diff options
Diffstat (limited to 'include/net')
66 files changed, 1474 insertions, 764 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..7dba80546f16 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); @@ -269,29 +269,34 @@ struct l2cap_ctrl { __u16 reqseq; __u16 txseq; __u8 retries; + __le16 psm; + bdaddr_t bdaddr; + struct l2cap_chan *chan; }; 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; +typedef void (*hci_req_complete_skb_t)(struct hci_dev *hdev, u8 status, + u16 opcode, struct sk_buff *skb); + +struct req_ctrl { + bool start; + u8 event; + hci_req_complete_t complete; + hci_req_complete_skb_t complete_skb; }; struct bt_skb_cb { __u8 pkt_type; - __u8 incoming; + __u8 force_active; __u16 opcode; __u16 expect; - __u8 force_active; - struct l2cap_chan *chan; - struct l2cap_ctrl control; - struct hci_req_ctrl req; - bdaddr_t bdaddr; - __le16 psm; + __u8 incoming:1; + union { + struct l2cap_ctrl l2cap; + struct req_ctrl req; + }; }; #define bt_cb(skb) ((struct bt_skb_cb *)((skb)->cb)) @@ -339,6 +344,11 @@ 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 +368,9 @@ 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..3acecf35420b 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 +226,8 @@ enum { HCI_HS_ENABLED, HCI_LE_ENABLED, HCI_ADVERTISING, + HCI_ADVERTISING_CONNECTABLE, + HCI_ADVERTISING_INSTANCE, HCI_CONNECTABLE, HCI_DISCOVERABLE, HCI_LIMITED_DISCOVERABLE, @@ -225,13 +236,13 @@ 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 +466,11 @@ 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_APPEARANCE 0x19 /* Device appearance */ +#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..93fd3e756b8a 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]; }; @@ -154,6 +155,17 @@ struct oob_data { u8 rand256[16]; }; +struct adv_info { + struct delayed_work timeout_exp; + __u8 instance; + __u32 flags; + __u16 timeout; + __u16 adv_data_len; + __u8 adv_data[HCI_MAX_AD_LENGTH]; + __u16 scan_rsp_len; + __u8 scan_rsp_data[HCI_MAX_AD_LENGTH]; +}; + #define HCI_MAX_SHORT_NAME_LENGTH 10 /* Default LE RPA expiry time, 15 minutes */ @@ -314,7 +326,6 @@ struct hci_dev { struct sk_buff_head raw_q; struct sk_buff_head cmd_q; - struct sk_buff *recv_evt; struct sk_buff *sent_cmd; struct sk_buff *reassembly[NUM_REASSEMBLY]; @@ -322,6 +333,7 @@ struct hci_dev { wait_queue_head_t req_wait_q; __u32 req_status; __u32 req_result; + struct sk_buff *req_skb; void *smp_data; void *smp_bredr_data; @@ -352,8 +364,7 @@ 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; @@ -364,6 +375,8 @@ struct hci_dev { __u8 scan_rsp_data[HCI_MAX_AD_LENGTH]; __u8 scan_rsp_data_len; + struct adv_info adv_instance; + __u8 irk[16]; __u32 rpa_timeout; struct delayed_work rpa_expired; @@ -373,6 +386,7 @@ 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 +512,29 @@ 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 +553,7 @@ 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; @@ -538,6 +563,11 @@ static inline void hci_discovery_filter_clear(struct hci_dev *hdev) hdev->discovery.scan_duration = 0; } +static inline void adv_info_init(struct hci_dev *hdev) +{ + memset(&hdev->adv_instance, 0, sizeof(struct adv_info)); +} + bool hci_discovery_active(struct hci_dev *hdev); void hci_discovery_set_state(struct hci_dev *hdev, int state); @@ -584,7 +614,6 @@ 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 +629,14 @@ 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 +998,8 @@ 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 +1056,10 @@ 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 +1081,6 @@ 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 +1089,69 @@ 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 +1165,27 @@ 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 +1193,12 @@ 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) @@ -1296,8 +1284,6 @@ static inline int hci_check_conn_params(u16 min, u16 max, u16 latency, int hci_register_cb(struct hci_cb *hcb); int hci_unregister_cb(struct hci_cb *hcb); -bool hci_req_pending(struct hci_dev *hdev); - struct sk_buff *__hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen, const void *param, u32 timeout); struct sk_buff *__hci_cmd_sync_ev(struct hci_dev *hdev, u16 opcode, u32 plen, @@ -1312,11 +1298,35 @@ 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 +1346,6 @@ 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); @@ -1382,9 +1391,6 @@ void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status); void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class, u8 status); void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status); -void mgmt_read_local_oob_data_complete(struct hci_dev *hdev, u8 *hash192, - u8 *rand192, u8 *hash256, u8 *rand256, - u8 status); void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 *dev_class, s8 rssi, u32 flags, u8 *eir, u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len); diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index e218a30f2061..b831242d48a4 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 +506,71 @@ 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_OP_ADD_ADVERTISING 0x003E +struct mgmt_cp_add_advertising { + __u8 instance; + __le32 flags; + __le16 duration; + __le16 timeout; + __u8 adv_data_len; + __u8 scan_rsp_len; + __u8 data[0]; +} __packed; +#define MGMT_ADD_ADVERTISING_SIZE 11 +struct mgmt_rp_add_advertising { + __u8 instance; +} __packed; + +#define MGMT_ADV_FLAG_CONNECTABLE BIT(0) +#define MGMT_ADV_FLAG_DISCOV BIT(1) +#define MGMT_ADV_FLAG_LIMITED_DISCOV BIT(2) +#define MGMT_ADV_FLAG_MANAGED_FLAGS BIT(3) +#define MGMT_ADV_FLAG_TX_POWER BIT(4) +#define MGMT_ADV_FLAG_APPEARANCE BIT(5) +#define MGMT_ADV_FLAG_LOCAL_NAME BIT(6) + +#define MGMT_OP_REMOVE_ADVERTISING 0x003F +struct mgmt_cp_remove_advertising { + __u8 instance; +} __packed; +#define MGMT_REMOVE_ADVERTISING_SIZE 1 +struct mgmt_rp_remove_advertising { + __u8 instance; +} __packed; + #define MGMT_EV_CMD_COMPLETE 0x0001 struct mgmt_ev_cmd_complete { __le16 opcode; @@ -647,9 +715,14 @@ 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 +758,29 @@ 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; + +#define MGMT_EV_ADVERTISING_ADDED 0x0023 +struct mgmt_ev_advertising_added { + __u8 instance; +} __packed; + +#define MGMT_EV_ADVERTISING_REMOVED 0x0024 +struct mgmt_ev_advertising_removed { + __u8 instance; +} __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/caif/cfpkt.h b/include/net/caif/cfpkt.h index 1c1ad46250d5..fe328c52c46b 100644 --- a/include/net/caif/cfpkt.h +++ b/include/net/caif/cfpkt.h @@ -171,7 +171,7 @@ struct cfpkt *cfpkt_split(struct cfpkt *pkt, u16 pos); * @return Checksum of buffer. */ -u16 