diff options
Diffstat (limited to 'include/net')
48 files changed, 851 insertions, 603 deletions
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 0d87674fb775..172632dd9930 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -100,8 +100,8 @@ struct vsock_transport { /* DGRAM. */ int (*dgram_bind)(struct vsock_sock *, struct sockaddr_vm *); - int (*dgram_dequeue)(struct kiocb *kiocb, struct vsock_sock *vsk, - struct msghdr *msg, size_t len, int flags); + int (*dgram_dequeue)(struct vsock_sock *vsk, struct msghdr *msg, + size_t len, int flags); int (*dgram_enqueue)(struct vsock_sock *, struct sockaddr_vm *, struct msghdr *, size_t len); bool (*dgram_allow)(u32 cid, u32 port); diff --git a/include/net/arp.h b/include/net/arp.h index 73c49864076b..5e0f891d476c 100644 --- a/include/net/arp.h +++ b/include/net/arp.h @@ -9,28 +9,17 @@ extern struct neigh_table arp_tbl; -static inline u32 arp_hashfn(u32 key, const struct net_device *dev, u32 hash_rnd) +static inline u32 arp_hashfn(const void *pkey, const struct net_device *dev, u32 *hash_rnd) { + u32 key = *(const u32 *)pkey; u32 val = key ^ hash32_ptr(dev); - return val * hash_rnd; + return val * hash_rnd[0]; } static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key) { - struct neigh_hash_table *nht = rcu_dereference_bh(arp_tbl.nht); - struct neighbour *n; - u32 hash_val; - - hash_val = arp_hashfn(key, dev, nht->hash_rnd[0]) >> (32 - nht->hash_shift); - for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); - n != NULL; - n = rcu_dereference_bh(n->next)) { - if (n->dev == dev && *(u32 *)n->primary_key == key) - return n; - } - - return NULL; + return ___neigh_lookup_noref(&arp_tbl, neigh_key_eq32, arp_hashfn, &key, dev); } static inline struct neighbour *__ipv4_neigh_lookup(struct net_device *dev, u32 key) @@ -47,7 +36,6 @@ static inline struct neighbour *__ipv4_neigh_lookup(struct net_device *dev, u32 } void arp_init(void); -int arp_find(unsigned char *haddr, struct sk_buff *skb); int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg); void arp_send(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, diff --git a/include/net/ax25.h b/include/net/ax25.h index bf0396e9a5d3..16a923a3a43a 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -12,6 +12,7 @@ #include <linux/list.h> #include <linux/slab.h> #include <linux/atomic.h> +#include <net/neighbour.h> #define AX25_T1CLAMPLO 1 #define AX25_T1CLAMPHI (30 * HZ) @@ -366,9 +367,7 @@ int ax25_kiss_rcv(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); /* ax25_ip.c */ -int ax25_hard_header(struct sk_buff *, struct net_device *, unsigned short, - const void *, const void *, unsigned int); -int ax25_rebuild_header(struct sk_buff *); +netdev_tx_t ax25_ip_xmit(struct sk_buff *skb); extern const struct header_ops ax25_header_ops; /* ax25_out.c */ diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index e00455aab18c..33a5e00025aa 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -245,10 +245,10 @@ int bt_sock_register(int proto, const struct net_proto_family *ops); void bt_sock_unregister(int proto); void bt_sock_link(struct bt_sock_list *l, struct sock *s); void bt_sock_unlink(struct bt_sock_list *l, struct sock *s); -int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len, int flags); -int bt_sock_stream_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t len, int flags); +int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags); +int bt_sock_stream_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags); uint bt_sock_poll(struct file *file, struct socket *sock, poll_table *wait); int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo); @@ -275,21 +275,17 @@ struct hci_dev; typedef void (*hci_req_complete_t)(struct hci_dev *hdev, u8 status, u16 opcode); -struct hci_req_ctrl { - bool start; - u8 event; - hci_req_complete_t complete; -}; - struct bt_skb_cb { __u8 pkt_type; - __u8 incoming; + __u8 force_active; __u16 opcode; __u16 expect; - __u8 force_active; + __u8 incoming:1; + __u8 req_start:1; + u8 req_event; + hci_req_complete_t req_complete; struct l2cap_chan *chan; struct l2cap_ctrl control; - struct hci_req_ctrl req; bdaddr_t bdaddr; __le16 psm; }; @@ -339,6 +335,11 @@ out: int bt_to_errno(__u16 code); +void hci_sock_set_flag(struct sock *sk, int nr); +void hci_sock_clear_flag(struct sock *sk, int nr); +int hci_sock_test_flag(struct sock *sk, int nr); +unsigned short hci_sock_get_channel(struct sock *sk); + int hci_sock_init(void); void hci_sock_cleanup(void); @@ -358,6 +359,9 @@ void l2cap_exit(void); int sco_init(void); void sco_exit(void); +int mgmt_init(void); +void mgmt_exit(void); + void bt_sock_reclassify_lock(struct sock *sk, int proto); #endif /* __BLUETOOTH_H */ diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 8e54f825153c..06e7eee31ce4 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -160,6 +160,14 @@ enum { * during the hdev->setup vendor callback. */ HCI_QUIRK_STRICT_DUPLICATE_FILTER, + + /* When this quirk is set, LE scan and BR/EDR inquiry is done + * simultaneously, otherwise it's interleaved. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. + */ + HCI_QUIRK_SIMULTANEOUS_DISCOVERY, }; /* HCI device flags */ @@ -179,13 +187,14 @@ enum { HCI_RESET, }; -/* BR/EDR and/or LE controller flags: the flags defined here should represent - * states configured via debugfs for debugging and testing purposes only. - */ +/* HCI socket flags */ enum { - HCI_DUT_MODE, - HCI_FORCE_BREDR_SMP, - HCI_FORCE_STATIC_ADDR, + HCI_SOCK_TRUSTED, + HCI_MGMT_INDEX_EVENTS, + HCI_MGMT_UNCONF_INDEX_EVENTS, + HCI_MGMT_EXT_INDEX_EVENTS, + HCI_MGMT_GENERIC_EVENTS, + HCI_MGMT_OOB_DATA_EVENTS, }; /* @@ -217,6 +226,7 @@ enum { HCI_HS_ENABLED, HCI_LE_ENABLED, HCI_ADVERTISING, + HCI_ADVERTISING_CONNECTABLE, HCI_CONNECTABLE, HCI_DISCOVERABLE, HCI_LIMITED_DISCOVERABLE, @@ -225,13 +235,13 @@ enum { HCI_FAST_CONNECTABLE, HCI_BREDR_ENABLED, HCI_LE_SCAN_INTERRUPTED, -}; -/* A mask for the flags that are supposed to remain when a reset happens - * or the HCI device is closed. - */ -#define HCI_PERSISTENT_MASK (BIT(HCI_LE_SCAN) | BIT(HCI_PERIODIC_INQ) | \ - BIT(HCI_FAST_CONNECTABLE) | BIT(HCI_LE_ADV)) + HCI_DUT_MODE, + HCI_FORCE_BREDR_SMP, + HCI_FORCE_STATIC_ADDR, + + __HCI_NUM_FLAGS, +}; /* HCI timeouts */ #define HCI_DISCONN_TIMEOUT msecs_to_jiffies(2000) /* 2 seconds */ @@ -455,6 +465,10 @@ enum { #define EIR_SSP_HASH_C 0x0E /* Simple Pairing Hash C */ #define EIR_SSP_RAND_R 0x0F /* Simple Pairing Randomizer R */ #define EIR_DEVICE_ID 0x10 /* device ID */ +#define EIR_LE_BDADDR 0x1B /* LE Bluetooth device address */ +#define EIR_LE_ROLE 0x1C /* LE role */ +#define EIR_LE_SC_CONFIRM 0x22 /* LE SC Confirmation Value */ +#define EIR_LE_SC_RANDOM 0x23 /* LE SC Random Value */ /* Low Energy Advertising Flags */ #define LE_AD_LIMITED 0x01 /* Limited Discoverable */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 52863c3e0b13..b65c53de6a69 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -76,6 +76,7 @@ struct discovery_state { u8 last_adv_data[HCI_MAX_AD_LENGTH]; u8 last_adv_data_len; bool report_invalid_rssi; + bool result_filtering; s8 rssi; u16 uuid_count; u8 (*uuids)[16]; @@ -108,7 +109,7 @@ struct bt_uuid { struct smp_csrk { bdaddr_t bdaddr; u8 bdaddr_type; - u8 master; + u8 type; u8 val[16]; }; @@ -352,8 +353,7 @@ struct hci_dev { struct rfkill *rfkill; - unsigned long dbg_flags; - unsigned long dev_flags; + DECLARE_BITMAP(dev_flags, __HCI_NUM_FLAGS); struct delayed_work le_scan_disable; struct delayed_work le_scan_restart; @@ -373,6 +373,7 @@ struct hci_dev { int (*close)(struct hci_dev *hdev); int (*flush)(struct hci_dev *hdev); int (*setup)(struct hci_dev *hdev); + int (*shutdown)(struct hci_dev *hdev); int (*send)(struct hci_dev *hdev, struct sk_buff *skb); void (*notify)(struct hci_dev *hdev, unsigned int evt); void (*hw_error)(struct hci_dev *hdev, u8 code); @@ -498,19 +499,29 @@ struct hci_conn_params { extern struct list_head hci_dev_list; extern struct list_head hci_cb_list; extern rwlock_t hci_dev_list_lock; -extern rwlock_t hci_cb_list_lock; +extern struct mutex hci_cb_list_lock; + +#define hci_dev_set_flag(hdev, nr) set_bit((nr), (hdev)->dev_flags) +#define hci_dev_clear_flag(hdev, nr) clear_bit((nr), (hdev)->dev_flags) +#define hci_dev_change_flag(hdev, nr) change_bit((nr), (hdev)->dev_flags) +#define hci_dev_test_flag(hdev, nr) test_bit((nr), (hdev)->dev_flags) +#define hci_dev_test_and_set_flag(hdev, nr) test_and_set_bit((nr), (hdev)->dev_flags) +#define hci_dev_test_and_clear_flag(hdev, nr) test_and_clear_bit((nr), (hdev)->dev_flags) +#define hci_dev_test_and_change_flag(hdev, nr) test_and_change_bit((nr), (hdev)->dev_flags) + +#define hci_dev_clear_volatile_flags(hdev) \ + do { \ + hci_dev_clear_flag(hdev, HCI_LE_SCAN); \ + hci_dev_clear_flag(hdev, HCI_LE_ADV); \ + hci_dev_clear_flag(hdev, HCI_PERIODIC_INQ); \ + } while (0) /* ----- HCI interface to upper protocols ----- */ int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr); -void l2cap_connect_cfm(struct hci_conn *hcon, u8 status); int l2cap_disconn_ind(struct hci_conn *hcon); -void l2cap_disconn_cfm(struct hci_conn *hcon, u8 reason); -int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt); int l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags); int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags); -void sco_connect_cfm(struct hci_conn *hcon, __u8 status); -void sco_disconn_cfm(struct hci_conn *hcon, __u8 reason); int sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb); /* ----- Inquiry cache ----- */ @@ -529,6 +540,7 @@ static inline void discovery_init(struct hci_dev *hdev) static inline void hci_discovery_filter_clear(struct hci_dev *hdev) { + hdev->discovery.result_filtering = false; hdev->discovery.report_invalid_rssi = true; hdev->discovery.rssi = HCI_RSSI_INVALID; hdev->discovery.uuid_count = 0; @@ -584,7 +596,6 @@ enum { HCI_CONN_SC_ENABLED, HCI_CONN_AES_CCM, HCI_CONN_POWER_SAVE, - HCI_CONN_REMOTE_OOB, HCI_CONN_FLUSH_KEY, HCI_CONN_ENCRYPT, HCI_CONN_AUTH, @@ -600,14 +611,14 @@ enum { static inline bool hci_conn_ssp_enabled(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; - return test_bit(HCI_SSP_ENABLED, &hdev->dev_flags) && + return hci_dev_test_flag(hdev, HCI_SSP_ENABLED) && test_bit(HCI_CONN_SSP_ENABLED, &conn->flags); } static inline bool hci_conn_sc_enabled(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; - return test_bit(HCI_SC_ENABLED, &hdev->dev_flags) && + return hci_dev_test_flag(hdev, HCI_SC_ENABLED) && test_bit(HCI_CONN_SC_ENABLED, &conn->flags); } @@ -969,6 +980,8 @@ struct smp_irk *hci_add_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, void hci_remove_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type); void hci_smp_irks_clear(struct hci_dev *hdev); +bool hci_bdaddr_is_paired(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type); + void hci_remote_oob_data_clear(struct hci_dev *hdev); struct oob_data *hci_find_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type); @@ -1025,10 +1038,10 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define lmp_host_le_capable(dev) (!!