_ecred_reconf_req { __le16 mtu; __le16 mps; - __le16 scid[0]; + __le16 scid[]; } __packed; #define L2CAP_RECONF_SUCCESS 0x0000 diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index f41cd87550dc..16e0d87bd8fa 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -70,14 +70,14 @@ struct mgmt_rp_read_version { struct mgmt_rp_read_commands { __le16 num_commands; __le16 num_events; - __le16 opcodes[0]; + __le16 opcodes[]; } __packed; #define MGMT_OP_READ_INDEX_LIST 0x0003 #define MGMT_READ_INDEX_LIST_SIZE 0 struct mgmt_rp_read_index_list { __le16 num_controllers; - __le16 index[0]; + __le16 index[]; } __packed; /* Reserve one extra byte for names in management messages so that they @@ -183,7 +183,7 @@ struct mgmt_link_key_info { struct mgmt_cp_load_link_keys { __u8 debug_keys; __le16 key_count; - struct mgmt_link_key_info keys[0]; + struct mgmt_link_key_info keys[]; } __packed; #define MGMT_LOAD_LINK_KEYS_SIZE 3 @@ -206,7 +206,7 @@ struct mgmt_ltk_info { #define MGMT_OP_LOAD_LONG_TERM_KEYS 0x0013 struct mgmt_cp_load_long_term_keys { __le16 key_count; - struct mgmt_ltk_info keys[0]; + struct mgmt_ltk_info keys[]; } __packed; #define MGMT_LOAD_LONG_TERM_KEYS_SIZE 2 @@ -223,7 +223,7 @@ struct mgmt_rp_disconnect { #define MGMT_GET_CONNECTIONS_SIZE 0 struct mgmt_rp_get_connections { __le16 conn_count; - struct mgmt_addr_info addr[0]; + struct mgmt_addr_info addr[]; } __packed; #define MGMT_OP_PIN_CODE_REPLY 0x0016 @@ -413,7 +413,7 @@ struct mgmt_irk_info { #define MGMT_OP_LOAD_IRKS 0x0030 struct mgmt_cp_load_irks { __le16 irk_count; - struct mgmt_irk_info irks[0]; + struct mgmt_irk_info irks[]; } __packed; #define MGMT_LOAD_IRKS_SIZE 2 @@ -465,7 +465,7 @@ struct mgmt_conn_param { #define MGMT_OP_LOAD_CONN_PARAM 0x0035 struct mgmt_cp_load_conn_param { __le16 param_count; - struct mgmt_conn_param params[0]; + struct mgmt_conn_param params[]; } __packed; #define MGMT_LOAD_CONN_PARAM_SIZE 2 @@ -473,7 +473,7 @@ struct mgmt_cp_load_conn_param { #define MGMT_READ_UNCONF_INDEX_LIST_SIZE 0 struct mgmt_rp_read_unconf_index_list { __le16 num_controllers; - __le16 index[0]; + __le16 index[]; } __packed; #define MGMT_OPTION_EXTERNAL_CONFIG 0x00000001 @@ -504,7 +504,7 @@ struct mgmt_cp_start_service_discovery { __u8 type; __s8 rssi; __le16 uuid_count; - __u8 uuids[0][16]; + __u8 uuids[][16]; } __packed; #define MGMT_START_SERVICE_DISCOVERY_SIZE 4 @@ -516,7 +516,7 @@ struct mgmt_cp_read_local_oob_ext_data { struct mgmt_rp_read_local_oob_ext_data { __u8 type; __le16 eir_len; - __u8 eir[0]; + __u8 eir[]; } __packed; #define MGMT_OP_READ_EXT_INDEX_LIST 0x003C @@ -527,7 +527,7 @@ struct mgmt_rp_read_ext_index_list { __le16 index; __u8 type; __u8 bus; - } entry[0]; + } entry[]; } __packed; #define MGMT_OP_READ_ADV_FEATURES 0x0003D @@ -538,7 +538,7 @@ struct mgmt_rp_read_adv_features { __u8 max_scan_rsp_len; __u8 max_instances; __u8 num_instances; - __u8 instance[0]; + __u8 instance[]; } __packed; #define MGMT_OP_ADD_ADVERTISING 0x003E @@ -549,7 +549,7 @@ struct mgmt_cp_add_advertising { __le16 timeout; __u8 adv_data_len; __u8 scan_rsp_len; - __u8 data[0]; + __u8 data[]; } __packed; #define MGMT_ADD_ADVERTISING_SIZE 11 struct mgmt_rp_add_advertising { @@ -603,7 +603,7 @@ struct mgmt_rp_read_ext_info { __le32 supported_settings; __le32 current_settings; __le16 eir_len; - __u8 eir[0]; + __u8 eir[]; } __packed; #define MGMT_OP_SET_APPEARANCE 0x0043 @@ -668,17 +668,45 @@ struct mgmt_blocked_key_info { struct mgmt_cp_set_blocked_keys { __le16 key_count; - struct mgmt_blocked_key_info keys[0]; + struct mgmt_blocked_key_info keys[]; } __packed; #define MGMT_OP_SET_BLOCKED_KEYS_SIZE 2 #define MGMT_OP_SET_WIDEBAND_SPEECH 0x0047 +#define MGMT_OP_READ_SECURITY_INFO 0x0048 +#define MGMT_READ_SECURITY_INFO_SIZE 0 +struct mgmt_rp_read_security_info { + __le16 sec_len; + __u8 sec[]; +} __packed; + +#define MGMT_OP_READ_EXP_FEATURES_INFO 0x0049 +#define MGMT_READ_EXP_FEATURES_INFO_SIZE 0 +struct mgmt_rp_read_exp_features_info { + __le16 feature_count; + struct { + __u8 uuid[16]; + __le32 flags; + } features[]; +} __packed; + +#define MGMT_OP_SET_EXP_FEATURE 0x004a +struct mgmt_cp_set_exp_feature { + __u8 uuid[16]; + __u8 param[]; +} __packed; +#define MGMT_SET_EXP_FEATURE_SIZE 16 +struct mgmt_rp_set_exp_feature { + __u8 uuid[16]; + __le32 flags; +} __packed; + #define MGMT_EV_CMD_COMPLETE 0x0001 struct mgmt_ev_cmd_complete { __le16 opcode; __u8 status; - __u8 data[0]; + __u8 data[]; } __packed; #define MGMT_EV_CMD_STATUS 0x0002 @@ -726,7 +754,7 @@ struct mgmt_ev_device_connected { struct mgmt_addr_info addr; __le32 flags; __le16 eir_len; - __u8 eir[0]; + __u8 eir[]; } __packed; #define MGMT_DEV_DISCONN_UNKNOWN 0x00 @@ -781,7 +809,7 @@ struct mgmt_ev_device_found { __s8 rssi; __le32 flags; __le16 eir_len; - __u8 eir[0]; + __u8 eir[]; } __packed; #define MGMT_EV_DISCOVERING 0x0013 @@ -876,7 +904,7 @@ struct mgmt_ev_ext_index { struct mgmt_ev_local_oob_data_updated { __u8 type; __le16 eir_len; - __u8 eir[0]; + __u8 eir[]; } __packed; #define MGMT_EV_ADVERTISING_ADDED 0x0023 @@ -892,10 +920,16 @@ struct mgmt_ev_advertising_removed { #define MGMT_EV_EXT_INFO_CHANGED 0x0025 struct mgmt_ev_ext_info_changed { __le16 eir_len; - __u8 eir[0]; + __u8 eir[]; } __packed; #define MGMT_EV_PHY_CONFIGURATION_CHANGED 0x0026 struct mgmt_ev_phy_configuration_changed { __le32 selected_phys; } __packed; + +#define MGMT_EV_EXP_FEATURE_CHANGED 0x0027 +struct mgmt_ev_exp_feature_changed { + __u8 uuid[16]; + __le32 flags; +} __packed; diff --git a/include/net/bond_alb.h b/include/net/bond_alb.h index b3504fcd773d..f6af76c87a6c 100644 --- a/include/net/bond_alb.h +++ b/include/net/bond_alb.h @@ -158,6 +158,10 @@ void bond_alb_handle_link_change(struct bonding *bond, struct slave *slave, char void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave); int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev); int bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev); +struct slave *bond_xmit_alb_slave_get(struct bonding *bond, + struct sk_buff *skb); +struct slave *bond_xmit_tlb_slave_get(struct bonding *bond, + struct sk_buff *skb); void bond_alb_monitor(struct work_struct *); int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr); void bond_alb_clear_vlan(struct bonding *bond, unsigned short vlan_id); diff --git a/include/net/bonding.h b/include/net/bonding.h index dc2ce31a1f52..aa854a9c01e2 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -200,7 +200,8 @@ struct bonding { struct slave __rcu *curr_active_slave; struct slave __rcu *current_arp_slave; struct slave __rcu *primary_slave; - struct bond_up_slave __rcu *slave_arr; /* Array of usable slaves */ + struct bond_up_slave __rcu *usable_slaves; + struct bond_up_slave __rcu *all_slaves; bool force_primary; s32 slave_cnt; /* never change this value outside the attach/detach wrappers */ int (*recv_probe)(const struct sk_buff *, struct bonding *, @@ -237,7 +238,6 @@ struct bonding { struct dentry *debug_dir; #endif /* CONFIG_DEBUG_FS */ struct rtnl_link_stats64 bond_stats; - struct lock_class_key stats_lock_key; }; #define bond_slave_get_rcu(dev) \ @@ -505,18 +505,17 @@ static inline unsigned long slave_last_rx(struct bonding *bond, } #ifdef CONFIG_NET_POLL_CONTROLLER -static inline void bond_netpoll_send_skb(const struct slave *slave, +static inline netdev_tx_t bond_netpoll_send_skb(const struct slave *slave, struct sk_buff *skb) { - struct netpoll *np = slave->np; - - if (np) - netpoll_send_skb(np, skb); + return netpoll_send_skb(slave->np, skb); } #else -static inline void bond_netpoll_send_skb(const struct slave *slave, +static inline netdev_tx_t bond_netpoll_send_skb(const struct slave *slave, struct sk_buff *skb) { + BUG(); + return NETDEV_TX_OK; } #endif @@ -610,7 +609,7 @@ struct bond_net { }; int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave); -void bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev); +netdev_tx_t bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev); int bond_create(struct net *net, const char *name); int bond_create_sysfs(struct bond_net *net); void bond_destroy_sysfs(struct bond_net *net); @@ -743,10 +742,11 @@ extern struct bond_parm_tbl ad_select_tbl[]; /* exported from bond_netlink.c */ extern struct rtnl_link_ops bond_link_ops; -static inline void bond_tx_drop(struct net_device *dev, struct sk_buff *skb) +static inline netdev_tx_t bond_tx_drop(struct net_device *dev, struct sk_buff *skb) { atomic_long_inc(&dev->tx_dropped); dev_kfree_skb_any(skb); + return NET_XMIT_DROP; } #endif /* _NET_BONDING_H */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 70e48f66dac8..b58ad1a3f695 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -128,6 +128,7 @@ enum ieee80211_channel_flags { * with cfg80211. * * @center_freq: center frequency in MHz + * @freq_offset: offset from @center_freq, in KHz * @hw_value: hardware-specific value for the channel * @flags: channel flags from &enum ieee80211_channel_flags. * @orig_flags: channel flags at registration time, used by regulatory @@ -149,6 +150,7 @@ enum ieee80211_channel_flags { struct ieee80211_channel { enum nl80211_band band; u32 center_freq; + u16 freq_offset; u16 hw_value; u32 flags; int max_antenna_gain; @@ -352,10 +354,13 @@ struct ieee80211_sta_he_cap { * * @types_mask: interface types mask * @he_cap: holds the HE capabilities + * @he_6ghz_capa: HE 6 GHz capabilities, must be filled in for a + * 6 GHz band channel (and 0 may be valid value). */ struct ieee80211_sband_iftype_data { u16 types_mask; struct ieee80211_sta_he_cap he_cap; + struct ieee80211_he_6ghz_capa he_6ghz_capa; }; /** @@ -508,6 +513,26 @@ ieee80211_get_he_sta_cap(const struct ieee80211_supported_band *sband) } /** + * ieee80211_get_he_6ghz_capa - return HE 6 GHz capabilities + * @sband: the sband to search for the STA on + * @iftype: the iftype to search for + * + * Return: the 6GHz capabilities + */ +static inline __le16 +ieee80211_get_he_6ghz_capa(const struct ieee80211_supported_band *sband, + enum nl80211_iftype iftype) +{ + const struct ieee80211_sband_iftype_data *data = + ieee80211_get_sband_iftype_data(sband, iftype); + + if (WARN_ON(!data || !data->he_cap.has_he)) + return 0; + + return data->he_6ghz_capa.capa; +} + +/** * wiphy_read_of_freq_limits - read frequency limits from device tree * * @wiphy: the wireless device to get extra limits for @@ -617,6 +642,7 @@ struct key_params { * If edmg is requested (i.e. the .channels member is non-zero), * chan will define the primary channel and all other * parameters are ignored. + * @freq1_offset: offset from @center_freq1, in KHz */ struct cfg80211_chan_def { struct ieee80211_channel *chan; @@ -624,8 +650,22 @@ struct cfg80211_chan_def { u32 center_freq1; u32 center_freq2; struct ieee80211_edmg edmg; + u16 freq1_offset; }; +/* + * cfg80211_bitrate_mask - masks for bitrate control + */ +struct cfg80211_bitrate_mask { + struct { + u32 legacy; + u8 ht_mcs[IEEE80211_HT_MCS_MASK_LEN]; + u16 vht_mcs[NL80211_VHT_NSS_MAX]; + enum nl80211_txrate_gi gi; + } control[NUM_NL80211_BANDS]; +}; + + /** * struct cfg80211_tid_cfg - TID specific configuration * @config_override: Flag to notify driver to reset TID configuration @@ -636,17 +676,23 @@ struct cfg80211_chan_def { * @noack: noack configuration value for the TID * @retry_long: retry count value * @retry_short: retry count value - * @ampdu: Enable/Disable aggregation + * @ampdu: Enable/Disable MPDU aggregation * @rtscts: Enable/Disable RTS/CTS + * @amsdu: Enable/Disable MSDU aggregation + * @txrate_type: Tx bitrate mask type + * @txrate_mask: Tx bitrate to be applied for the TID */ struct cfg80211_tid_cfg { bool config_override; u8 tids; - u32 mask; + u64 mask; enum nl80211_tid_config noack; u8 retry_long, retry_short; enum nl80211_tid_config ampdu; enum nl80211_tid_config rtscts; + enum nl80211_tid_config amsdu; + enum nl80211_tx_rate_setting txrate_type; + struct cfg80211_bitrate_mask txrate_mask; }; /** @@ -713,6 +759,7 @@ cfg80211_chandef_identical(const struct cfg80211_chan_def *chandef1, return (chandef1->chan == chandef2->chan && chandef1->width == chandef2->width && chandef1->center_freq1 == chandef2->center_freq1 && + chandef1->freq1_offset == chandef2->freq1_offset && chandef1->center_freq2 == chandef2->center_freq2); } @@ -1000,18 +1047,6 @@ struct cfg80211_acl_data { struct mac_address mac_addrs[]; }; -/* - * cfg80211_bitrate_mask - masks for bitrate control - */ -struct cfg80211_bitrate_mask { - struct { - u32 legacy; - u8 ht_mcs[IEEE80211_HT_MCS_MASK_LEN]; - u16 vht_mcs[NL80211_VHT_NSS_MAX]; - enum nl80211_txrate_gi gi; - } control[NUM_NL80211_BANDS]; -}; - /** * enum cfg80211_ap_settings_flags - AP settings flags * @@ -1054,6 +1089,7 @@ enum cfg80211_ap_settings_flags { * @ht_required: stations must support HT * @vht_required: stations must support VHT * @twt_responder: Enable Target Wait Time + * @he_required: stations must support HE * @flags: flags, as defined in enum cfg80211_ap_settings_flags * @he_obss_pd: OBSS Packet Detection settings * @he_bss_color: BSS Color settings @@ -1083,7 +1119,7 @@ struct cfg80211_ap_settings { const struct ieee80211_vht_cap *vht_cap; const struct ieee80211_he_cap_elem *he_cap; const struct ieee80211_he_operation *he_oper; - bool ht_required, vht_required; + bool ht_required, vht_required, he_required; bool twt_responder; u32 flags; struct ieee80211_he_obss_pd he_obss_pd; @@ -1225,6 +1261,7 @@ struct sta_txpwr { * @he_capa_len: the length of the HE capabilities * @airtime_weight: airtime scheduler weight for this station * @txpwr: transmit power for an associated station + * @he_6ghz_capa: HE 6 GHz Band capabilities of station */ struct station_parameters { const u8 *supported_rates; @@ -1257,6 +1294,7 @@ struct station_parameters { u8 he_capa_len; u16 airtime_weight; struct sta_txpwr txpwr; + const struct ieee80211_he_6ghz_capa *he_6ghz_capa; }; /** @@ -2029,7 +2067,7 @@ struct cfg80211_scan_request { bool no_cck; /* keep last */ - struct ieee80211_channel *channels[0]; + struct ieee80211_channel *channels[]; }; static inline void get_random_mask_addr(u8 *buf, const u8 *addr, const u8 *mask) @@ -2175,7 +2213,7 @@ struct cfg80211_sched_scan_request { struct list_head list; /* keep last */ - struct ieee80211_channel *channels[0]; + struct ieee80211_channel *channels[]; }; /** @@ -2297,7 +2335,7 @@ struct cfg80211_bss { u8 bssid_index; u8 max_bssid_indicator; - u8 priv[0] __aligned(sizeof(void *)); + u8 priv[] __aligned(sizeof(void *)); }; /** @@ -2898,12 +2936,17 @@ struct cfg80211_wowlan_wakeup { /** * struct cfg80211_gtk_rekey_data - rekey data - * @kek: key encryption key (NL80211_KEK_LEN bytes) - * @kck: key confirmation key (NL80211_KCK_LEN bytes) + * @kek: key encryption key (@kek_len bytes) + * @kck: key confirmation key (@kck_len bytes) * @replay_ctr: replay counter (NL80211_REPLAY_CTR_LEN bytes) + * @kek_len: length of kek + * @kck_len length of kck + * @akm: akm (oui, id) */ struct cfg80211_gtk_rekey_data { const u8 *kek, *kck, *replay_ctr; + u32 akm; + u8 kek_len, kck_len; }; /** @@ -3385,6 +3428,21 @@ struct cfg80211_update_owe_info { }; /** + * struct mgmt_frame_regs - management frame registrations data + * @global_stypes: bitmap of management frame subtypes registered + * for the entire device + * @interface_stypes: bitmap of management frame subtypes registered + * for the given