diff options
| author | Dmitry Torokhov <dmitry.torokhov@gmail.com> | 2015-09-03 10:01:44 -0700 |
|---|---|---|
| committer | Dmitry Torokhov <dmitry.torokhov@gmail.com> | 2015-09-03 10:01:44 -0700 |
| commit | 01b944fe1cd4e21a2a9ed51adbdbafe2d5e905ba (patch) | |
| tree | 85f506cf9fce3d8fd47cf624dd8698472bffc13f /include/net | |
| parent | e51e38494a8ecc18650efb0c840600637891de2c (diff) | |
| parent | 58f1eae48e5372200553de07b5ecc7574803ee91 (diff) | |
Merge branch 'next' into for-linus
Prepare first round of input updates for 4.3 merge window.
Diffstat (limited to 'include/net')
96 files changed, 3213 insertions, 1473 deletions
diff --git a/include/net/9p/client.h b/include/net/9p/client.h index 6fab66c5c5af..c6b97e58cf84 100644 --- a/include/net/9p/client.h +++ b/include/net/9p/client.h @@ -211,6 +211,8 @@ struct p9_dirent { char d_name[256]; }; +struct iov_iter; + int p9_client_statfs(struct p9_fid *fid, struct p9_rstatfs *sb); int p9_client_rename(struct p9_fid *fid, struct p9_fid *newdirfid, const char *name); @@ -236,10 +238,8 @@ int p9_client_clunk(struct p9_fid *fid); int p9_client_fsync(struct p9_fid *fid, int datasync); int p9_client_remove(struct p9_fid *fid); int p9_client_unlinkat(struct p9_fid *dfid, const char *name, int flags); -int p9_client_read(struct p9_fid *fid, char *data, char __user *udata, - u64 offset, u32 count); -int p9_client_write(struct p9_fid *fid, char *data, const char __user *udata, - u64 offset, u32 count); +int p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err); +int p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err); int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset); int p9dirent_read(struct p9_client *clnt, char *buf, int len, struct p9_dirent *dirent); diff --git a/include/net/9p/transport.h b/include/net/9p/transport.h index 2a25dec30211..5122b5e40f78 100644 --- a/include/net/9p/transport.h +++ b/include/net/9p/transport.h @@ -61,7 +61,7 @@ struct p9_trans_module { int (*cancel) (struct p9_client *, struct p9_req_t *req); int (*cancelled)(struct p9_client *, struct p9_req_t *req); int (*zc_request)(struct p9_client *, struct p9_req_t *, - char *, char *, int , int, int, int); + struct iov_iter *, struct iov_iter *, int , int, int); }; void v9fs_register_trans(struct p9_trans_module *m); diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 80456f72d70a..def59d3a34d5 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -142,6 +142,7 @@ void ipv6_mc_unmap(struct inet6_dev *idev); void ipv6_mc_remap(struct inet6_dev *idev); void ipv6_mc_init_dev(struct inet6_dev *idev); void ipv6_mc_destroy_dev(struct inet6_dev *idev); +int ipv6_mc_check_mld(struct sk_buff *skb, struct sk_buff **skb_trimmed); void addrconf_dad_failure(struct inet6_ifaddr *ifp); bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, diff --git a/include/net/af_unix.h b/include/net/af_unix.h index a175ba4a7adb..4a167b30a12f 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -39,7 +39,6 @@ struct unix_skb_parms { }; #define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb)) -#define UNIXSID(skb) (&UNIXCB((skb)).secid) #define unix_state_lock(s) spin_lock(&unix_sk(s)->lock) #define unix_state_unlock(s) spin_unlock(&unix_sk(s)->lock) diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 0d87674fb775..db639a4c5ab8 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -74,7 +74,7 @@ void vsock_pending_work(struct work_struct *work); struct sock *__vsock_create(struct net *net, struct socket *sock, struct sock *parent, - gfp_t priority, unsigned short type); + gfp_t priority, unsigned short type, int kern); /**** TRANSPORT ****/ @@ -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..e602f8177ebf 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -12,6 +12,8 @@ #include <linux/list.h> #include <linux/slab.h> #include <linux/atomic.h> +#include <net/neighbour.h> +#include <net/sock.h> #define AX25_T1CLAMPLO 1 #define AX25_T1CLAMPHI (30 * HZ) @@ -245,7 +247,20 @@ typedef struct ax25_cb { atomic_t refcount; } ax25_cb; -#define ax25_sk(__sk) ((ax25_cb *)(__sk)->sk_protinfo) +struct ax25_sock { + struct sock sk; + struct ax25_cb *cb; +}; + +static inline struct ax25_sock *ax25_sk(const struct sock *sk) +{ + return (struct ax25_sock *) sk; +} + +static inline struct ax25_cb *sk_to_ax25(const struct sock *sk) +{ + return ax25_sk(sk)->cb; +} #define ax25_for_each(__ax25, list) \ hlist_for_each_entry(__ax25, list, ax25_node) @@ -366,9 +381,7 @@ 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..38d8a34d3589 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); @@ -355,8 +365,22 @@ extern struct dentry *bt_debugfs; int l2cap_init(void); void l2cap_exit(void); +#if IS_ENABLED(CONFIG_BT_BREDR) int sco_init(void); void sco_exit(void); +#else +static inline int sco_init(void) +{ + return 0; +} + +static inline void sco_exit(void) +{ +} +#endif + +int mgmt_init(void); +void mgmt_exit(void); void bt_sock_reclassify_lock(struct sock *sk, int proto); diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 8e54f825153c..7ca6690355ea 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 */ @@ -363,6 +374,7 @@ enum { /* LE features */ #define HCI_LE_ENCRYPTION 0x01 #define HCI_LE_CONN_PARAM_REQ_PROC 0x02 +#define HCI_LE_SLAVE_FEATURES 0x08 #define HCI_LE_PING 0x10 #define HCI_LE_DATA_LEN_EXT 0x20 #define HCI_LE_EXT_SCAN_POLICY 0x80 @@ -452,9 +464,16 @@ enum { #define EIR_NAME_COMPLETE 0x09 /* complete local name */ #define EIR_TX_POWER 0x0A /* transmit power level */ #define EIR_CLASS_OF_DEV 0x0D /* Class of Device */ -#define EIR_SSP_HASH_C 0x0E /* Simple Pairing Hash C */ -#define EIR_SSP_RAND_R 0x0F /* Simple Pairing Randomizer R */ +#define EIR_SSP_HASH_C192 0x0E /* Simple Pairing Hash C-192 */ +#define EIR_SSP_RAND_R192 0x0F /* Simple Pairing Randomizer R-192 */ #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_SSP_HASH_C256 0x1D /* Simple Pairing Hash C-256 */ +#define EIR_SSP_RAND_R256 0x1E /* Simple Pairing Rand R-256 */ +#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 */ @@ -1183,6 +1202,16 @@ struct hci_rp_read_clock { __le16 accuracy; } __packed; +#define HCI_OP_READ_ENC_KEY_SIZE 0x1408 +struct hci_cp_read_enc_key_size { + __le16 handle; +} __packed; +struct hci_rp_read_enc_key_size { + __u8 status; + __le16 handle; + __u8 key_size; +} __packed; + #define HCI_OP_READ_LOCAL_AMP_INFO 0x1409 struct hci_rp_read_local_amp_info { __u8 status; @@ -1358,6 +1387,11 @@ struct hci_cp_le_conn_update { __le16 max_ce_len; } __packed; +#define HCI_OP_LE_READ_REMOTE_FEATURES 0x2016 +struct hci_cp_le_read_remote_features { + __le16 handle; +} __packed; + #define HCI_OP_LE_START_ENC 0x2019 struct hci_cp_le_start_enc { __le16 handle; @@ -1850,6 +1884,13 @@ struct hci_ev_le_conn_update_complete { __le16 supervision_timeout; } __packed; +#define HCI_EV_LE_REMOTE_FEAT_COMPLETE 0x04 +struct hci_ev_le_remote_feat_complete { + __u8 status; + __le16 handle; + __u8 features[8]; +} __packed; + #define HCI_EV_LE_LTK_REQ 0x05 struct hci_ev_le_ltk_req { __le16 handle; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 52863c3e0b13..3bd618d3e55d 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 +155,23 @@ struct oob_data { u8 rand256[16]; }; +struct adv_info { + struct list_head list; + bool pending; + __u8 instance; + __u32 flags; + __u16 timeout; + __u16 remaining_time; + __u16 duration; + __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_ADV_INSTANCES 5 +#define HCI_DEFAULT_ADV_DURATION 2 + #define HCI_MAX_SHORT_NAME_LENGTH 10 /* Default LE RPA expiry time, 15 minutes */ @@ -173,7 +191,6 @@ struct amp_assoc { #define HCI_MAX_PAGES 3 -#define NUM_REASSEMBLY 4 struct hci_dev { struct list_head list; struct mutex lock; @@ -314,14 +331,13 @@ 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]; struct mutex req_lock; 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 +368,7 @@ 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 +379,12 @@ struct hci_dev { __u8 scan_rsp_data[HCI_MAX_AD_LENGTH]; __u8 scan_rsp_data_len; + struct list_head adv_instances; + unsigned int adv_instance_cnt; + __u8 cur_adv_instance; + __u16 adv_instance_timeout; + struct delayed_work adv_instance_expire; + __u8 irk[16]; __u32 rpa_timeout; struct delayed_work rpa_expired; @@ -373,6 +394,7 @@ 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); @@ -498,20 +520,42 @@ 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); +void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags); +#if IS_ENABLED(CONFIG_BT_BREDR) 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); +void sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb); +#else +static inline int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, + __u8 *flags) +{ + return 0; +} + +static inline void sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb) +{ +} +#endif /* ----- Inquiry cache ----- */ #define INQUIRY_CACHE_AGE_MAX (HZ*30) /* 30 seconds */ @@ -529,6 +573,7 @@ static inline void discovery_init(struct hci_dev *hdev) static inline void hci_discovery_filter_clear(struct hci_dev *hdev) { + hdev->discovery.result_filtering = false; hdev->discovery.report_invalid_rssi = true; hdev->discovery.rssi = HCI_RSSI_INVALID; hdev->discovery.uuid_count = 0; @@ -584,7 +629,6 @@ 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 +644,14 @@ 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 +1013,8 @@ 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); @@ -978,10 +1024,18 @@ int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type); +void hci_adv_instances_clear(struct hci_dev *hdev); +struct adv_info *hci_find_adv_instance(struct hci_dev *hdev, u8 instance); +struct adv_info *hci_get_next_instance(struct hci_dev *hdev, u8 instance); +int hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags, + u16 adv_data_len, u8 *adv_data, + u16 scan_rsp_len, u8 *scan_rsp_data, + u16 timeout, u16 duration); +int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance); + void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb); int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb); -int hci_recv_stream_fragment(struct hci_dev *hdev, void *data, int count); void hci_init_sysfs(struct hci_dev *hdev); void hci_conn_init_sysfs(struct hci_conn *conn); @@ -1025,10 +1079,10 @@ 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 +1104,6 @@ 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 +1112,69 @@ 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 +1188,27 @@ 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 +1216,12 @@ 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 +1307,6 @@ 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 +1321,35 @@ 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 +1369,6 @@ 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); @@ -1344,6 +1376,7 @@ void mgmt_set_powered_failed(struct hci_dev *hdev, int err); int mgmt_powered(struct hci_dev *hdev, u8 powered); int mgmt_update_adv_data(struct hci_dev *hdev); void mgmt_discoverable_timeout(struct hci_dev *hdev); +void mgmt_adv_timeout_expired(struct hci_dev *hdev); void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, bool persistent); void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn, @@ -1382,9 +1415,6 @@ 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); @@ -1405,7 +1435,7 @@ void mgmt_smp_complete(struct hci_conn *conn, bool complete); u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, u16 to_multiplier); void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __le64 rand, - __u8 ltk[16]); + __u8 ltk[16], __u8 key_size); void hci_copy_identity_address(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 *bdaddr_type); 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/bond_options.h b/include/net/bond_options.h index ea6546d2c946..c28aca25320e 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -63,6 +63,9 @@ enum { BOND_OPT_LP_INTERVAL, BOND_OPT_SLAVES, BOND_OPT_TLB_DYNAMIC_LB, + BOND_OPT_AD_ACTOR_SYS_PRIO, + BOND_OPT_AD_ACTOR_SYSTEM, + BOND_OPT_AD_USER_PORT_KEY, BOND_OPT_LAST }; diff --git a/include/net/bonding.h b/include/net/bonding.h index fda6feeb6c1f..20defc0353d1 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -30,13 +30,6 @@ #include <net/bond_alb.h> #include <net/bond_options.h> -#define DRV_VERSION "3.7.1" -#define DRV_RELDATE "April 27, 2011" -#define DRV_NAME "bonding" -#define DRV_DESCRIPTION "Ethernet Channel Bonding Driver" - -#define bond_version DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n" - #define BOND_MAX_ARP_TARGETS 16 #define BOND_DEFAULT_MIIMON 100 @@ -143,6 +136,9 @@ struct bond_params { int packets_per_slave; int tlb_dynamic_lb; struct reciprocal_value reciprocal_packets_per_slave; + u16 ad_actor_sys_prio; + u16 ad_user_port_key; + u8 ad_actor_system[ETH_ALEN]; }; struct bond_parm_tbl { diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 64e09e1e8099..a741678f24a2 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -111,7 +111,7 @@ enum ieee80211_band { * This may be due to the driver or due to regulatory bandwidth * restrictions. * @IEEE80211_CHAN_INDOOR_ONLY: see %NL80211_FREQUENCY_ATTR_INDOOR_ONLY - * @IEEE80211_CHAN_GO_CONCURRENT: see %NL80211_FREQUENCY_ATTR_GO_CONCURRENT + * @IEEE80211_CHAN_IR_CONCURRENT: see %NL80211_FREQUENCY_ATTR_IR_CONCURRENT * @IEEE80211_CHAN_NO_20MHZ: 20 MHz bandwidth is not permitted * on this channel. * @IEEE80211_CHAN_NO_10MHZ: 10 MHz bandwidth is not permitted @@ -129,7 +129,7 @@ enum ieee80211_channel_flags { IEEE80211_CHAN_NO_80MHZ = 1<<7, IEEE80211_CHAN_NO_160MHZ = 1<<8, IEEE80211_CHAN_INDOOR_ONLY = 1<<9, - IEEE80211_CHAN_GO_CONCURRENT = 1<<10, + IEEE80211_CHAN_IR_CONCURRENT = 1<<10, IEEE80211_CHAN_NO_20MHZ = 1<<11, IEEE80211_CHAN_NO_10MHZ = 1<<12, }; @@ -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); } @@ -4535,13 +4575,15 @@ void cfg80211_roamed_bss(struct net_device *dev, struct cfg80211_bss *bss, * @ie: information elements of the deauth/disassoc frame (may be %NULL) * @ie_len: length of IEs * @reason: reason code for the disconnection, set it to 0 if unknown + * @locally_generated: disconnection was requested locally * @gfp: allocation flags * * After it calls this function, the driver should enter an idle state * and not try to connect to any AP any more. */ void cfg80211_disconnected(struct net_device *dev, u16 reason, - const u8 *ie, size_t ie_len, gfp_t gfp); + const u8 *ie, size_t ie_len, + bool locally_generated, gfp_t gfp); /** * cfg80211_ready_on_channel - notification of remain_on_channel start @@ -4862,6 +4904,17 @@ 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 @@ -4950,6 +5003,64 @@ int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len, u8 *buf, unsigned int bufsize); /** + * ieee80211_ie_split_ric - split an IE buffer according to ordering (with RIC) + * @ies: the IE buffer + * @ielen: the length of the IE buffer + * @ids: an array with element IDs that are allowed before + * the split + * @n_ids: the size of the element ID array + * @after_ric: array IE types that come after the RIC element + * @n_after_ric: size of the @after_ric array + * @offset: offset where to start splitting in the buffer + * + * This function splits an IE buffer by updating the @offset + * variable to point to the location where the buffer should be + * split. + * + * It assumes that the given IE buffer is well-formed, this + * has to be guaranteed by the caller! + * + * It also assumes that the IEs in the buffer are ordered + * correctly, if not the result of using this function will not + * be ordered correctly either, i.e. it does no reordering. + * + * The function returns the offset where the next part of the + * buffer starts, which may be @ielen if the entire (remainder) + * of the buffer should be used. + */ +size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen, + const u8 *ids, int n_ids, + const u8 *after_ric, int n_after_ric, + size_t offset); + +/** + * ieee80211_ie_split - split an IE buffer according to ordering + * @ies: the IE buffer + * @ielen: the length of the IE buffer + * @ids: an array with element IDs that are allowed before + * the split + * @n_ids: the size of the element ID array + * @offset: offset where to start splitting in the buffer + * + * This function splits an IE buffer by updating the @offset + * variable to point to the location where the buffer should be + * split. + * + * It assumes that the given IE buffer is well-formed, this + * has to be guaranteed by the caller! + * + * It also assumes that the IEs in the buffer are ordered + * correctly, if not the result of using this function will not + * be ordered correctly either, i.e. it does no reordering. + * + * The function returns the offset where the next part of the + * buffer starts, which may be @ielen if the entire (remainder) + * of the buffer should be used. + */ +size_t ieee80211_ie_split(const u8 *ies, size_t ielen, + const u8 *ids, int n_ids, size_t offset); + +/** * cfg80211_report_wowlan_wakeup - report wakeup from WoWLAN * @wdev: the wireless device reporting the wakeup * @wakeup: the wakeup report diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index eeda67652766..290a9a69af07 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -30,11 +30,13 @@ struct wpan_phy_cca; struct cfg802154_ops { struct net_device * (*add_virtual_intf_deprecated)(struct wpan_phy *wpan_phy, const char *name, + unsigned char name_assign_type, int type); void (*del_virtual_intf_deprecated)(struct wpan_phy *wpan_phy, struct net_device *dev); int (*add_virtual_intf)(struct wpan_phy *wpan_phy, const char *name, + unsigned char name_assign_type, enum nl802154_iftype type, __le64 extended_addr); int (*del_virtual_intf)(struct wpan_phy *wpan_phy, @@ -42,6 +44,8 @@ struct cfg802154_ops { int (*set_channel)(struct wpan_phy *wpan_phy, u8 page, u8 channel); int (*set_cca_mode)(struct wpan_phy *wpan_phy, const struct wpan_phy_cca *cca); + int (*set_cca_ed_level)(struct wpan_phy *wpan_phy, s32 ed_level); + int (*set_tx_power)(struct wpan_phy *wpan_phy, s32 power); int (*set_pan_id)(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, __le16 pan_id); int (*set_short_addr)(struct wpan_phy *wpan_phy, @@ -59,14 +63,66 @@ struct cfg802154_ops { struct wpan_dev *wpan_dev, bool mode); }; +static inline bool +wpan_phy_supported_bool(bool b, enum nl802154_supported_bool_states st) +{ + switch (st) { + case NL802154_SUPPORTED_BOOL_TRUE: + return b; + case NL802154_SUPPORTED_BOOL_FALSE: + return !b; + case NL802154_SUPPORTED_BOOL_BOTH: + return true; + default: + WARN_ON(1); + } + + return false; +} + +struct wpan_phy_supported { + u32 channels[IEEE802154_MAX_PAGE + 1], + cca_modes, cca_opts, iftypes; + enum nl802154_supported_bool_states lbt; + u8 min_minbe, max_minbe, min_maxbe, max_maxbe, + min_csma_backoffs, max_csma_backoffs; + s8 min_frame_retries, max_frame_retries; + size_t tx_powers_size, cca_ed_levels_size; + const s32 *tx_powers, *cca_ed_levels; +}; + struct wpan_phy_cca { enum nl802154_cca_modes mode; enum nl802154_cca_opts opt; }; -struct wpan_phy { - struct mutex pib_lock; +static inline bool +wpan_phy_cca_cmp(const struct wpan_phy_cca *a, const struct wpan_phy_cca *b) +{ + if (a->mode != b->mode) + return false; + + if (a->mode == NL802154_CCA_ENERGY_CARRIER) + return a->opt == b->opt; + return true; +} + +/** + * @WPAN_PHY_FLAG_TRANSMIT_POWER: Indicates that transceiver will support + * transmit power setting. + * @WPAN_PHY_FLAG_CCA_ED_LEVEL: Indicates that transceiver will support cca ed + * level setting. + * @WPAN_PHY_FLAG_CCA_MODE: Indicates that transceiver will support cca mode + * setting. + */ +enum wpan_phy_flags { + WPAN_PHY_FLAG_TXPOWER = BIT(1), + WPAN_PHY_FLAG_CCA_ED_LEVEL = BIT(2), + WPAN_PHY_FLAG_CCA_MODE = BIT(3), +}; + +struct wpan_phy { /* If multiple wpan_phys are registered and you're handed e.g. * a regular netdev with assigned ieee802154_ptr, you won't * know whether it points to a wpan_phy your driver has registered @@ -75,6 +131,8 @@ struct