((dev)->features[1][0] & LMP_HOST_LE)) #define lmp_host_le_br_capable(dev) (!!((dev)->features[1][0] & LMP_HOST_LE_BREDR)) -#define hdev_is_powered(hdev) (test_bit(HCI_UP, &hdev->flags) && \ - !test_bit(HCI_AUTO_OFF, &hdev->dev_flags)) -#define bredr_sc_enabled(dev) (lmp_sc_capable(dev) && \ - test_bit(HCI_SC_ENABLED, &(dev)->dev_flags)) +#define hdev_is_powered(dev) (test_bit(HCI_UP, &(dev)->flags) && \ + !hci_dev_test_flag(dev, HCI_AUTO_OFF)) +#define bredr_sc_enabled(dev) (lmp_sc_capable(dev) && \ + hci_dev_test_flag(dev, HCI_SC_ENABLED)) /* ----- HCI protocols ----- */ #define HCI_PROTO_DEFER 0x01 @@ -1050,28 +1063,6 @@ static inline int hci_proto_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, } } -static inline void hci_proto_connect_cfm(struct hci_conn *conn, __u8 status) -{ - switch (conn->type) { - case ACL_LINK: - case LE_LINK: - l2cap_connect_cfm(conn, status); - break; - - case SCO_LINK: - case ESCO_LINK: - sco_connect_cfm(conn, status); - break; - - default: - BT_ERR("unknown link type %d", conn->type); - break; - } - - if (conn->connect_cfm_cb) - conn->connect_cfm_cb(conn, status); -} - static inline int hci_proto_disconn_ind(struct hci_conn *conn) { if (conn->type != ACL_LINK && conn->type != LE_LINK) @@ -1080,91 +1071,69 @@ static inline int hci_proto_disconn_ind(struct hci_conn *conn) return l2cap_disconn_ind(conn); } -static inline void hci_proto_disconn_cfm(struct hci_conn *conn, __u8 reason) -{ - switch (conn->type) { - case ACL_LINK: - case LE_LINK: - l2cap_disconn_cfm(conn, reason); - break; - - case SCO_LINK: - case ESCO_LINK: - sco_disconn_cfm(conn, reason); - break; - - /* L2CAP would be handled for BREDR chan */ - case AMP_LINK: - break; +/* ----- HCI callbacks ----- */ +struct hci_cb { + struct list_head list; - default: - BT_ERR("unknown link type %d", conn->type); - break; - } + char *name; - if (conn->disconn_cfm_cb) - conn->disconn_cfm_cb(conn, reason); -} + void (*connect_cfm) (struct hci_conn *conn, __u8 status); + void (*disconn_cfm) (struct hci_conn *conn, __u8 status); + void (*security_cfm) (struct hci_conn *conn, __u8 status, + __u8 encrypt); + void (*key_change_cfm) (struct hci_conn *conn, __u8 status); + void (*role_switch_cfm) (struct hci_conn *conn, __u8 status, __u8 role); +}; -static inline void hci_proto_auth_cfm(struct hci_conn *conn, __u8 status) +static inline void hci_connect_cfm(struct hci_conn *conn, __u8 status) { - __u8 encrypt; - - if (conn->type != ACL_LINK && conn->type != LE_LINK) - return; - - if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags)) - return; + struct hci_cb *cb; - encrypt = test_bit(HCI_CONN_ENCRYPT, &conn->flags) ? 0x01 : 0x00; - l2cap_security_cfm(conn, status, encrypt); + mutex_lock(&hci_cb_list_lock); + list_for_each_entry(cb, &hci_cb_list, list) { + if (cb->connect_cfm) + cb->connect_cfm(conn, status); + } + mutex_unlock(&hci_cb_list_lock); - if (conn->security_cfm_cb) - conn->security_cfm_cb(conn, status); + if (conn->connect_cfm_cb) + conn->connect_cfm_cb(conn, status); } -static inline void hci_proto_encrypt_cfm(struct hci_conn *conn, __u8 status, - __u8 encrypt) +static inline void hci_disconn_cfm(struct hci_conn *conn, __u8 reason) { - if (conn->type != ACL_LINK && conn->type != LE_LINK) - return; + struct hci_cb *cb; - l2cap_security_cfm(conn, status, encrypt); + mutex_lock(&hci_cb_list_lock); + list_for_each_entry(cb, &hci_cb_list, list) { + if (cb->disconn_cfm) + cb->disconn_cfm(conn, reason); + } + mutex_unlock(&hci_cb_list_lock); - if (conn->security_cfm_cb) - conn->security_cfm_cb(conn, status); + if (conn->disconn_cfm_cb) + conn->disconn_cfm_cb(conn, reason); } -/* ----- HCI callbacks ----- */ -struct hci_cb { - struct list_head list; - - char *name; - - void (*security_cfm) (struct hci_conn *conn, __u8 status, - __u8 encrypt); - void (*key_change_cfm) (struct hci_conn *conn, __u8 status); - void (*role_switch_cfm) (struct hci_conn *conn, __u8 status, __u8 role); -}; - static inline void hci_auth_cfm(struct hci_conn *conn, __u8 status) { struct hci_cb *cb; __u8 encrypt; - hci_proto_auth_cfm(conn, status); - if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags)) return; encrypt = test_bit(HCI_CONN_ENCRYPT, &conn->flags) ? 0x01 : 0x00; - read_lock(&hci_cb_list_lock); + mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->security_cfm) cb->security_cfm(conn, status, encrypt); } - read_unlock(&hci_cb_list_lock); + mutex_unlock(&hci_cb_list_lock); + + if (conn->security_cfm_cb) + conn->security_cfm_cb(conn, status); } static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status, @@ -1178,26 +1147,27 @@ static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status, if (conn->pending_sec_level > conn->sec_level) conn->sec_level = conn->pending_sec_level; - hci_proto_encrypt_cfm(conn, status, encrypt); - - read_lock(&hci_cb_list_lock); + mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->security_cfm) cb->security_cfm(conn, status, encrypt); } - read_unlock(&hci_cb_list_lock); + mutex_unlock(&hci_cb_list_lock); + + if (conn->security_cfm_cb) + conn->security_cfm_cb(conn, status); } static inline void hci_key_change_cfm(struct hci_conn *conn, __u8 status) { struct hci_cb *cb; - read_lock(&hci_cb_list_lock); + mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->key_change_cfm) cb->key_change_cfm(conn, status); } - read_unlock(&hci_cb_list_lock); + mutex_unlock(&hci_cb_list_lock); } static inline void hci_role_switch_cfm(struct hci_conn *conn, __u8 status, @@ -1205,12 +1175,12 @@ static inline void hci_role_switch_cfm(struct hci_conn *conn, __u8 status, { struct hci_cb *cb; - read_lock(&hci_cb_list_lock); + mutex_lock(&hci_cb_list_lock); list_for_each_entry(cb, &hci_cb_list, list) { if (cb->role_switch_cfm) cb->role_switch_cfm(conn, status, role); } - read_unlock(&hci_cb_list_lock); + mutex_unlock(&hci_cb_list_lock); } static inline bool eir_has_data_type(u8 *data, size_t data_len, u8 type) @@ -1312,11 +1282,35 @@ void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode); /* ----- HCI Sockets ----- */ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb); -void hci_send_to_control(struct sk_buff *skb, struct sock *skip_sk); +void hci_send_to_channel(unsigned short channel, struct sk_buff *skb, + int flag, struct sock *skip_sk); void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb); void hci_sock_dev_event(struct hci_dev *hdev, int event); +#define HCI_MGMT_VAR_LEN BIT(0) +#define HCI_MGMT_NO_HDEV BIT(1) +#define HCI_MGMT_UNTRUSTED BIT(2) +#define HCI_MGMT_UNCONFIGURED BIT(3) + +struct hci_mgmt_handler { + int (*func) (struct sock *sk, struct hci_dev *hdev, void *data, + u16 data_len); + size_t data_len; + unsigned long flags; +}; + +struct hci_mgmt_chan { + struct list_head list; + unsigned short channel; + size_t handler_count; + const struct hci_mgmt_handler *handlers; + void (*hdev_init) (struct sock *sk, struct hci_dev *hdev); +}; + +int hci_mgmt_chan_register(struct hci_mgmt_chan *c); +void hci_mgmt_chan_unregister(struct hci_mgmt_chan *c); + /* Management interface */ #define DISCOV_TYPE_BREDR (BIT(BDADDR_BREDR)) #define DISCOV_TYPE_LE (BIT(BDADDR_LE_PUBLIC) | \ @@ -1336,7 +1330,6 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event); #define DISCOV_BREDR_INQUIRY_LEN 0x08 #define DISCOV_LE_RESTART_DELAY msecs_to_jiffies(200) /* msec */ -int mgmt_control(struct sock *sk, struct msghdr *msg, size_t len); int mgmt_new_settings(struct hci_dev *hdev); void mgmt_index_added(struct hci_dev *hdev); void mgmt_index_removed(struct hci_dev *hdev); diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index e218a30f2061..a1a68671bf88 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -43,6 +43,8 @@ #define MGMT_STATUS_CANCELLED 0x10 #define MGMT_STATUS_INVALID_INDEX 0x11 #define MGMT_STATUS_RFKILLED 0x12 +#define MGMT_STATUS_ALREADY_PAIRED 0x13 +#define MGMT_STATUS_PERMISSION_DENIED 0x14 struct mgmt_hdr { __le16 opcode; @@ -98,6 +100,7 @@ struct mgmt_rp_read_index_list { #define MGMT_SETTING_DEBUG_KEYS 0x00001000 #define MGMT_SETTING_PRIVACY 0x00002000 #define MGMT_SETTING_CONFIGURATION 0x00004000 +#define MGMT_SETTING_STATIC_ADDRESS 0x00008000 #define MGMT_OP_READ_INFO 0x0004 #define MGMT_READ_INFO_SIZE 0 @@ -503,6 +506,39 @@ struct mgmt_cp_start_service_discovery { } __packed; #define MGMT_START_SERVICE_DISCOVERY_SIZE 4 +#define MGMT_OP_READ_LOCAL_OOB_EXT_DATA 0x003B +struct mgmt_cp_read_local_oob_ext_data { + __u8 type; +} __packed; +#define MGMT_READ_LOCAL_OOB_EXT_DATA_SIZE 1 +struct mgmt_rp_read_local_oob_ext_data { + __u8 type; + __le16 eir_len; + __u8 eir[0]; +} __packed; + +#define MGMT_OP_READ_EXT_INDEX_LIST 0x003C +#define MGMT_READ_EXT_INDEX_LIST_SIZE 0 +struct mgmt_rp_read_ext_index_list { + __le16 num_controllers; + struct { + __le16 index; + __u8 type; + __u8 bus; + } entry[0]; +} __packed; + +#define MGMT_OP_READ_ADV_FEATURES 0x0003D +#define MGMT_READ_ADV_FEATURES_SIZE 0 +struct mgmt_rp_read_adv_features { + __le32 supported_flags; + __u8 max_adv_data_len; + __u8 max_scan_rsp_len; + __u8 max_instances; + __u8 num_instances; + __u8 instance[0]; +} __packed; + #define MGMT_EV_CMD_COMPLETE 0x0001 struct mgmt_ev_cmd_complete { __le16 opcode; @@ -647,9 +683,14 @@ struct mgmt_ev_new_irk { struct mgmt_irk_info irk; } __packed; +#define MGMT_CSRK_LOCAL_UNAUTHENTICATED 0x00 +#define MGMT_CSRK_REMOTE_UNAUTHENTICATED 0x01 +#define MGMT_CSRK_LOCAL_AUTHENTICATED 0x02 +#define MGMT_CSRK_REMOTE_AUTHENTICATED 0x03 + struct mgmt_csrk_info { struct mgmt_addr_info addr; - __u8 master; + __u8 type; __u8 val[16]; } __packed; @@ -685,3 +726,19 @@ struct mgmt_ev_new_conn_param { #define MGMT_EV_UNCONF_INDEX_REMOVED 0x001e #define MGMT_EV_NEW_CONFIG_OPTIONS 0x001f + +struct mgmt_ev_ext_index { + __u8 type; + __u8 bus; +} __packed; + +#define MGMT_EV_EXT_INDEX_ADDED 0x0020 + +#define MGMT_EV_EXT_INDEX_REMOVED 0x0021 + +#define MGMT_EV_LOCAL_OOB_DATA_UPDATED 0x0022 +struct mgmt_ev_local_oob_data_updated { + __u8 type; + __le16 eir_len; + __u8 eir[0]; +} __packed; diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index f04cdbb7848e..c2a40a172fcd 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -82,6 +82,13 @@ typedef enum { AD_TRANSMIT /* tx Machine */ } tx_states_t; +/* churn machine states(43.4.17 in the 802.3ad standard) */ +typedef enum { + AD_CHURN_MONITOR, /* monitoring for churn */ + AD_CHURN, /* churn detected (error) */ + AD_NO_CHURN /* no churn (no error) */ +} churn_state_t; + /* rx indication types */ typedef enum { AD_TYPE_LACPDU = 1, /* type lacpdu */ @@ -229,6 +236,12 @@ typedef struct port { u16 sm_mux_timer_counter; /* state machine mux timer counter */ tx_states_t sm_tx_state; /* state machine tx state */ u16 sm_tx_timer_counter; /* state machine tx timer counter(allways on - enter to transmit state 3 time per second) */ + u16 sm_churn_actor_timer_counter; + u16 sm_churn_partner_timer_counter; + u32 