interface + * @global_mcast_rx: mcast RX is needed globally for these subtypes + * @interface_mcast_stypes: mcast RX is needed on this interface + * for these subtypes + */ +struct mgmt_frame_regs { + u32 global_stypes, interface_stypes; + u32 global_mcast_stypes, interface_mcast_stypes; +}; + +/** * struct cfg80211_ops - backend description for wireless configuration * * This struct is registered by fullmac card drivers and/or wireless stacks @@ -3608,8 +3666,8 @@ struct cfg80211_update_owe_info { * The driver should not call cfg80211_sched_scan_stopped() for a requested * stop (when this method returns 0). * - * @mgmt_frame_register: Notify driver that a management frame type was - * registered. The callback is allowed to sleep. + * @update_mgmt_frame_registrations: Notify the driver that management frame + * registrations were updated. The callback is allowed to sleep. * * @set_antenna: Set antenna configuration (tx_ant, rx_ant) on the device. * Parameters are bitmaps of allowed antennas to use for TX/RX. Drivers may @@ -3932,9 +3990,9 @@ struct cfg80211_ops { struct net_device *dev, u32 rate, u32 pkts, u32 intvl); - void (*mgmt_frame_register)(struct wiphy *wiphy, - struct wireless_dev *wdev, - u16 frame_type, bool reg); + void (*update_mgmt_frame_registrations)(struct wiphy *wiphy, + struct wireless_dev *wdev, + struct mgmt_frame_regs *upd); int (*set_antenna)(struct wiphy *wiphy, u32 tx_ant, u32 rx_ant); int (*get_antenna)(struct wiphy *wiphy, u32 *tx_ant, u32 *rx_ant); @@ -4046,7 +4104,8 @@ struct cfg80211_ops { struct net_device *dev, const u8 *buf, size_t len, const u8 *dest, const __be16 proto, - const bool noencrypt); + const bool noencrypt, + u64 *cookie); int (*get_ftm_responder_stats)(struct wiphy *wiphy, struct net_device *dev, @@ -4112,9 +4171,10 @@ struct cfg80211_ops { * beaconing mode (AP, IBSS, Mesh, ...). * @WIPHY_FLAG_HAS_STATIC_WEP: The device supports static WEP key installation * before connection. + * @WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK: The device supports bigger kek and kck keys */ enum wiphy_flags { - /* use hole at 0 */ + WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK = BIT(0), /* use hole at 1 */ /* use hole at 2 */ WIPHY_FLAG_NETNS_OK = BIT(3), @@ -4829,7 +4889,7 @@ struct wiphy { u8 max_data_retry_count; - char priv[0] __aligned(NETDEV_ALIGN); + char priv[] __aligned(NETDEV_ALIGN); }; static inline struct net *wiphy_net(struct wiphy *wiphy) @@ -5015,6 +5075,7 @@ struct cfg80211_cqm_config; * by cfg80211 on change_interface * @mgmt_registrations: list of registrations for management frames * @mgmt_registrations_lock: lock for the list + * @mgmt_registrations_update_wk: update work to defer from atomic context * @mtx: mutex used to lock data in this struct, may be used by drivers * and some API functions require it held * @beacon_interval: beacon interval used on this device for transmitting @@ -5045,6 +5106,8 @@ struct cfg80211_cqm_config; * @pmsr_list: (private) peer measurement requests * @pmsr_lock: (private) peer measurements requests/results lock * @pmsr_free_wk: (private) peer measurements cleanup work + * @unprot_beacon_reported: (private) timestamp of last + * unprotected beacon report */ struct wireless_dev { struct wiphy *wiphy; @@ -5058,6 +5121,7 @@ struct wireless_dev { struct list_head mgmt_registrations; spinlock_t mgmt_registrations_lock; + struct work_struct mgmt_registrations_update_wk; struct mutex mtx; @@ -5121,6 +5185,8 @@ struct wireless_dev { struct list_head pmsr_list; spinlock_t pmsr_lock; struct work_struct pmsr_free_wk; + + unsigned long unprot_beacon_reported; }; static inline u8 *wdev_address(struct wireless_dev *wdev) @@ -5156,29 +5222,106 @@ static inline void *wdev_priv(struct wireless_dev *wdev) */ /** + * ieee80211_channel_equal - compare two struct ieee80211_channel + * + * @a: 1st struct ieee80211_channel + * @b: 2nd struct ieee80211_channel + * Return: true if center frequency of @a == @b + */ +static inline bool +ieee80211_channel_equal(struct ieee80211_channel *a, + struct ieee80211_channel *b) +{ + return (a->center_freq == b->center_freq && + a->freq_offset == b->freq_offset); +} + +/** + * ieee80211_channel_to_khz - convert ieee80211_channel to frequency in KHz + * @chan: struct ieee80211_channel to convert + * Return: The corresponding frequency (in KHz) + */ +static inline u32 +ieee80211_channel_to_khz(const struct ieee80211_channel *chan) +{ + return MHZ_TO_KHZ(chan->center_freq) + chan->freq_offset; +} + +/** + * ieee80211_channel_to_freq_khz - convert channel number to frequency + * @chan: channel number + * @band: band, necessary due to channel number overlap + * Return: The corresponding frequency (in KHz), or 0 if the conversion failed. + */ +u32 ieee80211_channel_to_freq_khz(int chan, enum nl80211_band band); + +/** * ieee80211_channel_to_frequency - convert channel number to frequency * @chan: channel number * @band: band, necessary due to channel number overlap * Return: The corresponding frequency (in MHz), or 0 if the conversion failed. */ -int ieee80211_channel_to_frequency(int chan, enum nl80211_band band); +static inline int +ieee80211_channel_to_frequency(int chan, enum nl80211_band band) +{ + return KHZ_TO_MHZ(ieee80211_channel_to_freq_khz(chan, band)); +} + +/** + * ieee80211_freq_khz_to_channel - convert frequency to channel number + * @freq: center frequency in KHz + * Return: The corresponding channel, or 0 if the conversion failed. + */ +int ieee80211_freq_khz_to_channel(u32 freq); /** * ieee80211_frequency_to_channel - convert frequency to channel number - * @freq: center frequency + * @freq: center frequency in MHz * Return: The corresponding channel, or 0 if the conversion failed. */ -int ieee80211_frequency_to_channel(int freq); +static inline int +ieee80211_frequency_to_channel(int freq) +{ + return ieee80211_freq_khz_to_channel(MHZ_TO_KHZ(freq)); +} + +/** + * ieee80211_get_channel_khz - get channel struct from wiphy for specified + * frequency + * @wiphy: the struct wiphy to get the channel for + * @freq: the center frequency (in KHz) of the channel + * Return: The channel struct from @wiphy at @freq. + */ +struct ieee80211_channel * +ieee80211_get_channel_khz(struct wiphy *wiphy, u32 freq); /** * ieee80211_get_channel - get channel struct from wiphy for specified frequency * * @wiphy: the struct wiphy to get the channel for - * @freq: the center frequency of the channel - * + * @freq: the center frequency (in MHz) of the channel * Return: The channel struct from @wiphy at @freq. */ -struct ieee80211_channel *ieee80211_get_channel(struct wiphy *wiphy, int freq); +static inline struct ieee80211_channel * +ieee80211_get_channel(struct wiphy *wiphy, int freq) +{ + return ieee80211_get_channel_khz(wiphy, MHZ_TO_KHZ(freq)); +} + +/** + * cfg80211_channel_is_psc - Check if the channel is a 6 GHz PSC + * @chan: control channel to check + * + * The Preferred Scanning Channels (PSC) are defined in + * Draft IEEE P802.11ax/D5.0, 26.17.2.3.3 + */ +static inline bool cfg80211_channel_is_psc(struct ieee80211_channel *chan) +{ + if (chan->band != NL80211_BAND_6GHZ) + return false; + + return ieee80211_frequency_to_channel(chan->center_freq) % 16 == 5; +} /** * ieee80211_get_response_rate - get basic rate for a given rate @@ -5211,7 +5354,7 @@ u32 ieee80211_mandatory_rates(struct ieee80211_supported_band *sband, * Radiotap parsing functions -- for controlled injection support * * Implemented in net/wireless/radiotap.c - * Documentation in Documentation/networking/radiotap-headers.txt + * Documentation in Documentation/networking/radiotap-headers.rst */ struct radiotap_align_size { @@ -6135,12 +6278,16 @@ void cfg80211_tx_mlme_mgmt(struct net_device *dev, const u8 *buf, size_t len); /** * cfg80211_rx_unprot_mlme_mgmt - notification of unprotected mlme mgmt frame * @dev: network device - * @buf: deauthentication frame (header + body) + * @buf: received management frame (header + body) * @len: length of the frame data * * This function is called whenever a received deauthentication or dissassoc * frame has been dropped in station mode because of MFP being used but the - * frame was not protected. This function may sleep. + * frame was not protected. This is also used to notify reception of a Beacon + * frame that was dropped because it did not include a valid MME MIC while + * beacon protection was enabled (BIGTK configured in station mode). + * + * This function may sleep. */ void cfg80211_rx_unprot_mlme_mgmt(struct net_device *dev, const u8 *buf, size_t len); @@ -6894,6 +7041,26 @@ void cfg80211_conn_failed(struct net_device *dev, const u8 *mac_addr, gfp_t gfp); /** + * cfg80211_rx_mgmt_khz - notification of received, unprocessed management frame + * @wdev: wireless device receiving the frame + * @freq: Frequency on which the frame was received in KHz + * @sig_dbm: signal strength in dBm, or 0 if unknown + * @buf: Management frame (header + body) + * @len: length of the frame data + * @flags: flags, as defined in enum nl80211_rxmgmt_flags + * + * This function is called whenever an Action frame is received for a station + * mode interface, but is not processed in kernel. + * + * Return: %true if a user space application has registered for this frame. + * For action frames, that makes it responsible for rejecting unrecognized + * action frames; %false otherwise, in which case for action frames the + * driver is responsible for rejecting the frame. + */ +bool cfg80211_rx_mgmt_khz(struct wireless_dev *wdev, int freq, int sig_dbm, + const u8 *buf, size_t len, u32 flags); + +/** * cfg80211_rx_mgmt - notification of received, unprocessed management frame * @wdev: wireless device receiving the frame * @freq: Frequency on which the frame was received in MHz @@ -6910,8 +7077,13 @@ void cfg80211_conn_failed(struct net_device *dev, const u8 *mac_addr, * action frames; %false otherwise, in which case for action frames the * driver is responsible for rejecting the frame. */ -bool cfg80211_rx_mgmt(struct wireless_dev *wdev, int freq, int sig_dbm, - const u8 *buf, size_t len, u32 flags); +static inline bool cfg80211_rx_mgmt(struct wireless_dev *wdev, int freq, + int sig_dbm, const u8 *buf, size_t len, + u32 flags) +{ + return cfg80211_rx_mgmt_khz(wdev, MHZ_TO_KHZ(freq), sig_dbm, buf, len, + flags); +} /** * cfg80211_mgmt_tx_status - notification of TX status for management frame @@ -6929,6 +7101,23 @@ bool cfg80211_rx_mgmt(struct wireless_dev *wdev, int freq, int sig_dbm, void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, const u8 *buf, size_t len, bool ack, gfp_t gfp); +/** + * cfg80211_control_port_tx_status - notification of TX status for control + * port frames + * @wdev: wireless device receiving the frame + * @cookie: Cookie returned by cfg80211_ops::tx_control_port() + * @buf: Data frame (header + body) + * @len: length of the frame data + * @ack: Whether frame was acknowledged + * @gfp: context flags + * + * This function is called whenever a control port frame was requested to be + * transmitted with cfg80211_ops::tx_control_port() to report the TX status of + * the transmission attempt. + */ +void cfg80211_control_port_tx_status(struct wireless_dev *wdev, u64 cookie, + const u8 *buf, size_t len, bool ack, + gfp_t gfp); /** * cfg80211_rx_control_port - notification about a received control port frame @@ -7110,6 +7299,21 @@ void cfg80211_probe_status(struct net_device *dev, const u8 *addr, bool is_valid_ack_signal, gfp_t gfp); /** + * cfg80211_report_obss_beacon_khz - report beacon from other APs + * @wiphy: The wiphy that received the beacon + * @frame: the frame + * @len: length of the frame + * @freq: frequency the frame was received on in KHz + * @sig_dbm: signal strength in dBm, or 0 if unknown + * + * Use this function to report to userspace when a beacon was + * received. It is not useful to call this when there is no + * netdev that is in AP/GO mode. + */ +void cfg80211_report_obss_beacon_khz(struct wiphy *wiphy, const u8 *frame, + size_t len, int freq, int sig_dbm); + +/** * cfg80211_report_obss_beacon - report beacon from other APs * @wiphy: The wiphy that received the beacon * @frame: the frame @@ -7121,9 +7325,13 @@ void cfg80211_probe_status(struct net_device *dev, const u8 *addr, * received. It is not useful to call this when there is no * netdev that is in AP/GO mode. */ -void cfg80211_report_obss_beacon(struct wiphy *wiphy, - const u8 *frame, size_t len, - int freq, int sig_dbm); +static inline void cfg80211_report_obss_beacon(struct wiphy *wiphy, + const u8 *frame, size_t len, + int freq, int sig_dbm) +{ + cfg80211_report_obss_beacon_khz(wiphy, frame, len, MHZ_TO_KHZ(freq), + sig_dbm); +} /** * cfg80211_reg_can_beacon - check if beaconing is allowed @@ -7202,6 +7410,19 @@ bool ieee80211_operating_class_to_band(u8 operating_class, bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef, u8 *op_class); +/** + * ieee80211_chandef_to_khz - convert chandef to frequency in KHz + * + * @chandef: the chandef to convert + * + * Returns the center frequency of chandef (1st segment) in KHz. + */ +static inline u32 +ieee80211_chandef_to_khz(const struct cfg80211_chan_def *chandef) +{ + return MHZ_TO_KHZ(chandef->center_freq1) + chandef->freq1_offset; +} + /* * cfg80211_tdls_oper_request - request userspace to perform TDLS operation * @dev: the device on which the operation is requested diff --git a/include/net/compat.h b/include/net/compat.h index e341260642fe..f241666117d8 100644 --- a/include/net/compat.h +++ b/include/net/compat.h @@ -30,6 +30,24 @@ struct compat_cmsghdr { compat_int_t cmsg_type; }; +struct compat_rtentry { + u32 rt_pad1; + struct sockaddr rt_dst; /* target address */ + struct sockaddr rt_gateway; /* gateway addr (RTF_GATEWAY) */ + struct sockaddr rt_genmask; /* target network mask (IP) */ + unsigned short rt_flags; + short rt_pad2; + u32 rt_pad3; + unsigned char rt_tos; + unsigned char rt_class; + short rt_pad4; + short rt_metric; /* +1 for binary compatibility! */ + compat_uptr_t rt_dev; /* forcing the device at add */ + u32 rt_mtu; /* per route MTU/Window */ + u32 rt_window; /* Window clamping */ + unsigned short rt_irtt; /* Initial RTT */ +}; + #else /* defined(CONFIG_COMPAT) */ /* * To avoid compiler warnings: @@ -49,11 +67,28 @@ int put_cmsg_compat(struct msghdr*, int, int, int, void *); int cmsghdr_from_user_compat_to_kern(struct msghdr *, struct sock *, unsigned char *, int); -int compat_mc_setsockopt(struct sock *, int, int, char __user *, unsigned int, - int (*)(struct sock *, int, int, char __user *, - unsigned int)); -int compat_mc_getsockopt(struct sock *, int, int, char __user *, int __user *, - int (*)(struct sock *, int, int, char __user *, - int __user *)); +struct compat_group_req { + __u32 gr_interface; + struct __kernel_sockaddr_storage gr_group + __aligned(4); +} __packed; + +struct compat_group_source_req { + __u32 gsr_interface; + struct __kernel_sockaddr_storage gsr_group + __aligned(4); + struct __kernel_sockaddr_storage gsr_source + __aligned(4); +} __packed; + +struct compat_group_filter { + __u32 gf_interface; + struct __kernel_sockaddr_storage gf_group + __aligned(4); + __u32 gf_fmode; + __u32 gf_numsrc; + struct __kernel_sockaddr_storage gf_slist[1] + __aligned(4); +} __packed; #endif /* NET_COMPAT_H */ diff --git a/include/net/devlink.h