wpan_phy { */ const void *privid; + u32 flags; + /* * This is a PIB according to 802.15.4-2011. * We do not provide timing-related variables, as they @@ -82,12 +140,14 @@ struct wpan_phy { */ u8 current_channel; u8 current_page; - u32 channels_supported[IEEE802154_MAX_PAGE + 1]; - s8 transmit_power; + struct wpan_phy_supported supported; + /* current transmit_power in mBm */ + s32 transmit_power; struct wpan_phy_cca cca; __le64 perm_extended_addr; + /* current cca ed threshold in mBm */ s32 cca_ed_level; /* PHY depended MAC PIB values */ @@ -119,9 +179,9 @@ struct wpan_dev { __le64 extended_addr; /* MAC BSN field */ - u8 bsn; + atomic_t bsn; /* MAC DSN field */ - u8 dsn; + atomic_t dsn; u8 min_be; u8 max_be; diff --git a/include/net/checksum.h b/include/net/checksum.h index 0a55ac715077..2d1d73cb773e 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -122,7 +122,9 @@ static inline __wsum csum_partial_ext(const void *buff, int len, __wsum sum) static inline void csum_replace4(__sum16 *sum, __be32 from, __be32 to) { - *sum = csum_fold(csum_add(csum_sub(~csum_unfold(*sum), from), to)); + __wsum tmp = csum_sub(~csum_unfold(*sum), (__force __wsum)from); + + *sum = csum_fold(csum_add(tmp, (__force __wsum)to)); } /* Implements RFC 1624 (Incremental Internet Checksum) diff --git a/include/net/codel.h b/include/net/codel.h index aeee28081245..267e70210061 100644 --- a/include/net/codel.h +++ b/include/net/codel.h @@ -7,7 +7,7 @@ * Copyright (C) 2011-2012 Kathleen Nichols <nichols@pollere.com> * Copyright (C) 2011-2012 Van Jacobson <van@pollere.net> * Copyright (C) 2012 Michael D. Taht <dave.taht@bufferbloat.net> - * Copyright (C) 2012 Eric Dumazet <edumazet@google.com> + * Copyright (C) 2012,2015 Eric Dumazet <edumazet@google.com> * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions @@ -119,12 +119,16 @@ static inline u32 codel_time_to_us(codel_time_t val) /** * struct codel_params - contains codel parameters * @target: target queue size (in time units) + * @ce_threshold: threshold for marking packets with ECN CE * @interval: width of moving time window + * @mtu: device mtu, or minimal queue backlog in bytes. * @ecn: is Explicit Congestion Notification enabled */ struct codel_params { codel_time_t target; + codel_time_t ce_threshold; codel_time_t interval; + u32 mtu; bool ecn; }; @@ -159,17 +163,24 @@ struct codel_vars { * @maxpacket: largest packet we've seen so far * @drop_count: temp count of dropped packets in dequeue() * ecn_mark: number of packets we ECN marked instead of dropping + * ce_mark: number of packets CE marked because sojourn time was above ce_threshold */ struct codel_stats { u32 maxpacket; u32 drop_count; u32 ecn_mark; + u32 ce_mark; }; -static void codel_params_init(struct codel_params *params) +#define CODEL_DISABLED_THRESHOLD INT_MAX + +static void codel_params_init(struct codel_params *params, + const struct Qdisc *sch) { params->interval = MS2TIME(100); params->target = MS2TIME(5); + params->mtu = psched_mtu(qdisc_dev(sch)); + params->ce_threshold = CODEL_DISABLED_THRESHOLD; params->ecn = false; } @@ -180,7 +191,7 @@ static void codel_vars_init(struct codel_vars *vars) static void codel_stats_init(struct codel_stats *stats) { - stats->maxpacket = 256; + stats->maxpacket = 0; } /* @@ -234,7 +245,7 @@ static bool codel_should_drop(const struct sk_buff *skb, stats->maxpacket = qdisc_pkt_len(skb); if (codel_time_before(vars->ldelay, params->target) || - sch->qstats.backlog <= stats->maxpacket) { + sch->qstats.backlog <= params->mtu) { /* went below - stay below for at least interval */ vars->first_above_time = 0; return false; @@ -350,6 +361,9 @@ static struct sk_buff *codel_dequeue(struct Qdisc *sch, vars->rec_inv_sqrt); } end: + if (skb && codel_time_after(vars->ldelay, params->ce_threshold) && + INET_ECN_set_ce(skb)) + stats->ce_mark++; return skb; } #endif diff --git a/include/net/compat.h b/include/net/compat.h index 42a9c8431177..48103cf94e97 100644 --- a/include/net/compat.h +++ b/include/net/compat.h @@ -40,7 +40,7 @@ int compat_sock_get_timestampns(struct sock *, struct timespec __user *); #define compat_mmsghdr mmsghdr #endif /* defined(CONFIG_COMPAT) */ -ssize_t get_compat_msghdr(struct msghdr *, struct compat_msghdr __user *, +int get_compat_msghdr(struct msghdr *, struct compat_msghdr __user *, struct sockaddr __user **, struct iovec **); asmlinkage long compat_sys_sendmsg(int, struct compat_msghdr __user *, unsigned int); 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..d0424269313f 100644 --- a/include/net/dn_neigh.h +++ b/include/net/dn_neigh.h @@ -18,10 +18,11 @@ struct dn_neigh { void dn_neigh_init(void); void dn_neigh_cleanup(void); -int dn_neigh_router_hello(struct sk_buff *skb); -int dn_neigh_endnode_hello(struct sk_buff *skb); +int dn_neigh_router_hello(struct sock *sk, struct sk_buff *skb); +int dn_neigh_endnode_hello(struct sock *sk, 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 sock *sk, 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 0fb99a26e973..2bc73f8a00a9 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -109,7 +109,6 @@ u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old); extern const u32 dst_default_metrics[]; #define DST_METRICS_READ_ONLY 0x1UL -#define DST_METRICS_FORCE_OVERWRITE 0x2UL #define DST_METRICS_FLAGS 0x3UL #define __DST_METRICS_PTR(Y) \ ((u32 *)((Y) & ~DST_METRICS_FLAGS)) @@ -120,11 +119,6 @@ static inline bool dst_metrics_read_only(const struct dst_entry *dst) return dst->_metrics & DST_METRICS_READ_ONLY; } -static inline void dst_metrics_set_force_overwrite(struct dst_entry *dst) -{ - dst->_metrics |= DST_METRICS_FORCE_OVERWRITE; -} - void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old); static inline void dst_destroy_metrics_generic(struct dst_entry *dst) @@ -355,18 +349,6 @@ static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, __skb_tunnel_rx(skb, dev, net); } -/* Children define the path of the packet through the - * Linux networking. Thus, destinations are stackable. - */ - -static inline struct dst_entry *skb_dst_pop(struct sk_buff *skb) -{ - struct dst_entry *child = dst_clone(skb_dst(skb)->child); - - skb_dst_drop(skb); - return child; -} - int dst_discard_sk(struct sock *sk, struct sk_buff *skb); static inline int dst_discard(struct sk_buff *skb) { 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..903a55efbffe 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -36,7 +36,8 @@ struct fib_lookup_arg { void *result; struct fib_rule *rule; int flags; -#define FIB_LOOKUP_NOREF 1 +#define FIB_LOOKUP_NOREF 1 +#define FIB_LOOKUP_IGNORE_LINKSTATE 2 }; struct fib_rules_ops { @@ -58,7 +59,7 @@ 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 +96,10 @@ 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/flow_dissector.h b/include/net/flow_dissector.h new file mode 100644 index 000000000000..1a8c22419936 --- /dev/null +++ b/include/net/flow_dissector.h @@ -0,0 +1,220 @@ +#ifndef _NET_FLOW_DISSECTOR_H +#define _NET_FLOW_DISSECTOR_H + +#include <linux/types.h> +#include <linux/skbuff.h> +#include <linux/in6.h> +#include <uapi/linux/if_ether.h> + +/** + * struct flow_dissector_key_control: + * @thoff: Transport header offset + */ +struct flow_dissector_key_control { + u16 thoff; + u16 addr_type; +}; + +/** + * struct flow_dissector_key_basic: + * @thoff: Transport header offset + * @n_proto: Network header protocol (eg. IPv4/IPv6) + * @ip_proto: Transport header protocol (eg. TCP/UDP) + */ +struct flow_dissector_key_basic { + __be16 n_proto; + u8 ip_proto; + u8 padding; +}; + +struct flow_dissector_key_tags { + u32 vlan_id:12, + flow_label:20; +}; + +struct flow_dissector_key_keyid { + __be32 keyid; +}; + +/** + * struct flow_dissector_key_ipv4_addrs: + * @src: source ip address + * @dst: destination ip address + */ +struct flow_dissector_key_ipv4_addrs { + /* (src,dst) must be grouped, in the same way than in IP header */ + __be32 src; + __be32 dst; +}; + +/** + * struct flow_dissector_key_ipv6_addrs: + * @src: source ip address + * @dst: destination ip address + */ +struct flow_dissector_key_ipv6_addrs { + /* (src,dst) must be grouped, in the same way than in IP header */ + struct in6_addr src; + struct in6_addr dst; +}; + +/** + * struct flow_dissector_key_tipc_addrs: + * @srcnode: source node address + */ +struct flow_dissector_key_tipc_addrs { + __be32 srcnode; +}; + +/** + * struct flow_dissector_key_addrs: + * @v4addrs: IPv4 addresses + * @v6addrs: IPv6 addresses + */ +struct flow_dissector_key_addrs { + union { + struct flow_dissector_key_ipv4_addrs v4addrs; + struct flow_dissector_key_ipv6_addrs v6addrs; + struct flow_dissector_key_tipc_addrs tipcaddrs; + }; +}; + +/** + * flow_dissector_key_tp_ports: + * @ports: port numbers of Transport header + * src: source port number + * dst: destination port number + */ +struct flow_dissector_key_ports { + union { + __be32 ports; + struct { + __be16 src; + __be16 dst; + }; + }; +}; + + +/** + * struct flow_dissector_key_eth_addrs: + * @src: source Ethernet address + * @dst: destination Ethernet address + */ +struct flow_dissector_key_eth_addrs { + /* (dst,src) must be grouped, in the same way than in ETH header */ + unsigned char dst[ETH_ALEN]; + unsigned char src[ETH_ALEN]; +}; + +enum flow_dissector_key_id { + FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */ + FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */ + FLOW_DISSECTOR_KEY_IPV4_ADDRS, /* struct flow_dissector_key_ipv4_addrs */ + FLOW_DISSECTOR_KEY_IPV6_ADDRS, /* struct flow_dissector_key_ipv6_addrs */ + FLOW_DISSECTOR_KEY_PORTS, /* struct flow_dissector_key_ports */ + FLOW_DISSECTOR_KEY_ETH_ADDRS, /* struct flow_dissector_key_eth_addrs */ + FLOW_DISSECTOR_KEY_TIPC_ADDRS, /* struct flow_dissector_key_tipc_addrs */ + FLOW_DISSECTOR_KEY_VLANID, /* struct flow_dissector_key_flow_tags */ + FLOW_DISSECTOR_KEY_FLOW_LABEL, /* struct flow_dissector_key_flow_tags */ + FLOW_DISSECTOR_KEY_GRE_KEYID, /* struct flow_dissector_key_keyid */ + FLOW_DISSECTOR_KEY_MPLS_ENTROPY, /* struct flow_dissector_key_keyid */ + + FLOW_DISSECTOR_KEY_MAX, +}; + +struct flow_dissector_key { + enum flow_dissector_key_id key_id; + size_t offset; /* offset of struct flow_dissector_key_* + in target the struct */ +}; + +struct flow_dissector { + unsigned int used_keys; /* each bit repesents presence of one key id */ + unsigned short int offset[FLOW_DISSECTOR_KEY_MAX]; +}; + +void skb_flow_dissector_init(struct flow_dissector *flow_dissector, + const struct flow_dissector_key *key, + unsigned int key_count); + +bool __skb_flow_dissect(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, + void *data, __be16 proto, int nhoff, int hlen); + +static inline bool skb_flow_dissect(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container) +{ + return __skb_flow_dissect(skb, flow_dissector, target_container, + NULL, 0, 0, 0); +} + +struct flow_keys { + struct flow_dissector_key_control control; +#define FLOW_KEYS_HASH_START_FIELD basic + struct flow_dissector_key_basic basic; + struct flow_dissector_key_tags tags; + struct flow_dissector_key_keyid keyid; + struct flow_dissector_key_ports ports; + struct flow_dissector_key_addrs addrs; +}; + +#define FLOW_KEYS_HASH_OFFSET \ + offsetof(struct flow_keys, FLOW_KEYS_HASH_START_FIELD) + +__be32 flow_get_u32_src(const struct flow_keys *flow); +__be32 flow_get_u32_dst(const struct flow_keys *flow); + +extern struct flow_dissector flow_keys_dissector; +extern struct flow_dissector flow_keys_buf_dissector; + +static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, + struct flow_keys *flow) +{ + memset(flow, 0, sizeof(*flow)); + return __skb_flow_dissect(skb, &flow_keys_dissector, flow, + NULL, 0, 0, 0); +} + +static inline bool skb_flow_dissect_flow_keys_buf(struct flow_keys *flow, + void *data, __be16 proto, + int nhoff, int hlen) +{ + memset(flow, 0, sizeof(*flow)); + return __skb_flow_dissect(NULL, &flow_keys_buf_dissector, flow, + data, proto, nhoff, hlen); +} + +__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, + void *data, int hlen_proto); + +static inline __be32 skb_flow_get_ports(const struct sk_buff *skb, + int thoff, u8 ip_proto) +{ + return __skb_flow_get_ports(skb, thoff, ip_proto, NULL, 0); +} + +u32 flow_hash_from_keys(struct flow_keys *keys); +void __skb_get_hash(struct sk_buff *skb); +u32 skb_get_poff(const struct sk_buff *skb); +u32 __skb_get_poff(const struct sk_buff *skb, void *data, + const struct flow_keys *keys, int hlen); + +/* struct flow_keys_digest: + * + * This structure is used to hold a digest of the full flow keys. This is a + * larger "hash" of a flow to allow definitively matching specific flows where + * the 32 bit skb->hash is not large enough. The size is limited to 16 bytes so + * that it can by used in CB of skb (see sch_choke for an example). + */ +#define FLOW_KEYS_DIGEST_LEN 16 +struct flow_keys_digest { + u8 data[FLOW_KEYS_DIGEST_LEN]; +}; + +void make_flow_keys_digest(struct flow_keys_digest *digest, + const struct flow_keys *flow); + +#endif diff --git a/include/net/flow_keys.h b/include/net/flow_keys.h deleted file mode 100644 index dc8fd81412bf..000000000000 --- a/include/net/flow_keys.h +++ /dev/null @@ -1,45 +0,0 @@ -#ifndef _NET_FLOW_KEYS_H -#define _NET_FLOW_KEYS_H - -/* struct flow_keys: - * @src: source ip address in case of IPv4 - * For IPv6 it contains 32bit hash of src address - * @dst: destination ip address in case of IPv4 - * For IPv6 it contains 32bit hash of dst address - * @ports: port numbers of Transport header - * port16[0]: src port number - * port16[1]: dst port number - * @thoff: Transport header offset - * @n_proto: Network header protocol (eg. IPv4/IPv6) - * @ip_proto: Transport header protocol (eg. TCP/UDP) - * All the members, except thoff, are in network byte order. - */ -struct flow_keys { - /* (src,dst) must be grouped, in the same way than in IP header */ - __be32 src; - __be32 dst; - union { - __be32 ports; - __be16 port16[2]; - }; - u16 thoff; - __be16 n_proto; - u8 ip_proto; -}; - -bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow, - void *data, __be16 proto, int nhoff, int hlen); -static inline bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow) -{ - return __skb_flow_dissect(skb, flow, NULL, 0, 0, 0); -} -__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, - void *data, int hlen_proto); -static inline __be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto) -{ - return __skb_flow_get_ports(skb, thoff, ip_proto, NULL, 0); -} -u32 flow_hash_from_keys(struct flow_keys *keys); -unsigned int flow_get_hlen(const unsigned char *data, unsigned int max_len, - __be16 protocol); -#endif 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/geneve.h b/include/net/geneve.h index 14fb8d3390b4..2a0543a1899d 100644 --- a/include/net/geneve.h +++ b/include/net/geneve.h @@ -62,6 +62,11 @@ struct genevehdr { struct geneve_opt options[]; }; +static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb) +{ + return (struct genevehdr *)(udp_hdr(skb) + 1); +} + #ifdef CONFIG_INET struct geneve_sock; diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h index 94a297052442..2c10a9f0c6d9 100644 --- a/include/net/ieee802154_netdev.h +++ b/include/net/ieee802154_netdev.h @@ -346,15 +346,15 @@ struct ieee802154_mac_params { struct wpan_phy; enum { - IEEE802154_LLSEC_PARAM_ENABLED = 1 << 0, - IEEE802154_LLSEC_PARAM_FRAME_COUNTER = 1 << 1, - IEEE802154_LLSEC_PARAM_OUT_LEVEL = 1 << 2, - IEEE802154_LLSEC_PARAM_OUT_KEY = 1 << 3, - IEEE802154_LLSEC_PARAM_KEY_SOURCE = 1 << 4, - IEEE802154_LLSEC_PARAM_PAN_ID = 1 << 5, - IEEE802154_LLSEC_PARAM_HWADDR = 1 << 6, - IEEE802154_LLSEC_PARAM_COORD_HWADDR = 1 << 7, - IEEE802154_LLSEC_PARAM_COORD_SHORTADDR = 1 << 8, + IEEE802154_LLSEC_PARAM_ENABLED = BIT(0), + IEEE802154_LLSEC_PARAM_FRAME_COUNTER = BIT(1), + IEEE802154_LLSEC_PARAM_OUT_LEVEL = BIT(2), + IEEE802154_LLSEC_PARAM_OUT_KEY = BIT(3), + IEEE802154_LLSEC_PARAM_KEY_SOURCE = BIT(4), + IEEE802154_LLSEC_PARAM_PAN_ID = BIT(5), + IEEE802154_LLSEC_PARAM_HWADDR = BIT(6), + IEEE802154_LLSEC_PARAM_COORD_HWADDR = BIT(7), + IEEE802154_LLSEC_PARAM_COORD_SHORTADDR = BIT(8), }; struct ieee802154_llsec_ops { @@ -422,16 +422,6 @@ struct ieee802154_mlme_ops { struct ieee802154_mac_params *params); struct ieee802154_llsec_ops *llsec; - - /* The fields below are required. */ - - /* - * FIXME: these should become the part of PIB/MIB interface. - * However we still don't have IB interface of any kind - */ - __le16 (*get_pan_id)(const struct net_device *dev); - __le16 (*get_short_addr)(const struct net_device *dev); - u8 (*get_dsn)(const struct net_device *dev); }; static inline struct ieee802154_mlme_ops * @@ -440,10 +430,4 @@ ieee802154_mlme_ops(const struct net_device *dev) return dev->ml_priv; } -static inline struct ieee802154_reduced_mlme_ops * -ieee802154_reduced_mlme_ops(const struct net_device *dev) -{ - return dev->ml_priv; -} - #endif 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..279f83591971 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); @@ -42,7 +41,7 @@ int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, static inline void inet_ctl_sock_destroy(struct sock *sk) { - sk_release_kernel(sk); + sock_release(sk->sk_socket); } #endif diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 5976bdecf58b..0320bbb7d7b5 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -98,7 +98,8 @@ struct inet_connection_sock { const struct tcp_congestion_ops *icsk_ca_ops; const struct inet_connection_sock_af_ops *icsk_af_ops; unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu); - __u8 icsk_ca_state:7, + __u8 icsk_ca_state:6, + icsk_ca_setsockopt:1, icsk_ca_dst_locked:1; __u8 icsk_retransmits; __u8 icsk_pending; @@ -126,10 +127,13 @@ 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; -#define ICSK_CA_PRIV_SIZE (16 * sizeof(u32)) + + u64 icsk_ca_priv[64 / sizeof(u64)]; +#define ICSK_CA_PRIV_SIZE (8 * sizeof(u64)) }; #define ICSK_TIME_RETRANS 1 /* Retransmit timer */ @@ -254,8 +258,7 @@ 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); @@ -278,18 +281,10 @@ static inline void inet_csk_reqsk_queue_add(struct sock *sk, void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout); -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); -} - 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) @@ -307,26 +302,7 @@ static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) return reqsk_queue_is_full(&inet_csk(sk)->icsk_accept_queue); } -static inline void inet_csk_reqsk_queue_unlink(struct sock *sk, - struct request_sock *req, - struct request_sock **prev) -{ - reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req, prev); -} - -static inline void inet_csk_reqsk_queue_drop(struct sock *sk, - struct request_sock *req, - struct request_sock **prev) -{ - inet_csk_reqsk_queue_unlink(sk, req, prev); - inet_csk_reqsk_queue_removed(sk, req); - reqsk_free(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_reqsk_queue_drop(struct sock *sk, struct request_sock *req); void inet_csk_destroy_sock(struct sock *sk); void inet_csk_prepare_forced_close(struct sock *sk); diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 8d1765577acc..e1300b3dd597 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -43,7 +43,7 @@ enum { * @len: total length of the original datagram * @meat: length of received fragments so far * @flags: fragment queue flags - * @max_size: (ipv4 only) maximum received fragment size with IP_DF set + * @max_size: maximum received fragment size * @net: namespace that this frag belongs to */ struct inet_frag_queue { diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index dd1950a7e273..b73c88a19dd4 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -24,7 +24,6 @@ #include <linux/spinlock.h> #include <linux/types.h> #include <linux/wait.h> -#include <linux/vmalloc.h> #include <net/inet_connection_sock.h> #include <net/inet_sock.h> @@ -76,9 +75,7 @@ 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; @@ -150,8 +147,6 @@ struct inet_hashinfo { */ struct inet_listen_hashbucket listening_hash[INET_LHTABLE_SIZE] ____cacheline_aligned_in_smp; - - atomic_t bsockets; }; static inline struct inet_ehash_bucket *inet_ehash_bucket( @@ -168,52 +163,12 @@ static inline spinlock_t *inet_ehash_lockp( return &hashinfo->ehash_locks[hash & hashinfo->ehash_locks_mask]; } -static inline int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo) -{ - unsigned int i, size = 256; -#if defined(CONFIG_PROVE_LOCKING) - unsigned int nr_pcpus = 2; -#else - unsigned int nr_pcpus = num_possible_cpus(); -#endif - if (nr_pcpus >= 4) - size = 512; - if (nr_pcpus >= 8) - size = 1024; - if (nr_pcpus >= 16) - size = 2048; - if (nr_pcpus >= 32) - size = 4096; - if (sizeof(spinlock_t) != 0) { -#ifdef CONFIG_NUMA - if (size * sizeof(spinlock_t) > PAGE_SIZE) - hashinfo->ehash_locks = vmalloc(size * sizeof(spinlock_t)); - else -#endif - hashinfo->ehash_locks = kmalloc(size * sizeof(spinlock_t), - GFP_KERNEL); - if (!hashinfo->ehash_locks) - return ENOMEM; - for (i = 0; i < size; i++) - spin_lock_init(&hashinfo->ehash_locks[i]); - } - hashinfo->ehash_locks_mask = size - 1; - return 0; -} +int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo); static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo) { - if (hashinfo->ehash_locks) { -#ifdef CONFIG_NUMA - unsigned int size = (hashinfo->ehash_locks_mask + 1) * - sizeof(spinlock_t); - if (size > PAGE_SIZE) - vfree(hashinfo->ehash_locks); - else -#endif - kfree(hashinfo->ehash_locks); - hashinfo->ehash_locks = NULL; - } + kvfree(hashinfo->ehash_locks); + hashinfo->ehash_locks = NULL; } struct inet_bind_bucket * @@ -223,8 +178,8 @@ 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 +188,7 @@ 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 +206,7 @@ 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 +341,32 @@ 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..47eb67b08abd 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 { @@ -183,6 +187,7 @@ struct inet_sock { transparent:1, mc_all:1, nodefrag:1; + __u8 bind_address_no_port:1; __u8 rcv_tos; __u8 convert_csum; int uc_index; @@ -239,18 +244,8 @@ 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..360c4802288d 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -31,67 +31,14 @@ struct inet_hashinfo; -#define INET_TWDR_RECYCLE_SLOTS_LOG 5 -#define INET_TWDR_RECYCLE_SLOTS (1 << INET_TWDR_RECYCLE_SLOTS_LOG) - -/* - * If time > 4sec, it is "slow" path, no recycling is required, - * so that we select tick to get range about 4 seconds. - */ -#if HZ <= 16 || HZ > 4096 -# error Unsupported: HZ <= 16 or HZ > 4096 -#elif HZ <= 32 -# define INET_TWDR_RECYCLE_TICK (5 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG) -#elif HZ <= 64 -# define INET_TWDR_RECYCLE_TICK (6 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG) -#elif HZ <= 128 -# define INET_TWDR_RECYCLE_TICK (7 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG) -#elif HZ <= 256 -# define INET_TWDR_RECYCLE_TICK (8 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG) -#elif HZ <= 512 -# define INET_TWDR_RECYCLE_TICK (9 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG) -#elif HZ <= 1024 -# define INET_TWDR_RECYCLE_TICK (10 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG) -#elif HZ <= 2048 -# define INET_TWDR_RECYCLE_TICK (11 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG) -#else -# define INET_TWDR_RECYCLE_TICK (12 + 2 - INET_TWDR_RECYCLE_SLOTS_LOG) -#endif - -static inline u32 inet_tw_time_stamp(void) -{ - return jiffies; -} - -/* TIME_WAIT reaping mechanism. */ -#define INET_TWDR_TWKILL_SLOTS 8 /* Please keep this a power of 2. */ - -#define INET_TWDR_TWKILL_QUOTA 100 - struct inet_timewait_death_row { - /* Short-time timewait calendar */ - int twcal_hand; - unsigned long twcal_jiffie; - struct timer_list twcal_timer; - struct hlist_head twcal_row[INET_TWDR_RECYCLE_SLOTS]; - - spinlock_t death_lock; - int tw_count; - int period; - u32 thread_slots; - struct work_struct twkill_work; - struct timer_list tw_timer; - int slot; - struct hlist_head cells[INET_TWDR_TWKILL_SLOTS]; - struct inet_hashinfo *hashinfo; + atomic_t tw_count; + + struct inet_hashinfo *hashinfo ____cacheline_aligned_in_smp; int sysctl_tw_recycle; int sysctl_max_tw_buckets; }; -void inet_twdr_hangman(unsigned long data); -void inet_twdr_twkill_work(struct work_struct *work); -void inet_twdr_twcal_tick(unsigned long data); - struct inet_bind_bucket; /* @@ -122,6 +69,7 @@ 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; @@ -132,52 +80,18 @@ struct inet_timewait_sock { __be16 tw_sport; kmemcheck_bitfield_begin(flags); /* And these are ours. */ - unsigned int tw_pad0 : 1, /* 1 bit hole */ + unsigned int tw_kill : 1, tw_transparent : 1, tw_flowlabel : 20, tw_pad : 2, /* 2 bits hole */ tw_tos : 8; kmemcheck_bitfield_end(flags); - u32 tw_ttd; + struct timer_list tw_timer; struct inet_bind_bucket *tw_tb; - struct hlist_node tw_death_node; + struct inet_timewait_death_row *tw_dr; }; #define tw_tclass tw_tos -static inline int inet_twsk_dead_hashed(const struct inet_timewait_sock *tw) -{ - return !hlist_unhashed(&tw->tw_death_node); -} - -static inline void inet_twsk_dead_node_init(struct inet_timewait_sock *tw) -{ - tw->tw_death_node.pprev = NULL; -} - -static inline void __inet_twsk_del_dead_node(struct inet_timewait_sock *tw) -{ - __hlist_del(&tw->tw_death_node); - inet_twsk_dead_node_init(tw); -} - -static inline int inet_twsk_del_dead_node(struct inet_timewait_sock *tw) -{ - if (inet_twsk_dead_hashed(tw)) { - __inet_twsk_del_dead_node(tw); - return 1; - } - return 0; -} - -#define inet_twsk_for_each(tw, node, head) \ - hlist_nulls_for_each_entry(tw, node, head, tw_node) - -#define inet_twsk_for_each_inmate(tw, jail) \ - hlist_for_each_entry(tw, jail, tw_death_node) - -#define inet_twsk_for_each_inmate_safe(tw, safe, jail) \ - hlist_for_each_entry_safe(tw, safe, jail, tw_death_node) - static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk) { return (struct inet_timewait_sock *)sk; @@ -192,16 +106,14 @@ int inet_twsk_bind_unhash(struct inet_timewait_sock *tw, struct inet_hashinfo *hashinfo); struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, + struct inet_timewait_death_row *dr, const int state); void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, struct inet_hashinfo *hashinfo); -void inet_twsk_schedule(struct inet_timewait_sock *tw, - struct inet_timewait_death_row *twdr, - const int timeo, const int timewait_len); -void inet_twsk_deschedule(struct inet_timewait_sock *tw, - struct inet_timewait_death_row *twdr); +void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo); +void inet_twsk_deschedule(struct inet_timewait_sock *tw); void inet_twsk_purge(struct inet_hashinfo *hashinfo, struct inet_timewait_death_row *twdr, int family); 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 6cc1eafb153a..0750a186ea63 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -31,7 +31,7 @@ #include <net/route.h> #include <net/snmp.h> #include <net/flow.h> -#include <net/flow_keys.h> +#include <net/flow_dissector.h> struct sock; @@ -45,6 +45,7 @@ struct inet_skb_parm { #define IPSKB_FRAG_COMPLETE BIT(3) #define IPSKB_REROUTED BIT(4) #define IPSKB_DOREDIRECT BIT(5) +#define IPSKB_FRAG_PMTU BIT(6) u16 frag_max_size; }; @@ -108,8 +109,8 @@ int ip_local_deliver(struct sk_buff *skb); int ip_mr_input(struct sk_buff *skb); int ip_output(struct sock *sk, struct sk_buff *skb); int ip_mc_output(struct sock *sk, struct sk_buff *skb); -int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)); -int ip_do_nat(struct sk_buff *skb); +int ip_do_fragment(struct sock *sk, struct sk_buff *skb, + int (*output)(struct sock *, struct sk_buff *)); void ip_send_check(struct iphdr *ip); int __ip_local_out(struct sk_buff *skb); int ip_local_out_sk(struct sock *sk, struct sk_buff *skb); @@ -318,9 +319,10 @@ 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 +339,14 @@ 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) @@ -352,15 +355,32 @@ static inline __wsum inet_compute_pseudo(struct sk_buff *skb, int proto) skb->len, proto, 0); } +/* copy IPv4 saddr & daddr to flow_keys, possibly using 64bit load/store + * Equivalent to : flow->v4addrs.src = iph->saddr; + * flow->v4addrs.dst = iph->daddr; + */ +static inline void iph_to_flow_copy_v4addrs(struct flow_keys *flow, + const struct iphdr *iph) +{ + BUILD_BUG_ON(offsetof(typeof(flow->addrs), v4addrs.dst) != + offsetof(typeof(flow->addrs), v4addrs.src) + + sizeof(flow->addrs.v4addrs.src)); + memcpy(&flow->addrs.v4addrs, &iph->saddr, sizeof(flow->addrs.v4addrs)); + flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; +} + static inline void inet_set_txhash(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); struct flow_keys keys; - keys.src = inet->inet_saddr; - keys.dst = inet->inet_daddr; - keys.port16[0] = inet->inet_sport; - keys.port16[1] = inet->inet_dport; + memset(&keys, 0, sizeof(keys)); + + keys.addrs.v4addrs.src = inet->inet_saddr; + keys.addrs.v4addrs.dst = inet->inet_daddr; + keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + keys.ports.src = inet->inet_sport; + keys.ports.dst = inet->inet_dport; sk->sk_txhash = flow_hash_from_keys(&keys); } @@ -475,6 +495,16 @@ enum ip_defrag_users { IP_DEFRAG_MACVLAN, }; +/* Return true if the value of 'user' is between 'lower_bond' + * and 'upper_bond' inclusively. + */ +static inline bool ip_defrag_user_in_between(u32 user, + enum ip_defrag_users lower_bond, + enum ip_defrag_users upper_bond) +{ + return user >= lower_bond && user <= upper_bond; +} + int ip_defrag(struct sk_buff *skb, u32 user); #ifdef CONFIG_INET struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user); diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 20e80fa7bbdd..3b76849c190f 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -120,45 +120,19 @@ struct rt6_info { struct rt6key rt6i_src; struct rt6key rt6i_prefsrc; + struct list_head rt6i_uncached; + struct uncached_list *rt6i_uncached_list; + struct inet6_dev *rt6i_idev; - unsigned long _rt6i_peer; + struct rt6_info * __percpu *rt6i_pcpu; u32 rt6i_metric; + u32 rt6i_pmtu; /* more non-fragment space at head required */ unsigned short rt6i_nfheader_len; u8 rt6i_protocol; }; -static inline struct inet_peer *rt6_peer_ptr(struct rt6_info *rt) -{ - return inetpeer_ptr(rt->_rt6i_peer); -} - -static inline bool rt6_has_peer(struct rt6_info *rt) -{ - return inetpeer_ptr_is_peer(rt->_rt6i_peer); -} - -static inline void __rt6_set_peer(struct rt6_info *rt, struct inet_peer *peer) -{ - __inetpeer_ptr_set_peer(&rt->_rt6i_peer, peer); -} - -static inline bool rt6_set_peer(struct rt6_info *rt, struct inet_peer *peer) -{ - return inetpeer_ptr_set_peer(&rt->_rt6i_peer, peer); -} - -static inline void rt6_init_peer(struct rt6_info *rt, struct inet_peer_base *base) -{ - inetpeer_init_ptr(&rt->_rt6i_peer, base); -} - -static inline void rt6_transfer_peer(struct rt6_info *rt, struct rt6_info *ort) -{ - inetpeer_transfer_peer(&rt->_rt6i_peer, &ort->_rt6i_peer); -} - static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst) { return ((struct rt6_info *)dst)->rt6i_idev; @@ -189,13 +163,12 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout) rt0->rt6i_flags |= RTF_EXPIRES; } -static inline void rt6_set_from(struct rt6_info *rt, struct rt6_info *from) +static inline u32 rt6_get_cookie(const struct rt6_info *rt) { - struct dst_entry *new = (struct dst_entry *) from; + if (rt->rt6i_flags & RTF_PCPU || unlikely(rt->dst.flags & DST_NOCACHE)) + rt = (struct rt6_info *)(rt->dst.from); - rt->rt6i_flags &= ~RTF_EXPIRES; - dst_hold(new); - rt->dst.from = new; + return rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; } static inline void ip6_rt_put(struct rt6_info *rt) diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index eda131d179d9..297629aadb19 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -145,7 +145,7 @@ static inline void __ip6_dst_store(struct sock *sk, struct dst_entry *dst, #ifdef CONFIG_IPV6_SUBTREES np->saddr_cache = saddr; #endif - np->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; + np->dst_cookie = rt6_get_cookie(rt); } static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst, @@ -163,14 +163,18 @@ static inline bool ipv6_unicast_destination(const struct sk_buff *skb) return rt->rt6i_flags & RTF_LOCAL; } -static inline bool ipv6_anycast_destination(const struct sk_buff *skb) +static inline bool ipv6_anycast_destination(const struct dst_entry *dst, + const struct in6_addr *daddr) { - struct rt6_info *rt = (struct rt6_info *) skb_dst(skb); + struct rt6_info *rt = (struct rt6_info *)dst; - return rt->rt6i_flags & RTF_ANYCAST; + return rt->rt6i_flags & RTF_ANYCAST || + (rt->rt6i_dst.plen != 128 && + ipv6_addr_equal(&rt->rt6i_dst.addr, daddr)); } -int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)); +int ip6_fragment(struct sock *sk, struct sk_buff *skb, + int (*output)(struct sock *, struct sk_buff *)); static inline int ip6_skb_dst_mtu(struct sk_buff *skb) { @@ -193,9 +197,15 @@ static inline bool ip6_sk_ignore_df(const struct sock *sk) inet6_sk(sk)->pmtudisc == IPV6_PMTUDISC_OMIT; } -static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt) +static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt, + struct in6_addr *daddr) { - return &rt->rt6i_gateway; + if (rt->rt6i_flags & RTF_GATEWAY) + return &rt->rt6i_gateway; + else if (unlikely(rt->rt6i_flags & RTF_CACHE)) + return &rt->rt6i_dst.addr; + else + return daddr; } #endif diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 76c091b53dae..b8529aa1dae7 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -71,14 +71,16 @@ __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) +static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, + struct net_device *dev) { struct net_device_stats *stats = &dev->stats; int pkt_len, err; pkt_len = skb->len; - err = ip6_local_out(skb); + err = ip6_local_out_sk(sk, skb); if (net_xmit_eval(err) == 0) { struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 5bd120e4bc0a..49c142bdf01e 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) @@ -220,16 +226,15 @@ 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_result *res, unsigned int flags) { + 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, flags | FIB_LOOKUP_NOREF)) err = 0; rcu_read_unlock(); @@ -244,33 +249,36 @@ void __net_exit fib4_rules_exit(struct net *net); struct fib_table *fib_new_table(struct net *net, u32 id); struct fib_table *fib_get_table(struct net *net, u32 id); -int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res); +int __fib_lookup(struct net *net, struct flowi4 *flp, + struct fib_result *res, unsigned int flags); static inline int fib_lookup(struct net *net, struct flowi4 *flp, - struct fib_result *res) + struct fib_result *res, unsigned int flags) { - 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; + + flags |= FIB_LOOKUP_NOREF; + if (net->ipv4.fib_has_custom_rules) + return __fib_lookup(net, flp, res, flags); + + 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, flags)) + break; + + tb = rcu_dereference_rtnl(net->ipv4.fib_default); + if (tb && !fib_table_lookup(tb, flp, res, flags)) + break; } - return __fib_lookup(net, flp, res); + + rcu_read_unlock(); + + return err; } #endif /* CONFIG_IP_MULTIPLE_TABLES */ @@ -294,17 +302,19 @@ 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); -int fib_sync_down_dev(struct net_device *dev, int force); +int fib_sync_down_dev(struct net_device *dev, unsigned long event); int fib_sync_down_addr(struct net *net, __be32 local); -int fib_sync_up(struct net_device *dev); +int fib_sync_up(struct net_device *dev, unsigned int nh_flags); 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..82dbdb092a5d 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -19,7 +19,7 @@ #include <net/if_inet6.h> #include <net/ndisc.h> #include <net/flow.h> -#include <net/flow_keys.h> +#include <net/flow_dissector.h> #include <net/snmp.h> #define SIN6_LEN_RFC2133 24 @@ -47,8 +47,6 @@ #define NEXTHDR_MAX 255 - - #define IPV6_DEFAULT_HOPLIMIT 64 #define IPV6_DEFAULT_MCASTHOPS 1 @@ -241,8 +239,10 @@ struct ip6_flowlabel { struct net *fl_net; }; -#define IPV6_FLOWINFO_MASK cpu_to_be32(0x0FFFFFFF) -#define IPV6_FLOWLABEL_MASK cpu_to_be32(0x000FFFFF) +#define IPV6_FLOWINFO_MASK cpu_to_be32(0x0FFFFFFF) +#define IPV6_FLOWLABEL_MASK cpu_to_be32(0x000FFFFF) +#define IPV6_FLOWLABEL_STATELESS_FLAG cpu_to_be32(0x00080000) + #define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK) #define IPV6_TCLASS_SHIFT 20 @@ -671,8 +671,10 @@ 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); +__be32 ipv6_select_ident(struct net *net, + const struct in6_addr *daddr, + const struct in6_addr *saddr); +void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb); int ip6_dst_hoplimit(struct dst_entry *dst); @@ -690,6 +692,20 @@ static inline int ip6_sk_dst_hoplimit(struct ipv6_pinfo *np, struct flowi6 *fl6, return hlimit; } +/* copy IPv6 saddr & daddr to flow_keys, possibly using 64bit load/store + * Equivalent to : flow->v6addrs.src = iph->saddr; + * flow->v6addrs.dst = iph->daddr; + */ +static inline void iph_to_flow_copy_v6addrs(struct flow_keys *flow, + const struct ipv6hdr *iph) +{ + BUILD_BUG_ON(offsetof(typeof(flow->addrs), v6addrs.dst) != + offsetof(typeof(flow->addrs), v6addrs.src) + + sizeof(flow->addrs.v6addrs.src)); + memcpy(&flow->addrs.v6addrs, &iph->saddr, sizeof(flow->addrs.v6addrs)); + flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; +} + #if IS_ENABLED(CONFIG_IPV6) static inline void ip6_set_txhash(struct sock *sk) { @@ -697,10 +713,15 @@ static inline void ip6_set_txhash(struct sock *sk) struct ipv6_pinfo *np = inet6_sk(sk); struct flow_keys keys; - keys.src = (__force __be32)ipv6_addr_hash(&np->saddr); - keys.dst = (__force __be32)ipv6_addr_hash(&sk->sk_v6_daddr); - keys.port16[0] = inet->inet_sport; - keys.port16[1] = inet->inet_dport; + memset(&keys, 0, sizeof(keys)); + + memcpy(&keys.addrs.v6addrs.src, &np->saddr, + sizeof(keys.addrs.v6addrs.src)); + memcpy(&keys.addrs.v6addrs.dst, &sk->sk_v6_daddr, + sizeof(keys.addrs.v6addrs.dst)); + keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + keys.ports.src = inet->inet_sport; + keys.ports.dst = inet->inet_dport; sk->sk_txhash = flow_hash_from_keys(&keys); } @@ -720,6 +741,9 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, hash ^= hash >> 12; flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK; + + if (net->ipv6.sysctl.flowlabel_state_ranges) + flowlabel |= IPV6_FLOWLABEL_STATELESS_FLAG; } return flowlabel; @@ -768,7 +792,7 @@ static inline u8 ip6_tclass(__be32 flowinfo) int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); -int ip6_rcv_finish(struct sk_buff *skb); +int ip6_rcv_finish(struct sock *sk, struct sk_buff *skb); /* * upper-layer output functions @@ -826,6 +850,7 @@ int ip6_input(struct sk_buff *skb); int ip6_mc_input(struct sk_buff *skb); int __ip6_local_out(struct sk_buff *skb); +int ip6_local_out_sk(struct sock *sk, struct sk_buff *skb); int ip6_local_out(struct sk_buff *skb); /* @@ -940,4 +965,8 @@ 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/llc_conn.h b/include/net/llc_conn.h index 0134681acc4c..fe994d2e5286 100644 --- a/include/net/llc_conn.h +++ b/include/net/llc_conn.h @@ -96,7 +96,7 @@ static __inline__ char llc_backlog_type(struct sk_buff *skb) } struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority, - struct proto *prot); + struct proto *prot, int kern); void llc_sk_free(struct sock *sk); void llc_sk_reset(struct sock *sk); diff --git a/include/net/mac80211.h b/include/net/mac80211.h index d52914b75331..6b1077c2a63f 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -84,6 +84,39 @@ * */ +/** + * DOC: mac80211 software tx queueing + * + * mac80211 provides an optional intermediate queueing implementation designed + * to allow the driver to keep hardware queues short and provide some fairness + * between different stations/interfaces. + * In this