churn_actor_count; + u32 churn_partner_count; + churn_state_t sm_churn_actor_state; + churn_state_t sm_churn_partner_state; struct slave *slave; /* pointer to the bond slave that this port belongs to */ struct aggregator *aggregator; /* pointer to an aggregator that this port related to */ struct port *next_port_in_aggregator; /* Next port on the linked list of the parent aggregator */ @@ -262,6 +275,22 @@ struct ad_slave_info { u16 id; }; +static inline const char *bond_3ad_churn_desc(churn_state_t state) +{ + static const char *const churn_description[] = { + "monitoring", + "churned", + "none", + "unknown" + }; + int max_size = sizeof(churn_description) / sizeof(churn_description[0]); + + if (state >= max_size) + state = max_size - 1; + + return churn_description[state]; +} + /* ========== AD Exported functions to the main bonding code ========== */ void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution); void bond_3ad_bind_slave(struct slave *slave); diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 64e09e1e8099..f977abec07f6 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -3183,10 +3183,8 @@ struct wiphy { const struct ieee80211_ht_cap *ht_capa_mod_mask; const struct ieee80211_vht_cap *vht_capa_mod_mask; -#ifdef CONFIG_NET_NS /* the network namespace this phy lives in currently */ - struct net *_net; -#endif + possible_net_t _net; #ifdef CONFIG_CFG80211_WEXT const struct iw_handler_def *wext; diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h index 597b88a94332..207d9ba1f92c 100644 --- a/include/net/dcbnl.h +++ b/include/net/dcbnl.h @@ -49,6 +49,9 @@ struct dcbnl_rtnl_ops { int (*ieee_setets) (struct net_device *, struct ieee_ets *); int (*ieee_getmaxrate) (struct net_device *, struct ieee_maxrate *); int (*ieee_setmaxrate) (struct net_device *, struct ieee_maxrate *); + int (*ieee_getqcn) (struct net_device *, struct ieee_qcn *); + int (*ieee_setqcn) (struct net_device *, struct ieee_qcn *); + int (*ieee_getqcnstats) (struct net_device *, struct ieee_qcn_stats *); int (*ieee_getpfc) (struct net_device *, struct ieee_pfc *); int (*ieee_setpfc) (struct net_device *, struct ieee_pfc *); int (*ieee_getapp) (struct net_device *, struct dcb_app *); diff --git a/include/net/dn_neigh.h b/include/net/dn_neigh.h index fac4e3f4a6d3..0f26aa707e62 100644 --- a/include/net/dn_neigh.h +++ b/include/net/dn_neigh.h @@ -22,6 +22,7 @@ int dn_neigh_router_hello(struct sk_buff *skb); int dn_neigh_endnode_hello(struct sk_buff *skb); void dn_neigh_pointopoint_hello(struct sk_buff *skb); int dn_neigh_elist(struct net_device *dev, unsigned char *ptr, int n); +int dn_to_neigh_output(struct sk_buff *skb); extern struct neigh_table dn_neigh_table; diff --git a/include/net/dsa.h b/include/net/dsa.h index ed3c34bbb67a..47917e5e1e12 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -72,6 +72,7 @@ struct dsa_platform_data { * to the root switch chip of the tree. */ struct device *netdev; + struct net_device *of_netdev; /* * Info structs describing each of the switch chips @@ -128,6 +129,11 @@ struct dsa_switch { int index; /* + * Tagging protocol understood by this switch + */ + enum dsa_tag_protocol tag_protocol; + + /* * Configuration data for this switch. */ struct dsa_chip_data *pd; @@ -165,6 +171,11 @@ static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p) return !!(ds->index == ds->dst->cpu_switch && p == ds->dst->cpu_port); } +static inline bool dsa_is_port_initialized(struct dsa_switch *ds, int p) +{ + return ds->phys_port_mask & (1 << p) && ds->ports[p]; +} + static inline u8 dsa_upstream_port(struct dsa_switch *ds) { struct dsa_switch_tree *dst = ds->dst; @@ -275,6 +286,16 @@ struct dsa_switch_driver { int (*get_regs_len)(struct dsa_switch *ds, int port); void (*get_regs)(struct dsa_switch *ds, int port, struct ethtool_regs *regs, void *p); + + /* + * Bridge integration + */ + int (*port_join_bridge)(struct dsa_switch *ds, int port, + u32 br_port_mask); + int (*port_leave_bridge)(struct dsa_switch *ds, int port, + u32 br_port_mask); + int (*port_stp_update)(struct dsa_switch *ds, int port, + u8 state); }; void register_switch_driver(struct dsa_switch_driver *type); diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 1f99a1de0e4f..d64253914a6a 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -12,7 +12,6 @@ struct sock; struct dst_ops { unsigned short family; - __be16 protocol; unsigned int gc_thresh; int (*gc)(struct dst_ops *ops); diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index e584de16e4c3..6d67383a5114 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -58,7 +58,7 @@ struct fib_rules_ops { struct sk_buff *, struct fib_rule_hdr *, struct nlattr **); - void (*delete)(struct fib_rule *); + int (*delete)(struct fib_rule *); int (*compare)(struct fib_rule *, struct fib_rule_hdr *, struct nlattr **); @@ -95,17 +95,10 @@ static inline void fib_rule_get(struct fib_rule *rule) atomic_inc(&rule->refcnt); } -static inline void fib_rule_put_rcu(struct rcu_head *head) -{ - struct fib_rule *rule = container_of(head, struct fib_rule, rcu); - release_net(rule->fr_net); - kfree(rule); -} - static inline void fib_rule_put(struct fib_rule *rule) { if (atomic_dec_and_test(&rule->refcnt)) - call_rcu(&rule->rcu, fib_rule_put_rcu); + kfree_rcu(rule, rcu); } static inline u32 frh_get_table(struct fib_rule_hdr *frh, struct nlattr **nla) diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 0574abd3db86..a9af1cc8c1bc 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -92,9 +92,7 @@ struct genl_info { struct genlmsghdr * genlhdr; void * userhdr; struct nlattr ** attrs; -#ifdef CONFIG_NET_NS - struct net * _net; -#endif + possible_net_t _net; void * user_ptr[2]; struct sock * dst_sk; }; diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h index 74af137304be..6d539e4e5ba7 100644 --- a/include/net/inet6_connection_sock.h +++ b/include/net/inet6_connection_sock.h @@ -28,8 +28,7 @@ int inet6_csk_bind_conflict(const struct sock *sk, struct dst_entry *inet6_csk_route_req(struct sock *sk, struct flowi6 *fl6, const struct request_sock *req); -struct request_sock *inet6_csk_search_req(const struct sock *sk, - struct request_sock ***prevp, +struct request_sock *inet6_csk_search_req(struct sock *sk, const __be16 rport, const struct in6_addr *raddr, const struct in6_addr *laddr, diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 9201afe083fa..7ff588ca6817 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -38,8 +38,6 @@ static inline unsigned int __inet6_ehashfn(const u32 lhash, return jhash_3words(lhash, fhash, ports, initval); } -int __inet6_hash(struct sock *sk, struct inet_timewait_sock *twp); - /* * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM diff --git a/include/net/inet_common.h b/include/net/inet_common.h index b2828a06a5a6..4a92423eefa5 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -21,12 +21,11 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags); int inet_accept(struct socket *sock, struct socket *newsock, int flags); -int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, - size_t size); +int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size); ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); -int inet_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, - size_t size, int flags); +int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int flags); int inet_shutdown(struct socket *sock, int how); int inet_listen(struct socket *sock, int backlog); void inet_sock_destruct(struct sock *sk); diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 5976bdecf58b..7b5887cd1172 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -126,6 +126,8 @@ struct inet_connection_sock { /* Information on the current probe. */ int probe_size; + + u32 probe_timestamp; } icsk_mtup; u32 icsk_ca_priv[16]; u32 icsk_user_timeout; @@ -254,8 +256,7 @@ inet_csk_rto_backoff(const struct inet_connection_sock *icsk, struct sock *inet_csk_accept(struct sock *sk, int flags, int *err); -struct request_sock *inet_csk_search_req(const struct sock *sk, - struct request_sock ***prevp, +struct request_sock *inet_csk_search_req(struct sock *sk, const __be16 rport, const __be32 raddr, const __be32 laddr); @@ -281,15 +282,13 @@ void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, static inline void inet_csk_reqsk_queue_removed(struct sock *sk, struct request_sock *req) { - if (reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req) == 0) - inet_csk_delete_keepalive_timer(sk); + reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); } static inline void inet_csk_reqsk_queue_added(struct sock *sk, const unsigned long timeout) { - if (reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue) == 0) - inet_csk_reset_keepalive_timer(sk, timeout); + reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue); } static inline int inet_csk_reqsk_queue_len(const struct sock *sk) @@ -308,26 +307,19 @@ static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) } static inline void inet_csk_reqsk_queue_unlink(struct sock *sk, - struct request_sock *req, - struct request_sock **prev) + struct request_sock *req) { - reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req, prev); + reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req); } static inline void inet_csk_reqsk_queue_drop(struct sock *sk, - struct request_sock *req, - struct request_sock **prev) + struct request_sock *req) { - inet_csk_reqsk_queue_unlink(sk, req, prev); + inet_csk_reqsk_queue_unlink(sk, req); inet_csk_reqsk_queue_removed(sk, req); - reqsk_free(req); + reqsk_put(req); } -void inet_csk_reqsk_queue_prune(struct sock *parent, - const unsigned long interval, - const unsigned long timeout, - const unsigned long max_rto); - void inet_csk_destroy_sock(struct sock *sk); void inet_csk_prepare_forced_close(struct sock *sk); diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index dd1950a7e273..73fe0f9525d9 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -76,9 +76,7 @@ struct inet_ehash_bucket { * ports are created in O(1) time? I thought so. ;-) -DaveM */ struct inet_bind_bucket { -#ifdef CONFIG_NET_NS - struct net *ib_net; -#endif + possible_net_t ib_net; unsigned short port; signed char fastreuse; signed char fastreuseport; @@ -223,8 +221,8 @@ inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net, void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket *tb); -static inline int inet_bhashfn(struct net *net, const __u16 lport, - const int bhash_size) +static inline u32 inet_bhashfn(const struct net *net, const __u16 lport, + const u32 bhash_size) { return (lport + net_hash_mix(net)) & (bhash_size - 1); } @@ -233,7 +231,7 @@ void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, const unsigned short snum); /* These can have wildcards, don't try too hard. */ -static inline int inet_lhashfn(struct net *net, const unsigned short num) +static inline u32 inet_lhashfn(const struct net *net, const unsigned short num) { return (num + net_hash_mix(net)) & (INET_LHTABLE_SIZE - 1); } @@ -251,6 +249,7 @@ void inet_put_port(struct sock *sk); void inet_hashinfo_init(struct inet_hashinfo *h); int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw); +int __inet_hash(struct sock *sk, struct inet_timewait_sock *tw); void inet_hash(struct sock *sk); void inet_unhash(struct sock *sk); @@ -385,13 +384,32 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, iph->daddr, dport, inet_iif(skb)); } +u32 sk_ehashfn(const struct sock *sk); +u32 inet6_ehashfn(const struct net *net, + const struct in6_addr *laddr, const u16 lport, + const struct in6_addr *faddr, const __be16 fport); + +static inline void sk_daddr_set(struct sock *sk, __be32 addr) +{ + sk->sk_daddr = addr; /* alias of inet_daddr */ +#if IS_ENABLED(CONFIG_IPV6) + ipv6_addr_set_v4mapped(addr, &sk->sk_v6_daddr); +#endif +} + +static inline void sk_rcv_saddr_set(struct sock *sk, __be32 addr) +{ + sk->sk_rcv_saddr = addr; /* alias of inet_rcv_saddr */ +#if IS_ENABLED(CONFIG_IPV6) + ipv6_addr_set_v4mapped(addr, &sk->sk_v6_rcv_saddr); +#endif +} + int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk, u32 port_offset, int (*check_established)(struct inet_timewait_death_row *, struct sock *, __u16, - struct inet_timewait_sock **), - int (*hash)(struct sock *sk, - struct inet_timewait_sock *twp)); + struct inet_timewait_sock **)); int inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk); diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index eb16c7beed1e..b6c3737da4e9 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -27,6 +27,7 @@ #include <net/sock.h> #include <net/request_sock.h> #include <net/netns/hash.h> +#include <net/tcp_states.h> /** struct ip_options - IP Options * @@ -77,6 +78,10 @@ struct inet_request_sock { #define ir_v6_rmt_addr req.__req_common.skc_v6_daddr #define ir_v6_loc_addr req.__req_common.skc_v6_rcv_saddr #define ir_iif req.__req_common.skc_bound_dev_if +#define ir_cookie req.__req_common.skc_cookie +#define ireq_net req.__req_common.skc_net +#define ireq_state req.__req_common.skc_state +#define ireq_family req.__req_common.skc_family kmemcheck_bitfield_begin(flags); u16 snd_wscale : 4, @@ -88,11 +93,11 @@ struct inet_request_sock { acked : 1, no_srccheck: 1; kmemcheck_bitfield_end(flags); + u32 ir_mark; union { struct ip_options_rcu *opt; struct sk_buff *pktopts; }; - u32 ir_mark; }; static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk) @@ -100,13 +105,12 @@ static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk) return (struct inet_request_sock *)sk; } -static inline u32 inet_request_mark(struct sock *sk, struct sk_buff *skb) +static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb) { - if (!sk->sk_mark && sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept) { + if (!sk->sk_mark && sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept) return skb->mark; - } else { - return sk->sk_mark; - } + + return sk->sk_mark; } struct inet_cork { @@ -239,18 +243,8 @@ static inline unsigned int __inet_ehashfn(const __be32 laddr, initval); } -static inline struct request_sock *inet_reqsk_alloc(struct request_sock_ops *ops) -{ - struct request_sock *req = reqsk_alloc(ops); - struct inet_request_sock *ireq = inet_rsk(req); - - if (req != NULL) { - kmemcheck_annotate_bitfield(ireq, flags); - ireq->opt = NULL; - } - - return req; -} +struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, + struct sock *sk_listener); static inline __u8 inet_sk_flowi_flags(const struct sock *sk) { diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 6c566034e26d..b7ce1003c429 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -122,6 +122,7 @@ struct inet_timewait_sock { #define tw_v6_rcv_saddr __tw_common.skc_v6_rcv_saddr #define tw_dport __tw_common.skc_dport #define tw_num __tw_common.skc_num +#define tw_cookie __tw_common.skc_cookie int tw_timeout; volatile unsigned char tw_substate; diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 5bd120e4bc0a..54271ed0ed45 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -136,7 +136,7 @@ struct fib_result { u32 tclassid; struct fib_info *fi; struct fib_table *table; - struct list_head *fa_head; + struct hlist_head *fa_head; }; struct fib_result_nl { @@ -185,7 +185,9 @@ struct fib_table { u32 tb_id; int tb_default; int tb_num_default; - unsigned long tb_data[0]; + struct rcu_head rcu; + unsigned long *tb_data; + unsigned long __data[0]; }; int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, @@ -195,10 +197,10 @@ int fib_table_delete(struct fib_table *, struct fib_config *); int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb); int fib_table_flush(struct fib_table *table); +struct fib_table *fib_trie_unmerge(struct fib_table *main_tb); +void fib_table_flush_external(struct fib_table *table); void fib_free_table(struct fib_table *tb); - - #ifndef CONFIG_IP_MULTIPLE_TABLES #define TABLE_LOCAL_INDEX (RT_TABLE_LOCAL & (FIB_TABLE_HASHSZ - 1)) @@ -206,12 +208,16 @@ void fib_free_table(struct fib_table *tb); static inline struct fib_table *fib_get_table(struct net *net, u32 id) { + struct hlist_node *tb_hlist; struct hlist_head *ptr; ptr = id == RT_TABLE_LOCAL ? &net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX] : &net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]; - return hlist_entry(ptr->first, struct fib_table, tb_hlist); + + tb_hlist = rcu_dereference_rtnl(hlist_first_rcu(ptr)); + + return hlist_entry(tb_hlist, struct fib_table, tb_hlist); } static inline struct fib_table *fib_new_table(struct net *net, u32 id) @@ -222,14 +228,13 @@ static inline struct fib_table *fib_new_table(struct net *net, u32 id) static inline int fib_lookup(struct net *net, const struct flowi4 *flp, struct fib_result *res) { + struct fib_table *tb; int err = -ENETUNREACH; rcu_read_lock(); - if (!fib_table_lookup(fib_get_table(net, RT_TABLE_LOCAL), flp, res, - FIB_LOOKUP_NOREF) || - !fib_table_lookup(fib_get_table(net, RT_TABLE_MAIN), flp, res, - FIB_LOOKUP_NOREF)) + tb = fib_get_table(net, RT_TABLE_MAIN); + if (tb && !fib_table_lookup(tb, flp, res, FIB_LOOKUP_NOREF)) err = 0; rcu_read_unlock(); @@ -249,28 +254,29 @@ int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res); static inline int fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res) { - if (!net->ipv4.fib_has_custom_rules) { - int err = -ENETUNREACH; - - rcu_read_lock(); - - res->tclassid = 0; - if ((net->ipv4.fib_local && - !fib_table_lookup(net->ipv4.fib_local, flp, res, - FIB_LOOKUP_NOREF)) || - (net->ipv4.fib_main && - !fib_table_lookup(net->ipv4.fib_main, flp, res, - FIB_LOOKUP_NOREF)) || - (net->ipv4.fib_default && - !fib_table_lookup(net->ipv4.fib_default, flp, res, - FIB_LOOKUP_NOREF))) - err = 0; - - rcu_read_unlock(); - - return err; + struct fib_table *tb; + int err; + + if (net->ipv4.fib_has_custom_rules) + return __fib_lookup(net, flp, res); + + rcu_read_lock(); + + res->tclassid = 0; + + for (err = 0; !err; err = -ENETUNREACH) { + tb = rcu_dereference_rtnl(net->ipv4.fib_main); + if (tb && !fib_table_lookup(tb, flp, res, FIB_LOOKUP_NOREF)) + break; + + tb = rcu_dereference_rtnl(net->ipv4.fib_default); + if (tb && !fib_table_lookup(tb, flp, res, FIB_LOOKUP_NOREF)) + break; } - return __fib_lookup(net, flp, res); + + rcu_read_unlock(); + + return err; } #endif /* CONFIG_IP_MULTIPLE_TABLES */ @@ -294,6 +300,8 @@ static inline int fib_num_tclassid_users(struct net *net) return 0; } #endif +int fib_unmerge(struct net *net); +void fib_flush_external(struct net *net); /* Exported by fib_semantics.c */ int ip_fib_check_default(__be32 gw, struct net_device *dev); @@ -304,7 +312,7 @@ void fib_select_multipath(struct fib_result *res); /* Exported by fib_trie.c */ void fib_trie_init(void); -struct fib_table *fib_trie_table(u32 id); +struct fib_table *fib_trie_table(u32 id, struct fib_table *alias); static inline void fib_combine_itag(u32 *itag, const struct fib_result *res) { diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 615b20b58545..4e3731ee4eac 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -47,13 +47,13 @@ static inline struct net *skb_net(const struct sk_buff *skb) * Start with the most likely hit * End with BUG */ - if (likely(skb->dev && skb->dev->nd_net)) + if (likely(skb->dev && dev_net(skb->dev))) return dev_net(skb->dev); if (skb_dst(skb) && skb_dst(skb)->dev) return dev_net(skb_dst(skb)->dev); WARN(skb->sk, "Maybe skb_sknet should be used in %s() at line:%d\n", __func__, __LINE__); - if (likely(skb->sk && skb->sk->sk_net)) + if (likely(skb->sk && sock_net(skb->sk))) return sock_net(skb->sk); pr_err("There is no net ptr to find in the skb in %s() line:%d\n", __func__, __LINE__); @@ -71,11 +71,11 @@ static inline struct net *skb_sknet(const struct sk_buff *skb) #ifdef CONFIG_NET_NS #ifdef CONFIG_IP_VS_DEBUG /* Start with the most likely hit */ - if (likely(skb->sk && skb->sk->sk_net)) + if (likely(skb->sk && sock_net(skb->sk))) return sock_net(skb->sk); WARN(skb->dev, "Maybe skb_net should be used instead in %s() line:%d\n", __func__, __LINE__); - if (likely(skb->dev && skb->dev->nd_net)) + if (likely(skb->dev && dev_net(skb->dev))) return dev_net(skb->dev); pr_err("There is no net ptr to find in the skb in %s() line:%d\n", __func__, __LINE__); @@ -365,15 +365,15 @@ struct ip_vs_seq { /* counters per cpu */ struct ip_vs_counters { - __u32 conns; /* connections scheduled */ - __u32 inpkts; /* incoming packets */ - __u32 outpkts; /* outgoing packets */ + __u64 conns; /* connections scheduled */ + __u64 inpkts; /* incoming packets */ + __u64 outpkts; /* outgoing packets */ __u64 inbytes; /* incoming bytes */ __u64 outbytes; /* outgoing bytes */ }; /* Stats per cpu */ struct ip_vs_cpu_stats { - struct ip_vs_counters ustats; + struct ip_vs_counters cnt; struct u64_stats_sync syncp; }; @@ -383,23 +383,40 @@ struct ip_vs_estimator { u64 last_inbytes; u64 last_outbytes; - u32 last_conns; - u32 last_inpkts; - u32 last_outpkts; - - u32 cps; - u32 inpps; - u32 outpps; - u32 inbps; - u32 outbps; + u64 last_conns; + u64 last_inpkts; + u64 last_outpkts; + + u64 cps; + u64 inpps; + u64 outpps; + u64 inbps; + u64 outbps; +}; + +/* + * IPVS statistics object, 64-bit kernel version of struct ip_vs_stats_user + */ +struct ip_vs_kstats { + u64 conns; /* connections scheduled */ + u64 inpkts; /* incoming packets */ + u64 outpkts; /* outgoing packets */ + u64 inbytes; /* incoming bytes */ + u64 outbytes; /* outgoing bytes */ + + u64 cps; /* current connection rate */ + u64 inpps; /* current in packet rate */ + u64 outpps; /* current out packet rate */ + u64 inbps; /* current in byte rate */ + u64 outbps; /* current out byte rate */ }; struct ip_vs_stats { - struct ip_vs_stats_user ustats; /* statistics */ + struct ip_vs_kstats kstats; /* kernel statistics */ struct ip_vs_estimator est; /* estimator */ struct ip_vs_cpu_stats __percpu *cpustats; /* per cpu counters */ spinlock_t lock; /* spin lock */ - struct ip_vs_stats_user ustats0; /* reset values */ + struct ip_vs_kstats