cfpkt_iterate(struct cfpkt *pkt, +int cfpkt_iterate(struct cfpkt *pkt, u16 (*iter_func)(u16 chks, void *buf, u16 len), u16 data); diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 64e09e1e8099..441306436569 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -215,6 +215,39 @@ enum ieee80211_rate_flags { }; /** + * enum ieee80211_bss_type - BSS type filter + * + * @IEEE80211_BSS_TYPE_ESS: Infrastructure BSS + * @IEEE80211_BSS_TYPE_PBSS: Personal BSS + * @IEEE80211_BSS_TYPE_IBSS: Independent BSS + * @IEEE80211_BSS_TYPE_MBSS: Mesh BSS + * @IEEE80211_BSS_TYPE_ANY: Wildcard value for matching any BSS type + */ +enum ieee80211_bss_type { + IEEE80211_BSS_TYPE_ESS, + IEEE80211_BSS_TYPE_PBSS, + IEEE80211_BSS_TYPE_IBSS, + IEEE80211_BSS_TYPE_MBSS, + IEEE80211_BSS_TYPE_ANY +}; + +/** + * enum ieee80211_privacy - BSS privacy filter + * + * @IEEE80211_PRIVACY_ON: privacy bit set + * @IEEE80211_PRIVACY_OFF: privacy bit clear + * @IEEE80211_PRIVACY_ANY: Wildcard value for matching any privacy setting + */ +enum ieee80211_privacy { + IEEE80211_PRIVACY_ON, + IEEE80211_PRIVACY_OFF, + IEEE80211_PRIVACY_ANY +}; + +#define IEEE80211_PRIVACY(x) \ + ((x) ? IEEE80211_PRIVACY_ON : IEEE80211_PRIVACY_OFF) + +/** * struct ieee80211_rate - bitrate definition * * This structure describes a bitrate that an 802.11 PHY can @@ -2423,6 +2456,7 @@ struct cfg80211_ops { struct wireless_dev * (*add_virtual_intf)(struct wiphy *wiphy, const char *name, + unsigned char name_assign_type, enum nl80211_iftype type, u32 *flags, struct vif_params *params); @@ -3183,10 +3217,8 @@ 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; @@ -4012,14 +4044,16 @@ struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy, struct ieee80211_channel *channel, const u8 *bssid, const u8 *ssid, size_t ssid_len, - u16 capa_mask, u16 capa_val); + enum ieee80211_bss_type bss_type, + enum ieee80211_privacy); static inline struct cfg80211_bss * cfg80211_get_ibss(struct wiphy *wiphy, struct ieee80211_channel *channel, const u8 *ssid, size_t ssid_len) { return cfg80211_get_bss(wiphy, channel, NULL, ssid, ssid_len, - WLAN_CAPABILITY_IBSS, WLAN_CAPABILITY_IBSS); + IEEE80211_BSS_TYPE_IBSS, + IEEE80211_PRIVACY_ANY); } /** @@ -4260,6 +4294,7 @@ struct sk_buff *__cfg80211_alloc_reply_skb(struct wiphy *wiphy, int approxlen); struct sk_buff *__cfg80211_alloc_event_skb(struct wiphy *wiphy, + struct wireless_dev *wdev, enum nl80211_commands cmd, enum nl80211_attrs attr, int vendor_event_idx, @@ -4314,6 +4349,7 @@ int cfg80211_vendor_cmd_reply(struct sk_buff *skb); /** * cfg80211_vendor_event_alloc - allocate vendor-specific event skb * @wiphy: the wiphy + * @wdev: the wireless device * @event_idx: index of the vendor event in the wiphy's vendor_events * @approxlen: an upper bound of the length of the data that will * be put into the skb @@ -4322,16 +4358,20 @@ int cfg80211_vendor_cmd_reply(struct sk_buff *skb); * This function allocates and pre-fills an skb for an event on the * vendor-specific multicast group. * + * If wdev != NULL, both the ifindex and identifier of the specified + * wireless device are added to the event message before the vendor data + * attribute. + * * When done filling the skb, call cfg80211_vendor_event() with the * skb to send the event. * * Return: An allocated and pre-filled skb. %NULL if any errors happen. */ static inline struct sk_buff * -cfg80211_vendor_event_alloc(struct wiphy *wiphy, int approxlen, - int event_idx, gfp_t gfp) +cfg80211_vendor_event_alloc(struct wiphy *wiphy, struct wireless_dev *wdev, + int approxlen, int event_idx, gfp_t gfp) { - return __cfg80211_alloc_event_skb(wiphy, NL80211_CMD_VENDOR, + return __cfg80211_alloc_event_skb(wiphy, wdev, NL80211_CMD_VENDOR, NL80211_ATTR_VENDOR_DATA, event_idx, approxlen, gfp); } @@ -4432,7 +4472,7 @@ static inline int cfg80211_testmode_reply(struct sk_buff *skb) static inline struct sk_buff * cfg80211_testmode_alloc_event_skb(struct wiphy *wiphy, int approxlen, gfp_t gfp) { - return __cfg80211_alloc_event_skb(wiphy, NL80211_CMD_TESTMODE, + return __cfg80211_alloc_event_skb(wiphy, NULL, NL80211_CMD_TESTMODE, NL80211_ATTR_TESTDATA, -1, approxlen, gfp); } @@ -4862,6 +4902,17 @@ void cfg80211_ch_switch_started_notify(struct net_device *dev, bool ieee80211_operating_class_to_band(u8 operating_class, enum ieee80211_band *band); +/** + * ieee80211_chandef_to_operating_class - convert chandef to operation class + * + * @chandef: the chandef to convert + * @op_class: a pointer to the resulting operating class + * + * Returns %true if the conversion was successful, %false otherwise. + */ +bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef, + u8 *op_class); + /* * cfg80211_tdls_oper_request - request userspace to perform TDLS operation * @dev: the device on which the operation is requested 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..fbca63ba8f73 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 +286,22 @@ 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); + int (*fdb_add)(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid); + int (*fdb_del)(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid); + int (*fdb_getnext)(struct dsa_switch *ds, int port, + unsigned char *addr, bool *is_static); }; void register_switch_driver(struct dsa_switch_driver *type); diff --git a/include/net/dst.h b/include/net/dst.h index a8ae4e760778..0fb99a26e973 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -481,6 +481,7 @@ void dst_init(void); enum { XFRM_LOOKUP_ICMP = 1 << 0, XFRM_LOOKUP_QUEUE = 1 << 1, + XFRM_LOOKUP_KEEP_DST_REF = 1 << 2, }; struct flowi; 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/if_inet6.h b/include/net/if_inet6.h index 98e5f9578f86..1c8b6820b694 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -41,18 +41,18 @@ enum { struct inet6_ifaddr { struct in6_addr addr; __u32 prefix_len; - + /* In seconds, relative to tstamp. Expiry is at tstamp + HZ * lft. */ __u32 valid_lft; __u32 prefered_lft; atomic_t refcnt; spinlock_t lock; - spinlock_t state_lock; int state; __u32 flags; __u8 dad_probes; + __u8 stable_privacy_retry; __u16 scope; 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/inetpeer.h b/include/net/inetpeer.h index 80479abddf73..d5332ddcea3f 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -19,6 +19,7 @@ struct inetpeer_addr_base { union { __be32 a4; __be32 a6[4]; + struct in6_addr in6; }; }; @@ -151,7 +152,7 @@ static inline struct inet_peer *inet_getpeer_v6(struct inet_peer_base *base, { struct inetpeer_addr daddr; - *(struct in6_addr *)daddr.addr.a6 = *v6daddr; + daddr.addr.in6 = *v6daddr; daddr.family = AF_INET6; return inet_getpeer(base, &daddr, create); } diff --git a/include/net/ip.h