b/include/net/devlink.h index 8ffc1b5cd89b..1df6dfec26c2 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -645,6 +645,50 @@ enum devlink_trap_generic_id { DEVLINK_TRAP_GENERIC_ID_OVERLAY_SMAC_MC, DEVLINK_TRAP_GENERIC_ID_INGRESS_FLOW_ACTION_DROP, DEVLINK_TRAP_GENERIC_ID_EGRESS_FLOW_ACTION_DROP, + DEVLINK_TRAP_GENERIC_ID_STP, + DEVLINK_TRAP_GENERIC_ID_LACP, + DEVLINK_TRAP_GENERIC_ID_LLDP, + DEVLINK_TRAP_GENERIC_ID_IGMP_QUERY, + DEVLINK_TRAP_GENERIC_ID_IGMP_V1_REPORT, + DEVLINK_TRAP_GENERIC_ID_IGMP_V2_REPORT, + DEVLINK_TRAP_GENERIC_ID_IGMP_V3_REPORT, + DEVLINK_TRAP_GENERIC_ID_IGMP_V2_LEAVE, + DEVLINK_TRAP_GENERIC_ID_MLD_QUERY, + DEVLINK_TRAP_GENERIC_ID_MLD_V1_REPORT, + DEVLINK_TRAP_GENERIC_ID_MLD_V2_REPORT, + DEVLINK_TRAP_GENERIC_ID_MLD_V1_DONE, + DEVLINK_TRAP_GENERIC_ID_IPV4_DHCP, + DEVLINK_TRAP_GENERIC_ID_IPV6_DHCP, + DEVLINK_TRAP_GENERIC_ID_ARP_REQUEST, + DEVLINK_TRAP_GENERIC_ID_ARP_RESPONSE, + DEVLINK_TRAP_GENERIC_ID_ARP_OVERLAY, + DEVLINK_TRAP_GENERIC_ID_IPV6_NEIGH_SOLICIT, + DEVLINK_TRAP_GENERIC_ID_IPV6_NEIGH_ADVERT, + DEVLINK_TRAP_GENERIC_ID_IPV4_BFD, + DEVLINK_TRAP_GENERIC_ID_IPV6_BFD, + DEVLINK_TRAP_GENERIC_ID_IPV4_OSPF, + DEVLINK_TRAP_GENERIC_ID_IPV6_OSPF, + DEVLINK_TRAP_GENERIC_ID_IPV4_BGP, + DEVLINK_TRAP_GENERIC_ID_IPV6_BGP, + DEVLINK_TRAP_GENERIC_ID_IPV4_VRRP, + DEVLINK_TRAP_GENERIC_ID_IPV6_VRRP, + DEVLINK_TRAP_GENERIC_ID_IPV4_PIM, + DEVLINK_TRAP_GENERIC_ID_IPV6_PIM, + DEVLINK_TRAP_GENERIC_ID_UC_LB, + DEVLINK_TRAP_GENERIC_ID_LOCAL_ROUTE, + DEVLINK_TRAP_GENERIC_ID_EXTERNAL_ROUTE, + DEVLINK_TRAP_GENERIC_ID_IPV6_UC_DIP_LINK_LOCAL_SCOPE, + DEVLINK_TRAP_GENERIC_ID_IPV6_DIP_ALL_NODES, + DEVLINK_TRAP_GENERIC_ID_IPV6_DIP_ALL_ROUTERS, + DEVLINK_TRAP_GENERIC_ID_IPV6_ROUTER_SOLICIT, + DEVLINK_TRAP_GENERIC_ID_IPV6_ROUTER_ADVERT, + DEVLINK_TRAP_GENERIC_ID_IPV6_REDIRECT, + DEVLINK_TRAP_GENERIC_ID_IPV4_ROUTER_ALERT, + DEVLINK_TRAP_GENERIC_ID_IPV6_ROUTER_ALERT, + DEVLINK_TRAP_GENERIC_ID_PTP_EVENT, + DEVLINK_TRAP_GENERIC_ID_PTP_GENERAL, + DEVLINK_TRAP_GENERIC_ID_FLOW_ACTION_SAMPLE, + DEVLINK_TRAP_GENERIC_ID_FLOW_ACTION_TRAP, /* Add new generic trap IDs above */ __DEVLINK_TRAP_GENERIC_ID_MAX, @@ -657,9 +701,28 @@ enum devlink_trap_generic_id { enum devlink_trap_group_generic_id { DEVLINK_TRAP_GROUP_GENERIC_ID_L2_DROPS, DEVLINK_TRAP_GROUP_GENERIC_ID_L3_DROPS, + DEVLINK_TRAP_GROUP_GENERIC_ID_L3_EXCEPTIONS, DEVLINK_TRAP_GROUP_GENERIC_ID_BUFFER_DROPS, DEVLINK_TRAP_GROUP_GENERIC_ID_TUNNEL_DROPS, DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_DROPS, + DEVLINK_TRAP_GROUP_GENERIC_ID_STP, + DEVLINK_TRAP_GROUP_GENERIC_ID_LACP, + DEVLINK_TRAP_GROUP_GENERIC_ID_LLDP, + DEVLINK_TRAP_GROUP_GENERIC_ID_MC_SNOOPING, + DEVLINK_TRAP_GROUP_GENERIC_ID_DHCP, + DEVLINK_TRAP_GROUP_GENERIC_ID_NEIGH_DISCOVERY, + DEVLINK_TRAP_GROUP_GENERIC_ID_BFD, + DEVLINK_TRAP_GROUP_GENERIC_ID_OSPF, + DEVLINK_TRAP_GROUP_GENERIC_ID_BGP, + DEVLINK_TRAP_GROUP_GENERIC_ID_VRRP, + DEVLINK_TRAP_GROUP_GENERIC_ID_PIM, + DEVLINK_TRAP_GROUP_GENERIC_ID_UC_LB, + DEVLINK_TRAP_GROUP_GENERIC_ID_LOCAL_DELIVERY, + DEVLINK_TRAP_GROUP_GENERIC_ID_IPV6, + DEVLINK_TRAP_GROUP_GENERIC_ID_PTP_EVENT, + DEVLINK_TRAP_GROUP_GENERIC_ID_PTP_GENERAL, + DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_SAMPLE, + DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_TRAP, /* Add new generic trap group IDs above */ __DEVLINK_TRAP_GROUP_GENERIC_ID_MAX, @@ -725,17 +788,143 @@ enum devlink_trap_group_generic_id { "ingress_flow_action_drop" #define DEVLINK_TRAP_GENERIC_NAME_EGRESS_FLOW_ACTION_DROP \ "egress_flow_action_drop" +#define DEVLINK_TRAP_GENERIC_NAME_STP \ + "stp" +#define DEVLINK_TRAP_GENERIC_NAME_LACP \ + "lacp" +#define DEVLINK_TRAP_GENERIC_NAME_LLDP \ + "lldp" +#define DEVLINK_TRAP_GENERIC_NAME_IGMP_QUERY \ + "igmp_query" +#define DEVLINK_TRAP_GENERIC_NAME_IGMP_V1_REPORT \ + "igmp_v1_report" +#define DEVLINK_TRAP_GENERIC_NAME_IGMP_V2_REPORT \ + "igmp_v2_report" +#define DEVLINK_TRAP_GENERIC_NAME_IGMP_V3_REPORT \ + "igmp_v3_report" +#define DEVLINK_TRAP_GENERIC_NAME_IGMP_V2_LEAVE \ + "igmp_v2_leave" +#define DEVLINK_TRAP_GENERIC_NAME_MLD_QUERY \ + "mld_query" +#define DEVLINK_TRAP_GENERIC_NAME_MLD_V1_REPORT \ + "mld_v1_report" +#define DEVLINK_TRAP_GENERIC_NAME_MLD_V2_REPORT \ + "mld_v2_report" +#define DEVLINK_TRAP_GENERIC_NAME_MLD_V1_DONE \ + "mld_v1_done" +#define DEVLINK_TRAP_GENERIC_NAME_IPV4_DHCP \ + "ipv4_dhcp" +#define DEVLINK_TRAP_GENERIC_NAME_IPV6_DHCP \ + "ipv6_dhcp" +#define DEVLINK_TRAP_GENERIC_NAME_ARP_REQUEST \ + "arp_request" +#define DEVLINK_TRAP_GENERIC_NAME_ARP_RESPONSE \ + "arp_response" +#define DEVLINK_TRAP_GENERIC_NAME_ARP_OVERLAY \ + "arp_overlay" +#define DEVLINK_TRAP_GENERIC_NAME_IPV6_NEIGH_SOLICIT \ + "ipv6_neigh_solicit" +#define DEVLINK_TRAP_GENERIC_NAME_IPV6_NEIGH_ADVERT \ + "ipv6_neigh_advert" +#define DEVLINK_TRAP_GENERIC_NAME_IPV4_BFD \ + "ipv4_bfd" +#define DEVLINK_TRAP_GENERIC_NAME_IPV6_BFD \ + "ipv6_bfd" +#define DEVLINK_TRAP_GENERIC_NAME_IPV4_OSPF \ + "ipv4_ospf" +#define DEVLINK_TRAP_GENERIC_NAME_IPV6_OSPF \ + "ipv6_ospf" +#define DEVLINK_TRAP_GENERIC_NAME_IPV4_BGP \ + "ipv4_bgp" +#define DEVLINK_TRAP_GENERIC_NAME_IPV6_BGP \ + "ipv6_bgp" +#define DEVLINK_TRAP_GENERIC_NAME_IPV4_VRRP \ + "ipv4_vrrp" +#define DEVLINK_TRAP_GENERIC_NAME_IPV6_VRRP \ + "ipv6_vrrp" +#define DEVLINK_TRAP_GENERIC_NAME_IPV4_PIM \ + "ipv4_pim" +#define DEVLINK_TRAP_GENERIC_NAME_IPV6_PIM \ + "ipv6_pim" +#define DEVLINK_TRAP_GENERIC_NAME_UC_LB \ + "uc_loopback" +#define DEVLINK_TRAP_GENERIC_NAME_LOCAL_ROUTE \ + "local_route" +#define DEVLINK_TRAP_GENERIC_NAME_EXTERNAL_ROUTE \ + "external_route" +#define DEVLINK_TRAP_GENERIC_NAME_IPV6_UC_DIP_LINK_LOCAL_SCOPE \ + "ipv6_uc_dip_link_local_scope" +#define DEVLINK_TRAP_GENERIC_NAME_IPV6_DIP_ALL_NODES \ + "ipv6_dip_all_nodes" +#define DEVLINK_TRAP_GENERIC_NAME_IPV6_DIP_ALL_ROUTERS \ + "ipv6_dip_all_routers" +#define DEVLINK_TRAP_GENERIC_NAME_IPV6_ROUTER_SOLICIT \ + "ipv6_router_solicit" +#define DEVLINK_TRAP_GENERIC_NAME_IPV6_ROUTER_ADVERT \ + "ipv6_router_advert" +#define DEVLINK_TRAP_GENERIC_NAME_IPV6_REDIRECT \ + "ipv6_redirect" +#define DEVLINK_TRAP_GENERIC_NAME_IPV4_ROUTER_ALERT \ + "ipv4_router_alert" +#define DEVLINK_TRAP_GENERIC_NAME_IPV6_ROUTER_ALERT \ + "ipv6_router_alert" +#define DEVLINK_TRAP_GENERIC_NAME_PTP_EVENT \ + "ptp_event" +#define DEVLINK_TRAP_GENERIC_NAME_PTP_GENERAL \ + "ptp_general" +#define DEVLINK_TRAP_GENERIC_NAME_FLOW_ACTION_SAMPLE \ + "flow_action_sample" +#define DEVLINK_TRAP_GENERIC_NAME_FLOW_ACTION_TRAP \ + "flow_action_trap" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \ "l2_drops" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_L3_DROPS \ "l3_drops" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_L3_EXCEPTIONS \ + "l3_exceptions" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_BUFFER_DROPS \ "buffer_drops" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_TUNNEL_DROPS \ "tunnel_drops" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_ACL_DROPS \ "acl_drops" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_STP \ + "stp" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_LACP \ + "lacp" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_LLDP \ + "lldp" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_MC_SNOOPING \ + "mc_snooping" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_DHCP \ + "dhcp" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_NEIGH_DISCOVERY \ + "neigh_discovery" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_BFD \ + "bfd" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_OSPF \ + "ospf" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_BGP \ + "bgp" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_VRRP \ + "vrrp" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_PIM \ + "pim" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_UC_LB \ + "uc_loopback" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_LOCAL_DELIVERY \ + "local_delivery" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_IPV6 \ + "ipv6" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_PTP_EVENT \ + "ptp_event" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_PTP_GENERAL \ + "ptp_general" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_ACL_SAMPLE \ + "acl_sample" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_ACL_TRAP \ + "acl_trap" #define DEVLINK_TRAP_GENERIC(_type, _init_action, _id, _group_id, \ _metadata_cap) \ diff --git a/include/net/dsa.h b/include/net/dsa.h index fb3f9222f2a1..50389772c597 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -282,6 +282,13 @@ struct dsa_switch { */ bool vlan_filtering_is_global; + /* Pass .port_vlan_add and .port_vlan_del to drivers even for bridges + * that have vlan_filtering=0. All drivers should ideally set this (and + * then the option would get removed), but it is unknown whether this + * would break things or not. + */ + bool configure_vlan_while_not_filtering; + /* In case vlan_filtering_is_global is set, the VLAN awareness state * should be retrieved from here and not from the per-port settings. */ @@ -574,10 +581,12 @@ struct dsa_switch_ops { /* * Cross-chip operations */ - int (*crosschip_bridge_join)(struct dsa_switch *ds, int sw_index, - int port, struct net_device *br); - void (*crosschip_bridge_leave)(struct dsa_switch *ds, int sw_index, - int port, struct net_device *br); + int (*crosschip_bridge_join)(struct dsa_switch *ds, int tree_index, + int sw_index, int port, + struct net_device *br); + void (*crosschip_bridge_leave)(struct dsa_switch *ds, int tree_index, + int sw_index, int port, + struct net_device *br); /* * PTP functionality @@ -637,6 +646,7 @@ void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds, void *occ_get_priv); void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds, u64 resource_id); +struct dsa_port *dsa_port_from_netdev(struct net_device *netdev); struct dsa_devlink_priv { struct dsa_switch *ds; @@ -650,7 +660,7 @@ struct dsa_switch_driver { struct net_device *dsa_dev_to_net_device(struct device *dev); /* Keep inline for faster access in hot path */ -static inline bool netdev_uses_dsa(struct net_device *dev) +static inline bool netdev_uses_dsa(const struct net_device *dev) { #if IS_ENABLED(CONFIG_NET_DSA) return dev->dsa_ptr && dev->dsa_ptr->rcv; @@ -669,6 +679,7 @@ static inline bool dsa_can_decode(const struct sk_buff *skb, void dsa_unregister_switch(struct dsa_switch *ds); int dsa_register_switch(struct dsa_switch *ds); +struct dsa_switch *dsa_switch_find(int tree_index, int sw_index); #ifdef CONFIG_PM_SLEEP int dsa_switch_suspend(struct dsa_switch *ds); int dsa_switch_resume(struct dsa_switch *ds); diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 443863c7b8da..88ff7bb2bb9b 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -53,9 +53,11 @@ static inline int dst_entries_get_slow(struct dst_ops *dst) return percpu_counter_sum_positive(&dst->pcpuc_entries); } +#define DST_PERCPU_COUNTER_BATCH 32 static inline void dst_entries_add(struct dst_ops *dst, int val) { - percpu_counter_add(&dst->pcpuc_entries, val); + percpu_counter_add_batch(&dst->pcpuc_entries, val, + DST_PERCPU_COUNTER_BATCH); } static inline int dst_entries_init(struct dst_ops *dst) diff --git a/include/net/erspan.h b/include/net/erspan.h index b39643ef4c95..0d9e86bd9893 100644 --- a/include/net/erspan.h +++ b/include/net/erspan.h @@ -2,7 +2,19 @@ #define __LINUX_ERSPAN_H /* - * GRE header for ERSPAN encapsulation (8 octets [34:41]) -- 8 bytes + * GRE header for ERSPAN type I encapsulation (4 octets [34:37]) + * 0 1 2 3 + * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * |0|0|0|0|0|00000|000000000|00000| Protocol Type for ERSPAN | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * The Type I ERSPAN frame format is based on the barebones IP + GRE + * encapsulation (as described above) on top of the raw mirrored frame. + * There is no extra ERSPAN header. + * + * + * GRE header for ERSPAN type II and II encapsulation (8 octets [34:41]) * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ @@ -43,7 +55,7 @@ * | Platform Specific Info | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * - * GRE proto ERSPAN type II = 0x88BE, type III = 0x22EB + * GRE proto ERSPAN type I/II = 0x88BE, type III = 0x22EB */ #include <uapi/linux/erspan.h> @@ -139,6 +151,9 @@ static inline u8 get_hwid(const struct erspan_md2 *md2) static inline int erspan_hdr_len(int version) { + if (version == 0) + return 0; + return sizeof(struct erspan_base_hdr) + (version == 1 ? ERSPAN_V1_MDSIZE : ERSPAN_V2_MDSIZE); } diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 628383915827..a7eba43fe4e4 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -8,6 +8,8 @@ #include <linux/string.h> #include <uapi/linux/if_ether.h> +struct bpf_prog; +struct net; struct sk_buff; /** @@ -59,13 +61,25 @@ struct flow_dissector_key_vlan { __be16 vlan_tpid; }; -struct flow_dissector_key_mpls { +struct flow_dissector_mpls_lse { u32 mpls_ttl:8, mpls_bos:1, mpls_tc:3, mpls_label:20; }; +#define FLOW_DIS_MPLS_MAX 7 +struct flow_dissector_key_mpls { + struct flow_dissector_mpls_lse ls[FLOW_DIS_MPLS_MAX]; /* Label Stack */ + u8 used_lses; /* One bit set for each Label Stack Entry in use */ +}; + +static inline void dissector_set_mpls_lse(struct flow_dissector_key_mpls *mpls, + int lse_index) +{ + mpls->used_lses |= 1 << lse_index; +} + #define FLOW_DIS_TUN_OPTS_MAX 255 /** * struct flow_dissector_key_enc_opts: @@ -357,4 +371,8 @@ flow_dissector_init_keys(struct flow_dissector_key_control *key_control, memset(key_basic, 0, sizeof(*key_basic)); } +#ifdef CONFIG_BPF_SYSCALL +int flow_dissector_bpf_prog_attach(struct net *net, struct bpf_prog *prog); +#endif /* CONFIG_BPF_SYSCALL */ + #endif diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index efc8350b42fb..69e13c8b6b3a 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -147,6 +147,7 @@ enum flow_action_id { FLOW_ACTION_MPLS_PUSH, FLOW_ACTION_MPLS_POP, FLOW_ACTION_MPLS_MANGLE, + FLOW_ACTION_GATE, NUM_FLOW_ACTIONS, }; @@ -167,10 +168,11 @@ enum flow_action_hw_stats_bit { FLOW_ACTION_HW_STATS_IMMEDIATE_BIT, FLOW_ACTION_HW_STATS_DELAYED_BIT, FLOW_ACTION_HW_STATS_DISABLED_BIT, + + FLOW_ACTION_HW_STATS_NUM_BITS }; enum flow_action_hw_stats { - FLOW_ACTION_HW_STATS_DONT_CARE = 0, FLOW_ACTION_HW_STATS_IMMEDIATE = BIT(FLOW_ACTION_HW_STATS_IMMEDIATE_BIT), FLOW_ACTION_HW_STATS_DELAYED = BIT(FLOW_ACTION_HW_STATS_DELAYED_BIT), @@ -178,6 +180,7 @@ enum flow_action_hw_stats { FLOW_ACTION_HW_STATS_DELAYED, FLOW_ACTION_HW_STATS_DISABLED = BIT(FLOW_ACTION_HW_STATS_DISABLED_BIT), + FLOW_ACTION_HW_STATS_DONT_CARE = BIT(FLOW_ACTION_HW_STATS_NUM_BITS) - 1, }; typedef void (*action_destr)(void *priv); @@ -258,6 +261,15 @@ struct flow_action_entry { u8 bos; u8 ttl; } mpls_mangle; + struct { + u32 index; + s32 prio; + u64 basetime; + u64 cycletime; + u64 cycletimeext; + u32 num_entries; + struct action_gate_entry *entries; + } gate; }; struct flow_action_cookie *cookie; /* user defined action cookie */ }; @@ -330,11 +342,12 @@ __flow_action_hw_stats_check(const struct flow_action *action, return false; action_entry = flow_action_first_entry_get(action); - if (action_entry->hw_stats == FLOW_ACTION_HW_STATS_DONT_CARE) - return true; + + /* Zero is not a legal value for hw_stats, catch anyone passing it */ + WARN_ON_ONCE(!action_entry->hw_stats); if (!check_allow_bit && - action_entry->hw_stats != FLOW_ACTION_HW_STATS_ANY) { + ~action_entry->hw_stats & FLOW_ACTION_HW_STATS_ANY) { NL_SET_ERR_MSG_MOD(extack, "Driver supports only default HW stats type \"any\""); return false; } else if (check_allow_bit && @@ -430,6 +443,16 @@ enum tc_setup_type; typedef int flow_setup_cb_t(enum tc_setup_type type, void *type_data, void *cb_priv); +struct flow_block_cb; + +struct flow_block_indr { + struct list_head list; + struct net_device *dev; + enum flow_block_binder_type binder_type; + void *data; + void (*cleanup)(struct flow_block_cb *block_cb); +}; + struct flow_block_cb { struct list_head driver_list; struct list_head list; @@ -437,6 +460,7 @@ struct flow_block_cb { void *cb_ident; void *cb_priv; void (*release)(void *cb_priv); + struct flow_block_indr indr; unsigned int refcnt; }; @@ -510,19 +534,18 @@ static inline void flow_block_init(struct flow_block *flow_block) typedef int flow_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv, enum tc_setup_type type, void *type_data); +int flow_indr_dev_register(flow_indr_block_bind_cb_t *cb, void *cb_priv); +void flow_indr_dev_unregister(flow_indr_block_bind_cb_t *cb, void *cb_priv, + flow_setup_cb_t *setup_cb); +int flow_indr_dev_setup_offload(struct net_device *dev, + enum tc_setup_type type, void *data, + struct flow_block_offload *bo, + void (*cleanup)(struct flow_block_cb *block_cb)); + typedef void flow_indr_block_cmd_t(struct net_device *dev, flow_indr_block_bind_cb_t *cb, void *cb_priv, enum flow_block_command command); -struct flow_indr_block_entry { - flow_indr_block_cmd_t *cb; - struct list_head list; -}; - -void flow_indr_add_block_cb(struct flow_indr_block_entry *entry); - -void flow_indr_del_block_cb(struct flow_indr_block_entry *entry); - int __flow_indr_block_cb_register(struct net_device *dev, void *cb_priv, flow_indr_block_bind_cb_t *cb, void *cb_ident); diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index a01981d7108f..8bf5906073bc 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -78,7 +78,7 @@ struct inet6_ifaddr { struct ip6_sf_socklist { unsigned int sl_max; unsigned int sl_count; - struct in6_addr sl_addr[0]; + struct in6_addr sl_addr[]; }; #define IP6_SFLSIZE(count) (sizeof(struct ip6_sf_socklist) + \ @@ -190,7 +190,6 @@ struct inet6_dev { int dead; u32 desync_factor; - u8 rndid[8]; struct list_head tempaddr_list; struct in6_addr token; diff --git a/include/net/inet_common.h b/include/net/inet_common.h index ae2ba897675c..cb2818862919 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -35,8 +35,14 @@ int inet_shutdown(struct socket *sock, int how); int inet_listen(struct socket *sock, int backlog); void inet_sock_destruct(struct sock *sk); int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); +/* Don't allocate port at this moment, defer to connect. */ +#define BIND_FORCE_ADDRESS_NO_PORT (1 << 0) +/* Grab and release socket lock. */ +#define BIND_WITH_LOCK (1 << 1) +/* Called from BPF program. */ +#define BIND_FROM_BPF (1 << 2) int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, - bool force_bind_address_no_port, bool with_lock); + u32 flags); int inet_getname(struct socket *sock, struct sockaddr *uaddr, int peer); int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index a3f076befa4f..2f1f8c3efb26 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -287,6 +287,14 @@ static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req); +static inline void inet_csk_prepare_for_destroy_sock(struct sock *sk) +{ + /* The below has to be done to allow calling inet_csk_destroy_sock */ + sock_set_flag(sk, SOCK_DEAD); + percpu_counter_inc(sk->sk_prot->orphan_count); + inet_sk(sk)->inet_num = 0; +} + void inet_csk_destroy_sock(struct sock *sk); void inet_csk_prepare_forced_close(struct sock *sk); diff --git a/include/net/ip.h b/include/net/ip.h index 5b317c9f4470..04ebe7bf54c6 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -765,4 +765,10 @@ static inline bool inetdev_valid_mtu(unsigned int mtu) return likely(mtu >= IPV4_MIN_MTU); } +void ip_sock_set_freebind(struct sock *sk); +int ip_sock_set_mtu_discover(struct sock *sk, int val); +void ip_sock_set_pktinfo(struct sock *sk); +void ip_sock_set_recverr(struct sock *sk); +void ip_sock_set_tos(struct sock *sk, int val); + #endif /* _IP_H */ diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 1d98828c6649..3f615a29766e 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -65,6 +65,7 @@ struct fib6_config { struct nl_info fc_nlinfo; struct nlattr *fc_encap; u16 fc_encap_type; + bool fc_is_fdb; }; struct fib6_node { @@ -544,6 +545,13 @@ static inline bool fib6_metric_locked(struct fib6_info *f6i, int metric) return !!(f6i->fib6_metrics->metrics[RTAX_LOCK - 1] & (1 << metric)); } +#if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL) +struct bpf_iter__ipv6_route { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct fib6_info *, rt); +}; +#endif + #ifdef CONFIG_IPV6_MULTIPLE_TABLES static inline bool fib6_has_custom_rules(const struct net *net) { diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 9947eb1e9eb6..2a5277758379 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -118,12 +118,13 @@ void ip6_route_init_special_entries(void); int ip6_route_init(void); void ip6_route_cleanup(void); -int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg); +int ipv6_route_ioctl(struct net *net, unsigned int cmd, + struct in6_rtmsg *rtmsg); int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); int ip6_ins_rt(struct net *net, struct fib6_info *f6i); -int ip6_del_rt(struct net *net, struct fib6_info *f6i); +int ip6_del_rt(struct net *net, struct fib6_info *f6i, bool skip_notify); void rt6_flush_exceptions(struct fib6_info *f6i); void rt6_age_exceptions(struct fib6_info *f6i, struct fib6_gc_args *gc_args, diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 236503a50759..076e5d7db7d3 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -269,7 +269,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, const u8 protocol); void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const u8 proto, int tunnel_hlen); -int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); +int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); +int ip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict); int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 1bf8065fe871..5e65bf2fd32d 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -908,7 +908,6 @@ static inline int ip6_default_np_autolabel(struct net *net) } } #else -static inline void ip6_set_txhash(struct sock *sk) { } static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, __be32 flowlabel, bool autolabel, struct flowi6 *fl6) @@ -1116,6 +1115,8 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); int inet6_getname(struct socket *sock, struct sockaddr *uaddr, int peer); int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); +int inet6_compat_ioctl(struct socket *sock, unsigned int cmd, + unsigned long arg); int inet6_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk); @@ -1135,9 +1136,10 @@ struct group_filter; int ip6_mc_source(int add, int omode, struct sock *sk, struct group_source_req *pgsr); -int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf); +int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf, + struct sockaddr_storage *list); int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, - struct group_filter __user *optval, int __user *optlen); + struct sockaddr_storage __user *p); #ifdef CONFIG_PROC_FS int ac6_proc_init(struct net *net); @@ -1175,4 +1177,96 @@ int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex, const struct in6_addr *addr, unsigned int mode); int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); + +static inline int ip6_sock_set_v6only(struct sock *sk) +{ + if (inet_sk(sk)->inet_num) + return -EINVAL; + lock_sock(sk); + sk->sk_ipv6only = true; + release_sock(sk); + return 0; +} + +static inline void ip6_sock_set_recverr(struct sock *sk) +{ + lock_sock(sk); + inet6_sk(sk)->recverr = true; + release_sock(sk); +} + +static inline int __ip6_sock_set_addr_preferences(struct sock *sk, int val) +{ + unsigned int pref = 0; + unsigned int prefmask = ~0; + + /* check PUBLIC/TMP/PUBTMP_DEFAULT conflicts */ + switch (val & (IPV6_PREFER_SRC_PUBLIC | + IPV6_PREFER_SRC_TMP | + IPV6_PREFER_SRC_PUBTMP_DEFAULT)) { + case IPV6_PREFER_SRC_PUBLIC: + pref |= IPV6_PREFER_SRC_PUBLIC; + prefmask &= ~(IPV6_PREFER_SRC_PUBLIC | + IPV6_PREFER_SRC_TMP); + break; + case IPV6_PREFER_SRC_TMP: + pref |= IPV6_PREFER_SRC_TMP; + prefmask &= ~(IPV6_PREFER_SRC_PUBLIC | + IPV6_PREFER_SRC_TMP); + break; + case IPV6_PREFER_SRC_PUBTMP_DEFAULT: + prefmask &= ~(IPV6_PREFER_SRC_PUBLIC | + IPV6_PREFER_SRC_TMP); + break; + case 0: + break; + default: + return -EINVAL; + } + + /* check HOME/COA conflicts */ + switch (val & (IPV6_PREFER_SRC_HOME | IPV6_PREFER_SRC_COA)) { + case IPV6_PREFER_SRC_HOME: + prefmask &= ~IPV6_PREFER_SRC_COA; + break; + case IPV6_PREFER_SRC_COA: + pref |= IPV6_PREFER_SRC_COA; + break; + case 0: + break; + default: + return -EINVAL; + } + + /* check CGA/NONCGA conflicts */ + switch (val & (IPV6_PREFER_SRC_CGA|IPV6_PREFER_SRC_NONCGA)) { + case IPV6_PREFER_SRC_CGA: + case IPV6_PREFER_SRC_NONCGA: + case 0: + break; + default: + return -EINVAL; + } + + inet6_sk(sk)->srcprefs = (inet6_sk(sk)->srcprefs & prefmask) | pref; + return 0; +} + +static inline int ip6_sock_set_addr_preferences(struct sock *sk, bool val) +{ + int ret; + + lock_sock(sk); + ret = __ip6_sock_set_addr_preferences(sk, val); + release_sock(sk); + return ret; +} + +static inline void ip6_sock_set_recvpktinfo(struct sock *sk) +{ + lock_sock(sk); + inet6_sk(sk)->rxopt.bits.rxinfo = true; + release_sock(sk); +} + #endif /* _NET_IPV6_H */ diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index 3e7d2c0e79ca..d7a7f7c81e7b 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -48,7 +48,7 @@ struct ipv6_stub { struct netlink_ext_ack *extack); void (*fib6_nh_release)(struct fib6_nh *fib6_nh); void (*fib6_update_sernum)(struct net *net, struct fib6_info *rt); - int (*ip6_del_rt)(struct net *net, struct fib6_info *rt); + int (*ip6_del_rt)(struct net *net, struct fib6_info *rt, bool skip_notify); void (*fib6_rt_update)(struct net *net, struct fib6_info *rt, struct nl_info *info); @@ -56,6 +56,12 @@ struct ipv6_stub { void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, bool router, bool solicited, bool override, bool inc_opt); +#if IS_ENABLED(CONFIG_XFRM) + void (*xfrm6_local_rxpmtu)(struct sk_buff *skb, u32 mtu); + int (*xfrm6_udp_encap_rcv)(struct sock *sk, struct sk_buff *skb); + int (*xfrm6_rcv_encap)(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type); +#endif struct neigh_table *nd_tbl; }; extern const struct ipv6_stub *ipv6_stub __read_mostly; @@ -63,7 +69,7 @@ extern const struct ipv6_stub *ipv6_stub __read_mostly; /* A stub used by bpf helpers. Similarly ugly as ipv6_stub */ struct ipv6_bpf_stub { int (*inet6_bind)(struct sock *sk, struct sockaddr *uaddr, int addr_len, - bool force_bind_address_no_port, bool with_lock); + u32 flags); struct sock *(*udp6_lib_lookup)(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, diff --git a/include/net/iucv/af_iucv.h b/include/net/iucv/af_iucv.h index 14a490246be9..9259ce2b22f3 100644 --- a/include/net/iucv/af_iucv.h +++ b/include/net/iucv/af_iucv.h @@ -158,12 +158,4 @@ struct iucv_sock_list { atomic_t autobind_name; }; -__poll_t iucv_sock_poll(struct file *file, struct socket *sock, - poll_table *wait); -void iucv_sock_link(struct iucv_sock_list *l, struct sock *s); -void iucv_sock_unlink(struct iucv_sock_list *l, struct sock *s); -void iucv_accept_enqueue(struct sock *parent, struct sock *sk); -void iucv_accept_unlink(struct sock *sk); -struct sock *iucv_accept_dequeue(struct sock *parent, struct socket *newsock); - #endif /* __IUCV_H */ diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 97fec4d310ac..11d5610d2ad5 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -7,7 +7,7 @@ * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018 - 2019 Intel Corporation + * Copyright (C) 2018 - 2020 Intel Corporation */ #ifndef MAC80211_H @@ -230,7 +230,7 @@ struct ieee80211_chanctx_conf { bool radar_enabled; - u8 drv_priv[0] __aligned(sizeof(void *)); + u8 drv_priv[] __aligned(sizeof(void *)); }; /** @@ -508,6 +508,7 @@ struct ieee80211_ftm_responder_params { * mode only, set if the AP advertises TWT responder role) * @twt_responder: does this BSS support TWT requester (relevant for managed * mode only, set if the AP advertises TWT responder role) + * @twt_protected: does this BSS support protected TWT frames * @assoc: association status * @ibss_joined: indicates whether this station is part of an IBSS * or not @@ -603,7 +604,7 @@ struct ieee80211_ftm_responder_params { * nontransmitted BSSIDs * @profile_periodicity: the least number of beacon frames need to be received * in order to discover all the nontransmitted BSSIDs in the set. - * @he_operation: HE operation information of the AP we are connected to + * @he_oper: HE operation information of the AP we are connected to * @he_obss_pd: OBSS Packet Detection parameters. * @he_bss_color: BSS coloring settings, if BSS supports HE */ @@ -618,6 +619,7 @@ struct ieee80211_bss_conf { bool he_support; bool twt_requester; bool twt_responder; + bool twt_protected; /* association related data */ bool assoc, ibss_joined; bool ibss_creator; @@ -666,7 +668,10 @@ struct ieee80211_bss_conf { u8 bssid_indicator; bool ema_ap; u8 profile_periodicity; - struct ieee80211_he_operation he_operation; + struct { + u32 params; + u16 nss_set; + } he_oper; struct ieee80211_he_obss_pd he_obss_pd; struct cfg80211_he_bss_color he_bss_color; }; @@ -818,6 +823,8 @@ enum mac80211_tx_info_flags { * @IEEE80211_TX_CTRL_AMSDU: This frame is an A-MSDU frame * @IEEE80211_TX_CTRL_FAST_XMIT: This frame is going through the fast_xmit path * @IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP: This frame skips mesh path lookup + * @IEEE80211_TX_CTRL_HW_80211_ENCAP: This frame uses hardware encapsulation + * (header conversion) * * These flags are used in tx_info->control.flags. */ @@ -1333,6 +1340,7 @@ enum mac80211_rx_encoding { * @freq: frequency the radio was tuned to when receiving this frame, in MHz * This field must be set for management frames, but isn't strictly needed * for data (other) frames - for those it only affects radiotap reporting. + * @freq_offset: @freq has a positive offset of 500Khz. * @signal: signal strength when receiving this frame, either in dBm, in dB or * unspecified depending on the hardware capabilities flags * @IEEE80211_HW_SIGNAL_* @@ -1363,7 +1371,7 @@ struct ieee80211_rx_status { u32 device_timestamp; u32 ampdu_reference; u32 flag; - u16 freq; + u16 freq: 13, freq_offset: 1; u8 enc_flags; u8 encoding:2, bw:3, he_ru:3; u8 he_gi:2, he_dcm:1; @@ -1379,6 +1387,13 @@ struct ieee80211_rx_status { u8 zero_length_psdu_type; }; +static inline u32 +ieee80211_rx_status_to_khz(struct ieee80211_rx_status *rx_status) +{ + return MHZ_TO_KHZ(rx_status->freq) + + (rx_status->freq_offset ? 