kstats0; /* reset values */ }; struct dst_entry; @@ -924,6 +941,7 @@ struct netns_ipvs { int sysctl_nat_icmp_send; int sysctl_pmtu_disc; int sysctl_backup_only; + int sysctl_conn_reuse_mode; /* ip_vs_lblc */ int sysctl_lblc_expiration; @@ -1042,6 +1060,11 @@ static inline int sysctl_backup_only(struct netns_ipvs *ipvs) ipvs->sysctl_backup_only; } +static inline int sysctl_conn_reuse_mode(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_conn_reuse_mode; +} + #else static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs) @@ -1109,6 +1132,11 @@ static inline int sysctl_backup_only(struct netns_ipvs *ipvs) return 0; } +static inline int sysctl_conn_reuse_mode(struct netns_ipvs *ipvs) +{ + return 1; +} + #endif /* IPVS core functions @@ -1388,8 +1416,7 @@ void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts); void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats); void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats); void ip_vs_zero_estimator(struct ip_vs_stats *stats); -void ip_vs_read_estimator(struct ip_vs_stats_user *dst, - struct ip_vs_stats *stats); +void ip_vs_read_estimator(struct ip_vs_kstats *dst, struct ip_vs_stats *stats); /* Various IPVS packet transmitters (from ip_vs_xmit.c) */ int ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 4c9fe224d73b..e7ba9758a345 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -940,4 +940,8 @@ int ipv6_sysctl_register(void); void ipv6_sysctl_unregister(void); #endif +int ipv6_sock_mc_join(struct sock *sk, int ifindex, + const struct in6_addr *addr); +int ipv6_sock_mc_drop(struct sock *sk, int ifindex, + const struct in6_addr *addr); #endif /* _NET_IPV6_H */ diff --git a/include/net/mac802154.h b/include/net/mac802154.h index 850647811749..fb4e8a3d6229 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -19,6 +19,7 @@ #include <net/af_ieee802154.h> #include <linux/ieee802154.h> #include <linux/skbuff.h> +#include <linux/unaligned/memmove.h> #include <net/cfg802154.h> @@ -233,9 +234,7 @@ struct ieee802154_ops { */ static inline void ieee802154_be64_to_le64(void *le64_dst, const void *be64_src) { - __le64 tmp = (__force __le64)swab64p(be64_src); - - memcpy(le64_dst, &tmp, IEEE802154_EXTENDED_ADDR_LEN); + __put_unaligned_memmove64(swab64p(be64_src), le64_dst); } /** @@ -245,9 +244,7 @@ static inline void ieee802154_be64_to_le64(void *le64_dst, const void *be64_src) */ static inline void ieee802154_le64_to_be64(void *be64_dst, const void *le64_src) { - __be64 tmp = (__force __be64)swab64p(le64_src); - - memcpy(be64_dst, &tmp, IEEE802154_EXTENDED_ADDR_LEN); + __put_unaligned_memmove64(swab64p(le64_src), be64_dst); } /* Basic interface to register ieee802154 hwice */ diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 6bbda34d5e59..b3a7751251b4 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -156,24 +156,7 @@ static inline u32 ndisc_hashfn(const void *pkey, const struct net_device *dev, _ static inline struct neighbour *__ipv6_neigh_lookup_noref(struct net_device *dev, const void *pkey) { - struct neigh_hash_table *nht; - const u32 *p32 = pkey; - struct neighbour *n; - u32 hash_val; - - nht = rcu_dereference_bh(nd_tbl.nht); - hash_val = ndisc_hashfn(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); - for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); - n != NULL; - n = rcu_dereference_bh(n->next)) { - u32 *n32 = (u32 *) n->primary_key; - if (n->dev == dev && - ((n32[0] ^ p32[0]) | (n32[1] ^ p32[1]) | - (n32[2] ^ p32[2]) | (n32[3] ^ p32[3])) == 0) - return n; - } - - return NULL; + return ___neigh_lookup_noref(&nd_tbl, neigh_key_eq128, ndisc_hashfn, pkey, dev); } static inline struct neighbour *__ipv6_neigh_lookup(struct net_device *dev, const void *pkey) diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 76f708486aae..e7bdf5170802 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -65,9 +65,7 @@ enum { }; struct neigh_parms { -#ifdef CONFIG_NET_NS - struct net *net; -#endif + possible_net_t net; struct net_device *dev; struct list_head list; int (*neigh_setup)(struct neighbour *); @@ -167,9 +165,7 @@ struct neigh_ops { struct pneigh_entry { struct pneigh_entry *next; -#ifdef CONFIG_NET_NS - struct net *net; -#endif + possible_net_t net; struct net_device *dev; u8 flags; u8 key[0]; @@ -193,9 +189,11 @@ struct neigh_table { int family; int entry_size; int key_len; + __be16 protocol; __u32 (*hash)(const void *pkey, const struct net_device *dev, __u32 *hash_rnd); + bool (*key_eq)(const struct neighbour *, const void *pkey); int (*constructor)(struct neighbour *); int (*pconstructor)(struct pneigh_entry *); void (*pdestructor)(struct pneigh_entry *); @@ -224,6 +222,7 @@ enum { NEIGH_ND_TABLE = 1, NEIGH_DN_TABLE = 2, NEIGH_NR_TABLES, + NEIGH_LINK_TABLE = NEIGH_NR_TABLES /* Pseudo table for neigh_xmit */ }; static inline int neigh_parms_family(struct neigh_parms *p) @@ -246,6 +245,57 @@ static inline void *neighbour_priv(const struct neighbour *n) #define NEIGH_UPDATE_F_ISROUTER 0x40000000 #define NEIGH_UPDATE_F_ADMIN 0x80000000 + +static inline bool neigh_key_eq16(const struct neighbour *n, const void *pkey) +{ + return *(const u16 *)n->primary_key == *(const u16 *)pkey; +} + +static inline bool neigh_key_eq32(const struct neighbour *n, const void *pkey) +{ + return *(const u32 *)n->primary_key == *(const u32 *)pkey; +} + +static inline bool neigh_key_eq128(const struct neighbour *n, const void *pkey) +{ + const u32 *n32 = (const u32 *)n->primary_key; + const u32 *p32 = pkey; + + return ((n32[0] ^ p32[0]) | (n32[1] ^ p32[1]) | + (n32[2] ^ p32[2]) | (n32[3] ^ p32[3])) == 0; +} + +static inline struct neighbour *___neigh_lookup_noref( + struct neigh_table *tbl, + bool (*key_eq)(const struct neighbour *n, const void *pkey), + __u32 (*hash)(const void *pkey, + const struct net_device *dev, + __u32 *hash_rnd), + const void *pkey, + struct net_device *dev) +{ + struct neigh_hash_table *nht = rcu_dereference_bh(tbl->nht); + struct neighbour *n; + u32 hash_val; + + hash_val = hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); + for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); + n != NULL; + n = rcu_dereference_bh(n->next)) { + if (n->dev == dev && key_eq(n, pkey)) + return n; + } + + return NULL; +} + +static inline struct neighbour *__neigh_lookup_noref(struct neigh_table *tbl, + const void *pkey, + struct net_device *dev) +{ + return ___neigh_lookup_noref(tbl, tbl->key_eq, tbl->hash, pkey, dev); +} + void neigh_table_init(int index, struct neigh_table *tbl); int neigh_table_clear(int index, struct neigh_table *tbl); struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, @@ -268,7 +318,6 @@ void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev); int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev); int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb); int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb); -int neigh_compat_output(struct neighbour *neigh, struct sk_buff *skb); int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb); struct neighbour *neigh_event_ns(struct neigh_table *tbl, u8 *lladdr, void *saddr, @@ -306,6 +355,7 @@ void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void *), void *cookie); void __neigh_for_each_release(struct neigh_table *tbl, int (*cb)(struct neighbour *)); +int neigh_xmit(int fam, struct net_device *, const void *, struct sk_buff *); void pneigh_for_each(struct neigh_table *tbl, void (*cb)(struct pneigh_entry *)); @@ -459,4 +509,6 @@ static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n, memcpy(dst, n->ha, dev->addr_len); } while (read_seqretry(&n->ha_lock, seq)); } + + #endif diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 36faf4990c4b..f733656404de 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -26,6 +26,7 @@ #endif #include <net/netns/nftables.h> #include <net/netns/xfrm.h> +#include <net/netns/mpls.h> #include <linux/ns_common.h> struct user_namespace; @@ -48,13 +49,10 @@ struct net { atomic_t count; /* To decided when the network * namespace should be shut down. */ -#ifdef NETNS_REFCNT_DEBUG - atomic_t use_count; /* To track references we - * destroy on demand - */ -#endif spinlock_t rules_mod_lock; + atomic64_t cookie_gen; + struct list_head list; /* list of network namespaces */ struct list_head cleanup_list; /* namespaces on death row */ struct list_head exit_list; /* Use only net_mutex */ @@ -130,6 +128,9 @@ struct net { #if IS_ENABLED(CONFIG_IP_VS) struct netns_ipvs *ipvs; #endif +#if IS_ENABLED(CONFIG_MPLS) + struct netns_mpls mpls; +#endif struct sock *diag_nlsk; atomic_t fnhe_genid; }; @@ -230,48 +231,27 @@ int net_eq(const struct net *net1, const struct net *net2) #endif -#ifdef NETNS_REFCNT_DEBUG -static inline struct net *hold_net(struct net *net) -{ - if (net) - atomic_inc(&net->use_count); - return net; -} - -static inline void release_net(struct net *net) -{ - if (net) - atomic_dec(&net->use_count); -} -#else -static inline struct net *hold_net(struct net *net) -{ - return net; -} - -static inline void release_net(struct net *net) -{ -} -#endif - +typedef struct { #ifdef CONFIG_NET_NS + struct net *net; +#endif +} possible_net_t; -static inline void write_pnet(struct net **pnet, struct net *net) +static inline void write_pnet(possible_net_t *pnet, struct net *net) { - *pnet = net; +#ifdef CONFIG_NET_NS + pnet->net = net; +#endif } -static inline struct net *read_pnet(struct net * const *pnet) +static inline struct net *read_pnet(const possible_net_t *pnet) { - return *pnet; -} - +#ifdef CONFIG_NET_NS + return pnet->net; #else - -#define write_pnet(pnet, net) do { (void)(net);} while (0) -#define read_pnet(pnet) (&init_net) - + return &init_net; #endif +} #define for_each_net(VAR) \ list_for_each_entry(VAR, &net_namespace_list, list) diff --git a/include/net/netfilter/ipv4/nf_reject.h b/include/net/netfilter/ipv4/nf_reject.h index 03e928a55229..77862c3645f0 100644 --- a/include/net/netfilter/ipv4/nf_reject.h +++ b/include/net/netfilter/ipv4/nf_reject.h @@ -5,18 +5,14 @@ #include <net/ip.h> #include <net/icmp.h> -static inline void nf_send_unreach(struct sk_buff *skb_in, int code) -{ - icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0); -} - +void nf_send_unreach(struct sk_buff *skb_in, int code, int hook); void nf_send_reset(struct sk_buff *oldskb, int hook); const struct tcphdr *nf_reject_ip_tcphdr_get(struct sk_buff *oldskb, struct tcphdr *_oth, int hook); struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, - __be16 protocol, int ttl); + __u8 protocol, int ttl); void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, const struct tcphdr *oth); diff --git a/include/net/netfilter/ipv6/nf_reject.h b/include/net/netfilter/ipv6/nf_reject.h index 23216d48abf9..0ea4fa37db16 100644 --- a/include/net/netfilter/ipv6/nf_reject.h +++ b/include/net/netfilter/ipv6/nf_reject.h @@ -3,15 +3,8 @@ #include <linux/icmpv6.h> -static inline void -nf_send_unreach6(struct net *net, struct sk_buff *skb_in, unsigned char code, - unsigned int