b/include/net/ip.h index 025c61c0dffb..69cd9cb8400c 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -318,9 +318,10 @@ static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb) } u32 ip_idents_reserve(u32 hash, int segs); -void __ip_select_ident(struct iphdr *iph, int segs); +void __ip_select_ident(struct net *net, struct iphdr *iph, int segs); -static inline void ip_select_ident_segs(struct sk_buff *skb, struct sock *sk, int segs) +static inline void ip_select_ident_segs(struct net *net, struct sk_buff *skb, + struct sock *sk, int segs) { struct iphdr *iph = ip_hdr(skb); @@ -337,13 +338,14 @@ static inline void ip_select_ident_segs(struct sk_buff *skb, struct sock *sk, in iph->id = 0; } } else { - __ip_select_ident(iph, segs); + __ip_select_ident(net, iph, segs); } } -static inline void ip_select_ident(struct sk_buff *skb, struct sock *sk) +static inline void ip_select_ident(struct net *net, struct sk_buff *skb, + struct sock *sk) { - ip_select_ident_segs(skb, sk, 1); + ip_select_ident_segs(net, skb, sk, 1); } static inline __wsum inet_compute_pseudo(struct sk_buff *skb, int proto) @@ -453,22 +455,6 @@ static __inline__ void inet_reset_saddr(struct sock *sk) #endif -static inline int sk_mc_loop(struct sock *sk) -{ - if (!sk) - return 1; - switch (sk->sk_family) { - case AF_INET: - return inet_sk(sk)->mc_loop; -#if IS_ENABLED(CONFIG_IPV6) - case AF_INET6: - return inet6_sk(sk)->mc_loop; -#endif - } - WARN_ON(1); - return 1; -} - bool ip_call_ra_chain(struct sk_buff *skb); /* diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 1d09b46c1e48..eda131d179d9 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -174,7 +174,8 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)); static inline int ip6_skb_dst_mtu(struct sk_buff *skb) { - struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL; + struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? + inet6_sk(skb->sk) : NULL; return (np && np->pmtudisc >= IPV6_PMTUDISC_PROBE) ? skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb)); diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 76c091b53dae..1668be5937e6 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -71,6 +71,7 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw); __u32 ip6_tnl_get_cap(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr); struct net *ip6_tnl_get_link_net(const struct net_device *dev); +int ip6_tnl_get_iflink(const struct net_device *dev); static inline void ip6tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { 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_tunnels.h b/include/net/ip_tunnels.h index 2c47061a6954..d8214cb88bbc 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -142,6 +142,7 @@ int ip_tunnel_init(struct net_device *dev); void ip_tunnel_uninit(struct net_device *dev); void ip_tunnel_dellink(struct net_device *dev, struct list_head *head); struct net *ip_tunnel_get_link_net(const struct net_device *dev); +int ip_tunnel_get_iflink(const struct net_device *dev); int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id, struct rtnl_link_ops *ops, char *devname); 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..65142e6af440 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -671,8 +671,9 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr)); } -void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt); -void ipv6_proxy_select_ident(struct sk_buff *skb); +void ipv6_select_ident(struct net *net, struct frag_hdr *fhdr, + struct rt6_info *rt); +void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb); int ip6_dst_hoplimit(struct dst_entry *dst); @@ -940,4 +941,8 @@ 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/iw_handler.h b/include/net/iw_handler.h index a830b01baba4..8f81bbbc38fc 100644 --- a/include/net/iw_handler.h +++ b/include/net/iw_handler.h @@ -519,6 +519,17 @@ iwe_stream_add_event(struct iw_request_info *info, char *stream, char *ends, return stream; } +static inline char * +iwe_stream_add_event_check(struct iw_request_info *info, char *stream, + char *ends, struct iw_event *iwe, int event_len) +{ + char *res = iwe_stream_add_event(info, stream, ends, iwe, event_len); + + if (res == stream) + return ERR_PTR(-E2BIG); + return res; +} + /*------------------------------------------------------------------*/ /* * Wrapper to add an short Wireless Event containing a pointer to a @@ -545,6 +556,17 @@ iwe_stream_add_point(struct iw_request_info *info, char *stream, char *ends, return stream; } +static inline char * +iwe_stream_add_point_check(struct iw_request_info *info, char *stream, + char *ends, struct iw_event *iwe, char *extra) +{ + char *res = iwe_stream_add_point(info, stream, ends, iwe, extra); + + if (res == stream) + return ERR_PTR(-E2BIG); + return res; +} + /*------------------------------------------------------------------*/ /* * Wrapper to add a value to a Wireless Event in a stream of events. diff --git a/include/net/mac80211.h b/include/net/mac80211.h index d52914b75331..201bc68e0cff 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -301,17 +301,86 @@ enum ieee80211_bss_change { #define IEEE80211_BSS_ARP_ADDR_LIST_LEN 4 /** - * enum ieee80211_rssi_event - RSSI threshold event - * An indicator for when RSSI goes below/above a certain threshold. - * @RSSI_EVENT_HIGH: AP's rssi crossed the high threshold set by the driver. - * @RSSI_EVENT_LOW: AP's rssi crossed the low threshold set by the driver. + * enum ieee80211_event_type - event to be notified to the low level driver + * @RSSI_EVENT: AP's rssi crossed the a threshold set by the driver. + * @MLME_EVENT: event related to MLME */ -enum ieee80211_rssi_event { +enum ieee80211_event_type { + RSSI_EVENT, + MLME_EVENT, +}; + +/** + * enum ieee80211_rssi_event_data - relevant when event type is %RSSI_EVENT + * @RSSI_EVENT_HIGH: AP's rssi went below the threshold set by the driver. + * @RSSI_EVENT_LOW: AP's rssi went above the threshold set by the driver. + */ +enum ieee80211_rssi_event_data { RSSI_EVENT_HIGH, RSSI_EVENT_LOW, }; /** + * enum ieee80211_rssi_event - data attached to an %RSSI_EVENT + * @data: See &enum ieee80211_rssi_event_data + */ +struct ieee80211_rssi_event { + enum ieee80211_rssi_event_data data; +}; + +/** + * enum ieee80211_mlme_event_data - relevant when event type is %MLME_EVENT + * @AUTH_EVENT: the MLME operation is authentication + * @ASSOC_EVENT: the MLME operation is association + * @DEAUTH_RX_EVENT: deauth received.. + * @DEAUTH_TX_EVENT: deauth sent. + */ +enum ieee80211_mlme_event_data { + AUTH_EVENT, + ASSOC_EVENT, + DEAUTH_RX_EVENT, + DEAUTH_TX_EVENT, +}; + +/** + * enum ieee80211_mlme_event_status - relevant when event type is %MLME_EVENT + * @MLME_SUCCESS: the MLME operation completed successfully. + * @MLME_DENIED: the MLME operation was denied by the peer. + * @MLME_TIMEOUT: the MLME operation timed out. + */ +enum ieee80211_mlme_event_status { + MLME_SUCCESS, + MLME_DENIED, + MLME_TIMEOUT, +}; + +/** + * enum ieee80211_mlme_event - data attached to an %MLME_EVENT + * @data: See &enum ieee80211_mlme_event_data + * @status: See &enum ieee80211_mlme_event_status + * @reason: the reason code if applicable + */ +struct ieee80211_mlme_event { + enum ieee80211_mlme_event_data data; + enum ieee80211_mlme_event_status status; + u16 reason; +}; + +/** + * struct ieee80211_event - event to be sent to the driver + * @type The event itself. See &enum ieee80211_event_type. + * @rssi: relevant if &type is %RSSI_EVENT + * @mlme: relevant if &type is %AUTH_EVENT + */ +struct ieee80211_event { + enum ieee80211_event_type type; + union { + struct ieee80211_rssi_event rssi; + struct ieee80211_mlme_event mlme; + } u; +}; + +/** * struct ieee80211_bss_conf - holds the BSS's changing parameters * * This structure keeps information about a BSS (and an association @@ -337,12 +406,15 @@ enum ieee80211_rssi_event { * HW flag %IEEE80211_HW_TIMING_BEACON_ONLY is set, then this can * only come from a beacon, but might not become valid until after * association when a beacon is received (which is notified with the - * %BSS_CHANGED_DTIM flag.) + * %BSS_CHANGED_DTIM flag.). See also sync_dtim_count important notice. * @sync_device_ts: the device timestamp corresponding to the sync_tsf, * the driver/device can use this to calculate synchronisation - * (see @sync_tsf) + * (see @sync_tsf). See also sync_dtim_count important notice. * @sync_dtim_count: Only valid when %IEEE80211_HW_TIMING_BEACON_ONLY * is requested, see @sync_tsf/@sync_device_ts. + * IMPORTANT: These three sync_* parameters would possibly be out of sync + * by the time the driver will use them. The synchronized view is currently + * guaranteed only in certain callbacks. * @beacon_int: beacon interval * @assoc_capability: capabilities taken from assoc resp * @basic_rates: bitmap of basic rates, each bit stands for an @@ -1279,6 +1351,19 @@ static inline bool ieee80211_vif_is_mesh(struct ieee80211_vif *vif) struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev); /** + * ieee80211_vif_to_wdev - return a wdev struct from a vif + * @vif: the vif to get the wdev for + * + * This can be used by mac80211 drivers with direct cfg80211 APIs + * (like the vendor commands) that needs to get the wdev for a vif. + * + * Note that this function may return %NULL if the given wdev isn't + * associated with a vif that the driver knows about (e.g. monitor + * or AP_VLAN interfaces.) + */ +struct wireless_dev *ieee80211_vif_to_wdev(struct ieee80211_vif *vif); + +/** * enum ieee80211_key_flags - key flags * * These flags are used for communication about keys between the driver @@ -1472,7 +1557,8 @@ struct ieee80211_sta_rates { * @supp_rates: Bitmap of supported rates (per band) * @ht_cap: HT capabilities of this STA; restricted to our own capabilities * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities - * @wme: indicates whether the STA supports QoS/WME. + * @wme: indicates whether the STA supports QoS/WME (if local devices does, + * otherwise always false) * @drv_priv: data area for driver use, will always be aligned to * sizeof(void *), size is determined in hw information. * @uapsd_queues: bitmap of queues configured for uapsd. Only valid @@ -1488,6 +1574,7 @@ struct ieee80211_sta_rates { * @tdls: indicates whether the STA is a TDLS peer * @tdls_initiator: indicates the STA is an initiator of the TDLS link. Only * valid if the STA is a TDLS peer in the first place. + * @mfp: indicates whether the STA uses management frame protection or not. */ struct ieee80211_sta { u32 supp_rates[IEEE80211_NUM_BANDS]; @@ -1504,6 +1591,7 @@ struct ieee80211_sta { struct ieee80211_sta_rates __rcu *rates; bool tdls; bool tdls_initiator; + bool mfp; /* must be last */ u8 drv_priv[0] __aligned(sizeof(void *)); @@ -2844,8 +2932,9 @@ enum ieee80211_reconfig_type { * @set_bitrate_mask: Set a mask of rates to be used for rate control selection * when transmitting a frame. Currently only legacy rates are handled. * The callback can sleep. - * @rssi_callback: Notify driver when the average RSSI goes above/below - * thresholds that were registered previously. The callback can sleep. + * @event_callback: Notify driver about any event in mac80211. See + * &enum ieee80211_event_type for the different types. + * The callback can sleep. * * @release_buffered_frames: Release buffered frames according to the given * parameters. In the case where the driver buffers some frames for @@ -3141,9 +3230,9 @@ struct ieee80211_ops { bool (*tx_frames_pending)(struct ieee80211_hw *hw); int (*set_bitrate_mask)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, const struct cfg80211_bitrate_mask *mask); - void (*rssi_callback)(struct ieee80211_hw *hw, - struct ieee80211_vif *vif, - enum ieee80211_rssi_event rssi_event); + void (*event_callback)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + const struct ieee80211_event *event); void (*allow_buffered_frames)(struct ieee80211_hw *hw, struct ieee80211_sta *sta, @@ -4343,13 +4432,33 @@ void ieee80211_sched_scan_stopped(struct ieee80211_hw *hw); * haven't been re-added to the driver yet. * @IEEE80211_IFACE_ITER_RESUME_ALL: During resume, iterate over all * interfaces, even if they haven't been re-added to the driver yet. + * @IEEE80211_IFACE_ITER_ACTIVE: Iterate only active interfaces (netdev is up). */ enum ieee80211_interface_iteration_flags { IEEE80211_IFACE_ITER_NORMAL = 0, IEEE80211_IFACE_ITER_RESUME_ALL = BIT(0), + IEEE80211_IFACE_ITER_ACTIVE = BIT(1), }; /** + * ieee80211_iterate_interfaces - iterate interfaces + * + * This function iterates over the interfaces associated with a given + * hardware and calls the callback for them. This includes active as well as + * inactive interfaces. This function allows the iterator function to sleep. + * Will iterate over a new interface during add_interface(). + * + * @hw: the hardware struct of which the interfaces should be iterated over + * @iter_flags: iteration flags, see &enum ieee80211_interface_iteration_flags + * @iterator: the iterator function to call + * @data: first argument of the iterator function + */ +void ieee80211_iterate_interfaces(struct ieee80211_hw *hw, u32 iter_flags, + void (*iterator)(void *data, u8 *mac, + struct ieee80211_vif *vif), + void *data); + +/** * ieee80211_iterate_active_interfaces - iterate active interfaces * * This function iterates over the interfaces associated with