500 : 0); +} + /** * struct ieee80211_vendor_radiotap - vendor radiotap data information * @present: presence bitmap for this vendor namespace @@ -1620,6 +1635,8 @@ enum ieee80211_vif_flags { * monitor interface (if that is requested.) * @probe_req_reg: probe requests should be reported to mac80211 for this * interface. + * @rx_mcast_action_reg: multicast Action frames should be reported to mac80211 + * for this interface. * @drv_priv: data area for driver use, will always be aligned to * sizeof(void \*). * @txq: the multicast data TX queue (if driver uses the TXQ abstraction) @@ -1647,12 +1664,13 @@ struct ieee80211_vif { struct dentry *debugfs_dir; #endif - unsigned int probe_req_reg; + bool probe_req_reg; + bool rx_mcast_action_reg; bool txqs_stopped[IEEE80211_NUM_ACS]; /* must be last */ - u8 drv_priv[0] __aligned(sizeof(void *)); + u8 drv_priv[] __aligned(sizeof(void *)); }; static inline bool ieee80211_vif_is_mesh(struct ieee80211_vif *vif) @@ -1780,7 +1798,7 @@ struct ieee80211_key_conf { s8 keyidx; u16 flags; u8 keylen; - u8 key[0]; + u8 key[]; }; #define IEEE80211_MAX_PN_LEN 16 @@ -1959,6 +1977,7 @@ struct ieee80211_sta_txpwr { * @ht_cap: HT capabilities of this STA; restricted to our own capabilities * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities * @he_cap: HE capabilities of this STA + * @he_6ghz_capa: on 6 GHz, holds the HE 6 GHz band capabilities * @max_rx_aggregation_subframes: maximal amount of frames in a single AMPDU * that this station is allowed to transmit to us. * Can be modified by driver. @@ -1998,6 +2017,7 @@ struct ieee80211_sta { struct ieee80211_sta_ht_cap ht_cap; struct ieee80211_sta_vht_cap vht_cap; struct ieee80211_sta_he_cap he_cap; + struct ieee80211_he_6ghz_capa he_6ghz_capa; u16 max_rx_aggregation_subframes; bool wme; u8 uapsd_queues; @@ -2035,7 +2055,7 @@ struct ieee80211_sta { struct ieee80211_txq *txq[IEEE80211_NUM_TIDS + 1]; /* must be last */ - u8 drv_priv[0] __aligned(sizeof(void *)); + u8 drv_priv[] __aligned(sizeof(void *)); }; /** @@ -2081,7 +2101,7 @@ struct ieee80211_txq { u8 ac; /* must be last */ - u8 drv_priv[0] __aligned(sizeof(void *)); + u8 drv_priv[] __aligned(sizeof(void *)); }; /** @@ -3091,6 +3111,8 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb); * @FIF_PSPOLL: pass PS Poll frames * * @FIF_PROBE_REQ: pass probe request frames + * + * @FIF_MCAST_ACTION: pass multicast Action frames */ enum ieee80211_filter_flags { FIF_ALLMULTI = 1<<1, @@ -3101,6 +3123,7 @@ enum ieee80211_filter_flags { FIF_OTHER_BSS = 1<<6, FIF_PSPOLL = 1<<7, FIF_PROBE_REQ = 1<<8, + FIF_MCAST_ACTION = 1<<9, }; /** @@ -3117,7 +3140,10 @@ enum ieee80211_filter_flags { * @IEEE80211_AMPDU_RX_START: start RX aggregation * @IEEE80211_AMPDU_RX_STOP: stop RX aggregation * @IEEE80211_AMPDU_TX_START: start TX aggregation, the driver must either - * call ieee80211_start_tx_ba_cb_irqsafe() or return the special + * call ieee80211_start_tx_ba_cb_irqsafe() or + * call ieee80211_start_tx_ba_cb_irqsafe() with status + * %IEEE80211_AMPDU_TX_START_DELAY_ADDBA to delay addba after + * ieee80211_start_tx_ba_cb_irqsafe is called, or just return the special * status %IEEE80211_AMPDU_TX_START_IMMEDIATE. * @IEEE80211_AMPDU_TX_OPERATIONAL: TX aggregation has become operational * @IEEE80211_AMPDU_TX_STOP_CONT: stop TX aggregation but continue transmitting @@ -3143,6 +3169,7 @@ enum ieee80211_ampdu_mlme_action { }; #define IEEE80211_AMPDU_TX_START_IMMEDIATE 1 +#define IEEE80211_AMPDU_TX_START_DELAY_ADDBA 2 /** * struct ieee80211_ampdu_params - AMPDU action parameters diff --git a/include/net/mpls.h b/include/net/mpls.h index ccaf238e8ea7..0bb7944e7b08 100644 --- a/include/net/mpls.h +++ b/include/net/mpls.h @@ -8,6 +8,7 @@ #include <linux/if_ether.h> #include <linux/netdevice.h> +#include <linux/mpls.h> #define MPLS_HLEN 4 @@ -25,4 +26,20 @@ static inline struct mpls_shim_hdr *mpls_hdr(const struct sk_buff *skb) { return (struct mpls_shim_hdr *)skb_network_header(skb); } + +static inline struct mpls_shim_hdr mpls_entry_encode(u32 label, + unsigned int ttl, + unsigned int tc, + bool bos) +{ + struct mpls_shim_hdr result; + + result.label_stack_entry = + cpu_to_be32((label << MPLS_LS_LABEL_SHIFT) | + (tc << MPLS_LS_TC_SHIFT) | + (bos ? (1 << MPLS_LS_S_SHIFT) : 0) | + (ttl << MPLS_LS_TTL_SHIFT)); + return result; +} + #endif diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 3bce2019e4da..46d0487d2b22 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -16,7 +16,10 @@ struct seq_file; /* MPTCP sk_buff extension data */ struct mptcp_ext { - u64 data_ack; + union { + u64 data_ack; + u32 data_ack32; + }; u64 data_seq; u32 subflow_seq; u16 data_len; @@ -68,6 +71,12 @@ static inline bool rsk_is_mptcp(const struct request_sock *req) return tcp_rsk(req)->is_mptcp; } +static inline bool rsk_drop_req(const struct request_sock *req) +{ + return tcp_rsk(req)->is_mptcp && tcp_rsk(req)->drop_req; +} + +void mptcp_space(const struct sock *ssk, int *space, int *full_space); bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, unsigned int *size, struct mptcp_out_options *opts); bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, @@ -120,8 +129,6 @@ static inline bool mptcp_skb_can_collapse(const struct sk_buff *to, skb_ext_find(from, SKB_EXT_MPTCP)); } -bool mptcp_sk_is_subflow(const struct sock *sk); - void mptcp_seq_show(struct seq_file *seq); #else @@ -139,6 +146,11 @@ static inline bool rsk_is_mptcp(const struct request_sock *req) return false; } +static inline bool rsk_drop_req(const struct request_sock *req) +{ + return false; +} + static inline void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr, int opsize, struct tcp_options_received *opt_rx) @@ -189,11 +201,7 @@ static inline bool mptcp_skb_can_collapse(const struct sk_buff *to, return true; } -static inline bool mptcp_sk_is_subflow(const struct sock *sk) -{ - return false; -} - +static inline void mptcp_space(const struct sock *ssk, int *s, int *fs) { } static inline void mptcp_seq_show(struct seq_file *seq) { } #endif /* CONFIG_MPTCP */ diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 8e001e049497..2ee5901bec7a 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -33,6 +33,7 @@ #include <net/netns/mpls.h> #include <net/netns/can.h> #include <net/netns/xdp.h> +#include <net/netns/bpf.h> #include <linux/ns_common.h> #include <linux/idr.h> #include <linux/skbuff.h> @@ -162,7 +163,8 @@ struct net { #endif struct net_generic __rcu *gen; - struct bpf_prog __rcu *flow_dissector_prog; + /* Used to store attached BPF programs */ + struct netns_bpf bpf; /* Note : following structs are cache line aligned */ #ifdef CONFIG_XFRM diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 4cad1f0a327a..88186b95b3c2 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -42,7 +42,8 @@ struct nf_conntrack_l4proto { /* Calculate tuple nlattr size */ unsigned int (*nlattr_tuple_size)(void); int (*nlattr_to_tuple)(struct nlattr *tb[], - struct nf_conntrack_tuple *t); + struct nf_conntrack_tuple *t, + u_int32_t flags); const struct nla_policy *nla_policy; struct { @@ -152,7 +153,8 @@ const struct nf_conntrack_l4proto *nf_ct_l4proto_find(u8 l4proto); int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple); int nf_ct_port_nlattr_to_tuple(struct nlattr *tb[], - struct nf_conntrack_tuple *t); + struct nf_conntrack_tuple *t, + u_int32_t flags); unsigned int nf_ct_port_nlattr_tuple_size(void); extern const struct nla_policy nf_ct_port_nla_policy[]; diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index c54a7f707e50..d7338bfd7b0f 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -175,6 +175,8 @@ void flow_offload_refresh(struct nf_flowtable *flow_table, struct flow_offload_tuple_rhash *flow_offload_lookup(struct nf_flowtable *flow_table, struct flow_offload_tuple *tuple); +void nf_flow_table_gc_cleanup(struct nf_flowtable *flowtable, + struct net_device *dev); void nf_flow_table_cleanup(struct net_device *dev); int nf_flow_table_init(struct nf_flowtable *flow_table); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 4ff7c81e6717..6f0f6fca9ac3 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -243,6 +243,10 @@ struct nft_set_elem { u32 buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)]; struct nft_data val; } key_end; + union { + u32 buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)]; + struct nft_data val; + } data; void *priv; }; @@ -998,6 +1002,7 @@ struct nft_stats { struct nft_hook { struct list_head list; + bool inactive; struct nf_hook_ops ops; struct rcu_head rcu; }; @@ -1477,10 +1482,16 @@ struct nft_trans_obj { struct nft_trans_flowtable { struct nft_flowtable *flowtable; + bool update; + struct list_head hook_list; }; #define nft_trans_flowtable(trans) \ (((struct nft_trans_flowtable *)trans->data)->flowtable) +#define nft_trans_flowtable_update(trans) \ + (((struct nft_trans_flowtable *)trans->data)->update) +#define nft_trans_flowtable_hooks(trans) \ + (((struct nft_trans_flowtable *)trans->data)->hook_list) int __init nft_chain_filter_init(void); void nft_chain_filter_fini(void); diff --git a/include/net/netlink.h b/include/net/netlink.h index 67c57d6942e3..c0411f14fb53 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -182,19 +182,28 @@ enum { NLA_BITFIELD32, NLA_REJECT, NLA_EXACT_LEN, - NLA_EXACT_LEN_WARN, NLA_MIN_LEN, __NLA_TYPE_MAX, }; #define NLA_TYPE_MAX (__NLA_TYPE_MAX - 1) +struct netlink_range_validation { + u64 min, max; +}; + +struct netlink_range_validation_signed { + s64 min, max; +}; + enum nla_policy_validation { NLA_VALIDATE_NONE, NLA_VALIDATE_RANGE, NLA_VALIDATE_MIN, NLA_VALIDATE_MAX, + NLA_VALIDATE_RANGE_PTR, NLA_VALIDATE_FUNCTION, + NLA_VALIDATE_WARN_TOO_LONG, }; /** @@ -217,7 +226,7 @@ enum nla_policy_validation { * NLA_NESTED, * NLA_NESTED_ARRAY Length verification is done by checking len of * nested header (or empty); len field is used if - * validation_data is also used, for the max attr + * nested_policy is also used, for the max attr * number in the nested policy. * NLA_U8, NLA_U16, * NLA_U32, NLA_U64, @@ -228,34 +237,32 @@ enum nla_policy_validation { * just like "All other" * NLA_BITFIELD32 Unused * NLA_REJECT Unused - * NLA_EXACT_LEN Attribute must have exactly this length, otherwise - * it is rejected. - * NLA_EXACT_LEN_WARN Attribute should have exactly this length, a warning - * is logged if it is longer, shorter is rejected. + * NLA_EXACT_LEN Attribute should have exactly this length, otherwise + * it is rejected or warned about, the latter happening + * if and only if the `validation_type' is set to + * NLA_VALIDATE_WARN_TOO_LONG. * NLA_MIN_LEN Minimum length of attribute payload * All other Minimum length of attribute payload * - * Meaning of `validation_data' field: + * Meaning of validation union: * NLA_BITFIELD32 This is a 32-bit bitmap/bitselector attribute and - * validation data must point to a u32 value of valid - * flags - * NLA_REJECT This attribute is always rejected and validation data + * `bitfield32_valid' is the u32 value of valid flags + * NLA_REJECT This attribute is always rejected and `reject_message' * may point to a string to report as the error instead * of the generic one in extended ACK. - * NLA_NESTED Points to a nested policy to validate, must also set - * `len' to the max attribute number. + * NLA_NESTED `nested_policy' to a nested policy to validate, must + * also set `len' to the max attribute number. Use the + * provided NLA_POLICY_NESTED() macro. * Note that nla_parse() will validate, but of course not * parse, the nested sub-policies. - * NLA_NESTED_ARRAY Points to a nested policy to validate, must also set - * `len' to the max attribute number. The difference to - * NLA_NESTED is the structure - NLA_NESTED has the - * nested attributes directly inside, while an array has - * the nested attributes at another level down and the - * attributes directly in the nesting don't matter. - * All other Unused - but note that it's a union - * - * Meaning of `min' and `max' fields, use via NLA_POLICY_MIN, NLA_POLICY_MAX - * and NLA_POLICY_RANGE: + * NLA_NESTED_ARRAY `nested_policy' points to a nested policy to validate, + * must also set `len' to the max attribute number. Use + * the provided NLA_POLICY_NESTED_ARRAY() macro. + * The difference to NLA_NESTED is the structure: + * NLA_NESTED has the nested attributes directly inside + * while an array has the nested attributes at another + * level down and the attribute types directly in the + * nesting don't matter. * NLA_U8, * NLA_U16, * NLA_U32, @@ -263,29 +270,47 @@ enum nla_policy_validation { * NLA_S8, * NLA_S16, * NLA_S32, - * NLA_S64 These are used depending on the validation_type - * field, if that is min/max/range then the minimum, - * maximum and both are used (respectively) to check + * NLA_S64 The `min' and `max' fields are used depending on the + * validation_type field, if that is min/max/range then + * the min, max or both are used (respectively) to check * the value of the integer attribute. * Note that in the interest of code simplicity and * struct size both limits are s16, so you cannot * enforce a range that doesn't fall within the range * of s16 - do that as usual in the code instead. + * Use the NLA_POLICY_MIN(), NLA_POLICY_MAX() and + * NLA_POLICY_RANGE() macros. + * NLA_U8, + * NLA_U16, + * NLA_U32, + * NLA_U64 If the validation_type field instead is set to + * NLA_VALIDATE_RANGE_PTR, `range' must be a pointer + * to a struct netlink_range_validation that indicates + * the min/max values. + * Use NLA_POLICY_FULL_RANGE(). + * NLA_S8, + * NLA_S16, + * NLA_S32, + * NLA_S64 If the validation_type field instead is set to + * NLA_VALIDATE_RANGE_PTR, `range_signed' must be a + * pointer to a struct netlink_range_validation_signed + * that indicates the min/max values. + * Use NLA_POLICY_FULL_RANGE_SIGNED(). * All other Unused - but note that it's a union * * Meaning of `validate' field, use via NLA_POLICY_VALIDATE_FN: - * NLA_BINARY Validation function called for the attribute, - * not compatible with use of the validation_data - * as in NLA_BITFIELD32, NLA_REJECT, NLA_NESTED and - * NLA_NESTED_ARRAY. + * NLA_BINARY Validation function called for the attribute. * All other Unused - but note that it's a union * * Example: + * + * static const u32 myvalidflags = 0xff231023; + * * static const struct nla_policy my_policy[ATTR_MAX+1] = { * [ATTR_FOO] = { .type = NLA_U16 }, * [ATTR_BAR] = { .type = NLA_STRING, .len = BARSIZ }, * [ATTR_BAZ] = { .type = NLA_EXACT_LEN, .len = sizeof(struct mystruct) }, - * [ATTR_GOO] = { .type = NLA_BITFIELD32, .validation_data = &myvalidflags }, + * [ATTR_GOO] = NLA_POLICY_BITFIELD32(myvalidflags), * }; */ struct nla_policy { @@ -293,7 +318,11 @@ struct nla_policy { u8 validation_type; u16 len; union { - const void *validation_data; + const u32 bitfield32_valid; + const char *reject_message; + const struct nla_policy *nested_policy; + struct netlink_range_validation *range; + struct netlink_range_validation_signed *range_signed; struct { s16 min, max; }; @@ -321,28 +350,39 @@ struct nla_policy { }; #define NLA_POLICY_EXACT_LEN(_len) { .type = NLA_EXACT_LEN, .len = _len } -#define NLA_POLICY_EXACT_LEN_WARN(_len) { .type = NLA_EXACT_LEN_WARN, \ - .len = _len } +#define NLA_POLICY_EXACT_LEN_WARN(_len) \ + { .type = NLA_EXACT_LEN, .len = _len, \ + .validation_type = NLA_VALIDATE_WARN_TOO_LONG, } #define NLA_POLICY_MIN_LEN(_len) { .type = NLA_MIN_LEN, .len = _len } #define NLA_POLICY_ETH_ADDR NLA_POLICY_EXACT_LEN(ETH_ALEN) #define NLA_POLICY_ETH_ADDR_COMPAT NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN) #define _NLA_POLICY_NESTED(maxattr, policy) \ - { .type = NLA_NESTED, .validation_data = policy, .len = maxattr } + { .type = NLA_NESTED, .nested_policy = policy, .len = maxattr } #define _NLA_POLICY_NESTED_ARRAY(maxattr, policy) \ - { .type = NLA_NESTED_ARRAY, .validation_data = policy, .len = maxattr } + { .type = NLA_NESTED_ARRAY, .nested_policy = policy, .len = maxattr } #define NLA_POLICY_NESTED(policy) \ _NLA_POLICY_NESTED(ARRAY_SIZE(policy) - 1, policy) #define NLA_POLICY_NESTED_ARRAY(policy) \ _NLA_POLICY_NESTED_ARRAY(ARRAY_SIZE(policy) - 1, policy) +#define NLA_POLICY_BITFIELD32(valid) \ + { .type = NLA_BITFIELD32, .bitfield32_valid = valid } #define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition)) +#define NLA_ENSURE_UINT_TYPE(tp) \ + (__NLA_ENSURE(tp == NLA_U8 || tp == NLA_U16 || \ + tp == NLA_U32 || tp == NLA_U64 || \ + tp == NLA_MSECS) + tp) +#define NLA_ENSURE_SINT_TYPE(tp) \ + (__NLA_ENSURE(tp == NLA_S8 || tp == NLA_S16 || \ + tp == NLA_S32 || tp == NLA_S64) + tp) #define NLA_ENSURE_INT_TYPE(tp) \ (__NLA_ENSURE(tp == NLA_S8 || tp == NLA_U8 || \ tp == NLA_S16 || tp == NLA_U16 || \ tp == NLA_S32 || tp == NLA_U32 || \ - tp == NLA_S64 || tp == NLA_U64) + tp) + tp == NLA_S64 || tp == NLA_U64 || \ + tp == NLA_MSECS) + tp) #define NLA_ENSURE_NO_VALIDATION_PTR(tp) \ (__NLA_ENSURE(tp != NLA_BITFIELD32 && \ tp != NLA_REJECT && \ @@ -356,6 +396,18 @@ struct nla_policy { .max = _max \ } +#define NLA_POLICY_FULL_RANGE(tp, _range) { \ + .type = NLA_ENSURE_UINT_TYPE(tp), \ + .validation_type = NLA_VALIDATE_RANGE_PTR, \ + .range = _range, \ +} + +#define NLA_POLICY_FULL_RANGE_SIGNED(tp, _range) { \ + .type = NLA_ENSURE_SINT_TYPE(tp), \ + .validation_type = NLA_VALIDATE_RANGE_PTR, \ + .range_signed = _range, \ +} + #define NLA_POLICY_MIN(tp, _min) { \ .type = NLA_ENSURE_INT_TYPE(tp), \ .validation_type = NLA_VALIDATE_MIN, \ @@ -1876,4 +1928,15 @@ static inline bool nla_is_last(const struct nlattr *nla, int rem) return nla->nla_len == rem; } +void nla_get_range_unsigned(const struct nla_policy *pt, + struct netlink_range_validation *range); +void nla_get_range_signed(const struct nla_policy *pt, + struct netlink_range_validation_signed *range); + +int netlink_policy_dump_start(const struct nla_policy *policy, + unsigned int maxtype, + unsigned long *state); +bool netlink_policy_dump_loop(unsigned long *state); +int netlink_policy_dump_write(struct sk_buff *skb, unsigned long state); + #endif diff --git a/include/net/netns/bpf.h b/include/net/netns/bpf.h new file mode 100644 index 000000000000..a8dce2a380c8 --- /dev/null +++ b/include/net/netns/bpf.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * BPF programs attached to network namespace + */ + +#ifndef __NETNS_BPF_H__ +#define __NETNS_BPF_H__ + +#include <linux/bpf-netns.h> + +struct bpf_prog; + +struct netns_bpf { + struct bpf_prog __rcu *progs[MAX_NETNS_BPF_ATTACH_TYPE]; + struct bpf_link *links[MAX_NETNS_BPF_ATTACH_TYPE]; +}; + +#endif /* __NETNS_BPF_H__ */ diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 154b8f01499b..9e36738c1fe1 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -111,6 +111,8 @@ struct netns_ipv4 { int sysctl_tcp_early_demux; int sysctl_udp_early_demux; + int sysctl_nexthop_compat_mode; + int sysctl_fwmark_reflect; int sysctl_tcp_fwmark_accept; #ifdef CONFIG_NET_L3_MASTER_DEV @@ -171,6 +173,7 @@ struct netns_ipv4 { int sysctl_tcp_rmem[3]; int sysctl_tcp_comp_sack_nr; unsigned long sysctl_tcp_comp_sack_delay_ns; + unsigned long sysctl_tcp_comp_sack_slack_ns; struct inet_timewait_death_row tcp_death_row; int sysctl_max_syn_backlog; int sysctl_tcp_fastopen; diff --git a/include/net/netns/nexthop.h b/include/net/netns/nexthop.h index c712ee5eebd9..1937476c94a0 100644 --- a/include/net/netns/nexthop.h +++ b/include/net/netns/nexthop.h @@ -14,5 +14,6 @@ struct netns_nexthop { unsigned int seq; /* protected by rtnl_mutex */ u32 last_id_allocated; + struct atomic_notifier_head notifier_chain; }; #endif diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 8c9f1a718859..e4b55b43e907 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -10,6 +10,7 @@ #define __LINUX_NEXTHOP_H #include <linux/netdevice.h> +#include <linux/notifier.h> #include <linux/route.h> #include <linux/types.h> #include <net/ip_fib.h> @@ -26,6 +27,7 @@ struct nh_config { u8 nh_family; u8 nh_protocol; u8 nh_blackhole; + u8 nh_fdb; u32 nh_flags; int nh_ifindex; @@ -52,6 +54,7 @@ struct nh_info { u8 family; bool reject_nh; + bool fdb_nh; union { struct fib_nh_common fib_nhc; @@ -81,6 +84,7 @@ struct nexthop { struct rb_node rb_node; /* entry on netns rbtree */ struct list_head fi_list; /* v4 entries using nh */ struct list_head f6i_list; /* v6 entries using nh */ + struct list_head fdb_list; /* fdb entries using this nh */ struct list_head grp_list; /* nh group entries using this nh */ struct net *net; @@ -89,6 +93,7 @@ struct nexthop { u8 protocol; /* app managing this nh */ u8 nh_flags; bool is_group; + bool is_fdb_nh; refcount_t refcnt; struct rcu_head rcu; @@ -99,6 +104,17 @@ struct nexthop { }; }; +enum nexthop_event_type { + NEXTHOP_EVENT_ADD, + NEXTHOP_EVENT_DEL +}; + +int call_nexthop_notifier(struct notifier_block *nb, struct net *net, + enum nexthop_event_type event_type, + struct nexthop *nh); +int register_nexthop_notifier(struct net *net, struct notifier_block *nb); +int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb); + /* caller is holding rcu or rtnl; no reference taken to nexthop */ struct nexthop *nexthop_find_by_id(struct net *net, u32 id); void nexthop_free_rcu(struct rcu_head *head); @@ -372,4 +388,32 @@ static inline void nexthop_path_fib6_result(struct fib6_result *res, int hash) int nexthop_for_each_fib6_nh(struct nexthop *nh, int (*cb)(struct fib6_nh *nh, void *arg), void *arg); + +static inline int nexthop_get_family(struct nexthop *nh) +{ + struct nh_info *nhi = rcu_dereference_rtnl(nh->nh_info); + + return nhi->family; +} + +static inline +struct fib_nh_common *nexthop_fdb_nhc(struct nexthop *nh) +{ + struct nh_info *nhi = rcu_dereference_rtnl(nh->nh_info); + + return &nhi->fib_nhc; +} + +static inline struct fib_nh_common *nexthop_path_fdb_result(struct nexthop *nh, + int hash) +{ + struct nh_info *nhi; + struct nexthop *nhp; + + nhp = nexthop_select_path(nh, hash); + if (unlikely(!nhp)) + return NULL; + nhi = rcu_dereference(nhp->nh_info); + return &nhi->fib_nhc; +} #endif diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 04aa0649f3b0..ed65619cbc47 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -325,6 +325,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, void tcf_exts_destroy(struct tcf_exts *exts); void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src); int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts); +int tcf_exts_terse_dump(struct sk_buff *skb, struct tcf_exts *exts); int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts); /** diff --git a/include/net/regulatory.h b/include/net/regulatory.h index 3469750df0f4..09a3099886e5 100644 --- a/include/net/regulatory.h +++ b/include/net/regulatory.h @@ -231,13 +231,6 @@ struct ieee80211_regdomain { struct ieee80211_reg_rule reg_rules[]; }; -#define MHZ_TO_KHZ(freq) ((freq) * 1000) -#define KHZ_TO_MHZ(freq) ((freq) / 1000) -#define DBI_TO_MBI(gain) ((gain) * 100) -#define MBI_TO_DBI(gain) ((gain) / 100) -#define DBM_TO_MBM(gain) ((gain) * 100) -#define MBM_TO_DBM(gain) ((gain) / 100) - #define REG_RULE_EXT(start, end, bw, gain, eirp, dfs_cac, reg_flags) \ { \ .freq_range.start_freq_khz = MHZ_TO_KHZ(start), \ diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 8428aa614265..c510b03b9751 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -330,6 +330,10 @@ struct tcf_proto_ops { int (*dump)(struct net*, struct tcf_proto*, void *, struct sk_buff *skb, struct tcmsg*, bool); + int (*terse_dump)(struct net *net, + struct tcf_proto *tp, void *fh, + struct sk_buff *skb, + struct tcmsg *t, bool rtnl_held); int (*tmplt_dump)(struct sk_buff *skb, struct net *net, void *tmplt_priv); @@ -711,11 +715,6 @@ static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i) } } -static inline void qdisc_reset_all_tx(struct net_device *dev) -{ - qdisc_reset_all_tx_gt(dev, 0); -} - /* Are all TX queues of the device empty? */ static inline bool qdisc_all_tx_empty(const struct net_device *dev) { diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 3ab5c6bbb90b..f8bcb75bb044 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -615,4 +615,11 @@ static inline bool sctp_newsk_ready(const struct sock *sk) return sock_flag(sk, SOCK_DEAD) || sk->sk_socket; } +static inline void sctp_sock_set_nodelay(struct sock *sk) +{ + lock_sock(sk); + sctp_sk(sk)->nodelay = true; + release_sock(sk); +} + #endif /* __net_sctp_h__ */ diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h index 0b032b92da0b..994e984eef32 100644 --- a/include/net/sctp/ulpevent.h +++ b/include/net/sctp/ulpevent.h @@ -80,7 +80,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_assoc_change( struct sctp_chunk *chunk, gfp_t gfp); -void sctp_ulpevent_nofity_peer_addr_change(struct sctp_transport *transport, +void sctp_ulpevent_notify_peer_addr_change(struct sctp_transport *transport, int state, int error); struct sctp_ulpevent *sctp_ulpevent_make_remote_error( diff --git a/include/net/sock.h b/include/net/sock.h index 3e8c6d4b4b59..c53cc42b5ab9 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1156,7 +1156,9 @@ struct proto { int (*sendpage)(struct sock *sk, struct page *page, int offset, size_t size, int flags); int (*bind)(struct sock *sk, - struct sockaddr *uaddr, int addr_len); + struct sockaddr *addr, int addr_len); + int (*bind_add)(struct sock *sk, + struct sockaddr *addr, int addr_len); int (*backlog_rcv) (struct sock *sk, struct sk_buff *skb); @@ -2688,4 +2690,16 @@ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif) void sock_def_readable(struct sock *sk); +int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk); +void sock_enable_timestamps(struct sock *sk); +void sock_no_linger(struct sock *sk); +void sock_set_keepalive(struct sock *sk); +void sock_set_priority(struct sock *sk, u32 priority); +void sock_set_rcvbuf(struct sock *sk, int val); +void sock_set_reuseaddr(struct sock *sk); +void sock_set_reuseport(struct sock *sk); +void sock_set_sndtimeo(struct sock *sk, s64 secs); + +int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len); + #endif /* _SOCK_H */ diff --git a/include/net/switchdev.h b/include/net/switchdev.h index aee86a189432..b8c059b4e06d 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -40,6 +40,10 @@ enum switchdev_attr_id { SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING, SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED, SWITCHDEV_ATTR_ID_BRIDGE_MROUTER, +#if IS_ENABLED(CONFIG_BRIDGE_MRP) + SWITCHDEV_ATTR_ID_MRP_PORT_STATE, + SWITCHDEV_ATTR_ID_MRP_PORT_ROLE, +#endif }; struct switchdev_attr { @@ -55,6 +59,10 @@ struct switchdev_attr { clock_t ageing_time; /* BRIDGE_AGEING_TIME */ bool vlan_filtering; /* BRIDGE_VLAN_FILTERING */ bool mc_disabled; /* MC_DISABLED */ +#if IS_ENABLED(CONFIG_BRIDGE_MRP) + u8 mrp_port_state; /* MRP_PORT_STATE */ + u8 mrp_port_role; /* MRP_PORT_ROLE */ +#endif } u; }; @@ -63,6 +71,12 @@ enum switchdev_obj_id { SWITCHDEV_OBJ_ID_PORT_VLAN, SWITCHDEV_OBJ_ID_PORT_MDB, SWITCHDEV_OBJ_ID_HOST_MDB, +#if IS_ENABLED(CONFIG_BRIDGE_MRP) + SWITCHDEV_OBJ_ID_MRP, + SWITCHDEV_OBJ_ID_RING_TEST_MRP, + SWITCHDEV_OBJ_ID_RING_ROLE_MRP, + SWITCHDEV_OBJ_ID_RING_STATE_MRP, +#endif }; struct switchdev_obj { @@ -94,6 +108,55 @@ struct switchdev_obj_port_mdb { #define SWITCHDEV_OBJ_PORT_MDB(OBJ) \ container_of((OBJ), struct switchdev_obj_port_mdb, obj) + +#if IS_ENABLED(CONFIG_BRIDGE_MRP) +/* SWITCHDEV_OBJ_ID_MRP */ +struct switchdev_obj_mrp { + struct switchdev_obj obj; + struct net_device *p_port; + struct net_device *s_port; + u32 ring_id; + u16 prio; +}; + +#define SWITCHDEV_OBJ_MRP(OBJ) \ + container_of((OBJ), struct switchdev_obj_mrp, obj) + +/* SWITCHDEV_OBJ_ID_RING_TEST_MRP */ +struct switchdev_obj_ring_test_mrp { + struct switchdev_obj obj; + /* The value is in us and a value of 0 represents to stop */ + u32 interval; + u8 max_miss; + u32 ring_id; + u32 period; + bool monitor; +}; + +#define SWITCHDEV_OBJ_RING_TEST_MRP(OBJ) \ + container_of((OBJ), struct switchdev_obj_ring_test_mrp, obj) + +/* SWICHDEV_OBJ_ID_RING_ROLE_MRP */ +struct switchdev_obj_ring_role_mrp { + struct switchdev_obj obj; + u8 ring_role; + u32 ring_id; +}; + +#define SWITCHDEV_OBJ_RING_ROLE_MRP(OBJ) \ + container_of((OBJ), struct switchdev_obj_ring_role_mrp, obj) + +struct switchdev_obj_ring_state_mrp { + struct switchdev_obj obj; + u8 ring_state; + u32 ring_id; +}; + +#define SWITCHDEV_OBJ_RING_STATE_MRP(OBJ) \ + container_of((OBJ), struct switchdev_obj_ring_state_mrp, obj) + +#endif + typedef int switchdev_obj_dump_cb_t(struct switchdev_obj *obj); enum switchdev_notifier_type { diff --git a/include/net/tc_act/tc_gate.h b/include/net/tc_act/tc_gate.h new file mode 100644 index 000000000000..8bc6be81a7ad --- /dev/null +++ b/include/net/tc_act/tc_gate.h @@ -0,0 +1,146 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright 2020 NXP */ + +#ifndef __NET_TC_GATE_H +#define __NET_TC_GATE_H + +#include <net/act_api.h> +#include <linux/tc_act/tc_gate.h> + +struct action_gate_entry { + u8 gate_state; + u32 interval; + s32 ipv; + s32 maxoctets; +}; + +struct tcfg_gate_entry { + int index; + u8 gate_state; + u32 interval; + s32 ipv; + s32 maxoctets; + struct list_head list; +}; + +struct tcf_gate_params { + s32 tcfg_priority; + u64 tcfg_basetime; + u64 tcfg_cycletime; + u64 tcfg_cycletime_ext; + u32 tcfg_flags; + s32 tcfg_clockid; + size_t num_entries; + struct list_head entries; +}; + +#define GATE_ACT_GATE_OPEN BIT(0) +#define GATE_ACT_PENDING BIT(1) + +struct tcf_gate { + struct tc_action common; + struct tcf_gate_params param; + u8 current_gate_status; + ktime_t current_close_time; + u32 current_entry_octets; + s32 current_max_octets; + struct tcfg_gate_entry *next_entry; + struct hrtimer hitimer; + enum tk_offsets tk_offset; +}; + +#define to_gate(a) ((struct tcf_gate *)a) + +static inline bool is_tcf_gate(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + if (a->ops && a->ops->id == TCA_ID_GATE) + return true; +#endif + return false; +} + +static inline u32 tcf_gate_index(const struct tc_action *a) +{ + return a->tcfa_index; +} + +static inline s32 tcf_gate_prio(const struct tc_action *a) +{ + s32 tcfg_prio; + + tcfg_prio = to_gate(a)->param.tcfg_priority; + + return tcfg_prio; +} + +static inline u64 tcf_gate_basetime(const struct tc_action *a) +{ + u64 tcfg_basetime; + + tcfg_basetime = to_gate(a)->param.tcfg_basetime; + + return tcfg_basetime; +} + +static inline u64 tcf_gate_cycletime(const struct tc_action *a) +{ + u64 tcfg_cycletime; + + tcfg_cycletime = to_gate(a)->param.tcfg_cycletime; + + return tcfg_cycletime; +} + +static inline u64 tcf_gate_cycletimeext(const struct tc_action *a) +{ + u64 tcfg_cycletimeext; + + tcfg_cycletimeext = to_gate(a)->param.tcfg_cycletime_ext; + + return tcfg_cycletimeext; +} + +static inline u32 tcf_gate_num_entries(const struct tc_action *a) +{ + u32 num_entries; + + num_entries = to_gate(a)->param.num_entries; + + return