hooknum) -{ - if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL) - skb_in->dev = net->loopback_dev; - - icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0); -} +void nf_send_unreach6(struct net *net, struct sk_buff *skb_in, unsigned char code, + unsigned int hooknum); void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook); @@ -20,7 +13,7 @@ const struct tcphdr *nf_reject_ip6_tcphdr_get(struct sk_buff *oldskb, unsigned int *otcplen, int hook); struct ipv6hdr *nf_reject_ip6hdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, - __be16 protocol, int hoplimit); + __u8 protocol, int hoplimit); void nf_reject_ip6_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, const struct tcphdr *oth, unsigned int otcplen); diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 74f271a172dd..095433b8a8b0 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -95,9 +95,8 @@ struct nf_conn { /* Timer function; drops refcnt when it goes off. */ struct timer_list timeout; -#ifdef CONFIG_NET_NS - struct net *ct_net; -#endif + possible_net_t ct_net; + /* all members below initialized via memset */ u8 __nfct_init_offset[0]; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index decb9a095ae7..d756af559977 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -409,74 +409,6 @@ struct nft_rule { __attribute__((aligned(__alignof__(struct nft_expr)))); }; -/** - * struct nft_trans - nf_tables object update in transaction - * - * @list: used internally - * @msg_type: message type - * @ctx: transaction context - * @data: internal information related to the transaction - */ -struct nft_trans { - struct list_head list; - int msg_type; - struct nft_ctx ctx; - char data[0]; -}; - -struct nft_trans_rule { - struct nft_rule *rule; -}; - -#define nft_trans_rule(trans) \ - (((struct nft_trans_rule *)trans->data)->rule) - -struct nft_trans_set { - struct nft_set *set; - u32 set_id; -}; - -#define nft_trans_set(trans) \ - (((struct nft_trans_set *)trans->data)->set) -#define nft_trans_set_id(trans) \ - (((struct nft_trans_set *)trans->data)->set_id) - -struct nft_trans_chain { - bool update; - char name[NFT_CHAIN_MAXNAMELEN]; - struct nft_stats __percpu *stats; - u8 policy; -}; - -#define nft_trans_chain_update(trans) \ - (((struct nft_trans_chain *)trans->data)->update) -#define nft_trans_chain_name(trans) \ - (((struct nft_trans_chain *)trans->data)->name) -#define nft_trans_chain_stats(trans) \ - (((struct nft_trans_chain *)trans->data)->stats) -#define nft_trans_chain_policy(trans) \ - (((struct nft_trans_chain *)trans->data)->policy) - -struct nft_trans_table { - bool update; - bool enable; -}; - -#define nft_trans_table_update(trans) \ - (((struct nft_trans_table *)trans->data)->update) -#define nft_trans_table_enable(trans) \ - (((struct nft_trans_table *)trans->data)->enable) - -struct nft_trans_elem { - struct nft_set *set; - struct nft_set_elem elem; -}; - -#define nft_trans_elem_set(trans) \ - (((struct nft_trans_elem *)trans->data)->set) -#define nft_trans_elem(trans) \ - (((struct nft_trans_elem *)trans->data)->elem) - static inline struct nft_expr *nft_expr_first(const struct nft_rule *rule) { return (struct nft_expr *)&rule->data[0]; @@ -544,6 +476,25 @@ enum nft_chain_type { NFT_CHAIN_T_MAX }; +/** + * struct nf_chain_type - nf_tables chain type info + * + * @name: name of the type + * @type: numeric identifier + * @family: address family + * @owner: module owner + * @hook_mask: mask of valid hooks + * @hooks: hookfn overrides + */ +struct nf_chain_type { + const char *name; + enum nft_chain_type type; + int family; + struct module *owner; + unsigned int hook_mask; + nf_hookfn *hooks[NF_MAX_HOOKS]; +}; + int nft_chain_validate_dependency(const struct nft_chain *chain, enum nft_chain_type type); int nft_chain_validate_hooks(const struct nft_chain *chain, @@ -600,7 +551,7 @@ struct nft_table { u64 hgenerator; u32 use; u16 flags; - char name[]; + char name[NFT_TABLE_MAXNAMELEN]; }; /** @@ -630,25 +581,6 @@ struct nft_af_info { int nft_register_afinfo(struct net *, struct nft_af_info *); void nft_unregister_afinfo(struct nft_af_info *); -/** - * struct nf_chain_type - nf_tables chain type info - * - * @name: name of the type - * @type: numeric identifier - * @family: address family - * @owner: module owner - * @hook_mask: mask of valid hooks - * @hooks: hookfn overrides - */ -struct nf_chain_type { - const char *name; - enum nft_chain_type type; - int family; - struct module *owner; - unsigned int hook_mask; - nf_hookfn *hooks[NF_MAX_HOOKS]; -}; - int nft_register_chain_type(const struct nf_chain_type *); void nft_unregister_chain_type(const struct nf_chain_type *); @@ -673,4 +605,72 @@ void nft_unregister_expr(struct nft_expr_type *); #define MODULE_ALIAS_NFT_SET() \ MODULE_ALIAS("nft-set") +/** + * struct nft_trans - nf_tables object update in transaction + * + * @list: used internally + * @msg_type: message type + * @ctx: transaction context + * @data: internal information related to the transaction + */ +struct nft_trans { + struct list_head list; + int msg_type; + struct nft_ctx ctx; + char data[0]; +}; + +struct nft_trans_rule { + struct nft_rule *rule; +}; + +#define nft_trans_rule(trans) \ + (((struct nft_trans_rule *)trans->data)->rule) + +struct nft_trans_set { + struct nft_set *set; + u32 set_id; +}; + +#define nft_trans_set(trans) \ + (((struct nft_trans_set *)trans->data)->set) +#define nft_trans_set_id(trans) \ + (((struct nft_trans_set *)trans->data)->set_id) + +struct nft_trans_chain { + bool update; + char name[NFT_CHAIN_MAXNAMELEN]; + struct nft_stats __percpu *stats; + u8 policy; +}; + +#define nft_trans_chain_update(trans) \ + (((struct nft_trans_chain *)trans->data)->update) +#define nft_trans_chain_name(trans) \ + (((struct nft_trans_chain *)trans->data)->name) +#define nft_trans_chain_stats(trans) \ + (((struct nft_trans_chain *)trans->data)->stats) +#define nft_trans_chain_policy(trans) \ + (((struct nft_trans_chain *)trans->data)->policy) + +struct nft_trans_table { + bool update; + bool enable; +}; + +#define nft_trans_table_update(trans) \ + (((struct nft_trans_table *)trans->data)->update) +#define nft_trans_table_enable(trans) \ + (((struct nft_trans_table *)trans->data)->enable) + +struct nft_trans_elem { + struct nft_set *set; + struct nft_set_elem elem; +}; + +#define nft_trans_elem_set(trans) \ + (((struct nft_trans_elem *)trans->data)->set) +#define nft_trans_elem(trans) \ + (((struct nft_trans_elem *)trans->data)->elem) + #endif /* _NET_NF_TABLES_H */ diff --git a/include/net/netns/hash.h b/include/net/netns/hash.h index c06ac58ca107..69a6715d9f3f 100644 --- a/include/net/netns/hash.h +++ b/include/net/netns/hash.h @@ -5,7 +5,7 @@ struct net; -static inline unsigned int net_hash_mix(struct net *net) +static inline u32 net_hash_mix(const struct net *net) { #ifdef CONFIG_NET_NS /* @@ -13,7 +13,7 @@ static inline unsigned int net_hash_mix(struct net *net) * always zeroed */ - return (unsigned)(((unsigned long)net) >> L1_CACHE_SHIFT); + return (u32)(((unsigned long)net) >> L1_CACHE_SHIFT); #else return 0; #endif diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index dbe225478adb..614a49be68a9 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -7,6 +7,7 @@ #include <linux/uidgid.h> #include <net/inet_frag.h> +#include <linux/rcupdate.h> struct tcpm_hash_bucket; struct ctl_table_header; @@ -38,21 +39,21 @@ struct netns_ipv4 { #ifdef CONFIG_IP_MULTIPLE_TABLES struct fib_rules_ops *rules_ops; bool fib_has_custom_rules; - struct fib_table *fib_local; - struct fib_table *fib_main; - struct fib_table *fib_default; + struct fib_table __rcu *fib_local; + struct fib_table __rcu *fib_main; + struct fib_table __rcu *fib_default; #endif #ifdef CONFIG_IP_ROUTE_CLASSID int fib_num_tclassid_users; #endif struct hlist_head *fib_table_hash; + bool fib_offload_disabled; struct sock *fibnl; struct sock * __percpu *icmp_sk; + struct sock *mc_autojoin_sk; struct inet_peer_base *peers; - struct tcpm_hash_bucket *tcp_metrics_hash; - unsigned int tcp_metrics_hash_log; struct sock * __percpu *tcp_sk; struct netns_frags frags; #ifdef CONFIG_NETFILTER @@ -84,6 +85,8 @@ struct netns_ipv4 { int sysctl_tcp_fwmark_accept; int sysctl_tcp_mtu_probing; int sysctl_tcp_base_mss; + int sysctl_tcp_probe_threshold; + u32 sysctl_tcp_probe_interval; struct ping_group_range ping_group_range; diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 69ae41f2098c..ca0db12cd089 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -67,6 +67,7 @@ struct netns_ipv6 { struct sock *ndisc_sk; struct sock *tcp_sk; struct sock *igmp_sk; + struct sock *mc_autojoin_sk; #ifdef CONFIG_IPV6_MROUTE #ifndef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES struct mr6_table *mrt6; diff --git a/include/net/netns/mpls.h b/include/net/netns/mpls.h new file mode 100644 index 000000000000..d29203651c01 --- /dev/null +++ b/include/net/netns/mpls.h @@ -0,0 +1,17 @@ +/* + * mpls in net namespaces + */ + +#ifndef __NETNS_MPLS_H__ +#define __NETNS_MPLS_H__ + +struct mpls_route; +struct ctl_table_header; + +struct netns_mpls { + size_t platform_labels; + struct mpls_route __rcu * __rcu *platform_label; + struct ctl_table_header *ctl; +}; + +#endif /* __NETNS_MPLS_H__ */ diff --git a/include/net/netns/x_tables.h b/include/net/netns/x_tables.h index c24060ee411e..4d6597ad6067 100644 --- a/include/net/netns/x_tables.h +++ b/include/net/netns/x_tables.h @@ -9,6 +9,7 @@ struct ebt_table; struct netns_xt { struct list_head tables[NFPROTO_NUMPROTO]; bool notrack_deprecated_warning; + bool clusterip_deprecated_warning; #if defined(CONFIG_BRIDGE_NF_EBTABLES) || \ defined(CONFIG_BRIDGE_NF_EBTABLES_MODULE) struct ebt_table *broute_table; diff --git a/include/net/ping.h b/include/net/ping.h index cc16d413f681..ac80cb45e630 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -75,12 +75,11 @@ void ping_err(struct sk_buff *skb, int offset, u32 info); int ping_getfrag(void *from, char *to, int offset, int fraglen, int odd, struct sk_buff *); -int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len, int noblock, int flags, int *addr_len); +int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, + int flags, int *addr_len); int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, void *user_icmph, size_t icmph_len); -int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len); +int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); bool ping_rcv(struct sk_buff *skb); diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 7f830ff67f08..6a91261d9b7b 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -49,7 +49,11 @@ int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req); */ struct request_sock { struct sock_common __req_common; +#define rsk_refcnt __req_common.skc_refcnt +#define rsk_hash __req_common.skc_hash + struct request_sock *dl_next; + struct sock *rsk_listener; u16 mss; u8 num_retrans; /* number of retransmits */ u8 cookie_ts:1; /* syncookie: encode tcpopts in timestamp */ @@ -58,32 +62,56 @@ struct request_sock { u32 window_clamp; /* window clamp at creation time */ u32 rcv_wnd; /* rcv_wnd offered first time */ u32 ts_recent; - unsigned long expires; + struct timer_list rsk_timer; const struct request_sock_ops *rsk_ops; struct sock *sk; u32 secid; u32 peer_secid; }; -static inline struct request_sock *reqsk_alloc(const struct request_sock_ops *ops) +static inline struct request_sock * +reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) { struct request_sock *req = kmem_cache_alloc(ops->slab, GFP_ATOMIC); - if (req != NULL) + if (req) { req->rsk_ops = ops; - + sock_hold(sk_listener); + req->rsk_listener = sk_listener; + + /* Following is temporary. It is coupled with debugging + * helpers in reqsk_put() & reqsk_free() + */ + atomic_set(&req->rsk_refcnt, 0); + } return req; } -static inline void __reqsk_free(struct request_sock *req) +static inline struct request_sock *inet_reqsk(struct sock *sk) { - kmem_cache_free(req->rsk_ops->slab, req); + return (struct request_sock *)sk; +} + +static inline struct sock *req_to_sk(struct request_sock *req) +{ + return (struct sock *)req; } static inline void reqsk_free(struct request_sock *req) { + /* temporary debugging */ + WARN_ON_ONCE(atomic_read(&req->rsk_refcnt) != 0); + req->rsk_ops->destructor(req); - __reqsk_free(req); + if (req->rsk_listener) + sock_put(req->rsk_listener); + kmem_cache_free(req->rsk_ops->slab, req); +} + +static inline void reqsk_put(struct request_sock *req) +{ + if (atomic_dec_and_test(&req->rsk_refcnt)) + reqsk_free(req); } extern int sysctl_max_syn_backlog; @@ -93,12 +121,16 @@ extern int sysctl_max_syn_backlog; * @max_qlen_log - log_2 of maximal queued SYNs/REQUESTs */ struct listen_sock { - u8 max_qlen_log; + int qlen_inc; /* protected by listener lock */ + int young_inc;/* protected by listener lock */ + + /* following fields can be updated by timer */ + atomic_t qlen_dec; /* qlen = qlen_inc - qlen_dec */ + atomic_t young_dec; + + u8 max_qlen_log ____cacheline_aligned_in_smp; u8 synflood_warned; /* 2 bytes hole, try to use */ - int qlen; - int qlen_young; - int clock_hand; u32 hash_rnd; u32 nr_table_entries; struct request_sock *syn_table[0]; @@ -151,9 +183,7 @@ struct fastopen_queue { struct request_sock_queue { struct request_sock *rskq_accept_head; struct request_sock *rskq_accept_tail; - rwlock_t syn_wait_lock; u8 rskq_defer_accept; - /* 3 bytes hole, try to pack */ struct listen_sock *listen_opt; struct fastopen_queue *fastopenq; /* This is non-NULL iff TFO has been * enabled on this listener. Check @@ -161,6 +191,9 @@ struct request_sock_queue { * to determine if TFO is enabled * right at this moment. */ + + /* temporary alignment, our goal is to get rid of this lock */ + rwlock_t syn_wait_lock ____cacheline_aligned_in_smp; }; int reqsk_queue_alloc(struct request_sock_queue *queue, @@ -186,12 +219,21 @@ static inline int reqsk_queue_empty(struct request_sock_queue *queue) } static inline void reqsk_queue_unlink(struct request_sock_queue *queue, - struct request_sock *req, - struct request_sock **prev_req) + struct request_sock *req) { + struct listen_sock *lopt = queue->listen_opt; + struct request_sock **prev; + write_lock(&queue->syn_wait_lock); - *prev_req = req->dl_next; + + prev = &lopt->syn_table[req->rsk_hash]; + while (*prev != req) + prev = &(*prev)->dl_next; + *prev = req->dl_next; + write_unlock(&queue->syn_wait_lock); + if (del_timer(&req->rsk_timer)) + reqsk_put(req); } static inline void reqsk_queue_add(struct request_sock_queue *queue, @@ -224,57 +266,53 @@ static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue return req; } -static inline int reqsk_queue_removed(struct request_sock_queue *queue, - struct request_sock *req) +static inline void reqsk_queue_removed(struct request_sock_queue *queue, + const struct request_sock *req) { struct listen_sock *lopt = queue->listen_opt; if (req->num_timeout == 0) - --lopt->qlen_young; - - return --lopt->qlen; + atomic_inc(&lopt->young_dec); + atomic_inc(&lopt->qlen_dec); } -static inline int reqsk_queue_added(struct request_sock_queue *queue) +static inline void reqsk_queue_added(struct request_sock_queue *queue) { struct listen_sock *lopt = queue->listen_opt; - const int prev_qlen = lopt->qlen; - lopt->qlen_young++; - lopt->qlen++; - return prev_qlen; + lopt->young_inc++; + lopt->qlen_inc++; } -static inline int reqsk_queue_len(const struct request_sock_queue *queue) +static inline int listen_sock_qlen(const struct listen_sock *lopt) { - return queue->listen_opt != NULL ? queue->listen_opt->qlen : 0; + return lopt->qlen_inc - atomic_read(&lopt->qlen_dec); } -static inline int reqsk_queue_len_young(const struct request_sock_queue *queue) +static inline int listen_sock_young(const struct listen_sock *lopt) { - return queue->listen_opt->qlen_young; + return lopt->young_inc - atomic_read(&lopt->young_dec); } -static inline int reqsk_queue_is_full(const struct request_sock_queue *queue) +static inline int reqsk_queue_len(const struct request_sock_queue *queue) { - return queue->listen_opt->qlen >> queue->listen_opt->max_qlen_log; + const struct listen_sock *lopt = queue->listen_opt; + + return lopt ? listen_sock_qlen(lopt) : 0; } -static inline void reqsk_queue_hash_req(struct request_sock_queue *queue, - u32 hash, struct request_sock *req, - unsigned long timeout) +static inline int reqsk_queue_len_young(const struct request_sock_queue *queue) { - struct listen_sock *lopt = queue->listen_opt; - - req->expires = jiffies + timeout; - req->num_retrans = 0; - req->num_timeout = 0; - req->sk = NULL; - req->dl_next = lopt->syn_table[hash]; + return listen_sock_young(queue->listen_opt); +} - write_lock(&queue->syn_wait_lock); - lopt->syn_table[hash] = req; - write_unlock(&queue->syn_wait_lock); +static inline int reqsk_queue_is_full(const struct request_sock_queue *queue) +{ + return reqsk_queue_len(queue) >> queue->listen_opt->max_qlen_log; } +void reqsk_queue_hash_req(struct request_sock_queue *queue, + u32 hash, struct request_sock *req, + unsigned long timeout); + #endif /* _REQUEST_SOCK_H */ diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index c605d305c577..6d778efcfdfd 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -213,7 +213,7 @@ struct tcf_proto_ops { const struct tcf_proto *, struct tcf_result *); int (*init)(struct tcf_proto*); - void (*destroy)(struct tcf_proto*); + bool (*destroy)(struct tcf_proto*, bool); unsigned long (*get)(struct tcf_proto*, u32 handle); int (*change)(struct net *net, struct sk_buff *, @@ -399,7 +399,7 @@ struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, u32 parentid); void __qdisc_calculate_pkt_len(struct sk_buff *skb, const struct qdisc_size_table *stab); -void tcf_destroy(struct tcf_proto *tp); +bool tcf_destroy(struct tcf_proto *tp, bool force); void tcf_destroy_chain(struct tcf_proto __rcu **fl); /* Reset all TX qdiscs greater then index of a device. */ diff --git a/include/net/sock.h b/include/net/sock.h index ab186b1d31ff..3f9b8ce56948 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -67,6 +67,7 @@ #include <linux/atomic.h> #include <net/dst.h> #include <net/checksum.h> +#include <net/tcp_states.h> #include <linux/net_tstamp.h> struct cgroup; @@ -190,15 +191,15 @@ struct sock_common { struct hlist_nulls_node skc_portaddr_node; }; struct proto *skc_prot; -#ifdef CONFIG_NET_NS - struct net *skc_net; -#endif + possible_net_t skc_net; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr skc_v6_daddr; struct in6_addr skc_v6_rcv_saddr; #endif + atomic64_t skc_cookie; + /* * fields between dontcopy_begin/dontcopy_end * are not copied in sock_copy() @@ -329,6 +330,7 @@ struct sock { #define sk_net __sk_common.skc_net #define sk_v6_daddr __sk_common.skc_v6_daddr #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr +#define sk_cookie __sk_common.skc_cookie socket_lock_t sk_lock; struct sk_buff_head sk_receive_queue; @@ -403,8 +405,8 @@ struct sock { rwlock_t sk_callback_lock; int sk_err, sk_err_soft; - unsigned short sk_ack_backlog; - unsigned short sk_max_ack_backlog; + u32 sk_ack_backlog; + u32 sk_max_ack_backlog; __u32 sk_priority; #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) __u32 sk_cgrp_prioidx; @@ -958,10 +960,9 @@ struct proto { int (*compat_ioctl)(struct sock *sk, unsigned int cmd, unsigned long arg); #endif - int (*sendmsg)(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len); - int (*recvmsg)(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, + int (*sendmsg)(struct sock *sk, struct msghdr *msg, + size_t len); + int (*recvmsg)(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len); int (*sendpage)(struct sock *sk, struct page *page, @@ -1562,9 +1563,8 @@ int sock_no_listen(struct socket *, int); int sock_no_shutdown(struct socket *, int); int sock_no_getsockopt(struct socket *, int , int, char __user *, int __user *); int sock_no_setsockopt(struct socket *, int, int, char __user *, unsigned int); -int sock_no_sendmsg(struct kiocb *, struct socket *, struct msghdr *, size_t); -int sock_no_recvmsg(struct kiocb *, struct socket *, struct msghdr *, size_t, - int); +int sock_no_sendmsg(struct socket *, struct msghdr *, size_t); +int sock_no_recvmsg(struct socket *, struct msghdr *, size_t, int); int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma); ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, @@ -1576,8 +1576,8 @@ ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, */ int sock_common_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); -int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, int flags); +int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int flags); int sock_common_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen); int compat_sock_common_getsockopt(struct socket *sock, int level, @@ -1626,7 +1626,7 @@ static inline void sock_put(struct sock *sk) sk_free(sk); } /* Generic version of sock_put(), dealing with all sockets - * (TCP_TIMEWAIT, ESTABLISHED...) + * (TCP_TIMEWAIT, TCP_NEW_SYN_RECV, ESTABLISHED...) */ void sock_gen_put(struct sock *sk); @@ -2078,6 +2078,29 @@ static inline int sock_intr_errno(long timeo) return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR; } +struct sock_skb_cb { + u32 dropcount; +}; + +/* Store sock_skb_cb at the end of skb->cb[] so protocol families + * using skb->cb[] would keep using it directly and utilize its + * alignement guarantee. + */ +#define SOCK_SKB_CB_OFFSET ((FIELD_SIZEOF(struct sk_buff, cb) - \ + sizeof(struct sock_skb_cb))) + +#define SOCK_SKB_CB(__skb) ((struct sock_skb_cb *)((__skb)->cb + \ + SOCK_SKB_CB_OFFSET)) + +#define sock_skb_cb_check_size(size) \ + BUILD_BUG_ON((size) > SOCK_SKB_CB_OFFSET) + +static inline void +sock_skb_set_dropcount(const struct sock *sk, struct sk_buff *skb) +{ + SOCK_SKB_CB(skb)->dropcount = atomic_read(&sk->sk_drops); +} + void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, @@ -2180,7 +2203,7 @@ static inline void sk_change_net(struct sock *sk, struct net *net) if (!net_eq(current_net, net)) { put_net(current_net); - sock_net_set(sk, hold_net(net)); + sock_net_set(sk, net); } } @@ -2196,6 +2219,14 @@ static inline struct sock *skb_steal_sock(struct sk_buff *skb) return NULL; } +/* This helper checks if a socket is a full socket, + * ie _not_ a timewait or request socket. + */ +static inline bool sk_fullsock(const struct sock *sk) +{ + return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV); +} + void sock_enable_timestamp(struct sock *sk, int flag); int sock_get_timestamp(struct sock *, struct timeval __user *); int sock_get_timestampns(struct sock *, struct timespec __user *); diff --git a/include/net/switchdev.h b/include/net/switchdev.h index cfcdac2e5d25..e5de53f92482 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -1,6 +1,7 @@ /* * include/net/switchdev.h - Switch device API * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us> + * Copyright (c) 2014-2015 Scott Feldman <sfeldma@gmail.