a given @@ -4364,11 +4473,16 @@ enum ieee80211_interface_iteration_flags { * @iterator: the iterator function to call * @data: first argument of the iterator function */ -void ieee80211_iterate_active_interfaces(struct ieee80211_hw *hw, - u32 iter_flags, - void (*iterator)(void *data, u8 *mac, - struct ieee80211_vif *vif), - void *data); +static inline void +ieee80211_iterate_active_interfaces(struct ieee80211_hw *hw, u32 iter_flags, + void (*iterator)(void *data, u8 *mac, + struct ieee80211_vif *vif), + void *data) +{ + ieee80211_iterate_interfaces(hw, + iter_flags | IEEE80211_IFACE_ITER_ACTIVE, + iterator, data); +} /** * ieee80211_iterate_active_interfaces_atomic - iterate active interfaces 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..bd33e66f49aa 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -42,6 +42,7 @@ enum { NEIGH_VAR_MCAST_PROBES, NEIGH_VAR_UCAST_PROBES, NEIGH_VAR_APP_PROBES, + NEIGH_VAR_MCAST_REPROBES, NEIGH_VAR_RETRANS_TIME, NEIGH_VAR_BASE_REACHABLE_TIME, NEIGH_VAR_DELAY_PROBE_TIME, @@ -65,9 +66,7 @@ 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 +166,7 @@ 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 +190,11 @@ 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 +223,7 @@ 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 +246,57 @@ 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 +319,6 @@ 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 +356,7 @@ 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 +510,6 @@ 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_log.h b/include/net/netfilter/nf_log.h index 534e1f2ac4fc..57639fca223a 100644 --- a/include/net/netfilter/nf_log.h +++ b/include/net/netfilter/nf_log.h @@ -79,6 +79,16 @@ void nf_log_packet(struct net *net, const struct nf_loginfo *li, const char *fmt, ...); +__printf(8, 9) +void nf_log_trace(struct net *net, + u_int8_t pf, + unsigned int hooknum, + const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct nf_loginfo *li, + const char *fmt, ...); + struct nf_log_buf; struct nf_log_buf *nf_log_buf_open(void); diff --git a/include/net/netfilter/nf_nat_l3proto.h b/include/net/netfilter/nf_nat_l3proto.h index 340c013795a4..a3127325f624 100644 --- a/include/net/netfilter/nf_nat_l3proto.h +++ b/include/net/netfilter/nf_nat_l3proto.h @@ -44,40 +44,32 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb, struct nf_conn *ct, unsigned int hooknum); unsigned int nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)); unsigned int nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)); unsigned int nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)); unsigned int nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)); int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct, @@ -85,40 +77,32 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct, unsigned int hooknum, unsigned int hdrlen); unsigned int nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)); unsigned int nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)); unsigned int nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)); unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, unsigned int (*do_chain)(const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, + const struct nf_hook_state *state, struct nf_conn *ct)); #endif /* _NF_NAT_L3PROTO_H */ diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index 84a53d780306..d81d584157e1 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -12,12 +12,8 @@ struct nf_queue_entry { unsigned int id; struct nf_hook_ops *elem; - u_int8_t pf; + struct nf_hook_state state; u16 size; /* sizeof(entry) + saved route keys */ - unsigned int hook; - struct net_device *indev; - struct net_device *outdev; - int (*okfn)(struct sk_buff *); /* extra space to store route keys */ }; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 9eaaa7884586..804981980393 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -26,12 +26,11 @@ struct nft_pktinfo { static inline void nft_set_pktinfo(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out) + const struct nf_hook_state *state) { pkt->skb = skb; - pkt->in = pkt->xt.in = in; - pkt->out = pkt->xt.out = out; + pkt->in = pkt->xt.in = state->in; + pkt->out = pkt->xt.out = state->out; pkt->ops = ops; pkt->xt.hooknum = ops->hooknum; pkt->xt.family = ops->pf; @@ -119,22 +118,31 @@ int nft_validate_data_load(const struct nft_ctx *ctx, enum nft_registers reg, const struct nft_data *data, enum nft_data_types type); + +/** + * struct nft_userdata - user defined data associated with an object + * + * @len: length of the data + * @data: content + * + * The presence of user data is indicated in an object specific fashion, + * so a length of zero can't occur and the value "len" indicates data + * of length len + 1. + */ +struct nft_userdata { + u8 len; + unsigned char data[0]; +}; + /** * struct nft_set_elem - generic representation of set elements * - * @cookie: implementation specific element cookie * @key: element key - * @data: element data (maps only) - * @flags: element flags (end of interval) - * - * The cookie can be used to store a handle to the element for subsequent - * removal. + * @priv: element private data and extensions */ struct nft_set_elem { - void *cookie; struct nft_data key; - struct nft_data data; - u32 flags; + void *priv; }; struct nft_set; @@ -186,11 +194,15 @@ struct nft_set_estimate { enum nft_set_class class; }; +struct nft_set_ext; + /** * struct nft_set_ops - nf_tables set operations * * @lookup: look up an element within the set * @insert: insert new element into set + * @activate: activate new element in the next generation + * @deactivate: deactivate element in the next generation * @remove: remove element from set * @walk: iterate over all set elemeennts * @privsize: function to return size of set private data @@ -198,16 +210,19 @@ struct nft_set_estimate { * @destroy: destroy private data of set instance * @list: nf_tables_set_ops list node * @owner: module reference + * @elemsize: element private size * @features: features supported by the implementation */ struct nft_set_ops { bool (*lookup)(const struct nft_set *set, const struct nft_data *key, - struct nft_data *data); - int (*get)(const struct nft_set *set, - struct nft_set_elem *elem); + const struct nft_set_ext **ext); int (*insert)(const struct nft_set *set, const struct nft_set_elem *elem); + void (*activate)(const struct nft_set *set, + const struct nft_set_elem *elem); + void * (*deactivate)(const struct nft_set *set, + const struct nft_set_elem *elem); void (*remove)(const struct nft_set *set, const struct nft_set_elem *elem); void (*walk)(const struct nft_ctx *ctx, @@ -225,6 +240,7 @@ struct nft_set_ops { struct list_head list; struct module *owner; + unsigned int elemsize; u32 features; }; @@ -243,6 +259,7 @@ void nft_unregister_set(struct nft_set_ops *ops); * @nelems: number of elements * @policy: set parameterization (see enum nft_set_policies) * @ops: set ops + * @pnet: network namespace * @flags: set flags * @klen: key length * @dlen: data length @@ -259,6 +276,7 @@ struct nft_set { u16 policy; /* runtime data below here */ const struct nft_set_ops *ops ____cacheline_aligned; + possible_net_t pnet; u16 flags; u8 klen; u8 dlen; @@ -295,6 +313,121 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding); +/** + * enum nft_set_extensions - set extension type IDs + * + * @NFT_SET_EXT_KEY: element key + * @NFT_SET_EXT_DATA: mapping data + * @NFT_SET_EXT_FLAGS: element flags + * @NFT_SET_EXT_NUM: number of extension types + */ +enum nft_set_extensions { + NFT_SET_EXT_KEY, + NFT_SET_EXT_DATA, + NFT_SET_EXT_FLAGS, + NFT_SET_EXT_NUM +}; + +/** + * struct nft_set_ext_type - set extension type + * + * @len: fixed part length of the extension + * @align: alignment requirements of the extension + */ +struct nft_set_ext_type { + u8 len; + u8 align; +}; + +extern const struct nft_set_ext_type nft_set_ext_types[]; + +/** + * struct nft_set_ext_tmpl - set extension template + * + * @len: length of extension area + * @offset: offsets of individual extension types + */ +struct nft_set_ext_tmpl { + u16 len; + u8 offset[NFT_SET_EXT_NUM]; +}; + +/** + * struct nft_set_ext - set extensions + * + * @genmask: generation mask + * @offset: offsets of individual extension types + * @data: beginning of extension data + */ +struct nft_set_ext { + u8 genmask; + u8 offset[NFT_SET_EXT_NUM]; + char data[0]; +}; + +static inline void nft_set_ext_prepare(struct nft_set_ext_tmpl *tmpl) +{ + memset(tmpl, 0, sizeof(*tmpl)); + tmpl->len = sizeof(struct nft_set_ext); +} + +static inline void nft_set_ext_add_length(struct nft_set_ext_tmpl *tmpl, u8 id, + unsigned int len) +{ + tmpl->len = ALIGN(tmpl->len, nft_set_ext_types[id].align); + BUG_ON(tmpl->len > U8_MAX); + tmpl->offset[id] = tmpl->len; + tmpl->len += nft_set_ext_types[id].len + len; +} + +static inline void nft_set_ext_add(struct nft_set_ext_tmpl *tmpl, u8 id) +{ + nft_set_ext_add_length(tmpl, id, 0); +} + +static inline void nft_set_ext_init(struct nft_set_ext *ext, + const struct nft_set_ext_tmpl *tmpl) +{ + memcpy(ext->offset, tmpl->offset, sizeof(ext->offset)); +} + +static inline bool __nft_set_ext_exists(const struct nft_set_ext *ext, u8 id) +{ + return !!ext->offset[id]; +} + +static inline bool nft_set_ext_exists(const struct nft_set_ext *ext, u8 id) +{ + return ext && __nft_set_ext_exists(ext, id); +} + +static inline void *nft_set_ext(const struct nft_set_ext *ext, u8 id) +{ + return (void *)ext + ext->offset[id]; +} + +static inline struct nft_data *nft_set_ext_key(const struct nft_set_ext *ext) +{ + return nft_set_ext(ext, NFT_SET_EXT_KEY); +} + +static inline struct nft_data *nft_set_ext_data(const struct nft_set_ext *ext) +{ + return nft_set_ext(ext, NFT_SET_EXT_DATA); +} + +static inline u8 *nft_set_ext_flags(const struct nft_set_ext *ext) +{ + return nft_set_ext(ext, NFT_SET_EXT_FLAGS); +} + +static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set, + void *elem) +{ + return elem + set->ops->elemsize; +} + +void nft_set_elem_destroy(const struct nft_set *set, void *elem); /** * struct nft_expr_type - nf_tables expression type @@ -380,7 +513,7 @@ static inline void *nft_expr_priv(const struct nft_expr *expr) * @handle: rule handle * @genmask: generation mask * @dlen: length of expression data - * @ulen: length of user data (used for comments) + * @udata: user data is appended to the rule * @data: expression data */ struct nft_rule { @@ -388,79 +521,11 @@ struct nft_rule { u64 handle:42, genmask:2, dlen:12, - ulen:8; + udata:1; unsigned char data[] __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]; @@ -476,7 +541,7 @@ static inline struct nft_expr *nft_expr_last(const struct nft_rule *rule) return (struct nft_expr *)&rule->data[rule->dlen]; } -static inline void *nft_userdata(const struct nft_rule *rule) +static inline struct nft_userdata *nft_userdata(const struct nft_rule *rule) { return (void *)&rule->data[rule->dlen]; } @@ -501,7 +566,6 @@ enum nft_chain_flags { * * @rules: list of rules in the chain * @list: used internally - * @net: net namespace that this chain belongs to * @table: table that this chain belongs to * @handle: chain handle * @use: number of jump references to this chain @@ -512,7 +576,6 @@ enum nft_chain_flags { struct nft_chain { struct list_head rules; struct list_head list; - struct net *net; struct nft_table *table; u64 handle; u32 use; @@ -528,6 +591,25 @@ 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, @@ -545,6 +627,7 @@ struct nft_stats { * struct nft_base_chain - nf_tables base chain * * @ops: netfilter hook ops + * @pnet: net namespace that this chain belongs to * @type: chain type * @policy: default policy * @stats: per-cpu chain stats @@ -552,6 +635,7 @@ struct nft_stats { */ struct nft_base_chain { struct nf_hook_ops ops[NFT_HOOK_OPS_MAX]; + possible_net_t pnet; const struct nf_chain_type *type; u8 policy; struct nft_stats __percpu *stats; @@ -584,7 +668,7 @@ struct nft_table { u64 hgenerator; u32 use; u16 flags; - char name[]; + char name[NFT_TABLE_MAXNAMELEN]; }; /** @@ -614,25 +698,6 @@ 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 *); @@ -657,4 +722,116 @@ void nft_unregister_expr(struct nft_expr_type *); #define MODULE_ALIAS_NFT_SET() \ MODULE_ALIAS("nft-set") +/* + * The gencursor defines two generations, the currently active and the + * next one. Objects contain a bitmask of 2 bits specifying the generations + * they're active in. A set bit means they're inactive in the generation + * represented by that bit. + * + * New objects start out as inactive in the current and active in the + * next generation. When committing the ruleset the bitmask is cleared, + * meaning they're active in all generations. When removing an object, + * it is set inactive in the next generation. After committing the ruleset, + * the objects are removed. + */ +static inline unsigned int nft_gencursor_next(const struct net *net) +{ + return net->nft.gencursor + 1 == 1 ? 1 : 0; +} + +static inline u8 nft_genmask_next(const struct net *net) +{ + return 1 << nft_gencursor_next(net); +} + +static inline u8 nft_genmask_cur(const struct net *net) +{ + /* Use ACCESS_ONCE() to prevent refetching the value for atomicity */ + return 1 << ACCESS_ONCE(net->nft.gencursor); +} + +/* + * Set element transaction helpers + */ + +static inline bool nft_set_elem_active(const struct nft_set_ext *ext, + u8 genmask) +{ + return !