num_entries; +} + +static inline struct action_gate_entry + *tcf_gate_get_list(const struct tc_action *a) +{ + struct action_gate_entry *oe; + struct tcf_gate_params *p; + struct tcfg_gate_entry *entry; + u32 num_entries; + int i = 0; + + p = &to_gate(a)->param; + num_entries = p->num_entries; + + list_for_each_entry(entry, &p->entries, list) + i++; + + if (i != num_entries) + return NULL; + + oe = kcalloc(num_entries, sizeof(*oe), GFP_ATOMIC); + if (!oe) + return NULL; + + i = 0; + list_for_each_entry(entry, &p->entries, list) { + oe[i].gate_state = entry->gate_state; + oe[i].interval = entry->interval; + oe[i].ipv = entry->ipv; + oe[i].maxoctets = entry->maxoctets; + i++; + } + + return oe; +} +#endif diff --git a/include/net/tcp.h b/include/net/tcp.h index cf5649a2e795..4de9485f73d9 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -125,6 +125,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); * to combine FIN-WAIT-2 timeout with * TIME-WAIT timer. */ +#define TCP_FIN_TIMEOUT_MAX (120 * HZ) /* max TCP_LINGER2 value (two minutes) */ #define TCP_DELACK_MAX ((unsigned)(HZ/5)) /* maximal time to delay before sending an ACK */ #if HZ >= 100 @@ -435,6 +436,7 @@ u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops, void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb); void tcp_v4_mtu_reduced(struct sock *sk); void tcp_req_err(struct sock *sk, u32 seq, bool abort); +void tcp_ld_RTO_revert(struct sock *sk, u32 seq); int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb); struct sock *tcp_create_openreq_child(const struct sock *sk, struct request_sock *req, @@ -659,7 +661,6 @@ void tcp_initialize_rcv_mss(struct sock *sk); int tcp_mtu_to_mss(struct sock *sk, int pmtu); int tcp_mss_to_mtu(struct sock *sk, int mss); void tcp_mtup_init(struct sock *sk); -void tcp_init_buffer_space(struct sock *sk); static inline void tcp_bound_rto(const struct sock *sk) { @@ -1287,26 +1288,22 @@ static inline bool tcp_needs_internal_pacing(const struct sock *sk) return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED; } -/* Return in jiffies the delay before one skb is sent. - * If @skb is NULL, we look at EDT for next packet being sent on the socket. +/* Estimates in how many jiffies next packet for this flow can be sent. + * Scheduling a retransmit timer too early would be silly. */ -static inline unsigned long tcp_pacing_delay(const struct sock *sk, - const struct sk_buff *skb) +static inline unsigned long tcp_pacing_delay(const struct sock *sk) { - s64 pacing_delay = skb ? skb->tstamp : tcp_sk(sk)->tcp_wstamp_ns; + s64 delay = tcp_sk(sk)->tcp_wstamp_ns - tcp_sk(sk)->tcp_clock_cache; - pacing_delay -= tcp_sk(sk)->tcp_clock_cache; - - return pacing_delay > 0 ? nsecs_to_jiffies(pacing_delay) : 0; + return delay > 0 ? nsecs_to_jiffies(delay) : 0; } static inline void tcp_reset_xmit_timer(struct sock *sk, const int what, unsigned long when, - const unsigned long max_when, - const struct sk_buff *skb) + const unsigned long max_when) { - inet_csk_reset_xmit_timer(sk, what, when + tcp_pacing_delay(sk, skb), + inet_csk_reset_xmit_timer(sk, what, when + tcp_pacing_delay(sk), max_when); } @@ -1334,8 +1331,7 @@ static inline void tcp_check_probe_timer(struct sock *sk) { if (!tcp_sk(sk)->packets_out && !inet_csk(sk)->icsk_pending) tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, - tcp_probe0_base(sk), TCP_RTO_MAX, - NULL); + tcp_probe0_base(sk), TCP_RTO_MAX); } static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq) diff --git a/include/net/tls.h b/include/net/tls.h index 18cd4f418464..3212d3c214a9 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -571,6 +571,15 @@ static inline bool tls_sw_has_ctx_tx(const struct sock *sk) return !!tls_sw_ctx_tx(ctx); } +static inline bool tls_sw_has_ctx_rx(const struct sock *sk) +{ + struct tls_context *ctx = tls_get_ctx(sk); + + if (!ctx) + return false; + return !!tls_sw_ctx_rx(ctx); +} + void tls_sw_write_space(struct sock *sk, struct tls_context *ctx); void tls_device_write_space(struct sock *sk, struct tls_context *ctx); @@ -598,12 +607,22 @@ tls_driver_ctx(const struct sock *sk, enum tls_offload_ctx_dir direction) #endif /* The TLS context is valid until sk_destruct is called */ +#define RESYNC_REQ (1 << 0) +#define RESYNC_REQ_FORCE (1 << 1) static inline void tls_offload_rx_resync_request(struct sock *sk, __be32 seq) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx); - atomic64_set(&rx_ctx->resync_req, ((u64)ntohl(seq) << 32) | 1); + atomic64_set(&rx_ctx->resync_req, ((u64)ntohl(seq) << 32) | RESYNC_REQ); +} + +static inline void tls_offload_rx_force_resync_request(struct sock *sk) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx); + + atomic64_set(&rx_ctx->resync_req, RESYNC_REQ | RESYNC_REQ_FORCE); } static inline void diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 373aadcfea21..3a41627cbdfe 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -7,6 +7,7 @@ #include <net/dst_metadata.h> #include <net/rtnetlink.h> #include <net/switchdev.h> +#include <net/nexthop.h> #define IANA_VXLAN_UDP_PORT 4789 @@ -487,4 +488,28 @@ static inline void vxlan_flag_attr_error(int attrtype, #undef VXLAN_FLAG } +static inline bool vxlan_fdb_nh_path_select(struct nexthop *nh, + int hash, + struct vxlan_rdst *rdst) +{ + struct fib_nh_common *nhc; + + nhc = nexthop_path_fdb_result(nh, hash); + if (unlikely(!nhc)) + return false; + + switch (nhc->nhc_gw_family) { + case AF_INET: + rdst->remote_ip.sin.sin_addr.s_addr = nhc->nhc_gw.ipv4; + rdst->remote_ip.sa.sa_family = AF_INET; + break; + case AF_INET6: + rdst->remote_ip.sin6.sin6_addr = nhc->nhc_gw.ipv6; + rdst->remote_ip.sa.sa_family = AF_INET6; + break; + } + + return true; +} + #endif diff --git a/include/net/xdp.h b/include/net/xdp.h index 40c6d3398458..609f819ed08b 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -6,6 +6,8 @@ #ifndef __LINUX_NET_XDP_H__ #define __LINUX_NET_XDP_H__ +#include <linux/skbuff.h> /* skb_shared_info */ + /** * DOC: XDP RX-queue information * @@ -37,7 +39,7 @@ enum xdp_mem_type { MEM_TYPE_PAGE_SHARED = 0, /* Split-page refcnt based model */ MEM_TYPE_PAGE_ORDER0, /* Orig XDP full page model */ MEM_TYPE_PAGE_POOL, - MEM_TYPE_ZERO_COPY, + MEM_TYPE_XSK_BUFF_POOL, MEM_TYPE_MAX, }; @@ -52,10 +54,6 @@ struct xdp_mem_info { struct page_pool; -struct zero_copy_allocator { - void (*free)(struct zero_copy_allocator *zca, unsigned long handle); -}; - struct xdp_rxq_info { struct net_device *dev; u32 queue_index; @@ -63,20 +61,36 @@ struct xdp_rxq_info { struct xdp_mem_info mem; } ____cacheline_aligned; /* perf critical, avoid false-sharing */ +struct xdp_txq_info { + struct net_device *dev; +}; + struct xdp_buff { void *data; void *data_end; void *data_meta; void *data_hard_start; - unsigned long handle; struct xdp_rxq_info *rxq; + struct xdp_txq_info *txq; + u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/ }; +/* Reserve memory area at end-of data area. + * + * This macro reserves tailroom in the XDP buffer by limiting the + * XDP/BPF data access to data_hard_end. Notice same area (and size) + * is used for XDP_PASS, when constructing the SKB via build_skb(). + */ +#define xdp_data_hard_end(xdp) \ + ((xdp)->data_hard_start + (xdp)->frame_sz - \ + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) + struct xdp_frame { void *data; u16 len; u16 headroom; - u16 metasize; + u32 metasize:8; + u32 frame_sz:24; /* Lifetime of xdp_rxq_info is limited to NAPI/enqueue time, * while mem info is valid on remote CPU. */ @@ -91,17 +105,31 @@ static inline void xdp_scrub_frame(struct xdp_frame *frame) frame->dev_rx = NULL; } +/* Avoids inlining WARN macro in fast-path */ +void xdp_warn(const char *msg, const char *func, const int line); +#define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__) + struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp); +static inline +void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) +{ + xdp->data_hard_start = frame->data - frame->headroom - sizeof(*frame); + xdp->data = frame->data; + xdp->data_end = frame->data + frame->len; + xdp->data_meta = frame->data - frame->metasize; + xdp->frame_sz = frame->frame_sz; +} + /* Convert xdp_buff to xdp_frame */ static inline -struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp) +struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp) { struct xdp_frame *xdp_frame; int metasize; int headroom; - if (xdp->rxq->mem.type == MEM_TYPE_ZERO_COPY) + if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) return xdp_convert_zc_to_xdp_frame(xdp); /* Assure headroom is available for storing info */ @@ -111,6 +139,12 @@ struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp) if (unlikely((headroom - metasize) < sizeof(*xdp_frame))) return NULL; + /* Catch if driver didn't reserve tailroom for skb_shared_info */ + if (unlikely(xdp->data_end > xdp_data_hard_end(xdp))) { + XDP_WARN("Driver BUG: missing reserved tailroom"); + return NULL; + } + /* Store info in top of packet */ xdp_frame = xdp->data_hard_start; @@ -118,6 +152,7 @@ struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp) xdp_frame->len = xdp->data_end - xdp->data; xdp_frame->headroom = headroom - sizeof(*xdp_frame); xdp_frame->metasize = metasize; + xdp_frame->frame_sz = xdp->frame_sz; /* rxq only valid until napi_schedule ends, convert to xdp_mem_info */ xdp_frame->mem = xdp->rxq->mem; @@ -181,4 +216,6 @@ bool xdp_attachment_flags_ok(struct xdp_attachment_info *info, void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf); +#define DEV_MAP_BULK_SIZE 16 + #endif /* __LINUX_NET_XDP_H__ */ diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index e86ec48ef627..96bfc5f5f24e 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -15,42 +15,16 @@ struct net_device; struct xsk_queue; - -/* Masks for xdp_umem_page flags. - * The low 12-bits of the addr will be 0 since this is the page address, so we - * can use them for flags. - */ -#define XSK_NEXT_PG_CONTIG_SHIFT 0 -#define XSK_NEXT_PG_CONTIG_MASK (1ULL << XSK_NEXT_PG_CONTIG_SHIFT) - -struct xdp_umem_page { - void *addr; - dma_addr_t dma; -}; - -struct xdp_umem_fq_reuse { - u32 nentries; - u32 length; - u64 handles[]; -}; - -/* Flags for the umem flags field. - * - * The NEED_WAKEUP flag is 1 due to the reuse of the flags field for public - * flags. See inlude/uapi/include/linux/if_xdp.h. - */ -#define XDP_UMEM_USES_NEED_WAKEUP (1 << 1) +struct xdp_buff; struct xdp_umem { struct xsk_queue *fq; struct xsk_queue *cq; - struct xdp_umem_page *pages; - u64 chunk_mask; + struct xsk_buff_pool *pool; u64 size; u32 headroom; - u32 chunk_size_nohr; + u32 chunk_size; struct user_struct *user; - unsigned long address; refcount_t users; struct work_struct work; struct page **pgs; @@ -60,28 +34,17 @@ struct xdp_umem { u8 flags; int id; struct net_device *dev; - struct xdp_umem_fq_reuse *fq_reuse; bool zc; - spinlock_t xsk_list_lock; - struct list_head xsk_list; + spinlock_t xsk_tx_list_lock; + struct list_head xsk_tx_list; }; -/* Nodes are linked in the struct xdp_sock map_list field, and used to - * track which maps a certain socket reside in. - */ - struct xsk_map { struct bpf_map map; spinlock_t lock; /* Synchronize map updates */ struct xdp_sock *xsk_map[]; }; -struct xsk_map_node { - struct list_head node; - struct xsk_map *map; - struct xdp_sock **map_entry; -}; - struct xdp_sock { /* struct sock must be the first member of struct xdp_sock */ struct sock sk; @@ -112,32 +75,9 @@ struct xdp_sock { spinlock_t map_list_lock; }; -struct xdp_buff; #ifdef CONFIG_XDP_SOCKETS -int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp); -bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs); -/* Used from netdev driver */ -bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt); -bool xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr); -void xsk_umem_release_addr(struct xdp_umem *umem); -void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries); -bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc); -void xsk_umem_consume_tx_done(struct xdp_umem *umem); -struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries); -struct xdp_umem_fq_reuse *xsk_reuseq_swap(struct xdp_umem *umem, - struct xdp_umem_fq_reuse *newq); -void xsk_reuseq_free(struct xdp_umem_fq_reuse *rq); -struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, u16 queue_id); -void xsk_set_rx_need_wakeup(struct xdp_umem *umem); -void xsk_set_tx_need_wakeup(struct xdp_umem *umem); -void xsk_clear_rx_need_wakeup(struct xdp_umem *umem); -void xsk_clear_tx_need_wakeup(struct xdp_umem *umem); -bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem); -void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, - struct xdp_sock **map_entry); -int xsk_map_inc(struct xsk_map *map); -void xsk_map_put(struct xsk_map *map); +int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp); int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp); void __xsk_map_flush(void); @@ -154,219 +94,13 @@ static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, return xs; } -static inline u64 xsk_umem_extract_addr(u64 addr) -{ - return addr & XSK_UNALIGNED_BUF_ADDR_MASK; -} - -static inline u64 xsk_umem_extract_offset(u64 addr) -{ - return addr >> XSK_UNALIGNED_BUF_OFFSET_SHIFT; -} - -static inline u64 xsk_umem_add_offset_to_addr(u64 addr) -{ - return xsk_umem_extract_addr(addr) + xsk_umem_extract_offset(addr); -} - -static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr) -{ - unsigned long page_addr; - - addr = xsk_umem_add_offset_to_addr(addr); - page_addr = (unsigned long)umem->pages[addr >> PAGE_SHIFT].addr; - - return (char *)(page_addr & PAGE_MASK) + (addr & ~PAGE_MASK); -} - -static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr) -{ - addr = xsk_umem_add_offset_to_addr(addr); - - return umem->pages[addr >> PAGE_SHIFT].dma + (addr & ~PAGE_MASK); -} - -/* Reuse-queue aware version of FILL queue helpers */ -static inline bool xsk_umem_has_addrs_rq(struct xdp_umem *umem, u32 cnt) -{ - struct xdp_umem_fq_reuse *rq = umem->fq_reuse; - - if (rq->length >= cnt) - return true; - - return xsk_umem_has_addrs(umem, cnt - rq->length); -} - -static inline bool xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr) -{ - struct xdp_umem_fq_reuse *rq = umem->fq_reuse; - - if (!rq->length) - return xsk_umem_peek_addr(umem, addr); - - *addr = rq->handles[rq->length - 1]; - return addr; -} - -static inline void xsk_umem_release_addr_rq(struct xdp_umem *umem) -{ - struct xdp_umem_fq_reuse *rq = umem->fq_reuse; - - if (!rq->length) - xsk_umem_release_addr(umem); - else - rq->length--; -} - -static inline void xsk_umem_fq_reuse(struct xdp_umem *umem, u64 addr) -{ - struct xdp_umem_fq_reuse *rq = umem->fq_reuse; - - rq->handles[rq->length++] = addr; -} - -/* Handle the offset appropriately depending on aligned or unaligned mode. - * For unaligned mode, we store the offset in the upper 16-bits of the address. - * For aligned mode, we simply add the offset to the address. - */ -static inline u64 xsk_umem_adjust_offset(struct xdp_umem *umem, u64 address, - u64 offset) -{ - if (umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG) - return address + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT); - else - return address + offset; -} #else + static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) { return -ENOTSUPP; } -static