model, the driver pulls data frames from the mac80211 queue instead + * of letting mac80211 push them via drv_tx(). + * Other frames (e.g. control or management) are still pushed using drv_tx(). + * + * Drivers indicate that they use this model by implementing the .wake_tx_queue + * driver operation. + * + * Intermediate queues (struct ieee80211_txq) are kept per-sta per-tid, with a + * single per-vif queue for multicast data frames. + * + * The driver is expected to initialize its private per-queue data for stations + * and interfaces in the .add_interface and .sta_add ops. + * + * The driver can't access the queue directly. To dequeue a frame, it calls + * ieee80211_tx_dequeue(). Whenever mac80211 adds a new frame to a queue, it + * calls the .wake_tx_queue driver op. + * + * For AP powersave TIM handling, the driver only needs to indicate if it has + * buffered packets in the driver specific data structures by calling + * ieee80211_sta_set_buffered(). For frames buffered in the ieee80211_txq + * struct, mac80211 sets the appropriate TIM PVB bits and calls + * .release_buffered_frames(). + * In that callback the driver is therefore expected to release its own + * buffered frames and afterwards also frames from the ieee80211_txq (obtained + * via the usual ieee80211_tx_dequeue). + */ + struct device; /** @@ -301,17 +334,107 @@ 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 + * @BAR_RX_EVENT: a BAR was received + * @BA_FRAME_TIMEOUT: Frames were released from the reordering buffer because + * they timed out. This won't be called for each frame released, but only + * once each time the timeout triggers. + */ +enum ieee80211_event_type { + RSSI_EVENT, + MLME_EVENT, + BAR_RX_EVENT, + BA_FRAME_TIMEOUT, +}; + +/** + * 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 { +enum ieee80211_rssi_event_data { RSSI_EVENT_HIGH, RSSI_EVENT_LOW, }; /** + * struct 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, +}; + +/** + * struct 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_ba_event - data attached for BlockAck related events + * @sta: pointer to the &ieee80211_sta to which this event relates + * @tid: the tid + * @ssn: the starting sequence number (for %BAR_RX_EVENT) + */ +struct ieee80211_ba_event { + struct ieee80211_sta *sta; + u16 tid; + u16 ssn; +}; + +/** + * 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 + * @ba: relevant if &type is %BAR_RX_EVENT or %BA_FRAME_TIMEOUT + * @u:union holding the fields above + */ +struct ieee80211_event { + enum ieee80211_event_type type; + union { + struct ieee80211_rssi_event rssi; + struct ieee80211_mlme_event mlme; + struct ieee80211_ba_event ba; + } u; +}; + +/** * struct ieee80211_bss_conf - holds the BSS's changing parameters * * This structure keeps information about a BSS (and an association @@ -323,12 +446,8 @@ enum ieee80211_rssi_event { * @ibss_creator: indicates if a new IBSS network is being created * @aid: association ID number, valid only when @assoc is true * @use_cts_prot: use CTS protection - * @use_short_preamble: use 802.11b short preamble; - * if the hardware cannot handle this it must set the - * IEEE80211_HW_2GHZ_SHORT_PREAMBLE_INCAPABLE hardware flag - * @use_short_slot: use short slot time (only relevant for ERP); - * if the hardware cannot handle this it must set the - * IEEE80211_HW_2GHZ_SHORT_SLOT_INCAPABLE hardware flag + * @use_short_preamble: use 802.11b short preamble + * @use_short_slot: use short slot time (only relevant for ERP) * @dtim_period: num of beacons before the next DTIM, for beaconing, * valid in station mode only if after the driver was notified * with the %BSS_CHANGED_BEACON_INFO flag, will be non-zero then. @@ -337,12 +456,15 @@ 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 @@ -749,6 +871,9 @@ struct ieee80211_tx_info { /* 4 bytes free */ } control; struct { + u64 cookie; + } ack; + struct { struct ieee80211_tx_rate rates[IEEE80211_TX_MAX_RATES]; s32 ack_signal; u8 ampdu_ack_len; @@ -1234,6 +1359,7 @@ enum ieee80211_vif_flags { * monitor interface (if that is requested.) * @drv_priv: data area for driver use, will always be aligned to * sizeof(void *). + * @txq: the multicast data TX queue (if driver uses the TXQ abstraction) */ struct ieee80211_vif { enum nl80211_iftype type; @@ -1245,6 +1371,8 @@ struct ieee80211_vif { u8 cab_queue; u8 hw_queue[IEEE80211_NUM_ACS]; + struct ieee80211_txq *txq; + struct ieee80211_chanctx_conf __rcu *chanctx_conf; u32 driver_flags; @@ -1279,6 +1407,19 @@ 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 @@ -1337,6 +1478,9 @@ enum ieee80211_key_flags { * wants to be given when a frame is transmitted and needs to be * encrypted in hardware. * @cipher: The key's cipher suite selector. + * @tx_pn: PN used for TX on non-TKIP keys, may be used by the driver + * as well if it needs to do software PN assignment by itself + * (e.g. due to TSO) * @flags: key flags, see &enum ieee80211_key_flags. * @keyidx: the key index (0-3) * @keylen: key material length @@ -1349,6 +1493,7 @@ enum ieee80211_key_flags { * @iv_len: The IV length for this key type */ struct ieee80211_key_conf { + atomic64_t tx_pn; u32 cipher; u8 icv_len; u8 iv_len; @@ -1359,6 +1504,47 @@ struct ieee80211_key_conf { u8 key[0]; }; +#define IEEE80211_MAX_PN_LEN 16 + +/** + * struct ieee80211_key_seq - key sequence counter + * + * @tkip: TKIP data, containing IV32 and IV16 in host byte order + * @ccmp: PN data, most significant byte first (big endian, + * reverse order than in packet) + * @aes_cmac: PN data, most significant byte first (big endian, + * reverse order than in packet) + * @aes_gmac: PN data, most significant byte first (big endian, + * reverse order than in packet) + * @gcmp: PN data, most significant byte first (big endian, + * reverse order than in packet) + * @hw: data for HW-only (e.g. cipher scheme) keys + */ +struct ieee80211_key_seq { + union { + struct { + u32 iv32; + u16 iv16; + } tkip; + struct { + u8 pn[6]; + } ccmp; + struct { + u8 pn[6]; + } aes_cmac; + struct { + u8 pn[6]; + } aes_gmac; + struct { + u8 pn[6]; + } gcmp; + struct { + u8 seq[IEEE80211_MAX_PN_LEN]; + u8 seq_len; + } hw; + }; +}; + /** * struct ieee80211_cipher_scheme - cipher scheme * @@ -1472,7 +1658,8 @@ 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 +1675,8 @@ 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. + * @txq: per-TID data TX queues (if driver uses the TXQ abstraction) */ struct ieee80211_sta { u32 supp_rates[IEEE80211_NUM_BANDS]; @@ -1504,6 +1693,9 @@ struct ieee80211_sta { struct ieee80211_sta_rates __rcu *rates; bool tdls; bool tdls_initiator; + bool mfp; + + struct ieee80211_txq *txq[IEEE80211_NUM_TIDS]; /* must be last */ u8 drv_priv[0] __aligned(sizeof(void *)); @@ -1533,6 +1725,28 @@ struct ieee80211_tx_control { }; /** + * struct ieee80211_txq - Software intermediate tx queue + * + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * @sta: station table entry, %NULL for per-vif queue + * @tid: the TID for this queue (unused for per-vif queue) + * @ac: the AC for this queue + * @drv_priv: driver private area, sized by hw->txq_data_size + * + * The driver can obtain packets from this queue by calling + * ieee80211_tx_dequeue(). + */ +struct ieee80211_txq { + struct ieee80211_vif *vif; + struct ieee80211_sta *sta; + u8 tid; + u8 ac; + + /* must be last */ + u8 drv_priv[0] __aligned(sizeof(void *)); +}; + +/** * enum ieee80211_hw_flags - hardware flags * * These flags are used to indicate hardware capabilities to @@ -1566,13 +1780,6 @@ struct ieee80211_tx_control { * multicast frames when there are power saving stations so that * the driver can fetch them with ieee80211_get_buffered_bc(). * - * @IEEE80211_HW_2GHZ_SHORT_SLOT_INCAPABLE: - * Hardware is not capable of short slot operation on the 2.4 GHz band. - * - * @IEEE80211_HW_2GHZ_SHORT_PREAMBLE_INCAPABLE: - * Hardware is not capable of receiving frames with short preamble on - * the 2.4 GHz band. - * * @IEEE80211_HW_SIGNAL_UNSPEC: * Hardware can provide signal values but we don't know its units. We * expect values between 0 and @max_signal. @@ -1647,6 +1854,10 @@ struct ieee80211_tx_control { * the driver returns 1. This also forces the driver to advertise its * supported cipher suites. * + * @IEEE80211_HW_SUPPORT_FAST_XMIT: The driver/hardware supports fast-xmit, + * this currently requires only the ability to calculate the duration + * for frames. + * * @IEEE80211_HW_QUEUE_CONTROL: The driver wants to control per-interface * queue mapping in order to use different queues (not just one per AC) * for different virtual interfaces. See the doc section on HW queue @@ -1674,41 +1885,44 @@ struct ieee80211_tx_control { * @IEEE80211_HW_SUPPORTS_CLONED_SKBS: The driver will never modify the payload * or tailroom of TX skbs without copying them first. * - * @IEEE80211_SINGLE_HW_SCAN_ON_ALL_BANDS: The HW supports scanning on all bands + * @IEEE80211_HW_SINGLE_SCAN_ON_ALL_BANDS: The HW supports scanning on all bands * in one command, mac80211 doesn't have to run separate scans per band. + * + * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { - IEEE80211_HW_HAS_RATE_CONTROL = 1<<0, - IEEE80211_HW_RX_INCLUDES_FCS = 1<<1, - IEEE80211_HW_HOST_BROADCAST_PS_BUFFERING = 1<<2, - IEEE80211_HW_2GHZ_SHORT_SLOT_INCAPABLE = 1<<3, - IEEE80211_HW_2GHZ_SHORT_PREAMBLE_INCAPABLE = 1<<4, - IEEE80211_HW_SIGNAL_UNSPEC = 1<<5, - IEEE80211_HW_SIGNAL_DBM = 1<<6, - IEEE80211_HW_NEED_DTIM_BEFORE_ASSOC = 1<<7, - IEEE80211_HW_SPECTRUM_MGMT = 1<<8, - IEEE80211_HW_AMPDU_AGGREGATION = 1<<9, - IEEE80211_HW_SUPPORTS_PS = 1<<10, - IEEE80211_HW_PS_NULLFUNC_STACK = 1<<11, - IEEE80211_HW_SUPPORTS_DYNAMIC_PS = 1<<12, - IEEE80211_HW_MFP_CAPABLE = 1<<13, - IEEE80211_HW_WANT_MONITOR_VIF = 1<<14, - IEEE80211_HW_NO_AUTO_VIF = 1<<15, - IEEE80211_HW_SW_CRYPTO_CONTROL = 1<<16, - /* free slots */ - IEEE80211_HW_REPORTS_TX_ACK_STATUS = 1<<18, - IEEE80211_HW_CONNECTION_MONITOR = 1<<19, - IEEE80211_HW_QUEUE_CONTROL = 1<<20, - IEEE80211_HW_SUPPORTS_PER_STA_GTK = 1<<21, - IEEE80211_HW_AP_LINK_PS = 1<<22, - IEEE80211_HW_TX_AMPDU_SETUP_IN_HW = 1<<23, - IEEE80211_HW_SUPPORTS_RC_TABLE = 1<<24, - IEEE80211_HW_P2P_DEV_ADDR_FOR_INTF = 1<<25, - IEEE80211_HW_TIMING_BEACON_ONLY = 1<<26, - IEEE80211_HW_SUPPORTS_HT_CCK_RATES = 1<<27, - IEEE80211_HW_CHANCTX_STA_CSA = 1<<28, - IEEE80211_HW_SUPPORTS_CLONED_SKBS = 1<<29, - IEEE80211_SINGLE_HW_SCAN_ON_ALL_BANDS = 1<<30, + IEEE80211_HW_HAS_RATE_CONTROL, + IEEE80211_HW_RX_INCLUDES_FCS, + IEEE80211_HW_HOST_BROADCAST_PS_BUFFERING, + IEEE80211_HW_SIGNAL_UNSPEC, + IEEE80211_HW_SIGNAL_DBM, + IEEE80211_HW_NEED_DTIM_BEFORE_ASSOC, + IEEE80211_HW_SPECTRUM_MGMT, + IEEE80211_HW_AMPDU_AGGREGATION, + IEEE80211_HW_SUPPORTS_PS, + IEEE80211_HW_PS_NULLFUNC_STACK, + IEEE80211_HW_SUPPORTS_DYNAMIC_PS, + IEEE80211_HW_MFP_CAPABLE, + IEEE80211_HW_WANT_MONITOR_VIF, + IEEE80211_HW_NO_AUTO_VIF, + IEEE80211_HW_SW_CRYPTO_CONTROL, + IEEE80211_HW_SUPPORT_FAST_XMIT, + IEEE80211_HW_REPORTS_TX_ACK_STATUS, + IEEE80211_HW_CONNECTION_MONITOR, + IEEE80211_HW_QUEUE_CONTROL, + IEEE80211_HW_SUPPORTS_PER_STA_GTK, + IEEE80211_HW_AP_LINK_PS, + IEEE80211_HW_TX_AMPDU_SETUP_IN_HW, + IEEE80211_HW_SUPPORTS_RC_TABLE, + IEEE80211_HW_P2P_DEV_ADDR_FOR_INTF, + IEEE80211_HW_TIMING_BEACON_ONLY, + IEEE80211_HW_SUPPORTS_HT_CCK_RATES, + IEEE80211_HW_CHANCTX_STA_CSA, + IEEE80211_HW_SUPPORTS_CLONED_SKBS, + IEEE80211_HW_SINGLE_SCAN_ON_ALL_BANDS, + + /* keep last, obviously */ + NUM_IEEE80211_HW_FLAGS }; /** @@ -1756,6 +1970,8 @@ enum ieee80211_hw_flags { * within &struct ieee80211_sta. * @chanctx_data_size: size (in bytes) of the drv_priv data area * within &struct ieee80211_chanctx_conf. + * @txq_data_size: size (in bytes) of the drv_priv data area + * within @struct ieee80211_txq. * * @max_rates: maximum number of alternate rate retry stages the hw * can handle. @@ -1787,8 +2003,8 @@ enum ieee80211_hw_flags { * Use the %IEEE80211_RADIOTAP_VHT_KNOWN_* values. * * @netdev_features: netdev features to be set in each netdev created - * from this HW. Note only HW checksum features are currently - * compatible with mac80211. Other feature bits will be rejected. + * from this HW. Note that not all features are usable with mac80211, + * other features will be rejected during HW registration. * * @uapsd_queues: This bitmap is included in (re)association frame to indicate * for each access category if it is uAPSD trigger-enabled and delivery- @@ -1804,18 +2020,22 @@ enum ieee80211_hw_flags { * @n_cipher_schemes: a size of an array of cipher schemes definitions. * @cipher_schemes: a pointer to an array of cipher scheme definitions * supported by HW. + * + * @txq_ac_max_pending: maximum number of frames per AC pending in all txq + * entries for a vif. */ struct ieee80211_hw { struct ieee80211_conf conf; struct wiphy *wiphy; const char *rate_control_algorithm; void *priv; - u32 flags; + unsigned long flags[BITS_TO_LONGS(NUM_IEEE80211_HW_FLAGS)]; unsigned int extra_tx_headroom; unsigned int extra_beacon_tailroom; int vif_data_size; int sta_data_size; int chanctx_data_size; + int txq_data_size; u16 queues; u16 max_listen_interval; s8 max_signal; @@ -1832,8 +2052,23 @@ struct ieee80211_hw { u8 uapsd_max_sp_len; u8 n_cipher_schemes; const struct ieee80211_cipher_scheme *cipher_schemes; + int txq_ac_max_pending; }; +static inline bool _ieee80211_hw_check(struct ieee80211_hw *hw, + enum ieee80211_hw_flags flg) +{ + return test_bit(flg, hw->flags); +} +#define ieee80211_hw_check(hw, flg) _ieee80211_hw_check(hw, IEEE80211_HW_##flg) + +static inline void _ieee80211_hw_set(struct ieee80211_hw *hw, + enum ieee80211_hw_flags flg) +{ + return __set_bit(flg, hw->flags); +} +#define ieee80211_hw_set(hw, flg) _ieee80211_hw_set(hw, IEEE80211_HW_##flg) + /** * struct ieee80211_scan_request - hw scan request * @@ -2347,10 +2582,6 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb); * stack. It is always safe to pass more frames than requested, * but this has negative impact on power consumption. * - * @FIF_PROMISC_IN_BSS: promiscuous mode within your BSS, - * think of the BSS as your network segment and then this corresponds - * to the regular ethernet device promiscuous mode. - * * @FIF_ALLMULTI: pass all multicast frames, this is used if requested * by the user or if the hardware is not capable of filtering by * multicast address. @@ -2367,18 +2598,16 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb); * mac80211 needs to do and the amount of CPU wakeups, so you should * honour this flag if possible. * - * @FIF_CONTROL: pass control frames (except for PS Poll), if PROMISC_IN_BSS - * is not set then only those addressed to this station. + * @FIF_CONTROL: pass control frames (except for PS Poll) addressed to this + * station * * @FIF_OTHER_BSS: pass frames destined to other BSSes * - * @FIF_PSPOLL: pass PS Poll frames, if PROMISC_IN_BSS is not set then only - * those addressed to this station. + * @FIF_PSPOLL: pass PS Poll frames * * @FIF_PROBE_REQ: pass probe request frames */ enum ieee80211_filter_flags { - FIF_PROMISC_IN_BSS = 1<<0, FIF_ALLMULTI = 1<<1, FIF_FCSFAIL = 1<<2, FIF_PLCPFAIL = 1<<3, @@ -2661,9 +2890,9 @@ enum ieee80211_reconfig_type { * Returns zero if statistics are available. * The callback can sleep. * - * @get_tkip_seq: If your device implements TKIP encryption in hardware this - * callback should be provided to read the TKIP transmit IVs (both IV32 - * and IV16) for the given key from hardware. + * @get_key_seq: If your device implements encryption in hardware and does + * IV/PN assignment then this callback should be provided to read the + * IV/PN for the given key from hardware. * The callback must be atomic. * * @set_frag_threshold: Configuration of fragmentation threshold. Assign this @@ -2844,8 +3073,9 @@ 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 must be atomic. * * @release_buffered_frames: Release buffered frames according to the given * parameters. In the case where the driver buffers some frames for @@ -2993,6 +3223,8 @@ enum ieee80211_reconfig_type { * response template is provided, together with the location of the * switch-timing IE within the template. The skb can only be used within * the function call. + * + * @wake_tx_queue: Called when new packets have been added to the queue. */ struct ieee80211_ops { void (*tx)(struct ieee80211_hw *hw, @@ -3059,8 +3291,9 @@ struct ieee80211_ops { struct ieee80211_vif *vif); int (*get_stats)(struct ieee80211_hw *hw, struct ieee80211_low_level_stats *stats); - void (*get_tkip_seq)(struct ieee80211_hw *hw, u8 hw_key_idx, - u32 *iv32, u16 *iv16); + void (*get_key_seq)(struct ieee80211_hw *hw, + struct ieee80211_key_conf *key, + struct ieee80211_key_seq *seq); int (*set_frag_threshold)(struct ieee80211_hw *hw, u32 value); int (*set_rts_threshold)(struct ieee80211_hw *hw, u32 value); int (*sta_add)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, @@ -3141,9 +3374,9 @@ 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, @@ -3224,6 +3457,9 @@ struct ieee80211_ops { void (*tdls_recv_channel_switch)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_tdls_ch_sw_params *params); + + void (*wake_tx_queue)(struct ieee80211_hw *hw, + struct ieee80211_txq *txq); }; /** @@ -3305,14 +3541,15 @@ enum ieee80211_tpt_led_trigger_flags { }; #ifdef CONFIG_MAC80211_LEDS -char *__ieee80211_get_tx_led_name(struct ieee80211_hw *hw); -char *__ieee80211_get_rx_led_name(struct ieee80211_hw *hw); -char *__ieee80211_get_assoc_led_name(struct ieee80211_hw *hw); -char *__ieee80211_get_radio_led_name(struct ieee80211_hw *hw); -char *__ieee80211_create_tpt_led_trigger(struct ieee80211_hw *hw, - unsigned int flags, - const struct ieee80211_tpt_blink *blink_table, - unsigned int blink_table_len); +const char *__ieee80211_get_tx_led_name(struct ieee80211_hw *hw); +const char *__ieee80211_get_rx_led_name(struct ieee80211_hw *hw); +const char *__ieee80211_get_assoc_led_name(struct ieee80211_hw *hw); +const char *__ieee80211_get_radio_led_name(struct ieee80211_hw *hw); +const char * +__ieee80211_create_tpt_led_trigger(struct ieee80211_hw *hw, + unsigned int flags, + const struct ieee80211_tpt_blink *blink_table, + unsigned int blink_table_len); #endif /** * ieee80211_get_tx_led_name - get name of TX LED @@ -3326,7 +3563,7 @@ char *__ieee80211_create_tpt_led_trigger(struct ieee80211_hw *hw, * * Return: The name of the LED trigger. %NULL if not configured for LEDs. */ -static inline char *ieee80211_get_tx_led_name(struct ieee80211_hw *hw) +static inline const char *ieee80211_get_tx_led_name(struct ieee80211_hw *hw) { #ifdef CONFIG_MAC80211_LEDS return __ieee80211_get_tx_led_name(hw); @@ -3347,7 +3584,7 @@ static inline char *ieee80211_get_tx_led_name(struct ieee80211_hw *hw) * * Return: The name of the LED trigger. %NULL if not configured for LEDs. */ -static inline char *ieee80211_get_rx_led_name(struct ieee80211_hw *hw) +static inline const char *ieee80211_get_rx_led_name(struct ieee80211_hw *hw) { #ifdef CONFIG_MAC80211_LEDS return __ieee80211_get_rx_led_name(hw); @@ -3368,7 +3605,7 @@ static inline char *ieee80211_get_rx_led_name(struct ieee80211_hw *hw) * * Return: The name of the LED trigger. %NULL if not configured for LEDs. */ -static inline char *ieee80211_get_assoc_led_name(struct ieee80211_hw *hw) +static inline const char *ieee80211_get_assoc_led_name(struct ieee80211_hw *hw) { #ifdef CONFIG_MAC80211_LEDS return __ieee80211_get_assoc_led_name(hw); @@ -3389,7 +3626,7 @@ static inline char *ieee80211_get_assoc_led_name(struct ieee80211_hw *hw) * * Return: The name of the LED trigger. %NULL if not configured for LEDs. */ -static inline char *ieee80211_get_radio_led_name(struct ieee80211_hw *hw) +static inline const char *ieee80211_get_radio_led_name(struct ieee80211_hw *hw) { #ifdef CONFIG_MAC80211_LEDS return __ieee80211_get_radio_led_name(hw); @@ -3410,7 +3647,7 @@ static inline char *ieee80211_get_radio_led_name(struct ieee80211_hw *hw) * * Note: This function must be called before ieee80211_register_hw(). */ -static inline