(ext->genmask & genmask); +} + +static inline void nft_set_elem_change_active(const struct nft_set *set, + struct nft_set_ext *ext) +{ + ext->genmask ^= nft_genmask_next(read_pnet(&set->pnet)); +} + +/** + * 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/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h index cba143fbd2e4..2df7f96902ee 100644 --- a/include/net/netfilter/nf_tables_ipv4.h +++ b/include/net/netfilter/nf_tables_ipv4.h @@ -8,12 +8,11 @@ static inline void nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out) + const struct nf_hook_state *state) { struct iphdr *ip; - nft_set_pktinfo(pkt, ops, skb, in, out); + nft_set_pktinfo(pkt, ops, skb, state); ip = ip_hdr(pkt->skb); pkt->tprot = ip->protocol; diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h index 74d976137658..97db2e3a5e65 100644 --- a/include/net/netfilter/nf_tables_ipv6.h +++ b/include/net/netfilter/nf_tables_ipv6.h @@ -8,13 +8,12 @@ static inline int nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops, struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out) + const struct nf_hook_state *state) { int protohdr, thoff = 0; unsigned short frag_off; - nft_set_pktinfo(pkt, ops, skb, in, out); + nft_set_pktinfo(pkt, ops, skb, state); protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, NULL); /* If malformed, drop it */ diff --git a/include/net/netlink.h b/include/net/netlink.h index e010ee8da41d..2a5dbcc90d1c 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -4,6 +4,7 @@ #include <linux/types.h> #include <linux/netlink.h> #include <linux/jiffies.h> +#include <linux/in6.h> /* ======================================================================== * Netlink Messages and Attributes Interface (As Seen On TV) @@ -105,6 +106,8 @@ * nla_put_string(skb, type, str) add string attribute to skb * nla_put_flag(skb, type) add flag attribute to skb * nla_put_msecs(skb, type, jiffies) add msecs attribute to skb + * nla_put_in_addr(skb, type, addr) add IPv4 address attribute to skb + * nla_put_in6_addr(skb, type, addr) add IPv6 address attribute to skb * * Nested Attributes Construction: * nla_nest_start(skb, type) start a nested attribute @@ -957,6 +960,32 @@ static inline int nla_put_msecs(struct sk_buff *skb, int attrtype, } /** + * nla_put_in_addr - Add an IPv4 address netlink attribute to a socket + * buffer + * @skb: socket buffer to add attribute to + * @attrtype: attribute type + * @addr: IPv4 address + */ +static inline int nla_put_in_addr(struct sk_buff *skb, int attrtype, + __be32 addr) +{ + return nla_put_be32(skb, attrtype, addr); +} + +/** + * nla_put_in6_addr - Add an IPv6 address netlink attribute to a socket + * buffer + * @skb: socket buffer to add attribute to + * @attrtype: attribute type + * @addr: IPv6 address + */ +static inline int nla_put_in6_addr(struct sk_buff *skb, int attrtype, + const struct in6_addr *addr) +{ + return nla_put(skb, attrtype, sizeof(*addr), addr); +} + +/** * nla_get_u32 - return payload of u32 attribute * @nla: u32 netlink attribute */ @@ -1099,6 +1128,27 @@ static inline unsigned long nla_get_msecs(const struct nlattr *nla) } /** + * nla_get_in_addr - return payload of IPv4 address attribute + * @nla: IPv4 address netlink attribute + */ +static inline __be32 nla_get_in_addr(const struct nlattr *nla) +{ + return *(__be32 *) nla_data(nla); +} + +/** + * nla_get_in6_addr - return payload of IPv6 address attribute + * @nla: IPv6 address netlink attribute + */ +static inline struct in6_addr nla_get_in6_addr(const struct nlattr *nla) +{ + struct in6_addr tmp; + + nla_memcpy(&tmp, nla, sizeof(tmp)); + return tmp; +} + +/** * nla_nest_start - Start a new level of nested attributes * @skb: socket buffer to add attributes to * @attrtype: attribute type of container 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..d2527bf81142 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -32,6 +32,8 @@ struct netns_sysctl_ipv6 { int icmpv6_time; int anycast_src_echo_reply; int fwmark_reflect; + int idgen_retries; + int idgen_delay; }; struct netns_ipv6 { @@ -67,6 +69,7 @@ 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..fe41f3ceb008 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -39,8 +39,7 @@ struct request_sock_ops { void (*send_reset)(struct sock *sk, struct sk_buff *skb); void (*destructor)(struct request_sock *req); - void (*syn_ack_timeout)(struct sock *sk, - struct request_sock *req); + void (*syn_ack_timeout)(const struct request_sock *req); }; int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req); @@ -49,7 +48,11 @@ 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 +61,56 @@ 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 +120,16 @@ 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]; @@ -142,18 +173,11 @@ struct fastopen_queue { * %syn_wait_lock is necessary only to avoid proc interface having to grab the main * lock sock while browsing the listening hash (otherwise it's deadlock prone). * - * This lock is acquired in read mode only from listening_get_next() seq_file - * op and it's acquired in write mode _only_ from code that is actively - * changing rskq_accept_head. All readers that are holding the master sock lock - * don't need to grab this lock in read mode too as rskq_accept_head. writes - * are always protected from the main sock lock. */ 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 +185,9 @@ 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 */ + spinlock_t syn_wait_lock ____cacheline_aligned_in_smp; }; int reqsk_queue_alloc(struct request_sock_queue *queue, @@ -186,12 +213,21 @@ 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) { - write_lock(&queue->syn_wait_lock); - *prev_req = req->dl_next; - write_unlock(&queue->syn_wait_lock); + struct listen_sock *lopt = queue->listen_opt; + struct request_sock **prev; + + spin_lock(&queue->syn_wait_lock); + + prev = &lopt->syn_table[req->rsk_hash]; + while (*prev != req) + prev = &(*prev)->dl_next; + *prev = req->dl_next; + + spin_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 +260,53 @@ 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/sctp/sctp.h b/include/net/sctp/sctp.h index 856f01cb51dd..c56a438c3a1e 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -166,6 +166,9 @@ void sctp_remaddr_proc_exit(struct net *net); */ extern struct kmem_cache *sctp_chunk_cachep __read_mostly; extern struct kmem_cache *sctp_bucket_cachep __read_mostly; +extern long sysctl_sctp_mem[3]; +extern int sysctl_sctp_rmem[3]; +extern int sysctl_sctp_wmem[3]; /* * Section: Macros, externs, and inlines diff --git a/include/net/sock.h b/include/net/sock.h index 