inline bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) -{ - return false; -} - -static inline bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt) -{ - return false; -} - -static inline u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr) -{ - return NULL; -} - -static inline void xsk_umem_release_addr(struct xdp_umem *umem) -{ -} - -static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries) -{ -} - -static inline bool xsk_umem_consume_tx(struct xdp_umem *umem, - struct xdp_desc *desc) -{ - return false; -} - -static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem) -{ -} - -static inline struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries) -{ - return NULL; -} - -static inline struct xdp_umem_fq_reuse *xsk_reuseq_swap( - struct xdp_umem *umem, - struct xdp_umem_fq_reuse *newq) -{ - return NULL; -} -static inline void xsk_reuseq_free(struct xdp_umem_fq_reuse *rq) -{ -} - -static inline struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, - u16 queue_id) -{ - return NULL; -} - -static inline u64 xsk_umem_extract_addr(u64 addr) -{ - return 0; -} - -static inline u64 xsk_umem_extract_offset(u64 addr) -{ - return 0; -} - -static inline u64 xsk_umem_add_offset_to_addr(u64 addr) -{ - return 0; -} - -static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr) -{ - return NULL; -} - -static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr) -{ - return 0; -} - -static inline bool xsk_umem_has_addrs_rq(struct xdp_umem *umem, u32 cnt) -{ - return false; -} - -static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr) -{ - return NULL; -} - -static inline void xsk_umem_release_addr_rq(struct xdp_umem *umem) -{ -} - -static inline void xsk_umem_fq_reuse(struct xdp_umem *umem, u64 addr) -{ -} - -static inline void xsk_set_rx_need_wakeup(struct xdp_umem *umem) -{ -} - -static inline void xsk_set_tx_need_wakeup(struct xdp_umem *umem) -{ -} - -static inline void xsk_clear_rx_need_wakeup(struct xdp_umem *umem) -{ -} - -static inline void xsk_clear_tx_need_wakeup(struct xdp_umem *umem) -{ -} - -static inline bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem) -{ - return false; -} - -static inline u64 xsk_umem_adjust_offset(struct xdp_umem *umem, u64 handle, - u64 offset) -{ - return 0; -} - static inline int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp) { return -EOPNOTSUPP; @@ -381,6 +115,7 @@ static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, { return NULL; } + #endif /* CONFIG_XDP_SOCKETS */ #endif /* _LINUX_XDP_SOCK_H */ diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h new file mode 100644 index 000000000000..ccf848f7efa4 --- /dev/null +++ b/include/net/xdp_sock_drv.h @@ -0,0 +1,232 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Interface for implementing AF_XDP zero-copy support in drivers. + * Copyright(c) 2020 Intel Corporation. + */ + +#ifndef _LINUX_XDP_SOCK_DRV_H +#define _LINUX_XDP_SOCK_DRV_H + +#include <net/xdp_sock.h> +#include <net/xsk_buff_pool.h> + +#ifdef CONFIG_XDP_SOCKETS + +void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries); +bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc); +void xsk_umem_consume_tx_done(struct xdp_umem *umem); +struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, u16 queue_id); +void xsk_set_rx_need_wakeup(struct xdp_umem *umem); +void xsk_set_tx_need_wakeup(struct xdp_umem *umem); +void xsk_clear_rx_need_wakeup(struct xdp_umem *umem); +void xsk_clear_tx_need_wakeup(struct xdp_umem *umem); +bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem); + +static inline u32 xsk_umem_get_headroom(struct xdp_umem *umem) +{ + return XDP_PACKET_HEADROOM + umem->headroom; +} + +static inline u32 xsk_umem_get_chunk_size(struct xdp_umem *umem) +{ + return umem->chunk_size; +} + +static inline u32 xsk_umem_get_rx_frame_size(struct xdp_umem *umem) +{ + return xsk_umem_get_chunk_size(umem) - xsk_umem_get_headroom(umem); +} + +static inline void xsk_buff_set_rxq_info(struct xdp_umem *umem, + struct xdp_rxq_info *rxq) +{ + xp_set_rxq_info(umem->pool, rxq); +} + +static inline void xsk_buff_dma_unmap(struct xdp_umem *umem, + unsigned long attrs) +{ + xp_dma_unmap(umem->pool, attrs); +} + +static inline int xsk_buff_dma_map(struct xdp_umem *umem, struct device *dev, + unsigned long attrs) +{ + return xp_dma_map(umem->pool, dev, attrs, umem->pgs, umem->npgs); +} + +static inline dma_addr_t xsk_buff_xdp_get_dma(struct xdp_buff *xdp) +{ + struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); + + return xp_get_dma(xskb); +} + +static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp) +{ + struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); + + return xp_get_frame_dma(xskb); +} + +static inline struct xdp_buff *xsk_buff_alloc(struct xdp_umem *umem) +{ + return xp_alloc(umem->pool); +} + +static inline bool xsk_buff_can_alloc(struct xdp_umem *umem, u32 count) +{ + return xp_can_alloc(umem->pool, count); +} + +static inline void xsk_buff_free(struct xdp_buff *xdp) +{ + struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); + + xp_free(xskb); +} + +static inline dma_addr_t xsk_buff_raw_get_dma(struct xdp_umem *umem, u64 addr) +{ + return xp_raw_get_dma(umem->pool, addr); +} + +static inline void *xsk_buff_raw_get_data(struct xdp_umem *umem, u64 addr) +{ + return xp_raw_get_data(umem->pool, addr); +} + +static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp) +{ + struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); + + xp_dma_sync_for_cpu(xskb); +} + +static inline void xsk_buff_raw_dma_sync_for_device(struct xdp_umem *umem, + dma_addr_t dma, + size_t size) +{ + xp_dma_sync_for_device(umem->pool, dma, size); +} + +#else + +static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries) +{ +} + +static inline bool xsk_umem_consume_tx(struct xdp_umem *umem, + struct xdp_desc *desc) +{ + return false; +} + +static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem) +{ +} + +static inline struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, + u16 queue_id) +{ + return NULL; +} + +static inline void xsk_set_rx_need_wakeup(struct xdp_umem *umem) +{ +} + +static inline void xsk_set_tx_need_wakeup(struct xdp_umem *umem) +{ +} + +static inline void xsk_clear_rx_need_wakeup(struct xdp_umem *umem) +{ +} + +static inline void xsk_clear_tx_need_wakeup(struct xdp_umem *umem) +{ +} + +static inline bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem) +{ + return false; +} + +static inline u32 xsk_umem_get_headroom(struct xdp_umem *umem) +{ + return 0; +} + +static inline u32 xsk_umem_get_chunk_size(struct xdp_umem *umem) +{ + return 0; +} + +static inline u32 xsk_umem_get_rx_frame_size(struct xdp_umem *umem) +{ + return 0; +} + +static inline void xsk_buff_set_rxq_info(struct xdp_umem *umem, + struct xdp_rxq_info *rxq) +{ +} + +static inline void xsk_buff_dma_unmap(struct xdp_umem *umem, + unsigned long attrs) +{ +} + +static inline int xsk_buff_dma_map(struct xdp_umem *umem, struct device *dev, + unsigned long attrs) +{ + return 0; +} + +static inline dma_addr_t xsk_buff_xdp_get_dma(struct xdp_buff *xdp) +{ + return 0; +} + +static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp) +{ + return 0; +} + +static inline struct xdp_buff *xsk_buff_alloc(struct xdp_umem *umem) +{ + return NULL; +} + +static inline bool xsk_buff_can_alloc(struct xdp_umem *umem, u32 count) +{ + return false; +} + +static inline void xsk_buff_free(struct xdp_buff *xdp) +{ +} + +static inline dma_addr_t xsk_buff_raw_get_dma(struct xdp_umem *umem, u64 addr) +{ + return 0; +} + +static inline void *xsk_buff_raw_get_data(struct xdp_umem *umem, u64 addr) +{ + return NULL; +} + +static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp) +{ +} + +static inline void xsk_buff_raw_dma_sync_for_device(struct xdp_umem *umem, + dma_addr_t dma, + size_t size) +{ +} + +#endif /* CONFIG_XDP_SOCKETS */ + +#endif /* _LINUX_XDP_SOCK_DRV_H */ diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 8f71c111e65a..094fe682f5d7 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -361,11 +361,6 @@ struct xfrm_state_afinfo { const struct xfrm_type *type_dstopts; int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); - int (*output_finish)(struct sock *sk, struct sk_buff *skb); - int (*extract_input)(struct xfrm_state *x, - struct sk_buff *skb); - int (*extract_output)(struct xfrm_state *x, - struct sk_buff *skb); int (*transport_finish)(struct sk_buff *skb, int async); void (*local_error)(struct sk_buff *skb, u32 mtu); @@ -1406,6 +1401,8 @@ struct xfrm4_protocol { struct xfrm6_protocol { int (*handler)(struct sk_buff *skb); + int (*input_handler)(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type); int (*cb_handler)(struct sk_buff *skb, int err); int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info); @@ -1562,7 +1559,6 @@ int pktgen_xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb); #endif void xfrm_local_error(struct sk_buff *skb, int mtu); -int xfrm4_extract_header(struct sk_buff *skb); int xfrm4_extract_input(struct xfrm_state *x, struct sk_buff *skb); int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); @@ -1578,7 +1574,6 @@ static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi) return xfrm_input(skb, nexthdr, spi, 0); } -int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb); int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb); int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb); int xfrm4_protocol_register(struct xfrm4_protocol *handler, unsigned char protocol); @@ -1586,10 +1581,11 @@ int xfrm4_protocol_deregister(struct xfrm4_protocol *handler, unsigned char prot int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family); int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family); void xfrm4_local_error(struct sk_buff *skb, u32 mtu); -int xfrm6_extract_header(struct sk_buff *skb); int xfrm6_extract_input(struct xfrm_state *x, struct sk_buff *skb); int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi, struct ip6_tnl *t); +int xfrm6_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type); int xfrm6_transport_finish(struct sk_buff *skb, int async); int xfrm6_rcv_tnl(struct sk_buff *skb, struct ip6_tnl *t); int xfrm6_rcv(struct sk_buff *skb); @@ -1602,14 +1598,15 @@ int xfrm6_tunnel_register(struct xfrm6_tunnel *handler, unsigned short family); int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family); __be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr); __be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr); -int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb); int xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb); int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb); int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb, u8 **prevhdr); #ifdef CONFIG_XFRM +void xfrm6_local_rxpmtu(struct sk_buff *skb, u32 mtu); int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb); +int xfrm6_udp_encap_rcv(struct sock *sk, struct sk_buff *skb); int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen); #else @@ -1992,4 +1989,20 @@ static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x, return 0; } + +#if IS_ENABLED(CONFIG_IPV6) +static inline bool xfrm6_local_dontfrag(const struct sock *sk) +{ + int proto; + + if (!sk || sk->sk_family != AF_INET6) + return false; + + proto = sk->sk_protocol; + if (proto == IPPROTO_UDP || proto == IPPROTO_RAW) + return inet6_sk(sk)->dontfrag; + + return false; +} +#endif #endif /* _NET_XFRM_H */ diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h new file mode 100644 index 000000000000..a4ff226505c9 --- /dev/null +++ b/include/net/xsk_buff_pool.h @@ -0,0 +1,140 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2020 Intel Corporation. */ + +#ifndef XSK_BUFF_POOL_H_ +#define XSK_BUFF_POOL_H_ + +#include <linux/if_xdp.h> +#include <linux/types.h> +#include <linux/dma-mapping.h> +#include <net/xdp.h> + +struct xsk_buff_pool; +struct xdp_rxq_info; +struct xsk_queue; +struct xdp_desc; +struct device; +struct page; + +struct xdp_buff_xsk { + struct xdp_buff xdp; + dma_addr_t dma; + dma_addr_t frame_dma; + struct xsk_buff_pool *pool; + bool unaligned; + u64 orig_addr; + struct list_head free_list_node; +}; + +struct xsk_buff_pool { + struct xsk_queue *fq; + struct list_head free_list; + dma_addr_t *dma_pages; + struct xdp_buff_xsk *heads; + u64 chunk_mask; + u64 addrs_cnt; + u32 free_list_cnt; + u32 dma_pages_cnt; + u32 heads_cnt; + u32 free_heads_cnt; + u32 headroom; + u32 chunk_size; + u32 frame_len; + bool cheap_dma; + bool unaligned; + void *addrs; + struct device *dev; + struct xdp_buff_xsk *free_heads[]; +}; + +/* AF_XDP core. */ +struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks, + u32 chunk_size, u32 headroom, u64 size, + bool unaligned); +void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq); +void xp_destroy(struct xsk_buff_pool *pool); +void xp_release(struct xdp_buff_xsk *xskb); + +/* AF_XDP, and XDP core. */ +void xp_free(struct xdp_buff_xsk *xskb); + +/* AF_XDP ZC drivers, via xdp_sock_buff.h */ +void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq); +int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, + unsigned long attrs, struct page **pages, u32 nr_pages); +void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs); +struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool); +bool xp_can_alloc(struct xsk_buff_pool *pool, u32 count); +void *xp_raw_get_data(struct xsk_buff_pool *pool, u64 addr); +dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr); +static inline dma_addr_t xp_get_dma(struct xdp_buff_xsk *xskb) +{ + return xskb->dma; +} + +static inline dma_addr_t xp_get_frame_dma(struct xdp_buff_xsk *xskb) +{ + return xskb->frame_dma; +} + +void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb); +static inline void xp_dma_sync_for_cpu(struct xdp_buff_xsk *xskb) +{ + if (xskb->pool->cheap_dma) + return; + + xp_dma_sync_for_cpu_slow(xskb); +} + +void xp_dma_sync_for_device_slow(struct xsk_buff_pool *pool, dma_addr_t dma, + size_t size); +static inline void xp_dma_sync_for_device(struct xsk_buff_pool *pool, + dma_addr_t dma, size_t size) +{ + if (pool->cheap_dma) + return; + + xp_dma_sync_for_device_slow(pool, dma, size); +} + +/* Masks for xdp_umem_page flags. + * The low 12-bits of the addr will be 0 since this is the page address, so we + * can use them for flags. + */ +#define XSK_NEXT_PG_CONTIG_SHIFT 0 +#define XSK_NEXT_PG_CONTIG_MASK BIT_ULL(XSK_NEXT_PG_CONTIG_SHIFT) + +static inline bool xp_desc_crosses_non_contig_pg(struct xsk_buff_pool *pool, + u64 addr, u32 len) +{ + bool cross_pg = (addr & (PAGE_SIZE - 1)) + len > PAGE_SIZE; + + if (pool->dma_pages_cnt && cross_pg) { + return !(pool->dma_pages[addr >> PAGE_SHIFT] & + XSK_NEXT_PG_CONTIG_MASK); + } + return false; +} + +static inline u64 xp_aligned_extract_addr(struct xsk_buff_pool *pool, u64 addr) +{ + return addr & pool->chunk_mask; +} + +static inline u64 xp_unaligned_extract_addr(u64 addr) +{ + return addr & XSK_UNALIGNED_BUF_ADDR_MASK; +} + +static inline u64 xp_unaligned_extract_offset(u64 addr) +{ + return addr >> XSK_UNALIGNED_BUF_OFFSET_SHIFT; +} + +static inline u64 xp_unaligned_add_offset_to_addr(u64 addr) +{ + return xp_unaligned_extract_addr(addr) + + xp_unaligned_extract_offset(addr); +} + +#endif /* XSK_BUFF_POOL_H_ */ |