char * +static inline const char * ieee80211_create_tpt_led_trigger(struct ieee80211_hw *hw, unsigned int flags, const struct ieee80211_tpt_blink *blink_table, unsigned int blink_table_len) @@ -4091,40 +4328,6 @@ void ieee80211_aes_cmac_calculate_k1_k2(struct ieee80211_key_conf *keyconf, u8 *k1, u8 *k2); /** - * struct ieee80211_key_seq - key sequence counter - * - * @tkip: TKIP data, containing IV32 and IV16 in host byte order - * @ccmp: PN data, most significant byte first (big endian, - * reverse order than in packet) - * @aes_cmac: PN data, most significant byte first (big endian, - * reverse order than in packet) - * @aes_gmac: PN data, most significant byte first (big endian, - * reverse order than in packet) - * @gcmp: PN data, most significant byte first (big endian, - * reverse order than in packet) - */ -struct ieee80211_key_seq { - union { - struct { - u32 iv32; - u16 iv16; - } tkip; - struct { - u8 pn[6]; - } ccmp; - struct { - u8 pn[6]; - } aes_cmac; - struct { - u8 pn[6]; - } aes_gmac; - struct { - u8 pn[6]; - } gcmp; - }; -}; - -/** * ieee80211_get_key_tx_seq - get key TX sequence counter * * @keyconf: the parameter passed with the set key @@ -4343,13 +4546,33 @@ 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 +4587,16 @@ 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 @@ -5194,30 +5422,13 @@ int ieee80211_reserve_tid(struct ieee80211_sta *sta, u8 tid); void ieee80211_unreserve_tid(struct ieee80211_sta *sta, u8 tid); /** - * ieee80211_ie_split - split an IE buffer according to ordering - * - * @ies: the IE buffer - * @ielen: the length of the IE buffer - * @ids: an array with element IDs that are allowed before - * the split - * @n_ids: the size of the element ID array - * @offset: offset where to start splitting in the buffer - * - * This function splits an IE buffer by updating the @offset - * variable to point to the location where the buffer should be - * split. + * ieee80211_tx_dequeue - dequeue a packet from a software tx queue * - * It assumes that the given IE buffer is well-formed, this - * has to be guaranteed by the caller! - * - * It also assumes that the IEs in the buffer are ordered - * correctly, if not the result of using this function will not - * be ordered correctly either, i.e. it does no reordering. + * @hw: pointer as obtained from ieee80211_alloc_hw() + * @txq: pointer obtained from station or virtual interface * - * The function returns the offset where the next part of the - * buffer starts, which may be @ielen if the entire (remainder) - * of the buffer should be used. + * Returns the skb if successful, %NULL if no frame was available. */ -size_t ieee80211_ie_split(const u8 *ies, size_t ielen, - const u8 *ids, int n_ids, size_t offset); +struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, + struct ieee80211_txq *txq); #endif /* MAC80211_H */ diff --git a/include/net/mac802154.h b/include/net/mac802154.h index 850647811749..f534a46911dc 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> @@ -30,99 +31,122 @@ */ #define MAC802154_FRAME_HARD_HEADER_LEN (2 + 1 + 20 + 14) -/* The following flags are used to indicate changed address settings from +/** + * enum ieee802154_hw_addr_filt_flags - hardware address filtering flags + * + * The following flags are used to indicate changed address settings from * the stack to the hardware. + * + * @IEEE802154_AFILT_SADDR_CHANGED: Indicates that the short address will be + * change. + * + * @IEEE802154_AFILT_IEEEADDR_CHANGED: Indicates that the extended address + * will be change. + * + * @IEEE802154_AFILT_PANID_CHANGED: Indicates that the pan id will be change. + * + * @IEEE802154_AFILT_PANC_CHANGED: Indicates that the address filter will + * do frame address filtering as a pan coordinator. */ +enum ieee802154_hw_addr_filt_flags { + IEEE802154_AFILT_SADDR_CHANGED = BIT(0), + IEEE802154_AFILT_IEEEADDR_CHANGED = BIT(1), + IEEE802154_AFILT_PANID_CHANGED = BIT(2), + IEEE802154_AFILT_PANC_CHANGED = BIT(3), +}; -/* indicates that the Short Address changed */ -#define IEEE802154_AFILT_SADDR_CHANGED 0x00000001 -/* indicates that the IEEE Address changed */ -#define IEEE802154_AFILT_IEEEADDR_CHANGED 0x00000002 -/* indicates that the PAN ID changed */ -#define IEEE802154_AFILT_PANID_CHANGED 0x00000004 -/* indicates that PAN Coordinator status changed */ -#define IEEE802154_AFILT_PANC_CHANGED 0x00000008 - +/** + * struct ieee802154_hw_addr_filt - hardware address filtering settings + * + * @pan_id: pan_id which should be set to the hardware address filter. + * + * @short_addr: short_addr which should be set to the hardware address filter. + * + * @ieee_addr: extended address which should be set to the hardware address + * filter. + * + * @pan_coord: boolean if hardware filtering should be operate as coordinator. + */ struct ieee802154_hw_addr_filt { - __le16 pan_id; /* Each independent PAN selects a unique - * identifier. This PAN id allows communication - * between devices within a network using short - * addresses and enables transmissions between - * devices across independent networks. - */ + __le16 pan_id; __le16 short_addr; __le64 ieee_addr; - u8 pan_coord; -}; - -struct ieee802154_vif { - int type; - - /* must be last */ - u8 drv_priv[0] __aligned(sizeof(void *)); + bool pan_coord; }; +/** + * struct ieee802154_hw - ieee802154 hardware + * + * @extra_tx_headroom: headroom to reserve in each transmit skb for use by the + * driver (e.g. for transmit headers.) + * + * @flags: hardware flags, see &enum ieee802154_hw_flags + * + * @parent: parent device of the hardware. + * + * @priv: pointer to private area that was allocated for driver use along with + * this structure. + * + * @phy: This points to the &struct wpan_phy allocated for this 802.15.4 PHY. + */ struct ieee802154_hw { /* filled by the driver */ int extra_tx_headroom; u32 flags; struct device *parent; + void *priv; /* filled by mac802154 core */ - struct ieee802154_hw_addr_filt hw_filt; - void *priv; struct wpan_phy *phy; - size_t vif_data_size; }; -/* Checksum is in hardware and is omitted from a packet +/** + * enum ieee802154_hw_flags - hardware flags * - * These following flags are used to indicate hardware capabilities to + * These flags are used to indicate hardware capabilities to * the stack. Generally, flags here should have their meaning * done in a way that the simplest hardware doesn't need setting * any particular flags. There are some exceptions to this rule, * however, so you are advised to review these flags carefully. + * + * @IEEE802154_HW_TX_OMIT_CKSUM: Indicates that xmitter will add FCS on it's + * own. + * + * @IEEE802154_HW_LBT: Indicates that transceiver will support listen before + * transmit. + * + * @IEEE802154_HW_CSMA_PARAMS: Indicates that transceiver will support csma + * parameters (max_be, min_be, backoff exponents). + * + * @IEEE802154_HW_FRAME_RETRIES: Indicates that transceiver will support ARET + * frame retries setting. + * + * @IEEE802154_HW_AFILT: Indicates that transceiver will support hardware + * address filter setting. + * + * @IEEE802154_HW_PROMISCUOUS: Indicates that transceiver will support + * promiscuous mode setting. + * + * @IEEE802154_HW_RX_OMIT_CKSUM: Indicates that receiver omits FCS. + * + * @IEEE802154_HW_RX_DROP_BAD_CKSUM: Indicates that receiver will not filter + * frames with bad checksum. */ - -/* Indicates that xmitter will add FCS on it's own. */ -#define IEEE802154_HW_TX_OMIT_CKSUM 0x00000001 -/* Indicates that receiver will autorespond with ACK frames. */ -#define IEEE802154_HW_AACK 0x00000002 -/* Indicates that transceiver will support transmit power setting. */ -#define IEEE802154_HW_TXPOWER 0x00000004 -/* Indicates that transceiver will support listen before transmit. */ -#define IEEE802154_HW_LBT 0x00000008 -/* Indicates that transceiver will support cca mode setting. */ -#define IEEE802154_HW_CCA_MODE 0x00000010 -/* Indicates that transceiver will support cca ed level setting. */ -#define IEEE802154_HW_CCA_ED_LEVEL 0x00000020 -/* Indicates that transceiver will support csma (max_be, min_be, csma retries) - * settings. */ -#define IEEE802154_HW_CSMA_PARAMS 0x00000040 -/* Indicates that transceiver will support ARET frame retries setting. */ -#define IEEE802154_HW_FRAME_RETRIES 0x00000080 -/* Indicates that transceiver will support hardware address filter setting. */ -#define IEEE802154_HW_AFILT 0x00000100 -/* Indicates that transceiver will support promiscuous mode setting. */ -#define IEEE802154_HW_PROMISCUOUS 0x00000200 -/* Indicates that receiver omits FCS. */ -#define IEEE802154_HW_RX_OMIT_CKSUM 0x00000400 -/* Indicates that receiver will not filter frames with bad checksum. */ -#define IEEE802154_HW_RX_DROP_BAD_CKSUM 0x00000800 +enum ieee802154_hw_flags { + IEEE802154_HW_TX_OMIT_CKSUM = BIT(0), + IEEE802154_HW_LBT = BIT(1), + IEEE802154_HW_CSMA_PARAMS = BIT(2), + IEEE802154_HW_FRAME_RETRIES = BIT(3), + IEEE802154_HW_AFILT = BIT(4), + IEEE802154_HW_PROMISCUOUS = BIT(5), + IEEE802154_HW_RX_OMIT_CKSUM = BIT(6), + IEEE802154_HW_RX_DROP_BAD_CKSUM = BIT(7), +}; /* Indicates that receiver omits FCS and xmitter will add FCS on it's own. */ #define IEEE802154_HW_OMIT_CKSUM (IEEE802154_HW_TX_OMIT_CKSUM | \ IEEE802154_HW_RX_OMIT_CKSUM) -/* This groups the most common CSMA support fields into one. */ -#define IEEE802154_HW_CSMA (IEEE802154_HW_CCA_MODE | \ - IEEE802154_HW_CCA_ED_LEVEL | \ - IEEE802154_HW_CSMA_PARAMS) - -/* This groups the most common ARET support fields into one. */ -#define IEEE802154_HW_ARET (IEEE802154_HW_CSMA | \ - IEEE802154_HW_FRAME_RETRIES) - /* struct ieee802154_ops - callbacks from mac802154 to the driver * * This structure contains various callbacks that the driver may @@ -170,7 +194,7 @@ struct ieee802154_hw { * Returns either zero, or negative errno. * * set_txpower: - * Set radio transmit power in dB. Called with pib_lock held. + * Set radio transmit power in mBm. Called with pib_lock held. * Returns either zero, or negative errno. * * set_lbt @@ -183,7 +207,7 @@ struct ieee802154_hw { * Returns either zero, or negative errno. * * set_cca_ed_level - * Sets the CCA energy detection threshold in dBm. Called with pib_lock + * Sets the CCA energy detection threshold in mBm. Called with pib_lock * held. * Returns either zero, or negative errno. * @@ -212,12 +236,11 @@ struct ieee802154_ops { int (*set_hw_addr_filt)(struct ieee802154_hw *hw, struct ieee802154_hw_addr_filt *filt, unsigned long changed); - int (*set_txpower)(struct ieee802154_hw *hw, int db); + int (*set_txpower)(struct ieee802154_hw *hw, s32 mbm); int (*set_lbt)(struct ieee802154_hw *hw, bool on); int (*set_cca_mode)(struct ieee802154_hw *hw, const struct wpan_phy_cca *cca); - int (*set_cca_ed_level)(struct ieee802154_hw *hw, - s32 level); + int (*set_cca_ed_level)(struct ieee802154_hw *hw, s32 mbm); int (*set_csma_params)(struct ieee802154_hw *hw, u8 min_be, u8 max_be, u8 retries); int (*set_frame_retries)(struct ieee802154_hw *hw, @@ -233,9 +256,7 @@ 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); } /** @@ -245,24 +266,112 @@ 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 */ +/** + * ieee802154_alloc_hw - Allocate a new hardware device + * + * This must be called once for each hardware device. The returned pointer + * must be used to refer to this device when calling other functions. + * mac802154 allocates a private data area for the driver pointed to by + * @priv in &struct ieee802154_hw, the size of this area is given as + * @priv_data_len. + * + * @priv_data_len: length of private data + * @ops: callbacks for this device + * + * Return: A pointer to the new hardware device, or %NULL on error. + */ struct ieee802154_hw * ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops); + +/** + * ieee802154_free_hw - free hardware descriptor + * + * This function frees everything that was allocated, including the + * private data for the driver. You must call ieee802154_unregister_hw() + * before calling this function. + * + * @hw: the hardware to free + */ void ieee802154_free_hw(struct ieee802154_hw *hw); + +/** + * ieee802154_register_hw - Register hardware device + * + * You must call this function before any other functions in + * mac802154. Note that before a hardware can be registered, you + * need to fill the contained wpan_phy's information. + * + * @hw: the device to register as returned by ieee802154_alloc_hw() + * + * Return: 0 on success. An error code otherwise. + */ int ieee802154_register_hw(struct ieee802154_hw *hw); + +/** + * ieee802154_unregister_hw - Unregister a hardware device + * + * This function instructs mac802154 to free allocated resources + * and unregister netdevices from the networking subsystem. + * + * @hw: the hardware to unregister + */ void ieee802154_unregister_hw(struct ieee802154_hw *hw); +/** + * ieee802154_rx - receive frame + * + * Use this function to hand received frames to mac802154. The receive + * buffer in @skb must start with an IEEE 802.15.4 header. In case of a + * paged @skb is used, the driver is recommended to put the ieee802154 + * header of the frame on the linear part of the @skb to avoid memory + * allocation and/or memcpy by the stack. + * + * This function may not be called in IRQ context. Calls to this function + * for a single hardware must be synchronized against each other. + * + * @hw: the hardware this frame came in on + * @skb: the buffer to receive, owned by mac802154 after this call + */ void ieee802154_rx(struct ieee802154_hw *hw, struct sk_buff *skb); + +/** + * ieee802154_rx_irqsafe - receive frame + * + * Like ieee802154_rx() but can be called in IRQ context + * (internally defers to a tasklet.) + * + * @hw: the hardware this frame came in on + * @skb: the buffer to receive, owned by mac802154 after this call + * @lqi: link quality indicator + */ void ieee802154_rx_irqsafe(struct ieee802154_hw *hw, struct sk_buff *skb, u8 lqi); - +/** + * ieee802154_wake_queue - wake ieee802154 queue + * @hw: pointer as obtained from ieee802154_alloc_hw(). + * + * Drivers should use this function instead of netif_wake_queue. + */ void ieee802154_wake_queue(struct ieee802154_hw *hw); + +/** + * ieee802154_stop_queue - stop ieee802154 queue + * @hw: pointer as obtained from ieee802154_alloc_hw(). + * + * Drivers should use this function instead of netif_stop_queue. + */ void ieee802154_stop_queue(struct ieee802154_hw *hw); + +/** + * ieee802154_xmit_complete - frame transmission complete + * + * @hw: pointer as obtained from ieee802154_alloc_hw(). + * @skb: buffer for transmission + * @ifs_handling: indicate interframe space handling + */ void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb, bool ifs_handling); 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..e951453e0a23 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -26,7 +26,10 @@ #endif #include <net/netns/nftables.h> #include <net/netns/xfrm.h> +#include <net/netns/mpls.h> #include <linux/ns_common.h> +#include <linux/idr.h> +#include <linux/skbuff.h> struct user_namespace; struct proc_dir_entry; @@ -48,18 +51,16 @@ 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 */ struct user_namespace *user_ns; /* Owning user namespace */ + spinlock_t nsid_lock; struct idr netns_ids; struct ns_common ns; @@ -130,6 +131,9 @@ 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 +234,27 @@ 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) @@ -291,7 +274,9 @@ static inline struct net *read_pnet(struct net * const *pnet) #define __net_initconst __initconst #endif +int peernet2id_alloc(struct net *net, struct net *peer); int peernet2id(struct net *net, struct net *peer); +bool peernet_has_id(struct net *net, struct net *peer); struct net *get_net_ns_by_id(struct net *net, int id); struct pernet_operations { diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h index 2aa6048a55c1..bab824bde92c 100644 --- a/include/net/netfilter/br_netfilter.h +++ b/include/net/netfilter/br_netfilter.h @@ -1,6 +1,66 @@ #ifndef _BR_NETFILTER_H_ #define _BR_NETFILTER_H_ +#include "../../../net/bridge/br_private.h" + +static inline struct nf_bridge_info *nf_bridge_alloc(struct sk_buff *skb) +{ + skb->nf_bridge = kzalloc(sizeof(struct nf_bridge_info), GFP_ATOMIC); + + if (likely(skb->nf_bridge)) + atomic_set(&(skb->nf_bridge->use), 1); + + return skb->nf_bridge; +} + +void nf_bridge_update_protocol(struct sk_buff *skb); + +static inline struct nf_bridge_info * +nf_bridge_info_get(const struct sk_buff *skb) +{ + return skb->nf_bridge; +} + +unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb); + +static inline void nf_bridge_push_encap_header(struct sk_buff *skb) +{ + unsigned int len = nf_bridge_encap_header_len(skb); + + skb_push(skb, len); + skb->network_header -= len; +} + +int br_nf_pre_routing_finish_bridge(struct sock *sk, struct sk_buff *skb); + +static inline struct rtable *bridge_parent_rtable(const struct net_device *dev) +{ + struct net_bridge_port *port; + + port = br_port_get_rcu(dev); + return port ? &port->br->fake_rtable : NULL; +} + +struct net_device *setup_pre_routing(struct sk_buff *skb); void br_netfilter_enable(void); +#if IS_ENABLED(CONFIG_IPV6) +int br_validate_ipv6(struct sk_buff *skb); +unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops, + struct sk_buff *skb, + const struct nf_hook_state *state); +#else +static inline int br_validate_ipv6(struct sk_buff *skb) +{ + return -1; +} + +static inline unsigned int +br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + return NF_DROP; +} +#endif + #endif /* _BR_NETFILTER_H_ */ 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_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..e8635854a55b 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 */ }; @@ -28,6 +24,8 @@ struct nf_queue_entry { struct nf_queue_handler { int (*outfn)(struct nf_queue_entry *entry, unsigned int queuenum); + void (*nf_hook_drop)(struct net *net, + struct nf_hook_ops *ops); }; void nf_register_queue_handler(const struct nf_queue_handler *qh); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index decb9a095ae7..2a246680a6c3 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1,6 +1,7 @@ #ifndef _NET_NF_TABLES_H #define _NET_NF_TABLES_H +#include <linux/module.h> #include <linux/list.h> #include <linux/netfilter.h> #include <linux/netfilter/nfnetlink.h> @@ -26,40 +27,53 @@ 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; } +/** + * struct nft_verdict - nf_tables verdict + * + * @code: nf_tables/netfilter verdict code + * @chain: destination chain for NFT_JUMP/NFT_GOTO + */ +struct nft_verdict { + u32 code; + struct nft_chain *chain; +}; + struct nft_data { union { - u32 data[4]; - struct { - u32 verdict; - struct nft_chain *chain; - }; + u32 data[4]; + struct nft_verdict verdict; }; } __attribute__((aligned(__alignof__(u64)))); -static inline int nft_data_cmp(const struct nft_data *d1, - const struct nft_data *d2, - unsigned int len) -{ - return memcmp(d1->data, d2->data, len); -} +/** + * struct nft_regs - nf_tables register set + * + * @data: data registers + * @verdict: verdict register + * + * The first four data registers alias to the verdict register. + */ +struct nft_regs { + union { + u32 data[20]; + struct nft_verdict verdict; + }; +}; -static inline void nft_data_copy(struct nft_data *dst, - const struct nft_data *src) +static inline void nft_data_copy(u32 *dst, const struct nft_data *src, + unsigned int len) { - BUILD_BUG_ON(__alignof__(*dst) != __alignof__(u64)); - *(u64 *)&dst->data[0] = *(u64 *)&src->data[0]; - *(u64 *)&dst->data[2] = *(u64 *)&src->data[2]; + memcpy(dst, src, len); } static inline void nft_data_debug(const struct nft_data *data) @@ -97,7 +111,8 @@ struct nft_data_desc { unsigned int len; }; -int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data, +int nft_data_init(const struct nft_ctx *ctx, + struct nft_data *data, unsigned int size, struct nft_data_desc *desc, const struct nlattr *nla); void nft_data_uninit(const struct nft_data *data, enum