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -13,6 +14,44 @@ #include <linux/netdevice.h> #include <linux/notifier.h> +struct fib_info; + +/** + * struct switchdev_ops - switchdev operations + * + * int (*swdev_parent_id_get)(struct net_device *dev, + * struct netdev_phys_item_id *psid); + * Called to get an ID of the switch chip this port is part of. + * If driver implements this, it indicates that it represents a port + * of a switch chip. + * + * int (*swdev_port_stp_update)(struct net_device *dev, u8 state); + * Called to notify switch device port of bridge port STP + * state change. + * + * int (*swdev_fib_ipv4_add)(struct net_device *dev, __be32 dst, + * int dst_len, struct fib_info *fi, + * u8 tos, u8 type, u32 nlflags, u32 tb_id); + * Called to add/modify IPv4 route to switch device. + * + * int (*swdev_fib_ipv4_del)(struct net_device *dev, __be32 dst, + * int dst_len, struct fib_info *fi, + * u8 tos, u8 type, u32 tb_id); + * Called to delete IPv4 route from switch device. + */ +struct swdev_ops { + int (*swdev_parent_id_get)(struct net_device *dev, + struct netdev_phys_item_id *psid); + int (*swdev_port_stp_update)(struct net_device *dev, u8 state); + int (*swdev_fib_ipv4_add)(struct net_device *dev, __be32 dst, + int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 nlflags, + u32 tb_id); + int (*swdev_fib_ipv4_del)(struct net_device *dev, __be32 dst, + int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 tb_id); +}; + enum netdev_switch_notifier_type { NETDEV_SWITCH_FDB_ADD = 1, NETDEV_SWITCH_FDB_DEL, @@ -51,6 +90,12 @@ int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags); int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags); +int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 nlflags, u32 tb_id); +int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 tb_id); +void netdev_switch_fib_ipv4_abort(struct fib_info *fi); + #else static inline int netdev_switch_parent_id_get(struct net_device *dev, @@ -109,6 +154,25 @@ static inline int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device * return 0; } +static inline int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, + struct fib_info *fi, + u8 tos, u8 type, + u32 nlflags, u32 tb_id) +{ + return 0; +} + +static inline int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, + struct fib_info *fi, + u8 tos, u8 type, u32 tb_id) +{ + return 0; +} + +static inline void netdev_switch_fib_ipv4_abort(struct fib_info *fi) +{ +} + #endif #endif /* _LINUX_SWITCHDEV_H_ */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 8d6b983d5099..082fd79132b7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -65,7 +65,13 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCP_MIN_MSS 88U /* The least MTU to use for probing */ -#define TCP_BASE_MSS 512 +#define TCP_BASE_MSS 1024 + +/* probing interval, default to 10 minutes as per RFC4821 */ +#define TCP_PROBE_INTERVAL 600 + +/* Specify interval when tcp mtu probing will stop */ +#define TCP_PROBE_THRESHOLD 8 /* After receiving this amount of duplicate ACKs fast retransmit starts. */ #define TCP_FASTRETRANS_THRESH 3 @@ -349,8 +355,7 @@ void tcp_v4_early_demux(struct sk_buff *skb); int tcp_v4_rcv(struct sk_buff *skb); int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw); -int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t size); +int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); void tcp_release_cb(struct sock *sk); @@ -401,8 +406,7 @@ enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, const struct tcphdr *th); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, struct request_sock **prev, - bool fastopen); + struct request_sock *req, bool fastopen); int tcp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); void tcp_enter_loss(struct sock *sk); @@ -430,8 +434,8 @@ int compat_tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen); void tcp_set_keepalive(struct sock *sk, int val); void tcp_syn_ack_timeout(struct sock *sk, struct request_sock *req); -int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len, int nonblock, int flags, int *addr_len); +int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, + int flags, int *addr_len); void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab, struct tcp_fastopen_cookie *foc); @@ -1132,31 +1136,6 @@ static inline int tcp_full_space(const struct sock *sk) return tcp_win_from_space(sk->sk_rcvbuf); } -static inline void tcp_openreq_init(struct request_sock *req, - struct tcp_options_received *rx_opt, - struct sk_buff *skb, struct sock *sk) -{ - struct inet_request_sock *ireq = inet_rsk(req); - - req->rcv_wnd = 0; /* So that tcp_send_synack() knows! */ - req->cookie_ts = 0; - tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; - tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; - tcp_rsk(req)->snt_synack = tcp_time_stamp; - tcp_rsk(req)->last_oow_ack_time = 0; - req->mss = rx_opt->mss_clamp; - req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0; - ireq->tstamp_ok = rx_opt->tstamp_ok; - ireq->sack_ok = rx_opt->sack_ok; - ireq->snd_wscale = rx_opt->snd_wscale; - ireq->wscale_ok = rx_opt->wscale_ok; - ireq->acked = 0; - ireq->ecn_ok = 0; - ireq->ir_rmt_port = tcp_hdr(skb)->source; - ireq->ir_num = ntohs(tcp_hdr(skb)->dest); - ireq->ir_mark = inet_request_mark(sk, skb); -} - extern void tcp_openreq_init_rwin(struct request_sock *req, struct sock *sk, struct dst_entry *dst); @@ -1236,36 +1215,8 @@ static inline bool tcp_paws_reject(const struct tcp_options_received *rx_opt, return true; } -/* Return true if we're currently rate-limiting out-of-window ACKs and - * thus shouldn't send a dupack right now. We rate-limit dupacks in - * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS - * attacks that send repeated SYNs or ACKs for the same connection. To - * do this, we do not send a duplicate SYNACK or ACK if the remote - * endpoint is sending out-of-window SYNs or pure ACKs at a high rate. - */ -static inline bool tcp_oow_rate_limited(struct net *net, - const struct sk_buff *skb, - int mib_idx, u32 *last_oow_ack_time) -{ - /* Data packets without SYNs are not likely part of an ACK loop. */ - if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) && - !tcp_hdr(skb)->syn) - goto not_rate_limited; - - if (*last_oow_ack_time) { - s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); - - if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { - NET_INC_STATS_BH(net, mib_idx); - return true; /* rate-limited: don't send yet! */ - } - } - - *last_oow_ack_time = tcp_time_stamp; - -not_rate_limited: - return false; /* not rate-limited: go ahead, send dupack now! */ -} +bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, + int mib_idx, u32 *last_oow_ack_time); static inline void tcp_mib_init(struct net *net) { diff --git a/include/net/tcp_states.h b/include/net/tcp_states.h index b0b645988bd8..50e78a74d0df 100644 --- a/include/net/tcp_states.h +++ b/include/net/tcp_states.h @@ -25,6 +25,7 @@ enum { TCP_LAST_ACK, TCP_LISTEN, TCP_CLOSING, /* Now a valid state */ + TCP_NEW_SYN_RECV, TCP_MAX_STATES /* Leave at the end! */ }; @@ -44,7 +45,8 @@ enum { TCPF_CLOSE_WAIT = (1 << 8), TCPF_LAST_ACK = (1 << 9), TCPF_LISTEN = (1 << 10), - TCPF_CLOSING = (1 << 11) + TCPF_CLOSING = (1 << 11), + TCPF_NEW_SYN_RECV = (1 << 12), }; #endif /* _LINUX_TCP_STATES_H */ diff --git a/include/net/udp.h b/include/net/udp.h index 07f9b70962f6..6d4ed18e1427 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -194,6 +194,8 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, int (*)(const struct sock *, const struct sock *), unsigned int hash2_nulladdr); +u32 udp_flow_hashrnd(void); + static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb, int min, int max, bool use_eth) { @@ -205,12 +207,19 @@ static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb, } hash = skb_get_hash(skb); - if (unlikely(!hash) && use_eth) { - /* Can't find a normal hash, caller has indicated an Ethernet - * packet so use that to compute a hash. - */ - hash = jhash(skb->data, 2 * ETH_ALEN, - (__force u32) skb->protocol); + if (unlikely(!hash)) { + if (use_eth) { + /* Can't find a normal hash, caller has indicated an + * Ethernet packet so use that to compute a hash. + */ + hash = jhash(skb->data, 2 * ETH_ALEN, + (__force u32) skb->protocol); + } else { + /* Can't derive any sort of hash for the packet, set + * to some consistent random value. + */ + hash = udp_flow_hashrnd(); + } } /* Since this is being sent on the wire obfuscate hash a bit @@ -229,8 +238,7 @@ int udp_get_port(struct sock *sk, unsigned short snum, int (*saddr_cmp)(const struct sock *, const struct sock *)); void udp_err(struct sk_buff *, u32); -int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len); +int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); int udp_push_pending_frames(struct sock *sk); void udp_flush_pending_frames(struct sock *sk); void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst); diff --git a/include/net/vxlan.h b/include/net/vxlan.h index c73e7abbbaa5..756e4636bad8 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -131,7 +131,7 @@ struct vxlan_sock { #define VXLAN_F_GBP 0x800 #define VXLAN_F_REMCSUM_NOPARTIAL 0x1000 -/* Flags that are used in the receive patch. These flags must match in +/* Flags that are used in the receive path. These flags must match in * order for a socket to be shareable */ #define VXLAN_F_RCV_FLAGS (VXLAN_F_GBP | \ diff --git a/include/net/xfrm.h b/include/net/xfrm.h index dc4865e90fe4..d0ac7d7be8a7 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -126,9 +126,7 @@ struct xfrm_state_walk { /* Full description of state of transformer. */ struct xfrm_state { -#ifdef CONFIG_NET_NS - struct net *xs_net; -#endif + possible_net_t xs_net; union { struct hlist_node gclist; struct hlist_node bydst; @@ -522,9 +520,7 @@ struct xfrm_policy_queue { }; struct xfrm_policy { -#ifdef CONFIG_NET_NS - struct net *xp_net; -#endif + possible_net_t xp_net; struct hlist_node bydst; struct hlist_node byidx; |