71c1300025e2..3a4898ec8c67 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -66,6 +66,7 @@ #include <linux/atomic.h> #include <net/dst.h> #include <net/checksum.h> +#include <net/tcp_states.h> #include <linux/net_tstamp.h> struct cgroup; @@ -189,15 +190,15 @@ 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() @@ -328,6 +329,7 @@ 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; @@ -402,8 +404,8 @@ 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; @@ -957,10 +959,9 @@ 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, @@ -1561,9 +1562,8 @@ 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, @@ -1575,8 +1575,8 @@ 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, @@ -1625,7 +1625,7 @@ 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); @@ -1761,6 +1761,8 @@ struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie); struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie); +bool sk_mc_loop(struct sock *sk); + static inline bool sk_can_gso(const struct sock *sk) { return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type); @@ -2077,6 +2079,29 @@ 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, @@ -2179,7 +2204,7 @@ 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); } } @@ -2195,6 +2220,14 @@ 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..d2e69ee3019a 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 +14,35 @@ #include <linux/netdevice.h> #include <linux/notifier.h> +struct fib_info; + +/** + * struct switchdev_ops - switchdev operations + * + * @swdev_parent_id_get: 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. + * + * @swdev_port_stp_update: Called to notify switch device port of bridge + * port STP state change. + * + * @swdev_fib_ipv4_add: Called to add/modify IPv4 route to switch device. + * + * @swdev_fib_ipv4_del: 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 +81,12 @@ 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 +145,25 @@ 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/tc_act/tc_bpf.h b/include/net/tc_act/tc_bpf.h index 86a070ffc930..a152e9858b2c 100644 --- a/include/net/tc_act/tc_bpf.h +++ b/include/net/tc_act/tc_bpf.h @@ -16,8 +16,12 @@ struct tcf_bpf { struct tcf_common common; struct bpf_prog *filter; + union { + u32 bpf_fd; + u16 bpf_num_ops; + }; struct sock_filter *bpf_ops; - u16 bpf_num_ops; + const char *bpf_name; }; #define to_bpf(a) \ container_of(a->priv, struct tcf_bpf, common) diff --git a/include/net/tcp.h b/include/net/tcp.h index 8d6b983d5099..963303fb96ae 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); @@ -429,9 +433,9 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname, 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); +void tcp_syn_ack_timeout(const struct request_sock *req); +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); @@ -443,6 +447,7 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th); 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); int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb); struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, @@ -524,8 +529,6 @@ int tcp_write_wakeup(struct sock *); void tcp_send_fin(struct sock *sk); void tcp_send_active_reset(struct sock *sk, gfp_t priority); int tcp_send_synack(struct sock *); -bool tcp_syn_flood_action(struct sock *sk, const struct sk_buff *skb, - const char *proto); void tcp_push_one(struct sock *, unsigned int mss_now); void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); @@ -1132,31 +1135,6 @@ 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 +1214,8 @@ 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) { @@ -1344,15 +1294,14 @@ struct tcp_md5sig_pool { }; /* - functions */ -int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, - const struct sock *sk, const struct request_sock *req, - const struct sk_buff *skb); +int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, + const struct sock *sk, const struct sk_buff *skb); int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, const u8 *newkey, u8 newkeylen, gfp_t gfp); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family); struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk, - struct sock *addr_sk); + const struct sock *addr_sk); #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, @@ -1663,28 +1612,26 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, struct tcp_sock_af_ops { #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *(*md5_lookup) (struct sock *sk, - struct sock *addr_sk); - int (*calc_md5_hash) (char *location, - struct tcp_md5sig_key *md5, - const struct sock *sk, - const struct request_sock *req, - const struct sk_buff *skb); - int (*md5_parse) (struct sock *sk, - char __user *optval, - int optlen); + const struct sock *addr_sk); + int (*calc_md5_hash)(char *location, + const struct tcp_md5sig_key *md5, + const struct sock *sk, + const struct sk_buff *skb); + int (*md5_parse)(struct sock *sk, + char __user *optval, + int optlen); #endif }; struct tcp_request_sock_ops { u16 mss_clamp; #ifdef CONFIG_TCP_MD5SIG - struct tcp_md5sig_key *(*md5_lookup) (struct sock *sk, - struct request_sock *req); - int (*calc_md5_hash) (char *location, - struct tcp_md5sig_key *md5, - const struct sock *sk, - const struct request_sock *req, - const struct sk_buff *skb); + struct tcp_md5sig_key *(*req_md5_lookup)(struct sock *sk, + const struct sock *addr_sk); + int (*calc_md5_hash) (char *location, + const struct tcp_md5sig_key *md5, + const struct sock *sk, + const struct sk_buff *skb); #endif void (*init_req)(struct request_sock *req, struct sock *sk, struct sk_buff *skb); 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 eabd3a038674..756e4636bad8 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -91,6 +91,7 @@ struct vxlanhdr { #define VXLAN_N_VID (1u << 24) #define VXLAN_VID_MASK (VXLAN_N_VID - 1) +#define VXLAN_VNI_MASK (VXLAN_VID_MASK << 8) #define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr)) struct vxlan_metadata { @@ -130,7 +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..461f83539493 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; @@ -1029,7 +1025,7 @@ xfrm_addr_any(const xfrm_address_t *addr, unsigned short family) case AF_INET: return addr->a4 == 0; case AF_INET6: - return ipv6_addr_any((struct in6_addr *)&addr->a6); + return ipv6_addr_any(&addr->in6); } return 0; } @@ -1242,8 +1238,8 @@ void xfrm_flowi_addr_get(const struct flowi *fl, memcpy(&daddr->a4, &fl->u.ip4.daddr, sizeof(daddr->a4)); break; case AF_INET6: - *(struct in6_addr *)saddr->a6 = fl->u.ip6.saddr; - *(struct in6_addr *)daddr->a6 = fl->u.ip6.daddr; + saddr->in6 = fl->u.ip6.saddr; + daddr->in6 = fl->u.ip6.daddr; break; } } |