nft_data_types type); int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data, @@ -113,12 +128,14 @@ static inline enum nft_registers nft_type_to_reg(enum nft_data_types type) return type == NFT_DATA_VERDICT ? NFT_REG_VERDICT : NFT_REG_1; } -int nft_validate_input_register(enum nft_registers reg); -int nft_validate_output_register(enum nft_registers reg); -int nft_validate_data_load(const struct nft_ctx *ctx, enum nft_registers reg, - const struct nft_data *data, - enum nft_data_types type); +unsigned int nft_parse_register(const struct nlattr *attr); +int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg); +int nft_validate_register_load(enum nft_registers reg, unsigned int len); +int nft_validate_register_store(const struct nft_ctx *ctx, + enum nft_registers reg, + const struct nft_data *data, + enum nft_data_types type, unsigned int len); /** * struct nft_userdata - user defined data associated with an object @@ -138,19 +155,15 @@ struct nft_userdata { /** * 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; + union { + u32 buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)]; + struct nft_data val; + } key; + void *priv; }; struct nft_set; @@ -202,11 +215,16 @@ struct nft_set_estimate { enum nft_set_class class; }; +struct nft_set_ext; +struct nft_expr; + /** * 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 @@ -214,16 +232,28 @@ 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 u32 *key, + const struct nft_set_ext **ext); + bool (*update)(struct nft_set *set, + const u32 *key, + void *(*new)(struct nft_set *, + const struct nft_expr *, + struct nft_regs *), + const struct nft_expr *expr, + struct nft_regs *regs, + 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, @@ -241,6 +271,7 @@ struct nft_set_ops { struct list_head list; struct module *owner; + unsigned int elemsize; u32 features; }; @@ -257,8 +288,12 @@ void nft_unregister_set(struct nft_set_ops *ops); * @dtype: data type (verdict or numeric type defined by userspace) * @size: maximum set size * @nelems: number of elements + * @ndeact: number of deactivated elements queued for removal + * @timeout: default timeout value in msecs + * @gc_int: garbage collection interval in msecs * @policy: set parameterization (see enum nft_set_policies) * @ops: set ops + * @pnet: network namespace * @flags: set flags * @klen: key length * @dlen: data length @@ -271,10 +306,14 @@ struct nft_set { u32 ktype; u32 dtype; u32 size; - u32 nelems; + atomic_t nelems; + u32 ndeact; + u64 timeout; + u32 gc_int; u16 policy; /* runtime data below here */ const struct nft_set_ops *ops ____cacheline_aligned; + possible_net_t pnet; u16 flags; u8 klen; u8 dlen; @@ -287,16 +326,27 @@ static inline void *nft_set_priv(const struct nft_set *set) return (void *)set->data; } +static inline struct nft_set *nft_set_container_of(const void *priv) +{ + return (void *)priv - offsetof(struct nft_set, data); +} + struct nft_set *nf_tables_set_lookup(const struct nft_table *table, const struct nlattr *nla); struct nft_set *nf_tables_set_lookup_byid(const struct net *net, const struct nlattr *nla); +static inline unsigned long nft_set_gc_interval(const struct nft_set *set) +{ + return set->gc_int ? msecs_to_jiffies(set->gc_int) : HZ; +} + /** * struct nft_set_binding - nf_tables set binding * * @list: set bindings list node * @chain: chain containing the rule bound to the set + * @flags: set action flags * * A set binding contains all information necessary for validation * of new elements added to a bound set. @@ -304,6 +354,7 @@ struct nft_set *nf_tables_set_lookup_byid(const struct net *net, struct nft_set_binding { struct list_head list; const struct nft_chain *chain; + u32 flags; }; int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, @@ -311,6 +362,215 @@ 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_TIMEOUT: element timeout + * @NFT_SET_EXT_EXPIRATION: element expiration time + * @NFT_SET_EXT_USERDATA: user data associated with the element + * @NFT_SET_EXT_EXPR: expression assiociated with the element + * @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_TIMEOUT, + NFT_SET_EXT_EXPIRATION, + NFT_SET_EXT_USERDATA, + NFT_SET_EXT_EXPR, + 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 u64 *nft_set_ext_timeout(const struct nft_set_ext *ext) +{ + return nft_set_ext(ext, NFT_SET_EXT_TIMEOUT); +} + +static inline unsigned long *nft_set_ext_expiration(const struct nft_set_ext *ext) +{ + return nft_set_ext(ext, NFT_SET_EXT_EXPIRATION); +} + +static inline struct nft_userdata *nft_set_ext_userdata(const struct nft_set_ext *ext) +{ + return nft_set_ext(ext, NFT_SET_EXT_USERDATA); +} + +static inline struct nft_expr *nft_set_ext_expr(const struct nft_set_ext *ext) +{ + return nft_set_ext(ext, NFT_SET_EXT_EXPR); +} + +static inline bool nft_set_elem_expired(const struct nft_set_ext *ext) +{ + return nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION) && + time_is_before_eq_jiffies(*nft_set_ext_expiration(ext)); +} + +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_init(const struct nft_set *set, + const struct nft_set_ext_tmpl *tmpl, + const u32 *key, const u32 *data, + u64 timeout, gfp_t gfp); +void nft_set_elem_destroy(const struct nft_set *set, void *elem); + +/** + * struct nft_set_gc_batch_head - nf_tables set garbage collection batch + * + * @rcu: rcu head + * @set: set the elements belong to + * @cnt: count of elements + */ +struct nft_set_gc_batch_head { + struct rcu_head rcu; + const struct nft_set *set; + unsigned int cnt; +}; + +#define NFT_SET_GC_BATCH_SIZE ((PAGE_SIZE - \ + sizeof(struct nft_set_gc_batch_head)) / \ + sizeof(void *)) + +/** + * struct nft_set_gc_batch - nf_tables set garbage collection batch + * + * @head: GC batch head + * @elems: garbage collection elements + */ +struct nft_set_gc_batch { + struct nft_set_gc_batch_head head; + void *elems[NFT_SET_GC_BATCH_SIZE]; +}; + +struct nft_set_gc_batch *nft_set_gc_batch_alloc(const struct nft_set *set, + gfp_t gfp); +void nft_set_gc_batch_release(struct rcu_head *rcu); + +static inline void nft_set_gc_batch_complete(struct nft_set_gc_batch *gcb) +{ + if (gcb != NULL) + call_rcu(&gcb->head.rcu, nft_set_gc_batch_release); +} + +static inline struct nft_set_gc_batch * +nft_set_gc_batch_check(const struct nft_set *set, struct nft_set_gc_batch *gcb, + gfp_t gfp) +{ + if (gcb != NULL) { + if (gcb->head.cnt + 1 < ARRAY_SIZE(gcb->elems)) + return gcb; + nft_set_gc_batch_complete(gcb); + } + return nft_set_gc_batch_alloc(set, gfp); +} + +static inline void nft_set_gc_batch_add(struct nft_set_gc_batch *gcb, + void *elem) +{ + gcb->elems[gcb->head.cnt++] = elem; +} /** * struct nft_expr_type - nf_tables expression type @@ -323,6 +583,7 @@ void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, * @policy: netlink attribute policy * @maxattr: highest netlink attribute number * @family: address family for AF-specific types + * @flags: expression type flags */ struct nft_expr_type { const struct nft_expr_ops *(*select_ops)(const struct nft_ctx *, @@ -334,8 +595,11 @@ struct nft_expr_type { const struct nla_policy *policy; unsigned int maxattr; u8 family; + u8 flags; }; +#define NFT_EXPR_STATEFUL 0x1 + /** * struct nft_expr_ops - nf_tables expression operations * @@ -351,7 +615,7 @@ struct nft_expr_type { struct nft_expr; struct nft_expr_ops { void (*eval)(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt); unsigned int size; @@ -389,6 +653,18 @@ static inline void *nft_expr_priv(const struct nft_expr *expr) return (void *)expr->data; } +struct nft_expr *nft_expr_init(const struct nft_ctx *ctx, + const struct nlattr *nla); +void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr); +int nft_expr_dump(struct sk_buff *skb, unsigned int attr, + const struct nft_expr *expr); + +static inline void nft_expr_clone(struct nft_expr *dst, struct nft_expr *src) +{ + __module_get(src->ops->type->owner); + memcpy(dst, src, src->ops->size); +} + /** * struct nft_rule - nf_tables rule * @@ -409,74 +685,6 @@ struct nft_rule { __attribute__((aligned(__alignof__(struct nft_expr)))); }; -/** - * struct nft_trans - nf_tables object update in transaction - * - * @list: used internally - * @msg_type: message type - * @ctx: transaction context - * @data: internal information related to the transaction - */ -struct nft_trans { - struct list_head list; - int msg_type; - struct nft_ctx ctx; - char data[0]; -}; - -struct nft_trans_rule { - struct nft_rule *rule; -}; - -#define nft_trans_rule(trans) \ - (((struct nft_trans_rule *)trans->data)->rule) - -struct nft_trans_set { - struct nft_set *set; - u32 set_id; -}; - -#define nft_trans_set(trans) \ - (((struct nft_trans_set *)trans->data)->set) -#define nft_trans_set_id(trans) \ - (((struct nft_trans_set *)trans->data)->set_id) - -struct nft_trans_chain { - bool update; - char name[NFT_CHAIN_MAXNAMELEN]; - struct nft_stats __percpu *stats; - u8 policy; -}; - -#define nft_trans_chain_update(trans) \ - (((struct nft_trans_chain *)trans->data)->update) -#define nft_trans_chain_name(trans) \ - (((struct nft_trans_chain *)trans->data)->name) -#define nft_trans_chain_stats(trans) \ - (((struct nft_trans_chain *)trans->data)->stats) -#define nft_trans_chain_policy(trans) \ - (((struct nft_trans_chain *)trans->data)->policy) - -struct nft_trans_table { - bool update; - bool enable; -}; - -#define nft_trans_table_update(trans) \ - (((struct nft_trans_table *)trans->data)->update) -#define nft_trans_table_enable(trans) \ - (((struct nft_trans_table *)trans->data)->enable) - -struct nft_trans_elem { - struct nft_set *set; - struct nft_set_elem elem; -}; - -#define nft_trans_elem_set(trans) \ - (((struct nft_trans_elem *)trans->data)->set) -#define nft_trans_elem(trans) \ - (((struct nft_trans_elem *)trans->data)->elem) - static inline struct nft_expr *nft_expr_first(const struct nft_rule *rule) { return (struct nft_expr *)&rule->data[0]; @@ -517,7 +725,6 @@ 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 @@ -528,7 +735,6 @@ 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; @@ -544,6 +750,25 @@ 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, @@ -556,22 +781,28 @@ struct nft_stats { }; #define NFT_HOOK_OPS_MAX 2 +#define NFT_BASECHAIN_DISABLED (1 << 0) /** * 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 * @chain: the chain + * @dev_name: device name that this base chain is attached to (if any) */ 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; + u8 flags; struct nft_stats __percpu *stats; struct nft_chain chain; + char dev_name[IFNAMSIZ]; }; static inline struct nft_base_chain *nft_base_chain(const struct nft_chain *chain) @@ -579,6 +810,11 @@ static inline struct nft_base_chain *nft_base_chain(const struct nft_chain *chai return container_of(chain, struct nft_base_chain, chain); } +int nft_register_basechain(struct nft_base_chain *basechain, + unsigned int hook_nops); +void nft_unregister_basechain(struct nft_base_chain *basechain, + unsigned int hook_nops); + unsigned int nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops); @@ -600,7 +836,11 @@ struct nft_table { u64 hgenerator; u32 use; u16 flags; - char name[]; + char name[NFT_TABLE_MAXNAMELEN]; +}; + +enum nft_af_flags { + NFT_AF_NEEDS_DEV = (1 << 0), }; /** @@ -611,6 +851,7 @@ struct nft_table { * @nhooks: number of hooks in this family * @owner: module owner * @tables: used internally + * @flags: family flags * @nops: number of hook ops in this family * @hook_ops_init: initialization function for chain hook ops * @hooks: hookfn overrides for packet validation @@ -621,6 +862,7 @@ struct nft_af_info { unsigned int nhooks; struct module *owner; struct list_head tables; + u32 flags; unsigned int nops; void (*hook_ops_init)(struct nf_hook_ops *, unsigned int); @@ -630,25 +872,6 @@ struct nft_af_info { int nft_register_afinfo(struct net *, struct nft_af_info *); void nft_unregister_afinfo(struct nft_af_info *); -/** - * struct nf_chain_type - nf_tables chain type info - * - * @name: name of the type - * @type: numeric identifier - * @family: address family - * @owner: module owner - * @hook_mask: mask of valid hooks - * @hooks: hookfn overrides - */ -struct nf_chain_type { - const char *name; - enum nft_chain_type type; - int family; - struct module *owner; - unsigned int hook_mask; - nf_hookfn *hooks[NF_MAX_HOOKS]; -}; - int nft_register_chain_type(const struct nf_chain_type *); void nft_unregister_chain_type(const struct nf_chain_type *); @@ -673,4 +896,153 @@ 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); +} + +#define NFT_GENMASK_ANY ((1 << 0) | (1 << 1)) + +/* + * 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)); +} + +/* + * We use a free bit in the genmask field to indicate the element + * is busy, meaning it is currently being processed either by + * the netlink API or GC. + * + * Even though the genmask is only a single byte wide, this works + * because the extension structure if fully constant once initialized, + * so there are no non-atomic write accesses unless it is already + * marked busy. + */ +#define NFT_SET_ELEM_BUSY_MASK (1 << 2) + +#if defined(__LITTLE_ENDIAN_BITFIELD) +#define NFT_SET_ELEM_BUSY_BIT 2 +#elif defined(__BIG_ENDIAN_BITFIELD) +#define NFT_SET_ELEM_BUSY_BIT (BITS_PER_LONG - BITS_PER_BYTE + 2) +#else +#error +#endif + +static inline int nft_set_elem_mark_busy(struct nft_set_ext *ext) +{ + unsigned long *word = (unsigned long *)ext; + + BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0); + return test_and_set_bit(NFT_SET_ELEM_BUSY_BIT, word); +} + +static inline void nft_set_elem_clear_busy(struct nft_set_ext *ext) +{ + unsigned long *word = (unsigned long *)ext; + + clear_bit(NFT_SET_ELEM_BUSY_BIT, word); +} + +/** + * 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_core.h b/include/net/netfilter/nf_tables_core.h index a75fc8e27cd6..c6f400cfaac8 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -31,6 +31,9 @@ void nft_cmp_module_exit(void); int nft_lookup_module_init(void); void nft_lookup_module_exit(void); +int nft_dynset_module_init(void); +void nft_dynset_module_exit(void); + int nft_bitwise_module_init(void); void nft_bitwise_module_exit(void); 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/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h index 0ee47c3e2e31..711887a09e91 100644 --- a/include/net/netfilter/nft_meta.h +++ b/include/net/netfilter/nft_meta.h @@ -26,11 +26,11 @@ int nft_meta_set_dump(struct sk_buff *skb, const struct nft_expr *expr); void nft_meta_get_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt); void nft_meta_set_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], + struct nft_regs *regs, const struct nft_pktinfo *pkt); #endif 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/generic.h b/include/net/netns/generic.h index 0931618c0f7f..70e158551704 100644 --- a/include/net/netns/generic.h +++ b/include/net/netns/generic.h @@ -38,11 +38,9 @@ static inline void *net_generic(const struct net *net, int id) rcu_read_lock(); ng = rcu_dereference(net->gen); - BUG_ON(id == 0 || id > ng->len); ptr = ng->ptr[id - 1]; rcu_read_unlock(); - BUG_ON(!ptr); return ptr; } #endif 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..c68926b4899c 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; @@ -18,6 +19,7 @@ struct sock; struct local_ports { seqlock_t lock; int range[2]; + bool warned; }; struct ping_group_range { @@ -38,21 +40,21 @@ 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 @@ -76,6 +78,8 @@ struct netns_ipv4 { struct local_ports ip_local_ports; int sysctl_tcp_ecn; + int sysctl_tcp_ecn_fallback; + int sysctl_ip_no_pmtu_disc; int sysctl_ip_fwd_use_pmtu; int sysctl_ip_nonlocal_bind; @@ -84,6 +88,8 @@ 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..8d93544a2d2b 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -32,6 +32,9 @@ struct netns_sysctl_ipv6 { int icmpv6_time; int anycast_src_echo_reply; int fwmark_reflect; + int idgen_retries; + int idgen_delay; + int flowlabel_state_ranges; }; struct netns_ipv6 { @@ -67,6 +70,7 @@ 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/netfilter.h b/include/net/netns/netfilter.h index 88740024ccf3..532e4ba64f49 100644 --- a/include/net/netns/netfilter.h +++ b/include/net/netns/netfilter.h @@ -1,9 +1,9 @@ #ifndef __NETNS_NETFILTER_H #define __NETNS_NETFILTER_H -#include <linux/proc_fs.h> -#include <linux/netfilter.h> +#include <linux/netfilter_defs.h> +struct proc_dir_entry; struct nf_logger; struct netns_nf { diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h index eee608b12cc9..c80781146019 100644 --- a/include/net/netns/nftables.h +++ b/include/net/netns/nftables.h @@ -13,6 +13,7 @@ struct netns_nftables { struct nft_af_info *inet; struct nft_af_info *arp; struct nft_af_info *bridge; + struct nft_af_info *netdev; unsigned int base_seq; u8 gencursor; }; diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h index 3573a81815ad..8ba379f9e467 100644 --- a/include/net/netns/sctp.h +++ b/include/net/netns/sctp.h @@ -31,6 +31,7 @@ struct netns_sctp { struct list_head addr_waitq; struct timer_list addr_wq_timer; struct list_head auto_asconf_splist; + /* Lock that protects both addr_waitq and auto_asconf_splist */ spinlock_t addr_wq_lock; /* Lock that protects the local_addr_list writers */ diff --git a/include/net/netns/x_tables.h b/include/net/netns/x_tables.h index c24060ee411e..c8a7681efa6a 100644 --- a/include/net/netns/x_tables.h +++ b/include/net/netns/x_tables.h @@ -2,13 +2,14 @@ #define __NETNS_X_TABLES_H #include <linux/list.h> -#include <linux/netfilter.h> +#include <linux/netfilter_defs.h> 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/nfc/hci.h b/include/net/nfc/hci.h index ab672b537dd4..316694dafa5b 100644 --- a/include/net/nfc/hci.h +++ b/include/net/nfc/hci.h @@ -83,6 +83,10 @@ struct nfc_hci_pipe { }; #define NFC_HCI_MAX_CUSTOM_GATES 50 +/* + * According to specification 102 622 chapter 4.4 Pipes, + * the pipe identifier is 7 bits long. + */ #define NFC_HCI_MAX_PIPES 127 struct nfc_hci_init_data { u8 gate_count; @@ -175,6 +179,13 @@ void nfc_hci_unregister_device(struct nfc_hci_dev *hdev); void nfc_hci_set_clientdata(struct nfc_hci_dev *hdev, void *clientdata); void *nfc_hci_get_clientdata(struct nfc_hci_dev *hdev); +static inline int nfc_hci_set_vendor_cmds(struct nfc_hci_dev *hdev, + struct nfc_vendor_cmd *cmds, + int n_cmds) +{ + return nfc_set_vendor_cmds(hdev->ndev, cmds, n_cmds); +} + void nfc_hci_driver_failure(struct nfc_hci_dev *hdev, int err); int nfc_hci_result_to_errno(u8 result); diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h index a2f2f3d3196d..75d2e1880059 100644 --- a/include/net/nfc/nci.h +++ b/include/net/nfc/nci.h @@ -35,6 +35,7 @@ #define NCI_MAX_NUM_RF_CONFIGS 10 #define NCI_MAX_NUM_CONN 10 #define NCI_MAX_PARAM_LEN 251 +#define NCI_MAX_PACKET_SIZE 258 /* NCI Status Codes */ #define NCI_STATUS_OK 0x00 diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index ff87f8611fa3..01fc8c531115 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -31,6 +31,7 @@ #include <linux/interrupt.h> #include <linux/skbuff.h> +#include <linux/tty.h> #include <net/nfc/nfc.h> #include <net/nfc/nci.h> @@ -66,11 +67,19 @@ enum nci_state { struct nci_dev; +struct nci_prop_ops { + __u16 opcode; + int (*rsp)(struct nci_dev *dev, struct sk_buff *skb); + int (*ntf)(struct nci_dev *dev, struct sk_buff *skb); +}; + struct nci_ops { + int (*init)(struct nci_dev *ndev); int (*open)(struct nci_dev *ndev); int (*close)(struct nci_dev *ndev); int (*send)(struct nci_dev *ndev, struct sk_buff *skb); int (*setup)(struct nci_dev *ndev); + int (*fw_download)(struct nci_dev *ndev, const char *firmware_name); __u32 (*get_rfprotocol)(struct nci_dev *ndev, __u8 rf_protocol); int (*discover_se)(struct nci_dev *ndev); int (*disable_se)(struct nci_dev *ndev, u32 se_idx); @@ -83,12 +92,16 @@ struct nci_ops { struct sk_buff *skb); void (*hci_cmd_received)(struct nci_dev *ndev, u8 pipe, u8 cmd, struct sk_buff *skb); + + struct nci_prop_ops *prop_ops; + size_t n_prop_ops; }; #define NCI_MAX_SUPPORTED_RF_INTERFACES 4 #define NCI_MAX_DISCOVERED_TARGETS 10 #define NCI_MAX_NUM_NFCEE 255 #define NCI_MAX_CONN_ID 7 +#define NCI_MAX_PROPRIETARY_CMD 64 struct nci_conn_info { struct list_head list; @@ -137,6 +150,10 @@ struct nci_conn_info { #define NCI_HCI_INVALID_HOST 0x80 #define NCI_HCI_MAX_CUSTOM_GATES 50 +/* + * According to specification 102 622 chapter 4.4 Pipes, + * the pipe identifier is 7 bits long. + */ #define NCI_HCI_MAX_PIPES 127 struct nci_hci_gate { @@ -259,6 +276,8 @@ int nci_request(struct nci_dev *ndev, void (*req)(struct nci_dev *ndev, unsigned long opt), unsigned long opt, __u32 timeout); +int nci_prop_cmd(struct nci_dev *ndev, __u8 oid, size_t len, __u8 *payload); + int nci_recv_frame(struct nci_dev *ndev, struct sk_buff *skb); int nci_set_config(struct nci_dev *ndev, __u8 id, size_t len, __u8 *val); @@ -313,8 +332,19 @@ static inline void *nci_get_drvdata(struct nci_dev *ndev) return ndev->driver_data; } +static inline int nci_set_vendor_cmds(struct nci_dev *ndev, + struct nfc_vendor_cmd *cmds, + int n_cmds) +{ + return nfc_set_vendor_cmds(ndev->nfc_dev, cmds, n_cmds); +} + void nci_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb); void nci_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb); +int nci_prop_rsp_packet(struct nci_dev *ndev, __u16 opcode, + struct sk_buff *skb); +int nci_prop_ntf_packet(struct nci_dev *ndev, __u16 opcode, + struct sk_buff *skb); void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb); int nci_send_cmd(struct nci_dev *ndev, __u16 opcode, __u8 plen, void *payload); int nci_send_data(struct nci_dev *ndev, __u8 conn_id, struct sk_buff *skb); @@ -362,4 +392,50 @@ int nci_spi_send(struct nci_spi *nspi, struct sk_buff *skb); struct sk_buff *nci_spi_read(struct nci_spi *nspi); +/* ----- NCI UART ---- */ + +/* Ioctl */ +#define NCIUARTSETDRIVER _IOW('U', 0, char *) + +enum nci_uart_driver { + NCI_UART_DRIVER_MARVELL = 0, + NCI_UART_DRIVER_MAX +}; + +struct nci_uart; + +struct nci_uart_ops { + int (*open)(struct nci_uart *nci_uart); + void (*close)(struct nci_uart *nci_uart); + int (*recv)(struct nci_uart *nci_uart, struct sk_buff *skb); + int (*recv_buf)(struct nci_uart *nci_uart, const u8 *data, char *flags, + int count); + int (*send)(struct nci_uart *nci_uart, struct sk_buff *skb); + void (*tx_start)(struct nci_uart *nci_uart); + void (*tx_done)(struct nci_uart *nci_uart); +}; + +struct nci_uart { + struct module *owner; + struct nci_uart_ops ops; + const char *name; + enum nci_uart_driver driver; + + /* Dynamic data */ + struct nci_dev *ndev; + spinlock_t rx_lock; + struct work_struct write_work; + struct tty_struct *tty; + unsigned long tx_state; + struct sk_buff_head tx_q; + struct sk_buff *tx_skb; + struct sk_buff *rx_skb; + int rx_packet_len; + void *drv_data; +}; + +int nci_uart_register(struct nci_uart *nu); +void nci_uart_unregister(struct nci_uart *nu); +void nci_uart_set_config(struct nci_uart *nu, int baudrate, int flow_ctrl); + #endif /* __NCI_CORE_H */ diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index 73190e65d5c1..f9e58ae45f9c 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -157,7 +157,7 @@ struct nfc_evt_transaction { u32 aid_len; u8 aid[NFC_MAX_AID_LENGTH]; u8 params_len; - u8 params[NFC_MAX_PARAMS_LENGTH]; + u8 params[0]; } __packed; struct nfc_genl_data { @@ -165,6 +165,12 @@ struct nfc_genl_data { struct mutex genl_data_mutex; }; +struct nfc_vendor_cmd { + __u32 vendor_id; + __u32 subcmd; + int (*doit)(struct nfc_dev *dev, void *data, size_t data_len); +}; + struct nfc_dev { int idx; u32 target_next_idx; @@ -193,6 +199,9 @@ struct nfc_dev { struct rfkill *rfkill; + struct nfc_vendor_cmd *vendor_cmds; + int n_vendor_cmds; + struct nfc_ops *ops; }; #define to_nfc_dev(_dev) container_of(_dev, struct nfc_dev, dev) @@ -296,4 +305,17 @@ struct nfc_se *nfc_find_se(struct nfc_dev *dev, u32 se_idx); void nfc_send_to_raw_sock(struct nfc_dev *dev, struct sk_buff *skb, u8 payload_type, u8 direction); +static inline int nfc_set_vendor_cmds(struct nfc_dev *dev, + struct nfc_vendor_cmd *cmds, + int n_cmds) +{ + if (dev->vendor_cmds || dev->n_vendor_cmds) + return -EINVAL; + + dev->vendor_cmds = cmds; + dev->n_vendor_cmds = n_cmds; + + return 0; +} + #endif /* __NET_NFC_H */ diff --git a/include/net/nl802154.h b/include/net/nl802154.h index f8b5bc997959..b0ab530d28cd 100644 --- a/include/net/nl802154.h +++ b/include/net/nl802154.h @@ -100,6 +100,10 @@ enum nl802154_attrs { NL802154_ATTR_EXTENDED_ADDR, + NL802154_ATTR_WPAN_PHY_CAPS, + + NL802154_ATTR_SUPPORTED_COMMANDS, + /* add attributes here, update the policy in nl802154.c */ __NL802154_ATTR_AFTER_LAST, @@ -120,6 +124,61 @@ enum nl802154_iftype { }; /** + * enum nl802154_wpan_phy_capability_attr - wpan phy capability attributes + * + * @__NL802154_CAP_ATTR_INVALID: attribute number 0 is reserved + * @NL802154_CAP_ATTR_CHANNELS: a nested attribute for nl802154_channel_attr + * @NL802154_CAP_ATTR_TX_POWERS: a nested attribute for + * nl802154_wpan_phy_tx_power + * @NL802154_CAP_ATTR_MIN_CCA_ED_LEVEL: minimum value for cca_ed_level + * @NL802154_CAP_ATTR_MAX_CCA_ED_LEVEL: maxmimum value for cca_ed_level + * @NL802154_CAP_ATTR_CCA_MODES: nl802154_cca_modes flags + * @NL802154_CAP_ATTR_CCA_OPTS: nl802154_cca_opts flags + * @NL802154_CAP_ATTR_MIN_MINBE: minimum of minbe value + * @NL802154_CAP_ATTR_MAX_MINBE: maximum of minbe value + * @NL802154_CAP_ATTR_MIN_MAXBE: minimum of maxbe value + * @NL802154_CAP_ATTR_MAX_MINBE: maximum of maxbe value + * @NL802154_CAP_ATTR_MIN_CSMA_BACKOFFS: minimum of csma backoff value + * @NL802154_CAP_ATTR_MAX_CSMA_BACKOFFS: maximum of csma backoffs value + * @NL802154_CAP_ATTR_MIN_FRAME_RETRIES: minimum of frame retries value + * @NL802154_CAP_ATTR_MAX_FRAME_RETRIES: maximum of frame retries value + * @NL802154_CAP_ATTR_IFTYPES: nl802154_iftype flags + * @NL802154_CAP_ATTR_LBT: nl802154_supported_bool_states flags + * @NL802154_CAP_ATTR_MAX: highest cap attribute currently defined + * @__NL802154_CAP_ATTR_AFTER_LAST: internal use + */ +enum nl802154_wpan_phy_capability_attr { + __NL802154_CAP_ATTR_INVALID, + + NL802154_CAP_ATTR_IFTYPES, + + NL802154_CAP_ATTR_CHANNELS, + NL802154_CAP_ATTR_TX_POWERS, + + NL802154_CAP_ATTR_CCA_ED_LEVELS, + NL802154_CAP_ATTR_CCA_MODES, + NL802154_CAP_ATTR_CCA_OPTS, + + NL802154_CAP_ATTR_MIN_MINBE, + NL802154_CAP_ATTR_MAX_MINBE, + + NL802154_CAP_ATTR_MIN_MAXBE, + NL802154_CAP_ATTR_MAX_MAXBE, + + NL802154_CAP_ATTR_MIN_CSMA_BACKOFFS, + NL802154_CAP_ATTR_MAX_CSMA_BACKOFFS, + + NL802154_CAP_ATTR_MIN_FRAME_RETRIES, + NL802154_CAP_ATTR_MAX_FRAME_RETRIES, + + NL802154_CAP_ATTR_LBT, + + /* keep last */ + __NL802154_CAP_ATTR_AFTER_LAST, + NL802154_CAP_ATTR_MAX = __NL802154_CAP_ATTR_AFTER_LAST - 1 +}; + +/** * enum nl802154_cca_modes - cca modes * * @__NL802154_CCA_INVALID: cca mode number 0 is reserved @@ -128,7 +187,7 @@ enum nl802154_iftype { * @NL802154_CCA_ENERGY_CARRIER: Carrier sense with energy above threshold * @NL802154_CCA_ALOHA: CCA shall always report an idle medium * @NL802154_CCA_UWB_SHR: UWB preamble sense based on the SHR of a frame - * @NL802154_CCA_UWB_MULTIPEXED: UWB preamble sense based on the packet with + * @NL802154_CCA_UWB_MULTIPLEXED: UWB preamble sense based on the packet with * the multiplexed preamble * @__NL802154_CCA_ATTR_AFTER_LAST: Internal * @NL802154_CCA_ATTR_MAX: Maximum CCA attribute number @@ -140,7 +199,7 @@ enum nl802154_cca_modes { NL802154_CCA_ENERGY_CARRIER, NL802154_CCA_ALOHA, NL802154_CCA_UWB_SHR, - NL802154_CCA_UWB_MULTIPEXED, + NL802154_CCA_UWB_MULTIPLEXED, /* keep last */ __NL802154_CCA_ATTR_AFTER_LAST, @@ -162,4 +221,26 @@ enum nl802154_cca_opts { NL802154_CCA_OPT_ATTR_MAX = __NL802154_CCA_OPT_ATTR_AFTER_LAST - 1 }; +/** + * enum nl802154_supported_bool_states - bool states for bool capability entry + * + * @NL802154_SUPPORTED_BOOL_FALSE: indicates to set false + * @NL802154_SUPPORTED_BOOL_TRUE: indicates to set true + * @__NL802154_SUPPORTED_BOOL_INVALD: reserved + * @NL802154_SUPPORTED_BOOL_BOTH: indicates to set true and false + * @__NL802154_SUPPORTED_BOOL_AFTER_LAST: Internal + * @NL802154_SUPPORTED_BOOL_MAX: highest value for bool states + */ +enum nl802154_supported_bool_states { + NL802154_SUPPORTED_BOOL_FALSE, + NL802154_SUPPORTED_BOOL_TRUE, + /* to handle them in a mask */ + __NL802154_SUPPORTED_BOOL_INVALD, + NL802154_SUPPORTED_BOOL_BOTH, + + /* keep last */ + __NL802154_SUPPORTED_BOOL_AFTER_LAST, + NL802154_SUPPORTED_BOOL_MAX = __NL802154_SUPPORTED_BOOL_AFTER_LAST - 1 +}; + #endif /* __NL802154_H */ 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..87935cad2f7b 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 +61,58 @@ 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 *saved_syn; 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; + req->saved_syn = NULL; + /* 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); + kfree(req->saved_syn); + 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 +122,16 @@ 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 +175,11 @@ 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 +187,9 @@ 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, @@ -185,15 +214,6 @@ static inline int reqsk_queue_empty(struct request_sock_queue *queue) return queue->rskq_accept_head == NULL; } -static inline void reqsk_queue_unlink(struct request_sock_queue *queue, - struct request_sock *req, - struct request_sock **prev_req) -{ - write_lock(&queue->syn_wait_lock); - *prev_req = req->dl_next; - write_unlock(&queue->syn_wait_lock); -} - static inline void reqsk_queue_add(struct request_sock_queue *queue, struct request_sock *req, struct sock *parent, @@ -224,57 +244,53 @@ 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/rtnetlink.h b/include/net/rtnetlink.h index 6c6d5393fc34..343d922d15c2 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -137,7 +137,7 @@ void rtnl_af_register(struct rtnl_af_ops *ops); void rtnl_af_unregister(struct rtnl_af_ops *ops); struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]); -struct net_device *rtnl_create_link(struct net *net, char *ifname, +struct net_device *rtnl_create_link(struct net *net, const char *ifname, unsigned char name_assign_type, const struct rtnl_link_ops *ops, struct nlattr *tb[]); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index c605d305c577..2738f6f87908 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. */ @@ -501,12 +501,6 @@ static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch) return sch->enqueue(skb, sch); } -static inline int qdisc_enqueue_root(struct sk_buff *skb, struct Qdisc *sch) -{ - qdisc_skb_cb(skb)->pkt_len = skb->len; - return qdisc_enqueue(skb, sch) & NET_XMIT_MASK; -} - static inline bool qdisc_is_percpu_stats(const struct Qdisc *q) { return q->flags & TCQ_F_CPUSTATS; @@ -745,23 +739,6 @@ static inline u32 qdisc_l2t(struct qdisc_rate_table* rtab, unsigned int pktlen) return rtab->data[slot]; } -#ifdef CONFIG_NET_CLS_ACT -static inline struct sk_buff *skb_act_clone(struct sk_buff *skb, gfp_t gfp_mask, - int action) -{ - struct sk_buff *n; - - n = skb_clone(skb, gfp_mask); - - if (n) { - n->tc_verd = SET_TC_VERD(n->tc_verd, 0); - n->tc_verd = CLR_TC_OK2MUNGE(n->tc_verd); - n->tc_verd = CLR_TC_MUNGED(n->tc_verd); - } - return n; -} -#endif - struct psched_ratecfg { u64 rate_bytes_ps; /* bytes per second */ u32 mult; diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 856f01cb51dd..ce13cf20f625 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 @@ -571,11 +574,14 @@ static inline void sctp_v6_map_v4(union sctp_addr *addr) /* Map v4 address to v4-mapped v6 address */ static inline void sctp_v4_map_v6(union sctp_addr *addr) { + __be16 port; + + port = addr->v4.sin_port; + addr->v6.sin6_addr.s6_addr32[3] = addr->v4.sin_addr.s_addr; + addr->v6.sin6_port = port; addr->v6.sin6_family = AF_INET6; addr->v6.sin6_flowinfo = 0; addr->v6.sin6_scope_id = 0; - addr->v6.sin6_port = addr->v4.sin_port; - addr->v6.sin6_addr.s6_addr32[3] = addr->v4.sin_addr.s_addr; addr->v6.sin6_addr.s6_addr32[0] = 0; addr->v6.sin6_addr.s6_addr32[1] = 0; addr->v6.sin6_addr.s6_addr32[2] = htonl(0x0000ffff); diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 2bb2fcf5b11f..495c87e367b3 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -223,6 +223,10 @@ struct sctp_sock { atomic_t pd_mode; /* Receive to here while partial delivery is in effect. */ struct sk_buff_head pd_lobby; + + /* These must be the last fields, as they will skipped on copies, + * like on accept and peeloff operations + */ struct list_head auto_asconf_list; int do_auto_asconf; }; diff --git a/include/net/sock.h b/include/net/sock.h index e4079c28e6b8..05a8c1aea251 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -57,7 +57,6 @@ #include <linux/page_counter.h> #include <linux/memcontrol.h> #include <linux/static_key.h> -#include <linux/aio.h> #include <linux/sched.h> #include <linux/filter.h> @@ -67,6 +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; @@ -184,21 +184,22 @@ struct sock_common { unsigned char skc_reuse:4; unsigned char skc_reuseport:1; unsigned char skc_ipv6only:1; + unsigned char skc_net_refcnt:1; int skc_bound_dev_if; union { struct hlist_node skc_bind_node; 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() @@ -276,7 +277,6 @@ struct cg_proto; * @sk_incoming_cpu: record cpu processing incoming packets * @sk_txhash: computed flow hash for use on transmit * @sk_filter: socket filtering instructions - * @sk_protinfo: private area, net family specific, when not using slab * @sk_timer: sock cleanup timer * @sk_stamp: time stamp of last packet received * @sk_tsflags: SO_TIMESTAMPING socket options @@ -323,12 +323,14 @@ struct sock { #define sk_reuse __sk_common.skc_reuse #define sk_reuseport __sk_common.skc_reuseport #define sk_ipv6only __sk_common.skc_ipv6only +#define sk_net_refcnt __sk_common.skc_net_refcnt #define sk_bound_dev_if __sk_common.skc_bound_dev_if #define sk_bind_node __sk_common.skc_bind_node #define sk_prot __sk_common.skc_prot #define sk_net __sk_common.skc_net #define sk_v6_daddr __sk_common.skc_v6_daddr #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr +#define sk_cookie __sk_common.skc_cookie socket_lock_t sk_lock; struct sk_buff_head sk_receive_queue; @@ -403,8 +405,8 @@ struct sock { rwlock_t sk_callback_lock; int sk_err, sk_err_soft; - unsigned short sk_ack_backlog; - unsigned short sk_max_ack_backlog; + u32 sk_ack_backlog; + u32 sk_max_ack_backlog; __u32 sk_priority; #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) __u32 sk_cgrp_prioidx; @@ -413,7 +415,6 @@ struct sock { const struct cred *sk_peer_cred; long sk_rcvtimeo; long sk_sndtimeo; - void *sk_protinfo; struct timer_list sk_timer; ktime_t sk_stamp; u16 sk_tsflags; @@ -923,7 +924,6 @@ static inline void sk_prot_clear_nulls(struct sock *sk, int size) /* Networking protocol blocks we attach to sockets. * socket layer -> transport layer interface - * transport -> network interface is defined by struct inet_proto */ struct proto { void (*close)(struct sock *sk, @@ -958,10 +958,9 @@ 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, @@ -1366,7 +1365,7 @@ static inline struct inode *SOCK_INODE(struct socket *socket) * Functions for memory accounting */ int __sk_mem_schedule(struct sock *sk, int size, int kind); -void __sk_mem_reclaim(struct sock *sk); +void __sk_mem_reclaim(struct sock *sk, int amount); #define SK_MEM_QUANTUM ((int)PAGE_SIZE) #define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM) @@ -1407,7 +1406,7 @@ static inline void sk_mem_reclaim(struct sock *sk) if (!sk_has_account(sk)) return; if (sk->sk_forward_alloc >= SK_MEM_QUANTUM) - __sk_mem_reclaim(sk); + __sk_mem_reclaim(sk, sk->sk_forward_alloc); } static inline void sk_mem_reclaim_partial(struct sock *sk) @@ -1415,7 +1414,7 @@ static inline void sk_mem_reclaim_partial(struct sock *sk) if (!sk_has_account(sk)) return; if (sk->sk_forward_alloc > SK_MEM_QUANTUM) - __sk_mem_reclaim(sk); + __sk_mem_reclaim(sk, sk->sk_forward_alloc - 1); } static inline void sk_mem_charge(struct sock *sk, int size) @@ -1514,9 +1513,9 @@ static inline void unlock_sock_fast(struct sock *sk, bool slow) struct sock *sk_alloc(struct net *net, int family, gfp_t priority, - struct proto *prot); + struct proto *prot, int kern); void sk_free(struct sock *sk); -void sk_release_kernel(struct sock *sk); +void sk_destruct(struct sock *sk); struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority); struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, @@ -1562,9 +1561,8 @@ int sock_no_listen(struct socket *, int); int sock_no_shutdown(struct socket *, int); int sock_no_getsockopt(struct socket *, int , int, char __user *, int __user *); int sock_no_setsockopt(struct socket *, int, int, char __user *, unsigned int); -int sock_no_sendmsg(struct kiocb *, struct socket *, struct msghdr *, size_t); -int sock_no_recvmsg(struct kiocb *, struct socket *, struct msghdr *, size_t, - int); +int sock_no_sendmsg(struct socket *, struct msghdr *, size_t); +int sock_no_recvmsg(struct socket *, struct msghdr *, size_t, int); int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma); ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, @@ -1576,8 +1574,8 @@ ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, */ int sock_common_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); -int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock, - struct msghdr *msg, size_t size, int flags); +int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, + int flags); int sock_common_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen); int compat_sock_common_getsockopt(struct socket *sock, int level, @@ -1626,7 +1624,7 @@ 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); @@ -2025,7 +2023,8 @@ static inline void sk_stream_moderate_sndbuf(struct sock *sk) } } -struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp); +struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, + bool force_schedule); /** * sk_page_frag - return an appropriate page_frag @@ -2080,6 +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, @@ -2170,22 +2192,6 @@ void sock_net_set(struct sock *sk, struct net *net) write_pnet(&sk->sk_net, net); } -/* - * Kernel sockets, f.e. rtnl or icmp_socket, are a part of a namespace. - * They should not hold a reference to a namespace in order to allow - * to stop it. - * Sockets after sk_change_net should be released using sk_release_kernel - */ -static inline void sk_change_net(struct sock *sk, struct net *net) -{ - struct net *current_net = sock_net(sk); - - if (!net_eq(current_net, net)) { - put_net(current_net); - sock_net_set(sk, hold_net(net)); - } -} - static inline struct sock *skb_steal_sock(struct sk_buff *skb) { if (skb->sk) { @@ -2198,6 +2204,14 @@ 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..d5671f118bfc 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 @@ -13,102 +14,263 @@ #include <linux/netdevice.h> #include <linux/notifier.h> -enum netdev_switch_notifier_type { - NETDEV_SWITCH_FDB_ADD = 1, - NETDEV_SWITCH_FDB_DEL, +#define SWITCHDEV_F_NO_RECURSE BIT(0) + +enum switchdev_trans { + SWITCHDEV_TRANS_NONE, + SWITCHDEV_TRANS_PREPARE, + SWITCHDEV_TRANS_ABORT, + SWITCHDEV_TRANS_COMMIT, +}; + +enum switchdev_attr_id { + SWITCHDEV_ATTR_UNDEFINED, + SWITCHDEV_ATTR_PORT_PARENT_ID, + SWITCHDEV_ATTR_PORT_STP_STATE, + SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS, +}; + +struct switchdev_attr { + enum switchdev_attr_id id; + enum switchdev_trans trans; + u32 flags; + union { + struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */ + u8 stp_state; /* PORT_STP_STATE */ + unsigned long brport_flags; /* PORT_BRIDGE_FLAGS */ + } u; +}; + +struct fib_info; + +enum switchdev_obj_id { + SWITCHDEV_OBJ_UNDEFINED, + SWITCHDEV_OBJ_PORT_VLAN, + SWITCHDEV_OBJ_IPV4_FIB, + SWITCHDEV_OBJ_PORT_FDB, +}; + +struct switchdev_obj { + enum switchdev_obj_id id; + enum switchdev_trans trans; + int (*cb)(struct net_device *dev, struct switchdev_obj *obj); + union { + struct switchdev_obj_vlan { /* PORT_VLAN */ + u16 flags; + u16 vid_begin; + u16 vid_end; + } vlan; + struct switchdev_obj_ipv4_fib { /* IPV4_FIB */ + u32 dst; + int dst_len; + struct fib_info *fi; + u8 tos; + u8 type; + u32 nlflags; + u32 tb_id; + } ipv4_fib; + struct switchdev_obj_fdb { /* PORT_FDB */ + const unsigned char *addr; + u16 vid; + } fdb; + } u; +}; + +/** + * struct switchdev_ops - switchdev operations + * + * @switchdev_port_attr_get: Get a port attribute (see switchdev_attr). + * + * @switchdev_port_attr_set: Set a port attribute (see switchdev_attr). + * + * @switchdev_port_obj_add: Add an object to port (see switchdev_obj). + * + * @switchdev_port_obj_del: Delete an object from port (see switchdev_obj). + * + * @switchdev_port_obj_dump: Dump port objects (see switchdev_obj). + */ +struct switchdev_ops { + int (*switchdev_port_attr_get)(struct net_device *dev, + struct switchdev_attr *attr); + int (*switchdev_port_attr_set)(struct net_device *dev, + struct switchdev_attr *attr); + int (*switchdev_port_obj_add)(struct net_device *dev, + struct switchdev_obj *obj); + int (*switchdev_port_obj_del)(struct net_device *dev, + struct switchdev_obj *obj); + int (*switchdev_port_obj_dump)(struct net_device *dev, + struct switchdev_obj *obj); +}; + +enum switchdev_notifier_type { + SWITCHDEV_FDB_ADD = 1, + SWITCHDEV_FDB_DEL, }; -struct netdev_switch_notifier_info { +struct switchdev_notifier_info { struct net_device *dev; }; -struct netdev_switch_notifier_fdb_info { - struct netdev_switch_notifier_info info; /* must be first */ +struct switchdev_notifier_fdb_info { + struct switchdev_notifier_info info; /* must be first */ const unsigned char *addr; u16 vid; }; static inline struct net_device * -netdev_switch_notifier_info_to_dev(const struct netdev_switch_notifier_info *info) +switchdev_notifier_info_to_dev(const struct switchdev_notifier_info *info) { return info->dev; } #ifdef CONFIG_NET_SWITCHDEV -int netdev_switch_parent_id_get(struct net_device *dev, - struct netdev_phys_item_id *psid); -int netdev_switch_port_stp_update(struct net_device *dev, u8 state); -int register_netdev_switch_notifier(struct notifier_block *nb); -int unregister_netdev_switch_notifier(struct notifier_block *nb); -int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev, - struct netdev_switch_notifier_info *info); -int netdev_switch_port_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags); -int netdev_switch_port_bridge_dellink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags); -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 switchdev_port_attr_get(struct net_device *dev, + struct switchdev_attr *attr); +int switchdev_port_attr_set(struct net_device *dev, + struct switchdev_attr *attr); +int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj); +int switchdev_port_obj_del(struct net_device *dev, struct switchdev_obj *obj); +int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj); +int register_switchdev_notifier(struct notifier_block *nb); +int unregister_switchdev_notifier(struct notifier_block *nb); +int call_switchdev_notifiers(unsigned long val, struct net_device *dev, + struct switchdev_notifier_info *info); +int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, + struct net_device *dev, u32 filter_mask, + int nlflags); +int switchdev_port_bridge_setlink(struct net_device *dev, + struct nlmsghdr *nlh, u16 flags); +int switchdev_port_bridge_dellink(struct net_device *dev, + struct nlmsghdr *nlh, u16 flags); +int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 nlflags, u32 tb_id); +int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, + u8 tos, u8 type, u32 tb_id); +void switchdev_fib_ipv4_abort(struct fib_info *fi); +int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, const unsigned char *addr, + u16 vid, u16 nlm_flags); +int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, const unsigned char *addr, + u16 vid); +int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, + struct net_device *dev, + struct net_device *filter_dev, int idx); + #else -static inline int netdev_switch_parent_id_get(struct net_device *dev, - struct netdev_phys_item_id *psid) +static inline int switchdev_port_attr_get(struct net_device *dev, + struct switchdev_attr *attr) +{ + return -EOPNOTSUPP; +} + +static inline int switchdev_port_attr_set(struct net_device *dev, + struct switchdev_attr *attr) +{ + return -EOPNOTSUPP; +} + +static inline int switchdev_port_obj_add(struct net_device *dev, + struct switchdev_obj *obj) +{ + return -EOPNOTSUPP; +} + +static inline int switchdev_port_obj_del(struct net_device *dev, + struct switchdev_obj *obj) { return -EOPNOTSUPP; } -static inline int netdev_switch_port_stp_update(struct net_device *dev, - u8 state) +static inline int switchdev_port_obj_dump(struct net_device *dev, + struct switchdev_obj *obj) { return -EOPNOTSUPP; } -static inline int register_netdev_switch_notifier(struct notifier_block *nb) +static inline int register_switchdev_notifier(struct notifier_block *nb) { return 0; } -static inline int unregister_netdev_switch_notifier(struct notifier_block *nb) +static inline int unregister_switchdev_notifier(struct notifier_block *nb) { return 0; } -static inline int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev, - struct netdev_switch_notifier_info *info) +static inline int call_switchdev_notifiers(unsigned long val, + struct net_device *dev, + struct switchdev_notifier_info *info) { return NOTIFY_DONE; } -static inline int netdev_switch_port_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh, - u16 flags) +static inline int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid, + u32 seq, struct net_device *dev, + u32 filter_mask, int nlflags) { return -EOPNOTSUPP; } -static inline int netdev_switch_port_bridge_dellink(struct net_device *dev, - struct nlmsghdr *nlh, - u16 flags) +static inline int switchdev_port_bridge_setlink(struct net_device *dev, + struct nlmsghdr *nlh, + u16 flags) { return -EOPNOTSUPP; } -static inline int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev, - struct nlmsghdr *nlh, - u16 flags) +static inline int switchdev_port_bridge_dellink(struct net_device *dev, + struct nlmsghdr *nlh, + u16 flags) +{ + return -EOPNOTSUPP; +} + +static inline int switchdev_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 ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh, - u16 flags) +static inline int switchdev_fib_ipv4_del(u32 dst, int dst_len, + struct fib_info *fi, + u8 tos, u8 type, u32 tb_id) { return 0; } +static inline void switchdev_fib_ipv4_abort(struct fib_info *fi) +{ +} + +static inline int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, + u16 vid, u16 nlm_flags) +{ + return -EOPNOTSUPP; +} + +static inline int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, u16 vid) +{ + return -EOPNOTSUPP; +} + +static inline int switchdev_port_fdb_dump(struct sk_buff *skb, + struct netlink_callback *cb, + struct net_device *dev, + struct net_device *filter_dev, + int idx) +{ + return -EOPNOTSUPP; +} + #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..950cfecaad3c 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 @@ -173,6 +179,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCPOPT_SACK 5 /* SACK Block */ #define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */ #define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */ +#define TCPOPT_FASTOPEN 34 /* Fast open (RFC7413) */ #define TCPOPT_EXP 254 /* Experimental */ /* Magic number to be after the option value for sharing TCP * experimental options. See draft-ietf-tcpm-experimental-options-00.txt @@ -188,6 +195,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCPOLEN_SACK_PERM 2 #define TCPOLEN_TIMESTAMP 10 #define TCPOLEN_MD5SIG 18 +#define TCPOLEN_FASTOPEN_BASE 2 #define TCPOLEN_EXP_FASTOPEN_BASE 4 /* But this is what stacks really send out. */ @@ -278,6 +286,14 @@ extern atomic_long_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; extern int tcp_memory_pressure; +/* optimized version of sk_under_memory_pressure() for TCP sockets */ +static inline bool tcp_under_memory_pressure(const struct sock *sk) +{ + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + return !!sk->sk_cgrp->memory_pressure; + + return tcp_memory_pressure; +} /* * The next routines deal with comparing 32 bit unsigned ints * and worry about wraparound (automatic with unsigned arithmetic). @@ -303,6 +319,8 @@ static inline bool tcp_out_of_memory(struct sock *sk) return false; } +void sk_forced_mem_schedule(struct sock *sk, int size); + static inline bool tcp_too_many_orphans(struct sock *sk, int shift) { struct percpu_counter *ocp = sk->sk_prot->orphan_count; @@ -318,18 +336,6 @@ static inline bool tcp_too_many_orphans(struct sock *sk, int shift) bool tcp_check_oom(struct sock *sk, int shift); -/* syncookies: remember time of last synqueue overflow */ -static inline void tcp_synq_overflow(struct sock *sk) -{ - tcp_sk(sk)->rx_opt.ts_recent_stamp = jiffies; -} - -/* syncookies: no recent synqueue overflow on this listening socket? */ -static inline bool tcp_synq_no_recent_overflow(const struct sock *sk) -{ - unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; - return time_after(jiffies, last_overflow + TCP_TIMEOUT_FALLBACK); -} extern struct proto tcp_prot; @@ -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, @@ -464,6 +469,9 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size); void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb); /* From syncookies.c */ +struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct dst_entry *dst); int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, u32 cookie); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); @@ -476,13 +484,35 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); * i.e. a sent cookie is valid only at most for 2*60 seconds (or less if * the counter advances immediately after a cookie is generated). */ -#define MAX_SYNCOOKIE_AGE 2 +#define MAX_SYNCOOKIE_AGE 2 +#define TCP_SYNCOOKIE_PERIOD (60 * HZ) +#define TCP_SYNCOOKIE_VALID (MAX_SYNCOOKIE_AGE * TCP_SYNCOOKIE_PERIOD) + +/* syncookies: remember time of last synqueue overflow + * But do not dirty this field too often (once per second is enough) + */ +static inline void tcp_synq_overflow(struct sock *sk) +{ + unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; + unsigned long now = jiffies; + + if (time_after(now, last_overflow + HZ)) + tcp_sk(sk)->rx_opt.ts_recent_stamp = now; +} + +/* syncookies: no recent synqueue overflow on this listening socket? */ +static inline bool tcp_synq_no_recent_overflow(const struct sock *sk) +{ + unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; + + return time_after(jiffies, last_overflow + TCP_SYNCOOKIE_VALID); +} static inline u32 tcp_cookie_time(void) { u64 val = get_jiffies_64(); - do_div(val, 60 * HZ); + do_div(val, TCP_SYNCOOKIE_PERIOD); return val; } @@ -520,12 +550,10 @@ int tcp_fragment(struct sock *, struct sk_buff *, u32, unsigned int, gfp_t); void tcp_send_probe0(struct sock *); void tcp_send_partial(struct sock *); -int tcp_write_wakeup(struct sock *); +int tcp_write_wakeup(struct sock *, int mib); 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); @@ -571,7 +599,7 @@ static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize) } /* tcp.c */ -void tcp_get_info(const struct sock *, struct tcp_info *); +void tcp_get_info(struct sock *, struct tcp_info *); /* Read 'sendfile()'-style from a TCP socket */ typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, @@ -687,6 +715,8 @@ static inline u32 tcp_skb_timestamp(const struct sk_buff *skb) #define TCPHDR_ECE 0x40 #define TCPHDR_CWR 0x80 +#define TCPHDR_SYN_ECN (TCPHDR_SYN | TCPHDR_ECE | TCPHDR_CWR) + /* This is what the send packet queuing engine uses to pass * TCP per-packet control information to the transmission code. * We also store the host-order sequence numbers in here too. @@ -700,11 +730,14 @@ struct tcp_skb_cb { /* Note : tcp_tw_isn is used in input path only * (isn chosen by tcp_timewait_state_process()) * - * tcp_gso_segs is used in write queue only, - * cf tcp_skb_pcount() + * tcp_gso_segs/size are used in write queue only, + * cf tcp_skb_pcount()/tcp_skb_mss() */ __u32 tcp_tw_isn; - __u32 tcp_gso_segs; + struct { + u16 tcp_gso_segs; + u16 tcp_gso_size; + }; }; __u8 tcp_flags; /* TCP header flags. (tcp[13]) */ @@ -760,10 +793,10 @@ static inline void tcp_skb_pcount_add(struct sk_buff *skb, int segs) TCP_SKB_CB(skb)->tcp_gso_segs += segs; } -/* This is valid iff tcp_skb_pcount() > 1. */ +/* This is valid iff skb is in write queue and tcp_skb_pcount() > 1. */ static inline int tcp_skb_mss(const struct sk_buff *skb) { - return skb_shinfo(skb)->gso_size; + return TCP_SKB_CB(skb)->tcp_gso_size; } /* Events passed to congestion control interface */ @@ -799,6 +832,8 @@ enum tcp_ca_ack_event_flags { /* Requires ECN/ECT set on all packets */ #define TCP_CONG_NEEDS_ECN 0x2 +union tcp_cc_info; + struct tcp_congestion_ops { struct list_head list; u32 key; @@ -824,7 +859,8 @@ struct tcp_congestion_ops { /* hook for packet ack accounting (optional) */ void (*pkts_acked)(struct sock *sk, u32 num_acked, s32 rtt_us); /* get info for inet_diag (optional) */ - void (*get_info)(struct sock *sk, u32 ext, struct sk_buff *skb); + size_t (*get_info)(struct sock *sk, u32 ext, int *attr, + union tcp_cc_info *info); char name[TCP_CA_NAME_MAX]; struct module *owner; @@ -1035,14 +1071,31 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk) return tp->is_cwnd_limited; } -static inline void tcp_check_probe_timer(struct sock *sk) +/* Something is really bad, we could not queue an additional packet, + * because qdisc is full or receiver sent a 0 window. + * We do not want to add fuel to the fire, or abort too early, + * so make sure the timer we arm now is at least 200ms in the future, + * regardless of current icsk_rto value (as it could be ~2ms) + */ +static inline unsigned long tcp_probe0_base(const struct sock *sk) { - const struct tcp_sock *tp = tcp_sk(sk); - const struct inet_connection_sock *icsk = inet_csk(sk); + return max_t(unsigned long, inet_csk(sk)->icsk_rto, TCP_RTO_MIN); +} + +/* Variant of inet_csk_rto_backoff() used for zero window probes */ +static inline unsigned long tcp_probe0_when(const struct sock *sk, + unsigned long max_when) +{ + u64 when = (u64)tcp_probe0_base(sk) << inet_csk(sk)->icsk_backoff; - if (!tp->packets_out && !icsk->icsk_pending) + return (unsigned long)min_t(u64, when, max_when); +} + +static inline void tcp_check_probe_timer(struct sock *sk) +{ + if (!tcp_sk(sk)->packets_out && !inet_csk(sk)->icsk_pending) inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0, - icsk->icsk_rto, TCP_RTO_MAX); + tcp_probe0_base(sk), TCP_RTO_MAX); } static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq) @@ -1132,31 +1185,6 @@ 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 +1264,8 @@ 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 +1344,14 @@ 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, @@ -1388,7 +1387,8 @@ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie, int *syn_loss, unsigned long *last_syn_loss); void tcp_fastopen_cache_set(struct sock *sk, u16 mss, - struct tcp_fastopen_cookie *cookie, bool syn_lost); + struct tcp_fastopen_cookie *cookie, bool syn_lost, + u16 try_exp); struct tcp_fastopen_request { /* Fast Open cookie. Size 0 means a cookie request */ struct tcp_fastopen_cookie cookie; @@ -1663,28 +1663,26 @@ 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/udp_tunnel.h b/include/net/udp_tunnel.h index 1a20d33d56bc..c491c1221606 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -77,13 +77,14 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, struct udp_tunnel_sock_cfg *sock_cfg); /* Transmit the skb using UDP encapsulation. */ -int udp_tunnel_xmit_skb(struct rtable *rt, struct sk_buff *skb, +int udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port, bool xnet, bool nocheck); #if IS_ENABLED(CONFIG_IPV6) -int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sk_buff *skb, +int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, struct net_device *dev, struct in6_addr *saddr, struct in6_addr *daddr, __u8 prio, __u8 ttl, __be16 src_port, diff --git a/include/net/vxlan.h b/include/net/vxlan.h index c73e7abbbaa5..0082b5d33d7d 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -131,7 +131,7 @@ struct vxlan_sock { #define VXLAN_F_GBP 0x800 #define VXLAN_F_REMCSUM_NOPARTIAL 0x1000 -/* Flags that are used in the receive patch. These flags must match in +/* Flags that are used in the receive path. These flags must match in * order for a socket to be shareable */ #define VXLAN_F_RCV_FLAGS (VXLAN_F_GBP | \ @@ -145,7 +145,7 @@ struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port, void vxlan_sock_release(struct vxlan_sock *vs); -int vxlan_xmit_skb(struct rtable *rt, struct sk_buff *skb, +int vxlan_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port, struct vxlan_metadata *md, bool xnet, u32 vxflags); diff --git a/include/net/xfrm.h b/include/net/xfrm.h index dc4865e90fe4..f0ee97eec24d 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; @@ -170,6 +168,7 @@ struct xfrm_state { struct xfrm_algo *ealg; struct xfrm_algo *calg; struct xfrm_algo_aead *aead; + const char *geniv; /* Data for encapsulator */ struct xfrm_encap_tmpl *encap; @@ -334,7 +333,7 @@ struct xfrm_state_afinfo { int (*tmpl_sort)(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n); int (*state_sort)(struct xfrm_state **dst, struct xfrm_state **src, int n); int (*output)(struct sock *sk, struct sk_buff *skb); - int (*output_finish)(struct sk_buff *skb); + int (*output_finish)(struct sock *sk, struct sk_buff *skb); int (*extract_input)(struct xfrm_state *x, struct sk_buff *skb); int (*extract_output)(struct xfrm_state *x, @@ -522,9 +521,7 @@ 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 +1026,7 @@ 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 +1239,8 @@ 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; } } @@ -1318,6 +1315,7 @@ static inline int xfrm_id_proto_match(u8 proto, u8 userproto) * xfrm algorithm information */ struct xfrm_algo_aead_info { + char *geniv; u16 icv_truncbits; }; @@ -1327,6 +1325,7 @@ struct xfrm_algo_auth_info { }; struct xfrm_algo_encr_info { + char *geniv; u16 blockbits; u16 defkeybits; }; @@ -1507,7 +1506,7 @@ int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb); int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int xfrm_input_resume(struct sk_buff *skb, int nexthdr); int xfrm_output_resume(struct sk_buff *skb, int err); -int xfrm_output(struct sk_buff *skb); +int xfrm_output(struct sock *sk, struct sk_buff *skb); int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb); void xfrm_local_error(struct sk_buff *skb, int mtu); int xfrm4_extract_header(struct sk_buff *skb); @@ -1528,7 +1527,7 @@ static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi) int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb); int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb); int xfrm4_output(struct sock *sk, struct sk_buff *skb); -int xfrm4_output_finish(struct sk_buff *skb); +int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb); int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err); int xfrm4_protocol_register(struct xfrm4_protocol *handler, unsigned char protocol); int xfrm4_protocol_deregister(struct xfrm4_protocol *handler, unsigned char protocol); @@ -1553,7 +1552,7 @@ __be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr); int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb); int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb); int xfrm6_output(struct sock *sk, struct sk_buff *skb); -int xfrm6_output_finish(struct sk_buff *skb); +int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb); int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb, u8 **prevhdr); |
